Compare commits

..

935 Commits

Author SHA1 Message Date
Sarah Hoffmann
9a979b7429 Merge pull request #3951 from Itz-Agasta/cli
Feat: Adds layer filtering option to search cli command
2026-01-29 09:58:06 +01:00
Itz-Agasta
6ad87db1eb Updates layer selection to allow optional default
- Modifies layer argument handling to permit no default layers appropriate.
- Update the help text for the layer parameter in the reverse command
2026-01-29 11:33:21 +05:30
Sarah Hoffmann
f4820bed0e Merge pull request #3950 from jayaddison/fixup/sql-debug-output-escaping
Fixup: add single-quote escaping within debug message
2026-01-28 20:30:11 +01:00
Itz-Agasta
bf6eb01d68 Adds layer filtering option to search command
Introduces a cli argument to restrict search results
to specified data layers, enabling more targeted queries.
2026-01-28 12:16:43 +05:30
James Addison
f07676a376 Fixup: add single-quote escaping within debug message 2026-01-28 01:27:53 +00:00
Sarah Hoffmann
67ecf5f6a0 Merge pull request #3943 from Itz-Agasta/test_fix
Tests: Replace eval() with ast.literal_eval() for safer parsing
2026-01-25 10:10:15 +01:00
Itz-Agasta
e77a4c2f35 Switch to ast.literal_eval for dict parsing
Due to  some test data in the BDD feature files includes Python raw strings and escape sequences that standard json.loads() cannot parse switching to safer Python literal evaluation
for converting string representations of dictionaries.
2026-01-24 15:32:47 +05:30
Itz-Agasta
9fa980bca2 Replaces eval with json.loads for safer dict parsing
Switches from eval to json.loads when parsing string representations
of dictionaries to  prevent arbitrary code
execution.
2026-01-24 15:32:47 +05:30
Sarah Hoffmann
fe773c12b2 Merge pull request #3946 from lonvia/enable-entrances-for-reverse
Enable entrance lookup for reverse and lookup
2026-01-23 22:10:43 +01:00
Sarah Hoffmann
cc96912580 Merge pull request #3906 from AyushDharDubey/fix/issue_2463-Use-search_name-table-for-TIGER-data-imports-on-'dropped'-databases
Use `search_name` as fallback for TIGER imports when update tables are dropped
2026-01-23 20:52:40 +01:00
Sarah Hoffmann
77a3ecd72d Merge pull request #3945 from lonvia/fix-starlette-tests
Update Starlette tests to using their TestClient
2026-01-23 20:45:15 +01:00
Sarah Hoffmann
6a6a064ef7 enable entrances for reverse and lookup 2026-01-23 17:38:47 +01:00
Sarah Hoffmann
35b42ad9ce update Starlette tests to using their TestClient 2026-01-23 16:28:13 +01:00
Sri Charan Chittineni
c4dc2c862e fix mypy typing for Starlette state object (#3944) 2026-01-22 13:21:34 +01:00
Sarah Hoffmann
7e44256f4a Merge pull request #3939 from lonvia/more-table-constraints
Add NOT NULL and UNIQUE contraints on tables
2026-01-14 15:04:45 +01:00
Ayush Dhar Dubey
eefd0efa59 update test frozen db: new tiger import mechanism 2026-01-09 17:47:07 +05:30
Ayush Dhar Dubey
2698382552 permit import of tiger after freeze 2026-01-09 17:35:01 +05:30
Ayush Dhar Dubey
954771a42d Add fallback search mechanism for dropped databases lookup 2026-01-09 17:35:01 +05:30
Sarah Hoffmann
e47601754a do not attempt to delete old data for newly created placex entries 2026-01-07 17:08:28 +01:00
Sarah Hoffmann
2cdf2db184 add NOT NULL and UNIQUE constraints where possible 2026-01-07 15:46:05 +01:00
Sarah Hoffmann
5200e11f33 ignore countries without geometry or country code for location_area 2026-01-07 11:43:32 +01:00
Sarah Hoffmann
ba1fc5a5b8 do not insert entries with empty name into search name 2026-01-07 11:27:55 +01:00
Sarah Hoffmann
d35a71c123 ensure correct indexed_status transitions 2026-01-07 11:12:35 +01:00
Sarah Hoffmann
e31862b7b5 make sure that importance is always set to a non-null value
Secondary importance might return invalid values in some cases.
2026-01-07 10:29:45 +01:00
Sarah Hoffmann
9ac5e0256d make sure array_merge() never returns null 2026-01-07 10:22:03 +01:00
Sarah Hoffmann
a4a2176ded immediately terminate indexing when a task catches an exception 2026-01-07 09:58:40 +01:00
Sarah Hoffmann
f30fcdcd9d BDD: make sure randomly generated names always contain a letter 2026-01-07 09:58:40 +01:00
otbutz
77b8e76be6 Add PR template (#3934) 2026-01-05 17:42:35 +01:00
Sarah Hoffmann
20a333dd9b Merge pull request #3930 from lonvia/remove-new-query-log-table
Remove unused new_query_log table
2026-01-02 09:58:05 +01:00
Sarah Hoffmann
084e1b8177 remove unused new_query_log table 2026-01-01 20:30:37 +01:00
Sarah Hoffmann
2e2ce2c979 fix version counts 2026-01-01 14:42:12 +01:00
Sarah Hoffmann
99643aa0e9 ignore postcode areas in countries without postcodes properly 2026-01-01 11:21:40 +01:00
Sarah Hoffmann
c05b8f241c make sure we use exactly the same table structure as osm2pgsql 2025-12-31 00:21:27 +01:00
Sarah Hoffmann
da94d7eea3 need an analyse after the migration 2025-12-30 19:49:07 +01:00
Sarah Hoffmann
f9864b7ec7 grant access right to www user for new postcode table 2025-12-30 17:48:33 +01:00
Sarah Hoffmann
df4abfd5cc Merge pull request #3926 from lonvia/rework-postcode-handling
Reorganise postcode handling
2025-12-30 15:54:33 +01:00
Sarah Hoffmann
42d139a5d0 analyze postcode table during import 2025-12-30 15:21:20 +01:00
Sarah Hoffmann
f2110e12d6 simplify postcode area for lookups 2025-12-30 15:21:20 +01:00
Sarah Hoffmann
3bcd1aa721 adapt BDD tests for new postcode table structure 2025-12-30 15:21:20 +01:00
Sarah Hoffmann
354aa07cad adapt unit tests to new postcode algorithms 2025-12-30 15:21:18 +01:00
Sarah Hoffmann
deb6654cfd add migration for new postcode table 2025-12-30 15:20:46 +01:00
Sarah Hoffmann
6a67cfcddf adapt search frontend to new postcode table 2025-12-30 15:20:46 +01:00
Sarah Hoffmann
f9cf320794 set custom postcode extents for some countries 2025-12-30 15:20:46 +01:00
Sarah Hoffmann
d1cb578535 rework postcode computation
Now adds areas to location_postcodes, ignores postcode points
inside areas and supports customizable extents.
2025-12-30 15:20:46 +01:00
Sarah Hoffmann
a97b5d97cb add support for custom per-country postcode extents 2025-12-30 15:20:46 +01:00
Sarah Hoffmann
9ec607b556 change confusing value in debug output for missing importance 2025-12-30 15:20:46 +01:00
Sarah Hoffmann
89821d01e0 reorganise layout of location_postcode table
Also renames the table as this will make it easier to migrate.
2025-12-30 15:20:46 +01:00
Sarah Hoffmann
7ef3f99fa4 drop new place sub-tables on freezing 2025-12-30 15:20:46 +01:00
Sarah Hoffmann
0aa9eee3e7 remove special casing for postcodes in trigger code 2025-12-30 15:20:46 +01:00
Sarah Hoffmann
340fe64e8b put postcodes in extra table on import 2025-12-30 15:20:46 +01:00
Sarah Hoffmann
0b11dd0eba Merge pull request #3925 from Aditya30ag/fix-typo-place-addressline-test
Fix typo in place_addressline table name in tests
2025-12-30 14:36:59 +01:00
Aditya30ag
3b182afa72 Fix typo in place_addressline table name in tests 2025-12-30 17:40:08 +05:30
Sarah Hoffmann
ae77a9512a Merge pull request #3919 from 28Deepakpandey/Fix-docs-locale-typo
Fix: Locale → Locales references in docs
2025-12-28 15:55:49 +01:00
28Deepakpandey
f7ba1fc9e1 Fix: corrected Locale → Locales references and ensured proper casing in docs 2025-12-26 02:46:26 +05:30
Sarah Hoffmann
26e62fda19 Merge pull request #3913 from AyushDharDubey/fix/issue_3909
Reuse Configuration instance in Locales
2025-12-22 16:38:27 +01:00
Ayush Dhar Dubey
4fd616254a update Locales constructor:
expect output names as argument and avoid redundant configuration initialization
2025-12-20 19:15:33 +05:30
Ayush Dhar Dubey
049164086a fix: ensure Locales is not initialized when provided in options 2025-12-20 19:12:15 +05:30
Sarah Hoffmann
5e965d5216 Merge pull request #3910 from lonvia/update-ps-names
Update default names for Palestinian Territories
2025-12-15 21:16:56 +01:00
Sarah Hoffmann
2097401b12 update default names for Palestinian Territories 2025-12-15 19:25:15 +01:00
Sarah Hoffmann
58e56ec53d Merge pull request #3901 from AyushDharDubey/fix/issue_3829-use-mwparserfromhell-to-parse-sp-wiki-page
Replace regex with `mwparserfromhell` based MW WikiCode Parsing for Special Phrases
2025-12-08 11:51:50 +01:00
Ayush Dhar Dubey
fe170c9286 add mwparserfromhell to apt prerequisites for CI build 2025-12-08 15:51:35 +05:30
Ayush Dhar Dubey
0c5af2e3e4 update new dependency instructions: mwparserfromhell 2025-12-08 15:01:35 +05:30
Sarah Hoffmann
681daeea29 Merge pull request #3902 from lonvia/fix-only-closest-housenumber
Reverse: only return housenumbers near street
2025-12-08 09:48:29 +01:00
Ayush Dhar Dubey
49454048c4 use mwparserfromhell to parse SP wiki page reliably 2025-12-08 11:01:14 +05:30
Ayush Dhar Dubey
4919240377 test for cell-per-line format 2025-12-08 11:01:14 +05:30
Ayush Dhar Dubey
56cb183c4e update sp test content
add latest <generator>MediaWiki 1.43.5</generator>
add test case for one-row-per-line
2025-12-08 10:59:10 +05:30
Sarah Hoffmann
35060164ab reverse: only return housenumbers near street 2025-12-07 11:00:23 +01:00
Sarah Hoffmann
4cfc1792fb Merge pull request #3899 from lonvia/improve-reverse-performance
Streamline reverse lookup slightly
2025-12-07 09:39:10 +01:00
Sarah Hoffmann
3bb5d00848 avoid extra query for finding closest housenumber in reverse 2025-12-05 17:09:13 +01:00
Sarah Hoffmann
b366b9df6f reverse: avoid interpolation lookup when result is already perfect 2025-12-05 17:08:46 +01:00
Sarah Hoffmann
6b12501c7a Merge pull request #3898 from lonvia/fix-country-restriction
Fix comparision between country tokens and country restriction
2025-12-04 20:03:14 +01:00
Sarah Hoffmann
ffd5c32f17 fix comparision between countr tokens and country restriction 2025-12-04 18:29:25 +01:00
Sarah Hoffmann
6c8869439f Merge pull request #3897 from lonvia/test-psycopg-33
Allow psycopg 3.3 back
2025-12-04 17:10:55 +01:00
Sarah Hoffmann
8188946394 ignore typing isssue 2025-12-03 10:22:11 +01:00
Sarah Hoffmann
19134cc15c exclude psycopg 3.3.0 which breaks named cursors 2025-12-03 10:22:04 +01:00
Sarah Hoffmann
d0b9aac400 Merge pull request #3895 from lonvia/flaky-test
Fix flaky test around postcode word match penalties
2025-12-02 12:46:43 +01:00
Sarah Hoffmann
48d13c593b fix flaky test around postcode word match penalties 2025-12-02 11:15:37 +01:00
Sarah Hoffmann
96d04e3a2e Merge pull request #3894 from lonvia/country-names-with-word-lookup
Add normalized form of country names to coutry tokens in word table
2025-12-01 14:54:24 +01:00
Sarah Hoffmann
23db1ab981 avoid most recent psycopg 3.3 release 2025-12-01 14:23:36 +01:00
Sarah Hoffmann
cd1b1736a9 add migration for changed country token format 2025-12-01 13:10:18 +01:00
Sarah Hoffmann
9447c90b09 adapt tests to new country token format 2025-12-01 13:10:18 +01:00
Sarah Hoffmann
81c6cb72e6 add normalised country name to word table
Country tokens now follow the usual convetion of having the
normalized version in the word column and the extra info about the
country code in the info column.
2025-12-01 13:10:18 +01:00
Sarah Hoffmann
f2a122c5c0 Merge pull request #3893 from lonvia/nature-reserve
Prefer leisure=nature_reserve as main tag over boundary=protected_area
2025-12-01 11:36:17 +01:00
Sarah Hoffmann
57ef0e1f98 prefer leisure=nature_reserve as main tag 2025-12-01 09:47:55 +01:00
Sarah Hoffmann
922667b650 Merge pull request #3892 from daishu0000/master
Add success message to setup.log: related to #3891
2025-11-30 14:13:51 +01:00
Sarah Hoffmann
fba803167c fix imprecise import 2025-11-30 11:50:55 +01:00
daishu0000
782df52ea0 Add success message to db log 2025-11-30 01:53:40 +08:00
Sarah Hoffmann
c36da68a48 Merge pull request #3890 from mtmail/remove-nat-name
Skip nat_name in default import
2025-11-28 14:13:30 +01:00
marc tobias
716de13bc9 Skip nat_name in default import 2025-11-28 11:35:35 +01:00
Sarah Hoffmann
1df56d7548 Merge pull request #3889 from lonvia/improve-linkage-code
Small improvements to place linking code
2025-11-26 22:11:11 +01:00
Sarah Hoffmann
9cfef7a31a prefer wikidata over name match when linking 2025-11-26 17:44:47 +01:00
Sarah Hoffmann
139678f367 fix linkage removal when nothing has changed 2025-11-26 17:03:19 +01:00
Sarah Hoffmann
e578c60ff4 Merge pull request #3874 from vytas7/falcon-4.2-typing
Adapt type annotations to Falcon App type changes
2025-11-16 16:12:35 +01:00
Vytautas Liuolia
7b4a3c8500 Add from __future__ import annotations to delay evaluation 2025-11-16 14:41:25 +01:00
Vytautas Liuolia
7751f9a6b6 Adapt type annotations to Falcon App type changes
See also: https://falcon.readthedocs.io/en/latest/api/typing.html#generic-app-types
2025-11-10 20:09:17 +01:00
Sarah Hoffmann
303ac42b47 Merge pull request #3862 from mtmail/skip-all-zero-postcodes
Postcode sanetizer now skips values which are only zeros
2025-10-31 10:36:05 +01:00
Sarah Hoffmann
6a2d2daad5 Merge pull request #3863 from lonvia/improve-bdd-test-names
Add custom pytest collector for BDD feature files
2025-10-31 10:19:56 +01:00
Sarah Hoffmann
a51c771107 disable improved BDD test naming for pytest < 8
Needs the improved test collector introduced in pytest 8.0.
2025-10-30 20:50:00 +01:00
Sarah Hoffmann
55547723bf add custom pytest collector for BDD feature files 2025-10-30 17:56:23 +01:00
marc tobias
362088775f postcode sanetizer skips postcodes which are only zeros 2025-10-30 13:45:29 +01:00
Sarah Hoffmann
9a13b62fb9 prepare release 5.2.0 2025-10-29 10:01:30 +01:00
Sarah Hoffmann
3ecda751c4 Merge pull request #3861 from lonvia/force-extra-tags
Force inclusion of extra tags when Nominatim internally depends on them
2025-10-29 08:51:40 +01:00
Sarah Hoffmann
5d4c29b84b force inclusion of extratags used directly by Nominatim 2025-10-28 17:20:17 +01:00
Sarah Hoffmann
f1fbc04f33 harmonize use of callback with set_entrance_filter
All other functions except a simple function, so do this here as well.
2025-10-28 14:33:45 +01:00
Sarah Hoffmann
353c985b9f Merge pull request #3859 from lonvia/fix-entrance-addresses
Move entrances to a separate table
2025-10-24 13:38:21 +02:00
Sarah Hoffmann
2dda9079f0 add BDD tests for importing into the new place_entrance table 2025-10-24 10:52:25 +02:00
Sarah Hoffmann
4c91a0bc8d fix syntax in presets 2025-10-24 09:43:06 +02:00
Sarah Hoffmann
31c8ec6db0 add documentation for entrance table configuration 2025-10-23 20:53:59 +02:00
Sarah Hoffmann
e2330ff4c1 add migration for separate entrance table 2025-10-23 17:25:20 +02:00
Sarah Hoffmann
589825d37e adapt tests for extra place_entrance table 2025-10-23 17:25:20 +02:00
Sarah Hoffmann
a93113bc44 use extra place_entrance table 2025-10-23 17:25:20 +02:00
Sarah Hoffmann
b042eca382 move entrances into extra table 2025-10-23 17:25:20 +02:00
Sarah Hoffmann
d202a8f7d8 Merge pull request #3857 from lonvia/leisure-garden
Be more conservative when including leisure=garden/commons
2025-10-22 14:03:19 +02:00
Sarah Hoffmann
af6386bd68 move some leisure features into manmade layer 2025-10-22 11:27:25 +02:00
Sarah Hoffmann
862bfdf6fb correct default values for layer on reverse 2025-10-22 11:27:25 +02:00
Sarah Hoffmann
28029edc8b exclude unamed gardens and commons
These are mostly private gardens and small streches of green
not of interest for a general search.

ddd
2025-10-22 11:26:58 +02:00
Sarah Hoffmann
d6e9196177 Merge pull request #3855 from hasandiwan/master
force layer to be address
2025-10-22 11:24:40 +02:00
Hasan Diwan
e0a750e089 force layer to be address 2025-10-22 07:55:10 +00:00
Sarah Hoffmann
93b2a0f194 update CI to test against PostgreSQL 18 2025-10-20 18:50:30 +02:00
Sarah Hoffmann
aa3fce6852 correct default setting for addressdetails parameter in lookup
Fixes #3850.
2025-10-11 09:20:10 +02:00
Sarah Hoffmann
535ffc1e3f Merge pull request #3840 from lonvia/normalize-penalties
Improve termination condition for forward search
2025-09-12 21:59:39 +02:00
Sarah Hoffmann
77ed4635f2 Merge pull request #3836 from Johannes-Andersen/chore/i18NorwegianCountries
chore: update no,nb,nn country-names translation
2025-09-12 21:01:03 +02:00
Sarah Hoffmann
7715a9d500 fix new mypy issue 2025-09-12 19:32:49 +02:00
Johannes Andersen
58d570ca8a chore: update no,nb,nn country-names translation 2025-09-12 18:20:56 +02:00
Sarah Hoffmann
5a8aa6cce4 adapt tests to new penalties 2025-09-12 17:45:22 +02:00
Sarah Hoffmann
72592da0cc reduce penalty for artificial housenumbers 2025-09-12 17:44:54 +02:00
Sarah Hoffmann
193d6c4173 in-word penalty for final address token 2025-09-12 12:05:29 +02:00
Sarah Hoffmann
4fd881bcb2 housenumber and postcode cross penalties for partials 2025-09-12 11:50:01 +02:00
Sarah Hoffmann
54620f9566 base penalty for housenumber searches on similar address searches 2025-09-12 10:52:42 +02:00
Sarah Hoffmann
42b687f545 stop searching earlier after the first results was found 2025-09-12 10:01:13 +02:00
Sarah Hoffmann
43ffceff27 remove base penalty for postcodes
This is a relict from having base penalties for all terms.
2025-09-12 09:45:57 +02:00
Sarah Hoffmann
2fb03cd103 Merge pull request #3835 from lonvia/remove-japanese-variants
Remove japanese variants
2025-09-11 17:45:30 +02:00
Sarah Hoffmann
8d3d24a1e4 Merge pull request #3834 from lonvia/neighbourhoods
Improve handling of neighbourhoods in addresses
2025-09-11 15:25:01 +02:00
Sarah Hoffmann
8efdab1d6f remove japanese variants
Variants are only meant for word morphing which does not exist
for Kanji.
2025-09-11 15:20:57 +02:00
Sarah Hoffmann
1d1d80e1e3 adapt BDD tests for new address ranks 2025-09-11 11:56:39 +02:00
Sarah Hoffmann
670cf98f93 fix query time logging for structured queries 2025-09-11 10:54:02 +02:00
Sarah Hoffmann
433c40cd68 downgrade neighbourhoods and landuses
Neighbourhoods shoud be below a quarter hierarchically speaking, so
downgrade them a bit. Consider named landuses the area form of a
meighbourhood and put it at the same level.
2025-09-11 10:20:33 +02:00
Sarah Hoffmann
a049569020 downgrade Japanese boundaries one level
Definition is shifted by one compared to other countries,
see https://wiki.openstreetmap.org/wiki/Tag:boundary%3Dadministrative
2025-09-11 10:01:24 +02:00
Sarah Hoffmann
bf49f6a46f Merge pull request #3833 from lonvia/rework-logging
Introduce generic query statistics and make log output configurable
2025-09-11 08:46:44 +02:00
Sarah Hoffmann
45a44f1411 export QueryStatistics type 2025-09-10 21:40:39 +02:00
Sarah Hoffmann
5a2bfd7a19 add documentation for library API 2025-09-10 21:38:09 +02:00
Sarah Hoffmann
fd12d2e9f3 add additional stats for search queries 2025-09-10 20:49:46 +02:00
Sarah Hoffmann
3d0867ff16 make log output configurable 2025-09-10 20:11:46 +02:00
Sarah Hoffmann
177b16b89b use new QueryStatistics in API server 2025-09-10 11:52:06 +02:00
Sarah Hoffmann
0b7bde2500 introduce parameter for saving query statistics 2025-09-10 10:24:20 +02:00
Sarah Hoffmann
7ac3591433 Merge pull request #3830 from lonvia/split-transliteration
Improve word match penalty for scripts without word boundaries
2025-09-09 10:28:21 +02:00
Sarah Hoffmann
07c2907064 split normalized word when transliteration is split up 2025-09-08 22:58:01 +02:00
Sarah Hoffmann
355cbcc7b8 Merge pull request #3828 from lonvia/code-cleanup
Code cleanup
2025-09-06 16:59:52 +02:00
Sarah Hoffmann
8339c2b928 no longer accept None in result maker functions 2025-09-06 11:09:40 +02:00
Sarah Hoffmann
341c09ee95 remove unused functions 2025-09-06 11:09:40 +02:00
Sarah Hoffmann
b0b909be93 Merge pull request #3827 from lonvia/rework-query-timeouts
Apply request timeouts while waiting for a connection
2025-09-06 11:08:55 +02:00
Sarah Hoffmann
bf604e36ee add test for timeout class 2025-09-05 23:31:09 +02:00
Sarah Hoffmann
3a50f749dd apply request timeout also while waiting for a connection from pool 2025-09-05 23:31:09 +02:00
Sarah Hoffmann
563255202d read request_timeout configuration only once 2025-09-05 09:18:50 +02:00
Sarah Hoffmann
94d22bbdac Merge pull request #3825 from emlove/entrance-docs
Some docs for the entrances output
2025-09-03 21:18:15 +02:00
Emily Love Watson
32d26f12c4 Add example entrances output 2025-09-03 09:55:43 -05:00
Sarah Hoffmann
0f324c8cb2 Merge pull request #3826 from lonvia/decrease-default-pool-size
reduce default DB pool size
2025-09-03 08:53:54 +02:00
Emily Love Watson
1e3b56d215 Some docs for the entrances output 2025-09-02 21:56:56 -05:00
Sarah Hoffmann
e855552e01 reduce default DB pool size 2025-09-02 22:10:30 +02:00
Sarah Hoffmann
79a1907c49 Merge pull request #3807 from emlove/return-entrance-location
Index and return entrance coordinates for places
2025-08-30 20:08:33 +02:00
Emily Love Watson
91e345f77f Store entrance fields as columns on table 2025-08-29 10:26:29 -05:00
Emily Love Watson
d0ad65f696 Select all entrances for results in one query 2025-08-29 10:26:29 -05:00
Emily Love Watson
e916d27b7c Update entrances when entrance nodes are updated 2025-08-29 10:26:29 -05:00
Emily Love Watson
823ad5d279 Update entrances schema 2025-08-29 10:26:29 -05:00
Emily Love Watson
048d571e46 Index and return entrance coordinates for indexed locations 2025-08-29 10:25:44 -05:00
Sarah Hoffmann
f5e4b74c38 Merge pull request #3823 from lonvia/fix-postcode-difference
Fix difference computation on postcode updates
2025-08-29 17:06:08 +02:00
Sarah Hoffmann
c2a311e69c fix poscode update computation: use distance 2025-08-29 15:10:27 +02:00
Sarah Hoffmann
5968f7d646 Merge pull request #3816 from anqixxx/locale-doc-update
Update to library locale documentation in light of refactor
2025-08-28 22:06:41 +02:00
anqixxx
4cdd2526b6 Updated and restructured library documentation to include Locale changes
Updated Getting Started Docs

Added documentation for Result Handling

removed api documentation
2025-08-27 09:18:16 -07:00
Sarah Hoffmann
4ff7696ed3 Merge pull request #3820 from mtmail/berlin-ost-hauptbahnhof
Sanetizer no longer strips name parts in brackets when more parts follow
2025-08-23 17:17:39 +02:00
marc tobias
247afe1f56 sanetizer no longer strips name parts in brackets when more parts follow 2025-08-23 01:06:35 +02:00
Sarah Hoffmann
6f74141fa4 Merge pull request #3819 from lonvia/ignore-survey
Ignore survey:* tags
2025-08-22 22:10:02 +02:00
Sarah Hoffmann
75ccf97de3 ignore survey:* tags 2025-08-22 10:59:58 +02:00
Sarah Hoffmann
196de9e974 Merge pull request #3796 from anqixxx/locale-refactor
Localize() + Results refactor
2025-08-13 14:08:42 +02:00
anqixxx
6b627df4fb Locales and localization refactor with Locales as a localizer object.
Removed auto-localization from search/search_address APIs (now explicit), simplified AddressLines to subclass List[AddressLine], made display_name a computed property in Results instead of field and removed result-localization circular dependencies
2025-08-12 08:05:37 -04:00
Sarah Hoffmann
b7d77b9b43 avoid symbolic link to files in packaging
Hatch cannot handle those correctly and will add a symbolic link to the
source package.
2025-08-06 21:59:13 +02:00
Sarah Hoffmann
7e84d38a92 Merge pull request #3811 from lonvia/fix-frequent-terms-with-viewbox
Don't restrict to viewbox for frequent terms
2025-08-06 21:10:07 +02:00
Sarah Hoffmann
c7df8738ed fix typing issue with latest falcon version 2025-08-06 20:08:10 +02:00
Sarah Hoffmann
0045203092 don't restrict to viewbox for frequent terms
All searched places may be outside the viewbox in which case the
restriction means that there are no results at all. Add the penalty for
being outside the viewbox earlier instead and then cut the list.
2025-08-06 17:27:52 +02:00
Sarah Hoffmann
b325413486 Merge pull request #3808 from lonvia/avoid-st-relate
Replace ST_Relate by shortcut functions
2025-08-06 16:28:51 +02:00
Sarah Hoffmann
6270c90052 replace ST_Relate by shortcut functions
For some reason ST_Relate returns wrong results in the context of
the trigger on Debian Trixie. Works fine with the Postgis version
from postgresql.org.
2025-08-06 14:43:07 +02:00
Sarah Hoffmann
a7709c768d add test for reverse with address layer and inherited address 2025-07-31 22:25:55 +02:00
Sarah Hoffmann
47c0a101b9 Merge pull request #3799 from lonvia/reduce-coordinate-precision
Reduce coordinate precision of centroids and interpolation lines
2025-07-30 14:50:36 +02:00
Sarah Hoffmann
64bb8c2a9c Merge pull request #3800 from lonvia/improve-style-docs
Improvements to documentation for custom import styles
2025-07-30 14:50:17 +02:00
Sarah Hoffmann
194b607491 Merge pull request #3797 from mtmail/database-version-not-found
Better hint to user if database import didnt finish
2025-07-30 12:08:10 +02:00
marc tobias
9bad3b1e61 Better hint to user if database import didnt finish 2025-07-30 10:25:14 +02:00
Sarah Hoffmann
69e882096c clarify what merging means 2025-07-29 23:04:14 +02:00
Sarah Hoffmann
f300b00c2d docs: add a list of available topics 2025-07-29 22:59:02 +02:00
Sarah Hoffmann
242fcc6e4d adapt BDD tests to different rounding of reduce precision 2025-07-29 22:35:55 +02:00
Sarah Hoffmann
83c6f27f5c reduce precision of interpolations to OSM precision 2025-07-29 22:35:47 +02:00
Sarah Hoffmann
1111597db5 reduce precision of computed centroids to 7 digits 2025-07-29 21:25:14 +02:00
Sarah Hoffmann
866e6bade9 Merge pull request #3789 from lonvia/align-deferred-delete-limits
Align limits for deferring delete and reindexing on insert
2025-07-22 11:15:56 +02:00
Sarah Hoffmann
4cbbe04f7f align limits for deferring delete and reindexing on insert
Right now when a boundary with an area between 1 and 2 broke, it
was deleted but on reinsert afer repair, the addresses are not updated
resulting in inconsistent data.
2025-07-21 16:11:06 +02:00
Sarah Hoffmann
e1cef3de0a remove unused code 2025-07-21 11:36:57 +02:00
Sarah Hoffmann
c6088cb4e7 Merge pull request #3785 from lonvia/raise-python-to-39
Raise minimum required Python version to 3.9
2025-07-19 23:02:13 +02:00
Sarah Hoffmann
a725cab2fc run old-version CI against oldest supported Python 2025-07-19 19:50:01 +02:00
Sarah Hoffmann
8bb53c22be raise minimum supported Python version to 3.9 2025-07-19 15:23:17 +02:00
Sarah Hoffmann
8a96e4f802 Merge pull request #3781 from lonvia/partial-address-index-lookup
Reduce number of tokens used for index lookups during search
2025-07-15 10:11:12 +02:00
Sarah Hoffmann
a9cd706bb6 adapt test to new lookup limits 2025-07-14 14:21:09 +02:00
Sarah Hoffmann
09b5ea097b restrict pre-selection by postcode to country 2025-07-14 14:21:09 +02:00
Sarah Hoffmann
e111257644 restrict name-only address searches early by postcode 2025-07-14 14:21:09 +02:00
Sarah Hoffmann
93ac1023f7 restrict name-only search more 2025-07-14 14:21:09 +02:00
Sarah Hoffmann
1fe2353682 restrict postcode distance computation to within country 2025-07-14 14:21:09 +02:00
Sarah Hoffmann
6d2b79870c only use most infrequent tokens for search index lookup 2025-07-14 14:18:22 +02:00
Sarah Hoffmann
621d8e785b Merge pull request #3779 from lonvia/fix-zero-devision-direction
Fix direction factor computation on empty strings
2025-07-11 14:51:00 +02:00
Sarah Hoffmann
830307484b Merge pull request #3777 from lonvia/harmonize-transition-penalties
Clean up word transition penalty assignment for searches
2025-07-11 14:17:48 +02:00
Sarah Hoffmann
5d6967a1d0 Merge pull request #3778 from lonvia/remove-log-db-setting
Remove defaults and documentations for LOG_DB setting
2025-07-11 14:17:24 +02:00
Sarah Hoffmann
26903aec0b add BDD test for empty queries 2025-07-11 14:16:48 +02:00
Sarah Hoffmann
c39183e3a5 remove any references to website setup or refresh
Does no longer exist.
2025-07-11 11:51:49 +02:00
Sarah Hoffmann
21ef3be433 fix direction factor computation on empty strings 2025-07-11 11:25:14 +02:00
Sarah Hoffmann
99562a197e remove LOG_DB setting, not implemented anymore 2025-07-11 11:15:41 +02:00
Sarah Hoffmann
fe30663b21 remove penalty from TokenRanges
The parameter is no longer needed.
2025-07-11 11:01:22 +02:00
Sarah Hoffmann
73ee17af95 adapt tests for new function signatures 2025-07-11 11:01:22 +02:00
Sarah Hoffmann
b9252cc348 reduce maximum number of SQL queries per search 2025-07-11 11:01:22 +02:00
Sarah Hoffmann
71025f3f43 fix order of address rankings prefering longest words 2025-07-11 11:01:21 +02:00
Sarah Hoffmann
e4b671f8b1 reinstate penalty for partial only matches 2025-07-11 11:01:21 +02:00
Sarah Hoffmann
7ebd121abc give word break slight advantage towards continuation
prefers longer words
2025-07-11 11:01:21 +02:00
Sarah Hoffmann
4634ad0720 rebalance word transition penalties 2025-07-11 11:01:21 +02:00
Sarah Hoffmann
4a9253a0a9 simplify QueryNode penalty and initial assignment 2025-07-11 11:01:09 +02:00
Sarah Hoffmann
1aeb8a262c Merge pull request #3774 from lonvia/remove-postcodes-from-nameaddressvector
Do not add postcodes from postcode boundaries to address vector
2025-07-08 17:23:05 +02:00
Sarah Hoffmann
ef7e842702 Merge pull request #3773 from lonvia/small-countries
Reduce area for geometry rank for very small countries
2025-07-08 15:01:37 +02:00
Sarah Hoffmann
ec42fda1bd do not add postcodes from postcode boundaries to address vector
Postcodes will be found through a special search, so we can save
the space.
2025-07-08 14:49:16 +02:00
Sarah Hoffmann
287ba2570e reduce area for geometry rank for very small countries 2025-07-08 13:50:20 +02:00
Sarah Hoffmann
4711deeccb Merge pull request #3772 from lonvia/fix-index-use-deletable
split up query for deletable endpoint by osm type
2025-07-08 13:49:31 +02:00
Sarah Hoffmann
cf9e8d6b8e split up query for deletable endpoint by osm type
This is needed to ensure index use on placex.
2025-07-08 11:03:29 +02:00
Sarah Hoffmann
06d5ab4c2d Merge pull request #3770 from lonvia/split-place-search
Split up SQL generation code for searches with and without housenumbers
2025-07-07 17:52:47 +02:00
Sarah Hoffmann
e327512667 adapt BDD test to refusal to search POI names with hnr only 2025-07-07 16:14:58 +02:00
Sarah Hoffmann
3e04eb2ffe increase penalty on mismatching postcodes for address searches
Otherwise there is an imbalance towards matching housenumbers
instead of the actual street (where no housenumber exists).
2025-07-07 16:07:32 +02:00
Sarah Hoffmann
970d81fb27 sort housenumber parents by accuracy first
Sorting them by presence of housenumber only will give an undue
preference to results with a housenumber while disregarding other
factors like matching postcodes.
2025-07-07 12:06:06 +02:00
Sarah Hoffmann
cecdbeb7cf reduce candidates for place search 2025-07-07 12:03:56 +02:00
Sarah Hoffmann
c634e9fc5f differentiate between place searches with and without address 2025-07-07 12:03:56 +02:00
Sarah Hoffmann
13eaea8aae split place search into address search and named search
The presence/absence of houenumbers makes quite a difference for search.
2025-07-07 09:13:48 +02:00
Sarah Hoffmann
ab5f348a4a Merge pull request #3769 from lonvia/refactor-api-searches
Refactor code around creating SQL for serach queries
2025-07-02 20:08:11 +02:00
Sarah Hoffmann
11d624e92a split db_searches moving each class in its own file 2025-07-01 22:57:04 +02:00
Sarah Hoffmann
a7797f8b37 Merge pull request #3765 from lonvia/update-ui-docs
Update instructions for UI integration
2025-06-27 20:01:28 +02:00
Sarah Hoffmann
c4dd0d4f95 update instructions for UI integration
Switches from defaulting to forwarding to UI to only forwarding
when requested. This avoids issues with auto-forwarding illegal URLs.
Also adapts to the much simplified nginx configuration.
2025-06-27 11:22:28 +02:00
Sarah Hoffmann
f43fec0d57 Merge pull request #3764 from lonvia/update-importance
'refresh --importance' also needs to refresh importances in search_name table
2025-06-27 10:02:18 +02:00
Sarah Hoffmann
af82c3debb remove duplicated test
There is a more extensive test of recompute_importance with
result check in test_refresh_wiki_data.py
2025-06-26 22:35:38 +02:00
Sarah Hoffmann
1ab4d445ea Merge pull request #3762 from lonvia/remove-gazetteer-output-support
Remove support for deprecated gazetteer osm2pgsql output
2025-06-26 20:28:16 +02:00
Sarah Hoffmann
678702ceb7 rewrite importances in search_name after updating in placex 2025-06-26 20:27:37 +02:00
Sarah Hoffmann
f9eb93c4ab remove support for deprecated gazetteer osm2pgsql output 2025-06-25 23:09:08 +02:00
Sarah Hoffmann
f97a0a76f2 Merge pull request #3747 from anqixxx/fix-special-phrases-filtering
Special Phrases Filtering: Add Command Line Functionality
2025-06-06 21:37:17 +02:00
anqixxx
cf9b946eba Added skip for when min =0 2025-06-05 09:25:14 +08:00
anqixxx
7dc3924a3c Added default min = 0 argument for private functions
empty
2025-06-04 01:12:36 -07:00
anqixxx
20cf4b56b9 Refactored min and associated tests to follow greater than or equal to logic, so that min=0 accounted for no filtering
r
2025-06-04 00:53:52 -07:00
anqixxx
40d5b78eb8 Added command line (default 0) min argument for minimum filtering, updated args.py to reflect this 2025-06-04 00:53:52 -07:00
Sarah Hoffmann
8d0e767826 Merge pull request #3748 from lonvia/airports
Improve finding airports by their codes
2025-06-02 14:39:02 +02:00
Sarah Hoffmann
87a8c246a0 improve result cutting when a POI comes out with top importance 2025-06-01 12:00:36 +02:00
Sarah Hoffmann
90050de717 only rerank results if there is more than one
With one result order is obvious.
2025-06-01 11:55:27 +02:00
Sarah Hoffmann
10a7d1106d reduce influence of query rematching a little bit 2025-06-01 11:54:21 +02:00
Sarah Hoffmann
f2236f68f1 when rematching only distinguish between perfect, somewhat and bad match 2025-06-01 11:53:23 +02:00
Sarah Hoffmann
831fccdaee add FAA codes (US version of IATA codes) for airports 2025-06-01 11:49:55 +02:00
Sarah Hoffmann
d2e691b63f work around bogus type error in latest starlette 2025-05-31 09:43:48 +02:00
Sarah Hoffmann
2a508b6c99 fix missing optional return 2025-05-30 12:03:00 +02:00
Sarah Hoffmann
02c3a6fffa Merge pull request #3744 from lonvia/add-unnamed-cemetries
Include unnamed cemetaries in POIs
2025-05-28 11:51:23 +02:00
Sarah Hoffmann
26348764d4 add landuse=cemetery as POI even when unnamed 2025-05-28 09:48:08 +02:00
Sarah Hoffmann
f8a56ab6e6 Merge pull request #3742 from lonvia/korean-defaults
Remove English as default language for South Korea
2025-05-26 14:13:54 +02:00
Sarah Hoffmann
75b4c7e56b adapt to changed loop handling of pytest_asyncio 2025-05-26 11:51:20 +02:00
Sarah Hoffmann
9f1dfb1876 remove English as default language for South Korea 2025-05-26 10:28:14 +02:00
Sarah Hoffmann
730b4204f6 Merge pull request #3741 from dave-meyer/patch-1
docs: Added missing code span for search API parameter value
2025-05-26 09:21:40 +02:00
Dave Meyer
4898704b5a docs: Added missing code span for search API parameter value 2025-05-25 20:42:09 +02:00
Sarah Hoffmann
0cf470f863 Merge pull request #3710 from anqixxx/fix-special-phrases-filtering
Fix special phrases filtering
2025-05-21 21:34:28 +02:00
anqixxx
6220bde2d6 Added mypy ignore fix for logging.py (library change), as well as quick mac fix on mem.cached 2025-05-21 11:11:56 -07:00
Sarah Hoffmann
a4d3b57f37 Merge pull request #3709 from anqixxx/update-readme
Improve README formatting and add install steps
2025-05-21 19:49:12 +02:00
anqixxx
618fbc63d7 Added testing to test get classtype pairs in import special phrases 2025-05-21 10:39:51 -07:00
anqixxx
3f51cb3fd1 Made the limit configurable with an optional argument, updating the testing as well to reflect this. default is now 0, meaning that it will return everything that occurs more than once. Removed mock database test, and got rid of fetch all. Rebased all tests to monkeypatch 2025-05-21 10:38:34 -07:00
anqixxx
59a947c5f5 Removed class type pair getter that used style sheets from both spi_importer and the associated testing function 2025-05-21 10:38:08 -07:00
anqixxx
1952290359 Removed magic mocking, using monkeypatch instead, and using a placex table to simulate a 'real database' 2025-05-21 10:37:42 -07:00
anqixxx
1a323165f9 Filter special phrases by style and frequency to fix #235 2025-05-21 10:36:46 -07:00
anqixxx
9c2fdf5eae Improve README formatting and add install steps, adding a general cloning step before the virtual environment. This would have been helpful for me during Nominatim setup 2025-05-21 10:14:36 -07:00
Sarah Hoffmann
800c56642b tweak full count cut-off (as per deployment on osm.org) 2025-05-11 11:48:07 +02:00
Sarah Hoffmann
b51fed025c Merge pull request #3732 from lonvia/exclude-country-from-direction-penalty
Exclude address searches with country from direction penalty
2025-04-30 10:45:37 +02:00
Sarah Hoffmann
34b72591cc exclude address searches with country from direction penalty
Countries are not adequately represented by partial term counts.
2025-04-29 17:37:31 +02:00
Sarah Hoffmann
bc450d110c Merge pull request #3722 from emmanuel-ferdman/master
resolve datetime deprecation warnings
2025-04-22 14:21:05 +02:00
Sarah Hoffmann
388acf4727 Merge pull request #3726 from lonvia/revert-json-format-change
Revert accidental change in json output format
2025-04-18 14:43:51 +02:00
Sarah Hoffmann
3999977941 revert accidental change in json output format 2025-04-18 12:05:25 +02:00
Emmanuel Ferdman
df58870e3f resolve datetime deprecation warnings
Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>
2025-04-17 11:15:16 -07:00
Sarah Hoffmann
478a8741db Merge pull request #3719 from lonvia/query-direction
Estimate query direction
2025-04-17 15:17:56 +02:00
Sarah Hoffmann
7f710d2394 add a comment about the precomputed denominator 2025-04-15 09:38:05 +02:00
Sarah Hoffmann
06e39e42d8 add direction penalties
Direction penalties are estimated by getting the name to address
ratio usage for each partial term in the query and computing the
linear regression of that ratio over the entire phrase. Or to put
it in ither words: we try to determine if the terms at the beginning
or the end of the query are more likely to constitute a name.

Direction penalties are currently used only in classic name queries.
2025-04-11 20:41:06 +02:00
Sarah Hoffmann
2ef0e20a3f reorganise token reranking
As the reranking is about changing penalties in presence of other
tokens, change the datastructure to have the other tokens readily
avilable.
2025-04-11 13:38:34 +02:00
Sarah Hoffmann
b680d81f0a ensure that bailout-check is done after each iteration 2025-04-11 11:02:11 +02:00
Sarah Hoffmann
e0e067b1d6 replace use of range when computing word list 2025-04-11 09:59:04 +02:00
Sarah Hoffmann
3980791cfd use iterator instead of list to go over partials 2025-04-11 09:38:24 +02:00
Sarah Hoffmann
497e27bb9a move partial token into a separate field in the query struct
There is exactly one token to be expected and the token is usually
present.
2025-04-11 08:57:34 +02:00
Sarah Hoffmann
1db717b886 Merge pull request #3716 from lonvia/github-cache-osm2pgsql-binary
Github actions: cache compiled osm2pgsql binary

For the tests on Ubunutu 22-04 we need to compile osm2pgsql because the version they ship is too old. This adds caching of the compiled binary, so that we don't need to recompile for each CI run. Together with the new BDD tests that shaves around 10 min off a CI run.
2025-04-10 17:20:32 +02:00
Sarah Hoffmann
b47c8ccfb1 actions: cache compiled osm2pgsql binary 2025-04-10 16:06:27 +02:00
Sarah Hoffmann
63b055283d Merge pull request #3714 from lonvia/postcode-update-without-project-dir
Change postcode update function to work without a project directory
2025-04-10 08:51:22 +02:00
Sarah Hoffmann
b80e6914e7 Merge pull request #3715 from lonvia/demote-tags-to-fallbacks
Demote historic and tourism=attraction to fallback tags
2025-04-10 08:51:06 +02:00
Sarah Hoffmann
9d00a137fe demote historic and tourism=attraction to fallback tags 2025-04-09 20:15:18 +02:00
Sarah Hoffmann
97d9e3c548 allow updating postcodes without a project directory
Postcodes will then be updated without looking for external postcodes.
2025-04-09 20:04:01 +02:00
Sarah Hoffmann
e4180936c1 Merge pull request #3713 from lonvia/bdd-pytest-db-test
Move BDD tests to pytest-bdd
2025-04-09 19:37:30 +02:00
Sarah Hoffmann
34e0ecb44f update documentation for BDD tests 2025-04-09 15:21:50 +02:00
Sarah Hoffmann
d95e9737da remove usage of behave 2025-04-09 14:57:39 +02:00
Sarah Hoffmann
b34991d85f add BDD tests for DB 2025-04-09 14:52:34 +02:00
Sarah Hoffmann
5f44aa2873 improve table comparison 2025-04-04 11:02:51 +02:00
Sarah Hoffmann
dae643c040 move database setup to generic conftest.py 2025-04-04 11:02:51 +02:00
Sarah Hoffmann
ee62d5e1cf remove old behave osm2pgsql BDD tests 2025-04-04 11:02:51 +02:00
Sarah Hoffmann
fb440f29a2 implement BDD osm2pgsql tests with pytest-bdd 2025-04-04 11:02:51 +02:00
Sarah Hoffmann
0f725b1880 enable python-bdd for github actions 2025-04-04 11:02:51 +02:00
Sarah Hoffmann
39f56ba4b8 restrict coordinate output to 7 digits 2025-04-04 11:02:51 +02:00
Sarah Hoffmann
6959577aa4 replace behave BDD API tests with pytest-bdd tests 2025-04-04 11:02:51 +02:00
Sarah Hoffmann
50d4b0a386 Merge pull request #3687 from asharmalik19/test-linked-places-language
test: linked places expand default language names
2025-04-04 10:58:53 +02:00
Ashar
9ff93bdb3d Update linked places name test
Clean up test scenario by removing extra language variations and
improving table readability.
2025-04-03 14:30:18 -04:00
Ashar
e0bf553aa5 test: linked places expand default language names
Add failing test for issue #2714 to verify default language expansion
2025-04-03 14:30:18 -04:00
Sarah Hoffmann
2ce2d031fa Merge pull request #3702 from lonvia/remove-tokenizer-dir
Remove automatic setup of tokenizer directory

So far the tokenizer factory would create a directory for private data for the tokenizer and then hand in the directory location to the tokenizer.

ICU tokenizer doesn't need any extra data anymore, so it doesn't make sense to create a directory which then remains empty. If a tokenizer needs such a directory in the future, it needs to create it on its own and make sure to handle the situation correctly where no project directory is used at all.
2025-04-03 09:04:48 +02:00
Sarah Hoffmann
186f562dd7 remove automatic setup of tokenizer directory
ICU tokenizer doesn't need any extra data anymore, so it doesn't
make sense to create a directory which then remains empty. If a
tokenizer needs such a directory in the future, it needs to create
it on its own and make sure to handle the situation correctly where
no project directory is used at all.
2025-04-02 20:20:04 +02:00
Sarah Hoffmann
c5bbeb626f Merge pull request #3700 from lonvia/ignore-inherited-addresses
Ignore POIs with inherited addresses for the address layer
2025-04-02 12:00:45 +02:00
Sarah Hoffmann
3bc77629c8 ignore POIs with inherited addresses for the address layer
We know that there is a building which describes the address as a
polygon and is therefore more suitable.
2025-04-02 10:30:45 +02:00
Sarah Hoffmann
6cf1287c4e Merge pull request #3686 from astridx/output_names
Output names as setting
2025-04-01 20:16:15 +02:00
Sarah Hoffmann
a49e8b9cf7 Merge pull request #3675 from TuringVerified/generic-preprocessors
Add generic preprocessors
2025-04-01 20:14:43 +02:00
TuringVerified
2eeec46040 Remove unnecessary assert statement, Fix regex_replace docstring and simplify regex_replace 2025-04-01 18:54:30 +05:30
TuringVerified
6d5a4a20c5 Update documentation, optimise regex_replace, add tests 2025-04-01 18:54:30 +05:30
TuringVerified
4665ea3e77 Add generic preprocessor 2025-04-01 18:54:30 +05:30
Sarah Hoffmann
9cf5eee5d4 add instructions for pip package upload 2025-04-01 11:59:03 +02:00
Sarah Hoffmann
fce279226f prepare release 5.1.0 2025-04-01 10:16:35 +02:00
Sarah Hoffmann
54d895c4ce Merge pull request #3695 from TuringVerified/doc-dependencies
[Small fix] Add documentation to install extras for mkdocstrings
2025-04-01 09:34:08 +02:00
TuringVerified
896a1c9d12 Add mkdocstrings extra 2025-04-01 11:06:46 +05:30
Sarah Hoffmann
32728d6c89 Merge pull request #3693 from lonvia/remove-unused-sql
Remove SQL function for address lookup
2025-03-31 17:11:39 +02:00
astridx
12ad95067d output names as setting 2025-03-31 16:55:05 +02:00
Sarah Hoffmann
bfd1c83cb0 Merge pull request #3692 from lonvia/word-lookup-variants
Avoid matching penalty for abbreviated search terms
2025-03-31 16:38:31 +02:00
Sarah Hoffmann
bbadc62371 remove SQL function for address lookup
This is now done in Python.
2025-03-31 15:09:40 +02:00
Sarah Hoffmann
5c9d3ca8d2 Merge pull request #3691 from lonvia/more-search-tweaks
More tweaks to search wights
2025-03-31 15:06:09 +02:00
Sarah Hoffmann
be4ba370ef adapt tests to extended results 2025-03-31 14:52:50 +02:00
Sarah Hoffmann
3cb183ffb0 add lookup word to variants in word table 2025-03-31 14:52:50 +02:00
Sarah Hoffmann
58ef032a2b do not write any word counts on initial word insert 2025-03-31 14:52:50 +02:00
Sarah Hoffmann
1705bb5f57 do not save word counts of 1
This is the default setting, which will be assumed when the count is
missing.
2025-03-31 14:52:50 +02:00
Sarah Hoffmann
f2aa15778f always use lookup when requested
Doesn't seem to cause any issues in production.
2025-03-31 11:38:21 +02:00
Sarah Hoffmann
efe65c3e49 increase allowable address counts 2025-03-31 11:38:21 +02:00
Sarah Hoffmann
51847ebfeb more agressively reduce expected count for multi-word terms
Improves searching of non-latin scripts with forced token spaces.
2025-03-31 11:18:22 +02:00
Sarah Hoffmann
46579f08e4 Merge pull request #3690 from lonvia/fix-signature
Fix function signature for newer SQLAlchemy
2025-03-31 11:17:03 +02:00
Sarah Hoffmann
d4994a152b fix function signature for newer SQLAlchemy 2025-03-31 09:42:29 +02:00
Sarah Hoffmann
00b3ace3cf Merge pull request #3684 from lonvia/compact-en-variants
Clean up English variants
2025-03-24 15:15:13 +01:00
Sarah Hoffmann
522bc942cf restrict some English variants to end of word 2025-03-21 21:22:38 +01:00
Sarah Hoffmann
d6e749d621 make English variant list more compact 2025-03-21 21:13:34 +01:00
Sarah Hoffmann
13cfb7efe2 Merge pull request #3682 from lonvia/fix-postcode-case
Fix case issues when parsing postcodes
2025-03-21 11:41:24 +01:00
Sarah Hoffmann
35baf77b18 make query upper-case when parsing postcodes
The postcode patterns expect upper-case letters.
2025-03-21 09:44:15 +01:00
Sarah Hoffmann
7e68613cc7 Merge pull request #3679 from lonvia/output-fixes
Minor fixes for v1 frontend code
2025-03-19 21:56:28 +01:00
Sarah Hoffmann
b1fc721f4b fix layer setting for structured search 2025-03-19 17:31:43 +01:00
Sarah Hoffmann
d400fd5f76 fix debug output for lookup type 2025-03-19 17:31:18 +01:00
Sarah Hoffmann
e4295dba10 Merge pull request #3678 from lonvia/search-tweaks
Some minor tweaks to postcode parsing in query
2025-03-19 16:00:52 +01:00
Sarah Hoffmann
9419c5adb2 penalize postcode searches with multiple name qualifiers 2025-03-19 10:05:36 +01:00
Sarah Hoffmann
2c61fe08a0 use word_token length when penalizing against postcodes 2025-03-19 09:52:40 +01:00
Sarah Hoffmann
7b3c725f2a postcode token should have transliterated term in word_token 2025-03-19 09:52:40 +01:00
Sarah Hoffmann
edc5ada625 improve handling of leading postcodes
Setting the direction of the query while yielding assignments is
a bad idea because it may override a direction already set.
2025-03-19 09:52:40 +01:00
Sarah Hoffmann
72d3360fa2 Merge pull request #3673 from otbutz/parallel_safe
Mark functions as PARALLEL SAFE
2025-03-18 21:46:53 +01:00
Sarah Hoffmann
0ffe384c57 Merge pull request #3676 from lonvia/adjust-place-levels-sa
Adjust place ranks for Saudi-Arabia
2025-03-18 18:31:48 +01:00
Sarah Hoffmann
9dad5edeb6 adjust for special use of province and municipality in Saudi-Arabia 2025-03-18 16:38:10 +01:00
Thomas Butz
d86d491f2e Mark functions as PARALLEL SAFE 2025-03-13 10:53:11 +01:00
Sarah Hoffmann
3026c333ca adapt typing for latest SQLAlchemy version 2025-03-13 10:49:08 +01:00
Sarah Hoffmann
ad84bbdec7 Merge pull request #3671 from lonvia/remove-osm2pgsql-libdir
Remove code for setting osm2pgsql location via config.lib_dir
2025-03-11 11:22:46 +01:00
Sarah Hoffmann
f5755a7a82 remove code for setting osm2pgsql via config.lib_dir
With the internal osm2pgsql gone, configuration of the binary location
via settings is the only option left that makes sense.
2025-03-11 09:04:05 +01:00
Sarah Hoffmann
cd08956c61 Merge pull request #3670 from lonvia/flake-for-tests
Extend linting with flake to tests
2025-03-10 09:35:24 +01:00
Sarah Hoffmann
12f5719184 remove unused bdd util functions 2025-03-09 17:34:40 +01:00
Sarah Hoffmann
78f839fbd3 enable flake for bdd test code 2025-03-09 17:34:04 +01:00
Sarah Hoffmann
c70dfccaca also enable flake for tests in github actions 2025-03-09 16:03:02 +01:00
Sarah Hoffmann
4cc788f69e enable flake for Python tests 2025-03-09 15:33:24 +01:00
Sarah Hoffmann
5a245e33e0 Merge pull request #3667 from eumiro/simplify-int-float
Simplify  int/float manipulation
2025-03-09 09:44:15 +01:00
Miroslav Šedivý
6ff51712fe Simplify int/float manipulation 2025-03-06 19:26:56 +01:00
Sarah Hoffmann
c431e0e45d Merge pull request #3666 from eumiro/math-isclose
Replace custom Almost with stdlib math.isclose
2025-03-06 17:53:01 +01:00
Sarah Hoffmann
c2d62a59cb Merge pull request #3664 from eumiro/consolidate-random
Consolidate usage of random module
2025-03-06 17:52:19 +01:00
Miroslav Šedivý
cd64788a58 Replace custom Almost with stdlib math.isclose 2025-03-05 20:35:01 +01:00
Miroslav Šedivý
800a41721a Consolidate usage of random module 2025-03-05 19:38:28 +01:00
Sarah Hoffmann
1b44fe2555 Merge pull request #3665 from lonvia/pattern-matching-postcodes
Add full parsing of postcodes in query
2025-03-05 16:02:03 +01:00
Sarah Hoffmann
6b0d58d9fd restrict postcode parsing in typed phrases
Postcodes can only appear in postcode-type phrases and must then
cover the full phrase
2025-03-05 10:09:33 +01:00
Sarah Hoffmann
afb89f9c7a add unit tests for postcode parser 2025-03-04 16:25:00 +01:00
Sarah Hoffmann
6712627d5e adapt BDD tests to new postcode handling 2025-03-04 15:18:46 +01:00
Sarah Hoffmann
434fbbfd18 add support for country prefixes in postcodes 2025-03-04 15:18:27 +01:00
Sarah Hoffmann
921db8bb2f cache all info of ICUQueryAnalyser in a single object 2025-03-04 08:58:57 +01:00
Sarah Hoffmann
a574b98e4a remove postcode computation for word table during import 2025-03-04 08:57:59 +01:00
Sarah Hoffmann
b2af358f66 reenable ZIP+ test 2025-03-04 08:57:59 +01:00
Sarah Hoffmann
e67ae701ac show token begin and end in debug output 2025-03-04 08:57:59 +01:00
Sarah Hoffmann
fc1c6261ed add postcode parser 2025-03-04 08:57:37 +01:00
Sarah Hoffmann
6759edfb5d make word generation from query a class method 2025-03-04 08:57:37 +01:00
Sarah Hoffmann
e362a965e1 search: merge QueryPart array with QueryNodes
The basic information on terms is pretty much always used together
with the node inforamtion. Merging them together saves some
allocation while making lookup easier at the same time.
2025-03-04 08:57:37 +01:00
Sarah Hoffmann
eff60ba6be enable parsing of US ZIP+ codes
The four-digit part of these postcodes will simply be ignored.
2025-02-25 20:29:06 +01:00
Sarah Hoffmann
157414a053 Merge pull request #3659 from lonvia/custom-datrie-structure
Replace datrie library with a simple custom Python implementation
2025-02-24 16:49:42 +01:00
Sarah Hoffmann
18d4996bec remove datrie dependency 2025-02-24 10:24:21 +01:00
Sarah Hoffmann
13db4c9731 replace datrie library with a more simple pure-Python class 2025-02-24 10:24:21 +01:00
Sarah Hoffmann
f567ea89cc Merge pull request #3658 from lonvia/minor-query-parsing-optimisations
Minor query parsing optimisations
2025-02-24 10:16:47 +01:00
Sarah Hoffmann
3e718e40d9 adapt documentation for PhraseType type 2025-02-21 17:16:42 +01:00
Sarah Hoffmann
49bd18b048 replace PhraseType enum with simple int constants 2025-02-21 16:44:12 +01:00
Sarah Hoffmann
31412e0674 replace TokenType enum with simple char constants 2025-02-21 10:23:41 +01:00
Sarah Hoffmann
4577669213 replace BreakType enum with simple char constants 2025-02-21 09:57:48 +01:00
Sarah Hoffmann
9bf1428d81 consistently use query module as qmod 2025-02-21 09:31:21 +01:00
Sarah Hoffmann
b56edf3d0a avoid yielding when extracting words from query 2025-02-20 23:32:39 +01:00
Sarah Hoffmann
abc911079e remove word_number counting for phrases
We can just examine the break types to know if we are dealing
with a partial token.
2025-02-20 17:36:50 +01:00
Sarah Hoffmann
adabfee3be Merge pull request #3655 from lonvia/remove-name-ranking-in-postcode-search
Tweak penalties for postcode searches
2025-02-20 14:32:43 +01:00
Sarah Hoffmann
46c4446dc2 remove address penalty for postcode search
Searches of the form <postcode> <city> are in fact quite common.
2025-02-20 11:11:45 +01:00
Sarah Hoffmann
add9244a2f do not rerank address by full match in postcode search
The reranking result will not be completely correct because
the address of a postcode refer to the address _and_ name
of the parent and reranking was only done against the
address. We assume here that the postcode is precise enough
as to not require a penalty to to partial matches.
2025-02-20 10:29:03 +01:00
Sarah Hoffmann
96d7a8e8f6 Merge pull request #3653 from lonvia/trailing-spaces-in-normalization
Strip leading and trailing space markers during normalization
2025-02-19 17:25:59 +01:00
Sarah Hoffmann
55c3176957 strip normalisation results of normal and special spaces 2025-02-19 14:40:35 +01:00
Sarah Hoffmann
e29823e28f add test for structured query with leading spaces 2025-02-19 10:31:36 +01:00
Sarah Hoffmann
97ed168996 Merge pull request #3652 from lonvia/update-variants
Cleanup and updates of tokenizer variant configuration
2025-02-18 19:47:45 +01:00
Sarah Hoffmann
9b8ef97d4b Merge pull request #3649 from lonvia/actions-move-to-ubuntu22
Move Github actions to Unbuntu-22 image
2025-02-18 13:21:09 +01:00
Sarah Hoffmann
4f3c88f0c1 remove e-ë mutation, this is taken care of by transliteration 2025-02-18 10:31:44 +01:00
mhsr21
7781186f3c Add USPS Standard Suffix Abbreviation 2025-02-18 09:28:13 +01:00
Sarah Hoffmann
f78686edb8 fix Norwegian variants
More cases of 'no' being interpreted as fasle by yaml.
2025-02-18 09:28:13 +01:00
Sarah Hoffmann
e330cd3162 remove ineffective and dupicate variants 2025-02-18 09:28:13 +01:00
Sarah Hoffmann
671af4cff2 Merge pull request #3555 from IvanShift/patch-1
Fixed Russian abbreviation list
2025-02-17 18:44:11 +01:00
Sarah Hoffmann
e612b7d550 actions: use Debians's script for adding the Postgres apt repo 2025-02-17 17:56:23 +01:00
Sarah Hoffmann
0b49d01703 actions: move tests to Ubuntu-20 2025-02-17 17:54:49 +01:00
Sarah Hoffmann
f6bc8e153f Merge pull request #3648 from lonvia/extratags-for-geocodejson
Enable output of extratags for geocodejson format
2025-02-17 11:14:52 +01:00
Sarah Hoffmann
f143ecaf1c add documentation for new extra field 2025-02-17 10:04:23 +01:00
Sarah Hoffmann
6730c8bac8 add optional output of extratags to geocodejson 2025-02-16 10:16:40 +01:00
Sarah Hoffmann
ee8915f2b6 prepare 5.0.0 release 2025-02-05 10:54:38 +01:00
Sarah Hoffmann
5475bf7b9c Merge pull request #3635 from lonvia/replace-wikimedia-importance-test-data
Update wikimedia importance file for test database
2025-01-14 16:49:52 +01:00
Sarah Hoffmann
95e2d8c846 adapt tests to changed wikimedia importance test table 2025-01-14 14:19:17 +01:00
Sarah Hoffmann
7552818866 replace wikimedia importance file for test data with CSV version 2025-01-14 09:16:25 +01:00
Sarah Hoffmann
db3991af74 Merge pull request #3626 from lonvia/import-performance
Import performance
2025-01-10 16:44:33 +01:00
Sarah Hoffmann
4523b9aaed Merge pull request #3631 from lonvia/avoid-transactions
Creating tables and indexes in autocommit mode
2025-01-10 16:44:18 +01:00
Sarah Hoffmann
8b1cabebd6 Merge pull request #3633 from lonvia/restrict-long-ways
Ignore overly long ways during import
2025-01-10 16:06:37 +01:00
Sarah Hoffmann
0cf636a80c ignore overly long ways during import 2025-01-10 13:55:43 +01:00
Sarah Hoffmann
c2cb6722fe use autocommit when creating tables and indexes
Might avoid some deadlock situations with autovacuum.
2025-01-09 17:14:37 +01:00
Sarah Hoffmann
f8337bedb2 Merge pull request #3629 from lonvia/additional-breaks
Introduce new break types and phrase splitting for Japanese addresses
2025-01-09 13:55:29 +01:00
Sarah Hoffmann
efc09a5cfc add japanese phrase preprocessing
Code adapted from GSOC code by @miku.
2025-01-09 09:24:10 +01:00
Sarah Hoffmann
86ad9efa8a keep break indicators [:-] during normalisation
All punctuation will be converted to '-'. Soft breaks : may be
added by preprocessors. The break signs are only used during
query analysis and are ignored during import token analysis.
2025-01-09 09:21:55 +01:00
Sarah Hoffmann
d984100e23 add inner word break penalty 2025-01-07 21:42:25 +01:00
Sarah Hoffmann
499110f549 add SOFT_PHRASE break and enable parsing
Also enables parsing of PART breaks.
2025-01-06 17:10:24 +01:00
Sarah Hoffmann
267e5dac0d split up MultiPolygons before adding them to large_areas table 2024-12-22 09:15:16 +01:00
Sarah Hoffmann
32d3eb46d5 move geometry split into insertLocationAreaLarge()
thus insert only needs to be called once.
2024-12-22 09:15:16 +01:00
Sarah Hoffmann
c8a0dc8af1 more efficient belongs-to-address determination 2024-12-22 09:15:16 +01:00
Sarah Hoffmann
14ecfc7834 Merge pull request #3619 from lonvia/demote-farms
Remove farms and isolated dwellings from computed addresses
2024-12-22 09:13:42 +01:00
Sarah Hoffmann
cad44eb00c remove farms and isolated dwellings from computed addresses
Farms and isolated dwellings are usually confined to a very small
area. It does not make sense if they are automatically used in
addressing surrounding features. Still works to use them for
parenting when used with addr:place.
2024-12-20 22:59:02 +01:00
Sarah Hoffmann
f76dbb0a16 docs: update Update docs for virtualenv use 2024-12-20 11:27:45 +01:00
Sarah Hoffmann
8dd218a1d0 Merge pull request #3618 from osm-search/settings-md-table-space-osm-index
Settings.md - one setting was repeated
2024-12-19 08:40:31 +01:00
mtmail
501e13483e Settings.md - one setting was repeated 2024-12-18 21:58:51 +01:00
Sarah Hoffmann
b1d25e404f Merge pull request #3617 from mtmail/pr-3615-wording
Slight wording changes for Import-Styles.md
2024-12-18 11:04:21 +01:00
marc tobias
71fceb6854 Slight wording changes for Import-Styles.md 2024-12-18 01:02:46 +01:00
Sarah Hoffmann
a06e123d70 Merge pull request #3616 from osm-search/tokenizers-md-typo
fix typo in Tokenizers.md
2024-12-17 08:43:16 +01:00
mtmail
df6f70d223 fix typo in Tokenizers.md 2024-12-16 23:38:18 +01:00
Sarah Hoffmann
9058dabf1a Merge pull request #3615 from lonvia/overhaul-osm2pgsql-style
Overhaul osm2pgsql style
2024-12-16 19:13:46 +01:00
Sarah Hoffmann
2535780282 exclude more tourism=information types 2024-12-16 10:44:37 +01:00
Sarah Hoffmann
48333bfbd4 reintroduce brand and remove etymology 2024-12-16 10:26:55 +01:00
Sarah Hoffmann
99cf552c17 exclude unnamed swimming pools
Publicly accessible ones are usually mapped as the bigger area
with the water park.
2024-12-16 10:26:55 +01:00
Sarah Hoffmann
ad214753fc include lock names mapped with "lock_name"
Fixes #3365.
2024-12-16 10:26:55 +01:00
Sarah Hoffmann
0d500d4bd1 do not save names when falling back to addresses
If an object doesn't have a useable main tag, then the names should
always be ignored, independently of the presence of housenumbers.
We have to assume that the name belongs to a feature that was
intentionally filtered out.
2024-12-16 10:26:55 +01:00
Sarah Hoffmann
b1e5265d33 switch to subtags for tourism=information and natural=water 2024-12-16 10:26:55 +01:00
Sarah Hoffmann
e2a9b5fdf7 exclude sidewalks and similar footways
These footways are part of a street that is usually already named.
2024-12-16 10:26:55 +01:00
Sarah Hoffmann
eeb3d5dd0a make nominatim callable with themepark style 2024-12-16 10:26:55 +01:00
Sarah Hoffmann
a75dd32f75 adapt documentation for style import 2024-12-16 10:26:55 +01:00
Sarah Hoffmann
e1e8182c72 adapt taginfo script to new configuration structure 2024-12-16 10:26:55 +01:00
Sarah Hoffmann
59bce26afe convert import styles to themepark
Introduces presets which avoid much of the previous configuration
duplication. The original import files are now thin wrappers around
the themepark themes.
2024-12-16 10:26:55 +01:00
Sarah Hoffmann
d1b7c14f79 osm2pgsql style: add modification for name and address, with tests 2024-12-16 10:26:55 +01:00
Sarah Hoffmann
59416178bd osm2pgsql style: simplify computation of extra tags
Now implemented as a simple filter function which can also be
customized by the user.
2024-12-16 10:26:55 +01:00
Sarah Hoffmann
70e351c528 osm2pgsql style: merge main tag and pre-filter handling
Defining a tag as deleteable/extratag and main tag is mutually exclusive
and deleting certain key/value combinations to exclude them from being
used as a main tag is confusing. By merging the handling, such
excludes can now be made explicit in the main list.

By using the same lookup table, it is now also possible to have a
short-cut for uninteresting objects.
2024-12-16 10:26:55 +01:00
Sarah Hoffmann
1eed2fa395 do not touch original tags of osm2pgsql OSM object 2024-12-16 10:26:55 +01:00
Sarah Hoffmann
438b8fed35 convert flex-base.lua into a themepark theme
This already allows to run Nominatim under themepark, currently
as a topic-less theme.
2024-12-16 10:26:55 +01:00
Sarah Hoffmann
4760e8341b move lua scripts into a separate directory 2024-12-16 10:26:55 +01:00
Sarah Hoffmann
639630d5fe Merge pull request #3610 from lonvia/search-preprocessing
Add configurable query preprocessing
2024-12-16 10:26:09 +01:00
Sarah Hoffmann
5b40aa579b add developers documentation for query-side of tokenizer 2024-12-13 17:09:42 +01:00
Sarah Hoffmann
fbb6edfdaf add documentation for new query preprocessing 2024-12-13 16:53:08 +01:00
Sarah Hoffmann
2b87c016db generalize normalization step for search query
It is now possible to configure functions for changing the query
input before it is analysed by the tokenizer.

Code is a cleaned-up version of the implementation by @miku.
2024-12-13 14:31:08 +01:00
Sarah Hoffmann
a894e0f3a4 docs: external osm2pgsql is not longer optional 2024-12-13 10:36:45 +01:00
Sarah Hoffmann
046665f8d9 Merge pull request #3609 from lonvia/reverse-ignore-postcode-areas
Ignore postcode areas on reverse
2024-12-13 09:00:26 +01:00
Sarah Hoffmann
d9b4d1591d ignore postcode areas on reverse
Postcode lookups are best done by doing reverse at a higher
level and then extracting the postcode.
2024-12-12 19:02:00 +01:00
Sarah Hoffmann
0862671104 Merge pull request #3608 from lonvia/reverse-fallback-country
Fall back to using the OSM grid country table when no countries are found in the OSM data
2024-12-12 18:51:18 +01:00
Sarah Hoffmann
416e70b97e have reverse fall back to country table when no country is found 2024-12-12 17:14:02 +01:00
Sarah Hoffmann
494640c535 docs: complete requirements list for dev env 2024-12-10 08:54:29 +01:00
Sarah Hoffmann
abe9737229 docs: more prominent mention of pip install 2024-11-25 14:31:44 +01:00
Sarah Hoffmann
5d237a06ea Merge pull request #3600 from clavisound/master
uvicorn.org vs www.uvicorn.org
2024-11-24 09:09:59 +01:00
clavisound
d5bfab02c2 uvicorn.org vs www.uvicorn.org
correct link
2024-11-24 08:53:12 +02:00
Sarah Hoffmann
79836e51d6 Merge pull request #3593 from lonvia/order-by-bbox
Use bbox size for secondary order of results
2024-11-19 11:50:55 +01:00
Sarah Hoffmann
0770eaa5d0 use bbox size for secondary order of results
Helps to return the largest object when deduplicating results.
2024-11-19 10:38:50 +01:00
Sarah Hoffmann
c172ca8c6c Merge pull request #3592 from lonvia/remove-cmake
Remove cmake building and bundled osm2pgsql
2024-11-19 10:02:53 +01:00
Sarah Hoffmann
4e59efa178 update instructions for Vagrant 2024-11-19 09:26:59 +01:00
Sarah Hoffmann
9cf5970e22 update release instructions 2024-11-19 09:17:50 +01:00
Sarah Hoffmann
4cce681ead switch actions to pip-based install 2024-11-18 18:52:26 +01:00
Sarah Hoffmann
c4a726c96b update Ubuntu22 install script for pip install 2024-11-18 18:51:54 +01:00
Sarah Hoffmann
a408da4ccc remove cmake and related installation instructions 2024-11-18 18:51:03 +01:00
Sarah Hoffmann
e0318344f6 remove vendored osm2pgsql 2024-11-18 13:38:03 +01:00
Sarah Hoffmann
02364ce6c8 Merge pull request #3591 from lonvia/increase-required-postgresql
Increase version requirements for PostgreSQL and PostGIS
2024-11-18 13:37:03 +01:00
Sarah Hoffmann
bf683d434b adapt BDD tests to changed simplification 2024-11-18 13:02:35 +01:00
Sarah Hoffmann
f1ba285319 actions: update to latest supported versions 2024-11-18 13:02:35 +01:00
Sarah Hoffmann
98c1b923fc remove code only needed for older PostgreSQL/PostGIS versions 2024-11-18 10:11:09 +01:00
Sarah Hoffmann
fd1f2bc719 increase minimum versions for PostgreSQL and PostGIS 2024-11-18 09:28:06 +01:00
Sarah Hoffmann
689bcbd6ea Merge pull request #3590 from lonvia/lookup-per-osm-type
Look up different OSM types in placex separately
2024-11-15 09:44:16 +01:00
Sarah Hoffmann
3acd7df5c4 Merge pull request #3588 from lonvia/optional-reverse-api
Add support for adding endpoints to server conditionally
2024-11-14 19:33:57 +01:00
Sarah Hoffmann
7d418da564 look up different OSM types in placex separately
There are separate indexes on placex for the different OSM types.
PostgreSQL can only use these indexes if the type is fixed per query.
2024-11-14 17:47:01 +01:00
Sarah Hoffmann
04d5f674eb fix grammar in issue template 2024-11-14 17:24:19 +01:00
Sarah Hoffmann
23369ce970 Merge pull request #3587 from danieldegroot2/lookup-spelling
Update lookup.py - Correct spelling for "simultaneously"
2024-11-14 16:53:11 +01:00
Sarah Hoffmann
20d0fb35ce enable search endpoint only when search table is available 2024-11-14 08:53:09 +01:00
Sarah Hoffmann
754ff15ebd move server route creation into async function 2024-11-13 21:27:14 +01:00
danieldegroot2
7c9002cae7 Update lookup.py - Correct spelling for "simultaneously"
Corrects minor spelling mistake.
2024-11-13 20:35:37 +01:00
Sarah Hoffmann
1a64c3bfcd Merge pull request #3586 from lonvia/reduce-lookup-calls
Reduce number of SQL queries for lookup call
2024-11-13 19:33:22 +01:00
Sarah Hoffmann
2735ea768a look up all places at once 2024-11-13 14:21:05 +01:00
Sarah Hoffmann
ae8694a6a6 Merge pull request #3582 from lonvia/switch-to-flake
Switch from pylint to flake8 for linting
2024-11-11 11:20:21 +01:00
Sarah Hoffmann
5ec07321d4 Merge pull request #3580 from lonvia/about-ai-prs
Contributions: some additional rules for AI use
2024-11-11 10:12:36 +01:00
Sarah Hoffmann
d77aa7dfc9 replace pylint with flake8 everywhere 2024-11-10 23:14:09 +01:00
Sarah Hoffmann
122ecd4626 remove remaining pylint hints 2024-11-10 22:49:29 +01:00
Sarah Hoffmann
1f07967787 fix style issue found by flake8 2024-11-10 22:47:14 +01:00
Sarah Hoffmann
8c14df55a6 contributions: some additional rules for AI use 2024-11-10 10:39:40 +01:00
Sarah Hoffmann
af756d61dd Merge pull request #3576 from lonvia/test-updating
Github action for testing migration
2024-11-04 15:56:20 +01:00
Sarah Hoffmann
2d115ea412 actions: add test for database migration 2024-11-04 10:19:56 +01:00
Sarah Hoffmann
981b879830 do not rename parameters in existing SQL function 2024-11-04 09:46:20 +01:00
Sarah Hoffmann
6415c9cf95 Merge pull request #3575 from lonvia/improve-centroid
Improve centroid computation for line strings
2024-11-04 09:09:40 +01:00
Sarah Hoffmann
7b21354a8a avoid multiple centroid computations 2024-11-03 22:06:36 +01:00
Sarah Hoffmann
ad50016c49 use line interpolation to create centroid for lines
ST_PointOnSurface always returns one of the vertices of a line.
This means that a two-point line will have the centroid at
one of the ends, which is less then ideal.
2024-11-03 22:06:36 +01:00
Sarah Hoffmann
b9e4563beb fix backward compatibility issues with Python 3.7 2024-10-25 23:43:59 +02:00
Sarah Hoffmann
2c0f2e1ede remove now unnecessary type-ignores 2024-10-25 17:56:47 +02:00
Sarah Hoffmann
ea98317370 Merge pull request #3558 from otbutz/patch-1
Fix gunicorn invocation
2024-10-25 15:33:59 +02:00
otbutz
2fe8b98d55 Fix gunicorn invocation 2024-10-09 10:07:43 +02:00
IvanShift
bea9249e38 Added "дом" and fixed order "школа" 2024-10-06 17:59:59 +03:00
Sarah Hoffmann
6299afcad7 Merge pull request #3554 from lonvia/postcode-bbox
Improve bounding boxes for postcodes
2024-09-30 10:50:43 +02:00
Sarah Hoffmann
5160a1d577 get bbox of postcode areas into results 2024-09-30 08:58:40 +02:00
Sarah Hoffmann
83013f819b derive bbox size for postcode nodes from rank_search 2024-09-30 08:58:40 +02:00
Sarah Hoffmann
15eb7f0bb1 add new format 'raw' for CLI commands
This dumps the original results with all details available.
2024-09-30 08:58:40 +02:00
Sarah Hoffmann
b2dc01ad81 Revert "work round typing bug in pyosmium 4.0"
This reverts commit f960a9bf7f.
2024-09-27 20:19:49 +02:00
Sarah Hoffmann
c2aa7a9b43 Merge pull request #3552 from lonvia/drop-some-migrations
Restrict migrations to versions 4.3+
2024-09-27 19:46:37 +02:00
Sarah Hoffmann
90e207a497 drop automatic migration from versions <4.3 2024-09-27 12:07:48 +02:00
Sarah Hoffmann
d856788bf5 Merge pull request #3542 from lonvia/remove-legacy-tokenizer
Remove legacy tokenizer
2024-09-24 15:42:40 +02:00
Sarah Hoffmann
f960a9bf7f work round typing bug in pyosmium 4.0 2024-09-24 11:51:01 +02:00
Sarah Hoffmann
188c770f5c supress new pylint errors 2024-09-22 21:58:25 +02:00
Sarah Hoffmann
a690605a96 remove support for unindexed tokens
This was a special feature of the legacy tokenizer who would not
index very frequent tokens.
2024-09-22 10:39:10 +02:00
Sarah Hoffmann
290c22a153 remove PHPCS configuration 2024-09-21 18:27:19 +02:00
Sarah Hoffmann
4825a0bda3 remove documentation around legacy tokenizer 2024-09-21 18:27:01 +02:00
Sarah Hoffmann
b54ff7d766 remove all references to a module path
No longer used now that legacy tokenizer is gone.
2024-09-21 17:39:01 +02:00
Sarah Hoffmann
9734bbf240 remove warning about now removed legacy tokenizer 2024-09-21 17:12:35 +02:00
Sarah Hoffmann
d4f3eda314 remove special casing for legacy tokenizer from BDD tests 2024-09-21 17:07:32 +02:00
Sarah Hoffmann
74c39267d9 remove PostgreSQL legacy module 2024-09-21 11:51:58 +02:00
Sarah Hoffmann
b87d6226fb remove legacy tokenizer and direct tests 2024-09-21 11:38:08 +02:00
Sarah Hoffmann
e92e03e2e6 Merge pull request #3536 from lonvia/remove-php
Remove PHP frontend
2024-09-16 21:49:01 +02:00
Sarah Hoffmann
9545f0bf80 add migration warning for PHP frontend removal 2024-09-16 09:40:26 +02:00
Sarah Hoffmann
c4f30de7a3 docs: remove all references to PHP 2024-09-15 16:08:26 +02:00
Sarah Hoffmann
7717bbf59d remove remaining references to php code 2024-09-15 15:33:59 +02:00
Sarah Hoffmann
7ba5152493 remove PHP frontend support from BDD tests 2024-09-15 13:51:51 +02:00
Sarah Hoffmann
6bc044d9c7 remove website setup
The website directory was for PHP scripts only and is no longer
needed.
2024-09-15 11:58:55 +02:00
Sarah Hoffmann
06683edaae remove PHP tests 2024-09-15 11:26:49 +02:00
Sarah Hoffmann
979aebbfcd remove PHP frontend 2024-09-15 11:22:13 +02:00
Sarah Hoffmann
3734f1d0b8 prepare 4.5.0 release 2024-09-11 17:51:38 +02:00
Sarah Hoffmann
a66c063314 Merge pull request #3532 from lonvia/refresh-docs
Update library documentation
2024-09-11 10:27:09 +02:00
Sarah Hoffmann
fe0ade81f5 docs: improve contents listing 2024-09-10 20:41:35 +02:00
Sarah Hoffmann
f52212abbd docs: rework library getting started 2024-09-10 20:41:35 +02:00
Sarah Hoffmann
8f30a32466 docs: avoid loading external fonts 2024-09-10 20:41:35 +02:00
Sarah Hoffmann
157c3cccd1 fix permalink character 2024-09-10 20:41:35 +02:00
Sarah Hoffmann
3e6be0b0be Merge pull request #3530 from lonvia/clean-use-of-os-environ
Don't use OS environment variables when an explicit environment was set
2024-09-02 09:49:10 +02:00
Sarah Hoffmann
882fb16881 restrict use of os.environ in Configuration
Only use the OS environment, when the environ parameter is set
to None. Currently it would use the OS env on an empty dict.
2024-09-01 16:17:30 +02:00
Sarah Hoffmann
72be143cef Merge pull request #3523 from mtmail/import-styles-country-code
Import-Styles.md - clarify country_code key
2024-08-26 14:03:47 +02:00
Sarah Hoffmann
086116b3a1 Merge pull request #3525 from lonvia/project-dir-less-library
Simplify handling of project directory for Nominatim library
2024-08-26 13:54:35 +02:00
marc tobias
ed7f0d9e46 Import-Styles.md - clarify country_code key 2024-08-23 13:50:25 +02:00
mtmail
b5a6d7a4a6 fix typo in Import-Styles.md 2024-08-23 00:40:13 +02:00
Sarah Hoffmann
7f11de0db9 allow None and str for project_dir in NominatimAPI init 2024-08-22 22:49:12 +02:00
Sarah Hoffmann
f535340d5a Merge pull request #3520 from lonvia/restrict-interpolation-range
Restrict interpolation housenumbers to 0-999999
2024-08-20 09:03:52 +02:00
Sarah Hoffmann
c7d80a2cc8 Merge pull request #3521 from lonvia/make-requests-optional
Fix error around missing requests library
2024-08-20 09:03:39 +02:00
Sarah Hoffmann
0efdd1b9a6 restrict interpolation housenumbers to 0-999999
Ensures that the numbers fit into integers.
2024-08-19 20:40:25 +02:00
Sarah Hoffmann
fd9437277e import requests library later than osmium
requests will usually be pulled in by osmium and is therefore not
a direct dependency of nominatim. Make sure it is only used, when
osmium is present.
2024-08-19 16:36:09 +02:00
Sarah Hoffmann
968f1cd453 Merge pull request #3519 from lonvia/api-error-handling
Improve error handling around CLI api commands
2024-08-19 16:26:18 +02:00
Sarah Hoffmann
adce7261ac translate UsageError in CLI API commands
UsageErrors are handled specially and don't show backtraces
unless explicitly requested. We want the same behaviour for
errors coming from the API functions.
2024-08-19 12:02:33 +02:00
Sarah Hoffmann
b01a836d1e use NominatimAPI in with context in CLI tool 2024-08-19 11:42:22 +02:00
Sarah Hoffmann
c2594aca40 make NominatimAPI[Async] a context manager
If close() isn't properly called, it can lead to odd error messages
about uncaught exceptions.
2024-08-19 11:31:38 +02:00
Sarah Hoffmann
8b41b80bff Merge pull request #3517 from lonvia/improve-custom-formatter
Extend use of custom result formatters to CLI tool
2024-08-18 10:20:53 +02:00
Sarah Hoffmann
feb8cc29a5 improve error message on missing modules from nominatim_api 2024-08-17 10:03:36 +02:00
Sarah Hoffmann
1cd8ffad0b improve docs on custom result formatters
Adds section on formatting errors and using CLI. Improves wording
in others.
2024-08-16 22:11:41 +02:00
Sarah Hoffmann
d648561a87 CLI: more useful error messages on JSON formatting errors 2024-08-16 19:47:48 +02:00
Sarah Hoffmann
8e8f7a641b use custom result formatters in CLI commands 2024-08-16 19:30:57 +02:00
Sarah Hoffmann
69369c08c8 add missing includes in result fomatting example 2024-08-16 11:32:38 +02:00
Sarah Hoffmann
fdb3fc2f7b Merge pull request #3516 from lonvia/fixed-country-order
Ensure consistent country assignments
2024-08-15 16:54:38 +02:00
Sarah Hoffmann
054efc8311 ensure consistent country assignments
When OSM data has areas with overlapping countries, use the country
assignments from the pre-defined country grid for tie-breaking.
If that fails, fall back to the country with the smaller partition
number.
2024-08-15 14:26:09 +02:00
Sarah Hoffmann
d7cf81c047 Merge pull request #3515 from lonvia/custom-result-formatting
Add the capability to define custom formatting functions for API output
2024-08-15 09:26:27 +02:00
Sarah Hoffmann
19eb4d91a0 add documentation for custom formatters 2024-08-14 18:24:40 +02:00
Sarah Hoffmann
5a61d3d5f6 configurable error formatting and content type in result formatter 2024-08-14 12:00:08 +02:00
Sarah Hoffmann
52ee5dc73c make API formatter loadable from project directory 2024-08-13 23:21:38 +02:00
Sarah Hoffmann
0c25e80be0 make formatting module non-static 2024-08-13 22:39:43 +02:00
Sarah Hoffmann
4e0602919c move ASGIAdoptor out of v1 module 2024-08-13 21:32:11 +02:00
Sarah Hoffmann
d22ca186e4 remove v1-specific functions from ASGIAdaptor 2024-08-13 19:38:14 +02:00
Sarah Hoffmann
4f4a288757 Merge pull request #3514 from lonvia/remove-pythonpath
Vagrant install: remove custom python path
2024-08-13 15:18:48 +02:00
Sarah Hoffmann
14cc047cf4 vagrant install: remove custom python path 2024-08-13 09:31:36 +02:00
Sarah Hoffmann
043d52821c Merge pull request #3510 from lonvia/indexing-precompute-count
Indexing: precompute counts of affected rows
2024-08-12 23:55:19 +02:00
Sarah Hoffmann
3905dd68dd indexing: precompute row counts
Doing this once for the whole batch of ranks saves about
half a second for small imports. Speeds up BDD tests.
2024-08-12 14:57:26 +02:00
Sarah Hoffmann
bd0316b5c3 Merge pull request #3509 from lonvia/deprecations
Add deprecation warnings and check for osm2pgsql version
2024-08-12 11:27:56 +02:00
Sarah Hoffmann
fd33ef92dc add deprecation warnings in the code 2024-08-09 19:25:15 +02:00
Sarah Hoffmann
6527b7cdcd fail if osm2pgsql is not recent enough 2024-08-09 19:25:15 +02:00
Sarah Hoffmann
3cc20581ae osm2pgsq: do not use deprecated tablespace options 2024-08-09 19:25:15 +02:00
Sarah Hoffmann
a2a44b875a add deprecation warnings throughout docs 2024-08-09 19:25:15 +02:00
Sarah Hoffmann
a14ab1c08c Merge pull request #3506 from mtmail/development-environment-more-dependencies
Development environment: add missing dependencies
2024-08-09 19:24:56 +02:00
marc tobias
0ba3d01982 Development environment: add missing dependencies 2024-08-09 17:57:18 +02:00
Sarah Hoffmann
f6e792f31b Merge pull request #3502 from mtmail/check-database-check-another-index
check-database: check for another required db index
2024-08-08 15:21:38 +02:00
Sarah Hoffmann
882f182374 Merge pull request #3503 from lonvia/mkdocs-without-cmake
Build documentation without CMake
2024-08-07 19:21:00 +02:00
Sarah Hoffmann
d1e7b85cc5 fix dangling links in documentation 2024-08-07 16:58:45 +02:00
Sarah Hoffmann
6b1c32893b move generated docs to site-html 2024-08-07 16:48:22 +02:00
Sarah Hoffmann
474a22cb3b build man page without CMake 2024-08-07 16:38:56 +02:00
Sarah Hoffmann
8e46458d9e remove CMake-based build of docs 2024-08-07 16:31:15 +02:00
Sarah Hoffmann
7282d816c8 build vagrant instructions dynamically with mkdocs-gen-files 2024-08-07 16:28:44 +02:00
marc tobias
7cf21f8caf check-database: check for another required db index 2024-08-07 15:19:40 +02:00
Sarah Hoffmann
738e99ce71 Merge pull request #3499 from mtmail/add-data-warn-if-frozen
Add data warn if frozen
2024-08-07 11:11:58 +02:00
Sarah Hoffmann
e104115134 switch instruction to use wikimedia CSV file 2024-08-07 10:43:45 +02:00
marc tobias
f0390cfe85 add-data: warn and exit if database is frozen 2024-08-05 16:14:19 +02:00
Sarah Hoffmann
a4d7cdd2ad Merge pull request #3493 from lonvia/clean-up-bdd-tests
Various cleanups of BDD tests
2024-07-31 17:02:39 +02:00
Sarah Hoffmann
2914284a83 adapt BDD tests for legacy tokenizer + Python frontend
Mostly disables the tests, the cases are not worth fixing anymore.
Others just avoid using terms that trigger abbreviations.
2024-07-31 14:55:16 +02:00
Sarah Hoffmann
a97bfaf26c fix postcode lookup with legacy tokenizer 2024-07-31 14:54:55 +02:00
Sarah Hoffmann
cfe5284f64 make housenumber search work with non-indexed partials 2024-07-31 14:09:35 +02:00
Sarah Hoffmann
2048009600 disable ZIP5+ test for Python frontend
Currently not working.
2024-07-31 14:08:57 +02:00
Sarah Hoffmann
d47acbc18a add forgotten BDD test 2024-07-31 11:16:49 +02:00
Sarah Hoffmann
f5fd2f0e7a switch CI to new handling of legacy BDD tests 2024-07-31 11:16:49 +02:00
Sarah Hoffmann
c8d45972bb remove support for PHP code coverage in BDD tests 2024-07-31 11:16:49 +02:00
Sarah Hoffmann
474aea61da bdd tests: get rid of dependency on build path
BDD tests will now use whatever osm2pgsql they find in the PATH.
For testing against legacy tokenizer, use -DSERVER_MODULE_PATH
to point to the module. This will no longer work out of the box.
2024-07-31 11:16:49 +02:00
Sarah Hoffmann
67462e0953 Merge pull request #3492 from lonvia/drop-waste-disposal
Remove waste disposals and hunting stands from index
2024-07-30 17:03:08 +02:00
Sarah Hoffmann
804fb5f93e Merge pull request #3490 from mtmail/which-url-after-webserver-install
After install point user to '/status' not '/' path
2024-07-30 15:39:22 +02:00
marc tobias
f52097c064 After install point user to /status not / path 2024-07-30 13:10:24 +02:00
Sarah Hoffmann
d336b81293 drop amenity=waste_prposal and amenity=hunting_stand 2024-07-30 10:41:13 +02:00
Sarah Hoffmann
507c0286da Merge pull request #3491 from mtmail/faq-unicode-encoding
Admin FAQ entry for UnicodeEncodeError
2024-07-29 22:01:46 +02:00
marc tobias
04a3f39371 Admin FAQ entry for UnicodeEncodeError 2024-07-29 18:26:11 +02:00
Sarah Hoffmann
bc75e5626e Merge pull request #3466 from mtmail/apple-silicon-parallels
Vagrant: add config for Apple Silicon
2024-07-29 16:52:54 +02:00
Sarah Hoffmann
0add25e335 Merge pull request #3487 from lonvia/port-to-psycopg3
Move importer code to psycopg3
2024-07-29 16:52:07 +02:00
Sarah Hoffmann
253dc7d7cd Ubuntu 22 doesn't have psycopg yet 2024-07-29 08:54:18 +02:00
Sarah Hoffmann
221b5cd8a2 fix dependencies and adapt documentation for psycopg3 2024-07-29 08:54:09 +02:00
Sarah Hoffmann
9659afbade port code to psycopg3 2024-07-29 08:50:19 +02:00
Sarah Hoffmann
3742fa2929 make DB helper functions free functions
Also changes the drop function so that it can drop multiple tables
at once.
2024-07-29 08:49:30 +02:00
Sarah Hoffmann
71249bd94a remove extension existence helper
This is only used in one place.
2024-07-29 08:49:02 +02:00
Sarah Hoffmann
e3353deee0 Merge pull request #3480 from mtmail/import-style-adits
full,extra import style: add adits
2024-07-24 22:59:29 +02:00
marc tobias
00563a1fa2 full,extra import style: add adits 2024-07-17 10:57:29 +02:00
Shumail Mohyuddin
b8686c19a0 fix docs link in update interval error message (#3479) 2024-07-17 10:37:07 +02:00
Sarah Hoffmann
b89144dcb2 Merge pull request #3468 from mtmail/setup-python-v5
Github Actions: now use setup-python v4->v5
2024-07-08 18:45:06 +02:00
Sarah Hoffmann
8e5a19b392 Merge pull request #3467 from mtmail/docs-datrie
Documentation: typo in python package name
2024-07-08 18:44:50 +02:00
marc tobias
5d12121f6d Github Actions: now use setup-python v4->v5 2024-07-08 17:26:36 +02:00
marc tobias
24f103dcbe Documentation: typo in python package name 2024-07-08 16:44:09 +02:00
marc tobias
0109f167f9 Vagrant: add config for Apple Silicon 2024-07-08 15:35:01 +02:00
Sarah Hoffmann
b63633857e Merge pull request #3463 from lonvia/sqlalchemy14-with-psycopg
Make sure SQLAlchemy can handle the loaded dialect
2024-07-02 18:43:28 +02:00
Sarah Hoffmann
8cb0d5b262 make sure SQLAlchemy can handle the loaded dialect
The psycopg dialect was only added in SQLAlchemy 2.0. To avoid loading
errors when SQLAlchemy 1.4 is installed together with psycopg3,
check that the dialect is really available.
2024-07-02 15:55:23 +02:00
Mateusz Konieczny
e51973f8b1 fix some typos 2024-07-01 15:03:57 +02:00
Sarah Hoffmann
c314a3092c Merge pull request #3458 from lonvia/python-package
Add support for installation via pip
2024-07-01 15:02:01 +02:00
Sarah Hoffmann
8dafd8bcb6 add mtm as maintainer for the Python packages 2024-07-01 14:25:26 +02:00
Sarah Hoffmann
ecf4693a79 improve wording
as per review
2024-06-29 16:27:26 +02:00
Sarah Hoffmann
fa1c402b47 enable CI tests for Ubuntu 24 2024-06-28 11:11:59 +02:00
Sarah Hoffmann
4da4cbfe27 reduce from 3 to 2 packages 2024-06-28 09:13:22 +02:00
Sarah Hoffmann
139cea5720 update documentation for new directory layout 2024-06-26 11:52:47 +02:00
Sarah Hoffmann
e2416f90af installation for Ubuntu 24.04 with packages
Also remove Ubuntu 20.04 instructions.
2024-06-26 11:52:47 +02:00
Sarah Hoffmann
1e88321371 switch to symlink approach for packages
Needed to make building work from sdist and source directory.
2024-06-26 11:52:47 +02:00
Sarah Hoffmann
a93ec09932 adapt packaging readmes 2024-06-26 11:52:47 +02:00
Sarah Hoffmann
9abf2c248e update licenses and discussion links 2024-06-26 11:52:47 +02:00
Sarah Hoffmann
ab746eebaf export UsageError and Configuration in api directly
Library users should not have to deal with the core package directly.
2024-06-26 11:52:47 +02:00
Sarah Hoffmann
3ba330c948 update CI commands for linting 2024-06-26 11:52:47 +02:00
Sarah Hoffmann
aef1357066 adapt cmake to new directory structure 2024-06-26 11:52:47 +02:00
Sarah Hoffmann
5d302a03a6 make use of nominatim-api in db package optional 2024-06-26 11:52:47 +02:00
Sarah Hoffmann
3a8c5df82d adapt bdd tests to new layout 2024-06-26 11:52:47 +02:00
Sarah Hoffmann
44d5148e5f fix merge issues 2024-06-26 11:52:47 +02:00
Sarah Hoffmann
63da70685a fix linting issues 2024-06-26 11:52:47 +02:00
Sarah Hoffmann
2bab0ca060 port unit tests to new python package layout 2024-06-26 11:52:47 +02:00
Sarah Hoffmann
c903559415 move API dependent functions out of args structure 2024-06-26 11:52:47 +02:00
Sarah Hoffmann
6511821001 add packaging for the different subprojects 2024-06-26 11:52:47 +02:00
Sarah Hoffmann
75abf237a6 add missing __init__.py 2024-06-26 11:52:47 +02:00
Sarah Hoffmann
dc7c11a9d1 adapt plugin imports 2024-06-26 11:52:47 +02:00
Sarah Hoffmann
44fface92a add script for in-source execution 2024-06-26 11:52:47 +02:00
Sarah Hoffmann
6e89310a92 split code into submodules 2024-06-26 11:52:47 +02:00
Sarah Hoffmann
0fb4fe8e4d add Python package configuration
The global configuration builds one large package.
2024-06-26 11:52:47 +02:00
Markus Döring
b0067a0345 update Search.md, fix typo (#3454) 2024-06-24 15:24:09 +02:00
Sarah Hoffmann
4c72cdaa86 Merge pull request #3447 from lonvia/avoid-invalidating-large-features
Restrict invalidation of child objects on large street features
2024-06-19 15:06:23 +02:00
Sarah Hoffmann
350bb0e1cd restrict invalidation of child objects on large street features
When streets become very large, it is more likely a mapping error.
So ignore such changes.
2024-06-19 14:23:29 +02:00
Sarah Hoffmann
ad95ff1d06 Merge pull request #3424 from lonvia/importance-csc-import
Implement a lighter format for wikipedia importance tables
2024-05-29 18:06:53 +02:00
Sarah Hoffmann
90eea6b909 adapt database test for wikipedia importance to new tables 2024-05-16 15:23:54 +02:00
Sarah Hoffmann
5b02cd22b9 add tests for new importance CSV import 2024-05-16 15:23:54 +02:00
Sarah Hoffmann
60b03d506f add CSV format for importance import 2024-05-16 15:23:54 +02:00
Sarah Hoffmann
5c7073901e Merge pull request #3423 from mudnug/patch-1
Update Output place_id documentation to match implementation
2024-05-15 11:26:01 +02:00
Matthew
b33afee468 Update Output place_id documentation to match implementation 2024-05-14 12:00:17 -06:00
Sarah Hoffmann
6a748204ff Merge pull request #3422 from lonvia/drop-non-parented-interpolations
Drop address interpolations when no parent can be found
2024-05-14 16:40:28 +02:00
Sarah Hoffmann
9889c72c55 work around new pylint warnings 2024-05-14 14:50:37 +02:00
Sarah Hoffmann
01f0f453dd drop interpolations when no parent can be found
A housenumber without the place it refers to is of only limited use.
2024-05-14 11:35:14 +02:00
Sarah Hoffmann
7f0d969d71 Merge pull request #3413 from osm-search/mtmail-patch-1
Special-Phrases.md - correct typo
2024-05-06 09:18:09 +02:00
mtmail
a47fa07558 Special-Phrases.md - correct typo 2024-05-05 22:46:21 +02:00
Sarah Hoffmann
2b3ea0abb7 Merge pull request #3411 from lonvia/fix-address-style
Address and street style: switch to explicit choice of highway values
2024-05-05 13:01:20 +02:00
Sarah Hoffmann
755ae0ef94 address and street style: switch to explicit choice of highway values
The non-street values for the highway tag are proliferating.
Switch the style to only include values explicitly choosen.
2024-05-05 11:21:48 +02:00
Sarah Hoffmann
ccb5cf155d Merge pull request #3410 from lonvia/docs-special-phrases
Add documentation of the format for special phrases CSV
2024-05-05 11:14:22 +02:00
Sarah Hoffmann
7080a13c54 fix typo 2024-05-05 09:59:46 +02:00
Sarah Hoffmann
cf2697f8f4 add documentation of special phrases CSV format 2024-05-05 09:59:32 +02:00
Sarah Hoffmann
a6b829e4a0 Merge pull request #3409 from lonvia/docs-secondary-importance
Add documentation for installing a secondary importance file
2024-05-04 15:11:19 +02:00
Sarah Hoffmann
f92e580293 Merge pull request #3408 from lonvia/update-postcode-parents
Reindex postcodes when their parent is deleted
2024-05-04 15:11:05 +02:00
Sarah Hoffmann
bc84db6460 add links to official secondary importance file 2024-05-04 13:13:00 +02:00
Sarah Hoffmann
77631f90fd reindex postcodes that loose their parents
When the parent place of a postcode is deleted, it needs to
be reindexed to get a new parent. Otherwise displaying of
results is broken.
2024-05-04 12:33:26 +02:00
Sarah Hoffmann
332de72045 Merge pull request #3403 from mtmail/project-directory-name
docs: use nominatim-project everywhere
2024-05-02 13:46:43 +02:00
Sarah Hoffmann
a2cf6db61b Merge pull request #3397 from lonvia/improve-handling-unlisted-places
Improve handling addr:place without a place node
2024-05-02 13:46:18 +02:00
marc tobias
82a98f3780 docs: use nominatim-project everywhere 2024-05-02 11:48:06 +02:00
Sarah Hoffmann
7fb3ef4633 add test for preference of full matches on unlisted places 2024-05-02 11:47:35 +02:00
Sarah Hoffmann
8f3845660f add full tokens to addresses
This is now needed to weigh results.
2024-05-02 11:47:35 +02:00
Sarah Hoffmann
d2bf986eae unlisted place names need to go into the address
Housenumbers with unlisted place names should be handled like
any ither housenumbers with missing address terms.
2024-05-02 11:47:35 +02:00
Sarah Hoffmann
9410263485 actions: use newest pytest-asyncio for ubuntu 20 2024-05-02 11:06:45 +02:00
Sarah Hoffmann
82970e2b4f Merge pull request #3390 from lonvia/poi-in-poi
Handle POIs in POIs during reverse lookup
2024-04-11 17:32:01 +02:00
Sarah Hoffmann
f923304eea add slight preference for locating point POIs over POI areas 2024-04-11 10:21:31 +02:00
Sarah Hoffmann
1a0f851d0d Merge pull request #3389 from mtmail/cli-autodiscover-valid-formats
CLI: get valid --format values via autodiscover
2024-04-09 14:58:53 +02:00
marc tobias
28444d9435 CLI: get valid --format values via autodiscover 2024-04-09 14:03:23 +02:00
Sarah Hoffmann
8c54f9d704 Merge pull request #3385 from mtmail/docs-reverse-only
Import documentation: reverse-only only a little faster import
2024-04-03 14:33:54 +02:00
marc tobias
c24dc56c65 Import documentation: reverse-only only a little faster import [skip ci] 2024-04-03 12:07:22 +02:00
Sarah Hoffmann
5c4c98d17e Merge pull request #3384 from mtmail/geocodejson-admin-levels-only-boundaries
geocodejson: admin level output should only print boundaries
2024-04-03 11:52:08 +02:00
Sarah Hoffmann
657aae5f1b Merge pull request #3383 from lonvia/window-searches
Reorganize SQL for place search using window functions
2024-04-03 10:55:10 +02:00
Sarah Hoffmann
38798bba13 increase search area when filtering by postcode 2024-04-02 19:36:16 +02:00
marc tobias
05eb1d5f42 geocodejson: admin level output should only print boundaries 2024-04-02 18:58:09 +02:00
Sarah Hoffmann
fe873ad0e2 adapt tests for windowing SQL
Results with high penalty are now thrown out earlier.
2024-04-02 16:32:49 +02:00
Sarah Hoffmann
bdded69ab6 housenumber position should hint on direction
rather than increasing penalty.
2024-04-02 16:30:50 +02:00
Sarah Hoffmann
9f42c3f3b8 remove restriction on frequent one word names
This is now solved by reducing results with the windowing SQL
during search.
2024-04-02 16:28:17 +02:00
Sarah Hoffmann
424ebd7fe9 split search SQL in windowed search_name lookup and constraint search 2024-04-02 16:28:12 +02:00
Sarah Hoffmann
78c19bc006 minimum counts for tokens should always be 1
to avoid accidental devision by 0.
2024-04-01 14:25:51 +02:00
Sarah Hoffmann
e53eb79923 Merge pull request #3375 from matkoniecz/patch-1
add missing space in taginfo listing
2024-03-27 10:03:45 +01:00
Sarah Hoffmann
c39fc5d180 don't even try heavily penalized searches 2024-03-26 22:00:25 +01:00
Sarah Hoffmann
a96b6a1289 reintroduce cutoffs when searching for very frequent words 2024-03-26 21:46:37 +01:00
Mateusz Konieczny
8f6f113e1c add missing space in taginfo listing
say https://taginfo.openstreetmap.org/tags/shop=guns#projects was listing description

`POI/feature in the search database(except for values: no).`
2024-03-26 15:43:00 +01:00
Sarah Hoffmann
436aff2fd3 Merge pull request #3373 from lonvia/restrict-man-made
Style tweaks: restrict man_made features to be imported
2024-03-25 15:20:47 +01:00
Sarah Hoffmann
44922af20e style: restrict man_made main tag to selected values 2024-03-25 11:46:39 +01:00
Sarah Hoffmann
4315debff5 Merge pull request #3367 from lonvia/address-word-counts
Introduce word usage statistics for addresses
2024-03-18 14:32:26 +01:00
Sarah Hoffmann
ace84ed0e3 use address counts for improving index lookup 2024-03-18 11:25:48 +01:00
Sarah Hoffmann
ff3230a7f3 add penalty for single words that look like stop words 2024-03-18 11:25:48 +01:00
Sarah Hoffmann
07b7fd1dbb add address counts to tokens 2024-03-18 11:25:48 +01:00
Sarah Hoffmann
bb5de9b955 extend word statistics to address index
Word frequency in names is not sufficient to interpolate word
frequency in the address because names of towns, states etc. are
much more frequently used than, say street names.
2024-03-18 11:25:48 +01:00
Sarah Hoffmann
40b87bbadf Merge pull request #3363 from mtmail/docs-link-correction
Docs: correct URL of an internal link
2024-03-14 17:46:34 +01:00
marc tobias
1c195eb1e4 docs: correct URL of an internal link 2024-03-14 13:50:24 +01:00
Sarah Hoffmann
9c48726691 add geometry details for postcode area output 2024-03-12 13:51:29 +01:00
Sarah Hoffmann
4fa349315b Merge pull request #3362 from lonvia/find-postcode-areas
Lookup postcode areas for postcode results
2024-03-12 10:05:16 +01:00
Sarah Hoffmann
50beac8305 remove BDD test for place_id details
It is not reliable.
2024-03-11 21:07:14 +01:00
Sarah Hoffmann
9de6bdd7dd exclude postcode test from legacy and php 2024-03-11 15:28:57 +01:00
Sarah Hoffmann
6e688a0113 postcodes: exclude seen places later
The seen list will only have the postcode area when available but
we want the postcode point excluded as well if the area has been seen.
2024-03-11 15:18:57 +01:00
Sarah Hoffmann
dc7cfd1708 look for postcode areas when finding something in the postcode table 2024-03-11 14:48:24 +01:00
Sarah Hoffmann
e5a5f02666 prepare release 4.4.0 2024-03-07 11:43:01 +01:00
Sarah Hoffmann
11ced26025 Merge pull request #3358 from lonvia/pg-module-for-pg16
Fix compilation of legacy module for PostgreSQL 16
2024-03-07 11:39:24 +01:00
Sarah Hoffmann
edb1eec46d actions: run legacy test against newest postgresql 16 2024-03-05 19:38:06 +01:00
Sarah Hoffmann
63eacc5589 fix compilation of PG module for PostgreSQL 16
This version requires an additional include for the macros used.
2024-03-05 16:31:02 +01:00
Sarah Hoffmann
e929693cae Merge pull request #3356 from lonvia/use-date-from-osm2pgsql-prop
Use import date from osm2pgsql property table if available
2024-03-05 15:32:16 +01:00
Sarah Hoffmann
ae7c584e28 use import date from osm2pgsql property table if available 2024-03-05 11:33:32 +01:00
Sarah Hoffmann
4d5faf9423 Merge pull request #3353 from mtmail/add-codespell
Github Actions: add codespell linter, warn only
2024-03-04 14:02:00 +01:00
marc tobias
b7eea4d53a Github Actions: add codespell linter, warn only 2024-03-04 00:22:24 +01:00
Sarah Hoffmann
dd2c794de5 Merge pull request #3350 from lonvia/improve-postcode-handling
Improve handling of postcode areas
2024-02-28 18:45:31 +01:00
Sarah Hoffmann
3b6d35fc12 Merge pull request #3349 from lonvia/remove-way-geometry-table-after-import
Drop lower-rank-ways index after import
2024-02-28 17:47:34 +01:00
Sarah Hoffmann
9fa73cfb15 improve display name for postcodes
Don't add the postcode again in the list of address details and
make sure that the result proper always comes before anything else
independently of the address rank.
2024-02-28 16:50:40 +01:00
Sarah Hoffmann
62b7670e0c for postcodes use rank_search as base rank for finding addresses
The rank_address reflects the position in the address which is
usually lower than what one would expect for a postcode area.
2024-02-28 14:40:36 +01:00
Sarah Hoffmann
d7bb449e74 drop lower-rank-ways index after import
The index becomes quite big and is only needed during import
because the full geometry import does not exist yet.
2024-02-28 14:35:56 +01:00
Sarah Hoffmann
247065ff6f Merge pull request #3342 from mtmail/tyops
Correct some typos
2024-02-28 14:25:16 +01:00
Sarah Hoffmann
9a84adef59 Merge pull request #3347 from lonvia/tweak-boundary-imports
Assorted style tweaks
2024-02-28 14:22:08 +01:00
Sarah Hoffmann
1879cf902c Merge pull request #3346 from lonvia/reduce-artificial-importance
Reduce default importance
2024-02-28 14:21:46 +01:00
Sarah Hoffmann
019a68a4bb Merge pull request #3345 from lonvia/simplify-large-geometries
Simplify very large polygons that are not used in addresses
2024-02-28 12:06:49 +01:00
Sarah Hoffmann
110491011f Merge pull request #3344 from lonvia/osm2pgsql-new-middle
Update osm2pgsql to latest 1.11.0 and add support for new middle format
2024-02-28 12:06:33 +01:00
Sarah Hoffmann
36b1660121 add support for new middle table format of osm2pgsql
Functions are adapted according to the format detected from the
osm2pgsql property table.
2024-02-27 18:18:19 +01:00
Sarah Hoffmann
56201feb28 simplify very large polygons non used in addresses
Polygons with rank_address = 0 are only used in search and (rarely)
for reverse lookup. Geometries do not need to be precise for that
because topology does not matter. OSM has some very large polygons
of natural features with sizes of more than 10MB. Simplify these
polygons to keep the database and indexes smaller.
2024-02-27 10:16:18 +01:00
Sarah Hoffmann
c6d40d4bf4 reduce importance when computed from search rank 2024-02-27 10:15:54 +01:00
Sarah Hoffmann
a4f2e6a893 do not send outdated parameters to osm2pgsql flex 2024-02-27 10:15:36 +01:00
Sarah Hoffmann
b427fc7965 update osm2pgsql to 1.11.0 2024-02-27 10:15:36 +01:00
Sarah Hoffmann
e264604894 drop more railway tags 2024-02-27 10:15:08 +01:00
Sarah Hoffmann
3a5d9f0377 drop amenity=parking_space/entrance objects
Parking is sufficiently covered with amenity=parking.
2024-02-27 10:15:08 +01:00
Sarah Hoffmann
8be27015b2 drop boundary=land_area
Usually a version of administrative boundaries without ocean area.
Resulting polygons are pretty larrge and having the boundaries
should be enough.
2024-02-27 10:15:08 +01:00
Sarah Hoffmann
100391fb8e import leisure=natural_reserve as fallback only
About half of the natural reserves have a double tagging with
boundary=protected_area. Avoid importing these objects twice.
2024-02-27 10:15:08 +01:00
Sarah Hoffmann
dc1baaa0af prefer min() function over if construct
Fixes a linter complaint.
2024-02-27 09:26:50 +01:00
marc tobias
7205491b84 Correct some typos 2024-02-26 18:13:30 +01:00
Sarah Hoffmann
918fec73c6 Merge pull request #3341 from mtmail/remove-php-faq-entries
PHP related FAQ entries are no longer needed
2024-02-21 08:56:18 +01:00
marc tobias
b6df486525 PHP related FAQ entries are no longer needed 2024-02-20 18:55:02 +01:00
Sarah Hoffmann
8bd8a040e0 Merge pull request #3340 from lonvia/fix-lua-liniting-issues
Fix some issues in the style files found by luacheck
2024-02-20 12:00:01 +01:00
Sarah Hoffmann
781e83ddc3 fix issues found by luacheck
The variable shadowing causes bad results when used with LuaJIT.
2024-02-20 10:43:51 +01:00
Sarah Hoffmann
5afd96d210 Merge pull request #3339 from lonvia/python-frontend-as-default
Switch to Python frontend as the default
2024-02-20 10:17:21 +01:00
Sarah Hoffmann
cf49a070fd switch Ubuntu installation scripts to Python frontend 2024-02-19 18:39:01 +01:00
Sarah Hoffmann
4aba36c5ac API debug: properly escape non-highlighted code 2024-02-19 18:39:01 +01:00
Sarah Hoffmann
ca6e65fff1 bdd: be more verbose on HTML parsing error 2024-02-19 18:39:01 +01:00
Sarah Hoffmann
1e0025b095 also switch unit tests for cli 2024-02-19 18:39:01 +01:00
Sarah Hoffmann
173e85c9e6 actions: make php the legacy tests 2024-02-19 18:39:01 +01:00
Sarah Hoffmann
ffb467028e update documentation to recommend Python frontend 2024-02-19 18:39:01 +01:00
Sarah Hoffmann
05fad607ff make Python frontend default and PHP optional 2024-02-19 18:39:01 +01:00
Sarah Hoffmann
19360a9552 Merge pull request #3338 from lonvia/remove-nested-cli-groups
Add documentation for importing without superuser rights
2024-02-16 19:27:25 +01:00
Sarah Hoffmann
b087f3ab7b actions: switch no-superuser test to PostgreSQL 16
The new premission restrictions on the public schema took only
place in PG15, so the previsouly used PG14 does not show any issues.
2024-02-16 17:14:47 +01:00
Sarah Hoffmann
2c8fb31381 add documentation for non-superuser import 2024-02-16 17:14:47 +01:00
Sarah Hoffmann
b2d3f0a8b3 remove unnecessary nested group in CLI import command 2024-02-16 11:32:50 +01:00
Sarah Hoffmann
bd8025feab Merge pull request #3333 from lonvia/set-empty-extratags-to-null
Extratags should become null when empty
2024-02-08 14:26:49 +01:00
Sarah Hoffmann
4c19762e33 extratags should become null when empty
Removing the artifical entries in the extratags may lead to
an empty hstore. Set it to null in that case.

Fixes #3055.
2024-02-08 10:21:48 +01:00
Sarah Hoffmann
1015ac40ae Merge pull request #3332 from lonvia/improve-cutting-of-result-list
Prefilter bad results before adding details and reranking
2024-02-07 10:50:32 +01:00
Sarah Hoffmann
4ce13f5c1f prefilter bad results before adding details and reranking
Move the first cutting of the result list before reranking
by result match. This means that results with significantly
less importance are removed early and independently of the
fact how well they match the original query.

Fixes #3266.
2024-02-06 20:29:48 +01:00
Sarah Hoffmann
2833362cf6 Merge pull request #3331 from lonvia/fix-word-table-rights
Properly grant rights to read-only user when switching out word table
2024-02-06 20:21:25 +01:00
Sarah Hoffmann
bc51378aee properly grant rights to read-only user when switching out word table 2024-02-06 17:30:01 +01:00
Sarah Hoffmann
39039e2a55 docs: mark layer parameter as python-only 2024-02-06 15:59:04 +01:00
Sarah Hoffmann
f523c01571 Merge pull request #3328 from lonvia/word-count-into-new-table
Recreate word table when refreshing counts
2024-02-05 11:58:11 +01:00
Sarah Hoffmann
81eed0680c recreate word table when refreshing counts
The counting touches a large part of the word table, leaving
bloated tables and indexes. Thus recreate the table instead and
swap it in.
2024-02-04 21:35:10 +01:00
Sarah Hoffmann
33c0f249b1 avoid LookupAny with address and too many name tokens
The index for nameaddress_vector has grown so large that PostgreSQL
will resort to a sequential scan if there are too many items
in the LookupAny list.
2024-01-29 16:52:14 +01:00
Sarah Hoffmann
76eadc562c print any collected debug output when returning a timeout error 2024-01-28 22:30:34 +01:00
Sarah Hoffmann
3cc3e3b2e3 Merge pull request #3321 from lonvia/remove-duplicate-partials
Improvements to query parsing
2024-01-28 20:32:58 +01:00
Sarah Hoffmann
f07f8530a8 housenumber-only searches cannot be combined with qualifiers 2024-01-28 19:03:11 +01:00
Sarah Hoffmann
103800a732 adjust rankings for housenumber-only searches
A normal address search with housenumber will use name rankings for
the street name. This is slightly different than weighing for
address parts. Use the same ranking for the first part of the
address for housenumber-only searches to make sure that penalties
remain comparable.
2024-01-28 19:03:11 +01:00
Sarah Hoffmann
f9ba7a465a always add a penalty for name + address search fallback
If there already was a search by full names, the search is likely
a repeatition that yields the same results, only running slower.
2024-01-28 19:03:11 +01:00
Sarah Hoffmann
fed46240d5 disallow category tokens in the middle of a query string
This already worked for left-to-right readings and now is also
implemented for right-to-left reading. A qualifier must always be
before or after the name.
2024-01-28 19:03:11 +01:00
Sarah Hoffmann
2703442fd2 protect against very frequent bad partials 2024-01-28 19:03:11 +01:00
Sarah Hoffmann
2813bf18e6 avoid duplicates in the list of partial tokens for a query
This messes with the estimates for expected results.
2024-01-28 19:03:11 +01:00
Sarah Hoffmann
dcebea376d Merge pull request #3320 from lonvia/fix-timeout-return-code
Fix returned HTTP error when query runs too long
2024-01-28 10:37:37 +01:00
Sarah Hoffmann
b3a2b3d484 catch special async timeout error in servers
In Python <= 3.10 this is not yet the same as TimeoutError.

Fixes #3303.
2024-01-27 20:57:23 +01:00
Sarah Hoffmann
7321e66d08 Merge pull request #3317 from lonvia/postcodes-for-highway-areas
Search postcodes for highway areas around the area
2024-01-26 19:51:02 +01:00
Sarah Hoffmann
9627352ee4 search postcodes for highway areas around the area
So far the code would only accept postcodes that are inside the area.

Fixes #3304.
2024-01-26 18:14:11 +01:00
Sarah Hoffmann
bfc7acbb18 Merge pull request #3301 from lonvia/fix-class-search-regression
Interpret stand-alone special terms always as near term
2024-01-17 10:47:35 +01:00
Sarah Hoffmann
e0ca2ce6ec interpret stand-alone special terms always as near term
Fixes #3298.
2024-01-16 17:19:21 +01:00
Sarah Hoffmann
b969c5a62f Merge pull request #3293 from lonvia/rematch-against-country-code
Add country code to words to be rematched
2024-01-08 18:48:32 +01:00
Sarah Hoffmann
28f7e51279 add country code to words to be rematched 2024-01-08 12:23:23 +01:00
Sarah Hoffmann
d35eb4105e Merge pull request #3292 from lonvia/faster-country-search
Speed up country search
2024-01-07 20:42:20 +01:00
Sarah Hoffmann
b2afe3ce3e when a country is in the results, restrict further searches to places
A country search result usually comes with a very high importance.
As a result only other very well known places will show up together
with country results and that means only places with lower address
ranks. Name searches for country names tend to yield a lot of POI
results because the country name is part of the name
(think "embassy of Sweden"). By excluding POIs from further searches,
the search is sped up quite a bit.
2024-01-07 17:29:12 +01:00
Sarah Hoffmann
7337898b84 dump params in log view 2024-01-07 15:37:53 +01:00
Sarah Hoffmann
4305160c91 prioritize country searches when penaly is equal 2024-01-07 15:28:37 +01:00
Sarah Hoffmann
dc52d0954e Merge pull request #3238 from mtmail/check-database-for-version-match
admin --check-database also checks database vs nominatim version
2024-01-07 15:24:00 +01:00
Sarah Hoffmann
d3a575319f Merge pull request #3289 from lonvia/viewbox-and-housenumbers
Do not restrict by viewbox when housenumber or postcode is available
2024-01-07 15:23:14 +01:00
Sarah Hoffmann
2592bf1954 Merge pull request #3290 from lonvia/near-vs-quaifier-words
Do not run near queries on qualifier words
2024-01-07 15:23:00 +01:00
Sarah Hoffmann
88d7ffa274 Merge pull request #3291 from lonvia/fix-timezone-handling
Fix timezone handling for timestamps from the database
2024-01-07 15:22:42 +01:00
Sarah Hoffmann
474d4230b8 fix timezone handling for timestamps from the database
SQLite is not timezone-aware, so make sure to convert to UTC
before inserting any data.
2024-01-07 11:37:40 +01:00
Sarah Hoffmann
10a5424a71 do not run near queries on qualifier words
There is too much potential for confusion (e.g. 'Rio Grande' read
as 'river near Grande') fir too little gain. Use near phrases
instead.
2024-01-07 11:33:11 +01:00
Sarah Hoffmann
7eb04f67e2 do not restrict by viewbox when housenumber or postcode is available
Fixes #3274.
2024-01-07 11:29:26 +01:00
Marc Tobias
1d7e078a2c check-database also checks database vs nominatim version 2024-01-06 20:56:56 +01:00
Sarah Hoffmann
f03ec3ea12 Merge pull request #3286 from lonvia/avoid-bind-parameters-in-lambdas
Avoid closure variables in lambda statements
2024-01-05 21:24:48 +01:00
Sarah Hoffmann
8e90fa3395 avoid closure variables in lambda statements
There is a bug in SQLAlchemy that assigns the wrong value to bind
parameters from closure variables when reusing lambda statements
that are later extended with other non-lambda expressions.

Thus either avoid lambda statements with closure variables or extending
them with non-lambda expressions.
2024-01-05 17:49:28 +01:00
Sarah Hoffmann
02af0a2c87 use correct SQLAlchemy pool for asynchronous connections
See https://github.com/sqlalchemy/sqlalchemy/issues/8771
2024-01-02 16:15:44 +01:00
Sarah Hoffmann
fa4e5513d1 API: avoid engine disposal on startup 2024-01-02 16:10:30 +01:00
Sarah Hoffmann
93afe5a7c3 update typing for latest changes in SQLAlchemy 2023-12-29 20:55:33 +01:00
Sarah Hoffmann
af85ad390f Merge pull request #3273 from lonvia/search-with-sqlite
Add forward search capability for SQLite databases
2023-12-12 12:15:22 +01:00
Sarah Hoffmann
ab45db5360 add minimal documentation for the SQLite usage 2023-12-09 16:30:31 +01:00
Sarah Hoffmann
89094cf92e error out when a SQLite database does not exist
Requires to mark the databse r/w when it is newly created in the
convert function.
2023-12-07 10:24:53 +01:00
Sarah Hoffmann
3f5484f48f enable search for sqlite conversion by default 2023-12-07 09:33:42 +01:00
Sarah Hoffmann
ff06b64329 enable all BDD API tests for sqlite 2023-12-07 09:32:02 +01:00
Sarah Hoffmann
6d39563b87 enable all API tests for sqlite and port missing features 2023-12-07 09:32:02 +01:00
Sarah Hoffmann
0d840c8d4e extend sqlite converter for search tables 2023-12-07 09:31:00 +01:00
Sarah Hoffmann
381bd0b576 remove unused function 2023-12-07 09:31:00 +01:00
Sarah Hoffmann
b5c61e0b5b improve typing for @compiles constructs
The first parameter is in fact the self parameter referring to
the function class.
2023-12-07 09:31:00 +01:00
Sarah Hoffmann
df6eddebcd void unnecessary aliases 2023-12-07 09:31:00 +01:00
Sarah Hoffmann
b6c8c0e72b factor out SQL for filtering by location
Also improves on the decision if an indexed is used or not.
2023-12-07 09:31:00 +01:00
Sarah Hoffmann
b06f5fddcb simplify handling of SQL lookup code for search_name
Use function classes which can be instantiated directly.
2023-12-07 09:31:00 +01:00
Sarah Hoffmann
8791c6cb69 correctly close API objects during testing 2023-12-07 09:31:00 +01:00
Sarah Hoffmann
615b166c68 clean up ST_DWithin and intersects() functions
A non-index version of ST_DWithin is not necessary. ST_Distance
can be used for that purpose. Index use for intersects can be
covered with a simple parameter.
2023-12-07 09:31:00 +01:00
Sarah Hoffmann
c41f2fed21 simplify weigh_search() function
Use JSON arrays which can have mixed types and therefore have
a more logical structure than separate arrays. Avoid JSON dicts
because of their verboseness.
2023-12-07 09:31:00 +01:00
Sarah Hoffmann
05e47fbb28 fix parameter formatting in sqlite debug output 2023-12-07 09:31:00 +01:00
Sarah Hoffmann
1b7c8240ba enable connection pools for sqlite
Connecting is reasonably expensive because the spatialite extension
needs to be loaded. Disable pooling for tests because there is some
memory leak when quickly opening and closing QueuePools with sqlite
connections.
2023-12-07 09:31:00 +01:00
Sarah Hoffmann
c4fd3ab97f hide type differences between Postgres and Sqlite in custom types
Also define a custom set of operators in preparation of differences
in implementation.
2023-12-07 09:31:00 +01:00
Sarah Hoffmann
8c7140d92b Merge pull request #3108 from mtmail/remove-legacy-wikipedia-tag-syntax
These days the OSM wikipedia tab no longer contains URLs
2023-12-07 09:24:32 +01:00
Sarah Hoffmann
3969ce0f55 Merge pull request #3268 from mtmail/wikipedia-file-path-warning
Improve error message when Wikipedia importance file is not found
2023-12-07 09:21:59 +01:00
Robbe Haesendonck
4f5f5ea8fc Removed unnecessary check for --prepare-database flag 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
5f7cc91cf9 Connect using localhost instead of socket 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
424c1f0d41 Added changing permissions of nominatim-project dir 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
cff05394a1 Added osm-import to sudoers file for tokenizer setup 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
638b40c3ec Fixing CI tests for install-no-superuser 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
53d2050dc5 Fixed typechecking error 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
97ac036df5 Added missing return types to functions 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
482f7fe3ba CI tests: Removed creation of user www-data.
Removed creation of user www-data as it already exists
2023-12-07 09:04:33 +01:00
Robbe Haesendonck
567c31ab6a Fixed legacy import command
Check whether prepare-database is true, if so exit early
2023-12-07 09:04:33 +01:00
Robbe Haesendonck
7d28fc35d1 Disabled pylint too-many-branches 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
c06f902398 Fixed setting tokenizer property 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
59ae63e6f5 Updated no-superuser install ci test
Added nominatim_database_webuser (www-data).
Set non-superuser password for importing
2023-12-07 09:04:33 +01:00
Robbe Haesendonck
9c7d947fd1 Updated check to see if osm_file is set 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
58db0ad6d8 Fixed formatting 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
3b09c39dbf Updated ci tests to reflect changes in Nominatim CLI 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
db917cb0d4 Made sure legacy import command still works 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
ba6cdd875d Removed unused variable, fixed connection 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
d231ff60ed Removed _is_complete_import check 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
c74904d075 Improved logic.
Fixed small oversight in mutually exclusiveness of arguments
2023-12-07 09:04:33 +01:00
Robbe Haesendonck
22204050f2 Added new psql user for importing the data 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
667197a47e Changed naming of flags.
Made sure legacy import is also still ok
2023-12-07 09:04:33 +01:00
Robbe Haesendonck
e8b866aa88 Added check to see if hstore is loaded 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
e7b8e1a2c2 Fixed ci-tests, osm-file flag
Preparing database should work without osm-file
2023-12-07 09:04:33 +01:00
Robbe Haesendonck
279b4fd6d2 Renamed flags 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
b7c83d3580 Fixed pylint warnings 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
d4018f2e3b Added check for hstore extension 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
38369ca3cf Fixed typo 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
cc0bdd34e9 Fixed linting errors 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
8e71ff329c Added version check for PostGis and Postgres 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
b4e3d0ea44 Updated CI tests to check new import flags 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
992703b15e Added --prepare-database flag 2023-12-07 09:04:33 +01:00
Robbe Haesendonck
ba5ec80611 Added --no-superuser flag
To allow import into already existing databases.
Refs: #2719
2023-12-07 09:04:33 +01:00
marc tobias
1c1447e709 Improve error message when Wikipedia importance file is not found 2023-12-06 14:31:07 +01:00
Sarah Hoffmann
3c32c0354a actions: pin pytest-asyncio version for Ubuntu 20
Newest versions are no longer compatible with older pytest.
2023-12-04 14:32:03 +01:00
Sarah Hoffmann
8a2c6067a2 skip lookup with full names when there are none 2023-12-01 12:11:58 +01:00
Sarah Hoffmann
d60a45715a Merge pull request #3263 from lonvia/near-search-penalty-inheritance
More tweaks for Python frontend search
2023-11-29 14:02:24 +01:00
Sarah Hoffmann
3c7a28dab0 further restrict stop search criterion 2023-11-29 11:28:54 +01:00
Sarah Hoffmann
0c72a434e0 use restrict for housenumber lookups with few numbers 2023-11-29 11:28:54 +01:00
Sarah Hoffmann
32e7b59b1f NearSearch needs to inherit penalty from inner search 2023-11-29 11:28:52 +01:00
Sarah Hoffmann
f448423727 Merge pull request #3262 from lonvia/fix-category-search
Fix use of category parameter for search() function
2023-11-28 20:02:36 +01:00
Sarah Hoffmann
b2319e52ff correctly exclude streets with housenumber searches
Street result are not subject to the full filtering in the SQL
query, so recheck.
2023-11-28 17:53:37 +01:00
Sarah Hoffmann
25279d009a add tests for interaction of category parameter with category terms 2023-11-28 16:56:08 +01:00
Sarah Hoffmann
3f72ca4bca rename use of category as POI search to near_item
Use the term category only as a short-cut for "tuple of key and value".
2023-11-28 16:27:05 +01:00
Sarah Hoffmann
70dc4957dc the category parameter in search should result in a qualifier 2023-11-28 12:01:49 +01:00
Sarah Hoffmann
d8ed565bce Merge pull request #3260 from lonvia/improve-catgeory-search
Various improvements to search with special phrases for Python frontend
2023-11-27 12:02:11 +01:00
Sarah Hoffmann
a7f5c6c8f5 drop category tokens when they make up a full phrase 2023-11-26 20:58:50 +01:00
Sarah Hoffmann
a8b023e57e restrict base results in near search by rank
This avoids in particular that roads or POIs are used as base
for the near search when a place result is present.
2023-11-26 17:41:29 +01:00
Sarah Hoffmann
47ca56f21b deduplicate categories/qualifiers 2023-11-26 17:11:15 +01:00
Sarah Hoffmann
580a7b032f order near searches by distance instead of importance 2023-11-26 16:48:04 +01:00
Sarah Hoffmann
8fcc2bb7f5 avoid duplicate lines during category search 2023-11-26 14:53:20 +01:00
Sarah Hoffmann
d6fe58f84e fix polygon selection for classtable lookups
Polygons should be used preferably with higher address ranks
where the areas are smaller.
2023-11-25 21:01:27 +01:00
Sarah Hoffmann
2d54de09bb Merge pull request #3257 from lonvia/slow-queries
Performance tweaks for search
2023-11-23 12:05:50 +01:00
Sarah Hoffmann
4e4d29f653 increase penalty for one-letter words 2023-11-23 10:51:58 +01:00
Sarah Hoffmann
195c13ee8a more preference for name-only queries in search 2023-11-22 23:57:23 +01:00
Sarah Hoffmann
ac5ef64701 avoid index use when filtering by layer 2023-11-22 20:54:04 +01:00
Sarah Hoffmann
e7dc24c026 add timestamps to text logging 2023-11-22 17:38:32 +01:00
Sarah Hoffmann
155f26060d avoid index on rank_address in near search 2023-11-22 17:33:17 +01:00
Sarah Hoffmann
a87fe8d8bf exclude country-level searches with non-address layers 2023-11-22 17:01:41 +01:00
Sarah Hoffmann
158df6b2e8 Merge pull request #3252 from kumarUjjawal/patch-1
minor typo fix
2023-11-22 12:51:37 +01:00
Kumar Ujjawal
b8db76c925 minor typo fix
fixed a minor typo, from 'wit' to 'with'.
2023-11-20 17:23:42 +05:30
Sarah Hoffmann
fffdfc9b88 add report on newest vulnerability 2023-11-20 10:44:48 +01:00
Sarah Hoffmann
6478409b05 improve code to collect the PostGIS version
The SQL contained an unchecked string literal, which may in theory be
used to attack the database.
2023-11-16 11:14:29 +01:00
Sarah Hoffmann
ee556fd42e Merge pull request #3248 from lonvia/fix-postcode-area-computation
PHP frontent: fix postcode area computation for address points
2023-11-15 22:10:21 +01:00
Sarah Hoffmann
9a1b8a67d6 adapt typing to newest version of SQLAlchemy 2023-11-15 19:59:26 +01:00
Sarah Hoffmann
383e3ccd25 php frontend: fix on-the-fly lookup of postcode areas 2023-11-15 17:45:12 +01:00
Sarah Hoffmann
b4ce1fb599 remove now unnecessary type igonre comment 2023-11-01 11:57:57 +01:00
Sarah Hoffmann
2bf8e62580 fix assertion on address list, it may be empty
Fixes #3237.
2023-10-31 21:10:54 +01:00
Sarah Hoffmann
afb439b089 Merge pull request #3235 from lonvia/fix-python-deploy
Python frontend deployment: add systemd service for the socket
2023-10-25 14:54:13 +02:00
Sarah Hoffmann
78a87ad16b python deployment: add systemd service for the socket 2023-10-25 11:31:42 +02:00
Sarah Hoffmann
5bf55a69a5 Merge pull request #3234 from lonvia/reduce-admin-style
Streamline admin style
2023-10-25 09:38:17 +02:00
Sarah Hoffmann
ca782e2f20 Merge pull request #3233 from lonvia/support-for-sqlite
Add support for SQLite DBs in frontend: reverse
2023-10-24 11:54:35 +02:00
Sarah Hoffmann
308de35802 further reduce admin style import to admin-only objects 2023-10-24 09:50:43 +02:00
Sarah Hoffmann
a9ac68a729 restrict geometry size for SQLite 2023-10-23 17:19:12 +02:00
Sarah Hoffmann
84d6b481ae convert sqlite: add index on parent_place_id 2023-10-23 17:19:12 +02:00
Sarah Hoffmann
613c8635a8 remove type info from SQLALchemy condition functions
A boolean type makes the SQLite dialect produce a costruct like
'func() = 1' in WHERE condition. While syntactically correct, it tends
to confuse the query planer.
2023-10-23 17:19:12 +02:00
Sarah Hoffmann
899a04ad26 make code work with Spatialite 4.3
Transfer is_address_point into SQLAlchemy function, so that
json.has_key() can use the older json_extract() function.
And work around broken Distance function.
2023-10-23 17:19:12 +02:00
Sarah Hoffmann
d8dca2a3a9 enable BDD tests for sqlite databases
The database must currently be created by hand and the name handed
in via -DAPI_TEST_DB='sqlite:...'.
2023-10-23 17:19:12 +02:00
Sarah Hoffmann
8216899a9a trim all coordinate output to 7 digits 2023-10-23 17:19:12 +02:00
Sarah Hoffmann
b1d419f458 add indexing support for DWithin and intersects for sqlite 2023-10-23 17:19:12 +02:00
Sarah Hoffmann
0417946153 make reverse API work with sqlite 2023-10-23 17:19:12 +02:00
Sarah Hoffmann
1149578e8f actions: enable sqlite testing 2023-10-23 17:19:12 +02:00
Sarah Hoffmann
37488ee82b try future annotations to resolve Generics compatibility 2023-10-23 17:19:12 +02:00
Sarah Hoffmann
06bbd501fd make status API work with sqlite incl. unit tests 2023-10-23 17:19:12 +02:00
Sarah Hoffmann
07e6c5cf69 make details API work with sqlite incl. unit tests 2023-10-23 17:19:12 +02:00
Sarah Hoffmann
d0c91e4acf make lookup call work with sqlite
Includes porting unit tests.
2023-10-23 17:19:12 +02:00
Sarah Hoffmann
114cdafe7e add exporting of SQLite table 2023-10-23 17:19:12 +02:00
Sarah Hoffmann
837bdecde8 add skeleton code for convert function 2023-10-23 17:19:12 +02:00
Sarah Hoffmann
d9d0e70e5b streamline SQLAlchemy DB schema
Remove all information not strictly used by the frontend as well as
any index information. This will make it easier to create a SQLite
database from the schema.
2023-10-23 17:19:12 +02:00
Sarah Hoffmann
1255efba7f remove unused code 2023-10-23 11:55:18 +02:00
Sarah Hoffmann
6ad397d4a9 Merge branch 'clean-deleted-relations' of https://github.com/lujoh/Nominatim into lujoh-clean-deleted-relations 2023-10-23 10:47:31 +02:00
Sarah Hoffmann
570ca22d71 Merge pull request #3228 from pawel-wroniszewski/fix/postcode-validation
Properly validate postcodes with country code
2023-10-23 10:35:42 +02:00
lujoh
418f381b49 made age a required argument for the -clean-deleted command 2023-10-20 15:31:55 -04:00
Paweł Wroniszewski
2cae37ccde Revert country settings 2023-10-20 12:50:28 +02:00
lujoh
650fbc2563 added --clean deleted command to the documentation 2023-10-18 02:05:46 -04:00
lujoh
9ec26c60ff adjusted tests for --clean-deleted-relations command 2023-10-17 23:03:37 -04:00
lujoh
06204dfcd8 moved sql function flush_deleted_places() to utils 2023-10-17 18:22:27 -04:00
Paweł Wroniszewski
fbe40e005d Properly validate postcodes with country code
Include postcode pattern in postcode normalisation regex, instead of
removing it from postcode pattern in config.

It properly handles postcode validation and normalization when country code
is part of the postcode, e.g. for Isle of Man, Jersey, Anguilla, Andorra,
Cayman Islands and more.

Fixes #3227.
2023-10-17 01:04:07 +02:00
lujoh
e9efef9095 added subcommand to clean deleted relations for issue # 2444 2023-10-16 11:30:58 -04:00
Sarah Hoffmann
95c3181a35 adapt typing for newer version of mypy 2023-10-16 17:03:48 +02:00
Sarah Hoffmann
12dbfb0777 Merge pull request #3222 from lonvia/fix-river-output
Make sure the place name always comes first in output
2023-10-10 11:20:12 +02:00
Sarah Hoffmann
b62dbd1f92 reduce influence of viewbox
Perfectly matching city names should still get priority.
2023-10-07 22:00:52 +02:00
Sarah Hoffmann
5011fde176 make sure the place name always comes first in output
Also deleted some now unused code.
2023-10-05 16:37:28 +02:00
Sarah Hoffmann
54cb9a33b1 Merge pull request #3212 from lonvia/more-tests
Add more unit tests for search
2023-10-05 16:36:53 +02:00
Sarah Hoffmann
f1fbcd863d switch back meaning of reverse and search in warm
Also do'n try to warm up searches on reverse-only databases.

Fixes #3213.
2023-10-04 15:19:24 +02:00
Sarah Hoffmann
b00b16aa3a more unit tests for search 2023-09-27 15:00:05 +02:00
Sarah Hoffmann
0f19695225 Merge pull request #3211 from lonvia/replace-get-addressdata
Move get_addressdata() implementation to Python
2023-09-26 21:29:15 +02:00
Sarah Hoffmann
7fcbe13669 move get_addressdata() implementation to Python
The pgsql function get_addressdata() does a lookup of a lot of data
that is already available in Python.
2023-09-26 11:21:36 +02:00
Sarah Hoffmann
87c91ec5c4 Merge pull request #3206 from lonvia/rerank-by-locale
Reintroduce result reranking
2023-09-21 09:24:18 +02:00
Sarah Hoffmann
0e10916b07 adapt tests to improved search 2023-09-20 14:58:54 +02:00
Sarah Hoffmann
21df87dedc filter duplicate results after DB query 2023-09-20 14:58:54 +02:00
Sarah Hoffmann
fd26310d6a rerank results by query
The algorithm is similar to the PHP reranking and uses the terms from
the display name to check against the query terms. However instead of
exact matching it uses a per-word-edit-distance, so that it is less
strict when it comes to mismatching accents or other one letter
differences.

Country names get a higher penalty because they don't receive a
penalty during token matching right now.

This will work badly with the legacy tokenizer. Given that it is
marked for removal, it is simply not worth optimising for it.
2023-09-20 14:52:05 +02:00
Sarah Hoffmann
5762a5bc80 move localization into add_result_details
This means that the locale now needs to be handed in into the search
functions already. At least search needs them for reranking.
2023-09-19 11:17:04 +02:00
Sarah Hoffmann
8106e67f14 Merge pull request #3201 from lonvia/tweak-expected-count
Reduce expected count for multi-part words
2023-09-17 17:04:27 +02:00
Sarah Hoffmann
f029fb3c65 'fix' issues with recent changes to psycopg2 typing
Some of the changes just make the warnings go away. The typing info
is still incorrect on the stub side, as far as I can determine.
2023-09-17 15:09:34 +02:00
Sarah Hoffmann
44da684d1d reduce expected count for multi-part words
Fixes #3196.
2023-09-11 17:45:34 +02:00
Marc Tobias
f59a072aa6 These days the OSM wikipedia tab no longer contains URLs 2023-07-07 17:36:11 +02:00
Alexander Sapozhnikov
1e4677b668 Expand Russian abbreviation list 2022-11-01 04:01:27 +05:00
Alexander Sapozhnikov
7f909dbbd8 Add replacement for Russian 2022-11-01 02:54:07 +05:00
833 changed files with 29570 additions and 37731 deletions

7
.codespellrc Normal file
View File

@@ -0,0 +1,7 @@
# https://github.com/codespell-project/codespell
[codespell]
skip = ./man/nominatim.1,data,./docs/styles.css,lib-php,module,munin,osm2pgsql,./test,./settings/*.lua,./settings/*.yaml,./settings/**/*.yaml,./settings/icu-rules,./nominatim/tokenizer/token_analysis/config_variants.py
# Need to be lowercase in the list
# Unter = Unter den Linden (an example address)
ignore-words-list = inout,unter

11
.flake8 Normal file
View File

@@ -0,0 +1,11 @@
[flake8]
max-line-length = 100
max-doc-length = 100
extend-ignore =
# something == None constructs are needed for SQLAlchemy
E711
per-file-ignores =
__init__.py: F401
test/python/utils/test_json_writer.py: E131
**/conftest.py: E402
test/bdd/*: F821

View File

@@ -2,3 +2,6 @@ contact_links:
- name: Nominatim Discussions
url: https://github.com/osm-search/Nominatim/discussions
about: Ask questions, get support, share ideas and discuss with community members.
- name: Discussions about OpenStreetMap data
url: https://community.openstreetmap.org/
about: Ask questions about the data used by Nominatim and discuss with the OSM community.

View File

@@ -17,11 +17,11 @@ assignees: ''
## What result did you expect?
**When the result in the right place and just named wrongly:**
**When the result is in the right place and just named wrongly:**
<!-- Please tell us the display name you expected. -->
**When the result missing completely:**
**When the result is missing completely:**
<!-- Make sure that the data you are looking for is in OpenStreetMap. Provide a link to the OpenStreetMap object or if you cannot get it, a link to the map on https://openstreetmap.org where you expect the result to be.

12
.github/PULL_REQUEST_TEMPLATE.md vendored Normal file
View File

@@ -0,0 +1,12 @@
## Summary
<!-- Describe the purpose of your pull request and, if present, link to existing issues. -->
## AI usage
<!-- Please list where and to what extent AI was used. -->
## Contributor guidelines (mandatory)
<!-- We only accept pull requests that follow our guidelines. A deliberate violation may result in a ban. -->
- [ ] I have adhered to the [coding style](https://github.com/osm-search/Nominatim/blob/master/CONTRIBUTING.md#coding-style)
- [ ] I have [tested](https://github.com/osm-search/Nominatim/blob/master/CONTRIBUTING.md#testing) the proposed changes
- [ ] I have [disclosed](https://github.com/osm-search/Nominatim/blob/master/CONTRIBUTING.md#using-ai-assisted-code-generators) above any use of AI to generate code, documentation, or the pull request description

View File

@@ -1,18 +1,10 @@
name: 'Build Nominatim'
inputs:
flavour:
description: 'Version of Ubuntu to install on'
dependencies:
description: 'Where to install dependencies from (pip/apt)'
required: false
default: 'ubuntu-20'
cmake-args:
description: 'Additional options to hand to cmake'
required: false
default: ''
lua:
description: 'Version of Lua to use'
required: false
default: '5.3'
default: 'pip'
runs:
using: "composite"
@@ -23,30 +15,30 @@ runs:
sudo rm -rf /opt/hostedtoolcache/go /opt/hostedtoolcache/CodeQL /usr/lib/jvm /usr/local/share/chromium /usr/local/lib/android
df -h
shell: bash
- name: Install${{ matrix.flavour }} prerequisites
- name: Install general prerequisites
run: |
sudo apt-get install -y -qq libboost-system-dev libboost-filesystem-dev libexpat1-dev zlib1g-dev libbz2-dev libpq-dev libproj-dev libicu-dev liblua${LUA_VERSION}-dev lua${LUA_VERSION} lua-dkjson nlohmann-json3-dev
if [ "$FLAVOUR" == "oldstuff" ]; then
pip3 install MarkupSafe==2.0.1 python-dotenv psycopg2==2.7.7 jinja2==2.8 psutil==5.4.2 pyicu==2.9 osmium PyYAML==5.1 sqlalchemy==1.4.31 datrie asyncpg
else
sudo apt-get install -y -qq python3-icu python3-datrie python3-pyosmium python3-jinja2 python3-psutil python3-psycopg2 python3-dotenv python3-yaml
pip3 install sqlalchemy psycopg
fi
sudo apt-get install -y -qq libspatialite-dev libsqlite3-mod-spatialite libicu-dev virtualenv python3-dev osm2pgsql
shell: bash
env:
FLAVOUR: ${{ inputs.flavour }}
CMAKE_ARGS: ${{ inputs.cmake-args }}
LUA_VERSION: ${{ inputs.lua }}
- name: Configure
run: mkdir build && cd build && cmake $CMAKE_ARGS ../Nominatim
shell: bash
env:
CMAKE_ARGS: ${{ inputs.cmake-args }}
- name: Build
- name: Install prerequisites from apt
run: |
make -j2 all
sudo make install
sudo apt-get install -y -qq python3-icu python3-datrie python3-jinja2 python3-psutil python3-dotenv python3-yaml python3-sqlalchemy python3-psycopg python3-asyncpg python3-mwparserfromhell
shell: bash
if: inputs.dependencies == 'apt'
- name: Setup virtual environment (for pip)
run: |
virtualenv venv
./venv/bin/pip install -U pip
shell: bash
if: inputs.dependencies == 'pip'
- name: Setup virtual environment (for apt)
run: |
virtualenv venv --system-site-packages
shell: bash
if: inputs.dependencies == 'apt'
- name: Build nominatim
run: ./venv/bin/pip install Nominatim/packaging/nominatim-{api,db}
shell: bash
working-directory: build

View File

@@ -4,9 +4,6 @@ inputs:
postgresql-version:
description: 'Version of PostgreSQL to install'
required: true
postgis-version:
description: 'Version of Postgis to install'
required: true
runs:
using: "composite"
@@ -14,21 +11,18 @@ runs:
steps:
- name: Remove existing PostgreSQL
run: |
sudo /usr/share/postgresql-common/pgdg/apt.postgresql.org.sh -y
sudo apt-get purge -yq postgresql*
sudo apt install curl ca-certificates gnupg
curl https://www.postgresql.org/media/keys/ACCC4CF8.asc | gpg --dearmor | sudo tee /etc/apt/trusted.gpg.d/apt.postgresql.org.gpg >/dev/null
sudo sh -c 'echo "deb https://apt.postgresql.org/pub/repos/apt $(lsb_release -cs)-pgdg main" > /etc/apt/sources.list.d/pgdg.list'
sudo apt-get update -qq
shell: bash
- name: Install PostgreSQL
run: |
sudo apt-get install -y -qq --no-install-suggests --no-install-recommends postgresql-client-${PGVER} postgresql-${PGVER}-postgis-${POSTGISVER} postgresql-${PGVER}-postgis-${POSTGISVER}-scripts postgresql-contrib-${PGVER} postgresql-${PGVER}
sudo apt-get install -y -qq --no-install-suggests --no-install-recommends postgresql-client-${PGVER} postgresql-${PGVER}-postgis-3 postgresql-${PGVER}-postgis-3-scripts postgresql-contrib-${PGVER} postgresql-${PGVER}
shell: bash
env:
PGVER: ${{ inputs.postgresql-version }}
POSTGISVER: ${{ inputs.postgis-version }}
- name: Adapt postgresql configuration
run: |

View File

@@ -11,7 +11,7 @@ jobs:
with:
submodules: true
- uses: actions/cache@v3
- uses: actions/cache@v4
with:
path: |
data/country_osm_grid.sql.gz
@@ -27,7 +27,7 @@ jobs:
mv nominatim-src.tar.bz2 Nominatim
- name: 'Upload Artifact'
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v4
with:
name: full-source
path: nominatim-src.tar.bz2
@@ -37,187 +37,108 @@ jobs:
needs: create-archive
strategy:
matrix:
flavour: [oldstuff, "ubuntu-20", "ubuntu-22"]
flavour: ["ubuntu-22", "ubuntu-24"]
include:
- flavour: oldstuff
ubuntu: 20
postgresql: '9.6'
postgis: '2.5'
php: '7.3'
lua: '5.1'
- flavour: ubuntu-20
ubuntu: 20
postgresql: 13
postgis: 3
php: '7.4'
lua: '5.3'
- flavour: ubuntu-22
ubuntu: 22
postgresql: 15
postgis: 3
php: '8.1'
postgresql: 12
lua: '5.1'
dependencies: pip
python: '3.9'
- flavour: ubuntu-24
ubuntu: 24
postgresql: 18
lua: '5.3'
dependencies: apt
python: 'builtin'
runs-on: ubuntu-${{ matrix.ubuntu }}.04
steps:
- uses: actions/download-artifact@v3
- uses: actions/download-artifact@v4
with:
name: full-source
- name: Unpack Nominatim
run: tar xf nominatim-src.tar.bz2
- name: Setup PHP
uses: shivammathur/setup-php@v2
with:
php-version: ${{ matrix.php }}
tools: phpunit:9, phpcs, composer
ini-values: opcache.jit=disable
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- uses: actions/setup-python@v4
with:
python-version: 3.7
if: matrix.flavour == 'oldstuff'
- uses: ./Nominatim/.github/actions/setup-postgresql
with:
postgresql-version: ${{ matrix.postgresql }}
postgis-version: ${{ matrix.postgis }}
- uses: ./Nominatim/.github/actions/build-nominatim
with:
flavour: ${{ matrix.flavour }}
lua: ${{ matrix.lua }}
dependencies: ${{ matrix.dependencies }}
- name: Install test prerequsites (behave from apt)
run: sudo apt-get install -y -qq python3-behave
if: matrix.flavour == 'ubuntu-20'
- uses: actions/cache@v4
with:
path: |
/usr/local/bin/osm2pgsql
key: osm2pgsql-bin-22-1
if: matrix.ubuntu == '22'
- name: Install test prerequsites (behave from pip)
run: pip3 install behave==1.2.6
if: (matrix.flavour == 'oldstuff') || (matrix.flavour == 'ubuntu-22')
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python }}
if: matrix.python != 'builtin'
- name: Install test prerequsites (from apt for Ununtu 2x)
run: sudo apt-get install -y -qq python3-pytest python3-pytest-asyncio uvicorn
if: matrix.flavour != 'oldstuff'
- name: Compile osm2pgsql
run: |
if [ ! -f /usr/local/bin/osm2pgsql ]; then
sudo apt-get install -y -qq libboost-system-dev libboost-filesystem-dev libexpat1-dev zlib1g-dev libbz2-dev libpq-dev libproj-dev libicu-dev liblua${LUA_VERSION}-dev lua-dkjson nlohmann-json3-dev
mkdir osm2pgsql-build
cd osm2pgsql-build
git clone https://github.com/osm2pgsql-dev/osm2pgsql
mkdir build
cd build
cmake ../osm2pgsql
make
sudo make install
cd ../..
rm -rf osm2pgsql-build
else
sudo apt-get install -y -qq libexpat1 liblua${LUA_VERSION}
fi
if: matrix.ubuntu == '22'
env:
LUA_VERSION: ${{ matrix.lua }}
- name: Install newer pytest-asyncio
run: pip3 install -U pytest-asyncio
if: matrix.flavour == 'ubuntu-20'
- name: Install test prerequisites (apt)
run: sudo apt-get install -y -qq python3-pytest python3-pytest-asyncio uvicorn python3-falcon python3-aiosqlite python3-pyosmium
if: matrix.dependencies == 'apt'
- name: Install test prerequsites (from pip for Ubuntu 18)
run: pip3 install pytest pytest-asyncio uvicorn
if: matrix.flavour == 'oldstuff'
- name: Install test prerequisites (pip)
run: ./venv/bin/pip install pytest-asyncio falcon starlette asgi_lifespan aiosqlite osmium uvicorn
if: matrix.dependencies == 'pip'
- name: Install Python webservers
run: pip3 install falcon starlette
- name: Install test prerequisites
run: ./venv/bin/pip install pytest-bdd
- name: Install latest pylint
run: pip3 install -U pylint asgi_lifespan
- name: PHP linting
run: phpcs --report-width=120 .
working-directory: Nominatim
- name: Install latest flake8
run: ./venv/bin/pip install -U flake8
- name: Python linting
run: python3 -m pylint nominatim
run: ../venv/bin/python -m flake8 src test/python test/bdd
working-directory: Nominatim
- name: PHP unit tests
run: phpunit ./
working-directory: Nominatim/test/php
- name: Install mypy and typechecking info
run: ./venv/bin/pip install -U mypy types-PyYAML types-jinja2 types-psutil types-requests types-ujson types-Pygments typing-extensions
if: matrix.dependencies == 'pip'
- name: Python static typechecking
run: ../venv/bin/python -m mypy --strict --python-version 3.9 src
working-directory: Nominatim
if: matrix.dependencies == 'pip'
- name: Python unit tests
run: python3 -m pytest test/python
run: ../venv/bin/python -m pytest test/python
working-directory: Nominatim
- name: BDD tests
run: |
python3 -m behave -DREMOVE_TEMPLATE=1 -DBUILDDIR=$GITHUB_WORKSPACE/build --format=progress3
working-directory: Nominatim/test/bdd
- name: Install mypy and typechecking info
run: pip3 install -U mypy osmium uvicorn types-PyYAML types-jinja2 types-psycopg2 types-psutil types-requests types-ujson types-Pygments typing-extensions
if: matrix.flavour != 'oldstuff'
- name: Python static typechecking
run: python3 -m mypy --strict nominatim
../venv/bin/python -m pytest test/bdd --nominatim-purge
working-directory: Nominatim
if: matrix.flavour != 'oldstuff'
legacy-test:
needs: create-archive
runs-on: ubuntu-20.04
steps:
- uses: actions/download-artifact@v3
with:
name: full-source
- name: Unpack Nominatim
run: tar xf nominatim-src.tar.bz2
- name: Setup PHP
uses: shivammathur/setup-php@v2
with:
php-version: '7.4'
- uses: ./Nominatim/.github/actions/setup-postgresql
with:
postgresql-version: 13
postgis-version: 3
- name: Install Postgresql server dev
run: sudo apt-get install postgresql-server-dev-13
- uses: ./Nominatim/.github/actions/build-nominatim
with:
cmake-args: -DBUILD_MODULE=on
- name: Install test prerequsites
run: sudo apt-get install -y -qq python3-behave
- name: BDD tests (legacy tokenizer)
run: |
python3 -m behave -DREMOVE_TEMPLATE=1 -DBUILDDIR=$GITHUB_WORKSPACE/build -DTOKENIZER=legacy --format=progress3
working-directory: Nominatim/test/bdd
python-api-test:
needs: create-archive
runs-on: ubuntu-22.04
steps:
- uses: actions/download-artifact@v3
with:
name: full-source
- name: Unpack Nominatim
run: tar xf nominatim-src.tar.bz2
- uses: ./Nominatim/.github/actions/setup-postgresql
with:
postgresql-version: 15
postgis-version: 3
- uses: ./Nominatim/.github/actions/build-nominatim
with:
flavour: 'ubuntu-22'
- name: Install test prerequsites
run: sudo apt-get install -y -qq python3-behave
- name: Install Python webservers
run: pip3 install starlette asgi_lifespan httpx
- name: BDD tests (starlette)
run: |
python3 -m behave -DREMOVE_TEMPLATE=1 -DBUILDDIR=$GITHUB_WORKSPACE/build -DAPI_ENGINE=starlette --format=progress3
working-directory: Nominatim/test/bdd
install:
runs-on: ubuntu-latest
@@ -225,16 +146,16 @@ jobs:
strategy:
matrix:
name: [Ubuntu-20, Ubuntu-22]
name: [Ubuntu-22, Ubuntu-24]
include:
- name: Ubuntu-20
image: "ubuntu:20.04"
ubuntu: 20
install_mode: install-apache
- name: Ubuntu-22
image: "ubuntu:22.04"
ubuntu: 22
install_mode: install-apache
- name: Ubuntu-24
image: "ubuntu:24.04"
ubuntu: 24
install_mode: install-apache
container:
image: ${{ matrix.image }}
@@ -265,7 +186,7 @@ jobs:
OS: ${{ matrix.name }}
INSTALL_MODE: ${{ matrix.install_mode }}
- uses: actions/download-artifact@v3
- uses: actions/download-artifact@v4
with:
name: full-source
path: /home/nominatim
@@ -283,19 +204,24 @@ jobs:
- name: Prepare import environment
run: |
mv Nominatim/test/testdb/apidb-test-data.pbf test.pbf
mv Nominatim/settings/flex-base.lua flex-base.lua
mv Nominatim/settings/import-extratags.lua import-extratags.lua
mv Nominatim/settings/taginfo.lua taginfo.lua
rm -rf Nominatim
mkdir data-env-reverse
working-directory: /home/nominatim
- name: Add nominatim to path
run: |
sudo ln -s /home/nominatim/nominatim-venv/bin/nominatim /usr/local/bin/nominatim
- name: Need lua binary
run: |
sudo apt-get install -y lua5.4 lua-dkjson
- name: Print version
run: nominatim --version
working-directory: /home/nominatim/nominatim-project
- name: Print taginfo
run: lua taginfo.lua
run: lua ./nominatim-venv/lib/*/site-packages/nominatim_db/resources/lib-lua/taginfo.lua
working-directory: /home/nominatim
- name: Collect host OS information
@@ -318,13 +244,12 @@ jobs:
run: nominatim admin --warm
working-directory: /home/nominatim/nominatim-project
- name: Prepare update (Ubuntu)
run: apt-get install -y python3-pip
shell: bash
- name: Install osmium
run: |
/home/nominatim/nominatim-venv/bin/pip install osmium
- name: Run update
run: |
pip3 install --user osmium
nominatim replication --init
NOMINATIM_REPLICATION_MAX_DIFF=1 nominatim replication --once
working-directory: /home/nominatim/nominatim-project
@@ -346,3 +271,91 @@ jobs:
- name: Clean up database (reverse-only import)
run: nominatim refresh --postcodes --word-tokens
working-directory: /home/nominatim/nominatim-project
install-no-superuser:
runs-on: ubuntu-24.04
needs: create-archive
steps:
- uses: actions/download-artifact@v4
with:
name: full-source
- name: Unpack Nominatim
run: tar xf nominatim-src.tar.bz2
- uses: ./Nominatim/.github/actions/setup-postgresql
with:
postgresql-version: 16
- uses: ./Nominatim/.github/actions/build-nominatim
- name: Prepare import environment
run: |
mv Nominatim/test/testdb/apidb-test-data.pbf test.pbf
rm -rf Nominatim
- name: Prepare Database
run: |
./venv/bin/nominatim import --prepare-database
- name: Create import user
run: |
sudo -u postgres createuser osm-import
psql -d nominatim -c "ALTER USER \"osm-import\" WITH PASSWORD 'osm-import'"
psql -d nominatim -c 'GRANT CREATE ON SCHEMA public TO "osm-import"'
- name: Run import
run: |
NOMINATIM_DATABASE_DSN="pgsql:host=127.0.0.1;dbname=nominatim;user=osm-import;password=osm-import" ./venv/bin/nominatim import --continue import-from-file --osm-file test.pbf
- name: Check full import
run: ./venv/bin/nominatim admin --check-database
migrate:
runs-on: ubuntu-24.04
needs: create-archive
steps:
- uses: actions/download-artifact@v4
with:
name: full-source
- name: Unpack Nominatim
run: tar xf nominatim-src.tar.bz2
- uses: ./Nominatim/.github/actions/setup-postgresql
with:
postgresql-version: 18
- name: Install Python dependencies
run: |
sudo apt-get install --no-install-recommends virtualenv osm2pgsql
- name: Install Nominatim master version
run: |
virtualenv master
cd Nominatim
../master/bin/pip install packaging/nominatim-db
- name: Install Nominatim from pypi
run: |
virtualenv release
./release/bin/pip install nominatim-db
- name: Import Nominatim database using release
run: |
./release/bin/nominatim import --osm-file Nominatim/test/testdb/apidb-test-data.pbf
./release/bin/nominatim add-data --file Nominatim/test/testdb/additional_api_test.data.osm
- name: Migrate to master version
run: |
./master/bin/nominatim admin --migrate
./release/bin/nominatim add-data --file Nominatim/test/testdb/additional_api_test.data.osm
codespell:
runs-on: ubuntu-latest
steps:
- uses: codespell-project/actions-codespell@v2
with:
only_warn: 1

4
.gitignore vendored
View File

@@ -1,9 +1,13 @@
*.log
*.pyc
*.swp
docs/develop/*.png
site-html
build
dist
.coverage
.vagrant
data/country_osm_grid.sql.gz

4
.gitmodules vendored
View File

@@ -1,4 +0,0 @@
[submodule "osm2pgsql"]
path = osm2pgsql
url = https://github.com/openstreetmap/osm2pgsql.git
ignore = dirty

View File

@@ -1,18 +0,0 @@
[MASTER]
extension-pkg-whitelist=osmium,falcon
ignored-modules=icu,datrie
[MESSAGES CONTROL]
[TYPECHECK]
# closing added here because it sometimes triggers a false positive with
# 'with' statements.
ignored-classes=NominatimArgs,closing
# 'too-many-ancestors' is triggered already by deriving from UserDict
# 'not-context-manager' disabled because it causes false positives once
# typed Python is enabled. See also https://github.com/PyCQA/pylint/issues/5273
disable=too-few-public-methods,duplicate-code,too-many-ancestors,bad-option-value,no-self-use,not-context-manager,use-dict-literal,chained-comparison,attribute-defined-outside-init
good-names=i,j,x,y,m,t,fd,db,cc,x1,x2,y1,y2,pt,k,v,nr

View File

@@ -1,284 +0,0 @@
#-----------------------------------------------------------------------------
#
# CMake Config
#
# Nominatim
#
#-----------------------------------------------------------------------------
cmake_minimum_required(VERSION 3.0 FATAL_ERROR)
list(APPEND CMAKE_MODULE_PATH "${CMAKE_SOURCE_DIR}/cmake")
#-----------------------------------------------------------------------------
#
# Project version
#
#-----------------------------------------------------------------------------
project(nominatim)
set(NOMINATIM_VERSION_MAJOR 4)
set(NOMINATIM_VERSION_MINOR 3)
set(NOMINATIM_VERSION_PATCH 0)
set(NOMINATIM_VERSION "${NOMINATIM_VERSION_MAJOR}.${NOMINATIM_VERSION_MINOR}.${NOMINATIM_VERSION_PATCH}")
add_definitions(-DNOMINATIM_VERSION="${NOMINATIM_VERSION}")
# Setting GIT_HASH
find_package(Git)
if (GIT_FOUND)
execute_process(
COMMAND "${GIT_EXECUTABLE}" log -1 --format=%h
WORKING_DIRECTORY ${CMAKE_CURRENT_LIST_DIR}
OUTPUT_VARIABLE GIT_HASH
OUTPUT_STRIP_TRAILING_WHITESPACE
ERROR_QUIET
)
endif()
#-----------------------------------------------------------------------------
# Configuration
#-----------------------------------------------------------------------------
set(BUILD_IMPORTER on CACHE BOOL "Build everything for importing/updating the database")
set(BUILD_API on CACHE BOOL "Build everything for the API server")
set(BUILD_MODULE off CACHE BOOL "Build PostgreSQL module for legacy tokenizer")
set(BUILD_TESTS on CACHE BOOL "Build test suite")
set(BUILD_DOCS on CACHE BOOL "Build documentation")
set(BUILD_MANPAGE on CACHE BOOL "Build Manual Page")
set(BUILD_OSM2PGSQL on CACHE BOOL "Build osm2pgsql (expert only)")
set(INSTALL_MUNIN_PLUGINS on CACHE BOOL "Install Munin plugins for supervising Nominatim")
#-----------------------------------------------------------------------------
# osm2pgsql (imports/updates only)
#-----------------------------------------------------------------------------
if (BUILD_IMPORTER AND BUILD_OSM2PGSQL)
if (NOT EXISTS "${CMAKE_SOURCE_DIR}/osm2pgsql/CMakeLists.txt")
message(FATAL_ERROR "The osm2pgsql directory is empty.\
Did you forget to check out Nominatim recursively?\
\nTry updating submodules with: git submodule update --init")
endif()
set(BUILD_TESTS_SAVED "${BUILD_TESTS}")
set(BUILD_TESTS off)
add_subdirectory(osm2pgsql)
set(BUILD_TESTS ${BUILD_TESTS_SAVED})
endif()
#-----------------------------------------------------------------------------
# python (imports/updates only)
#-----------------------------------------------------------------------------
if (BUILD_IMPORTER)
find_package(PythonInterp 3.7 REQUIRED)
endif()
#-----------------------------------------------------------------------------
# PHP
#-----------------------------------------------------------------------------
# Setting PHP binary variable as to command line (prevailing) or auto detect
if (BUILD_API OR BUILD_IMPORTER)
if (NOT PHP_BIN)
find_program (PHP_BIN php)
endif()
# sanity check if PHP binary exists
if (NOT EXISTS ${PHP_BIN})
message(FATAL_ERROR "PHP binary not found. Install php or provide location with -DPHP_BIN=/path/php ")
else()
message (STATUS "Using PHP binary " ${PHP_BIN})
endif()
endif()
#-----------------------------------------------------------------------------
# import scripts and utilities (importer only)
#-----------------------------------------------------------------------------
if (BUILD_IMPORTER)
find_file(COUNTRY_GRID_FILE country_osm_grid.sql.gz
PATHS ${PROJECT_SOURCE_DIR}/data
NO_DEFAULT_PATH
DOC "Location of the country grid file."
)
if (NOT COUNTRY_GRID_FILE)
message(FATAL_ERROR "\nYou need to download the country_osm_grid first:\n"
" wget -O ${PROJECT_SOURCE_DIR}/data/country_osm_grid.sql.gz https://www.nominatim.org/data/country_grid.sql.gz")
endif()
configure_file(${PROJECT_SOURCE_DIR}/cmake/tool.tmpl
${PROJECT_BINARY_DIR}/nominatim)
endif()
#-----------------------------------------------------------------------------
# Tests
#-----------------------------------------------------------------------------
if (BUILD_TESTS)
include(CTest)
set(TEST_BDD db osm2pgsql api)
find_program(PYTHON_BEHAVE behave)
find_program(PYLINT NAMES pylint3 pylint)
find_program(PYTEST NAMES pytest py.test-3 py.test)
find_program(PHPCS phpcs)
find_program(PHPUNIT phpunit)
if (PYTHON_BEHAVE)
message(STATUS "Using Python behave binary ${PYTHON_BEHAVE}")
foreach (test ${TEST_BDD})
add_test(NAME bdd_${test}
COMMAND ${PYTHON_BEHAVE} ${test}
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}/test/bdd)
set_tests_properties(bdd_${test}
PROPERTIES ENVIRONMENT "NOMINATIM_DIR=${PROJECT_BINARY_DIR}")
endforeach()
else()
message(WARNING "behave not found. BDD tests disabled." )
endif()
if (PHPUNIT)
message(STATUS "Using phpunit binary ${PHPUNIT}")
add_test(NAME php
COMMAND ${PHPUNIT} ./
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}/test/php)
else()
message(WARNING "phpunit not found. PHP unit tests disabled." )
endif()
if (PHPCS)
message(STATUS "Using phpcs binary ${PHPCS}")
add_test(NAME phpcs
COMMAND ${PHPCS} --report-width=120 --colors lib-php
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})
else()
message(WARNING "phpcs not found. PHP linting tests disabled." )
endif()
if (PYLINT)
message(STATUS "Using pylint binary ${PYLINT}")
add_test(NAME pylint
COMMAND ${PYLINT} nominatim
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})
else()
message(WARNING "pylint not found. Python linting tests disabled.")
endif()
if (PYTEST)
message(STATUS "Using pytest binary ${PYTEST}")
add_test(NAME pytest
COMMAND ${PYTEST} test/python
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})
else()
message(WARNING "pytest not found. Python tests disabled." )
endif()
endif()
#-----------------------------------------------------------------------------
# Postgres module
#-----------------------------------------------------------------------------
if (BUILD_MODULE)
add_subdirectory(module)
endif()
#-----------------------------------------------------------------------------
# Documentation
#-----------------------------------------------------------------------------
if (BUILD_DOCS)
add_subdirectory(docs)
endif()
#-----------------------------------------------------------------------------
# Manual page
#-----------------------------------------------------------------------------
if (BUILD_MANPAGE)
add_subdirectory(man)
endif()
#-----------------------------------------------------------------------------
# Installation
#-----------------------------------------------------------------------------
include(GNUInstallDirs)
set(NOMINATIM_DATADIR ${CMAKE_INSTALL_FULL_DATADIR}/${PROJECT_NAME})
set(NOMINATIM_LIBDIR ${CMAKE_INSTALL_FULL_LIBDIR}/${PROJECT_NAME})
set(NOMINATIM_CONFIGDIR ${CMAKE_INSTALL_FULL_SYSCONFDIR}/${PROJECT_NAME})
set(NOMINATIM_MUNINDIR ${CMAKE_INSTALL_FULL_DATADIR}/munin/plugins)
if (BUILD_IMPORTER)
configure_file(${PROJECT_SOURCE_DIR}/cmake/tool-installed.tmpl installed.bin)
install(PROGRAMS ${PROJECT_BINARY_DIR}/installed.bin
DESTINATION ${CMAKE_INSTALL_BINDIR}
RENAME nominatim)
install(DIRECTORY nominatim
DESTINATION ${NOMINATIM_LIBDIR}/lib-python
FILES_MATCHING PATTERN "*.py"
PATTERN "paths.py" EXCLUDE
PATTERN __pycache__ EXCLUDE)
configure_file(${PROJECT_SOURCE_DIR}/cmake/paths-py.tmpl paths-py.installed)
install(FILES ${PROJECT_BINARY_DIR}/paths-py.installed
DESTINATION ${NOMINATIM_LIBDIR}/lib-python/nominatim
RENAME paths.py)
install(DIRECTORY lib-sql DESTINATION ${NOMINATIM_LIBDIR})
install(FILES ${COUNTRY_GRID_FILE}
data/words.sql
DESTINATION ${NOMINATIM_DATADIR})
endif()
if (BUILD_OSM2PGSQL)
if (${CMAKE_VERSION} VERSION_LESS 3.13)
# Installation of subdirectory targets was only introduced in 3.13.
# So just copy the osm2pgsql file for older versions.
install(PROGRAMS ${PROJECT_BINARY_DIR}/osm2pgsql/osm2pgsql
DESTINATION ${NOMINATIM_LIBDIR})
else()
install(TARGETS osm2pgsql RUNTIME DESTINATION ${NOMINATIM_LIBDIR})
endif()
endif()
if (BUILD_MODULE)
install(PROGRAMS ${PROJECT_BINARY_DIR}/module/nominatim.so
DESTINATION ${NOMINATIM_LIBDIR}/module)
endif()
if (BUILD_API)
install(DIRECTORY lib-php DESTINATION ${NOMINATIM_LIBDIR})
endif()
install(FILES settings/env.defaults
settings/address-levels.json
settings/phrase-settings.json
settings/import-admin.lua
settings/import-street.lua
settings/import-address.lua
settings/import-full.lua
settings/import-extratags.lua
settings/flex-base.lua
settings/icu_tokenizer.yaml
settings/country_settings.yaml
DESTINATION ${NOMINATIM_CONFIGDIR})
install(DIRECTORY settings/icu-rules
DESTINATION ${NOMINATIM_CONFIGDIR})
install(DIRECTORY settings/country-names
DESTINATION ${NOMINATIM_CONFIGDIR})
if (INSTALL_MUNIN_PLUGINS)
install(FILES munin/nominatim_importlag
munin/nominatim_query_speed
munin/nominatim_requests
DESTINATION ${NOMINATIM_MUNINDIR})
endif()

View File

@@ -30,6 +30,19 @@ feature pull requests. If you plan to make larger changes, please open
an issue first or comment on the appropriate issue already existing so
that duplicate work can be avoided.
### Using AI-assisted code generators
PRs that include AI-generated content, may that be in code, in the PR
description or in documentation need to
1. clearly mark the AI-generated sections as such, for example, by
mentioning all use of AI in the PR description, and
2. include proof that you have run the generated code on an actual
installation of Nominatim. Adding and excuting tests will not be
sufficient. You need to show that the code actually solves the problem
the PR claims to solve.
## Coding style
Nominatim historically hasn't followed a particular coding style but we
@@ -46,14 +59,11 @@ are in process of consolidating the style. The following rules apply:
* no spaces after opening and before closing bracket
* leave out space between a function name and bracket
but add one between control statement(if, while, etc.) and bracket
* for PHP variables use CamelCase with a prefixing letter indicating the type
(i - integer, f - float, a - array, s - string, o - object)
The coding style is enforced with PHPCS and pylint. It can be tested with:
The coding style is enforced with flake8. It can be tested with:
```
phpcs --report-width=120 --colors .
pylint3 --extension-pkg-whitelist=osmium nominatim
make lint
```
## Testing
@@ -61,32 +71,34 @@ pylint3 --extension-pkg-whitelist=osmium nominatim
Before submitting a pull request make sure that the tests pass:
```
cd build
make test
make tests
```
## Releases
Nominatim follows semantic versioning. Major releases are done for large changes
that require (or at least strongly recommend) a reimport of the databases.
Minor releases can usually be applied to exisiting databases. Patch releases
Minor releases can usually be applied to existing databases. Patch releases
contain bug fixes only and are released from a separate branch where the
relevant changes are cherry-picked from the master branch.
Checklist for releases:
* [ ] increase version in `nominatim/version.py` and CMakeLists.txt
* [ ] increase versions in
* `src/nominatim_api/version.py`
* `src/nominatim_db/version.py`
* [ ] update `ChangeLog` (copy information from patch releases from release branch)
* [ ] complete `docs/admin/Migration.md`
* [ ] update EOL dates in `SECURITY.md`
* [ ] commit and make sure CI tests pass
* [ ] update OSMF production repo and release new version -post1 there
* [ ] test migration
* download, build and import previous version
* migrate using master version
* run updates using master version
* [ ] prepare tarball:
* `git clone --recursive https://github.com/osm-search/Nominatim` (switch to right branch!)
* `rm -r .git* osm2pgsql/.git*`
* `git clone https://github.com/osm-search/Nominatim` (switch to right branch!)
* `rm -r .git*`
* copy country data into `data/`
* add version to base directory and package
* [ ] upload tarball to https://nominatim.org
@@ -100,3 +112,6 @@ Checklist for releases:
* compile and import Nominatim
* run `nominatim --version` to confirm correct version
* [ ] tag new release and add a release on github.com
* [ ] build pip packages and upload to pypi
* `make build`
* `twine upload dist/*`

457
COPYING
View File

@@ -1,339 +1,232 @@
GNU GENERAL PUBLIC LICENSE
Version 2, June 1991
GNU GENERAL PUBLIC LICENSE
Version 3, 29 June 2007
Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Copyright © 2007 Free Software Foundation, Inc. <https://fsf.org/>
Preamble
Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed.
The licenses for most software are designed to take away your
freedom to share and change it. By contrast, the GNU General Public
License is intended to guarantee your freedom to share and change free
software--to make sure the software is free for all its users. This
General Public License applies to most of the Free Software
Foundation's software and to any other program whose authors commit to
using it. (Some other Free Software Foundation software is covered by
the GNU Lesser General Public License instead.) You can apply it to
your programs, too.
Preamble
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
this service if you wish), that you receive source code or can get it
if you want it, that you can change the software or use pieces of it
in new free programs; and that you know you can do these things.
The GNU General Public License is a free, copyleft license for software and other kinds of works.
To protect your rights, we need to make restrictions that forbid
anyone to deny you these rights or to ask you to surrender the rights.
These restrictions translate to certain responsibilities for you if you
distribute copies of the software, or if you modify it.
The licenses for most software and other practical works are designed to take away your freedom to share and change the works. By contrast, the GNU General Public License is intended to guarantee your freedom to share and change all versions of a program--to make sure it remains free software for all its users. We, the Free Software Foundation, use the GNU General Public License for most of our software; it applies also to any other work released this way by its authors. You can apply it to your programs, too.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must give the recipients all the rights that
you have. You must make sure that they, too, receive or can get the
source code. And you must show them these terms so they know their
rights.
When we speak of free software, we are referring to freedom, not price. Our General Public Licenses are designed to make sure that you have the freedom to distribute copies of free software (and charge for them if you wish), that you receive source code or can get it if you want it, that you can change the software or use pieces of it in new free programs, and that you know you can do these things.
We protect your rights with two steps: (1) copyright the software, and
(2) offer you this license which gives you legal permission to copy,
distribute and/or modify the software.
To protect your rights, we need to prevent others from denying you these rights or asking you to surrender the rights. Therefore, you have certain responsibilities if you distribute copies of the software, or if you modify it: responsibilities to respect the freedom of others.
Also, for each author's protection and ours, we want to make certain
that everyone understands that there is no warranty for this free
software. If the software is modified by someone else and passed on, we
want its recipients to know that what they have is not the original, so
that any problems introduced by others will not reflect on the original
authors' reputations.
For example, if you distribute copies of such a program, whether gratis or for a fee, you must pass on to the recipients the same freedoms that you received. You must make sure that they, too, receive or can get the source code. And you must show them these terms so they know their rights.
Finally, any free program is threatened constantly by software
patents. We wish to avoid the danger that redistributors of a free
program will individually obtain patent licenses, in effect making the
program proprietary. To prevent this, we have made it clear that any
patent must be licensed for everyone's free use or not licensed at all.
Developers that use the GNU GPL protect your rights with two steps: (1) assert copyright on the software, and (2) offer you this License giving you legal permission to copy, distribute and/or modify it.
The precise terms and conditions for copying, distribution and
modification follow.
For the developers' and authors' protection, the GPL clearly explains that there is no warranty for this free software. For both users' and authors' sake, the GPL requires that modified versions be marked as changed, so that their problems will not be attributed erroneously to authors of previous versions.
GNU GENERAL PUBLIC LICENSE
TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
Some devices are designed to deny users access to install or run modified versions of the software inside them, although the manufacturer can do so. This is fundamentally incompatible with the aim of protecting users' freedom to change the software. The systematic pattern of such abuse occurs in the area of products for individuals to use, which is precisely where it is most unacceptable. Therefore, we have designed this version of the GPL to prohibit the practice for those products. If such problems arise substantially in other domains, we stand ready to extend this provision to those domains in future versions of the GPL, as needed to protect the freedom of users.
0. This License applies to any program or other work which contains
a notice placed by the copyright holder saying it may be distributed
under the terms of this General Public License. The "Program", below,
refers to any such program or work, and a "work based on the Program"
means either the Program or any derivative work under copyright law:
that is to say, a work containing the Program or a portion of it,
either verbatim or with modifications and/or translated into another
language. (Hereinafter, translation is included without limitation in
the term "modification".) Each licensee is addressed as "you".
Finally, every program is threatened constantly by software patents. States should not allow patents to restrict development and use of software on general-purpose computers, but in those that do, we wish to avoid the special danger that patents applied to a free program could make it effectively proprietary. To prevent this, the GPL assures that patents cannot be used to render the program non-free.
Activities other than copying, distribution and modification are not
covered by this License; they are outside its scope. The act of
running the Program is not restricted, and the output from the Program
is covered only if its contents constitute a work based on the
Program (independent of having been made by running the Program).
Whether that is true depends on what the Program does.
The precise terms and conditions for copying, distribution and modification follow.
1. You may copy and distribute verbatim copies of the Program's
source code as you receive it, in any medium, provided that you
conspicuously and appropriately publish on each copy an appropriate
copyright notice and disclaimer of warranty; keep intact all the
notices that refer to this License and to the absence of any warranty;
and give any other recipients of the Program a copy of this License
along with the Program.
TERMS AND CONDITIONS
You may charge a fee for the physical act of transferring a copy, and
you may at your option offer warranty protection in exchange for a fee.
0. Definitions.
2. You may modify your copy or copies of the Program or any portion
of it, thus forming a work based on the Program, and copy and
distribute such modifications or work under the terms of Section 1
above, provided that you also meet all of these conditions:
“This License” refers to version 3 of the GNU General Public License.
a) You must cause the modified files to carry prominent notices
stating that you changed the files and the date of any change.
“Copyright” also means copyright-like laws that apply to other kinds of works, such as semiconductor masks.
b) You must cause any work that you distribute or publish, that in
whole or in part contains or is derived from the Program or any
part thereof, to be licensed as a whole at no charge to all third
parties under the terms of this License.
“The Program” refers to any copyrightable work licensed under this License. Each licensee is addressed as “you”. “Licensees” and “recipients” may be individuals or organizations.
c) If the modified program normally reads commands interactively
when run, you must cause it, when started running for such
interactive use in the most ordinary way, to print or display an
announcement including an appropriate copyright notice and a
notice that there is no warranty (or else, saying that you provide
a warranty) and that users may redistribute the program under
these conditions, and telling the user how to view a copy of this
License. (Exception: if the Program itself is interactive but
does not normally print such an announcement, your work based on
the Program is not required to print an announcement.)
To “modify” a work means to copy from or adapt all or part of the work in a fashion requiring copyright permission, other than the making of an exact copy. The resulting work is called a “modified version” of the earlier work or a work “based on” the earlier work.
These requirements apply to the modified work as a whole. If
identifiable sections of that work are not derived from the Program,
and can be reasonably considered independent and separate works in
themselves, then this License, and its terms, do not apply to those
sections when you distribute them as separate works. But when you
distribute the same sections as part of a whole which is a work based
on the Program, the distribution of the whole must be on the terms of
this License, whose permissions for other licensees extend to the
entire whole, and thus to each and every part regardless of who wrote it.
A “covered work” means either the unmodified Program or a work based on the Program.
Thus, it is not the intent of this section to claim rights or contest
your rights to work written entirely by you; rather, the intent is to
exercise the right to control the distribution of derivative or
collective works based on the Program.
To “propagate” a work means to do anything with it that, without permission, would make you directly or secondarily liable for infringement under applicable copyright law, except executing it on a computer or modifying a private copy. Propagation includes copying, distribution (with or without modification), making available to the public, and in some countries other activities as well.
In addition, mere aggregation of another work not based on the Program
with the Program (or with a work based on the Program) on a volume of
a storage or distribution medium does not bring the other work under
the scope of this License.
To “convey” a work means any kind of propagation that enables other parties to make or receive copies. Mere interaction with a user through a computer network, with no transfer of a copy, is not conveying.
3. You may copy and distribute the Program (or a work based on it,
under Section 2) in object code or executable form under the terms of
Sections 1 and 2 above provided that you also do one of the following:
An interactive user interface displays “Appropriate Legal Notices” to the extent that it includes a convenient and prominently visible feature that (1) displays an appropriate copyright notice, and (2) tells the user that there is no warranty for the work (except to the extent that warranties are provided), that licensees may convey the work under this License, and how to view a copy of this License. If the interface presents a list of user commands or options, such as a menu, a prominent item in the list meets this criterion.
a) Accompany it with the complete corresponding machine-readable
source code, which must be distributed under the terms of Sections
1 and 2 above on a medium customarily used for software interchange; or,
1. Source Code.
The “source code” for a work means the preferred form of the work for making modifications to it. “Object code” means any non-source form of a work.
b) Accompany it with a written offer, valid for at least three
years, to give any third party, for a charge no more than your
cost of physically performing source distribution, a complete
machine-readable copy of the corresponding source code, to be
distributed under the terms of Sections 1 and 2 above on a medium
customarily used for software interchange; or,
A “Standard Interface” means an interface that either is an official standard defined by a recognized standards body, or, in the case of interfaces specified for a particular programming language, one that is widely used among developers working in that language.
c) Accompany it with the information you received as to the offer
to distribute corresponding source code. (This alternative is
allowed only for noncommercial distribution and only if you
received the program in object code or executable form with such
an offer, in accord with Subsection b above.)
The “System Libraries” of an executable work include anything, other than the work as a whole, that (a) is included in the normal form of packaging a Major Component, but which is not part of that Major Component, and (b) serves only to enable use of the work with that Major Component, or to implement a Standard Interface for which an implementation is available to the public in source code form. A “Major Component”, in this context, means a major essential component (kernel, window system, and so on) of the specific operating system (if any) on which the executable work runs, or a compiler used to produce the work, or an object code interpreter used to run it.
The source code for a work means the preferred form of the work for
making modifications to it. For an executable work, complete source
code means all the source code for all modules it contains, plus any
associated interface definition files, plus the scripts used to
control compilation and installation of the executable. However, as a
special exception, the source code distributed need not include
anything that is normally distributed (in either source or binary
form) with the major components (compiler, kernel, and so on) of the
operating system on which the executable runs, unless that component
itself accompanies the executable.
The “Corresponding Source” for a work in object code form means all the source code needed to generate, install, and (for an executable work) run the object code and to modify the work, including scripts to control those activities. However, it does not include the work's System Libraries, or general-purpose tools or generally available free programs which are used unmodified in performing those activities but which are not part of the work. For example, Corresponding Source includes interface definition files associated with source files for the work, and the source code for shared libraries and dynamically linked subprograms that the work is specifically designed to require, such as by intimate data communication or control flow between those subprograms and other parts of the work.
If distribution of executable or object code is made by offering
access to copy from a designated place, then offering equivalent
access to copy the source code from the same place counts as
distribution of the source code, even though third parties are not
compelled to copy the source along with the object code.
The Corresponding Source need not include anything that users can regenerate automatically from other parts of the Corresponding Source.
4. You may not copy, modify, sublicense, or distribute the Program
except as expressly provided under this License. Any attempt
otherwise to copy, modify, sublicense or distribute the Program is
void, and will automatically terminate your rights under this License.
However, parties who have received copies, or rights, from you under
this License will not have their licenses terminated so long as such
parties remain in full compliance.
The Corresponding Source for a work in source code form is that same work.
5. You are not required to accept this License, since you have not
signed it. However, nothing else grants you permission to modify or
distribute the Program or its derivative works. These actions are
prohibited by law if you do not accept this License. Therefore, by
modifying or distributing the Program (or any work based on the
Program), you indicate your acceptance of this License to do so, and
all its terms and conditions for copying, distributing or modifying
the Program or works based on it.
2. Basic Permissions.
All rights granted under this License are granted for the term of copyright on the Program, and are irrevocable provided the stated conditions are met. This License explicitly affirms your unlimited permission to run the unmodified Program. The output from running a covered work is covered by this License only if the output, given its content, constitutes a covered work. This License acknowledges your rights of fair use or other equivalent, as provided by copyright law.
6. Each time you redistribute the Program (or any work based on the
Program), the recipient automatically receives a license from the
original licensor to copy, distribute or modify the Program subject to
these terms and conditions. You may not impose any further
restrictions on the recipients' exercise of the rights granted herein.
You are not responsible for enforcing compliance by third parties to
this License.
You may make, run and propagate covered works that you do not convey, without conditions so long as your license otherwise remains in force. You may convey covered works to others for the sole purpose of having them make modifications exclusively for you, or provide you with facilities for running those works, provided that you comply with the terms of this License in conveying all material for which you do not control copyright. Those thus making or running the covered works for you must do so exclusively on your behalf, under your direction and control, on terms that prohibit them from making any copies of your copyrighted material outside their relationship with you.
7. If, as a consequence of a court judgment or allegation of patent
infringement or for any other reason (not limited to patent issues),
conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot
distribute so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you
may not distribute the Program at all. For example, if a patent
license would not permit royalty-free redistribution of the Program by
all those who receive copies directly or indirectly through you, then
the only way you could satisfy both it and this License would be to
refrain entirely from distribution of the Program.
Conveying under any other circumstances is permitted solely under the conditions stated below. Sublicensing is not allowed; section 10 makes it unnecessary.
If any portion of this section is held invalid or unenforceable under
any particular circumstance, the balance of the section is intended to
apply and the section as a whole is intended to apply in other
circumstances.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological measure under any applicable law fulfilling obligations under article 11 of the WIPO copyright treaty adopted on 20 December 1996, or similar laws prohibiting or restricting circumvention of such measures.
It is not the purpose of this section to induce you to infringe any
patents or other property right claims or to contest validity of any
such claims; this section has the sole purpose of protecting the
integrity of the free software distribution system, which is
implemented by public license practices. Many people have made
generous contributions to the wide range of software distributed
through that system in reliance on consistent application of that
system; it is up to the author/donor to decide if he or she is willing
to distribute software through any other system and a licensee cannot
impose that choice.
When you convey a covered work, you waive any legal power to forbid circumvention of technological measures to the extent such circumvention is effected by exercising rights under this License with respect to the covered work, and you disclaim any intention to limit operation or modification of the work as a means of enforcing, against the work's users, your or third parties' legal rights to forbid circumvention of technological measures.
This section is intended to make thoroughly clear what is believed to
be a consequence of the rest of this License.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you receive it, in any medium, provided that you conspicuously and appropriately publish on each copy an appropriate copyright notice; keep intact all notices stating that this License and any non-permissive terms added in accord with section 7 apply to the code; keep intact all notices of the absence of any warranty; and give all recipients a copy of this License along with the Program.
8. If the distribution and/or use of the Program is restricted in
certain countries either by patents or by copyrighted interfaces, the
original copyright holder who places the Program under this License
may add an explicit geographical distribution limitation excluding
those countries, so that distribution is permitted only in or among
countries not thus excluded. In such case, this License incorporates
the limitation as if written in the body of this License.
You may charge any price or no price for each copy that you convey, and you may offer support or warranty protection for a fee.
9. The Free Software Foundation may publish revised and/or new versions
of the General Public License from time to time. Such new versions will
be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to produce it from the Program, in the form of source code under the terms of section 4, provided that you also meet all of these conditions:
Each version is given a distinguishing version number. If the Program
specifies a version number of this License which applies to it and "any
later version", you have the option of following the terms and conditions
either of that version or of any later version published by the Free
Software Foundation. If the Program does not specify a version number of
this License, you may choose any version ever published by the Free Software
Foundation.
a) The work must carry prominent notices stating that you modified it, and giving a relevant date.
10. If you wish to incorporate parts of the Program into other free
programs whose distribution conditions are different, write to the author
to ask for permission. For software which is copyrighted by the Free
Software Foundation, write to the Free Software Foundation; we sometimes
make exceptions for this. Our decision will be guided by the two goals
of preserving the free status of all derivatives of our free software and
of promoting the sharing and reuse of software generally.
b) The work must carry prominent notices stating that it is released under this License and any conditions added under section 7. This requirement modifies the requirement in section 4 to “keep intact all notices”.
NO WARRANTY
c) You must license the entire work, as a whole, under this License to anyone who comes into possession of a copy. This License will therefore apply, along with any applicable section 7 additional terms, to the whole of the work, and all its parts, regardless of how they are packaged. This License gives no permission to license the work in any other way, but it does not invalidate such permission if you have separately received it.
11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS
TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE
PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
REPAIR OR CORRECTION.
d) If the work has interactive user interfaces, each must display Appropriate Legal Notices; however, if the Program has interactive interfaces that do not display Appropriate Legal Notices, your work need not make them do so.
12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
POSSIBILITY OF SUCH DAMAGES.
A compilation of a covered work with other separate and independent works, which are not by their nature extensions of the covered work, and which are not combined with it such as to form a larger program, in or on a volume of a storage or distribution medium, is called an “aggregate” if the compilation and its resulting copyright are not used to limit the access or legal rights of the compilation's users beyond what the individual works permit. Inclusion of a covered work in an aggregate does not cause this License to apply to the other parts of the aggregate.
END OF TERMS AND CONDITIONS
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms of sections 4 and 5, provided that you also convey the machine-readable Corresponding Source under the terms of this License, in one of these ways:
How to Apply These Terms to Your New Programs
a) Convey the object code in, or embodied in, a physical product (including a physical distribution medium), accompanied by the Corresponding Source fixed on a durable physical medium customarily used for software interchange.
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
b) Convey the object code in, or embodied in, a physical product (including a physical distribution medium), accompanied by a written offer, valid for at least three years and valid for as long as you offer spare parts or customer support for that product model, to give anyone who possesses the object code either (1) a copy of the Corresponding Source for all the software in the product that is covered by this License, on a durable physical medium customarily used for software interchange, for a price no more than your reasonable cost of physically performing this conveying of source, or (2) access to copy the Corresponding Source from a network server at no charge.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
convey the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
c) Convey individual copies of the object code with a copy of the written offer to provide the Corresponding Source. This alternative is allowed only occasionally and noncommercially, and only if you received the object code with such an offer, in accord with subsection 6b.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
d) Convey the object code by offering access from a designated place (gratis or for a charge), and offer equivalent access to the Corresponding Source in the same way through the same place at no further charge. You need not require recipients to copy the Corresponding Source along with the object code. If the place to copy the object code is a network server, the Corresponding Source may be on a different server (operated by you or a third party) that supports equivalent copying facilities, provided you maintain clear directions next to the object code saying where to find the Corresponding Source. Regardless of what server hosts the Corresponding Source, you remain obligated to ensure that it is available for as long as needed to satisfy these requirements.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
e) Convey the object code using peer-to-peer transmission, provided you inform other peers where the object code and Corresponding Source of the work are being offered to the general public at no charge under subsection 6d.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
A separable portion of the object code, whose source code is excluded from the Corresponding Source as a System Library, need not be included in conveying the object code work.
You should have received a copy of the GNU General Public License along
with this program; if not, write to the Free Software Foundation, Inc.,
51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
A “User Product” is either (1) a “consumer product”, which means any tangible personal property which is normally used for personal, family, or household purposes, or (2) anything designed or sold for incorporation into a dwelling. In determining whether a product is a consumer product, doubtful cases shall be resolved in favor of coverage. For a particular product received by a particular user, “normally used” refers to a typical or common use of that class of product, regardless of the status of the particular user or of the way in which the particular user actually uses, or expects or is expected to use, the product. A product is a consumer product regardless of whether the product has substantial commercial, industrial or non-consumer uses, unless such uses represent the only significant mode of use of the product.
“Installation Information” for a User Product means any methods, procedures, authorization keys, or other information required to install and execute modified versions of a covered work in that User Product from a modified version of its Corresponding Source. The information must suffice to ensure that the continued functioning of the modified object code is in no case prevented or interfered with solely because modification has been made.
If you convey an object code work under this section in, or with, or specifically for use in, a User Product, and the conveying occurs as part of a transaction in which the right of possession and use of the User Product is transferred to the recipient in perpetuity or for a fixed term (regardless of how the transaction is characterized), the Corresponding Source conveyed under this section must be accompanied by the Installation Information. But this requirement does not apply if neither you nor any third party retains the ability to install modified object code on the User Product (for example, the work has been installed in ROM).
The requirement to provide Installation Information does not include a requirement to continue to provide support service, warranty, or updates for a work that has been modified or installed by the recipient, or for the User Product in which it has been modified or installed. Access to a network may be denied when the modification itself materially and adversely affects the operation of the network or violates the rules and protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided, in accord with this section must be in a format that is publicly documented (and with an implementation available to the public in source code form), and must require no special password or key for unpacking, reading or copying.
7. Additional Terms.
“Additional permissions” are terms that supplement the terms of this License by making exceptions from one or more of its conditions. Additional permissions that are applicable to the entire Program shall be treated as though they were included in this License, to the extent that they are valid under applicable law. If additional permissions apply only to part of the Program, that part may be used separately under those permissions, but the entire Program remains governed by this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option remove any additional permissions from that copy, or from any part of it. (Additional permissions may be written to require their own removal in certain cases when you modify the work.) You may place additional permissions on material, added by you to a covered work, for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you add to a covered work, you may (if authorized by the copyright holders of that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or author attributions in that material or in the Appropriate Legal Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or requiring that modified versions of such material be marked in reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or authors of the material; or
e) Declining to grant rights under trademark law for use of some trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that material by anyone who conveys the material (or modified versions of it) with contractual assumptions of liability to the recipient, for any liability that these contractual assumptions directly impose on those licensors and authors.
All other non-permissive additional terms are considered “further restrictions” within the meaning of section 10. If the Program as you received it, or any part of it, contains a notice stating that it is governed by this License along with a term that is a further restriction, you may remove that term. If a license document contains a further restriction but permits relicensing or conveying under this License, you may add to a covered work material governed by the terms of that license document, provided that the further restriction does not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you must place, in the relevant source files, a statement of the additional terms that apply to those files, or a notice indicating where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the form of a separately written license, or stated as exceptions; the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly provided under this License. Any attempt otherwise to propagate or modify it is void, and will automatically terminate your rights under this License (including any patent licenses granted under the third paragraph of section 11).
However, if you cease all violation of this License, then your license from a particular copyright holder is reinstated (a) provisionally, unless and until the copyright holder explicitly and finally terminates your license, and (b) permanently, if the copyright holder fails to notify you of the violation by some reasonable means prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is reinstated permanently if the copyright holder notifies you of the violation by some reasonable means, this is the first time you have received notice of violation of this License (for any work) from that copyright holder, and you cure the violation prior to 30 days after your receipt of the notice.
Termination of your rights under this section does not terminate the licenses of parties who have received copies or rights from you under this License. If your rights have been terminated and not permanently reinstated, you do not qualify to receive new licenses for the same material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or run a copy of the Program. Ancillary propagation of a covered work occurring solely as a consequence of using peer-to-peer transmission to receive a copy likewise does not require acceptance. However, nothing other than this License grants you permission to propagate or modify any covered work. These actions infringe copyright if you do not accept this License. Therefore, by modifying or propagating a covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically receives a license from the original licensors, to run, modify and propagate that work, subject to this License. You are not responsible for enforcing compliance by third parties with this License.
An “entity transaction” is a transaction transferring control of an organization, or substantially all assets of one, or subdividing an organization, or merging organizations. If propagation of a covered work results from an entity transaction, each party to that transaction who receives a copy of the work also receives whatever licenses to the work the party's predecessor in interest had or could give under the previous paragraph, plus a right to possession of the Corresponding Source of the work from the predecessor in interest, if the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the rights granted or affirmed under this License. For example, you may not impose a license fee, royalty, or other charge for exercise of rights granted under this License, and you may not initiate litigation (including a cross-claim or counterclaim in a lawsuit) alleging that any patent claim is infringed by making, using, selling, offering for sale, or importing the Program or any portion of it.
11. Patents.
A “contributor” is a copyright holder who authorizes use under this License of the Program or a work on which the Program is based. The work thus licensed is called the contributor's “contributor version”.
A contributor's “essential patent claims” are all patent claims owned or controlled by the contributor, whether already acquired or hereafter acquired, that would be infringed by some manner, permitted by this License, of making, using, or selling its contributor version, but do not include claims that would be infringed only as a consequence of further modification of the contributor version. For purposes of this definition, “control” includes the right to grant patent sublicenses in a manner consistent with the requirements of this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free patent license under the contributor's essential patent claims, to make, use, sell, offer for sale, import and otherwise run, modify and propagate the contents of its contributor version.
In the following three paragraphs, a “patent license” is any express agreement or commitment, however denominated, not to enforce a patent (such as an express permission to practice a patent or covenant not to sue for patent infringement). To “grant” such a patent license to a party means to make such an agreement or commitment not to enforce a patent against the party.
If you convey a covered work, knowingly relying on a patent license, and the Corresponding Source of the work is not available for anyone to copy, free of charge and under the terms of this License, through a publicly available network server or other readily accessible means, then you must either (1) cause the Corresponding Source to be so available, or (2) arrange to deprive yourself of the benefit of the patent license for this particular work, or (3) arrange, in a manner consistent with the requirements of this License, to extend the patent license to downstream recipients. “Knowingly relying” means you have actual knowledge that, but for the patent license, your conveying the covered work in a country, or your recipient's use of the covered work in a country, would infringe one or more identifiable patents in that country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or arrangement, you convey, or propagate by procuring conveyance of, a covered work, and grant a patent license to some of the parties receiving the covered work authorizing them to use, propagate, modify or convey a specific copy of the covered work, then the patent license you grant is automatically extended to all recipients of the covered work and works based on it.
A patent license is “discriminatory” if it does not include within the scope of its coverage, prohibits the exercise of, or is conditioned on the non-exercise of one or more of the rights that are specifically granted under this License. You may not convey a covered work if you are a party to an arrangement with a third party that is in the business of distributing software, under which you make payment to the third party based on the extent of your activity of conveying the work, and under which the third party grants, to any of the parties who would receive the covered work from you, a discriminatory patent license (a) in connection with copies of the covered work conveyed by you (or copies made from those copies), or (b) primarily for and in connection with specific products or compilations that contain the covered work, unless you entered into that arrangement, or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting any implied license or other defenses to infringement that may otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or otherwise) that contradict the conditions of this License, they do not excuse you from the conditions of this License. If you cannot convey a covered work so as to satisfy simultaneously your obligations under this License and any other pertinent obligations, then as a consequence you may not convey it at all. For example, if you agree to terms that obligate you to collect a royalty for further conveying from those to whom you convey the Program, the only way you could satisfy both those terms and this License would be to refrain entirely from conveying the Program.
13. Use with the GNU Affero General Public License.
Notwithstanding any other provision of this License, you have permission to link or combine any covered work with a work licensed under version 3 of the GNU Affero General Public License into a single combined work, and to convey the resulting work. The terms of this License will continue to apply to the part which is the covered work, but the special requirements of the GNU Affero General Public License, section 13, concerning interaction through a network will apply to the combination as such.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of the GNU General Public License from time to time. Such new versions will be similar in spirit to the present version, but may differ in detail to address new problems or concerns.
Each version is given a distinguishing version number. If the Program specifies that a certain numbered version of the GNU General Public License “or any later version” applies to it, you have the option of following the terms and conditions either of that numbered version or of any later version published by the Free Software Foundation. If the Program does not specify a version number of the GNU General Public License, you may choose any version ever published by the Free Software Foundation.
If the Program specifies that a proxy can decide which future versions of the GNU General Public License can be used, that proxy's public statement of acceptance of a version permanently authorizes you to choose that version for the Program.
Later license versions may give you additional or different permissions. However, no additional obligations are imposed on any author or copyright holder as a result of your choosing to follow a later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM “AS IS” WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided above cannot be given local legal effect according to their terms, reviewing courts shall apply local law that most closely approximates an absolute waiver of all civil liability in connection with the Program, unless a warranty or assumption of liability accompanies a copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest possible use to the public, the best way to achieve this is to make it free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest to attach them to the start of each source file to most effectively state the exclusion of warranty; and each file should have at least the “copyright” line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.
You should have received a copy of the GNU General Public License along with this program. If not, see <https://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If the program is interactive, make it output a short notice like this
when it starts in an interactive mode:
If the program does terminal interaction, make it output a short notice like this when it starts in an interactive mode:
Gnomovision version 69, Copyright (C) year name of author
Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
<program> Copyright (C) <year> <name of author>
This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it under certain conditions; type `show c' for details.
The hypothetical commands `show w' and `show c' should show the appropriate
parts of the General Public License. Of course, the commands you use may
be called something other than `show w' and `show c'; they could even be
mouse-clicks or menu items--whatever suits your program.
The hypothetical commands `show w' and `show c' should show the appropriate parts of the General Public License. Of course, your program's commands might be different; for a GUI interface, you would use an “about box”.
You should also get your employer (if you work as a programmer) or your
school, if any, to sign a "copyright disclaimer" for the program, if
necessary. Here is a sample; alter the names:
You should also get your employer (if you work as a programmer) or school, if any, to sign a “copyright disclaimer” for the program, if necessary. For more information on this, and how to apply and follow the GNU GPL, see <https://www.gnu.org/licenses/>.
Yoyodyne, Inc., hereby disclaims all copyright interest in the program
`Gnomovision' (which makes passes at compilers) written by James Hacker.
<signature of Ty Coon>, 1 April 1989
Ty Coon, President of Vice
This General Public License does not permit incorporating your program into
proprietary programs. If your program is a subroutine library, you may
consider it more useful to permit linking proprietary applications with the
library. If this is what you want to do, use the GNU Lesser General
Public License instead of this License.
The GNU General Public License does not permit incorporating your program into proprietary programs. If your program is a subroutine library, you may consider it more useful to permit linking proprietary applications with the library. If this is what you want to do, use the GNU Lesser General Public License instead of this License. But first, please read <https://www.gnu.org/philosophy/why-not-lgpl.html>.

167
ChangeLog
View File

@@ -1,3 +1,158 @@
5.2.0
* increase minimum required Python to 3.9
* index and output entrances of buildings and areas (thanks @emlove)
* name tags used for creating display names are now configurable
(thanks @astridx)
* new pattern-replacement query preprocessor (thanks @TuringVerified)
* special phrases can now be filtered by presence of tags (thanks @anqixxx)
* lua import style now always includes tags required by Nominatim
* improved query time reporting and logging
* improve word matching for languages with no word boundaries
* POIs with addresses inherited from surrounding building are no
longer returned in the address layer
* avoid creating a directory for the tokenizer when not needed
* replace behave with pytest-bdd for BDD testing
* refactoring and performance improvements to query parsing
* various smaller updates to styles
* remove English as default language for South Korea
* remove Japanese word variants
* updated country names for Norwegians (thanks @Johannes-Andersen)
* remove support for deprecated osm2pgsql gazetteer style
* fix updating of importances (also needs to update search_name table)
* fix query for deletable endpoint to use index again
* fix reindexing of contained places when a boundary is deleted and reinstated
* fix difference computation error when updating postcodes
* bracket handling sanitizer no longer strips bracket terms in the middle of
name
* reduce precision of stored coordinates to 7-digits everywhere
* avoid ST_Relate as it seems buggy on some systems
* remove setting for logging queries in DB, no longer functional
* postcode updates no longer require a project directory (needed for tests)
* refactor locale handling code (thanks @anqixxx)
* code updates for newer Python (thanks @emmanuel-ferdman)
* better test coverage (thanks @asharmalik19)
* various fixes and improvements to documentation
(thanks @anqixxx, @dave-meyer, @hasandiwan)
5.1.0
* replace datrie with simple internal trie implementation
* add pattern-based postcode parser for queries,
postcodes no longer need to be present in OSM to be found
* take variants into account when computing token similarity
* add extratags output to geocodejson format
* fix default layer setting used for structured queries
* update abbreviation lists for Russian and English
(thanks @shoorick, @IvanShift, @mhsrn21)
* fix variant generation for Norwegian
* fix normalization around space-like characters
* improve postcode search and handling of postcodes in queries
* reorganise internal query structure and get rid of slow enums
* enable code linting for tests
* various code moderinsations in test code (thanks @eumiro)
* remove setting osm2pgsql location via config.lib_dir
* make SQL functions parallel save as far as possible (thanks @otbutz)
* various fixes and improvements to documentation (thanks @TuringVerified)
5.0.0
* increase required versions for PostgreSQL (12+), PostGIS (3.0+)
* remove installation via cmake and debundle osm2pgsql
* remove deprecated PHP frontend
* remove deprecated legacy tokenizer
* add configurable pre-processing of queries
* add query pre-processor to split up Japanese addresses
* rewrite of osm2pgsql style implementation
(also adds support for osm2pgsql-themepark)
* reduce the number of SQL queries needed to complete a 'lookup' call
* improve computation of centroid for lines with only two points
* improve bbox output for postcode areas
* improve result order by returning the largest object when other things are
equal
* add fallback for reverse geocoding to default country tables
* exclude postcode areas from reverse geocoding
* disable search endpoint when database is reverse-only (regression)
* minor performance improvements to area split algorithm
* switch table and index creation to use autocommit mode to avoid deadlocks
* drop overly long ways during import
* restrict automatic migrations to versions 4.3+
* switch linting from pylint to flake8
* switch tests to use a wikimedia test file in the new CSV style
* various fixes and improvements to documentation
4.5.0
* allow building Nominatim as a pip package
* make osm2pgsql building optional
* switch importer to psycopg3
* allow output format of web search to be customized in self-installations
* look up potential postcode areas for postcode results
* add word usage statistics for address terms
* implement more light-weight CSV format for wiki importance tables
* rewrite SQL for place search to use window functions
* increase search radius when filtering by postcode
* prefer POI points over POI areas
* reintroduce full terms for address terms in search_name table
* reindex postcodes when their parent is deleted
* indexing: precompute counts of affected rows
* ensure consistent country assignments for overlapping countries
* make Nominatim[Async]API context manager to ensure proper calling of
close()
* make usage of project dir optional for library
* drop interpolations when no parent can be found
* style tweaks to reflect OSM usage (man_made, highway and others)
* deprecation of: bundled osm2pgsql, legacy tokenizer, PHP frontend
* make documentation buildable without CMake
* various fixes and improvements to documentation
4.4.1
* fix geocodejson output: admin level output should only print boundaries
* updating: restrict invalidation of child objects on large street features
* restrict valid interpolation house numbers to 0-999999
* fix import error when SQLAlchemy 1.4 and psycopg3 are installed
* various typo fixes in the documentation
4.4.0
* add export to SQLite database and SQLite support for the frontend
* switch to Python frontend as the default frontend
* update to osm2pgsql 1.11.0
* add support for new osm2pgsql middle table format
* simplify geometry for large polygon objects not used in addresses
* various performance tweaks for search in Python frontend
* fix regression in search with categories where it was confused with near
search
* partially roll back use of SQLAlchemy lambda statements due to bugs
in SQLAlchemy
* fix handling of timezones for timestamps from the database
* fix handling of full address searches in connection with a viewbox
* fix postcode computation of highway areas
* fix handling of timeout errors for Python <= 3.10
* fix address computation for postcode areas
* fix variable shadowing in osm2pgsql flex script, causing bugs with LuaJIT
* make sure extratags are always null when empty
* reduce importance of places without wikipedia reference
* improve performance of word count computations
* drop support for wikipedia tags with full URLs
* replace get_addressdata() SQL implementation with a Python function
* improve display name for non-address features
* fix postcode validation for postcodes with country code
(thanks @pawel-wroniszewski)
* add possibility to run imports without superuser database rights
(thanks @robbe-haesendonck)
* new CLI command for cleaning deleted relations (thanks @lujoh)
* add check for database version in the CLI check command
* updates to import styles ignoring more unused objects
* various typo fixes (thanks @kumarUjjawal)
4.3.2
* fix potential SQL injection issue for 'nominatim admin --collect-os-info'
* PHP frontend: fix on-the-fly lookup of postcode areas near boundaries
* Python frontend: improve handling of viewbox
* Python frontend: correct deployment instructions
4.3.1
* reintroduce result rematching
* improve search of multi-part names
* fix accidentally switched meaning of --reverse-only and --search-only in
warm command
4.3.0
* fix failing importance recalculation command
* fix merging of linked names into unnamed boundaries
@@ -23,7 +178,7 @@
* new documentation section for library
* various smaller fixes to existing documentation
(thanks @woodpeck, @bloom256, @biswajit-k)
* updates to vagrant install scripts, drop support for Ubunut 18
* updates to vagrant install scripts, drop support for Ubuntu 18
(thanks @n-timofeev)
* removed obsolete configuration variables from env.defaults
* add script for generating a taginfo description (thanks @biswajit-k)
@@ -240,7 +395,7 @@
* increase splitting for large geometries to improve indexing speed
* remove deprecated get_magic_quotes_gpc() function
* make sure that all postcodes have an entry in word and are thus searchable
* remove use of ST_Covers in conjunction woth ST_Intersects,
* remove use of ST_Covers in conjunction with ST_Intersects,
causes bad query planning and slow updates in Postgis3
* update osm2pgsql
@@ -297,7 +452,7 @@
* exclude postcode ranges separated by colon from centre point calculation
* update osm2pgsql, better handling of imports without flatnode file
* switch to more efficient algorithm for word set computation
* use only boundries for country and state parts of addresses
* use only boundaries for country and state parts of addresses
* improve updates of addresses with housenumbers and interpolations
* remove country from place_addressline table and use country_code instead
* optimise indexes on search_name partition tables
@@ -336,7 +491,7 @@
* complete rewrite of reverse search algorithm
* add new geojson and geocodejson output formats
* add simple export script to exprot addresses to CSV
* add simple export script to export addresses to CSV
* remove is_in terms from address computation
* remove unused search_name_country tables
* various smaller fixes to query parsing
@@ -401,7 +556,7 @@
* move installation documentation into this repo
* add self-documenting vagrant scripts
* remove --create-website, recommend to use website directory in build
* add accessor functions for URL parameters and improve erro checking
* add accessor functions for URL parameters and improve error checking
* remove IP blocking and rate-limiting code
* enable CI via travis
* reformatting for more consistent coding style
@@ -412,7 +567,7 @@
* update to refactored osm2pgsql which use libosmium based types
* switch from osmosis to pyosmium for updates
* be more strict when matching against special search terms
* handle postcode entries with mutliple values correctly
* handle postcode entries with multiple values correctly
2.5

202
LICENSES/Apache-2.0.txt Normal file
View File

@@ -0,0 +1,202 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

339
LICENSES/GPL-2.0-only.txt Normal file
View File

@@ -0,0 +1,339 @@
GNU GENERAL PUBLIC LICENSE
Version 2, June 1991
Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The licenses for most software are designed to take away your
freedom to share and change it. By contrast, the GNU General Public
License is intended to guarantee your freedom to share and change free
software--to make sure the software is free for all its users. This
General Public License applies to most of the Free Software
Foundation's software and to any other program whose authors commit to
using it. (Some other Free Software Foundation software is covered by
the GNU Lesser General Public License instead.) You can apply it to
your programs, too.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
this service if you wish), that you receive source code or can get it
if you want it, that you can change the software or use pieces of it
in new free programs; and that you know you can do these things.
To protect your rights, we need to make restrictions that forbid
anyone to deny you these rights or to ask you to surrender the rights.
These restrictions translate to certain responsibilities for you if you
distribute copies of the software, or if you modify it.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must give the recipients all the rights that
you have. You must make sure that they, too, receive or can get the
source code. And you must show them these terms so they know their
rights.
We protect your rights with two steps: (1) copyright the software, and
(2) offer you this license which gives you legal permission to copy,
distribute and/or modify the software.
Also, for each author's protection and ours, we want to make certain
that everyone understands that there is no warranty for this free
software. If the software is modified by someone else and passed on, we
want its recipients to know that what they have is not the original, so
that any problems introduced by others will not reflect on the original
authors' reputations.
Finally, any free program is threatened constantly by software
patents. We wish to avoid the danger that redistributors of a free
program will individually obtain patent licenses, in effect making the
program proprietary. To prevent this, we have made it clear that any
patent must be licensed for everyone's free use or not licensed at all.
The precise terms and conditions for copying, distribution and
modification follow.
GNU GENERAL PUBLIC LICENSE
TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
0. This License applies to any program or other work which contains
a notice placed by the copyright holder saying it may be distributed
under the terms of this General Public License. The "Program", below,
refers to any such program or work, and a "work based on the Program"
means either the Program or any derivative work under copyright law:
that is to say, a work containing the Program or a portion of it,
either verbatim or with modifications and/or translated into another
language. (Hereinafter, translation is included without limitation in
the term "modification".) Each licensee is addressed as "you".
Activities other than copying, distribution and modification are not
covered by this License; they are outside its scope. The act of
running the Program is not restricted, and the output from the Program
is covered only if its contents constitute a work based on the
Program (independent of having been made by running the Program).
Whether that is true depends on what the Program does.
1. You may copy and distribute verbatim copies of the Program's
source code as you receive it, in any medium, provided that you
conspicuously and appropriately publish on each copy an appropriate
copyright notice and disclaimer of warranty; keep intact all the
notices that refer to this License and to the absence of any warranty;
and give any other recipients of the Program a copy of this License
along with the Program.
You may charge a fee for the physical act of transferring a copy, and
you may at your option offer warranty protection in exchange for a fee.
2. You may modify your copy or copies of the Program or any portion
of it, thus forming a work based on the Program, and copy and
distribute such modifications or work under the terms of Section 1
above, provided that you also meet all of these conditions:
a) You must cause the modified files to carry prominent notices
stating that you changed the files and the date of any change.
b) You must cause any work that you distribute or publish, that in
whole or in part contains or is derived from the Program or any
part thereof, to be licensed as a whole at no charge to all third
parties under the terms of this License.
c) If the modified program normally reads commands interactively
when run, you must cause it, when started running for such
interactive use in the most ordinary way, to print or display an
announcement including an appropriate copyright notice and a
notice that there is no warranty (or else, saying that you provide
a warranty) and that users may redistribute the program under
these conditions, and telling the user how to view a copy of this
License. (Exception: if the Program itself is interactive but
does not normally print such an announcement, your work based on
the Program is not required to print an announcement.)
These requirements apply to the modified work as a whole. If
identifiable sections of that work are not derived from the Program,
and can be reasonably considered independent and separate works in
themselves, then this License, and its terms, do not apply to those
sections when you distribute them as separate works. But when you
distribute the same sections as part of a whole which is a work based
on the Program, the distribution of the whole must be on the terms of
this License, whose permissions for other licensees extend to the
entire whole, and thus to each and every part regardless of who wrote it.
Thus, it is not the intent of this section to claim rights or contest
your rights to work written entirely by you; rather, the intent is to
exercise the right to control the distribution of derivative or
collective works based on the Program.
In addition, mere aggregation of another work not based on the Program
with the Program (or with a work based on the Program) on a volume of
a storage or distribution medium does not bring the other work under
the scope of this License.
3. You may copy and distribute the Program (or a work based on it,
under Section 2) in object code or executable form under the terms of
Sections 1 and 2 above provided that you also do one of the following:
a) Accompany it with the complete corresponding machine-readable
source code, which must be distributed under the terms of Sections
1 and 2 above on a medium customarily used for software interchange; or,
b) Accompany it with a written offer, valid for at least three
years, to give any third party, for a charge no more than your
cost of physically performing source distribution, a complete
machine-readable copy of the corresponding source code, to be
distributed under the terms of Sections 1 and 2 above on a medium
customarily used for software interchange; or,
c) Accompany it with the information you received as to the offer
to distribute corresponding source code. (This alternative is
allowed only for noncommercial distribution and only if you
received the program in object code or executable form with such
an offer, in accord with Subsection b above.)
The source code for a work means the preferred form of the work for
making modifications to it. For an executable work, complete source
code means all the source code for all modules it contains, plus any
associated interface definition files, plus the scripts used to
control compilation and installation of the executable. However, as a
special exception, the source code distributed need not include
anything that is normally distributed (in either source or binary
form) with the major components (compiler, kernel, and so on) of the
operating system on which the executable runs, unless that component
itself accompanies the executable.
If distribution of executable or object code is made by offering
access to copy from a designated place, then offering equivalent
access to copy the source code from the same place counts as
distribution of the source code, even though third parties are not
compelled to copy the source along with the object code.
4. You may not copy, modify, sublicense, or distribute the Program
except as expressly provided under this License. Any attempt
otherwise to copy, modify, sublicense or distribute the Program is
void, and will automatically terminate your rights under this License.
However, parties who have received copies, or rights, from you under
this License will not have their licenses terminated so long as such
parties remain in full compliance.
5. You are not required to accept this License, since you have not
signed it. However, nothing else grants you permission to modify or
distribute the Program or its derivative works. These actions are
prohibited by law if you do not accept this License. Therefore, by
modifying or distributing the Program (or any work based on the
Program), you indicate your acceptance of this License to do so, and
all its terms and conditions for copying, distributing or modifying
the Program or works based on it.
6. Each time you redistribute the Program (or any work based on the
Program), the recipient automatically receives a license from the
original licensor to copy, distribute or modify the Program subject to
these terms and conditions. You may not impose any further
restrictions on the recipients' exercise of the rights granted herein.
You are not responsible for enforcing compliance by third parties to
this License.
7. If, as a consequence of a court judgment or allegation of patent
infringement or for any other reason (not limited to patent issues),
conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot
distribute so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you
may not distribute the Program at all. For example, if a patent
license would not permit royalty-free redistribution of the Program by
all those who receive copies directly or indirectly through you, then
the only way you could satisfy both it and this License would be to
refrain entirely from distribution of the Program.
If any portion of this section is held invalid or unenforceable under
any particular circumstance, the balance of the section is intended to
apply and the section as a whole is intended to apply in other
circumstances.
It is not the purpose of this section to induce you to infringe any
patents or other property right claims or to contest validity of any
such claims; this section has the sole purpose of protecting the
integrity of the free software distribution system, which is
implemented by public license practices. Many people have made
generous contributions to the wide range of software distributed
through that system in reliance on consistent application of that
system; it is up to the author/donor to decide if he or she is willing
to distribute software through any other system and a licensee cannot
impose that choice.
This section is intended to make thoroughly clear what is believed to
be a consequence of the rest of this License.
8. If the distribution and/or use of the Program is restricted in
certain countries either by patents or by copyrighted interfaces, the
original copyright holder who places the Program under this License
may add an explicit geographical distribution limitation excluding
those countries, so that distribution is permitted only in or among
countries not thus excluded. In such case, this License incorporates
the limitation as if written in the body of this License.
9. The Free Software Foundation may publish revised and/or new versions
of the General Public License from time to time. Such new versions will
be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the Program
specifies a version number of this License which applies to it and "any
later version", you have the option of following the terms and conditions
either of that version or of any later version published by the Free
Software Foundation. If the Program does not specify a version number of
this License, you may choose any version ever published by the Free Software
Foundation.
10. If you wish to incorporate parts of the Program into other free
programs whose distribution conditions are different, write to the author
to ask for permission. For software which is copyrighted by the Free
Software Foundation, write to the Free Software Foundation; we sometimes
make exceptions for this. Our decision will be guided by the two goals
of preserving the free status of all derivatives of our free software and
of promoting the sharing and reuse of software generally.
NO WARRANTY
11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS
TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE
PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
REPAIR OR CORRECTION.
12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
POSSIBILITY OF SUCH DAMAGES.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
convey the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License along
with this program; if not, write to the Free Software Foundation, Inc.,
51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
Also add information on how to contact you by electronic and paper mail.
If the program is interactive, make it output a short notice like this
when it starts in an interactive mode:
Gnomovision version 69, Copyright (C) year name of author
Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
The hypothetical commands `show w' and `show c' should show the appropriate
parts of the General Public License. Of course, the commands you use may
be called something other than `show w' and `show c'; they could even be
mouse-clicks or menu items--whatever suits your program.
You should also get your employer (if you work as a programmer) or your
school, if any, to sign a "copyright disclaimer" for the program, if
necessary. Here is a sample; alter the names:
Yoyodyne, Inc., hereby disclaims all copyright interest in the program
`Gnomovision' (which makes passes at compilers) written by James Hacker.
<signature of Ty Coon>, 1 April 1989
Ty Coon, President of Vice
This General Public License does not permit incorporating your program into
proprietary programs. If your program is a subroutine library, you may
consider it more useful to permit linking proprietary applications with the
library. If this is what you want to do, use the GNU Lesser General
Public License instead of this License.

44
Makefile Normal file
View File

@@ -0,0 +1,44 @@
all:
# Building of wheels
build: clean-build build-db build-api
clean-build:
rm -f dist/*
build-db:
python3 -m build packaging/nominatim-db --outdir dist/
build-api:
python3 -m build packaging/nominatim-api --outdir dist/
# Tests
tests: mypy lint pytest bdd
mypy:
mypy --strict --python-version 3.9 src
pytest:
pytest test/python
lint:
flake8 src test/python test/bdd
bdd:
pytest test/bdd --nominatim-purge
# Documentation
doc:
mkdocs build
serve-doc:
mkdocs serve
manpage:
argparse-manpage --pyfile man/create-manpage.py --function get_parser --project-name Nominatim --url https://nominatim.org > man/nominatim.1 --author 'the Nominatim developer community' --author-email info@nominatim.org
.PHONY: tests mypy pytest lint bdd build clean-build build-db build-api doc serve-doc manpage

View File

@@ -1,5 +1,4 @@
[![Build Status](https://github.com/osm-search/Nominatim/workflows/CI%20Tests/badge.svg)](https://github.com/osm-search/Nominatim/actions?query=workflow%3A%22CI+Tests%22)
[![codecov](https://codecov.io/gh/osm-search/Nominatim/branch/master/graph/badge.svg?token=8P1LXrhCMy)](https://codecov.io/gh/osm-search/Nominatim)
Nominatim
=========
@@ -28,40 +27,58 @@ can be found at nominatim.org as well.
A quick summary of the necessary steps:
1. Compile Nominatim:
mkdir build
cd build
cmake ..
make
sudo make install
1. Clone this git repository and download the country grid
2. Create a project directory, get OSM data and import:
git clone https://github.com/osm-search/Nominatim.git
wget -O Nominatim/data/country_osm_grid.sql.gz https://nominatim.org/data/country_grid.sql.gz
2. Create a Python virtualenv and install the packages:
python3 -m venv nominatim-venv
./nominatim-venv/bin/pip install packaging/nominatim-{api,db}
3. Create a project directory, get OSM data and import:
mkdir nominatim-project
cd nominatim-project
nominatim import --osm-file <your planet file>
../nominatim-venv/bin/nominatim import --osm-file <your planet file> 2>&1 | tee setup.log
3. Point your webserver to the nominatim-project/website directory.
4. Start the webserver:
./nominatim-venv/bin/pip install uvicorn falcon
../nominatim-venv/bin/nominatim serve
License
=======
The source code is available under a GPLv2 license.
The Python source code is available under a GPL license version 3 or later.
The Lua configuration files for osm2pgsql are released under the
Apache License, Version 2.0. All other files are under a GPLv2 license.
Contributing
============
Contributions, bugreport and pull requests are welcome.
For details see [contribution guide](CONTRIBUTING.md).
Contributions, bug reports and pull requests are welcome. When reporting a
bug, please use one of the
[issue templates](https://github.com/osm-search/Nominatim/issues/new/choose)
and make sure to provide all the information requested. If you are not
sure if you have really found a bug, please ask for help in the forums
first (see 'Questions' below).
For details on contributing, have a look at the
[contribution guide](CONTRIBUTING.md).
Questions and help
==================
For questions, community help and discussions you can use the
[Github discussions forum](https://github.com/osm-search/Nominatim/discussions)
or join the
[geocoding mailing list](https://lists.openstreetmap.org/listinfo/geocoding).
If you have questions about search results and the OpenStreetMap data
used in the search, use the [OSM Forum](https://community.openstreetmap.org/).
For questions, community help and discussions around the software and
your own installation of Nominatim, use the
[Github discussions forum](https://github.com/osm-search/Nominatim/discussions).

View File

@@ -9,10 +9,11 @@ versions.
| Version | End of support for security updates |
| ------- | ----------------------------------- |
| 4.3.x | 2025-09-07 |
| 4.2.x | 2024-11-24 |
| 4.1.x | 2024-08-05 |
| 4.0.x | 2023-11-02 |
| 5.2.x | 2027-10-29 |
| 5.1.x | 2027-04-01 |
| 5.0.x | 2027-02-06 |
| 4.5.x | 2026-09-12 |
| 4.4.x | 2026-03-07 |
## Reporting a Vulnerability
@@ -31,10 +32,10 @@ description of the nature and severity of the issue. **
Patches for identified security issues are applied to all affected versions and
new minor versions are released. At the same time we release a statement at
the [Nominatim blog](https://nominatim.org/blog/) describing the nature of the
incident. Announcements will also be published at the
[geocoding mailinglist](https://lists.openstreetmap.org/listinfo/geocoding).
incident.
## List of Previous Incidents
* 2020-05-04 - [SQL injection issue on /details endpoint](https://lists.openstreetmap.org/pipermail/geocoding/2020-May/002012.html)
* 2023-11-20 - [SQL injection vulnerability](https://nominatim.org/2023/11/20/release-432.html)
* 2023-02-21 - [cross-site scripting vulnerability](https://nominatim.org/2023/02/21/release-421.html)
* 2020-05-04 - [SQL injection issue on /details endpoint](https://lists.openstreetmap.org/pipermail/geocoding/2020-May/002012.html)

View File

@@ -1,6 +1,6 @@
# Install Nominatim in a virtual machine for development and testing
This document describes how you can install Nominatim inside a Ubuntu 22
This document describes how you can install Nominatim inside a Ubuntu 24
virtual machine on your desktop/laptop (host machine). The goal is to give
you a development environment to easily edit code and run the test suite
without affecting the rest of your system.
@@ -15,29 +15,22 @@ is.
2. [Vagrant](https://www.vagrantup.com/downloads.html)
3. Nominatim
git clone --recursive https://github.com/openstreetmap/Nominatim.git
If you forgot `--recursive`, it you can later load the submodules using
git submodule init
git submodule update
3. Nominatim
git clone https://github.com/openstreetmap/Nominatim.git
## Installation
1. Start the virtual machine
vagrant up ubuntu
vagrant up ubuntu24-nginx
2. Log into the virtual machine
vagrant ssh ubuntu
vagrant ssh ubuntu24-nginx
3. Import a small country (Monaco)
See the FAQ how to skip this step and point Nominatim to an existing database.
```
@@ -61,73 +54,22 @@ see Nominatim in action on [localhost:8089](http://localhost:8089/nominatim/).
You edit code on your host machine in any editor you like. There is no need to
restart any software: just refresh your browser window.
Note that the webserver uses files from the /build directory. If you change
files in Nominatim/website or Nominatim/utils for example you first need to
copy them into the /build directory by running the `cmake` step from the
installation.
PHP errors are written to `/var/log/apache2/error.log`.
With `echo` and `var_dump()` you write into the output (HTML/XML/JSON) when
you either add `&debug=1` to the URL.
Use the functions of the `log()` object to create temporary debug output.
Add `&debug=1` to the URL to see the output.
In the Python BDD test you can use `logger.info()` for temporary debug
statements.
## Running unit tests
cd ~/Nominatim/tests/php
phpunit ./
## Running PHP code style tests
cd ~/Nominatim
phpcs --colors .
## Running functional tests
Tests in `test/bdd/db` and `test/bdd/osm2pgsql` have to pass 100%. Other
tests might require full planet-wide data. Sadly even if you have your own
planet-wide data there will be enough differences to the openstreetmap.org
installation to cause false positives in the other tests (see FAQ).
To run the full test suite
cd ~/Nominatim/test/bdd
behave -DBUILDDIR=/home/vagrant/build/ db osm2pgsql
To run a single file
behave -DBUILDDIR=/home/vagrant/build/ api/lookup/simple.feature
Or a single test by line number
behave -DBUILDDIR=/home/vagrant/build/ api/lookup/simple.feature:34
To run specific groups of tests you can add tags just before the `Scenario line`, e.g.
@bug-34
Scenario: address lookup for non-existing or invalid node, way, relation
and then
behave -DBUILDDIR=/home/vagrant/build/ --tags @bug-34
For more information on running tests, see
https://nominatim.org/release-docs/develop/develop/Testing/
## FAQ
##### Will it run on Windows?
Yes, Vagrant and Virtualbox can be installed on MS Windows just fine. You need a 64bit
version of Windows.
Yes, Vagrant and Virtualbox can be installed on MS Windows just fine. You need
a 64bit version of Windows.
##### Will it run on Apple Silicon?
@@ -136,11 +78,11 @@ There is no free/open source version of Parallels.
##### Why Monaco, can I use another country?
Of course! The Monaco import takes less than 30 minutes and works with 2GB RAM.
Of course! The Monaco import takes less than 10 minutes and works with 2GB RAM.
##### Will the results be the same as those from nominatim.openstreetmap.org?
No. Long running Nominatim installations will differ once new import features (or
No. Long-running Nominatim installations will differ once new import features (or
bug fixes) get added since those usually only get applied to new/changed data.
Also this document skips the optional Wikipedia data import which affects ranking
@@ -188,7 +130,3 @@ e.g. `psql --host localhost --port 9999 nominatim_it`
Yes. It's possible to start the virtual machine on [Amazon AWS (plugin)](https://github.com/mitchellh/vagrant-aws)
or [DigitalOcean (plugin)](https://github.com/smdahlen/vagrant-digitalocean).

32
Vagrantfile vendored
View File

@@ -34,11 +34,19 @@ Vagrant.configure("2") do |config|
end
end
config.vm.provider "parallels" do |prl, override|
prl.update_guest_tools = false
prl.memory = 2048
if ENV['CHECKOUT'] != 'y' then
override.vm.synced_folder ".", "/home/vagrant/Nominatim"
end
end
config.vm.provider "libvirt" do |lv, override|
lv.memory = 2048
lv.nested = true
if ENV['CHECKOUT'] != 'y' then
override.vm.synced_folder ".", "/home/vagrant/Nominatim", type: 'nfs'
override.vm.synced_folder ".", "/home/vagrant/Nominatim", type: 'nfs', nfs_udp: false
end
end
@@ -69,28 +77,32 @@ Vagrant.configure("2") do |config|
end
end
config.vm.define "ubuntu20" do |sub|
sub.vm.box = "generic/ubuntu2004"
config.vm.define "ubuntu24" do |sub|
sub.vm.box = "bento/ubuntu-24.04"
if RUBY_PLATFORM.include?('darwin') && RUBY_PLATFORM.include?('arm64')
# Apple M processor
sub.vm.box = 'gutehall/ubuntu24-04'
end
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Ubuntu-20.sh"
s.path = "vagrant/Install-on-Ubuntu-24.sh"
s.privileged = false
s.args = [checkout]
end
end
config.vm.define "ubuntu20-apache" do |sub|
sub.vm.box = "generic/ubuntu2004"
config.vm.define "ubuntu24-apache" do |sub|
sub.vm.box = "bento/ubuntu-24.04"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Ubuntu-20.sh"
s.path = "vagrant/Install-on-Ubuntu-24.sh"
s.privileged = false
s.args = [checkout, "install-apache"]
end
end
config.vm.define "ubuntu20-nginx" do |sub|
sub.vm.box = "generic/ubuntu2004"
config.vm.define "ubuntu24-nginx" do |sub|
sub.vm.box = "bento/ubuntu-24.04"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Ubuntu-20.sh"
s.path = "vagrant/Install-on-Ubuntu-24.sh"
s.privileged = false
s.args = [checkout, "install-nginx"]
end

View File

@@ -1,15 +0,0 @@
# SPDX-License-Identifier: GPL-2.0-only
#
# This file is part of Nominatim. (https://nominatim.org)
#
# Copyright (C) 2022 by the Nominatim developer community.
# For a full list of authors see the git log.
"""
Path settings for extra data used by Nominatim (installed version).
"""
from pathlib import Path
PHPLIB_DIR = (Path('@NOMINATIM_LIBDIR@') / 'lib-php').resolve()
SQLLIB_DIR = (Path('@NOMINATIM_LIBDIR@') / 'lib-sql').resolve()
DATA_DIR = Path('@NOMINATIM_DATADIR@').resolve()
CONFIG_DIR = Path('@NOMINATIM_CONFIGDIR@').resolve()

View File

@@ -1,13 +0,0 @@
#!/usr/bin/env python3
import sys
import os
sys.path.insert(1, '@NOMINATIM_LIBDIR@/lib-python')
from nominatim import cli
from nominatim import version
version.GIT_COMMIT_HASH = '@GIT_HASH@'
exit(cli.nominatim(module_dir='@NOMINATIM_LIBDIR@/module',
osm2pgsql_path='@NOMINATIM_LIBDIR@/osm2pgsql'))

View File

@@ -1,13 +0,0 @@
#!/usr/bin/env python3
import sys
import os
sys.path.insert(1, '@CMAKE_SOURCE_DIR@')
from nominatim import cli
from nominatim import version
version.GIT_COMMIT_HASH = '@GIT_HASH@'
exit(cli.nominatim(module_dir='@CMAKE_BINARY_DIR@/module',
osm2pgsql_path='@CMAKE_BINARY_DIR@/osm2pgsql/osm2pgsql'))

View File

@@ -1,35 +0,0 @@
# Auto-generated vagrant install documentation
# build the actual documentation
configure_file(mkdocs.yml ../mkdocs.yml)
file(MAKE_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/appendix)
set (DOC_SOURCES
admin
develop
api
customize
library
index.md
extra.css
styles.css
)
foreach (src ${DOC_SOURCES})
execute_process(
COMMAND ${CMAKE_COMMAND} -E create_symlink ${CMAKE_CURRENT_SOURCE_DIR}/${src} ${CMAKE_CURRENT_BINARY_DIR}/${src}
)
endforeach()
ADD_CUSTOM_TARGET(doc
COMMAND ${CMAKE_CURRENT_SOURCE_DIR}/bash2md.sh ${PROJECT_SOURCE_DIR}/vagrant/Install-on-Ubuntu-20.sh ${CMAKE_CURRENT_BINARY_DIR}/appendix/Install-on-Ubuntu-20.md
COMMAND ${CMAKE_CURRENT_SOURCE_DIR}/bash2md.sh ${PROJECT_SOURCE_DIR}/vagrant/Install-on-Ubuntu-22.sh ${CMAKE_CURRENT_BINARY_DIR}/appendix/Install-on-Ubuntu-22.md
COMMAND mkdocs build -d ${CMAKE_CURRENT_BINARY_DIR}/../site-html -f ${CMAKE_CURRENT_BINARY_DIR}/../mkdocs.yml
)
ADD_CUSTOM_TARGET(serve-doc
COMMAND mkdocs serve -f ${CMAKE_CURRENT_BINARY_DIR}/../mkdocs.yml
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}
)

View File

@@ -5,6 +5,35 @@ your Nominatim database. It is assumed that you have already successfully
installed the Nominatim software itself, if not return to the
[installation page](Installation.md).
## Importing with a database user without superuser rights
Nominatim usually creates its own PostgreSQL database at the beginning of the
import process. This makes usage easier for the user but means that the
database user doing the import needs the appropriate rights.
If you prefer to run the import with a database user with limited rights,
you can do so by changing the import process as follows:
1. Run the command for database preparation with a database user with
superuser rights. For example, to use a db user 'dbadmin' for a
database 'nominatim', execute:
```
NOMINATIM_DATABASE_DSN="pgsql:dbname=nominatim;user=dbadmin" nominatim import --prepare-database
```
2. Grant the import user the right to create tables. For example, foe user 'import-user':
```
psql -d nominatim -c 'GRANT CREATE ON SCHEMA public TO "import-user"'
```
3. Now run the reminder of the import with the import user:
```
NOMINATIM_DATABASE_DSN="pgsql:dbname=nominatim;user=import-user" nominatim import --continue import-from-file --osm-file file.pbf
```
## Importing multiple regions (without updates)
To import multiple regions in your database you can simply give multiple
@@ -102,76 +131,13 @@ script ([Geofabrik](https://download.geofabrik.de)) provides daily updates.
## Using an external PostgreSQL database
You can install Nominatim using a database that runs on a different server when
you have physical access to the file system on the other server. Nominatim
uses a custom normalization library that needs to be made accessible to the
PostgreSQL server. This section explains how to set up the normalization
library.
!!! note
The external module is only needed when using the legacy tokenizer.
If you have chosen the ICU tokenizer, then you can ignore this section
and follow the standard import documentation.
### Option 1: Compiling the library on the database server
The most sure way to get a working library is to compile it on the database
server. From the prerequisites you need at least cmake, gcc and the
PostgreSQL server package.
Clone or unpack the Nominatim source code, enter the source directory and
create and enter a build directory.
```sh
cd Nominatim
mkdir build
cd build
```
Now configure cmake to only build the PostgreSQL module and build it:
```
cmake -DBUILD_IMPORTER=off -DBUILD_API=off -DBUILD_TESTS=off -DBUILD_DOCS=off -DBUILD_OSM2PGSQL=off ..
make
```
When done, you find the normalization library in `build/module/nominatim.so`.
Copy it to a place where it is readable and executable by the PostgreSQL server
process.
### Option 2: Compiling the library on the import machine
You can also compile the normalization library on the machine from where you
run the import.
!!! important
You can only do this when the database server and the import machine have
the same architecture and run the same version of Linux. Otherwise there is
no guarantee that the compiled library is compatible with the PostgreSQL
server running on the database server.
Make sure that the PostgreSQL server package is installed on the machine
**with the same version as on the database server**. You do not need to install
the PostgreSQL server itself.
Download and compile Nominatim as per standard instructions. Once done, you find
the normalization library in `build/module/nominatim.so`. Copy the file to
the database server at a location where it is readable and executable by the
PostgreSQL server process.
### Running the import
On the client side you now need to configure the import to point to the
correct location of the library **on the database server**. Add the following
line to your your `.env` file:
```php
NOMINATIM_DATABASE_MODULE_PATH="<directory on the database server where nominatim.so resides>"
```
Now change the `NOMINATIM_DATABASE_DSN` to point to your remote server and continue
to follow the [standard instructions for importing](Import.md).
You can install Nominatim using a database that runs on a different server.
Simply point the configuration variable `NOMINATIM_DATABASE_DSN` to the
server and follow the standard import documentation.
The import will be faster, if the import is run directly from the database
machine. You can easily switch to a different machine for the query frontend
after the import.
## Moving the database to another machine
@@ -196,20 +162,9 @@ target machine.
data updates but the resulting database is only about a third of the size
of a full database.
Next install Nominatim on the target machine by following the standard installation
instructions. Again, make sure to use the same version as the source machine.
Next install nominatim-api on the target machine by following the standard
installation instructions. Again, make sure to use the same version as the
source machine.
Create a project directory on your destination machine and set up the `.env`
file to match the configuration on the source machine. Finally run
nominatim refresh --website
to make sure that the local installation of Nominatim will be used.
If you are using the legacy tokenizer you might also have to switch to the
PostgreSQL module that was compiled on your target machine. If you get errors
that PostgreSQL cannot find or access `nominatim.so` then rerun
nominatim refresh --functions
on the target machine to update the the location of the module.
file to match the configuration on the source machine. That's all.

View File

@@ -1,148 +0,0 @@
# Deploying Nominatim using the PHP frontend
The Nominatim API is implemented as a PHP application. The `website/` directory
in the project directory contains the configured website. You can serve this
in a production environment with any web server that is capable to run
PHP scripts.
This section gives a quick overview on how to configure Apache and Nginx to
serve Nominatim. It is not meant as a full system administration guide on how
to run a web service. Please refer to the documentation of
[Apache](https://httpd.apache.org/docs/current/) and
[Nginx](https://nginx.org/en/docs/)
for background information on configuring the services.
!!! Note
Throughout this page, we assume your Nominatim project directory is
located in `/srv/nominatim-project` and you have installed Nominatim
using the default installation prefix `/usr/local`. If you have put it
somewhere else, you need to adjust the commands and configuration
accordingly.
We further assume that your web server runs as user `www-data`. Older
versions of CentOS may still use the user name `apache`. You also need
to adapt the instructions in this case.
## Making the website directory accessible
You need to make sure that the `website` directory is accessible for the
web server user. You can check that the permissions are correct by accessing
on of the php files as the web server user:
``` sh
sudo -u www-data head -n 1 /srv/nominatim-project/website/search.php
```
If this shows a permission error, then you need to adapt the permissions of
each directory in the path so that it is executable for `www-data`.
If you have SELinux enabled, further adjustments may be necessary to give the
web server access. At a minimum the following SELinux labelling should be done
for Nominatim:
``` sh
sudo semanage fcontext -a -t httpd_sys_content_t "/usr/local/nominatim/lib/lib-php(/.*)?"
sudo semanage fcontext -a -t httpd_sys_content_t "/srv/nominatim-project/website(/.*)?"
sudo semanage fcontext -a -t lib_t "/srv/nominatim-project/module/nominatim.so"
sudo restorecon -R -v /usr/local/lib/nominatim
sudo restorecon -R -v /srv/nominatim-project
```
## Nominatim with Apache
### Installing the required packages
With Apache you can use the PHP module to run Nominatim.
Under Ubuntu/Debian install them with:
``` sh
sudo apt install apache2 libapache2-mod-php
```
### Configuring Apache
Make sure your Apache configuration contains the required permissions for the
directory and create an alias:
``` apache
<Directory "/srv/nominatim-project/website">
Options FollowSymLinks MultiViews
AddType text/html .php
DirectoryIndex search.php
Require all granted
</Directory>
Alias /nominatim /srv/nominatim-project/website
```
After making changes in the apache config you need to restart apache.
The website should now be available on `http://localhost/nominatim`.
## Nominatim with Nginx
### Installing the required packages
Nginx has no built-in PHP interpreter. You need to use php-fpm as a daemon for
serving PHP cgi.
On Ubuntu/Debian install nginx and php-fpm with:
``` sh
sudo apt install nginx php-fpm
```
### Configure php-fpm and Nginx
By default php-fpm listens on a network socket. If you want it to listen to a
Unix socket instead, change the pool configuration
(`/etc/php/<php version>/fpm/pool.d/www.conf`) as follows:
``` ini
; Replace the tcp listener and add the unix socket
listen = /var/run/php-fpm-nominatim.sock
; Ensure that the daemon runs as the correct user
listen.owner = www-data
listen.group = www-data
listen.mode = 0666
```
Tell nginx that php files are special and to fastcgi_pass to the php-fpm
unix socket by adding the location definition to the default configuration.
``` nginx
root /srv/nominatim-project/website;
index search.php;
location / {
try_files $uri $uri/ @php;
}
location @php {
fastcgi_param SCRIPT_FILENAME "$document_root$uri.php";
fastcgi_param PATH_TRANSLATED "$document_root$uri.php";
fastcgi_param QUERY_STRING $args;
fastcgi_pass unix:/var/run/php-fpm-nominatim.sock;
fastcgi_index index.php;
include fastcgi_params;
}
location ~ [^/]\.php(/|$) {
fastcgi_split_path_info ^(.+?\.php)(/.*)$;
if (!-f $document_root$fastcgi_script_name) {
return 404;
}
fastcgi_pass unix:/var/run/php-fpm-nominatim.sock;
fastcgi_index search.php;
include fastcgi.conf;
}
```
Restart the nginx and php-fpm services and the website should now be available
at `http://localhost/`.
## Nominatim with other webservers
Users have created instructions for other webservers:
* [Caddy](https://github.com/osm-search/Nominatim/discussions/2580)

View File

@@ -1,6 +1,6 @@
# Deploying the Nominatim Python frontend
The Nominatim can be run as a Python-based
Nominatim can be run as a Python-based
[ASGI web application](https://asgi.readthedocs.io/en/latest/). You have the
choice between [Falcon](https://falcon.readthedocs.io/en/stable/)
and [Starlette](https://www.starlette.io/) as the ASGI framework.
@@ -12,30 +12,39 @@ to configure it.
!!! Note
Throughout this page, we assume your Nominatim project directory is
located in `/srv/nominatim-project` and you have installed Nominatim
using the default installation prefix `/usr/local`. If you have put it
somewhere else, you need to adjust the commands and configuration
accordingly.
located in `/srv/nominatim-project`. If you have put it somewhere else,
you need to adjust the commands and configuration accordingly.
We further assume that your web server runs as user `www-data`. Older
versions of CentOS may still use the user name `apache`. You also need
to adapt the instructions in this case.
### Installing the required packages
The Nominatim frontend is best run from its own virtual environment. If
you have already created one for the database backend during the
[installation](Installation.md#building-nominatim), you can use that. Otherwise
create one now with:
```sh
sudo apt-get install virtualenv
virtualenv /srv/nominatim-venv
```
The Nominatim frontend is contained in the 'nominatim-api' package. To
install directly from the source tree run:
```sh
cd Nominatim
/srv/nominatim-venv/bin/pip install packaging/nominatim-api
```
The recommended way to deploy a Python ASGI application is to run
the ASGI runner [uvicorn](https://uvicorn.org/)
the ASGI runner [uvicorn](https://www.uvicorn.org/)
together with [gunicorn](https://gunicorn.org/) HTTP server. We use
Falcon here as the web framework.
Create a virtual environment for the Python packages and install the necessary
dependencies:
Add the necessary packages to your virtual environment:
``` sh
sudo apt install virtualenv
virtualenv /srv/nominatim-venv
/srv/nominatim-venv/bin/pip install SQLAlchemy PyICU psycopg[binary] \
psycopg2-binary python-dotenv PyYAML falcon uvicorn gunicorn
/srv/nominatim-venv/bin/pip install falcon uvicorn gunicorn
```
### Setting up Nominatim as a systemd job
@@ -43,6 +52,22 @@ virtualenv /srv/nominatim-venv
Next you need to set up the service that runs the Nominatim frontend. This is
easiest done with a systemd job.
First you need to tell systemd to create a socket file to be used by
hunicorn. Create the following file `/etc/systemd/system/nominatim.socket`:
``` systemd
[Unit]
Description=Gunicorn socket for Nominatim
[Socket]
ListenStream=/run/nominatim.sock
SocketUser=www-data
[Install]
WantedBy=multi-user.target
```
Now you can add the systemd service for Nominatim itself.
Create the following file `/etc/systemd/system/nominatim.service`:
``` systemd
@@ -53,11 +78,10 @@ Requires=nominatim.socket
[Service]
Type=simple
Environment="PYTHONPATH=/usr/local/lib/nominatim/lib-python/"
User=www-data
Group=www-data
WorkingDirectory=/srv/nominatim-project
ExecStart=/srv/nominatim-venv/bin/gunicorn -b unix:/run/nominatim.sock -w 4 -k uvicorn.workers.UvicornWorker nominatim.server.falcon.server:run_wsgi
ExecStart=/srv/nominatim-venv/bin/gunicorn -b unix:/run/nominatim.sock -w 4 -k uvicorn.workers.UvicornWorker "nominatim_api.server.falcon.server:run_wsgi()"
ExecReload=/bin/kill -s HUP $MAINPID
StandardOutput=append:/var/log/gunicorn-nominatim.log
StandardError=inherit
@@ -74,12 +98,14 @@ its own Python process using
[`NOMINATIM_API_POOL_SIZE`](../customize/Settings.md#nominatim_api_pool_size)
connections to the database to serve requests in parallel.
Make the new service known to systemd and start it:
Make the new services known to systemd and start it:
``` sh
sudo systemctl daemon-reload
sudo systemctl enable nominatim
sudo systemctl start nominatim
sudo systemctl enable nominatim.socket
sudo systemctl start nominatim.socket
sudo systemctl enable nominatim.service
sudo systemctl start nominatim.service
```
This sets the service up, so that Nominatim is automatically started

View File

@@ -37,65 +37,6 @@ nominatim import --continue indexing
Otherwise it's best to start the full setup from the beginning.
### PHP "open_basedir restriction in effect" warnings
PHP Warning: file_get_contents(): open_basedir restriction in effect.
You need to adjust the
[open_basedir](https://www.php.net/manual/en/ini.core.php#ini.open-basedir)
setting in your PHP configuration (`php.ini` file). By default this setting may
look like this:
open_basedir = /srv/http/:/home/:/tmp/:/usr/share/pear/
Either add reported directories to the list or disable this setting temporarily
by adding ";" at the beginning of the line. Don't forget to enable this setting
again once you are done with the PHP command line operations.
### PHP timezeone warnings
The Apache log may contain lots of PHP warnings like this:
`PHP Warning: date_default_timezone_set() function.`
You should set the default time zone as instructed in the warning in
your `php.ini` file. Find the entry about timezone and set it to
something like this:
; Defines the default timezone used by the date functions
; https://php.net/date.timezone
date.timezone = 'America/Denver'
Or
```
echo "date.timezone = 'America/Denver'" > /etc/php.d/timezone.ini
```
### nominatim.so version mismatch
When running the import you may get a version mismatch:
`COPY_END for place failed: ERROR: incompatible library "/srv/Nominatim/nominatim/build/module/nominatim.so": version mismatch`
pg_config seems to use bad includes sometimes when multiple versions
of PostgreSQL are available in the system. Make sure you remove the
server development libraries (`postgresql-server-dev-13` on Ubuntu)
and recompile (`cmake .. && make`).
### I see the error "ERROR: permission denied for language c"
`nominatim.so`, written in C, is required to be installed on the database
server. Some managed database (cloud) services like Amazon RDS do not allow
this. There is currently no work-around other than installing a database
on a non-managed machine.
### I see the error: "function transliteration(text) does not exist"
Reinstall the nominatim functions with `nominatim refresh --functions`
and check for any errors, e.g. a missing `nominatim.so` file.
### I see the error: "ERROR: mmap (remap) failed"
This may be a simple out-of-memory error. Try reducing the memory used
@@ -137,45 +78,31 @@ for default Ubuntu operating system for example it's `www-data`.
GRANT SELECT ON ALL TABLES IN SCHEMA public TO "www-data";
```
### Website reports "Could not load library "nominatim.so"
Example error message
```
SELECT make_standard_name('3039 E MEADOWLARK LN') [nativecode=ERROR: could not
load library "/srv/nominatim/Nominatim-3.1.0/build/module/nominatim.so":
/srv/nominatim/Nominatim-3.1.0/build/module/nominatim.so: cannot open shared
object file: Permission denied
CONTEXT: PL/pgSQL function make_standard_name(text) line 5 at assignment]
```
The PostgreSQL database, i.e. user `postgres`, needs to have access to that file.
The permission need to be read & executable by everybody, but not writeable
by everybody, e.g.
```
-rwxr-xr-x 1 nominatim nominatim 297984 build/module/nominatim.so
```
Try `chmod a+r nominatim.so; chmod a+x nominatim.so`.
When you recently updated your operating system, updated PostgreSQL to
a new version or moved files (e.g. the build directory) you should
recreate `nominatim.so`. Try
```
cd build
rm -r module/
cmake $main_Nominatim_path && make
```
### Setup.php fails with "DB Error: extension not found"
### Setup fails with "DB Error: extension not found"
Make sure you have the PostgreSQL extensions "hstore" and "postgis" installed.
See the installation instructions for a full list of required packages.
### UnicodeEncodeError: 'ascii' codec can't encode character
Make sure that the operating system's locale is UTF-8. With some prebuilt
images (e.g. LXC containers from Proxmox, see
[discussion](https://github.com/osm-search/Nominatim/discussions/2343)) or
images that optimize for size it might be missing.
On Ubuntu you can check the locale is installed:
```
grep UTF-8 /etc/default/locale
```
And install it using
```
dpkg-reconfigure locales
```
### I forgot to delete the flatnodes file before starting an import.
That's fine. For each import the flatnodes file get overwritten.
@@ -187,4 +114,6 @@ for more information.
### Can I import negative OSM ids into Nominatim?
See [this question of Stackoverflow](https://help.openstreetmap.org/questions/64662/nominatim-flatnode-with-negative-id).
No, negative IDs are no longer supported by osm2pgsql. You can use
large 64-bit IDs that are guaranteed not to clash with OSM IDs. However,
you will not able to use a flatnode file with them.

View File

@@ -14,15 +14,15 @@ to a single Nominatim setup: configuration, extra data, etc. Create a project
directory apart from the Nominatim software and change into the directory:
```
mkdir ~/nominatim-planet
cd ~/nominatim-planet
mkdir ~/nominatim-project
cd ~/nominatim-project
```
In the following, we refer to the project directory as `$PROJECT_DIR`. To be
able to copy&paste instructions, you can export the appropriate variable:
```
export PROJECT_DIR=~/nominatim-planet
export PROJECT_DIR=~/nominatim-project
```
The Nominatim tool assumes per default that the current working directory is
@@ -74,15 +74,18 @@ but it will improve the quality of the results if this is installed.
This data is available as a binary download. Put it into your project directory:
cd $PROJECT_DIR
wget https://nominatim.org/data/wikimedia-importance.sql.gz
wget https://nominatim.org/data/wikimedia-importance.csv.gz
wget -O secondary_importance.sql.gz https://nominatim.org/data/wikimedia-secondary-importance.sql.gz
The file is about 400MB and adds around 4GB to the Nominatim database.
The files are about 400MB and add around 4GB to the Nominatim database. For
more information about importance,
see [Importance Customization](../customize/Importance.md).
!!! tip
If you forgot to download the wikipedia rankings, then you can
also add importances after the import. Download the SQL files, then
run `nominatim refresh --wiki-data --importance`. Updating
importances for a planet will take a couple of hours.
run `nominatim refresh --wiki-data --secondary-importance --importance`.
Updating importances for a planet will take a couple of hours.
### External postcodes
@@ -153,7 +156,7 @@ if you plan to use the installation only for exports to a
[photon](https://photon.komoot.io/) database, then you can set up a database
without search indexes. Add `--reverse-only` to your setup command above.
This saves about 5% of disk space.
This saves about 5% of disk space, import time won't be significant faster.
### Filtering Imported Data
@@ -228,7 +231,7 @@ to load the OSM data into the PostgreSQL database. This step is very demanding
in terms of RAM usage. osm2pgsql and PostgreSQL are running in parallel at
this point. PostgreSQL blocks at least the part of RAM that has been configured
with the `shared_buffers` parameter during
[PostgreSQL tuning](Installation.md#postgresql-tuning)
[PostgreSQL tuning](Installation.md#tuning-the-postgresql-database)
and needs some memory on top of that. osm2pgsql needs at least 2GB of RAM for
its internal data structures, potentially more when it has to process very large
relations. In addition it needs to maintain a cache for node locations. The size
@@ -254,8 +257,8 @@ successfully.
nominatim admin --check-database
```
Now you can try out your installation by executing a simple query on the
command line:
If you have installed the `nominatim-api` package, then you can try out
your installation by executing a simple query on the command line:
``` sh
nominatim search --query Berlin
@@ -267,27 +270,8 @@ or, when you have a reverse-only installation:
nominatim reverse --lat 51 --lon 45
```
If you want to run Nominatim as a service, you need to make a choice between
running the traditional PHP frontend or the new experimental Python frontend.
Make sure you have installed the right packages as per
[Installation](Installation.md#software).
#### Testing the PHP frontend
You can run a small test server with the PHP frontend like this:
```sh
nominatim serve
```
Go to `http://localhost:8088/status.php` and you should see the message `OK`.
You can also run a search query, e.g. `http://localhost:8088/search.php?q=Berlin`
or, for reverse-only installations a reverse query,
e.g. `http://localhost:8088/reverse.php?lat=27.1750090510034&lon=78.04209025`.
Do not use this test server in production.
To run Nominatim via webservers like Apache or nginx, please continue reading
[Deploy the PHP frontend](Deployment-PHP.md).
If you want to run Nominatim as a service, make sure you have installed
the right packages as per [Installation](Installation.md#software).
#### Testing the Python frontend
@@ -296,19 +280,19 @@ web framework to use, either starlette or falcon. Make sure the appropriate
packages are installed. Then run
``` sh
nominatim serve --engine falcon
nominatim serve
```
or
or, if you prefer to use Starlette instead of Falcon as webserver,
``` sh
nominatim serve --engine starlette
```
Go to `http://localhost:8088/status.php` and you should see the message `OK`.
You can also run a search query, e.g. `http://localhost:8088/search.php?q=Berlin`
Go to `http://localhost:8088/status` and you should see the message `OK`.
You can also run a search query, e.g. `http://localhost:8088/search?q=Berlin`
or, for reverse-only installations a reverse query,
e.g. `http://localhost:8088/reverse.php?lat=27.1750090510034&lon=78.04209025`.
e.g. `http://localhost:8088/reverse?lat=27.1750090510034&lon=78.04209025`.
Do not use this test server in production.
To run Nominatim via webservers like Apache or nginx, please continue reading

View File

@@ -4,8 +4,8 @@ This page contains generic installation instructions for Nominatim and its
prerequisites. There are also step-by-step instructions available for
the following operating systems:
* [Ubuntu 22.04](../appendix/Install-on-Ubuntu-22.md)
* [Ubuntu 20.04](../appendix/Install-on-Ubuntu-20.md)
* [Ubuntu 24.04](Install-on-Ubuntu-24.md)
* [Ubuntu 22.04](Install-on-Ubuntu-22.md)
These OS-specific instructions can also be found in executable form
in the `vagrant/` directory.
@@ -22,51 +22,33 @@ and can't offer support.
### Software
!!! Warning
For larger installations you **must have** PostgreSQL 11+ and PostGIS 3+
otherwise import and queries will be slow to the point of being unusable.
Query performance has marked improvements with PostgreSQL 13+ and PostGIS 3.2+.
For compiling:
* [cmake](https://cmake.org/)
* [expat](https://libexpat.github.io/)
* [proj](https://proj.org/)
* [bzip2](http://www.bzip.org/)
* [zlib](https://www.zlib.net/)
* [ICU](http://site.icu-project.org/)
* [nlohmann/json](https://json.nlohmann.me/)
* [Boost libraries](https://www.boost.org/), including system and filesystem
* PostgreSQL client libraries
* a recent C++ compiler (gcc 5+ or Clang 3.8+)
For running Nominatim:
* [PostgreSQL](https://www.postgresql.org) (9.6+ will work, 11+ strongly recommended)
* [PostGIS](https://postgis.net) (2.2+ will work, 3.0+ strongly recommended)
* [Python 3](https://www.python.org/) (3.7+)
* [Psycopg2](https://www.psycopg.org) (2.7+)
* [PostgreSQL](https://www.postgresql.org) (12+ will work, 13+ strongly recommended)
* [PostGIS](https://postgis.net) (3.0+ will work, 3.2+ strongly recommended)
* [osm2pgsql](https://osm2pgsql.org) (1.8+)
* [Python 3](https://www.python.org/) (3.9+)
Furthermore the following Python libraries are required:
* [Psycopg3](https://www.psycopg.org)
* [Python Dotenv](https://github.com/theskumar/python-dotenv)
* [psutil](https://github.com/giampaolo/psutil)
* [Jinja2](https://palletsprojects.com/p/jinja/)
* [SQLAlchemy](https://www.sqlalchemy.org/) (1.4.31+ with greenlet support)
* [asyncpg](https://magicstack.github.io/asyncpg) (0.8+)
* [PyICU](https://pypi.org/project/PyICU/)
* [PyYaml](https://pyyaml.org/) (5.1+)
* [datrie](https://github.com/pytries/datrie)
* [mwparserfromhell](https://github.com/earwig/mwparserfromhell/)
When running the PHP frontend:
* [PHP](https://php.net) (7.3+)
* PHP-pgsql
* PHP-intl (bundled with PHP)
These will be installed automatically when using pip installation.
For running continuous updates:
* [pyosmium](https://osmcode.org/pyosmium/)
For running the experimental Python frontend:
For running the Python frontend:
* [SQLAlchemy](https://www.sqlalchemy.org/) (1.4.31+ with greenlet support)
* [asyncpg](https://magicstack.github.io/asyncpg) (0.8+, only when using SQLAlchemy < 2.0)
* one of the following web frameworks:
* [falcon](https://falconframework.org/) (3.0+)
* [starlette](https://www.starlette.io/)
@@ -86,7 +68,7 @@ Take into account that the OSM database is growing fast.
Fast disks are essential. Using NVME disks is recommended.
Even on a well configured machine the import of a full planet takes
around 2 days. When using traditional SSDs, 4-5 days are more realistic.
around 2.5 days. When using traditional SSDs, 4-5 days are more realistic.
## Tuning the PostgreSQL database
@@ -98,14 +80,16 @@ your `postgresql.conf` file.
maintenance_work_mem = (10GB)
autovacuum_work_mem = 2GB
work_mem = (50MB)
effective_cache_size = (24GB)
synchronous_commit = off
max_wal_size = 1GB
checkpoint_timeout = 10min
checkpoint_timeout = 60min
checkpoint_completion_target = 0.9
random_page_cost = 1.0
wal_level = minimal
max_wal_senders = 0
The numbers in brackets behind some parameters seem to work fine for
64GB RAM machine. Adjust to your setup. A higher number for `max_wal_size`
128GB RAM machine. Adjust to your setup. A higher number for `max_wal_size`
means that PostgreSQL needs to run checkpoints less often but it does require
the additional space on your disk.
@@ -118,6 +102,15 @@ you might consider setting:
and even reduce `autovacuum_work_mem` further. This will reduce the amount
of memory that autovacuum takes away from the import process.
## Installing the latest release
Nominatim is easiest installed directly from Pypi. Make sure you have installed
osm2pgsql, PostgreSQL/PostGIS and libICU together with its header files.
Then you can install Nominatim with:
pip install nominatim-db nominatim-api
## Downloading and building Nominatim
### Downloading the latest release
@@ -127,11 +120,10 @@ The release contains all necessary files. Just unpack it.
### Downloading the latest development version
If you want to install latest development version from github, make sure to
also check out the osm2pgsql subproject:
If you want to install latest development version from github:
```
git clone --recursive https://github.com/openstreetmap/Nominatim.git
git clone https://github.com/osm-search/Nominatim.git
```
The development version does not include the country grid. Download it separately:
@@ -142,41 +134,14 @@ wget -O Nominatim/data/country_osm_grid.sql.gz https://nominatim.org/data/countr
### Building Nominatim
The code must be built in a separate directory. Create the directory and
change into it.
Nominatim is easiest to run from its own virtual environment. To create one, run:
```
mkdir build
cd build
```
sudo apt-get install virtualenv
virtualenv /srv/nominatim-venv
Nominatim uses cmake and make for building. Assuming that you have created the
build at the same level as the Nominatim source directory run:
To install Nominatim directly from the source tree into the virtual environment, run:
```
cmake ../Nominatim
make
sudo make install
```
/srv/nominatim-venv/bin/pip install packaging/nominatim-{db,api}
!!! warning
The default installation no longer compiles the PostgreSQL module that
is needed for the legacy tokenizer from older Nominatim versions. If you
are upgrading an older database or want to run the
[legacy tokenizer](../customize/Tokenizers.md#legacy-tokenizer) for
some other reason, you need to enable the PostgreSQL module via
cmake: `cmake -DBUILD_MODULE=on ../Nominatim`. To compile the module
you need to have the server development headers for PostgreSQL installed.
On Ubuntu/Debian run: `sudo apt install postgresql-server-dev-<postgresql version>`
Nominatim installs itself into `/usr/local` per default. To choose a different
installation directory add `-DCMAKE_INSTALL_PREFIX=<install root>` to the
cmake command. Make sure that the `bin` directory is available in your path
in that case, e.g.
```
export PATH=<install root>/bin:$PATH
```
Now continue with [importing the database](Import.md).

View File

@@ -60,16 +60,13 @@ to finish the recomputation.
## Removing large deleted objects
Command: `nominatim admin --clean-deleted <PostgreSQL Time Interval>`
Nominatim refuses to delete very large areas because often these deletions are
accidental and are reverted within hours. Instead the deletions are logged in
the `import_polygon_delete` table and left to the administrator to clean up.
There is currently no command to do that. You can use the following SQL
query to force a deletion on all objects that have been deleted more than
a certain timespan ago (here: 1 month):
To run this command you will need to pass a PostgreSQL time interval. For example to
delete any objects that have been deleted more than a month ago you would run:
`nominatim admin --clean-deleted '1 month'`
```sql
SELECT place_force_delete(p.place_id) FROM import_polygon_delete d, placex p
WHERE p.osm_type = d.osm_type and p.osm_id = d.osm_id
and age(p.indexed_date) > '1 month'::interval
```

View File

@@ -1,19 +1,97 @@
# Database Migrations
Since version 3.7.0 Nominatim offers automatic migrations. Please follow
Nominatim offers automatic migrations for versions 4.3+. Please follow
the following steps:
* stop any updates that are potentially running
* update Nominatim to the newer version
* go to your project directory and run `nominatim admin --migrate`
* (optionally) restart updates
* Stop any updates that are potentially running
* Update the backend: `pip install -U nominatim-db`
* Go to your project directory and run `nominatim admin --migrate`
* Update the frontend: `pip install -U nominatim-api`
* (optionally) Restart updates
Below you find additional migrations and hints about other structural and
breaking changes. **Please read them before running the migration.**
!!! note
If you are migrating from a version <3.6, then you still have to follow
the manual migration steps up to 3.6.
If you are migrating from a version <4.3, you need to install 4.3
and migrate to 4.3 first. Then you can migrate to the current
version. It is strongly recommended to do a reimport instead.
## 5.1.0 -> 5.2.0
### Lua import style: required extratags removed
Tags that are required by Nominatim as extratags are now always included
independent of what is defined in the style. The line
flex.add_for_extratags('required')
is no longer required in custom styles and will throw an error. Simply
remove the line from your style.
## 4.5.0 -> 5.0.0
### PHP frontend removed
The PHP frontend has been completely removed. Please switch to the Python
frontend.
Without the PHP code, the `nominatim refresh --website` command is no longer
needed. It currently omits a warning and does otherwise nothing. It will be
removed in later versions of Nominatim. So make sure you remove it from your
scripts.
### CMake building removed
Nominatim can now only be installed via pip. Please follow the installation
instructions for the current version to change to pip.
### osm2pgsql no longer vendored in
Nominatim no longer ships its own version of osm2pgsql. Please install a
stock version of osm2pgsql from your distribution. See the
[installation instruction for osm2pgsql](https://osm2pgsql.org/doc/install.html)
for details. A minimum version of 1.8 is required. The current stable versions
of Ubuntu and Debian already ship with an appropriate versions. For older
installation, you may have to compile a newer osm2pgsql yourself.
### Legacy tokenizer removed
The `legacy` tokenizer is no longer enabled. This tokenizer has been superseded
by the `ICU` tokenizer a long time ago. In the unlikely case that your database
still uses the `legacy` tokenizer, you must reimport your database.
### osm2pgsql style overhauled
There are some fundamental changes to how customized osm2pgsql styles should
be written. The changes are mostly backwards compatible, i.e. custom styles
should still work with the new implementation. The only exception is a
customization of the `process_tags()` function. This function is no longer
considered public and neither are the helper functions used in it.
They currently still work but will be removed at some point. If you have
been making changes to `process_tags`, please review your style and try
to switch to the new convenience functions.
For more information on the changes, see the
[pull request](https://github.com/osm-search/Nominatim/pull/3615)
and read the new
[customization documentation](https://nominatim.org/release-docs/latest/customize/Import-Styles/).
## 4.4.0 -> 4.5.0
### New structure for Python packages
The nominatim Python package has been split into `nominatim-db` and `nominatim-api`.
Any imports need to be adapted accordingly.
If you are running the Python frontend, change the server module from
`nominatim.server.falcon.server` to `nominatim_api.server.falcon.server`.
If you are using the Nominatim library, all imports need to be changed
from `nominatim.api.<module>` to `nominatim_api.<module>`.
If you have written custom tokenizers or sanitizers, the appropriate modules
are now found in `nominatim_db`.
## 4.2.0 -> 4.3.0

View File

@@ -36,11 +36,11 @@ The website is now available at `http://localhost:8765`.
## Forwarding searches to nominatim-ui
Nominatim used to provide the search interface directly by itself when
`format=html` was requested. For all endpoints except for `/reverse` and
`/lookup` this even used to be the default.
`format=html` was requested. For the `/search` endpoint this even used
to be the default.
The following section describes how to set up Apache or nginx, so that your
users are forwarded to nominatim-ui when they go to URL that formerly presented
users are forwarded to nominatim-ui when they go to a URL that formerly presented
the UI.
### Setting up forwarding in Nginx
@@ -73,41 +73,28 @@ map $args $format {
# Determine from the URI and the format parameter above if forwarding is needed.
map $uri/$format $forward_to_ui {
default 1; # The default is to forward.
~^/ui 0; # If the URI point to the UI already, we are done.
~/other$ 0; # An explicit non-html format parameter. No forwarding.
~/reverse.*/default 0; # Reverse and lookup assume xml format when
~/lookup.*/default 0; # no format parameter is given. No forwarding.
default 0; # no forwarding by default
~/search.*/default 1; # Use this line only, if search should go to UI by default.
~/reverse.*/html 1; # Forward API calls that UI supports, when
~/status.*/html 1; # format=html is explicitly requested.
~/search.*/html 1;
~/details.*/html 1;
}
```
The `$forward_to_ui` parameter can now be used to conditionally forward the
calls:
```
# When no endpoint is given, default to search.
# Need to add a rewrite so that the rewrite rules below catch it correctly.
rewrite ^/$ /search;
location @php {
# fastcgi stuff..
``` nginx
location / {
if ($forward_to_ui) {
rewrite ^(/[^/]*) https://yourserver.com/ui$1.html redirect;
rewrite ^(/[^/.]*) https://$http_host/ui$1.html redirect;
}
}
location ~ [^/]\.php(/|$) {
# fastcgi stuff..
if ($forward_to_ui) {
rewrite (.*).php https://yourserver.com/ui$1.html redirect;
}
# proxy_pass commands
}
```
!!! warning
Be aware that the rewrite commands are slightly different for URIs with and
without the .php suffix.
Reload nginx and the UI should be available.
### Setting up forwarding in Apache
@@ -159,18 +146,16 @@ directory like this:
RewriteBase "/nominatim/"
# If no endpoint is given, then use search.
RewriteRule ^(/|$) "search.php"
RewriteRule ^(/|$) "search"
# If format-html is explicitly requested, forward to the UI.
RewriteCond %{QUERY_STRING} "format=html"
RewriteRule ^([^/]+)(.php)? ui/$1.html [R,END]
RewriteRule ^([^/.]+) ui/$1.html [R,END]
# If no format parameter is there then forward anything
# but /reverse and /lookup to the UI.
# Optionally: if no format parameter is there then forward /search.
RewriteCond %{QUERY_STRING} "!format="
RewriteCond %{REQUEST_URI} "!/lookup"
RewriteCond %{REQUEST_URI} "!/reverse"
RewriteRule ^([^/]+)(.php)? ui/$1.html [R,END]
RewriteCond %{REQUEST_URI} "/search"
RewriteRule ^([^/.]+) ui/$1.html [R,END]
</Directory>
```

View File

@@ -68,10 +68,10 @@ the update interval no new data has been published yet, it will go to sleep
until the next expected update and only then attempt to download the next batch.
The one-time mode is particularly useful if you want to run updates continuously
but need to schedule other work in between updates. For example, the main
service at osm.org uses it, to regularly recompute postcodes -- a process that
must not be run while updates are in progress. Its update script
looks like this:
but need to schedule other work in between updates. For example, you might
want to regularly recompute postcodes -- a process that
must not be run while updates are in progress. An update script refreshing
postcodes regularly might look like this:
```sh
#!/bin/bash
@@ -109,17 +109,19 @@ Unit=nominatim-updates.service
WantedBy=multi-user.target
```
And then a similar service definition: `/etc/systemd/system/nominatim-updates.service`:
`OnUnitActiveSec` defines how often the individual update command is run.
Then add a service definition for the timer in `/etc/systemd/system/nominatim-updates.service`:
```
[Unit]
Description=Single updates of Nominatim
[Service]
WorkingDirectory=/srv/nominatim
ExecStart=nominatim replication --once
StandardOutput=append:/var/log/nominatim-updates.log
StandardError=append:/var/log/nominatim-updates.error.log
WorkingDirectory=/srv/nominatim-project
ExecStart=/srv/nominatim-venv/bin/nominatim replication --once
StandardOutput=journald
StandardError=inherit
User=nominatim
Group=nominatim
Type=simple
@@ -128,9 +130,9 @@ Type=simple
WantedBy=multi-user.target
```
Replace the `WorkingDirectory` with your project directory. Also adapt user and
group names as required. `OnUnitActiveSec` defines how often the individual
update command is run.
Replace the `WorkingDirectory` with your project directory. `ExecStart` points
to the nominatim binary that was installed in your virtualenv earlier.
Finally, you might need to adapt user and group names as required.
Now activate the service and start the updates:
@@ -140,12 +142,13 @@ sudo systemctl enable nominatim-updates.timer
sudo systemctl start nominatim-updates.timer
```
You can stop future data updates, while allowing any current, in-progress
You can stop future data updates while allowing any current, in-progress
update steps to finish, by running `sudo systemctl stop
nominatim-updates.timer` and waiting until `nominatim-updates.service` isn't
running (`sudo systemctl is-active nominatim-updates.service`). Current output
from the update can be seen like above (`systemctl status
nominatim-updates.service`).
running (`sudo systemctl is-active nominatim-updates.service`).
To check the output from the update process, use journalctl: `journalctl -u
nominatim-updates.service`
#### Catch-up mode
@@ -155,13 +158,13 @@ all changes from the server until the database is up-to-date. The catch-up mode
still respects the parameter `NOMINATIM_REPLICATION_MAX_DIFF`. It downloads and
applies the changes in appropriate batches until all is done.
The catch-up mode is foremost useful to bring the database up to speed after the
The catch-up mode is foremost useful to bring the database up to date after the
initial import. Give that the service usually is not in production at this
point, you can temporarily be a bit more generous with the batch size and
number of threads you use for the updates by running catch-up like this:
```
cd /srv/nominatim
cd /srv/nominatim-project
NOMINATIM_REPLICATION_MAX_DIFF=5000 nominatim replication --catch-up --threads 15
```
@@ -173,13 +176,13 @@ replication catch-up at whatever interval you desire.
When running scheduled updates with catch-up, it is a good idea to choose
a replication source with an update frequency that is an order of magnitude
lower. For example, if you want to update once a day, use an hourly updated
source. This makes sure that you don't miss an entire day of updates when
source. This ensures that you don't miss an entire day of updates when
the source is unexpectedly late to publish its update.
If you want to use the source with the same update frequency (e.g. a daily
updated source with daily updates), use the
continuous update mode. It ensures to re-request the newest update until it
is published.
once mode together with a frequently run systemd script as described above.
It ensures to re-request the newest update until they have been published.
#### Continuous updates
@@ -197,36 +200,3 @@ parameters:
The update application keeps running forever and retrieves and applies
new updates from the server as they are published.
You can run this command as a simple systemd service. Create a service
description like that in `/etc/systemd/system/nominatim-updates.service`:
```
[Unit]
Description=Continuous updates of Nominatim
[Service]
WorkingDirectory=/srv/nominatim
ExecStart=nominatim replication
StandardOutput=append:/var/log/nominatim-updates.log
StandardError=append:/var/log/nominatim-updates.error.log
User=nominatim
Group=nominatim
Type=simple
[Install]
WantedBy=multi-user.target
```
Replace the `WorkingDirectory` with your project directory. Also adapt user
and group names as required.
Now activate the service and start the updates:
```
sudo systemctl daemon-reload
sudo systemctl enable nominatim-updates
sudo systemctl start nominatim-updates
```

View File

@@ -59,13 +59,6 @@ When set, then JSON output will be wrapped in a callback function with
the given name. See [JSONP](https://en.wikipedia.org/wiki/JSONP) for more
information.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| pretty | 0 or 1 | 0 |
`[PHP-only]` Add indentation to the output to make it more human-readable.
### Output details
| Parameter | Value | Default |
@@ -95,10 +88,8 @@ members.
|-----------| ----- | ------- |
| hierarchy | 0 or 1 | 0 |
Include details of places lower in the address hierarchy.
`[Python-only]` will only return properly parented places. These are address
or POI-like places that reuse the address of their parent street or place.
Include details of POIs and address that depend on the place. Only POIs
that use this place to determine their address will be returned.
| Parameter | Value | Default |
|-----------| ----- | ------- |
@@ -114,6 +105,13 @@ grouped by type.
Include geometry of result.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| entrances | 0 or 1 | 0 |
When set to 1, include the tagged entrances in the result.
### Language of results
| Parameter | Value | Default |
@@ -129,7 +127,7 @@ as the ["Accept-Language" HTTP header](https://developer.mozilla.org/en-US/docs/
##### JSON
[https://nominatim.openstreetmap.org/details.php?osmtype=W&osmid=38210407&format=json](https://nominatim.openstreetmap.org/details.php?osmtype=W&osmid=38210407&format=json)
[https://nominatim.openstreetmap.org/details?osmtype=W&osmid=38210407&format=json](https://nominatim.openstreetmap.org/details?osmtype=W&osmid=38210407&format=json)
```json

View File

@@ -49,7 +49,7 @@ Only has an effect for JSON output formats.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| addressdetails | 0 or 1 | 0 |
| addressdetails | 0 or 1 | 1 |
When set to 1, include a breakdown of the address into elements.
The exact content of the address breakdown depends on the output format.
@@ -77,6 +77,12 @@ that is available in the database, e.g. wikipedia link, opening hours.
When set to 1, include a full list of names for the result. These may include
language variants, older names, references and brand.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| entrances | 0 or 1 | 0 |
When set to 1, include the tagged entrances in the result.
### Language of results
@@ -93,7 +99,7 @@ as the ["Accept-Language" HTTP header](https://developer.mozilla.org/en-US/docs/
results when using Nominatim in the browser versus in a command-line tool
like wget or curl. The command-line tools
usually don't send any Accept-Language header, prompting Nominatim
to show results in the local language. Browsers on the contratry always
to show results in the local language. Browsers on the contrary always
send the currently chosen browser language.

View File

@@ -12,7 +12,7 @@ a single place (for reverse) of the following format:
```
{
"place_id": "100149",
"place_id": 100149,
"licence": "Data © OpenStreetMap contributors, ODbL 1.0. https://osm.org/copyright",
"osm_type": "node",
"osm_id": "107775",
@@ -60,6 +60,8 @@ The possible fields are:
* `namedetails` - dictionary with full list of available names including ref etc.
* `geojson`, `svg`, `geotext`, `geokml` - full geometry
(only with the appropriate `polygon_*` parameter)
* `entrances` - array of objects representing tagged entrances for the object, or
null if none are found (only with `entrances=1`)
## JSONv2
@@ -87,6 +89,8 @@ The properties object has the following fields:
* `extratags` - dictionary with additional useful tags like `website` or `maxspeed`
(only with `extratags=1`)
* `namedetails` - dictionary with full list of available names including ref etc.
* `entrances` - array of objects representing tagged entrances for the object, or
null if none are found (only with `entrances=1`)
Use `polygon_geojson` to output the full geometry of the object instead
of the centroid.
@@ -106,8 +110,13 @@ The following feature attributes are implemented:
* `name` - localised name of the place
* `housenumber`, `street`, `locality`, `district`, `postcode`, `city`,
`county`, `state`, `country` -
provided when it can be determined from the address
provided when it can be determined from the address (only with `addressdetails=1`)
* `admin` - list of localised names of administrative boundaries (only with `addressdetails=1`)
* `extra` - dictionary with additional useful tags like `website` or `maxspeed`
(only with `extratags=1`)
* `entrances` - array of objects representing tagged entrances for the object, or
null if none are found (only with `entrances=1`)
Use `polygon_geojson` to output the full geometry of the object instead
of the centroid.
@@ -159,8 +168,8 @@ The place information can be found in the `result` element. The attributes of th
The full address of the result can be found in the content of the
`result` element as a comma-separated list.
Additional information requested with `addressdetails=1`, `extratags=1` and
`namedetails=1` can be found in extra elements.
Additional information requested with `addressdetails=1`, `extratags=1`,
`namedetails=1`, and `entrances=1` can be found in extra elements.
### Search and Lookup
@@ -168,7 +177,7 @@ Additional information requested with `addressdetails=1`, `extratags=1` and
<searchresults timestamp="Sat, 11 Aug 18 11:55:35 +0000"
attribution="Data © OpenStreetMap contributors, ODbL 1.0. https://www.openstreetmap.org/copyright"
querystring="london" polygon="false" exclude_place_ids="100149"
more_url="https://nominatim.openstreetmap.org/search.php?q=london&addressdetails=1&extratags=1&exclude_place_ids=100149&format=xml&accept-language=en-US%2Cen%3Bq%3D0.7%2Cde%3Bq%3D0.3">
more_url="https://nominatim.openstreetmap.org/search?q=london&addressdetails=1&extratags=1&exclude_place_ids=100149&format=xml&accept-language=en-US%2Cen%3Bq%3D0.7%2Cde%3Bq%3D0.3">
<place place_id="100149" osm_type="node" osm_id="107775" place_rank="15" address_rank="15"
boundingbox="51.3473219,51.6673219,-0.2876474,0.0323526" lat="51.5073219" lon="-0.1276474"
display_name="London, Greater London, England, SW1A 2DU, United Kingdom"
@@ -221,9 +230,9 @@ be more than one. The attributes of that element contain:
When `addressdetails=1` is requested, the localised address parts appear
as subelements with the type of the address part.
Additional information requested with `extratags=1` and `namedetails=1` can
be found in extra elements as sub-element of `extratags` and `namedetails`
respectively.
Additional information requested with `extratags=1`, `namedetails=1`, and
`entrances=1` can be found in extra elements as sub-element of `extratags`,
`namedetails`, and `entrances` respectively.
## Notes on field values
@@ -300,3 +309,78 @@ with a designation label. Per default the following labels may appear:
They roughly correspond to the classification of the OpenStreetMap data
according to either the `place` tag or the main key of the object.
### entrances
Entrance details in the xml and json formats return the latitude and longitude
of the entrance, the osm node ID, the [type of
entrance](https://wiki.openstreetmap.org/wiki/Key:entrance), and any extra tags
associated with the entrance node.
* osm_id
* type
* lat
* lon
* extratags
They roughly correspond to the classification of the OpenStreetMap data
according to either the `place` tag or the main key of the object.
#### Example
##### JSON
[https://nominatim.openstreetmap.org/details?osmtype=W&osmid=32619803&entrances=1&format=json](https://nominatim.openstreetmap.org/details?osmtype=W&osmid=32619803&entrances=1&format=json)
```json
{
"place_id": 124325848,
"parent_place_id": 123936289,
"osm_type": "W",
"osm_id": 32619803,
"category": "shop",
"type": "supermarket",
"admin_level": 15,
"localname": "PENNY",
...
"entrances": [
{
"osm_id": 1733488238,
"type": "yes",
"lat": "51.0466704",
"lon": "12.8077106",
"extratags": {
"foot": "yes"
}
},
{
"osm_id": 1733488256,
"type": "main",
"lat": "51.0467197",
"lon": "12.8078448",
"extratags": {
"foot": "yes"
}
},
{
"osm_id": 1733498087,
"type": "exit",
"lat": "51.0467081",
"lon": "12.8078131",
"extratags": {
"foot": "yes"
}
},
{
"osm_id": 7914950851,
"type": "service",
"lat": "51.0468487",
"lon": "12.8075876",
"extratags": {
"access": "delivery"
}
}
]
}
```

View File

@@ -1,14 +1,3 @@
### Nominatim API
!!! Attention
The current version of Nominatim implements two different search frontends:
the old PHP frontend and the new Python frontend. They have a very similar
API but differ in some implementation details. These are marked in the
documentation as `[Python-only]` or `[PHP-only]`.
`https://nominatim.openstreetmap.org` implements the **Python frontend**.
So users should refer to the **`[Python-only]`** comments.
This section describes the API V1 of the Nominatim web service. The
service offers the following endpoints:

View File

@@ -32,10 +32,9 @@ projection. The API returns exactly one result or an error when the coordinate
is in an area with no OSM data coverage.
!!! danger "Deprecation warning"
The reverse API used to allow address lookup for a single OSM object by
its OSM id for `[PHP-only]`. The use is considered deprecated.
Use the [Address Lookup API](Lookup.md) instead.
!!! tip
The reverse API allows a lookup of object by coordinate. If you want
to look up an object by ID, use the [Address Lookup API](Lookup.md) instead.
!!! danger "Deprecation warning"
The API can also be used with the URL
@@ -99,6 +98,12 @@ that is available in the database, e.g. wikipedia link, opening hours.
When set to 1, include a full list of names for the result. These may include
language variants, older names, references and brand.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| entrances | 0 or 1 | 0 |
When set to 1, include the tagged entrances in the result.
### Language of results
@@ -115,7 +120,7 @@ as the ["Accept-Language" HTTP header](https://developer.mozilla.org/en-US/docs/
results when using Nominatim in the browser versus in a command-line tool
like wget or curl. The command-line tools
usually don't send any Accept-Language header, prompting Nominatim
to show results in the local language. Browsers on the contratry always
to show results in the local language. Browsers on the contrary always
send the currently chosen browser language.
@@ -147,7 +152,7 @@ In terms of address details the zoom levels are as follows:
| Parameter | Value | Default |
|-----------| ----- | ------- |
| layer | comma-separated list of: `address`, `poi`, `railway`, `natural`, `manmade` | _unset_ (no restriction) |
| layer | comma-separated list of: `address`, `poi`, `railway`, `natural`, `manmade` | `address,poi` |
The layer filter allows to select places by themes.
@@ -163,7 +168,7 @@ The `railway` layer includes railway infrastructure like tracks.
Note that in Nominatim's standard configuration, only very few railway
features are imported into the database.
The `natural` layer collects feautures like rivers, lakes and mountains while
The `natural` layer collects features like rivers, lakes and mountains while
the `manmade` layer functions as a catch-all for features not covered by the
other layers.
@@ -213,7 +218,7 @@ This overrides the specified machine readable format.
## Examples
* [https://nominatim.openstreetmap.org/reverse?format=xml&lat=52.5487429714954&lon=-1.81602098644987&zoom=18&addressdetails=1](https://nominatim.openstreetmap.org/reverse?format=xml&lat=52.5487429714954&lon=-1.81602098644987&zoom=18&addressdetails=1)
* [https://nominatim.openstreetmap.org/reverse?format=xml&lat=52.5487429714954&lon=-1.81602098644987&zoom=18&addressdetails=1&layer=address](https://nominatim.openstreetmap.org/reverse?format=xml&lat=52.5487429714954&lon=-1.81602098644987&zoom=18&addressdetails=1&layer=address)
```xml
<reversegeocode timestamp="Fri, 06 Nov 09 16:33:54 +0000" querystring="...">
@@ -236,7 +241,7 @@ This overrides the specified machine readable format.
##### Example with `format=jsonv2`
* [https://nominatim.openstreetmap.org/reverse?format=jsonv2&lat=-34.44076&lon=-58.70521](https://nominatim.openstreetmap.org/reverse?format=jsonv2&lat=-34.44076&lon=-58.70521)
* [https://nominatim.openstreetmap.org/reverse?format=jsonv2&lat=-34.44076&lon=-58.70521&layer=address](https://nominatim.openstreetmap.org/reverse?format=jsonv2&lat=-34.44076&lon=-58.70521&layer=address)
```json
{
@@ -268,7 +273,7 @@ This overrides the specified machine readable format.
##### Example with `format=geojson`
* [https://nominatim.openstreetmap.org/reverse?format=geojson&lat=44.50155&lon=11.33989](https://nominatim.openstreetmap.org/reverse?format=geojson&lat=44.50155&lon=11.33989)
* [https://nominatim.openstreetmap.org/reverse?format=geojson&lat=44.50155&lon=11.33989&layer=address](https://nominatim.openstreetmap.org/reverse?format=geojson&lat=44.50155&lon=11.33989&layer=address)
```json
{
@@ -320,7 +325,7 @@ This overrides the specified machine readable format.
##### Example with `format=geocodejson`
[https://nominatim.openstreetmap.org/reverse?format=geocodejson&lat=60.2299&lon=11.1663](https://nominatim.openstreetmap.org/reverse?format=geocodejson&lat=60.2299&lon=11.1663)
[https://nominatim.openstreetmap.org/reverse?format=geocodejson&lat=60.2299&lon=11.1663&layer=address](https://nominatim.openstreetmap.org/reverse?format=geocodejson&lat=60.2299&lon=11.1663&layer=address)
```json
{

View File

@@ -136,6 +136,12 @@ that is available in the database, e.g. wikipedia link, opening hours.
When set to 1, include a full list of names for the result. These may include
language variants, older names, references and brand.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| entrances | 0 or 1 | 0 |
When set to 1, include the tagged entrances in the result.
### Language of results
@@ -152,7 +158,7 @@ as the ["Accept-Language" HTTP header](https://developer.mozilla.org/en-US/docs/
results when using Nominatim in the browser versus in a command-line tool
like wget or curl. The command-line tools
usually don't send any Accept-Language header, prompting Nominatim
to show results in the local language. Browsers on the contratry always
to show results in the local language. Browsers on the contrary always
send the currently chosen browser language.
### Result restriction
@@ -165,7 +171,7 @@ results and thus give a preference to some results over others.
|-----------| ----- | ------- |
| countrycodes | comma-separated list of country codes | _unset_ |
Filer that limits the search results to one or more countries.
Filter that limits the search results to one or more countries.
The country code must be the
[ISO 3166-1alpha2](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) code
of the country, e.g. `gb` for the United Kingdom, `de` for Germany.
@@ -179,7 +185,7 @@ also excluded when the filter is set.
This parameter should not be confused with the 'country' parameter of
the structured query. The 'country' parameter contains a search term
and will be handled with some fuzziness. The `countrycodes` parameter
is a hard filter and as such should be prefered. Having both parameters
is a hard filter and as such should be preferred. Having both parameters
in the same query will work. If the parameters contradict each other,
the search will come up empty.
@@ -201,7 +207,7 @@ The `railway` layer includes railway infrastructure like tracks.
Note that in Nominatim's standard configuration, only very few railway
features are imported into the database.
The `natural` layer collects feautures like rivers, lakes and mountains while
The `natural` layer collects features like rivers, lakes and mountains while
the `manmade` layer functions as a catch-all for features not covered by the
other layers.
@@ -212,10 +218,10 @@ other layers.
The featureType allows to have a more fine-grained selection for places
from the address layer. Results can be restricted to places that make up
the 'state', 'country' or 'city' part of an address. A featureType of
settlement selects any human inhabited feature from 'state' down to
`settlement` selects any human inhabited feature from 'state' down to
'neighbourhood'.
When featureType ist set, then results are automatically restricted
When featureType is set, then results are automatically restricted
to the address layer (see above).
!!! tip
@@ -225,7 +231,7 @@ to the address layer (see above).
| Parameter | Value | Default |
|-----------| ----- | ------- |
| exclude_place_ids | comma-separeted list of place ids |
| exclude_place_ids | comma-separated list of place ids |
If you do not want certain OSM objects to appear in the search
result, give a comma separated list of the `place_id`s you want to skip.
@@ -246,7 +252,7 @@ box. `x` is longitude, `y` is latitude.
| bounded | 0 or 1 | 0 |
When set to 1, then it turns the 'viewbox' parameter (see above) into
a filter paramter, excluding any results outside the viewbox.
a filter parameter, excluding any results outside the viewbox.
When `bounded=1` is given and the viewbox is small enough, then an amenity-only
search is allowed. Give the special keyword for the amenity in square

View File

@@ -1,7 +0,0 @@
#!/bin/sh
#
# Extract markdown-formatted documentation from a source file
#
# Usage: bash2md.sh <infile> <outfile>
sed '/^#!/d;s:^#\( \|$\)::;s/.*#DOCS://' $1 > $2

View File

@@ -1,95 +1,136 @@
## Configuring the Import
# Configuring the Import of OSM data
In the very first step of a Nominatim import, OSM data is loaded into the
database. Nominatim uses [osm2pgsql](https://osm2pgsql.org) for this task.
It comes with a [flex style](https://osm2pgsql.org/doc/manual.html#the-flex-output)
specifically tailored to filter and convert OSM data into Nominatim's
internal data representation.
There are a number of default configurations for the flex style which
result in geocoding databases of different detail. The
internal data representation. Nominatim ships with a few preset
configurations for this import, each results in a geocoding database of
different detail. The
[Import section](../admin/Import.md#filtering-imported-data) explains
these default configurations in detail.
You can also create your own custom style. Put the style file into your
project directory and then set `NOMINATIM_IMPORT_STYLE` to the name of the file.
It is always recommended to start with one of the standard styles and customize
those. You find the standard styles under the name `import-<stylename>.lua`
in the standard Nominatim configuration path (usually `/etc/nominatim` or
`/usr/local/etc/nominatim`).
If you want to have more control over which OSM data is added to the database,
you can also create your own custom style. Create a new lua style file, put it
into your project directory and then set `NOMINATIM_IMPORT_STYLE` to the name
of the file. Custom style files can be used to modify the existing preset
configurations or to implement your own configuration from scratch.
The remainder of the page describes how the flex style works and how to
customize it.
### The `flex-base.lua` module
## The `flex-base` lua module
The core of Nominatim's flex import configuration is the `flex-base` module.
It defines the table layout used by Nominatim and provides standard
implementations for the import callbacks that make it easy to customize
implementations for the import callbacks that help with customizing
how OSM tags are used by Nominatim.
Every custom style should include this module to make sure that the correct
Every custom style must include this module to make sure that the correct
tables are created. Thus start your custom style as follows:
``` lua
local flex = require('flex-base')
```
The following sections explain how the module can be customized.
### Using preset configurations
If you want to start with one of the existing presets, then you can import
its settings using the `load_topic()` function:
### Changing the recognized tags
``` lua
local flex = require('flex-base')
If you just want to change which OSM tags are recognized during import,
then there are a number of convenience functions to set the tag lists used
during the processing.
flex.load_topic('streets')
```
!!! warning
There are no built-in defaults for the tag lists, so all the functions
need to be called from your style script to fully process the data.
Make sure you start from one of the default style and only modify
the data you are interested in. You can also derive your style from an
existing style by importing the appropriate module, e.g.
`local flex = require('import-street')`.
The `load_topic` function takes an optional second configuration
parameter. The available options are explained in the
[themepark section](#using-osm2pgsql-themepark).
Many of the following functions take _key match lists_. These lists can
Available topics are: `admin`, `street`, `address`, `full`. These topic
correspond to the [import styles](../admin/Import.md#filtering-imported-data)
you can choose during import. To start with the 'extratags' style, use the
`full` topic with the appropriate config parameter:
``` lua
flex.load_topic('full', {with_extratags = true})
```
!!! note
You can also directly import the preset style files, e.g.
`local flex = require('import-street')`. It is not possible to
set extra configuration this way.
### How processing works
When Nominatim processes an OSM object, it looks for four kinds of tags:
The _main tags_ classify what kind of place the OSM object represents. One
OSM object can have more than one main tag. In such case one database entry
is created for each main tag. _Name tags_ represent searchable names of the
place. _Address tags_ are used to compute the address information of the place.
Address tags are used for searching and for creating a display name of the place.
_Extra tags_ are any tags that are not directly related to search but
contain interesting additional information. These are just saved in the database
and may be returned with the result [on request](../api/Search.md#output-details).
!!! danger
Some tags in the extratags category are used by Nominatim to better
classify the place. These tags will always be added, independent of
any settings in the style.
Configuring the style means deciding which key and/or key/value is used
in which category.
## Changing the recognized tags
The flex style offers a number of functions to set the classification of
each OSM tag. Most of these functions can also take a preset string instead
of a tag description. These presets describe common configurations that
are also used in the definition of the predefined styles. This section
lists the configuration functions and the accepted presets.
#### Key match lists
Some of the following functions take _key match lists_. These lists can
contain three kinds of strings to match against tag keys:
A string that ends in an asterisk `*` is a prefix match and accordingly matches
against any key that starts with the given string (minus the `*`).
A suffix match can be defined similarly with a string that starts with a `*`.
Any other string is matched exactly against tag keys.
### Main tags
#### `set_main_tags()` - principal tags
`set/modify_main_tags()` allow to define which tags are used as main tags. It
takes a lua table parameter which defines for keys and key/value
combinations, how they are classified.
If a principal or main tag is found on an OSM object, then the object
is included in Nominatim's search index. A single object may also have
multiple main tags. In that case, the object will be included multiple
times in the index, once for each main tag.
The following classifications are recognized:
The flex script distinguishes between four types of main tags:
| classification | meaning |
| :-------------- | :------ |
| always | Unconditionally use this tag as a main tag. |
| named | Consider as main tag, when the object has a primary name (see [names](#name-tags) below) |
| named_with_key | Consider as main tag, when the object has a primary name with a domain prefix. For example, if the main tag is `bridge=yes`, then it will only be added as an extra entry, if there is a tag `bridge:name[:XXX]` for the same object. If this property is set, all names that are not domain-specific are ignored. |
| fallback | Consider as main tag only when no other main tag was found. Fallback always implies `named`, i.e. fallbacks are only tried for objects with primary names. |
| postcode_area | Tag indicates a postcode area. Copy area into the table of postcodes but only when the object is a relation and has a postcode tagged. |
| delete | Completely ignore the tag in any further processing |
| extra | Move the tag to extratags and then ignore it for further processing |
| `<function>`| Advanced handling, see [below](#advanced-main-tag-handling) |
* __always__: a main tag that is used unconditionally
* __named__: consider this main tag only, if the object has a proper name
(a reference is not enough, see below).
* __named_with_key__: consider this main tag only, when the object has
a proper name with a domain prefix. For example, if the main tag is
`bridge=yes`, then it will only be added as an extra row, if there is
a tag `bridge:name[:XXX]` for the same object. If this property is set,
all other names that are not domain-specific are ignored.
* __fallback__: use this main tag only, if there is no other main tag.
Fallback always implied `named`, i.e. fallbacks are only tried for
named objects.
Each key in the table parameter defines an OSM tag key. The value may
be directly a classification as described above. Then the tag will
be considered a main tag for any possible value that is not further defined.
To further restrict which values are acceptable, give a table with the
permitted values and their kind of main tag. If the table contains a simple
value without key, then this is used as default for values that are not listed.
The `set_main_tags()` function takes exactly one table parameter which
defines the keys and key/value combinations to include and the kind of
main tag. Each lua table key defines an OSM tag key. The value may
be a string defining the kind of main key as described above. Then the tag will
be considered a main tag for any possible value. To further restrict
which values are acceptable, give a table with the permitted values
and their kind of main tag. If the table contains a simple value without
key, then this is used as default for values that are not listed.
`set_main_tags()` will completely replace the current main tag configuration
with the new configuration. `modify_main_tags()` will merge the new
configuration with the existing one. Merging is done at value level.
For example, when the current setting is `highway = {'always', primary = 'named'}`,
then `set_main_tags{highway = 'delete'}` will result in a rule
`highway = {'delete', primary = 'named'}`.
!!! example
``` lua
@@ -97,28 +138,145 @@ key, then this is used as default for values that are not listed.
flex.set_main_tags{
boundary = {administrative = 'named'},
highway = {'always', street_lamp = 'named'},
highway = {'always', street_lamp = 'named', no = 'delete'},
landuse = 'fallback'
}
```
In this example an object with a `boundary` tag will only be included
when it has a value of `administrative`. Objects with `highway` tags are
always included. However when the value is `street_lamp` then the object
must have a name, too. With any other value, the object is included
independently of the name. Finally, if a `landuse` tag is present then
it will be used independely of the concrete value if neither boundary
nor highway tags were found and the object is named.
always included with two exceptions: the troll tag `highway=no` is
deleted on the spot. And when the value is `street_lamp` then the object
must also have a name, to be included. Finally, if a `landuse` tag is
present then it will be used independently of the concrete value when
neither boundary nor highway tags were found and the object is named.
##### Presets
| Name | Description |
| :----- | :---------- |
| admin | Basic tag set collecting places and administrative boundaries. This set is needed also to ensure proper address computation and should therefore always be present. You can disable selected place types like `place=locality` after adding this set, if they are not relevant for your use case. |
| all_boundaries | Extends the set of recognized boundaries and places to all available ones. |
| natural | Tags for natural features like rivers and mountain peaks. |
| street/default | Tags for streets. Major streets are always included, minor ones only when they have a name. |
| street/car | Tags for all streets that can be used by a motor vehicle. |
| street/all | Includes all highway features named and unnamed. |
| poi/delete | Adds most POI features with and without name. Some frequent but very domain-specific values are excluded by deleting them. |
| poi/extra | Like 'poi/delete' but excluded values are moved to extratags. |
#### `set_prefilters()` - ignoring tags
##### Advanced main tag handling
Pre-filtering of tags allows to ignore them for any further processing.
Thus pre-filtering takes precedence over any other tag processing. This is
useful when some specific key/value combinations need to be excluded from
processing. When tags are filtered, they may either be deleted completely
or moved to `extratags`. Extra tags are saved with the object and returned
to the user when requested, but are not used otherwise.
The groups described above are in fact only a preset for a filtering function
that is used to make the final decision how a pre-selected main tag is entered
into Nominatim's internal table. To further customize handling you may also
supply your own filtering function.
The function takes up to three parameters: a Place object of the object
being processed, the key of the main tag and the value of the main tag.
The function may return one of three values:
* `nil` or `false` causes the entry to be ignored
* the Place object causes the place to be added as is
* `Place.copy(names=..., address=..., extratags=...) causes the
place to be enter into the database but with name/address/extratags
set to the given different values.
The Place object has some read-only values that can be used to determine
the handling:
* **object** is the original OSM object data handed in by osm2pgsql
* **admin_level** is the content of the admin_level tag, parsed into an integer and normalized to a value between 0 and 15
* **has_name** is a boolean indicating if the object has a primary name tag
* **names** is a table with the collected list of name tags
* **address** is a table with the collected list of address tags
* **extratags** is a table with the collected list of additional tags to save
!!! example
``` lua
local flex = require('flex-base')
flex.add_topic('street')
local function no_sidewalks(place, k, v)
if place.object.tags.footway == 'sidewalk' then
return false
end
-- default behaviour is to have all footways
return place
end
flex.modify_main_tags(highway = {'footway' = no_sidewalks}
```
This script adds a custom handler for `highway=footway`. It only includes
them in the database, when the object doesn't have a tag `footway=sidewalk`
indicating that it is just part of a larger street which should already
be indexed. Note that it is not necessary to check the key and value
of the main tag because the function is only used for the specific
main tag.
### Ignored tags
The function `ignore_keys()` sets the `delete` classification for keys.
This function takes a _key match list_ so that it is possible to exclude
groups of keys.
Note that full matches always take precedence over suffix matches, which
in turn take precedence over prefix matches.
!!! example
``` lua
local flex = require('flex-base')
flex.add_topic('admin')
flex.ignore_keys{'old_name', 'old_name:*'}
```
This example uses the `admin` preset with the exception that names
that are no longer are in current use, are ignored.
##### Presets
| Name | Description |
| :----- | :---------- |
| metatags | Tags with meta information about the OSM tag like source, notes and import sources. |
| name | Non-names that actually describe properties or name parts. These names can throw off search and should always be removed. |
| address | Extra `addr:*` tags that are not useful for Nominatim. |
### Tags for `extratags`
The function `add_for_extratags()` sets the `extra` classification for keys.
This function takes a
_key match list_ so that it is possible to move groups of keys to extratags.
Note that full matches always take precedence over suffix matches, which
in turn take precedence over prefix matches.
!!! example
``` lua
local flex = require('flex-base')
flex.add_topic('street')
flex.add_for_extratags{'surface', 'access', 'vehicle', 'maxspeed'}
```
This example uses the `street` preset but adds a couple of tags that
are of interest about the condition of the street.
##### Presets
Accepts all [presets from ignored tags](#presets_1).
### General pre-filtering
_(deprecated)_ `set_prefilters()` allows to set the `delete` and `extra`
classification for main tags.
This function removes all previously set main tags with `delete` and `extra`
classification and then adds the newly defined tags.
`set_prefilters()` takes a table with four optional fields:
@@ -130,47 +288,34 @@ to the user when requested, but are not used otherwise.
* __extra_tags__ contains a table of tag keys pointing to a list of tag
values. Tags with matching key/value pairs are moved to extratags.
Key list may contain three kinds of strings:
A string that ends in an asterisk `*` is a prefix match and accordingly matches
against any key that starts with the given string (minus the `*`).
A suffix match can be defined similarly with a string that starts with a `*`.
Any other string is matched exactly against tag keys.
!!! danger "Deprecation warning"
Use of this function should be replaced with `modify_main_tags()` to
set the data from `delete_tags` and `extra_tags`, with `ignore_keys()`
for the `delete_keys` parameter and with `add_for_extratags()` for the
`extra_keys` parameter.
!!! example
``` lua
local flex = require('import-full')
### Name tags
flex.set_prefilters{
delete_keys = {'source', 'source:*'},
extra_tags = {amenity = {'yes', 'no'}}
}
flex.set_main_tags{
amenity = 'always'
}
```
`set/modify_name_tags()` allow to define the tags used for naming places. Name tags
can only be selected by their keys. The import script distinguishes
between primary and auxiliary names. A primary name is the given name of
a place. Having a primary name makes a place _named_. This is important
for main tags that are only included when a name is present. Auxiliary names
are identifiers like references. They may be searched for but should not
be included on their own.
In this example any tags `source` and tags that begin with `source:` are
deleted before any other processing is done. Getting rid of frequent tags
this way can speed up the import.
The functions take a table with two optional fields `main` and `extra`.
They take _key match lists_ for primary and auxiliary names respectively.
A third field `house` can contain tags for names that appear in place of
house numbers in addresses. This field can only contain complete key names.
'house tags' are special in that they cause the OSM object to be added to
the database independently of the presence of other main tags.
Tags with `amenity=yes` or `amenity=no` are moved to extratags. Later
all tags with an `amenity` key are made a main tag. This effectively means
that Nominatim will use all amenity tags except for those with value
yes and no.
#### `set_name_tags()` - defining names
The flex script distinguishes between two kinds of names:
* __main__: the primary names make an object fully searchable.
Main tags of type _named_ will only cause the object to be included when
such a primary name is present. Primary names are usually those found
in the `name` tag and its variants.
* __extra__: extra names are still added to the search index but they are
alone not sufficient to make an object named.
`set_name_tags()` takes a table with two optional fields `main` and `extra`.
They take _key match lists_ for main and extra names respectively.
`set_name_tags()` overwrites the current configuration, while
`modify_name_tags()` replaces the fields that are given. (Be aware that
the fields are replaced as a whole. `main = {'foo_name'}` will cause
`foo_name` to become the only recognized primary name. Any previously
defined primary names are forgotten.)
!!! example
``` lua
@@ -186,29 +331,33 @@ They take _key match lists_ for main and extra names respectively.
only include those that have a common name and not those which just
have some reference ID from the city.
#### `set_address_tags()` - defining address parts
##### Presets
Address tags will be used to build up the address of an object.
| Name | Description |
| :----- | :---------- |
| core | Basic set of recognized names for all places. |
| address | Additional names useful when indexing full addresses. |
| poi | Extended set of recognized names for pois. Use on top of the core set. |
`set_address_tags()` takes a table with arbitrary fields pointing to
_key match lists_. To fields have a special meaning:
### Address tags
* __main__: defines
the tags that make a full address object out of the OSM object. This
is usually the housenumber or variants thereof. If a main address tag
appears, then the object will always be included, if necessary with a
fallback of `place=house`. If the key has a prefix of `addr:` or `is_in:`
this will be stripped.
`set/modify_address_tags()` defines the tags that will be used to build
up the address of an object. Address tags can only be chosen by their key.
* __extra__: defines all supplementary tags for addresses, tags like `addr:street`, `addr:city` etc. If the key has a prefix of `addr:` or `is_in:` this will be stripped.
The functions take a table with arbitrary fields, each defining
a key list or _key match list_. Some fields have a special meaning:
All other fields will be handled as summary fields. If a key matches the
key match list, then its value will be added to the address tags with the
name of the field as key. If multiple tags match, then an arbitrary one
wins.
| Field | Type | Description |
| :---------| :-------- | :-----------|
| main | key list | Tags that make a full address object out of the OSM object. This is usually the house number or variants thereof. If a main address tag appears, then the object will always be included, if necessary with a fallback of `place=house`. If the key has a prefix of `addr:` or `is_in:` this will be stripped. |
| extra | key match list | Supplementary tags for addresses, tags like `addr:street`, `addr:city` etc. If the key has a prefix of `addr:` or `is_in:` this will be stripped. |
| interpolation | key list | Tags that identify address interpolation lines. |
| country | key match list | Tags that may contain the country the place is in. The first found value with a two-letter code will be accepted, all other values are discarded. |
| _other_ | key match list | Summary field. If a key matches the key match list, then its value will be added to the address tags with the name of the field as key. If multiple tags match, then an arbitrary one wins. |
Country tags are handled slightly special. Only tags with a two-letter code
are accepted, all other values are discarded.
`set_address_tags()` overwrites the current configuration, while
`modify_address_tags()` replaces the fields that are given. (Be aware that
the fields are replaced as a whole.)
!!! example
``` lua
@@ -218,7 +367,7 @@ are accepted, all other values are discarded.
main = {'addr:housenumber'},
extra = {'addr:*'},
postcode = {'postal_code', 'postcode', 'addr:postcode'},
country = {'country-code', 'ISO3166-1'}
country = {'country_code', 'ISO3166-1'}
}
```
@@ -227,26 +376,38 @@ are accepted, all other values are discarded.
object will fall back to be entered as a `place=house` in the database
unless there is another interested main tag to be found.
Tags with keys `country-code` and `ISO3166-1` are saved with their
Tags with keys `country_code` and `ISO3166-1` are saved with their
value under `country` in the address tag list. The same thing happens
to postcodes, they will always be saved under the key `postcode` thus
normalizing the multitude of keys that are used in the OSM database.
##### Presets
#### `set_unused_handling()` - processing remaining tags
| Name | Description |
| :----- | :---------- |
| core | Basic set of tags needed to recognize address relationship for any place. Always include this. |
| houses | Additional set of tags needed to recognize proper addresses |
This function defines what to do with tags that remain after all tags
### Handling of unclassified tags
`set_unused_handling()` defines what to do with tags that remain after all tags
have been classified using the functions above. There are two ways in
which the function can be used:
`set_unused_handling(delete_keys = ..., delete_tags = ...)` deletes all
keys that match the descriptions in the parameters and moves all remaining
tags into the extratags list.
`set_unused_handling(extra_keys = ..., extra_tags = ...)` moves all tags
matching the parameters into the extratags list and then deletes the remaining
tags. For the format of the parameters see the description in `set_prefilters()`
above.
When no special handling is set, then unused tags will be discarded with one
exception: place tags are kept in extratags for administrative boundaries.
When using a custom setting, you should also make sure that the place tag
is added for extratags.
!!! example
``` lua
local flex = require('import-full')
@@ -263,24 +424,80 @@ above.
already delete the tiger tags with `set_prefilters()` because that
would remove tiger:county before the address tags are processed.
### Customizing osm2pgsql callbacks
## Filling additional tables
Most of the OSM objects are saved in the main `place` table for further
processing. In addition to that, there are some smaller tables that save
specialised information. The content of these tables can be customized as
well.
### Entrance table
The table `place_entrance` saves information about OSM nodes that represent
an entrance. This data is later mingled with buildings and other areas and
can be returned [on request](../api/Search.md#output-details). The table
saves the type of entrance as well as a set of custom extra tags.
The function `set_entrance_filter()` can be used to customize the table's
content.
When called without any parameter, then filling the entrance table will be
disabled. When called with a preset name, the appropriate preset will be
applied.
To create a custom configuration, call the function
with a table with the following fields:
* __main_tags__ is a list of tags that mark an entrance node. The value of the
first tag found in the list will be used as the entrance type.
* __extra_include__ is an optional list of tags to be added to the extratags
for this entrance. When left out, all tags except for the ones defined
in 'main_tags' will be included. To disable saving of extra tags, set
this to the empty list.
* __extra_exclude__ defines an optional list of tags to drop before including
the remaining tags as extratags. Note that the tags defined in 'main_tags'
will always be excluded, independently of this setting.
To have even more fine-grained control over the output, you can also hand
in a callback for processing entrance information. The callback function
receives a single parameter, the
[osm2pgsql object](https://osm2pgsql.org/doc/manual.html#processing-callbacks).
This object itself must not be modified. The callback should return either
`nil` when the object is not an entrance. Or it returns a table with a
mandatory `entrance` field containing a string with the type of entrance
and an optional `extratags` field with a simple key-value table of extra
information.
##### Presets
| Name | Description |
| :----- | :---------- |
| default | Standard configuration used with `full` and `extratags` styles. |
## Customizing osm2pgsql callbacks
osm2pgsql expects the flex style to implement three callbacks, one process
function per OSM type. If you want to implement special handling for
certain OSM types, you can override the default implementations provided
by the flex-base module.
#### Changing the relation types to be handled
### Enabling additional relation types
The default scripts only allows relations of type `multipolygon`, `boundary`
and `waterway`. To add other types relations, set `RELATION_TYPES` for
OSM relations can represent very diverse
[types of real-world objects](https://wiki.openstreetmap.org/wiki/Key:type). To
be able to process them correctly, Nominatim needs to understand how to
create a geometry for each type. By default, the script knows how to
process relations of type `multipolygon`, `boundary` and `waterway`. All
other relation types are ignored.
To add other types relations, set `RELATION_TYPES` for
the type to the kind of geometry that should be created. The following
kinds of geometries can be used:
* __relation_as_multipolygon__ creates a (Multi)Polygon from the ways in
the relation. If the ways do not form a valid area, then the object is
silently discarded.
* __relation_as_multiline__ creates a (Mutli)LineString from the ways in
* __relation_as_multiline__ creates a (Multi)LineString from the ways in
the relations. Ways are combined as much as possible without any regards
to their order in the relation.
@@ -297,7 +514,7 @@ kinds of geometries can be used:
geometry.
#### Adding additional logic to processing functions
### Adding additional logic to processing functions
The default processing functions are also exported by the flex-base module
as `process_node`, `process_way` and `process_relation`. These can be used
@@ -322,122 +539,85 @@ logic.
### Customizing the main processing function
The main processing function of the flex style can be found in the function
`process_tags`. This function is called for all OSM object kinds and is
responsible for filtering the tags and writing out the rows into Postgresql.
!!! danger "Deprecation Warning"
The style used to allow overwriting the internal processing function
`process_tags()`. While this is currently still possible, it is no longer
encouraged and may stop working in future versions. The internal
`Place` class should now be considered read-only.
## Using osm2pgsql-themepark
The Nominatim osm2pgsql style is designed so that it can also be used as
a theme for [osm2pgsql-themepark](https://osm2pgsql.org/themepark/). This
makes it easy to combine Nominatim with other projects like
[openstreetmap-carto](https://github.com/gravitystorm/openstreetmap-carto)
in the same database.
To set up one of the preset styles, simply include a topic with the same name:
```
local themepark = require('themepark')
themepark:add_topic('nominatim/address')
```
Themepark topics offer two configuration options:
* **street_theme** allows to choose one of the sub topics for streets:
* _default_ - include all major streets and named minor paths
* _car_ - include all streets physically usable by cars
* _all_ - include all major streets and minor paths
* **with_extratags**, when set to a truthy value, then tags that are
not specifically used for address or naming are added to the
extratags column
The customization functions described in the
[Changing recognized tags](#changing-the-recognized-tags) section
are available from the theme. To access the theme you need to explicitly initialize it.
!!! Example
``` lua
local flex = require('import-full')
local themepark = require('themepark')
local original_process_tags = flex.process_tags
themepark:add_topic('nominatim/full', {with_extratags = true})
function flex.process_tags(o)
if o.object.tags.highway ~= nil and o.object.tags.access == 'no' then
return
end
local flex = themepark:init_theme('nominatim')
original_process_tags(o)
end
flex.modify_main_tags{'amenity' = {
'waste_basket' = 'delete'}
}
```
This example uses the full Nominatim configuration but disables
importing waste baskets.
This example shows the most simple customization of the process_tags function.
It simply adds some additional processing before running the original code.
To do that, first save the original function and then overwrite process_tags
from the module. In this example all highways which are not accessible
by anyone will be ignored.
You may also write a new configuration from scratch. Simply omit including
a Nominatim topic and only call the required customization functions.
Customizing the osm2pgsql processing functions as explained
[above](#adding-additional-logic-to-processing-functions) is not possible
when running under themepark. Instead include other topics that make the
necessary modifications or add an additional processor before including
the Nominatim topic.
#### The `Place` class
!!! Example
``` lua
local themepark = require('themepark')
The `process_tags` function receives a Lua object of `Place` type which comes
with some handy functions to collect the data necessary for geocoding and
writing it into the place table. Always use this object to fill the table.
local function discard_country_boundaries(object)
if object.tags.boundary == 'administrative' and object.tags.admin_level == '2' then
return 'stop'
end
end
The Place class has some attributes which you may access read-only:
themepark:add_proc('relation', discard_country_boundaries)
-- Order matters here. The topic needs to be added after the custom callback.
themepark:add_topic('nominatim/full', {with_extratags = true})
```
Discarding country-level boundaries when running under themepark.
* __object__ is the original OSM object data handed in by osm2pgsql
* __admin_level__ is the content of the admin_level tag, parsed into an
integer and normalized to a value between 0 and 15
* __has_name__ is a boolean indicating if the object has a full name
* __names__ is a table with the collected list of name tags
* __address__ is a table with the collected list of address tags
* __extratags__ is a table with the collected list of additional tags to save
## Changing the style of existing databases
There are a number of functions to fill these fields. All functions expect
a table parameter with fields as indicated in the description.
Many of these functions expect match functions which are described in detail
further below.
* __delete{match=...}__ removes all tags that match the match function given
in _match_.
* __grab_extratags{match=...}__ moves all tags that match the match function
given in _match_ into extratags. Returns the number of tags moved.
* __clean{delete=..., extra=...}__ deletes all tags that match _delete_ and
moves the ones that match _extra_ into extratags
* __grab_address_parts{groups=...}__ moves matching tags into the address table.
_groups_ must be a group match function. Tags of the group `main` and
`extra` are added to the address table as is but with `addr:` and `is_in:`
prefixes removed from the tag key. All other groups are added with the
group name as key and the value from the tag. Multiple values of the same
group overwrite each other. The function returns the number of tags saved
from the main group.
* __grab_main_parts{groups=...}__ moves matching tags into the name table.
_groups_ must be a group match function. If a tags of the group `main` is
present, the object will be marked as having a name. Tags of group `house`
produce a fallback to `place=house`. This fallback is return by the function
if present.
There are two functions to write a row into the place table. Both functions
expect the main tag (key and value) for the row and then use the collected
information from the name, address, extratags etc. fields to complete the row.
They also have a boolean parameter `save_extra_mains` which defines how any
unprocessed tags are handled: when True, the tags will be saved as extratags,
when False, they will be simply discarded.
* __write_row(key, value, save_extra_mains)__ creates a new table row from
the current state of the Place object.
* __write_place(key, value, mtype, save_extra_mains)__ creates a new row
conditionally. When value is nil, the function will attempt to look up the
value in the object tags. If value is still nil or mtype is nil, the row
is ignored. An mtype of `always` will then always write out the row,
a mtype of `named` only, when the object has a full name. When mtype
is `named_with_key`, the function checks for a domain name, i.e. a name
tag prefixed with the name of the main key. Only if at least one is found,
the row will be written. The names are replaced with the domain names found.
#### Match functions
The Place functions usually expect either a _match function_ or a
_group match function_ to find the tags to apply their function to.
The __match function__ is a Lua function which takes two parameters,
key and value, and returns a boolean to indicate that a tag matches. The
flex-base module has a convenience function `tag_match()` to create such a
function. It takes a table with two optional fields: `keys` takes a key match
list (see above), `tags` takes a table with keys that point to a list of
possible values, thus defining key/value matches.
The __group match function__ is a Lua function which also takes two parameters,
key and value, and returns a string indicating to which group or type they
belong to. The `tag_group()` can be used to create such a function. It expects
a table where the group names are the keys and the values are a key match list.
### Using the gazetteer output of osm2pgsql
Nominatim still allows you to configure the gazetteer output to remain
backwards compatible with older imports. It will be automatically used
when the style file name ends in `.style`. For documentation of the
old import style, please refer to the documentation of older releases
of Nominatim. Do not use the gazetteer output for new imports. There is no
guarantee that new versions of Nominatim are fully compatible with the
gazetteer output.
### Changing the Style of Existing Databases
There is normally no issue changing the style of a database that is already
There is usually no issue changing the style of a database that is already
imported and now kept up-to-date with change files. Just be aware that any
change in the style applies to updates only. If you want to change the data
that is already in the database, then a reimport is necessary.

View File

@@ -12,7 +12,7 @@ customize them.
The main value for importance is derived from page ranking values for Wikipedia
pages for a place. For places that do not have their own
Wikipedia page, a formula is used that derives a static importance from the
places [search rank](../customize/Ranking.md#search-rank).
place's [search rank](../customize/Ranking.md#search-rank).
In a second step, a secondary importance value is added which is meant to
represent how well-known the general area is where the place is located. It
@@ -21,7 +21,13 @@ importance values.
nominatim.org has preprocessed importance tables for the
[primary Wikipedia rankings](https://nominatim.org/data/wikimedia-importance.sql.gz)
and for a secondary importance based on the number of tile views on openstreetmap.org.
and for [secondary importance](https://nominatim.org/data/wikimedia-secondary-importance.sql.gz)
based on Wikipedia importance of the administrative areas.
The source code for creating these files is available in the Github projects
[osm-search/wikipedia-wikidata](https://github.com/osm-search/wikipedia-wikidata)
and
[osm-search/secondary-importance](https://github.com/osm-search/secondary-importance).
### Customizing secondary importance
@@ -41,8 +47,8 @@ table will be ignored. You must furthermore create an index as follows:
CREATE INDEX ON secondary_importance USING gist(ST_ConvexHull(gist))
```
The following raster2pgsql command will create a table that conforms to
the requirements:
The following raster2pgsql command will create a table from a tiff file
that conforms to the requirements:
```
raster2pgsql -I -C -Y -d -t 128x128 input.tiff public.secondary_importance

View File

@@ -7,6 +7,8 @@ the following configurable parts:
can be set in your local `.env` configuration
* [Import styles](Import-Styles.md) explains how to write your own import style
in order to control what kind of OSM data will be imported
* [API Result Formatting](Result-Formatting.md) shows how to change the
output of the Nominatim API
* [Place ranking](Ranking.md) describes the configuration around classifing
places in terms of their importance and their role in an address
* [Tokenizers](Tokenizers.md) describes the configuration of the module

View File

@@ -0,0 +1,259 @@
# Changing the Appearance of Results in the Server API
The Nominatim Server API offers a number of formatting options that
present search results in [different output formats](../api/Output.md).
These results only contain a subset of all the information that Nominatim
has about the result. This page explains how to adapt the result output
or add additional result formatting.
## Defining custom result formatting
To change the result output, you need to place a file `api/v1/format.py`
into your project directory. This file needs to define a single variable
`dispatch` containing a [FormatDispatcher](#formatdispatcher). This class
serves to collect the functions for formatting the different result types
and offers helper functions to apply the formatters.
There are two ways to define the `dispatch` variable. If you want to reuse
the default output formatting and just make some changes or add an additional
format type, then import the dispatch object from the default API:
``` python
from nominatim_api.v1.format import dispatch as dispatch
```
If you prefer to define a completely new result output, then you can
create an empty dispatcher object:
``` python
from nominatim_api import FormatDispatcher
dispatch = FormatDispatcher()
```
## The formatting function
The dispatcher organises the formatting functions by format and result type.
The format corresponds to the `format` parameter of the API. It can contain
one of the predefined format names or you can invent your own new format.
API calls return data classes or an array of a data class which represent
the result. You need to make sure there are formatters defined for the
following result types:
* StatusResult (single object, returned by `/status`)
* DetailedResult (single object, returned by `/details`)
* SearchResults (list of objects, returned by `/search`)
* ReverseResults (list of objects, returned by `/reverse` and `/lookup`)
* RawDataList (simple object, returned by `/deletable` and `/polygons`)
A formatter function has the following signature:
``` python
def format_func(result: ResultType, options: Mapping[str, Any]) -> str
```
The options dictionary contains additional information about the original
query. See the [reference below](#options-for-different-result-types)
about the possible options.
To set the result formatter for a certain result type and format, you need
to write the format function and decorate it with the
[`format_func`](#nominatim_api.FormatDispatcher.format_func)
decorator.
For example, let us extend the result for the status call in text format
and add the server URL. Such a formatter would look like this:
``` python
from nominatim_api import StatusResult
@dispatch.format_func(StatusResult, 'text')
def _format_status_text(result, _):
header = 'Status for server nominatim.openstreetmap.org'
if result.status:
return f"{header}\n\nERROR: {result.message}"
return f"{header}\n\nOK"
```
If your dispatcher is derived from the default one, then this definition
will overwrite the original formatter function. This way it is possible
to customize the output of selected results.
## Adding new formats
You may also define a completely different output format. This is as simple
as adding formatting functions for all result types using the custom
format name:
``` python
from nominatim_api import StatusResult
@dispatch.format_func(StatusResult, 'chatty')
def _format_status_text(result, _):
if result.status:
return f"The server is currently not running. {result.message}"
return "Good news! The server is running just fine."
```
That's all. Nominatim will automatically pick up the new format name and
will allow the user to use it. There is no need to implement formatter
functions for all the result types, when you invent a new one. The
available formats will be determined for each API endpoint separately.
To find out which formats are available, you can use the `--list-formats`
option of the CLI tool:
```
me@machine:planet-project$ nominatim status --list-formats
2024-08-16 19:54:00: Using project directory: /home/nominatim/planet-project
text
json
chatty
debug
me@machine:planet-project$
```
The `debug` format listed in the last line will always appear. It is a
special format that enables debug output via the command line (the same
as the `debug=1` parameter enables for the server API). To not clash
with this built-in function, you shouldn't name your own format 'debug'.
### Content type of new formats
All responses will be returned with the content type application/json by
default. If your format produces a different content type, you need
to configure the content type with the `set_content_type()` function.
For example, the 'chatty' format above returns just simple text. So the
content type should be set up as:
``` python
from nominatim_api.server.content_types import CONTENT_TEXT
dispatch.set_content_type('chatty', CONTENT_TEXT)
```
The `content_types` module used above provides constants for the most
frequent content types. You set the content type to an arbitrary string,
if the content type you need is not available.
## Formatting error messages
Any exception thrown during processing of a request is given to
a special error formatting function. It takes the requested content type,
the status code and the error message. It should return the error message
in a form appropriate for the given content type.
You can overwrite the default formatting function with the decorator
`error_format_func`:
``` python
import nominatim_api.server.content_types as ct
@dispatch.error_format_func
def _format_error(content_type: str, msg: str, status: int) -> str:
if content_type == ct.CONTENT_XML:
return f"""<?xml version="1.0" encoding="UTF-8" ?>
<message>{msg}</message>
"""
if content_type == ct.CONTENT_JSON:
return f'"{msg}"'
return f"ERROR: {msg}"
```
## Debugging custom formatters
The easiest way to try out your custom formatter is by using the Nominatim
CLI commands. Custom formats can be chosen with the `--format` parameter:
```
me@machine:planet-project$ nominatim status --format chatty
2024-08-16 19:54:00: Using project directory: /home/nominatim/planet-project
Good news! The server is running just fine.
me@machine:planet-project$
```
They will also emit full error messages when there is a problem with the
code you need to debug.
!!! danger
In some cases, when you make an error with your import statement, the
CLI will not give you an error but instead tell you, that the API
commands are no longer available:
me@machine: nominatim status
usage: nominatim [-h] [--version] {import,freeze,replication,special-phrases,add-data,index,refresh,admin} ...
nominatim: error: argument subcommand: invalid choice: 'status'
This happens because the CLI tool is meant to still work when the
nominatim-api package is not installed. Import errors involving
`nominatim_api` are interpreted as "package not installed".
Use the help command to find out which is the offending import that
could not be found:
me@machine: nominatim -h
... [other help text] ...
Nominatim API package not found (was looking for module: nominatim_api.xxx).
## Reference
### FormatDispatcher
::: nominatim_api.FormatDispatcher
options:
heading_level: 6
group_by_category: False
### JsonWriter
::: nominatim_api.utils.json_writer.JsonWriter
options:
heading_level: 6
group_by_category: False
### Options for different result types
This section lists the options that may be handed in with the different result
types in the v1 version of the Nominatim API.
#### StatusResult
_None._
#### DetailedResult
| Option | Description |
|-----------------|-------------|
| locales | [Locales](../library/Result-Handling.md#locale) object for the requested language(s) |
| group_hierarchy | Setting of [group_hierarchy](../api/Details.md#output-details) parameter |
| icon_base_url | (optional) URL pointing to icons as set in [NOMINATIM_MAPICON_URL](Settings.md#nominatim_mapicon_url) |
#### SearchResults
| Option | Description |
|-----------------|-------------|
| query | Original query string |
| more_url | URL for requesting additional results for the same query |
| exclude_place_ids | List of place IDs already returned |
| viewbox | Setting of [viewbox](../api/Search.md#result-restriction) parameter |
| extratags | Setting of [extratags](../api/Search.md#output-details) parameter |
| namedetails | Setting of [namedetails](../api/Search.md#output-details) parameter |
| addressdetails | Setting of [addressdetails](../api/Search.md#output-details) parameter |
#### ReverseResults
| Option | Description |
|-----------------|-------------|
| query | Original query string |
| extratags | Setting of [extratags](../api/Search.md#output-details) parameter |
| namedetails | Setting of [namedetails](../api/Search.md#output-details) parameter |
| addressdetails | Setting of [addressdetails](../api/Search.md#output-details) parameter |
#### RawDataList
_None._

60
docs/customize/SQLite.md Normal file
View File

@@ -0,0 +1,60 @@
A Nominatim database can be converted into an SQLite database and used as
a read-only source for geocoding queries. This sections describes how to
create and use an SQLite database.
!!! danger
This feature is in an experimental state at the moment. Use at your own
risk.
## Installing prerequisites
To use a SQLite database, you need to install:
* SQLite (>= 3.30)
* Spatialite (> 5.0.0)
* aiosqlite
On Ubuntu/Debian, you can run:
sudo apt install sqlite3 libsqlite3-mod-spatialite libspatialite7
Install the aiosqlite Python package in your virtual environment:
/srv/nominatim-venv/bin/pip install aiosqlite
## Creating a new SQLite database
Nominatim cannot import directly into SQLite database. Instead you have to
first create a geocoding database in PostgreSQL by running a
[regular Nominatim import](../admin/Import.md).
Once this is done, the database can be converted to SQLite with
nominatim convert -o mydb.sqlite
This will create a database where all geocoding functions are available.
Depending on what functions you need, the database can be made smaller:
* `--without-reverse` omits indexes only needed for reverse geocoding
* `--without-search` omit tables and indexes used for forward search
* `--without-details` leaves out extra information only available in the
details API
## Using an SQLite database
Once you have created the database, you can use it by simply pointing the
database DSN to the SQLite file:
NOMINATIM_DATABASE_DSN=sqlite:dbname=mydb.sqlite
Please note that SQLite support is only available for the Python frontend. To
use the test server with an SQLite database, you therefore need to switch
the frontend engine:
nominatim serve --engine falcon
You need to install falcon or starlette for this, depending on which engine
you choose.
The CLI query commands and the library interface already use the new Python
frontend and therefore work right out of the box.

View File

@@ -57,34 +57,13 @@ parameter that is understood by libpq. See the [Postgres documentation](https://
| **After Changes:** | cannot be changed after import |
Defines the name of the database user that will run search queries. Usually
this is the user under which the webserver is executed. When running Nominatim
via php-fpm, you can also define a separate query user. The Postgres user
this is the user under which the webserver is executed. The Postgres user
needs to be set up before starting the import.
Nominatim grants minimal rights to this user to all tables that are needed
for running geocoding queries.
#### NOMINATIM_DATABASE_MODULE_PATH
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Directory where to find the PostgreSQL server module |
| **Format:** | path |
| **Default:** | _empty_ (use `<project_directory>/module`) |
| **After Changes:** | run `nominatim refresh --functions` |
| **Comment:** | Legacy tokenizer only |
Defines the directory in which the PostgreSQL server module `nominatim.so`
is stored. The directory and module must be accessible by the PostgreSQL
server.
For information on how to use this setting when working with external databases,
see [Advanced Installations](../admin/Advanced-Installations.md).
The option is only used by the Legacy tokenizer and ignored otherwise.
#### NOMINATIM_TOKENIZER
| Summary | |
@@ -115,20 +94,6 @@ on the file format.
If a relative path is given, then the file is searched first relative to the
project directory and then in the global settings directory.
#### NOMINATIM_MAX_WORD_FREQUENCY
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Number of occurrences before a word is considered frequent |
| **Format:** | int |
| **Default:** | 50000 |
| **After Changes:** | cannot be changed after import |
| **Comment:** | Legacy tokenizer only |
The word frequency count is used by the Legacy tokenizer to automatically
identify _stop words_. Any partial term that occurs more often then what
is defined in this setting, is effectively ignored during search.
#### NOMINATIM_LIMIT_REINDEXING
@@ -163,25 +128,6 @@ codes, to restrict import to a subset of languages.
Currently only affects the initial import of country names and special phrases.
#### NOMINATIM_TERM_NORMALIZATION
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Rules for normalizing terms for comparisons |
| **Format:** | string: semicolon-separated list of ICU rules |
| **Default:** | :: NFD (); [[:Nonspacing Mark:] [:Cf:]] >; :: lower (); [[:Punctuation:][:Space:]]+ > ' '; :: NFC (); |
| **Comment:** | Legacy tokenizer only |
[Special phrases](Special-Phrases.md) have stricter matching requirements than
normal search terms. They must appear exactly in the query after this term
normalization has been applied.
Only has an effect on the Legacy tokenizer. For the ICU tokenizer the rules
defined in the
[normalization section](Tokenizers.md#normalization-and-transliteration)
will be used.
#### NOMINATIM_USE_US_TIGER_DATA
| Summary | |
@@ -390,7 +336,7 @@ NOMINATIM_TABLESPACE_SEARCH_INDEX
NOMINATIM_TABLESPACE_OSM_DATA
: Raw OSM data cache used for import and updates.
NOMINATIM_TABLESPACE_OSM_DATA
NOMINATIM_TABLESPACE_OSM_INDEX
: Indexes on the raw OSM data cache.
NOMINATIM_TABLESPACE_PLACE_DATA
@@ -544,38 +490,6 @@ the local languages (in OSM: the name tag without any language suffix) is
used.
#### NOMINATIM_SEARCH_BATCH_MODE
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Enable a special batch query mode |
| **Format:** | boolean |
| **Default:** | no |
| **After Changes:** | run `nominatim refresh --website` |
| **Comment:** | PHP frontend only |
This feature is currently undocumented and potentially broken.
#### NOMINATIM_SEARCH_NAME_ONLY_THRESHOLD
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Threshold for switching the search index lookup strategy |
| **Format:** | integer |
| **Default:** | 500 |
| **After Changes:** | run `nominatim refresh --website` |
| **Comment:** | PHP frontend only |
This setting defines the threshold over which a name is no longer considered
as rare. When searching for places with rare names, only the name is used
for place lookups. Otherwise the name and any address information is used.
This setting only has an effect after `nominatim refresh --word-counts` has
been called to compute the word frequencies.
#### NOMINATIM_LOOKUP_MAX_COUNT
| Summary | |
@@ -616,7 +530,6 @@ Setting this parameter to 0 disables polygon output completely.
| **Format:** | boolean |
| **Default:** | no |
| **After Changes:** | run `nominatim refresh --website` |
| **Comment:** | PHP frontend only |
Enable to search elements just within countries.
@@ -689,25 +602,44 @@ results gathered so far.
Note that under high load you may observe that users receive different results
than usual without seeing an error. This may cause some confusion.
### Logging Settings
#### NOMINATIM_LOG_DB
#### NOMINATIM_OUTPUT_NAMES
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Log requests into the database |
| **Format:** | boolean |
| **Default:** | no |
| **After Changes:** | run `nominatim refresh --website` |
| **Description:** | Specifies order of name tags |
| **Format:** | string: comma-separated list of tag names |
| **Default:** | name:XX,name,brand,official_name:XX,short_name:XX,official_name,short_name,ref |
Enable logging requests into a database table with this setting. The logs
can be found in the table `new_query_log`.
Specifies the order in which different name tags are used.
The values in this list determine the preferred order of name variants,
including language-specific names (in OSM: the name tag with and without any language suffix).
When using this logging method, it is advisable to set up a job that
regularly clears out old logging information. Nominatim will not do that
on its own.
Comma-separated list, where :XX stands for language suffix
(e.g. name:en) and no :XX stands for general tags (e.g. name).
Can be used as the same time as NOMINATIM_LOG_FILE.
See also [NOMINATIM_DEFAULT_LANGUAGE](#nominatim_default_language).
!!! note
If NOMINATIM_OUTPUT_NAMES = `name:XX,name,short_name:XX,short_name` the search follows
```
'name', 'short_name'
```
if we have no preferred language order for showing search results.
For languages ['en', 'es'] the search follows
```
'name:en', 'name:es',
'name',
'short_name:en', 'short_name:es',
'short_name'
```
For those familiar with the internal implementation, the `_place_*` expansion is added, but to simplify, it is not included in this example.
### Logging Settings
#### NOMINATIM_LOG_FILE
@@ -716,22 +648,53 @@ Can be used as the same time as NOMINATIM_LOG_FILE.
| **Description:** | Log requests into a file |
| **Format:** | path |
| **Default:** | _empty_ (logging disabled) |
| **After Changes:** | run `nominatim refresh --website` |
Enable logging of requests into a file with this setting by setting the log
file where to log to. A relative file name is assumed to be relative to
the project directory.
the project directory. The format of the log output can be set
with NOMINATIM_LOG_FORMAT.
#### NOMINATIM_LOG_FORMAT
The entries in the log file have the following format:
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Log requests into a file |
| **Format:** | [Python String Format](https://docs.python.org/3/library/string.html#formatstrings) string |
| **Default:** | `[{start}] {total_time:.4f} {results_total} {endpoint} "{query_string}"` |
<request time> <execution time in s> <number of results> <type> "<query string>"
Describes the content of a log line for a single request. The format
must be readable by Python's format function. Nominatim provides a number
of metrics than can be logged. The default set of metrics is the following:
Request time is the time when the request was started. The execution time is
given in seconds and corresponds to the time the query took executing in PHP.
type contains the name of the endpoint used.
/// html | div.simple-table
| name | type | Description |
| --------------- | ------ | ------------|
| start | time | Point in time when the request arrived. |
| end | time | Point in time when the request was done. |
| query_start | time | Point in time when processing started. |
| total_time | float | Total time in seconds to handle the request. |
| wait_time | float | Time in seconds the request waited for a database connection to be available. |
| query_time | float | Total time in seconds to process the request once a connection was available. |
| results_total | int | Number of results found. |
| endpoint | string | API endpoint used. |
| query_string | string | Raw query string received. |
///
Variables of type 'time' contain a UTC timestamp string in ISO format.
Nominatim also exposes additional metrics to help with development. These
are subject to change between versions:
/// html | div.simple-table
| name | type | Description |
| ------------------------- | ------ | ------------|
| search_rounds | int | Total number of searches executed for the request. |
| search_min_penalty | float | Minimal possible penalty for the request. |
| search_first_result_round | int | Number of first search to yield any result. |
| search_min_result_penalty | float | Minimal penalty by a result found. |
| search_best_penalty_round | int | Search round that yielded the best penalty result. |
///
Can be used as the same time as NOMINATIM_LOG_DB.
#### NOMINATIM_DEBUG_SQL

View File

@@ -11,16 +11,31 @@ nominatim special-phrases --import-from-wiki
## Importing custom special phrases
But, it is also possible to import some phrases from a csv file.
To do so, you have access to the following command:
Special phrases may also be imported from any custom CSV file. The file needs
to have a header line, use comma as delimiter and define the following
columns:
* **phrase**: the keyword to look for
* **class**: key of the main tag of the place to find
(see [Import styles](Import-Styles.md#how-processing-works)
* **type**: value of the main tag
* **operator**: type of special phrase, may be one of:
* *in*: place is within the place defined by the search term (e.g. "_Hotels in_ Berlin")
* *near*: place is near the place defined by the search term (e.g. "_bus stops near_ Big Ben")
* *named*: special phrase is a classifier (e.g. "_hotel_ California")
* *-*: unspecified, can be any of the above
If the file contains any other columns, then they are silently ignored
To import the CSV file, use the following command:
```sh
nominatim special-phrases --import-from-csv <csv file>
```
Note that the two previous import commands will update the phrases from your database.
This means that if you import some phrases from a csv file, only the phrases
present in the csv file will be kept into the database. All other phrases will
This means that if you import some phrases from a CSV file, only the phrases
present in the CSV file will be kept in the database. All other phrases will
be removed.
If you want to only add new phrases and not update the other ones you can add
@@ -30,5 +45,5 @@ the argument `--no-replace` to the import command. For example:
nominatim special-phrases --import-from-csv <csv file> --no-replace
```
This will add the phrases present in the csv file into the database without
This will add the phrases present in the CSV file into the database without
removing the other ones.

View File

@@ -4,59 +4,16 @@ The tokenizer module in Nominatim is responsible for analysing the names given
to OSM objects and the terms of an incoming query in order to make sure, they
can be matched appropriately.
Nominatim offers different tokenizer modules, which behave differently and have
different configuration options. This sections describes the tokenizers and how
they can be configured.
Nominatim currently offers only one tokenizer module, the ICU tokenizer. This section
describes the tokenizer and how it can be configured.
!!! important
The use of a tokenizer is tied to a database installation. You need to choose
The selection of tokenizer is tied to a database installation. You need to choose
and configure the tokenizer before starting the initial import. Once the import
is done, you cannot switch to another tokenizer anymore. Reconfiguring the
chosen tokenizer is very limited as well. See the comments in each tokenizer
section.
## Legacy tokenizer
The legacy tokenizer implements the analysis algorithms of older Nominatim
versions. It uses a special Postgresql module to normalize names and queries.
This tokenizer is automatically installed and used when upgrading an older
database. It should not be used for new installations anymore.
### Compiling the PostgreSQL module
The tokeinzer needs a special C module for PostgreSQL which is not compiled
by default. If you need the legacy tokenizer, compile Nominatim as follows:
```
mkdir build
cd build
cmake -DBUILD_MODULE=on
make
```
### Enabling the tokenizer
To enable the tokenizer add the following line to your project configuration:
```
NOMINATIM_TOKENIZER=legacy
```
The Postgresql module for the tokenizer is available in the `module` directory
and also installed with the remainder of the software under
`lib/nominatim/module/nominatim.so`. You can specify a custom location for
the module with
```
NOMINATIM_DATABASE_MODULE_PATH=<path to directory where nominatim.so resides>
```
This is in particular useful when the database runs on a different server.
See [Advanced installations](../admin/Advanced-Installations.md#importing-nominatim-to-an-external-postgresql-database) for details.
There are no other configuration options for the legacy tokenizer. All
normalization functions are hard-coded.
## ICU tokenizer
The ICU tokenizer uses the [ICU library](http://site.icu-project.org/) to
@@ -85,10 +42,19 @@ On import the tokenizer processes names in the following three stages:
See the [Token analysis](#token-analysis) section below for more
information.
During query time, only normalization and transliteration are relevant.
An incoming query is first split into name chunks (this usually means splitting
the string at the commas) and the each part is normalised and transliterated.
The result is used to look up places in the search index.
During query time, the tokeinzer is responsible for processing incoming
queries. This happens in two stages:
1. During **query preprocessing** the incoming text is split into name
chunks and normalised. This usually means applying the same normalisation
as during the import process but may involve other processing like,
for example, word break detection.
2. The **token analysis** step breaks down the query parts into tokens,
looks them up in the database and assigns them possible functions and
probabilities.
Query processing can be further customized while the rest of the analysis
is hard-coded.
### Configuration
@@ -100,6 +66,14 @@ have no effect.
Here is an example configuration file:
``` yaml
query-preprocessing:
- step: split_japanese_phrases
- step: regex_replace
replacements:
- pattern: https?://[^\s]* # Filter URLs starting with http or https
replace: ''
- step: normalize
normalization:
- ":: lower ()"
- "ß > 'ss'" # German szet is unambiguously equal to double ss
@@ -120,8 +94,37 @@ token-analysis:
replacements: ['ä', 'ae']
```
The configuration file contains four sections:
`normalization`, `transliteration`, `sanitizers` and `token-analysis`.
The configuration file contains five sections:
`query-preprocessing`, `normalization`, `transliteration`, `sanitizers` and `token-analysis`.
#### Query preprocessing
The section for `query-preprocessing` defines an ordered list of functions
that are applied to the query before the token analysis.
The following is a list of preprocessors that are shipped with Nominatim.
##### normalize
::: nominatim_api.query_preprocessing.normalize
options:
members: False
heading_level: 6
docstring_section_style: spacy
##### regex-replace
::: nominatim_api.query_preprocessing.regex_replace
options:
members: False
heading_level: 6
docstring_section_style: spacy
description:
This option runs any given regex pattern on the input and replaces values accordingly
replacements:
- pattern: regex pattern
replace: string to replace with
#### Normalization and Transliteration
@@ -175,7 +178,7 @@ The following is a list of sanitizers that are shipped with Nominatim.
##### split-name-list
::: nominatim.tokenizer.sanitizers.split_name_list
::: nominatim_db.tokenizer.sanitizers.split_name_list
options:
members: False
heading_level: 6
@@ -183,7 +186,7 @@ The following is a list of sanitizers that are shipped with Nominatim.
##### strip-brace-terms
::: nominatim.tokenizer.sanitizers.strip_brace_terms
::: nominatim_db.tokenizer.sanitizers.strip_brace_terms
options:
members: False
heading_level: 6
@@ -191,7 +194,7 @@ The following is a list of sanitizers that are shipped with Nominatim.
##### tag-analyzer-by-language
::: nominatim.tokenizer.sanitizers.tag_analyzer_by_language
::: nominatim_db.tokenizer.sanitizers.tag_analyzer_by_language
options:
members: False
heading_level: 6
@@ -199,7 +202,7 @@ The following is a list of sanitizers that are shipped with Nominatim.
##### clean-housenumbers
::: nominatim.tokenizer.sanitizers.clean_housenumbers
::: nominatim_db.tokenizer.sanitizers.clean_housenumbers
options:
members: False
heading_level: 6
@@ -207,7 +210,7 @@ The following is a list of sanitizers that are shipped with Nominatim.
##### clean-postcodes
::: nominatim.tokenizer.sanitizers.clean_postcodes
::: nominatim_db.tokenizer.sanitizers.clean_postcodes
options:
members: False
heading_level: 6
@@ -215,7 +218,7 @@ The following is a list of sanitizers that are shipped with Nominatim.
##### clean-tiger-tags
::: nominatim.tokenizer.sanitizers.clean_tiger_tags
::: nominatim_db.tokenizer.sanitizers.clean_tiger_tags
options:
members: False
heading_level: 6
@@ -223,7 +226,7 @@ The following is a list of sanitizers that are shipped with Nominatim.
#### delete-tags
::: nominatim.tokenizer.sanitizers.delete_tags
::: nominatim_db.tokenizer.sanitizers.delete_tags
options:
members: False
heading_level: 6
@@ -231,7 +234,7 @@ The following is a list of sanitizers that are shipped with Nominatim.
#### tag-japanese
::: nominatim.tokenizer.sanitizers.tag_japanese
::: nominatim_db.tokenizer.sanitizers.tag_japanese
options:
members: False
heading_level: 6
@@ -394,7 +397,7 @@ The analyzer cannot be customized.
##### Postcode token analyzer
The analyzer `postcodes` is pupose-made to analyze postcodes. It supports
a 'lookup' varaint of the token, which produces variants with optional
a 'lookup' variant of the token, which produces variants with optional
spaces. Use together with the clean-postcodes sanitizer.
The analyzer cannot be customized.

View File

@@ -3,8 +3,7 @@
### Import tables
OSM data is initially imported using [osm2pgsql](https://osm2pgsql.org).
Nominatim uses its own data output style 'gazetteer', which differs from the
output style created for map rendering.
Nominatim uses a custom flex style to create the initial import tables.
The import process creates the following tables:
@@ -14,7 +13,7 @@ The `planet_osm_*` tables are the usual backing tables for OSM data. Note
that Nominatim uses them to look up special relations and to find nodes on
ways.
The gazetteer style produces a single table `place` as output with the following
The osm2pgsql import produces a single table `place` as output with the following
columns:
* `osm_type` - kind of OSM object (**N** - node, **W** - way, **R** - relation)
@@ -80,7 +79,7 @@ the placex table. Only three columns are special:
Address interpolations are always ways in OSM, which is why there is no column
`osm_type`.
The **location_postcode** table holds computed centroids of all postcodes that
The **location_postcodes** table holds computed centroids of all postcodes that
can be found in the OSM data. The meaning of the columns is again the same
as that of the placex table.

View File

@@ -4,19 +4,19 @@ This chapter gives an overview how to set up Nominatim for development
and how to run tests.
!!! Important
This guide assumes that you develop under the latest version of Ubuntu. You
can of course also use your favourite distribution. You just might have to
adapt the commands below slightly, in particular the commands for installing
additional software.
This guide assumes you develop under the latest version of Debian/Ubuntu.
You can of course also use your favourite distribution. You just might have
to adapt the commands below slightly, in particular the commands for
installing additional software.
## Installing Nominatim
The first step is to install Nominatim itself. Please follow the installation
instructions in the [Admin section](../admin/Installation.md). You don't need
to set up a webserver for development, the webserver that is included with PHP
is sufficient.
to set up a webserver for development, the webserver that can be started
via `nominatim serve` is sufficient.
If you want to run Nominatim in a VM via Vagrant, use the default `ubuntu` setup.
If you want to run Nominatim in a VM via Vagrant, use the default `ubuntu24` setup.
Vagrant's libvirt provider runs out-of-the-box under Ubuntu. You also need to
install an NFS daemon to enable directory sharing between host and guest. The
following packages should get you started:
@@ -25,84 +25,98 @@ following packages should get you started:
## Prerequisites for testing and documentation
The Nominatim test suite consists of behavioural tests (using behave) and
unit tests (using PHPUnit for PHP code and pytest for Python code).
It has the following additional requirements:
The Nominatim test suite consists of behavioural tests (using pytest-bdd) and
unit tests (using pytest). It has the following additional requirements:
* [behave test framework](https://behave.readthedocs.io) >= 1.2.6
* [phpunit](https://phpunit.de) (9.5 is known to work)
* [PHP CodeSniffer](https://github.com/squizlabs/PHP_CodeSniffer)
* [Pylint](https://pylint.org/) (CI always runs the latest version from pip)
* [flake8](https://flake8.pycqa.org/en/stable/) (CI always runs the latest version from pip)
* [mypy](http://mypy-lang.org/) (plus typing information for external libs)
* [Python Typing Extensions](https://github.com/python/typing_extensions) (for Python < 3.9)
* [pytest](https://pytest.org)
* [pytest-asyncio](https://pytest-asyncio.readthedocs.io)
* [pytest-bdd](https://pytest-bdd.readthedocs.io)
For testing the Python search frontend, you need to install extra dependencies
depending on your choice of webserver framework:
* [httpx](https://www.python-httpx.org/) (starlette only)
* [asgi-lifespan](https://github.com/florimondmanca/asgi-lifespan) (starlette only)
* [httpx](https://www.python-httpx.org/) (Starlette only)
* [asgi-lifespan](https://github.com/florimondmanca/asgi-lifespan) (Starlette only)
The documentation is built with mkdocs:
* [mkdocs](https://www.mkdocs.org/) >= 1.1.2
* [mkdocstrings](https://mkdocstrings.github.io/) >= 0.18
* [mkdocstrings-python](https://mkdocstrings.github.io/python/)
* [mkdocstrings](https://mkdocstrings.github.io/) >= 0.25
* [mkdocs-material](https://squidfunk.github.io/mkdocs-material/)
* [mkdocs-gen-files](https://oprypin.github.io/mkdocs-gen-files/)
### Installing prerequisites on Ubuntu/Debian
Some of the Python packages require the newest version which is not yet
available with the current distributions. Therefore it is recommended to
install pip to get the newest versions.
To install all necessary packages run:
The Python tools should always be run with the most recent version.
The easiest way, to handle these Python dependencies is to run your
development from within a virtual environment.
```sh
sudo apt install php-cgi phpunit php-codesniffer \
python3-pip python3-setuptools python3-dev
pip3 install --user behave mkdocs mkdocstrings pytest pytest-asyncio pylint \
mypy types-PyYAML types-jinja2 types-psycopg2 types-psutil \
types-ujson types-requests types-Pygments typing-extensions\
httpx asgi-lifespan
sudo apt install libsqlite3-mod-spatialite osm2pgsql \
postgresql-postgis postgresql-postgis-scripts \
pkg-config libicu-dev virtualenv
```
The `mkdocs` executable will be located in `.local/bin`. You may have to add
this directory to your path, for example by running:
To set up the virtual environment with all necessary packages run:
```
echo 'export PATH=~/.local/bin:$PATH' > ~/.profile
```sh
virtualenv ~/nominatim-dev-venv
~/nominatim-dev-venv/bin/pip install\
psutil 'psycopg[binary]' PyICU SQLAlchemy \
python-dotenv jinja2 pyYAML \
mkdocs 'mkdocstrings[python]' mkdocs-gen-files \
pytest pytest-asyncio pytest-bdd flake8 \
types-jinja2 types-markupsafe types-psutil types-psycopg2 \
types-pygments types-pyyaml types-requests types-ujson \
types-urllib3 typing-extensions unicorn falcon starlette \
uvicorn mypy osmium aiosqlite mwparserfromhell
```
If your distribution does not have PHPUnit 7.3+, you can install it (as well
as CodeSniffer) via composer:
Now enter the virtual environment whenever you want to develop:
```
sudo apt-get install composer
composer global require "squizlabs/php_codesniffer=*"
composer global require "phpunit/phpunit=8.*"
```sh
. ~/nominatim-dev-venv/bin/activate
```
The binaries are found in `.config/composer/vendor/bin`. You need to add this
to your PATH as well:
### Running Nominatim during development
The source code for Nominatim can be found in the `src` directory and can
be run in-place. The source directory features a special script
`nominatim-cli.py` which does the same as the installed 'nominatim' binary
but executes against the code in the source tree. For example:
```
echo 'export PATH=~/.config/composer/vendor/bin:$PATH' > ~/.profile
me@machine:~$ cd Nominatim
me@machine:~Nominatim$ ./nominatim-cli.py --version
Nominatim version 5.1.0-0
```
Make sure you have activated the virtual environment holding all
necessary dependencies.
## Executing Tests
All tests are located in the `/test` directory.
To run all tests just go to the build directory and run make:
To run all tests, run make from the source root:
```sh
cd build
make test
make tests
```
There are also make targets for executing only parts of the test suite.
For example to run linting only use:
```sh
make lint
```
The possible testing targets are: mypy, lint, pytest, bdd.
For more information about the structure of the tests and how to change and
extend the test suite, see the [Testing chapter](Testing.md).
@@ -113,18 +127,14 @@ built using the [MkDocs](https://www.mkdocs.org/) static site generation
framework. The master branch is automatically deployed every night on
[https://nominatim.org/release-docs/develop/](https://nominatim.org/release-docs/develop/)
To build the documentation, go to the build directory and run
To build the documentation run
```
make doc
INFO - Cleaning site directory
INFO - Building documentation to directory: /home/vagrant/build/site-html
```
This runs `mkdocs build` plus extra transformation of some files and adds
symlinks (see `CMakeLists.txt` for the exact steps).
Now you can start webserver for local testing
For local testing, you can start webserver:
```
build> make serve-doc
@@ -136,7 +146,7 @@ If you develop inside a Vagrant virtual machine, use a port that is forwarded
to your host:
```
build> PYTHONPATH=$SRCDIR mkdocs serve --dev-addr 0.0.0.0:8088
build> mkdocs serve --dev-addr 0.0.0.0:8088
[server:296] Serving on http://0.0.0.0:8088
[handlers:62] Start watching changes
```

View File

@@ -14,10 +14,11 @@ of sanitizers and token analysis.
implemented, it is not guaranteed to be stable at the moment.
## Using non-standard sanitizers and token analyzers
## Using non-standard modules
Sanitizer names (in the `step` property) and token analysis names (in the
`analyzer`) may refer to externally supplied modules. There are two ways
Sanitizer names (in the `step` property), token analysis names (in the
`analyzer`) and query preprocessor names (in the `step` property)
may refer to externally supplied modules. There are two ways
to include external modules: through a library or from the project directory.
To include a module from a library, use the absolute import path as name and
@@ -27,6 +28,53 @@ To use a custom module without creating a library, you can put the module
somewhere in your project directory and then use the relative path to the
file. Include the whole name of the file including the `.py` ending.
## Custom query preprocessors
A query preprocessor must export a single factory function `create` with
the following signature:
``` python
create(self, config: QueryConfig) -> Callable[[list[Phrase]], list[Phrase]]
```
The function receives the custom configuration for the preprocessor and
returns a callable (function or class) with the actual preprocessing
code. When a query comes in, then the callable gets a list of phrases
and needs to return the transformed list of phrases. The list and phrases
may be changed in place or a completely new list may be generated.
The `QueryConfig` is a simple dictionary which contains all configuration
options given in the yaml configuration of the ICU tokenizer. It is up to
the function to interpret the values.
A `nominatim_api.search.Phrase` describes a part of the query that contains one or more independent
search terms. Breaking a query into phrases helps reducing the number of
possible tokens Nominatim has to take into account. However a phrase break
is definitive: a multi-term search word cannot go over a phrase break.
A Phrase object has two fields:
* `ptype` further refines the type of phrase (see list below)
* `text` contains the query text for the phrase
The order of phrases matters to Nominatim when doing further processing.
Thus, while you may split or join phrases, you should not reorder them
unless you really know what you are doing.
Phrase types can further help narrowing down how the tokens in the phrase
are interpreted. The following phrase types are known:
| Name | Description |
|----------------|-------------|
| PHRASE_ANY | No specific designation (i.e. source is free-form query) |
| PHRASE_AMENITY | Contains name or type of a POI |
| PHRASE_STREET | Contains a street name optionally with a housenumber |
| PHRASE_CITY | Contains the postal city |
| PHRASE_COUNTY | Contains the equivalent of a county |
| PHRASE_STATE | Contains a state or province |
| PHRASE_POSTCODE| Contains a postal code |
| PHRASE_COUNTRY | Contains the country name or code |
## Custom sanitizer modules
A sanitizer module must export a single factory function `create` with the
@@ -52,7 +100,7 @@ the function.
### Sanitizer configuration
::: nominatim.tokenizer.sanitizers.config.SanitizerConfig
::: nominatim_db.tokenizer.sanitizers.config.SanitizerConfig
options:
heading_level: 6
@@ -73,14 +121,14 @@ adding extra attributes) or completely replace the list with a different one.
#### PlaceInfo - information about the place
::: nominatim.data.place_info.PlaceInfo
::: nominatim_db.data.place_info.PlaceInfo
options:
heading_level: 6
#### PlaceName - extended naming information
::: nominatim.data.place_name.PlaceName
::: nominatim_db.data.place_name.PlaceName
options:
heading_level: 6
@@ -90,21 +138,22 @@ adding extra attributes) or completely replace the list with a different one.
The following sanitizer removes the directional prefixes from street names
in the US:
``` python
import re
!!! example
``` python
import re
def _filter_function(obj):
if obj.place.country_code == 'us' \
and obj.place.rank_address >= 26 and obj.place.rank_address <= 27:
for name in obj.names:
name.name = re.sub(r'^(north|south|west|east) ',
'',
name.name,
flags=re.IGNORECASE)
def _filter_function(obj):
if obj.place.country_code == 'us' \
and obj.place.rank_address >= 26 and obj.place.rank_address <= 27:
for name in obj.names:
name.name = re.sub(r'^(north|south|west|east) ',
'',
name.name,
flags=re.IGNORECASE)
def create(config):
return _filter_function
```
def create(config):
return _filter_function
```
This is the most simple form of a sanitizer module. If defines a single
filter function and implements the required `create()` function by returning
@@ -128,23 +177,23 @@ sanitizers:
!!! warning
This example is just a simplified show case on how to create a sanitizer.
It is not really read for real-world use: while the sanitizer would
correcly transform `West 5th Street` into `5th Street`. it would also
It is not really meant for real-world use: while the sanitizer would
correctly transform `West 5th Street` into `5th Street`. it would also
shorten a simple `North Street` to `Street`.
For more sanitizer examples, have a look at the sanitizers provided by Nominatim.
They can be found in the directory
[`nominatim/tokenizer/sanitizers`](https://github.com/osm-search/Nominatim/tree/master/nominatim/tokenizer/sanitizers).
[`src/nominatim_db/tokenizer/sanitizers`](https://github.com/osm-search/Nominatim/tree/master/src/nominatim_db/tokenizer/sanitizers).
## Custom token analysis module
::: nominatim.tokenizer.token_analysis.base.AnalysisModule
::: nominatim_db.tokenizer.token_analysis.base.AnalysisModule
options:
heading_level: 6
::: nominatim.tokenizer.token_analysis.base.Analyzer
::: nominatim_db.tokenizer.token_analysis.base.Analyzer
options:
heading_level: 6

View File

@@ -8,9 +8,9 @@ the tests, see the [Development setup chapter](Development-Environment.md).
There are two kind of tests in this test suite. There are functional tests
which test the API interface using a BDD test framework and there are unit
tests for specific PHP functions.
tests for the Python code.
This test directory is sturctured as follows:
This test directory is structured as follows:
```
-+- bdd Functional API tests
@@ -20,28 +20,11 @@ This test directory is sturctured as follows:
| +- db Tests for internal data processing on import and update
| +- api Tests for API endpoints (search, reverse, etc.)
|
+- php PHP unit tests
+- python Python unit tests
+- testdb Base data for generating API test database
+- testdata Additional test data used by unit tests
```
## PHP Unit Tests (`test/php`)
Unit tests for PHP code can be found in the `php/` directory. They test selected
PHP functions. Very low coverage.
To execute the test suite run
cd test/php
UNIT_TEST_DSN='pgsql:dbname=nominatim_unit_tests' phpunit ../
It will read phpunit.xml which points to the library, test path, bootstrap
strip and sets other parameters.
It will use (and destroy) a local database 'nominatim_unit_tests'. You can set
a different connection string with e.g. UNIT_TEST_DSN='pgsql:dbname=foo_unit_tests'.
## Python Unit Tests (`test/python`)
Unit tests for Python code can be found in the `python/` directory. The goal is
@@ -60,56 +43,62 @@ The name of the pytest binary depends on your installation.
## BDD Functional Tests (`test/bdd`)
Functional tests are written as BDD instructions. For more information on
the philosophy of BDD testing, see the
[Behave manual](http://pythonhosted.org/behave/philosophy.html).
The following explanation assume that the reader is familiar with the BDD
notations of features, scenarios and steps.
All possible steps can be found in the `steps` directory and should ideally
be documented.
the philosophy of BDD testing, read the Wikipedia article on
[Behaviour-driven development](https://en.wikipedia.org/wiki/Behavior-driven_development).
### General Usage
To run the functional tests, do
cd test/bdd
behave
pytest test/bdd
The tests can be configured with a set of environment variables (`behave -D key=val`):
You can run a single feature file using expression matching:
* `BUILDDIR` - build directory of Nominatim installation to test
* `TEMPLATE_DB` - name of template database used as a skeleton for
the test databases (db tests)
* `TEST_DB` - name of test database (db tests)
* `API_TEST_DB` - name of the database containing the API test data (api tests)
* `API_TEST_FILE` - OSM file to be imported into the API test database (api tests)
* `API_ENGINE` - webframe to use for running search queries, same values as
`nominatim serve --engine` parameter
* `DB_HOST` - (optional) hostname of database host
* `DB_PORT` - (optional) port of database on host
* `DB_USER` - (optional) username of database login
* `DB_PASS` - (optional) password for database login
* `SERVER_MODULE_PATH` - (optional) path on the Postgres server to Nominatim
module shared library file
* `REMOVE_TEMPLATE` - if true, the template and API database will not be reused
during the next run. Reusing the base templates speeds
up tests considerably but might lead to outdated errors
for some changes in the database layout.
* `KEEP_TEST_DB` - if true, the test database will not be dropped after a test
is finished. Should only be used if one single scenario is
run, otherwise the result is undefined.
pytest test/bdd -k osm2pgsql/import/entrances.feature
This even works for running single tests by adding the line number of the
scenario header like that:
pytest test/bdd -k 'osm2pgsql/import/entrances.feature and L4'
The BDD tests create databases for the tests. You can set name of the databases
through configuration variables in your `pytest.ini`:
* `nominatim_test_db` defines the name of the temporary database created for
a single test (default: `test_nominatim`)
* `nominatim_api_test_db` defines the name of the database containing
the API test data, see also below (default: `test_api_nominatim`)
* `nominatim_template_db` defines the name of the template database used
for creating the temporary test databases. It contains some static setup
which usually doesn't change between imports of OSM data
(default: `test_template_nominatim`)
To change other connection parameters for the PostgreSQL database, use
the [libpq enivronment variables](https://www.postgresql.org/docs/current/libpq-envars.html).
Never set a password through these variables. Use a
[password file](https://www.postgresql.org/docs/current/libpq-pgpass.html) instead.
The API test database and the template database are only created once and then
left untouched. This is usually what you want because it speeds up subsequent
runs of BDD tests. If you do change code that has an influence on the content
of these databases, you can run pytest with the `--nominatim-purge` parameter
and the databases will be dropped and recreated from scratch.
When running the BDD tests with make (using `make tests` or `make bdd`), then
the databases will always be purged.
The temporary test database is usually dropped directly after the test, so
it does not take up unnecessary space. If you want to keep the database around,
for example while debugging a specific BDD test, use the parameter
`--nominatim-keep-db`.
Logging can be defined through command line parameters of behave itself. Check
out `behave --help` for details. Also have a look at the 'work-in-progress'
feature of behave which comes in handy when writing new tests.
### API Tests (`test/bdd/api`)
These tests are meant to test the different API endpoints and their parameters.
They require to import several datasets into a test database. This is normally
done automatically during setup of the test. The API test database is then
kept around and reused in subsequent runs of behave. Use `behave -DREMOVE_TEMPLATE`
kept around and reused in subsequent runs of behave. Use `--nominatim-purge`
to force a reimport of the database.
The official test dataset is saved in the file `test/testdb/apidb-test-data.pbf`
@@ -119,26 +108,9 @@ and compromises the following data:
* extract of Autauga country, Alabama, US (for tests against Tiger data)
* additional data from `test/testdb/additional_api_test.data.osm`
API tests should only be testing the functionality of the website PHP code.
API tests should only be testing the functionality of the website frontend code.
Most tests should be formulated as BDD DB creation tests (see below) instead.
#### Code Coverage (PHP engine only)
The API tests also support code coverage tests. You need to install
[PHP_CodeCoverage](https://github.com/sebastianbergmann/php-code-coverage).
On Debian/Ubuntu run:
apt-get install php-codecoverage php-xdebug
Then run the API tests as follows:
behave api -DPHPCOV=<coverage output dir>
The output directory must be an absolute path. To generate reports, you can use
the [phpcov](https://github.com/sebastianbergmann/phpcov) tool:
phpcov merge --html=<report output dir> <coverage output dir>
### DB Creation Tests (`test/bdd/db`)
These tests check the import and update of the Nominatim database. They do not
@@ -146,12 +118,12 @@ test the correctness of osm2pgsql. Each test will write some data into the `plac
table (and optionally the `planet_osm_*` tables if required) and then run
Nominatim's processing functions on that.
These tests need to create their own test databases. By default they will be
called `test_template_nominatim` and `test_nominatim`. Names can be changed with
the environment variables `TEMPLATE_DB` and `TEST_DB`. The user running the tests
needs superuser rights for postgres.
These tests use the template database and create temporary test databases for
each test.
### Import Tests (`test/bdd/osm2pgsql`)
These tests check that data is imported correctly into the place table. They
use the same template database as the DB Creation tests, so the same remarks apply.
These tests check that data is imported correctly into the place table.
These tests also use the template database and create temporary test databases
for each test.

View File

@@ -91,19 +91,19 @@ for a custom tokenizer implementation.
### Directory Structure
Nominatim expects two files for a tokenizer:
Nominatim expects two files containing the Python part of the implementation:
* `nominatim/tokenizer/<NAME>_tokenizer.py` containing the Python part of the
implementation
* `lib-php/tokenizer/<NAME>_tokenizer.php` with the PHP part of the
implementation
* `src/nominatim_db/tokenizer/<NAME>_tokenizer.py` contains the tokenizer
code used during import and
* `src/nominatim_api/search/<NAME>_tokenizer.py` has the code used during
query time.
where `<NAME>` is a unique name for the tokenizer consisting of only lower-case
`<NAME>` is a unique name for the tokenizer consisting of only lower-case
letters, digits and underscore. A tokenizer also needs to install some SQL
functions. By convention, these should be placed in `lib-sql/tokenizer`.
If the tokenizer has a default configuration file, this should be saved in
the `settings/<NAME>_tokenizer.<SUFFIX>`.
`settings/<NAME>_tokenizer.<SUFFIX>`.
### Configuration and Persistence
@@ -115,9 +115,11 @@ are tied to a database installation and must only be read during installation
time. If they are needed for the runtime then they must be saved into the
`nominatim_properties` table and later loaded from there.
### The Python module
### The Python modules
The Python module is expect to export a single factory function:
#### `src/nominatim_db/tokenizer/`
The import Python module is expected to export a single factory function:
```python
def create(dsn: str, data_dir: Path) -> AbstractTokenizer
@@ -128,18 +130,39 @@ is a directory in the project directory that the tokenizer may use to save
database-specific data. The function must return the instance of the tokenizer
class as defined below.
#### `src/nominatim_api/search/`
The query-time Python module must also export a factory function:
``` python
def create_query_analyzer(conn: SearchConnection) -> AbstractQueryAnalyzer
```
The `conn` parameter contains the current search connection. See the
[library documentation](../library/Low-Level-DB-Access.md#searchconnection-class)
for details on the class. The function must return the instance of the tokenizer
class as defined below.
### Python Tokenizer Class
All tokenizers must inherit from `nominatim.tokenizer.base.AbstractTokenizer`
All tokenizers must inherit from `nominatim_db.tokenizer.base.AbstractTokenizer`
and implement the abstract functions defined there.
::: nominatim.tokenizer.base.AbstractTokenizer
::: nominatim_db.tokenizer.base.AbstractTokenizer
options:
heading_level: 6
### Python Analyzer Class
::: nominatim.tokenizer.base.AbstractAnalyzer
::: nominatim_db.tokenizer.base.AbstractAnalyzer
options:
heading_level: 6
### Python Query Analyzer Class
::: nominatim_api.search.query_analyzer_factory.AbstractQueryAnalyzer
options:
heading_level: 6
@@ -282,73 +305,3 @@ permanently. The indexer calls this function when all processing is done and
replaces the content of the `token_info` column with the returned value before
the trigger stores the information in the database. May return NULL if no
information should be stored permanently.
### PHP Tokenizer class
The PHP tokenizer class is instantiated once per request and responsible for
analyzing the incoming query. Multiple requests may be in flight in
parallel.
The class is expected to be found under the
name of `\Nominatim\Tokenizer`. To find the class the PHP code includes the file
`tokenizer/tokenizer.php` in the project directory. This file must be created
when the tokenizer is first set up on import. The file should initialize any
configuration variables by setting PHP constants and then require the file
with the actual implementation of the tokenizer.
The tokenizer class must implement the following functions:
```php
public function __construct(object &$oDB)
```
The constructor of the class receives a database connection that can be used
to query persistent data in the database.
```php
public function checkStatus()
```
Check that the tokenizer can access its persistent data structures. If there
is an issue, throw an `\Exception`.
```php
public function normalizeString(string $sTerm) : string
```
Normalize string to a form to be used for comparisons when reordering results.
Nominatim reweighs results how well the final display string matches the actual
query. Before comparing result and query, names and query are normalised against
this function. The tokenizer can thus remove all properties that should not be
taken into account for reweighing, e.g. special characters or case.
```php
public function tokensForSpecialTerm(string $sTerm) : array
```
Return the list of special term tokens that match the given term.
```php
public function extractTokensFromPhrases(array &$aPhrases) : TokenList
```
Parse the given phrases, splitting them into word lists and retrieve the
matching tokens.
The phrase array may take on two forms. In unstructured searches (using `q=`
parameter) the search query is split at the commas and the elements are
put into a sorted list. For structured searches the phrase array is an
associative array where the key designates the type of the term (street, city,
county etc.) The tokenizer may ignore the phrase type at this stage in parsing.
Matching phrase type and appropriate search token type will be done later
when the SearchDescription is built.
For each phrase in the list of phrases, the function must analyse the phrase
string and then call `setWordSets()` to communicate the result of the analysis.
A word set is a list of strings, where each string refers to a search token.
A phrase may have multiple interpretations. Therefore a list of word sets is
usually attached to the phrase. The search tokens themselves are returned
by the function in an associative array, where the key corresponds to the
strings given in the word sets. The value is a list of search tokens. Thus
a single string in the list of word sets may refer to multiple search tokens.

View File

@@ -9,7 +9,7 @@ the address computation and the search frontend.
The __data import__ stage reads the raw OSM data and extracts all information
that is useful for geocoding. This part is done by osm2pgsql, the same tool
that can also be used to import a rendering database. It uses the special
gazetteer output plugin in `osm2pgsql/src/output-gazetter.[ch]pp`. The result of
flex output style defined in the directory `/lib-lua`. The result of
the import can be found in the database table `place`.
The __address computation__ or __indexing__ stage takes the data from `place`
@@ -20,5 +20,5 @@ and can be found in the files in the `sql/functions/` directory.
The __search frontend__ implements the actual API. It takes search
and reverse geocoding queries from the user, looks up the data and
returns the results in the requested format. This part is written in PHP
and can be found in the `lib/` and `website/` directories.
returns the results in the requested format. This part is located in the
`nominatim-api` package. The source code can be found in `src/nominatim_api`.

View File

@@ -18,7 +18,7 @@ elseif (has 'addr:place'?) then (yes)
**with same name**;
kill
else (no)
:add addr:place to adress;
:add addr:place to address;
:**Use closest place**\n**rank 16 to 25**;
kill
endif

File diff suppressed because one or more lines are too long

Before

Width:  |  Height:  |  Size: 9.8 KiB

After

Width:  |  Height:  |  Size: 9.8 KiB

View File

@@ -74,15 +74,16 @@ map place_addressline {
isaddress => BOOLEAN
}
map location_postcode {
map location_postcodes {
place_id => BIGINT
osm_id => BIGINT
postcode => TEXT
parent_place_id => BIGINT
rank_search => SMALLINT
rank_address => SMALLINT
indexed_status => SMALLINT
indexed_date => TIMESTAMP
geometry => GEOMETRY
centroid -> GEOMETRY
}
placex::place_id <-- search_name::place_id
@@ -94,6 +95,6 @@ search_name::nameaddress_vector --> word::word_id
place_addressline -[hidden]> location_property_osmline
search_name -[hidden]> place_addressline
location_property_osmline -[hidden]-> location_postcode
location_property_osmline -[hidden]-> location_postcodes
@enduml

View File

@@ -2,8 +2,8 @@
display: none!important
}
.wy-nav-content {
max-width: 900px!important
.md-content {
max-width: 800px
}
table {
@@ -34,3 +34,14 @@ th {
.md-footer__inner {
display: none;
}
.headerlink {
filter: grayscale(100%);
font-size: 80%;
}
.simple-table table:not([class]) th,
.simple-table table:not([class]) td {
padding: 2px 4px;
background: white;
}

View File

@@ -1,11 +1,13 @@
# Configuration
When using Nominatim through the library, it can be configured in exactly
the same way as when running as a service. This means that you should have
created a [project directory](../admin/Import.md#creating-the-project-directory)
which contains all files belonging to the Nominatim instance. It can also contain
an `.env` file with configuration options. Setting configuration parameters
via environment variables works as well.
the same way as when running as a service. You may instantiate the library
against the [project directory](../admin/Import.md#creating-the-project-directory)
of your Nominatim installation. It contains all files belonging to the
Nominatim instance. This may include an `.env` file with configuration options.
Setting configuration parameters via environment variables works as well.
Alternatively to using the operating system's environment, a set of
configuration parameters may also be passed to the Nomiantim API object.
Configuration options are resolved in the following order:
@@ -20,7 +22,7 @@ configuration parameters, see the [Configuration page](../customize/Settings.md)
## `Configuration` class
::: nominatim.config.Configuration
::: nominatim_api.Configuration
options:
members:
- get_bool

View File

@@ -1,20 +1,21 @@
# Getting Started
The Nominatim search frontend can directly be used as a Python library in
scripts and applications. When you have imported your own Nominatim database,
then it is no longer necessary to run a full web service for it and access
the database through http requests. There are
also less constraints on the kinds of data that can be accessed. The library
allows to get access to more detailed information about the objects saved
in the database.
The Nominatim search frontend is implemented as a Python library and can as
such directly be used in Python scripts and applications. You don't need to
set up a web frontend and access it through HTTP calls. The library gives
direct access to the Nominatim database through similar search functions as
offered by the web API. In addition, it will give you a more complete and
detailed view on the search objects stored in the database.
!!! danger
The library interface is currently in an experimental stage. There might
be some smaller adjustments to the public interface until the next version.
!!! warning
The library also misses a proper installation routine, so some manipulation
of the PYTHONPATH is required. At the moment, use is only recommended for
developers wit some experience in Python.
The Nominatim library is used for accessing a local Nominatim database.
It is not meant to be used against web services of Nominatim like the
one on https://nominatim.openstreetmap.org. If you need a Python library
to access these web services, have a look at
[GeoPy](https://geopy.readthedocs.io). Don't forget to consult the
usage policy of the service you want to use before accessing such
a web service.
## Installation
@@ -22,14 +23,18 @@ To use the Nominatim library, you need access to a local Nominatim database.
Follow the [installation](../admin/Installation.md) and
[import](../admin/Import.md) instructions to set up your database.
It is not yet possible to install it in the usual way via pip or inside a
virtualenv. To get access to the library you need to set an appropriate
`PYTHONPATH`. With the default installation, the python library can be found
under `/usr/local/share/nominatim/lib-python`. If you have installed
Nominatim under a different prefix, adapt the `/usr/local/` part accordingly.
You can also point the `PYTHONPATH` to the Nominatim source code.
The Nominatim frontend library is contained in the Python package `nominatim-api`.
You can install the latest released version directly from pip:
### A simple search example
pip install nominatim-api
To install the package from the source tree directly, run:
pip install packaging/nominatim-api
Usually you would want to run this in a virtual environment.
## A simple search example
To query the Nominatim database you need to first set up a connection. This
is done by creating an Nominatim API object. This object exposes all the
@@ -40,15 +45,13 @@ This code snippet implements a simple search for the town of 'Brugge':
!!! example
=== "NominatimAPIAsync"
``` python
from pathlib import Path
import asyncio
import nominatim.api as napi
import nominatim_api as napi
async def search(query):
api = napi.NominatimAPIAsync(Path('.'))
return await api.search(query)
async with napi.NominatimAPIAsync() as api:
return await api.search(query)
results = asyncio.run(search('Brugge'))
if not results:
@@ -59,13 +62,10 @@ This code snippet implements a simple search for the town of 'Brugge':
=== "NominatimAPI"
``` python
from pathlib import Path
import nominatim_api as napi
import nominatim.api as napi
api = napi.NominatimAPI(Path('.'))
results = api.search('Brugge')
with napi.NominatimAPI() as api:
results = api.search('Brugge')
if not results:
print('Cannot find Brugge')
@@ -88,7 +88,7 @@ implementations. The documentation itself will usually refer only to
available only for the synchronous or asynchronous version, this will be
explicitly mentioned.
### Defining which database to use
## Defining which database to use
The [Configuration](../admin/Import.md#configuration-setup-in-env)
section explains how Nominatim is configured using the
@@ -97,76 +97,120 @@ The same configuration mechanism is used with the
Nominatim API library. You should therefore be sure you are familiar with
the section.
The constructor of the 'Nominatim API class' takes one mandatory parameter:
the path to the [project directory](../admin/Import.md#creating-the-project-directory).
You should have set up this directory as part of the Nominatim import.
Any configuration found in the `.env` file in this directory will automatically
used.
Yo may also configure Nominatim be setting environment variables.
Normally, Nominatim will check the operating system environment. This can be
overwritten by giving the constructor a dictionary of configuration parameters.
Let us look up 'Brugge' in the special database named 'belgium' instead of the
standard 'nominatim' database:
There are three different ways, how configuration options can be set for
a 'Nominatim API class'. When you have set up your Nominatim database, you
have normally created a [project directory](../admin/Import.md#creating-the-project-directory)
which stores the various configuration and customization files that Nominatim
needs. You may pass the location of the project directory to your
'Nominatim API class' constructor and it will read the .env file in the
directory and set the configuration accordingly. Here is the simple search
example, using the configuration from a pre-defined project directory in
`/srv/nominatim-project`:
!!! example
=== "NominatimAPIAsync"
``` python
from pathlib import Path
import asyncio
import nominatim.api as napi
import nominatim_api as napi
async def search(query):
async with napi.NominatimAPIAsync('/srv/nominatim-project') as api:
return await api.search(query)
results = asyncio.run(search('Brugge'))
if not results:
print('Cannot find Brugge')
else:
print(f'Found a place at {results[0].centroid.x},{results[0].centroid.y}')
```
=== "NominatimAPI"
``` python
import nominatim_api as napi
with napi.NominatimAPI('/srv/nominatim-project') as api:
results = api.search('Brugge')
if not results:
print('Cannot find Brugge')
else:
print(f'Found a place at {results[0].centroid.x},{results[0].centroid.y}')
```
You may also configure Nominatim by setting environment variables.
Normally Nominatim will check the operating system environment. Lets
say you want to look up 'Brugge' in the special database named 'belgium' instead of the
standard 'nominatim' database. You can run the example script above like this:
```
NOMINATIM_DATABASE_DSN=pgsql:dbname=belgium python3 example.py
```
The third option to configure the library is to hand in the configuration
parameters into the 'Nominatim API class'. Changing the database would look
like this:
!!! example
=== "NominatimAPIAsync"
``` python
import asyncio
import nominatim_api as napi
config_params = {
'NOMINATIM_DATABASE_DSN': 'pgsql:dbname=belgium'
}
async def search(query):
api = napi.NominatimAPIAsync(Path('.'), environ=config_params)
return await api.search(query)
async with napi.NominatimAPIAsync(environ=config_params) as api:
return await api.search(query)
results = asyncio.run(search('Brugge'))
```
=== "NominatimAPI"
``` python
from pathlib import Path
import nominatim.api as napi
import nominatim_api as napi
config_params = {
'NOMINATIM_DATABASE_DSN': 'pgsql:dbname=belgium'
}
api = napi.NominatimAPI(Path('.'), environ=config_params)
results = api.search('Brugge')
with napi.NominatimAPI(environ=config_params) as api:
results = api.search('Brugge')
```
### Presenting results to humans
When the `environ` parameter is given, then only configuration variables
from this dictionary will be used. The operating system's environment
variables will be ignored.
All search functions return the raw results from the database. There is no
full human-readable label. To create such a label, you need two things:
## Presenting results to humans
All search functions return full result objects from the database. Such a
result object contains lots of details: names, address information, OSM tags etc.
This gives you lots of flexibility what to do with the results.
One of the most common things to get is some kind of human-readable label
that describes the result in a compact form. Usually this would be the name
of the object and some parts of the address to explain where in the world
it is. To create such a label, you need two things:
* the address details of the place
* adapt the result to the language you wish to use for display
* all names for the label adapted to the language you wish to use for display
Again searching for 'Brugge', this time with a nicely formatted result:
!!! example
=== "NominatimAPIAsync"
``` python
from pathlib import Path
import asyncio
import nominatim.api as napi
import nominatim_api as napi
async def search(query):
api = napi.NominatimAPIAsync(Path('.'))
return await api.search(query, address_details=True)
async with napi.NominatimAPIAsync() as api:
return await api.search(query, address_details=True)
results = asyncio.run(search('Brugge'))
@@ -178,13 +222,10 @@ Again searching for 'Brugge', this time with a nicely formatted result:
=== "NominatimAPI"
``` python
from pathlib import Path
import nominatim_api as napi
import nominatim.api as napi
api = napi.NominatimAPI(Path('.'))
results = api.search('Brugge', address_details=True)
with napi.NominatimAPI() as api:
results = api.search('Brugge', address_details=True)
locale = napi.Locales(['fr', 'en'])
for i, result in enumerate(results):
@@ -207,19 +248,19 @@ of the result. To do that, you first need to decide in which language the
results should be presented. As with the names in the result itself, the
places in `address_rows` contain all possible name translation for each row.
The library has a helper class `Locale` which helps extracting a name of a
The library has a helper class `Locales` which helps extracting a name of a
place in the preferred language. It takes a single parameter with a list
of language codes in the order of preference. So
``` python
locale = napi.Locale(['fr', 'en'])
locale = napi.Locales(['fr', 'en'])
```
creates a helper class that returns the name preferably in French. If that is
not possible, it tries English and eventually falls back to the default `name`
or `ref`.
The `Locale` object can be applied to a name dictionary to return the best-matching
The `Locales` object can be applied to a name dictionary to return the best-matching
name out of it:
``` python
@@ -227,20 +268,24 @@ name out of it:
'Brugges'
```
The `address_row` field has a helper function to apply the function to all
its members and save the result in the `local_name` field. It also returns
all the localized names as a convenient simple list. This list can be used
to create a human-readable output:
The `address_row` field has a helper function to compute the display name for each Address Line
component based on its `local_name` field. This is then utilized by the overall `result` object,
which has a helper function to apply the function to all its address_row members and saves
the result in the `locale_name` field.
However, in order to set this `local_name` field in a preferred language, you must use the `Locales`
object which contains the function `localize_results`, which explicitly sets each `local_name field`.
``` python
>>> address_parts = results[0].address_rows.localize(locale)
>>> Locales().localize_results(results)
>>> address_parts = results[0].address_rows
>>> print(', '.join(address_parts))
Bruges, Flandre-Occidentale, Flandre, Belgique
```
This is a fairly simple way to create a human-readable description. The
place information in `address_rows` contains further information about each
place. For example, which OSM `adlin_level` was used, what category the place
place. For example, which OSM `admin_level` was used, what category the place
belongs to or what rank Nominatim has assigned. Use this to adapt the output
to local address formats.

View File

@@ -5,26 +5,26 @@ in the query functions of the API object.
## Place identification
The [details](NominatimAPI.md#nominatim.api.core.NominatimAPI.details) and
[lookup](NominatimAPI.md#nominatim.api.core.NominatimAPI.lookup) functions
The [details](NominatimAPI.md#nominatim_api.NominatimAPI.details) and
[lookup](NominatimAPI.md#nominatim_api.NominatimAPI.lookup) functions
require references to places in the database. Below the possible
types for place identification are listed. All types are dataclasses.
### PlaceID
::: nominatim.api.PlaceID
::: nominatim_api.PlaceID
options:
heading_level: 6
### OsmID
::: nominatim.api.OsmID
::: nominatim_api.OsmID
options:
heading_level: 6
## Geometry types
::: nominatim.api.GeometryFormat
::: nominatim_api.GeometryFormat
options:
heading_level: 6
members_order: source
@@ -33,14 +33,14 @@ types for place identification are listed. All types are dataclasses.
### Point
::: nominatim.api.Point
::: nominatim_api.Point
options:
heading_level: 6
show_signature_annotations: True
### Bbox
::: nominatim.api.Bbox
::: nominatim_api.Bbox
options:
heading_level: 6
show_signature_annotations: True
@@ -54,9 +54,7 @@ orthogonal to restriction by address ranks, which groups places by their
geographic extent.
::: nominatim.api.DataLayer
::: nominatim_api.DataLayer
options:
heading_level: 6
members_order: source

View File

@@ -24,12 +24,11 @@ the placex table:
```
import asyncio
from pathlib import Path
import sqlalchemy as sa
from nominatim.api import NominatimAPIAsync
from nominatim_api import NominatimAPIAsync
async def print_table_size():
api = NominatimAPIAsync(Path('.'))
api = NominatimAPIAsync()
async with api.begin() as conn:
cnt = await conn.scalar(sa.select(sa.func.count()).select_from(conn.t.placex))
@@ -45,7 +44,7 @@ asyncio.run(print_table_size())
## SearchConnection class
::: nominatim.api.SearchConnection
::: nominatim_api.SearchConnection
options:
members:
- scalar

View File

@@ -6,7 +6,7 @@ to instantiate a separate instance for each thread.
### NominatimAPI
::: nominatim.api.NominatimAPI
::: nominatim_api.NominatimAPI
options:
members:
- __init__
@@ -25,7 +25,7 @@ to instantiate a separate instance for each thread.
### NominatimAPIAsync
::: nominatim.api.NominatimAPIAsync
::: nominatim_api.NominatimAPIAsync
options:
members:
- __init__

View File

@@ -12,7 +12,7 @@ functions that allow further processing of the results.
Nominatim takes the result data from multiple sources. The `source_table` field
in the result describes, from which source the result was retrieved.
::: nominatim.api.SourceTable
::: nominatim_api.SourceTable
options:
heading_level: 6
members_order: source
@@ -31,7 +31,7 @@ contains the result place itself and some artificial entries, for example,
for the house number or the country code. This makes processing and creating
a full address easier.
::: nominatim.api.AddressLine
::: nominatim_api.AddressLine
options:
heading_level: 6
members_order: source
@@ -43,16 +43,20 @@ may be used to find a place, when the `keywords` parameter is set. Search
terms are split into terms for the name of the place and search terms for
its address.
::: nominatim.api.WordInfo
::: nominatim_api.WordInfo
options:
heading_level: 6
## Localization
Results are always returned with the full list of available names.
Results are always returned with the full list of available names. However, the
default `locale_name` must be explicitly set using the `localize` function within
`Locales`. This parses through the full list of available names to find the one
most preferred by the user. Once this is set, the user can simply use the
`display_name` field within a `Result` object to retrive the localized name.
### Locale
::: nominatim.api.Locales
::: nominatim_api.Locales
options:
heading_level: 6

View File

@@ -0,0 +1,32 @@
# SPDX-License-Identifier: GPL-3.0-or-later
#
# This file is part of Nominatim. (https://nominatim.org)
#
# Copyright (C) 2024 by the Nominatim developer community.
from pathlib import Path
import mkdocs_gen_files
VAGRANT_PATH = Path(__file__, '..', '..', 'vagrant').resolve()
for infile in VAGRANT_PATH.glob('Install-on-*.sh'):
outfile = f"admin/{infile.stem}.md"
title = infile.stem.replace('-', ' ')
with mkdocs_gen_files.open(outfile, "w") as outfd, infile.open() as infd:
print("#", title, file=outfd)
has_empty = False
for line in infd:
line = line.rstrip()
docpos = line.find('#DOCS:')
if docpos >= 0:
line = line[docpos + 6:]
elif line == '#' or line.startswith('#!'):
line = ''
elif line.startswith('# '):
line = line[2:]
if line or not has_empty:
print(line, file=outfd)
has_empty = not bool(line)
mkdocs_gen_files.set_edit_path(outfile, "docs/mk_install_instructions.py")

14
lib-lua/flex-base.lua Normal file
View File

@@ -0,0 +1,14 @@
-- This is just an alias for the Nominatim themepark theme module
local flex = require('themes/nominatim/init')
function flex.load_topic(name, cfg)
local topic_file = debug.getinfo(1, "S").source:sub(2):match("(.*/)") .. 'themes/nominatim/topics/'.. name .. '.lua'
if topic_file == nil then
error('Cannot find topic: ' .. name)
end
loadfile(topic_file)(nil, flex, cfg or {})
end
return flex

View File

@@ -0,0 +1,6 @@
-- This is just an alias for the Nominatim themepark address topic
local flex = require('flex-base')
flex.load_topic('address')
return flex

6
lib-lua/import-admin.lua Normal file
View File

@@ -0,0 +1,6 @@
-- This is just an alias for the Nominatim themepark admin topic
local flex = require('flex-base')
flex.load_topic('admin')
return flex

View File

@@ -0,0 +1,6 @@
-- This is just an alias for the Nominatim themepark full topic
local flex = require('flex-base')
flex.load_topic('full', {with_extratags = true})
return flex

6
lib-lua/import-full.lua Normal file
View File

@@ -0,0 +1,6 @@
-- This is just an alias for the Nominatim themepark full topic
local flex = require('flex-base')
flex.load_topic('full')
return flex

View File

@@ -0,0 +1,6 @@
-- This is just an alias for the Nominatim themepark street topic
local flex = require('flex-base')
flex.load_topic('street')
return flex

118
lib-lua/taginfo.lua Normal file
View File

@@ -0,0 +1,118 @@
-- Prints taginfo project description in the standard output
--
-- create fake "osm2pgsql" table for flex-base, originally created by the main C++ program
osm2pgsql = {}
function osm2pgsql.define_table(...) end
-- provide path to flex-style lua file
package.path = arg[0]:match("(.*/)") .. "?.lua;" .. package.path
local flex = require('import-' .. (arg[1] or 'extratags'))
local json = require ('dkjson')
local NAME_DESCRIPTIONS = {
'Searchable auxiliary name of the place',
main = 'Searchable primary name of the place',
house = 'House name part of an address, searchable'
}
local ADDRESS_DESCRIPTIONS = {
'Used to determine the address of a place',
main = 'Primary key for an address point',
postcode = 'Used to determine the postcode of a place',
country = 'Used to determine country of a place (only if written as two-letter code)',
interpolation = 'Primary key for an address interpolation line'
}
------------ helper functions ---------------------
-- Sets the key order for the resulting JSON table
local function set_keyorder(table, order)
setmetatable(table, {
__jsonorder = order
})
end
local function get_key_description(key, description)
local desc = {}
desc.key = key
desc.description = description
set_keyorder(desc, {'key', 'description'})
return desc
end
local function get_key_value_description(key, value, description)
local desc = {key = key, value = value, description = description}
set_keyorder(desc, {'key', 'value', 'description'})
return desc
end
local function group_table_to_keys(tags, data, descriptions)
for group, values in pairs(data) do
local desc = descriptions[group] or descriptions[1]
for _, key in pairs(values) do
if key:sub(1, 1) ~= '*' and key:sub(#key, #key) ~= '*' then
table.insert(tags, get_key_description(key, desc))
end
end
end
end
-- Prints the collected tags in the required format in JSON
local function print_taginfo()
local taginfo = flex.get_taginfo()
local tags = {}
for k, values in pairs(taginfo.main) do
if values[1] == nil or values[1] == 'delete' or values[1] == 'extra' then
for v, group in pairs(values) do
if type(v) == 'string' and group ~= 'delete' and group ~= 'extra' then
local text = 'POI/feature in the search database'
if type(group) ~= 'function' then
text = 'Fallback ' .. text
end
table.insert(tags, get_key_value_description(k, v, text))
end
end
elseif type(values[1]) == 'function' or values[1] == 'fallback' then
local desc = 'POI/feature in the search database'
if values[1] == 'fallback' then
desc = 'Fallback ' .. desc
end
local excp = {}
for v, group in pairs(values) do
if group == 'delete' or group == 'extra' then
table.insert(excp, v)
end
end
if next(excp) ~= nil then
desc = desc .. string.format(' (except for values: %s)',
table.concat(excp, ', '))
end
table.insert(tags, get_key_description(k, desc))
end
end
group_table_to_keys(tags, taginfo.name, NAME_DESCRIPTIONS)
group_table_to_keys(tags, taginfo.address, ADDRESS_DESCRIPTIONS)
local format = {
data_format = 1,
data_url = 'https://nominatim.openstreetmap.org/taginfo.json',
project = {
name = 'Nominatim',
description = 'OSM search engine.',
project_url = 'https://nominatim.openstreetmap.org',
doc_url = 'https://nominatim.org/release-docs/develop/',
contact_name = 'Sarah Hoffmann',
contact_email = 'lonvia@denofr.de'
}
}
format.tags = tags
set_keyorder(format, {'data_format', 'data_url', 'project', 'tags'})
set_keyorder(format.project, {'name', 'description', 'project_url', 'doc_url',
'contact_name', 'contact_email'})
print(json.encode(format))
end
print_taginfo()

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,389 @@
-- Defines defaults used in the topic definitions.
local module = {}
-- Helper functions
local function group_merge(group1, group2)
for name, values in pairs(group2) do
if group1[name] == nil then
group1[name] = values
else
for _, v in pairs(values) do
table.insert(group1[name], v)
end
end
end
return group1
end
-- Customized main tag filter functions
local EXCLUDED_FOOTWAYS = { sidewalk = 1, crossing = 1, link = 1, traffic_aisle }
local function filter_footways(place)
if place.has_name then
local footway = place.object.tags.footway
if footway == nil or EXCLUDED_FOOTWAYS[footway] ~= 1 then
return place
end
end
return false
end
local function include_when_tag_present(key, value, named)
if named then
return function(place)
if place.has_name and place.intags[key] == value then
return place
end
return false
end
else
return function(place)
if place.intags[key] == value then
return place
end
return false
end
end
end
local function exclude_when_key_present(key, named)
if named then
return function(place)
if place.has_name and place.intags[key] == nil then
return place
end
return false
end
else
return function(place)
if place.intags[key] == nil then
return place
end
return false
end
end
end
local function lock_transform(place)
if place.object.tags.waterway ~= nil then
local name = place.object.tags.lock_name
if name ~= nil then
return place:clone{names={name=name, ref=place.object.tags.lock_ref}}
end
end
return false
end
-- Main tag definition
module.MAIN_TAGS = {}
module.MAIN_TAGS.admin = {
boundary = {administrative = 'named'},
landuse = {residential = 'fallback',
farm = 'fallback',
farmyard = 'fallback',
industrial = 'fallback',
commercial = 'fallback',
allotments = 'fallback',
retail = 'fallback'},
place = {county = 'always',
district = 'always',
municipality = 'always',
city = 'always',
town = 'always',
borough = 'always',
village = 'always',
suburb = 'always',
hamlet = 'always',
croft = 'always',
subdivision = 'always',
allotments = 'always',
neighbourhood = 'always',
quarter = 'always',
isolated_dwelling = 'always',
farm = 'always',
city_block = 'always',
locality = 'always'}
}
module.MAIN_TAGS.all_boundaries = {
boundary = {'named',
place = 'delete',
land_area = 'delete',
protected_area = 'fallback',
postal_code = 'postcode_area'},
landuse = 'fallback',
place = 'always'
}
module.MAIN_TAGS.natural = {
waterway = {'named',
riverbank = 'delete'},
natural = {'named',
yes = 'delete',
no = 'delete',
coastline = 'delete',
saddle = 'fallback',
water = exclude_when_key_present('water', true)},
mountain_pass = {'always',
no = 'delete'},
water = {include_when_tag_present('natural', 'water', true),
river = 'never',
stream = 'never',
canal = 'never',
ditch = 'never',
drain = 'never',
fish_pass = 'never',
yes = 'delete',
intermittent = 'delete',
tidal = 'delete'
}
}
module.MAIN_TAGS_POIS = function (group)
group = group or 'delete'
return {
aerialway = {'always',
no = group,
pylon = group},
aeroway = {'always',
no = group},
amenity = {'always',
no = group,
parking_space = group,
parking_entrance = group,
waste_disposal = group,
hunting_stand = group},
building = {'fallback',
no = group},
bridge = {'named_with_key',
no = group},
club = {'always',
no = group},
craft = {'always',
no = group},
emergency = {'always',
no = group,
yes = group,
fire_hydrant = group},
healthcare = {'fallback',
yes = group,
no = group},
highway = {'always',
no = group,
turning_circle = group,
mini_roundabout = group,
noexit = group,
crossing = group,
give_way = group,
stop = group,
turning_loop = group,
passing_place = group,
street_lamp = 'named',
traffic_signals = 'named'},
historic = {'fallback',
yes = group,
no = group},
information = {include_when_tag_present('tourism', 'information'),
yes = 'delete',
route_marker = 'never',
trail_blaze = 'never'},
junction = {'fallback',
no = group},
landuse = {cemetery = 'always'},
leisure = {'always',
nature_reserve = 'named',
swimming_pool = 'named',
garden = 'named',
common = 'named',
no = group},
lock = {yes = lock_transform},
man_made = {pier = 'always',
tower = 'always',
bridge = 'always',
works = 'named',
water_tower = 'always',
dyke = 'named',
adit = 'named',
lighthouse = 'always',
watermill = 'always',
tunnel = 'always'},
military = {'always',
yes = group,
no = group},
office = {'always',
no = group},
railway = {'named',
rail = group,
no = group,
abandoned = group,
disused = group,
razed = group,
level_crossing = group,
switch = group,
signal = group,
buffer_stop = group},
shop = {'always',
no = group},
tourism = {'always',
attraction = 'fallback',
no = group,
yes = group,
information = exclude_when_key_present('information')},
tunnel = {'named_with_key',
no = group}
} end
module.MAIN_TAGS_STREETS = {}
module.MAIN_TAGS_STREETS.default = {
place = {square = 'always'},
highway = {motorway = 'always',
trunk = 'always',
primary = 'always',
secondary = 'always',
tertiary = 'always',
unclassified = 'always',
residential = 'always',
road = 'always',
living_street = 'always',
pedestrian = 'always',
service = 'named',
cycleway = 'named',
path = 'named',
footway = filter_footways,
steps = 'named',
bridleway = 'named',
track = 'named',
motorway_link = 'named',
trunk_link = 'named',
primary_link = 'named',
secondary_link = 'named',
tertiary_link = 'named'}
}
module.MAIN_TAGS_STREETS.car = {
place = {square = 'always'},
highway = {motorway = 'always',
trunk = 'always',
primary = 'always',
secondary = 'always',
tertiary = 'always',
unclassified = 'always',
residential = 'always',
road = 'always',
living_street = 'always',
service = 'always',
track = 'always',
motorway_link = 'always',
trunk_link = 'always',
primary_link = 'always',
secondary_link = 'always',
tertiary_link = 'always'}
}
module.MAIN_TAGS_STREETS.all = {
place = {square = 'always'},
highway = {motorway = 'always',
trunk = 'always',
primary = 'always',
secondary = 'always',
tertiary = 'always',
unclassified = 'always',
residential = 'always',
road = 'always',
living_street = 'always',
pedestrian = 'always',
service = 'always',
cycleway = 'always',
path = 'always',
footway = 'always',
steps = 'always',
bridleway = 'always',
track = 'always',
motorway_link = 'always',
trunk_link = 'always',
primary_link = 'always',
secondary_link = 'always',
tertiary_link = 'always'}
}
-- name tags
module.NAME_TAGS = {}
module.NAME_TAGS.core = {main = {'name', 'name:*',
'int_name', 'int_name:*',
'reg_name', 'reg_name:*',
'loc_name', 'loc_name:*',
'old_name', 'old_name:*',
'alt_name', 'alt_name:*', 'alt_name_*',
'official_name', 'official_name:*',
'place_name', 'place_name:*',
'short_name', 'short_name:*'},
extra = {'ref', 'int_ref', 'nat_ref', 'reg_ref',
'loc_ref', 'old_ref', 'ISO3166-2'}
}
module.NAME_TAGS.address = {house = {'addr:housename'}}
module.NAME_TAGS.poi = group_merge({main = {'brand'},
extra = {'iata', 'icao', 'faa'}},
module.NAME_TAGS.core)
-- Address tagging
module.ADDRESS_TAGS = {}
module.ADDRESS_TAGS.core = { extra = {'addr:*', 'is_in:*', 'tiger:county'},
postcode = {'postal_code', 'postcode', 'addr:postcode',
'tiger:zip_left', 'tiger:zip_right'},
country = {'country_code', 'ISO3166-1',
'addr:country_code', 'is_in:country_code',
'addr:country', 'is_in:country'}
}
module.ADDRESS_TAGS.houses = { main = {'addr:housenumber',
'addr:conscriptionnumber',
'addr:streetnumber'},
interpolation = {'addr:interpolation'}
}
-- Ignored tags (prefiltered away)
module.IGNORE_KEYS = {}
module.IGNORE_KEYS.metatags = {'note', 'note:*', 'source', 'source:*', '*source',
'attribution', 'comment', 'fixme', 'created_by',
'tiger:cfcc', 'tiger:reviewed', 'nysgissam:*',
'NHD:*', 'nhd:*', 'gnis:*', 'geobase:*', 'yh:*',
'osak:*', 'naptan:*', 'CLC:*', 'import', 'it:fvg:*',
'lacounty:*', 'ref:linz:*', 'survey:*',
'ref:bygningsnr', 'ref:ruian:*', 'building:ruian:type',
'type',
'is_in:postcode'}
module.IGNORE_KEYS.name = {'*:prefix', '*:suffix', 'name:prefix:*', 'name:suffix:*',
'name:etymology', 'name:etymology:*',
'name:signed', 'name:botanical'}
module.IGNORE_KEYS.address = {'addr:street:*', 'addr:city:*', 'addr:district:*',
'addr:province:*', 'addr:subdistrict:*', 'addr:place:*',
'addr:TW:dataset'}
-- INTERNAL: Required extra tags
module.EXTRATAGS = {keys = {'wikipedia', 'wikipedia:*', 'wikidata', 'capital'}}
-- Defaults for the entrance table
module.ENTRANCE_TABLE = {}
module.ENTRANCE_TABLE.default = {main_tags = {'entrance', 'routing:entrance'},
extra_exclude = module.IGNORE_KEYS.metatags}
return module

View File

@@ -0,0 +1,22 @@
local _, flex, cfg = ...
flex.set_main_tags('admin')
flex.modify_main_tags('street/' .. (cfg.street_theme or 'default'))
flex.modify_main_tags{boundary = {postal_code = 'always'}}
flex.set_name_tags('core')
flex.modify_name_tags('address')
flex.set_address_tags('core')
flex.modify_address_tags('houses')
flex.ignore_keys('metatags')
if cfg.with_extratags then
flex.set_unused_handling{delete_keys = {'tiger:*'}}
flex.add_for_extratags('name')
flex.add_for_extratags('address')
else
flex.ignore_keys('name')
flex.ignore_keys('address')
end

View File

@@ -0,0 +1,19 @@
local _, flex, cfg = ...
flex.set_main_tags('admin')
flex.set_name_tags('core')
flex.set_address_tags('core')
flex.set_postcode_fallback(false)
flex.ignore_keys('metatags')
if cfg.with_extratags then
flex.set_unused_handling{delete_keys = {'tiger:*'}}
flex.add_for_extratags('name')
flex.add_for_extratags('address')
else
flex.ignore_keys('name')
flex.ignore_keys('address')
end

View File

@@ -0,0 +1,33 @@
local _, flex, cfg = ...
local group
if cfg.with_extratags then
group = 'extra'
else
group = 'delete'
end
flex.set_main_tags('all_boundaries')
flex.modify_main_tags('natural')
flex.modify_main_tags('street/' .. (cfg.street_theme or 'default'))
flex.modify_main_tags('poi/' .. group)
flex.set_name_tags('core')
flex.modify_name_tags('address')
flex.modify_name_tags('poi')
flex.set_address_tags('core')
flex.modify_address_tags('houses')
flex.ignore_keys('metatags')
if cfg.with_extratags then
flex.set_unused_handling{delete_keys = {'tiger:*'}}
flex.add_for_extratags('name')
flex.add_for_extratags('address')
else
flex.ignore_keys('name')
flex.ignore_keys('address')
end
flex.set_entrance_filter('default')

View File

@@ -0,0 +1,21 @@
local _, flex, cfg = ...
flex.set_main_tags('admin')
flex.modify_main_tags('street/' .. (cfg.street_theme or 'default'))
flex.modify_main_tags{boundary = {postal_code = 'always'}}
flex.set_name_tags('core')
flex.set_address_tags('core')
flex.set_postcode_fallback(false)
flex.ignore_keys('metatags')
if cfg.with_extratags then
flex.set_unused_handling{delete_keys = {'tiger:*'}}
flex.add_for_extratags('name')
flex.add_for_extratags('address')
else
flex.ignore_keys('name')
flex.ignore_keys('address')
end

View File

@@ -1,191 +0,0 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
require_once(CONST_LibDir.'/ClassTypes.php');
/**
* Detailed list of address parts for a single result
*/
class AddressDetails
{
private $iPlaceID;
private $aAddressLines;
public function __construct(&$oDB, $iPlaceID, $sHousenumber, $mLangPref)
{
$this->iPlaceID = $iPlaceID;
if (is_array($mLangPref)) {
$mLangPref = $oDB->getArraySQL($oDB->getDBQuotedList($mLangPref));
}
if (!isset($sHousenumber)) {
$sHousenumber = -1;
}
$sSQL = 'SELECT *,';
$sSQL .= ' get_name_by_language(name,'.$mLangPref.') as localname';
$sSQL .= ' FROM get_addressdata('.$iPlaceID.','.$sHousenumber.')';
$sSQL .= ' ORDER BY rank_address DESC, isaddress DESC';
$this->aAddressLines = $oDB->getAll($sSQL);
}
private static function isAddress($aLine)
{
return $aLine['isaddress'] || $aLine['type'] == 'country_code';
}
public function getAddressDetails($bAll = false)
{
if ($bAll) {
return $this->aAddressLines;
}
return array_filter($this->aAddressLines, array(__CLASS__, 'isAddress'));
}
public function getLocaleAddress()
{
$aParts = array();
$sPrevResult = '';
foreach ($this->aAddressLines as $aLine) {
if ($aLine['isaddress'] && $sPrevResult != $aLine['localname']) {
$sPrevResult = $aLine['localname'];
$aParts[] = $sPrevResult;
}
}
return join(', ', $aParts);
}
public function getAddressNames()
{
$aAddress = array();
foreach ($this->aAddressLines as $aLine) {
if (!self::isAddress($aLine)) {
continue;
}
$sTypeLabel = ClassTypes\getLabelTag($aLine);
$sName = null;
if (isset($aLine['localname']) && $aLine['localname']!=='') {
$sName = $aLine['localname'];
} elseif (isset($aLine['housenumber']) && $aLine['housenumber']!=='') {
$sName = $aLine['housenumber'];
}
if (isset($sName)
&& (!isset($aAddress[$sTypeLabel])
|| $aLine['class'] == 'place')
) {
$aAddress[$sTypeLabel] = $sName;
if (!empty($aLine['name'])) {
$this->addSubdivisionCode($aAddress, $aLine['admin_level'], $aLine['name']);
}
}
}
return $aAddress;
}
/**
* Annotates the given json with geocodejson address information fields.
*
* @param array $aJson Json hash to add the fields to.
*
* Geocodejson has the following fields:
* street, locality, postcode, city, district,
* county, state, country
*
* Postcode and housenumber are added by type, district is not used.
* All other fields are set according to address rank.
*/
public function addGeocodeJsonAddressParts(&$aJson)
{
foreach (array_reverse($this->aAddressLines) as $aLine) {
if (!$aLine['isaddress']) {
continue;
}
if (!isset($aLine['localname']) || $aLine['localname'] == '') {
continue;
}
if ($aLine['type'] == 'postcode' || $aLine['type'] == 'postal_code') {
$aJson['postcode'] = $aLine['localname'];
continue;
}
if ($aLine['type'] == 'house_number') {
$aJson['housenumber'] = $aLine['localname'];
continue;
}
if ($this->iPlaceID == $aLine['place_id']) {
continue;
}
$iRank = (int)$aLine['rank_address'];
if ($iRank > 25 && $iRank < 28) {
$aJson['street'] = $aLine['localname'];
} elseif ($iRank >= 22 && $iRank <= 25) {
$aJson['locality'] = $aLine['localname'];
} elseif ($iRank >= 17 && $iRank <= 21) {
$aJson['district'] = $aLine['localname'];
} elseif ($iRank >= 13 && $iRank <= 16) {
$aJson['city'] = $aLine['localname'];
} elseif ($iRank >= 10 && $iRank <= 12) {
$aJson['county'] = $aLine['localname'];
} elseif ($iRank >= 5 && $iRank <= 9) {
$aJson['state'] = $aLine['localname'];
} elseif ($iRank == 4) {
$aJson['country'] = $aLine['localname'];
}
}
}
public function getAdminLevels()
{
$aAddress = array();
foreach (array_reverse($this->aAddressLines) as $aLine) {
if (self::isAddress($aLine)
&& isset($aLine['admin_level'])
&& $aLine['admin_level'] < 15
&& !isset($aAddress['level'.$aLine['admin_level']])
) {
$aAddress['level'.$aLine['admin_level']] = $aLine['localname'];
}
}
return $aAddress;
}
public function debugInfo()
{
return $this->aAddressLines;
}
private function addSubdivisionCode(&$aAddress, $iAdminLevel, $nameDetails)
{
if (is_string($nameDetails)) {
$nameDetails = json_decode('{' . str_replace('"=>"', '":"', $nameDetails) . '}', true);
}
if (!empty($nameDetails['ISO3166-2'])) {
$aAddress["ISO3166-2-lvl$iAdminLevel"] = $nameDetails['ISO3166-2'];
}
}
}

View File

@@ -1,576 +0,0 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim\ClassTypes;
/**
* Create a label tag for the given place that can be used as an XML name.
*
* @param array[] $aPlace Information about the place to label.
*
* A label tag groups various object types together under a common
* label. The returned value is lower case and has no spaces
*/
function getLabelTag($aPlace, $sCountry = null)
{
$iRank = (int) ($aPlace['rank_address'] ?? 30);
$sLabel;
if (isset($aPlace['place_type'])) {
$sLabel = $aPlace['place_type'];
} elseif ($aPlace['class'] == 'boundary' && $aPlace['type'] == 'administrative') {
$sLabel = getBoundaryLabel($iRank/2, $sCountry);
} elseif ($aPlace['type'] == 'postal_code') {
$sLabel = 'postcode';
} elseif ($iRank < 26) {
$sLabel = $aPlace['type'];
} elseif ($iRank < 28) {
$sLabel = 'road';
} elseif ($aPlace['class'] == 'place'
&& ($aPlace['type'] == 'house_number' ||
$aPlace['type'] == 'house_name' ||
$aPlace['type'] == 'country_code')
) {
$sLabel = $aPlace['type'];
} else {
$sLabel = $aPlace['class'];
}
return strtolower(str_replace(' ', '_', $sLabel));
}
/**
* Create a label for the given place.
*
* @param array[] $aPlace Information about the place to label.
*/
function getLabel($aPlace, $sCountry = null)
{
if (isset($aPlace['place_type'])) {
return ucwords(str_replace('_', ' ', $aPlace['place_type']));
}
if ($aPlace['class'] == 'boundary' && $aPlace['type'] == 'administrative') {
return getBoundaryLabel(($aPlace['rank_address'] ?? 30)/2, $sCountry ?? null);
}
// Return a label only for 'important' class/type combinations
if (getImportance($aPlace) !== null) {
return ucwords(str_replace('_', ' ', $aPlace['type']));
}
return null;
}
/**
* Return a simple label for an administrative boundary for the given country.
*
* @param int $iAdminLevel Content of admin_level tag.
* @param string $sCountry Country code of the country where the object is
* in. May be null, in which case a world-wide
* fallback is used.
* @param string $sFallback String to return if no explicit string is listed.
*
* @return string
*/
function getBoundaryLabel($iAdminLevel, $sCountry, $sFallback = 'Administrative')
{
static $aBoundaryList = array (
'default' => array (
1 => 'Continent',
2 => 'Country',
3 => 'Region',
4 => 'State',
5 => 'State District',
6 => 'County',
7 => 'Municipality',
8 => 'City',
9 => 'City District',
10 => 'Suburb',
11 => 'Neighbourhood',
12 => 'City Block'
),
'no' => array (
3 => 'State',
4 => 'County'
),
'se' => array (
3 => 'State',
4 => 'County'
)
);
if (isset($aBoundaryList[$sCountry])
&& isset($aBoundaryList[$sCountry][$iAdminLevel])
) {
return $aBoundaryList[$sCountry][$iAdminLevel];
}
return $aBoundaryList['default'][$iAdminLevel] ?? $sFallback;
}
/**
* Return an estimated radius of how far the object node extends.
*
* @param array[] $aPlace Information about the place. This must be a node
* feature.
*
* @return float The radius around the feature in degrees.
*/
function getDefRadius($aPlace)
{
$aSpecialRadius = array(
'place:continent' => 25,
'place:country' => 7,
'place:state' => 2.6,
'place:province' => 2.6,
'place:region' => 1.0,
'place:county' => 0.7,
'place:city' => 0.16,
'place:municipality' => 0.16,
'place:island' => 0.32,
'place:postcode' => 0.16,
'place:town' => 0.04,
'place:village' => 0.02,
'place:hamlet' => 0.02,
'place:district' => 0.02,
'place:borough' => 0.02,
'place:suburb' => 0.02,
'place:locality' => 0.01,
'place:neighbourhood'=> 0.01,
'place:quarter' => 0.01,
'place:city_block' => 0.01,
'landuse:farm' => 0.01,
'place:farm' => 0.01,
'place:airport' => 0.015,
'aeroway:aerodrome' => 0.015,
'railway:station' => 0.005
);
$sClassPlace = $aPlace['class'].':'.$aPlace['type'];
return $aSpecialRadius[$sClassPlace] ?? 0.00005;
}
/**
* Get the icon to use with the given object.
*/
function getIcon($aPlace)
{
$aIcons = array(
'boundary:administrative' => 'poi_boundary_administrative',
'place:city' => 'poi_place_city',
'place:town' => 'poi_place_town',
'place:village' => 'poi_place_village',
'place:hamlet' => 'poi_place_village',
'place:suburb' => 'poi_place_village',
'place:locality' => 'poi_place_village',
'place:airport' => 'transport_airport2',
'aeroway:aerodrome' => 'transport_airport2',
'railway:station' => 'transport_train_station2',
'amenity:place_of_worship' => 'place_of_worship_unknown3',
'amenity:pub' => 'food_pub',
'amenity:bar' => 'food_bar',
'amenity:university' => 'education_university',
'tourism:museum' => 'tourist_museum',
'amenity:arts_centre' => 'tourist_art_gallery2',
'tourism:zoo' => 'tourist_zoo',
'tourism:theme_park' => 'poi_point_of_interest',
'tourism:attraction' => 'poi_point_of_interest',
'leisure:golf_course' => 'sport_golf',
'historic:castle' => 'tourist_castle',
'amenity:hospital' => 'health_hospital',
'amenity:school' => 'education_school',
'amenity:theatre' => 'tourist_theatre',
'amenity:library' => 'amenity_library',
'amenity:fire_station' => 'amenity_firestation3',
'amenity:police' => 'amenity_police2',
'amenity:bank' => 'money_bank2',
'amenity:post_office' => 'amenity_post_office',
'tourism:hotel' => 'accommodation_hotel2',
'amenity:cinema' => 'tourist_cinema',
'tourism:artwork' => 'tourist_art_gallery2',
'historic:archaeological_site' => 'tourist_archaeological2',
'amenity:doctors' => 'health_doctors',
'leisure:sports_centre' => 'sport_leisure_centre',
'leisure:swimming_pool' => 'sport_swimming_outdoor',
'shop:supermarket' => 'shopping_supermarket',
'shop:convenience' => 'shopping_convenience',
'amenity:restaurant' => 'food_restaurant',
'amenity:fast_food' => 'food_fastfood',
'amenity:cafe' => 'food_cafe',
'tourism:guest_house' => 'accommodation_bed_and_breakfast',
'amenity:pharmacy' => 'health_pharmacy_dispensing',
'amenity:fuel' => 'transport_fuel',
'natural:peak' => 'poi_peak',
'natural:wood' => 'landuse_coniferous_and_deciduous',
'shop:bicycle' => 'shopping_bicycle',
'shop:clothes' => 'shopping_clothes',
'shop:hairdresser' => 'shopping_hairdresser',
'shop:doityourself' => 'shopping_diy',
'shop:estate_agent' => 'shopping_estateagent2',
'shop:car' => 'shopping_car',
'shop:garden_centre' => 'shopping_garden_centre',
'shop:car_repair' => 'shopping_car_repair',
'shop:bakery' => 'shopping_bakery',
'shop:butcher' => 'shopping_butcher',
'shop:apparel' => 'shopping_clothes',
'shop:laundry' => 'shopping_laundrette',
'shop:beverages' => 'shopping_alcohol',
'shop:alcohol' => 'shopping_alcohol',
'shop:optician' => 'health_opticians',
'shop:chemist' => 'health_pharmacy',
'shop:gallery' => 'tourist_art_gallery2',
'shop:jewelry' => 'shopping_jewelry',
'tourism:information' => 'amenity_information',
'historic:ruins' => 'tourist_ruin',
'amenity:college' => 'education_school',
'historic:monument' => 'tourist_monument',
'historic:memorial' => 'tourist_monument',
'historic:mine' => 'poi_mine',
'tourism:caravan_site' => 'accommodation_caravan_park',
'amenity:bus_station' => 'transport_bus_station',
'amenity:atm' => 'money_atm2',
'tourism:viewpoint' => 'tourist_view_point',
'tourism:guesthouse' => 'accommodation_bed_and_breakfast',
'railway:tram' => 'transport_tram_stop',
'amenity:courthouse' => 'amenity_court',
'amenity:recycling' => 'amenity_recycling',
'amenity:dentist' => 'health_dentist',
'natural:beach' => 'tourist_beach',
'railway:tram_stop' => 'transport_tram_stop',
'amenity:prison' => 'amenity_prison',
'highway:bus_stop' => 'transport_bus_stop2'
);
$sClassPlace = $aPlace['class'].':'.$aPlace['type'];
return $aIcons[$sClassPlace] ?? null;
}
/**
* Get an icon for the given object with its full URL.
*/
function getIconFile($aPlace)
{
if (CONST_MapIcon_URL === false) {
return null;
}
$sIcon = getIcon($aPlace);
if (!isset($sIcon)) {
return null;
}
return CONST_MapIcon_URL.'/'.$sIcon.'.p.20.png';
}
/**
* Return a class importance value for the given place.
*
* @param array[] $aPlace Information about the place.
*
* @return int An importance value. The lower the value, the more
* important the class.
*/
function getImportance($aPlace)
{
static $aWithImportance = null;
if ($aWithImportance === null) {
$aWithImportance = array_flip(array(
'boundary:administrative',
'place:country',
'place:state',
'place:province',
'place:county',
'place:city',
'place:region',
'place:island',
'place:town',
'place:village',
'place:hamlet',
'place:suburb',
'place:locality',
'landuse:farm',
'place:farm',
'highway:motorway_junction',
'highway:motorway',
'highway:trunk',
'highway:primary',
'highway:secondary',
'highway:tertiary',
'highway:residential',
'highway:unclassified',
'highway:living_street',
'highway:service',
'highway:track',
'highway:road',
'highway:byway',
'highway:bridleway',
'highway:cycleway',
'highway:pedestrian',
'highway:footway',
'highway:steps',
'highway:motorway_link',
'highway:trunk_link',
'highway:primary_link',
'landuse:industrial',
'landuse:residential',
'landuse:retail',
'landuse:commercial',
'place:airport',
'aeroway:aerodrome',
'railway:station',
'amenity:place_of_worship',
'amenity:pub',
'amenity:bar',
'amenity:university',
'tourism:museum',
'amenity:arts_centre',
'tourism:zoo',
'tourism:theme_park',
'tourism:attraction',
'leisure:golf_course',
'historic:castle',
'amenity:hospital',
'amenity:school',
'amenity:theatre',
'amenity:public_building',
'amenity:library',
'amenity:townhall',
'amenity:community_centre',
'amenity:fire_station',
'amenity:police',
'amenity:bank',
'amenity:post_office',
'leisure:park',
'amenity:park',
'landuse:park',
'landuse:recreation_ground',
'tourism:hotel',
'tourism:motel',
'amenity:cinema',
'tourism:artwork',
'historic:archaeological_site',
'amenity:doctors',
'leisure:sports_centre',
'leisure:swimming_pool',
'shop:supermarket',
'shop:convenience',
'amenity:restaurant',
'amenity:fast_food',
'amenity:cafe',
'tourism:guest_house',
'amenity:pharmacy',
'amenity:fuel',
'natural:peak',
'waterway:waterfall',
'natural:wood',
'natural:water',
'landuse:forest',
'landuse:cemetery',
'landuse:allotments',
'landuse:farmyard',
'railway:rail',
'waterway:canal',
'waterway:river',
'waterway:stream',
'shop:bicycle',
'shop:clothes',
'shop:hairdresser',
'shop:doityourself',
'shop:estate_agent',
'shop:car',
'shop:garden_centre',
'shop:car_repair',
'shop:newsagent',
'shop:bakery',
'shop:furniture',
'shop:butcher',
'shop:apparel',
'shop:electronics',
'shop:department_store',
'shop:books',
'shop:yes',
'shop:outdoor',
'shop:mall',
'shop:florist',
'shop:charity',
'shop:hardware',
'shop:laundry',
'shop:shoes',
'shop:beverages',
'shop:dry_cleaning',
'shop:carpet',
'shop:computer',
'shop:alcohol',
'shop:optician',
'shop:chemist',
'shop:gallery',
'shop:mobile_phone',
'shop:sports',
'shop:jewelry',
'shop:pet',
'shop:beauty',
'shop:stationery',
'shop:shopping_centre',
'shop:general',
'shop:electrical',
'shop:toys',
'shop:jeweller',
'shop:betting',
'shop:household',
'shop:travel_agency',
'shop:hifi',
'amenity:shop',
'tourism:information',
'place:house',
'place:house_name',
'place:house_number',
'place:country_code',
'leisure:pitch',
'highway:unsurfaced',
'historic:ruins',
'amenity:college',
'historic:monument',
'railway:subway',
'historic:memorial',
'leisure:nature_reserve',
'leisure:common',
'waterway:lock_gate',
'natural:fell',
'amenity:nightclub',
'highway:path',
'leisure:garden',
'landuse:reservoir',
'leisure:playground',
'leisure:stadium',
'historic:mine',
'natural:cliff',
'tourism:caravan_site',
'amenity:bus_station',
'amenity:kindergarten',
'highway:construction',
'amenity:atm',
'amenity:emergency_phone',
'waterway:lock',
'waterway:riverbank',
'natural:coastline',
'tourism:viewpoint',
'tourism:hostel',
'tourism:bed_and_breakfast',
'railway:halt',
'railway:platform',
'railway:tram',
'amenity:courthouse',
'amenity:recycling',
'amenity:dentist',
'natural:beach',
'place:moor',
'amenity:grave_yard',
'waterway:drain',
'landuse:grass',
'landuse:village_green',
'natural:bay',
'railway:tram_stop',
'leisure:marina',
'highway:stile',
'natural:moor',
'railway:light_rail',
'railway:narrow_gauge',
'natural:land',
'amenity:village_hall',
'waterway:dock',
'amenity:veterinary',
'landuse:brownfield',
'leisure:track',
'railway:historic_station',
'landuse:construction',
'amenity:prison',
'landuse:quarry',
'amenity:telephone',
'highway:traffic_signals',
'natural:heath',
'historic:house',
'amenity:social_club',
'landuse:military',
'amenity:health_centre',
'historic:building',
'amenity:clinic',
'highway:services',
'amenity:ferry_terminal',
'natural:marsh',
'natural:hill',
'highway:raceway',
'amenity:taxi',
'amenity:take_away',
'amenity:car_rental',
'place:islet',
'amenity:nursery',
'amenity:nursing_home',
'amenity:toilets',
'amenity:hall',
'waterway:boatyard',
'highway:mini_roundabout',
'historic:manor',
'tourism:chalet',
'amenity:bicycle_parking',
'amenity:hotel',
'waterway:weir',
'natural:wetland',
'natural:cave_entrance',
'amenity:crematorium',
'tourism:picnic_site',
'landuse:wood',
'landuse:basin',
'natural:tree',
'leisure:slipway',
'landuse:meadow',
'landuse:piste',
'amenity:care_home',
'amenity:club',
'amenity:medical_centre',
'historic:roman_road',
'historic:fort',
'railway:subway_entrance',
'historic:yes',
'highway:gate',
'leisure:fishing',
'historic:museum',
'amenity:car_wash',
'railway:level_crossing',
'leisure:bird_hide',
'natural:headland',
'tourism:apartments',
'amenity:shopping',
'natural:scrub',
'natural:fen',
'building:yes',
'mountain_pass:yes',
'amenity:parking',
'highway:bus_stop',
'place:postcode',
'amenity:post_box',
'place:houses',
'railway:preserved',
'waterway:derelict_canal',
'amenity:dead_pub',
'railway:disused_station',
'railway:abandoned',
'railway:disused'
));
}
$sClassPlace = $aPlace['class'].':'.$aPlace['type'];
return $aWithImportance[$sClassPlace] ?? null;
}

View File

@@ -1,362 +0,0 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
require_once(CONST_LibDir.'/DatabaseError.php');
/**
* Uses PDO to access the database specified in the CONST_Database_DSN
* setting.
*/
class DB
{
protected $connection;
public function __construct($sDSN = null)
{
$this->sDSN = $sDSN ?? getSetting('DATABASE_DSN');
}
public function connect($bNew = false, $bPersistent = true)
{
if (isset($this->connection) && !$bNew) {
return true;
}
$aConnOptions = array(
\PDO::ATTR_ERRMODE => \PDO::ERRMODE_EXCEPTION,
\PDO::ATTR_DEFAULT_FETCH_MODE => \PDO::FETCH_ASSOC,
\PDO::ATTR_PERSISTENT => $bPersistent
);
// https://secure.php.net/manual/en/ref.pdo-pgsql.connection.php
try {
$this->connection = new \PDO($this->sDSN, null, null, $aConnOptions);
} catch (\PDOException $e) {
$sMsg = 'Failed to establish database connection:' . $e->getMessage();
throw new \Nominatim\DatabaseError($sMsg, 500, null, $e->getMessage());
}
$this->connection->exec("SET DateStyle TO 'sql,european'");
$this->connection->exec("SET client_encoding TO 'utf-8'");
// Disable JIT and parallel workers. They interfere badly with search SQL.
$this->connection->exec('SET max_parallel_workers_per_gather TO 0');
if ($this->getPostgresVersion() >= 11) {
$this->connection->exec('SET jit_above_cost TO -1');
}
$iMaxExecution = ini_get('max_execution_time');
if ($iMaxExecution > 0) {
$this->connection->setAttribute(\PDO::ATTR_TIMEOUT, $iMaxExecution); // seconds
}
return true;
}
// returns the number of rows that were modified or deleted by the SQL
// statement. If no rows were affected returns 0.
public function exec($sSQL, $aInputVars = null, $sErrMessage = 'Database query failed')
{
$val = null;
try {
if (isset($aInputVars)) {
$stmt = $this->connection->prepare($sSQL);
$stmt->execute($aInputVars);
} else {
$val = $this->connection->exec($sSQL);
}
} catch (\PDOException $e) {
throw new \Nominatim\DatabaseError($sErrMessage, 500, null, $e, $sSQL);
}
return $val;
}
/**
* Executes query. Returns first row as array.
* Returns false if no result found.
*
* @param string $sSQL
*
* @return array[]
*/
public function getRow($sSQL, $aInputVars = null, $sErrMessage = 'Database query failed')
{
try {
$stmt = $this->getQueryStatement($sSQL, $aInputVars, $sErrMessage);
$row = $stmt->fetch();
} catch (\PDOException $e) {
throw new \Nominatim\DatabaseError($sErrMessage, 500, null, $e, $sSQL);
}
return $row;
}
/**
* Executes query. Returns first value of first result.
* Returns false if no results found.
*
* @param string $sSQL
*
* @return array[]
*/
public function getOne($sSQL, $aInputVars = null, $sErrMessage = 'Database query failed')
{
try {
$stmt = $this->getQueryStatement($sSQL, $aInputVars, $sErrMessage);
$row = $stmt->fetch(\PDO::FETCH_NUM);
if ($row === false) {
return false;
}
} catch (\PDOException $e) {
throw new \Nominatim\DatabaseError($sErrMessage, 500, null, $e, $sSQL);
}
return $row[0];
}
/**
* Executes query. Returns array of results (arrays).
* Returns empty array if no results found.
*
* @param string $sSQL
*
* @return array[]
*/
public function getAll($sSQL, $aInputVars = null, $sErrMessage = 'Database query failed')
{
try {
$stmt = $this->getQueryStatement($sSQL, $aInputVars, $sErrMessage);
$rows = $stmt->fetchAll();
} catch (\PDOException $e) {
throw new \Nominatim\DatabaseError($sErrMessage, 500, null, $e, $sSQL);
}
return $rows;
}
/**
* Executes query. Returns array of the first value of each result.
* Returns empty array if no results found.
*
* @param string $sSQL
*
* @return array[]
*/
public function getCol($sSQL, $aInputVars = null, $sErrMessage = 'Database query failed')
{
$aVals = array();
try {
$stmt = $this->getQueryStatement($sSQL, $aInputVars, $sErrMessage);
while (($val = $stmt->fetchColumn(0)) !== false) { // returns first column or false
$aVals[] = $val;
}
} catch (\PDOException $e) {
throw new \Nominatim\DatabaseError($sErrMessage, 500, null, $e, $sSQL);
}
return $aVals;
}
/**
* Executes query. Returns associate array mapping first value to second value of each result.
* Returns empty array if no results found.
*
* @param string $sSQL
*
* @return array[]
*/
public function getAssoc($sSQL, $aInputVars = null, $sErrMessage = 'Database query failed')
{
try {
$stmt = $this->getQueryStatement($sSQL, $aInputVars, $sErrMessage);
$aList = array();
while ($aRow = $stmt->fetch(\PDO::FETCH_NUM)) {
$aList[$aRow[0]] = $aRow[1];
}
} catch (\PDOException $e) {
throw new \Nominatim\DatabaseError($sErrMessage, 500, null, $e, $sSQL);
}
return $aList;
}
/**
* Executes query. Returns a PDO statement to iterate over.
*
* @param string $sSQL
*
* @return PDOStatement
*/
public function getQueryStatement($sSQL, $aInputVars = null, $sErrMessage = 'Database query failed')
{
try {
if (isset($aInputVars)) {
$stmt = $this->connection->prepare($sSQL);
$stmt->execute($aInputVars);
} else {
$stmt = $this->connection->query($sSQL);
}
} catch (\PDOException $e) {
throw new \Nominatim\DatabaseError($sErrMessage, 500, null, $e, $sSQL);
}
return $stmt;
}
/**
* St. John's Way => 'St. John\'s Way'
*
* @param string $sVal Text to be quoted.
*
* @return string
*/
public function getDBQuoted($sVal)
{
return $this->connection->quote($sVal);
}
/**
* Like getDBQuoted, but takes an array.
*
* @param array $aVals List of text to be quoted.
*
* @return array[]
*/
public function getDBQuotedList($aVals)
{
return array_map(function ($sVal) {
return $this->getDBQuoted($sVal);
}, $aVals);
}
/**
* [1,2,'b'] => 'ARRAY[1,2,'b']''
*
* @param array $aVals List of text to be quoted.
*
* @return string
*/
public function getArraySQL($a)
{
return 'ARRAY['.join(',', $a).']';
}
/**
* Check if a table exists in the database. Returns true if it does.
*
* @param string $sTableName
*
* @return boolean
*/
public function tableExists($sTableName)
{
$sSQL = 'SELECT count(*) FROM pg_tables WHERE tablename = :tablename';
return ($this->getOne($sSQL, array(':tablename' => $sTableName)) == 1);
}
/**
* Deletes a table. Returns true if deleted or didn't exist.
*
* @param string $sTableName
*
* @return boolean
*/
public function deleteTable($sTableName)
{
return $this->exec('DROP TABLE IF EXISTS '.$sTableName.' CASCADE') == 0;
}
/**
* Tries to connect to the database but on failure doesn't throw an exception.
*
* @return boolean
*/
public function checkConnection()
{
$bExists = true;
try {
$this->connect(true);
} catch (\Nominatim\DatabaseError $e) {
$bExists = false;
}
return $bExists;
}
/**
* e.g. 9.6, 10, 11.2
*
* @return float
*/
public function getPostgresVersion()
{
$sVersionString = $this->getOne('SHOW server_version_num');
preg_match('#([0-9]?[0-9])([0-9][0-9])[0-9][0-9]#', $sVersionString, $aMatches);
return (float) ($aMatches[1].'.'.$aMatches[2]);
}
/**
* e.g. 2, 2.2
*
* @return float
*/
public function getPostgisVersion()
{
$sVersionString = $this->getOne('select postgis_lib_version()');
preg_match('#^([0-9]+)[.]([0-9]+)[.]#', $sVersionString, $aMatches);
return (float) ($aMatches[1].'.'.$aMatches[2]);
}
/**
* Returns an associate array of postgresql database connection settings. Keys can
* be 'database', 'hostspec', 'port', 'username', 'password'.
* Returns empty array on failure, thus check if at least 'database' is set.
*
* @return array[]
*/
public static function parseDSN($sDSN)
{
// https://secure.php.net/manual/en/ref.pdo-pgsql.connection.php
$aInfo = array();
if (preg_match('/^pgsql:(.+)$/', $sDSN, $aMatches)) {
foreach (explode(';', $aMatches[1]) as $sKeyVal) {
list($sKey, $sVal) = explode('=', $sKeyVal, 2);
if ($sKey == 'host') {
$sKey = 'hostspec';
} elseif ($sKey == 'dbname') {
$sKey = 'database';
} elseif ($sKey == 'user') {
$sKey = 'username';
}
$aInfo[$sKey] = $sVal;
}
}
return $aInfo;
}
/**
* Takes an array of settings and return the DNS string. Key names can be
* 'database', 'hostspec', 'port', 'username', 'password' but aliases
* 'dbname', 'host' and 'user' are also supported.
*
* @return string
*
*/
public static function generateDSN($aInfo)
{
$sDSN = sprintf(
'pgsql:host=%s;port=%s;dbname=%s;user=%s;password=%s;',
$aInfo['host'] ?? $aInfo['hostspec'] ?? '',
$aInfo['port'] ?? '',
$aInfo['dbname'] ?? $aInfo['database'] ?? '',
$aInfo['user'] ?? '',
$aInfo['password'] ?? ''
);
$sDSN = preg_replace('/\b\w+=;/', '', $sDSN);
$sDSN = preg_replace('/;\Z/', '', $sDSN);
return $sDSN;
}
}

View File

@@ -1,42 +0,0 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
class DatabaseError extends \Exception
{
public function __construct($message, $code, $previous, $oPDOErr, $sSql = null)
{
parent::__construct($message, $code, $previous);
// https://secure.php.net/manual/en/class.pdoexception.php
$this->oPDOErr = $oPDOErr;
$this->sSql = $sSql;
}
public function __toString()
{
return __CLASS__ . ": [{$this->code}]: {$this->message}\n";
}
public function getSqlError()
{
return $this->oPDOErr->getMessage();
}
public function getSqlDebugDump()
{
if (CONST_Debug) {
return var_export($this->oPDOErr, true);
} else {
return $this->sSql;
}
}
}

View File

@@ -1,189 +0,0 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
class Debug
{
public static function newFunction($sHeading)
{
echo "<pre><h2>Debug output for $sHeading</h2></pre>\n";
}
public static function newSection($sHeading)
{
echo "<hr><pre><h3>$sHeading</h3></pre>\n";
}
public static function printVar($sHeading, $mVar)
{
echo '<pre><b>'.$sHeading. ':</b> ';
Debug::outputVar($mVar, str_repeat(' ', strlen($sHeading) + 3));
echo "</pre>\n";
}
public static function fmtArrayVals($aArr)
{
return array('__debug_format' => 'array_vals', 'data' => $aArr);
}
public static function printDebugArray($sHeading, $oVar)
{
if ($oVar === null) {
Debug::printVar($sHeading, 'null');
} else {
Debug::printVar($sHeading, $oVar->debugInfo());
}
}
public static function printDebugTable($sHeading, $aVar)
{
echo '<b>'.$sHeading.":</b>\n";
echo "<table border='1'>\n";
if (!empty($aVar)) {
echo " <tr>\n";
$aKeys = array();
$aInfo = reset($aVar);
if (!is_array($aInfo)) {
$aInfo = $aInfo->debugInfo();
}
foreach ($aInfo as $sKey => $mVal) {
echo ' <th><small>'.$sKey.'</small></th>'."\n";
$aKeys[] = $sKey;
}
echo " </tr>\n";
foreach ($aVar as $oRow) {
$aInfo = $oRow;
if (!is_array($oRow)) {
$aInfo = $oRow->debugInfo();
}
echo " <tr>\n";
foreach ($aKeys as $sKey) {
echo ' <td><pre>';
if (isset($aInfo[$sKey])) {
Debug::outputVar($aInfo[$sKey], '');
}
echo '</pre></td>'."\n";
}
echo " </tr>\n";
}
}
echo "</table>\n";
}
public static function printGroupedSearch($aSearches, $aWordsIDs)
{
echo '<table border="1">';
echo '<tr><th>rank</th><th>Name Tokens</th><th>Name Not</th>';
echo '<th>Address Tokens</th><th>Address Not</th>';
echo '<th>country</th><th>operator</th>';
echo '<th>class</th><th>type</th><th>postcode</th><th>housenumber</th></tr>';
foreach ($aSearches as $aRankedSet) {
foreach ($aRankedSet as $aRow) {
$aRow->dumpAsHtmlTableRow($aWordsIDs);
}
}
echo '</table>';
}
public static function printGroupTable($sHeading, $aVar)
{
echo '<b>'.$sHeading.":</b>\n";
echo "<table border='1'>\n";
if (!empty($aVar)) {
echo " <tr>\n";
echo ' <th><small>Group</small></th>'."\n";
$aKeys = array();
$aInfo = reset($aVar)[0];
if (!is_array($aInfo)) {
$aInfo = $aInfo->debugInfo();
}
foreach ($aInfo as $sKey => $mVal) {
echo ' <th><small>'.$sKey.'</small></th>'."\n";
$aKeys[] = $sKey;
}
echo " </tr>\n";
foreach ($aVar as $sGrpKey => $aGroup) {
foreach ($aGroup as $oRow) {
$aInfo = $oRow;
if (!is_array($oRow)) {
$aInfo = $oRow->debugInfo();
}
echo " <tr>\n";
echo ' <td><pre>'.$sGrpKey.'</pre></td>'."\n";
foreach ($aKeys as $sKey) {
echo ' <td><pre>';
if (!empty($aInfo[$sKey])) {
Debug::outputVar($aInfo[$sKey], '');
}
echo '</pre></td>'."\n";
}
echo " </tr>\n";
}
}
}
echo "</table>\n";
}
public static function printSQL($sSQL)
{
echo '<p><tt><b>'.date('c').'</b> <font color="#aaa">'.htmlspecialchars($sSQL, ENT_QUOTES | ENT_SUBSTITUTE | ENT_HTML401).'</font></tt></p>'."\n";
}
private static function outputVar($mVar, $sPreNL)
{
if (is_array($mVar) && !isset($mVar['__debug_format'])) {
$sPre = '';
foreach ($mVar as $mKey => $aValue) {
echo $sPre;
$iKeyLen = Debug::outputSimpleVar($mKey);
echo ' => ';
Debug::outputVar(
$aValue,
$sPreNL.str_repeat(' ', $iKeyLen + 4)
);
$sPre = "\n".$sPreNL;
}
} elseif (is_array($mVar) && isset($mVar['__debug_format'])) {
if (!empty($mVar['data'])) {
$sPre = '';
foreach ($mVar['data'] as $mValue) {
echo $sPre;
Debug::outputSimpleVar($mValue);
$sPre = ', ';
}
}
} elseif (is_object($mVar) && method_exists($mVar, 'debugInfo')) {
Debug::outputVar($mVar->debugInfo(), $sPreNL);
} elseif (is_a($mVar, 'stdClass')) {
Debug::outputVar(json_decode(json_encode($mVar), true), $sPreNL);
} else {
Debug::outputSimpleVar($mVar);
}
}
private static function outputSimpleVar($mVar)
{
if (is_bool($mVar)) {
echo '<i>'.($mVar ? 'True' : 'False').'</i>';
return $mVar ? 4 : 5;
}
if (is_string($mVar)) {
$sOut = "'$mVar'";
} else {
$sOut = (string)$mVar;
}
echo htmlspecialchars($sOut, ENT_QUOTES | ENT_SUBSTITUTE | ENT_HTML401);
return strlen($sOut);
}
}

View File

@@ -1,19 +0,0 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
class Debug
{
public static function __callStatic($name, $arguments)
{
// nothing
}
}

View File

@@ -1,938 +0,0 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
require_once(CONST_LibDir.'/PlaceLookup.php');
require_once(CONST_LibDir.'/Phrase.php');
require_once(CONST_LibDir.'/ReverseGeocode.php');
require_once(CONST_LibDir.'/SearchDescription.php');
require_once(CONST_LibDir.'/SearchContext.php');
require_once(CONST_LibDir.'/SearchPosition.php');
require_once(CONST_LibDir.'/TokenList.php');
require_once(CONST_TokenizerDir.'/tokenizer.php');
class Geocode
{
protected $oDB;
protected $oPlaceLookup;
protected $oTokenizer;
protected $aLangPrefOrder = array();
protected $aExcludePlaceIDs = array();
protected $iLimit = 20;
protected $iFinalLimit = 10;
protected $iOffset = 0;
protected $bFallback = false;
protected $aCountryCodes = false;
protected $bBoundedSearch = false;
protected $aViewBox = false;
protected $aRoutePoints = false;
protected $aRouteWidth = false;
protected $iMaxRank = 20;
protected $iMinAddressRank = 0;
protected $iMaxAddressRank = 30;
protected $aAddressRankList = array();
protected $sAllowedTypesSQLList = false;
protected $sQuery = false;
protected $aStructuredQuery = false;
public function __construct(&$oDB)
{
$this->oDB =& $oDB;
$this->oPlaceLookup = new PlaceLookup($this->oDB);
$this->oTokenizer = new \Nominatim\Tokenizer($this->oDB);
}
public function setLanguagePreference($aLangPref)
{
$this->aLangPrefOrder = $aLangPref;
}
public function getMoreUrlParams()
{
if ($this->aStructuredQuery) {
$aParams = $this->aStructuredQuery;
} else {
$aParams = array('q' => $this->sQuery);
}
$aParams = array_merge($aParams, $this->oPlaceLookup->getMoreUrlParams());
if ($this->aExcludePlaceIDs) {
$aParams['exclude_place_ids'] = implode(',', $this->aExcludePlaceIDs);
}
if ($this->bBoundedSearch) {
$aParams['bounded'] = '1';
}
if ($this->aCountryCodes) {
$aParams['countrycodes'] = implode(',', $this->aCountryCodes);
}
if ($this->aViewBox) {
$aParams['viewbox'] = join(',', $this->aViewBox);
}
return $aParams;
}
public function setLimit($iLimit = 10)
{
if ($iLimit > 50) {
$iLimit = 50;
} elseif ($iLimit < 1) {
$iLimit = 1;
}
$this->iFinalLimit = $iLimit;
$this->iLimit = $iLimit + max($iLimit, 10);
}
public function setFeatureType($sFeatureType)
{
switch ($sFeatureType) {
case 'country':
$this->setRankRange(4, 4);
break;
case 'state':
$this->setRankRange(8, 8);
break;
case 'city':
$this->setRankRange(14, 16);
break;
case 'settlement':
$this->setRankRange(8, 20);
break;
}
}
public function setRankRange($iMin, $iMax)
{
$this->iMinAddressRank = $iMin;
$this->iMaxAddressRank = $iMax;
}
public function setViewbox($aViewbox)
{
$aBox = array_map('floatval', $aViewbox);
$this->aViewBox[0] = max(-180.0, min($aBox[0], $aBox[2]));
$this->aViewBox[1] = max(-90.0, min($aBox[1], $aBox[3]));
$this->aViewBox[2] = min(180.0, max($aBox[0], $aBox[2]));
$this->aViewBox[3] = min(90.0, max($aBox[1], $aBox[3]));
if ($this->aViewBox[2] - $this->aViewBox[0] < 0.000000001
|| $this->aViewBox[3] - $this->aViewBox[1] < 0.000000001
) {
userError("Bad parameter 'viewbox'. Not a box.");
}
}
private function viewboxImportanceFactor($fX, $fY)
{
if (!$this->aViewBox) {
return 1;
}
$fWidth = ($this->aViewBox[2] - $this->aViewBox[0])/2;
$fHeight = ($this->aViewBox[3] - $this->aViewBox[1])/2;
$fXDist = abs($fX - ($this->aViewBox[0] + $this->aViewBox[2])/2);
$fYDist = abs($fY - ($this->aViewBox[1] + $this->aViewBox[3])/2);
if ($fXDist <= $fWidth && $fYDist <= $fHeight) {
return 1;
}
if ($fXDist <= $fWidth * 3 && $fYDist <= 3 * $fHeight) {
return 0.5;
}
return 0.25;
}
public function setQuery($sQueryString)
{
$this->sQuery = $sQueryString;
$this->aStructuredQuery = false;
}
public function getQueryString()
{
return $this->sQuery;
}
public function loadParamArray($oParams, $sForceGeometryType = null)
{
$this->bBoundedSearch = $oParams->getBool('bounded', $this->bBoundedSearch);
$this->setLimit($oParams->getInt('limit', $this->iFinalLimit));
$this->iOffset = $oParams->getInt('offset', $this->iOffset);
$this->bFallback = $oParams->getBool('fallback', $this->bFallback);
// List of excluded Place IDs - used for more accurate pageing
$sExcluded = $oParams->getStringList('exclude_place_ids');
if ($sExcluded) {
foreach ($sExcluded as $iExcludedPlaceID) {
$iExcludedPlaceID = (int)$iExcludedPlaceID;
if ($iExcludedPlaceID) {
$aExcludePlaceIDs[$iExcludedPlaceID] = $iExcludedPlaceID;
}
}
if (isset($aExcludePlaceIDs)) {
$this->aExcludePlaceIDs = $aExcludePlaceIDs;
}
}
// Only certain ranks of feature
$sFeatureType = $oParams->getString('featureType');
if (!$sFeatureType) {
$sFeatureType = $oParams->getString('featuretype');
}
if ($sFeatureType) {
$this->setFeatureType($sFeatureType);
}
// Country code list
$sCountries = $oParams->getStringList('countrycodes');
if ($sCountries) {
foreach ($sCountries as $sCountryCode) {
if (preg_match('/^[a-zA-Z][a-zA-Z]$/', $sCountryCode)) {
$aCountries[] = strtolower($sCountryCode);
}
}
if (isset($aCountries)) {
$this->aCountryCodes = $aCountries;
}
}
$aViewbox = $oParams->getStringList('viewboxlbrt');
if ($aViewbox) {
if (count($aViewbox) != 4) {
userError("Bad parameter 'viewboxlbrt'. Expected 4 coordinates.");
}
$this->setViewbox($aViewbox);
} else {
$aViewbox = $oParams->getStringList('viewbox');
if ($aViewbox) {
if (count($aViewbox) != 4) {
userError("Bad parameter 'viewbox'. Expected 4 coordinates.");
}
$this->setViewBox($aViewbox);
} else {
$aRoute = $oParams->getStringList('route');
$fRouteWidth = $oParams->getFloat('routewidth');
if ($aRoute && $fRouteWidth) {
$this->aRoutePoints = $aRoute;
$this->aRouteWidth = $fRouteWidth;
}
}
}
$this->oPlaceLookup->loadParamArray($oParams, $sForceGeometryType);
$this->oPlaceLookup->setIncludeAddressDetails($oParams->getBool('addressdetails', false));
}
public function setQueryFromParams($oParams)
{
// Search query
$sQuery = $oParams->getString('q');
if (!$sQuery) {
$this->setStructuredQuery(
$oParams->getString('amenity'),
$oParams->getString('street'),
$oParams->getString('city'),
$oParams->getString('county'),
$oParams->getString('state'),
$oParams->getString('country'),
$oParams->getString('postalcode')
);
} else {
$this->setQuery($sQuery);
}
}
public function loadStructuredAddressElement($sValue, $sKey, $iNewMinAddressRank, $iNewMaxAddressRank, $aItemListValues)
{
$sValue = trim($sValue);
if (!$sValue) {
return false;
}
$this->aStructuredQuery[$sKey] = $sValue;
if ($this->iMinAddressRank == 0 && $this->iMaxAddressRank == 30) {
$this->iMinAddressRank = $iNewMinAddressRank;
$this->iMaxAddressRank = $iNewMaxAddressRank;
}
if ($aItemListValues) {
$this->aAddressRankList = array_merge($this->aAddressRankList, $aItemListValues);
}
return true;
}
public function setStructuredQuery($sAmenity = false, $sStreet = false, $sCity = false, $sCounty = false, $sState = false, $sCountry = false, $sPostalCode = false)
{
$this->sQuery = false;
// Reset
$this->iMinAddressRank = 0;
$this->iMaxAddressRank = 30;
$this->aAddressRankList = array();
$this->aStructuredQuery = array();
$this->sAllowedTypesSQLList = false;
$this->loadStructuredAddressElement($sAmenity, 'amenity', 26, 30, false);
$this->loadStructuredAddressElement($sStreet, 'street', 26, 30, false);
$this->loadStructuredAddressElement($sCity, 'city', 14, 24, false);
$this->loadStructuredAddressElement($sCounty, 'county', 9, 13, false);
$this->loadStructuredAddressElement($sState, 'state', 8, 8, false);
$this->loadStructuredAddressElement($sPostalCode, 'postalcode', 5, 11, array(5, 11));
$this->loadStructuredAddressElement($sCountry, 'country', 4, 4, false);
if (!empty($this->aStructuredQuery)) {
$this->sQuery = join(', ', $this->aStructuredQuery);
if ($this->iMaxAddressRank < 30) {
$this->sAllowedTypesSQLList = '(\'place\',\'boundary\')';
}
}
}
public function fallbackStructuredQuery()
{
$aParams = $this->aStructuredQuery;
if (!$aParams || count($aParams) == 1) {
return false;
}
$aOrderToFallback = array('postalcode', 'street', 'city', 'county', 'state');
foreach ($aOrderToFallback as $sType) {
if (isset($aParams[$sType])) {
unset($aParams[$sType]);
$this->setStructuredQuery(@$aParams['amenity'], @$aParams['street'], @$aParams['city'], @$aParams['county'], @$aParams['state'], @$aParams['country'], @$aParams['postalcode']);
return true;
}
}
return false;
}
public function getGroupedSearches($aSearches, $aPhrases, $oValidTokens)
{
/*
Calculate all searches using oValidTokens i.e.
'Wodsworth Road, Sheffield' =>
Phrase Wordset
0 0 (wodsworth road)
0 1 (wodsworth)(road)
1 0 (sheffield)
Score how good the search is so they can be ordered
*/
foreach ($aPhrases as $iPhrase => $oPhrase) {
$aNewPhraseSearches = array();
$oPosition = new SearchPosition(
$oPhrase->getPhraseType(),
$iPhrase,
count($aPhrases)
);
foreach ($oPhrase->getWordSets() as $aWordset) {
$aWordsetSearches = $aSearches;
// Add all words from this wordset
foreach ($aWordset as $iToken => $sToken) {
$aNewWordsetSearches = array();
$oPosition->setTokenPosition($iToken, count($aWordset));
foreach ($aWordsetSearches as $oCurrentSearch) {
foreach ($oValidTokens->get($sToken) as $oSearchTerm) {
if ($oSearchTerm->isExtendable($oCurrentSearch, $oPosition)) {
$aNewSearches = $oSearchTerm->extendSearch(
$oCurrentSearch,
$oPosition
);
foreach ($aNewSearches as $oSearch) {
if ($oSearch->getRank() < $this->iMaxRank) {
$aNewWordsetSearches[] = $oSearch;
}
}
}
}
}
// Sort and cut
usort($aNewWordsetSearches, array('Nominatim\SearchDescription', 'bySearchRank'));
$aWordsetSearches = array_slice($aNewWordsetSearches, 0, 50);
}
$aNewPhraseSearches = array_merge($aNewPhraseSearches, $aNewWordsetSearches);
usort($aNewPhraseSearches, array('Nominatim\SearchDescription', 'bySearchRank'));
$aSearchHash = array();
foreach ($aNewPhraseSearches as $iSearch => $aSearch) {
$sHash = serialize($aSearch);
if (isset($aSearchHash[$sHash])) {
unset($aNewPhraseSearches[$iSearch]);
} else {
$aSearchHash[$sHash] = 1;
}
}
$aNewPhraseSearches = array_slice($aNewPhraseSearches, 0, 50);
}
// Re-group the searches by their score, junk anything over 20 as just not worth trying
$aGroupedSearches = array();
foreach ($aNewPhraseSearches as $aSearch) {
$iRank = $aSearch->getRank();
if ($iRank < $this->iMaxRank) {
if (!isset($aGroupedSearches[$iRank])) {
$aGroupedSearches[$iRank] = array();
}
$aGroupedSearches[$iRank][] = $aSearch;
}
}
ksort($aGroupedSearches);
$iSearchCount = 0;
$aSearches = array();
foreach ($aGroupedSearches as $aNewSearches) {
$iSearchCount += count($aNewSearches);
$aSearches = array_merge($aSearches, $aNewSearches);
if ($iSearchCount > 50) {
break;
}
}
}
// Revisit searches, drop bad searches and give penalty to unlikely combinations.
$aGroupedSearches = array();
foreach ($aSearches as $oSearch) {
if (!$oSearch->isValidSearch()) {
continue;
}
$iRank = $oSearch->getRank();
if (!isset($aGroupedSearches[$iRank])) {
$aGroupedSearches[$iRank] = array();
}
$aGroupedSearches[$iRank][] = $oSearch;
}
ksort($aGroupedSearches);
return $aGroupedSearches;
}
/* Perform the actual query lookup.
Returns an ordered list of results, each with the following fields:
osm_type: type of corresponding OSM object
N - node
W - way
R - relation
P - postcode (internally computed)
osm_id: id of corresponding OSM object
class: general object class (corresponds to tag key of primary OSM tag)
type: subclass of object (corresponds to tag value of primary OSM tag)
admin_level: see https://wiki.openstreetmap.org/wiki/Admin_level
rank_search: rank in search hierarchy
(see also https://wiki.openstreetmap.org/wiki/Nominatim/Development_overview#Country_to_street_level)
rank_address: rank in address hierarchy (determines orer in address)
place_id: internal key (may differ between different instances)
country_code: ISO country code
langaddress: localized full address
placename: localized name of object
ref: content of ref tag (if available)
lon: longitude
lat: latitude
importance: importance of place based on Wikipedia link count
addressimportance: cumulated importance of address elements
extra_place: type of place (for admin boundaries, if there is a place tag)
aBoundingBox: bounding Box
label: short description of the object class/type (English only)
name: full name (currently the same as langaddress)
foundorder: secondary ordering for places with same importance
*/
public function lookup()
{
Debug::newFunction('Geocode::lookup');
if (!$this->sQuery && !$this->aStructuredQuery) {
return array();
}
Debug::printDebugArray('Geocode', $this);
$oCtx = new SearchContext();
if ($this->aRoutePoints) {
$oCtx->setViewboxFromRoute(
$this->oDB,
$this->aRoutePoints,
$this->aRouteWidth,
$this->bBoundedSearch
);
} elseif ($this->aViewBox) {
$oCtx->setViewboxFromBox($this->aViewBox, $this->bBoundedSearch);
}
if ($this->aExcludePlaceIDs) {
$oCtx->setExcludeList($this->aExcludePlaceIDs);
}
if ($this->aCountryCodes) {
$oCtx->setCountryList($this->aCountryCodes);
}
Debug::newSection('Query Preprocessing');
$sQuery = $this->sQuery;
if (!preg_match('//u', $sQuery)) {
userError('Query string is not UTF-8 encoded.');
}
// Do we have anything that looks like a lat/lon pair?
$sQuery = $oCtx->setNearPointFromQuery($sQuery);
if ($sQuery || $this->aStructuredQuery) {
// Start with a single blank search
$aSearches = array(new SearchDescription($oCtx));
if ($sQuery) {
$sQuery = $aSearches[0]->extractKeyValuePairs($sQuery);
}
$sSpecialTerm = '';
if ($sQuery) {
preg_match_all(
'/\\[([\\w ]*)\\]/u',
$sQuery,
$aSpecialTermsRaw,
PREG_SET_ORDER
);
if (!empty($aSpecialTermsRaw)) {
Debug::printVar('Special terms', $aSpecialTermsRaw);
}
foreach ($aSpecialTermsRaw as $aSpecialTerm) {
$sQuery = str_replace($aSpecialTerm[0], ' ', $sQuery);
if (!$sSpecialTerm) {
$sSpecialTerm = $aSpecialTerm[1];
}
}
}
if (!$sSpecialTerm && $this->aStructuredQuery
&& isset($this->aStructuredQuery['amenity'])) {
$sSpecialTerm = $this->aStructuredQuery['amenity'];
unset($this->aStructuredQuery['amenity']);
}
if ($sSpecialTerm && !$aSearches[0]->hasOperator()) {
$aTokens = $this->oTokenizer->tokensForSpecialTerm($sSpecialTerm);
if (!empty($aTokens)) {
$aNewSearches = array();
$oPosition = new SearchPosition('', 0, 1);
$oPosition->setTokenPosition(0, 1);
foreach ($aSearches as $oSearch) {
foreach ($aTokens as $oToken) {
$aNewSearches = array_merge(
$aNewSearches,
$oToken->extendSearch($oSearch, $oPosition)
);
}
}
$aSearches = $aNewSearches;
}
}
// Split query into phrases
// Commas are used to reduce the search space by indicating where phrases split
$aPhrases = array();
if ($this->aStructuredQuery) {
foreach ($this->aStructuredQuery as $iPhrase => $sPhrase) {
$aPhrases[] = new Phrase($sPhrase, $iPhrase);
}
} else {
foreach (explode(',', $sQuery) as $sPhrase) {
$aPhrases[] = new Phrase($sPhrase, '');
}
}
Debug::printDebugArray('Search context', $oCtx);
Debug::printDebugArray('Base search', empty($aSearches) ? null : $aSearches[0]);
Debug::newSection('Tokenization');
$oValidTokens = $this->oTokenizer->extractTokensFromPhrases($aPhrases);
if ($oValidTokens->count() > 0) {
$oCtx->setFullNameWords($oValidTokens->getFullWordIDs());
$aPhrases = array_filter($aPhrases, function ($oPhrase) {
return $oPhrase->getWordSets() !== null;
});
// Any words that have failed completely?
// TODO: suggestions
Debug::printGroupTable('Valid Tokens', $oValidTokens->debugInfo());
Debug::printDebugTable('Phrases', $aPhrases);
Debug::newSection('Search candidates');
$aGroupedSearches = $this->getGroupedSearches($aSearches, $aPhrases, $oValidTokens);
if (!$this->aStructuredQuery) {
// Reverse phrase array and also reverse the order of the wordsets in
// the first and final phrase. Don't bother about phrases in the middle
// because order in the address doesn't matter.
$aPhrases = array_reverse($aPhrases);
$aPhrases[0]->invertWordSets();
if (count($aPhrases) > 1) {
$aPhrases[count($aPhrases)-1]->invertWordSets();
}
$aReverseGroupedSearches = $this->getGroupedSearches($aSearches, $aPhrases, $oValidTokens);
foreach ($aReverseGroupedSearches as $aSearches) {
foreach ($aSearches as $aSearch) {
if (!isset($aGroupedSearches[$aSearch->getRank()])) {
$aGroupedSearches[$aSearch->getRank()] = array();
}
$aGroupedSearches[$aSearch->getRank()][] = $aSearch;
}
}
ksort($aGroupedSearches);
}
} else {
// Re-group the searches by their score, junk anything over 20 as just not worth trying
$aGroupedSearches = array();
foreach ($aSearches as $aSearch) {
if ($aSearch->getRank() < $this->iMaxRank) {
if (!isset($aGroupedSearches[$aSearch->getRank()])) {
$aGroupedSearches[$aSearch->getRank()] = array();
}
$aGroupedSearches[$aSearch->getRank()][] = $aSearch;
}
}
ksort($aGroupedSearches);
}
// Filter out duplicate searches
$aSearchHash = array();
foreach ($aGroupedSearches as $iGroup => $aSearches) {
foreach ($aSearches as $iSearch => $aSearch) {
$sHash = serialize($aSearch);
if (isset($aSearchHash[$sHash])) {
unset($aGroupedSearches[$iGroup][$iSearch]);
if (empty($aGroupedSearches[$iGroup])) {
unset($aGroupedSearches[$iGroup]);
}
} else {
$aSearchHash[$sHash] = 1;
}
}
}
Debug::printGroupedSearch(
$aGroupedSearches,
$oValidTokens->debugTokenByWordIdList()
);
// Start the search process
$iGroupLoop = 0;
$iQueryLoop = 0;
$aNextResults = array();
foreach ($aGroupedSearches as $iGroupedRank => $aSearches) {
$iGroupLoop++;
$aResults = $aNextResults;
foreach ($aSearches as $oSearch) {
$iQueryLoop++;
Debug::newSection("Search Loop, group $iGroupLoop, loop $iQueryLoop");
Debug::printGroupedSearch(
array($iGroupedRank => array($oSearch)),
$oValidTokens->debugTokenByWordIdList()
);
$aNewResults = $oSearch->query(
$this->oDB,
$this->iMinAddressRank,
$this->iMaxAddressRank,
$this->iLimit
);
// The same result may appear in different rounds, only
// use the one with minimal rank.
foreach ($aNewResults as $iPlace => $oRes) {
if (!isset($aResults[$iPlace])
|| $aResults[$iPlace]->iResultRank > $oRes->iResultRank) {
$aResults[$iPlace] = $oRes;
}
}
if ($iQueryLoop > 20) {
break;
}
}
if (!empty($aResults)) {
$aSplitResults = Result::splitResults($aResults);
Debug::printVar('Split results', $aSplitResults);
if ($iGroupLoop <= 4
&& reset($aSplitResults['head'])->iResultRank > 0
&& $iGroupedRank !== array_key_last($aGroupedSearches)) {
// Haven't found an exact match for the query yet.
// Therefore add result from the next group level.
$aNextResults = $aSplitResults['head'];
foreach ($aNextResults as $oRes) {
$oRes->iResultRank--;
}
foreach ($aSplitResults['tail'] as $oRes) {
$oRes->iResultRank--;
$aNextResults[$oRes->iId] = $oRes;
}
$aResults = array();
} else {
$aResults = $aSplitResults['head'];
}
}
if (!empty($aResults) && ($this->iMinAddressRank != 0 || $this->iMaxAddressRank != 30)) {
// Need to verify passes rank limits before dropping out of the loop (yuk!)
// reduces the number of place ids, like a filter
// rank_address is 30 for interpolated housenumbers
$aFilterSql = array();
$sPlaceIds = Result::joinIdsByTable($aResults, Result::TABLE_PLACEX);
if ($sPlaceIds) {
$sSQL = 'SELECT place_id FROM placex ';
$sSQL .= 'WHERE place_id in ('.$sPlaceIds.') ';
$sSQL .= ' AND (';
$sSQL .= " placex.rank_address between $this->iMinAddressRank and $this->iMaxAddressRank ";
$sSQL .= " OR placex.rank_search between $this->iMinAddressRank and $this->iMaxAddressRank ";
if ($this->aAddressRankList) {
$sSQL .= ' OR placex.rank_address in ('.join(',', $this->aAddressRankList).')';
}
$sSQL .= ')';
$aFilterSql[] = $sSQL;
}
$sPlaceIds = Result::joinIdsByTable($aResults, Result::TABLE_POSTCODE);
if ($sPlaceIds) {
$sSQL = ' SELECT place_id FROM location_postcode lp ';
$sSQL .= 'WHERE place_id in ('.$sPlaceIds.') ';
$sSQL .= " AND (lp.rank_address between $this->iMinAddressRank and $this->iMaxAddressRank ";
if ($this->aAddressRankList) {
$sSQL .= ' OR lp.rank_address in ('.join(',', $this->aAddressRankList).')';
}
$sSQL .= ') ';
$aFilterSql[] = $sSQL;
}
$aFilteredIDs = array();
if ($aFilterSql) {
$sSQL = join(' UNION ', $aFilterSql);
Debug::printSQL($sSQL);
$aFilteredIDs = $this->oDB->getCol($sSQL);
}
$tempIDs = array();
foreach ($aResults as $oResult) {
if (($this->iMaxAddressRank == 30 &&
($oResult->iTable == Result::TABLE_OSMLINE
|| $oResult->iTable == Result::TABLE_TIGER))
|| in_array($oResult->iId, $aFilteredIDs)
) {
$tempIDs[$oResult->iId] = $oResult;
}
}
$aResults = $tempIDs;
}
if (!empty($aResults) || $iGroupLoop > 4 || $iQueryLoop > 30) {
break;
}
}
} else {
// Just interpret as a reverse geocode
$oReverse = new ReverseGeocode($this->oDB);
$oReverse->setZoom(18);
$oLookup = $oReverse->lookupPoint($oCtx->sqlNear, false);
Debug::printVar('Reverse search', $oLookup);
if ($oLookup) {
$aResults = array($oLookup->iId => $oLookup);
}
}
// No results? Done
if (empty($aResults)) {
if ($this->bFallback && $this->fallbackStructuredQuery()) {
return $this->lookup();
}
return array();
}
if ($this->aAddressRankList) {
$this->oPlaceLookup->setAddressRankList($this->aAddressRankList);
}
$this->oPlaceLookup->setAllowedTypesSQLList($this->sAllowedTypesSQLList);
$this->oPlaceLookup->setLanguagePreference($this->aLangPrefOrder);
if ($oCtx->hasNearPoint()) {
$this->oPlaceLookup->setAnchorSql($oCtx->sqlNear);
}
$aSearchResults = $this->oPlaceLookup->lookup($aResults);
$aRecheckWords = preg_split('/\b[\s,\\-]*/u', $sQuery);
foreach ($aRecheckWords as $i => $sWord) {
if (!preg_match('/[\pL\pN]/', $sWord)) {
unset($aRecheckWords[$i]);
}
}
Debug::printVar('Recheck words', $aRecheckWords);
foreach ($aSearchResults as $iIdx => $aResult) {
$fRadius = ClassTypes\getDefRadius($aResult);
$aOutlineResult = $this->oPlaceLookup->getOutlines($aResult['place_id'], $aResult['lon'], $aResult['lat'], $fRadius);
if ($aOutlineResult) {
$aResult = array_merge($aResult, $aOutlineResult);
}
// Is there an icon set for this type of result?
$sIcon = ClassTypes\getIconFile($aResult);
if (isset($sIcon)) {
$aResult['icon'] = $sIcon;
}
$sLabel = ClassTypes\getLabel($aResult);
if (isset($sLabel)) {
$aResult['label'] = $sLabel;
}
$aResult['name'] = $aResult['langaddress'];
if ($oCtx->hasNearPoint()) {
$aResult['importance'] = 0.001;
$aResult['foundorder'] = $aResult['addressimportance'];
} else {
if ($aResult['importance'] == 0) {
$aResult['importance'] = 0.0001;
}
$aResult['importance'] *= $this->viewboxImportanceFactor(
$aResult['lon'],
$aResult['lat']
);
// secondary ordering (for results with same importance (the smaller the better):
// - approximate importance of address parts
if (isset($aResult['addressimportance']) && $aResult['addressimportance']) {
$aResult['foundorder'] = -$aResult['addressimportance']/10;
} else {
$aResult['foundorder'] = -$aResult['importance'];
}
// - number of exact matches from the query
$aResult['foundorder'] -= $aResults[$aResult['place_id']]->iExactMatches;
// - importance of the class/type
$iClassImportance = ClassTypes\getImportance($aResult);
if (isset($iClassImportance)) {
$aResult['foundorder'] += 0.0001 * $iClassImportance;
} else {
$aResult['foundorder'] += 0.01;
}
// - rank
$aResult['foundorder'] -= 0.00001 * (30 - $aResult['rank_search']);
// Adjust importance for the number of exact string matches in the result
$iCountWords = 0;
$sAddress = $aResult['langaddress'];
foreach ($aRecheckWords as $i => $sWord) {
if (grapheme_stripos($sAddress, $sWord)!==false) {
$iCountWords++;
if (preg_match('/(^|,)\s*'.preg_quote($sWord, '/').'\s*(,|$)/', $sAddress)) {
$iCountWords += 0.1;
}
}
}
// 0.1 is a completely arbitrary number but something in the range 0.1 to 0.5 would seem right
$aResult['importance'] = $aResult['importance'] + ($iCountWords*0.1);
}
$aSearchResults[$iIdx] = $aResult;
}
uasort($aSearchResults, 'byImportance');
Debug::printVar('Pre-filter results', $aSearchResults);
$aOSMIDDone = array();
$aClassTypeNameDone = array();
$aToFilter = $aSearchResults;
$aSearchResults = array();
foreach ($aToFilter as $aResult) {
$this->aExcludePlaceIDs[$aResult['place_id']] = $aResult['place_id'];
if (!$this->oPlaceLookup->doDeDupe() || (!isset($aOSMIDDone[$aResult['osm_type'].$aResult['osm_id']])
&& !isset($aClassTypeNameDone[$aResult['osm_type'].$aResult['class'].$aResult['type'].$aResult['name'].$aResult['admin_level']]))
) {
$aOSMIDDone[$aResult['osm_type'].$aResult['osm_id']] = true;
$aClassTypeNameDone[$aResult['osm_type'].$aResult['class'].$aResult['type'].$aResult['name'].$aResult['admin_level']] = true;
$aSearchResults[] = $aResult;
}
// Absolute limit on number of results
if (count($aSearchResults) >= $this->iFinalLimit) {
break;
}
}
Debug::printVar('Post-filter results', $aSearchResults);
return $aSearchResults;
} // end lookup()
public function debugInfo()
{
return array(
'Query' => $this->sQuery,
'Structured query' => $this->aStructuredQuery,
'Name keys' => Debug::fmtArrayVals($this->aLangPrefOrder),
'Excluded place IDs' => Debug::fmtArrayVals($this->aExcludePlaceIDs),
'Limit (for searches)' => $this->iLimit,
'Limit (for results)'=> $this->iFinalLimit,
'Country codes' => Debug::fmtArrayVals($this->aCountryCodes),
'Bounded search' => $this->bBoundedSearch,
'Viewbox' => Debug::fmtArrayVals($this->aViewBox),
'Route points' => Debug::fmtArrayVals($this->aRoutePoints),
'Route width' => $this->aRouteWidth,
'Max rank' => $this->iMaxRank,
'Min address rank' => $this->iMinAddressRank,
'Max address rank' => $this->iMaxAddressRank,
'Address rank list' => Debug::fmtArrayVals($this->aAddressRankList)
);
}
} // end class

View File

@@ -1,157 +0,0 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
class ParameterParser
{
private $aParams;
public function __construct($aParams = null)
{
$this->aParams = ($aParams === null) ? $_GET : $aParams;
}
public function getBool($sName, $bDefault = false)
{
if (!isset($this->aParams[$sName])
|| !is_string($this->aParams[$sName])
|| strlen($this->aParams[$sName]) == 0
) {
return $bDefault;
}
return (bool) $this->aParams[$sName];
}
public function getInt($sName, $bDefault = false)
{
if (!isset($this->aParams[$sName]) || is_array($this->aParams[$sName])) {
return $bDefault;
}
if (!preg_match('/^[+-]?[0-9]+$/', $this->aParams[$sName])) {
userError("Integer number expected for parameter '$sName'");
}
return (int) $this->aParams[$sName];
}
public function getFloat($sName, $bDefault = false)
{
if (!isset($this->aParams[$sName]) || is_array($this->aParams[$sName])) {
return $bDefault;
}
if (!preg_match('/^[+-]?[0-9]*\.?[0-9]+$/', $this->aParams[$sName])) {
userError("Floating-point number expected for parameter '$sName'");
}
return (float) $this->aParams[$sName];
}
public function getString($sName, $bDefault = false)
{
if (!isset($this->aParams[$sName])
|| !is_string($this->aParams[$sName])
|| strlen($this->aParams[$sName]) == 0
) {
return $bDefault;
}
return $this->aParams[$sName];
}
public function getSet($sName, $aValues, $sDefault = false)
{
if (!isset($this->aParams[$sName])
|| !is_string($this->aParams[$sName])
|| strlen($this->aParams[$sName]) == 0
) {
return $sDefault;
}
if (!in_array($this->aParams[$sName], $aValues, true)) {
userError("Parameter '$sName' must be one of: ".join(', ', $aValues));
}
return $this->aParams[$sName];
}
public function getStringList($sName, $aDefault = false)
{
$sValue = $this->getString($sName);
if ($sValue) {
// removes all NULL, FALSE and Empty Strings but leaves 0 (zero) values
return array_values(array_filter(explode(',', $sValue), 'strlen'));
}
return $aDefault;
}
public function getPreferredLanguages($sFallback = null)
{
if ($sFallback === null && isset($_SERVER['HTTP_ACCEPT_LANGUAGE'])) {
$sFallback = $_SERVER['HTTP_ACCEPT_LANGUAGE'];
}
$aLanguages = array();
$sLangString = $this->getString('accept-language', $sFallback);
if ($sLangString
&& preg_match_all('/(([a-z]{1,8})([-_][a-z]{1,8})?)\s*(;\s*q\s*=\s*(1|0\.[0-9]+))?/i', $sLangString, $aLanguagesParse, PREG_SET_ORDER)
) {
foreach ($aLanguagesParse as $iLang => $aLanguage) {
$aLanguages[$aLanguage[1]] = isset($aLanguage[5])?(float)$aLanguage[5]:1 - ($iLang/100);
if (!isset($aLanguages[$aLanguage[2]])) {
$aLanguages[$aLanguage[2]] = $aLanguages[$aLanguage[1]]/10;
}
}
arsort($aLanguages);
}
if (empty($aLanguages) && CONST_Default_Language) {
$aLanguages[CONST_Default_Language] = 1;
}
foreach ($aLanguages as $sLanguage => $fLanguagePref) {
$this->addNameTag($aLangPrefOrder, 'name:'.$sLanguage);
}
$this->addNameTag($aLangPrefOrder, 'name');
$this->addNameTag($aLangPrefOrder, 'brand');
foreach ($aLanguages as $sLanguage => $fLanguagePref) {
$this->addNameTag($aLangPrefOrder, 'official_name:'.$sLanguage);
$this->addNameTag($aLangPrefOrder, 'short_name:'.$sLanguage);
}
$this->addNameTag($aLangPrefOrder, 'official_name');
$this->addNameTag($aLangPrefOrder, 'short_name');
$this->addNameTag($aLangPrefOrder, 'ref');
$this->addNameTag($aLangPrefOrder, 'type');
return $aLangPrefOrder;
}
private function addNameTag(&$aLangPrefOrder, $sTag)
{
$aLangPrefOrder[$sTag] = $sTag;
$aLangPrefOrder['_place_'.$sTag] = '_place_'.$sTag;
}
public function hasSetAny($aParamNames)
{
foreach ($aParamNames as $sName) {
if ($this->getBool($sName)) {
return true;
}
}
return false;
}
}

View File

@@ -1,89 +0,0 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
/**
* Segment of a query string.
*
* The parts of a query strings are usually separated by commas.
*/
class Phrase
{
// Complete phrase as a string (guaranteed to have no leading or trailing
// spaces).
private $sPhrase;
// Element type for structured searches.
private $sPhraseType;
// Possible segmentations of the phrase.
private $aWordSets;
public function __construct($sPhrase, $sPhraseType)
{
$this->sPhrase = trim($sPhrase);
$this->sPhraseType = $sPhraseType;
}
/**
* Get the original phrase of the string.
*/
public function getPhrase()
{
return $this->sPhrase;
}
/**
* Return the element type of the phrase.
*
* @return string Pharse type if the phrase comes from a structured query
* or empty string otherwise.
*/
public function getPhraseType()
{
return $this->sPhraseType;
}
public function setWordSets($aWordSets)
{
$this->aWordSets = $aWordSets;
}
/**
* Return the array of possible segmentations of the phrase.
*
* @return string[][] Array of segmentations, each consisting of an
* array of terms.
*/
public function getWordSets()
{
return $this->aWordSets;
}
/**
* Invert the set of possible segmentations.
*
* @return void
*/
public function invertWordSets()
{
foreach ($this->aWordSets as $i => $aSet) {
$this->aWordSets[$i] = array_reverse($aSet);
}
}
public function debugInfo()
{
return array(
'Type' => $this->sPhraseType,
'Phrase' => $this->sPhrase,
'WordSets' => $this->aWordSets
);
}
}

View File

@@ -1,615 +0,0 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
require_once(CONST_LibDir.'/AddressDetails.php');
require_once(CONST_LibDir.'/Result.php');
class PlaceLookup
{
protected $oDB;
protected $aLangPrefOrderSql = "''";
protected $bAddressDetails = false;
protected $bExtraTags = false;
protected $bNameDetails = false;
protected $bIncludePolygonAsText = false;
protected $bIncludePolygonAsGeoJSON = false;
protected $bIncludePolygonAsKML = false;
protected $bIncludePolygonAsSVG = false;
protected $fPolygonSimplificationThreshold = 0.0;
protected $sAnchorSql = null;
protected $sAddressRankListSql = null;
protected $sAllowedTypesSQLList = null;
protected $bDeDupe = true;
public function __construct(&$oDB)
{
$this->oDB =& $oDB;
}
public function doDeDupe()
{
return $this->bDeDupe;
}
public function setIncludeAddressDetails($b)
{
$this->bAddressDetails = $b;
}
public function loadParamArray($oParams, $sGeomType = null)
{
$aLangs = $oParams->getPreferredLanguages();
$this->aLangPrefOrderSql =
'ARRAY['.join(',', $this->oDB->getDBQuotedList($aLangs)).']';
$this->bExtraTags = $oParams->getBool('extratags', false);
$this->bNameDetails = $oParams->getBool('namedetails', false);
$this->bDeDupe = $oParams->getBool('dedupe', $this->bDeDupe);
if ($sGeomType === null || $sGeomType == 'geojson') {
$this->bIncludePolygonAsGeoJSON = $oParams->getBool('polygon_geojson');
}
if ($oParams->getString('format', '') !== 'geojson') {
if ($sGeomType === null || $sGeomType == 'text') {
$this->bIncludePolygonAsText = $oParams->getBool('polygon_text');
}
if ($sGeomType === null || $sGeomType == 'kml') {
$this->bIncludePolygonAsKML = $oParams->getBool('polygon_kml');
}
if ($sGeomType === null || $sGeomType == 'svg') {
$this->bIncludePolygonAsSVG = $oParams->getBool('polygon_svg');
}
}
$this->fPolygonSimplificationThreshold
= $oParams->getFloat('polygon_threshold', 0.0);
$iWantedTypes =
($this->bIncludePolygonAsText ? 1 : 0) +
($this->bIncludePolygonAsGeoJSON ? 1 : 0) +
($this->bIncludePolygonAsKML ? 1 : 0) +
($this->bIncludePolygonAsSVG ? 1 : 0);
if ($iWantedTypes > CONST_PolygonOutput_MaximumTypes) {
if (CONST_PolygonOutput_MaximumTypes) {
userError('Select only '.CONST_PolygonOutput_MaximumTypes.' polygon output option');
} else {
userError('Polygon output is disabled');
}
}
}
public function getMoreUrlParams()
{
$aParams = array();
if ($this->bAddressDetails) {
$aParams['addressdetails'] = '1';
}
if ($this->bExtraTags) {
$aParams['extratags'] = '1';
}
if ($this->bNameDetails) {
$aParams['namedetails'] = '1';
}
if ($this->bIncludePolygonAsText) {
$aParams['polygon_text'] = '1';
}
if ($this->bIncludePolygonAsGeoJSON) {
$aParams['polygon_geojson'] = '1';
}
if ($this->bIncludePolygonAsKML) {
$aParams['polygon_kml'] = '1';
}
if ($this->bIncludePolygonAsSVG) {
$aParams['polygon_svg'] = '1';
}
if ($this->fPolygonSimplificationThreshold > 0.0) {
$aParams['polygon_threshold'] = $this->fPolygonSimplificationThreshold;
}
if (!$this->bDeDupe) {
$aParams['dedupe'] = '0';
}
return $aParams;
}
public function setAnchorSql($sPoint)
{
$this->sAnchorSql = $sPoint;
}
public function setAddressRankList($aList)
{
$this->sAddressRankListSql = '('.join(',', $aList).')';
}
public function setAllowedTypesSQLList($sSql)
{
$this->sAllowedTypesSQLList = $sSql;
}
public function setLanguagePreference($aLangPrefOrder)
{
$this->aLangPrefOrderSql = $this->oDB->getArraySQL(
$this->oDB->getDBQuotedList($aLangPrefOrder)
);
}
private function addressImportanceSql($sGeometry, $sPlaceId)
{
if ($this->sAnchorSql) {
$sSQL = 'ST_Distance('.$this->sAnchorSql.','.$sGeometry.')';
} else {
$sSQL = '(SELECT max(ai_p.importance * (ai_p.rank_address + 2))';
$sSQL .= ' FROM place_addressline ai_s, placex ai_p';
$sSQL .= ' WHERE ai_s.place_id = '.$sPlaceId;
$sSQL .= ' AND ai_p.place_id = ai_s.address_place_id ';
$sSQL .= ' AND ai_s.isaddress ';
$sSQL .= ' AND ai_p.importance is not null)';
}
return $sSQL.' AS addressimportance,';
}
private function langAddressSql($sHousenumber)
{
if ($this->bAddressDetails) {
return ''; // langaddress will be computed from address details
}
return 'get_address_by_language(place_id,'.$sHousenumber.','.$this->aLangPrefOrderSql.') AS langaddress,';
}
public function lookupOSMID($sType, $iID)
{
$sSQL = 'select place_id from placex where osm_type = :type and osm_id = :id';
$iPlaceID = $this->oDB->getOne($sSQL, array(':type' => $sType, ':id' => $iID));
if (!$iPlaceID) {
return null;
}
$aResults = $this->lookup(array($iPlaceID => new Result($iPlaceID)), 0, 30, true);
return empty($aResults) ? null : reset($aResults);
}
public function lookup($aResults, $iMinRank = 0, $iMaxRank = 30, $bAllowLinked = false)
{
Debug::newFunction('Place lookup');
if (empty($aResults)) {
return array();
}
$aSubSelects = array();
$sPlaceIDs = Result::joinIdsByTable($aResults, Result::TABLE_PLACEX);
if ($sPlaceIDs) {
Debug::printVar('Ids from placex', $sPlaceIDs);
$sSQL = 'SELECT ';
$sSQL .= ' osm_type,';
$sSQL .= ' osm_id,';
$sSQL .= ' class,';
$sSQL .= ' type,';
$sSQL .= ' admin_level,';
$sSQL .= ' rank_search,';
$sSQL .= ' rank_address,';
$sSQL .= ' min(place_id) AS place_id,';
$sSQL .= ' min(parent_place_id) AS parent_place_id,';
$sSQL .= ' -1 as housenumber,';
$sSQL .= ' country_code,';
$sSQL .= $this->langAddressSql('-1');
$sSQL .= ' get_name_by_language(name,'.$this->aLangPrefOrderSql.') AS placename,';
$sSQL .= " get_name_by_language(name, ARRAY['ref']) AS ref,";
if ($this->bExtraTags) {
$sSQL .= 'hstore_to_json(extratags)::text AS extra,';
}
if ($this->bNameDetails) {
$sSQL .= 'hstore_to_json(name)::text AS names,';
}
$sSQL .= ' avg(ST_X(centroid)) AS lon, ';
$sSQL .= ' avg(ST_Y(centroid)) AS lat, ';
$sSQL .= ' COALESCE(importance,0.75-(rank_search::float/40)) AS importance, ';
$sSQL .= $this->addressImportanceSql(
'ST_Collect(centroid)',
'min(CASE WHEN placex.rank_search < 28 THEN placex.place_id ELSE placex.parent_place_id END)'
);
$sSQL .= " COALESCE(extratags->'place', extratags->'linked_place') AS extra_place ";
$sSQL .= ' FROM placex';
$sSQL .= " WHERE place_id in ($sPlaceIDs) ";
$sSQL .= ' AND (';
$sSQL .= " placex.rank_address between $iMinRank and $iMaxRank ";
if (14 >= $iMinRank && 14 <= $iMaxRank) {
$sSQL .= " OR (extratags->'place') = 'city'";
}
if ($this->sAddressRankListSql) {
$sSQL .= ' OR placex.rank_address in '.$this->sAddressRankListSql;
}
$sSQL .= ' ) ';
if ($this->sAllowedTypesSQLList) {
$sSQL .= 'AND placex.class in '.$this->sAllowedTypesSQLList;
}
if (!$bAllowLinked) {
$sSQL .= ' AND linked_place_id is null ';
}
$sSQL .= ' GROUP BY ';
$sSQL .= ' osm_type, ';
$sSQL .= ' osm_id, ';
$sSQL .= ' class, ';
$sSQL .= ' type, ';
$sSQL .= ' admin_level, ';
$sSQL .= ' rank_search, ';
$sSQL .= ' rank_address, ';
$sSQL .= ' housenumber,';
$sSQL .= ' country_code, ';
$sSQL .= ' importance, ';
if (!$this->bDeDupe) {
$sSQL .= 'place_id,';
}
if (!$this->bAddressDetails) {
$sSQL .= 'langaddress, ';
}
$sSQL .= ' placename, ';
$sSQL .= ' ref, ';
if ($this->bExtraTags) {
$sSQL .= 'extratags, ';
}
if ($this->bNameDetails) {
$sSQL .= 'name, ';
}
$sSQL .= ' extra_place ';
$aSubSelects[] = $sSQL;
}
// postcode table
$sPlaceIDs = Result::joinIdsByTable($aResults, Result::TABLE_POSTCODE);
if ($sPlaceIDs) {
Debug::printVar('Ids from location_postcode', $sPlaceIDs);
$sSQL = 'SELECT';
$sSQL .= " 'P' as osm_type,";
$sSQL .= ' (SELECT osm_id from placex p WHERE p.place_id = lp.parent_place_id) as osm_id,';
$sSQL .= " 'place' as class, 'postcode' as type,";
$sSQL .= ' null::smallint as admin_level, rank_search, rank_address,';
$sSQL .= ' place_id, parent_place_id,';
$sSQL .= ' -1 as housenumber,';
$sSQL .= ' country_code,';
$sSQL .= $this->langAddressSql('-1');
$sSQL .= ' postcode as placename,';
$sSQL .= ' postcode as ref,';
if ($this->bExtraTags) {
$sSQL .= 'null::text AS extra,';
}
if ($this->bNameDetails) {
$sSQL .= 'null::text AS names,';
}
$sSQL .= ' ST_x(geometry) AS lon, ST_y(geometry) AS lat,';
$sSQL .= ' (0.75-(rank_search::float/40)) AS importance, ';
$sSQL .= $this->addressImportanceSql('geometry', 'lp.parent_place_id');
$sSQL .= ' null::text AS extra_place ';
$sSQL .= 'FROM location_postcode lp';
$sSQL .= " WHERE place_id in ($sPlaceIDs) ";
$sSQL .= " AND lp.rank_address between $iMinRank and $iMaxRank";
$aSubSelects[] = $sSQL;
}
// All other tables are rank 30 only.
if ($iMaxRank == 30) {
// TIGER table
if (CONST_Use_US_Tiger_Data) {
$sPlaceIDs = Result::joinIdsByTable($aResults, Result::TABLE_TIGER);
if ($sPlaceIDs) {
Debug::printVar('Ids from Tiger table', $sPlaceIDs);
$sHousenumbers = Result::sqlHouseNumberTable($aResults, Result::TABLE_TIGER);
// Tiger search only if a housenumber was searched and if it was found
// (realized through a join)
$sSQL = ' SELECT ';
$sSQL .= " 'T' AS osm_type, ";
$sSQL .= ' (SELECT osm_id from placex p WHERE p.place_id=blub.parent_place_id) as osm_id, ';
$sSQL .= " 'place' AS class, ";
$sSQL .= " 'house' AS type, ";
$sSQL .= ' null::smallint AS admin_level, ';
$sSQL .= ' 30 AS rank_search, ';
$sSQL .= ' 30 AS rank_address, ';
$sSQL .= ' place_id, ';
$sSQL .= ' parent_place_id, ';
$sSQL .= ' housenumber_for_place as housenumber,';
$sSQL .= " 'us' AS country_code, ";
$sSQL .= $this->langAddressSql('housenumber_for_place');
$sSQL .= ' null::text AS placename, ';
$sSQL .= ' null::text AS ref, ';
if ($this->bExtraTags) {
$sSQL .= 'null::text AS extra,';
}
if ($this->bNameDetails) {
$sSQL .= 'null::text AS names,';
}
$sSQL .= ' st_x(centroid) AS lon, ';
$sSQL .= ' st_y(centroid) AS lat,';
$sSQL .= ' -1.15 AS importance, ';
$sSQL .= $this->addressImportanceSql('centroid', 'blub.parent_place_id');
$sSQL .= ' null::text AS extra_place ';
$sSQL .= ' FROM (';
$sSQL .= ' SELECT place_id, '; // interpolate the Tiger housenumbers here
$sSQL .= ' CASE WHEN startnumber != endnumber';
$sSQL .= ' THEN ST_LineInterpolatePoint(linegeo, (housenumber_for_place-startnumber::float)/(endnumber-startnumber)::float)';
$sSQL .= ' ELSE ST_LineInterpolatePoint(linegeo, 0.5) END AS centroid, ';
$sSQL .= ' parent_place_id, ';
$sSQL .= ' housenumber_for_place';
$sSQL .= ' FROM (';
$sSQL .= ' location_property_tiger ';
$sSQL .= ' JOIN (values '.$sHousenumbers.') AS housenumbers(place_id, housenumber_for_place) USING(place_id)) ';
$sSQL .= ' WHERE ';
$sSQL .= ' housenumber_for_place >= startnumber';
$sSQL .= ' AND housenumber_for_place <= endnumber';
$sSQL .= ' ) AS blub'; //postgres wants an alias here
$aSubSelects[] = $sSQL;
}
}
// osmline - interpolated housenumbers
$sPlaceIDs = Result::joinIdsByTable($aResults, Result::TABLE_OSMLINE);
if ($sPlaceIDs) {
Debug::printVar('Ids from interpolation', $sPlaceIDs);
$sHousenumbers = Result::sqlHouseNumberTable($aResults, Result::TABLE_OSMLINE);
// interpolation line search only if a housenumber was searched
// (realized through a join)
$sSQL = 'SELECT ';
$sSQL .= " 'W' AS osm_type, ";
$sSQL .= ' osm_id, ';
$sSQL .= " 'place' AS class, ";
$sSQL .= " 'house' AS type, ";
$sSQL .= ' null::smallint AS admin_level, ';
$sSQL .= ' 30 AS rank_search, ';
$sSQL .= ' 30 AS rank_address, ';
$sSQL .= ' place_id, ';
$sSQL .= ' parent_place_id, ';
$sSQL .= ' housenumber_for_place as housenumber,';
$sSQL .= ' country_code, ';
$sSQL .= $this->langAddressSql('housenumber_for_place');
$sSQL .= ' null::text AS placename, ';
$sSQL .= ' null::text AS ref, ';
if ($this->bExtraTags) {
$sSQL .= 'null::text AS extra, ';
}
if ($this->bNameDetails) {
$sSQL .= 'null::text AS names, ';
}
$sSQL .= ' st_x(centroid) AS lon, ';
$sSQL .= ' st_y(centroid) AS lat, ';
// slightly smaller than the importance for normal houses
$sSQL .= ' -0.1 AS importance, ';
$sSQL .= $this->addressImportanceSql('centroid', 'blub.parent_place_id');
$sSQL .= ' null::text AS extra_place ';
$sSQL .= ' FROM (';
$sSQL .= ' SELECT ';
$sSQL .= ' osm_id, ';
$sSQL .= ' place_id, ';
$sSQL .= ' country_code, ';
$sSQL .= ' CASE '; // interpolate the housenumbers here
$sSQL .= ' WHEN startnumber != endnumber ';
$sSQL .= ' THEN ST_LineInterpolatePoint(linegeo, (housenumber_for_place-startnumber::float)/(endnumber-startnumber)::float) ';
$sSQL .= ' ELSE linegeo ';
$sSQL .= ' END as centroid, ';
$sSQL .= ' parent_place_id, ';
$sSQL .= ' housenumber_for_place ';
$sSQL .= ' FROM (';
$sSQL .= ' location_property_osmline ';
$sSQL .= ' JOIN (values '.$sHousenumbers.') AS housenumbers(place_id, housenumber_for_place) USING(place_id)';
$sSQL .= ' ) ';
$sSQL .= ' WHERE housenumber_for_place >= 0 ';
$sSQL .= ' ) as blub'; //postgres wants an alias here
$aSubSelects[] = $sSQL;
}
}
if (empty($aSubSelects)) {
return array();
}
$sSQL = join(' UNION ', $aSubSelects);
Debug::printSQL($sSQL);
$aPlaces = $this->oDB->getAll($sSQL, null, 'Could not lookup place');
foreach ($aPlaces as &$aPlace) {
$aPlace['importance'] = (float) $aPlace['importance'];
if ($this->bAddressDetails) {
// to get addressdetails for tiger data, the housenumber is needed
$aPlace['address'] = new AddressDetails(
$this->oDB,
$aPlace['place_id'],
$aPlace['housenumber'],
$this->aLangPrefOrderSql
);
$aPlace['langaddress'] = $aPlace['address']->getLocaleAddress();
}
if ($this->bExtraTags) {
if ($aPlace['extra']) {
$aPlace['sExtraTags'] = json_decode($aPlace['extra'], true);
} else {
$aPlace['sExtraTags'] = (object) array();
}
}
if ($this->bNameDetails) {
$aPlace['sNameDetails'] = $this->extractNames($aPlace['names']);
}
$aPlace['addresstype'] = ClassTypes\getLabelTag(
$aPlace,
$aPlace['country_code']
);
$aResults[$aPlace['place_id']] = $aPlace;
}
$aResults = array_filter(
$aResults,
function ($v) {
return !($v instanceof Result);
}
);
Debug::printVar('Places', $aResults);
return $aResults;
}
private function extractNames($sNames)
{
if (!$sNames) {
return (object) array();
}
$aFullNames = json_decode($sNames, true);
$aNames = array();
foreach ($aFullNames as $sKey => $sValue) {
if (strpos($sKey, '_place_') === 0) {
$sSubKey = substr($sKey, 7);
if (array_key_exists($sSubKey, $aFullNames)) {
$aNames[$sKey] = $sValue;
} else {
$aNames[$sSubKey] = $sValue;
}
} else {
$aNames[$sKey] = $sValue;
}
}
return $aNames;
}
/* returns an array which will contain the keys
* aBoundingBox
* and may also contain one or more of the keys
* asgeojson
* askml
* assvg
* astext
* lat
* lon
*/
public function getOutlines($iPlaceID, $fLon = null, $fLat = null, $fRadius = null, $fLonReverse = null, $fLatReverse = null)
{
$aOutlineResult = array();
if (!$iPlaceID) {
return $aOutlineResult;
}
// Get the bounding box and outline polygon
$sSQL = 'select place_id,0 as numfeatures,st_area(geometry) as area,';
$sSQL .= ' ST_Y(centroid) as centrelat, ST_X(centroid) as centrelon,';
$sSQL .= ' ST_YMin(geometry) as minlat,ST_YMax(geometry) as maxlat,';
$sSQL .= ' ST_XMin(geometry) as minlon,ST_XMax(geometry) as maxlon';
if ($this->bIncludePolygonAsGeoJSON) {
$sSQL .= ',ST_AsGeoJSON(geometry) as asgeojson';
}
if ($this->bIncludePolygonAsKML) {
$sSQL .= ',ST_AsKML(geometry) as askml';
}
if ($this->bIncludePolygonAsSVG) {
$sSQL .= ',ST_AsSVG(geometry) as assvg';
}
if ($this->bIncludePolygonAsText) {
$sSQL .= ',ST_AsText(geometry) as astext';
}
$sSQL .= ' FROM (SELECT place_id';
if ($fLonReverse != null && $fLatReverse != null) {
$sSQL .= ',CASE WHEN (class = \'highway\') AND (ST_GeometryType(geometry) = \'ST_LineString\') THEN ';
$sSQL .=' ST_ClosestPoint(geometry, ST_SetSRID(ST_Point('.$fLatReverse.','.$fLonReverse.'),4326))';
$sSQL .=' ELSE centroid END AS centroid';
} else {
$sSQL .= ',centroid';
}
if ($this->fPolygonSimplificationThreshold > 0) {
$sSQL .= ',ST_SimplifyPreserveTopology(geometry,'.$this->fPolygonSimplificationThreshold.') as geometry';
} else {
$sSQL .= ',geometry';
}
$sSQL .= ' FROM placex where place_id = '.$iPlaceID.') as plx';
$aPointPolygon = $this->oDB->getRow($sSQL, null, 'Could not get outline');
if ($aPointPolygon && $aPointPolygon['place_id']) {
if ($aPointPolygon['centrelon'] !== null && $aPointPolygon['centrelat'] !== null) {
$aOutlineResult['lat'] = $aPointPolygon['centrelat'];
$aOutlineResult['lon'] = $aPointPolygon['centrelon'];
}
if ($this->bIncludePolygonAsGeoJSON) {
$aOutlineResult['asgeojson'] = $aPointPolygon['asgeojson'];
}
if ($this->bIncludePolygonAsKML) {
$aOutlineResult['askml'] = $aPointPolygon['askml'];
}
if ($this->bIncludePolygonAsSVG) {
$aOutlineResult['assvg'] = $aPointPolygon['assvg'];
}
if ($this->bIncludePolygonAsText) {
$aOutlineResult['astext'] = $aPointPolygon['astext'];
}
if (abs($aPointPolygon['minlat'] - $aPointPolygon['maxlat']) < 0.0000001) {
$aPointPolygon['minlat'] = $aPointPolygon['minlat'] - $fRadius;
$aPointPolygon['maxlat'] = $aPointPolygon['maxlat'] + $fRadius;
}
if (abs($aPointPolygon['minlon'] - $aPointPolygon['maxlon']) < 0.0000001) {
$aPointPolygon['minlon'] = $aPointPolygon['minlon'] - $fRadius;
$aPointPolygon['maxlon'] = $aPointPolygon['maxlon'] + $fRadius;
}
$aOutlineResult['aBoundingBox'] = array(
(string)$aPointPolygon['minlat'],
(string)$aPointPolygon['maxlat'],
(string)$aPointPolygon['minlon'],
(string)$aPointPolygon['maxlon']
);
}
// as a fallback we generate a bounding box without knowing the size of the geometry
if ((!isset($aOutlineResult['aBoundingBox'])) && isset($fLon)) {
$aBounds = array(
'minlat' => $fLat - $fRadius,
'maxlat' => $fLat + $fRadius,
'minlon' => $fLon - $fRadius,
'maxlon' => $fLon + $fRadius
);
$aOutlineResult['aBoundingBox'] = array(
(string)$aBounds['minlat'],
(string)$aBounds['maxlat'],
(string)$aBounds['minlon'],
(string)$aBounds['maxlon']
);
}
return $aOutlineResult;
}
}

View File

@@ -1,129 +0,0 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
/**
* A single result of a search operation or a reverse lookup.
*
* This object only contains the id of the result. It does not yet
* have any details needed to format the output document.
*/
class Result
{
const TABLE_PLACEX = 0;
const TABLE_POSTCODE = 1;
const TABLE_OSMLINE = 2;
const TABLE_TIGER = 3;
/// Database table that contains the result.
public $iTable;
/// Id of the result.
public $iId;
/// House number (only for interpolation results).
public $iHouseNumber = -1;
/// Number of exact matches in address (address searches only).
public $iExactMatches = 0;
/// Subranking within the results (the higher the worse).
public $iResultRank = 0;
/// Address rank of the result.
public $iAddressRank;
public function debugInfo()
{
return array(
'Table' => $this->iTable,
'ID' => $this->iId,
'House number' => $this->iHouseNumber,
'Exact Matches' => $this->iExactMatches,
'Result rank' => $this->iResultRank
);
}
public function __construct($sId, $iTable = Result::TABLE_PLACEX)
{
$this->iTable = $iTable;
$this->iId = (int) $sId;
}
public static function joinIdsByTable($aResults, $iTable)
{
return join(',', array_keys(array_filter(
$aResults,
function ($aValue) use ($iTable) {
return $aValue->iTable == $iTable;
}
)));
}
public static function joinIdsByTableMinRank($aResults, $iTable, $iMinAddressRank)
{
return join(',', array_keys(array_filter(
$aResults,
function ($aValue) use ($iTable, $iMinAddressRank) {
return $aValue->iTable == $iTable && $aValue->iAddressRank >= $iMinAddressRank;
}
)));
}
public static function joinIdsByTableMaxRank($aResults, $iTable, $iMaxAddressRank)
{
return join(',', array_keys(array_filter(
$aResults,
function ($aValue) use ($iTable, $iMaxAddressRank) {
return $aValue->iTable == $iTable && $aValue->iAddressRank <= $iMaxAddressRank;
}
)));
}
public static function sqlHouseNumberTable($aResults, $iTable)
{
$sHousenumbers = '';
$sSep = '';
foreach ($aResults as $oResult) {
if ($oResult->iTable == $iTable) {
$sHousenumbers .= $sSep.'('.$oResult->iId.',';
$sHousenumbers .= $oResult->iHouseNumber.')';
$sSep = ',';
}
}
return $sHousenumbers;
}
/**
* Split a result array into highest ranked result and the rest
*
* @param object[] $aResults List of results to split.
*
* @return array[]
*/
public static function splitResults($aResults)
{
$aHead = array();
$aTail = array();
$iMinRank = 10000;
foreach ($aResults as $oRes) {
if ($oRes->iResultRank < $iMinRank) {
$aTail += $aHead;
$aHead = array($oRes->iId => $oRes);
$iMinRank = $oRes->iResultRank;
} elseif ($oRes->iResultRank == $iMinRank) {
$aHead[$oRes->iId] = $oRes;
} else {
$aTail[$oRes->iId] = $oRes;
}
}
return array('head' => $aHead, 'tail' => $aTail);
}
}

View File

@@ -1,401 +0,0 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
require_once(CONST_LibDir.'/Result.php');
class ReverseGeocode
{
protected $oDB;
protected $iMaxRank = 28;
public function __construct(&$oDB)
{
$this->oDB =& $oDB;
}
public function setZoom($iZoom)
{
// Zoom to rank, this could probably be calculated but a lookup gives fine control
$aZoomRank = array(
0 => 2, // Continent / Sea
1 => 2,
2 => 2,
3 => 4, // Country
4 => 4,
5 => 8, // State
6 => 10, // Region
7 => 10,
8 => 12, // County
9 => 12,
10 => 17, // City
11 => 17,
12 => 18, // Town
13 => 19, // Village
14 => 22, // Neighbourhood
15 => 25, // Locality
16 => 26, // major street
17 => 27, // minor street
18 => 30, // or >, Building
19 => 30, // or >, Building
);
$this->iMaxRank = (isset($iZoom) && isset($aZoomRank[$iZoom]))?$aZoomRank[$iZoom]:28;
}
/**
* Find the closest interpolation with the given search diameter.
*
* @param string $sPointSQL Reverse geocoding point as SQL
* @param float $fSearchDiam Search diameter
*
* @return Record of the interpolation or null.
*/
protected function lookupInterpolation($sPointSQL, $fSearchDiam)
{
Debug::newFunction('lookupInterpolation');
$sSQL = 'SELECT place_id, parent_place_id, 30 as rank_search,';
$sSQL .= ' (CASE WHEN endnumber != startnumber';
$sSQL .= ' THEN (endnumber - startnumber) * ST_LineLocatePoint(linegeo,'.$sPointSQL.')';
$sSQL .= ' ELSE startnumber END) as fhnr,';
$sSQL .= ' startnumber, endnumber, step,';
$sSQL .= ' ST_Distance(linegeo,'.$sPointSQL.') as distance';
$sSQL .= ' FROM location_property_osmline';
$sSQL .= ' WHERE ST_DWithin('.$sPointSQL.', linegeo, '.$fSearchDiam.')';
$sSQL .= ' and indexed_status = 0 and startnumber is not NULL ';
$sSQL .= ' and parent_place_id != 0';
$sSQL .= ' ORDER BY distance ASC limit 1';
Debug::printSQL($sSQL);
return $this->oDB->getRow(
$sSQL,
null,
'Could not determine closest housenumber on an osm interpolation line.'
);
}
protected function lookupLargeArea($sPointSQL, $iMaxRank)
{
$sCountryCode = $this->getCountryCode($sPointSQL);
if (CONST_Search_WithinCountries and $sCountryCode == null) {
return null;
}
if ($iMaxRank > 4) {
$aPlace = $this->lookupPolygon($sPointSQL, $iMaxRank);
if ($aPlace) {
return new Result($aPlace['place_id']);
}
}
// If no polygon which contains the searchpoint is found,
// searches in the country_osm_grid table for a polygon.
return $this->lookupInCountry($sPointSQL, $iMaxRank, $sCountryCode);
}
protected function getCountryCode($sPointSQL)
{
Debug::newFunction('getCountryCode');
// searches for polygon in table country_osm_grid which contains the searchpoint
// and searches for the nearest place node to the searchpoint in this polygon
$sSQL = 'SELECT country_code FROM country_osm_grid';
$sSQL .= ' WHERE ST_CONTAINS(geometry, '.$sPointSQL.') LIMIT 1';
Debug::printSQL($sSQL);
$sCountryCode = $this->oDB->getOne(
$sSQL,
null,
'Could not determine country polygon containing the point.'
);
return $sCountryCode;
}
protected function lookupInCountry($sPointSQL, $iMaxRank, $sCountryCode)
{
Debug::newFunction('lookupInCountry');
if ($sCountryCode) {
if ($iMaxRank > 4) {
// look for place nodes with the given country code
$sSQL = 'SELECT place_id FROM';
$sSQL .= ' (SELECT place_id, rank_search,';
$sSQL .= ' ST_distance('.$sPointSQL.', geometry) as distance';
$sSQL .= ' FROM placex';
$sSQL .= ' WHERE osm_type = \'N\'';
$sSQL .= ' AND country_code = \''.$sCountryCode.'\'';
$sSQL .= ' AND rank_address between 4 and 25'; // needed to select right index
$sSQL .= ' AND rank_search between 5 and ' .min(25, $iMaxRank);
$sSQL .= ' AND type != \'postcode\'';
$sSQL .= ' AND name IS NOT NULL ';
$sSQL .= ' and indexed_status = 0 and linked_place_id is null';
$sSQL .= ' AND ST_Buffer(geometry, reverse_place_diameter(rank_search)) && '.$sPointSQL;
$sSQL .= ') as a ';
$sSQL .= 'WHERE distance <= reverse_place_diameter(rank_search)';
$sSQL .= ' ORDER BY rank_search DESC, distance ASC';
$sSQL .= ' LIMIT 1';
Debug::printSQL($sSQL);
$aPlace = $this->oDB->getRow($sSQL, null, 'Could not determine place node.');
Debug::printVar('Country node', $aPlace);
if ($aPlace) {
return new Result($aPlace['place_id']);
}
}
// still nothing, then return the country object
$sSQL = 'SELECT place_id, ST_distance('.$sPointSQL.', centroid) as distance';
$sSQL .= ' FROM placex';
$sSQL .= ' WHERE country_code = \''.$sCountryCode.'\'';
$sSQL .= ' AND rank_search = 4 AND rank_address = 4';
$sSQL .= ' AND class in (\'boundary\', \'place\')';
$sSQL .= ' AND linked_place_id is null';
$sSQL .= ' ORDER BY distance ASC';
Debug::printSQL($sSQL);
$aPlace = $this->oDB->getRow($sSQL, null, 'Could not determine place node.');
Debug::printVar('Country place', $aPlace);
if ($aPlace) {
return new Result($aPlace['place_id']);
}
}
return null;
}
/**
* Search for areas or nodes for areas or nodes between state and suburb level.
*
* @param string $sPointSQL Search point as SQL string.
* @param int $iMaxRank Maximum address rank of the feature.
*
* @return Record of the found feature or null.
*
* Searches first for polygon that contains the search point.
* If such a polygon is found, place nodes with a higher rank are
* searched inside the polygon.
*/
protected function lookupPolygon($sPointSQL, $iMaxRank)
{
Debug::newFunction('lookupPolygon');
// polygon search begins at suburb-level
if ($iMaxRank > 25) {
$iMaxRank = 25;
}
// no polygon search over country-level
if ($iMaxRank < 5) {
$iMaxRank = 5;
}
// search for polygon
$sSQL = 'SELECT place_id, parent_place_id, rank_address, rank_search FROM';
$sSQL .= '(select place_id, parent_place_id, rank_address, rank_search, country_code, geometry';
$sSQL .= ' FROM placex';
$sSQL .= ' WHERE ST_GeometryType(geometry) in (\'ST_Polygon\', \'ST_MultiPolygon\')';
// Ensure that query planner doesn't use the index on rank_search.
$sSQL .= ' AND coalesce(rank_search, 0) between 5 and ' .$iMaxRank;
$sSQL .= ' AND rank_address between 4 and 25'; // needed for index selection
$sSQL .= ' AND geometry && '.$sPointSQL;
$sSQL .= ' AND type != \'postcode\' ';
$sSQL .= ' AND name is not null';
$sSQL .= ' AND indexed_status = 0 and linked_place_id is null';
$sSQL .= ' ORDER BY rank_search DESC LIMIT 50 ) as a';
$sSQL .= ' WHERE ST_Contains(geometry, '.$sPointSQL.' )';
$sSQL .= ' ORDER BY rank_search DESC LIMIT 1';
Debug::printSQL($sSQL);
$aPoly = $this->oDB->getRow($sSQL, null, 'Could not determine polygon containing the point.');
Debug::printVar('Polygon result', $aPoly);
if ($aPoly) {
// if a polygon is found, search for placenodes begins ...
$iRankAddress = $aPoly['rank_address'];
$iRankSearch = $aPoly['rank_search'];
$iPlaceID = $aPoly['place_id'];
if ($iRankSearch != $iMaxRank) {
$sSQL = 'SELECT place_id FROM ';
$sSQL .= '(SELECT place_id, rank_search, country_code, geometry,';
$sSQL .= ' ST_distance('.$sPointSQL.', geometry) as distance';
$sSQL .= ' FROM placex';
$sSQL .= ' WHERE osm_type = \'N\'';
$sSQL .= ' AND rank_search > '.$iRankSearch;
$sSQL .= ' AND rank_search <= '.$iMaxRank;
$sSQL .= ' AND rank_address between 4 and 25'; // needed to select right index
$sSQL .= ' AND type != \'postcode\'';
$sSQL .= ' AND name IS NOT NULL ';
$sSQL .= ' AND indexed_status = 0 AND linked_place_id is null';
$sSQL .= ' AND ST_Buffer(geometry, reverse_place_diameter(rank_search)) && '.$sPointSQL;
$sSQL .= ' ORDER BY rank_search DESC, distance ASC';
$sSQL .= ' limit 100) as a';
$sSQL .= ' WHERE ST_Contains((SELECT geometry FROM placex WHERE place_id = '.$iPlaceID.'), geometry )';
$sSQL .= ' AND distance <= reverse_place_diameter(rank_search)';
$sSQL .= ' ORDER BY rank_search DESC, distance ASC';
$sSQL .= ' LIMIT 1';
Debug::printSQL($sSQL);
$aPlaceNode = $this->oDB->getRow($sSQL, null, 'Could not determine place node.');
Debug::printVar('Nearest place node', $aPlaceNode);
if ($aPlaceNode) {
return $aPlaceNode;
}
}
}
return $aPoly;
}
public function lookup($fLat, $fLon, $bDoInterpolation = true)
{
return $this->lookupPoint(
'ST_SetSRID(ST_Point('.$fLon.','.$fLat.'),4326)',
$bDoInterpolation
);
}
public function lookupPoint($sPointSQL, $bDoInterpolation = true)
{
Debug::newFunction('lookupPoint');
// Find the nearest point
$fSearchDiam = 0.006;
$oResult = null;
$aPlace = null;
// for POI or street level
if ($this->iMaxRank >= 26) {
// starts if the search is on POI or street level,
// searches for the nearest POI or street,
// if a street is found and a POI is searched for,
// the nearest POI which the found street is a parent of is chosen.
$sSQL = 'select place_id,parent_place_id,rank_address,country_code,';
$sSQL .= ' ST_distance('.$sPointSQL.', geometry) as distance';
$sSQL .= ' FROM ';
$sSQL .= ' placex';
$sSQL .= ' WHERE ST_DWithin('.$sPointSQL.', geometry, '.$fSearchDiam.')';
$sSQL .= ' AND';
$sSQL .= ' rank_address between 26 and '.$this->iMaxRank;
$sSQL .= ' and (name is not null or housenumber is not null';
$sSQL .= ' or rank_address between 26 and 27)';
$sSQL .= ' and (rank_address between 26 and 27';
$sSQL .= ' or ST_GeometryType(geometry) != \'ST_LineString\')';
$sSQL .= ' and class not in (\'boundary\')';
$sSQL .= ' and indexed_status = 0 and linked_place_id is null';
$sSQL .= ' and (ST_GeometryType(geometry) not in (\'ST_Polygon\',\'ST_MultiPolygon\') ';
$sSQL .= ' OR ST_DWithin('.$sPointSQL.', centroid, '.$fSearchDiam.'))';
$sSQL .= ' ORDER BY distance ASC limit 1';
Debug::printSQL($sSQL);
$aPlace = $this->oDB->getRow($sSQL, null, 'Could not determine closest place.');
Debug::printVar('POI/street level result', $aPlace);
if ($aPlace) {
$iPlaceID = $aPlace['place_id'];
$oResult = new Result($iPlaceID);
$iRankAddress = $aPlace['rank_address'];
}
if ($aPlace) {
// if street and maxrank > streetlevel
if ($iRankAddress <= 27 && $this->iMaxRank > 27) {
// find the closest object (up to a certain radius) of which the street is a parent of
$sSQL = ' select place_id,';
$sSQL .= ' ST_distance('.$sPointSQL.', geometry) as distance';
$sSQL .= ' FROM ';
$sSQL .= ' placex';
// radius ?
$sSQL .= ' WHERE ST_DWithin('.$sPointSQL.', geometry, 0.001)';
$sSQL .= ' AND parent_place_id = '.$iPlaceID;
$sSQL .= ' and rank_address > 28';
$sSQL .= ' and ST_GeometryType(geometry) != \'ST_LineString\'';
$sSQL .= ' and (name is not null or housenumber is not null)';
$sSQL .= ' and class not in (\'boundary\')';
$sSQL .= ' and indexed_status = 0 and linked_place_id is null';
$sSQL .= ' ORDER BY distance ASC limit 1';
Debug::printSQL($sSQL);
$aStreet = $this->oDB->getRow($sSQL, null, 'Could not determine closest place.');
Debug::printVar('Closest POI result', $aStreet);
if ($aStreet) {
$aPlace = $aStreet;
$oResult = new Result($aStreet['place_id']);
$iRankAddress = 30;
}
}
// In the US we can check TIGER data for nearest housenumber
if (CONST_Use_US_Tiger_Data
&& $iRankAddress <= 27
&& $aPlace['country_code'] == 'us'
&& $this->iMaxRank >= 28
) {
$sSQL = 'SELECT place_id,parent_place_id,30 as rank_search,';
$sSQL .= ' (endnumber - startnumber) * ST_LineLocatePoint(linegeo,'.$sPointSQL.') as fhnr,';
$sSQL .= ' startnumber, endnumber, step,';
$sSQL .= ' ST_Distance('.$sPointSQL.', linegeo) as distance';
$sSQL .= ' FROM location_property_tiger WHERE parent_place_id = '.$oResult->iId;
$sSQL .= ' AND ST_DWithin('.$sPointSQL.', linegeo, 0.001)';
$sSQL .= ' ORDER BY distance ASC limit 1';
Debug::printSQL($sSQL);
$aPlaceTiger = $this->oDB->getRow($sSQL, null, 'Could not determine closest Tiger place.');
Debug::printVar('Tiger house number result', $aPlaceTiger);
if ($aPlaceTiger) {
$aPlace = $aPlaceTiger;
$oResult = new Result($aPlaceTiger['place_id'], Result::TABLE_TIGER);
$iRndNum = max(0, round($aPlaceTiger['fhnr'] / $aPlaceTiger['step']) * $aPlaceTiger['step']);
$oResult->iHouseNumber = $aPlaceTiger['startnumber'] + $iRndNum;
if ($oResult->iHouseNumber > $aPlaceTiger['endnumber']) {
$oResult->iHouseNumber = $aPlaceTiger['endnumber'];
}
$iRankAddress = 30;
}
}
}
if ($bDoInterpolation && $this->iMaxRank >= 30) {
$fDistance = $fSearchDiam;
if ($aPlace) {
// We can't reliably go from the closest street to an
// interpolation line because the closest interpolation
// may have a different street segments as a parent.
// Therefore allow an interpolation line to take precedence
// even when the street is closer.
$fDistance = $iRankAddress < 28 ? 0.001 : $aPlace['distance'];
}
$aHouse = $this->lookupInterpolation($sPointSQL, $fDistance);
Debug::printVar('Interpolation result', $aPlace);
if ($aHouse) {
$oResult = new Result($aHouse['place_id'], Result::TABLE_OSMLINE);
$iRndNum = max(0, round($aHouse['fhnr'] / $aHouse['step']) * $aHouse['step']);
$oResult->iHouseNumber = $aHouse['startnumber'] + $iRndNum;
if ($oResult->iHouseNumber > $aHouse['endnumber']) {
$oResult->iHouseNumber = $aHouse['endnumber'];
}
$aPlace = $aHouse;
}
}
if (!$aPlace) {
// if no POI or street is found ...
$oResult = $this->lookupLargeArea($sPointSQL, 25);
}
} else {
// lower than street level ($iMaxRank < 26 )
$oResult = $this->lookupLargeArea($sPointSQL, $this->iMaxRank);
}
Debug::printVar('Final result', $oResult);
return $oResult;
}
}

View File

@@ -1,319 +0,0 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
require_once(CONST_LibDir.'/lib.php');
/**
* Collection of search constraints that are independent of the
* actual interpretation of the search query.
*
* The search context is shared between all SearchDescriptions. This
* object mainly serves as context provider for the database queries.
* Therefore most data is directly cached as SQL statements.
*/
class SearchContext
{
/// Search radius around a given Near reference point.
private $fNearRadius = false;
/// True if search must be restricted to viewbox only.
public $bViewboxBounded = false;
/// Reference point for search (as SQL).
public $sqlNear = '';
/// Viewbox selected for search (as SQL).
public $sqlViewboxSmall = '';
/// Viewbox with a larger buffer around (as SQL).
public $sqlViewboxLarge = '';
/// Reference along a route (as SQL).
public $sqlViewboxCentre = '';
/// List of countries to restrict search to (as array).
public $aCountryList = null;
/// List of countries to restrict search to (as SQL).
public $sqlCountryList = '';
/// List of place IDs to exclude (as SQL).
private $sqlExcludeList = '';
/// Subset of word ids of full words in the query.
private $aFullNameWords = array();
public function setFullNameWords($aWordList)
{
$this->aFullNameWords = $aWordList;
}
public function getFullNameTerms()
{
return $this->aFullNameWords;
}
/**
* Check if a reference point is defined.
*
* @return bool True if a reference point is defined.
*/
public function hasNearPoint()
{
return $this->fNearRadius !== false;
}
/**
* Get radius around reference point.
*
* @return float Search radius around reference point.
*/
public function nearRadius()
{
return $this->fNearRadius;
}
/**
* Set search reference point in WGS84.
*
* If set, then only places around this point will be taken into account.
*
* @param float $fLat Latitude of point.
* @param float $fLon Longitude of point.
* @param float $fRadius Search radius around point.
*
* @return void
*/
public function setNearPoint($fLat, $fLon, $fRadius = 0.1)
{
$this->fNearRadius = $fRadius;
$this->sqlNear = 'ST_SetSRID(ST_Point('.$fLon.','.$fLat.'),4326)';
}
/**
* Check if the search is geographically restricted.
*
* Searches are restricted if a reference point is given or if
* a bounded viewbox is set.
*
* @return bool True, if the search is geographically bounded.
*/
public function isBoundedSearch()
{
return $this->hasNearPoint() || ($this->sqlViewboxSmall && $this->bViewboxBounded);
}
/**
* Set rectangular viewbox.
*
* The viewbox may be bounded which means that no search results
* must be outside the viewbox.
*
* @param float[4] $aViewBox Coordinates of the viewbox.
* @param bool $bBounded True if the viewbox is bounded.
*
* @return void
*/
public function setViewboxFromBox(&$aViewBox, $bBounded)
{
$this->bViewboxBounded = $bBounded;
$this->sqlViewboxCentre = '';
$this->sqlViewboxSmall = sprintf(
'ST_SetSRID(ST_MakeBox2D(ST_Point(%F,%F),ST_Point(%F,%F)),4326)',
$aViewBox[0],
$aViewBox[1],
$aViewBox[2],
$aViewBox[3]
);
$fHeight = abs($aViewBox[0] - $aViewBox[2]);
$fWidth = abs($aViewBox[1] - $aViewBox[3]);
$this->sqlViewboxLarge = sprintf(
'ST_SetSRID(ST_MakeBox2D(ST_Point(%F,%F),ST_Point(%F,%F)),4326)',
max($aViewBox[0], $aViewBox[2]) + $fHeight,
max($aViewBox[1], $aViewBox[3]) + $fWidth,
min($aViewBox[0], $aViewBox[2]) - $fHeight,
min($aViewBox[1], $aViewBox[3]) - $fWidth
);
}
/**
* Set viewbox along a route.
*
* The viewbox may be bounded which means that no search results
* must be outside the viewbox.
*
* @param object $oDB Nominatim::DB instance to use for computing the box.
* @param string[] $aRoutePoints List of x,y coordinates along a route.
* @param float $fRouteWidth Buffer around the route to use.
* @param bool $bBounded True if the viewbox bounded.
*
* @return void
*/
public function setViewboxFromRoute(&$oDB, $aRoutePoints, $fRouteWidth, $bBounded)
{
$this->bViewboxBounded = $bBounded;
$this->sqlViewboxCentre = "ST_SetSRID('LINESTRING(";
$sSep = '';
foreach ($aRoutePoints as $aPoint) {
$fPoint = (float)$aPoint;
$this->sqlViewboxCentre .= $sSep.$fPoint;
$sSep = ($sSep == ' ') ? ',' : ' ';
}
$this->sqlViewboxCentre .= ")'::geometry,4326)";
$sSQL = 'ST_BUFFER('.$this->sqlViewboxCentre.','.($fRouteWidth/69).')';
$sGeom = $oDB->getOne('select '.$sSQL, null, 'Could not get small viewbox');
$this->sqlViewboxSmall = "'".$sGeom."'::geometry";
$sSQL = 'ST_BUFFER('.$this->sqlViewboxCentre.','.($fRouteWidth/30).')';
$sGeom = $oDB->getOne('select '.$sSQL, null, 'Could not get large viewbox');
$this->sqlViewboxLarge = "'".$sGeom."'::geometry";
}
/**
* Set list of excluded place IDs.
*
* @param integer[] $aExcluded List of IDs.
*
* @return void
*/
public function setExcludeList($aExcluded)
{
$this->sqlExcludeList = ' not in ('.join(',', $aExcluded).')';
}
/**
* Set list of countries to restrict search to.
*
* @param string[] $aCountries List of two-letter lower-case country codes.
*
* @return void
*/
public function setCountryList($aCountries)
{
$this->sqlCountryList = '('.join(',', array_map('addQuotes', $aCountries)).')';
$this->aCountryList = $aCountries;
}
/**
* Extract a reference point from a query string.
*
* @param string $sQuery Query to scan.
*
* @return string The remaining query string.
*/
public function setNearPointFromQuery($sQuery)
{
$aResult = parseLatLon($sQuery);
if ($aResult !== false
&& $aResult[1] <= 90.1
&& $aResult[1] >= -90.1
&& $aResult[2] <= 180.1
&& $aResult[2] >= -180.1
) {
$this->setNearPoint($aResult[1], $aResult[2]);
$sQuery = trim(str_replace($aResult[0], ' ', $sQuery));
}
return $sQuery;
}
/**
* Get an SQL snippet for computing the distance from the reference point.
*
* @param string $sObj SQL variable name to compute the distance from.
*
* @return string An SQL string.
*/
public function distanceSQL($sObj)
{
return 'ST_Distance('.$this->sqlNear.", $sObj)";
}
/**
* Get an SQL snippet for checking if something is within range of the
* reference point.
*
* @param string $sObj SQL variable name to compute if it is within range.
*
* @return string An SQL string.
*/
public function withinSQL($sObj)
{
return sprintf('ST_DWithin(%s, %s, %F)', $sObj, $this->sqlNear, $this->fNearRadius);
}
/**
* Get an SQL snippet of the importance factor of the viewbox.
*
* The importance factor is computed by checking if an object is within
* the viewbox and/or the extended version of the viewbox.
*
* @param string $sObj SQL variable name of object to weight the importance
*
* @return string SQL snippet of the factor with a leading multiply sign.
*/
public function viewboxImportanceSQL($sObj)
{
$sSQL = '';
if ($this->sqlViewboxSmall) {
$sSQL = " * CASE WHEN ST_Contains($this->sqlViewboxSmall, $sObj) THEN 1 ELSE 0.5 END";
}
if ($this->sqlViewboxLarge) {
$sSQL = " * CASE WHEN ST_Contains($this->sqlViewboxLarge, $sObj) THEN 1 ELSE 0.5 END";
}
return $sSQL;
}
/**
* SQL snippet checking if a place ID should be excluded.
*
* @param string $sVariable SQL variable name of place ID to check,
* potentially prefixed with more SQL.
*
* @return string SQL snippet.
*/
public function excludeSQL($sVariable)
{
if ($this->sqlExcludeList) {
return $sVariable.$this->sqlExcludeList;
}
return '';
}
/**
* Check if the given country is covered by the search context.
*
* @param string $sCountryCode Country code of the country to check.
*
* @return True, if no country code restrictions are set or the
* country is included in the country list.
*/
public function isCountryApplicable($sCountryCode)
{
return $this->aCountryList === null || in_array($sCountryCode, $this->aCountryList);
}
public function debugInfo()
{
return array(
'Near radius' => $this->fNearRadius,
'Near point (SQL)' => $this->sqlNear,
'Bounded viewbox' => $this->bViewboxBounded,
'Viewbox (SQL, small)' => $this->sqlViewboxSmall,
'Viewbox (SQL, large)' => $this->sqlViewboxLarge,
'Viewbox (SQL, centre)' => $this->sqlViewboxCentre,
'Countries (SQL)' => $this->sqlCountryList,
'Excluded IDs (SQL)' => $this->sqlExcludeList
);
}
}

View File

@@ -1,985 +0,0 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
require_once(CONST_LibDir.'/SpecialSearchOperator.php');
require_once(CONST_LibDir.'/SearchContext.php');
require_once(CONST_LibDir.'/Result.php');
/**
* Description of a single interpretation of a search query.
*/
class SearchDescription
{
/// Ranking how well the description fits the query.
private $iSearchRank = 0;
/// Country code of country the result must belong to.
private $sCountryCode = '';
/// List of word ids making up the name of the object.
private $aName = array();
/// True if the name is rare enough to force index use on name.
private $bRareName = false;
/// True if the name requires to be accompanied by address terms.
private $bNameNeedsAddress = false;
/// List of word ids making up the address of the object.
private $aAddress = array();
/// List of word ids that appear in the name but should be ignored.
private $aNameNonSearch = array();
/// List of word ids that appear in the address but should be ignored.
private $aAddressNonSearch = array();
/// Kind of search for special searches, see Nominatim::Operator.
private $iOperator = Operator::NONE;
/// Class of special feature to search for.
private $sClass = '';
/// Type of special feature to search for.
private $sType = '';
/// Housenumber of the object.
private $sHouseNumber = '';
/// Postcode for the object.
private $sPostcode = '';
/// Global search constraints.
private $oContext;
// Temporary values used while creating the search description.
/// Index of phrase currently processed.
private $iNamePhrase = -1;
/**
* Create an empty search description.
*
* @param object $oContext Global context to use. Will be inherited by
* all derived search objects.
*/
public function __construct($oContext)
{
$this->oContext = $oContext;
}
/**
* Get current search rank.
*
* The higher the search rank the lower the likelihood that the
* search is a correct interpretation of the search query.
*
* @return integer Search rank.
*/
public function getRank()
{
return $this->iSearchRank;
}
/**
* Extract key/value pairs from a query.
*
* Key/value pairs are recognised if they are of the form [<key>=<value>].
* If multiple terms of this kind are found then all terms are removed
* but only the first is used for search.
*
* @param string $sQuery Original query string.
*
* @return string The query string with the special search patterns removed.
*/
public function extractKeyValuePairs($sQuery)
{
// Search for terms of kind [<key>=<value>].
preg_match_all(
'/\\[([\\w_]*)=([\\w_]*)\\]/',
$sQuery,
$aSpecialTermsRaw,
PREG_SET_ORDER
);
foreach ($aSpecialTermsRaw as $aTerm) {
$sQuery = str_replace($aTerm[0], ' ', $sQuery);
if (!$this->hasOperator()) {
$this->setPoiSearch(Operator::TYPE, $aTerm[1], $aTerm[2]);
}
}
return $sQuery;
}
/**
* Check if the combination of parameters is sensible.
*
* @return bool True, if the search looks valid.
*/
public function isValidSearch()
{
if (empty($this->aName)) {
if ($this->sHouseNumber) {
return false;
}
if (!$this->sClass && !$this->sCountryCode) {
return false;
}
}
if ($this->bNameNeedsAddress && empty($this->aAddress)) {
return false;
}
return true;
}
/////////// Search building functions
/**
* Create a copy of this search description adding to search rank.
*
* @param integer $iTermCost Cost to add to the current search rank.
*
* @return object Cloned search description.
*/
public function clone($iTermCost)
{
$oSearch = clone $this;
$oSearch->iSearchRank += $iTermCost;
return $oSearch;
}
/**
* Check if the search currently includes a name.
*
* @param bool bIncludeNonNames If true stop-word tokens are taken into
* account, too.
*
* @return bool True, if search has a name.
*/
public function hasName($bIncludeNonNames = false)
{
return !empty($this->aName)
|| (!empty($this->aNameNonSearch) && $bIncludeNonNames);
}
/**
* Check if the search currently includes an address term.
*
* @return bool True, if any address term is included, including stop-word
* terms.
*/
public function hasAddress()
{
return !empty($this->aAddress) || !empty($this->aAddressNonSearch);
}
/**
* Check if a country restriction is currently included in the search.
*
* @return bool True, if a country restriction is set.
*/
public function hasCountry()
{
return $this->sCountryCode !== '';
}
/**
* Check if a postcode is currently included in the search.
*
* @return bool True, if a postcode is set.
*/
public function hasPostcode()
{
return $this->sPostcode !== '';
}
/**
* Check if a house number is set for the search.
*
* @return bool True, if a house number is set.
*/
public function hasHousenumber()
{
return $this->sHouseNumber !== '';
}
/**
* Check if a special type of place is requested.
*
* param integer iOperator When set, check for the particular
* operator used for the special type.
*
* @return bool True, if speial type is requested or, if requested,
* a special type with the given operator.
*/
public function hasOperator($iOperator = null)
{
return $iOperator === null ? $this->iOperator != Operator::NONE : $this->iOperator == $iOperator;
}
/**
* Add the given token to the list of terms to search for in the address.
*
* @param integer iID ID of term to add.
* @param bool bSearchable Term should be used to search for result
* (i.e. term is not a stop word).
*/
public function addAddressToken($iId, $bSearchable = true)
{
if ($bSearchable) {
$this->aAddress[$iId] = $iId;
} else {
$this->aAddressNonSearch[$iId] = $iId;
}
}
/**
* Add the given full-word token to the list of terms to search for in the
* name.
*
* @param integer iId ID of term to add.
* @param bool bRareName True if the term is infrequent enough to not
* require other constraints for efficient search.
*/
public function addNameToken($iId, $bRareName)
{
$this->aName[$iId] = $iId;
$this->bRareName = $bRareName;
$this->bNameNeedsAddress = false;
}
/**
* Add the given partial token to the list of terms to search for in
* the name.
*
* @param integer iID ID of term to add.
* @param bool bSearchable Term should be used to search for result
* (i.e. term is not a stop word).
* @param bool bNeedsAddress True if the term is too unspecific to be used
* in a stand-alone search without an address
* to narrow down the search.
* @param integer iPhraseNumber Index of phrase, where the partial term
* appears.
*/
public function addPartialNameToken($iId, $bSearchable, $bNeedsAddress, $iPhraseNumber)
{
if (empty($this->aName)) {
$this->bNameNeedsAddress = $bNeedsAddress;
} elseif ($bSearchable && count($this->aName) >= 2) {
$this->bNameNeedsAddress = false;
} else {
$this->bNameNeedsAddress &= $bNeedsAddress;
}
if ($bSearchable) {
$this->aName[$iId] = $iId;
} else {
$this->aNameNonSearch[$iId] = $iId;
}
$this->iNamePhrase = $iPhraseNumber;
}
/**
* Set country restriction for the search.
*
* @param string sCountryCode Country code of country to restrict search to.
*/
public function setCountry($sCountryCode)
{
$this->sCountryCode = $sCountryCode;
$this->iNamePhrase = -1;
}
/**
* Set postcode search constraint.
*
* @param string sPostcode Postcode the result should have.
*/
public function setPostcode($sPostcode)
{
$this->sPostcode = $sPostcode;
$this->iNamePhrase = -1;
}
/**
* Make this search a search for a postcode object.
*
* @param integer iId Token Id for the postcode.
* @param string sPostcode Postcode to look for.
*/
public function setPostcodeAsName($iId, $sPostcode)
{
$this->iOperator = Operator::POSTCODE;
$this->aAddress = array_merge($this->aAddress, $this->aName);
$this->aName = array($iId => $sPostcode);
$this->bRareName = true;
$this->iNamePhrase = -1;
}
/**
* Set house number search cnstraint.
*
* @param string sNumber House number the result should have.
*/
public function setHousenumber($sNumber)
{
$this->sHouseNumber = $sNumber;
$this->iNamePhrase = -1;
}
/**
* Make this search a search for a house number.
*
* @param integer iId Token Id for the house number.
*/
public function setHousenumberAsName($iId)
{
$this->aAddress = array_merge($this->aAddress, $this->aName);
$this->bRareName = false;
$this->bNameNeedsAddress = true;
$this->aName = array($iId => $iId);
$this->iNamePhrase = -1;
}
/**
* Make this search a POI search.
*
* In a POI search, objects are not (only) searched by their name
* but also by the primary OSM key/value pair (class and type in Nominatim).
*
* @param integer $iOperator Type of POI search
* @param string $sClass Class (or OSM tag key) of POI.
* @param string $sType Type (or OSM tag value) of POI.
*
* @return void
*/
public function setPoiSearch($iOperator, $sClass, $sType)
{
$this->iOperator = $iOperator;
$this->sClass = $sClass;
$this->sType = $sType;
$this->iNamePhrase = -1;
}
public function getNamePhrase()
{
return $this->iNamePhrase;
}
/**
* Get the global search context.
*
* @return object Objects of global search constraints.
*/
public function getContext()
{
return $this->oContext;
}
/////////// Query functions
/**
* Query database for places that match this search.
*
* @param object $oDB Nominatim::DB instance to use.
* @param integer $iMinRank Minimum address rank to restrict search to.
* @param integer $iMaxRank Maximum address rank to restrict search to.
* @param integer $iLimit Maximum number of results.
*
* @return mixed[] An array with two fields: IDs contains the list of
* matching place IDs and houseNumber the houseNumber
* if applicable or -1 if not.
*/
public function query(&$oDB, $iMinRank, $iMaxRank, $iLimit)
{
$aResults = array();
if ($this->sCountryCode
&& empty($this->aName)
&& !$this->iOperator
&& !$this->sClass
&& !$this->oContext->hasNearPoint()
) {
// Just looking for a country - look it up
if (4 >= $iMinRank && 4 <= $iMaxRank) {
$aResults = $this->queryCountry($oDB);
}
} elseif (empty($this->aName) && empty($this->aAddress)) {
// Neither name nor address? Then we must be
// looking for a POI in a geographic area.
if ($this->oContext->isBoundedSearch()) {
$aResults = $this->queryNearbyPoi($oDB, $iLimit);
}
} elseif ($this->iOperator == Operator::POSTCODE) {
// looking for postcode
$aResults = $this->queryPostcode($oDB, $iLimit);
} else {
// Ordinary search:
// First search for places according to name and address.
$aResults = $this->queryNamedPlace(
$oDB,
$iMinRank,
$iMaxRank,
$iLimit
);
// finally get POIs if requested
if ($this->sClass && !empty($aResults)) {
$aResults = $this->queryPoiByOperator($oDB, $aResults, $iLimit);
}
}
Debug::printDebugTable('Place IDs', $aResults);
if (!empty($aResults) && $this->sPostcode) {
$sPlaceIds = Result::joinIdsByTable($aResults, Result::TABLE_PLACEX);
if ($sPlaceIds) {
$sSQL = 'SELECT place_id FROM placex';
$sSQL .= ' WHERE place_id in ('.$sPlaceIds.')';
$sSQL .= " AND postcode != '".$this->sPostcode."'";
Debug::printSQL($sSQL);
$aFilteredPlaceIDs = $oDB->getCol($sSQL);
if ($aFilteredPlaceIDs) {
foreach ($aFilteredPlaceIDs as $iPlaceId) {
$aResults[$iPlaceId]->iResultRank++;
}
}
}
}
return $aResults;
}
private function queryCountry(&$oDB)
{
$sSQL = 'SELECT place_id FROM placex ';
$sSQL .= "WHERE country_code='".$this->sCountryCode."'";
$sSQL .= ' AND rank_search = 4';
if ($this->oContext->bViewboxBounded) {
$sSQL .= ' AND ST_Intersects('.$this->oContext->sqlViewboxSmall.', geometry)';
}
$sSQL .= ' ORDER BY st_area(geometry) DESC LIMIT 1';
Debug::printSQL($sSQL);
$iPlaceId = $oDB->getOne($sSQL);
$aResults = array();
if ($iPlaceId) {
$aResults[$iPlaceId] = new Result($iPlaceId);
}
return $aResults;
}
private function queryNearbyPoi(&$oDB, $iLimit)
{
if (!$this->sClass) {
return array();
}
$aDBResults = array();
$sPoiTable = $this->poiTable();
if ($oDB->tableExists($sPoiTable)) {
$sSQL = 'SELECT place_id FROM '.$sPoiTable.' ct';
if ($this->oContext->sqlCountryList) {
$sSQL .= ' JOIN placex USING (place_id)';
}
if ($this->oContext->hasNearPoint()) {
$sSQL .= ' WHERE '.$this->oContext->withinSQL('ct.centroid');
} elseif ($this->oContext->bViewboxBounded) {
$sSQL .= ' WHERE ST_Contains('.$this->oContext->sqlViewboxSmall.', ct.centroid)';
}
if ($this->oContext->sqlCountryList) {
$sSQL .= ' AND country_code in '.$this->oContext->sqlCountryList;
}
$sSQL .= $this->oContext->excludeSQL(' AND place_id');
if ($this->oContext->sqlViewboxCentre) {
$sSQL .= ' ORDER BY ST_Distance(';
$sSQL .= $this->oContext->sqlViewboxCentre.', ct.centroid) ASC';
} elseif ($this->oContext->hasNearPoint()) {
$sSQL .= ' ORDER BY '.$this->oContext->distanceSQL('ct.centroid').' ASC';
}
$sSQL .= " LIMIT $iLimit";
Debug::printSQL($sSQL);
$aDBResults = $oDB->getCol($sSQL);
}
if ($this->oContext->hasNearPoint()) {
$sSQL = 'SELECT place_id FROM placex WHERE ';
$sSQL .= 'class = :class and type = :type';
$sSQL .= ' AND '.$this->oContext->withinSQL('geometry');
$sSQL .= ' AND linked_place_id is null';
if ($this->oContext->sqlCountryList) {
$sSQL .= ' AND country_code in '.$this->oContext->sqlCountryList;
}
$sSQL .= ' ORDER BY '.$this->oContext->distanceSQL('centroid').' ASC';
$sSQL .= " LIMIT $iLimit";
Debug::printSQL($sSQL);
$aDBResults = $oDB->getCol(
$sSQL,
array(':class' => $this->sClass, ':type' => $this->sType)
);
}
$aResults = array();
foreach ($aDBResults as $iPlaceId) {
$aResults[$iPlaceId] = new Result($iPlaceId);
}
return $aResults;
}
private function queryPostcode(&$oDB, $iLimit)
{
$sSQL = 'SELECT p.place_id FROM location_postcode p ';
if (!empty($this->aAddress)) {
$sSQL .= ', search_name s ';
$sSQL .= 'WHERE s.place_id = p.parent_place_id ';
$sSQL .= 'AND array_cat(s.nameaddress_vector, s.name_vector)';
$sSQL .= ' @> '.$oDB->getArraySQL($this->aAddress).' AND ';
} else {
$sSQL .= 'WHERE ';
}
$sSQL .= "p.postcode = '".reset($this->aName)."'";
$sSQL .= $this->countryCodeSQL(' AND p.country_code');
if ($this->oContext->bViewboxBounded) {
$sSQL .= ' AND ST_Intersects('.$this->oContext->sqlViewboxSmall.', geometry)';
}
$sSQL .= $this->oContext->excludeSQL(' AND p.place_id');
$sSQL .= " LIMIT $iLimit";
Debug::printSQL($sSQL);
$aResults = array();
foreach ($oDB->getCol($sSQL) as $iPlaceId) {
$aResults[$iPlaceId] = new Result($iPlaceId, Result::TABLE_POSTCODE);
}
return $aResults;
}
private function queryNamedPlace(&$oDB, $iMinAddressRank, $iMaxAddressRank, $iLimit)
{
$aTerms = array();
$aOrder = array();
if (!empty($this->aName)) {
$aTerms[] = 'name_vector @> '.$oDB->getArraySQL($this->aName);
}
if (!empty($this->aAddress)) {
// For infrequent name terms disable index usage for address
if ($this->bRareName) {
$aTerms[] = 'array_cat(nameaddress_vector,ARRAY[]::integer[]) @> '.$oDB->getArraySQL($this->aAddress);
} else {
$aTerms[] = 'nameaddress_vector @> '.$oDB->getArraySQL($this->aAddress);
}
}
$sCountryTerm = $this->countryCodeSQL('country_code');
if ($sCountryTerm) {
$aTerms[] = $sCountryTerm;
}
if ($this->sHouseNumber) {
$aTerms[] = 'address_rank between 16 and 30';
} elseif (!$this->sClass || $this->iOperator == Operator::NAME) {
if ($iMinAddressRank > 0) {
$aTerms[] = "((address_rank between $iMinAddressRank and $iMaxAddressRank) or (search_rank between $iMinAddressRank and $iMaxAddressRank))";
}
}
if ($this->oContext->hasNearPoint()) {
$aTerms[] = $this->oContext->withinSQL('centroid');
$aOrder[] = $this->oContext->distanceSQL('centroid');
} elseif ($this->sPostcode) {
if (empty($this->aAddress)) {
$aTerms[] = "EXISTS(SELECT place_id FROM location_postcode p WHERE p.postcode = '".$this->sPostcode."' AND ST_DWithin(search_name.centroid, p.geometry, 0.12))";
} else {
$aOrder[] = "(SELECT min(ST_Distance(search_name.centroid, p.geometry)) FROM location_postcode p WHERE p.postcode = '".$this->sPostcode."')";
}
}
$sExcludeSQL = $this->oContext->excludeSQL('place_id');
if ($sExcludeSQL) {
$aTerms[] = $sExcludeSQL;
}
if ($this->oContext->bViewboxBounded) {
$aTerms[] = 'centroid && '.$this->oContext->sqlViewboxSmall;
}
if ($this->sHouseNumber) {
$sImportanceSQL = '- abs(26 - address_rank) + 3';
} else {
$sImportanceSQL = '(CASE WHEN importance = 0 OR importance IS NULL THEN 0.75001-(search_rank::float/40) ELSE importance END)';
}
$sImportanceSQL .= $this->oContext->viewboxImportanceSQL('centroid');
$aOrder[] = "$sImportanceSQL DESC";
$aFullNameAddress = $this->oContext->getFullNameTerms();
if (!empty($aFullNameAddress)) {
$sExactMatchSQL = ' ( ';
$sExactMatchSQL .= ' SELECT count(*) FROM ( ';
$sExactMatchSQL .= ' SELECT unnest('.$oDB->getArraySQL($aFullNameAddress).')';
$sExactMatchSQL .= ' INTERSECT ';
$sExactMatchSQL .= ' SELECT unnest(nameaddress_vector)';
$sExactMatchSQL .= ' ) s';
$sExactMatchSQL .= ') as exactmatch';
$aOrder[] = 'exactmatch DESC';
} else {
$sExactMatchSQL = '0::int as exactmatch';
}
if (empty($aTerms)) {
return array();
}
if ($this->hasHousenumber()) {
$sHouseNumberRegex = $oDB->getDBQuoted('\\\\m'.$this->sHouseNumber.'\\\\M');
// Housenumbers on streets and places.
$sPlacexSql = 'SELECT array_agg(place_id) FROM placex';
$sPlacexSql .= ' WHERE parent_place_id = sin.place_id AND sin.address_rank < 30';
$sPlacexSql .= $this->oContext->excludeSQL(' AND place_id');
$sPlacexSql .= ' and housenumber ~* E'.$sHouseNumberRegex;
// Interpolations on streets and places.
$sInterpolSql = 'null';
$sTigerSql = 'null';
if (preg_match('/^[0-9]+$/', $this->sHouseNumber)) {
$sIpolHnr = 'WHERE parent_place_id = sin.place_id ';
$sIpolHnr .= ' AND startnumber is not NULL AND sin.address_rank < 30';
$sIpolHnr .= ' AND '.$this->sHouseNumber.' between startnumber and endnumber';
$sIpolHnr .= ' AND ('.$this->sHouseNumber.' - startnumber) % step = 0';
$sInterpolSql = 'SELECT array_agg(place_id) FROM location_property_osmline '.$sIpolHnr;
if (CONST_Use_US_Tiger_Data) {
$sTigerSql = 'SELECT array_agg(place_id) FROM location_property_tiger '.$sIpolHnr;
$sTigerSql .= " and sin.country_code = 'us'";
}
}
if ($this->sClass) {
$iLimit = 40;
}
$sSelfHnr = 'SELECT * FROM placex WHERE place_id = search_name.place_id';
$sSelfHnr .= ' AND housenumber ~* E'.$sHouseNumberRegex;
$aTerms[] = '(address_rank < 30 or exists('.$sSelfHnr.'))';
$sSQL = 'SELECT sin.*, ';
$sSQL .= '('.$sPlacexSql.') as placex_hnr, ';
$sSQL .= '('.$sInterpolSql.') as interpol_hnr, ';
$sSQL .= '('.$sTigerSql.') as tiger_hnr ';
$sSQL .= ' FROM (';
$sSQL .= ' SELECT place_id, address_rank, country_code,'.$sExactMatchSQL.',';
$sSQL .= ' CASE WHEN importance = 0 OR importance IS NULL';
$sSQL .= ' THEN 0.75001-(search_rank::float/40) ELSE importance END as importance';
$sSQL .= ' FROM search_name';
$sSQL .= ' WHERE '.join(' and ', $aTerms);
$sSQL .= ' ORDER BY '.join(', ', $aOrder);
$sSQL .= ' LIMIT 40000';
$sSQL .= ') as sin';
$sSQL .= ' ORDER BY address_rank = 30 desc, placex_hnr, interpol_hnr, tiger_hnr,';
$sSQL .= ' importance';
$sSQL .= ' LIMIT '.$iLimit;
} else {
if ($this->sClass) {
$iLimit = 40;
}
$sSQL = 'SELECT place_id, address_rank, '.$sExactMatchSQL;
$sSQL .= ' FROM search_name';
$sSQL .= ' WHERE '.join(' and ', $aTerms);
$sSQL .= ' ORDER BY '.join(', ', $aOrder);
$sSQL .= ' LIMIT '.$iLimit;
}
Debug::printSQL($sSQL);
$aDBResults = $oDB->getAll($sSQL, null, 'Could not get places for search terms.');
$aResults = array();
foreach ($aDBResults as $aResult) {
$oResult = new Result($aResult['place_id']);
$oResult->iExactMatches = $aResult['exactmatch'];
$oResult->iAddressRank = $aResult['address_rank'];
$bNeedResult = true;
if ($this->hasHousenumber() && $aResult['address_rank'] < 30) {
if ($aResult['placex_hnr']) {
foreach (explode(',', substr($aResult['placex_hnr'], 1, -1)) as $sPlaceID) {
$iPlaceID = intval($sPlaceID);
$oHnrResult = new Result($iPlaceID);
$oHnrResult->iExactMatches = $aResult['exactmatch'];
$oHnrResult->iAddressRank = 30;
$aResults[$iPlaceID] = $oHnrResult;
$bNeedResult = false;
}
}
if ($aResult['interpol_hnr']) {
foreach (explode(',', substr($aResult['interpol_hnr'], 1, -1)) as $sPlaceID) {
$iPlaceID = intval($sPlaceID);
$oHnrResult = new Result($iPlaceID, Result::TABLE_OSMLINE);
$oHnrResult->iExactMatches = $aResult['exactmatch'];
$oHnrResult->iAddressRank = 30;
$oHnrResult->iHouseNumber = intval($this->sHouseNumber);
$aResults[$iPlaceID] = $oHnrResult;
$bNeedResult = false;
}
}
if ($aResult['tiger_hnr']) {
foreach (explode(',', substr($aResult['tiger_hnr'], 1, -1)) as $sPlaceID) {
$iPlaceID = intval($sPlaceID);
$oHnrResult = new Result($iPlaceID, Result::TABLE_TIGER);
$oHnrResult->iExactMatches = $aResult['exactmatch'];
$oHnrResult->iAddressRank = 30;
$oHnrResult->iHouseNumber = intval($this->sHouseNumber);
$aResults[$iPlaceID] = $oHnrResult;
$bNeedResult = false;
}
}
if ($aResult['address_rank'] < 26) {
$oResult->iResultRank += 2;
} else {
$oResult->iResultRank++;
}
}
if ($bNeedResult) {
$aResults[$aResult['place_id']] = $oResult;
}
}
return $aResults;
}
private function queryPoiByOperator(&$oDB, $aParentIDs, $iLimit)
{
$aResults = array();
$sPlaceIDs = Result::joinIdsByTable($aParentIDs, Result::TABLE_PLACEX);
if (!$sPlaceIDs) {
return $aResults;
}
if ($this->iOperator == Operator::TYPE || $this->iOperator == Operator::NAME) {
// If they were searching for a named class (i.e. 'Kings Head pub')
// then we might have an extra match
$sSQL = 'SELECT place_id FROM placex ';
$sSQL .= " WHERE place_id in ($sPlaceIDs)";
$sSQL .= " AND class='".$this->sClass."' ";
$sSQL .= " AND type='".$this->sType."'";
$sSQL .= ' AND linked_place_id is null';
$sSQL .= $this->oContext->excludeSQL(' AND place_id');
$sSQL .= ' ORDER BY rank_search ASC ';
$sSQL .= " LIMIT $iLimit";
Debug::printSQL($sSQL);
foreach ($oDB->getCol($sSQL) as $iPlaceId) {
$aResults[$iPlaceId] = new Result($iPlaceId);
}
}
// NEAR and IN are handled the same
if ($this->iOperator == Operator::TYPE || $this->iOperator == Operator::NEAR) {
$sClassTable = $this->poiTable();
$bCacheTable = $oDB->tableExists($sClassTable);
$sSQL = "SELECT min(rank_search) FROM placex WHERE place_id in ($sPlaceIDs)";
Debug::printSQL($sSQL);
$iMaxRank = (int) $oDB->getOne($sSQL);
// For state / country level searches the normal radius search doesn't work very well
$sPlaceGeom = false;
if ($iMaxRank < 9 && $bCacheTable) {
// Try and get a polygon to search in instead
$sSQL = 'SELECT geometry FROM placex';
$sSQL .= " WHERE place_id in ($sPlaceIDs)";
$sSQL .= " AND rank_search < $iMaxRank + 5";
$sSQL .= ' AND ST_Area(Box2d(geometry)) < 20';
$sSQL .= " AND ST_GeometryType(geometry) in ('ST_Polygon','ST_MultiPolygon')";
$sSQL .= ' ORDER BY rank_search ASC ';
$sSQL .= ' LIMIT 1';
Debug::printSQL($sSQL);
$sPlaceGeom = $oDB->getOne($sSQL);
}
if ($sPlaceGeom) {
$sPlaceIDs = false;
} else {
$iMaxRank += 5;
$sSQL = 'SELECT place_id FROM placex';
$sSQL .= " WHERE place_id in ($sPlaceIDs) and rank_search < $iMaxRank";
Debug::printSQL($sSQL);
$aPlaceIDs = $oDB->getCol($sSQL);
$sPlaceIDs = join(',', $aPlaceIDs);
}
if ($sPlaceIDs || $sPlaceGeom) {
$fRange = 0.01;
if ($bCacheTable) {
// More efficient - can make the range bigger
$fRange = 0.05;
$sOrderBySQL = '';
if ($this->oContext->hasNearPoint()) {
$sOrderBySQL = $this->oContext->distanceSQL('l.centroid');
} elseif ($sPlaceIDs) {
$sOrderBySQL = 'ST_Distance(l.centroid, f.geometry)';
} elseif ($sPlaceGeom) {
$sOrderBySQL = "ST_Distance(st_centroid('".$sPlaceGeom."'), l.centroid)";
}
$sSQL = 'SELECT distinct i.place_id';
if ($sOrderBySQL) {
$sSQL .= ', i.order_term';
}
$sSQL .= ' from (SELECT l.place_id';
if ($sOrderBySQL) {
$sSQL .= ','.$sOrderBySQL.' as order_term';
}
$sSQL .= ' from '.$sClassTable.' as l';
if ($sPlaceIDs) {
$sSQL .= ',placex as f WHERE ';
$sSQL .= "f.place_id in ($sPlaceIDs) ";
$sSQL .= " AND ST_DWithin(l.centroid, f.centroid, $fRange)";
} elseif ($sPlaceGeom) {
$sSQL .= " WHERE ST_Contains('$sPlaceGeom', l.centroid)";
}
$sSQL .= $this->oContext->excludeSQL(' AND l.place_id');
$sSQL .= 'limit 300) i ';
if ($sOrderBySQL) {
$sSQL .= 'order by order_term asc';
}
$sSQL .= " limit $iLimit";
Debug::printSQL($sSQL);
foreach ($oDB->getCol($sSQL) as $iPlaceId) {
$aResults[$iPlaceId] = new Result($iPlaceId);
}
} else {
if ($this->oContext->hasNearPoint()) {
$fRange = $this->oContext->nearRadius();
}
$sOrderBySQL = '';
if ($this->oContext->hasNearPoint()) {
$sOrderBySQL = $this->oContext->distanceSQL('l.geometry');
} else {
$sOrderBySQL = 'ST_Distance(l.geometry, f.geometry)';
}
$sSQL = 'SELECT distinct l.place_id';
if ($sOrderBySQL) {
$sSQL .= ','.$sOrderBySQL.' as orderterm';
}
$sSQL .= ' FROM placex as l, placex as f';
$sSQL .= " WHERE f.place_id in ($sPlaceIDs)";
$sSQL .= " AND ST_DWithin(l.geometry, f.centroid, $fRange)";
$sSQL .= " AND l.class='".$this->sClass."'";
$sSQL .= " AND l.type='".$this->sType."'";
$sSQL .= $this->oContext->excludeSQL(' AND l.place_id');
if ($sOrderBySQL) {
$sSQL .= 'ORDER BY orderterm ASC';
}
$sSQL .= " limit $iLimit";
Debug::printSQL($sSQL);
foreach ($oDB->getCol($sSQL) as $iPlaceId) {
$aResults[$iPlaceId] = new Result($iPlaceId);
}
}
}
}
return $aResults;
}
private function poiTable()
{
return 'place_classtype_'.$this->sClass.'_'.$this->sType;
}
private function countryCodeSQL($sVar)
{
if ($this->sCountryCode) {
return $sVar.' = \''.$this->sCountryCode."'";
}
if ($this->oContext->sqlCountryList) {
return $sVar.' in '.$this->oContext->sqlCountryList;
}
return '';
}
/////////// Sort functions
public static function bySearchRank($a, $b)
{
if ($a->iSearchRank == $b->iSearchRank) {
return $a->iOperator + strlen($a->sHouseNumber)
- $b->iOperator - strlen($b->sHouseNumber);
}
return $a->iSearchRank < $b->iSearchRank ? -1 : 1;
}
//////////// Debugging functions
public function debugInfo()
{
return array(
'Search rank' => $this->iSearchRank,
'Country code' => $this->sCountryCode,
'Name terms' => $this->aName,
'Name terms (stop words)' => $this->aNameNonSearch,
'Address terms' => $this->aAddress,
'Address terms (stop words)' => $this->aAddressNonSearch,
'Address terms (full words)' => $this->aFullNameAddress ?? '',
'Special search' => $this->iOperator,
'Class' => $this->sClass,
'Type' => $this->sType,
'House number' => $this->sHouseNumber,
'Postcode' => $this->sPostcode
);
}
public function dumpAsHtmlTableRow(&$aWordIDs)
{
$kf = function ($k) use (&$aWordIDs) {
return $aWordIDs[$k] ?? '['.$k.']';
};
echo '<tr>';
echo "<td>$this->iSearchRank</td>";
echo '<td>'.join(', ', array_map($kf, $this->aName)).'</td>';
echo '<td>'.join(', ', array_map($kf, $this->aNameNonSearch)).'</td>';
echo '<td>'.join(', ', array_map($kf, $this->aAddress)).'</td>';
echo '<td>'.join(', ', array_map($kf, $this->aAddressNonSearch)).'</td>';
echo '<td>'.$this->sCountryCode.'</td>';
echo '<td>'.Operator::toString($this->iOperator).'</td>';
echo '<td>'.$this->sClass.'</td>';
echo '<td>'.$this->sType.'</td>';
echo '<td>'.$this->sPostcode.'</td>';
echo '<td>'.$this->sHouseNumber.'</td>';
echo '</tr>';
}
}

View File

@@ -1,95 +0,0 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
/**
* Description of the position of a token within a query.
*/
class SearchPosition
{
private $sPhraseType;
private $iPhrase;
private $iNumPhrases;
private $iToken;
private $iNumTokens;
public function __construct($sPhraseType, $iPhrase, $iNumPhrases)
{
$this->sPhraseType = $sPhraseType;
$this->iPhrase = $iPhrase;
$this->iNumPhrases = $iNumPhrases;
}
public function setTokenPosition($iToken, $iNumTokens)
{
$this->iToken = $iToken;
$this->iNumTokens = $iNumTokens;
}
/**
* Check if the phrase can be of the given type.
*
* @param string $sType Type of phrse requested.
*
* @return True if the phrase is untyped or of the given type.
*/
public function maybePhrase($sType)
{
return $this->sPhraseType == '' || $this->sPhraseType == $sType;
}
/**
* Check if the phrase is exactly of the given type.
*
* @param string $sType Type of phrse requested.
*
* @return True if the phrase of the given type.
*/
public function isPhrase($sType)
{
return $this->sPhraseType == $sType;
}
/**
* Return true if the token is the very first in the query.
*/
public function isFirstToken()
{
return $this->iPhrase == 0 && $this->iToken == 0;
}
/**
* Check if the token is the final one in the query.
*/
public function isLastToken()
{
return $this->iToken + 1 == $this->iNumTokens && $this->iPhrase + 1 == $this->iNumPhrases;
}
/**
* Check if the current token is part of the first phrase in the query.
*/
public function isFirstPhrase()
{
return $this->iPhrase == 0;
}
/**
* Get the phrase position in the query.
*/
public function getPhrase()
{
return $this->iPhrase;
}
}

View File

@@ -1,92 +0,0 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
class Shell
{
public function __construct($sBaseCmd, ...$aParams)
{
if (!$sBaseCmd) {
throw new \Exception('Command missing in new() call');
}
$this->baseCmd = $sBaseCmd;
$this->aParams = array();
$this->aEnv = null; // null = use the same environment as the current PHP process
$this->stdoutString = null;
foreach ($aParams as $sParam) {
$this->addParams($sParam);
}
}
public function addParams(...$aParams)
{
foreach ($aParams as $sParam) {
if (isset($sParam) && $sParam !== null && $sParam !== '') {
array_push($this->aParams, $sParam);
}
}
return $this;
}
public function addEnvPair($sKey, $sVal)
{
if (isset($sKey) && $sKey && isset($sVal)) {
if (!isset($this->aEnv)) {
$this->aEnv = $_ENV;
}
$this->aEnv = array_merge($this->aEnv, array($sKey => $sVal), $_ENV);
}
return $this;
}
public function escapedCmd()
{
$aEscaped = array_map(function ($sParam) {
return $this->escapeParam($sParam);
}, array_merge(array($this->baseCmd), $this->aParams));
return join(' ', $aEscaped);
}
public function run($bExitOnFail = false)
{
$sCmd = $this->escapedCmd();
// $aEnv does not need escaping, proc_open seems to handle it fine
$aFDs = array(
0 => array('pipe', 'r'),
1 => STDOUT,
2 => STDERR
);
$aPipes = null;
$hProc = @proc_open($sCmd, $aFDs, $aPipes, null, $this->aEnv);
if (!is_resource($hProc)) {
throw new \Exception('Unable to run command: ' . $sCmd);
}
fclose($aPipes[0]); // no stdin
$iStat = proc_close($hProc);
if ($iStat != 0 && $bExitOnFail) {
exit($iStat);
}
return $iStat;
}
private function escapeParam($sParam)
{
return (preg_match('/^-*\w+$/', $sParam)) ? $sParam : escapeshellarg($sParam);
}
}

View File

@@ -1,144 +0,0 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
/**
* A word list creator based on simple splitting by space.
*
* Creates possible permutations of split phrases by finding all combination
* of splitting the phrase on space boundaries.
*/
class SimpleWordList
{
const MAX_WORDSET_LEN = 20;
const MAX_WORDSETS = 100;
// The phrase as a list of simple terms (without spaces).
private $aWords;
/**
* Create a new word list
*
* @param string sPhrase Phrase to create the word list from. The phrase is
* expected to be normalised, so that there are no
* subsequent spaces.
*/
public function __construct($sPhrase)
{
if (strlen($sPhrase) > 0) {
$this->aWords = explode(' ', $sPhrase);
} else {
$this->aWords = array();
}
}
/**
* Get all possible tokens that are present in this word list.
*
* @return array The list of string tokens in the word list.
*/
public function getTokens()
{
$aTokens = array();
$iNumWords = count($this->aWords);
for ($i = 0; $i < $iNumWords; $i++) {
$sPhrase = $this->aWords[$i];
$aTokens[$sPhrase] = $sPhrase;
for ($j = $i + 1; $j < $iNumWords; $j++) {
$sPhrase .= ' '.$this->aWords[$j];
$aTokens[$sPhrase] = $sPhrase;
}
}
return $aTokens;
}
/**
* Compute all possible permutations of phrase splits that result in
* words which are in the token list.
*/
public function getWordSets($oTokens)
{
$iNumWords = count($this->aWords);
if ($iNumWords == 0) {
return null;
}
// Caches the word set for the partial phrase up to word i.
$aSetCache = array_fill(0, $iNumWords, array());
// Initialise first element of cache. There can only be the word.
if ($oTokens->containsAny($this->aWords[0])) {
$aSetCache[0][] = array($this->aWords[0]);
}
// Now do the next elements using what we already have.
for ($i = 1; $i < $iNumWords; $i++) {
for ($j = $i; $j > 0; $j--) {
$sPartial = $j == $i ? $this->aWords[$j] : $this->aWords[$j].' '.$sPartial;
if (!empty($aSetCache[$j - 1]) && $oTokens->containsAny($sPartial)) {
$aPartial = array($sPartial);
foreach ($aSetCache[$j - 1] as $aSet) {
if (count($aSet) < SimpleWordList::MAX_WORDSET_LEN) {
$aSetCache[$i][] = array_merge($aSet, $aPartial);
}
}
if (count($aSetCache[$i]) > 2 * SimpleWordList::MAX_WORDSETS) {
usort(
$aSetCache[$i],
array('\Nominatim\SimpleWordList', 'cmpByArraylen')
);
$aSetCache[$i] = array_slice(
$aSetCache[$i],
0,
SimpleWordList::MAX_WORDSETS
);
}
}
}
// finally the current full phrase
$sPartial = $this->aWords[0].' '.$sPartial;
if ($oTokens->containsAny($sPartial)) {
$aSetCache[$i][] = array($sPartial);
}
}
$aWordSets = $aSetCache[$iNumWords - 1];
usort($aWordSets, array('\Nominatim\SimpleWordList', 'cmpByArraylen'));
return array_slice($aWordSets, 0, SimpleWordList::MAX_WORDSETS);
}
/**
* Custom search routine which takes two arrays. The array with the fewest
* items wins. If same number of items then the one with the longest first
* element wins.
*/
public static function cmpByArraylen($aA, $aB)
{
$iALen = count($aA);
$iBLen = count($aB);
if ($iALen == $iBLen) {
return strlen($aB[0]) <=> strlen($aA[0]);
}
return ($iALen < $iBLen) ? -1 : 1;
}
public function debugInfo()
{
return $this->aWords;
}
}

View File

@@ -1,52 +0,0 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
/**
* Operators describing special searches.
*/
abstract class Operator
{
/// No operator selected.
const NONE = 0;
/// Search for POI of the given type.
const TYPE = 1;
/// Search for POIs near the given place.
const NEAR = 2;
/// Search for POIS in the given place.
const IN = 3;
/// Search for POIS named as given.
const NAME = 4;
/// Search for postcodes.
const POSTCODE = 5;
private static $aConstantNames = null;
public static function toString($iOperator)
{
if ($iOperator == Operator::NONE) {
return '';
}
if (Operator::$aConstantNames === null) {
$oReflector = new \ReflectionClass('Nominatim\Operator');
$aConstants = $oReflector->getConstants();
Operator::$aConstantNames = array();
foreach ($aConstants as $sName => $iValue) {
Operator::$aConstantNames[$iValue] = $sName;
}
}
return Operator::$aConstantNames[$iOperator];
}
}

View File

@@ -1,59 +0,0 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
require_once(CONST_TokenizerDir.'/tokenizer.php');
use Exception;
class Status
{
protected $oDB;
public function __construct(&$oDB)
{
$this->oDB =& $oDB;
}
public function status()
{
if (!$this->oDB) {
throw new Exception('No database', 700);
}
try {
$this->oDB->connect();
} catch (\Nominatim\DatabaseError $e) {
throw new Exception('Database connection failed', 700);
}
$oTokenizer = new \Nominatim\Tokenizer($this->oDB);
$oTokenizer->checkStatus();
}
public function dataDate()
{
$sSQL = 'SELECT EXTRACT(EPOCH FROM lastimportdate) FROM import_status LIMIT 1';
$iDataDateEpoch = $this->oDB->getOne($sSQL);
if ($iDataDateEpoch === false) {
throw new Exception('Import date is not available', 705);
}
return $iDataDateEpoch;
}
public function databaseVersion()
{
$sSQL = 'SELECT value FROM nominatim_properties WHERE property = \'database_version\'';
return $this->oDB->getOne($sSQL);
}
}

Some files were not shown because too many files have changed in this diff Show More