Compare commits

..

947 Commits

Author SHA1 Message Date
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
Sarah Hoffmann
64c1a4fc8c add changelog for 4.2.3 2023-09-07 10:07:16 +02:00
Sarah Hoffmann
ec47459410 prepare release 4.3.0 2023-09-06 20:08:28 +02:00
Sarah Hoffmann
c55c3657c3 reenable logging of details calls 2023-09-06 11:35:53 +02:00
Sarah Hoffmann
8b56b55761 restrict deduplication to results from placex
All other sources do not have deduplicatable entries.
2023-09-06 10:43:55 +02:00
Sarah Hoffmann
9056c9276f add bbox output to lookup results
Fixes #3149.
2023-09-06 10:27:03 +02:00
marc tobias
09ae312f09 documentation: fix a broken link, typos 2023-09-05 17:06:32 +02:00
Sarah Hoffmann
d6960c72e4 Merge pull request #3190 from lonvia/fix-internal-server-errors
Fix more failing queries
2023-09-05 17:00:31 +02:00
Sarah Hoffmann
b529e054cf Merge pull request #3189 from lonvia/add-country-area-restriction
Implement NOMINATIM_SEARCH_WITHIN_COUNTRIES for Python frontend
2023-09-05 14:29:44 +02:00
Sarah Hoffmann
b4a4ca81d1 actions: update to checkout v4 2023-09-05 11:44:12 +02:00
Sarah Hoffmann
c284df2dc9 restrict range for interpolated housenumbers
Interpolations are only supported up to 2^32 by the database.
Limit to 8 digits, which is still more than should be needed.
2023-09-05 11:41:41 +02:00
Sarah Hoffmann
18b2a4c204 avoid interpreting integral numbers as coordinates
There are addresses of type '123 W 345 N, Reigh', where 'W 345 N' is
the actual name of the street.
2023-09-05 11:26:47 +02:00
Sarah Hoffmann
e1303fb592 Merge pull request #3188 from lonvia/update-osm2pgsql
Update osm2pgsql to 1.9.2
2023-09-05 10:44:32 +02:00
Sarah Hoffmann
bd25cf04ed update osm2pgsql to 1.9.2 2023-09-04 14:53:46 +02:00
Sarah Hoffmann
ce1f4cbbdc allow lower case OSM types in lookup query 2023-09-04 14:39:35 +02:00
Sarah Hoffmann
e0aea0f27a Merge pull request #3186 from lonvia/tablespaces-for-flex
Make tablespace arguments work again for flex tables
2023-09-04 14:25:45 +02:00
Sarah Hoffmann
9848c4c56c implement NOMINATIM_SEARCH_WITHIN_COUNTRIES setting 2023-09-04 14:10:36 +02:00
Sarah Hoffmann
cb8149f8ea reenable tablespace arguments for flex tables 2023-09-04 10:45:52 +02:00
Sarah Hoffmann
0e74e82a38 add a shutdown handler for falcon server closing DB connections 2023-08-31 09:40:56 +02:00
Sarah Hoffmann
15e09f2b24 remove alias where it does not work with lambdas
Fixes #3177.
2023-08-30 21:55:34 +02:00
Sarah Hoffmann
2de8256863 fix parameter name for layer filter 2023-08-30 09:57:46 +02:00
Sarah Hoffmann
aff43fb1a3 Merge pull request #3178 from lonvia/library-documentation
Update documentation for new Python frontend
2023-08-30 09:17:24 +02:00
Sarah Hoffmann
cafd8e2b1e fix typos and grammar issues 2023-08-29 12:14:44 +02:00
Sarah Hoffmann
3794080327 rename documentation to 'Nominatim Manual' 2023-08-28 10:59:26 +02:00
Sarah Hoffmann
4e2683f068 adapt installation instruction for different frontends 2023-08-28 10:48:34 +02:00
Sarah Hoffmann
6e5f595d48 update API documentation 2023-08-28 10:31:58 +02:00
Sarah Hoffmann
2c24ba6d2d add deployment documentation for Python frontend 2023-08-27 21:27:16 +02:00
Sarah Hoffmann
3bb27fbee6 update documentation for configuration 2023-08-27 16:08:06 +02:00
Sarah Hoffmann
ef1b52eee5 add getting started section for library docs 2023-08-27 14:42:04 +02:00
Sarah Hoffmann
f917fa67aa switch to material theme
Needed for tabbed code blocks.
2023-08-25 22:47:07 +02:00
Sarah Hoffmann
386b4c82da preliminary library reference finished 2023-08-25 21:40:20 +02:00
Sarah Hoffmann
a987f22cfb more library documentation 2023-08-25 21:40:20 +02:00
Sarah Hoffmann
558c42ec83 finish configuration section 2023-08-25 21:40:20 +02:00
Sarah Hoffmann
309ac46b98 restructure library documentation 2023-08-25 21:40:20 +02:00
Sarah Hoffmann
399b04596e initial configuration documentation 2023-08-25 21:40:20 +02:00
Sarah Hoffmann
75513a23a8 docs: documentation of API classes 2023-08-25 21:40:20 +02:00
Sarah Hoffmann
e672de036e more adaptions for mkdocstrings griffin plugin 2023-08-25 21:40:20 +02:00
Sarah Hoffmann
6533af6a91 add base framework for library reference 2023-08-25 21:40:20 +02:00
Sarah Hoffmann
d3372e69ec update to modern mkdocstrings python handler 2023-08-25 21:40:20 +02:00
Sarah Hoffmann
f3809a52e8 Merge pull request #3174 from lonvia/osm2pgsql-update-fix
Be more precise on what is deleted on updates
2023-08-25 21:26:23 +02:00
Sarah Hoffmann
c5f5ab5363 be more strict about removal from place_to_be_deleted
If the type of a place is changed and then the same insert issued
again, the old data will effectively remain in the table.

Fixed #3168.
2023-08-25 14:22:49 +02:00
Sarah Hoffmann
26dfb868e9 add test case for bad update 2023-08-25 14:22:49 +02:00
Sarah Hoffmann
d5b6042118 Merge pull request #3172 from lonvia/query-timeout
Introduce timeouts for queries
2023-08-25 10:00:22 +02:00
Sarah Hoffmann
1115705cbc add additional timeout for entire request 2023-08-25 09:16:53 +02:00
Sarah Hoffmann
161d17d85b use backwards-compatible asyncio timeout implementation 2023-08-25 08:50:03 +02:00
Sarah Hoffmann
5a2ebfcd4a translate query timeouts into proper HTTP responses
Need to use a 503 here because a 408 (Request timeout) will motivate
browsers to immediately resent the request.
2023-08-25 08:50:03 +02:00
Sarah Hoffmann
06a974df36 add a timeout for DB queries 2023-08-25 08:50:03 +02:00
Sarah Hoffmann
2762c45569 apply adjusted counts only to final result 2023-08-24 21:37:02 +02:00
Sarah Hoffmann
fd85483ce3 Merge pull request #3169 from lonvia/tweak-search-with-frequent-names
Further tweak detection of queries that would return a massive amount of results
2023-08-24 14:22:35 +02:00
Sarah Hoffmann
0a2d0c3b5c allow terms with frequent searches together with viewbox 2023-08-24 09:21:09 +02:00
Sarah Hoffmann
de7f9a4bd9 Merge pull request #3167 from lonvia/explicit-encoding
Send explicit charset in content-type when returning json
2023-08-24 08:53:11 +02:00
Sarah Hoffmann
c5836c8090 Merge pull request #3139 from mtmail/update-search-examples
Search.md - update XML and JSON example output
2023-08-23 23:41:30 +02:00
Sarah Hoffmann
dcdda314e2 further tweak search containing very frequent tokens
Excluding non-rare full names is not really possible because it makes
addresses with street names like 'main st' unsearchable. This tries to
leav all names in but refrain from ordering results by accuracy
when too many results are expected. This means that the DB will simply
get the first n results without any particular order.
2023-08-23 23:04:12 +02:00
Sarah Hoffmann
a9edd57fe2 send charset again in content-type when returning json
There are quite a few applications out there that will use some local
encoding when the charset is not explicitly given.
2023-08-23 20:55:57 +02:00
Sarah Hoffmann
cbd9fad94b Merge pull request #3165 from lonvia/update-osm2pgsql
Update osm2pgsql to 1.9.1
2023-08-23 15:57:55 +02:00
Sarah Hoffmann
bc1009f8c2 vagrant scripts: add missing yaml library 2023-08-23 08:34:12 +02:00
Sarah Hoffmann
719b66e5ed add new required json library for osm2pgsql 2023-08-23 00:24:31 +02:00
Sarah Hoffmann
5f09ba4e10 update osm2pgsql to 1.9.1 2023-08-23 00:24:31 +02:00
Sarah Hoffmann
517a0cb673 Merge pull request #3159 from lonvia/fix-name-lookup-for-housenames
Fix name lookup for housenames
2023-08-20 15:52:20 +02:00
Sarah Hoffmann
7c79b07817 fix parameter use for ST_Project
Before postgis 3.4 ST_Project required a geography as input and seemed
to have implicitly converted to geography. Since 3.4 geometry input
is supported but leads to a completely different result.
2023-08-20 13:52:03 +02:00
Sarah Hoffmann
23eed4ff2f fix tag name for housename addresses in layer selection
Fixes #3156.
2023-08-19 15:57:33 +02:00
Sarah Hoffmann
4559886d83 Merge pull request #3155 from lonvia/caching-of-transliterators
Cache ICU transliterators between calls
2023-08-16 22:55:54 +02:00
Sarah Hoffmann
bfc706a596 cache ICU transliterators and reuse them 2023-08-15 23:08:44 +02:00
Sarah Hoffmann
9805a461eb Merge pull request #3150 from alfmarcua/allow_neg_id_details
Allow negative osm_id in details page by setting default parameter to 0
2023-08-14 11:41:42 +02:00
Sarah Hoffmann
bcf8433ba8 fix regression in default setting for details linkedplaces 2023-08-13 16:24:19 +02:00
Sarah Hoffmann
746dd057b9 prefer name-only searches more 2023-08-13 15:24:16 +02:00
Sarah Hoffmann
b710297d05 return bbox of full country for country searches
Fixes #3149.
2023-08-13 14:37:28 +02:00
Sarah Hoffmann
0a8e8cec0f fix application of label to wrong expression 2023-08-13 11:59:01 +02:00
Sarah Hoffmann
96e5a23727 avoid lambda SQL in connection with alias tables 2023-08-13 11:40:49 +02:00
Sarah Hoffmann
611b925368 use coalsce() instead of indexless postgis functions
ST_Intersects is deemed too expensive by the query planer which
leads to odd plans when index use is avoided.
2023-08-12 19:14:13 +02:00
Sarah Hoffmann
cab2a74740 do not use index when searching in large areas
This concerns viewboxes as well as radius search.
2023-08-12 16:12:44 +02:00
Sarah Hoffmann
fa3ac22a8f adapt tests to changes in search 2023-08-12 16:12:31 +02:00
Sarah Hoffmann
95d1048789 take token_assignment penalty into account
Also computes the expected count differently when addresses are
involved. Address token counts do not bare a direct relation to
real counts.
2023-08-12 15:33:50 +02:00
Sarah Hoffmann
38b2b8a143 fix debug output for NearSearch
The search info is in a subsearch and was therefore not taken into
account.
2023-08-12 11:27:55 +02:00
Sarah Hoffmann
3d0bc85b4d improve penalty for token-split words
The rematch penalty for partial words created by the transliteration
need to take into account that they are rematched against the full word.
That means that missing beginning and end should not get a significant
penalty.
2023-08-12 11:26:02 +02:00
alfmarcua
25a391070b Allow negative osm_id in details page by setting default parameter to 0 2023-08-11 10:46:28 +02:00
Sarah Hoffmann
926c4a7d04 fix lookup polygon output
Fixes #3147.
2023-08-08 21:31:25 +02:00
marc tobias
5683f55646 Search.md - update XML and JSON example output 2023-08-08 17:49:11 +02:00
Sarah Hoffmann
671f4e943e Merge pull request #3146 from lonvia/forbid-mixed-queries
Do not allow to mix structured and unstructured search
2023-08-08 17:34:32 +02:00
Sarah Hoffmann
282c0da941 return an error when q is used together with structured parameters 2023-08-08 15:54:55 +02:00
Sarah Hoffmann
78648f1faf remove lookup by address only
There are too many lookups where the address is very frequent,
even when many address parts are present.
2023-08-06 21:00:10 +02:00
Sarah Hoffmann
8d9b5e4775 allow oversized viewboxes again
This seems to be a rather regular thing when unconditionally sending
the current view and being zoomed out.

Fixes #3137.
2023-08-06 17:50:35 +02:00
Sarah Hoffmann
996026e5ed provide full URL in more field
This is a regression against the PHP version.

Fixes #3138.
2023-08-06 17:50:02 +02:00
Sarah Hoffmann
2c7e1db5f6 remove SQL lambdas with IN expressions
The values of IN expressions are incorrectly cached.
2023-08-02 12:34:07 +02:00
Sarah Hoffmann
2171b38551 only print non-empty search tables 2023-08-02 09:25:47 +02:00
Sarah Hoffmann
afdbdb02a1 do not lookup by address vector when only few tokens are available
Names of countries and states are exceedingly rare in the word count
but are very frequent in the address. A short name has the danger
of producing too many results.
2023-08-02 09:25:47 +02:00
Sarah Hoffmann
8adeaa2c7e fix regression with lat/lon in json output
lat, lon is returned as strings in the PHP output. Reproduce that in the
Python frontend.

See #3115.
2023-08-01 14:27:43 +02:00
Sarah Hoffmann
d15f605129 allow OPTIONS method in starlette CORS middleware
If not allowed, then the middleware will return a 400 on pre-flight
CORS requests.

Fixes #3129.
2023-08-01 11:12:36 +02:00
Sarah Hoffmann
252fe42612 Merge pull request #3122 from miku0/sanitizer-final
Adds sanitizer for Japanese addresses to correspond to block address
2023-08-01 10:38:58 +02:00
miku0
67e1c7dc72 Moved KANJI_MAP to icu-rules 2023-07-31 11:57:49 +00:00
Sarah Hoffmann
c29ffc38e6 Merge pull request #3128 from lonvia/fix-classtype-lookup
Fix query over classtype tables
2023-07-31 10:20:58 +02:00
miku0
4d61cc87cf Add the test of reconbine_place 2023-07-31 02:39:56 +00:00
miku0
2350018106 Fixed cosmetic issues 2023-07-31 02:39:04 +00:00
Sarah Hoffmann
8fc3dd9457 fix query over classtype tables
The case statement prevented the index on the classtype tables
from being used. Move the case statement inside the geometry
function instead.
2023-07-30 23:51:36 +02:00
Sarah Hoffmann
d97ca9fcb2 Merge pull request #3127 from lonvia/file-logging
Add file logging for Python frontend
2023-07-30 21:22:48 +02:00
Sarah Hoffmann
e523da9e12 reintroduce file logging for Python frontend 2023-07-30 19:58:00 +02:00
miku0
67706cec4e add @fail-legacy 2023-07-27 07:33:53 +00:00
miku0
fac8c32cda Moved KANJI_MAP to global variable 2023-07-26 21:43:22 +00:00
Sarah Hoffmann
1c6f426363 Merge pull request #3125 from lonvia/warm-to-python
Port warm and export functions to Python
2023-07-26 22:37:37 +02:00
Sarah Hoffmann
8cba65809c older version of Postgres cannot convert jsonb to int 2023-07-26 17:45:21 +02:00
Sarah Hoffmann
77ed4f98bb older Python versions need a reference to the loop for a lock 2023-07-26 15:17:18 +02:00
miku0
848e5ac5de Correction to PR's comment 2023-07-26 09:50:25 +00:00
Sarah Hoffmann
9448c5e16f add tests for new arm and export Python functions 2023-07-26 11:09:52 +02:00
miku0
0722495434 add japanese sanitizer 2023-07-26 07:54:58 +00:00
Sarah Hoffmann
d545c6d73c mostly remove php-cgi requirement
This is now only needed for BDD tests against the php API.
2023-07-26 00:10:11 +02:00
Sarah Hoffmann
f69fea4210 remove now unused run_api_script function 2023-07-25 22:45:29 +02:00
Sarah Hoffmann
4cd0a4ced4 remove now unused run_legacy_script() 2023-07-25 21:39:23 +02:00
Sarah Hoffmann
0804cc0cff port export function to Python
Some of the parameters have been renoved as they don't make sense
anymore.
2023-07-25 21:39:23 +02:00
Sarah Hoffmann
faeee7528f move warm script to python code 2023-07-25 21:39:23 +02:00
Sarah Hoffmann
261e0cfd5a Merge pull request #3121 from lonvia/port-remaining-api-calls
Port remaining API endpoints to Python
2023-07-25 20:56:38 +02:00
Sarah Hoffmann
66ecb56cea add tests for new endpoints 2023-07-25 10:57:19 +02:00
Sarah Hoffmann
79bd54f610 add /polygons endpoint to Python v1 API 2023-07-22 20:59:13 +02:00
Sarah Hoffmann
30cef4d5fd add deletable endpoint 2023-07-22 17:21:24 +02:00
Sarah Hoffmann
8d52032263 remove debug print 2023-07-22 13:54:23 +02:00
Sarah Hoffmann
4a5786334b Merge pull request #3117 from lonvia/fix-assorted-search-errors
More improvements to the Python search algorithm
2023-07-22 11:45:36 +02:00
Sarah Hoffmann
587698a6f3 disallow special housenumber search with a single frequent partial 2023-07-20 18:05:54 +02:00
Sarah Hoffmann
927d2cc824 do not split names from typed phrases
When phrases are typed, they should only contain exactly one term.
2023-07-17 20:09:08 +02:00
Sarah Hoffmann
7f9cb4e68d split up get_assignment functon in more readable parts 2023-07-17 16:27:25 +02:00
Sarah Hoffmann
d48ea4f22c disallow address searches that start with a postcode
These are postcode searches and nothing else.
2023-07-17 16:27:25 +02:00
Sarah Hoffmann
412bd2ec20 block search queries with too many tokens 2023-07-17 16:27:25 +02:00
Sarah Hoffmann
1c189060c2 simplify yield_lookups() function
Move creation of field lookups in separate functions to make the code
more readable.
2023-07-17 16:27:25 +02:00
Sarah Hoffmann
4a00a3c0f5 penalize name token splitting when phrases are used 2023-07-17 16:27:25 +02:00
Sarah Hoffmann
8366e4ca83 penalize search with frequent partials
Avoid search against frequent partials if we have already looked for
the full name equivalents.
2023-07-17 16:27:25 +02:00
Sarah Hoffmann
283db76e45 avoid splitting of first token when a housenumber is present
This only covers the case of <poi name> <street name> <housenumber>
which is exceedingly rare.
2023-07-17 16:27:25 +02:00
Sarah Hoffmann
8a36ed4f6f increase threshold for full name searches
They still should be preferrred over expensive partial name searches.
2023-07-17 16:27:25 +02:00
Sarah Hoffmann
d0f45155c8 fix search for housenumber names
The search still included a lookup of housenumbers in children which is
wrong.
2023-07-17 16:27:25 +02:00
Sarah Hoffmann
9fc235d670 Merge pull request #3112 from jenkin/fix-polgyon-polygon-typo
fix polgyon polygon typo
2023-07-17 14:20:14 +02:00
Alessio Cimarelli
42c549274f fix polgyon polygon typo 2023-07-17 10:11:57 +02:00
Sarah Hoffmann
2e56182a7f Merge pull request #3110 from lonvia/sql-lambda-queries
Use SQLAlchemy's lambda statements
2023-07-14 18:57:31 +02:00
Sarah Hoffmann
7932b1849b selected lambdas for search 2023-07-14 15:43:29 +02:00
Sarah Hoffmann
886374d779 add lambdas for layer filters 2023-07-14 15:27:20 +02:00
Sarah Hoffmann
d42e2e391f avoid forwarding variables via SQL 2023-07-14 15:27:16 +02:00
Sarah Hoffmann
f264eaeda2 make SQL statements in reverse lambda functions
Further improves internal caching of statements by SQLAlchemy.
2023-07-14 14:39:14 +02:00
Sarah Hoffmann
35fd74af6d Merge pull request #3096 from alfmarcua/search-within-countries-parameter
Parameterise the search only within countries
2023-07-12 17:45:55 +02:00
alfmarcua
4b53cf1464 Split lookupInCountry in two functions and document NOMINATIM_SEARCH_WITHIN_COUNTRIES parameter 2023-07-12 13:53:23 +02:00
alfmarcua
26e78efbb9 Parameterise the search only within countries 2023-07-12 13:53:23 +02:00
Sarah Hoffmann
157f0b8a83 Merge pull request #3109 from lonvia/prepared-statements
Make prepared statements work with Python API
2023-07-10 11:45:29 +02:00
Sarah Hoffmann
d743cf308e avoid index-use on rank parameters for reverse lookups 2023-07-09 22:49:31 +02:00
Sarah Hoffmann
f4cdcb995c force a fixed pool size and make it configurable 2023-07-09 00:31:53 +02:00
Sarah Hoffmann
75139961a3 use constant expressions to select partial indexes in reverse
When expressions are generated with SQLAlchemy, any constants are
replaced with bind parameters. The bind parameters become parameters of
prepared statements. The result is that the query planner tends to
oversee that the partial indexes can be used.
2023-07-09 00:31:53 +02:00
Sarah Hoffmann
3e2dd59a94 remove disabling of prepared statements
Fixes for query planning with prepared statements to follow in
subsequent commits.
2023-07-08 15:59:15 +02:00
Sarah Hoffmann
c01386b5b4 Merge pull request #3107 from lonvia/performance-search
Assorted fixes to Python search code
2023-07-08 15:53:42 +02:00
Marc Tobias
f59a072aa6 These days the OSM wikipedia tab no longer contains URLs 2023-07-07 17:36:11 +02:00
Sarah Hoffmann
9cb8447673 increase minimum required SQLAlchemy version to 1.4.31 2023-07-06 14:15:51 +02:00
Sarah Hoffmann
e67355ab0e make get_addressdata calls cachable
VALUEs() is not a cachable construct in SQLAlchemy, so use arrays
instead. Also add a special case for single results, the usual result
for reverse queries.
2023-07-06 12:16:57 +02:00
Sarah Hoffmann
9cb9b670d1 add support for postcompile literals in debug output 2023-07-06 12:16:57 +02:00
Sarah Hoffmann
3e725bb2db fix SRID handling in Geometry type 2023-07-06 12:16:57 +02:00
Sarah Hoffmann
cc45930ef9 avoid lookup via partials on frequent words
Drops expensive searches via partials on terms like 'rue de'.

See #2979.
2023-07-06 12:16:57 +02:00
Sarah Hoffmann
3266daa8fd add a small penalty to lookups in address vectors 2023-07-04 16:54:42 +02:00
Sarah Hoffmann
ce17b0eeca Merge pull request #3101 from lonvia/custom-geometry-type
Improve use of SQLAlchemy statement cache with search queries
2023-07-03 11:03:26 +02:00
Sarah Hoffmann
17a65d82bb make types compatible with older Python versions 2023-07-02 23:06:42 +02:00
Sarah Hoffmann
cc7646665c remove GeoAlchemy as dependency 2023-07-02 23:06:42 +02:00
Sarah Hoffmann
82216ebf8b always run function update on migrations
This means that we can have migrations which require nothing but
an update of the functions.
2023-07-01 20:18:59 +02:00
Sarah Hoffmann
49e0d83d5d fix linting issues 2023-07-01 20:18:59 +02:00
Sarah Hoffmann
673c3c7a55 replace regexp_match with generic op() functions
Works around a bug in SQLAlchemy where regexp_match creates an
unstable cache key.
2023-07-01 18:15:22 +02:00
Sarah Hoffmann
5135041405 replace CASE construct with plpgsql function 2023-07-01 18:15:22 +02:00
Sarah Hoffmann
42631b85c7 band-aid for SQLAlchemy 1.4 2023-07-01 18:03:07 +02:00
Sarah Hoffmann
9f6f12cfeb move search to bind parameters 2023-07-01 18:03:07 +02:00
Sarah Hoffmann
6c4c9ec1f2 switch reverse() to new Geometry datatype
Also switches to using bind parameters for recurring parameters.
2023-07-01 18:03:07 +02:00
Sarah Hoffmann
4bb4db0668 introduce slim Geometry database type 2023-07-01 18:03:07 +02:00
Sarah Hoffmann
505fdd02ca Merge pull request #3100 from lonvia/fix-name-merging-in-unnamed-boundaries
Fix merging of linked names into unnamed boundaries
2023-07-01 15:36:56 +02:00
Sarah Hoffmann
a873f260cf fix merging of linked names into unnamed boundaries
The NULL value of the boundaries' name field was erasing all
content when used in SQL operations.
2023-06-30 22:14:11 +02:00
Sarah Hoffmann
b45f761227 Merge pull request #3099 from lonvia/determine-place-address-from-tokenizer
Use information from tokenizer to determine street vs. place address
2023-06-30 21:47:57 +02:00
Sarah Hoffmann
d7a3039c2a also switch legacy tokenizer to new street/place choice behaviour 2023-06-30 17:03:17 +02:00
Sarah Hoffmann
6c5589c9d2 fix optional string representation or repr(PlaceName) 2023-06-30 11:10:44 +02:00
Sarah Hoffmann
645ea5a057 use information from tokenizer to determine street vs. place address
So far the SQL logic used the information from the address field
to determine if an address is attached to a street or place.
This changes the logic to use the information provided in the
token_info. This allows sanitizers to enforce a certain parenting
without changing the visible address information.
2023-06-30 11:08:25 +02:00
Sarah Hoffmann
2755ebe883 Merge pull request #3094 from lonvia/fix-failing-bdd-tests
Add BDD tests against Python frontend to CI
2023-06-22 22:28:31 +02:00
Sarah Hoffmann
4b829b5ff9 Merge pull request #3090 from mtmail/check-database-on-frozen-database
check-database on frozen db shouldnt recommend indexing
2023-06-22 20:11:30 +02:00
Sarah Hoffmann
ed19340af0 add python frontend tests to CI 2023-06-22 17:29:44 +02:00
Sarah Hoffmann
2d05ff0190 slightly adapt postcode tests 2023-06-22 16:51:59 +02:00
Sarah Hoffmann
0d338fa4c0 bdd: fix faking HTTP headers for python web frameworks 2023-06-22 14:00:33 +02:00
mtmail
15a66e7b7d Merge branch 'osm-search:master' into check-database-on-frozen-database 2023-06-22 12:14:55 +02:00
Sarah Hoffmann
3a21999a17 move text normalization into extra function 2023-06-22 10:48:05 +02:00
Sarah Hoffmann
08dcd05d7b Merge pull request #3093 from lonvia/remove-sanic
Remove support for Sanic
2023-06-22 09:55:32 +02:00
Marc Tobias
2337cc653b check-database on frozen db shouldnt recommend indexing 2023-06-21 17:47:57 +02:00
Sarah Hoffmann
0deb9262c9 use in operator for enum tests
Fixes a complaint by mypy.
2023-06-21 15:30:40 +02:00
Sarah Hoffmann
9bc5be837b remove useless check
Found by new mypy version.
2023-06-21 11:56:39 +02:00
Sarah Hoffmann
b79d5494f9 remove support for sanic framework
There is no performance gain over falcon or starlette but the special
structure of sanic makes it hard to have exchangable code
2023-06-21 10:53:57 +02:00
Sarah Hoffmann
ded2c5bf68 update project information for taginfo.json 2023-06-21 10:06:25 +02:00
Sarah Hoffmann
bd2c64876f Merge pull request #3045 from biswajit-k/taginfo
Add script to generate taginfo project description
2023-06-21 10:01:40 +02:00
Sarah Hoffmann
7c66fef63f Merge pull request #3091 from lonvia/fix-postcode-search
Assorted smaller fixes for Python-based search code
2023-06-20 16:13:20 +02:00
Sarah Hoffmann
4ad8818809 avoid fallback country lookup when places are excluded 2023-06-20 12:22:08 +02:00
Sarah Hoffmann
2f4342810d allow empty parts in excluded_place_id
This worked before.
2023-06-20 11:56:43 +02:00
Sarah Hoffmann
36df56b093 fix header name for browser languages 2023-06-20 11:56:43 +02:00
Sarah Hoffmann
d0a1e8e311 tweak postcode search
Give a preference to left-right reading, i.e <postcode>,<address>
prefers a postcode search while <address>,<postcode> rather does
an address search.

Also exclude non-addressables, countries and state from results when a
postcode is contained in the query.
2023-06-20 11:56:43 +02:00
Sarah Hoffmann
1b50381852 use string representation when dumping variables 2023-06-20 10:15:51 +02:00
Sarah Hoffmann
3443d2c129 fix debug output for searches
Fields have been renamed.
2023-06-20 10:12:19 +02:00
Sarah Hoffmann
1f83efa8f2 Merge pull request #3086 from lonvia/close-connection-on-replication
Close database connections while waiting for the next update cycle
2023-06-19 15:48:00 +02:00
Sarah Hoffmann
a7bd39b62a Merge pull request #3087 from lonvia/conditional-spgist
Disable SPGist for PostgreSQL < 11
2023-06-19 15:47:37 +02:00
Sarah Hoffmann
1177b30a60 Merge pull request #3085 from lonvia/allow-brackets-in-password
Do not fail php script generation when curly braces are present
2023-06-19 14:44:22 +02:00
Sarah Hoffmann
10e56e0de7 no longer recommend continuous update mode 2023-06-19 12:07:09 +02:00
Sarah Hoffmann
6f3339cc49 close DB connection when waiting for next update cycle 2023-06-19 12:02:51 +02:00
Sarah Hoffmann
771be0e056 do not fail php script generation when curly braces are present
Fixes #3084.
2023-06-19 11:23:30 +02:00
Sarah Hoffmann
71ad4fc406 Add custom config to information required for bug reports 2023-06-18 09:27:55 +02:00
Sarah Hoffmann
6a5695d059 disable SPGist for PostgreSQL < 11
Before that version, an operator needed to be given.
2023-06-13 15:15:43 +02:00
Sarah Hoffmann
aaf0e7db06 add instructions for switching to user for install scripts
Fixes #3057.
2023-06-13 14:12:56 +02:00
Sarah Hoffmann
7aa0aba382 remove Ubuntu 18 installation from TOC
Fixes #3072.
2023-06-13 14:05:54 +02:00
Sarah Hoffmann
9af190a43c Merge pull request #3073 from mtmail/vagrantfile-remove-ubuntu-18
Vagrantfile - remove Ubuntu 18
2023-06-13 12:31:10 +02:00
marc tobias
2e46bc0aea Vagrantfile - remove Ubuntu 18 2023-05-30 00:22:18 +02:00
Sarah Hoffmann
a413aae8a3 Merge pull request #3067 from lonvia/python-search-api
Python implementation of Search API
2023-05-27 08:56:06 +02:00
Sarah Hoffmann
317cc5c544 make code backwards-compatible with older Python versions 2023-05-26 23:33:35 +02:00
Sarah Hoffmann
41bf162306 remove tests for old PHP cli commands 2023-05-26 17:36:05 +02:00
Sarah Hoffmann
43c27dffd2 fix new linting warning 2023-05-26 16:31:43 +02:00
Sarah Hoffmann
8f299838f7 fix various failing BDD tests 2023-05-26 15:08:48 +02:00
Sarah Hoffmann
146a0b29c0 add support for search by houenumber 2023-05-26 14:10:57 +02:00
Sarah Hoffmann
964bc7fbe0 ignore name rankings without variants 2023-05-26 13:53:34 +02:00
Sarah Hoffmann
75aa3cc9bd properly close connections when shutting down starlette 2023-05-26 13:53:34 +02:00
Sarah Hoffmann
0843fefad3 fix geocodejson address assignment
The categories should be assigned the address part with the
highest address rank not lowest.
2023-05-26 11:43:11 +02:00
Sarah Hoffmann
371a780ef4 add server fronting for search endpoint
This also implements some of the quirks of free-text search of the
V1 API, in particular, search for categories and coordinates.
2023-05-26 11:40:45 +02:00
Sarah Hoffmann
c7db69a30c add timestamps to HTML debug output 2023-05-26 09:05:44 +02:00
Sarah Hoffmann
b48cda7173 mingle names from linked places into results 2023-05-24 23:17:15 +02:00
Sarah Hoffmann
0608cf1476 switch CLI search command to python implementation 2023-05-24 22:54:54 +02:00
Sarah Hoffmann
f335e78d1e make localisation of results explicit
Localisation was previously done as part of the formatting but might
also be useful on its own when working with the results directly.
2023-05-24 18:12:34 +02:00
Sarah Hoffmann
dcfb228c9a add API functions for search functions
Search is now split into three functions: for free-text search,
for structured search and for search by category. Note that the
free-text search does not have as many hidden features like
coordinate search. Use the search parameters for that.
2023-05-24 18:05:43 +02:00
Sarah Hoffmann
dc99bbb0af implement actual database searches 2023-05-24 13:52:31 +02:00
Sarah Hoffmann
c42273a4db implement search builder 2023-05-23 11:23:44 +02:00
Sarah Hoffmann
3bf489cd7c implement token assignment 2023-05-22 15:49:03 +02:00
Sarah Hoffmann
d8240f9ee4 add query analyser for legacy tokenizer 2023-05-22 11:07:14 +02:00
Sarah Hoffmann
2448cf2a14 add factory for query analyzer 2023-05-22 09:23:19 +02:00
Sarah Hoffmann
004883bdb1 query analyzer for ICU tokenizer 2023-05-22 08:46:19 +02:00
biswajit-k
11a1191ba0 add ci-test for taginfo file generation 2023-05-21 23:49:04 +05:30
Sarah Hoffmann
ff66595f7a add data structure for tokenized query 2023-05-21 09:30:57 +02:00
biswajit-k
9de2a342e8 docs: add installation instruction for dkjson package 2023-05-19 23:22:42 +05:30
biswajit-k
562f8bc84a Add script to generate taginfo project description 2023-05-19 18:02:06 +05:30
Sarah Hoffmann
d69411f414 Merge pull request #3064 from lonvia/clicmd-debug-output
Enable debug output on command line
2023-05-19 08:55:26 +02:00
Sarah Hoffmann
39ccb15880 enable debug output on command line 2023-05-18 22:37:46 +02:00
Sarah Hoffmann
d2c56f9f96 Merge pull request #3063 from lonvia/variable-parameters
Rework how search parameters are handed to the Python API
2023-05-18 22:27:18 +02:00
Sarah Hoffmann
7f1a0ce94a fix use of subquery in reverse 2023-05-18 20:27:07 +02:00
Sarah Hoffmann
32dbf83747 move zoom_to_rank computation to extra file 2023-05-18 18:29:41 +02:00
Sarah Hoffmann
d9d8b9c526 add tests for parameter converter 2023-05-18 18:09:07 +02:00
Sarah Hoffmann
9036bf3398 Merge pull request #3062 from lonvia/enable-psycopg
Add support for psycopg 3 in the frontend
2023-05-18 18:07:11 +02:00
Sarah Hoffmann
bef5cea48e switch API parameters to keyword arguments
This switches the input parameters for API calls to a generic
keyword argument catch-all which is then loaded into a dataclass
where the parameters are checked and forwarded to internal
function.

The dataclass gives more flexibility with the parameters and makes
it easier to reuse common parameters for the different API calls.
2023-05-18 17:42:23 +02:00
Sarah Hoffmann
84abf7c95a actions: run tests against psycopg 2023-05-18 16:08:32 +02:00
Sarah Hoffmann
1f0e1bec0e enable API use with psycopg 3 2023-05-18 16:08:32 +02:00
Sarah Hoffmann
8f88613a6b Merge pull request #3050 from mtmail/tiger-check-if-database-frozen
when adding Tiger data, check first if database is in frozen state
2023-05-08 16:35:31 +02:00
Marc Tobias
e5f332bd71 when adding Tiger data, check first if database is in frozen state 2023-05-08 14:35:30 +02:00
Sarah Hoffmann
07589cfc34 Merge pull request #3054 from lonvia/add-amenity-to-documentation
Docs: reintroduce amenity parameter for structured search
2023-05-08 11:12:17 +02:00
Sarah Hoffmann
68e0306e62 docs: reintroduce amenity parameter for structured search 2023-05-08 10:24:12 +02:00
Sarah Hoffmann
5751686fdc Merge pull request #3006 from biswajit-k/generalize-filter
generalize filter function for sanitizers
2023-04-11 19:20:08 +02:00
Sarah Hoffmann
2af20f8df8 Merge pull request #3030 from lonvia/interpolation-corner-cases
Fix a number of corner cases with interpolation splitting
2023-04-07 13:59:52 +02:00
Sarah Hoffmann
60c1301fca fix a number of corner cases with interpolation splitting
Snapping a line to a point before splitting was meant to ensure
that the split point is really on the line. However, ST_Snap() does
not always behave well for this case. It may shorten the interpolation
line in some cases with the result that two points housenumbers
suddenly fall on the same point. It might also shorten the line down
to a single point which then makes ST_Split() crash.

Switch to a combination of ST_LineLocatePoint and ST_LineSubString
instead, which guarantees to keep the original geometry. Explicitly
handle the corner cases, where the split point falls on the beginning
or end of the line.
2023-04-06 16:54:00 +02:00
Sarah Hoffmann
b8a7319212 use place_to_be_deleted when force deleting objects 2023-04-04 11:09:17 +02:00
Sarah Hoffmann
6ef4d04b46 Merge pull request #3023 from lonvia/lookup-api
Python implementation of Lookup API
2023-04-03 16:20:47 +02:00
Sarah Hoffmann
1dce2b98b4 switch CLI lookup command to Python implementation 2023-04-03 14:40:41 +02:00
Sarah Hoffmann
86c4897c9b add lookup call to server glue 2023-04-03 14:40:41 +02:00
Sarah Hoffmann
2237603677 add tests for new lookup API 2023-04-03 14:40:41 +02:00
Sarah Hoffmann
6e81596609 rename lookup() API to details and add lookup call
The initial plan to serve /details and /lookup endpoints from
the same API call turned out to be impractical, so the API now
also has deparate functions for both.
2023-04-03 14:40:41 +02:00
Sarah Hoffmann
4607c7ed04 python lookup: add function for simple lookups 2023-04-03 14:40:41 +02:00
Sarah Hoffmann
63638eb447 python lookup: factor out finding in tables into own function 2023-04-03 14:40:41 +02:00
Sarah Hoffmann
c92ac84679 Merge pull request #3021 from lonvia/readd-postalcode-relations
Flex style: reinstate postalcode relations
2023-04-03 12:11:49 +02:00
Sarah Hoffmann
ed9cd9f0e5 bdd: disable detail tests searching by place ID
Place IDs are not stable and cannot be used in tests.
2023-04-03 10:07:06 +02:00
Sarah Hoffmann
7d30dbebc5 flex style: reinstate postcode boundaries
Postcode boundaries don't have a name, so need to be imported
unconditionally.
2023-04-03 09:17:50 +02:00
biswajit-k
8f03c80ce8 generalize filter for sanitizers 2023-04-01 19:24:09 +05:30
Sarah Hoffmann
ee0366af88 Merge pull request #3019 from lonvia/add-data-postprocessing
Add postprocessing to add-data function
2023-03-31 22:19:46 +02:00
Sarah Hoffmann
683a3cb3ec call osm2pgsql postprocessing flush_deleted_places() when adding data 2023-03-31 18:05:07 +02:00
Sarah Hoffmann
f8bca4fbcb Merge pull request #3020 from lonvia/reverse-api
Python implementation of reverse
2023-03-31 18:01:50 +02:00
Sarah Hoffmann
1e2a1d9ce5 limit results for country lookup 2023-03-30 10:00:19 +02:00
Sarah Hoffmann
1feac2069b add BDD tests for new layers parameter 2023-03-30 09:54:55 +02:00
Sarah Hoffmann
26ee6b6dde python reverse: add support for point geometries in interpolations 2023-03-29 17:21:33 +02:00
Sarah Hoffmann
c150ca4889 add wsgi entry point for falcon server 2023-03-28 15:05:52 +02:00
Sarah Hoffmann
e717e349d0 add wsgi entry point for starlette
uvicorn needs a parameter-free function to start.
2023-03-28 15:03:00 +02:00
Sarah Hoffmann
e158017086 ignore broken data in interpolation table 2023-03-28 14:57:39 +02:00
Sarah Hoffmann
36d068871d disable prepared statements
Prepared statements do not work well with the partial indexes that
Nominatim uses because all Python constants are replaced with
parameters. A query like:

  placex.select().where(placex.c.rank_address.between(4, 25)

gets translated into a prepared query with two parameters:

  SELECT * FROM placex WHERE rank_address BETWEEN %s and %s

And this does not work with a partial index of:

  CREATE INDEX on placex(geometry) WHERE rank_address between 4 and 25
2023-03-28 14:53:45 +02:00
Sarah Hoffmann
6c67a4b500 switch reverse CLI command to Python implementation 2023-03-26 18:09:33 +02:00
Sarah Hoffmann
86b43dc605 make sure PHP and Python reverse code does the same
The only allowable difference is precision of coordinates. Python uses
a precision of 7 digits where possible, which corresponds to the
precision of OSM data.

Also fixes some smaller bugs found by the BDD tests.
2023-03-26 16:21:43 +02:00
Sarah Hoffmann
300921a93e add server glue for reverse API call 2023-03-25 17:04:02 +01:00
Sarah Hoffmann
35b52c4656 add output formatters for ReverseResults
These formatters are written in a way that they can be reused for
search results later.
2023-03-25 15:45:03 +01:00
Sarah Hoffmann
878302a622 ignore NotImplementedErrors when compiling SQL 2023-03-24 11:16:02 +01:00
Sarah Hoffmann
55277738d4 factor out layer checks in reverse function 2023-03-24 10:08:01 +01:00
Sarah Hoffmann
2f54732500 python: implement reverse lookup function
The implementation follows for most part the PHP code but introduces an
additional layer parameter with which the kind of places to be returned
can be restricted. This replaces the hard-coded exclusion lists.
2023-03-23 22:38:37 +01:00
Sarah Hoffmann
41da298b18 add python implementation of reverse
This adds an additional layer parameter and slightly changes the
queries to do more efficient lookups for large area features.
2023-03-23 10:16:50 +01:00
Sarah Hoffmann
ebcf8c2b6b api: make details parameter optional 2023-03-23 10:16:50 +01:00
Sarah Hoffmann
1facfd019b api: generalize error handling
Return a consistent error response which takes into account the chosen
content type. Also adds tests for V1 server glue.
2023-03-23 10:16:50 +01:00
Sarah Hoffmann
00e3a752c9 split SearchResult type
Use adapted types for the different result types. This makes it
easier to have adapted output formatting and means there are only
result fields that are filled.
2023-03-23 10:16:50 +01:00
Sarah Hoffmann
d03fd3f883 Merge pull request #3013 from mtmail/changelog-4-2-x
update ChangeLog to verison 4.2.2
2023-03-23 09:20:25 +01:00
marc tobias
fa3d13ac7e update ChangeLog to verison 4.2.2 2023-03-22 23:45:59 +01:00
Sarah Hoffmann
434bd5a5bb Merge pull request #3011 from lonvia/fix-flex-scripts
Fix extra tag handling in some flex scripts
2023-03-21 09:58:53 +01:00
Sarah Hoffmann
9aca389bda Merge pull request #3010 from lonvia/adapt-zoom-for-reverse
Minor adjustments to reverse zoom translation
2023-03-21 08:56:25 +01:00
Sarah Hoffmann
69ce42b22c remove more tags from full style
The full style should only save the necessary tags needed for
processing.
2023-03-20 21:42:24 +01:00
Sarah Hoffmann
114cc776be fix handling of unused extra tags
The tags can only be moved to extra tags after the main tags have been
handled.
2023-03-20 21:20:27 +01:00
Sarah Hoffmann
5e5cff897f minor adjustment to reverse zoom translation
Add a 'village' zoom level at 13 between town and neighbourhood
and a all locality-like objects for zoom 15. These zoom levels had
the same behaviour as the lower level so far. However, the distinction
for village and locality may be useful at times.
2023-03-20 20:47:42 +01:00
Sarah Hoffmann
a8bedb6ab9 Merge pull request #3003 from lonvia/rework-bdd-api-tests
Reorganize code around BDD API tests and extend reverse API tests
2023-03-10 10:01:24 +01:00
Sarah Hoffmann
81430bd3bd bdd: be more fuzzy with coordinate comparisons 2023-03-09 22:37:45 +01:00
Sarah Hoffmann
93203f355a avoid recent Python dialect 2023-03-09 20:57:43 +01:00
Sarah Hoffmann
b730d286ad fix polygon simplification in reverse results
polygon_threshold has never really worked for reverse.
2023-03-09 20:24:07 +01:00
Sarah Hoffmann
3f2296e3ea bdd: extend reverse API tests for format checks
Reorganise the API reverse tests and extend the checks for the
output format, testing for all expected fields.
2023-03-09 20:20:50 +01:00
Sarah Hoffmann
2b7eb4906a bdd: add tests for valid debug output 2023-03-09 20:10:51 +01:00
Sarah Hoffmann
db1aa4d02e bdd: replace old formatting strings 2023-03-09 19:49:55 +01:00
Sarah Hoffmann
ad88d7a3e0 bdd: more format checks for reverse XML 2023-03-09 19:40:24 +01:00
Sarah Hoffmann
e42c1c9c7a bdd: new step variant 'result contains in field'
This replaces the + notation for recursing into result dictionaries.
2023-03-09 19:31:21 +01:00
Sarah Hoffmann
556bb2386d bdd: factor out computation of result to-check lists 2023-03-09 18:01:45 +01:00
Sarah Hoffmann
1e58cef174 bdd: replace property_list construct with standard check functions 2023-03-09 17:56:28 +01:00
Sarah Hoffmann
01010e443f bdd: remove special case for osm_type field
The fuzzy field check hide cover formatting errors. Use 'osm' when
only caring about the conent.
2023-03-09 17:44:34 +01:00
Sarah Hoffmann
da0a7a765e bdd: reorganise field comparisons
Move comparision on Field values from assert_field() into a
comparator class. Replace BadRowValueAssert with a simpler
check_row() function.
2023-03-09 17:05:05 +01:00
Sarah Hoffmann
9769a0dcdb bdd: use new check_for_attributes() function also in steps 2023-03-09 16:44:07 +01:00
Sarah Hoffmann
fbff4fa218 bdd: fully check correctness of geojson and geocodejson
Parse code now checks presence of all required fields and exports
all fields for inspection.
2023-03-09 16:36:46 +01:00
Sarah Hoffmann
d17ec56e54 bdd: remove OrderedDict
dicts are guaranteed to keep insertion order by since Python 3.7, making
use of ORderedDict mute.
2023-03-09 16:08:39 +01:00
Sarah Hoffmann
9a5f75dba7 Merge pull request #2993 from biswajit-k/delete-tags
Adds sanitizer for preventing certain tags to enter search index based on parameters
2023-03-09 14:31:45 +01:00
biswajit-k
ca149fb796 Adds sanitizer for preventing certain tags to enter search index based on parameters
fix: pylint error

added docs for delete tags sanitizer

fixed typos in docs and code comments

fix: python typechecking error

fixed rank address type

Revert "fixed typos in docs and code comments"

This reverts commit 6839eea755a87f557895f30524fb5c03dd983d60.

added default parameters and refactored code

added test for all parameters
2023-03-09 14:18:39 +05:30
Sarah Hoffmann
08f19e074b Merge pull request #2999 from biswajit-k/fix-typos
fixed typos in docs and code comments
2023-03-08 08:55:27 +01:00
biswajit-k
36388cafe9 fixed typos in docs and code comments 2023-03-06 17:09:38 +05:30
Sarah Hoffmann
8191c747b9 add latest security incident
Also removes 3.6 which is no longer supported.
2023-02-22 11:24:04 +01:00
Sarah Hoffmann
d078763fa1 harmonize flags for PHP's htmlspecialchars 2023-02-20 16:46:53 +01:00
Sarah Hoffmann
412ead5f2d adapt PHP tests for debug output 2023-02-20 16:23:28 +01:00
Sarah Hoffmann
513175ce23 properly encode special HTML characters in debug mode 2023-02-20 15:43:03 +01:00
Sarah Hoffmann
8db6dd995a Merge pull request #2986 from mtmail/add-more-languages-from-osm-wiki
sp_wiki_loader: add more default languages
2023-02-20 11:12:08 +01:00
marc tobias
4be6970bd4 sp_wiki_loader: add more default languages 2023-02-18 13:54:48 +01:00
Sarah Hoffmann
fa681ce246 add timestamp to debug SQL output 2023-02-18 09:49:30 +01:00
Sarah Hoffmann
dd5cd97713 add warning for reverse index migration 2023-02-18 09:43:37 +01:00
Sarah Hoffmann
89d47d26f0 Merge pull request #2985 from lonvia/fix-place-rank-inheritance
Restrict place rank inheritance to address items
2023-02-18 09:35:19 +01:00
Sarah Hoffmann
d574ceb598 restrict place rank inheritance to address items
Place tags must have no influence on street- or POI-level
objects.
2023-02-17 16:25:26 +01:00
Sarah Hoffmann
92e2f5ca8e Merge pull request #2983 from lonvia/improve-reverse-place-node-lookup
Improve reverse place node lookup
2023-02-17 15:51:55 +01:00
Sarah Hoffmann
f2bc792178 use reverse buffered index for search within country 2023-02-17 14:10:01 +01:00
Sarah Hoffmann
8ed096f938 speed up reverse lookup of place nodes
Add a special index that contains the place nodes buffered by their
respective area according to their search rank. This replaces the
maximum area search for place nodes and reduces drastically the number
of place nodes that need to be retrieved.
2023-02-17 14:10:01 +01:00
Sarah Hoffmann
3405dbf90e Merge pull request #2981 from lonvia/add-point-wkb-decoder
Python frontend: add a WKB decoder for the Point class
2023-02-17 08:40:14 +01:00
Sarah Hoffmann
ee0c5e24bb add a WKB decoder for the Point class
This allows to return point geometries from the database and makes
the SQL a bit simpler.
2023-02-16 17:29:56 +01:00
Sarah Hoffmann
b320f1c7e3 Merge pull request #2978 from lonvia/add-debug-view
Add debug view to Python API
2023-02-14 14:08:42 +01:00
Sarah Hoffmann
6c6b1c0606 add typing information for pygments to requirements 2023-02-14 11:58:08 +01:00
Sarah Hoffmann
a5f5add630 actions: use token to avoid rate limiting 2023-02-14 11:57:37 +01:00
Sarah Hoffmann
8557105c40 add debug output for unit tests
This uses the debug output facility meant for pretty HTML output
to give us debugging output for the unit tests.
2023-02-14 11:57:37 +01:00
Sarah Hoffmann
24e7ffb289 add HTML-formatted debug output to lookup 2023-02-14 11:57:37 +01:00
Sarah Hoffmann
0b9bcfe01d Merge pull request #2974 from bloom256/main-tag-in-reverse-lookup
Main tag information added to geocodejson in reverse geocoding
2023-02-11 11:01:11 +01:00
Sarah Hoffmann
1a0e8f810b Merge pull request #2975 from bloom256/typo-fix
typo fixed
2023-02-11 11:00:15 +01:00
danil
7698f0672d typo fixed 2023-02-08 00:21:58 +04:00
danil
da064ea702 Main tag information added to geocodejson in reverse geocoding 2023-02-08 00:19:49 +04:00
Sarah Hoffmann
0c65289a80 Merge pull request #2970 from lonvia/add-details-endpoint
Python implementation of details endpoint
2023-02-06 16:32:35 +01:00
Sarah Hoffmann
95c90a785f actions: force PHPUnit 9
PHPUnit 10 is incompatible with our tests. Not worth adapting anymore.
2023-02-04 21:22:22 +01:00
Sarah Hoffmann
42c3754dcd add tests for details result formatting and trim results
Values that are None are no longer included in the output to save
a bit of bandwidth.
2023-02-04 21:22:22 +01:00
Sarah Hoffmann
b742200442 expand details BDD tests
There are now minor differences in the output between PHP and
Python versions, so introduce specific tests.
2023-02-04 21:22:22 +01:00
Sarah Hoffmann
3ac70f7cc2 implement details endpoint in Python servers 2023-02-04 21:22:22 +01:00
Sarah Hoffmann
104722a56a switch details cli command to new Python implementation 2023-02-04 21:22:22 +01:00
Sarah Hoffmann
1924beeb20 add lookup of postcdoe data 2023-02-04 21:22:22 +01:00
Sarah Hoffmann
70f6f9a711 add lookup of tiger data 2023-02-04 21:22:22 +01:00
Sarah Hoffmann
f1ceefe9a6 add lookup of address interpolations 2023-02-04 21:22:22 +01:00
Sarah Hoffmann
e1fc1566f3 fix new linting issues from pylint 2.16 2023-02-04 21:22:22 +01:00
Sarah Hoffmann
189f74a40d add unit tests for lookup function 2023-02-04 21:22:22 +01:00
Sarah Hoffmann
370c9b38c0 improve scaffolding for API unit tests
Use the static table definition to create the test database.
Add helper function to simplify filling the tables.
2023-02-04 21:22:22 +01:00
Sarah Hoffmann
df65c10360 add lookup() call to the library API
Currently only looks places up in placex.
2023-02-04 21:22:22 +01:00
Sarah Hoffmann
4573389da7 docs: fix internal links
Fixes #2968.
2023-02-04 21:21:23 +01:00
Sarah Hoffmann
5c55c1d8a1 Merge pull request #2963 from lonvia/add-sqlalchemy-schema
Add table definitions for SQLAlchemy
2023-01-30 11:17:22 +01:00
Sarah Hoffmann
a1d4e53eb8 add pytest-asyncio as a requirement for testing 2023-01-30 09:36:17 +01:00
Sarah Hoffmann
16b6484c65 add property cache for API
This caches results from querying nominatim_properties.
2023-01-30 09:36:17 +01:00
Sarah Hoffmann
2156fd4909 adapt annotations for SQLAlchemy 2.x
It is not possible to produce type annotations that work with both
versions 1.4 and 2.0. So keep to the principle of only supporting
newest versions when it comes to mypy. This means that some types
may have to be string quoted to not cause issues when running with
SQLAlchemy 1.4.
2023-01-28 11:51:26 +01:00
Sarah Hoffmann
7f5fbe1dc7 add new geoalchemy requirement 2023-01-28 11:51:26 +01:00
Sarah Hoffmann
2e9090d121 adapt status to use SQLAlchemy tables 2023-01-28 11:51:26 +01:00
Sarah Hoffmann
23f2690c54 convert StatusResult to a dataclass
This gives us nice str() functions.
2023-01-28 11:51:26 +01:00
Sarah Hoffmann
5226cd2a0b add SQLAlchemy table schema for Nominatim tables
Also defines an extended connection object that includes access to
the table definitions. Makes it easier to access the tables from
code that has been split off into separate modules.
2023-01-28 11:51:26 +01:00
Sarah Hoffmann
c7e8a82d68 Merge pull request #2958 from lonvia/streaming-json-writer
Introduce streaming json writer for JSON output
2023-01-25 17:36:23 +01:00
Sarah Hoffmann
77bec1261e add streaming json writer for JSON output 2023-01-25 15:05:33 +01:00
Sarah Hoffmann
dfcb24061e Merge pull request #2957 from lonvia/reorganise-api-module
Assorted improvements to the new api library module
2023-01-25 09:29:31 +01:00
Sarah Hoffmann
f85b0c6208 allow to add php-compatible endpoints
If the new setting NOMINATIM_SERVE_LEGACY_URLS is set, the servers
expose the endpoints also with the .php suffix to ensure backwards
compatibility.
2023-01-24 21:39:19 +01:00
Sarah Hoffmann
e490a30a4a add support for CORS headers
Adds the additional dependency to sanic-cors for the Sanic server.
2023-01-24 21:39:19 +01:00
Sarah Hoffmann
654b652530 factor out common server implementation code
Most of the server implementation of V1 API now resides in
api.v1.server_glue. The webframeworks only supply some glue code
which is independent to changes in the API code.
2023-01-24 21:39:19 +01:00
Sarah Hoffmann
8f4426fbc8 reorganize code around result formatting
Code is now organized by api version. So formatting has moved to
the api.v1 module. Instead of holding a separate ResultFormatter
object per result format, simply move the functions to the
formater collector and hand in the requested format as a parameter.
Thus reorganized, the api.v1 module can export three simple functions
for result formatting which in turn makes the code that uses
the formatters much simpler.
2023-01-24 17:20:51 +01:00
Sarah Hoffmann
32c1e59622 reorganize api submodule
Use a directory for the submodule where the __init__ file contains
the public API. This makes it easier to separate public interface
from the internal implementation.
2023-01-24 13:28:04 +01:00
Sarah Hoffmann
e56957f047 api: delay setup of initial database connection
Defer database setup until the first call to a function. Needs an
additional lock because the setup still needs to be done sequentially.
2023-01-24 10:56:22 +01:00
Sarah Hoffmann
3cc357bffa Merge pull request #2955 from lonvia/fix-importance-refresh
Fix importance recalculation
2023-01-23 09:07:43 +01:00
Sarah Hoffmann
388faa2c54 Merge pull request #2954 from lonvia/remove-comma-as-separator
Remove comma as name separator
2023-01-23 09:06:23 +01:00
Sarah Hoffmann
ce9ed993c8 fix importance recalculation
The signature of the compute_importance() function has changed.
2023-01-22 22:32:16 +01:00
Sarah Hoffmann
929a13d4cd remove comma as name separator
Commas are most of the time used as a part of a name, not to
separate multiple names.

See also #2950.
2023-01-22 22:29:36 +01:00
Sarah Hoffmann
56f0d678e3 exclude names ending in :wikipedia from indexing
The wikipedia prefix is used for referencing a wikipedia article
for the given tag, not the object, so not useful to search.
2023-01-21 11:16:08 +01:00
Sarah Hoffmann
02645277c8 fix typo in argument to details CLI command
Fixes #2951.
2023-01-21 10:44:10 +01:00
Sarah Hoffmann
5f4e98e0d9 update Makefile in test directory 2023-01-09 20:49:33 +01:00
Sarah Hoffmann
e9e14834bc Merge pull request #2940 from lonvia/remove-ubuntu-18-from-actions
Actions: use Ubuntu 20 image for testing old versions of dependent software
2023-01-05 20:16:19 +01:00
Sarah Hoffmann
5a57d6308e increase minimum required version of PHP to 7.3
Other versions are not tested anymore.
2023-01-05 16:58:46 +01:00
Sarah Hoffmann
cb73d562d5 actions: move tests from Ubuntu 18 to 20
These are the tests that try to make sure old library version really
still work as expected. Increases PHP to 7.3 because 7.2 has errors.
2023-01-05 16:55:32 +01:00
Sarah Hoffmann
6c61690ef3 do not run osm2pgsql append with mutliple threads
As the updates modify the placex table, there may be deadlocks
when different objects want to forward modifications to the same
place (for example because they are both linked to it).
2023-01-05 11:34:56 +01:00
Sarah Hoffmann
bf1f6a997c Merge pull request #2937 from lonvia/python-server-stub
Scaffolding for new Python-based search frontend
2023-01-03 14:26:33 +01:00
Sarah Hoffmann
90b29aa808 Merge pull request #2856 from t-tomek/patch-1
Update DB.php
2023-01-03 10:58:50 +01:00
Sarah Hoffmann
31d0468cd2 no type checking on old Ubuntu 18 2023-01-03 10:03:00 +01:00
Sarah Hoffmann
38f467bae3 add event handler for default connection settings 2023-01-03 10:03:00 +01:00
Sarah Hoffmann
5c7c4bb9a8 update versions for Python packages 2023-01-03 10:03:00 +01:00
Sarah Hoffmann
9646ec4edd drop official support for Ubuntu 18 2023-01-03 10:03:00 +01:00
Sarah Hoffmann
c665796c52 drop support for Python 3.6 2023-01-03 10:03:00 +01:00
Sarah Hoffmann
a72e2ecb3f update dependencies for Actions 2023-01-03 10:03:00 +01:00
Sarah Hoffmann
0c47558729 convert version to named tuple
Also return the new NominatimVersion rather than a string in the
status result.
2023-01-03 10:03:00 +01:00
Sarah Hoffmann
93b9288c30 fix error message for non-existing database 2023-01-03 10:03:00 +01:00
Sarah Hoffmann
9d31a67116 add unit tests for new Python API 2023-01-03 10:03:00 +01:00
Sarah Hoffmann
cf19036ce6 docs: extend dependency documentation 2023-01-03 10:03:00 +01:00
Sarah Hoffmann
7219ee6532 extend BDD API tests to query via Python frameworks
A new config option ENGINE allows to choose between php and any of the
supported Python engines.
2023-01-03 10:03:00 +01:00
Sarah Hoffmann
d7bc846c3c fix liniting issues and add type annotations 2023-01-03 10:03:00 +01:00
Sarah Hoffmann
1adb0a9886 add support for starlette framework 2023-01-03 10:03:00 +01:00
Sarah Hoffmann
8aa01c9c8e add support for falcon as server framework 2023-01-03 10:03:00 +01:00
Sarah Hoffmann
23dabad0b0 add sanic development server implementation 2023-01-03 10:02:53 +01:00
Sarah Hoffmann
45c675bd78 implement command line status call in Python 2023-01-03 10:02:35 +01:00
Sarah Hoffmann
860c6ecbcc Merge pull request #2936 from lonvia/fix-query-for-index-use
Split query that deletes old objects from placex
2023-01-03 09:56:03 +01:00
Sarah Hoffmann
3f38091421 split query that deletes old objects from placex
placex only has partial indexes over OSM types, so the OSM type
needs to be hardcoded to ensure these indexes are used.
2023-01-02 17:25:38 +01:00
Sarah Hoffmann
7704b3fc7b Merge pull request #2932 from lonvia/rework-flex-framework
Switch to osm2pgsql flex output
2022-12-29 17:23:38 +01:00
t-tomek
151b3c4021 Update DB.php 2022-12-27 08:34:20 +01:00
Sarah Hoffmann
610af95ed1 remove old import styles 2022-12-23 19:29:07 +01:00
Sarah Hoffmann
018ef5bd53 bdd: recreate project directory for every run 2022-12-23 18:36:41 +01:00
Sarah Hoffmann
200eae3bc0 add tests for examples in lua style documentation
And fix all the errors the tests have found.
2022-12-23 17:35:28 +01:00
Sarah Hoffmann
9321e425a4 add documentation for flex style
Includes minor adaptions to bring the code in line with the
documentation.
2022-12-23 11:10:40 +01:00
Sarah Hoffmann
9395c0dadc Merge pull request #2931 from mtmail/vagrant-md-use-dotenv
VAGRANT.md - replace local.php settings with .env
2022-12-22 10:20:15 +01:00
marc tobias
a40065878b VAGRANT.md - replace local.php settings with .env 2022-12-22 03:12:30 +01:00
t-tomek
e8d3c0a99a Update DB.php 2022-12-21 19:56:24 +01:00
t-tomek
2e6ff1b750 Update DB.php 2022-12-21 16:32:33 +01:00
t-tomek
15f9e397dd Update DB.php 2022-12-21 16:31:39 +01:00
t-tomek
87a109d0e9 Update DB.php 2022-12-21 16:30:55 +01:00
Sarah Hoffmann
f3ffbe167d use canonical url for nominatim.org 2022-12-20 16:55:47 +01:00
Sarah Hoffmann
89a34e7508 adapt tests for new lua styles 2022-12-19 17:32:28 +01:00
Sarah Hoffmann
f6fc750f08 install new lua import scripts 2022-12-19 17:27:40 +01:00
Sarah Hoffmann
c32f686c62 switch to osm2pgsql flex style by default 2022-12-18 10:10:58 +01:00
Sarah Hoffmann
2ca83efc36 flez: add other default styles 2022-12-18 10:10:58 +01:00
Sarah Hoffmann
06796745ff flex: hide compiled matchers 2022-12-18 10:10:58 +01:00
Sarah Hoffmann
093d531509 flex: switch to functions for substyles
This gives us a bit more flexibility about the implementation
in the future.
2022-12-18 10:10:58 +01:00
Sarah Hoffmann
a915815e4d explicit export for functions in flex-base 2022-12-18 10:10:58 +01:00
Sarah Hoffmann
de3c28104c flex: add combining clean function 2022-12-18 10:10:58 +01:00
Sarah Hoffmann
d9d13a6204 flex: simplify name handling 2022-12-18 10:10:58 +01:00
Sarah Hoffmann
d1f5820711 flex: simplify address configuration 2022-12-18 10:10:58 +01:00
Sarah Hoffmann
7592f8f189 update osm2pgsql (flex not building index) 2022-12-18 10:10:58 +01:00
Sarah Hoffmann
ffbb61713a Merge pull request #2927 from lonvia/remove-forward-dependencies
Remove shortcut disabling forward dependencies
2022-12-17 15:59:09 +01:00
Sarah Hoffmann
6f51c1ba33 remove code that disables processing of forward dependencies 2022-12-11 19:35:58 +01:00
Sarah Hoffmann
cd861345b7 Merge pull request #2921 from lonvia/case-insensitive-utf8
Use grapheme_stripos instead of stripos in PHP code
2022-12-11 15:57:01 +01:00
Sarah Hoffmann
823502a40a use grapheme_stripos instead of stripos in PHP code
The stripos() does not handle non-ASCII correctly.
2022-12-11 13:55:27 +01:00
Sarah Hoffmann
4efad0bb95 Merge pull request #2920 from lonvia/no-postcode-for-rivers
Do not assign postcodes to long linear features
2022-12-10 17:30:32 +01:00
Sarah Hoffmann
922352e215 do not assign postcodes to long linear features
This avoids a postcode in particular for waterway features and
long natural featues like ridges and valleys.

Fixes #2915.
2022-12-10 14:53:08 +01:00
Frederik Ramm
8a0b2dc0be Fix typo in NOMINATIM_LOG_FILE (#2919)
* fix typo in docs (NOMINATIM_LOG_FILE uses s not ms)
2022-12-08 17:34:54 +01:00
Sarah Hoffmann
7eced34e20 Merge pull request #2916 from lonvia/faq-postcodes
Add FAQ about finding bad postcodes
2022-12-08 08:42:10 +01:00
Sarah Hoffmann
64d00c1c8e add FAQ about finding bad postcodes 2022-12-07 21:38:53 +01:00
Sarah Hoffmann
6d48798d45 Merge pull request #2913 from lonvia/remove-duplicate-spaces-in-transliteration
contract duplicate spaces in transliteration string
2022-12-02 19:43:07 +01:00
Sarah Hoffmann
0e186835b9 contract duplicate spaces in transliteration string
There are some pathological cases where an isolated letter may
be deleted because it is in itself meaningless. If this happens in
the middle of a sentence, then the transliteration contains two
consecutive spaces. Add a final rule to fix this.

See #2909.
2022-12-02 10:15:02 +01:00
Sarah Hoffmann
b607eb9678 Merge pull request #2908 from n-timofeev/update-vagrantfile
Update Vagrantfile
2022-11-29 10:33:16 +01:00
n-timofeev
85a68f1e56 Update Vagrantfile 2022-11-29 11:12:10 +03:00
Sarah Hoffmann
45d13bc295 Merge pull request #2906 from lonvia/move-data-dirs-into-module
Reorganize how Nominatim finds its extra data and libraries
2022-11-28 08:44:29 +01:00
Sarah Hoffmann
2231401483 clean up uses of cli.nominatim()
They should not hand in data paths anymore.
2022-11-27 15:27:04 +01:00
Sarah Hoffmann
2abe9e6fd9 use data paths from new nominatim.paths 2022-11-27 12:15:41 +01:00
Sarah Hoffmann
20f56dfc77 introduce paths module which contains the data paths
This means that nominatim can find its data even when not called
from the command line tool.
2022-11-27 12:02:37 +01:00
Sarah Hoffmann
67664406da Merge pull request #2905 from lonvia/remove-nominatim-tool-var
Remove NOMINATIM_NOMINATIM_TOOL variable
2022-11-26 20:24:58 +01:00
Sarah Hoffmann
0ed60d29cb remove NOMINATIM_NOMINATIM_TOOL variable
This was used by the old PHP scripts to call the Python tool.
With the scripts now gone, the variable can be removed.
2022-11-26 16:40:20 +01:00
Sarah Hoffmann
04ee39467a actions: install keys for postgres repo 2022-11-24 14:04:05 +01:00
Sarah Hoffmann
1f3edf6eba prepare release 4.2.0 2022-11-24 10:43:29 +01:00
Sarah Hoffmann
a15c197547 add checklist for releases 2022-11-24 10:43:25 +01:00
Sarah Hoffmann
13dbeb75c7 Merge pull request #2903 from lonvia/migration-for-index-reorganization
Add migration for reorganization of pending indexes
2022-11-24 10:13:38 +01:00
Sarah Hoffmann
6aded60045 add migration for reorganization of pending indexes
Fixes #2900.
2022-11-24 08:48:05 +01:00
Sarah Hoffmann
8dfdf64dd5 Merge pull request #2902 from lonvia/tiger-county-sanitizer
Tiger county sanitizer
2022-11-23 17:58:42 +01:00
Sarah Hoffmann
41e8bddaa9 remove BDD test for tiger:county
We no longer rely on the import to strip the tag.
2022-11-23 10:37:27 +01:00
Sarah Hoffmann
fd3dec8efe add sanitizer for TIGER tags
Currently only takes over cleaning the tiger:county data. This was
done by the import until now.
2022-11-23 10:37:27 +01:00
Sarah Hoffmann
55ee08f42b Merge pull request #2892 from lonvia/optional-forward-dependecies
Add experimental configuration switch for enabling forward dependencies
2022-11-21 16:57:45 +01:00
Sarah Hoffmann
b6ff697ff0 add experimental option for enabling forward dependencies 2022-11-21 14:48:00 +01:00
Sarah Hoffmann
925ac1e1b9 Merge pull request #2890 from lonvia/use-rank-search-for-reverse-polygon-match
Use rank search for reverse polygon match
2022-11-20 22:11:35 +01:00
Sarah Hoffmann
77acc1c2be force use of geometry index for reverse polygon lookup 2022-11-20 20:22:44 +01:00
Sarah Hoffmann
ebe489c227 use rank_search for reverse polygon match 2022-11-20 20:22:23 +01:00
Sarah Hoffmann
9c152a030a fix condition under which place_to_be_deleted is created
It is needed for updates, independently if reverse-only is set.
2022-11-19 21:53:14 +01:00
Sarah Hoffmann
b310c86c55 Merge pull request #2889 from lonvia/fix-interpolation-updates
Drop illegal values for addr:interpolation on update
2022-11-18 18:51:11 +01:00
Sarah Hoffmann
c9ff7d2130 drop illegal values for addr:interpolation on update 2022-11-18 17:26:56 +01:00
Sarah Hoffmann
52456230cc Merge pull request #2887 from lonvia/lookup-linked-places
Add support for lookup of linked places
2022-11-17 13:35:53 +01:00
Sarah Hoffmann
4422533adb Merge pull request #2886 from lonvia/closest-street-in-associated
Handle associatedStreet relations with multiple streets correctly
2022-11-17 07:29:25 +01:00
Sarah Hoffmann
c4b13f2b7f add support for lookup of linked places 2022-11-16 21:34:45 +01:00
Sarah Hoffmann
4f05a03d13 handle associatedStreet relations with multiple streets
When a associatedStreet relation has multiple street members
always take the closest one. Avoid geometry operations for
the frequent case that there is only one street.
2022-11-16 17:25:51 +01:00
Sarah Hoffmann
7a2e586cce Merge pull request #2884 from lonvia/tweak-special-term-penalties
Correctly handle special term + name combination
2022-11-15 19:29:55 +01:00
Sarah Hoffmann
98ce424650 Merge pull request #2885 from lonvia/remove-unused-countries
Remove dependent territories from country list
2022-11-15 19:29:39 +01:00
Sarah Hoffmann
3059a3da4e correctly handle special term + name combination
Special terms with operator name usually appear in combination with the
name. The current penalties only took name + special term into account
not special term + name.

Fixes #2876.
2022-11-15 11:55:40 +01:00
Sarah Hoffmann
d63d7cb9a8 remove dependent territories from country list
Removes territories of US, France, Australia and Netherlands from the
country list. These territories have their own country code (which is
why they are in the list in the first place) but are mapped as part of
the admin_level 2 relations for the respective parent countries.
Therefore they never had any places attached. In practical terms, the
change only affects the number of tables created.
2022-11-15 11:37:30 +01:00
Sarah Hoffmann
f3f542e864 Merge pull request #2881 from lonvia/more-update-tests-for-osm2pgsql
Experimental support for osm2pgsql flex output
2022-11-15 09:39:46 +01:00
Sarah Hoffmann
93ada250f7 bdd: add tests for osm2pgsql update of postcode nodes 2022-11-14 17:27:04 +01:00
Sarah Hoffmann
d8e3ba3b54 bdd: add osm2pgsql tests for updating interpolations 2022-11-14 16:57:31 +01:00
Sarah Hoffmann
a46348da38 bdd: test placex content when updating with osm2pgsql 2022-11-14 14:48:44 +01:00
Sarah Hoffmann
36cf0eb922 reorganize handling of place type changes
Always replace existing entries in place, never delete them because
a direct delete will cause conflicts.
2022-11-14 13:57:26 +01:00
Sarah Hoffmann
63a9bc94f7 fix country handling in flex style
If the country tag does not match a 2-letter code, it needs to
be dropped.
2022-11-10 15:52:13 +01:00
Sarah Hoffmann
2dafc4cf4f remove tests that differ between lua and gazetteer versions 2022-11-10 15:51:55 +01:00
Sarah Hoffmann
68d09f9cad node locations must be stable for osm2pgsql update tests 2022-11-10 11:11:45 +01:00
Sarah Hoffmann
b98d3d3f00 bdd: extend osm2pgsql update tests
Now also checks for correct indexing state of placex table.
2022-11-10 09:38:25 +01:00
Sarah Hoffmann
3683cf7ddc optimise tag match function 2022-11-10 09:38:25 +01:00
Sarah Hoffmann
84e5e601e1 add lua requirements for vagrant scripts 2022-11-10 09:38:25 +01:00
Sarah Hoffmann
a1da149211 CI: require lua libraries 2022-11-10 09:38:25 +01:00
Sarah Hoffmann
74405e9684 add migration for place_to_be_deleted table 2022-11-10 09:38:25 +01:00
Sarah Hoffmann
2fac507453 change updates to handle delete/insert workflow
This makes Nominatim compatible with osm2pgsql's default update
modus operandi of deleting and reinserting data. Deletes are diverted
into a TODO table instead of executing them. When data is reinserted,
the corresponding entry in the TODO table is deleted. After updates are
finished, the remaining entries in the TODO table are executed, doing
the same work as the delete trigger did before.

The new behaviour also works against the gazetteer output with its
insert-only mechanism.
2022-11-10 09:38:23 +01:00
Sarah Hoffmann
51ed55cc32 initial flex import scripts
Only implements the extratags style for the moment. Tests pass
for the same behaviour as the gazetteer output. Updates still need
to be done.
2022-11-10 09:37:38 +01:00
Sarah Hoffmann
de2a3bd5f8 bdd tests: make import style configurable
The switch is for development. Tests are not guaranteed to still
work when run with anything but the 'extratags' style.
2022-11-10 09:37:38 +01:00
Sarah Hoffmann
981e9700be add osm2pgsql gazetteer tests
This ports the gazetteer tests from osm2pgsql to BDD tests.
2022-11-10 09:37:38 +01:00
Sarah Hoffmann
b52ce4f9f2 Merge pull request #2869 from mtmail/improve-tiger-install-doc
Tiger install doc: add -refresh website- step
2022-11-09 20:48:39 +01:00
Sarah Hoffmann
64c591da7f fix type issues with calls to pyosmium 2022-11-09 20:46:33 +01:00
Marc Tobias
2387648a85 Tiger install doc: add -refresh website- step 2022-11-09 17:33:31 +01:00
Sarah Hoffmann
846ecff0c5 Merge pull request #2871 from lonvia/fix-timeout-for-updates
Fix timeout for updates
2022-11-09 14:26:39 +01:00
Sarah Hoffmann
26a5b59c28 add types-requests dependency 2022-11-09 09:12:37 +01:00
Sarah Hoffmann
6ddb39fda3 respect socket timeout also in other replication functions 2022-11-09 09:12:37 +01:00
Sarah Hoffmann
1fdcec985a fix timeout use for replication timeout
The timeout parameter is no longer taken into account since
pyosmium switched to the requests library. This adds the parameter
back.
2022-11-09 09:12:37 +01:00
Sarah Hoffmann
30f526c943 Merge pull request #2870 from mtmail/update-github-actions-to-node-16
update those github action packages still using node12
2022-11-08 17:24:53 +01:00
Marc Tobias
253127cb9f update those github action packages still using node12 2022-11-08 15:16:55 +01:00
Sarah Hoffmann
3237ca587f Merge pull request #2866 from lonvia/reverse-ignore-interpolations-without-parent
Ignore interpolations without parent on reverse search
2022-11-07 09:00:59 +01:00
Sarah Hoffmann
0dbc0ae6d5 ignore interpolations without parent on reverse search
If no parent can be found for an interpolation, there is most
likely a data error involved. So don' t show these interpolations
in reverse search results.
2022-11-05 22:16:09 +01:00
Sarah Hoffmann
7461ff4680 Merge pull request #2865 from Romeo-PHILLIPS/fix/documentation_status_code
Fix: documentation status code
2022-11-05 22:14:44 +01:00
Romeo
afc714e1d3 fix: format 2022-11-04 18:05:40 +01:00
Romeo
3bc0db8d91 fix: markup 2022-11-04 18:04:28 +01:00
Romeo
d573da5b2c fix: 705 Status Code Documentation 2022-11-04 18:03:49 +01:00
Romeo
ecd5a3fdf9 fix: 705 Status Code Documenation 2022-11-04 17:59:36 +01:00
Sarah Hoffmann
543d63e7a9 Merge pull request #2862 from mtmail/remove-version-from-fpm-sock-file
Install scripts: remove version from /var/run/php-fpm filenames
2022-11-04 17:32:50 +01:00
Sarah Hoffmann
7a22ae6bf9 Merge pull request #2863 from lonvia/add-support-for-postgresql-15
Update CI tests to postgresql 15
2022-11-04 17:32:06 +01:00
Sarah Hoffmann
ebe23d6882 update CI tests to postgresql 15 2022-11-04 16:21:15 +01:00
marc tobias
33c805aee0 Install scripts: remove version from /var/run/php-fpm filenames 2022-11-04 14:22:11 +01:00
t-tomek
244b6fcef6 Update DB.php
Use SET instead of UPDATE queries to support read only databases
2022-11-02 14:11:52 +01:00
Sarah Hoffmann
616ff4ae25 actions: pin pyicu to 2.9 2022-10-24 14:21:44 +02:00
Sarah Hoffmann
e221eaa977 Merge pull request #2836 from mtmail/tiger2022
Documentation: remove year from TIGER filename, new 2022 data
2022-10-24 11:21:55 +02:00
Sarah Hoffmann
eed7abb839 Merge pull request #2838 from lonvia/update-osm2pgsql
Update osm2pgsql to latest 1.7.1 release
2022-10-05 18:59:13 +02:00
Sarah Hoffmann
5f6dcd36ed fix flaky API test
The search 'landstr' produces many duplicates so that with
some bad luck 4 or less results may appear. Disable deduplication
to make it more predictable.
2022-10-05 15:16:14 +02:00
Sarah Hoffmann
f395054536 update osm2pgsql to 1.7.1 2022-10-04 21:16:57 +02:00
Sarah Hoffmann
afeafc8aa7 Merge pull request #2835 from lonvia/secondary-importance
Secondary importance
2022-10-04 16:25:47 +02:00
marc tobias
f1ece658f8 Documentation: remove year from TIGER filename 2022-10-04 14:19:36 +02:00
Sarah Hoffmann
b3abb355eb docs: add customization hints for secondary importance
Removing the download links for now as the tile importance
is still too experimental.
2022-10-01 11:01:49 +02:00
Sarah Hoffmann
5877b69d51 do not run unit test when postgis_raster is not available 2022-10-01 11:01:49 +02:00
Sarah Hoffmann
5ec2c1b712 adapt unit tests to changed function names 2022-10-01 11:01:49 +02:00
Sarah Hoffmann
0a73ed7d64 add secondary importance to API BDD tests
Also fixes a path issue during API test DB creation that could
never possibly have worked.
2022-10-01 11:01:49 +02:00
Sarah Hoffmann
abf349fb0d simplify use of secondary importance
The values in the raster are already normalized between 0 and 2**16,
so a simple conversion to [0, 1] will do.

Check for existance of secondary_importance table statically when
creating the SQL function. For that to work importance tables need
to be created before the functions.
2022-10-01 11:01:49 +02:00
Sarah Hoffmann
3185fad918 load views as a SQL file and rename to 'secondary importance'
The only requirement for secondary importance is that a raster table
comes out of it. The generic name leaves open where the data comes
from.
2022-10-01 11:01:49 +02:00
Tareq Al-Ahdal
0ab0f0ea44 Integrated OSM views into importance computation 2022-10-01 11:01:49 +02:00
Tareq Al-Ahdal
ac467c7a2d Enhanced the implementation of OSM views GeoTIFF import functionality 2022-10-01 11:01:49 +02:00
Tareq Al-Ahdal
c85b74497b Initial implementation of GeoTIFF import functionality 2022-10-01 11:01:49 +02:00
Sarah Hoffmann
3381a92d92 Merge pull request #2832 from lonvia/conditional-analyze-on-indexing
Only run analyze on indexing when work was done
2022-09-28 15:17:40 +02:00
Sarah Hoffmann
a2ee58d8a1 only run analyze on indexing when work was done
This speeds up processing when continuing indexing after it was
interrupted.
2022-09-28 10:22:54 +02:00
Sarah Hoffmann
051f3720ce Merge pull request #2829 from lonvia/optimize-indexes
Further optimize indexes
2022-09-26 10:02:51 +02:00
Sarah Hoffmann
f017e1e9a1 make sure indexes are used 2022-09-25 14:09:45 +02:00
Sarah Hoffmann
33ba6896a8 further split up the big geometry index
Adds partial indexes for all geometry queries used during import.
A full index is not necessary anymore at that point. Still create
the index afterwards for use in queries.

Also adds documentation for all indexes on where they are used.
2022-09-21 16:21:41 +02:00
Sarah Hoffmann
f4d3ae6f70 consolidate indexes over geometry_sectors
The index over geometry_sectors are mainly used for ordering
the places which need indexing. That means they function effectively
as a TODO list. Consolodate them so that they always only contain
the places which are still to do. Also add the appropriate index
for the boundary indexing phase.
2022-09-21 10:38:58 +02:00
Sarah Hoffmann
860f3559a1 split up large osmid index on placex
This doesn't do anything in terms of lookup speeds but the resulting
indexes are quite a bit smaller.
2022-09-21 09:24:57 +02:00
Sarah Hoffmann
d8be8a7293 fix funding link 2022-09-19 15:39:58 +02:00
Sarah Hoffmann
9750a361c9 add Github Sponsering to funding page 2022-09-19 15:38:56 +02:00
Sarah Hoffmann
ed3dd81d04 run final index creation in parallel 2022-09-19 11:55:25 +02:00
Sarah Hoffmann
bef1aebf1c add function for parallel execution of SQL scripts 2022-09-19 11:52:17 +02:00
Sarah Hoffmann
26688ba35d add link to funding page 2022-09-19 10:30:58 +02:00
Sarah Hoffmann
a1158feeb8 Merge pull request #2818 from lonvia/better-geometry-index
Add index for lookup of addressable areas
2022-09-19 10:18:43 +02:00
Sarah Hoffmann
aef014a47d add indexes for lookup of addressable areas
The generic geometry index has become to slow for that purpose.
2022-09-18 16:57:12 +02:00
Sarah Hoffmann
d6a0947e5a update security policy for 4.1 version 2022-09-13 08:58:31 +02:00
Sarah Hoffmann
bc94318d83 mypy: fix new warnings due to external type updates 2022-09-05 17:39:35 +02:00
Sarah Hoffmann
d4c6e58b57 Merge pull request #2812 from mausch/patch-1
docs: fix links to rank docs
2022-09-05 17:27:09 +02:00
Mauricio Scheffer
66832cf0a5 docs: fix links to rank docs 2022-09-05 11:11:13 +01:00
Sarah Hoffmann
bcfe817212 Merge pull request #2799 from lonvia/fix-inclusions-with-extratags
Ignore irrelevant extra tags on address interpolations
2022-08-13 19:02:27 +02:00
Sarah Hoffmann
07d72f950b Merge pull request #2739 from tareqpi/collect_os_info.sh
integration of host system information script into Nominatim CLI tool
2022-08-13 19:02:14 +02:00
Sarah Hoffmann
dddfa3a075 ignore irrelevant extra tags on address interpolations
When deciding if an address interpolation has address information, only
look for addr:street and addr:place. If they are not there go looking
for the address on the address nodes. Ignores irrelevant tags like
addr:inclusion.

Fixes #2797.
2022-08-13 14:07:06 +02:00
Tareq Al-Ahdal
74019877a4 Added the feature of collecting host system information to the CI tests 2022-08-13 06:22:13 +08:00
Tareq Al-Ahdal
465d82a92f Integrated 'collect_os_info.py' into Nominatim's CLI tool 2022-08-13 06:18:10 +08:00
Tareq Al-Ahdal
49f889bf09 Enhanced and refactored 'collect_os_info.py'
Changed the script to functional programming paradigm to remove the big number of local attributes to decrease memory usage when running it. Additional OS info are now included.
2022-08-13 06:13:05 +08:00
Tareq Al-Ahdal
5e477e3b5b Merge remote-tracking branch 'upstream/master' into collect_os_info.sh 2022-08-13 05:53:39 +08:00
Sarah Hoffmann
67cfad6a2c Merge pull request #2798 from lonvia/more-rank-change-fixes
Invalidations when boundaries and places change their rank
2022-08-12 11:42:03 +02:00
Sarah Hoffmann
487e81fe3c more invalidations when boundary changes rank
When a boundary or place changes its address rank, all places where
it participates as address need to be potentially reindexed.
Also use the computed rank when testing place nodes against
boundaries. Boundaries are computed earlier.

Fixes #2794.
2022-08-12 09:48:46 +02:00
Sarah Hoffmann
18f525ac54 Merge pull request #2793 from lonvia/increase-minimum-results
Fix minimum number of results that are searched for
2022-08-09 20:08:45 +02:00
Sarah Hoffmann
e0c184e097 fix base number of returned results
The intent was to always search for at least 10 results.

Improves on #882.
2022-08-09 13:53:20 +02:00
Sarah Hoffmann
78716ab8b9 Merge pull request #2792 from lonvia/new-type-annotations
Adapt to new type annotations from typeshed
2022-08-09 13:52:20 +02:00
Sarah Hoffmann
8d082c13e0 adapt to new type annotations from typeshed
Some more functions frrom psycopg are now properly annotated.
No ignoring necessary anymore.
2022-08-09 11:06:54 +02:00
Sarah Hoffmann
196dc2a659 docs: add types-psutil requirement 2022-08-08 09:46:25 +02:00
Sarah Hoffmann
4fe797d704 remove mypy ignore for psutil.virtual_memory()
Now available in typeshed.
2022-08-08 09:44:45 +02:00
Sarah Hoffmann
3c188164ab Merge pull request #2789 from lonvia/update-osm2pgsql
Update osm2pgsql (fixes admin_level parsing)
2022-08-08 09:15:58 +02:00
Sarah Hoffmann
5330370076 update osm2pgsql (fix admin_level parsing) 2022-08-07 18:34:47 +02:00
Micah David Cochran
8bda59fbe7 made collect_os_info script in Python 2022-01-03 14:57:01 -06:00
Micah David Cochran
f20d85738f add utils/collect_os_info.sh script 2021-12-13 11:26:09 -06:00
465 changed files with 33206 additions and 8923 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

2
.github/FUNDING.yml vendored Normal file
View File

@@ -0,0 +1,2 @@
github: lonvia
custom: "https://nominatim.org/funding/"

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

@@ -7,10 +7,13 @@ assignees: ''
---
<!-- Note: if you are installing Nominatim through a docker image, you should report issues with the installation process with the docker repository first. -->
<!-- Note: if you are installing Nominatim through a docker image, you should report issues with the installation process with the docker repository first.
Do not send screen shots! Copy any console output directly into the issue.
-->
**Describe the bug**
<!-- A clear and concise description of what the bug is. -->
<!-- A clear and concise description of what the bug is.-->
**To Reproduce**
<!-- Please describe what you did to get to the issue. -->
@@ -25,12 +28,15 @@ assignees: ''
- RAM:
- number of CPUs:
- type and size of disks:
- bare metal/AWS/other cloud service:
**Postgresql Configuration:**
<!-- List any configuration items you changed in your postgresql configuration. -->
**Nominatim Configuration:**
<!-- List the contents of your customized `.env` file. -->
**Additional context**
<!-- Add any other context about the problem here. -->

View File

@@ -1,14 +1,18 @@
name: 'Build Nominatim'
inputs:
ubuntu:
flavour:
description: 'Version of Ubuntu to install on'
required: false
default: '20'
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'
runs:
using: "composite"
@@ -19,18 +23,20 @@ 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 prerequisites
- name: Install${{ matrix.flavour }} prerequisites
run: |
sudo apt-get install -y -qq libboost-system-dev libboost-filesystem-dev libexpat1-dev zlib1g-dev libbz2-dev libpq-dev libproj-dev libicu-dev
if [ "x$UBUNTUVER" == "x18" ]; then
pip3 install python-dotenv psycopg2==2.7.7 jinja2==2.8 psutil==5.4.2 pyicu==2.9 osmium PyYAML==5.1 datrie
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 libspatialite7 libsqlite3-mod-spatialite
if [ "$FLAVOUR" == "oldstuff" ]; then
pip3 install MarkupSafe==2.0.1 python-dotenv jinja2==2.8 psutil==5.4.2 pyicu==2.9 osmium PyYAML==5.1 sqlalchemy==1.4.31 psycopg==3.1.7 datrie asyncpg aiosqlite
else
sudo apt-get install -y -qq python3-icu python3-datrie python3-pyosmium python3-jinja2 python3-psutil python3-psycopg2 python3-dotenv python3-yaml
sudo apt-get install -y -qq python3-icu python3-datrie python3-pyosmium python3-jinja2 python3-psutil python3-dotenv python3-yaml
pip3 install sqlalchemy psycopg aiosqlite
fi
shell: bash
env:
UBUNTUVER: ${{ inputs.ubuntu }}
FLAVOUR: ${{ inputs.flavour }}
CMAKE_ARGS: ${{ inputs.cmake-args }}
LUA_VERSION: ${{ inputs.lua }}
- name: Configure
run: mkdir build && cd build && cmake $CMAKE_ARGS ../Nominatim

View File

@@ -15,7 +15,9 @@ runs:
- name: Remove existing PostgreSQL
run: |
sudo apt-get purge -yq postgresql*
sudo sh -c 'echo "deb http://apt.postgresql.org/pub/repos/apt $(lsb_release -cs)-pgdg main" > /etc/apt/sources.list.d/pgdg.list'
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

View File

@@ -7,11 +7,11 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- uses: actions/checkout@v4
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
@@ -37,45 +37,38 @@ jobs:
needs: create-archive
strategy:
matrix:
ubuntu: [18, 20, 22]
flavour: [oldstuff, "ubuntu-20", "ubuntu-22"]
include:
- ubuntu: 18
postgresql: 9.6
postgis: 2.5
pytest: pytest
php: 7.2
- ubuntu: 20
- flavour: oldstuff
ubuntu: 20
postgresql: '9.6'
postgis: '2.5'
lua: '5.1'
- flavour: ubuntu-20
ubuntu: 20
postgresql: 13
postgis: 3
pytest: py.test-3
php: 7.4
- ubuntu: 22
postgresql: 14
lua: '5.3'
- flavour: ubuntu-22
ubuntu: 22
postgresql: 15
postgis: 3
pytest: py.test-3
php: 8.1
lua: '5.3'
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
- uses: actions/setup-python@v5
with:
php-version: ${{ matrix.php }}
tools: phpunit, phpcs, composer
ini-values: opcache.jit=disable
- uses: actions/setup-python@v4
with:
python-version: 3.6
if: matrix.ubuntu == 18
python-version: 3.7
if: matrix.flavour == 'oldstuff'
- uses: ./Nominatim/.github/actions/setup-postgresql
with:
@@ -84,59 +77,70 @@ jobs:
- uses: ./Nominatim/.github/actions/build-nominatim
with:
ubuntu: ${{ matrix.ubuntu }}
flavour: ${{ matrix.flavour }}
lua: ${{ matrix.lua }}
- name: Install test prerequsites
run: sudo apt-get install -y -qq python3-pytest python3-behave
if: matrix.ubuntu == 20
- name: Install test prerequisites (behave from apt)
run: sudo apt-get install -y -qq python3-behave
if: matrix.flavour == 'ubuntu-20'
- name: Install test prerequsites
run: pip3 install pylint pytest behave==1.2.6
if: ${{ (matrix.ubuntu == 18) || (matrix.ubuntu == 22) }}
- name: Install test prerequisites (behave from pip)
run: pip3 install behave==1.2.6
if: (matrix.flavour == 'oldstuff') || (matrix.flavour == 'ubuntu-22')
- name: Install test prerequsites
run: sudo apt-get install -y -qq python3-pytest
if: matrix.ubuntu == 22
- name: Install test prerequisites (from apt for Ununtu 2x)
run: sudo apt-get install -y -qq python3-pytest python3-pytest-asyncio uvicorn
if: matrix.flavour != 'oldstuff'
- name: Install latest pylint/mypy
run: pip3 install -U pylint mypy types-PyYAML types-jinja2 types-psycopg2 types-psutil types-requests typing-extensions
- name: Install newer pytest-asyncio
run: pip3 install -U pytest-asyncio
if: matrix.flavour == 'ubuntu-20'
- name: PHP linting
run: phpcs --report-width=120 .
working-directory: Nominatim
- name: Install test prerequisites (from pip for Ubuntu 18)
run: pip3 install pytest pytest-asyncio uvicorn
if: matrix.flavour == 'oldstuff'
- name: Install Python webservers
run: pip3 install falcon starlette asgi_lifespan
- name: Install latest pylint
run: pip3 install -U pylint
if: matrix.flavour == 'ubuntu-22'
- name: Python linting
run: pylint nominatim
run: python3 -m pylint src
working-directory: Nominatim
- name: Python static typechecking
run: mypy --strict nominatim
working-directory: Nominatim
- name: PHP unit tests
run: phpunit ./
working-directory: Nominatim/test/php
if: ${{ (matrix.ubuntu == 20) || (matrix.ubuntu == 22) }}
if: matrix.flavour == 'ubuntu-22'
- name: Python unit tests
run: $PYTEST test/python
run: python3 -m pytest test/python
working-directory: Nominatim
env:
PYTEST: ${{ matrix.pytest }}
- name: BDD tests
run: |
behave -DREMOVE_TEMPLATE=1 -DBUILDDIR=$GITHUB_WORKSPACE/build --format=progress3
export PATH=$GITHUB_WORKSPACE/build/osm2pgsql:$PATH
python3 -m behave -DREMOVE_TEMPLATE=1 --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 src
working-directory: Nominatim
if: matrix.flavour != 'oldstuff'
legacy-test:
needs: create-archive
runs-on: ubuntu-20.04
strategy:
matrix:
postgresql: ["13", "16"]
steps:
- uses: actions/download-artifact@v3
- uses: actions/download-artifact@v4
with:
name: full-source
@@ -146,27 +150,77 @@ jobs:
- name: Setup PHP
uses: shivammathur/setup-php@v2
with:
php-version: 7.4
php-version: '7.4'
- uses: ./Nominatim/.github/actions/setup-postgresql
with:
postgresql-version: 13
postgresql-version: ${{ matrix.postgresql }}
postgis-version: 3
- name: Install Postgresql server dev
run: sudo apt-get install postgresql-server-dev-13
run: sudo apt-get install postgresql-server-dev-$PGVER
env:
PGVER: ${{ matrix.postgresql }}
- uses: ./Nominatim/.github/actions/build-nominatim
with:
ubuntu: 20
cmake-args: -DBUILD_MODULE=on
- name: Install test prerequsites
- name: Install test prerequisites
run: sudo apt-get install -y -qq python3-behave
- name: BDD tests (legacy tokenizer)
run: |
behave -DREMOVE_TEMPLATE=1 -DBUILDDIR=$GITHUB_WORKSPACE/build -DTOKENIZER=legacy --format=progress3
export PATH=$GITHUB_WORKSPACE/build/osm2pgsql:$PATH
python3 -m behave -DREMOVE_TEMPLATE=1 -DSERVER_MODULE_PATH=$GITHUB_WORKSPACE/build/module -DAPI_ENGINE=php -DTOKENIZER=legacy --format=progress3
working-directory: Nominatim/test/bdd
php-test:
needs: create-archive
runs-on: ubuntu-22.04
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: 15
postgis-version: 3
- name: Setup PHP
uses: shivammathur/setup-php@v2
with:
php-version: 8.1
tools: phpunit:9, phpcs, composer
ini-values: opcache.jit=disable
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: PHP linting
run: phpcs --report-width=120 .
working-directory: Nominatim
- name: PHP unit tests
run: phpunit ./
working-directory: Nominatim/test/php
- uses: ./Nominatim/.github/actions/build-nominatim
with:
flavour: 'ubuntu-22'
- name: Install test prerequisites
run: sudo apt-get install -y -qq python3-behave
- name: BDD tests (php)
run: |
export PATH=$GITHUB_WORKSPACE/build/osm2pgsql:$PATH
python3 -m behave -DREMOVE_TEMPLATE=1 -DAPI_ENGINE=php --format=progress3
working-directory: Nominatim/test/bdd
@@ -176,23 +230,16 @@ jobs:
strategy:
matrix:
name: [Ubuntu-18, Ubuntu-20, Ubuntu-22]
name: [Ubuntu-22, Ubuntu-24]
include:
- name: Ubuntu-18
flavour: ubuntu
image: "ubuntu:18.04"
ubuntu: 18
install_mode: install-nginx
- name: Ubuntu-20
flavour: ubuntu
image: "ubuntu:20.04"
ubuntu: 20
install_mode: install-apache
- name: Ubuntu-22
flavour: ubuntu
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: ${{ matrix.image }}
@@ -212,14 +259,6 @@ jobs:
apt-get install -y git sudo wget
ln -snf /usr/share/zoneinfo/$CONTAINER_TIMEZONE /etc/localtime && echo $CONTAINER_TIMEZONE > /etc/timezone
shell: bash
if: matrix.flavour == 'ubuntu'
- name: Prepare container (CentOS)
run: |
dnf update -y
dnf install -y sudo glibc-langpack-en
shell: bash
if: matrix.flavour == 'centos'
- name: Setup import user
run: |
@@ -231,7 +270,7 @@ 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
@@ -249,22 +288,35 @@ 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: Prepare import environment (CentOS)
- name: Add nominatim to path
run: |
sudo ln -s /usr/local/bin/nominatim /usr/bin/nominatim
echo NOMINATIM_DATABASE_WEBUSER="apache" > nominatim-project/.env
cp nominatim-project/.env data-env-reverse/.env
working-directory: /home/nominatim
if: matrix.flavour == 'centos'
sudo ln -s /home/nominatim/nominatim-venv/bin/nominatim /usr/local/bin/nominatim
if: matrix.ubuntu == 24
- name: Need lua binary
run: |
sudo apt-get install -y lua5.4 lua-dkjson
if: matrix.ubuntu == 24
- name: Print version
run: nominatim --version
working-directory: /home/nominatim/nominatim-project
- name: Print taginfo
run: lua taginfo.lua
working-directory: /home/nominatim
- name: Collect host OS information
run: nominatim admin --collect-os-info
working-directory: /home/nominatim/nominatim-project
- name: Import
run: nominatim import --osm-file ../test.pbf
working-directory: /home/nominatim/nominatim-project
@@ -284,11 +336,19 @@ jobs:
- name: Prepare update (Ubuntu)
run: apt-get install -y python3-pip
shell: bash
if: matrix.flavour == 'ubuntu'
- name: Install osmium (Ubuntu 22)
run: |
pip3 install --user osmium
if: matrix.ubuntu == 22
- name: Install osmium (Ubuntu 24)
run: |
/home/nominatim/nominatim-venv/bin/pip install osmium
if: matrix.ubuntu == 24
- 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
@@ -310,3 +370,54 @@ 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-latest
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
postgis-version: 3
- uses: ./Nominatim/.github/actions/build-nominatim
with:
flavour: ubuntu-22
lua: 5.3
- name: Prepare import environment
run: |
mv Nominatim/test/testdb/apidb-test-data.pbf test.pbf
rm -rf Nominatim
- name: Prepare Database
run: |
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" nominatim import --continue import-from-file --osm-file test.pbf
- name: Check full import
run: nominatim admin --check-database
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

View File

@@ -1,9 +1,13 @@
[mypy]
plugins = sqlalchemy.ext.mypy.plugin
[mypy-sanic_cors.*]
ignore_missing_imports = True
[mypy-icu.*]
ignore_missing_imports = True
[mypy-osmium.*]
[mypy-asyncpg.*]
ignore_missing_imports = True
[mypy-datrie.*]
@@ -11,3 +15,9 @@ ignore_missing_imports = True
[mypy-dotenv.*]
ignore_missing_imports = True
[mypy-falcon.*]
ignore_missing_imports = True
[mypy-geoalchemy2.*]
ignore_missing_imports = True

View File

@@ -1,6 +1,6 @@
[MASTER]
extension-pkg-whitelist=osmium
extension-pkg-whitelist=osmium,falcon
ignored-modules=icu,datrie
[MESSAGES CONTROL]
@@ -13,6 +13,10 @@ 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
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,too-many-boolean-expressions,contextmanager-generator-missing-cleanup
good-names=i,x,y,fd,db,cc
good-names=i,j,x,y,m,t,fd,db,cc,x1,x2,y1,y2,pt,k,v,nr
[DESIGN]
max-returns=7

View File

@@ -19,8 +19,8 @@ list(APPEND CMAKE_MODULE_PATH "${CMAKE_SOURCE_DIR}/cmake")
project(nominatim)
set(NOMINATIM_VERSION_MAJOR 4)
set(NOMINATIM_VERSION_MINOR 1)
set(NOMINATIM_VERSION_PATCH 2)
set(NOMINATIM_VERSION_MINOR 5)
set(NOMINATIM_VERSION_PATCH 0)
set(NOMINATIM_VERSION "${NOMINATIM_VERSION_MAJOR}.${NOMINATIM_VERSION_MINOR}.${NOMINATIM_VERSION_PATCH}")
@@ -46,8 +46,6 @@ set(BUILD_IMPORTER on CACHE BOOL "Build everything for importing/updating the da
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")
@@ -63,7 +61,6 @@ if (BUILD_IMPORTER AND BUILD_OSM2PGSQL)
endif()
set(BUILD_TESTS_SAVED "${BUILD_TESTS}")
set(BUILD_TESTS off)
set(WITH_LUA off CACHE BOOL "")
add_subdirectory(osm2pgsql)
set(BUILD_TESTS ${BUILD_TESTS_SAVED})
endif()
@@ -73,8 +70,8 @@ endif()
# python (imports/updates only)
#-----------------------------------------------------------------------------
if (BUILD_IMPORTER)
find_package(PythonInterp 3.6 REQUIRED)
if (BUILD_IMPORTER OR BUILD_API)
find_package(PythonInterp 3.7 REQUIRED)
endif()
#-----------------------------------------------------------------------------
@@ -83,26 +80,17 @@ endif()
# Setting PHP binary variable as to command line (prevailing) or auto detect
if (BUILD_API OR BUILD_IMPORTER)
if (BUILD_API)
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 ")
message(WARNING "PHP binary not found. Only Python frontend can be used.")
set(PHP_BIN "")
else()
message (STATUS "Using PHP binary " ${PHP_BIN})
endif()
if (NOT PHPCGI_BIN)
find_program (PHPCGI_BIN php-cgi)
endif()
# sanity check if PHP binary exists
if (NOT EXISTS ${PHPCGI_BIN})
message(WARNING "php-cgi binary not found. nominatim tool will not provide query functions.")
set (PHPCGI_BIN "")
else()
message (STATUS "Using php-cgi binary " ${PHPCGI_BIN})
endif()
endif()
#-----------------------------------------------------------------------------
@@ -198,22 +186,6 @@ 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
#-----------------------------------------------------------------------------
@@ -231,10 +203,23 @@ if (BUILD_IMPORTER)
DESTINATION ${CMAKE_INSTALL_BINDIR}
RENAME nominatim)
install(DIRECTORY nominatim
DESTINATION ${NOMINATIM_LIBDIR}/lib-python
FILES_MATCHING PATTERN "*.py"
PATTERN __pycache__ EXCLUDE)
if (EXISTS ${PHP_BIN})
configure_file(${PROJECT_SOURCE_DIR}/cmake/paths-py.tmpl paths-py.installed)
else()
configure_file(${PROJECT_SOURCE_DIR}/cmake/paths-py-no-php.tmpl paths-py.installed)
endif()
foreach (submodule nominatim_db nominatim_api)
install(DIRECTORY src/${submodule}
DESTINATION ${NOMINATIM_LIBDIR}/lib-python
FILES_MATCHING PATTERN "*.py"
PATTERN "paths.py" EXCLUDE
PATTERN __pycache__ EXCLUDE)
install(FILES ${PROJECT_BINARY_DIR}/paths-py.installed
DESTINATION ${NOMINATIM_LIBDIR}/lib-python/${submodule}
RENAME paths.py)
endforeach()
install(DIRECTORY lib-sql DESTINATION ${NOMINATIM_LIBDIR})
install(FILES ${COUNTRY_GRID_FILE}
@@ -258,18 +243,19 @@ if (BUILD_MODULE)
DESTINATION ${NOMINATIM_LIBDIR}/module)
endif()
if (BUILD_API)
if (BUILD_API AND EXISTS ${PHP_BIN})
install(DIRECTORY lib-php DESTINATION ${NOMINATIM_LIBDIR})
endif()
install(FILES settings/env.defaults
settings/address-levels.json
settings/phrase-settings.json
settings/import-admin.style
settings/import-street.style
settings/import-address.style
settings/import-full.style
settings/import-extratags.style
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})
@@ -285,3 +271,7 @@ if (INSTALL_MUNIN_PLUGINS)
munin/nominatim_requests
DESTINATION ${NOMINATIM_MUNINDIR})
endif()
message(WARNING "Building with CMake is deprecated and will be removed in Nominatim 5.0."
"Use Nominatim pip packages instead.\n"
"See https://nominatim.org/release-docs/develop/admin/Installation/#downloading-and-building-nominatim")

View File

@@ -64,3 +64,43 @@ Before submitting a pull request make sure that the tests pass:
cd build
make test
```
## 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 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 versions in
* `src/nominatim_api/version.py`
* `src/nominatim_db/version.py`
* CMakeLists.txt
* [ ] 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
* [ ] 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*`
* copy country data into `data/`
* add version to base directory and package
* [ ] upload tarball to https://nominatim.org
* [ ] prepare documentation
* check out new docs branch
* change git checkout instructions to tarball download instructions or adapt version on existing ones
* build documentation and copy to https://github.com/osm-search/nominatim-org-site
* add new version to history
* [ ] check release tarball
* download tarball as per new documentation instructions
* 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

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>.

160
ChangeLog
View File

@@ -1,11 +1,148 @@
4.1.2
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
* fix a number of corner cases with interpolation splitting resulting in
invalid geometries
* fix failure in website generation when password contains curly brackets
* fix broken use of ST_Project in PostGIS 3.4
* new NOMINATIM_SEARCH_WITHIN_COUNTRIES setting to restrict reverse lookups
to known countries (thanks @alfmarcua)
* allow negative OSM IDs (thanks @alfmarcua)
* disallow import of Tiger data in a frozen DB
* avoid UPDATE to change settings to be compatible with r/o DBs (thanks @t-tomek)
* update bundled osm2pgsql to 1.9.2
* reorganise osm2pgsql flex style and make it the default
* exclude names ending in :wikipedia from indexing
* no longer accept comma as a list separator in name tags
* process forward dependencies on update to catch updates in geometries
of ways and relations
* fix handling of isolated silent letters during transliteration
* no longer assign postcodes to large linear features like rivers
* introduce nominatim.paths module for finding data and libraries
* documentation layout changed to material theme
* new documentation section for library
* various smaller fixes to existing documentation
(thanks @woodpeck, @bloom256, @biswajit-k)
* 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)
* modernize Python code around BDD test and add testing of Python frontend
* lots of new BDD tests for API output
4.2.3
* fix deletion handling for 'nominatim add-data'
* adapt place_force_delete() to new deletion handling
* flex style: avoid dropping of postcode areas
* fix update errors on address interpolation handling
4.2.2
* extend flex-style library to fully support all default styles
* fix handling of Hebrew aleph
* do not assign postcodes to rivers
* fix string matching in PHP code
* update osm2pgsql (various updates to flex)
* fix slow query when deleting places on update
* fix CLI details query
* fix recalculation of importance values
* fix polygon simplification in reverse results
* add class/type information to reverse geocodejson result
* minor improvements to default tokenizer configuration
* various smaller fixes to documentation
4.2.1
* fix XSS vulnerability in debug view
4.1.1
4.2.0
* add experimental support for osm2pgsql flex style
* introduce secondary importance value to be retrieved from a raster data file
(currently still unused, to replace address importance, thanks to @tareqpi)
* add new report tool `nominatim admin --collect-os-info`
(thanks @micahcochran, @tareqpi)
* reorganise index to improve lookup performance and size
* run index creation after import in parallel
* run ANALYZE more selectively to speed up continuation of indexing
* fix crash on update when addr:interpolation receives an illegal value
* fix minimum number of retrived results to be at least 10
* fix minimum number of retrieved results to be at least 10
* fix search for combinations of special term + name (e.g Hotel Bellevue)
* do not return interpolations without a parent street on reverse search
* improve invalidation of linked places on updates
@@ -13,8 +150,13 @@
* make sure socket timeouts are respected during replication
(working around a bug in some versions of pyosmium)
* update bundled osm2pgsql to 1.7.1
* add support for PostgreSQL 15
* typing fixes to work with latest type annotations from typeshed
* smaller improvements to documention (thanks to @mausch)
* smaller improvements to documentation (thanks to @mausch)
4.1.1
* fix XSS vulnerability in debug view
4.1.0
@@ -173,7 +315,7 @@
* 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
@@ -230,7 +372,7 @@
* 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
@@ -269,7 +411,7 @@
* 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
@@ -334,7 +476,7 @@
* 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
@@ -345,7 +487,7 @@
* 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 src
pytest:
pytest test/python
lint:
pylint src
bdd:
cd test/bdd; behave -DREMOVE_TEMPLATE=1
# 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
=========
@@ -48,20 +47,31 @@ A quick summary of the necessary steps:
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 +9,10 @@ versions.
| Version | End of support for security updates |
| ------- | ----------------------------------- |
| 4.0.x | 2023-11-02 |
| 3.7.x | 2023-04-05 |
| 3.6.x | 2022-12-12 |
| 3.5.x | 2022-06-05 |
| 4.5.x | 2026-09-12 |
| 4.4.x | 2026-03-07 |
| 4.3.x | 2025-09-07 |
| 4.2.x | 2024-11-24 |
## Reporting a Vulnerability
@@ -36,4 +36,6 @@ incident. Announcements will also be published at the
## List of Previous Incidents
* 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 16
This document describes how you can install Nominatim inside a Ubuntu 22
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.
@@ -69,8 +69,7 @@ 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 (preferred) or set
`@define('CONST_Debug', true);` in `settings/local.php`.
you either add `&debug=1` to the URL.
In the Python BDD test you can use `logger.info()` for temporary debug
statements.
@@ -130,6 +129,10 @@ and then
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?
You might need to replace Virtualbox with [Parallels](https://www.parallels.com/products/desktop/).
There is no free/open source version of Parallels.
##### Why Monaco, can I use another country?
@@ -141,11 +144,12 @@ No. Long running Nominatim installations will differ once new import features (o
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
of search results. See [Nominatim installation](https://nominatim.org/release-docs/latest/admin/Installation) for details.
of search results. See [Nominatim installation](https://nominatim.org/release-docs/latest/admin/Installation)
for details.
##### Why Ubuntu? Can I test CentOS/Fedora/CoreOS/FreeBSD?
There is a Vagrant script for CentOS available, but the Nominatim directory
There used to be a Vagrant script for CentOS available, but the Nominatim directory
isn't symlinked/mounted to the host which makes development trickier. We used
it mainly for debugging installation with SELinux.
@@ -154,14 +158,17 @@ are slightly different, e.g. the name of the package manager, Apache2 package
name, location of files. We chose Ubuntu because that is closest to the
nominatim.openstreetmap.org production environment.
You can configure/download other Vagrant boxes from [https://app.vagrantup.com/boxes/search](https://app.vagrantup.com/boxes/search).
You can configure/download other Vagrant boxes from
[https://app.vagrantup.com/boxes/search](https://app.vagrantup.com/boxes/search).
##### How can I connect to an existing database?
Let's say you have a Postgres database named `nominatim_it` on server `your-server.com` and port `5432`. The Postgres username is `postgres`. You can edit `settings/local.php` and point Nominatim to it.
Let's say you have a Postgres database named `nominatim_it` on server `your-server.com`
and port `5432`. The Postgres username is `postgres`. You can edit the `.env` in your
project directory and point Nominatim to it.
NOMINATIM_DATABASE_DSN="pgsql:host=your-server.com;port=5432;user=postgres;dbname=nominatim_it
pgsql:host=your-server.com;port=5432;user=postgres;dbname=nominatim_it
No data import or restarting necessary.
If the Postgres installation is behind a firewall, you can try
@@ -169,11 +176,12 @@ If the Postgres installation is behind a firewall, you can try
ssh -L 9999:localhost:5432 your-username@your-server.com
inside the virtual machine. It will map the port to `localhost:9999` and then
you edit `settings/local.php` with
you edit `.env` file with
@define('CONST_Database_DSN', 'pgsql:host=localhost;port=9999;user=postgres;dbname=nominatim_it');
NOMINATIM_DATABASE_DSN="pgsql:host=localhost;port=9999;user=postgres;dbname=nominatim_it"
To access postgres directly remember to specify the hostname, e.g. `psql --host localhost --port 9999 nominatim_it`
To access postgres directly remember to specify the hostname,
e.g. `psql --host localhost --port 9999 nominatim_it`
##### My computer is slow and the import takes too long. Can I start the virtual machine "in the cloud"?

78
Vagrantfile vendored
View File

@@ -17,6 +17,14 @@ Vagrant.configure("2") do |config|
checkout = "no"
end
config.vm.provider "hyperv" do |hv, override|
hv.memory = 2048
hv.linked_clone = true
if ENV['CHECKOUT'] != 'y' then
override.vm.synced_folder ".", "/home/vagrant/Nominatim", type: "smb", smb_host: ENV['SMB_HOST'] || ENV['COMPUTERNAME']
end
end
config.vm.provider "virtualbox" do |vb, override|
vb.gui = false
vb.memory = 2048
@@ -26,85 +34,77 @@ 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
config.vm.define "ubuntu", primary: true do |sub|
sub.vm.box = "generic/ubuntu2004"
config.vm.define "ubuntu22", primary: true do |sub|
sub.vm.box = "generic/ubuntu2204"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Ubuntu-20.sh"
s.path = "vagrant/Install-on-Ubuntu-22.sh"
s.privileged = false
s.args = [checkout]
end
end
config.vm.define "ubuntu-apache" do |sub|
sub.vm.box = "generic/ubuntu2004"
config.vm.define "ubuntu22-apache" do |sub|
sub.vm.box = "generic/ubuntu2204"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Ubuntu-20.sh"
s.path = "vagrant/Install-on-Ubuntu-22.sh"
s.privileged = false
s.args = [checkout, "install-apache"]
end
end
config.vm.define "ubuntu-nginx" do |sub|
sub.vm.box = "generic/ubuntu2004"
config.vm.define "ubuntu22-nginx" do |sub|
sub.vm.box = "generic/ubuntu2204"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Ubuntu-20.sh"
s.path = "vagrant/Install-on-Ubuntu-22.sh"
s.privileged = false
s.args = [checkout, "install-nginx"]
end
end
config.vm.define "ubuntu18" do |sub|
sub.vm.box = "generic/ubuntu1804"
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-18.sh"
s.path = "vagrant/Install-on-Ubuntu-24.sh"
s.privileged = false
s.args = [checkout]
end
end
config.vm.define "ubuntu18-apache" do |sub|
sub.vm.box = "generic/ubuntu1804"
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-18.sh"
s.path = "vagrant/Install-on-Ubuntu-24.sh"
s.privileged = false
s.args = [checkout, "install-apache"]
end
end
config.vm.define "ubuntu18-nginx" do |sub|
sub.vm.box = "generic/ubuntu1804"
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-18.sh"
s.path = "vagrant/Install-on-Ubuntu-24.sh"
s.privileged = false
s.args = [checkout, "install-nginx"]
end
end
config.vm.define "centos7" do |sub|
sub.vm.box = "centos/7"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Centos-7.sh"
s.privileged = false
s.args = [checkout]
end
end
config.vm.define "centos" do |sub|
sub.vm.box = "generic/centos8"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Centos-8.sh"
s.privileged = false
s.args = [checkout]
end
end
end

View File

@@ -0,0 +1,15 @@
# 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 = None
SQLLIB_DIR = (Path('@NOMINATIM_LIBDIR@') / 'lib-sql').resolve()
DATA_DIR = Path('@NOMINATIM_DATADIR@').resolve()
CONFIG_DIR = Path('@NOMINATIM_CONFIGDIR@').resolve()

15
cmake/paths-py.tmpl Normal file
View File

@@ -0,0 +1,15 @@
# 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

@@ -4,17 +4,10 @@ import os
sys.path.insert(1, '@NOMINATIM_LIBDIR@/lib-python')
os.environ['NOMINATIM_NOMINATIM_TOOL'] = os.path.abspath(__file__)
from nominatim import cli
from nominatim import version
from nominatim_db import cli
from nominatim_db import version
version.GIT_COMMIT_HASH = '@GIT_HASH@'
exit(cli.nominatim(module_dir='@NOMINATIM_LIBDIR@/module',
osm2pgsql_path='@NOMINATIM_LIBDIR@/osm2pgsql',
phplib_dir='@NOMINATIM_LIBDIR@/lib-php',
sqllib_dir='@NOMINATIM_LIBDIR@/lib-sql',
data_dir='@NOMINATIM_DATADIR@',
config_dir='@NOMINATIM_CONFIGDIR@',
phpcgi_path='@PHPCGI_BIN@'))
osm2pgsql_path='@NOMINATIM_LIBDIR@/osm2pgsql'))

View File

@@ -2,19 +2,12 @@
import sys
import os
sys.path.insert(1, '@CMAKE_SOURCE_DIR@')
sys.path.insert(1, '@CMAKE_SOURCE_DIR@/src')
os.environ['NOMINATIM_NOMINATIM_TOOL'] = os.path.abspath(__file__)
from nominatim import cli
from nominatim import version
from nominatim_db import cli
from nominatim_db import version
version.GIT_COMMIT_HASH = '@GIT_HASH@'
exit(cli.nominatim(module_dir='@CMAKE_BINARY_DIR@/module',
osm2pgsql_path='@CMAKE_BINARY_DIR@/osm2pgsql/osm2pgsql',
phplib_dir='@CMAKE_SOURCE_DIR@/lib-php',
sqllib_dir='@CMAKE_SOURCE_DIR@/lib-sql',
data_dir='@CMAKE_SOURCE_DIR@/data',
config_dir='@CMAKE_SOURCE_DIR@/settings',
phpcgi_path='@PHPCGI_BIN@'))
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
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-18.sh ${CMAKE_CURRENT_BINARY_DIR}/appendix/Install-on-Ubuntu-18.md
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 ${CMAKE_CURRENT_BINARY_DIR}/appendix/Install-on-Ubuntu-22.md
COMMAND PYTHONPATH=${PROJECT_SOURCE_DIR} mkdocs build -d ${CMAKE_CURRENT_BINARY_DIR}/../site-html -f ${CMAKE_CURRENT_BINARY_DIR}/../mkdocs.yml
)
ADD_CUSTOM_TARGET(serve-doc
COMMAND PYTHONPATH=${PROJECT_SOURCE_DIR} mkdocs serve
WORKING_DIRECTORY ${PROJECT_BINARY_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
@@ -36,16 +65,15 @@ which has the following structure:
```bash
update
   ├── europe
   │   ├── andorra
   │   │   └── sequence.state
   │   └── monaco
   │   └── sequence.state
   └── tmp
└── europe
├── andorra-latest.osm.pbf
└── monaco-latest.osm.pbf
├── europe
├── andorra
│ │ └── sequence.state
└── monaco
└── sequence.state
└── tmp
└── europe
├── andorra-latest.osm.pbf
└── monaco-latest.osm.pbf
```
@@ -99,7 +127,7 @@ Change into the project directory and run the following command:
This will get diffs from the replication server, import diffs and index
the database. The default replication server in the
script([Geofabrik](https://download.geofabrik.de)) provides daily updates.
script ([Geofabrik](https://download.geofabrik.de)) provides daily updates.
## Using an external PostgreSQL database
@@ -211,6 +239,6 @@ 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
nominatim refresh --functions
on the target machine to update the the location of the module.

View File

@@ -1,4 +1,7 @@
# Deploying Nominatim
# Deploying Nominatim using the PHP frontend
!!! danger
The PHP frontend is deprecated and will be removed in Nominatim 5.0.
The Nominatim API is implemented as a PHP application. The `website/` directory
in the project directory contains the configured website. You can serve this
@@ -8,13 +11,13 @@ 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](http://httpd.apache.org/docs/current/) and
[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 that your Nominatim project directory is
located in `/srv/nominatim-project` and that you have installed Nominatim
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.

View File

@@ -0,0 +1,148 @@
# Deploying the Nominatim Python frontend
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.
This section gives a quick overview on how to configure Nginx to serve
Nominatim. Please refer to the documentation of
[Nginx](https://nginx.org/en/docs/) for background information on how
to configure it.
!!! Note
Throughout this page, we assume your Nominatim project directory is
located in `/srv/nominatim-project`. If you have put it somewhere else,
you need to adjust the commands and configuration accordingly.
### 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/)
together with [gunicorn](https://gunicorn.org/) HTTP server. We use
Falcon here as the web framework.
Add the necessary packages to your virtual environment:
``` sh
/srv/nominatim-venv/bin/pip install falcon uvicorn gunicorn
```
### Setting up Nominatim as a systemd job
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
[Unit]
Description=Nominatim running as a gunicorn application
After=network.target
Requires=nominatim.socket
[Service]
Type=simple
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_api.server.falcon.server:run_wsgi
ExecReload=/bin/kill -s HUP $MAINPID
StandardOutput=append:/var/log/gunicorn-nominatim.log
StandardError=inherit
PrivateTmp=true
TimeoutStopSec=5
KillMode=mixed
[Install]
WantedBy=multi-user.target
```
This sets up gunicorn with 4 workers (`-w 4` in ExecStart). Each worker runs
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 services known to systemd and start it:
``` sh
sudo systemctl daemon-reload
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
on reboot.
### Configuring nginx
To make the service available to the world, you need to proxy it through
nginx. Add the following definition to the default configuration:
``` nginx
upstream nominatim_service {
server unix:/run/nominatim.sock fail_timeout=0;
}
server {
listen 80;
listen [::]:80;
root /var/www/html;
index /search;
location / {
proxy_set_header Host $http_host;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
proxy_redirect off;
proxy_pass http://nominatim_service;
}
}
```
Reload nginx with
```
sudo systemctl reload nginx
```
and you should be able to see the status of your server under
`http://localhost/status`.

View File

@@ -37,40 +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
@@ -170,12 +136,31 @@ recreate `nominatim.so`. Try
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.

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://www.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, you can also add
importances after the import. Download the files, then run
`nominatim refresh --wiki-data --importance`. Updating importances for
a planet can take a couple of hours.
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 --secondary-importance --importance`.
Updating importances for a planet will take a couple of hours.
### External postcodes
@@ -92,8 +95,8 @@ and the UK (using the [CodePoint OpenData set](https://osdatahub.os.uk/downloads
This data can be optionally downloaded into the project directory:
cd $PROJECT_DIR
wget https://www.nominatim.org/data/gb_postcodes.csv.gz
wget https://www.nominatim.org/data/us_postcodes.csv.gz
wget https://nominatim.org/data/gb_postcodes.csv.gz
wget https://nominatim.org/data/us_postcodes.csv.gz
You can also add your own custom postcode sources, see
[Customization of postcodes](../customize/Postcodes.md).
@@ -139,7 +142,7 @@ import. So this option is particularly interesting if you plan to transfer the
database or reuse the space later.
!!! warning
The datastructure for updates are also required when adding additional data
The data structure for updates are also required when adding additional data
after the import, for example [TIGER housenumber data](../customize/Tiger.md).
If you plan to use those, you must not use the `--no-updates` parameter.
Do a normal import, add the external data and once you are done with
@@ -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
@@ -254,26 +257,74 @@ successfully.
nominatim admin --check-database
```
Now you can try out your installation by running:
Now you can try out your installation by executing a simple query on the
command line:
```sh
``` sh
nominatim search --query Berlin
```
or, when you have a reverse-only installation:
``` sh
nominatim reverse --lat 51 --lon 45
```
If you want to run Nominatim as a service, you need to make a choice between
running the modern Python frontend and the legacy PHP frontend.
Make sure you have installed the right packages as per
[Installation](Installation.md#software).
#### Testing the Python frontend
To run the test server against the Python frontend, you must choose a
web framework to use, either starlette or falcon. Make sure the appropriate
packages are installed. Then run
``` sh
nominatim serve
```
This runs a small test server normally used for development. You can use it
to verify that your installation is working. 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, if you prefer to use Starlette instead of Falcon as webserver,
Note that search query is not supported for reverse-only imports. You can run a
reverse query, e.g. `http://localhost:8088/reverse.php?lat=27.1750090510034&lon=78.04209025`.
``` sh
nominatim serve --engine starlette
```
To run Nominatim via webservers like Apache or nginx, please read the
[Deployment chapter](Deployment.md).
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`.
## Adding search through category phrases
Do not use this test server in production.
To run Nominatim via webservers like Apache or nginx, please continue reading
[Deploy the Python frontend](Deployment-Python.md).
If you want to be able to search for places by their type through
#### Testing the PHP frontend
!!! danger
The PHP fronted is deprecated and will be removed in Nominatim 5.0.
You can run a small test server with the PHP frontend like this:
```sh
nominatim serve --engine php
```
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).
## Enabling search by category phrases
To be able to search for places by their type using
[special phrases](https://wiki.openstreetmap.org/wiki/Nominatim/Special_Phrases)
you also need to import these key phrases like this:

View File

@@ -4,9 +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 18.04](../appendix/Install-on-Ubuntu-18.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.
@@ -28,7 +27,26 @@ and can't offer support.
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:
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)
* [osm2pgsql](https://osm2pgsql.org) (1.8+, optional when building with CMake)
* [Python 3](https://www.python.org/) (3.7+)
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/)
* [PyICU](https://pypi.org/project/PyICU/)
* [PyYaml](https://pyyaml.org/) (5.1+)
* [datrie](https://github.com/pytries/datrie)
These will be installed automatically when using pip installation.
When using legacy CMake-based installation:
* [cmake](https://cmake.org/)
* [expat](https://libexpat.github.io/)
@@ -36,31 +54,31 @@ For compiling:
* [bzip2](http://www.bzip.org/)
* [zlib](https://www.zlib.net/)
* [ICU](http://site.icu-project.org/)
* [Boost libraries](https://www.boost.org/), including system and filesystem
* [nlohmann/json](https://json.nlohmann.me/)
* [Boost libraries](https://www.boost.org/), including system and file system
* 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/) (3.6+)
* [Psycopg2](https://www.psycopg.org) (2.7+)
* [Python Dotenv](https://github.com/theskumar/python-dotenv)
* [psutil](https://github.com/giampaolo/psutil)
* [Jinja2](https://palletsprojects.com/p/jinja/)
* [PyICU](https://pypi.org/project/PyICU/)
* [PyYaml](https://pyyaml.org/) (5.1+)
* [datrie](https://github.com/pytries/datrie)
* [PHP](https://php.net) (7.0 or later)
* PHP-pgsql
* PHP-intl (bundled with PHP)
* PHP-cgi (for running queries from the command line)
For running continuous updates:
* [pyosmium](https://osmcode.org/pyosmium/)
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/)
* [uvicorn](https://www.uvicorn.org/)
For running the legacy PHP frontend (deprecated, will be removed in Nominatim 5.0):
* [PHP](https://php.net) (7.3+)
* PHP-pgsql
* PHP-intl (bundled with PHP)
For dependencies for running tests and building documentation, see
the [Development section](../develop/Development-Environment.md).
@@ -75,7 +93,7 @@ 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. On traditional spinning disks, 7-8 days are more realistic.
around 2.5 days. When using traditional SSDs, 4-5 days are more realistic.
## Tuning the PostgreSQL database
@@ -87,14 +105,16 @@ 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.
@@ -107,15 +127,6 @@ 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.
For the initial import, you should also set:
fsync = off
full_page_writes = off
Don't forget to re-enable them after the initial import or you risk database
corruption.
## Downloading and building Nominatim
### Downloading the latest release
@@ -135,11 +146,28 @@ git clone --recursive https://github.com/openstreetmap/Nominatim.git
The development version does not include the country grid. Download it separately:
```
wget -O Nominatim/data/country_osm_grid.sql.gz https://www.nominatim.org/data/country_grid.sql.gz
wget -O Nominatim/data/country_osm_grid.sql.gz https://nominatim.org/data/country_grid.sql.gz
```
### Building Nominatim
#### Building the latest development version with pip
Nominatim is easiest to run from its own virtual environment. To create one, run:
sudo apt-get install virtualenv
virtualenv /srv/nominatim-venv
To install Nominatim directly from the source tree into the virtual environment, run:
/srv/nominatim-venv/bin/pip install packaging/nominatim-{db,api}
#### Building in legacy CMake mode
!!! warning
Installing Nominatim through CMake is now deprecated. The infrastructure
will be removed in Nominatim 5.0. Please switch to pip installation.
The code must be built in a separate directory. Create the directory and
change into it.
@@ -166,6 +194,7 @@ sudo make install
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>`
The legacy tokenizer is deprecated and will be removed in Nominatim 5.0
Nominatim installs itself into `/usr/local` per default. To choose a different

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

@@ -1,12 +1,17 @@
# Database Migrations
Since version 3.7.0 Nominatim offers automatic migrations. Please follow
Nominatim offers automatic migrations since version 3.7. 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
If you are still using CMake for the installation of Nominatim, then you
need to update the software in one step before migrating the database.
It is not recommended to do this while the machine is serving requests.
Below you find additional migrations and hints about other structural and
breaking changes. **Please read them before running the migration.**
@@ -15,6 +20,41 @@ breaking changes. **Please read them before running the migration.**
If you are migrating from a version <3.6, then you still have to follow
the manual migration steps up to 3.6.
## 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
### New indexes for reverse lookup
The reverse lookup algorithm has changed slightly to improve performance.
This change needs a different index in the database. The required index
will be automatically build during migration. Until the new index is available
performance of the /reverse endpoint is significantly reduced. You should
therefore either remove traffic from the machine before attempting a
version update or create the index manually **before** starting the update
using the following SQL:
```sql
CREATE INDEX IF NOT EXISTS idx_placex_geometry_reverse_lookupPlaceNode
ON placex USING gist (ST_Buffer(geometry, reverse_place_diameter(rank_search)))
WHERE rank_address between 4 and 25 AND type != 'postcode'
AND name is not null AND linked_place_id is null AND osm_type = 'N';
```
## 4.0.0 -> 4.1.0
### ICU tokenizer is the new default

View File

@@ -59,47 +59,6 @@ imported multiple country extracts and want to keep them
up-to-date, [Advanced installations section](Advanced-Installations.md)
contains instructions to set up and update multiple country extracts.
#### Continuous updates
This is the easiest mode. Simply run the replication command without any
parameters:
nominatim replication
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
```
#### One-time mode
When the `--once` parameter is given, then Nominatim will download exactly one
@@ -221,3 +180,53 @@ replication catch-up at whatever interval you desire.
updated source with daily updates), use the
continuous update mode. It ensures to re-request the newest update until it
is published.
#### Continuous updates
!!! danger
This mode is no longer recommended to use and will removed in future
releases. systemd is much better
suited for running regular updates. Please refer to the setup
instructions for running one-time mode with systemd above.
This is the easiest mode. Simply run the replication command without any
parameters:
nominatim replication
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

@@ -2,13 +2,17 @@
Show all details about a single place saved in the database.
This API endpoint is meant for visual inspection of the data in the database,
mainly together with [Nominatim-UI](https://github.com/osm-search/nominatim-ui/).
The parameters of the endpoint and the output may change occasionally between
versions of Nominatim. Do not rely on the output in scripts or applications.
!!! warning
The details page exists for debugging only. You may not use it in scripts
or to automatically query details about a result.
The details endpoint at https://nominatim.openstreetmap.org
may not used in scripts or bots at all.
See [Nominatim Usage Policy](https://operations.osmfoundation.org/policies/nominatim/).
## Parameters
The details API supports the following two request formats:
@@ -35,59 +39,90 @@ for a place is different between Nominatim installation (servers) and
changes when data gets reimported. Therefore it cannot be used as
a permanent id and shouldn't be used in bug reports.
!!! danger "Deprecation warning"
The API can also be used with the URL
`https://nominatim.openstreetmap.org/details.php`. This is now deprecated
and will be removed in future versions.
Additional optional parameters are explained below.
## Parameters
This section lists additional optional parameters.
### Output format
* `json_callback=<string>`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| json_callback | function name | _unset_ |
Wrap JSON output in a callback function (JSONP) i.e. `<string>(<json>)`.
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.
* `pretty=[0|1]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| pretty | 0 or 1 | 0 |
Add indentation to make it more human-readable. (Default: 0)
`[PHP-only]` Add indentation to the output to make it more human-readable.
### Output details
* `addressdetails=[0|1]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| addressdetails | 0 or 1 | 0 |
Include a breakdown of the address into elements. (Default: 0)
When set to 1, include a breakdown of the address into elements.
* `keywords=[0|1]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| keywords | 0 or 1 | 0 |
Include a list of name keywords and address keywords (word ids). (Default: 0)
When set to 1, include a list of name keywords and address keywords
in the result.
* `linkedplaces=[0|1]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| linkedplaces | 0 or 1 | 1 |
Include a details of places that are linked with this one. Places get linked
Include details of places that are linked with this one. Places get linked
together when they are different forms of the same physical object. Nominatim
links two kinds of objects together: place nodes get linked with the
corresponding administrative boundaries. Waterway relations get linked together with their
members.
(Default: 1)
* `hierarchy=[0|1]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| hierarchy | 0 or 1 | 0 |
Include details of places lower in the address hierarchy. (Default: 0)
Include details of places lower in the address hierarchy.
* `group_hierarchy=[0|1]`
`[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.
For JSON output will group the places by type. (Default: 0)
| Parameter | Value | Default |
|-----------| ----- | ------- |
| group_hierarchy | 0 or 1 | 0 |
* `polygon_geojson=[0|1]`
When set to 1, the output of the address hierarchy will be
grouped by type.
Include geometry of result. (Default: 0)
| Parameter | Value | Default |
|-----------| ----- | ------- |
| polygon_geojson | 0 or 1 | 0 |
Include geometry of result.
### Language of results
* `accept-language=<browser language string>`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| accept-language | browser language string | content of "Accept-Language" HTTP header |
Preferred language order for showing result, overrides the value
specified in the "Accept-Language" HTTP header.
Either use a standard RFC2616 accept-language string or a simple
comma-separated list of language codes.
Preferred language order for showing search results. This may either be
a simple comma-separated list of language codes or have the same format
as the ["Accept-Language" HTTP header](https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Accept-Language).
## Examples

View File

@@ -59,3 +59,27 @@ suited for these kinds of queries.
That said if you installed your own Nominatim instance you can use the
`nominatim export` PHP script as basis to return such lists.
#### 7. My result has a wrong postcode. Where does it come from?
Most places in OSM don't have a postcode, so Nominatim tries to interpolate
one. It first look at all the places that make up the address of the place.
If one of them has a postcode defined, this is the one to be used. When
none of the address parts has a postcode either, Nominatim interpolates one
from the surrounding objects. If the postcode is for your result is one, then
most of the time there is an OSM object with the wrong postcode nearby.
To find the bad postcode, go to
[https://nominatim.openstreetmap.org](https://nominatim.openstreetmap.org)
and search for your place. When you have found it, click on the 'details' link
under the result to go to the details page. There is a field 'Computed Postcode'
which should display the bad postcode. Click on the 'how?' link. A small
explanation text appears. It contains a link to a query for Overpass Turbo.
Click on that and you get a map with all places in the area that have the bad
postcode. If none is displayed, zoom the map out a bit and then click on 'Run'.
Now go to [OpenStreetMap](https://openstreetmap.org) and fix the error you
have just found. It will take at least a day for Nominatim to catch up with
your data fix. Sometimes longer, depending on how much editing activity is in
the area.

View File

@@ -3,7 +3,7 @@
The lookup API allows to query the address and other details of one or
multiple OSM objects like node, way or relation.
## Parameters
## Endpoint
The lookup API has the following format:
@@ -15,75 +15,129 @@ The lookup API has the following format:
prefixed with its type, one of node(N), way(W) or relation(R). Up to 50 ids
can be queried at the same time.
Additional optional parameters are explained below.
!!! danger "Deprecation warning"
The API can also be used with the URL
`https://nominatim.openstreetmap.org/lookup.php`. This is now deprecated
and will be removed in future versions.
## Parameters
This section lists additional optional parameters.
### Output format
* `format=[xml|json|jsonv2|geojson|geocodejson]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| format | one of: `xml`, `json`, `jsonv2`, `geojson`, `geocodejson` | `jsonv2` |
See [Place Output Formats](Output.md) for details on each format. (Default: xml)
See [Place Output Formats](Output.md) for details on each format.
* `json_callback=<string>`
Wrap JSON output in a callback function (JSONP) i.e. `<string>(<json>)`.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| json_callback | function name | _unset_ |
When given, 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.
Only has an effect for JSON output formats.
### Output details
* `addressdetails=[0|1]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| addressdetails | 0 or 1 | 0 |
Include a breakdown of the address into elements. (Default: 0)
When set to 1, include a breakdown of the address into elements.
The exact content of the address breakdown depends on the output format.
!!! tip
If you are interested in a stable classification of address categories
(suburb, city, state, etc), have a look at the `geocodejson` format.
All other formats return classifications according to OSM tagging.
There is a much larger set of categories and they are not always consistent,
which makes them very hard to work with.
* `extratags=[0|1]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| extratags | 0 or 1 | 0 |
Include additional information in the result if available,
e.g. wikipedia link, opening hours. (Default: 0)
When set to 1, the response include any additional information in the result
that is available in the database, e.g. wikipedia link, opening hours.
* `namedetails=[0|1]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| namedetails | 0 or 1 | 0 |
Include a list of alternative names in the results. These may include
language variants, references, operator and brand. (Default: 0)
When set to 1, include a full list of names for the result. These may include
language variants, older names, references and brand.
### Language of results
* `accept-language=<browser language string>`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| accept-language | browser language string | content of "Accept-Language" HTTP header |
Preferred language order for showing search results. This may either be
a simple comma-separated list of language codes or have the same format
as the ["Accept-Language" HTTP header](https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Accept-Language).
!!! tip
First-time users of Nominatim tend to be confused that they get different
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 contrary always
send the currently chosen browser language.
Preferred language order for showing search results, overrides the value
specified in the "Accept-Language" HTTP header.
Either use a standard RFC2616 accept-language string or a simple
comma-separated list of language codes.
### Polygon output
* `polygon_geojson=1`
* `polygon_kml=1`
* `polygon_svg=1`
* `polygon_text=1`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| polygon_geojson | 0 or 1 | 0 |
| polygon_kml | 0 or 1 | 0 |
| polygon_svg | 0 or 1 | 0 |
| polygon_text | 0 or 1 | 0 |
Output geometry of results as a GeoJSON, KML, SVG or WKT. Only one of these
options can be used at a time. (Default: 0)
Add the full geometry of the place to the result output. Output formats
in GeoJSON, KML, SVG or WKT are supported. Only one of these
options can be used at a time.
* `polygon_threshold=0.0`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| polygon_threshold | floating-point number | 0.0 |
Return a simplified version of the output geometry. The parameter is the
When one of the polygon_* outputs is chosen, return a simplified version
of the output geometry. The parameter describes the
tolerance in degrees with which the geometry may differ from the original
geometry. Topology is preserved in the result. (Default: 0.0)
geometry. Topology is preserved in the geometry.
### Other
* `email=<valid email address>`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| email | valid email address | _unset_ |
If you are making large numbers of request please include an appropriate email
address to identify your requests. See Nominatim's [Usage Policy](https://operations.osmfoundation.org/policies/nominatim/) for more details.
address to identify your requests. See Nominatim's
[Usage Policy](https://operations.osmfoundation.org/policies/nominatim/) for more details.
* `debug=[0|1]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| debug | 0 or 1 | 0 |
Output assorted developer debug information. Data on internals of Nominatim's
"Search Loop" logic, and SQL queries. The output is (rough) HTML format.
This overrides the specified machine readable format. (Default: 0)
"search loop" logic, and SQL queries. The output is HTML format.
This overrides the specified machine readable format.
## Examples

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",
@@ -211,8 +211,8 @@ be more than one. The attributes of that element contain:
* `ref` - content of `ref` tag if it exists
* `lat`, `lon` - latitude and longitude of the centroid of the object
* `boundingbox` - comma-separated list of corner coordinates ([see notes](#boundingbox))
* `place_rank` - class [search rank](../customize/Ranking#search-rank)
* `address_rank` - place [address rank](../customize/Ranking#address-rank)
* `place_rank` - class [search rank](../customize/Ranking.md#search-rank)
* `address_rank` - place [address rank](../customize/Ranking.md#address-rank)
* `display_name` - full comma-separated address
* `class`, `type` - key and value of the main OSM tag
* `importance` - computed importance rank

View File

@@ -1,8 +1,14 @@
### 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]`.
Nominatim indexes named (or numbered) features within the OpenStreetMap (OSM) dataset and a subset of other unnamed features (pubs, hotels, churches, etc).
`https://nominatim.openstreetmap.org` implements the **Python frontend**.
So users should refer to the **`[Python-only]`** comments.
Its API has the following endpoints for querying the data:
This section describes the API V1 of the Nominatim web service. The
service offers the following endpoints:
* __[/search](Search.md)__ - search OSM objects by name or type
* __[/reverse](Reverse.md)__ - search OSM object by their location
@@ -12,3 +18,6 @@ Its API has the following endpoints for querying the data:
back in Nominatim in case the deletion was accidental
* __/polygons__ - list of broken polygons detected by Nominatim
* __[/details](Details.md)__ - show internal details for an object (for debugging only)

View File

@@ -1,6 +1,7 @@
# Reverse Geocoding
Reverse geocoding generates an address from a latitude and longitude.
Reverse geocoding generates an address from a coordinate given as
latitude and longitude.
## How it works
@@ -18,8 +19,7 @@ The other issue to be aware of is that the closest OSM object may not always
have a similar enough address to the coordinate you were requesting. For
example, in dense city areas it may belong to a completely different street.
## Parameters
## Endpoint
The main format of the reverse API is
@@ -31,57 +31,101 @@ where `lat` and `lon` are latitude and longitude of a coordinate in WGS84
projection. The API returns exactly one result or an error when the coordinate
is in an area with no OSM data coverage.
Additional parameters are accepted as listed below.
!!! warning "Deprecation warning"
!!! danger "Deprecation warning"
The reverse API used to allow address lookup for a single OSM object by
its OSM id. This use is now deprecated. Use the [Address Lookup API](../Lookup)
instead.
its OSM id for `[PHP-only]`. The use is considered deprecated.
Use the [Address Lookup API](Lookup.md) instead.
!!! danger "Deprecation warning"
The API can also be used with the URL
`https://nominatim.openstreetmap.org/reverse.php`. This is now deprecated
and will be removed in future versions.
## Parameters
This section lists additional parameters to further influence the output.
### Output format
* `format=[xml|json|jsonv2|geojson|geocodejson]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| format | one of: `xml`, `json`, `jsonv2`, `geojson`, `geocodejson` | `xml` |
See [Place Output Formats](Output.md) for details on each format. (Default: xml)
See [Place Output Formats](Output.md) for details on each format.
* `json_callback=<string>`
Wrap JSON output in a callback function ([JSONP](https://en.wikipedia.org/wiki/JSONP)) i.e. `<string>(<json>)`.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| json_callback | function name | _unset_ |
When given, 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.
Only has an effect for JSON output formats.
### Output details
* `addressdetails=[0|1]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| addressdetails | 0 or 1 | 1 |
Include a breakdown of the address into elements. (Default: 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.
!!! tip
If you are interested in a stable classification of address categories
(suburb, city, state, etc), have a look at the `geocodejson` format.
All other formats return classifications according to OSM tagging.
There is a much larger set of categories and they are not always consistent,
which makes them very hard to work with.
* `extratags=[0|1]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| extratags | 0 or 1 | 0 |
Include additional information in the result if available,
e.g. wikipedia link, opening hours. (Default: 0)
When set to 1, the response include any additional information in the result
that is available in the database, e.g. wikipedia link, opening hours.
* `namedetails=[0|1]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| namedetails | 0 or 1 | 0 |
Include a list of alternative names in the results. These may include
language variants, references, operator and brand. (Default: 0)
When set to 1, include a full list of names for the result. These may include
language variants, older names, references and brand.
### Language of results
* `accept-language=<browser language string>`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| accept-language | browser language string | content of "Accept-Language" HTTP header |
Preferred language order for showing search results, overrides the value
specified in the "Accept-Language" HTTP header.
Either use a standard RFC2616 accept-language string or a simple
comma-separated list of language codes.
Preferred language order for showing search results. This may either be
a simple comma-separated list of language codes or have the same format
as the ["Accept-Language" HTTP header](https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Accept-Language).
### Result limitation
!!! tip
First-time users of Nominatim tend to be confused that they get different
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 contrary always
send the currently chosen browser language.
* `zoom=[0-18]`
Level of detail required for the address. Default: 18. This is a number that
### Result restriction
| Parameter | Value | Default |
|-----------| ----- | ------- |
| zoom | 0-18 | 18 |
Level of detail required for the address. This is a number that
corresponds roughly to the zoom level used in XYZ tile sources in frameworks
like Leaflet.js, Openlayers etc.
In terms of address details the zoom levels are as follows:
@@ -92,41 +136,81 @@ In terms of address details the zoom levels are as follows:
5 | state
8 | county
10 | city
14 | suburb
12 | town / borough
13 | village / suburb
14 | neighbourhood
15 | any settlement
16 | major streets
17 | major and minor streets
18 | building
| Parameter | Value | Default |
|-----------| ----- | ------- |
| layer | comma-separated list of: `address`, `poi`, `railway`, `natural`, `manmade` | _unset_ (no restriction) |
**`[Python-only]`**
The layer filter allows to select places by themes.
The `address` layer contains all places that make up an address:
address points with house numbers, streets, inhabited places (suburbs, villages,
cities, states etc.) and administrative boundaries.
The `poi` layer selects all point of interest. This includes classic points
of interest like restaurants, shops, hotels but also less obvious features
like recycling bins, guideposts or benches.
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 features like rivers, lakes and mountains while
the `manmade` layer functions as a catch-all for features not covered by the
other layers.
### Polygon output
* `polygon_geojson=1`
* `polygon_kml=1`
* `polygon_svg=1`
* `polygon_text=1`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| polygon_geojson | 0 or 1 | 0 |
| polygon_kml | 0 or 1 | 0 |
| polygon_svg | 0 or 1 | 0 |
| polygon_text | 0 or 1 | 0 |
Output geometry of results as a GeoJSON, KML, SVG or WKT. Only one of these
options can be used at a time. (Default: 0)
Add the full geometry of the place to the result output. Output formats
in GeoJSON, KML, SVG or WKT are supported. Only one of these
options can be used at a time.
* `polygon_threshold=0.0`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| polygon_threshold | floating-point number | 0.0 |
Return a simplified version of the output geometry. The parameter is the
When one of the polygon_* outputs is chosen, return a simplified version
of the output geometry. The parameter describes the
tolerance in degrees with which the geometry may differ from the original
geometry. Topology is preserved in the result. (Default: 0.0)
geometry. Topology is preserved in the geometry.
### Other
* `email=<valid email address>`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| email | valid email address | _unset_ |
If you are making a large number of requests, please include an appropriate email
address to identify your requests. See Nominatim's [Usage Policy](https://operations.osmfoundation.org/policies/nominatim/) for more details.
If you are making large numbers of request please include an appropriate email
address to identify your requests. See Nominatim's
[Usage Policy](https://operations.osmfoundation.org/policies/nominatim/) for more details.
* `debug=[0|1]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| debug | 0 or 1 | 0 |
Output assorted developer debug information. Data on internals of Nominatim's
"Search Loop" logic, and SQL queries. The output is (rough) HTML format.
This overrides the specified machine readable format. (Default: 0)
"search loop" logic, and SQL queries. The output is HTML format.
This overrides the specified machine readable format.
## Examples

View File

@@ -8,12 +8,12 @@ The search query may also contain
which are translated into specific OpenStreetMap (OSM) tags (e.g. Pub => `amenity=pub`).
This can be used to narrow down the kind of objects to be returned.
!!! warning
!!! note
Special phrases are not suitable to query all objects of a certain type in an
area. Nominatim will always just return a collection of the best matches. To
download OSM data by object type, use the [Overpass API](https://overpass-api.de/).
## Parameters
## Endpoint
The search API has the following format:
@@ -21,35 +21,62 @@ The search API has the following format:
https://nominatim.openstreetmap.org/search?<params>
```
The search term may be specified with two different sets of parameters:
!!! danger "Deprecation warning"
The API can also be used with the URL
`https://nominatim.openstreetmap.org/search.php`. This is now deprecated
and will be removed in future versions.
* `q=<query>`
The query term can be given in two different forms: free-form or structured.
Free-form query string to search for.
Free-form queries are processed first left-to-right and then right-to-left if that fails. So you may search for
[pilkington avenue, birmingham](https://nominatim.openstreetmap.org/search?q=pilkington+avenue,birmingham) as well as for
[birmingham, pilkington avenue](https://nominatim.openstreetmap.org/search?q=birmingham,+pilkington+avenue).
Commas are optional, but improve performance by reducing the complexity of the search.
### Free-form query
| Parameter | Value |
|-----------| ----- |
| q | Free-form query string to search for |
* `street=<housenumber> <streetname>`
* `city=<city>`
* `county=<county>`
* `state=<state>`
* `country=<country>`
* `postalcode=<postalcode>`
In this form, the query can be unstructured.
Free-form queries are processed first left-to-right and then right-to-left if that fails. So you may search for
[pilkington avenue, birmingham](https://nominatim.openstreetmap.org/search?q=pilkington+avenue,birmingham) as well as for
[birmingham, pilkington avenue](https://nominatim.openstreetmap.org/search?q=birmingham,+pilkington+avenue).
Commas are optional, but improve performance by reducing the complexity of the search.
Alternative query string format split into several parameters for structured requests.
Structured requests are faster but are less robust against alternative
OSM tagging schemas. **Do not combine with** `q=<query>` **parameter**.
The free-form may also contain special phrases to describe the type of
place to be returned or a coordinate to search close to a position.
Both query forms accept the additional parameters listed below.
### Structured query
| Parameter | Value |
|----------- | ----- |
| amenity | name and/or type of POI |
| street | housenumber and streetname |
| city | city |
| county | county |
| state | state |
| country | country |
| postalcode | postal code |
The structured form of the search query allows to lookup up an address
that is already split into its components. Each parameter represents a field
of the address. All parameters are optional. You should only use the ones
that are relevant for the address you want to geocode.
!!! Attention
Cannot be combined with the `q=<query>` parameter. Newer versions of
the API will return an error if you do so. Older versions simply return
unexpected results.
## Parameters
The following parameters can be used to further restrict the search and
change the output. They are usable for both forms of the search query.
### Output format
* `format=[xml|json|jsonv2|geojson|geocodejson]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| format | one of: `xml`, `json`, `jsonv2`, `geojson`, `geocodejson` | `jsonv2` |
See [Place Output Formats](Output.md) for details on each format. (Default: jsonv2)
See [Place Output Formats](Output.md) for details on each format.
!!! note
The Nominatim service at
@@ -57,52 +84,150 @@ See [Place Output Formats](Output.md) for details on each format. (Default: json
has a different default behaviour for historical reasons. When the
`format` parameter is omitted, the request will be forwarded to the Web UI.
* `json_callback=<string>`
Wrap JSON output in a callback function ([JSONP](https://en.wikipedia.org/wiki/JSONP)) i.e. `<string>(<json>)`.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| json_callback | function name | _unset_ |
When given, 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.
Only has an effect for JSON output formats.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| limit | number | 10 |
Limit the maximum number of returned results. Cannot be more than 40.
Nominatim may decide to return less results than given, if additional
results do not sufficiently match the query.
### Output details
* `addressdetails=[0|1]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| addressdetails | 0 or 1 | 0 |
Include a breakdown of the address into elements. (Default: 0)
When set to 1, include a breakdown of the address into elements.
The exact content of the address breakdown depends on the output format.
!!! tip
If you are interested in a stable classification of address categories
(suburb, city, state, etc), have a look at the `geocodejson` format.
All other formats return classifications according to OSM tagging.
There is a much larger set of categories and they are not always consistent,
which makes them very hard to work with.
* `extratags=[0|1]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| extratags | 0 or 1 | 0 |
Include additional information in the result if available,
e.g. wikipedia link, opening hours. (Default: 0)
When set to 1, the response include any additional information in the result
that is available in the database, e.g. wikipedia link, opening hours.
* `namedetails=[0|1]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| namedetails | 0 or 1 | 0 |
Include a list of alternative names in the results. These may include
language variants, references, operator and brand. (Default: 0)
When set to 1, include a full list of names for the result. These may include
language variants, older names, references and brand.
### Language of results
* `accept-language=<browser language string>`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| accept-language | browser language string | content of "Accept-Language" HTTP header |
Preferred language order for showing search results, overrides the value
specified in the ["Accept-Language" HTTP header](https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Accept-Language).
Either use a standard RFC2616 accept-language string or a simple
comma-separated list of language codes.
Preferred language order for showing search results. This may either be
a simple comma-separated list of language codes or have the same format
as the ["Accept-Language" HTTP header](https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Accept-Language).
### Result limitation
!!! tip
First-time users of Nominatim tend to be confused that they get different
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 contrary always
send the currently chosen browser language.
* `countrycodes=<countrycode>[,<countrycode>][,<countrycode>]...`
### Result restriction
Limit search results to one or more countries. `<countrycode>` must be the
[ISO 3166-1alpha2](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) code,
e.g. `gb` for the United Kingdom, `de` for Germany.
There are two ways to influence the results. *Filters* exclude certain
kinds of results completely. *Boost parameters* only change the order of the
results and thus give a preference to some results over others.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| countrycodes | comma-separated list of country codes | _unset_ |
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.
Each place in Nominatim is assigned to one country code based
on OSM country boundaries. In rare cases a place may not be in any country
at all, for example, in international waters.
at all, for example, when it is in international waters. These places are
also excluded when the filter is set.
* `exclude_place_ids=<place_id,[place_id],[place_id]`
!!! Note
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 preferred. Having both parameters
in the same query will work. If the parameters contradict each other,
the search will come up empty.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| layer | comma-separated list of: `address`, `poi`, `railway`, `natural`, `manmade` | _unset_ (no restriction) |
**`[Python-only]`**
The layer filter allows to select places by themes.
The `address` layer contains all places that make up an address:
address points with house numbers, streets, inhabited places (suburbs, villages,
cities, states tec.) and administrative boundaries.
The `poi` layer selects all point of interest. This includes classic POIs like
restaurants, shops, hotels but also less obvious features like recycling bins,
guideposts or benches.
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 features like rivers, lakes and mountains while
the `manmade` layer functions as a catch-all for features not covered by the
other layers.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| featureType | one of: `country`, `state`, `city`, `settlement` | _unset_ |
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
'neighbourhood'.
When featureType is set, then results are automatically restricted
to the address layer (see above).
!!! tip
Instead of using the featureType filters `country`, `state` or `city`,
you can also use a structured query without the finer-grained parameters
amenity or street.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| 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.
@@ -110,180 +235,212 @@ This can be used to retrieve additional search results. For example, if a
previous query only returned a few results, then including those here would
cause the search to return other, less accurate, matches (if possible).
| Parameter | Value | Default |
|-----------| ----- | ------- |
| viewbox | `<x1>,<y1>,<x2>,<y2>` | _unset_ |
* `limit=<integer>`
Boost parameter which focuses the search on the given area.
Any two corner points of the box are accepted as long as they make a proper
box. `x` is longitude, `y` is latitude.
Limit the number of returned results. (Default: 10, Maximum: 50)
| Parameter | Value | Default |
|-----------| ----- | ------- |
| bounded | 0 or 1 | 0 |
When set to 1, then it turns the 'viewbox' parameter (see above) into
a filter parameter, excluding any results outside the viewbox.
* `viewbox=<x1>,<y1>,<x2>,<y2>`
The preferred area to find search results. Any two corner points of the box
are accepted as long as they span a real box. `x` is longitude,
`y` is latitude.
* `bounded=[0|1]`
When a viewbox is given, restrict the result to items contained within that
viewbox (see above). When `viewbox` and `bounded=1` are given, an amenity
only search is allowed. Give the special keyword for the amenity in square
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
brackets, e.g. `[pub]` and a selection of objects of this type is returned.
There is no guarantee that the result is complete. (Default: 0)
There is no guarantee that the result returns all objects in the area.
### Polygon output
* `polygon_geojson=1`
* `polygon_kml=1`
* `polygon_svg=1`
* `polygon_text=1`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| polygon_geojson | 0 or 1 | 0 |
| polygon_kml | 0 or 1 | 0 |
| polygon_svg | 0 or 1 | 0 |
| polygon_text | 0 or 1 | 0 |
Output geometry of results as a GeoJSON, KML, SVG or WKT. Only one of these
options can be used at a time. (Default: 0)
Add the full geometry of the place to the result output. Output formats
in GeoJSON, KML, SVG or WKT are supported. Only one of these
options can be used at a time.
* `polygon_threshold=0.0`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| polygon_threshold | floating-point number | 0.0 |
Return a simplified version of the output geometry. The parameter is the
When one of the polygon_* outputs is chosen, return a simplified version
of the output geometry. The parameter describes the
tolerance in degrees with which the geometry may differ from the original
geometry. Topology is preserved in the result. (Default: 0.0)
geometry. Topology is preserved in the geometry.
### Other
* `email=<valid email address>`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| email | valid email address | _unset_ |
If you are making large numbers of request please include an appropriate email
address to identify your requests. See Nominatim's [Usage Policy](https://operations.osmfoundation.org/policies/nominatim/) for more details.
address to identify your requests. See Nominatim's
[Usage Policy](https://operations.osmfoundation.org/policies/nominatim/) for more details.
* `dedupe=[0|1]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| dedupe | 0 or 1 | 1 |
Sometimes you have several objects in OSM identifying the same place or
object in reality. The simplest case is a street being split into many
different OSM ways due to different characteristics. Nominatim will
attempt to detect such duplicates and only return one match unless
this parameter is set to 0. (Default: 1)
attempt to detect such duplicates and only return one match. Setting
this parameter to 0 disables this deduplication mechanism and
ensures that all results are returned.
* `debug=[0|1]`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| debug | 0 or 1 | 0 |
Output assorted developer debug information. Data on internals of Nominatim's
"Search Loop" logic, and SQL queries. The output is (rough) HTML format.
This overrides the specified machine readable format. (Default: 0)
"search loop" logic, and SQL queries. The output is HTML format.
This overrides the specified machine readable format.
## Examples
##### XML with kml polygon
##### XML with KML polygon
* [https://nominatim.openstreetmap.org/search?q=135+pilkington+avenue,+birmingham&format=xml&polygon_geojson=1&addressdetails=1](https://nominatim.openstreetmap.org/search?q=135+pilkington+avenue,+birmingham&format=xml&polygon_geojson=1&addressdetails=1)
* [https://nominatim.openstreetmap.org/search?q=135+pilkington+avenue,+birmingham&format=xml&polygon_kml=1&addressdetails=1](https://nominatim.openstreetmap.org/search?q=135+pilkington+avenue,+birmingham&format=xml&polygon_kml=1&addressdetails=1)
```xml
<searchresults timestamp="Sat, 07 Nov 09 14:42:10 +0000" querystring="135 pilkington, avenue birmingham" polygon="true">
<place
place_id="1620612" osm_type="node" osm_id="452010817"
boundingbox="52.548641204834,52.5488433837891,-1.81612110137939,-1.81592094898224"
lat="52.5487429714954" lon="-1.81602098644987"
display_name="135, Pilkington Avenue, Wylde Green, City of Birmingham, West Midlands (county), B72, United Kingdom"
class="place" type="house">
<geokml>
<Polygon>
<outerBoundaryIs>
<LinearRing>
<coordinates>-1.816513,52.548756599999997 -1.816434,52.548747300000002 -1.816429,52.5487629 -1.8163717,52.548756099999999 -1.8163464,52.548834599999999 -1.8164599,52.548848100000001 -1.8164685,52.5488213 -1.8164913,52.548824000000003 -1.816513,52.548756599999997</coordinates>
</LinearRing>
</outerBoundaryIs>
</Polygon>
</geokml>
<house_number>135</house_number>
<road>Pilkington Avenue</road>
<village>Wylde Green</village>
<town>Sutton Coldfield</town>
<city>City of Birmingham</city>
<county>West Midlands (county)</county>
<postcode>B72</postcode>
<country>United Kingdom</country>
<country_code>gb</country_code>
</place>
</searchresults>
<?xml version="1.0" encoding="UTF-8" ?>
<searchresults timestamp="Tue, 08 Aug 2023 15:45:41 +00:00"
attribution="Data © OpenStreetMap contributors, ODbL 1.0. http://osm.org/copyright"
querystring="135 pilkington avenue, birmingham"
more_url="https://nominatim.openstreetmap.org/search?q=135+pilkington+avenue%2C+birmingham&amp;polygon_kml=1&amp;addressdetails=1&amp;limit=20&amp;exclude_place_ids=125279639&amp;format=xml"
exclude_place_ids="125279639">
<place place_id="125279639"
osm_type="way"
osm_id="90394480"
lat="52.5487921"
lon="-1.8164308"
boundingbox="52.5487473,52.5488481,-1.8165130,-1.8163464"
place_rank="30"
address_rank="30"
display_name="135, Pilkington Avenue, Maney, Sutton Coldfield, Wylde Green, Birmingham, West Midlands Combined Authority, England, B72 1LH, United Kingdom"
class="building"
type="residential"
importance="9.999999994736442e-08">
<geokml>
<Polygon>
<outerBoundaryIs>
<LinearRing>
<coordinates>-1.816513,52.5487566 -1.816434,52.5487473 -1.816429,52.5487629 -1.8163717,52.5487561 -1.8163464,52.5488346 -1.8164599,52.5488481 -1.8164685,52.5488213 -1.8164913,52.548824 -1.816513,52.5487566</coordinates>
</LinearRing>
</outerBoundaryIs>
</Polygon>
</geokml>
<house_number>135</house_number>
<road>Pilkington Avenue</road>
<hamlet>Maney</hamlet>
<town>Sutton Coldfield</town>
<village>Wylde Green</village>
<city>Birmingham</city>
<ISO3166-2-lvl8>GB-BIR</ISO3166-2-lvl8>
<state_district>West Midlands Combined Authority</state_district>
<state>England</state>
<ISO3166-2-lvl4>GB-ENG</ISO3166-2-lvl4>
<postcode>B72 1LH</postcode>
<country>United Kingdom</country>
<country_code>gb</country_code>
</place>
</searchresults>
```
##### JSON with SVG polygon
[https://nominatim.openstreetmap.org/search/Unter%20den%20Linden%201%20Berlin?format=json&addressdetails=1&limit=1&polygon_svg=1](https://nominatim.openstreetmap.org/search/Unter%20den%20Linden%201%20Berlin?format=json&addressdetails=1&limit=1&polygon_svg=1)
[https://nominatim.openstreetmap.org/search?q=Unter%20den%20Linden%201%20Berlin&format=json&addressdetails=1&limit=1&polygon_svg=1](https://nominatim.openstreetmap.org/search?q=Unter%20den%20Linden%201%20Berlin&format=json&addressdetails=1&limit=1&polygon_svg=1)
```json
{
"address": {
"city": "Berlin",
"city_district": "Mitte",
"construction": "Unter den Linden",
"continent": "European Union",
"country": "Deutschland",
"country_code": "de",
"house_number": "1",
"neighbourhood": "Scheunenviertel",
"postcode": "10117",
"public_building": "Kommandantenhaus",
"state": "Berlin",
"suburb": "Mitte"
},
"boundingbox": [
"52.5170783996582",
"52.5173187255859",
"13.3975105285645",
"13.3981599807739"
],
"class": "amenity",
"display_name": "Kommandantenhaus, 1, Unter den Linden, Scheunenviertel, Mitte, Berlin, 10117, Deutschland, European Union",
"importance": 0.73606775332943,
"lat": "52.51719785",
"licence": "Data \u00a9 OpenStreetMap contributors, ODbL 1.0. https://www.openstreetmap.org/copyright",
"lon": "13.3978352028938",
"osm_id": "15976890",
"osm_type": "way",
"place_id": "30848715",
"svg": "M 13.397511 -52.517283599999999 L 13.397829400000001 -52.517299800000004 13.398131599999999 -52.517315099999998 13.398159400000001 -52.517112099999999 13.3975388 -52.517080700000001 Z",
"type": "public_building"
}
[
{
"address": {
"ISO3166-2-lvl4": "DE-BE",
"borough": "Mitte",
"city": "Berlin",
"country": "Deutschland",
"country_code": "de",
"historic": "Kommandantenhaus",
"house_number": "1",
"neighbourhood": "Friedrichswerder",
"postcode": "10117",
"road": "Unter den Linden",
"suburb": "Mitte"
},
"boundingbox": [
"52.5170798",
"52.5173311",
"13.3975116",
"13.3981577"
],
"class": "historic",
"display_name": "Kommandantenhaus, 1, Unter den Linden, Friedrichswerder, Mitte, Berlin, 10117, Deutschland",
"importance": 0.8135042058306902,
"lat": "52.51720765",
"licence": "Data © OpenStreetMap contributors, ODbL 1.0. https://osm.org/copyright",
"lon": "13.397834399325466",
"osm_id": 15976890,
"osm_type": "way",
"place_id": 108681845,
"svg": "M 13.3975116 -52.5172905 L 13.397549 -52.5170798 13.397715 -52.5170906 13.3977122 -52.5171064 13.3977392 -52.5171086 13.3977417 -52.5170924 13.3979655 -52.5171069 13.3979623 -52.5171233 13.3979893 -52.5171248 13.3979922 -52.5171093 13.3981577 -52.5171203 13.398121 -52.5173311 13.3978115 -52.5173103 Z",
"type": "house"
}
]
```
##### JSON with address details
[https://nominatim.openstreetmap.org/?addressdetails=1&q=bakery+in+berlin+wedding&format=json&limit=1](https://nominatim.openstreetmap.org/?addressdetails=1&q=bakery+in+berlin+wedding&format=json&limit=1)
[https://nominatim.openstreetmap.org/search?addressdetails=1&q=bakery+in+berlin+wedding&format=jsonv2&limit=1](https://nominatim.openstreetmap.org/search?addressdetails=1&q=bakery+in+berlin+wedding&format=jsonv2&limit=1)
```json
{
"address": {
"bakery": "B\u00e4cker Kamps",
"city_district": "Mitte",
"continent": "European Union",
"country": "Deutschland",
"country_code": "de",
"footway": "Bahnsteig U6",
"neighbourhood": "Sprengelkiez",
"postcode": "13353",
"state": "Berlin",
"suburb": "Wedding"
},
"boundingbox": [
"52.5460929870605",
"52.5460968017578",
"13.3591794967651",
"13.3591804504395"
],
"class": "shop",
"display_name": "B\u00e4cker Kamps, Bahnsteig U6, Sprengelkiez, Wedding, Mitte, Berlin, 13353, Deutschland, European Union",
"icon": "https://nominatim.openstreetmap.org/images/mapicons/shopping_bakery.p.20.png",
"importance": 0.201,
"lat": "52.5460941",
"licence": "Data \u00a9 OpenStreetMap contributors, ODbL 1.0. https://www.openstreetmap.org/copyright",
"lon": "13.35918",
"osm_id": "317179427",
"osm_type": "node",
"place_id": "1453068",
"type": "bakery"
}
[
{
"address": {
"ISO3166-2-lvl4": "DE-BE",
"borough": "Mitte",
"city": "Berlin",
"country": "Deutschland",
"country_code": "de",
"neighbourhood": "Sprengelkiez",
"postcode": "13347",
"road": "Lindower Straße",
"shop": "Ditsch",
"suburb": "Wedding"
},
"addresstype": "shop",
"boundingbox": [
"52.5427201",
"52.5427654",
"13.3668619",
"13.3669442"
],
"category": "shop",
"display_name": "Ditsch, Lindower Straße, Sprengelkiez, Wedding, Mitte, Berlin, 13347, Deutschland",
"importance": 9.99999999995449e-06,
"lat": "52.54274275",
"licence": "Data © OpenStreetMap contributors, ODbL 1.0. http://osm.org/copyright",
"lon": "13.36690305710228",
"name": "Ditsch",
"osm_id": 437595031,
"osm_type": "way",
"place_id": 204751033,
"place_rank": 30,
"type": "bakery"
}
]
```
##### GeoJSON

View File

@@ -1,35 +1,50 @@
# Status
Useful for checking if the service and database is running. The JSON output also shows
Report on the state of the service and database. Useful for checking if the
service is up and running. The JSON output also reports
when the database was last updated.
## Endpoint
The status API has the following format:
```
https://nominatim.openstreetmap.org/status
```
!!! danger "Deprecation warning"
The API can also be used with the URL
`https://nominatim.openstreetmap.org/status.php`. This is now deprecated
and will be removed in future versions.
## Parameters
* `format=[text|json]` (defaults to 'text')
The status endpoint takes a single optional parameter:
| Parameter | Value | Default |
|-----------| ----- | ------- |
| format | one of: `text`, `json` | 'text' |
Selects the output format. See below.
## Output
#### Text format
```
https://nominatim.openstreetmap.org/status.php
```
When everything is okay, a status code 200 is returned and a simple message: `OK`
will return HTTP status code 200 and print `OK`.
On error it will return HTTP status code 500 and print a message, e.g.
On error it will return HTTP status code 500 and print a detailed error message, e.g.
`ERROR: Database connection failed`.
#### JSON format
```
https://nominatim.openstreetmap.org/status.php?format=json
```
Always returns a HTTP code 200, when the status call could be executed.
will return HTTP code 200 and a structure
On success a JSON dictionary with the following structure is returned:
```json
{
@@ -45,8 +60,8 @@ The `software_version` field contains the version of Nominatim used to serve
the API. The `database_version` field contains the version of the data format
in the database.
On error will also return HTTP status code 200 and a structure with error
code and message, e.g.
On error will return a shorter JSON dictionary with the error message
and status only, e.g.
```json
{
@@ -54,13 +69,3 @@ code and message, e.g.
"message": "Database connection failed"
}
```
Possible status codes are
| | message | notes |
|-----|----------------------|---------------------------------------------------|
| 700 | "No database" | connection failed |
| 701 | "Module failed" | database could not load nominatim.so |
| 702 | "Module call failed" | nominatim.so loaded but calling a function failed |
| 703 | "Query failed" | test query against a database table failed |
| 704 | "No value" | test query worked but returned no results |

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

@@ -1,149 +1,439 @@
## Configuring the Import
Which OSM objects are added to the database and which of the tags are used
can be configured via the import style configuration file. This
is a JSON file which contains a list of rules which are matched against every
tag of every object and then assign the tag its specific role.
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.
The style to use is given by the `NOMINATIM_IMPORT_STYLE` configuration
option. There are a number of default styles, which are explained in detail
in the [Import section](../admin/Import.md#filtering-imported-data). These
standard styles may be referenced by their name.
There are a number of default configurations for the flex style which
result in geocoding databases 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>.style`
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`).
The remainder of the page describes the format of the file.
The remainder of the page describes how the flex style works and how to
customize it.
### Configuration Rules
### The `flex-base.lua` module
A single rule looks like this:
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
how OSM tags are used by Nominatim.
Every custom style should 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')
```json
{
"keys" : ["key1", "key2", ...],
"values" : {
"value1" : "prop",
"value2" : "prop1,prop2"
}
}
```
A rule first defines a list of keys to apply the rule to. This is always a list
of strings. The string may have four forms. An empty string matches against
any key. 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 constitutes an exact match.
The following sections explain how the module can be customized.
The second part of the rules defines a list of values and the properties that
apply to a successful match. Value strings may be either empty, which
means that they match any value, or describe an exact match. Prefix
or suffix matching of values is not possible.
For a rule to match, it has to find a valid combination of keys and values. The
resulting property is that of the matched values.
### Changing the recognized tags
The rules in a configuration file are processed sequentially and the first
match for each tag wins.
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.
A rule where key and value are the empty string is special. This defines the
fallback when none of the rules match. The fallback is always used as a last
resort when nothing else matches, no matter where the rule appears in the file.
Defining multiple fallback rules is not allowed. What happens in this case,
is undefined.
!!! 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')`.
### Tag Properties
Many 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.
One or more of the following properties may be given for each tag:
* `main`
#### `set_main_tags()` - principal tags
A principal tag. A new row will be added for the object with key and value
as `class` and `type`.
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.
* `with_name`
The flex script distinguishes between four types of main tags:
When the tag is a principal tag (`main` property set): only really add a new
row, if there is any name tag found (a reference tag is not sufficient, see
below).
* __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.
* `with_name_key`
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.
When the tag is a principal tag (`main` property set): only really add a new
row, if there is also a name tag that matches the key of the principal tag.
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.
!!! example
``` lua
local flex = require('import-full')
* `fallback`
flex.set_main_tags{
boundary = {administrative = 'named'},
highway = {'always', street_lamp = 'named'},
landuse = 'fallback'
}
```
When the tag is a principal tag (`main` property set): only really add a new
row, when no other principal tags for this object have been found. Only one
fallback tag can win for an object.
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.
* `operator`
When the tag is a principal tag (`main` property set): also include the
`operator` tag in the list of names. This is a special construct for an
out-dated tagging practise in OSM. Fuel stations and chain restaurants
in particular used to have the name of the chain tagged as `operator`.
These days the chain can be more commonly found in the `brand` tag but
there is still enough old data around to warrant this special case.
#### `set_prefilters()` - ignoring tags
* `name`
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.
Add tag to the list of names.
`set_prefilters()` takes a table with four optional fields:
* `ref`
* __delete_keys__ is a _key match list_ for tags that should be deleted
* __delete_tags__ contains a table of tag keys pointing to a list of tag
values. Tags with matching key/value pairs are deleted.
* __extra_keys__ is a _key match list_ for tags which should be saved into
extratags
* __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.
Add tag to the list of names as a reference. At the moment this only means
that the object is not considered to be named for `with_name`.
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.
* `address`
!!! example
``` lua
local flex = require('import-full')
Add tag to the list of address tags. If the tag starts with `addr:` or
`is_in:`, then this prefix is cut off before adding it to the list.
flex.set_prefilters{
delete_keys = {'source', 'source:*'},
extra_tags = {amenity = {'yes', 'no'}}
}
flex.set_main_tags{
amenity = 'always'
}
```
* `postcode`
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.
Add the value as a postcode to the address tags. If multiple tags are
candidate for postcodes, one wins out and the others are dropped.
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.
* `country`
#### `set_name_tags()` - defining names
Add the value as a country code to the address tags. The value must be a
two letter country code, otherwise it is ignored. If there are multiple
tags that match, then one wins out and the others are dropped.
The flex script distinguishes between two kinds of names:
* `house`
* __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.
If no principle tags can be found for the object, still add the object with
`class`=`place` and `type`=`house`. Use this for address nodes that have no
other function.
`set_name_tags()` takes a table with two optional fields `main` and `extra`.
They take _key match lists_ for main and extra names respectively.
* `interpolation`
!!! example
``` lua
local flex = require('flex-base')
Add this object as an address interpolation (appears as `class`=`place` and
`type`=`houses` in the database).
flex.set_main_tags{highway = {traffic_light = 'named'}}
flex.set_name_tags{main = {'name', 'name:*'},
extra = {'ref'}
}
```
* `extra`
This example creates a search index over traffic lights but will
only include those that have a common name and not those which just
have some reference ID from the city.
Add tag to the list of extra tags.
#### `set_address_tags()` - defining address parts
* `skip`
Address tags will be used to build up the address of an object.
Skip the tag completely. Useful when a custom default fallback is defined
or to define exceptions to rules.
`set_address_tags()` takes a table with arbitrary fields pointing to
_key match lists_. Two fields have a special meaning:
A rule can define as many of these properties for one match as it likes. For
example, if the property is `"main,extra"` then the tag will open a new row
but also have the tag appear in the list of extra 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.
* __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.
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.
Country tags are handled slightly special. Only tags with a two-letter code
are accepted, all other values are discarded.
!!! example
``` lua
local flex = require('import-full')
flex.set_address_tags{
main = {'addr:housenumber'},
extra = {'addr:*'},
postcode = {'postal_code', 'postcode', 'addr:postcode'},
country = {'country_code', 'ISO3166-1'}
}
```
In this example all tags which begin with `addr:` will be saved in
the address tag list. If one of the tags is `addr:housenumber`, the
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
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.
#### `set_unused_handling()` - processing remaining tags
This function 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.
!!! example
``` lua
local flex = require('import-full')
flex.set_address_tags{
main = {'addr:housenumber'},
extra = {'addr:*', 'tiger:county'}
}
flex.set_unused_handling{delete_keys = {'tiger:*'}}
```
In this example all remaining tags except those beginning with `tiger:`
are moved to the extratags list. Note that it is not possible to
already delete the tiger tags with `set_prefilters()` because that
would remove tiger:county before the address tags are processed.
### 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
The default scripts only allows relations of type `multipolygon`, `boundary`
and `waterway`. 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 (Multi)LineString from the ways in
the relations. Ways are combined as much as possible without any regards
to their order in the relation.
!!! Example
``` lua
local flex = require('import-full')
flex.RELATION_TYPES['site'] = flex.relation_as_multipolygon
```
With this line relations of `type=site` will be included in the index
according to main tags found. This only works when the site relation
resolves to a valid area. Nodes in the site relation are not part of the
geometry.
#### 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
to implement your own processing functions with some additional processing
logic.
!!! Example
``` lua
local flex = require('import-full')
function osm2pgsql.process_relation(object)
if object.tags.boundary ~= 'administrative' or object.tags.admin_level ~= '2' then
flex.process_relation(object)
end
end
```
This example discards all country-level boundaries and uses standard
handling for everything else. This can be useful if you want to use
your own custom country boundaries.
### 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.
!!! Example
``` lua
local flex = require('import-full')
local original_process_tags = flex.process_tags
function flex.process_tags(o)
if o.object.tags.highway ~= nil and o.object.tags.access == 'no' then
return
end
original_process_tags(o)
end
```
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.
#### The `Place` class
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.
The Place class has some attributes which you may access read-only:
* __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
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

View File

@@ -0,0 +1,55 @@
## Importance
Search requests can yield multiple results which match equally well with
the original query. In such case Nominatim needs to order the results
according to a different criterion: importance. This is a measure for how
likely it is that a user will search for a given place. This section explains
the sources Nominatim uses for computing importance of a place and how to
customize them.
### How importance is computed
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
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
functions as a tie-breaker between places with very similar primary
importance values.
nominatim.org has preprocessed importance tables for the
[primary Wikipedia rankings](https://nominatim.org/data/wikimedia-importance.sql.gz)
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
The secondary importance is implemented as a simple
[Postgis raster](https://postgis.net/docs/raster.html) table, where Nominatim
looks up the value for the coordinates of the centroid of a place. You can
provide your own secondary importance raster in form of an SQL file named
`secondary_importance.sql.gz` in your project directory.
The SQL file needs to drop and (re)create a table `secondary_importance` which
must as a minimum contain a column `rast` of type `raster`. The raster must
be in EPSG:4326 and contain 16bit unsigned ints
(`raster_constraint_pixel_types(rast) = '{16BUI}'). Any other columns in the
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 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 | [Locale](../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

@@ -91,7 +91,7 @@ The option is only used by the Legacy tokenizer and ignored otherwise.
| -------------- | --------------------------------------------------- |
| **Description:** | Tokenizer used for normalizing and parsing queries and names |
| **Format:** | string |
| **Default:** | legacy |
| **Default:** | icu |
| **After Changes:** | cannot be changed after import |
Sets the tokenizer type to use for the import. For more information on
@@ -552,6 +552,8 @@ used.
| **Format:** | boolean |
| **Default:** | no |
| **After Changes:** | run `nominatim refresh --website` |
| **Comment:** | PHP frontend only |
This feature is currently undocumented and potentially broken.
@@ -564,6 +566,7 @@ This feature is currently undocumented and potentially broken.
| **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
@@ -604,6 +607,88 @@ with a single query.
Setting this parameter to 0 disables polygon output completely.
#### NOMINATIM_SEARCH_WITHIN_COUNTRIES
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Disable search for elements that are not in the country grid |
| **Format:** | boolean |
| **Default:** | no |
| **After Changes:** | run `nominatim refresh --website` |
| **Comment:** | PHP frontend only |
Enable to search elements just within countries.
When enabled, if, despite not finding a point within the static grid of countries, it
finds a geometry of a region, do not return the geometry.
Return "Unable to geocode" instead.
#### NOMINATIM_SERVE_LEGACY_URLS
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Enable serving via URLs with a .php suffix |
| **Format:** | boolean |
| **Default:** | yes |
| **Comment:** | Python frontend only |
When enabled, then endpoints are reachable as `/<name>` as well as `/<name>.php`.
This can be useful when you want to be backwards-compatible with previous
versions of Nominatim.
#### NOMINATIM_API_POOL_SIZE
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Number of parallel database connections per worker |
| **Format:** | number |
| **Default:** | 10 |
| **Comment:** | Python frontend only |
Sets the maximum number of database connections available for a single instance
of Nominatim. When configuring the maximum number of connections that your
PostgreSQL database can handle, you need at least
`NOMINATIM_API_POOL_SIZE` * `<number of configured workers>` connections.
For configuring the number of workers, refer to the section about
[Deploying the Python frontend](../admin/Deployment-Python.md).
#### NOMINATIM_QUERY_TIMEOUT
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Timeout for SQL queries to the database |
| **Format:** | number (seconds) |
| **Default:** | 10 |
| **Comment:** | Python frontend only |
When this timeout is set, then all SQL queries that run longer than the
specified numbers of seconds will be cancelled and the user receives a
timeout exceptions. Users of the API see a 503 HTTP error.
The timeout does ont apply when using the
[low-level DB access](../library/Low-Level-DB-Access.md)
of the library. A timeout can be manually set, if required.
#### NOMINATIM_REQUEST_TIMEOUT
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Timeout for search queries |
| **Format:** | number (seconds) |
| **Default:** | 60 |
| **Comment:** | Python frontend only |
When this timeout is set, a search query will finish sending queries
to the database after the timeout has passed and immediately return the
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
@@ -643,7 +728,24 @@ The entries in the log file have the following format:
<request time> <execution time in s> <number of results> <type> "<query string>"
Request time is the time when the request was started. The execution time is
given in ms and corresponds to the time the query took executing in PHP.
given in seconds and corresponds to the time the query took executing in PHP.
type contains the name of the endpoint used.
Can be used as the same time as NOMINATIM_LOG_DB.
#### NOMINATIM_DEBUG_SQL
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Enable printing of raw SQL by SQLAlchemy |
| **Format:** | boolean |
| **Default:** | no |
| **Comment:** | **For developers only.** |
This settings enables
[SQL debugging](https://docs.sqlalchemy.org/en/20/core/engines.html#dbengine-logging)
by SQLAlchemy. This can be helpful when debugging some bugs with internal
query handling. It should only be used together with the CLI query functions.
Enabling it for server mode may have unintended consequences. Use the `debug`
parameter instead, which prints information on how the search is executed
including SQL statements.

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 [principal tags in import style](Import-Styles.md#set_main_tags-principal-tags)
* **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

@@ -17,6 +17,11 @@ they can be configured.
## Legacy tokenizer
!!! danger
The Legacy tokenizer is deprecated and will be removed in Nominatim 5.0.
If you still use a database with the legacy tokenizer, you must reimport
it using the ICU tokenizer below.
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
@@ -52,7 +57,7 @@ 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.
See [Advanced installations](../admin/Advanced-Installations.md#using-an-external-postgresql-database) for details.
There are no other configuration options for the legacy tokenizer. All
normalization functions are hard-coded.
@@ -102,7 +107,7 @@ Here is an example configuration file:
``` yaml
normalization:
- ":: lower ()"
- "ß > 'ss'" # German szet is unimbigiously equal to double ss
- "ß > 'ss'" # German szet is unambiguously equal to double ss
transliteration:
- !include /etc/nominatim/icu-rules/extended-unicode-to-asccii.yaml
- ":: Ascii ()"
@@ -128,7 +133,7 @@ The configuration file contains four sections:
The normalization and transliteration sections each define a set of
ICU rules that are applied to the names.
The **normalisation** rules are applied after sanitation. They should remove
The **normalization** rules are applied after sanitation. They should remove
any information that is not relevant for search at all. Usual rules to be
applied here are: lower-casing, removing of special characters, cleanup of
spaces.
@@ -175,44 +180,67 @@ The following is a list of sanitizers that are shipped with Nominatim.
##### split-name-list
::: nominatim.tokenizer.sanitizers.split_name_list
selection:
::: nominatim_db.tokenizer.sanitizers.split_name_list
options:
members: False
rendering:
heading_level: 6
docstring_section_style: spacy
##### strip-brace-terms
::: nominatim.tokenizer.sanitizers.strip_brace_terms
selection:
::: nominatim_db.tokenizer.sanitizers.strip_brace_terms
options:
members: False
rendering:
heading_level: 6
docstring_section_style: spacy
##### tag-analyzer-by-language
::: nominatim.tokenizer.sanitizers.tag_analyzer_by_language
selection:
::: nominatim_db.tokenizer.sanitizers.tag_analyzer_by_language
options:
members: False
rendering:
heading_level: 6
docstring_section_style: spacy
##### clean-housenumbers
::: nominatim.tokenizer.sanitizers.clean_housenumbers
selection:
::: nominatim_db.tokenizer.sanitizers.clean_housenumbers
options:
members: False
rendering:
heading_level: 6
docstring_section_style: spacy
##### clean-postcodes
::: nominatim.tokenizer.sanitizers.clean_postcodes
selection:
::: nominatim_db.tokenizer.sanitizers.clean_postcodes
options:
members: False
rendering:
heading_level: 6
docstring_section_style: spacy
##### clean-tiger-tags
::: nominatim_db.tokenizer.sanitizers.clean_tiger_tags
options:
members: False
heading_level: 6
docstring_section_style: spacy
#### delete-tags
::: nominatim_db.tokenizer.sanitizers.delete_tags
options:
members: False
heading_level: 6
docstring_section_style: spacy
#### tag-japanese
::: nominatim_db.tokenizer.sanitizers.tag_japanese
options:
members: False
heading_level: 6
docstring_section_style: spacy
#### Token Analysis
@@ -371,7 +399,7 @@ 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

@@ -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:
@@ -36,34 +36,60 @@ It has the following additional requirements:
* [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)
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)
The documentation is built with mkdocs:
* [mkdocs](https://www.mkdocs.org/) >= 1.1.2
* [mkdocstrings](https://mkdocstrings.github.io/) >= 0.16
* [mkdocstrings-python-legacy](https://mkdocstrings.github.io/python-legacy/)
* [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/)
Please be aware that tests always run against the globally installed
osm2pgsql, so you need to have this set up. If you want to test against
the vendored version of osm2pgsql, you need to set the PATH accordingly.
### 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.
In particular, pylint tends to have a lot of breaking changes between versions.
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 pylint \
mypy types-PyYAML types-jinja2 types-psycopg2 types-psutil
sudo apt install libsqlite3-mod-spatialite php-cli
```
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:
```sh
virtualenv ~/nominatim-dev-venv
~/nominatim-dev-venv/bin/pip install\
psutil psycopg[binary] PyICU SQLAlchemy \
python-dotenv jinja2 pyYAML datrie behave \
mkdocs mkdocstrings mkdocs-gen-files pytest pytest-asyncio pylint \
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
```
echo 'export PATH=~/.local/bin:$PATH' > ~/.profile
Now enter the virtual environment whenever you want to develop:
```sh
. ~/nominatim-dev-venv/bin/activate
```
For installing the PHP development tools, run:
```sh
sudo apt install php-cgi phpunit php-codesniffer
```
If your distribution does not have PHPUnit 7.3+, you can install it (as well
@@ -76,24 +102,47 @@ composer global require "phpunit/phpunit=8.*"
```
The binaries are found in `.config/composer/vendor/bin`. You need to add this
to your PATH as well:
to your PATH:
```
echo 'export PATH=~/.config/composer/vendor/bin:$PATH' > ~/.profile
```
### 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:
```
me@machine:~$ cd Nominatim
me@machine:~Nominatim$ ./nominatim-cli.py --version
Nominatim version 4.4.99-1
```
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).
@@ -104,18 +153,14 @@ 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
@@ -127,7 +172,7 @@ 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

@@ -52,9 +52,8 @@ the function.
### Sanitizer configuration
::: nominatim.tokenizer.sanitizers.config.SanitizerConfig
rendering:
show_source: no
::: nominatim_db.tokenizer.sanitizers.config.SanitizerConfig
options:
heading_level: 6
### The main filter function of the sanitizer
@@ -62,12 +61,10 @@ the function.
The filter function receives a single object of type `ProcessInfo`
which has with three members:
* `place`: read-only information about the place being processed.
* `place: PlaceInfo`: read-only information about the place being processed.
See PlaceInfo below.
* `names`: The current list of names for the place. Each name is a
PlaceName object.
* `address`: The current list of address names for the place. Each name
is a PlaceName object.
* `names: List[PlaceName]`: The current list of names for the place.
* `address: List[PlaceName]`: The current list of address names for the place.
While the `place` member is provided for information only, the `names` and
`address` lists are meant to be manipulated by the sanitizer. It may add and
@@ -76,17 +73,15 @@ adding extra attributes) or completely replace the list with a different one.
#### PlaceInfo - information about the place
::: nominatim.data.place_info.PlaceInfo
rendering:
show_source: no
::: nominatim_db.data.place_info.PlaceInfo
options:
heading_level: 6
#### PlaceName - extended naming information
::: nominatim.data.place_name.PlaceName
rendering:
show_source: no
::: nominatim_db.data.place_name.PlaceName
options:
heading_level: 6
@@ -134,7 +129,7 @@ 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
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.
@@ -144,15 +139,13 @@ They can be found in the directory
## Custom token analysis module
::: nominatim.tokenizer.token_analysis.base.AnalysisModule
rendering:
show_source: no
::: nominatim_db.tokenizer.token_analysis.base.AnalysisModule
options:
heading_level: 6
::: nominatim.tokenizer.token_analysis.base.Analyzer
rendering:
show_source: no
::: nominatim_db.tokenizer.token_analysis.base.Analyzer
options:
heading_level: 6
### Example: Creating acronym variants for long names

View File

@@ -10,7 +10,7 @@ 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.
This test directory is sturctured as follows:
This test directory is structured as follows:
```
-+- bdd Functional API tests
@@ -78,18 +78,19 @@ To run the functional tests, do
The tests can be configured with a set of environment variables (`behave -D key=val`):
* `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
module shared library file (only needed for legacy tokenizer)
* `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
@@ -120,23 +121,6 @@ and compromises the following data:
API tests should only be testing the functionality of the website PHP code.
Most tests should be formulated as BDD DB creation tests (see below) instead.
#### Code Coverage
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
@@ -153,7 +137,3 @@ needs superuser rights for postgres.
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.
Note that most testing of the gazetteer output of osm2pgsql is done in the tests
of osm2pgsql itself. The BDD tests are just there to ensure compatibility of
the osm2pgsql and Nominatim code.

View File

@@ -130,18 +130,18 @@ 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
rendering:
heading_level: 4
::: nominatim_db.tokenizer.base.AbstractTokenizer
options:
heading_level: 6
### Python Analyzer Class
::: nominatim.tokenizer.base.AbstractAnalyzer
rendering:
heading_level: 4
::: nominatim_db.tokenizer.base.AbstractAnalyzer
options:
heading_level: 6
### PL/pgSQL Functions
@@ -189,6 +189,28 @@ a house number token text. If a place has multiple house numbers they must
be listed with a semicolon as delimiter. Must be NULL when the place has no
house numbers.
```sql
FUNCTION token_is_street_address(info JSONB) RETURNS BOOLEAN
```
Return true if this is an object that should be parented against a street.
Only relevant for objects with address rank 30.
```sql
FUNCTION token_has_addr_street(info JSONB) RETURNS BOOLEAN
```
Return true if there are street names to match against for finding the
parent of the object.
```sql
FUNCTION token_has_addr_place(info JSONB) RETURNS BOOLEAN
```
Return true if there are place names to match against for finding the
parent of the object.
```sql
FUNCTION token_matches_street(info JSONB, street_tokens INTEGER[]) RETURNS BOOLEAN
```

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

@@ -2,6 +2,10 @@
display: none!important
}
.wy-nav-content {
max-width: 900px!important
}
table {
margin-bottom: 12pt
}
@@ -16,9 +20,22 @@ th {
.doc-object h6 {
margin-bottom: 0.8em;
font-size: 120%;
font-size: 130%;
}
.doc-object {
margin-bottom: 1.3em;
}
.doc-children .doc-contents {
margin-left: 3em;
}
.md-footer__inner {
display: none;
}
.headerlink {
filter: grayscale(100%);
font-size: 80%;
}

View File

@@ -1,10 +1,15 @@
Nominatim (from the Latin, 'by name') is a tool to search OSM data by name and address and to generate synthetic addresses of OSM points (reverse geocoding).
Nominatim (from the Latin, 'by name') is a tool to search OSM data by name and
address and to generate synthetic addresses of OSM points (reverse geocoding).
It has also limited capability to search features by their type
(pubs, hotels, churches, etc).
This guide comes in four parts:
This guide comes in five parts:
* __[API reference](api/Overview.md)__ for users of Nominatim
* __[Administration Guide](admin/Installation.md)__ for those who want
to install their own Nominatim server
* __[Customization Guide](customize/Overview.md)__ for those who want to
adapt their own installation to their special requirements
* __[Library Guide](library/Getting-Started.md)__ for Python developers who
want to use Nominatim as a library in their project
* __[Developer's Guide](develop/overview.md)__ for developers of the software

View File

@@ -0,0 +1,33 @@
# Configuration
When using Nominatim through the library, it can be configured in exactly
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:
* from the OS environment (or the dictionary given in `environ`,
(see NominatimAPI.md#nominatim.api.core.NominatimAPI.__init__)
* from the .env file in the project directory of the installation
* from the default installation in the configuration directory
For more information on configuration via dotenv and a list of possible
configuration parameters, see the [Configuration page](../customize/Settings.md).
## `Configuration` class
::: nominatim_api.Configuration
options:
members:
- get_bool
- get_int
- get_str_list
- get_path
heading_level: 6
show_signature_annotations: True

View File

@@ -0,0 +1,289 @@
# Getting Started
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.
!!! warning
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
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.
The Nominatim frontend library is contained in the Python package `nominatim-api`.
You can install the latest released version directly from pip:
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
search functions of Nominatim that are also known from its web API.
This code snippet implements a simple search for the town of 'Brugge':
!!! example
=== "NominatimAPIAsync"
``` python
import asyncio
import nominatim_api as napi
async def search(query):
async with napi.NominatimAPIAsync() 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() 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}')
```
The Nominatim library is designed around
[asyncio](https://docs.python.org/3/library/asyncio.html). `NominatimAPIAsync`
provides you with an interface of coroutines.
If you have many requests to make, coroutines can speed up your applications
significantly.
For smaller scripts there is also a synchronous wrapper around the API. By
using `NominatimAPI`, you get exactly the same interface using classic functions.
The examples in this chapter will always show-case both
implementations. The documentation itself will usually refer only to
'Nominatim API class' when both flavours are meant. If a functionality is
available only for the synchronous or asynchronous version, this will be
explicitly mentioned.
## Defining which database to use
The [Configuration](../admin/Import.md#configuration-setup-in-env)
section explains how Nominatim is configured using the
[dotenv](https://github.com/theskumar/python-dotenv) library.
The same configuration mechanism is used with the
Nominatim API library. You should therefore be sure you are familiar with
the section.
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
import asyncio
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):
async with napi.NominatimAPIAsync(environ=config_params) as api:
return await api.search(query)
results = asyncio.run(search('Brugge'))
```
=== "NominatimAPI"
``` python
import nominatim_api as napi
config_params = {
'NOMINATIM_DATABASE_DSN': 'pgsql:dbname=belgium'
}
with napi.NominatimAPI(environ=config_params) as api:
results = api.search('Brugge')
```
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.
## 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
* 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
import asyncio
import nominatim_api as napi
async def search(query):
async with napi.NominatimAPIAsync() as api:
return await api.search(query, address_details=True)
results = asyncio.run(search('Brugge'))
locale = napi.Locales(['fr', 'en'])
for i, result in enumerate(results):
address_parts = result.address_rows.localize(locale)
print(f"{i + 1}. {', '.join(address_parts)}")
```
=== "NominatimAPI"
``` python
import nominatim_api as napi
with napi.NominatimAPI() as api:
results = api.search('Brugge', address_details=True)
locale = napi.Locales(['fr', 'en'])
for i, result in enumerate(results):
address_parts = result.address_rows.localize(locale)
print(f"{i + 1}. {', '.join(address_parts)}")
```
To request information about the address of a result, add the optional
parameter 'address_details' to your search:
``` python
>>> results = api.search('Brugge', address_details=True)
```
An additional field `address_rows` will set in results that are returned.
It contains a list of all places that make up the address of the place. For
simplicity, this includes name and house number of the place itself. With
the names in this list it is possible to create a human-readable description
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
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'])
```
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
name out of it:
``` python
>>> print(locale.display_name(results[0].names))
'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:
``` python
>>> address_parts = results[0].address_rows.localize(locale)
>>> 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 `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.
For more information on address rows, see
[detailed address description](Result-Handling.md#detailed-address-description).

View File

@@ -0,0 +1,60 @@
# Input Parameter Types
This page describes in more detail some of the input parameter types used
in the query functions of the API object.
## Place identification
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
options:
heading_level: 6
### OsmID
::: nominatim_api.OsmID
options:
heading_level: 6
## Geometry types
::: nominatim_api.GeometryFormat
options:
heading_level: 6
members_order: source
## Geometry input
### Point
::: nominatim_api.Point
options:
heading_level: 6
show_signature_annotations: True
### Bbox
::: nominatim_api.Bbox
options:
heading_level: 6
show_signature_annotations: True
members_order: source
group_by_category: False
## Layers
Layers allow to restrict the search result to thematic groups. This is
orthogonal to restriction by address ranks, which groups places by their
geographic extent.
::: nominatim_api.DataLayer
options:
heading_level: 6
members_order: source

View File

@@ -0,0 +1,55 @@
# Low-level connections
The `NominatimAPIAsync` class allows to directly access the underlying
database connection to explore the raw data. Nominatim uses
[SQLAlchemy](https://docs.sqlalchemy.org/) for building queries. Please
refer to the documentation of the library to understand how to write SQL.
To get access to a search connection, use the `begin()` function of your
API object. This returns a `SearchConnection` object described below
wrapped in a context manager. Its
`t` property has definitions for all Nominatim search tables. For an
overview of available tables, refer to the
[Development Layout](../develop/Database-Layout.md) in in the development
chapter. Note that only tables that are needed for search are accessible
as SQLAlchemy tables.
!!! warning
The database layout is not part of the API definition and may change
without notice. If you play with the low-level access functions, you
need to be prepared for such changes.
Here is a simple example, which prints how many places are available in
the placex table:
```
import asyncio
import sqlalchemy as sa
from nominatim_api import NominatimAPIAsync
async def print_table_size():
api = NominatimAPIAsync()
async with api.begin() as conn:
cnt = await conn.scalar(sa.select(sa.func.count()).select_from(conn.t.placex))
print(f'placex table has {cnt} rows.')
asyncio.run(print_table_size())
```
!!! warning
Low-level connections may only be used to read data from the database.
Do not use it to add or modify data or you might break Nominatim's
normal functions.
## SearchConnection class
::: nominatim_api.SearchConnection
options:
members:
- scalar
- execute
- get_class_table
- get_db_property
- get_property
heading_level: 6

View File

@@ -0,0 +1,36 @@
# The Nominatim API classes
The API classes are the core object of the search library. Always instantiate
one of these classes first. The API classes are **not threadsafe**. You need
to instantiate a separate instance for each thread.
### NominatimAPI
::: nominatim_api.NominatimAPI
options:
members:
- __init__
- config
- close
- status
- details
- lookup
- reverse
- search
- search_address
- search_category
heading_level: 6
group_by_category: False
### NominatimAPIAsync
::: nominatim_api.NominatimAPIAsync
options:
members:
- __init__
- setup_database
- close
- begin
heading_level: 6
group_by_category: False

View File

@@ -0,0 +1,58 @@
# Result handling
The search functions of the Nominatim API always return a result object
with the raw information about the place that is available in the
database. This section discusses data types used in the results and utility
functions that allow further processing of the results.
## Result fields
### Sources
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
options:
heading_level: 6
members_order: source
### Detailed address description
When the `address_details` parameter is set, then functions return not
only information about the result place but also about the place that
make up the address. This information is almost always required when you
want to present the user with a human-readable description of the result.
See also [Localization](#localization) below.
The address details are available in the `address_rows` field as a ordered
list of `AddressLine` objects with the country information last. The list also
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
options:
heading_level: 6
members_order: source
### Detailed search terms
The `details` function can return detailed information about which search terms
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
options:
heading_level: 6
## Localization
Results are always returned with the full list of available names.
### Locale
::: 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")

View File

@@ -38,23 +38,25 @@ class DB
// https://secure.php.net/manual/en/ref.pdo-pgsql.connection.php
try {
$conn = new \PDO($this->sDSN, null, null, $aConnOptions);
$this->connection = new \PDO($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());
}
$conn->exec("SET DateStyle TO 'sql,european'");
$conn->exec("SET client_encoding TO 'utf-8'");
$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.
$conn->exec("UPDATE pg_settings SET setting = -1 WHERE name = 'jit_above_cost'");
$conn->exec("UPDATE pg_settings SET setting = 0 WHERE name = 'max_parallel_workers_per_gather'");
$this->connection->exec('SET max_parallel_workers_per_gather TO 0');
if ($this->getPostgresVersion() >= 11) {
$this->connection->exec('SET jit_above_cost TO -1');
}
$iMaxExecution = ini_get('max_execution_time');
if ($iMaxExecution > 0) {
$conn->setAttribute(\PDO::ATTR_TIMEOUT, $iMaxExecution); // seconds
$this->connection->setAttribute(\PDO::ATTR_TIMEOUT, $iMaxExecution); // seconds
}
$this->connection = $conn;
return true;
}

View File

@@ -135,7 +135,7 @@ class Debug
public static function printSQL($sSQL)
{
echo '<p><tt><font color="#aaa">'.htmlspecialchars($sSQL, ENT_QUOTES | ENT_SUBSTITUTE | ENT_HTML401).'</font></tt></p>'."\n";
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)

View File

@@ -874,7 +874,7 @@ class Geocode
$iCountWords = 0;
$sAddress = $aResult['langaddress'];
foreach ($aRecheckWords as $i => $sWord) {
if (stripos($sAddress, $sWord)!==false) {
if (grapheme_stripos($sAddress, $sWord)!==false) {
$iCountWords++;
if (preg_match('/(^|,)\s*'.preg_quote($sWord, '/').'\s*(,|$)/', $sAddress)) {
$iCountWords += 0.1;

View File

@@ -86,7 +86,7 @@ class PlaceLookup
($this->bIncludePolygonAsSVG ? 1 : 0);
if ($iWantedTypes > CONST_PolygonOutput_MaximumTypes) {
if (CONST_PolygonOutput_MaximumTypes) {
userError('Select only '.CONST_PolygonOutput_MaximumTypes.' polgyon output option');
userError('Select only '.CONST_PolygonOutput_MaximumTypes.' polygon output option');
} else {
userError('Polygon output is disabled');
}
@@ -187,12 +187,12 @@ class PlaceLookup
return null;
}
$aResults = $this->lookup(array($iPlaceID => new Result($iPlaceID)));
$aResults = $this->lookup(array($iPlaceID => new Result($iPlaceID)), 0, 30, true);
return empty($aResults) ? null : reset($aResults);
}
public function lookup($aResults, $iMinRank = 0, $iMaxRank = 30)
public function lookup($aResults, $iMinRank = 0, $iMaxRank = 30, $bAllowLinked = false)
{
Debug::newFunction('Place lookup');
@@ -247,7 +247,9 @@ class PlaceLookup
if ($this->sAllowedTypesSQLList) {
$sSQL .= 'AND placex.class in '.$this->sAllowedTypesSQLList;
}
$sSQL .= ' AND linked_place_id is null ';
if (!$bAllowLinked) {
$sSQL .= ' AND linked_place_id is null ';
}
$sSQL .= ' GROUP BY ';
$sSQL .= ' osm_type, ';
$sSQL .= ' osm_id, ';
@@ -522,12 +524,7 @@ class PlaceLookup
// Get the bounding box and outline polygon
$sSQL = 'select place_id,0 as numfeatures,st_area(geometry) as area,';
if ($fLonReverse != null && $fLatReverse != null) {
$sSQL .= ' ST_Y(closest_point) as centrelat,';
$sSQL .= ' ST_X(closest_point) as centrelon,';
} else {
$sSQL .= ' ST_Y(centroid) as centrelat, ST_X(centroid) as centrelon,';
}
$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) {
@@ -542,19 +539,21 @@ class PlaceLookup
if ($this->bIncludePolygonAsText) {
$sSQL .= ',ST_AsText(geometry) as astext';
}
$sSQL .= ' FROM (SELECT place_id';
if ($fLonReverse != null && $fLatReverse != null) {
$sFrom = ' from (SELECT * , CASE WHEN (class = \'highway\') AND (ST_GeometryType(geometry) = \'ST_LineString\') THEN ';
$sFrom .=' ST_ClosestPoint(geometry, ST_SetSRID(ST_Point('.$fLatReverse.','.$fLonReverse.'),4326))';
$sFrom .=' ELSE centroid END AS closest_point';
$sFrom .= ' from placex where place_id = '.$iPlaceID.') as plx';
$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 {
$sFrom = ' from placex where place_id = '.$iPlaceID;
$sSQL .= ',centroid';
}
if ($this->fPolygonSimplificationThreshold > 0) {
$sSQL .= ' from (select place_id,centroid,ST_SimplifyPreserveTopology(geometry,'.$this->fPolygonSimplificationThreshold.') as geometry'.$sFrom.') as plx';
$sSQL .= ',ST_SimplifyPreserveTopology(geometry,'.$this->fPolygonSimplificationThreshold.') as geometry';
} else {
$sSQL .= $sFrom;
$sSQL .= ',geometry';
}
$sSQL .= ' FROM placex where place_id = '.$iPlaceID.') as plx';
$aPointPolygon = $this->oDB->getRow($sSQL, null, 'Could not get outline');

View File

@@ -40,10 +40,10 @@ class ReverseGeocode
9 => 12,
10 => 17, // City
11 => 17,
12 => 18, // Town / Village
13 => 18,
14 => 22, // Suburb
15 => 22,
12 => 18, // Town
13 => 19, // Village
14 => 22, // Neighbourhood
15 => 25, // Locality
16 => 26, // major street
17 => 27, // minor street
18 => 30, // or >, Building
@@ -85,6 +85,11 @@ class ReverseGeocode
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) {
@@ -94,12 +99,12 @@ class ReverseGeocode
// If no polygon which contains the searchpoint is found,
// searches in the country_osm_grid table for a polygon.
return $this->lookupInCountry($sPointSQL, $iMaxRank);
return $this->lookupInCountry($sPointSQL, $iMaxRank, $sCountryCode);
}
protected function lookupInCountry($sPointSQL, $iMaxRank)
protected function getCountryCode($sPointSQL)
{
Debug::newFunction('lookupInCountry');
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';
@@ -111,8 +116,12 @@ class ReverseGeocode
null,
'Could not determine country polygon containing the point.'
);
Debug::printVar('Country code', $sCountryCode);
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
@@ -122,12 +131,13 @@ class ReverseGeocode
$sSQL .= ' FROM placex';
$sSQL .= ' WHERE osm_type = \'N\'';
$sSQL .= ' AND country_code = \''.$sCountryCode.'\'';
$sSQL .= ' AND rank_search < 26 '; // needed to select right index
$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 class = \'place\' AND type != \'postcode\'';
$sSQL .= ' AND type != \'postcode\'';
$sSQL .= ' AND name IS NOT NULL ';
$sSQL .= ' and indexed_status = 0 and linked_place_id is null';
$sSQL .= ' AND ST_DWithin('.$sPointSQL.', geometry, 1.8)) p ';
$sSQL .= ' AND ST_Buffer(geometry, reverse_place_diameter(rank_search)) && '.$sPointSQL;
$sSQL .= ') as a ';
$sSQL .= 'WHERE distance <= reverse_place_diameter(rank_search)';
$sSQL .= ' ORDER BY rank_search DESC, distance ASC';
$sSQL .= ' LIMIT 1';
@@ -189,14 +199,16 @@ class ReverseGeocode
$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\')';
$sSQL .= ' AND rank_address Between 5 AND ' .$iMaxRank;
// 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_address DESC LIMIT 50 ) as a';
$sSQL .= ' WHERE ST_CONTAINS(geometry, '.$sPointSQL.' )';
$sSQL .= ' ORDER BY rank_address DESC LIMIT 1';
$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.');
@@ -208,29 +220,24 @@ class ReverseGeocode
$iRankSearch = $aPoly['rank_search'];
$iPlaceID = $aPoly['place_id'];
if ($iRankAddress != $iMaxRank) {
if ($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\'';
// using rank_search because of a better differentiation
// for place nodes at rank_address 16
$sSQL .= ' AND rank_search > '.$iRankSearch;
$sSQL .= ' AND rank_search <= '.$iMaxRank;
$sSQL .= ' AND rank_search < 26 '; // needed to select right index
$sSQL .= ' AND rank_address > 0';
$sSQL .= ' AND class = \'place\'';
$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';
$sSQL .= ' AND ST_DWithin('.$sPointSQL.', geometry, reverse_place_diameter('.$iRankSearch.'::smallint))';
$sSQL .= ' ORDER BY distance ASC,';
$sSQL .= ' rank_address DESC';
$sSQL .= ' limit 500) as a';
$sSQL .= ' WHERE ST_CONTAINS((SELECT geometry FROM placex WHERE place_id = '.$iPlaceID.'), geometry )';
$sSQL .= ' AND ST_Buffer(geometry, reverse_place_diameter(rank_search)) && '.$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 distance ASC, rank_search DESC';
$sSQL .= ' ORDER BY rank_search DESC, distance ASC';
$sSQL .= ' LIMIT 1';
Debug::printSQL($sSQL);

View File

@@ -1,190 +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.
*/
@define('CONST_LibDir', dirname(dirname(__FILE__)));
// Script to extract structured city and street data
// from a running nominatim instance as CSV data
require_once(CONST_LibDir.'/init-cmd.php');
require_once(CONST_LibDir.'/ParameterParser.php');
ini_set('memory_limit', '800M');
$aCMDOptions = array(
'Export addresses as CSV file from a Nominatim database',
array('help', 'h', 0, 1, 0, 0, false, 'Show Help'),
array('quiet', 'q', 0, 1, 0, 0, 'bool', 'Quiet output'),
array('verbose', 'v', 0, 1, 0, 0, 'bool', 'Verbose output'),
array('output-type', '', 0, 1, 1, 1, 'str', 'Type of places to output (see below)'),
array('output-format', '', 0, 1, 1, 1, 'str', 'Column mapping (see below)'),
array('output-all-postcodes', '', 0, 1, 0, 0, 'bool', 'List all postcodes for address instead of just the most likely one'),
array('language', '', 0, 1, 1, 1, 'str', 'Preferred language for output (local name, if omitted)'),
array('restrict-to-country', '', 0, 1, 1, 1, 'str', 'Export only objects within country (country code)'),
array('restrict-to-osm-node', '', 0, 1, 1, 1, 'int', 'Export only objects that are children of this OSM node'),
array('restrict-to-osm-way', '', 0, 1, 1, 1, 'int', 'Export only objects that are children of this OSM way'),
array('restrict-to-osm-relation', '', 0, 1, 1, 1, 'int', 'Export only objects that are children of this OSM relation'),
array('project-dir', '', 0, 1, 1, 1, 'realpath', 'Base directory of the Nominatim installation (default: .)'),
"\nAddress ranks: continent, country, state, county, city, suburb, street, path",
'Additional output types: postcode, placeid (placeid for each object)',
"\noutput-format must be a semicolon-separated list of address ranks. Multiple ranks",
'can be merged into one column by simply using a comma-separated list.',
"\nDefault output-type: street",
'Default output format: street;suburb;city;county;state;country'
);
getCmdOpt($_SERVER['argv'], $aCMDOptions, $aCMDResult, true, true);
loadSettings($aCMDResult['project-dir'] ?? getcwd());
$aRankmap = array(
'continent' => 1,
'country' => 4,
'state' => 8,
'county' => 12,
'city' => 16,
'suburb' => 20,
'street' => 26,
'path' => 27
);
$oDB = new Nominatim\DB();
$oDB->connect();
if (isset($aCMDResult['output-type'])) {
if (!isset($aRankmap[$aCMDResult['output-type']])) {
fail('unknown output-type: '.$aCMDResult['output-type']);
}
$iOutputRank = $aRankmap[$aCMDResult['output-type']];
} else {
$iOutputRank = $aRankmap['street'];
}
// Preferred language
$oParams = new Nominatim\ParameterParser();
if (!isset($aCMDResult['language'])) {
$aCMDResult['language'] = 'xx';
}
$aLangPrefOrder = $oParams->getPreferredLanguages($aCMDResult['language']);
$sLanguagePrefArraySQL = $oDB->getArraySQL($oDB->getDBQuotedList($aLangPrefOrder));
// output formatting: build up a lookup table that maps address ranks to columns
$aColumnMapping = array();
$iNumCol = 0;
if (!isset($aCMDResult['output-format'])) {
$aCMDResult['output-format'] = 'street;suburb;city;county;state;country';
}
foreach (preg_split('/\s*;\s*/', $aCMDResult['output-format']) as $sColumn) {
$bHasData = false;
foreach (preg_split('/\s*,\s*/', $sColumn) as $sRank) {
if ($sRank == 'postcode' || $sRank == 'placeid') {
$aColumnMapping[$sRank] = $iNumCol;
$bHasData = true;
} elseif (isset($aRankmap[$sRank])) {
$iRank = $aRankmap[$sRank];
if ($iRank <= $iOutputRank) {
$aColumnMapping[(string)$iRank] = $iNumCol;
$bHasData = true;
}
}
}
if ($bHasData) {
$iNumCol++;
}
}
// build the query for objects
$sPlacexSQL = 'select min(place_id) as place_id, ';
$sPlacexSQL .= 'array_agg(place_id) as place_ids, ';
$sPlacexSQL .= 'country_code as cc, ';
$sPlacexSQL .= 'postcode, ';
// get the address places excluding postcodes
$sPlacexSQL .= 'array(select address_place_id from place_addressline a';
$sPlacexSQL .= ' where a.place_id = placex.place_id and isaddress';
$sPlacexSQL .= ' and address_place_id != placex.place_id';
$sPlacexSQL .= ' and not cached_rank_address in (5,11)';
$sPlacexSQL .= ' and cached_rank_address > 2 order by cached_rank_address)';
$sPlacexSQL .= ' as address';
$sPlacexSQL .= ' from placex where name is not null and linked_place_id is null';
$sPlacexSQL .= ' and rank_address = '.$iOutputRank;
if (isset($aCMDResult['restrict-to-country'])) {
$sPlacexSQL .= ' and country_code = '.$oDB->getDBQuoted($aCMDResult['restrict-to-country']);
}
// restriction to parent place id
$sParentId = false;
$sOsmType = false;
if (isset($aCMDResult['restrict-to-osm-node'])) {
$sOsmType = 'N';
$sOsmId = $aCMDResult['restrict-to-osm-node'];
}
if (isset($aCMDResult['restrict-to-osm-way'])) {
$sOsmType = 'W';
$sOsmId = $aCMDResult['restrict-to-osm-way'];
}
if (isset($aCMDResult['restrict-to-osm-relation'])) {
$sOsmType = 'R';
$sOsmId = $aCMDResult['restrict-to-osm-relation'];
}
if ($sOsmType) {
$sSQL = 'select place_id from placex where osm_type = :osm_type and osm_id = :osm_id';
$sParentId = $oDB->getOne($sSQL, array('osm_type' => $sOsmType, 'osm_id' => $sOsmId));
if (!$sParentId) {
fail('Could not find place '.$sOsmType.' '.$sOsmId);
}
}
if ($sParentId) {
$sPlacexSQL .= ' and place_id in (select place_id from place_addressline where address_place_id = '.$sParentId.' and isaddress)';
}
$sPlacexSQL .= " group by name->'name', address, postcode, country_code, placex.place_id";
// Iterate over placeids
// to get further hierarchical information
//var_dump($sPlacexSQL);
$oResults = $oDB->getQueryStatement($sPlacexSQL);
$fOutstream = fopen('php://output', 'w');
while ($aRow = $oResults->fetch()) {
$iPlaceID = $aRow['place_id'];
$sSQL = "select rank_address,get_name_by_language(name,$sLanguagePrefArraySQL) as localname from get_addressdata(:place_id, -1)";
$sSQL .= ' WHERE isaddress';
$sSQL .= ' order by rank_address desc,isaddress desc';
$aAddressLines = $oDB->getAll($sSQL, array('place_id' => $iPlaceID));
$aOutput = array_fill(0, $iNumCol, '');
// output address parts
foreach ($aAddressLines as $aAddress) {
if (isset($aColumnMapping[$aAddress['rank_address']])) {
$aOutput[$aColumnMapping[$aAddress['rank_address']]] = $aAddress['localname'];
}
}
// output postcode
if (isset($aColumnMapping['postcode'])) {
if ($aCMDResult['output-all-postcodes']) {
$sSQL = 'select array_agg(px.postcode) from placex px join place_addressline pa ';
$sSQL .= 'on px.place_id = pa.address_place_id ';
$sSQL .= 'where pa.cached_rank_address in (5,11) ';
$sSQL .= 'and pa.place_id in (select place_id from place_addressline where address_place_id in (:first_place_id)) ';
$sSQL .= 'group by postcode order by count(*) desc limit 1';
$sRes = $oDB->getOne($sSQL, array('first_place_id' => substr($aRow['place_ids'], 1, -1)));
$aOutput[$aColumnMapping['postcode']] = substr($sRes, 1, -1);
} else {
$aOutput[$aColumnMapping['postcode']] = $aRow['postcode'];
}
}
if (isset($aColumnMapping['placeid'])) {
$aOutput[$aColumnMapping['placeid']] = substr($aRow['place_ids'], 1, -1);
}
fputcsv($fOutstream, $aOutput);
}
fclose($fOutstream);

View File

@@ -1,114 +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.
*/
@define('CONST_LibDir', dirname(dirname(__FILE__)));
require_once(CONST_LibDir.'/init-cmd.php');
require_once(CONST_LibDir.'/log.php');
require_once(CONST_LibDir.'/PlaceLookup.php');
require_once(CONST_LibDir.'/ReverseGeocode.php');
ini_set('memory_limit', '800M');
$aCMDOptions = array(
'Tools to warm nominatim db',
array('help', 'h', 0, 1, 0, 0, false, 'Show Help'),
array('quiet', 'q', 0, 1, 0, 0, 'bool', 'Quiet output'),
array('verbose', 'v', 0, 1, 0, 0, 'bool', 'Verbose output'),
array('reverse-only', '', 0, 1, 0, 0, 'bool', 'Warm reverse only'),
array('search-only', '', 0, 1, 0, 0, 'bool', 'Warm search only'),
array('project-dir', '', 0, 1, 1, 1, 'realpath', 'Base directory of the Nominatim installation (default: .)'),
);
getCmdOpt($_SERVER['argv'], $aCMDOptions, $aResult, true, true);
loadSettings($aCMDResult['project-dir'] ?? getcwd());
@define('CONST_Database_DSN', getSetting('DATABASE_DSN'));
@define('CONST_Default_Language', getSetting('DEFAULT_LANGUAGE', false));
@define('CONST_Log_DB', getSettingBool('LOG_DB'));
@define('CONST_Log_File', getSetting('LOG_FILE', false));
@define('CONST_NoAccessControl', getSettingBool('CORS_NOACCESSCONTROL'));
@define('CONST_Places_Max_ID_count', getSetting('LOOKUP_MAX_COUNT'));
@define('CONST_PolygonOutput_MaximumTypes', getSetting('POLYGON_OUTPUT_MAX_TYPES'));
@define('CONST_Search_BatchMode', getSettingBool('SEARCH_BATCH_MODE'));
@define('CONST_Search_NameOnlySearchFrequencyThreshold', getSetting('SEARCH_NAME_ONLY_THRESHOLD'));
@define('CONST_Use_US_Tiger_Data', getSettingBool('USE_US_TIGER_DATA'));
@define('CONST_MapIcon_URL', getSetting('MAPICON_URL', false));
@define('CONST_TokenizerDir', CONST_InstallDir.'/tokenizer');
require_once(CONST_LibDir.'/Geocode.php');
$oDB = new Nominatim\DB();
$oDB->connect();
$bVerbose = $aResult['verbose'];
function print_results($aResults, $bVerbose)
{
if ($bVerbose) {
if ($aResults && count($aResults)) {
echo $aResults[0]['langaddress']."\n";
} else {
echo "<not found>\n";
}
} else {
echo '.';
}
}
if (!$aResult['search-only']) {
$oReverseGeocode = new Nominatim\ReverseGeocode($oDB);
$oReverseGeocode->setZoom(20);
$oPlaceLookup = new Nominatim\PlaceLookup($oDB);
$oPlaceLookup->setIncludeAddressDetails(true);
$oPlaceLookup->setLanguagePreference(array('en'));
echo 'Warm reverse: ';
if ($bVerbose) {
echo "\n";
}
for ($i = 0; $i < 1000; $i++) {
$fLat = rand(-9000, 9000) / 100;
$fLon = rand(-18000, 18000) / 100;
if ($bVerbose) {
echo "$fLat, $fLon = ";
}
$oLookup = $oReverseGeocode->lookup($fLat, $fLon);
$aSearchResults = $oLookup ? $oPlaceLookup->lookup(array($oLookup->iId => $oLookup)) : null;
print_results($aSearchResults, $bVerbose);
}
echo "\n";
}
if (!$aResult['reverse-only']) {
$oGeocode = new Nominatim\Geocode($oDB);
echo 'Warm search: ';
if ($bVerbose) {
echo "\n";
}
$oTokenizer = new \Nominatim\Tokenizer($oDB);
$aWords = $oTokenizer->mostFrequentWords(1000);
$sSQL = 'SELECT word FROM word WHERE word is not null ORDER BY search_name_count DESC LIMIT 1000';
foreach ($aWords as $sWord) {
if ($bVerbose) {
echo "$sWord = ";
}
$oGeocode->setLanguagePreference(array('en'));
$oGeocode->setQuery($sWord);
$aSearchResults = $oGeocode->lookup();
print_results($aSearchResults, $bVerbose);
}
echo "\n";
}

View File

@@ -36,6 +36,9 @@ if (empty($aPlace)) {
$aFilteredPlaces['properties']['geocoding']['osm_id'] = $aPlace['osm_id'];
}
$aFilteredPlaces['properties']['geocoding']['osm_key'] = $aPlace['class'];
$aFilteredPlaces['properties']['geocoding']['osm_value'] = $aPlace['type'];
$aFilteredPlaces['properties']['geocoding']['type'] = addressRankToGeocodeJsonType($aPlace['rank_address']);
$aFilteredPlaces['properties']['geocoding']['accuracy'] = (int) $fDistance;

View File

@@ -23,7 +23,7 @@ $aLangPrefOrder = $oParams->getPreferredLanguages();
$sPlaceId = $oParams->getString('place_id');
$sOsmType = $oParams->getSet('osmtype', array('N', 'W', 'R'));
$iOsmId = $oParams->getInt('osmid', -1);
$iOsmId = $oParams->getInt('osmid', 0);
$sClass = $oParams->getString('class');
$bIncludeKeywords = $oParams->getBool('keywords', false);
@@ -38,7 +38,7 @@ $oDB->connect();
$sLanguagePrefArraySQL = $oDB->getArraySQL($oDB->getDBQuotedList($aLangPrefOrder));
if ($sOsmType && $iOsmId > 0) {
if ($sOsmType && $iOsmId !== 0) {
$sSQL = 'SELECT place_id FROM placex WHERE osm_type = :type AND osm_id = :id';
$aSQLParams = array(':type' => $sOsmType, ':id' => $iOsmId);
// osm_type and osm_id are not unique enough

View File

@@ -187,6 +187,7 @@ BEGIN
-- --- Return the record for the base entry.
current_rank_address := 1000;
FOR location IN
SELECT placex.place_id, osm_type, osm_id, name,
coalesce(extratags->'linked_place', extratags->'place') as place_type,
@@ -261,7 +262,7 @@ BEGIN
-- If the place had a postcode assigned, take this one only
-- into consideration when it is an area and the place does not have
-- a postcode itself.
IF location.fromarea AND location.isaddress
IF location.fromarea AND location_isaddress
AND (place.address is null or not place.address ? 'postcode')
THEN
place.postcode := null; -- remove the less exact postcode

View File

@@ -20,6 +20,54 @@ CREATE TYPE place_importance as (
wikipedia TEXT
);
{% if 'wikimedia_importance' in db.tables %}
CREATE OR REPLACE FUNCTION get_wikipedia_match(extratags HSTORE, country_code varchar(2))
RETURNS wikipedia_article_match
AS $$
DECLARE
i INT;
wiki_article_title TEXT;
wiki_article_language TEXT;
result wikipedia_article_match;
entry RECORD;
BEGIN
IF extratags ? 'wikipedia' and strpos(extratags->'wikipedia', ':') IN (3,4) THEN
wiki_article_language := lower(trim(split_part(extratags->'wikipedia', ':', 1)));
wiki_article_title := trim(substr(extratags->'wikipedia',
strpos(extratags->'wikipedia', ':') + 1));
FOR result IN
SELECT language, title, importance FROM wikimedia_importance
WHERE language = wiki_article_language
and title = replace(wiki_article_title, ' ', '_')
LOOP
RETURN result;
END LOOP;
END IF;
FOREACH wiki_article_language IN ARRAY ARRAY['ar','bg','ca','cs','da','de','en','es','eo','eu','fa','fr','ko','hi','hr','id','it','he','lt','hu','ms','nl','ja','no','pl','pt','kk','ro','ru','sk','sl','sr','fi','sv','tr','uk','vi','vo','war','zh']
LOOP
IF extratags ? ('wikipedia:' || wiki_article_language) THEN
wiki_article_title := extratags->('wikipedia:' || wiki_article_language);
FOR result IN
SELECT language, title, importance FROM wikimedia_importance
WHERE language = wiki_article_language
and title = replace(wiki_article_title, ' ', '_')
LOOP
RETURN result;
END LOOP;
END IF;
END LOOP;
RETURN NULL;
END;
$$
LANGUAGE plpgsql IMMUTABLE;
{% else %}
-- See: http://stackoverflow.com/questions/6410088/how-can-i-mimic-the-php-urldecode-function-in-postgresql
CREATE OR REPLACE FUNCTION decode_url_part(p varchar)
@@ -62,10 +110,6 @@ BEGIN
WHILE langs[i] IS NOT NULL LOOP
wiki_article := extratags->(case when langs[i] in ('english','country') THEN 'wikipedia' ELSE 'wikipedia:'||langs[i] END);
IF wiki_article is not null THEN
wiki_article := regexp_replace(wiki_article,E'^(.*?)([a-z]{2,3}).wikipedia.org/wiki/',E'\\2:');
wiki_article := regexp_replace(wiki_article,E'^(.*?)([a-z]{2,3}).wikipedia.org/w/index.php\\?title=',E'\\2:');
wiki_article := regexp_replace(wiki_article,E'^(.*?)/([a-z]{2,3})/wiki/',E'\\2:');
--wiki_article := regexp_replace(wiki_article,E'^(.*?)([a-z]{2,3})[=:]',E'\\2:');
wiki_article := replace(wiki_article,' ','_');
IF strpos(wiki_article, ':') IN (3,4) THEN
wiki_article_language := lower(trim(split_part(wiki_article, ':', 1)));
@@ -97,35 +141,66 @@ END;
$$
LANGUAGE plpgsql STABLE;
{% endif %}
CREATE OR REPLACE FUNCTION compute_importance(extratags HSTORE,
country_code varchar(2),
osm_type varchar(1), osm_id BIGINT)
rank_search SMALLINT,
centroid GEOMETRY)
RETURNS place_importance
AS $$
DECLARE
match RECORD;
result place_importance;
osm_views_exists BIGINT;
views BIGINT;
BEGIN
FOR match IN SELECT * FROM get_wikipedia_match(extratags, country_code)
WHERE language is not NULL
-- add importance by wikipedia article if the place has one
FOR match IN
SELECT * FROM get_wikipedia_match(extratags, country_code)
WHERE language is not NULL
LOOP
result.importance := match.importance;
result.wikipedia := match.language || ':' || match.title;
RETURN result;
END LOOP;
IF extratags ? 'wikidata' THEN
FOR match IN SELECT * FROM wikipedia_article
WHERE wd_page_title = extratags->'wikidata'
ORDER BY language = 'en' DESC, langcount DESC LIMIT 1 LOOP
-- Nothing? Then try with the wikidata tag.
IF result.importance is null AND extratags ? 'wikidata' THEN
FOR match IN
{% if 'wikimedia_importance' in db.tables %}
SELECT * FROM wikimedia_importance
WHERE wikidata = extratags->'wikidata'
LIMIT 1
{% else %}
SELECT * FROM wikipedia_article
WHERE wd_page_title = extratags->'wikidata'
ORDER BY language = 'en' DESC, langcount DESC LIMIT 1
{% endif %}
LOOP
result.importance := match.importance;
result.wikipedia := match.language || ':' || match.title;
RETURN result;
END LOOP;
END IF;
RETURN null;
-- Still nothing? Fall back to a default.
IF result.importance is null THEN
result.importance := 0.40001 - (rank_search::float / 75);
END IF;
{% if 'secondary_importance' in db.tables %}
FOR match IN
SELECT ST_Value(rast, centroid) as importance
FROM secondary_importance
WHERE ST_Intersects(ST_ConvexHull(rast), centroid) LIMIT 1
LOOP
-- Secondary importance as tie breaker with 0.0001 weight.
result.importance := result.importance + match.importance::float / 655350000;
END LOOP;
{% endif %}
RETURN result;
END;
$$
LANGUAGE plpgsql;

View File

@@ -52,7 +52,9 @@ BEGIN
IF parent_place_id is null THEN
FOR location IN SELECT place_id FROM placex
WHERE ST_DWithin(geom, placex.geometry, 0.001) and placex.rank_search = 26
WHERE ST_DWithin(geom, placex.geometry, 0.001)
and placex.rank_search = 26
and placex.osm_type = 'W' -- needed for index selection
ORDER BY CASE WHEN ST_GeometryType(geom) = 'ST_Line' THEN
(ST_distance(placex.geometry, ST_LineInterpolatePoint(geom,0))+
ST_distance(placex.geometry, ST_LineInterpolatePoint(geom,0.5))+
@@ -65,10 +67,6 @@ BEGIN
END LOOP;
END IF;
IF parent_place_id is null THEN
RETURN 0;
END IF;
RETURN parent_place_id;
END;
$$
@@ -162,7 +160,7 @@ DECLARE
newend INTEGER;
moddiff SMALLINT;
linegeo GEOMETRY;
splitline GEOMETRY;
splitpoint FLOAT;
sectiongeo GEOMETRY;
postcode TEXT;
stepmod SMALLINT;
@@ -181,6 +179,13 @@ BEGIN
ST_PointOnSurface(NEW.linegeo),
NEW.linegeo);
-- Cannot find a parent street. We will not be able to display a reliable
-- address, so drop entire interpolation.
IF NEW.parent_place_id is NULL THEN
DELETE FROM location_property_osmline where place_id = OLD.place_id;
RETURN NULL;
END IF;
NEW.token_info := token_strip_info(NEW.token_info);
IF NEW.address ? '_inherited' THEN
NEW.address := hstore('interpolation', NEW.address->'interpolation');
@@ -217,19 +222,32 @@ BEGIN
-- formatted postcode and therefore 'postcode' contains a derived
-- variant.
CASE WHEN address ? 'postcode' THEN placex.postcode ELSE NULL::text END as postcode,
substring(address->'housenumber','[0-9]+')::integer as hnr
(address->'housenumber')::integer as hnr
FROM placex, generate_series(1, array_upper(waynodes, 1)) nodeidpos
WHERE osm_type = 'N' and osm_id = waynodes[nodeidpos]::BIGINT
and address is not NULL and address ? 'housenumber'
and address->'housenumber' ~ '^[0-9]{1,6}$'
and ST_Distance(NEW.linegeo, geometry) < 0.0005
ORDER BY nodeidpos
LOOP
{% if debug %}RAISE WARNING 'processing point % (%)', nextnode.hnr, ST_AsText(nextnode.geometry);{% endif %}
IF linegeo is null THEN
linegeo := NEW.linegeo;
ELSE
splitline := ST_Split(ST_Snap(linegeo, nextnode.geometry, 0.0005), nextnode.geometry);
sectiongeo := ST_GeometryN(splitline, 1);
linegeo := ST_GeometryN(splitline, 2);
splitpoint := ST_LineLocatePoint(linegeo, nextnode.geometry);
IF splitpoint = 0 THEN
-- Corner case where the splitpoint falls on the first point
-- and thus would not return a geometry. Skip that section.
sectiongeo := NULL;
ELSEIF splitpoint = 1 THEN
-- Point is at the end of the line.
sectiongeo := linegeo;
linegeo := NULL;
ELSE
-- Split the line.
sectiongeo := ST_LineSubstring(linegeo, 0, splitpoint);
linegeo := ST_LineSubstring(linegeo, splitpoint, 1);
END IF;
END IF;
IF prevnode.hnr is not null
@@ -237,6 +255,9 @@ BEGIN
-- regularly mapped housenumbers.
-- (Conveniently also fails if one of the house numbers is not a number.)
and abs(prevnode.hnr - nextnode.hnr) > NEW.step
-- If the interpolation geometry is broken or two nodes are at the
-- same place, then splitting might produce a point. Ignore that.
and ST_GeometryType(sectiongeo) = 'ST_LineString'
THEN
IF prevnode.hnr < nextnode.hnr THEN
startnumber := prevnode.hnr;
@@ -298,12 +319,12 @@ BEGIN
NEW.address, postcode,
NEW.country_code, NEW.geometry_sector, 0);
END IF;
END IF;
-- early break if we are out of line string,
-- might happen when a line string loops back on itself
IF ST_GeometryType(linegeo) != 'ST_LineString' THEN
RETURN NEW;
END IF;
-- early break if we are out of line string,
-- might happen when a line string loops back on itself
IF linegeo is null or ST_GeometryType(linegeo) != 'ST_LineString' THEN
RETURN NEW;
END IF;
prevnode := nextnode;

View File

@@ -34,6 +34,11 @@ BEGIN
RETURN null;
END IF;
-- Remove the place from the list of places to be deleted
DELETE FROM place_to_be_deleted pdel
WHERE pdel.osm_type = NEW.osm_type and pdel.osm_id = NEW.osm_id
and pdel.class = NEW.class and pdel.type = NEW.type;
-- Have we already done this place?
SELECT * INTO existing
FROM place
@@ -42,8 +47,6 @@ BEGIN
{% if debug %}RAISE WARNING 'Existing: %',existing.osm_id;{% endif %}
-- Handle a place changing type by removing the old data.
-- (This trigger is executed BEFORE INSERT of the NEW tuple.)
IF existing.osm_type IS NULL THEN
DELETE FROM place where osm_type = NEW.osm_type and osm_id = NEW.osm_id and class = NEW.class;
END IF;
@@ -187,15 +190,11 @@ BEGIN
END IF;
{% endif %}
IF existing.osm_type IS NOT NULL THEN
-- Pathological case caused by the triggerless copy into place during initial import
-- force delete even for large areas, it will be reinserted later
UPDATE place SET geometry = ST_SetSRID(ST_Point(0,0), 4326)
WHERE osm_type = NEW.osm_type and osm_id = NEW.osm_id
and class = NEW.class and type = NEW.type;
DELETE FROM place
WHERE osm_type = NEW.osm_type and osm_id = NEW.osm_id
and class = NEW.class and type = NEW.type;
IF existingplacex.osm_type is not NULL THEN
-- Mark any existing place for delete in the placex table
UPDATE placex SET indexed_status = 100
WHERE placex.osm_type = NEW.osm_type and placex.osm_id = NEW.osm_id
and placex.class = NEW.class and placex.type = NEW.type;
END IF;
-- Process it as a new insertion
@@ -206,6 +205,27 @@ BEGIN
{% if debug %}RAISE WARNING 'insert done % % % % %',NEW.osm_type,NEW.osm_id,NEW.class,NEW.type,NEW.name;{% endif %}
IF existing.osm_type is not NULL THEN
-- If there is already an entry in place, just update that, if necessary.
IF coalesce(existing.name, ''::hstore) != coalesce(NEW.name, ''::hstore)
or coalesce(existing.address, ''::hstore) != coalesce(NEW.address, ''::hstore)
or coalesce(existing.extratags, ''::hstore) != coalesce(NEW.extratags, ''::hstore)
or coalesce(existing.admin_level, 15) != coalesce(NEW.admin_level, 15)
or existing.geometry::text != NEW.geometry::text
THEN
UPDATE place
SET name = NEW.name,
address = NEW.address,
extratags = NEW.extratags,
admin_level = NEW.admin_level,
geometry = NEW.geometry
WHERE osm_type = NEW.osm_type and osm_id = NEW.osm_id
and class = NEW.class and type = NEW.type;
END IF;
RETURN NULL;
END IF;
RETURN NEW;
END IF;
@@ -276,7 +296,9 @@ BEGIN
extratags = NEW.extratags,
admin_level = NEW.admin_level,
indexed_status = 2,
geometry = NEW.geometry
geometry = CASE WHEN existingplacex.rank_address = 0
THEN simplify_large_polygons(NEW.geometry)
ELSE NEW.geometry END
WHERE place_id = existingplacex.place_id;
-- Invalidate linked places: they potentially get a new name and addresses.
@@ -321,35 +343,25 @@ BEGIN
END;
$$ LANGUAGE plpgsql;
CREATE OR REPLACE FUNCTION place_delete()
RETURNS TRIGGER
AS $$
DECLARE
has_rank BOOLEAN;
deferred BOOLEAN;
BEGIN
{% if debug %}RAISE WARNING 'Delete for % % %/%', OLD.osm_type, OLD.osm_id, OLD.class, OLD.type;{% endif %}
{% if debug %}RAISE WARNING 'delete: % % % %',OLD.osm_type,OLD.osm_id,OLD.class,OLD.type;{% endif %}
-- deleting large polygons can have a massive effect on the system - require manual intervention to let them through
IF st_area(OLD.geometry) > 2 and st_isvalid(OLD.geometry) THEN
SELECT bool_or(not (rank_address = 0 or rank_address > 25)) as ranked FROM placex WHERE osm_type = OLD.osm_type and osm_id = OLD.osm_id and class = OLD.class and type = OLD.type INTO has_rank;
IF has_rank THEN
insert into import_polygon_delete (osm_type, osm_id, class, type) values (OLD.osm_type,OLD.osm_id,OLD.class,OLD.type);
RETURN NULL;
END IF;
deferred := ST_IsValid(OLD.geometry) and ST_Area(OLD.geometry) > 2;
IF deferred THEN
SELECT bool_or(not (rank_address = 0 or rank_address > 25)) INTO deferred
FROM placex
WHERE osm_type = OLD.osm_type and osm_id = OLD.osm_id
and class = OLD.class and type = OLD.type;
END IF;
-- mark for delete
UPDATE placex set indexed_status = 100 where osm_type = OLD.osm_type and osm_id = OLD.osm_id and class = OLD.class and type = OLD.type;
INSERT INTO place_to_be_deleted (osm_type, osm_id, class, type, deferred)
VALUES(OLD.osm_type, OLD.osm_id, OLD.class, OLD.type, deferred);
-- interpolations are special
IF OLD.osm_type='W' and OLD.class = 'place' and OLD.type = 'houses' THEN
UPDATE location_property_osmline set indexed_status = 100 where osm_id = OLD.osm_id; -- osm_id = wayid (=old.osm_id)
END IF;
RETURN OLD;
RETURN NULL;
END;
$$
LANGUAGE plpgsql;
$$ LANGUAGE plpgsql;

View File

@@ -2,7 +2,7 @@
--
-- This file is part of Nominatim. (https://nominatim.org)
--
-- Copyright (C) 2022 by the Nominatim developer community.
-- Copyright (C) 2024 by the Nominatim developer community.
-- For a full list of authors see the git log.
-- Trigger functions for the placex table.
@@ -88,12 +88,18 @@ BEGIN
-- Add all names from the place nodes that deviate from the name
-- in the relation with the prefix '_place_'. Deviation means that
-- either the value is different or a given key is missing completely
SELECT hstore(array_agg('_place_' || key), array_agg(value)) INTO extra_names
FROM each(location.name - result.name);
{% if debug %}RAISE WARNING 'Extra names: %', extra_names;{% endif %}
IF result.name is null THEN
SELECT hstore(array_agg('_place_' || key), array_agg(value))
INTO result.name
FROM each(location.name);
ELSE
SELECT hstore(array_agg('_place_' || key), array_agg(value)) INTO extra_names
FROM each(location.name - result.name);
{% if debug %}RAISE WARNING 'Extra names: %', extra_names;{% endif %}
IF extra_names is not null THEN
result.name := result.name || extra_names;
IF extra_names is not null THEN
result.name := result.name || extra_names;
END IF;
END IF;
{% if debug %}RAISE WARNING 'Final names: %', result.name;{% endif %}
@@ -107,13 +113,20 @@ LANGUAGE plpgsql STABLE;
CREATE OR REPLACE FUNCTION find_associated_street(poi_osm_type CHAR(1),
poi_osm_id BIGINT)
poi_osm_id BIGINT,
bbox GEOMETRY)
RETURNS BIGINT
AS $$
DECLARE
location RECORD;
member JSONB;
parent RECORD;
result BIGINT;
distance FLOAT;
new_distance FLOAT;
waygeom GEOMETRY;
BEGIN
{% if db.middle_db_format == '1' %}
FOR location IN
SELECT members FROM planet_osm_rels
WHERE parts @> ARRAY[poi_osm_id]
@@ -123,19 +136,68 @@ BEGIN
FOR i IN 1..array_upper(location.members, 1) BY 2 LOOP
IF location.members[i+1] = 'street' THEN
FOR parent IN
SELECT place_id from placex
SELECT place_id, geometry
FROM placex
WHERE osm_type = upper(substring(location.members[i], 1, 1))::char(1)
and osm_id = substring(location.members[i], 2)::bigint
and name is not null
and rank_search between 26 and 27
LOOP
RETURN parent.place_id;
-- Find the closest 'street' member.
-- Avoid distance computation for the frequent case where there is
-- only one street member.
IF waygeom is null THEN
result := parent.place_id;
waygeom := parent.geometry;
ELSE
distance := coalesce(distance, ST_Distance(waygeom, bbox));
new_distance := ST_Distance(parent.geometry, bbox);
IF new_distance < distance THEN
distance := new_distance;
result := parent.place_id;
waygeom := parent.geometry;
END IF;
END IF;
END LOOP;
END IF;
END LOOP;
END LOOP;
RETURN NULL;
{% else %}
FOR member IN
SELECT value FROM planet_osm_rels r, LATERAL jsonb_array_elements(members)
WHERE planet_osm_member_ids(members, poi_osm_type::char(1)) && ARRAY[poi_osm_id]
and tags->>'type' = 'associatedStreet'
and value->>'role' = 'street'
LOOP
FOR parent IN
SELECT place_id, geometry
FROM placex
WHERE osm_type = (member->>'type')::char(1)
and osm_id = (member->>'ref')::bigint
and name is not null
and rank_search between 26 and 27
LOOP
-- Find the closest 'street' member.
-- Avoid distance computation for the frequent case where there is
-- only one street member.
IF waygeom is null THEN
result := parent.place_id;
waygeom := parent.geometry;
ELSE
distance := coalesce(distance, ST_Distance(waygeom, bbox));
new_distance := ST_Distance(parent.geometry, bbox);
IF new_distance < distance THEN
distance := new_distance;
result := parent.place_id;
waygeom := parent.geometry;
END IF;
END IF;
END LOOP;
END LOOP;
{% endif %}
RETURN result;
END;
$$
LANGUAGE plpgsql STABLE;
@@ -162,7 +224,7 @@ BEGIN
{% if debug %}RAISE WARNING 'finding street for % %', poi_osm_type, poi_osm_id;{% endif %}
-- Is this object part of an associatedStreet relation?
parent_place_id := find_associated_street(poi_osm_type, poi_osm_id);
parent_place_id := find_associated_street(poi_osm_type, poi_osm_id, bbox);
IF parent_place_id is null THEN
parent_place_id := find_parent_for_address(token_info, poi_partition, bbox);
@@ -185,7 +247,7 @@ BEGIN
RETURN location.place_id;
END IF;
parent_place_id := find_associated_street('W', location.osm_id);
parent_place_id := find_associated_street('W', location.osm_id, bbox);
END LOOP;
END IF;
@@ -197,6 +259,7 @@ BEGIN
SELECT place_id FROM placex
WHERE bbox && geometry AND _ST_Covers(geometry, ST_Centroid(bbox))
AND rank_address between 5 and 25
AND ST_GeometryType(geometry) in ('ST_Polygon','ST_MultiPolygon')
ORDER BY rank_address desc
LOOP
RETURN location.place_id;
@@ -212,6 +275,7 @@ BEGIN
SELECT place_id FROM placex
WHERE bbox && geometry AND _ST_Covers(geometry, ST_Centroid(bbox))
AND rank_address between 5 and 25
AND ST_GeometryType(geometry) in ('ST_Polygon','ST_MultiPolygon')
ORDER BY rank_address desc
LOOP
RETURN location.place_id;
@@ -229,7 +293,11 @@ CREATE OR REPLACE FUNCTION find_linked_place(bnd placex)
RETURNS placex
AS $$
DECLARE
{% if db.middle_db_format == '1' %}
relation_members TEXT[];
{% else %}
relation_members JSONB;
{% endif %}
rel_member RECORD;
linked_placex placex%ROWTYPE;
bnd_name TEXT;
@@ -275,7 +343,9 @@ BEGIN
-- If extratags has a place tag, look for linked nodes by their place type.
-- Area and node still have to have the same name.
IF bnd.extratags ? 'place' and bnd_name is not null THEN
IF bnd.extratags ? 'place' and bnd.extratags->'place' != 'postcode'
and bnd_name is not null
THEN
FOR linked_placex IN
SELECT * FROM placex
WHERE (position(lower(name->'name') in bnd_name) > 0
@@ -284,7 +354,6 @@ BEGIN
AND placex.osm_type = 'N'
AND (placex.linked_place_id is null or placex.linked_place_id = bnd.place_id)
AND placex.rank_search < 26 -- needed to select the right index
AND placex.type != 'postcode'
AND ST_Covers(bnd.geometry, placex.geometry)
LOOP
{% if debug %}RAISE WARNING 'Found type-matching place node %', linked_placex.osm_id;{% endif %}
@@ -412,24 +481,20 @@ BEGIN
name_vector := array_merge(name_vector, hnr_vector);
END IF;
IF is_place_addr THEN
addr_place_ids := token_addr_place_search_tokens(token_info);
IF not addr_place_ids <@ parent_name_vector THEN
-- make sure addr:place terms are always searchable
nameaddress_vector := array_merge(nameaddress_vector, addr_place_ids);
-- If there is a housenumber, also add the place name as a name,
-- so we can search it by the usual housenumber+place algorithms.
IF hnr_vector is not null THEN
name_vector := array_merge(name_vector, addr_place_ids);
END IF;
END IF;
END IF;
-- Cheating here by not recomputing all terms but simply using the ones
-- from the parent object.
nameaddress_vector := array_merge(nameaddress_vector, parent_name_vector);
nameaddress_vector := array_merge(nameaddress_vector, parent_address_vector);
-- make sure addr:place terms are always searchable
IF is_place_addr THEN
addr_place_ids := token_addr_place_search_tokens(token_info);
IF hnr_vector is not null AND not addr_place_ids <@ parent_name_vector
THEN
name_vector := array_merge(name_vector, hnr_vector);
END IF;
nameaddress_vector := array_merge(nameaddress_vector, addr_place_ids);
END IF;
END;
$$
LANGUAGE plpgsql;
@@ -649,6 +714,12 @@ BEGIN
NEW.country_code := NULL;
END IF;
-- Simplify polygons with a very large memory footprint when they
-- do not take part in address computation.
IF NEW.rank_address = 0 THEN
NEW.geometry := simplify_large_polygons(NEW.geometry);
END IF;
END IF;
{% if debug %}RAISE WARNING 'placex_insert:END: % % % %',NEW.osm_type,NEW.osm_id,NEW.class,NEW.type;{% endif %}
@@ -656,10 +727,12 @@ BEGIN
{% if not disable_diff_updates %}
-- The following is not needed until doing diff updates, and slows the main index process down
IF NEW.rank_address > 0 THEN
IF NEW.rank_address between 2 and 27 THEN
IF (ST_GeometryType(NEW.geometry) in ('ST_Polygon','ST_MultiPolygon') AND ST_IsValid(NEW.geometry)) THEN
-- Performance: We just can't handle re-indexing for country level changes
IF st_area(NEW.geometry) < 1 THEN
IF (NEW.rank_address < 26 and st_area(NEW.geometry) < 1)
OR (NEW.rank_address >= 26 and st_area(NEW.geometry) < 0.01)
THEN
-- mark items within the geometry for re-indexing
-- RAISE WARNING 'placex poly insert: % % % %',NEW.osm_type,NEW.osm_id,NEW.class,NEW.type;
@@ -674,9 +747,11 @@ BEGIN
or name is not null
or (NEW.rank_address >= 16 and address ? 'place'));
END IF;
ELSE
ELSEIF ST_GeometryType(NEW.geometry) not in ('ST_LineString', 'ST_MultiLineString')
OR ST_Length(NEW.geometry) < 0.5
THEN
-- mark nearby items for re-indexing, where 'nearby' depends on the features rank_search and is a complete guess :(
diameter := update_place_diameter(NEW.rank_search);
diameter := update_place_diameter(NEW.rank_address);
IF diameter > 0 THEN
-- RAISE WARNING 'placex point insert: % % % % %',NEW.osm_type,NEW.osm_id,NEW.class,NEW.type,diameter;
IF NEW.rank_search >= 26 THEN
@@ -720,7 +795,11 @@ CREATE OR REPLACE FUNCTION placex_update()
DECLARE
i INTEGER;
location RECORD;
{% if db.middle_db_format == '1' %}
relation_members TEXT[];
{% else %}
relation_member JSONB;
{% endif %}
geom GEOMETRY;
parent_address_level SMALLINT;
@@ -765,6 +844,9 @@ BEGIN
result := deleteLocationArea(NEW.partition, NEW.place_id, NEW.rank_search);
NEW.extratags := NEW.extratags - 'linked_place'::TEXT;
IF NEW.extratags = ''::hstore THEN
NEW.extratags := NULL;
END IF;
-- NEW.linked_place_id contains the precomputed linkee. Save this and restore
-- the previous link status.
@@ -846,7 +928,8 @@ BEGIN
FROM placex
WHERE osm_type = 'R' and class = 'boundary' and type = 'administrative'
and admin_level < NEW.admin_level and admin_level > 3
and rank_address > 0
and rank_address between 1 and 25 -- for index selection
and ST_GeometryType(geometry) in ('ST_Polygon','ST_MultiPolygon') -- for index selection
and geometry && NEW.centroid and _ST_Covers(geometry, NEW.centroid)
ORDER BY admin_level desc LIMIT 1
LOOP
@@ -874,8 +957,9 @@ BEGIN
FROM placex,
LATERAL compute_place_rank(country_code, 'A', class, type,
admin_level, False, null) prank
WHERE class = 'place' and rank_address < 24
WHERE class = 'place' and rank_address between 1 and 23
and prank.address_rank >= NEW.rank_address
and ST_GeometryType(geometry) in ('ST_Polygon','ST_MultiPolygon') -- select right index
and geometry && NEW.geometry
and geometry ~ NEW.geometry -- needed because ST_Relate does not do bbox cover test
and ST_Relate(geometry, NEW.geometry, 'T*T***FF*') -- contains but not equal
@@ -896,6 +980,8 @@ BEGIN
LATERAL compute_place_rank(country_code, 'A', class, type,
admin_level, False, null) prank
WHERE prank.address_rank < 24
and rank_address between 1 and 25 -- select right index
and ST_GeometryType(geometry) in ('ST_Polygon','ST_MultiPolygon') -- select right index
and prank.address_rank >= NEW.rank_address
and geometry && NEW.geometry
and geometry ~ NEW.geometry -- needed because ST_Relate does not do bbox cover test
@@ -916,6 +1002,8 @@ BEGIN
LATERAL compute_place_rank(country_code, 'A', class, type,
admin_level, False, null) prank
WHERE osm_type = 'R'
and rank_address between 1 and 25 -- select right index
and ST_GeometryType(geometry) in ('ST_Polygon','ST_MultiPolygon') -- select right index
and ((class = 'place' and prank.address_rank = NEW.rank_address)
or (class = 'boundary' and rank_address = NEW.rank_address))
and geometry && NEW.centroid and _ST_Covers(geometry, NEW.centroid)
@@ -933,6 +1021,7 @@ BEGIN
-- waterway ways are linked when they are part of a relation and have the same class/type
IF NEW.osm_type = 'R' and NEW.class = 'waterway' THEN
{% if db.middle_db_format == '1' %}
FOR relation_members IN select members from planet_osm_rels r where r.id = NEW.osm_id and r.parts != array[]::bigint[]
LOOP
FOR i IN 1..array_upper(relation_members, 1) BY 2 LOOP
@@ -951,12 +1040,35 @@ BEGIN
END IF;
END LOOP;
END LOOP;
{% else %}
FOR relation_member IN
SELECT value FROM planet_osm_rels r, LATERAL jsonb_array_elements(r.members)
WHERE r.id = NEW.osm_id
LOOP
IF relation_member->>'role' IN ('', 'main_stream', 'side_stream')
and relation_member->>'type' = 'W'
THEN
{% if debug %}RAISE WARNING 'waterway parent %, child %', NEW.osm_id, relation_member;{% endif %}
FOR linked_node_id IN
SELECT place_id FROM placex
WHERE osm_type = 'W' and osm_id = (relation_member->>'ref')::bigint
and class = NEW.class and type in ('river', 'stream', 'canal', 'drain', 'ditch')
and (relation_member->>'role' != 'side_stream' or NEW.name->'name' = name->'name')
LOOP
UPDATE placex SET linked_place_id = NEW.place_id WHERE place_id = linked_node_id;
{% if 'search_name' in db.tables %}
DELETE FROM search_name WHERE place_id = linked_node_id;
{% endif %}
END LOOP;
END IF;
END LOOP;
{% endif %}
{% if debug %}RAISE WARNING 'Waterway processed';{% endif %}
END IF;
NEW.importance := null;
SELECT wikipedia, importance
FROM compute_importance(NEW.extratags, NEW.country_code, NEW.osm_type, NEW.osm_id)
FROM compute_importance(NEW.extratags, NEW.country_code, NEW.rank_search, NEW.centroid)
INTO NEW.wikipedia,NEW.importance;
{% if debug %}RAISE WARNING 'Importance computed from wikipedia: %', NEW.importance;{% endif %}
@@ -967,7 +1079,7 @@ BEGIN
{% if debug %}RAISE WARNING 'finding street for % %', NEW.osm_type, NEW.osm_id;{% endif %}
NEW.parent_place_id := null;
is_place_address := coalesce(not NEW.address ? 'street' and NEW.address ? 'place', FALSE);
is_place_address := not token_is_street_address(NEW.token_info);
-- We have to find our parent road.
NEW.parent_place_id := find_parent_for_poi(NEW.osm_type, NEW.osm_id,
@@ -984,7 +1096,7 @@ BEGIN
SELECT p.country_code, p.postcode, p.name FROM placex p
WHERE p.place_id = NEW.parent_place_id INTO location;
IF is_place_address THEN
IF is_place_address and NEW.address ? 'place' THEN
-- Check if the addr:place tag is part of the parent name
SELECT count(*) INTO i
FROM svals(location.name) AS pname WHERE pname = NEW.address->'place';
@@ -1038,7 +1150,7 @@ BEGIN
IF linked_place is not null THEN
-- Recompute the ranks here as the ones from the linked place might
-- have been shifted to accommodate surrounding boundaries.
SELECT place_id, osm_id, class, type, extratags,
SELECT place_id, osm_id, class, type, extratags, rank_search,
centroid, geometry,
(compute_place_rank(country_code, osm_type, class, type, admin_level,
(extratags->'capital') = 'yes', null)).*
@@ -1079,7 +1191,7 @@ BEGIN
SELECT wikipedia, importance
FROM compute_importance(location.extratags, NEW.country_code,
'N', location.osm_id)
location.rank_search, NEW.centroid)
INTO linked_wikipedia,linked_importance;
-- Use the maximum importance if one could be computed from the linked object.
@@ -1091,7 +1203,7 @@ BEGIN
ELSE
-- No linked place? As a last resort check if the boundary is tagged with
-- a place type and adapt the rank address.
IF NEW.rank_address > 0 and NEW.extratags ? 'place' THEN
IF NEW.rank_address between 4 and 25 and NEW.extratags ? 'place' THEN
SELECT address_rank INTO place_address_level
FROM compute_place_rank(NEW.country_code, 'A', 'place',
NEW.extratags->'place', 0::SMALLINT, False, null);
@@ -1153,6 +1265,8 @@ BEGIN
END IF;
ELSEIF NEW.rank_address > 25 THEN
max_rank := 25;
ELSEIF NEW.class in ('place','boundary') and NEW.type in ('postcode','postal_code') THEN
max_rank := NEW.rank_search;
ELSE
max_rank := NEW.rank_address;
END IF;
@@ -1201,8 +1315,14 @@ BEGIN
{% endif %}
END IF;
IF NEW.postcode is null AND NEW.rank_search > 8 THEN
NEW.postcode := get_nearest_postcode(NEW.country_code, NEW.geometry);
IF NEW.postcode is null AND NEW.rank_search > 8
AND (NEW.rank_address > 0
OR ST_GeometryType(NEW.geometry) not in ('ST_LineString','ST_MultiLineString')
OR ST_Length(NEW.geometry) < 0.02)
THEN
NEW.postcode := get_nearest_postcode(NEW.country_code,
CASE WHEN NEW.rank_address > 25
THEN NEW.centroid ELSE NEW.geometry END);
END IF;
{% if debug %}RAISE WARNING 'place update % % finished.', NEW.osm_type, NEW.osm_id;{% endif %}
@@ -1283,6 +1403,8 @@ BEGIN
{% if debug %}RAISE WARNING 'placex_delete:12 % %',OLD.osm_type,OLD.osm_id;{% endif %}
UPDATE location_postcode SET indexed_status = 2 WHERE parent_place_id = OLD.place_id;
RETURN OLD;
END;

View File

@@ -284,3 +284,24 @@ BEGIN
END;
$$
LANGUAGE plpgsql IMMUTABLE;
CREATE OR REPLACE FUNCTION weigh_search(search_vector INT[],
rankings TEXT,
def_weight FLOAT)
RETURNS FLOAT
AS $$
DECLARE
rank JSON;
BEGIN
FOR rank IN
SELECT * FROM json_array_elements(rankings::JSON)
LOOP
IF true = ALL(SELECT x::int = ANY(search_vector) FROM json_array_elements_text(rank->1) as x) THEN
RETURN (rank->>0)::float;
END IF;
END LOOP;
RETURN def_weight;
END;
$$
LANGUAGE plpgsql IMMUTABLE;

View File

@@ -73,6 +73,26 @@ END;
$$
LANGUAGE plpgsql IMMUTABLE;
CREATE OR REPLACE FUNCTION get_rel_node_members(members JSONB, memberLabels TEXT[])
RETURNS SETOF BIGINT
AS $$
DECLARE
member JSONB;
BEGIN
FOR member IN SELECT * FROM jsonb_array_elements(members)
LOOP
IF member->>'type' = 'N' and member->>'role' = ANY(memberLabels) THEN
RETURN NEXT (member->>'ref')::bigint;
END IF;
END LOOP;
RETURN;
END;
$$
LANGUAGE plpgsql IMMUTABLE;
-- Copy 'name' to or from the default language.
--
-- \param country_code Country code of the object being named.
@@ -144,18 +164,44 @@ CREATE OR REPLACE FUNCTION get_country_code(place geometry)
DECLARE
place_centre GEOMETRY;
nearcountry RECORD;
countries TEXT[];
BEGIN
place_centre := ST_PointOnSurface(place);
-- RAISE WARNING 'get_country_code, start: %', ST_AsText(place_centre);
-- Try for a OSM polygon
FOR nearcountry IN
SELECT country_code from location_area_country
WHERE country_code is not null and st_covers(geometry, place_centre) limit 1
LOOP
RETURN nearcountry.country_code;
END LOOP;
SELECT array_agg(country_code) FROM location_area_country
WHERE country_code is not null and st_covers(geometry, place_centre)
INTO countries;
IF array_length(countries, 1) = 1 THEN
RETURN countries[1];
END IF;
IF array_length(countries, 1) > 1 THEN
-- more than one country found, confirm against the fallback data what to choose
FOR nearcountry IN
SELECT country_code FROM country_osm_grid
WHERE ST_Covers(geometry, place_centre) AND country_code = ANY(countries)
ORDER BY area ASC
LOOP
RETURN nearcountry.country_code;
END LOOP;
-- Still nothing? Choose the country code with the smallest partition number.
-- And failing that, just go by the alphabet.
FOR nearcountry IN
SELECT cc,
(SELECT partition FROM country_name WHERE country_code = cc) as partition
FROM unnest(countries) cc
ORDER BY partition, cc
LOOP
RETURN nearcountry.cc;
END LOOP;
-- Should never be reached.
RETURN countries[1];
END IF;
-- RAISE WARNING 'osm fallback: %', ST_AsText(place_centre);
@@ -273,8 +319,8 @@ BEGIN
END IF;
RETURN ST_Envelope(ST_Collect(
ST_Project(geom, radius, 0.785398)::geometry,
ST_Project(geom, radius, 3.9269908)::geometry));
ST_Project(geom::geography, radius, 0.785398)::geometry,
ST_Project(geom::geography, radius, 3.9269908)::geometry));
END;
$$
LANGUAGE plpgsql IMMUTABLE;
@@ -416,6 +462,20 @@ END;
$$
LANGUAGE plpgsql IMMUTABLE;
CREATE OR REPLACE FUNCTION simplify_large_polygons(geometry GEOMETRY)
RETURNS GEOMETRY
AS $$
BEGIN
IF ST_GeometryType(geometry) in ('ST_Polygon','ST_MultiPolygon')
and ST_MemSize(geometry) > 3000000
THEN
geometry := ST_SimplifyPreserveTopology(geometry, 0.0001);
END IF;
RETURN geometry;
END;
$$
LANGUAGE plpgsql IMMUTABLE;
CREATE OR REPLACE FUNCTION place_force_delete(placeid BIGINT)
RETURNS BOOLEAN
@@ -429,9 +489,10 @@ BEGIN
SELECT osm_type, osm_id, class, type FROM placex WHERE place_id = placeid INTO osmtype, osmid, pclass, ptype;
DELETE FROM import_polygon_delete where osm_type = osmtype and osm_id = osmid and class = pclass and type = ptype;
DELETE FROM import_polygon_error where osm_type = osmtype and osm_id = osmid and class = pclass and type = ptype;
-- force delete from place/placex by making it a very small geometry
UPDATE place set geometry = ST_SetSRID(ST_Point(0,0), 4326) where osm_type = osmtype and osm_id = osmid and class = pclass and type = ptype;
DELETE FROM place where osm_type = osmtype and osm_id = osmid and class = pclass and type = ptype;
-- force delete by directly entering it into the to-be-deleted table
INSERT INTO place_to_be_deleted (osm_type, osm_id, class, type, deferred)
VALUES(osmtype, osmid, pclass, ptype, false);
PERFORM flush_deleted_places();
RETURN TRUE;
END;
@@ -486,3 +547,56 @@ BEGIN
END;
$$
LANGUAGE plpgsql;
CREATE OR REPLACE FUNCTION flush_deleted_places()
RETURNS INTEGER
AS $$
BEGIN
-- deleting large polygons can have a massive effect on the system - require manual intervention to let them through
INSERT INTO import_polygon_delete (osm_type, osm_id, class, type)
SELECT osm_type, osm_id, class, type FROM place_to_be_deleted WHERE deferred;
-- delete from place table
ALTER TABLE place DISABLE TRIGGER place_before_delete;
DELETE FROM place USING place_to_be_deleted
WHERE place.osm_type = place_to_be_deleted.osm_type
and place.osm_id = place_to_be_deleted.osm_id
and place.class = place_to_be_deleted.class
and place.type = place_to_be_deleted.type
and not deferred;
ALTER TABLE place ENABLE TRIGGER place_before_delete;
-- Mark for delete in the placex table
UPDATE placex SET indexed_status = 100 FROM place_to_be_deleted
WHERE placex.osm_type = 'N' and place_to_be_deleted.osm_type = 'N'
and placex.osm_id = place_to_be_deleted.osm_id
and placex.class = place_to_be_deleted.class
and placex.type = place_to_be_deleted.type
and not deferred;
UPDATE placex SET indexed_status = 100 FROM place_to_be_deleted
WHERE placex.osm_type = 'W' and place_to_be_deleted.osm_type = 'W'
and placex.osm_id = place_to_be_deleted.osm_id
and placex.class = place_to_be_deleted.class
and placex.type = place_to_be_deleted.type
and not deferred;
UPDATE placex SET indexed_status = 100 FROM place_to_be_deleted
WHERE placex.osm_type = 'R' and place_to_be_deleted.osm_type = 'R'
and placex.osm_id = place_to_be_deleted.osm_id
and placex.class = place_to_be_deleted.class
and placex.type = place_to_be_deleted.type
and not deferred;
-- Mark for delete in interpolations
UPDATE location_property_osmline SET indexed_status = 100 FROM place_to_be_deleted
WHERE place_to_be_deleted.osm_type = 'W'
and place_to_be_deleted.class = 'place'
and place_to_be_deleted.type = 'houses'
and location_property_osmline.osm_id = place_to_be_deleted.osm_id
and not deferred;
-- Clear todo list.
TRUNCATE TABLE place_to_be_deleted;
RETURN NULL;
END;
$$ LANGUAGE plpgsql;

View File

@@ -10,65 +10,105 @@
CREATE INDEX IF NOT EXISTS idx_place_addressline_address_place_id
ON place_addressline USING BTREE (address_place_id) {{db.tablespace.search_index}};
---
CREATE INDEX IF NOT EXISTS idx_placex_rank_search
ON placex USING BTREE (rank_search) {{db.tablespace.search_index}};
---
CREATE INDEX IF NOT EXISTS idx_placex_rank_address
ON placex USING BTREE (rank_address) {{db.tablespace.search_index}};
---
CREATE INDEX IF NOT EXISTS idx_placex_parent_place_id
ON placex USING BTREE (parent_place_id) {{db.tablespace.search_index}}
WHERE parent_place_id IS NOT NULL;
---
-- Used to find postcode areas after a search in location_postcode.
CREATE INDEX IF NOT EXISTS idx_placex_postcode_areas
ON placex USING BTREE (country_code, postcode) {{db.tablespace.search_index}}
WHERE osm_type = 'R' AND class = 'boundary' AND type = 'postal_code';
---
CREATE INDEX IF NOT EXISTS idx_placex_geometry ON placex
USING GIST (geometry) {{db.tablespace.search_index}};
-- Index is needed during import but can be dropped as soon as a full
-- geometry index is in place. The partial index is almost as big as the full
-- index.
---
DROP INDEX IF EXISTS idx_placex_geometry_lower_rank_ways;
---
CREATE INDEX IF NOT EXISTS idx_placex_geometry_reverse_lookupPolygon
ON placex USING gist (geometry) {{db.tablespace.search_index}}
WHERE St_GeometryType(geometry) in ('ST_Polygon', 'ST_MultiPolygon')
AND rank_address between 4 and 25 AND type != 'postcode'
AND name is not null AND indexed_status = 0 AND linked_place_id is null;
---
-- used in reverse large area lookup
CREATE INDEX IF NOT EXISTS idx_placex_geometry_reverse_lookupPlaceNode
ON placex USING gist (ST_Buffer(geometry, reverse_place_diameter(rank_search)))
{{db.tablespace.search_index}}
WHERE rank_address between 4 and 25 AND type != 'postcode'
AND name is not null AND linked_place_id is null AND osm_type = 'N';
---
CREATE INDEX IF NOT EXISTS idx_osmline_parent_place_id
ON location_property_osmline USING BTREE (parent_place_id) {{db.tablespace.search_index}}
WHERE parent_place_id is not null;
---
CREATE INDEX IF NOT EXISTS idx_osmline_parent_osm_id
ON location_property_osmline USING BTREE (osm_id) {{db.tablespace.search_index}};
---
CREATE INDEX IF NOT EXISTS idx_postcode_postcode
ON location_postcode USING BTREE (postcode) {{db.tablespace.search_index}};
{% if drop %}
---
DROP INDEX IF EXISTS idx_placex_geometry_address_area_candidates;
DROP INDEX IF EXISTS idx_placex_geometry_buildings;
DROP INDEX IF EXISTS idx_placex_wikidata;
DROP INDEX IF EXISTS idx_placex_rank_address_sector;
DROP INDEX IF EXISTS idx_placex_rank_boundaries_sector;
{% else %}
-- Indices only needed for updating.
{% if not drop %}
CREATE INDEX IF NOT EXISTS idx_placex_pendingsector
ON placex USING BTREE (rank_address,geometry_sector) {{db.tablespace.address_index}}
WHERE indexed_status > 0;
---
CREATE INDEX IF NOT EXISTS idx_location_area_country_place_id
ON location_area_country USING BTREE (place_id) {{db.tablespace.address_index}};
---
CREATE UNIQUE INDEX IF NOT EXISTS idx_place_osm_unique
ON place USING btree(osm_id, osm_type, class, type) {{db.tablespace.address_index}};
---
-- Table needed for running updates with osm2pgsql on place.
CREATE TABLE IF NOT EXISTS place_to_be_deleted (
osm_type CHAR(1),
osm_id BIGINT,
class TEXT,
type TEXT,
deferred BOOLEAN
);
---
CREATE INDEX IF NOT EXISTS idx_location_postcode_parent_place_id
ON location_postcode USING BTREE (parent_place_id) {{db.tablespace.address_index}};
{% endif %}
-- Indices only needed for search.
{% if 'search_name' in db.tables %}
---
CREATE INDEX IF NOT EXISTS idx_search_name_nameaddress_vector
ON search_name USING GIN (nameaddress_vector) WITH (fastupdate = off) {{db.tablespace.search_index}};
---
CREATE INDEX IF NOT EXISTS idx_search_name_name_vector
ON search_name USING GIN (name_vector) WITH (fastupdate = off) {{db.tablespace.search_index}};
---
CREATE INDEX IF NOT EXISTS idx_search_name_centroid
ON search_name USING GIST (centroid) {{db.tablespace.search_index}};
{% if postgres.has_index_non_key_column %}
---
CREATE INDEX IF NOT EXISTS idx_placex_housenumber
ON placex USING btree (parent_place_id)
INCLUDE (housenumber) {{db.tablespace.search_index}}
WHERE housenumber is not null;
---
CREATE INDEX IF NOT EXISTS idx_osmline_parent_osm_id_with_hnr
ON location_property_osmline USING btree(parent_place_id)
INCLUDE (startnumber, endnumber) {{db.tablespace.search_index}}
WHERE startnumber is not null;
{% endif %}
{% endif %}

View File

@@ -137,7 +137,9 @@ CREATE TABLE place_addressline (
) {{db.tablespace.search_data}};
CREATE INDEX idx_place_addressline_place_id on place_addressline USING BTREE (place_id) {{db.tablespace.search_index}};
drop table if exists placex;
--------- PLACEX - storage for all indexed places -----------------
DROP TABLE IF EXISTS placex;
CREATE TABLE placex (
place_id BIGINT NOT NULL,
parent_place_id BIGINT,
@@ -157,20 +159,65 @@ CREATE TABLE placex (
postcode TEXT,
centroid GEOMETRY(Geometry, 4326)
) {{db.tablespace.search_data}};
CREATE UNIQUE INDEX idx_place_id ON placex USING BTREE (place_id) {{db.tablespace.search_index}};
CREATE INDEX idx_placex_osmid ON placex USING BTREE (osm_type, osm_id) {{db.tablespace.search_index}};
CREATE INDEX idx_placex_linked_place_id ON placex USING BTREE (linked_place_id) {{db.tablespace.address_index}} WHERE linked_place_id IS NOT NULL;
CREATE INDEX idx_placex_rank_search ON placex USING BTREE (rank_search, geometry_sector) {{db.tablespace.address_index}};
CREATE INDEX idx_placex_geometry ON placex USING GIST (geometry) {{db.tablespace.search_index}};
{% for osm_type in ('N', 'W', 'R') %}
CREATE INDEX idx_placex_osmid_{{osm_type | lower}} ON placex
USING BTREE (osm_id) {{db.tablespace.search_index}}
WHERE osm_type = '{{osm_type}}';
{% endfor %}
-- Usage: - removing linkage status on update
-- - lookup linked places for /details
CREATE INDEX idx_placex_linked_place_id ON placex
USING BTREE (linked_place_id) {{db.tablespace.address_index}}
WHERE linked_place_id IS NOT NULL;
-- Usage: - check that admin boundaries do not overtake each other rank-wise
-- - check that place node in a admin boundary with the same address level
-- - boundary is not completely contained in a place area
-- - parenting of large-area or unparentable features
CREATE INDEX idx_placex_geometry_address_area_candidates ON placex
USING gist (geometry) {{db.tablespace.address_index}}
WHERE rank_address between 1 and 25
and ST_GeometryType(geometry) in ('ST_Polygon','ST_MultiPolygon');
-- Usage: - POI is within building with housenumber
CREATE INDEX idx_placex_geometry_buildings ON placex
USING {{postgres.spgist_geom}} (geometry) {{db.tablespace.search_index}}
USING {{postgres.spgist_geom}} (geometry) {{db.tablespace.address_index}}
WHERE address is not null and rank_search = 30
and ST_GeometryType(geometry) in ('ST_Polygon','ST_MultiPolygon');
-- Usage: - linking of similar named places to boundaries
-- - linking of place nodes with same type to boundaries
CREATE INDEX idx_placex_geometry_placenode ON placex
USING {{postgres.spgist_geom}} (geometry) {{db.tablespace.search_index}}
USING {{postgres.spgist_geom}} (geometry) {{db.tablespace.address_index}}
WHERE osm_type = 'N' and rank_search < 26
and class = 'place' and type != 'postcode' and linked_place_id is null;
CREATE INDEX idx_placex_wikidata on placex USING BTREE ((extratags -> 'wikidata')) {{db.tablespace.address_index}} WHERE extratags ? 'wikidata' and class = 'place' and osm_type = 'N' and rank_search < 26;
and class = 'place' and type != 'postcode';
-- Usage: - is node part of a way?
-- - find parent of interpolation spatially
CREATE INDEX idx_placex_geometry_lower_rank_ways ON placex
USING {{postgres.spgist_geom}} (geometry) {{db.tablespace.address_index}}
WHERE osm_type = 'W' and rank_search >= 26;
-- Usage: - linking place nodes by wikidata tag to boundaries
CREATE INDEX idx_placex_wikidata on placex
USING BTREE ((extratags -> 'wikidata')) {{db.tablespace.address_index}}
WHERE extratags ? 'wikidata' and class = 'place'
and osm_type = 'N' and rank_search < 26;
-- The following two indexes function as a todo list for indexing.
CREATE INDEX idx_placex_rank_address_sector ON placex
USING BTREE (rank_address, geometry_sector) {{db.tablespace.address_index}}
WHERE indexed_status > 0;
CREATE INDEX idx_placex_rank_boundaries_sector ON placex
USING BTREE (rank_search, geometry_sector) {{db.tablespace.address_index}}
WHERE class = 'boundary' and type = 'administrative'
and indexed_status > 0;
DROP SEQUENCE IF EXISTS seq_place;
CREATE SEQUENCE seq_place start 1;
@@ -226,35 +273,27 @@ GRANT SELECT ON import_polygon_delete TO "{{config.DATABASE_WEBUSER}}";
DROP SEQUENCE IF EXISTS file;
CREATE SEQUENCE file start 1;
-- null table so it won't error
-- deliberately no drop - importing the table is expensive and static, if it is already there better to avoid removing it
CREATE TABLE wikipedia_article (
language text NOT NULL,
title text NOT NULL,
langcount integer,
othercount integer,
totalcount integer,
lat double precision,
lon double precision,
importance double precision,
osm_type character(1),
osm_id bigint,
wd_page_title text,
instance_of text
);
ALTER TABLE ONLY wikipedia_article ADD CONSTRAINT wikipedia_article_pkey PRIMARY KEY (language, title);
CREATE INDEX idx_wikipedia_article_osm_id ON wikipedia_article USING btree (osm_type, osm_id);
CREATE TABLE wikipedia_redirect (
language text,
from_title text,
to_title text
);
ALTER TABLE ONLY wikipedia_redirect ADD CONSTRAINT wikipedia_redirect_pkey PRIMARY KEY (language, from_title);
{% if 'wikimedia_importance' not in db.tables and 'wikipedia_article' not in db.tables %}
-- create dummy tables here, if nothing was imported
CREATE TABLE wikimedia_importance (
language TEXT NOT NULL,
title TEXT NOT NULL,
importance double precision NOT NULL,
wikidata TEXT
) {{db.tablespace.address_data}};
{% endif %}
-- osm2pgsql does not create indexes on the middle tables for Nominatim
-- Add one for lookup of associated street relations.
CREATE INDEX planet_osm_rels_parts_associated_idx ON planet_osm_rels USING gin(parts) WHERE tags @> ARRAY['associatedStreet'];
{% if db.middle_db_format == '1' %}
CREATE INDEX planet_osm_rels_parts_associated_idx ON planet_osm_rels USING gin(parts)
{{db.tablespace.address_index}}
WHERE tags @> ARRAY['associatedStreet'];
{% else %}
CREATE INDEX planet_osm_rels_relation_members_idx ON planet_osm_rels USING gin(planet_osm_member_ids(members, 'R'::character(1)))
WITH (fastupdate=off)
{{db.tablespace.address_index}};
{% endif %}
-- Needed for lookups if a node is part of an interpolation.
CREATE INDEX IF NOT EXISTS idx_place_interpolations

View File

@@ -41,10 +41,17 @@ AS $$
$$ LANGUAGE SQL IMMUTABLE STRICT;
CREATE OR REPLACE FUNCTION token_is_street_address(info JSONB)
RETURNS BOOLEAN
AS $$
SELECT info->>'street' is not null or info->>'place' is null;
$$ LANGUAGE SQL IMMUTABLE;
CREATE OR REPLACE FUNCTION token_has_addr_street(info JSONB)
RETURNS BOOLEAN
AS $$
SELECT info->>'street' is not null;
SELECT info->>'street' is not null and info->>'street' != '{}';
$$ LANGUAGE SQL IMMUTABLE;

View File

@@ -1,40 +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.
DROP TABLE IF EXISTS word;
CREATE TABLE word (
word_id INTEGER,
word_token text NOT NULL,
type text NOT NULL,
word text,
info jsonb
) {{db.tablespace.search_data}};
CREATE INDEX idx_word_word_token ON word
USING BTREE (word_token) {{db.tablespace.search_index}};
-- Used when updating country names from the boundary relation.
CREATE INDEX idx_word_country_names ON word
USING btree(word) {{db.tablespace.address_index}}
WHERE type = 'C';
-- Used when inserting new postcodes on updates.
CREATE INDEX idx_word_postcodes ON word
USING btree(word) {{db.tablespace.address_index}}
WHERE type = 'P';
-- Used when inserting full words.
CREATE INDEX idx_word_full_word ON word
USING btree(word) {{db.tablespace.address_index}}
WHERE type = 'W';
-- Used when inserting analyzed housenumbers (exclude old-style entries).
CREATE INDEX idx_word_housenumbers ON word
USING btree(word) {{db.tablespace.address_index}}
WHERE type = 'H' and word is not null;
GRANT SELECT ON word TO "{{config.DATABASE_WEBUSER}}";
DROP SEQUENCE IF EXISTS seq_word;
CREATE SEQUENCE seq_word start 1;
GRANT SELECT ON seq_word to "{{config.DATABASE_WEBUSER}}";

View File

@@ -41,10 +41,17 @@ AS $$
$$ LANGUAGE SQL IMMUTABLE STRICT;
CREATE OR REPLACE FUNCTION token_is_street_address(info JSONB)
RETURNS BOOLEAN
AS $$
SELECT info->>'street' is not null or info->>'place_search' is null;
$$ LANGUAGE SQL IMMUTABLE;
CREATE OR REPLACE FUNCTION token_has_addr_street(info JSONB)
RETURNS BOOLEAN
AS $$
SELECT info->>'street' is not null;
SELECT info->>'street' is not null and info->>'street' != '{}';
$$ LANGUAGE SQL IMMUTABLE;
@@ -340,7 +347,7 @@ BEGIN
END LOOP;
END IF;
-- consider parts before an opening braket a full word as well
-- consider parts before an opening bracket a full word as well
words := regexp_split_to_array(value, E'[(]');
IF array_upper(words, 1) > 1 THEN
s := make_standard_name(words[1]);

View File

@@ -1,15 +0,0 @@
# Creates and installs manual page
configure_file(${CMAKE_CURRENT_SOURCE_DIR}/create-manpage.tmpl create_manpage.py)
find_program(ARGPARSEMANPAGE argparse-manpage)
ADD_CUSTOM_TARGET(manpage
COMMAND ${ARGPARSEMANPAGE} --pyfile ${CMAKE_CURRENT_BINARY_DIR}/create_manpage.py
--function get_parser --project-name Nominatim
--url https://nominatim.org > ${CMAKE_CURRENT_SOURCE_DIR}/nominatim.1
--author 'the Nominatim developer community'
--author-email info@nominatim.org
)
install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/nominatim.1 DESTINATION share/man/man1 )

12
man/create-manpage.py Normal file
View File

@@ -0,0 +1,12 @@
import sys
import os
from pathlib import Path
sys.path.append(str(Path(__file__, '..', '..', 'src').resolve()))
from nominatim_db.cli import get_set_parser
def get_parser():
parser = get_set_parser()
return parser.parser

View File

@@ -1,12 +0,0 @@
#!/usr/bin/env python3
import sys
import os
sys.path.append('@PROJECT_SOURCE_DIR@')
from nominatim.cli import get_set_parser
def get_parser():
parser = get_set_parser(phpcgi_path='@PHPCGI_BIN@')
return parser.parser

View File

@@ -3,7 +3,7 @@
nominatim
.SH SYNOPSIS
.B nominatim
[-h] {import,freeze,replication,special-phrases,add-data,index,refresh,admin,export,serve,search,reverse,lookup,details,status} ...
[-h] [--version] {import,freeze,replication,special-phrases,add-data,index,refresh,admin,export,convert,serve,search,reverse,lookup,details,status} ...
.SH DESCRIPTION
Command\-line tools for importing, updating, administrating and
.br
@@ -12,6 +12,9 @@ nominatim
.SH OPTIONS
.TP
\fB\-\-version\fR
Print Nominatim version and exit
.SS
\fBSub-commands\fR
@@ -41,7 +44,10 @@ nominatim
Analyse and maintain the database.
.TP
\fBnominatim\fR \fI\,export\/\fR
Export addresses as CSV file from the database.
Export places as CSV file from the database.
.TP
\fBnominatim\fR \fI\,convert\/\fR
Convert an existing database into a different format. (EXPERIMENTAL)
.TP
\fBnominatim\fR \fI\,serve\/\fR
Start a simple web server for serving the API.
@@ -59,13 +65,15 @@ nominatim
Execute API details query.
.TP
\fBnominatim\fR \fI\,status\/\fR
Execute API status query.
.SH OPTIONS 'nominatim import'
usage: nominatim import [-h] [-q] [-v] [--project-dir DIR] [-j NUM]
(--osm-file FILE | --continue {load-data,indexing,db-postprocess})
[--osm-file FILE]
[--continue {import-from-file,load-data,indexing,db-postprocess}]
[--osm2pgsql-cache SIZE] [--reverse-only]
[--no-partitions] [--no-updates] [--ignore-errors]
[--index-noanalyse]
[--no-partitions] [--no-updates] [--offline]
[--ignore-errors] [--index-noanalyse]
[--prepare-database]
Create a new Nominatim database from an OSM file.
.br
@@ -102,7 +110,7 @@ Number of parallel threads to use
OSM file to be imported (repeat for importing multiple files)
.TP
\fB\-\-continue\fR {load\-data,indexing,db\-postprocess}
\fB\-\-continue\fR {import\-from\-file,load\-data,indexing,db\-postprocess}
Continue an import that was interrupted
.TP
@@ -121,6 +129,10 @@ Do not partition search indices (speeds up import of single country extracts)
\fB\-\-no\-updates\fR
Do not keep tables that are only needed for updating the database later
.TP
\fB\-\-offline\fR
Do not attempt to load any additional data from the internet
.TP
\fB\-\-ignore\-errors\fR
Continue import even when errors in SQL are present
@@ -129,6 +141,10 @@ Continue import even when errors in SQL are present
\fB\-\-index\-noanalyse\fR
Do not perform analyse operations during index (expert only)
.TP
\fB\-\-prepare\-database\fR
Create the database but do not import any data
.SH OPTIONS 'nominatim freeze'
usage: nominatim freeze [-h] [-q] [-v] [--project-dir DIR] [-j NUM]
@@ -171,8 +187,8 @@ Number of parallel threads to use
.SH OPTIONS 'nominatim replication'
usage: nominatim replication [-h] [-q] [-v] [--project-dir DIR] [-j NUM]
[--init] [--no-update-functions]
[--check-for-updates] [--once] [--no-index]
[--osm2pgsql-cache SIZE]
[--check-for-updates] [--once] [--catch-up]
[--no-index] [--osm2pgsql-cache SIZE]
[--socket-timeout SOCKET_TIMEOUT]
Update the database using an online replication service.
@@ -229,7 +245,7 @@ Initialise the update process
.TP
\fB\-\-no\-update\-functions\fR
Do not update the trigger function to support differential updates.
Do not update the trigger function to support differential updates (EXPERT)
.TP
\fB\-\-check\-for\-updates\fR
@@ -239,6 +255,10 @@ Check if new updates are available and exit
\fB\-\-once\fR
Download and apply updates only once. When not set, updates are continuously applied
.TP
\fB\-\-catch\-up\fR
Download and apply updates until no new data is available on the server
.TP
\fB\-\-no\-index\fR
Do not index the new data. Only usable together with \-\-once
@@ -290,6 +310,20 @@ usage: nominatim special-phrases [-h] [-q] [-v] [--project-dir DIR] [-j NUM]
.br
'test/testdb/full_en_phrases_test.csv'.
.br
.br
The import can be further configured to ignore specific key/value pairs.
.br
This is particularly useful when importing phrases from the wiki. The
.br
default configuration excludes some very common tags like building=yes.
.br
The configuration can be customized by putting a file `phrase\-settings.json`
.br
with custom rules into the project directory or by using the `\-\-config`
.br
option to point to another configuration file.
.br
@@ -350,7 +384,7 @@ usage: nominatim add-data [-h] [-q] [-v] [--project-dir DIR] [-j NUM]
.br
data. See the online documentation at
.br
https://nominatim.org/release\-docs/latest/admin/Import/#installing\-tiger\-housenumber\-data\-for\-the\-us
https://nominatim.org/release\-docs/latest/customize/Tiger/
.br
for more information.
.br
@@ -465,10 +499,11 @@ Maximum/finishing rank
.SH OPTIONS 'nominatim refresh'
usage: nominatim refresh [-h] [-q] [-v] [--project-dir DIR] [-j NUM]
[--postcodes] [--word-counts] [--address-levels]
[--functions] [--wiki-data] [--importance]
[--website] [--no-diff-updates]
[--enable-debug-statements]
[--postcodes] [--word-tokens] [--word-counts]
[--address-levels] [--functions] [--wiki-data]
[--secondary-importance] [--importance] [--website]
[--data-object OBJECT] [--data-area OBJECT]
[--no-diff-updates] [--enable-debug-statements]
Recompute auxiliary data used by the indexing process.
.br
@@ -512,6 +547,10 @@ Number of parallel threads to use
\fB\-\-postcodes\fR
Update postcode centroid table
.TP
\fB\-\-word\-tokens\fR
Clean up search terms
.TP
\fB\-\-word\-counts\fR
Compute frequency of full\-word search terms
@@ -528,6 +567,10 @@ Update the PL/pgSQL functions in the database
\fB\-\-wiki\-data\fR
Update Wikipedia/data importance numbers
.TP
\fB\-\-secondary\-importance\fR
Update secondary importance raster data
.TP
\fB\-\-importance\fR
Recompute place importances (expensive!)
@@ -536,6 +579,14 @@ Recompute place importances (expensive!)
\fB\-\-website\fR
Refresh the directory that serves the scripts for the web API
.TP
\fB\-\-data\-object\fR OBJECT
Mark the given OSM object as requiring an update (format: [NWR]<id>)
.TP
\fB\-\-data\-area\fR OBJECT
Mark the area around the given OSM object as requiring an update (format: [NWR]<id>)
.TP
\fB\-\-no\-diff\-updates\fR
Do not enable code for propagating updates
@@ -546,7 +597,7 @@ Enable debug warning statements in functions
.SH OPTIONS 'nominatim admin'
usage: nominatim admin [-h] [-q] [-v] [--project-dir DIR] [-j NUM]
(--warm | --check-database | --migrate | --analyse-indexing)
(--warm | --check-database | --migrate | --analyse-indexing | --collect-os-info | --clean-deleted AGE)
[--search-only] [--reverse-only]
[--osm-id OSM_ID | --place-id PLACE_ID]
@@ -588,6 +639,14 @@ Migrate the database to a new software version
\fB\-\-analyse\-indexing\fR
Print performance analysis of the indexing process
.TP
\fB\-\-collect\-os\-info\fR
Generate a report about the host system information
.TP
\fB\-\-clean\-deleted\fR AGE
Clean up deleted relations
.TP
\fB\-\-search\-only\fR
Only pre\-warm tables for search queries
@@ -606,14 +665,17 @@ Analyse indexing of the given Nominatim object
.SH OPTIONS 'nominatim export'
usage: nominatim export [-h] [-q] [-v] [--project-dir DIR] [-j NUM]
[--output-type {continent,country,state,county,city,suburb,street,path}]
[--output-format OUTPUT_FORMAT]
[--output-all-postcodes] [--language LANGUAGE]
[--output-type {country,state,county,city,suburb,street,path}]
[--output-format OUTPUT_FORMAT] [--language LANGUAGE]
[--restrict-to-country COUNTRY_CODE]
[--restrict-to-osm-node ID] [--restrict-to-osm-way ID]
[--restrict-to-osm-relation ID]
Export addresses as CSV file from the database.
Export places as CSV file from the database.
.br
.br
.br
@@ -636,16 +698,12 @@ Base directory of the Nominatim installation (default:.)
Number of parallel threads to use
.TP
\fB\-\-output\-type\fR {continent,country,state,county,city,suburb,street,path}
\fB\-\-output\-type\fR {country,state,county,city,suburb,street,path}
Type of places to output (default: street)
.TP
\fB\-\-output\-format\fR \fI\,OUTPUT_FORMAT\/\fR
Semicolon\-separated list of address types (see \-\-output\-type). Multiple ranks can be merged into one column by simply using a comma\-separated list.
.TP
\fB\-\-output\-all\-postcodes\fR
List all postcodes for address instead of just the most likely one
Semicolon\-separated list of address types (see \-\-output\-type). Additionally accepts:placeid,postcode
.TP
\fB\-\-language\fR \fI\,LANGUAGE\/\fR
@@ -667,21 +725,85 @@ Export only children of this OSM way
\fB\-\-restrict\-to\-osm\-relation\fR ID
Export only children of this OSM relation
.SH OPTIONS 'nominatim convert'
usage: nominatim convert [-h] [-q] [-v] [--project-dir DIR] [-j NUM]
[--format {sqlite}] --output OUTPUT [--with-reverse]
[--with-search] [--with-details]
Convert an existing database into a different format. (EXPERIMENTAL)
.br
.br
Dump a read\-only version of the database in a different format.
.br
At the moment only a SQLite database suitable for reverse lookup
.br
can be created.
.br
.TP
\fB\-\-format\fR {sqlite}
Format of the output database (must be sqlite currently)
.TP
\fB\-\-output\fR \fI\,OUTPUT\/\fR, \fB\-o\fR \fI\,OUTPUT\/\fR
File to write the database to.
.TP
\fB\-q\fR, \fB\-\-quiet\fR
Print only error messages
.TP
\fB\-v\fR, \fB\-\-verbose\fR
Increase verboseness of output
.TP
\fB\-\-project\-dir\fR DIR
Base directory of the Nominatim installation (default:.)
.TP
\fB\-j\fR NUM, \fB\-\-threads\fR NUM
Number of parallel threads to use
.TP
\fB\-\-with\-reverse\fR, \fB\-\-without\-reverse\fR
Enable/disable support for reverse and lookup API (default: enabled)
.TP
\fB\-\-with\-search\fR, \fB\-\-without\-search\fR
Enable/disable support for search API (default: disabled)
.TP
\fB\-\-with\-details\fR, \fB\-\-without\-details\fR
Enable/disable support for details API (default: enabled)
.SH OPTIONS 'nominatim serve'
usage: nominatim serve [-h] [-q] [-v] [--project-dir DIR] [-j NUM]
[--server SERVER]
[--server SERVER] [--engine {php,falcon,starlette}]
Start a simple web server for serving the API.
.br
.br
This command starts the built\-in PHP webserver to serve the website
This command starts a built\-in webserver to serve the website
.br
from the current project directory. This webserver is only suitable
.br
for testing and development. Do not use it in production setups!
.br
.br
There are different webservers available. The default 'php' engine
.br
runs the classic PHP frontend. The other engines are Python servers
.br
which run the new Python frontend code. This is highly experimental
.br
at the moment and may not include the full API.
.br
.br
By the default, the webserver can be accessed at: http://127.0.0.1:8088
.br
@@ -709,12 +831,16 @@ Number of parallel threads to use
\fB\-\-server\fR \fI\,SERVER\/\fR
The address the server will listen to.
.TP
\fB\-\-engine\fR {php,falcon,starlette}
Webserver framework to run. (default: falcon)
.SH OPTIONS 'nominatim search'
usage: nominatim search [-h] [-q] [-v] [--project-dir DIR] [-j NUM]
[--query QUERY] [--street STREET] [--city CITY]
[--county COUNTY] [--state STATE] [--country COUNTRY]
[--postalcode POSTALCODE]
[--format {xml,json,jsonv2,geojson,geocodejson}]
[--query QUERY] [--amenity AMENITY] [--street STREET]
[--city CITY] [--county COUNTY] [--state STATE]
[--country COUNTRY] [--postalcode POSTALCODE]
[--format {xml,geojson,geocodejson,json,jsonv2,debug}]
[--addressdetails] [--extratags] [--namedetails]
[--lang LANGS]
[--polygon-output {geojson,kml,svg,text}]
@@ -758,6 +884,10 @@ Number of parallel threads to use
\fB\-\-query\fR \fI\,QUERY\/\fR
Free\-form query string
.TP
\fB\-\-amenity\fR \fI\,AMENITY\/\fR
Structured query: name and/or type of POI
.TP
\fB\-\-street\fR \fI\,STREET\/\fR
Structured query: housenumber and street
@@ -783,7 +913,7 @@ Structured query: country
Structured query: postcode
.TP
\fB\-\-format\fR {xml,json,jsonv2,geojson,geocodejson}
\fB\-\-format\fR {xml,geojson,geocodejson,json,jsonv2,debug}
Format of result
.TP
@@ -836,8 +966,8 @@ Do not remove duplicates from the result list
.SH OPTIONS 'nominatim reverse'
usage: nominatim reverse [-h] [-q] [-v] [--project-dir DIR] [-j NUM] --lat LAT
--lon LON [--zoom ZOOM]
[--format {xml,json,jsonv2,geojson,geocodejson}]
--lon LON [--zoom ZOOM] [--layer LAYER]
[--format {xml,geojson,geocodejson,json,jsonv2,debug}]
[--addressdetails] [--extratags] [--namedetails]
[--lang LANGS]
[--polygon-output {geojson,kml,svg,text}]
@@ -888,7 +1018,11 @@ Longitude of coordinate to look up (in WGS84)
Level of detail required for the address
.TP
\fB\-\-format\fR {xml,json,jsonv2,geojson,geocodejson}
\fB\-\-layer\fR LAYER
OSM id to lookup in format <NRW><id> (may be repeated)
.TP
\fB\-\-format\fR {xml,geojson,geocodejson,json,jsonv2,debug}
Format of result
.TP
@@ -917,7 +1051,7 @@ Simplify output geometry.Parameter is difference tolerance in degrees.
.SH OPTIONS 'nominatim lookup'
usage: nominatim lookup [-h] [-q] [-v] [--project-dir DIR] [-j NUM] --id OSMID
[--format {xml,json,jsonv2,geojson,geocodejson}]
[--format {xml,geojson,geocodejson,json,jsonv2,debug}]
[--addressdetails] [--extratags] [--namedetails]
[--lang LANGS]
[--polygon-output {geojson,kml,svg,text}]
@@ -960,7 +1094,7 @@ Number of parallel threads to use
OSM id to lookup in format <NRW><id> (may be repeated)
.TP
\fB\-\-format\fR {xml,json,jsonv2,geojson,geocodejson}
\fB\-\-format\fR {xml,geojson,geocodejson,json,jsonv2,debug}
Format of result
.TP

View File

@@ -1,6 +1,14 @@
site_name: Nominatim Documentation
theme: readthedocs
docs_dir: ${CMAKE_CURRENT_BINARY_DIR}
site_name: Nominatim Manual
theme:
font: false
name: material
features:
- navigation.tabs
- toc.integrate
plugins:
- privacy
copyright: Copyright &copy; Nominatim developer community
docs_dir: docs
site_url: https://nominatim.org
repo_url: https://github.com/openstreetmap/Nominatim
nav:
@@ -18,22 +26,35 @@ nav:
- 'Basic Installation': 'admin/Installation.md'
- 'Import' : 'admin/Import.md'
- 'Update' : 'admin/Update.md'
- 'Deploy' : 'admin/Deployment.md'
- 'Deploy (Python frontend)' : 'admin/Deployment-Python.md'
- 'Deploy (PHP frontend)' : 'admin/Deployment-PHP.md'
- 'Nominatim UI' : 'admin/Setup-Nominatim-UI.md'
- 'Advanced Installations' : 'admin/Advanced-Installations.md'
- 'Maintenance' : 'admin/Maintenance.md'
- 'Migration from older Versions' : 'admin/Migration.md'
- 'Troubleshooting' : 'admin/Faq.md'
- 'Installation on Ubuntu 22' : 'admin/Install-on-Ubuntu-22.md'
- 'Installation on Ubuntu 24' : 'admin/Install-on-Ubuntu-24.md'
- 'Customization Guide':
- 'Overview': 'customize/Overview.md'
- 'Import Styles': 'customize/Import-Styles.md'
- 'Configuration Settings': 'customize/Settings.md'
- 'API Result Formatting': 'customize/Result-Formatting.md'
- 'Per-Country Data': 'customize/Country-Settings.md'
- 'Place Ranking' : 'customize/Ranking.md'
- 'Importance' : 'customize/Importance.md'
- 'Tokenizers' : 'customize/Tokenizers.md'
- 'Special Phrases': 'customize/Special-Phrases.md'
- 'External data: US housenumbers from TIGER': 'customize/Tiger.md'
- 'External data: Postcodes': 'customize/Postcodes.md'
- 'Conversion to SQLite': 'customize/SQLite.md'
- 'Library Guide':
- 'Getting Started': 'library/Getting-Started.md'
- 'Nominatim API class': 'library/NominatimAPI.md'
- 'Configuration': 'library/Configuration.md'
- 'Input Parameter Types': 'library/Input-Parameter-Types.md'
- 'Result Handling': 'library/Result-Handling.md'
- 'Low-level DB Access': 'library/Low-Level-DB-Access.md'
- 'Developers Guide':
- 'Architecture Overview' : 'develop/overview.md'
- 'Database Layout' : 'develop/Database-Layout.md'
@@ -43,22 +64,29 @@ nav:
- 'Setup for Development' : 'develop/Development-Environment.md'
- 'Testing' : 'develop/Testing.md'
- 'External Data Sources': 'develop/data-sources.md'
- 'Appendix':
- 'Installation on Ubuntu 18' : 'appendix/Install-on-Ubuntu-18.md'
- 'Installation on Ubuntu 20' : 'appendix/Install-on-Ubuntu-20.md'
- 'Installation on Ubuntu 22' : 'appendix/Install-on-Ubuntu-22.md'
markdown_extensions:
- codehilite
- admonition
- pymdownx.superfences
- pymdownx.tabbed:
alternate_style: true
- def_list
- toc:
permalink:
toc_depth: 4
permalink: 🔗
extra_css: [extra.css, styles.css]
exclude_docs: |
mk_install_instructions.py
site_dir: site-html
plugins:
- search
- mkdocstrings:
handlers:
python-legacy:
rendering:
show_source: false
show_signature_annotations: false
python:
paths: ["src"]
options:
show_source: False
show_bases: False
- gen-files:
scripts:
- docs/mk_install_instructions.py

View File

@@ -1,6 +1,6 @@
# just use the pgxs makefile
foreach(suffix ${PostgreSQL_ADDITIONAL_VERSIONS} "14" "13" "12" "11" "10" "9.6")
foreach(suffix ${PostgreSQL_ADDITIONAL_VERSIONS} "16" "15" "14" "13" "12" "11" "10" "9.6")
list(APPEND PG_CONFIG_HINTS
"/usr/pgsql-${suffix}/bin")
endforeach()

View File

@@ -11,10 +11,12 @@
#include "mb/pg_wchar.h"
#include <utfasciitable.h>
#ifdef PG_MODULE_MAGIC
PG_MODULE_MAGIC;
#if PG_MAJORVERSION_NUM > 15
#include "varatt.h"
#endif
PG_MODULE_MAGIC;
Datum transliteration( PG_FUNCTION_ARGS );
Datum gettokenstring( PG_FUNCTION_ARGS );
void str_replace(char* buffer, int* len, int* changes, char* from, int fromlen, char* to, int tolen, int);

18
nominatim-cli.py Executable file
View File

@@ -0,0 +1,18 @@
#!/usr/bin/env python3
# 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.
# For a full list of authors see the git log.
"""
Helper script for development to run nominatim from the source directory.
"""
from pathlib import Path
import sys
sys.path.insert(1, str((Path(__file__) / '..' / 'src').resolve()))
from nominatim_db import cli
exit(cli.nominatim(module_dir=None, osm2pgsql_path=None))

View File

@@ -1,26 +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.
"""
Subcommand definitions for the command-line tool.
"""
# mypy and pylint disagree about the style of explicit exports,
# see https://github.com/PyCQA/pylint/issues/6006.
# pylint: disable=useless-import-alias
from nominatim.clicmd.setup import SetupAll as SetupAll
from nominatim.clicmd.replication import UpdateReplication as UpdateReplication
from nominatim.clicmd.api import (APISearch as APISearch,
APIReverse as APIReverse,
APILookup as APILookup,
APIDetails as APIDetails,
APIStatus as APIStatus)
from nominatim.clicmd.index import UpdateIndex as UpdateIndex
from nominatim.clicmd.refresh import UpdateRefresh as UpdateRefresh
from nominatim.clicmd.add_data import UpdateAddData as UpdateAddData
from nominatim.clicmd.admin import AdminFuncs as AdminFuncs
from nominatim.clicmd.freeze import SetupFreeze as SetupFreeze
from nominatim.clicmd.special_phrases import ImportSpecialPhrases as ImportSpecialPhrases

View File

@@ -1,283 +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.
"""
Subcommand definitions for API calls from the command line.
"""
from typing import Mapping, Dict
import argparse
import logging
from nominatim.tools.exec_utils import run_api_script
from nominatim.errors import UsageError
from nominatim.clicmd.args import NominatimArgs
# Do not repeat documentation of subcommand classes.
# pylint: disable=C0111
LOG = logging.getLogger()
STRUCTURED_QUERY = (
('street', 'housenumber and street'),
('city', 'city, town or village'),
('county', 'county'),
('state', 'state'),
('country', 'country'),
('postalcode', 'postcode')
)
EXTRADATA_PARAMS = (
('addressdetails', 'Include a breakdown of the address into elements'),
('extratags', ("Include additional information if available "
"(e.g. wikipedia link, opening hours)")),
('namedetails', 'Include a list of alternative names')
)
DETAILS_SWITCHES = (
('addressdetails', 'Include a breakdown of the address into elements'),
('keywords', 'Include a list of name keywords and address keywords'),
('linkedplaces', 'Include a details of places that are linked with this one'),
('hierarchy', 'Include details of places lower in the address hierarchy'),
('group_hierarchy', 'Group the places by type'),
('polygon_geojson', 'Include geometry of result')
)
def _add_api_output_arguments(parser: argparse.ArgumentParser) -> None:
group = parser.add_argument_group('Output arguments')
group.add_argument('--format', default='jsonv2',
choices=['xml', 'json', 'jsonv2', 'geojson', 'geocodejson'],
help='Format of result')
for name, desc in EXTRADATA_PARAMS:
group.add_argument('--' + name, action='store_true', help=desc)
group.add_argument('--lang', '--accept-language', metavar='LANGS',
help='Preferred language order for presenting search results')
group.add_argument('--polygon-output',
choices=['geojson', 'kml', 'svg', 'text'],
help='Output geometry of results as a GeoJSON, KML, SVG or WKT')
group.add_argument('--polygon-threshold', type=float, metavar='TOLERANCE',
help=("Simplify output geometry."
"Parameter is difference tolerance in degrees."))
def _run_api(endpoint: str, args: NominatimArgs, params: Mapping[str, object]) -> int:
script_file = args.project_dir / 'website' / (endpoint + '.php')
if not script_file.exists():
LOG.error("Cannot find API script file.\n\n"
"Make sure to run 'nominatim' from the project directory \n"
"or use the option --project-dir.")
raise UsageError("API script not found.")
return run_api_script(endpoint, args.project_dir,
phpcgi_bin=args.phpcgi_path, params=params)
class APISearch:
"""\
Execute a search query.
This command works exactly the same as if calling the /search endpoint on
the web API. See the online documentation for more details on the
various parameters:
https://nominatim.org/release-docs/latest/api/Search/
"""
def add_args(self, parser: argparse.ArgumentParser) -> None:
group = parser.add_argument_group('Query arguments')
group.add_argument('--query',
help='Free-form query string')
for name, desc in STRUCTURED_QUERY:
group.add_argument('--' + name, help='Structured query: ' + desc)
_add_api_output_arguments(parser)
group = parser.add_argument_group('Result limitation')
group.add_argument('--countrycodes', metavar='CC,..',
help='Limit search results to one or more countries')
group.add_argument('--exclude_place_ids', metavar='ID,..',
help='List of search object to be excluded')
group.add_argument('--limit', type=int,
help='Limit the number of returned results')
group.add_argument('--viewbox', metavar='X1,Y1,X2,Y2',
help='Preferred area to find search results')
group.add_argument('--bounded', action='store_true',
help='Strictly restrict results to viewbox area')
group = parser.add_argument_group('Other arguments')
group.add_argument('--no-dedupe', action='store_false', dest='dedupe',
help='Do not remove duplicates from the result list')
def run(self, args: NominatimArgs) -> int:
params: Dict[str, object]
if args.query:
params = dict(q=args.query)
else:
params = {k: getattr(args, k) for k, _ in STRUCTURED_QUERY if getattr(args, k)}
for param, _ in EXTRADATA_PARAMS:
if getattr(args, param):
params[param] = '1'
for param in ('format', 'countrycodes', 'exclude_place_ids', 'limit', 'viewbox'):
if getattr(args, param):
params[param] = getattr(args, param)
if args.lang:
params['accept-language'] = args.lang
if args.polygon_output:
params['polygon_' + args.polygon_output] = '1'
if args.polygon_threshold:
params['polygon_threshold'] = args.polygon_threshold
if args.bounded:
params['bounded'] = '1'
if not args.dedupe:
params['dedupe'] = '0'
return _run_api('search', args, params)
class APIReverse:
"""\
Execute API reverse query.
This command works exactly the same as if calling the /reverse endpoint on
the web API. See the online documentation for more details on the
various parameters:
https://nominatim.org/release-docs/latest/api/Reverse/
"""
def add_args(self, parser: argparse.ArgumentParser) -> None:
group = parser.add_argument_group('Query arguments')
group.add_argument('--lat', type=float, required=True,
help='Latitude of coordinate to look up (in WGS84)')
group.add_argument('--lon', type=float, required=True,
help='Longitude of coordinate to look up (in WGS84)')
group.add_argument('--zoom', type=int,
help='Level of detail required for the address')
_add_api_output_arguments(parser)
def run(self, args: NominatimArgs) -> int:
params = dict(lat=args.lat, lon=args.lon, format=args.format)
if args.zoom is not None:
params['zoom'] = args.zoom
for param, _ in EXTRADATA_PARAMS:
if getattr(args, param):
params[param] = '1'
if args.lang:
params['accept-language'] = args.lang
if args.polygon_output:
params['polygon_' + args.polygon_output] = '1'
if args.polygon_threshold:
params['polygon_threshold'] = args.polygon_threshold
return _run_api('reverse', args, params)
class APILookup:
"""\
Execute API lookup query.
This command works exactly the same as if calling the /lookup endpoint on
the web API. See the online documentation for more details on the
various parameters:
https://nominatim.org/release-docs/latest/api/Lookup/
"""
def add_args(self, parser: argparse.ArgumentParser) -> None:
group = parser.add_argument_group('Query arguments')
group.add_argument('--id', metavar='OSMID',
action='append', required=True, dest='ids',
help='OSM id to lookup in format <NRW><id> (may be repeated)')
_add_api_output_arguments(parser)
def run(self, args: NominatimArgs) -> int:
params: Dict[str, object] = dict(osm_ids=','.join(args.ids), format=args.format)
for param, _ in EXTRADATA_PARAMS:
if getattr(args, param):
params[param] = '1'
if args.lang:
params['accept-language'] = args.lang
if args.polygon_output:
params['polygon_' + args.polygon_output] = '1'
if args.polygon_threshold:
params['polygon_threshold'] = args.polygon_threshold
return _run_api('lookup', args, params)
class APIDetails:
"""\
Execute API details query.
This command works exactly the same as if calling the /details endpoint on
the web API. See the online documentation for more details on the
various parameters:
https://nominatim.org/release-docs/latest/api/Details/
"""
def add_args(self, parser: argparse.ArgumentParser) -> None:
group = parser.add_argument_group('Query arguments')
objs = group.add_mutually_exclusive_group(required=True)
objs.add_argument('--node', '-n', type=int,
help="Look up the OSM node with the given ID.")
objs.add_argument('--way', '-w', type=int,
help="Look up the OSM way with the given ID.")
objs.add_argument('--relation', '-r', type=int,
help="Look up the OSM relation with the given ID.")
objs.add_argument('--place_id', '-p', type=int,
help='Database internal identifier of the OSM object to look up')
group.add_argument('--class', dest='object_class',
help=("Class type to disambiguated multiple entries "
"of the same object."))
group = parser.add_argument_group('Output arguments')
for name, desc in DETAILS_SWITCHES:
group.add_argument('--' + name, action='store_true', help=desc)
group.add_argument('--lang', '--accept-language', metavar='LANGS',
help='Preferred language order for presenting search results')
def run(self, args: NominatimArgs) -> int:
if args.node:
params = dict(osmtype='N', osmid=args.node)
elif args.way:
params = dict(osmtype='W', osmid=args.node)
elif args.relation:
params = dict(osmtype='R', osmid=args.node)
else:
params = dict(place_id=args.place_id)
if args.object_class:
params['class'] = args.object_class
for name, _ in DETAILS_SWITCHES:
params[name] = '1' if getattr(args, name) else '0'
if args.lang:
params['accept-language'] = args.lang
return _run_api('details', args, params)
class APIStatus:
"""\
Execute API status query.
This command works exactly the same as if calling the /status endpoint on
the web API. See the online documentation for more details on the
various parameters:
https://nominatim.org/release-docs/latest/api/Status/
"""
def add_args(self, parser: argparse.ArgumentParser) -> None:
group = parser.add_argument_group('API parameters')
group.add_argument('--format', default='text', choices=['text', 'json'],
help='Format of result')
def run(self, args: NominatimArgs) -> int:
return _run_api('status', args, dict(format=args.format))

View File

@@ -1,236 +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.
""" Non-blocking database connections.
"""
from typing import Callable, Any, Optional, Iterator, Sequence
import logging
import select
import time
import psycopg2
from psycopg2.extras import wait_select
# psycopg2 emits different exceptions pre and post 2.8. Detect if the new error
# module is available and adapt the error handling accordingly.
try:
import psycopg2.errors # pylint: disable=no-name-in-module,import-error
__has_psycopg2_errors__ = True
except ImportError:
__has_psycopg2_errors__ = False
from nominatim.typing import T_cursor, Query
LOG = logging.getLogger()
class DeadlockHandler:
""" Context manager that catches deadlock exceptions and calls
the given handler function. All other exceptions are passed on
normally.
"""
def __init__(self, handler: Callable[[], None], ignore_sql_errors: bool = False) -> None:
self.handler = handler
self.ignore_sql_errors = ignore_sql_errors
def __enter__(self) -> 'DeadlockHandler':
return self
def __exit__(self, exc_type: Any, exc_value: Any, traceback: Any) -> bool:
if __has_psycopg2_errors__:
if exc_type == psycopg2.errors.DeadlockDetected: # pylint: disable=E1101
self.handler()
return True
elif exc_type == psycopg2.extensions.TransactionRollbackError \
and exc_value.pgcode == '40P01':
self.handler()
return True
if self.ignore_sql_errors and isinstance(exc_value, psycopg2.Error):
LOG.info("SQL error ignored: %s", exc_value)
return True
return False
class DBConnection:
""" A single non-blocking database connection.
"""
def __init__(self, dsn: str,
cursor_factory: Optional[Callable[..., T_cursor]] = None,
ignore_sql_errors: bool = False) -> None:
self.dsn = dsn
self.current_query: Optional[Query] = None
self.current_params: Optional[Sequence[Any]] = None
self.ignore_sql_errors = ignore_sql_errors
self.conn: Optional['psycopg2.connection'] = None
self.cursor: Optional['psycopg2.cursor'] = None
self.connect(cursor_factory=cursor_factory)
def close(self) -> None:
""" Close all open connections. Does not wait for pending requests.
"""
if self.conn is not None:
if self.cursor is not None:
self.cursor.close() # type: ignore[no-untyped-call]
self.cursor = None
self.conn.close()
self.conn = None
def connect(self, cursor_factory: Optional[Callable[..., T_cursor]] = None) -> None:
""" (Re)connect to the database. Creates an asynchronous connection
with JIT and parallel processing disabled. If a connection was
already open, it is closed and a new connection established.
The caller must ensure that no query is pending before reconnecting.
"""
self.close()
# Use a dict to hand in the parameters because async is a reserved
# word in Python3.
self.conn = psycopg2.connect(**{'dsn': self.dsn, 'async': True}) # type: ignore
assert self.conn
self.wait()
if cursor_factory is not None:
self.cursor = self.conn.cursor(cursor_factory=cursor_factory)
else:
self.cursor = self.conn.cursor()
# Disable JIT and parallel workers as they are known to cause problems.
# Update pg_settings instead of using SET because it does not yield
# errors on older versions of Postgres where the settings are not
# implemented.
self.perform(
""" UPDATE pg_settings SET setting = -1 WHERE name = 'jit_above_cost';
UPDATE pg_settings SET setting = 0
WHERE name = 'max_parallel_workers_per_gather';""")
self.wait()
def _deadlock_handler(self) -> None:
LOG.info("Deadlock detected (params = %s), retry.", str(self.current_params))
assert self.cursor is not None
assert self.current_query is not None
assert self.current_params is not None
self.cursor.execute(self.current_query, self.current_params)
def wait(self) -> None:
""" Block until any pending operation is done.
"""
while True:
with DeadlockHandler(self._deadlock_handler, self.ignore_sql_errors):
wait_select(self.conn)
self.current_query = None
return
def perform(self, sql: Query, args: Optional[Sequence[Any]] = None) -> None:
""" Send SQL query to the server. Returns immediately without
blocking.
"""
assert self.cursor is not None
self.current_query = sql
self.current_params = args
self.cursor.execute(sql, args)
def fileno(self) -> int:
""" File descriptor to wait for. (Makes this class select()able.)
"""
assert self.conn is not None
return self.conn.fileno()
def is_done(self) -> bool:
""" Check if the connection is available for a new query.
Also checks if the previous query has run into a deadlock.
If so, then the previous query is repeated.
"""
assert self.conn is not None
if self.current_query is None:
return True
with DeadlockHandler(self._deadlock_handler, self.ignore_sql_errors):
if self.conn.poll() == psycopg2.extensions.POLL_OK:
self.current_query = None
return True
return False
class WorkerPool:
""" A pool of asynchronous database connections.
The pool may be used as a context manager.
"""
REOPEN_CONNECTIONS_AFTER = 100000
def __init__(self, dsn: str, pool_size: int, ignore_sql_errors: bool = False) -> None:
self.threads = [DBConnection(dsn, ignore_sql_errors=ignore_sql_errors)
for _ in range(pool_size)]
self.free_workers = self._yield_free_worker()
self.wait_time = 0.0
def finish_all(self) -> None:
""" Wait for all connection to finish.
"""
for thread in self.threads:
while not thread.is_done():
thread.wait()
self.free_workers = self._yield_free_worker()
def close(self) -> None:
""" Close all connections and clear the pool.
"""
for thread in self.threads:
thread.close()
self.threads = []
self.free_workers = iter([])
def next_free_worker(self) -> DBConnection:
""" Get the next free connection.
"""
return next(self.free_workers)
def _yield_free_worker(self) -> Iterator[DBConnection]:
ready = self.threads
command_stat = 0
while True:
for thread in ready:
if thread.is_done():
command_stat += 1
yield thread
if command_stat > self.REOPEN_CONNECTIONS_AFTER:
self._reconnect_threads()
ready = self.threads
command_stat = 0
else:
tstart = time.time()
_, ready, _ = select.select([], self.threads, [])
self.wait_time += time.time() - tstart
def _reconnect_threads(self) -> None:
for thread in self.threads:
while not thread.is_done():
thread.wait()
thread.connect()
def __enter__(self) -> 'WorkerPool':
return self
def __exit__(self, exc_type: Any, exc_value: Any, traceback: Any) -> None:
self.finish_all()
self.close()

View File

@@ -1,245 +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.
"""
Specialised connection and cursor functions.
"""
from typing import Optional, Any, Callable, ContextManager, Dict, cast, overload, Tuple, Iterable
import contextlib
import logging
import os
import psycopg2
import psycopg2.extensions
import psycopg2.extras
from psycopg2 import sql as pysql
from nominatim.typing import SysEnv, Query, T_cursor
from nominatim.errors import UsageError
LOG = logging.getLogger()
class Cursor(psycopg2.extras.DictCursor):
""" A cursor returning dict-like objects and providing specialised
execution functions.
"""
# pylint: disable=arguments-renamed,arguments-differ
def execute(self, query: Query, args: Any = None) -> None:
""" Query execution that logs the SQL query when debugging is enabled.
"""
if LOG.isEnabledFor(logging.DEBUG):
LOG.debug(self.mogrify(query, args).decode('utf-8')) # type: ignore[no-untyped-call]
super().execute(query, args)
def execute_values(self, sql: Query, argslist: Iterable[Tuple[Any, ...]],
template: Optional[Query] = None) -> None:
""" Wrapper for the psycopg2 convenience function to execute
SQL for a list of values.
"""
LOG.debug("SQL execute_values(%s, %s)", sql, argslist)
psycopg2.extras.execute_values(self, sql, argslist, template=template)
def scalar(self, sql: Query, args: Any = None) -> Any:
""" Execute query that returns a single value. The value is returned.
If the query yields more than one row, a ValueError is raised.
"""
self.execute(sql, args)
if self.rowcount != 1:
raise RuntimeError("Query did not return a single row.")
result = self.fetchone()
assert result is not None
return result[0]
def drop_table(self, name: str, if_exists: bool = True, cascade: bool = False) -> None:
""" Drop the table with the given name.
Set `if_exists` to False if a non-existent table should raise
an exception instead of just being ignored. If 'cascade' is set
to True then all dependent tables are deleted as well.
"""
sql = 'DROP TABLE '
if if_exists:
sql += 'IF EXISTS '
sql += '{}'
if cascade:
sql += ' CASCADE'
self.execute(pysql.SQL(sql).format(pysql.Identifier(name)))
class Connection(psycopg2.extensions.connection):
""" A connection that provides the specialised cursor by default and
adds convenience functions for administrating the database.
"""
@overload # type: ignore[override]
def cursor(self) -> Cursor:
...
@overload
def cursor(self, name: str) -> Cursor:
...
@overload
def cursor(self, cursor_factory: Callable[..., T_cursor]) -> T_cursor:
...
def cursor(self, cursor_factory = Cursor, **kwargs): # type: ignore
""" Return a new cursor. By default the specialised cursor is returned.
"""
return super().cursor(cursor_factory=cursor_factory, **kwargs)
def table_exists(self, table: str) -> bool:
""" Check that a table with the given name exists in the database.
"""
with self.cursor() as cur:
num = cur.scalar("""SELECT count(*) FROM pg_tables
WHERE tablename = %s and schemaname = 'public'""", (table, ))
return num == 1 if isinstance(num, int) else False
def table_has_column(self, table: str, column: str) -> bool:
""" Check if the table 'table' exists and has a column with name 'column'.
"""
with self.cursor() as cur:
has_column = cur.scalar("""SELECT count(*) FROM information_schema.columns
WHERE table_name = %s
and column_name = %s""",
(table, column))
return has_column > 0 if isinstance(has_column, int) else False
def index_exists(self, index: str, table: Optional[str] = None) -> bool:
""" Check that an index with the given name exists in the database.
If table is not None then the index must relate to the given
table.
"""
with self.cursor() as cur:
cur.execute("""SELECT tablename FROM pg_indexes
WHERE indexname = %s and schemaname = 'public'""", (index, ))
if cur.rowcount == 0:
return False
if table is not None:
row = cur.fetchone()
if row is None or not isinstance(row[0], str):
return False
return row[0] == table
return True
def drop_table(self, name: str, if_exists: bool = True, cascade: bool = False) -> None:
""" Drop the table with the given name.
Set `if_exists` to False if a non-existent table should raise
an exception instead of just being ignored.
"""
with self.cursor() as cur:
cur.drop_table(name, if_exists, cascade)
self.commit()
def server_version_tuple(self) -> Tuple[int, int]:
""" Return the server version as a tuple of (major, minor).
Converts correctly for pre-10 and post-10 PostgreSQL versions.
"""
version = self.server_version
if version < 100000:
return (int(version / 10000), int((version % 10000) / 100))
return (int(version / 10000), version % 10000)
def postgis_version_tuple(self) -> Tuple[int, int]:
""" Return the postgis version installed in the database as a
tuple of (major, minor). Assumes that the PostGIS extension
has been installed already.
"""
with self.cursor() as cur:
version = cur.scalar('SELECT postgis_lib_version()')
version_parts = version.split('.')
if len(version_parts) < 2:
raise UsageError(f"Error fetching Postgis version. Bad format: {version}")
return (int(version_parts[0]), int(version_parts[1]))
class ConnectionContext(ContextManager[Connection]):
""" Context manager of the connection that also provides direct access
to the underlying connection.
"""
connection: Connection
def connect(dsn: str) -> ConnectionContext:
""" Open a connection to the database using the specialised connection
factory. The returned object may be used in conjunction with 'with'.
When used outside a context manager, use the `connection` attribute
to get the connection.
"""
try:
conn = psycopg2.connect(dsn, connection_factory=Connection)
ctxmgr = cast(ConnectionContext, contextlib.closing(conn))
ctxmgr.connection = conn
return ctxmgr
except psycopg2.OperationalError as err:
raise UsageError(f"Cannot connect to database: {err}") from err
# Translation from PG connection string parameters to PG environment variables.
# Derived from https://www.postgresql.org/docs/current/libpq-envars.html.
_PG_CONNECTION_STRINGS = {
'host': 'PGHOST',
'hostaddr': 'PGHOSTADDR',
'port': 'PGPORT',
'dbname': 'PGDATABASE',
'user': 'PGUSER',
'password': 'PGPASSWORD',
'passfile': 'PGPASSFILE',
'channel_binding': 'PGCHANNELBINDING',
'service': 'PGSERVICE',
'options': 'PGOPTIONS',
'application_name': 'PGAPPNAME',
'sslmode': 'PGSSLMODE',
'requiressl': 'PGREQUIRESSL',
'sslcompression': 'PGSSLCOMPRESSION',
'sslcert': 'PGSSLCERT',
'sslkey': 'PGSSLKEY',
'sslrootcert': 'PGSSLROOTCERT',
'sslcrl': 'PGSSLCRL',
'requirepeer': 'PGREQUIREPEER',
'ssl_min_protocol_version': 'PGSSLMINPROTOCOLVERSION',
'ssl_max_protocol_version': 'PGSSLMAXPROTOCOLVERSION',
'gssencmode': 'PGGSSENCMODE',
'krbsrvname': 'PGKRBSRVNAME',
'gsslib': 'PGGSSLIB',
'connect_timeout': 'PGCONNECT_TIMEOUT',
'target_session_attrs': 'PGTARGETSESSIONATTRS',
}
def get_pg_env(dsn: str,
base_env: Optional[SysEnv] = None) -> Dict[str, str]:
""" Return a copy of `base_env` with the environment variables for
PostgresSQL set up from the given database connection string.
If `base_env` is None, then the OS environment is used as a base
environment.
"""
env = dict(base_env if base_env is not None else os.environ)
for param, value in psycopg2.extensions.parse_dsn(dsn).items():
if param in _PG_CONNECTION_STRINGS:
env[_PG_CONNECTION_STRINGS[param]] = value
else:
LOG.error("Unknown connection parameter '%s' ignored.", param)
return env

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