mirror of
https://github.com/osm-search/Nominatim.git
synced 2026-02-14 18:37:58 +00:00
Compare commits
1 Commits
helm-chart
...
docs-3.6.x
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
b20a1531c1 |
10
.github/ISSUE_TEMPLATE/feature_request.md
vendored
10
.github/ISSUE_TEMPLATE/feature_request.md
vendored
@@ -7,16 +7,16 @@ assignees: ''
|
||||
|
||||
---
|
||||
|
||||
<!-- Before opening a new feature request, please search through the open issue to check that your request hasn't been reported already. -->
|
||||
Before opening a new feature request, please search through the open issue to check that your request hasn't been reported already.
|
||||
|
||||
**Is your feature request related to a problem? Please describe.**
|
||||
<!-- A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] -->
|
||||
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
|
||||
|
||||
**Describe the solution you'd like**
|
||||
<!-- A clear and concise description of what you want to happen. -->
|
||||
A clear and concise description of what you want to happen.
|
||||
|
||||
**Describe alternatives you've considered**
|
||||
<!-- A clear and concise description of any alternative solutions or features you've considered. -->
|
||||
A clear and concise description of any alternative solutions or features you've considered.
|
||||
|
||||
**Additional context**
|
||||
<!-- Add any other context or screenshots about the feature request here. -->
|
||||
Add any other context or screenshots about the feature request here.
|
||||
|
||||
@@ -9,7 +9,7 @@ assignees: ''
|
||||
|
||||
## What did you search for?
|
||||
|
||||
<!-- Please try to provide a link to your search. You can go to https://nominatim.openstreetmap.org and repeat your search there. If you originally found the issue somewhere else, please tell us what software/website you were using. -->
|
||||
Please try to provide a link to your search. You can go to https://nominatim.openstreetmap.org and repeat your search there. If you originally found the issue somewhere else, please tell us what software/website you were using.
|
||||
|
||||
## What result did you get?
|
||||
|
||||
@@ -17,11 +17,11 @@ assignees: ''
|
||||
|
||||
**Is the result in the right place and just named wrongly?**
|
||||
|
||||
<!-- Please tell us the display name you expected. -->
|
||||
Please tell us the display name you expected.
|
||||
|
||||
**Is the result missing completely?**
|
||||
|
||||
<!-- Make sure that the data you are looking for is in OpenStreetMap. Provide a link to the OpenStreetMap object or if you cannot get it, a link to the map on https://openstreetmap.org where you expect the result to be.
|
||||
Make sure that the data you are looking for is in OpenStreetMap. Provide a link to the OpenStreetMap object or if you cannot get it, a link to the map on https://openstreetmap.org where you expect the result to be.
|
||||
|
||||
To get the link to the OSM object, you can try the following:
|
||||
|
||||
@@ -30,8 +30,7 @@ To get the link to the OSM object, you can try the following:
|
||||
* Click on the question mark on the right side of the map. You get a question cursor. Use it to click on the map where your object is located.
|
||||
* Find the object of interest in the list that appears on the left side.
|
||||
* Click on the object and report back the URL that the browser shows.
|
||||
-->
|
||||
|
||||
## Further details
|
||||
|
||||
<!-- Anything else we should know about the search. Particularities with addresses in the area etc. -->
|
||||
Anything else we should know about the search. Particularities with addresses in the area etc.
|
||||
|
||||
@@ -7,13 +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.___
|
||||
|
||||
**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. -->
|
||||
Please describe what you did to get to the issue.
|
||||
|
||||
**Software Environment (please complete the following information):**
|
||||
- Nominatim version:
|
||||
@@ -27,10 +27,5 @@ assignees: ''
|
||||
- type and size of disks:
|
||||
- bare metal/AWS/other cloud service:
|
||||
|
||||
**Postgresql Configuration:**
|
||||
|
||||
<!-- List any configuration items you changed in your postgresql configuration. -->
|
||||
|
||||
**Additional context**
|
||||
|
||||
<!-- Add any other context about the problem here. -->
|
||||
Add any other context about the problem here.
|
||||
|
||||
38
.github/actions/build-nominatim/action.yml
vendored
38
.github/actions/build-nominatim/action.yml
vendored
@@ -1,42 +1,28 @@
|
||||
name: 'Build Nominatim'
|
||||
|
||||
inputs:
|
||||
ubuntu:
|
||||
description: 'Version of Ubuntu to install on'
|
||||
required: false
|
||||
default: '20'
|
||||
|
||||
runs:
|
||||
using: "composite"
|
||||
|
||||
steps:
|
||||
- name: Install 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 osmium PyYAML==5.1 datrie
|
||||
else
|
||||
sudo apt-get install -y -qq python3-icu python3-datrie python3-pyosmium python3-jinja2 python3-psutil python3-psycopg2 python3-dotenv python3-yaml
|
||||
fi
|
||||
shell: bash
|
||||
env:
|
||||
UBUNTUVER: ${{ inputs.ubuntu }}
|
||||
|
||||
- name: Download dependencies
|
||||
run: |
|
||||
if [ ! -f country_grid.sql.gz ]; then
|
||||
wget --no-verbose https://www.nominatim.org/data/country_grid.sql.gz
|
||||
fi
|
||||
cp country_grid.sql.gz Nominatim/data/country_osm_grid.sql.gz
|
||||
- name: Install prerequisits
|
||||
run: sudo apt-get install -y -qq libboost-system-dev libboost-filesystem-dev libexpat1-dev zlib1g-dev libbz2-dev libpq-dev libproj-dev python3-psycopg2 python3-pyosmium
|
||||
shell: bash
|
||||
|
||||
- name: Configure
|
||||
run: mkdir build && cd build && cmake ../Nominatim
|
||||
run: mkdir build && cd build && cmake ..
|
||||
shell: bash
|
||||
|
||||
- name: Build
|
||||
run: |
|
||||
make -j2 all
|
||||
sudo make install
|
||||
./utils/setup.php --setup-website
|
||||
shell: bash
|
||||
working-directory: build
|
||||
|
||||
- name: Download dependencies
|
||||
run: |
|
||||
if [ ! -f data/country_osm_grid.sql.gz ]; then
|
||||
wget --no-verbose -O data/country_osm_grid.sql.gz https://www.nominatim.org/data/country_grid.sql.gz
|
||||
fi
|
||||
shell: bash
|
||||
|
||||
|
||||
4
.github/actions/setup-postgresql/action.yml
vendored
4
.github/actions/setup-postgresql/action.yml
vendored
@@ -14,10 +14,8 @@ runs:
|
||||
steps:
|
||||
- name: Remove existing PostgreSQL
|
||||
run: |
|
||||
sudo apt-get purge -yq postgresql*
|
||||
sudo sh -c 'echo "deb http://apt.postgresql.org/pub/repos/apt $(lsb_release -cs)-pgdg main" > /etc/apt/sources.list.d/pgdg.list'
|
||||
sudo apt-get update -qq
|
||||
|
||||
sudo apt-get purge -yq postgresql*
|
||||
shell: bash
|
||||
|
||||
- name: Install PostgreSQL
|
||||
|
||||
185
.github/workflows/ci-tests.yml
vendored
185
.github/workflows/ci-tests.yml
vendored
@@ -4,40 +4,21 @@ on: [ push, pull_request ]
|
||||
|
||||
jobs:
|
||||
tests:
|
||||
runs-on: ubuntu-20.04
|
||||
|
||||
strategy:
|
||||
matrix:
|
||||
ubuntu: [18, 20]
|
||||
postgresql: [9.5, 13]
|
||||
include:
|
||||
- ubuntu: 18
|
||||
postgresql: 9.5
|
||||
- postgresql: 9.5
|
||||
postgis: 2.5
|
||||
pytest: pytest
|
||||
php: 7.2
|
||||
- ubuntu: 20
|
||||
postgresql: 13
|
||||
- postgresql: 13
|
||||
postgis: 3
|
||||
pytest: py.test-3
|
||||
php: 7.4
|
||||
|
||||
runs-on: ubuntu-${{ matrix.ubuntu }}.04
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
with:
|
||||
submodules: true
|
||||
path: Nominatim
|
||||
|
||||
- name: Setup PHP
|
||||
uses: shivammathur/setup-php@v2
|
||||
with:
|
||||
php-version: ${{ matrix.php }}
|
||||
coverage: xdebug
|
||||
tools: phpunit, phpcs, composer
|
||||
|
||||
- uses: actions/setup-python@v2
|
||||
with:
|
||||
python-version: 3.6
|
||||
if: matrix.ubuntu == 18
|
||||
|
||||
- name: Get Date
|
||||
id: get-date
|
||||
@@ -48,96 +29,39 @@ jobs:
|
||||
- uses: actions/cache@v2
|
||||
with:
|
||||
path: |
|
||||
country_grid.sql.gz
|
||||
key: nominatim-country-data-${{ steps.get-date.outputs.date }}
|
||||
data/country_osm_grid.sql.gz
|
||||
monaco-latest.osm.pbf
|
||||
key: nominatim-data-${{ steps.get-date.outputs.date }}
|
||||
|
||||
- uses: ./Nominatim/.github/actions/setup-postgresql
|
||||
- uses: ./.github/actions/setup-postgresql
|
||||
with:
|
||||
postgresql-version: ${{ matrix.postgresql }}
|
||||
postgis-version: ${{ matrix.postgis }}
|
||||
|
||||
- uses: ./Nominatim/.github/actions/build-nominatim
|
||||
with:
|
||||
ubuntu: ${{ matrix.ubuntu }}
|
||||
|
||||
- name: Install test prerequsites
|
||||
run: sudo apt-get install -y -qq pylint python3-pytest python3-behave python3-pytest-cov php-codecoverage
|
||||
if: matrix.ubuntu == 20
|
||||
- uses: ./.github/actions/build-nominatim
|
||||
|
||||
- name: Install test prerequsites
|
||||
run: |
|
||||
pip3 install pylint==2.6.0 pytest pytest-cov behave==1.2.6
|
||||
if: matrix.ubuntu == 18
|
||||
sudo apt-get install -y -qq php-codesniffer python3-tidylib
|
||||
sudo pip3 install behave nose
|
||||
|
||||
- name: PHP linting
|
||||
run: phpcs --report-width=120 .
|
||||
working-directory: Nominatim
|
||||
|
||||
- name: Python linting
|
||||
run: pylint nominatim
|
||||
working-directory: Nominatim
|
||||
|
||||
- name: PHP unit tests
|
||||
run: phpunit --coverage-clover ../../coverage-php.xml ./
|
||||
working-directory: Nominatim/test/php
|
||||
if: matrix.ubuntu == 20
|
||||
|
||||
- name: Python unit tests
|
||||
run: $PYTEST --cov=nominatim --cov-report=xml test/python
|
||||
working-directory: Nominatim
|
||||
env:
|
||||
PYTEST: ${{ matrix.pytest }}
|
||||
run: phpunit ./
|
||||
working-directory: test/php
|
||||
|
||||
- name: BDD tests
|
||||
run: |
|
||||
mkdir cov
|
||||
behave -DREMOVE_TEMPLATE=1 -DBUILDDIR=$GITHUB_WORKSPACE/build --format=progress3 -DPHPCOV=./cov
|
||||
composer require phpunit/phpcov:7.0.2
|
||||
vendor/bin/phpcov merge --clover ../../coverage-bdd.xml ./cov
|
||||
working-directory: Nominatim/test/bdd
|
||||
if: matrix.ubuntu == 20
|
||||
|
||||
- name: BDD tests
|
||||
run: |
|
||||
behave -DREMOVE_TEMPLATE=1 -DBUILDDIR=$GITHUB_WORKSPACE/build --format=progress3
|
||||
working-directory: Nominatim/test/bdd
|
||||
if: matrix.ubuntu == 18
|
||||
|
||||
- name: BDD tests (legacy_icu tokenizer)
|
||||
run: |
|
||||
behave -DREMOVE_TEMPLATE=1 -DBUILDDIR=$GITHUB_WORKSPACE/build -DTOKENIZER=legacy_icu --format=progress3
|
||||
working-directory: Nominatim/test/bdd
|
||||
|
||||
- name: Upload coverage to Codecov
|
||||
uses: codecov/codecov-action@v1
|
||||
with:
|
||||
files: ./Nominatim/coverage*.xml
|
||||
directory: ./
|
||||
name: codecov-umbrella
|
||||
fail_ci_if_error: false
|
||||
path_to_write_report: ./coverage/codecov_report.txt
|
||||
verbose: true
|
||||
if: matrix.ubuntu == 20
|
||||
run: behave -DREMOVE_TEMPLATE=1 --format=progress3 db osm2pgsql
|
||||
working-directory: test/bdd
|
||||
|
||||
import:
|
||||
strategy:
|
||||
matrix:
|
||||
ubuntu: [18, 20]
|
||||
include:
|
||||
- ubuntu: 18
|
||||
postgresql: 9.5
|
||||
postgis: 2.5
|
||||
- ubuntu: 20
|
||||
postgresql: 13
|
||||
postgis: 3
|
||||
|
||||
runs-on: ubuntu-${{ matrix.ubuntu }}.04
|
||||
runs-on: ubuntu-20.04
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
with:
|
||||
submodules: true
|
||||
path: Nominatim
|
||||
|
||||
- name: Get Date
|
||||
id: get-date
|
||||
@@ -148,70 +72,49 @@ jobs:
|
||||
- uses: actions/cache@v2
|
||||
with:
|
||||
path: |
|
||||
country_grid.sql.gz
|
||||
key: nominatim-country-data-${{ steps.get-date.outputs.date }}
|
||||
data/country_osm_grid.sql.gz
|
||||
monaco-latest.osm.pbf
|
||||
key: nominatim-data-${{ steps.get-date.outputs.date }}
|
||||
|
||||
- uses: actions/cache@v2
|
||||
- uses: ./.github/actions/setup-postgresql
|
||||
with:
|
||||
path: |
|
||||
monaco-latest.osm.pbf
|
||||
key: nominatim-test-data-${{ steps.get-date.outputs.date }}
|
||||
postgresql-version: 13
|
||||
postgis-version: 3
|
||||
- uses: ./.github/actions/build-nominatim
|
||||
|
||||
- uses: actions/setup-python@v2
|
||||
with:
|
||||
python-version: 3.6
|
||||
if: matrix.ubuntu == 18
|
||||
- name: Create configuration
|
||||
run: |
|
||||
echo '<?php' > settings/local.php
|
||||
echo " @define('CONST_Pyosmium_Binary', '/usr/lib/python3-pyosmium/pyosmium-get-changes');" >> settings/local.php
|
||||
working-directory: build
|
||||
|
||||
- uses: ./Nominatim/.github/actions/setup-postgresql
|
||||
with:
|
||||
postgresql-version: ${{ matrix.postgresql }}
|
||||
postgis-version: ${{ matrix.postgis }}
|
||||
- uses: ./Nominatim/.github/actions/build-nominatim
|
||||
with:
|
||||
ubuntu: ${{ matrix.ubuntu }}
|
||||
|
||||
- name: Clean installation
|
||||
run: rm -rf Nominatim build
|
||||
shell: bash
|
||||
|
||||
- name: Prepare import environment
|
||||
- name: Download import data
|
||||
run: |
|
||||
if [ ! -f monaco-latest.osm.pbf ]; then
|
||||
wget --no-verbose https://download.geofabrik.de/europe/monaco-latest.osm.pbf
|
||||
fi
|
||||
mkdir data-env
|
||||
cd data-env
|
||||
shell: bash
|
||||
|
||||
- name: Import
|
||||
run: nominatim import --osm-file ../monaco-latest.osm.pbf
|
||||
shell: bash
|
||||
working-directory: data-env
|
||||
run: php ./utils/setup.php --osm-file ../monaco-latest.osm.pbf --osm2pgsql-cache 500 --all
|
||||
working-directory: build
|
||||
|
||||
- name: Import special phrases
|
||||
run: nominatim special-phrases --import-from-wiki
|
||||
working-directory: data-env
|
||||
run: php ./utils/specialphrases.php --wiki-import | psql -d nominatim
|
||||
working-directory: build
|
||||
|
||||
- name: Check full import
|
||||
run: nominatim admin --check-database
|
||||
working-directory: data-env
|
||||
|
||||
- name: Warm up database
|
||||
run: nominatim admin --warm
|
||||
working-directory: data-env
|
||||
- name: Check import
|
||||
run: php ./utils/check_import_finished.php
|
||||
working-directory: build
|
||||
|
||||
- name: Run update
|
||||
run: |
|
||||
nominatim replication --init
|
||||
nominatim replication --once
|
||||
working-directory: data-env
|
||||
php ./utils/update.php --init-updates
|
||||
php ./utils/update.php --import-osmosis
|
||||
working-directory: build
|
||||
|
||||
- name: Run reverse-only import
|
||||
run : nominatim import --osm-file ../monaco-latest.osm.pbf --reverse-only --no-updates
|
||||
working-directory: data-env
|
||||
env:
|
||||
NOMINATIM_DATABASE_DSN: pgsql:dbname=reverse
|
||||
|
||||
- name: Check reverse import
|
||||
run: nominatim admin --check-database
|
||||
working-directory: data-env
|
||||
run : |
|
||||
dropdb nominatim
|
||||
php ./utils/setup.php --osm-file ../monaco-latest.osm.pbf --reverse-only --all
|
||||
working-directory: build
|
||||
|
||||
1
.gitignore
vendored
1
.gitignore
vendored
@@ -9,4 +9,3 @@ data/wiki_specialphrases.sql
|
||||
data/osmosischange.osc
|
||||
|
||||
.vagrant
|
||||
data/country_osm_grid.sql.gz
|
||||
|
||||
15
.pylintrc
15
.pylintrc
@@ -1,15 +0,0 @@
|
||||
[MASTER]
|
||||
|
||||
extension-pkg-whitelist=osmium
|
||||
ignored-modules=icu,datrie
|
||||
|
||||
[MESSAGES CONTROL]
|
||||
|
||||
[TYPECHECK]
|
||||
|
||||
# closing added here because it sometimes triggers a false positive with
|
||||
# 'with' statements.
|
||||
ignored-classes=NominatimArgs,closing
|
||||
disable=too-few-public-methods,duplicate-code
|
||||
|
||||
good-names=i,x,y,fd,db
|
||||
237
CMakeLists.txt
237
CMakeLists.txt
@@ -6,7 +6,7 @@
|
||||
#
|
||||
#-----------------------------------------------------------------------------
|
||||
|
||||
cmake_minimum_required(VERSION 3.0 FATAL_ERROR)
|
||||
cmake_minimum_required(VERSION 2.8 FATAL_ERROR)
|
||||
list(APPEND CMAKE_MODULE_PATH "${CMAKE_SOURCE_DIR}/cmake")
|
||||
|
||||
|
||||
@@ -19,7 +19,7 @@ list(APPEND CMAKE_MODULE_PATH "${CMAKE_SOURCE_DIR}/cmake")
|
||||
project(nominatim)
|
||||
|
||||
set(NOMINATIM_VERSION_MAJOR 3)
|
||||
set(NOMINATIM_VERSION_MINOR 7)
|
||||
set(NOMINATIM_VERSION_MINOR 6)
|
||||
set(NOMINATIM_VERSION_PATCH 0)
|
||||
|
||||
set(NOMINATIM_VERSION "${NOMINATIM_VERSION_MAJOR}.${NOMINATIM_VERSION_MINOR}.${NOMINATIM_VERSION_PATCH}")
|
||||
@@ -36,7 +36,6 @@ set(BUILD_API on CACHE BOOL "Build everything for the API server")
|
||||
set(BUILD_MODULE on CACHE BOOL "Build PostgreSQL module")
|
||||
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)")
|
||||
|
||||
#-----------------------------------------------------------------------------
|
||||
@@ -58,11 +57,20 @@ endif()
|
||||
|
||||
|
||||
#-----------------------------------------------------------------------------
|
||||
# python (imports/updates only)
|
||||
# python and pyosmium (imports/updates only)
|
||||
#-----------------------------------------------------------------------------
|
||||
|
||||
if (BUILD_IMPORTER)
|
||||
find_package(PythonInterp 3.6 REQUIRED)
|
||||
find_package(PythonInterp 3)
|
||||
|
||||
find_program(PYOSMIUM pyosmium-get-changes)
|
||||
if (NOT EXISTS "${PYOSMIUM}")
|
||||
set(PYOSMIUM_PATH "")
|
||||
message(WARNING "pyosmium-get-changes not found (required for updates)")
|
||||
else()
|
||||
set(PYOSMIUM_PATH "${PYOSMIUM}")
|
||||
message(STATUS "Using pyosmium-get-changes at ${PYOSMIUM_PATH}")
|
||||
endif()
|
||||
endif()
|
||||
|
||||
#-----------------------------------------------------------------------------
|
||||
@@ -78,19 +86,8 @@ if (BUILD_API OR BUILD_IMPORTER)
|
||||
# sanity check if PHP binary exists
|
||||
if (NOT EXISTS ${PHP_BIN})
|
||||
message(FATAL_ERROR "PHP binary not found. Install php or provide location with -DPHP_BIN=/path/php ")
|
||||
else()
|
||||
message (STATUS "Using PHP binary " ${PHP_BIN})
|
||||
endif()
|
||||
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()
|
||||
message (STATUS "Using PHP binary " ${PHP_BIN})
|
||||
endif()
|
||||
|
||||
#-----------------------------------------------------------------------------
|
||||
@@ -98,21 +95,70 @@ endif()
|
||||
#-----------------------------------------------------------------------------
|
||||
|
||||
if (BUILD_IMPORTER)
|
||||
find_file(COUNTRY_GRID_FILE country_osm_grid.sql.gz
|
||||
PATHS ${PROJECT_SOURCE_DIR}/data
|
||||
NO_DEFAULT_PATH
|
||||
DOC "Location of the country grid file."
|
||||
)
|
||||
set(CUSTOMSCRIPTS
|
||||
utils/check_import_finished.php
|
||||
utils/country_languages.php
|
||||
utils/importWikipedia.php
|
||||
utils/export.php
|
||||
utils/query.php
|
||||
utils/setup.php
|
||||
utils/specialphrases.php
|
||||
utils/update.php
|
||||
utils/warm.php
|
||||
)
|
||||
|
||||
if (NOT COUNTRY_GRID_FILE)
|
||||
message(FATAL_ERROR "\nYou need to download the country_osm_grid first:\n"
|
||||
" wget -O ${PROJECT_SOURCE_DIR}/data/country_osm_grid.sql.gz https://www.nominatim.org/data/country_grid.sql.gz")
|
||||
endif()
|
||||
|
||||
configure_file(${PROJECT_SOURCE_DIR}/cmake/tool.tmpl
|
||||
${PROJECT_BINARY_DIR}/nominatim)
|
||||
foreach (script_source ${CUSTOMSCRIPTS})
|
||||
configure_file(${PROJECT_SOURCE_DIR}/cmake/script.tmpl
|
||||
${PROJECT_BINARY_DIR}/${script_source})
|
||||
endforeach()
|
||||
endif()
|
||||
|
||||
#-----------------------------------------------------------------------------
|
||||
# webserver scripts (API only)
|
||||
#-----------------------------------------------------------------------------
|
||||
|
||||
if (BUILD_API)
|
||||
set(WEBSITESCRIPTS
|
||||
website/deletable.php
|
||||
website/details.php
|
||||
website/lookup.php
|
||||
website/polygons.php
|
||||
website/reverse.php
|
||||
website/search.php
|
||||
website/status.php
|
||||
)
|
||||
|
||||
foreach (script_source ${WEBSITESCRIPTS})
|
||||
configure_file(${PROJECT_SOURCE_DIR}/cmake/website.tmpl
|
||||
${PROJECT_BINARY_DIR}/${script_source})
|
||||
endforeach()
|
||||
|
||||
set(WEBPATHS css images js)
|
||||
|
||||
foreach (wp ${WEBPATHS})
|
||||
execute_process(
|
||||
COMMAND ln -sf ${PROJECT_SOURCE_DIR}/website/${wp} ${PROJECT_BINARY_DIR}/website/
|
||||
)
|
||||
endforeach()
|
||||
|
||||
add_custom_target(serve
|
||||
php -S 127.0.0.1:8088
|
||||
WORKING_DIRECTORY ${PROJECT_BINARY_DIR}/website
|
||||
)
|
||||
|
||||
add_custom_target(serve-global
|
||||
php -S 0.0.0.0:8088
|
||||
WORKING_DIRECTORY ${PROJECT_BINARY_DIR}/website
|
||||
)
|
||||
endif()
|
||||
|
||||
#-----------------------------------------------------------------------------
|
||||
# default settings
|
||||
#-----------------------------------------------------------------------------
|
||||
|
||||
configure_file(${PROJECT_SOURCE_DIR}/settings/defaults.php
|
||||
${PROJECT_BINARY_DIR}/settings/settings.php)
|
||||
|
||||
#-----------------------------------------------------------------------------
|
||||
# Tests
|
||||
#-----------------------------------------------------------------------------
|
||||
@@ -122,60 +168,21 @@ if (BUILD_TESTS)
|
||||
|
||||
set(TEST_BDD db osm2pgsql api)
|
||||
|
||||
find_program(PYTHON_BEHAVE behave)
|
||||
find_program(PYLINT NAMES pylint3 pylint)
|
||||
find_program(PYTEST NAMES pytest py.test-3 py.test)
|
||||
find_program(PHPCS phpcs)
|
||||
find_program(PHPUNIT phpunit)
|
||||
foreach (test ${TEST_BDD})
|
||||
add_test(NAME bdd_${test}
|
||||
COMMAND behave ${test}
|
||||
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}/test/bdd)
|
||||
set_tests_properties(bdd_${test}
|
||||
PROPERTIES ENVIRONMENT "NOMINATIM_DIR=${PROJECT_BINARY_DIR}")
|
||||
endforeach()
|
||||
|
||||
if (PYTHON_BEHAVE)
|
||||
message(STATUS "Using Python behave binary ${PYTHON_BEHAVE}")
|
||||
foreach (test ${TEST_BDD})
|
||||
add_test(NAME bdd_${test}
|
||||
COMMAND ${PYTHON_BEHAVE} ${test}
|
||||
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}/test/bdd)
|
||||
set_tests_properties(bdd_${test}
|
||||
PROPERTIES ENVIRONMENT "NOMINATIM_DIR=${PROJECT_BINARY_DIR}")
|
||||
endforeach()
|
||||
else()
|
||||
message(WARNING "behave not found. BDD tests disabled." )
|
||||
endif()
|
||||
add_test(NAME php
|
||||
COMMAND phpunit ./
|
||||
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}/test/php)
|
||||
|
||||
if (PHPUNIT)
|
||||
message(STATUS "Using phpunit binary ${PHPUNIT}")
|
||||
add_test(NAME php
|
||||
COMMAND ${PHPUNIT} ./
|
||||
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}/test/php)
|
||||
else()
|
||||
message(WARNING "phpunit not found. PHP unit tests disabled." )
|
||||
endif()
|
||||
|
||||
if (PHPCS)
|
||||
message(STATUS "Using phpcs binary ${PHPCS}")
|
||||
add_test(NAME phpcs
|
||||
COMMAND ${PHPCS} --report-width=120 --colors lib website utils
|
||||
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})
|
||||
else()
|
||||
message(WARNING "phpcs not found. PHP linting tests disabled." )
|
||||
endif()
|
||||
|
||||
if (PYLINT)
|
||||
message(STATUS "Using pylint binary ${PYLINT}")
|
||||
add_test(NAME pylint
|
||||
COMMAND ${PYLINT} nominatim
|
||||
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})
|
||||
else()
|
||||
message(WARNING "pylint not found. Python linting tests disabled.")
|
||||
endif()
|
||||
|
||||
if (PYTEST)
|
||||
message(STATUS "Using pytest binary ${PYTEST}")
|
||||
add_test(NAME pytest
|
||||
COMMAND ${PYTEST} test/python
|
||||
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})
|
||||
else()
|
||||
message(WARNING "pytest not found. Python tests disabled." )
|
||||
endif()
|
||||
add_test(NAME phpcs
|
||||
COMMAND phpcs --report-width=120 --colors lib website utils
|
||||
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})
|
||||
endif()
|
||||
|
||||
#-----------------------------------------------------------------------------
|
||||
@@ -193,71 +200,3 @@ endif()
|
||||
if (BUILD_DOCS)
|
||||
add_subdirectory(docs)
|
||||
endif()
|
||||
|
||||
#-----------------------------------------------------------------------------
|
||||
# Manual page
|
||||
#-----------------------------------------------------------------------------
|
||||
|
||||
if (BUILD_MANPAGE)
|
||||
add_subdirectory(manual)
|
||||
endif()
|
||||
|
||||
#-----------------------------------------------------------------------------
|
||||
# Installation
|
||||
#-----------------------------------------------------------------------------
|
||||
|
||||
|
||||
include(GNUInstallDirs)
|
||||
set(NOMINATIM_DATADIR ${CMAKE_INSTALL_FULL_DATADIR}/${PROJECT_NAME})
|
||||
set(NOMINATIM_LIBDIR ${CMAKE_INSTALL_FULL_LIBDIR}/${PROJECT_NAME})
|
||||
set(NOMINATIM_CONFIGDIR ${CMAKE_INSTALL_FULL_SYSCONFDIR}/${PROJECT_NAME})
|
||||
|
||||
if (BUILD_IMPORTER)
|
||||
configure_file(${PROJECT_SOURCE_DIR}/cmake/tool-installed.tmpl installed.bin)
|
||||
install(PROGRAMS ${PROJECT_BINARY_DIR}/installed.bin
|
||||
DESTINATION ${CMAKE_INSTALL_BINDIR}
|
||||
RENAME nominatim)
|
||||
|
||||
install(DIRECTORY nominatim
|
||||
DESTINATION ${NOMINATIM_LIBDIR}/lib-python
|
||||
FILES_MATCHING PATTERN "*.py"
|
||||
PATTERN __pycache__ EXCLUDE)
|
||||
install(DIRECTORY lib-sql DESTINATION ${NOMINATIM_LIBDIR})
|
||||
|
||||
install(FILES data/country_name.sql
|
||||
${COUNTRY_GRID_FILE}
|
||||
data/words.sql
|
||||
DESTINATION ${NOMINATIM_DATADIR})
|
||||
endif()
|
||||
|
||||
if (BUILD_OSM2PGSQL)
|
||||
if (${CMAKE_VERSION} VERSION_LESS 3.13)
|
||||
# Installation of subdirectory targets was only introduced in 3.13.
|
||||
# So just copy the osm2pgsql file for older versions.
|
||||
install(PROGRAMS ${PROJECT_BINARY_DIR}/osm2pgsql/osm2pgsql
|
||||
DESTINATION ${NOMINATIM_LIBDIR})
|
||||
else()
|
||||
install(TARGETS osm2pgsql RUNTIME DESTINATION ${NOMINATIM_LIBDIR})
|
||||
endif()
|
||||
endif()
|
||||
|
||||
if (BUILD_MODULE)
|
||||
install(PROGRAMS ${PROJECT_BINARY_DIR}/module/nominatim.so
|
||||
DESTINATION ${NOMINATIM_LIBDIR}/module)
|
||||
endif()
|
||||
|
||||
if (BUILD_API)
|
||||
install(DIRECTORY lib-php DESTINATION ${NOMINATIM_LIBDIR})
|
||||
endif()
|
||||
|
||||
install(FILES settings/env.defaults
|
||||
settings/address-levels.json
|
||||
settings/phrase-settings.json
|
||||
settings/import-admin.style
|
||||
settings/import-street.style
|
||||
settings/import-address.style
|
||||
settings/import-full.style
|
||||
settings/import-extratags.style
|
||||
settings/legacy_icu_tokenizer.yaml
|
||||
settings/icu-rules/extended-unicode-to-asccii.yaml
|
||||
DESTINATION ${NOMINATIM_CONFIGDIR})
|
||||
|
||||
@@ -49,18 +49,22 @@ are in process of consolidating the style. The following rules apply:
|
||||
* for PHP variables use CamelCase with a prefixing letter indicating the type
|
||||
(i - integer, f - float, a - array, s - string, o - object)
|
||||
|
||||
The coding style is enforced with PHPCS and pylint. It can be tested with:
|
||||
The coding style is enforced with PHPCS and can be tested with:
|
||||
|
||||
```
|
||||
phpcs --report-width=120 --colors .
|
||||
pylint3 --extension-pkg-whitelist=osmium nominatim
|
||||
phpcs --report-width=120 --colors .
|
||||
```
|
||||
|
||||
## Testing
|
||||
|
||||
Before submitting a pull request make sure that the tests pass:
|
||||
Before submitting a pull request make sure that the following tests pass:
|
||||
|
||||
```
|
||||
cd build
|
||||
make test
|
||||
cd test/bdd
|
||||
behave -DBUILDDIR=<builddir> db osm2pgsql
|
||||
```
|
||||
|
||||
```
|
||||
cd test/php
|
||||
phpunit ./
|
||||
```
|
||||
|
||||
23
ChangeLog
23
ChangeLog
@@ -1,26 +1,3 @@
|
||||
3.7.0
|
||||
|
||||
* switch to dotenv for configuration file
|
||||
* introduce 'make install' (reorganising most of the code)
|
||||
* introduce nominatim tool as replacement for various php scripts
|
||||
* introduce project directories and allow multiple installations from same build
|
||||
* clean up BDD tests: drop nose, reorganise step code
|
||||
* simplify test database for API BDD tests and autoinstall database
|
||||
* port most of the code for command-line tools to Python
|
||||
(thanks to @darkshredder and @AntoJvlt)
|
||||
* add tests for all tooling
|
||||
* replace pyosmium-get-changes with custom internal implementation using
|
||||
pyosmium
|
||||
* improve search for queries with housenumber and partial terms
|
||||
* add database versioning
|
||||
* use jinja2 for preprocessing SQL files
|
||||
* introduce automatic migrations
|
||||
* reverse fix preference of interpolations over housenumbers
|
||||
* parallelize indexing of postcodes
|
||||
* add non-key indexes to speed up housenumber + street searches
|
||||
* switch housenumber field in placex to save transliterated names
|
||||
|
||||
|
||||
3.6.0
|
||||
|
||||
* add full support for searching by and displaying of addr:* tags
|
||||
|
||||
34
README.md
34
README.md
@@ -1,5 +1,4 @@
|
||||
[](https://github.com/osm-search/Nominatim/actions?query=workflow%3A%22CI+Tests%22)
|
||||
[](https://codecov.io/gh/osm-search/Nominatim)
|
||||
|
||||
Nominatim
|
||||
=========
|
||||
@@ -25,14 +24,15 @@ Installing and running Nominatim is something for experienced system
|
||||
administrators only who can do some trouble-shooting themselves. We are sorry,
|
||||
but we can not provide installation support. We are all doing this in our free
|
||||
time and there is just so much of that time to go around. Do not open issues in
|
||||
our bug tracker if you need help. Use the discussions forum
|
||||
or ask for help on [help.openstreetmap.org](https://help.openstreetmap.org/).**
|
||||
our bug tracker if you need help. You can ask questions on the mailing list
|
||||
(see below) or on [help.openstreetmap.org](https://help.openstreetmap.org/).**
|
||||
|
||||
The latest stable release can be downloaded from https://nominatim.org.
|
||||
There you can also find [installation instructions for the release](https://nominatim.org/release-docs/latest/admin/Installation), as well as an extensive [Troubleshooting/FAQ section](https://nominatim.org/release-docs/latest/admin/Faq/).
|
||||
|
||||
[Detailed installation instructions for current master](https://nominatim.org/release-docs/develop/admin/Installation)
|
||||
can be found at nominatim.org as well.
|
||||
Detailed installation instructions for the development version can be
|
||||
found at [nominatim.org](https://nominatim.org/release-docs/develop/admin/Installation)
|
||||
as well.
|
||||
|
||||
A quick summary of the necessary steps:
|
||||
|
||||
@@ -42,15 +42,12 @@ A quick summary of the necessary steps:
|
||||
cd build
|
||||
cmake ..
|
||||
make
|
||||
sudo make install
|
||||
|
||||
2. Create a project directory, get OSM data and import:
|
||||
2. Get OSM data and import:
|
||||
|
||||
mkdir nominatim-project
|
||||
cd nominatim-project
|
||||
nominatim import --osm-file <your planet file>
|
||||
./build/utils/setup.php --osm-file <your planet file> --all
|
||||
|
||||
3. Point your webserver to the nominatim-project/website directory.
|
||||
3. Point your webserver to the ./build/website directory.
|
||||
|
||||
|
||||
License
|
||||
@@ -62,14 +59,13 @@ The source code is available under a GPLv2 license.
|
||||
Contributing
|
||||
============
|
||||
|
||||
Contributions, bugreport and pull requests are welcome.
|
||||
For details see [contribution guide](CONTRIBUTING.md).
|
||||
Contributions are welcome. For details see [contribution guide](CONTRIBUTING.md).
|
||||
|
||||
Both bug reports and pull requests are welcome.
|
||||
|
||||
|
||||
Questions and help
|
||||
==================
|
||||
Mailing list
|
||||
============
|
||||
|
||||
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).
|
||||
For questions you can join the geocoding mailing list, see
|
||||
https://lists.openstreetmap.org/listinfo/geocoding
|
||||
|
||||
39
SECURITY.md
39
SECURITY.md
@@ -1,39 +0,0 @@
|
||||
# Security Policy
|
||||
|
||||
## Supported Versions
|
||||
|
||||
All Nominatim releases receive security updates for two years.
|
||||
|
||||
The following table lists the end of support for all currently supported
|
||||
versions.
|
||||
|
||||
| Version | End of support for security updates |
|
||||
| ------- | ----------------------------------- |
|
||||
| 3.7.x | 2023-04-05 |
|
||||
| 3.6.x | 2022-12-12 |
|
||||
| 3.5.x | 2022-06-05 |
|
||||
| 3.4.x | 2021-10-24 |
|
||||
|
||||
## Reporting a Vulnerability
|
||||
|
||||
If you believe, you have found an issue in Nominatim that has implications on
|
||||
security, please send a description of the issue to **security@nominatim.org**.
|
||||
You will receive an acknowledgement of your mail within 3 work days where we
|
||||
also notify you of the next steps.
|
||||
|
||||
## How we Disclose Security Issues
|
||||
|
||||
** The following section only applies to security issues found in released
|
||||
versions. Issues that concern the master development branch only will be
|
||||
fixed immediately on the branch with the corresponding PR containing the
|
||||
description of the nature and severity of the issue. **
|
||||
|
||||
Patches for identified security issues are applied to all affected versions and
|
||||
new minor versions are released. At the same time we release a statement at
|
||||
the [Nominatim blog](https://nominatim.org/blog/) describing the nature of the
|
||||
incident. Announcements will also be published at the
|
||||
[geocoding mailinglist](https://lists.openstreetmap.org/listinfo/geocoding).
|
||||
|
||||
## List of Previous Incidents
|
||||
|
||||
* 2020-05-04 - [SQL injection issue on /details endpoint](https://lists.openstreetmap.org/pipermail/geocoding/2020-May/002012.html)
|
||||
4
cmake/script.tmpl
Executable file
4
cmake/script.tmpl
Executable file
@@ -0,0 +1,4 @@
|
||||
#!@PHP_BIN@ -Cq
|
||||
<?php
|
||||
require_once(dirname(dirname(__FILE__)).'/settings/settings.php');
|
||||
require_once(CONST_BasePath.'/@script_source@');
|
||||
@@ -1,17 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
import sys
|
||||
import os
|
||||
|
||||
sys.path.insert(1, '@NOMINATIM_LIBDIR@/lib-python')
|
||||
|
||||
os.environ['NOMINATIM_NOMINATIM_TOOL'] = os.path.abspath(__file__)
|
||||
|
||||
from nominatim import cli
|
||||
|
||||
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@'))
|
||||
@@ -1,17 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
import sys
|
||||
import os
|
||||
|
||||
sys.path.insert(1, '@CMAKE_SOURCE_DIR@')
|
||||
|
||||
os.environ['NOMINATIM_NOMINATIM_TOOL'] = os.path.abspath(__file__)
|
||||
|
||||
from nominatim import cli
|
||||
|
||||
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@'))
|
||||
5
cmake/website.tmpl
Executable file
5
cmake/website.tmpl
Executable file
@@ -0,0 +1,5 @@
|
||||
<?php
|
||||
@define('CONST_Debug', (isset($_GET['debug']) && $_GET['debug']));
|
||||
require_once(dirname(dirname(__FILE__)).'/settings/settings-frontend.php');
|
||||
|
||||
require_once(CONST_BasePath.'/@script_source@');
|
||||
14
codecov.yml
14
codecov.yml
@@ -1,14 +0,0 @@
|
||||
codecov:
|
||||
require_ci_to_pass: yes
|
||||
|
||||
coverage:
|
||||
status:
|
||||
project: off
|
||||
patch: off
|
||||
|
||||
comment:
|
||||
require_changes: true
|
||||
after_n_builds: 2
|
||||
|
||||
fixes:
|
||||
- "Nominatim/::"
|
||||
26
data/gb_postcode_table.sql
Normal file
26
data/gb_postcode_table.sql
Normal file
@@ -0,0 +1,26 @@
|
||||
-- This data contains Ordnance Survey data © Crown copyright and database right 2010.
|
||||
-- Code-Point Open contains Royal Mail data © Royal Mail copyright and database right 2010.
|
||||
-- OS data may be used under the terms of the OS OpenData licence:
|
||||
-- http://www.ordnancesurvey.co.uk/oswebsite/opendata/licence/docs/licence.pdf
|
||||
|
||||
SET statement_timeout = 0;
|
||||
SET client_encoding = 'UTF8';
|
||||
SET standard_conforming_strings = off;
|
||||
SET check_function_bodies = false;
|
||||
SET client_min_messages = warning;
|
||||
SET escape_string_warning = off;
|
||||
|
||||
SET search_path = public, pg_catalog;
|
||||
|
||||
SET default_tablespace = '';
|
||||
|
||||
SET default_with_oids = false;
|
||||
|
||||
CREATE TABLE gb_postcode (
|
||||
id integer,
|
||||
postcode character varying(9),
|
||||
geometry geometry,
|
||||
CONSTRAINT enforce_dims_geometry CHECK ((st_ndims(geometry) = 2)),
|
||||
CONSTRAINT enforce_srid_geometry CHECK ((st_srid(geometry) = 4326))
|
||||
);
|
||||
|
||||
16
data/us_postcode_table.sql
Normal file
16
data/us_postcode_table.sql
Normal file
@@ -0,0 +1,16 @@
|
||||
SET statement_timeout = 0;
|
||||
SET client_encoding = 'UTF8';
|
||||
SET check_function_bodies = false;
|
||||
SET client_min_messages = warning;
|
||||
|
||||
SET search_path = public, pg_catalog;
|
||||
|
||||
SET default_tablespace = '';
|
||||
|
||||
SET default_with_oids = false;
|
||||
|
||||
CREATE TABLE us_postcode (
|
||||
postcode text,
|
||||
x double precision,
|
||||
y double precision
|
||||
);
|
||||
@@ -29787,7 +29787,7 @@ st 5557484
|
||||
|
||||
-- prefill word table
|
||||
|
||||
select count(precompute_words(v)) from (select distinct svals(name) as v from place) as w where v is not null;
|
||||
select count(make_keywords(v)) from (select distinct svals(name) as v from place) as w where v is not null;
|
||||
select count(getorcreate_housenumber_id(make_standard_name(v))) from (select distinct address->'housenumber' as v from place where address ? 'housenumber') as w;
|
||||
|
||||
-- copy the word frequencies
|
||||
|
||||
@@ -47,16 +47,15 @@ The file `import_multiple_regions.sh` needs to be edited as per your requirement
|
||||
|
||||
BASEURL="https://download.geofabrik.de"
|
||||
DOWNCOUNTRYPOSTFIX="-latest.osm.pbf"
|
||||
|
||||
### Setting up multiple regions
|
||||
|
||||
|
||||
!!! tip
|
||||
If your database already exists and you want to add more countries,
|
||||
replace the setting up part
|
||||
If your database already exists and you want to add more countries, replace the setting up part
|
||||
`${SETUPFILE} --osm-file ${UPDATEDIR}/tmp/combined.osm.pbf --all 2>&1`
|
||||
with `${UPDATEFILE} --import-file ${UPDATEDIR}/tmp/combined.osm.pbf --index --index-instances N 2>&1`
|
||||
where N is the numbers of CPUs in your system.
|
||||
|
||||
### Setting up multiple regions
|
||||
|
||||
Run the following command from your Nominatim directory after configuring the file.
|
||||
|
||||
bash ./utils/import_multiple_regions.sh
|
||||
@@ -155,7 +154,7 @@ Make sure that the PostgreSQL server package is installed on the machine
|
||||
the PostgreSQL server itself.
|
||||
|
||||
Download and compile Nominatim as per standard instructions. Once done, you find
|
||||
the normalization library in `build/module/nominatim.so`. Copy the file to
|
||||
the nomrmalization library in `build/module/nominatim.so`. Copy the file to
|
||||
the database server at a location where it is readable and executable by the
|
||||
PostgreSQL server process.
|
||||
|
||||
@@ -163,11 +162,11 @@ PostgreSQL server process.
|
||||
|
||||
On the client side you now need to configure the import to point to the
|
||||
correct location of the library **on the database server**. Add the following
|
||||
line to your your `.env` file:
|
||||
line to your your `settings/local.php` file:
|
||||
|
||||
```php
|
||||
NOMINATIM_DATABASE_MODULE_PATH="<directory on the database server where nominatim.so resides>"
|
||||
@define('CONST_Database_Module_Path', '<directory on the database server where nominatim.so resides>');
|
||||
```
|
||||
|
||||
Now change the `NOMINATIM_DATABASE_DSN` to point to your remote server and continue
|
||||
Now change the `CONST_Database_DSN` to point to your remote server and continue
|
||||
to follow the [standard instructions for importing](/admin/Import).
|
||||
|
||||
@@ -1,101 +0,0 @@
|
||||
# Customization of the Database
|
||||
|
||||
This section explains in detail how to configure a Nominatim import and
|
||||
the various means to use external data.
|
||||
|
||||
## External postcode data
|
||||
|
||||
Nominatim creates a table of known postcode centroids during import. This table
|
||||
is used for searches of postcodes and for adding postcodes to places where the
|
||||
OSM data does not provide one. These postcode centroids are mainly computed
|
||||
from the OSM data itself. In addition, Nominatim supports reading postcode
|
||||
information from an external CSV file, to supplement the postcodes that are
|
||||
missing in OSM.
|
||||
|
||||
To enable external postcode support, simply put one CSV file per country into
|
||||
your project directory and name it `<CC>_postcodes.csv`. `<CC>` must be the
|
||||
two-letter country code for which to apply the file. The file may also be
|
||||
gzipped. Then it must be called `<CC>_postcodes.csv.gz`.
|
||||
|
||||
The CSV file must use commas as a delimiter and have a header line. Nominatim
|
||||
expects three columns to be present: `postcode`, `lat` and `lon`. All other
|
||||
columns are ignored. `lon` and `lat` must describe the x and y coordinates of the
|
||||
postcode centroids in WGS84.
|
||||
|
||||
The postcode files are loaded only when there is data for the given country
|
||||
in your database. For example, if there is a `us_postcodes.csv` file in your
|
||||
project directory but you import only an excerpt of Italy, then the US postcodes
|
||||
will simply be ignored.
|
||||
|
||||
As a rule, the external postcode data should be put into the project directory
|
||||
**before** starting the initial import. Still, you can add, remove and update the
|
||||
external postcode data at any time. Simply
|
||||
run:
|
||||
|
||||
```
|
||||
nominatim refresh --postcodes
|
||||
```
|
||||
|
||||
to make the changes visible in your database. Be aware, however, that the changes
|
||||
only have an immediate effect on searches for postcodes. Postcodes that were
|
||||
added to places are only updated, when they are reindexed. That usually happens
|
||||
only during replication updates.
|
||||
|
||||
## Installing Tiger housenumber data for the US
|
||||
|
||||
Nominatim is able to use the official [TIGER](https://www.census.gov/geographies/mapping-files/time-series/geo/tiger-line-file.html)
|
||||
address set to complement the OSM house number data in the US. You can add
|
||||
TIGER data to your own Nominatim instance by following these steps. The
|
||||
entire US adds about 10GB to your database.
|
||||
|
||||
1. Get preprocessed TIGER 2020 data:
|
||||
|
||||
cd $PROJECT_DIR
|
||||
wget https://nominatim.org/data/tiger2020-nominatim-preprocessed.csv.tar.gz
|
||||
|
||||
2. Import the data into your Nominatim database:
|
||||
|
||||
nominatim add-data --tiger-data tiger2020-nominatim-preprocessed.csv.tar.gz
|
||||
|
||||
3. Enable use of the Tiger data in your `.env` by adding:
|
||||
|
||||
echo NOMINATIM_USE_US_TIGER_DATA=yes >> .env
|
||||
|
||||
4. Apply the new settings:
|
||||
|
||||
nominatim refresh --functions
|
||||
|
||||
|
||||
See the [developer's guide](../develop/data-sources.md#us-census-tiger) for more
|
||||
information on how the data got preprocessed.
|
||||
|
||||
## Special phrases import
|
||||
|
||||
As described in the [Importation chapter](Import.md), it is possible to
|
||||
import special phrases from the wiki with the following command:
|
||||
|
||||
```sh
|
||||
nominatim special-phrases --import-from-wiki
|
||||
```
|
||||
|
||||
But, it is also possible to import some phrases from a csv file.
|
||||
To do so, you have access to 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
|
||||
be removed.
|
||||
|
||||
If you want to only add new phrases and not update the other ones you can add
|
||||
the argument `--no-replace` to the import command. For example:
|
||||
|
||||
```sh
|
||||
nominatim special-phrases --import-from-csv <csv file> --no-replace
|
||||
```
|
||||
|
||||
This will add the phrases present in the csv file into the database without
|
||||
removing the other ones.
|
||||
@@ -1,7 +1,7 @@
|
||||
# Deploying Nominatim
|
||||
|
||||
The Nominatim API is implemented as a PHP application. The `website/` directory
|
||||
in the project directory contains the configured website. You can serve this
|
||||
in the build directory contains the configured website. You can serve this
|
||||
in a production environment with any web server that is capable to run
|
||||
PHP scripts.
|
||||
|
||||
@@ -13,11 +13,10 @@ to run a web service. Please refer to the documentation of
|
||||
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
|
||||
using the default installation prefix `/usr/local`. If you have put it
|
||||
somewhere else, you need to adjust the commands and configuration
|
||||
accordingly.
|
||||
Throughout this page, we assume that your Nominatim build directory is
|
||||
located in `/srv/nominatim/build` and the source code in
|
||||
`/srv/nominatim/Nominatim`. If you have put it somewhere else, you
|
||||
need to adjust the commands and configuration accordingly.
|
||||
|
||||
We further assume that your web server runs as user `www-data`. Older
|
||||
versions of CentOS may still use the user name `apache`. You also need
|
||||
@@ -30,7 +29,7 @@ web server user. You can check that the permissions are correct by accessing
|
||||
on of the php files as the web server user:
|
||||
|
||||
``` sh
|
||||
sudo -u www-data head -n 1 /srv/nominatim-project/website/search.php
|
||||
sudo -u www-data head -n 1 /srv/nominatim/build/website/search.php
|
||||
```
|
||||
|
||||
If this shows a permission error, then you need to adapt the permissions of
|
||||
@@ -41,11 +40,11 @@ web server access. At a minimum the following SELinux labelling should be done
|
||||
for Nominatim:
|
||||
|
||||
``` sh
|
||||
sudo semanage fcontext -a -t httpd_sys_content_t "/usr/local/nominatim/lib/lib-php(/.*)?"
|
||||
sudo semanage fcontext -a -t httpd_sys_content_t "/srv/nominatim-project/website(/.*)?"
|
||||
sudo semanage fcontext -a -t lib_t "/srv/nominatim-project/module/nominatim.so"
|
||||
sudo restorecon -R -v /usr/local/lib/nominatim
|
||||
sudo restorecon -R -v /srv/nominatim-project
|
||||
sudo semanage fcontext -a -t httpd_sys_content_t "/srv/nominatim/Nominatim/(website|lib|settings)(/.*)?"
|
||||
sudo semanage fcontext -a -t httpd_sys_content_t "/srv/nominatim/build/(website|settings)(/.*)?"
|
||||
sudo semanage fcontext -a -t lib_t "/srv/nominatim/build/module/nominatim.so"
|
||||
sudo restorecon -R -v /srv/nominatim/Nominatim
|
||||
sudo restorecon -R -v /srv/nominatim/build
|
||||
```
|
||||
|
||||
## Nominatim with Apache
|
||||
@@ -66,13 +65,13 @@ Make sure your Apache configuration contains the required permissions for the
|
||||
directory and create an alias:
|
||||
|
||||
``` apache
|
||||
<Directory "/srv/nominatim-project/website">
|
||||
<Directory "/srv/nominatim/build/website">
|
||||
Options FollowSymLinks MultiViews
|
||||
AddType text/html .php
|
||||
DirectoryIndex search.php
|
||||
Require all granted
|
||||
</Directory>
|
||||
Alias /nominatim /srv/nominatim-project/website
|
||||
Alias /nominatim /srv/nominatim/build/website
|
||||
```
|
||||
|
||||
After making changes in the apache config you need to restart apache.
|
||||
@@ -111,7 +110,7 @@ Tell nginx that php files are special and to fastcgi_pass to the php-fpm
|
||||
unix socket by adding the location definition to the default configuration.
|
||||
|
||||
``` nginx
|
||||
root /srv/nominatim-project/website;
|
||||
root /srv/nominatim/build/website;
|
||||
index search.php;
|
||||
location / {
|
||||
try_files $uri $uri/ @php;
|
||||
|
||||
@@ -16,7 +16,7 @@ was killed. If it looks like this:
|
||||
then you can resume with the following command:
|
||||
|
||||
```sh
|
||||
nominatim import --continue indexing
|
||||
./utils/setup.php --index --create-search-indices --create-country-names
|
||||
```
|
||||
|
||||
If the reported rank is 26 or higher, you can also safely add `--index-noanalyse`.
|
||||
@@ -31,7 +31,7 @@ list for hints.
|
||||
If it happened during index creation you can try rerunning the step with
|
||||
|
||||
```sh
|
||||
nominatim import --continue indexing
|
||||
./utils/setup.php --create-search-indices --ignore-errors
|
||||
```
|
||||
|
||||
Otherwise it's best to start the full setup from the beginning.
|
||||
@@ -93,7 +93,7 @@ on a non-managed machine.
|
||||
|
||||
### I see the error: "function transliteration(text) does not exist"
|
||||
|
||||
Reinstall the nominatim functions with `nominatim refresh --functions`
|
||||
Reinstall the nominatim functions with `setup.php --create--functions`
|
||||
and check for any errors, e.g. a missing `nominatim.so` file.
|
||||
|
||||
### I see the error: "ERROR: mmap (remap) failed"
|
||||
@@ -113,8 +113,7 @@ Double-check clang is installed. Instead of `make` try running `make CLANG=true`
|
||||
|
||||
### nominatim UPDATE failed: ERROR: buffer 179261 is not owned by resource owner Portal
|
||||
|
||||
Several users [reported this](https://github.com/openstreetmap/Nominatim/issues/1168)
|
||||
during the initial import of the database. It's
|
||||
Several users [reported this](https://github.com/openstreetmap/Nominatim/issues/1168) during the initial import of the database. It's
|
||||
something PostgreSQL internal Nominatim doesn't control. And PostgreSQL forums
|
||||
suggest it's threading related but definitely some kind of crash of a process.
|
||||
Users reported either rebooting the server, different hardware or just trying
|
||||
@@ -203,7 +202,7 @@ See the installation instructions for a full list of required packages.
|
||||
### I forgot to delete the flatnodes file before starting an import.
|
||||
|
||||
That's fine. For each import the flatnodes file get overwritten.
|
||||
See [https://help.openstreetmap.org/questions/52419/nominatim-flatnode-storage](https://help.openstreetmap.org/questions/52419/nominatim-flatnode-storage)
|
||||
See [https://help.openstreetmap.org/questions/52419/nominatim-flatnode-storage]()
|
||||
for more information.
|
||||
|
||||
|
||||
@@ -212,3 +211,11 @@ for more information.
|
||||
### Can I import negative OSM ids into Nominatim?
|
||||
|
||||
See [this question of Stackoverflow](https://help.openstreetmap.org/questions/64662/nominatim-flatnode-with-negative-id).
|
||||
|
||||
### Missing XML or text declaration
|
||||
|
||||
The website might show: `XML Parsing Error: XML or text declaration not at start of entity Location.`
|
||||
|
||||
Make sure there are no spaces at the beginning of your `settings/local.php` file.
|
||||
|
||||
|
||||
|
||||
@@ -1,54 +1,22 @@
|
||||
# Importing the Database
|
||||
|
||||
The following instructions explain how to create a Nominatim database
|
||||
from an OSM planet file. It is assumed that you have already successfully
|
||||
installed the Nominatim software itself and the `nominatim` tool can be found
|
||||
in your `PATH`. If this is not the case, return to the
|
||||
[installation page](Installation.md).
|
||||
from an OSM planet file and how to keep the database up to date. It
|
||||
is assumed that you have already successfully installed the Nominatim
|
||||
software itself, if not return to the [installation page](Installation.md).
|
||||
|
||||
## Creating the project directory
|
||||
## Configuration setup in settings/local.php
|
||||
|
||||
Before you start the import, you should create a project directory for your
|
||||
new database installation. This directory receives all data that is related
|
||||
to a single Nominatim setup: configuration, extra data, etc. Create a project
|
||||
directory apart from the Nominatim software and change into the directory:
|
||||
The Nominatim server can be customized via the file `settings/local.php`
|
||||
in the build directory. Note that this is a PHP file, so it must always
|
||||
start like this:
|
||||
|
||||
```
|
||||
mkdir ~/nominatim-planet
|
||||
cd ~/nominatim-planet
|
||||
```
|
||||
<?php
|
||||
|
||||
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
|
||||
```
|
||||
|
||||
The Nominatim tool assumes per default that the current working directory is
|
||||
the project directory but you may explicitly state a different directory using
|
||||
the `--project-dir` parameter. The following instructions assume that you run
|
||||
all commands from the project directory.
|
||||
|
||||
!!! tip "Migration Tip"
|
||||
|
||||
Nominatim used to be run directly from the build directory until version 3.6.
|
||||
Essentially, the build directory functioned as the project directory
|
||||
for the database installation. This setup still works and can be useful for
|
||||
development purposes. It is not recommended anymore for production setups.
|
||||
Create a project directory that is separate from the Nominatim software.
|
||||
|
||||
### Configuration setup in `.env`
|
||||
|
||||
The Nominatim server can be customized via an `.env` configuration file in the
|
||||
project directory. This is a file in [dotenv](https://github.com/theskumar/python-dotenv)
|
||||
format which looks the same as variable settings in a standard shell environment.
|
||||
You can also set the same configuration via environment variables. All
|
||||
settings have a `NOMINATIM_` prefix to avoid conflicts with other environment
|
||||
variables.
|
||||
without any leading spaces.
|
||||
|
||||
There are lots of configuration settings you can tweak. Have a look
|
||||
at `Nominatim/settings/env.default` for a full list. Most should have a sensible default.
|
||||
at `settings/default.php` for a full list. Most should have a sensible default.
|
||||
|
||||
#### Flatnode files
|
||||
|
||||
@@ -56,9 +24,9 @@ If you plan to import a large dataset (e.g. Europe, North America, planet),
|
||||
you should also enable flatnode storage of node locations. With this
|
||||
setting enabled, node coordinates are stored in a simple file instead
|
||||
of the database. This will save you import time and disk storage.
|
||||
Add to your `.env`:
|
||||
Add to your `settings/local.php`:
|
||||
|
||||
NOMINATIM_FLATNODE_FILE="/path/to/flatnode.file"
|
||||
@define('CONST_Osm2pgsql_Flatnode_File', '/path/to/flatnode.file');
|
||||
|
||||
Replace the second part with a suitable path on your system and make sure
|
||||
the directory exists. There should be at least 75GB of free space.
|
||||
@@ -70,9 +38,9 @@ the directory exists. There should be at least 75GB of free space.
|
||||
Wikipedia can be used as an optional auxiliary data source to help indicate
|
||||
the importance of OSM features. Nominatim will work without this information
|
||||
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:
|
||||
This data is available as a binary download:
|
||||
|
||||
cd $PROJECT_DIR
|
||||
cd $NOMINATIM_SOURCE_DIR/data
|
||||
wget https://www.nominatim.org/data/wikimedia-importance.sql.gz
|
||||
|
||||
The file is about 400MB and adds around 4GB to the Nominatim database.
|
||||
@@ -80,22 +48,17 @@ The file is about 400MB and adds around 4GB to the Nominatim database.
|
||||
!!! 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.
|
||||
`./utils/setup.php --import-wikipedia-articles`
|
||||
and `./utils/update.php --recompute-importance`.
|
||||
|
||||
### External postcodes
|
||||
### Great Britain, USA postcodes
|
||||
|
||||
Nominatim can use postcodes from an external source to improve searching with
|
||||
postcodes. We provide precomputed postcodes sets for the US (using TIGER data)
|
||||
and the UK (using the [CodePoint OpenData set](https://osdatahub.os.uk/downloads/open/CodePointOpen).
|
||||
This data can be optionally downloaded into the project directory:
|
||||
Nominatim can use postcodes from an external source to improve searches that
|
||||
involve a GB or US postcode. This data can be optionally downloaded:
|
||||
|
||||
cd $PROJECT_DIR
|
||||
wget https://www.nominatim.org/data/gb_postcodes.csv.gz
|
||||
wget https://www.nominatim.org/data/us_postcodes.csv.gz
|
||||
|
||||
You can also add your own custom postcode sources, see
|
||||
[Customization of postcodes](Customization.md#external-postcode-data).
|
||||
cd $NOMINATIM_SOURCE_DIR/data
|
||||
wget https://www.nominatim.org/data/gb_postcode_data.sql.gz
|
||||
wget https://www.nominatim.org/data/us_postcode_data.sql.gz
|
||||
|
||||
## Choosing the data to import
|
||||
|
||||
@@ -123,14 +86,11 @@ that Nominatim cannot compute the areas for some administrative areas.
|
||||
About half of the data in Nominatim's database is not really used for serving
|
||||
the API. It is only there to allow the data to be updated from the latest
|
||||
changes from OSM. For many uses these dynamic updates are not really required.
|
||||
If you don't plan to apply updates, you can run the import with the
|
||||
`--no-updates` parameter. This will drop the dynamic part of the database as
|
||||
soon as it is not required anymore.
|
||||
|
||||
You can also drop the dynamic part later using the following command:
|
||||
If you don't plan to apply updates, the dynamic part of the database can be
|
||||
safely dropped using the following command:
|
||||
|
||||
```
|
||||
nominatim freeze
|
||||
./utils/setup.php --drop
|
||||
```
|
||||
|
||||
Note that you still need to provide for sufficient disk space for the initial
|
||||
@@ -164,7 +124,7 @@ import styles available which only read selected data:
|
||||
Like the full style but also adds most of the OSM tags into the extratags
|
||||
column.
|
||||
|
||||
The style can be changed with the configuration `NOMINATIM_IMPORT_STYLE`.
|
||||
The style can be changed with the configuration `CONST_Import_Style`.
|
||||
|
||||
To give you an idea of the impact of using the different styles, the table
|
||||
below gives rough estimates of the final database size after import of a
|
||||
@@ -193,15 +153,12 @@ can be found in the development section.
|
||||
[Geofabrik](https://download.geofabrik.de).
|
||||
|
||||
Download the data to import. Then issue the following command
|
||||
from the **project directory** to start the import:
|
||||
from the **build directory** to start the import:
|
||||
|
||||
```sh
|
||||
nominatim import --osm-file <data file> 2>&1 | tee setup.log
|
||||
./utils/setup.php --osm-file <data file> --all 2>&1 | tee setup.log
|
||||
```
|
||||
|
||||
The **project directory** is the one that you have set up at the beginning.
|
||||
See [creating the project directory](Import#creating-the-project-directory).
|
||||
|
||||
### Notes on full planet imports
|
||||
|
||||
Even on a perfectly configured machine
|
||||
@@ -235,19 +192,29 @@ MB. Make sure you leave enough RAM for PostgreSQL and osm2pgsql as mentioned
|
||||
above. If the system starts swapping or you are getting out-of-memory errors,
|
||||
reduce the cache size or even consider using a flatnode file.
|
||||
|
||||
|
||||
### Testing the installation
|
||||
### Verify the import
|
||||
|
||||
Run this script to verify all required tables and indices got created successfully.
|
||||
|
||||
```sh
|
||||
nominatim admin --check-database
|
||||
./utils/check_import_finished.php
|
||||
```
|
||||
|
||||
### Setting up the website
|
||||
|
||||
Run the following command to set up the configuration file for the API frontend
|
||||
`settings/settings-frontend.php`. These settings are used in website/*.php files.
|
||||
|
||||
```sh
|
||||
./utils/setup.php --setup-website
|
||||
```
|
||||
!!! Note
|
||||
This step is not necessary if you use `--all` option while setting up the DB.
|
||||
|
||||
Now you can try out your installation by running:
|
||||
|
||||
```sh
|
||||
nominatim serve
|
||||
make serve
|
||||
```
|
||||
|
||||
This runs a small test server normally used for development. You can use it
|
||||
@@ -255,9 +222,6 @@ 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`.
|
||||
|
||||
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`.
|
||||
|
||||
To run Nominatim via webservers like Apache or nginx, please read the
|
||||
[Deployment chapter](Deployment.md).
|
||||
|
||||
@@ -268,7 +232,7 @@ planner to make the right decisions. Recomputing them can improve the performanc
|
||||
of forward geocoding in particular under high load. To recompute word counts run:
|
||||
|
||||
```sh
|
||||
nominatim refresh --word-counts
|
||||
./utils/update.php --recompute-word-counts
|
||||
```
|
||||
|
||||
This will take a couple of hours for a full planet installation. You can
|
||||
@@ -278,14 +242,44 @@ running this function.
|
||||
|
||||
If you want to be able to search for places by their type through
|
||||
[special key phrases](https://wiki.openstreetmap.org/wiki/Nominatim/Special_Phrases)
|
||||
you also need to import these key phrases like this:
|
||||
you also need to enable these key phrases like this:
|
||||
|
||||
```sh
|
||||
nominatim special-phrases --import-from-wiki
|
||||
```
|
||||
./utils/specialphrases.php --wiki-import > specialphrases.sql
|
||||
psql -d nominatim -f specialphrases.sql
|
||||
|
||||
Note that this command downloads the phrases from the wiki link above. You
|
||||
need internet access for the step.
|
||||
|
||||
You can also import special phrases from a csv file, for more
|
||||
information please read the [Customization chapter](Customization.md).
|
||||
|
||||
## Installing Tiger housenumber data for the US
|
||||
|
||||
Nominatim is able to use the official [TIGER](https://www.census.gov/geographies/mapping-files/time-series/geo/tiger-line-file.html)
|
||||
address set to complement the OSM house number data in the US. You can add
|
||||
TIGER data to your own Nominatim instance by following these steps. The
|
||||
entire US adds about 10GB to your database.
|
||||
|
||||
1. Get preprocessed TIGER 2019 data and unpack it into the
|
||||
data directory in your Nominatim sources:
|
||||
|
||||
cd Nominatim/data
|
||||
wget https://nominatim.org/data/tiger2019-nominatim-preprocessed.tar.gz
|
||||
tar xf tiger2019-nominatim-preprocessed.tar.gz
|
||||
|
||||
2. Import the data into your Nominatim database:
|
||||
|
||||
./utils/setup.php --import-tiger-data
|
||||
|
||||
3. Enable use of the Tiger data in your `settings/local.php` by adding:
|
||||
|
||||
@define('CONST_Use_US_Tiger_Data', true);
|
||||
|
||||
4. Apply the new settings:
|
||||
|
||||
```sh
|
||||
./utils/setup.php --create-functions --enable-diff-updates --create-partition-functions
|
||||
```
|
||||
|
||||
|
||||
See the [developer's guide](../develop/data-sources.md#us-census-tiger) for more
|
||||
information on how the data got preprocessed.
|
||||
|
||||
|
||||
@@ -17,7 +17,6 @@ and can't offer support.
|
||||
|
||||
* [Docker](https://github.com/mediagis/nominatim-docker)
|
||||
* [Docker on Kubernetes](https://github.com/peter-evans/nominatim-k8s)
|
||||
* [Kubernetes with Helm](https://github.com/robjuz/helm-charts/blob/master/charts/nominatim/README.md)
|
||||
* [Ansible](https://github.com/synthesio/infra-ansible-nominatim)
|
||||
|
||||
## Prerequisites
|
||||
@@ -31,31 +30,23 @@ For compiling:
|
||||
* [proj](https://proj.org/)
|
||||
* [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
|
||||
* PostgreSQL client libraries
|
||||
* a recent C++ compiler (gcc 5+ or Clang 3.8+)
|
||||
|
||||
For running Nominatim:
|
||||
|
||||
* [PostgreSQL](https://www.postgresql.org) (9.5+ will work, 11+ strongly recommended)
|
||||
* [PostgreSQL](https://www.postgresql.org) (9.3+)
|
||||
* [PostGIS](https://postgis.net) (2.2+)
|
||||
* [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)
|
||||
* [Python 3](https://www.python.org/)
|
||||
* [Psycopg2](https://www.psycopg.org)
|
||||
* [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/)
|
||||
* [pyosmium](https://osmcode.org/pyosmium/) (with Python 3)
|
||||
|
||||
For dependencies for running tests and building documentation, see
|
||||
the [Development section](../develop/Development-Environment.md).
|
||||
@@ -151,16 +142,6 @@ build at the same level as the Nominatim source directory run:
|
||||
```
|
||||
cmake ../Nominatim
|
||||
make
|
||||
sudo make install
|
||||
```
|
||||
|
||||
Nominatim installs itself into `/usr/local` per default. To choose a different
|
||||
installation directory add `-DCMAKE_INSTALL_PREFIX=<install root>` to the
|
||||
cmake command. Make sure that the `bin` directory is available in your path
|
||||
in that case, e.g.
|
||||
|
||||
```
|
||||
export PATH=<install root>/bin:$PATH
|
||||
```
|
||||
|
||||
Now continue with [importing the database](Import.md).
|
||||
|
||||
@@ -1,66 +1,10 @@
|
||||
# Database Migrations
|
||||
|
||||
Since version 3.7.0 Nominatim offers automatic migrations. Please follow
|
||||
the following steps:
|
||||
This page describes database migrations necessary to update existing databases
|
||||
to newer versions of Nominatim.
|
||||
|
||||
* 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
|
||||
|
||||
Below you find additional migrations and hints about other structural and
|
||||
breaking changes. **Please read them before running the migration.**
|
||||
|
||||
!!! note
|
||||
If you are migrating from a version <3.6, then you still have to follow
|
||||
the manual migration steps up to 3.6.
|
||||
|
||||
## 3.6.0 -> 3.7.0
|
||||
|
||||
### New format and name of configuration file
|
||||
|
||||
The configuration for an import is now saved in a `.env` file in the project
|
||||
directory. This file follows the dotenv format. For more information, see
|
||||
the [installation chapter](Import.md#configuration-setup-in-env).
|
||||
|
||||
To migrate to the new system, create a new project directory, add the `.env`
|
||||
file and port your custom configuration from `settings/local.php`. Most
|
||||
settings are named similar and only have received a `NOMINATIM_` prefix.
|
||||
Use the default settings in `settings/env.defaults` as a reference.
|
||||
|
||||
### New location for data files
|
||||
|
||||
External data files for Wikipedia importance, postcodes etc. are no longer
|
||||
expected to reside in the source tree by default. Instead they will be searched
|
||||
in the project directory. If you have an automated setup script you must
|
||||
either adapt the download location or explicitly set the location of the
|
||||
files to the old place in your `.env`.
|
||||
|
||||
### Introducing `nominatim` command line tool
|
||||
|
||||
The various php utilities have been replaced with a single `nominatim`
|
||||
command line tool. Make sure to adapt any scripts. There is no direct 1:1
|
||||
matching between the old utilities and the commands of nominatim CLI. The
|
||||
following list gives you a list of nominatim sub-commands that contain
|
||||
functionality of each script:
|
||||
|
||||
* ./utils/setup.php: `import`, `freeze`, `refresh`
|
||||
* ./utils/update.php: `replication`, `add-data`, `index`, `refresh`
|
||||
* ./utils/specialphrases.php: `special-phrases`
|
||||
* ./utils/check_import_finished.php: `admin`
|
||||
* ./utils/warm.php: `admin`
|
||||
* ./utils/export.php: `export`
|
||||
|
||||
Try `nominatim <command> --help` for more information about each subcommand.
|
||||
|
||||
`./utils/query.php` no longer exists in its old form. `nominatim search`
|
||||
provides a replacement but returns different output.
|
||||
|
||||
### Switch to normalized house numbers
|
||||
|
||||
The housenumber column in the placex table uses now normalized version.
|
||||
The automatic migration step will convert the column but this may take a
|
||||
very long time. It is advisable to take the machine offline while doing that.
|
||||
SQL statements should be executed from the PostgreSQL commandline. Execute
|
||||
`psql nominatim` to enter command line mode.
|
||||
|
||||
## 3.5.0 -> 3.6.0
|
||||
|
||||
@@ -124,14 +68,6 @@ configuration file, run the following command after updating:
|
||||
./utils/setup.php --setup-website
|
||||
```
|
||||
|
||||
### Update SQL code
|
||||
|
||||
To update the SQL code to the leatest version run:
|
||||
|
||||
```
|
||||
./utils/setup.php --create-functions --enable-diff-updates --create-partition-functions
|
||||
```
|
||||
|
||||
## 3.4.0 -> 3.5.0
|
||||
|
||||
### New Wikipedia/Wikidata importance tables
|
||||
|
||||
@@ -10,11 +10,12 @@ installation. For more details, please also have a look at the
|
||||
|
||||
## Installing nominatim-ui
|
||||
|
||||
We provide regular releases of nominatim-ui that contain the packaged website.
|
||||
They do not need any special installation. Just download, configure
|
||||
and run it. Grab the latest release from
|
||||
[nominatim-ui's Github release page](https://github.com/osm-search/nominatim-ui/releases)
|
||||
and unpack it. You can use `nominatim-ui-x.x.x.tar.gz` or `nominatim-ui-x.x.x.zip`.
|
||||
nominatim-ui does not need any special installation, just download, configure
|
||||
and run it.
|
||||
|
||||
Clone the source from github:
|
||||
|
||||
git clone https://github.com/osm-search/nominatim-ui
|
||||
|
||||
Copy the example configuration into the right place:
|
||||
|
||||
|
||||
@@ -1,205 +0,0 @@
|
||||
# Tokenizers
|
||||
|
||||
The tokenizer module in Nominatim is responsible for analysing the names given
|
||||
to OSM objects and the terms of an incoming query in order to make sure, they
|
||||
can be matched appropriately.
|
||||
|
||||
Nominatim offers different tokenizer modules, which behave differently and have
|
||||
different configuration options. This sections describes the tokenizers and how
|
||||
they can be configured.
|
||||
|
||||
!!! important
|
||||
The use of a tokenizer is tied to a database installation. You need to choose
|
||||
and configure the tokenizer before starting the initial import. Once the import
|
||||
is done, you cannot switch to another tokenizer anymore. Reconfiguring the
|
||||
chosen tokenizer is very limited as well. See the comments in each tokenizer
|
||||
section.
|
||||
|
||||
## Legacy tokenizer
|
||||
|
||||
The legacy tokenizer implements the analysis algorithms of older Nominatim
|
||||
versions. It uses a special Postgresql module to normalize names and queries.
|
||||
This tokenizer is currently the default.
|
||||
|
||||
To enable the tokenizer add the following line to your project configuration:
|
||||
|
||||
```
|
||||
NOMINATIM_TOKENIZER=legacy
|
||||
```
|
||||
|
||||
The Postgresql module for the tokenizer is available in the `module` directory
|
||||
and also installed with the remainder of the software under
|
||||
`lib/nominatim/module/nominatim.so`. You can specify a custom location for
|
||||
the module with
|
||||
|
||||
```
|
||||
NOMINATIM_DATABASE_MODULE_PATH=<path to directory where nominatim.so resides>
|
||||
```
|
||||
|
||||
This is in particular useful when the database runs on a different server.
|
||||
See [Advanced installations](Advanced-Installations.md#importing-nominatim-to-an-external-postgresql-database) for details.
|
||||
|
||||
There are no other configuration options for the legacy tokenizer. All
|
||||
normalization functions are hard-coded.
|
||||
|
||||
## ICU tokenizer
|
||||
|
||||
!!! danger
|
||||
This tokenizer is currently in active development and still subject
|
||||
to backwards-incompatible changes.
|
||||
|
||||
The ICU tokenizer uses the [ICU library](http://site.icu-project.org/) to
|
||||
normalize names and queries. It also offers configurable decomposition and
|
||||
abbreviation handling.
|
||||
|
||||
### How it works
|
||||
|
||||
On import the tokenizer processes names in the following four stages:
|
||||
|
||||
1. The **Normalization** part removes all non-relevant information from the
|
||||
input.
|
||||
2. Incoming names are now converted to **full names**. This process is currently
|
||||
hard coded and mostly serves to handle name tags from OSM that contain
|
||||
multiple names (e.g. [Biel/Bienne](https://www.openstreetmap.org/node/240097197)).
|
||||
3. Next the tokenizer creates **variants** from the full names. These variants
|
||||
cover decomposition and abbreviation handling. Variants are saved to the
|
||||
database, so that it is not necessary to create the variants for a search
|
||||
query.
|
||||
4. The final **Tokenization** step converts the names to a simple ASCII form,
|
||||
potentially removing further spelling variants for better matching.
|
||||
|
||||
At query time only stage 1) and 4) are used. The query is normalized and
|
||||
tokenized and the resulting string used for searching in the database.
|
||||
|
||||
### Configuration
|
||||
|
||||
The ICU tokenizer is configured using a YAML file which can be configured using
|
||||
`NOMINATIM_TOKENIZER_CONFIG`. The configuration is read on import and then
|
||||
saved as part of the internal database status. Later changes to the variable
|
||||
have no effect.
|
||||
|
||||
Here is an example configuration file:
|
||||
|
||||
``` yaml
|
||||
normalization:
|
||||
- ":: lower ()"
|
||||
- "ß > 'ss'" # German szet is unimbigiously equal to double ss
|
||||
transliteration:
|
||||
- !include /etc/nominatim/icu-rules/extended-unicode-to-asccii.yaml
|
||||
- ":: Ascii ()"
|
||||
variants:
|
||||
- language: de
|
||||
words:
|
||||
- ~haus => haus
|
||||
- ~strasse -> str
|
||||
- language: en
|
||||
words:
|
||||
- road -> rd
|
||||
- bridge -> bdge,br,brdg,bri,brg
|
||||
```
|
||||
|
||||
The configuration file contains three sections:
|
||||
`normalization`, `transliteration`, `variants`.
|
||||
|
||||
The normalization and transliteration sections each must contain a list of
|
||||
[ICU transformation rules](https://unicode-org.github.io/icu/userguide/transforms/general/rules.html).
|
||||
The rules are applied in the order in which they appear in the file.
|
||||
You can also include additional rules from external yaml file using the
|
||||
`!include` tag. The included file must contain a valid YAML list of ICU rules
|
||||
and may again include other files.
|
||||
|
||||
!!! warning
|
||||
The ICU rule syntax contains special characters that conflict with the
|
||||
YAML syntax. You should therefore always enclose the ICU rules in
|
||||
double-quotes.
|
||||
|
||||
The variants section defines lists of replacements which create alternative
|
||||
spellings of a name. To create the variants, a name is scanned from left to
|
||||
right and the longest matching replacement is applied until the end of the
|
||||
string is reached.
|
||||
|
||||
The variants section must contain a list of replacement groups. Each group
|
||||
defines a set of properties that describes where the replacements are
|
||||
applicable. In addition, the word section defines the list of replacements
|
||||
to be made. The basic replacement description is of the form:
|
||||
|
||||
```
|
||||
<source>[,<source>[...]] => <target>[,<target>[...]]
|
||||
```
|
||||
|
||||
The left side contains one or more `source` terms to be replaced. The right side
|
||||
lists one or more replacements. Each source is replaced with each replacement
|
||||
term.
|
||||
|
||||
!!! tip
|
||||
The source and target terms are internally normalized using the
|
||||
normalization rules given in the configuration. This ensures that the
|
||||
strings match as expected. In fact, it is better to use unnormalized
|
||||
words in the configuration because then it is possible to change the
|
||||
rules for normalization later without having to adapt the variant rules.
|
||||
|
||||
#### Decomposition
|
||||
|
||||
In its standard form, only full words match against the source. There
|
||||
is a special notation to match the prefix and suffix of a word:
|
||||
|
||||
``` yaml
|
||||
- ~strasse => str # matches "strasse" as full word and in suffix position
|
||||
- hinter~ => hntr # matches "hinter" as full word and in prefix position
|
||||
```
|
||||
|
||||
There is no facility to match a string in the middle of the word. The suffix
|
||||
and prefix notation automatically trigger the decomposition mode: two variants
|
||||
are created for each replacement, one with the replacement attached to the word
|
||||
and one separate. So in above example, the tokenization of "hauptstrasse" will
|
||||
create the variants "hauptstr" and "haupt str". Similarly, the name "rote strasse"
|
||||
triggers the variants "rote str" and "rotestr". By having decomposition work
|
||||
both ways, it is sufficient to create the variants at index time. The variant
|
||||
rules are not applied at query time.
|
||||
|
||||
To avoid automatic decomposition, use the '|' notation:
|
||||
|
||||
``` yaml
|
||||
- ~strasse |=> str
|
||||
```
|
||||
|
||||
simply changes "hauptstrasse" to "hauptstr" and "rote strasse" to "rote str".
|
||||
|
||||
#### Initial and final terms
|
||||
|
||||
It is also possible to restrict replacements to the beginning and end of a
|
||||
name:
|
||||
|
||||
``` yaml
|
||||
- ^south => s # matches only at the beginning of the name
|
||||
- road$ => rd # matches only at the end of the name
|
||||
```
|
||||
|
||||
So the first example would trigger a replacement for "south 45th street" but
|
||||
not for "the south beach restaurant".
|
||||
|
||||
#### Replacements vs. variants
|
||||
|
||||
The replacement syntax `source => target` works as a pure replacement. It changes
|
||||
the name instead of creating a variant. To create an additional version, you'd
|
||||
have to write `source => source,target`. As this is a frequent case, there is
|
||||
a shortcut notation for it:
|
||||
|
||||
```
|
||||
<source>[,<source>[...]] -> <target>[,<target>[...]]
|
||||
```
|
||||
|
||||
The simple arrow causes an additional variant to be added. Note that
|
||||
decomposition has an effect here on the source as well. So a rule
|
||||
|
||||
``` yaml
|
||||
- "~strasse -> str"
|
||||
```
|
||||
|
||||
means that for a word like `hauptstrasse` four variants are created:
|
||||
`hauptstrasse`, `haupt strasse`, `hauptstr` and `haupt str`.
|
||||
|
||||
### Reconfiguration
|
||||
|
||||
Changing the configuration after the import is currently not possible, although
|
||||
this feature may be added at a later time.
|
||||
@@ -1,10 +1,8 @@
|
||||
# Updating the Database
|
||||
|
||||
There are many different ways to update your Nominatim database.
|
||||
The following section describes how to keep it up-to-date using
|
||||
an [online replication service for OpenStreetMap data](https://wiki.openstreetmap.org/wiki/Planet.osm/diffs)
|
||||
For a list of other methods to add or update data see the output of
|
||||
`nominatim add-data --help`.
|
||||
The following section describes how to keep it up-to-date with Pyosmium.
|
||||
For a list of other methods see the output of `./utils/update.php --help`.
|
||||
|
||||
!!! important
|
||||
If you have configured a flatnode file for the import, then you
|
||||
@@ -19,37 +17,50 @@ Run (as the same user who will later run the updates):
|
||||
pip3 install --user osmium
|
||||
```
|
||||
|
||||
Nominatim needs a tool called `pyosmium-get-changes` which comes with
|
||||
Pyosmium. You need to tell Nominatim where to find it. Add the
|
||||
following line to your `settings/local.php`:
|
||||
|
||||
@define('CONST_Pyosmium_Binary', '/home/user/.local/bin/pyosmium-get-changes');
|
||||
|
||||
The path above is fine if you used the `--user` parameter with pip.
|
||||
Replace `user` with your user name.
|
||||
|
||||
#### Setting up the update process
|
||||
|
||||
Next the update needs to be initialised. By default Nominatim is configured
|
||||
to update using the global minutely diffs.
|
||||
|
||||
If you want a different update source you will need to add some settings
|
||||
to `.env`. For example, to use the daily country extracts
|
||||
to `settings/local.php`. For example, to use the daily country extracts
|
||||
diffs for Ireland from Geofabrik add the following:
|
||||
|
||||
# base URL of the replication service
|
||||
NOMINATIM_REPLICATION_URL="https://download.geofabrik.de/europe/ireland-and-northern-ireland-updates"
|
||||
# How often upstream publishes diffs (in seconds)
|
||||
NOMINATIM_REPLICATION_UPDATE_INTERVAL=86400
|
||||
# How long to sleep if no update found yet (in seconds)
|
||||
NOMINATIM_REPLICATION_RECHECK_INTERVAL=900
|
||||
// base URL of the replication service
|
||||
@define('CONST_Replication_Url', 'https://download.geofabrik.de/europe/ireland-and-northern-ireland-updates');
|
||||
// How often upstream publishes diffs
|
||||
@define('CONST_Replication_Update_Interval', '86400');
|
||||
// How long to sleep if no update found yet
|
||||
@define('CONST_Replication_Recheck_Interval', '900');
|
||||
|
||||
To set up the update process now run the following command:
|
||||
|
||||
nominatim replication --init
|
||||
./utils/update.php --init-updates
|
||||
|
||||
It outputs the date where updates will start. Recheck that this date is
|
||||
what you expect.
|
||||
|
||||
The `replication --init` command needs to be rerun whenever the replication
|
||||
service is changed.
|
||||
The `--init-updates` command needs to be rerun whenever the replication service
|
||||
is changed.
|
||||
|
||||
#### Updating Nominatim
|
||||
|
||||
The following command will keep your database constantly up to date:
|
||||
|
||||
nominatim replication
|
||||
./utils/update.php --import-osmosis-all
|
||||
|
||||
(Note that even though the old name "import-osmosis-all" has been kept for
|
||||
compatibility reasons, Osmosis is not required to run this - it uses pyosmium
|
||||
behind the scenes.)
|
||||
|
||||
If you have imported multiple country extracts and want to keep them
|
||||
up-to-date, [Advanced installations section](Advanced-Installations.md) contains instructions
|
||||
|
||||
@@ -58,4 +58,4 @@ The [Overpass API](https://wiki.openstreetmap.org/wiki/Overpass_API) is more
|
||||
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.
|
||||
`/utils/export.php` PHP script as basis to return such lists.
|
||||
|
||||
@@ -162,7 +162,7 @@ This overrides the specified machine readable format. (Default: 0)
|
||||
"licence":"Data © OpenStreetMap contributors, ODbL 1.0. https:\/\/www.openstreetmap.org\/copyright",
|
||||
"osm_type":"way",
|
||||
"osm_id":"280940520",
|
||||
"lat":"-34.4391708",
|
||||
"lat":"-34.4391708",
|
||||
"lon":"-58.7064573",
|
||||
"place_rank":"26",
|
||||
"category":"highway",
|
||||
|
||||
@@ -35,16 +35,10 @@ will return HTTP code 200 and a structure
|
||||
{
|
||||
"status": 0,
|
||||
"message": "OK",
|
||||
"data_updated": "2020-05-04T14:47:00+00:00",
|
||||
"software_version": "3.6.0-0",
|
||||
"database_version": "3.6.0-0"
|
||||
"data_updated": "2020-05-04T14:47:00+00:00"
|
||||
}
|
||||
```
|
||||
|
||||
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.
|
||||
|
||||
|
||||
@@ -26,14 +26,12 @@ following packages should get you started:
|
||||
## Prerequisites for testing and documentation
|
||||
|
||||
The Nominatim test suite consists of behavioural tests (using behave) and
|
||||
unit tests (using PHPUnit for PHP code and pytest for Python code).
|
||||
It has the following additional requirements:
|
||||
unit tests (using PHPUnit). It has the following additional requirements:
|
||||
|
||||
* [behave test framework](https://behave.readthedocs.io) >= 1.2.6
|
||||
* [behave test framework](https://behave.readthedocs.io) >= 1.2.5
|
||||
* [nose](https://nose.readthedocs.io)
|
||||
* [phpunit](https://phpunit.de) >= 7.3
|
||||
* [PHP CodeSniffer](https://github.com/squizlabs/PHP_CodeSniffer)
|
||||
* [Pylint](https://pylint.org/) (2.6.0 is used for the CI)
|
||||
* [pytest](https://pytest.org)
|
||||
|
||||
The documentation is built with mkdocs:
|
||||
|
||||
@@ -49,9 +47,9 @@ To install all necessary packages run:
|
||||
|
||||
```sh
|
||||
sudo apt install php-cgi phpunit php-codesniffer \
|
||||
python3-pip python3-setuptools python3-dev pylint
|
||||
python3-pip python3-setuptools python3-dev
|
||||
|
||||
pip3 install --user behave mkdocs pytest
|
||||
pip3 install --user behave nose mkdocs
|
||||
```
|
||||
|
||||
The `mkdocs` executable will be located in `.local/bin`. You may have to add
|
||||
@@ -80,15 +78,58 @@ echo 'export PATH=~/.config/composer/vendor/bin:$PATH' > ~/.profile
|
||||
|
||||
## Executing Tests
|
||||
|
||||
All tests are located in the `/test` directory.
|
||||
All tests are located in the `\test` directory.
|
||||
|
||||
To run all tests just go to the build directory and run make:
|
||||
### Preparing the test database
|
||||
|
||||
Some of the behavioural test expect a test database to be present. You need at
|
||||
least 2GB RAM and 10GB disk space to create the database.
|
||||
|
||||
First create a separate directory for the test DB and fetch the test planet
|
||||
data and the Tiger data for South Dakota:
|
||||
|
||||
```
|
||||
mkdir testdb
|
||||
cd testdb
|
||||
wget https://www.nominatim.org/data/test/nominatim-api-testdata.pbf
|
||||
wget -O - https://nominatim.org/data/tiger2018-nominatim-preprocessed.tar.gz | tar xz --wildcards --no-anchored '46*'
|
||||
```
|
||||
|
||||
Configure and build Nominatim in the usual way:
|
||||
|
||||
```
|
||||
cmake $USERNAME/Nominatim
|
||||
make
|
||||
```
|
||||
|
||||
Copy the test settings:
|
||||
|
||||
```
|
||||
cp $USERNAME/Nominatim/test/testdb/local.php settings/
|
||||
```
|
||||
|
||||
Inspect the file to check that all settings are correct for your local setup.
|
||||
|
||||
Now you can import the test database:
|
||||
|
||||
```
|
||||
dropdb --if-exists test_api_nominatim
|
||||
./utils/setup.php --all --osm-file nominatim-api-testdb.pbf 2>&1 | tee import.log
|
||||
./utils/specialphrases.php --wiki-import | psql -d test_api_nominatim 2>&1 | tee -a import.log
|
||||
./utils/setup.php --import-tiger-data 2>&1 | tee -a import.log
|
||||
```
|
||||
|
||||
### Running the tests
|
||||
|
||||
To run all tests just go to the test directory and run make:
|
||||
|
||||
```sh
|
||||
cd build
|
||||
make test
|
||||
cd test
|
||||
make
|
||||
```
|
||||
|
||||
To skip tests that require the test database, run `make no-test-db` instead.
|
||||
|
||||
For more information about the structure of the tests and how to change and
|
||||
extend the test suite, see the [Testing chapter](Testing.md).
|
||||
|
||||
|
||||
@@ -29,7 +29,7 @@ once with `class` of `highway` and once with a `class` of `bridge`. Thus the
|
||||
## Configuring the Import
|
||||
|
||||
How tags are interpreted and assigned to the different `place` columns can be
|
||||
configured via the import style configuration file (`NOMINATIM_IMPORT_STYLE`). This
|
||||
configured via the import style configuration file (`CONST_Import_style`). 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.
|
||||
|
||||
|
||||
@@ -14,7 +14,7 @@ country's format, e.g. if Swiss postcodes are 4 digits.
|
||||
## Regular updating calculated postcodes
|
||||
|
||||
The script to rerun the calculation is
|
||||
`nominatim refresh --postcodes`
|
||||
`build/utils/update.php --calculate-postcodes`
|
||||
and runs once per night on nominatim.openstreetmap.org.
|
||||
|
||||
|
||||
|
||||
@@ -87,9 +87,9 @@ into the database. There are a few hard-coded rules for the assignment:
|
||||
* highway nodes
|
||||
* landuse that is not an area
|
||||
|
||||
Other than that, the ranks can be freely assigned via the JSON file according
|
||||
to their type and the country they are in. The name of the config file to be
|
||||
used can be changed with the setting `NOMINATIM_ADDRESS_LEVEL_CONFIG`.
|
||||
Other than that, the ranks can be freely assigned via the JSON file
|
||||
defined with `CONST_Address_Level_Config` according to their type and
|
||||
the country they are in.
|
||||
|
||||
The address level configuration must consist of an array of configuration
|
||||
entries, each containing a tag definition and an optional country array:
|
||||
|
||||
@@ -21,15 +21,14 @@ This test directory is sturctured as follows:
|
||||
| +- api Tests for API endpoints (search, reverse, etc.)
|
||||
|
|
||||
+- php PHP unit tests
|
||||
+- python Python unit tests
|
||||
+- scenes Geometry test data
|
||||
+- testdb Base data for generating API test database
|
||||
```
|
||||
|
||||
## PHP Unit Tests (`test/php`)
|
||||
|
||||
Unit tests for PHP code can be found in the `php/` directory. They test selected
|
||||
PHP functions. Very low coverage.
|
||||
Unit tests can be found in the php/ directory. They test selected php functions.
|
||||
Very low coverage.
|
||||
|
||||
To execute the test suite run
|
||||
|
||||
@@ -37,26 +36,11 @@ To execute the test suite run
|
||||
UNIT_TEST_DSN='pgsql:dbname=nominatim_unit_tests' phpunit ../
|
||||
|
||||
It will read phpunit.xml which points to the library, test path, bootstrap
|
||||
strip and sets other parameters.
|
||||
strip and set other parameters.
|
||||
|
||||
It will use (and destroy) a local database 'nominatim_unit_tests'. You can set
|
||||
a different connection string with e.g. UNIT_TEST_DSN='pgsql:dbname=foo_unit_tests'.
|
||||
|
||||
## Python Unit Tests (`test/python`)
|
||||
|
||||
Unit tests for Python code can be found in the `python/` directory. The goal is
|
||||
to have complete coverage of the Python library in `nominatim`.
|
||||
|
||||
To execute the tests run
|
||||
|
||||
py.test-3 test/python
|
||||
|
||||
or
|
||||
|
||||
pytest test/python
|
||||
|
||||
The name of the pytest binary depends on your installation.
|
||||
|
||||
## BDD Functional Tests (`test/bdd`)
|
||||
|
||||
Functional tests are written as BDD instructions. For more information on
|
||||
@@ -83,17 +67,17 @@ The tests can be configured with a set of environment variables (`behave -D key=
|
||||
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)
|
||||
* `DB_HOST` - (optional) hostname of database host
|
||||
* `DB_PORT` - (optional) port of database on host
|
||||
* `DB_USER` - (optional) username of database login
|
||||
* `DB_PASS` - (optional) password for database login
|
||||
* `SERVER_MODULE_PATH` - (optional) path on the Postgres server to Nominatim
|
||||
module shared library file
|
||||
* `REMOVE_TEMPLATE` - if true, the template and API database will not be reused
|
||||
during the next run. Reusing the base templates speeds
|
||||
up tests considerably but might lead to outdated errors
|
||||
for some changes in the database layout.
|
||||
* `TEST_SETTINGS_TEMPLATE` - file to write temporary Nominatim settings to
|
||||
* `REMOVE_TEMPLATE` - if true, the template database will not be reused during
|
||||
the next run. Reusing the base templates speeds up tests
|
||||
considerably but might lead to outdated errors for some
|
||||
changes in the database layout.
|
||||
* `KEEP_TEST_DB` - if true, the test database will not be dropped after a test
|
||||
is finished. Should only be used if one single scenario is
|
||||
run, otherwise the result is undefined.
|
||||
@@ -105,20 +89,23 @@ feature of behave which comes in handy when writing new tests.
|
||||
### API Tests (`test/bdd/api`)
|
||||
|
||||
These tests are meant to test the different API endpoints and their parameters.
|
||||
They require to import several datasets into a test database. This is normally
|
||||
done automatically during setup of the test. The API test database is then
|
||||
kept around and reused in subsequent runs of behave. Use `behave -DREMOVE_TEMPLATE`
|
||||
to force a reimport of the database.
|
||||
They require to import several datasets into a test database.
|
||||
See the [Development Setup chapter](Development-Environment.md#preparing-the-test-database)
|
||||
for instructions on how to set up this database.
|
||||
|
||||
The official test dataset is saved in the file `test/testdb/apidb-test-data.pbf`
|
||||
and compromises the following data:
|
||||
The official test dataset was derived from the 180924 planet (note: such
|
||||
file no longer exists at https://planet.openstreetmap.org/planet/2018/).
|
||||
Newer planets are likely to work as well but you may see isolated test
|
||||
failures where the data has changed.
|
||||
|
||||
* Geofabrik extract of Liechtenstein
|
||||
* extract of Autauga country, Alabama, US (for tests against Tiger data)
|
||||
* additional data from `test/testdb/additional_api_test.data.osm`
|
||||
The official test dataset can always be downloaded from
|
||||
[nominatim.org](https://www.nominatim.org/data/test/nominatim-api-testdata.pbf)
|
||||
To recreate the input data for the test database run:
|
||||
|
||||
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.
|
||||
```
|
||||
wget https://ftp5.gwdg.de/pub/misc/openstreetmap/planet.openstreetmap.org/pbf/planet-180924.osm.pbf
|
||||
osmconvert planet-180924.osm.pbf -B=test/testdb/testdb.polys -o=testdb.pbf
|
||||
```
|
||||
|
||||
#### Code Coverage
|
||||
|
||||
@@ -153,7 +140,3 @@ 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.
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
site_name: Nominatim Documentation
|
||||
site_name: Nominatim 3.6.0
|
||||
theme: readthedocs
|
||||
docs_dir: ${CMAKE_CURRENT_BINARY_DIR}
|
||||
site_url: https://nominatim.org
|
||||
@@ -19,8 +19,6 @@ pages:
|
||||
- 'Import' : 'admin/Import.md'
|
||||
- 'Update' : 'admin/Update.md'
|
||||
- 'Deploy' : 'admin/Deployment.md'
|
||||
- 'Customize Imports' : 'admin/Customization.md'
|
||||
- 'Tokenizers' : 'admin/Tokenizers.md'
|
||||
- 'Nominatim UI' : 'admin/Setup-Nominatim-UI.md'
|
||||
- 'Advanced Installations' : 'admin/Advanced-Installations.md'
|
||||
- 'Migration from older Versions' : 'admin/Migration.md'
|
||||
|
||||
@@ -1,87 +0,0 @@
|
||||
<?php
|
||||
|
||||
namespace Nominatim;
|
||||
|
||||
/**
|
||||
* Description of the position of a token within a query.
|
||||
*/
|
||||
class SearchPosition
|
||||
{
|
||||
private $sPhraseType;
|
||||
|
||||
private $iPhrase;
|
||||
private $iNumPhrases;
|
||||
|
||||
private $iToken;
|
||||
private $iNumTokens;
|
||||
|
||||
|
||||
public function __construct($sPhraseType, $iPhrase, $iNumPhrases)
|
||||
{
|
||||
$this->sPhraseType = $sPhraseType;
|
||||
$this->iPhrase = $iPhrase;
|
||||
$this->iNumPhrases = $iNumPhrases;
|
||||
}
|
||||
|
||||
public function setTokenPosition($iToken, $iNumTokens)
|
||||
{
|
||||
$this->iToken = $iToken;
|
||||
$this->iNumTokens = $iNumTokens;
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if the phrase can be of the given type.
|
||||
*
|
||||
* @param string $sType Type of phrse requested.
|
||||
*
|
||||
* @return True if the phrase is untyped or of the given type.
|
||||
*/
|
||||
public function maybePhrase($sType)
|
||||
{
|
||||
return $this->sPhraseType == '' || $this->sPhraseType == $sType;
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if the phrase is exactly of the given type.
|
||||
*
|
||||
* @param string $sType Type of phrse requested.
|
||||
*
|
||||
* @return True if the phrase of the given type.
|
||||
*/
|
||||
public function isPhrase($sType)
|
||||
{
|
||||
return $this->sPhraseType == $sType;
|
||||
}
|
||||
|
||||
/**
|
||||
* Return true if the token is the very first in the query.
|
||||
*/
|
||||
public function isFirstToken()
|
||||
{
|
||||
return $this->iPhrase == 0 && $this->iToken == 0;
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if the token is the final one in the query.
|
||||
*/
|
||||
public function isLastToken()
|
||||
{
|
||||
return $this->iToken + 1 == $this->iNumTokens && $this->iPhrase + 1 == $this->iNumPhrases;
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if the current token is part of the first phrase in the query.
|
||||
*/
|
||||
public function isFirstPhrase()
|
||||
{
|
||||
return $this->iPhrase == 0;
|
||||
}
|
||||
|
||||
/**
|
||||
* Get the phrase position in the query.
|
||||
*/
|
||||
public function getPhrase()
|
||||
{
|
||||
return $this->iPhrase;
|
||||
}
|
||||
}
|
||||
@@ -1,51 +0,0 @@
|
||||
<?php
|
||||
|
||||
namespace Nominatim;
|
||||
|
||||
require_once(CONST_TokenizerDir.'/tokenizer.php');
|
||||
|
||||
use Exception;
|
||||
|
||||
class Status
|
||||
{
|
||||
protected $oDB;
|
||||
|
||||
public function __construct(&$oDB)
|
||||
{
|
||||
$this->oDB =& $oDB;
|
||||
}
|
||||
|
||||
public function status()
|
||||
{
|
||||
if (!$this->oDB) {
|
||||
throw new Exception('No database', 700);
|
||||
}
|
||||
|
||||
try {
|
||||
$this->oDB->connect();
|
||||
} catch (\Nominatim\DatabaseError $e) {
|
||||
throw new Exception('Database connection failed', 700);
|
||||
}
|
||||
|
||||
$oTokenizer = new \Nominatim\Tokenizer($this->oDB);
|
||||
$oTokenizer->checkStatus();
|
||||
}
|
||||
|
||||
public function dataDate()
|
||||
{
|
||||
$sSQL = 'SELECT EXTRACT(EPOCH FROM lastimportdate) FROM import_status LIMIT 1';
|
||||
$iDataDateEpoch = $this->oDB->getOne($sSQL);
|
||||
|
||||
if ($iDataDateEpoch === false) {
|
||||
throw new Exception('Import date is not available', 705);
|
||||
}
|
||||
|
||||
return $iDataDateEpoch;
|
||||
}
|
||||
|
||||
public function databaseVersion()
|
||||
{
|
||||
$sSQL = 'SELECT value FROM nominatim_properties WHERE property = \'database_version\'';
|
||||
return $this->oDB->getOne($sSQL);
|
||||
}
|
||||
}
|
||||
@@ -1,72 +0,0 @@
|
||||
<?php
|
||||
|
||||
namespace Nominatim\Token;
|
||||
|
||||
/**
|
||||
* A country token.
|
||||
*/
|
||||
class Country
|
||||
{
|
||||
/// Database word id, if available.
|
||||
private $iId;
|
||||
/// Two-letter country code (lower-cased).
|
||||
private $sCountryCode;
|
||||
|
||||
public function __construct($iId, $sCountryCode)
|
||||
{
|
||||
$this->iId = $iId;
|
||||
$this->sCountryCode = $sCountryCode;
|
||||
}
|
||||
|
||||
public function getId()
|
||||
{
|
||||
return $this->iId;
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if the token can be added to the given search.
|
||||
* Derive new searches by adding this token to an existing search.
|
||||
*
|
||||
* @param object $oSearch Partial search description derived so far.
|
||||
* @param object $oPosition Description of the token position within
|
||||
the query.
|
||||
*
|
||||
* @return True if the token is compatible with the search configuration
|
||||
* given the position.
|
||||
*/
|
||||
public function isExtendable($oSearch, $oPosition)
|
||||
{
|
||||
return !$oSearch->hasCountry() && $oPosition->maybePhrase('country');
|
||||
}
|
||||
|
||||
/**
|
||||
* Derive new searches by adding this token to an existing search.
|
||||
*
|
||||
* @param object $oSearch Partial search description derived so far.
|
||||
* @param object $oPosition Description of the token position within
|
||||
the query.
|
||||
*
|
||||
* @return SearchDescription[] List of derived search descriptions.
|
||||
*/
|
||||
public function extendSearch($oSearch, $oPosition)
|
||||
{
|
||||
$oNewSearch = $oSearch->clone($oPosition->isLastToken() ? 1 : 6);
|
||||
$oNewSearch->setCountry($this->sCountryCode);
|
||||
|
||||
return array($oNewSearch);
|
||||
}
|
||||
|
||||
public function debugInfo()
|
||||
{
|
||||
return array(
|
||||
'ID' => $this->iId,
|
||||
'Type' => 'country',
|
||||
'Info' => $this->sCountryCode
|
||||
);
|
||||
}
|
||||
|
||||
public function debugCode()
|
||||
{
|
||||
return 'C';
|
||||
}
|
||||
}
|
||||
@@ -1,108 +0,0 @@
|
||||
<?php
|
||||
|
||||
namespace Nominatim\Token;
|
||||
|
||||
/**
|
||||
* A house number token.
|
||||
*/
|
||||
class HouseNumber
|
||||
{
|
||||
/// Database word id, if available.
|
||||
private $iId;
|
||||
/// Normalized house number.
|
||||
private $sToken;
|
||||
|
||||
public function __construct($iId, $sToken)
|
||||
{
|
||||
$this->iId = $iId;
|
||||
$this->sToken = $sToken;
|
||||
}
|
||||
|
||||
public function getId()
|
||||
{
|
||||
return $this->iId;
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if the token can be added to the given search.
|
||||
* Derive new searches by adding this token to an existing search.
|
||||
*
|
||||
* @param object $oSearch Partial search description derived so far.
|
||||
* @param object $oPosition Description of the token position within
|
||||
the query.
|
||||
*
|
||||
* @return True if the token is compatible with the search configuration
|
||||
* given the position.
|
||||
*/
|
||||
public function isExtendable($oSearch, $oPosition)
|
||||
{
|
||||
return !$oSearch->hasHousenumber()
|
||||
&& !$oSearch->hasOperator(\Nominatim\Operator::POSTCODE)
|
||||
&& $oPosition->maybePhrase('street');
|
||||
}
|
||||
|
||||
/**
|
||||
* Derive new searches by adding this token to an existing search.
|
||||
*
|
||||
* @param object $oSearch Partial search description derived so far.
|
||||
* @param object $oPosition Description of the token position within
|
||||
the query.
|
||||
*
|
||||
* @return SearchDescription[] List of derived search descriptions.
|
||||
*/
|
||||
public function extendSearch($oSearch, $oPosition)
|
||||
{
|
||||
$aNewSearches = array();
|
||||
|
||||
// sanity check: if the housenumber is not mainly made
|
||||
// up of numbers, add a penalty
|
||||
$iSearchCost = 1;
|
||||
if (preg_match('/\\d/', $this->sToken) === 0
|
||||
|| preg_match_all('/[^0-9]/', $this->sToken, $aMatches) > 2) {
|
||||
$iSearchCost++;
|
||||
}
|
||||
if (!$oSearch->hasOperator(\Nominatim\Operator::NONE)) {
|
||||
$iSearchCost++;
|
||||
}
|
||||
if (empty($this->iId)) {
|
||||
$iSearchCost++;
|
||||
}
|
||||
// also must not appear in the middle of the address
|
||||
if ($oSearch->hasAddress() || $oSearch->hasPostcode()) {
|
||||
$iSearchCost++;
|
||||
}
|
||||
|
||||
$oNewSearch = $oSearch->clone($iSearchCost);
|
||||
$oNewSearch->setHousenumber($this->sToken);
|
||||
$aNewSearches[] = $oNewSearch;
|
||||
|
||||
// Housenumbers may appear in the name when the place has its own
|
||||
// address terms.
|
||||
if ($this->iId !== null
|
||||
&& ($oSearch->getNamePhrase() >= 0 || !$oSearch->hasName())
|
||||
&& !$oSearch->hasAddress()
|
||||
) {
|
||||
$oNewSearch = $oSearch->clone($iSearchCost);
|
||||
$oNewSearch->setHousenumberAsName($this->iId);
|
||||
|
||||
$aNewSearches[] = $oNewSearch;
|
||||
}
|
||||
|
||||
return $aNewSearches;
|
||||
}
|
||||
|
||||
|
||||
public function debugInfo()
|
||||
{
|
||||
return array(
|
||||
'ID' => $this->iId,
|
||||
'Type' => 'house number',
|
||||
'Info' => array('nr' => $this->sToken)
|
||||
);
|
||||
}
|
||||
|
||||
public function debugCode()
|
||||
{
|
||||
return 'H';
|
||||
}
|
||||
}
|
||||
@@ -1,126 +0,0 @@
|
||||
<?php
|
||||
|
||||
namespace Nominatim;
|
||||
|
||||
require_once(CONST_LibDir.'/TokenCountry.php');
|
||||
require_once(CONST_LibDir.'/TokenHousenumber.php');
|
||||
require_once(CONST_LibDir.'/TokenPostcode.php');
|
||||
require_once(CONST_LibDir.'/TokenSpecialTerm.php');
|
||||
require_once(CONST_LibDir.'/TokenWord.php');
|
||||
require_once(CONST_LibDir.'/TokenPartial.php');
|
||||
require_once(CONST_LibDir.'/SpecialSearchOperator.php');
|
||||
|
||||
/**
|
||||
* Saves information about the tokens that appear in a search query.
|
||||
*
|
||||
* Tokens are sorted by their normalized form, the token word. There are different
|
||||
* kinds of tokens, represented by different Token* classes. Note that
|
||||
* tokens do not have a common base class. All tokens need to have a field
|
||||
* with the word id that points to an entry in the `word` database table
|
||||
* but otherwise the information saved about a token can be very different.
|
||||
*/
|
||||
class TokenList
|
||||
{
|
||||
// List of list of tokens indexed by their word_token.
|
||||
private $aTokens = array();
|
||||
|
||||
|
||||
/**
|
||||
* Return total number of tokens.
|
||||
*
|
||||
* @return Integer
|
||||
*/
|
||||
public function count()
|
||||
{
|
||||
return count($this->aTokens);
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if there are tokens for the given token word.
|
||||
*
|
||||
* @param string $sWord Token word to look for.
|
||||
*
|
||||
* @return bool True if there is one or more token for the token word.
|
||||
*/
|
||||
public function contains($sWord)
|
||||
{
|
||||
return isset($this->aTokens[$sWord]);
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if there are partial or full tokens for the given word.
|
||||
*
|
||||
* @param string $sWord Token word to look for.
|
||||
*
|
||||
* @return bool True if there is one or more token for the token word.
|
||||
*/
|
||||
public function containsAny($sWord)
|
||||
{
|
||||
return isset($this->aTokens[$sWord]);
|
||||
}
|
||||
|
||||
/**
|
||||
* Get the list of tokens for the given token word.
|
||||
*
|
||||
* @param string $sWord Token word to look for.
|
||||
*
|
||||
* @return object[] Array of tokens for the given token word or an
|
||||
* empty array if no tokens could be found.
|
||||
*/
|
||||
public function get($sWord)
|
||||
{
|
||||
return isset($this->aTokens[$sWord]) ? $this->aTokens[$sWord] : array();
|
||||
}
|
||||
|
||||
public function getFullWordIDs()
|
||||
{
|
||||
$ids = array();
|
||||
|
||||
foreach ($this->aTokens as $aTokenList) {
|
||||
foreach ($aTokenList as $oToken) {
|
||||
if (is_a($oToken, '\Nominatim\Token\Word')) {
|
||||
$ids[$oToken->getId()] = $oToken->getId();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return $ids;
|
||||
}
|
||||
|
||||
/**
|
||||
* Add a new token for the given word.
|
||||
*
|
||||
* @param string $sWord Word the token describes.
|
||||
* @param object $oToken Token object to add.
|
||||
*
|
||||
* @return void
|
||||
*/
|
||||
public function addToken($sWord, $oToken)
|
||||
{
|
||||
if (isset($this->aTokens[$sWord])) {
|
||||
$this->aTokens[$sWord][] = $oToken;
|
||||
} else {
|
||||
$this->aTokens[$sWord] = array($oToken);
|
||||
}
|
||||
}
|
||||
|
||||
public function debugTokenByWordIdList()
|
||||
{
|
||||
$aWordsIDs = array();
|
||||
foreach ($this->aTokens as $sToken => $aWords) {
|
||||
foreach ($aWords as $aToken) {
|
||||
$iId = $aToken->getId();
|
||||
if ($iId !== null) {
|
||||
$aWordsIDs[$iId] = '#'.$sToken.'('.$aToken->debugCode().' '.$iId.')#';
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return $aWordsIDs;
|
||||
}
|
||||
|
||||
public function debugInfo()
|
||||
{
|
||||
return $this->aTokens;
|
||||
}
|
||||
}
|
||||
@@ -1,118 +0,0 @@
|
||||
<?php
|
||||
|
||||
namespace Nominatim\Token;
|
||||
|
||||
/**
|
||||
* A standard word token.
|
||||
*/
|
||||
class Partial
|
||||
{
|
||||
/// Database word id, if applicable.
|
||||
private $iId;
|
||||
/// Number of appearances in the database.
|
||||
private $iSearchNameCount;
|
||||
/// True, if the token consists exclusively of digits and spaces.
|
||||
private $bNumberToken;
|
||||
|
||||
public function __construct($iId, $sToken, $iSearchNameCount)
|
||||
{
|
||||
$this->iId = $iId;
|
||||
$this->bNumberToken = (bool) preg_match('#^[0-9 ]+$#', $sToken);
|
||||
$this->iSearchNameCount = $iSearchNameCount;
|
||||
}
|
||||
|
||||
public function getId()
|
||||
{
|
||||
return $this->iId;
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if the token can be added to the given search.
|
||||
* Derive new searches by adding this token to an existing search.
|
||||
*
|
||||
* @param object $oSearch Partial search description derived so far.
|
||||
* @param object $oPosition Description of the token position within
|
||||
the query.
|
||||
*
|
||||
* @return True if the token is compatible with the search configuration
|
||||
* given the position.
|
||||
*/
|
||||
public function isExtendable($oSearch, $oPosition)
|
||||
{
|
||||
return !$oPosition->isPhrase('country');
|
||||
}
|
||||
|
||||
/**
|
||||
* Derive new searches by adding this token to an existing search.
|
||||
*
|
||||
* @param object $oSearch Partial search description derived so far.
|
||||
* @param object $oPosition Description of the token position within
|
||||
the query.
|
||||
*
|
||||
* @return SearchDescription[] List of derived search descriptions.
|
||||
*/
|
||||
public function extendSearch($oSearch, $oPosition)
|
||||
{
|
||||
$aNewSearches = array();
|
||||
|
||||
// Partial token in Address.
|
||||
if (($oPosition->isPhrase('') || !$oPosition->isFirstPhrase())
|
||||
&& $oSearch->hasName()
|
||||
) {
|
||||
$iSearchCost = $this->bNumberToken ? 2 : 1;
|
||||
if ($this->iSearchNameCount >= CONST_Max_Word_Frequency) {
|
||||
$iSearchCost += 1;
|
||||
}
|
||||
|
||||
$oNewSearch = $oSearch->clone($iSearchCost);
|
||||
$oNewSearch->addAddressToken(
|
||||
$this->iId,
|
||||
$this->iSearchNameCount < CONST_Max_Word_Frequency
|
||||
);
|
||||
|
||||
$aNewSearches[] = $oNewSearch;
|
||||
}
|
||||
|
||||
// Partial token in Name.
|
||||
if ((!$oSearch->hasPostcode() && !$oSearch->hasAddress())
|
||||
&& (!$oSearch->hasName(true)
|
||||
|| $oSearch->getNamePhrase() == $oPosition->getPhrase())
|
||||
) {
|
||||
$iSearchCost = 1;
|
||||
if (!$oSearch->hasName(true)) {
|
||||
$iSearchCost += 1;
|
||||
}
|
||||
if ($this->bNumberToken) {
|
||||
$iSearchCost += 1;
|
||||
}
|
||||
|
||||
$oNewSearch = $oSearch->clone($iSearchCost);
|
||||
$oNewSearch->addPartialNameToken(
|
||||
$this->iId,
|
||||
$this->iSearchNameCount < CONST_Max_Word_Frequency,
|
||||
$oPosition->getPhrase()
|
||||
);
|
||||
|
||||
$aNewSearches[] = $oNewSearch;
|
||||
}
|
||||
|
||||
return $aNewSearches;
|
||||
}
|
||||
|
||||
|
||||
public function debugInfo()
|
||||
{
|
||||
return array(
|
||||
'ID' => $this->iId,
|
||||
'Type' => 'partial',
|
||||
'Info' => array(
|
||||
'count' => $this->iSearchNameCount
|
||||
)
|
||||
);
|
||||
}
|
||||
|
||||
public function debugCode()
|
||||
{
|
||||
return 'w';
|
||||
}
|
||||
}
|
||||
@@ -1,98 +0,0 @@
|
||||
<?php
|
||||
|
||||
namespace Nominatim\Token;
|
||||
|
||||
/**
|
||||
* A postcode token.
|
||||
*/
|
||||
class Postcode
|
||||
{
|
||||
/// Database word id, if available.
|
||||
private $iId;
|
||||
/// Full nomralized postcode (upper cased).
|
||||
private $sPostcode;
|
||||
// Optional country code the postcode belongs to (currently unused).
|
||||
private $sCountryCode;
|
||||
|
||||
public function __construct($iId, $sPostcode, $sCountryCode = '')
|
||||
{
|
||||
$this->iId = $iId;
|
||||
$this->sPostcode = $sPostcode;
|
||||
$this->sCountryCode = empty($sCountryCode) ? '' : $sCountryCode;
|
||||
}
|
||||
|
||||
public function getId()
|
||||
{
|
||||
return $this->iId;
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if the token can be added to the given search.
|
||||
* Derive new searches by adding this token to an existing search.
|
||||
*
|
||||
* @param object $oSearch Partial search description derived so far.
|
||||
* @param object $oPosition Description of the token position within
|
||||
the query.
|
||||
*
|
||||
* @return True if the token is compatible with the search configuration
|
||||
* given the position.
|
||||
*/
|
||||
public function isExtendable($oSearch, $oPosition)
|
||||
{
|
||||
return !$oSearch->hasPostcode() && $oPosition->maybePhrase('postalcode');
|
||||
}
|
||||
|
||||
/**
|
||||
* Derive new searches by adding this token to an existing search.
|
||||
*
|
||||
* @param object $oSearch Partial search description derived so far.
|
||||
* @param object $oPosition Description of the token position within
|
||||
the query.
|
||||
*
|
||||
* @return SearchDescription[] List of derived search descriptions.
|
||||
*/
|
||||
public function extendSearch($oSearch, $oPosition)
|
||||
{
|
||||
$aNewSearches = array();
|
||||
|
||||
// If we have structured search or this is the first term,
|
||||
// make the postcode the primary search element.
|
||||
if ($oSearch->hasOperator(\Nominatim\Operator::NONE) && $oPosition->isFirstToken()) {
|
||||
$oNewSearch = $oSearch->clone(1);
|
||||
$oNewSearch->setPostcodeAsName($this->iId, $this->sPostcode);
|
||||
|
||||
$aNewSearches[] = $oNewSearch;
|
||||
}
|
||||
|
||||
// If we have a structured search or this is not the first term,
|
||||
// add the postcode as an addendum.
|
||||
if (!$oSearch->hasOperator(\Nominatim\Operator::POSTCODE)
|
||||
&& ($oPosition->isPhrase('postalcode') || $oSearch->hasName())
|
||||
) {
|
||||
$iPenalty = 1;
|
||||
if (strlen($this->sPostcode) < 4) {
|
||||
$iPenalty += 4 - strlen($this->sPostcode);
|
||||
}
|
||||
$oNewSearch = $oSearch->clone($iPenalty);
|
||||
$oNewSearch->setPostcode($this->sPostcode);
|
||||
|
||||
$aNewSearches[] = $oNewSearch;
|
||||
}
|
||||
|
||||
return $aNewSearches;
|
||||
}
|
||||
|
||||
public function debugInfo()
|
||||
{
|
||||
return array(
|
||||
'ID' => $this->iId,
|
||||
'Type' => 'postcode',
|
||||
'Info' => $this->sPostcode.'('.$this->sCountryCode.')'
|
||||
);
|
||||
}
|
||||
|
||||
public function debugCode()
|
||||
{
|
||||
return 'P';
|
||||
}
|
||||
}
|
||||
@@ -1,102 +0,0 @@
|
||||
<?php
|
||||
|
||||
namespace Nominatim\Token;
|
||||
|
||||
require_once(CONST_LibDir.'/SpecialSearchOperator.php');
|
||||
|
||||
/**
|
||||
* A word token describing a place type.
|
||||
*/
|
||||
class SpecialTerm
|
||||
{
|
||||
/// Database word id, if applicable.
|
||||
private $iId;
|
||||
/// Class (or OSM tag key) of the place to look for.
|
||||
private $sClass;
|
||||
/// Type (or OSM tag value) of the place to look for.
|
||||
private $sType;
|
||||
/// Relationship of the operator to the object (see Operator class).
|
||||
private $iOperator;
|
||||
|
||||
public function __construct($iID, $sClass, $sType, $iOperator)
|
||||
{
|
||||
$this->iId = $iID;
|
||||
$this->sClass = $sClass;
|
||||
$this->sType = $sType;
|
||||
$this->iOperator = $iOperator;
|
||||
}
|
||||
|
||||
public function getId()
|
||||
{
|
||||
return $this->iId;
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if the token can be added to the given search.
|
||||
* Derive new searches by adding this token to an existing search.
|
||||
*
|
||||
* @param object $oSearch Partial search description derived so far.
|
||||
* @param object $oPosition Description of the token position within
|
||||
the query.
|
||||
*
|
||||
* @return True if the token is compatible with the search configuration
|
||||
* given the position.
|
||||
*/
|
||||
public function isExtendable($oSearch, $oPosition)
|
||||
{
|
||||
return !$oSearch->hasOperator() && $oPosition->isPhrase('');
|
||||
}
|
||||
|
||||
/**
|
||||
* Derive new searches by adding this token to an existing search.
|
||||
*
|
||||
* @param object $oSearch Partial search description derived so far.
|
||||
* @param object $oPosition Description of the token position within
|
||||
the query.
|
||||
*
|
||||
* @return SearchDescription[] List of derived search descriptions.
|
||||
*/
|
||||
public function extendSearch($oSearch, $oPosition)
|
||||
{
|
||||
$iSearchCost = 2;
|
||||
|
||||
$iOp = $this->iOperator;
|
||||
if ($iOp == \Nominatim\Operator::NONE) {
|
||||
if ($oSearch->hasName() || $oSearch->getContext()->isBoundedSearch()) {
|
||||
$iOp = \Nominatim\Operator::NAME;
|
||||
} else {
|
||||
$iOp = \Nominatim\Operator::NEAR;
|
||||
}
|
||||
$iSearchCost += 2;
|
||||
} elseif (!$oPosition->isFirstToken() && !$oPosition->isLastToken()) {
|
||||
$iSearchCost += 2;
|
||||
}
|
||||
if ($oSearch->hasHousenumber()) {
|
||||
$iSearchCost ++;
|
||||
}
|
||||
|
||||
$oNewSearch = $oSearch->clone($iSearchCost);
|
||||
$oNewSearch->setPoiSearch($iOp, $this->sClass, $this->sType);
|
||||
|
||||
return array($oNewSearch);
|
||||
}
|
||||
|
||||
|
||||
public function debugInfo()
|
||||
{
|
||||
return array(
|
||||
'ID' => $this->iId,
|
||||
'Type' => 'special term',
|
||||
'Info' => array(
|
||||
'class' => $this->sClass,
|
||||
'type' => $this->sType,
|
||||
'operator' => \Nominatim\Operator::toString($this->iOperator)
|
||||
)
|
||||
);
|
||||
}
|
||||
|
||||
public function debugCode()
|
||||
{
|
||||
return 'S';
|
||||
}
|
||||
}
|
||||
@@ -1,102 +0,0 @@
|
||||
<?php
|
||||
|
||||
namespace Nominatim\Token;
|
||||
|
||||
/**
|
||||
* A standard word token.
|
||||
*/
|
||||
class Word
|
||||
{
|
||||
/// Database word id, if applicable.
|
||||
private $iId;
|
||||
/// Number of appearances in the database.
|
||||
private $iSearchNameCount;
|
||||
/// Number of terms in the word.
|
||||
private $iTermCount;
|
||||
|
||||
public function __construct($iId, $iSearchNameCount, $iTermCount)
|
||||
{
|
||||
$this->iId = $iId;
|
||||
$this->iSearchNameCount = $iSearchNameCount;
|
||||
$this->iTermCount = $iTermCount;
|
||||
}
|
||||
|
||||
public function getId()
|
||||
{
|
||||
return $this->iId;
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if the token can be added to the given search.
|
||||
* Derive new searches by adding this token to an existing search.
|
||||
*
|
||||
* @param object $oSearch Partial search description derived so far.
|
||||
* @param object $oPosition Description of the token position within
|
||||
the query.
|
||||
*
|
||||
* @return True if the token is compatible with the search configuration
|
||||
* given the position.
|
||||
*/
|
||||
public function isExtendable($oSearch, $oPosition)
|
||||
{
|
||||
return !$oPosition->isPhrase('country');
|
||||
}
|
||||
|
||||
/**
|
||||
* Derive new searches by adding this token to an existing search.
|
||||
*
|
||||
* @param object $oSearch Partial search description derived so far.
|
||||
* @param object $oPosition Description of the token position within
|
||||
the query.
|
||||
*
|
||||
* @return SearchDescription[] List of derived search descriptions.
|
||||
*/
|
||||
public function extendSearch($oSearch, $oPosition)
|
||||
{
|
||||
// Full words can only be a name if they appear at the beginning
|
||||
// of the phrase. In structured search the name must forcably in
|
||||
// the first phrase. In unstructured search it may be in a later
|
||||
// phrase when the first phrase is a house number.
|
||||
if ($oSearch->hasName()
|
||||
|| !($oPosition->isFirstPhrase() || $oPosition->isPhrase(''))
|
||||
) {
|
||||
if ($this->iTermCount > 1
|
||||
&& ($oPosition->isPhrase('') || !$oPosition->isFirstPhrase())
|
||||
) {
|
||||
$oNewSearch = $oSearch->clone(1);
|
||||
$oNewSearch->addAddressToken($this->iId);
|
||||
|
||||
return array($oNewSearch);
|
||||
}
|
||||
} elseif (!$oSearch->hasName(true)) {
|
||||
$oNewSearch = $oSearch->clone(1);
|
||||
$oNewSearch->addNameToken(
|
||||
$this->iId,
|
||||
CONST_Search_NameOnlySearchFrequencyThreshold
|
||||
&& $this->iSearchNameCount
|
||||
< CONST_Search_NameOnlySearchFrequencyThreshold
|
||||
);
|
||||
|
||||
return array($oNewSearch);
|
||||
}
|
||||
|
||||
return array();
|
||||
}
|
||||
|
||||
public function debugInfo()
|
||||
{
|
||||
return array(
|
||||
'ID' => $this->iId,
|
||||
'Type' => 'word',
|
||||
'Info' => array(
|
||||
'count' => $this->iSearchNameCount,
|
||||
'terms' => $this->iTermCount
|
||||
)
|
||||
);
|
||||
}
|
||||
|
||||
public function debugCode()
|
||||
{
|
||||
return 'W';
|
||||
}
|
||||
}
|
||||
@@ -1,13 +0,0 @@
|
||||
<?php
|
||||
|
||||
require('Symfony/Component/Dotenv/autoload.php');
|
||||
|
||||
function loadDotEnv()
|
||||
{
|
||||
$dotenv = new \Symfony\Component\Dotenv\Dotenv();
|
||||
$dotenv->load(CONST_ConfigDir.'/env.defaults');
|
||||
|
||||
if (file_exists('.env')) {
|
||||
$dotenv->load('.env');
|
||||
}
|
||||
}
|
||||
@@ -1,5 +0,0 @@
|
||||
<?php
|
||||
|
||||
require_once('init.php');
|
||||
require_once('cmd.php');
|
||||
require_once('DebugNone.php');
|
||||
@@ -1,4 +0,0 @@
|
||||
<?php
|
||||
|
||||
require_once(CONST_LibDir.'/lib.php');
|
||||
require_once(CONST_LibDir.'/DB.php');
|
||||
@@ -1,21 +0,0 @@
|
||||
<?php
|
||||
|
||||
$phpPhraseSettingsFile = $argv[1];
|
||||
$jsonPhraseSettingsFile = dirname($phpPhraseSettingsFile).'/'.basename($phpPhraseSettingsFile, '.php').'.json';
|
||||
|
||||
if (file_exists($phpPhraseSettingsFile) && !file_exists($jsonPhraseSettingsFile)) {
|
||||
include $phpPhraseSettingsFile;
|
||||
|
||||
$data = array();
|
||||
|
||||
if (isset($aTagsBlacklist)) {
|
||||
$data['blackList'] = $aTagsBlacklist;
|
||||
}
|
||||
if (isset($aTagsWhitelist)) {
|
||||
$data['whiteList'] = $aTagsWhitelist;
|
||||
}
|
||||
|
||||
$jsonFile = fopen($jsonPhraseSettingsFile, 'w');
|
||||
fwrite($jsonFile, json_encode($data));
|
||||
fclose($jsonFile);
|
||||
}
|
||||
@@ -1,30 +0,0 @@
|
||||
<?php
|
||||
|
||||
|
||||
function formatOSMType($sType, $bIncludeExternal = true)
|
||||
{
|
||||
if ($sType == 'N') {
|
||||
return 'node';
|
||||
}
|
||||
if ($sType == 'W') {
|
||||
return 'way';
|
||||
}
|
||||
if ($sType == 'R') {
|
||||
return 'relation';
|
||||
}
|
||||
|
||||
if (!$bIncludeExternal) {
|
||||
return '';
|
||||
}
|
||||
|
||||
if ($sType == 'T') {
|
||||
return 'way';
|
||||
}
|
||||
if ($sType == 'I') {
|
||||
return 'way';
|
||||
}
|
||||
|
||||
// not handled: P, L
|
||||
|
||||
return '';
|
||||
}
|
||||
@@ -1,19 +0,0 @@
|
||||
<?php
|
||||
|
||||
function getOsm2pgsqlBinary()
|
||||
{
|
||||
$sBinary = getSetting('OSM2PGSQL_BINARY');
|
||||
|
||||
return $sBinary ? $sBinary : CONST_Default_Osm2pgsql;
|
||||
}
|
||||
|
||||
function getImportStyle()
|
||||
{
|
||||
$sStyle = getSetting('IMPORT_STYLE');
|
||||
|
||||
if (in_array($sStyle, array('admin', 'street', 'address', 'full', 'extratags'))) {
|
||||
return CONST_ConfigDir.'/import-'.$sStyle.'.style';
|
||||
}
|
||||
|
||||
return $sStyle;
|
||||
}
|
||||
@@ -1,246 +0,0 @@
|
||||
<?php
|
||||
|
||||
namespace Nominatim;
|
||||
|
||||
class Tokenizer
|
||||
{
|
||||
private $oDB;
|
||||
|
||||
private $oNormalizer;
|
||||
private $oTransliterator;
|
||||
private $aCountryRestriction;
|
||||
|
||||
public function __construct(&$oDB)
|
||||
{
|
||||
$this->oDB =& $oDB;
|
||||
$this->oNormalizer = \Transliterator::createFromRules(CONST_Term_Normalization_Rules);
|
||||
$this->oTransliterator = \Transliterator::createFromRules(CONST_Transliteration);
|
||||
}
|
||||
|
||||
public function checkStatus()
|
||||
{
|
||||
$sSQL = 'SELECT word_id FROM word limit 1';
|
||||
$iWordID = $this->oDB->getOne($sSQL);
|
||||
if ($iWordID === false) {
|
||||
throw new \Exception('Query failed', 703);
|
||||
}
|
||||
if (!$iWordID) {
|
||||
throw new \Exception('No value', 704);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
public function setCountryRestriction($aCountries)
|
||||
{
|
||||
$this->aCountryRestriction = $aCountries;
|
||||
}
|
||||
|
||||
|
||||
public function normalizeString($sTerm)
|
||||
{
|
||||
if ($this->oNormalizer === null) {
|
||||
return $sTerm;
|
||||
}
|
||||
|
||||
return $this->oNormalizer->transliterate($sTerm);
|
||||
}
|
||||
|
||||
private function makeStandardWord($sTerm)
|
||||
{
|
||||
return trim($this->oTransliterator->transliterate(' '.$sTerm.' '));
|
||||
}
|
||||
|
||||
|
||||
public function tokensForSpecialTerm($sTerm)
|
||||
{
|
||||
$aResults = array();
|
||||
|
||||
$sSQL = "SELECT word_id, info->>'class' as class, info->>'type' as type ";
|
||||
$sSQL .= ' FROM word WHERE word_token = :term and type = \'S\'';
|
||||
|
||||
Debug::printVar('Term', $sTerm);
|
||||
Debug::printSQL($sSQL);
|
||||
$aSearchWords = $this->oDB->getAll($sSQL, array(':term' => $this->makeStandardWord($sTerm)));
|
||||
|
||||
Debug::printVar('Results', $aSearchWords);
|
||||
|
||||
foreach ($aSearchWords as $aSearchTerm) {
|
||||
$aResults[] = new \Nominatim\Token\SpecialTerm(
|
||||
$aSearchTerm['word_id'],
|
||||
$aSearchTerm['class'],
|
||||
$aSearchTerm['type'],
|
||||
\Nominatim\Operator::TYPE
|
||||
);
|
||||
}
|
||||
|
||||
Debug::printVar('Special term tokens', $aResults);
|
||||
|
||||
return $aResults;
|
||||
}
|
||||
|
||||
|
||||
public function extractTokensFromPhrases(&$aPhrases)
|
||||
{
|
||||
$sNormQuery = '';
|
||||
$aWordLists = array();
|
||||
$aTokens = array();
|
||||
foreach ($aPhrases as $iPhrase => $oPhrase) {
|
||||
$sNormQuery .= ','.$this->normalizeString($oPhrase->getPhrase());
|
||||
$sPhrase = $this->makeStandardWord($oPhrase->getPhrase());
|
||||
Debug::printVar('Phrase', $sPhrase);
|
||||
if (strlen($sPhrase) > 0) {
|
||||
$aWords = explode(' ', $sPhrase);
|
||||
Tokenizer::addTokens($aTokens, $aWords);
|
||||
$aWordLists[] = $aWords;
|
||||
} else {
|
||||
$aWordLists[] = array();
|
||||
}
|
||||
}
|
||||
|
||||
Debug::printVar('Tokens', $aTokens);
|
||||
Debug::printVar('WordLists', $aWordLists);
|
||||
|
||||
$oValidTokens = $this->computeValidTokens($aTokens, $sNormQuery);
|
||||
|
||||
foreach ($aPhrases as $iPhrase => $oPhrase) {
|
||||
$oPhrase->computeWordSets($aWordLists[$iPhrase], $oValidTokens);
|
||||
}
|
||||
|
||||
return $oValidTokens;
|
||||
}
|
||||
|
||||
|
||||
private function computeValidTokens($aTokens, $sNormQuery)
|
||||
{
|
||||
$oValidTokens = new TokenList();
|
||||
|
||||
if (!empty($aTokens)) {
|
||||
$this->addTokensFromDB($oValidTokens, $aTokens, $sNormQuery);
|
||||
|
||||
// Try more interpretations for Tokens that could not be matched.
|
||||
foreach ($aTokens as $sToken) {
|
||||
if ($sToken[0] != ' ' && !$oValidTokens->contains($sToken)) {
|
||||
if (preg_match('/^([0-9]{5}) [0-9]{4}$/', $sToken, $aData)) {
|
||||
// US ZIP+4 codes - merge in the 5-digit ZIP code
|
||||
$oValidTokens->addToken(
|
||||
$sToken,
|
||||
new Token\Postcode(null, $aData[1], 'us')
|
||||
);
|
||||
} elseif (preg_match('/^[0-9]+$/', $sToken)) {
|
||||
// Unknown single word token with a number.
|
||||
// Assume it is a house number.
|
||||
$oValidTokens->addToken(
|
||||
$sToken,
|
||||
new Token\HouseNumber(null, trim($sToken))
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return $oValidTokens;
|
||||
}
|
||||
|
||||
|
||||
private function addTokensFromDB(&$oValidTokens, $aTokens, $sNormQuery)
|
||||
{
|
||||
// Check which tokens we have, get the ID numbers
|
||||
$sSQL = 'SELECT word_id, word_token, type, word,';
|
||||
$sSQL .= " info->>'op' as operator,";
|
||||
$sSQL .= " info->>'class' as class, info->>'type' as ctype,";
|
||||
$sSQL .= " info->>'count' as count";
|
||||
$sSQL .= ' FROM word WHERE word_token in (';
|
||||
$sSQL .= join(',', $this->oDB->getDBQuotedList($aTokens)).')';
|
||||
|
||||
Debug::printSQL($sSQL);
|
||||
|
||||
$aDBWords = $this->oDB->getAll($sSQL, null, 'Could not get word tokens.');
|
||||
|
||||
foreach ($aDBWords as $aWord) {
|
||||
$iId = (int) $aWord['word_id'];
|
||||
$sTok = $aWord['word_token'];
|
||||
|
||||
switch ($aWord['type']) {
|
||||
case 'C': // country name tokens
|
||||
if ($aWord['word'] !== null
|
||||
&& (!$this->aCountryRestriction
|
||||
|| in_array($aWord['word'], $this->aCountryRestriction))
|
||||
) {
|
||||
$oValidTokens->addToken(
|
||||
$sTok,
|
||||
new Token\Country($iId, $aWord['word'])
|
||||
);
|
||||
}
|
||||
break;
|
||||
case 'H': // house number tokens
|
||||
$oValidTokens->addToken($sTok, new Token\HouseNumber($iId, $aWord['word_token']));
|
||||
break;
|
||||
case 'P': // postcode tokens
|
||||
// Postcodes are not normalized, so they may have content
|
||||
// that makes SQL injection possible. Reject postcodes
|
||||
// that would need special escaping.
|
||||
if ($aWord['word'] !== null
|
||||
&& pg_escape_string($aWord['word']) == $aWord['word']
|
||||
) {
|
||||
$sNormPostcode = $this->normalizeString($aWord['word']);
|
||||
if (strpos($sNormQuery, $sNormPostcode) !== false) {
|
||||
$oValidTokens->addToken(
|
||||
$sTok,
|
||||
new Token\Postcode($iId, $aWord['word'], null)
|
||||
);
|
||||
}
|
||||
}
|
||||
break;
|
||||
case 'S': // tokens for classification terms (special phrases)
|
||||
if ($aWord['class'] !== null && $aWord['ctype'] !== null) {
|
||||
$oValidTokens->addToken($sTok, new Token\SpecialTerm(
|
||||
$iId,
|
||||
$aWord['class'],
|
||||
$aWord['ctype'],
|
||||
(isset($aWord['operator'])) ? Operator::NEAR : Operator::NONE
|
||||
));
|
||||
}
|
||||
break;
|
||||
case 'W': // full-word tokens
|
||||
$oValidTokens->addToken($sTok, new Token\Word(
|
||||
$iId,
|
||||
(int) $aWord['count'],
|
||||
substr_count($aWord['word_token'], ' ')
|
||||
));
|
||||
break;
|
||||
case 'w': // partial word terms
|
||||
$oValidTokens->addToken($sTok, new Token\Partial(
|
||||
$iId,
|
||||
$aWord['word_token'],
|
||||
(int) $aWord['count']
|
||||
));
|
||||
break;
|
||||
default:
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Add the tokens from this phrase to the given list of tokens.
|
||||
*
|
||||
* @param string[] $aTokens List of tokens to append.
|
||||
*
|
||||
* @return void
|
||||
*/
|
||||
private static function addTokens(&$aTokens, $aWords)
|
||||
{
|
||||
$iNumWords = count($aWords);
|
||||
|
||||
for ($i = 0; $i < $iNumWords; $i++) {
|
||||
$sPhrase = $aWords[$i];
|
||||
$aTokens[$sPhrase] = $sPhrase;
|
||||
|
||||
for ($j = $i + 1; $j < $iNumWords; $j++) {
|
||||
$sPhrase .= ' '.$aWords[$j];
|
||||
$aTokens[$sPhrase] = $sPhrase;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,266 +0,0 @@
|
||||
<?php
|
||||
|
||||
namespace Nominatim;
|
||||
|
||||
class Tokenizer
|
||||
{
|
||||
private $oDB;
|
||||
|
||||
private $oNormalizer = null;
|
||||
private $aCountryRestriction = null;
|
||||
|
||||
public function __construct(&$oDB)
|
||||
{
|
||||
$this->oDB =& $oDB;
|
||||
$this->oNormalizer = \Transliterator::createFromRules(CONST_Term_Normalization_Rules);
|
||||
}
|
||||
|
||||
public function checkStatus()
|
||||
{
|
||||
$sStandardWord = $this->oDB->getOne("SELECT make_standard_name('a')");
|
||||
if ($sStandardWord === false) {
|
||||
throw new \Exception('Module failed', 701);
|
||||
}
|
||||
|
||||
if ($sStandardWord != 'a') {
|
||||
throw new \Exception('Module call failed', 702);
|
||||
}
|
||||
|
||||
$sSQL = "SELECT word_id FROM word WHERE word_token IN (' a')";
|
||||
$iWordID = $this->oDB->getOne($sSQL);
|
||||
if ($iWordID === false) {
|
||||
throw new \Exception('Query failed', 703);
|
||||
}
|
||||
if (!$iWordID) {
|
||||
throw new \Exception('No value', 704);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
public function setCountryRestriction($aCountries)
|
||||
{
|
||||
$this->aCountryRestriction = $aCountries;
|
||||
}
|
||||
|
||||
|
||||
public function normalizeString($sTerm)
|
||||
{
|
||||
if ($this->oNormalizer === null) {
|
||||
return $sTerm;
|
||||
}
|
||||
|
||||
return $this->oNormalizer->transliterate($sTerm);
|
||||
}
|
||||
|
||||
|
||||
public function tokensForSpecialTerm($sTerm)
|
||||
{
|
||||
$aResults = array();
|
||||
|
||||
$sSQL = 'SELECT word_id, class, type FROM word ';
|
||||
$sSQL .= ' WHERE word_token = \' \' || make_standard_name(:term)';
|
||||
$sSQL .= ' AND class is not null AND class not in (\'place\')';
|
||||
|
||||
Debug::printVar('Term', $sTerm);
|
||||
Debug::printSQL($sSQL);
|
||||
$aSearchWords = $this->oDB->getAll($sSQL, array(':term' => $sTerm));
|
||||
|
||||
Debug::printVar('Results', $aSearchWords);
|
||||
|
||||
foreach ($aSearchWords as $aSearchTerm) {
|
||||
$aResults[] = new \Nominatim\Token\SpecialTerm(
|
||||
$aSearchTerm['word_id'],
|
||||
$aSearchTerm['class'],
|
||||
$aSearchTerm['type'],
|
||||
\Nominatim\Operator::TYPE
|
||||
);
|
||||
}
|
||||
|
||||
Debug::printVar('Special term tokens', $aResults);
|
||||
|
||||
return $aResults;
|
||||
}
|
||||
|
||||
|
||||
public function extractTokensFromPhrases(&$aPhrases)
|
||||
{
|
||||
// First get the normalized version of all phrases
|
||||
$sNormQuery = '';
|
||||
$sSQL = 'SELECT ';
|
||||
$aParams = array();
|
||||
foreach ($aPhrases as $iPhrase => $oPhrase) {
|
||||
$sNormQuery .= ','.$this->normalizeString($oPhrase->getPhrase());
|
||||
$sSQL .= 'make_standard_name(:' .$iPhrase.') as p'.$iPhrase.',';
|
||||
$aParams[':'.$iPhrase] = $oPhrase->getPhrase();
|
||||
}
|
||||
$sSQL = substr($sSQL, 0, -1);
|
||||
|
||||
Debug::printSQL($sSQL);
|
||||
Debug::printVar('SQL parameters', $aParams);
|
||||
|
||||
$aNormPhrases = $this->oDB->getRow($sSQL, $aParams);
|
||||
|
||||
Debug::printVar('SQL result', $aNormPhrases);
|
||||
|
||||
// now compute all possible tokens
|
||||
$aWordLists = array();
|
||||
$aTokens = array();
|
||||
foreach ($aNormPhrases as $sPhrase) {
|
||||
if (strlen($sPhrase) > 0) {
|
||||
$aWords = explode(' ', $sPhrase);
|
||||
Tokenizer::addTokens($aTokens, $aWords);
|
||||
$aWordLists[] = $aWords;
|
||||
} else {
|
||||
$aWordLists[] = array();
|
||||
}
|
||||
}
|
||||
|
||||
Debug::printVar('Tokens', $aTokens);
|
||||
Debug::printVar('WordLists', $aWordLists);
|
||||
|
||||
$oValidTokens = $this->computeValidTokens($aTokens, $sNormQuery);
|
||||
|
||||
foreach ($aPhrases as $iPhrase => $oPhrase) {
|
||||
$oPhrase->computeWordSets($aWordLists[$iPhrase], $oValidTokens);
|
||||
}
|
||||
|
||||
return $oValidTokens;
|
||||
}
|
||||
|
||||
|
||||
private function computeValidTokens($aTokens, $sNormQuery)
|
||||
{
|
||||
$oValidTokens = new TokenList();
|
||||
|
||||
if (!empty($aTokens)) {
|
||||
$this->addTokensFromDB($oValidTokens, $aTokens, $sNormQuery);
|
||||
|
||||
// Try more interpretations for Tokens that could not be matched.
|
||||
foreach ($aTokens as $sToken) {
|
||||
if ($sToken[0] != ' ' && !$oValidTokens->contains($sToken)) {
|
||||
if (preg_match('/^([0-9]{5}) [0-9]{4}$/', $sToken, $aData)) {
|
||||
// US ZIP+4 codes - merge in the 5-digit ZIP code
|
||||
$oValidTokens->addToken(
|
||||
$sToken,
|
||||
new Token\Postcode(null, $aData[1], 'us')
|
||||
);
|
||||
} elseif (preg_match('/^[0-9]+$/', $sToken)) {
|
||||
// Unknown single word token with a number.
|
||||
// Assume it is a house number.
|
||||
$oValidTokens->addToken(
|
||||
$sToken,
|
||||
new Token\HouseNumber(null, trim($sToken))
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return $oValidTokens;
|
||||
}
|
||||
|
||||
|
||||
private function addTokensFromDB(&$oValidTokens, $aTokens, $sNormQuery)
|
||||
{
|
||||
// Check which tokens we have, get the ID numbers
|
||||
$sSQL = 'SELECT word_id, word_token, word, class, type, country_code,';
|
||||
$sSQL .= ' operator, coalesce(search_name_count, 0) as count';
|
||||
$sSQL .= ' FROM word WHERE word_token in (';
|
||||
$sSQL .= join(',', $this->oDB->getDBQuotedList($aTokens)).')';
|
||||
|
||||
Debug::printSQL($sSQL);
|
||||
|
||||
$aDBWords = $this->oDB->getAll($sSQL, null, 'Could not get word tokens.');
|
||||
|
||||
foreach ($aDBWords as $aWord) {
|
||||
$oToken = null;
|
||||
$iId = (int) $aWord['word_id'];
|
||||
|
||||
if ($aWord['class']) {
|
||||
// Special terms need to appear in their normalized form.
|
||||
// (postcodes are not normalized in the word table)
|
||||
$sNormWord = $this->normalizeString($aWord['word']);
|
||||
if ($aWord['word'] && strpos($sNormQuery, $sNormWord) === false) {
|
||||
continue;
|
||||
}
|
||||
|
||||
if ($aWord['class'] == 'place' && $aWord['type'] == 'house') {
|
||||
$oToken = new Token\HouseNumber($iId, trim($aWord['word_token']));
|
||||
} elseif ($aWord['class'] == 'place' && $aWord['type'] == 'postcode') {
|
||||
if ($aWord['word']
|
||||
&& pg_escape_string($aWord['word']) == $aWord['word']
|
||||
) {
|
||||
$oToken = new Token\Postcode(
|
||||
$iId,
|
||||
$aWord['word'],
|
||||
$aWord['country_code']
|
||||
);
|
||||
}
|
||||
} else {
|
||||
// near and in operator the same at the moment
|
||||
$oToken = new Token\SpecialTerm(
|
||||
$iId,
|
||||
$aWord['class'],
|
||||
$aWord['type'],
|
||||
$aWord['operator'] ? Operator::NEAR : Operator::NONE
|
||||
);
|
||||
}
|
||||
} elseif ($aWord['country_code']) {
|
||||
// Filter country tokens that do not match restricted countries.
|
||||
if (!$this->aCountryRestriction
|
||||
|| in_array($aWord['country_code'], $this->aCountryRestriction)
|
||||
) {
|
||||
$oToken = new Token\Country($iId, $aWord['country_code']);
|
||||
}
|
||||
} elseif ($aWord['word_token'][0] == ' ') {
|
||||
$oToken = new Token\Word(
|
||||
$iId,
|
||||
(int) $aWord['count'],
|
||||
substr_count($aWord['word_token'], ' ')
|
||||
);
|
||||
// For backward compatibility: ignore all partial tokens with more
|
||||
// than one word.
|
||||
} elseif (strpos($aWord['word_token'], ' ') === false) {
|
||||
$oToken = new Token\Partial(
|
||||
$iId,
|
||||
$aWord['word_token'],
|
||||
(int) $aWord['count']
|
||||
);
|
||||
}
|
||||
|
||||
if ($oToken) {
|
||||
// remove any leading spaces
|
||||
if ($aWord['word_token'][0] == ' ') {
|
||||
$oValidTokens->addToken(substr($aWord['word_token'], 1), $oToken);
|
||||
} else {
|
||||
$oValidTokens->addToken($aWord['word_token'], $oToken);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Add the tokens from this phrase to the given list of tokens.
|
||||
*
|
||||
* @param string[] $aTokens List of tokens to append.
|
||||
*
|
||||
* @return void
|
||||
*/
|
||||
private static function addTokens(&$aTokens, $aWords)
|
||||
{
|
||||
$iNumWords = count($aWords);
|
||||
|
||||
for ($i = 0; $i < $iNumWords; $i++) {
|
||||
$sPhrase = $aWords[$i];
|
||||
$aTokens[' '.$sPhrase] = ' '.$sPhrase;
|
||||
$aTokens[$sPhrase] = $sPhrase;
|
||||
|
||||
for ($j = $i + 1; $j < $iNumWords; $j++) {
|
||||
$sPhrase .= ' '.$aWords[$j];
|
||||
$aTokens[' '.$sPhrase] = ' '.$sPhrase;
|
||||
$aTokens[$sPhrase] = $sPhrase;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,12 +0,0 @@
|
||||
<?php
|
||||
|
||||
require_once(CONST_LibDir.'/init-website.php');
|
||||
require_once(CONST_LibDir.'/ParameterParser.php');
|
||||
|
||||
$oParams = new Nominatim\ParameterParser();
|
||||
|
||||
// Format for output
|
||||
$sOutputFormat = $oParams->getSet('format', array('xml', 'json', 'jsonv2', 'geojson', 'geocodejson'), 'jsonv2');
|
||||
set_exception_handler_by_format($sOutputFormat);
|
||||
|
||||
throw new Exception('Reverse-only import does not support forward searching.', 404);
|
||||
@@ -1,48 +0,0 @@
|
||||
<?php
|
||||
|
||||
require_once(CONST_LibDir.'/init-website.php');
|
||||
require_once(CONST_LibDir.'/ParameterParser.php');
|
||||
require_once(CONST_LibDir.'/Status.php');
|
||||
|
||||
$oParams = new Nominatim\ParameterParser();
|
||||
$sOutputFormat = $oParams->getSet('format', array('text', 'json'), 'text');
|
||||
|
||||
$oDB = new Nominatim\DB(CONST_Database_DSN);
|
||||
|
||||
if ($sOutputFormat == 'json') {
|
||||
header('content-type: application/json; charset=UTF-8');
|
||||
}
|
||||
|
||||
|
||||
try {
|
||||
$oStatus = new Nominatim\Status($oDB);
|
||||
$oStatus->status();
|
||||
|
||||
if ($sOutputFormat == 'json') {
|
||||
$epoch = $oStatus->dataDate();
|
||||
$aResponse = array(
|
||||
'status' => 0,
|
||||
'message' => 'OK',
|
||||
'data_updated' => (new DateTime('@'.$epoch))->format(DateTime::RFC3339),
|
||||
'software_version' => CONST_NominatimVersion
|
||||
);
|
||||
$sDatabaseVersion = $oStatus->databaseVersion();
|
||||
if ($sDatabaseVersion) {
|
||||
$aResponse['database_version'] = $sDatabaseVersion;
|
||||
}
|
||||
javascript_renderData($aResponse);
|
||||
} else {
|
||||
echo 'OK';
|
||||
}
|
||||
} catch (Exception $oErr) {
|
||||
if ($sOutputFormat == 'json') {
|
||||
$aResponse = array(
|
||||
'status' => $oErr->getCode(),
|
||||
'message' => $oErr->getMessage()
|
||||
);
|
||||
javascript_renderData($aResponse);
|
||||
} else {
|
||||
header('HTTP/1.0 500 Internal Server Error');
|
||||
echo 'ERROR: '.$oErr->getMessage();
|
||||
}
|
||||
}
|
||||
@@ -1,19 +0,0 @@
|
||||
{% include('functions/utils.sql') %}
|
||||
{% include('functions/ranking.sql') %}
|
||||
{% include('functions/importance.sql') %}
|
||||
{% include('functions/address_lookup.sql') %}
|
||||
{% include('functions/interpolation.sql') %}
|
||||
|
||||
{% if 'place' in db.tables %}
|
||||
{% include 'functions/place_triggers.sql' %}
|
||||
{% endif %}
|
||||
|
||||
{% if 'placex' in db.tables %}
|
||||
{% include 'functions/placex_triggers.sql' %}
|
||||
{% endif %}
|
||||
|
||||
{% if 'location_postcode' in db.tables %}
|
||||
{% include 'functions/postcode_triggers.sql' %}
|
||||
{% endif %}
|
||||
|
||||
{% include('functions/partition-functions.sql') %}
|
||||
@@ -1,62 +0,0 @@
|
||||
-- Indices used only during search and update.
|
||||
-- These indices are created only after the indexing process is done.
|
||||
|
||||
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;
|
||||
|
||||
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;
|
||||
|
||||
CREATE INDEX IF NOT EXISTS idx_osmline_parent_place_id
|
||||
ON location_property_osmline USING BTREE (parent_place_id) {{db.tablespace.search_index}};
|
||||
|
||||
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}};
|
||||
|
||||
-- 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}};
|
||||
{% 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) 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);
|
||||
{% endif %}
|
||||
{% endif %}
|
||||
@@ -1,30 +0,0 @@
|
||||
drop table IF EXISTS search_name_blank CASCADE;
|
||||
CREATE TABLE search_name_blank (
|
||||
place_id BIGINT,
|
||||
address_rank smallint,
|
||||
name_vector integer[],
|
||||
centroid GEOMETRY(Geometry, 4326)
|
||||
);
|
||||
|
||||
|
||||
{% for partition in db.partitions %}
|
||||
CREATE TABLE location_area_large_{{ partition }} () INHERITS (location_area_large) {{db.tablespace.address_data}};
|
||||
CREATE INDEX idx_location_area_large_{{ partition }}_place_id ON location_area_large_{{ partition }} USING BTREE (place_id) {{db.tablespace.address_index}};
|
||||
CREATE INDEX idx_location_area_large_{{ partition }}_geometry ON location_area_large_{{ partition }} USING GIST (geometry) {{db.tablespace.address_index}};
|
||||
|
||||
CREATE TABLE search_name_{{ partition }} () INHERITS (search_name_blank) {{db.tablespace.address_data}};
|
||||
CREATE INDEX idx_search_name_{{ partition }}_place_id ON search_name_{{ partition }} USING BTREE (place_id) {{db.tablespace.address_index}};
|
||||
CREATE INDEX idx_search_name_{{ partition }}_centroid_street ON search_name_{{ partition }} USING GIST (centroid) {{db.tablespace.address_index}} where address_rank between 26 and 27;
|
||||
CREATE INDEX idx_search_name_{{ partition }}_centroid_place ON search_name_{{ partition }} USING GIST (centroid) {{db.tablespace.address_index}} where address_rank between 2 and 25;
|
||||
|
||||
DROP TABLE IF EXISTS location_road_{{ partition }};
|
||||
CREATE TABLE location_road_{{ partition }} (
|
||||
place_id BIGINT,
|
||||
partition SMALLINT,
|
||||
country_code VARCHAR(2),
|
||||
geometry GEOMETRY(Geometry, 4326)
|
||||
) {{db.tablespace.address_data}};
|
||||
CREATE INDEX idx_location_road_{{ partition }}_geometry ON location_road_{{ partition }} USING GIST (geometry) {{db.tablespace.address_index}};
|
||||
CREATE INDEX idx_location_road_{{ partition }}_place_id ON location_road_{{ partition }} USING BTREE (place_id) {{db.tablespace.address_index}};
|
||||
|
||||
{% endfor %}
|
||||
@@ -1,15 +0,0 @@
|
||||
DROP TABLE IF EXISTS gb_postcode;
|
||||
CREATE TABLE gb_postcode (
|
||||
id integer,
|
||||
postcode character varying(9),
|
||||
geometry geometry,
|
||||
CONSTRAINT enforce_dims_geometry CHECK ((st_ndims(geometry) = 2)),
|
||||
CONSTRAINT enforce_srid_geometry CHECK ((st_srid(geometry) = 4326))
|
||||
);
|
||||
|
||||
DROP TABLE IF EXISTS us_postcode;
|
||||
CREATE TABLE us_postcode (
|
||||
postcode text,
|
||||
x double precision,
|
||||
y double precision
|
||||
);
|
||||
@@ -1,17 +0,0 @@
|
||||
--index only on parent_place_id
|
||||
CREATE INDEX IF NOT EXISTS idx_location_property_tiger_parent_place_id_imp
|
||||
ON location_property_tiger_import (parent_place_id) {{db.tablespace.aux_index}};
|
||||
CREATE UNIQUE INDEX IF NOT EXISTS idx_location_property_tiger_place_id_imp
|
||||
ON location_property_tiger_import (place_id) {{db.tablespace.aux_index}};
|
||||
|
||||
GRANT SELECT ON location_property_tiger_import TO "{{config.DATABASE_WEBUSER}}";
|
||||
|
||||
DROP TABLE IF EXISTS location_property_tiger;
|
||||
ALTER TABLE location_property_tiger_import RENAME TO location_property_tiger;
|
||||
|
||||
ALTER INDEX IF EXISTS idx_location_property_tiger_parent_place_id_imp RENAME TO idx_location_property_tiger_housenumber_parent_place_id;
|
||||
ALTER INDEX IF EXISTS idx_location_property_tiger_place_id_imp RENAME TO idx_location_property_tiger_place_id;
|
||||
|
||||
DROP FUNCTION tiger_line_import (linegeo GEOMETRY, in_startnumber INTEGER,
|
||||
in_endnumber INTEGER, interpolationtype TEXT,
|
||||
token_info JSONB, in_postcode TEXT);
|
||||
@@ -1,29 +0,0 @@
|
||||
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';
|
||||
|
||||
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}}";
|
||||
@@ -1,157 +0,0 @@
|
||||
-- Get tokens used for searching the given place.
|
||||
--
|
||||
-- These are the tokens that will be saved in the search_name table.
|
||||
CREATE OR REPLACE FUNCTION token_get_name_search_tokens(info JSONB)
|
||||
RETURNS INTEGER[]
|
||||
AS $$
|
||||
SELECT (info->>'names')::INTEGER[]
|
||||
$$ LANGUAGE SQL IMMUTABLE STRICT;
|
||||
|
||||
|
||||
-- Get tokens for matching the place name against others.
|
||||
--
|
||||
-- This should usually be restricted to full name tokens.
|
||||
CREATE OR REPLACE FUNCTION token_get_name_match_tokens(info JSONB)
|
||||
RETURNS INTEGER[]
|
||||
AS $$
|
||||
SELECT (info->>'names')::INTEGER[]
|
||||
$$ LANGUAGE SQL IMMUTABLE STRICT;
|
||||
|
||||
|
||||
-- Return the housenumber tokens applicable for the place.
|
||||
CREATE OR REPLACE FUNCTION token_get_housenumber_search_tokens(info JSONB)
|
||||
RETURNS INTEGER[]
|
||||
AS $$
|
||||
SELECT (info->>'hnr_tokens')::INTEGER[]
|
||||
$$ LANGUAGE SQL IMMUTABLE STRICT;
|
||||
|
||||
|
||||
-- Return the housenumber in the form that it can be matched during search.
|
||||
CREATE OR REPLACE FUNCTION token_normalized_housenumber(info JSONB)
|
||||
RETURNS TEXT
|
||||
AS $$
|
||||
SELECT info->>'hnr';
|
||||
$$ LANGUAGE SQL IMMUTABLE STRICT;
|
||||
|
||||
|
||||
CREATE OR REPLACE FUNCTION token_addr_street_match_tokens(info JSONB)
|
||||
RETURNS INTEGER[]
|
||||
AS $$
|
||||
SELECT (info->>'street')::INTEGER[]
|
||||
$$ LANGUAGE SQL IMMUTABLE STRICT;
|
||||
|
||||
|
||||
CREATE OR REPLACE FUNCTION token_addr_place_match_tokens(info JSONB)
|
||||
RETURNS INTEGER[]
|
||||
AS $$
|
||||
SELECT (info->>'place_match')::INTEGER[]
|
||||
$$ LANGUAGE SQL IMMUTABLE STRICT;
|
||||
|
||||
|
||||
CREATE OR REPLACE FUNCTION token_addr_place_search_tokens(info JSONB)
|
||||
RETURNS INTEGER[]
|
||||
AS $$
|
||||
SELECT (info->>'place_search')::INTEGER[]
|
||||
$$ LANGUAGE SQL IMMUTABLE STRICT;
|
||||
|
||||
|
||||
DROP TYPE IF EXISTS token_addresstoken CASCADE;
|
||||
CREATE TYPE token_addresstoken AS (
|
||||
key TEXT,
|
||||
match_tokens INT[],
|
||||
search_tokens INT[]
|
||||
);
|
||||
|
||||
CREATE OR REPLACE FUNCTION token_get_address_tokens(info JSONB)
|
||||
RETURNS SETOF token_addresstoken
|
||||
AS $$
|
||||
SELECT key, (value->>1)::int[] as match_tokens,
|
||||
(value->>0)::int[] as search_tokens
|
||||
FROM jsonb_each(info->'addr');
|
||||
$$ LANGUAGE SQL IMMUTABLE STRICT;
|
||||
|
||||
|
||||
CREATE OR REPLACE FUNCTION token_normalized_postcode(postcode TEXT)
|
||||
RETURNS TEXT
|
||||
AS $$
|
||||
SELECT CASE WHEN postcode SIMILAR TO '%(,|;)%' THEN NULL ELSE upper(trim(postcode))END;
|
||||
$$ LANGUAGE SQL IMMUTABLE STRICT;
|
||||
|
||||
|
||||
-- Return token info that should be saved permanently in the database.
|
||||
CREATE OR REPLACE FUNCTION token_strip_info(info JSONB)
|
||||
RETURNS JSONB
|
||||
AS $$
|
||||
SELECT NULL::JSONB;
|
||||
$$ LANGUAGE SQL IMMUTABLE STRICT;
|
||||
|
||||
--------------- private functions ----------------------------------------------
|
||||
|
||||
CREATE OR REPLACE FUNCTION getorcreate_full_word(norm_term TEXT, lookup_terms TEXT[],
|
||||
OUT full_token INT,
|
||||
OUT partial_tokens INT[])
|
||||
AS $$
|
||||
DECLARE
|
||||
partial_terms TEXT[] = '{}'::TEXT[];
|
||||
term TEXT;
|
||||
term_id INTEGER;
|
||||
term_count INTEGER;
|
||||
BEGIN
|
||||
SELECT min(word_id) INTO full_token
|
||||
FROM word WHERE word = norm_term and type = 'W';
|
||||
|
||||
IF full_token IS NULL THEN
|
||||
full_token := nextval('seq_word');
|
||||
INSERT INTO word (word_id, word_token, type, word, info)
|
||||
SELECT full_token, lookup_term, 'W', norm_term,
|
||||
json_build_object('count', 0)
|
||||
FROM unnest(lookup_terms) as lookup_term;
|
||||
END IF;
|
||||
|
||||
FOR term IN SELECT unnest(string_to_array(unnest(lookup_terms), ' ')) LOOP
|
||||
term := trim(term);
|
||||
IF NOT (ARRAY[term] <@ partial_terms) THEN
|
||||
partial_terms := partial_terms || term;
|
||||
END IF;
|
||||
END LOOP;
|
||||
|
||||
partial_tokens := '{}'::INT[];
|
||||
FOR term IN SELECT unnest(partial_terms) LOOP
|
||||
SELECT min(word_id), max(info->>'count') INTO term_id, term_count
|
||||
FROM word WHERE word_token = term and type = 'w';
|
||||
|
||||
IF term_id IS NULL THEN
|
||||
term_id := nextval('seq_word');
|
||||
term_count := 0;
|
||||
INSERT INTO word (word_id, word_token, type, info)
|
||||
VALUES (term_id, term, 'w', json_build_object('count', term_count));
|
||||
END IF;
|
||||
|
||||
IF term_count < {{ max_word_freq }} THEN
|
||||
partial_tokens := array_merge(partial_tokens, ARRAY[term_id]);
|
||||
END IF;
|
||||
END LOOP;
|
||||
END;
|
||||
$$
|
||||
LANGUAGE plpgsql;
|
||||
|
||||
|
||||
CREATE OR REPLACE FUNCTION getorcreate_hnr_id(lookup_term TEXT)
|
||||
RETURNS INTEGER
|
||||
AS $$
|
||||
DECLARE
|
||||
return_id INTEGER;
|
||||
BEGIN
|
||||
SELECT min(word_id) INTO return_id FROM word
|
||||
WHERE word_token = lookup_term and type = 'H';
|
||||
|
||||
IF return_id IS NULL THEN
|
||||
return_id := nextval('seq_word');
|
||||
INSERT INTO word (word_id, word_token, type)
|
||||
VALUES (return_id, lookup_term, 'H');
|
||||
END IF;
|
||||
|
||||
RETURN return_id;
|
||||
END;
|
||||
$$
|
||||
LANGUAGE plpgsql;
|
||||
@@ -1,393 +0,0 @@
|
||||
-- Get tokens used for searching the given place.
|
||||
--
|
||||
-- These are the tokens that will be saved in the search_name table.
|
||||
CREATE OR REPLACE FUNCTION token_get_name_search_tokens(info JSONB)
|
||||
RETURNS INTEGER[]
|
||||
AS $$
|
||||
SELECT (info->>'names')::INTEGER[]
|
||||
$$ LANGUAGE SQL IMMUTABLE STRICT;
|
||||
|
||||
|
||||
-- Get tokens for matching the place name against others.
|
||||
--
|
||||
-- This should usually be restricted to full name tokens.
|
||||
CREATE OR REPLACE FUNCTION token_get_name_match_tokens(info JSONB)
|
||||
RETURNS INTEGER[]
|
||||
AS $$
|
||||
SELECT (info->>'names')::INTEGER[]
|
||||
$$ LANGUAGE SQL IMMUTABLE STRICT;
|
||||
|
||||
|
||||
-- Return the housenumber tokens applicable for the place.
|
||||
CREATE OR REPLACE FUNCTION token_get_housenumber_search_tokens(info JSONB)
|
||||
RETURNS INTEGER[]
|
||||
AS $$
|
||||
SELECT (info->>'hnr_tokens')::INTEGER[]
|
||||
$$ LANGUAGE SQL IMMUTABLE STRICT;
|
||||
|
||||
|
||||
-- Return the housenumber in the form that it can be matched during search.
|
||||
CREATE OR REPLACE FUNCTION token_normalized_housenumber(info JSONB)
|
||||
RETURNS TEXT
|
||||
AS $$
|
||||
SELECT info->>'hnr';
|
||||
$$ LANGUAGE SQL IMMUTABLE STRICT;
|
||||
|
||||
|
||||
CREATE OR REPLACE FUNCTION token_addr_street_match_tokens(info JSONB)
|
||||
RETURNS INTEGER[]
|
||||
AS $$
|
||||
SELECT (info->>'street')::INTEGER[]
|
||||
$$ LANGUAGE SQL IMMUTABLE STRICT;
|
||||
|
||||
|
||||
CREATE OR REPLACE FUNCTION token_addr_place_match_tokens(info JSONB)
|
||||
RETURNS INTEGER[]
|
||||
AS $$
|
||||
SELECT (info->>'place_match')::INTEGER[]
|
||||
$$ LANGUAGE SQL IMMUTABLE STRICT;
|
||||
|
||||
|
||||
CREATE OR REPLACE FUNCTION token_addr_place_search_tokens(info JSONB)
|
||||
RETURNS INTEGER[]
|
||||
AS $$
|
||||
SELECT (info->>'place_search')::INTEGER[]
|
||||
$$ LANGUAGE SQL IMMUTABLE STRICT;
|
||||
|
||||
|
||||
DROP TYPE IF EXISTS token_addresstoken CASCADE;
|
||||
CREATE TYPE token_addresstoken AS (
|
||||
key TEXT,
|
||||
match_tokens INT[],
|
||||
search_tokens INT[]
|
||||
);
|
||||
|
||||
CREATE OR REPLACE FUNCTION token_get_address_tokens(info JSONB)
|
||||
RETURNS SETOF token_addresstoken
|
||||
AS $$
|
||||
SELECT key, (value->>1)::int[] as match_tokens,
|
||||
(value->>0)::int[] as search_tokens
|
||||
FROM jsonb_each(info->'addr');
|
||||
$$ LANGUAGE SQL IMMUTABLE STRICT;
|
||||
|
||||
|
||||
CREATE OR REPLACE FUNCTION token_normalized_postcode(postcode TEXT)
|
||||
RETURNS TEXT
|
||||
AS $$
|
||||
SELECT CASE WHEN postcode SIMILAR TO '%(,|;)%' THEN NULL ELSE upper(trim(postcode))END;
|
||||
$$ LANGUAGE SQL IMMUTABLE STRICT;
|
||||
|
||||
|
||||
-- Return token info that should be saved permanently in the database.
|
||||
CREATE OR REPLACE FUNCTION token_strip_info(info JSONB)
|
||||
RETURNS JSONB
|
||||
AS $$
|
||||
SELECT NULL::JSONB;
|
||||
$$ LANGUAGE SQL IMMUTABLE STRICT;
|
||||
|
||||
--------------- private functions ----------------------------------------------
|
||||
|
||||
-- Functions for term normalisation and access to the 'word' table.
|
||||
|
||||
CREATE OR REPLACE FUNCTION transliteration(text) RETURNS text
|
||||
AS '{{ modulepath }}/nominatim.so', 'transliteration'
|
||||
LANGUAGE c IMMUTABLE STRICT;
|
||||
|
||||
|
||||
CREATE OR REPLACE FUNCTION gettokenstring(text) RETURNS text
|
||||
AS '{{ modulepath }}/nominatim.so', 'gettokenstring'
|
||||
LANGUAGE c IMMUTABLE STRICT;
|
||||
|
||||
|
||||
CREATE OR REPLACE FUNCTION make_standard_name(name TEXT) RETURNS TEXT
|
||||
AS $$
|
||||
DECLARE
|
||||
o TEXT;
|
||||
BEGIN
|
||||
o := public.gettokenstring(public.transliteration(name));
|
||||
RETURN trim(substr(o,1,length(o)));
|
||||
END;
|
||||
$$
|
||||
LANGUAGE plpgsql IMMUTABLE;
|
||||
|
||||
-- returns NULL if the word is too common
|
||||
CREATE OR REPLACE FUNCTION getorcreate_word_id(lookup_word TEXT)
|
||||
RETURNS INTEGER
|
||||
AS $$
|
||||
DECLARE
|
||||
lookup_token TEXT;
|
||||
return_word_id INTEGER;
|
||||
count INTEGER;
|
||||
BEGIN
|
||||
lookup_token := trim(lookup_word);
|
||||
SELECT min(word_id), max(search_name_count) FROM word
|
||||
WHERE word_token = lookup_token and class is null and type is null
|
||||
INTO return_word_id, count;
|
||||
IF return_word_id IS NULL THEN
|
||||
return_word_id := nextval('seq_word');
|
||||
INSERT INTO word VALUES (return_word_id, lookup_token, null, null, null, null, 0);
|
||||
ELSE
|
||||
IF count > {{ max_word_freq }} THEN
|
||||
return_word_id := NULL;
|
||||
END IF;
|
||||
END IF;
|
||||
RETURN return_word_id;
|
||||
END;
|
||||
$$
|
||||
LANGUAGE plpgsql;
|
||||
|
||||
|
||||
-- Create housenumber tokens from an OSM addr:housenumber.
|
||||
-- The housnumber is split at comma and semicolon as necessary.
|
||||
-- The function returns the normalized form of the housenumber suitable
|
||||
-- for comparison.
|
||||
CREATE OR REPLACE FUNCTION create_housenumbers(housenumbers TEXT[],
|
||||
OUT tokens TEXT,
|
||||
OUT normtext TEXT)
|
||||
AS $$
|
||||
BEGIN
|
||||
SELECT array_to_string(array_agg(trans), ';'), array_agg(tid)::TEXT
|
||||
INTO normtext, tokens
|
||||
FROM (SELECT lookup_word as trans, getorcreate_housenumber_id(lookup_word) as tid
|
||||
FROM (SELECT make_standard_name(h) as lookup_word
|
||||
FROM unnest(housenumbers) h) x) y;
|
||||
END;
|
||||
$$ LANGUAGE plpgsql STABLE STRICT;
|
||||
|
||||
|
||||
CREATE OR REPLACE FUNCTION getorcreate_housenumber_id(lookup_word TEXT)
|
||||
RETURNS INTEGER
|
||||
AS $$
|
||||
DECLARE
|
||||
lookup_token TEXT;
|
||||
return_word_id INTEGER;
|
||||
BEGIN
|
||||
lookup_token := ' ' || trim(lookup_word);
|
||||
SELECT min(word_id) FROM word
|
||||
WHERE word_token = lookup_token and class='place' and type='house'
|
||||
INTO return_word_id;
|
||||
IF return_word_id IS NULL THEN
|
||||
return_word_id := nextval('seq_word');
|
||||
INSERT INTO word VALUES (return_word_id, lookup_token, null,
|
||||
'place', 'house', null, 0);
|
||||
END IF;
|
||||
RETURN return_word_id;
|
||||
END;
|
||||
$$
|
||||
LANGUAGE plpgsql;
|
||||
|
||||
|
||||
CREATE OR REPLACE FUNCTION create_postcode_id(postcode TEXT)
|
||||
RETURNS BOOLEAN
|
||||
AS $$
|
||||
DECLARE
|
||||
r RECORD;
|
||||
lookup_token TEXT;
|
||||
return_word_id INTEGER;
|
||||
BEGIN
|
||||
lookup_token := ' ' || make_standard_name(postcode);
|
||||
FOR r IN
|
||||
SELECT word_id FROM word
|
||||
WHERE word_token = lookup_token and word = postcode
|
||||
and class='place' and type='postcode'
|
||||
LOOP
|
||||
RETURN false;
|
||||
END LOOP;
|
||||
|
||||
INSERT INTO word VALUES (nextval('seq_word'), lookup_token, postcode,
|
||||
'place', 'postcode', null, 0);
|
||||
RETURN true;
|
||||
END;
|
||||
$$
|
||||
LANGUAGE plpgsql;
|
||||
|
||||
|
||||
CREATE OR REPLACE FUNCTION getorcreate_name_id(lookup_word TEXT, src_word TEXT)
|
||||
RETURNS INTEGER
|
||||
AS $$
|
||||
DECLARE
|
||||
lookup_token TEXT;
|
||||
nospace_lookup_token TEXT;
|
||||
return_word_id INTEGER;
|
||||
BEGIN
|
||||
lookup_token := ' '||trim(lookup_word);
|
||||
SELECT min(word_id) FROM word
|
||||
WHERE word_token = lookup_token and class is null and type is null
|
||||
INTO return_word_id;
|
||||
IF return_word_id IS NULL THEN
|
||||
return_word_id := nextval('seq_word');
|
||||
INSERT INTO word VALUES (return_word_id, lookup_token, src_word,
|
||||
null, null, null, 0);
|
||||
END IF;
|
||||
RETURN return_word_id;
|
||||
END;
|
||||
$$
|
||||
LANGUAGE plpgsql;
|
||||
|
||||
|
||||
-- Normalize a string and lookup its word ids (partial words).
|
||||
CREATE OR REPLACE FUNCTION addr_ids_from_name(lookup_word TEXT)
|
||||
RETURNS INTEGER[]
|
||||
AS $$
|
||||
DECLARE
|
||||
words TEXT[];
|
||||
id INTEGER;
|
||||
return_word_id INTEGER[];
|
||||
word_ids INTEGER[];
|
||||
j INTEGER;
|
||||
BEGIN
|
||||
words := string_to_array(make_standard_name(lookup_word), ' ');
|
||||
IF array_upper(words, 1) IS NOT NULL THEN
|
||||
FOR j IN 1..array_upper(words, 1) LOOP
|
||||
IF (words[j] != '') THEN
|
||||
SELECT array_agg(word_id) INTO word_ids
|
||||
FROM word
|
||||
WHERE word_token = words[j] and class is null and type is null;
|
||||
|
||||
IF word_ids IS NULL THEN
|
||||
id := nextval('seq_word');
|
||||
INSERT INTO word VALUES (id, words[j], null, null, null, null, 0);
|
||||
return_word_id := return_word_id || id;
|
||||
ELSE
|
||||
return_word_id := array_merge(return_word_id, word_ids);
|
||||
END IF;
|
||||
END IF;
|
||||
END LOOP;
|
||||
END IF;
|
||||
|
||||
RETURN return_word_id;
|
||||
END;
|
||||
$$
|
||||
LANGUAGE plpgsql;
|
||||
|
||||
|
||||
-- Normalize a string and look up its name ids (full words).
|
||||
CREATE OR REPLACE FUNCTION word_ids_from_name(lookup_word TEXT)
|
||||
RETURNS INTEGER[]
|
||||
AS $$
|
||||
DECLARE
|
||||
lookup_token TEXT;
|
||||
return_word_ids INTEGER[];
|
||||
BEGIN
|
||||
lookup_token := ' '|| make_standard_name(lookup_word);
|
||||
SELECT array_agg(word_id) FROM word
|
||||
WHERE word_token = lookup_token and class is null and type is null
|
||||
INTO return_word_ids;
|
||||
RETURN return_word_ids;
|
||||
END;
|
||||
$$
|
||||
LANGUAGE plpgsql STABLE STRICT;
|
||||
|
||||
|
||||
CREATE OR REPLACE FUNCTION make_keywords(src HSTORE)
|
||||
RETURNS INTEGER[]
|
||||
AS $$
|
||||
DECLARE
|
||||
result INTEGER[];
|
||||
s TEXT;
|
||||
w INTEGER;
|
||||
words TEXT[];
|
||||
value TEXT;
|
||||
j INTEGER;
|
||||
BEGIN
|
||||
result := '{}'::INTEGER[];
|
||||
|
||||
FOR value IN SELECT unnest(regexp_split_to_array(svals(src), E'[,;]')) LOOP
|
||||
-- full name
|
||||
s := make_standard_name(value);
|
||||
w := getorcreate_name_id(s, value);
|
||||
|
||||
IF not(ARRAY[w] <@ result) THEN
|
||||
result := result || w;
|
||||
END IF;
|
||||
|
||||
-- partial single-word terms
|
||||
words := string_to_array(s, ' ');
|
||||
IF array_upper(words, 1) IS NOT NULL THEN
|
||||
FOR j IN 1..array_upper(words, 1) LOOP
|
||||
IF (words[j] != '') THEN
|
||||
w = getorcreate_word_id(words[j]);
|
||||
IF w IS NOT NULL AND NOT (ARRAY[w] <@ result) THEN
|
||||
result := result || w;
|
||||
END IF;
|
||||
END IF;
|
||||
END LOOP;
|
||||
END IF;
|
||||
|
||||
-- consider parts before an opening braket a full word as well
|
||||
words := regexp_split_to_array(value, E'[(]');
|
||||
IF array_upper(words, 1) > 1 THEN
|
||||
s := make_standard_name(words[1]);
|
||||
IF s != '' THEN
|
||||
w := getorcreate_name_id(s, words[1]);
|
||||
IF w IS NOT NULL AND NOT (ARRAY[w] <@ result) THEN
|
||||
result := result || w;
|
||||
END IF;
|
||||
END IF;
|
||||
END IF;
|
||||
|
||||
s := regexp_replace(value, '市$', '');
|
||||
IF s != value THEN
|
||||
s := make_standard_name(s);
|
||||
IF s != '' THEN
|
||||
w := getorcreate_name_id(s, value);
|
||||
IF NOT (ARRAY[w] <@ result) THEN
|
||||
result := result || w;
|
||||
END IF;
|
||||
END IF;
|
||||
END IF;
|
||||
|
||||
END LOOP;
|
||||
|
||||
RETURN result;
|
||||
END;
|
||||
$$
|
||||
LANGUAGE plpgsql;
|
||||
|
||||
|
||||
CREATE OR REPLACE FUNCTION precompute_words(src TEXT)
|
||||
RETURNS INTEGER
|
||||
AS $$
|
||||
DECLARE
|
||||
s TEXT;
|
||||
w INTEGER;
|
||||
words TEXT[];
|
||||
i INTEGER;
|
||||
j INTEGER;
|
||||
BEGIN
|
||||
s := make_standard_name(src);
|
||||
w := getorcreate_name_id(s, src);
|
||||
|
||||
w := getorcreate_word_id(s);
|
||||
|
||||
words := string_to_array(s, ' ');
|
||||
IF array_upper(words, 1) IS NOT NULL THEN
|
||||
FOR j IN 1..array_upper(words, 1) LOOP
|
||||
IF (words[j] != '') THEN
|
||||
w := getorcreate_word_id(words[j]);
|
||||
END IF;
|
||||
END LOOP;
|
||||
END IF;
|
||||
|
||||
words := regexp_split_to_array(src, E'[,;()]');
|
||||
IF array_upper(words, 1) != 1 THEN
|
||||
FOR j IN 1..array_upper(words, 1) LOOP
|
||||
s := make_standard_name(words[j]);
|
||||
IF s != '' THEN
|
||||
w := getorcreate_word_id(s);
|
||||
END IF;
|
||||
END LOOP;
|
||||
END IF;
|
||||
|
||||
s := regexp_replace(src, '市$', '');
|
||||
IF s != src THEN
|
||||
s := make_standard_name(s);
|
||||
IF s != '' THEN
|
||||
w := getorcreate_name_id(s, src);
|
||||
END IF;
|
||||
END IF;
|
||||
|
||||
RETURN 1;
|
||||
END;
|
||||
$$
|
||||
LANGUAGE plpgsql;
|
||||
@@ -1,2 +0,0 @@
|
||||
CREATE INDEX IF NOT EXISTS idx_word_word_id
|
||||
ON word USING BTREE (word_id) {{db.tablespace.search_index}};
|
||||
@@ -1,21 +0,0 @@
|
||||
DROP TABLE IF EXISTS word;
|
||||
CREATE TABLE word (
|
||||
word_id INTEGER,
|
||||
word_token text NOT NULL,
|
||||
word text,
|
||||
class text,
|
||||
type text,
|
||||
country_code varchar(2),
|
||||
search_name_count INTEGER,
|
||||
operator TEXT
|
||||
) {{db.tablespace.search_data}};
|
||||
|
||||
CREATE INDEX idx_word_word_token ON word
|
||||
USING BTREE (word_token) {{db.tablespace.search_index}};
|
||||
CREATE INDEX idx_word_word ON word
|
||||
USING BTREE (word) {{db.tablespace.search_index}} WHERE 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}}";
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
namespace Nominatim;
|
||||
|
||||
require_once(CONST_LibDir.'/ClassTypes.php');
|
||||
require_once(CONST_BasePath.'/lib/ClassTypes.php');
|
||||
|
||||
/**
|
||||
* Detailed list of address parts for a single result
|
||||
@@ -61,7 +61,7 @@ class AddressDetails
|
||||
return join(', ', $aParts);
|
||||
}
|
||||
|
||||
public function getAddressNames()
|
||||
public function getAddressNames($sCountry = null)
|
||||
{
|
||||
$aAddress = array();
|
||||
|
||||
@@ -79,11 +79,13 @@ class AddressDetails
|
||||
$sName = $aLine['housenumber'];
|
||||
}
|
||||
|
||||
if (isset($sName)
|
||||
&& (!isset($aAddress[$sTypeLabel])
|
||||
|| $aLine['class'] == 'place')
|
||||
) {
|
||||
$aAddress[$sTypeLabel] = $sName;
|
||||
if (isset($sName)) {
|
||||
$sTypeLabel = strtolower(str_replace(' ', '_', $sTypeLabel));
|
||||
if (!isset($aAddress[$sTypeLabel])
|
||||
|| $aLine['class'] == 'place'
|
||||
) {
|
||||
$aAddress[$sTypeLabel] = $sName;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
namespace Nominatim;
|
||||
|
||||
require_once(CONST_LibDir.'/DatabaseError.php');
|
||||
require_once(CONST_BasePath.'/lib/DatabaseError.php');
|
||||
|
||||
/**
|
||||
* Uses PDO to access the database specified in the CONST_Database_DSN
|
||||
@@ -12,9 +12,9 @@ class DB
|
||||
{
|
||||
protected $connection;
|
||||
|
||||
public function __construct($sDSN = null)
|
||||
public function __construct($sDSN = CONST_Database_DSN)
|
||||
{
|
||||
$this->sDSN = $sDSN ?? getSetting('DATABASE_DSN');
|
||||
$this->sDSN = $sDSN;
|
||||
}
|
||||
|
||||
public function connect($bNew = false, $bPersistent = true)
|
||||
@@ -39,9 +39,7 @@ class DB
|
||||
$conn->exec("SET DateStyle TO 'sql,european'");
|
||||
$conn->exec("SET client_encoding TO 'utf-8'");
|
||||
$iMaxExecution = ini_get('max_execution_time');
|
||||
if ($iMaxExecution > 0) {
|
||||
$conn->setAttribute(\PDO::ATTR_TIMEOUT, $iMaxExecution); // seconds
|
||||
}
|
||||
if ($iMaxExecution > 0) $conn->setAttribute(\PDO::ATTR_TIMEOUT, $iMaxExecution); // seconds
|
||||
|
||||
$this->connection = $conn;
|
||||
return true;
|
||||
@@ -97,9 +95,7 @@ class DB
|
||||
try {
|
||||
$stmt = $this->getQueryStatement($sSQL, $aInputVars, $sErrMessage);
|
||||
$row = $stmt->fetch(\PDO::FETCH_NUM);
|
||||
if ($row === false) {
|
||||
return false;
|
||||
}
|
||||
if ($row === false) return false;
|
||||
} catch (\PDOException $e) {
|
||||
throw new \Nominatim\DatabaseError($sErrMessage, 500, null, $e, $sSQL);
|
||||
}
|
||||
@@ -244,6 +240,16 @@ class DB
|
||||
return ($this->getOne($sSQL, array(':tablename' => $sTableName)) == 1);
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns a list of table names in the database
|
||||
*
|
||||
* @return array[]
|
||||
*/
|
||||
public function getListOfTables()
|
||||
{
|
||||
return $this->getCol("SELECT tablename FROM pg_tables WHERE schemaname='public'");
|
||||
}
|
||||
|
||||
/**
|
||||
* Deletes a table. Returns true if deleted or didn't exist.
|
||||
*
|
||||
@@ -256,6 +262,76 @@ class DB
|
||||
return $this->exec('DROP TABLE IF EXISTS '.$sTableName.' CASCADE') == 0;
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if an index exists in the database. Optional filtered by tablename
|
||||
*
|
||||
* @param string $sTableName
|
||||
*
|
||||
* @return boolean
|
||||
*/
|
||||
public function indexExists($sIndexName, $sTableName = null)
|
||||
{
|
||||
return in_array($sIndexName, $this->getListOfIndices($sTableName));
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns a list of index names in the database, optional filtered by tablename
|
||||
*
|
||||
* @param string $sTableName
|
||||
*
|
||||
* @return array
|
||||
*/
|
||||
public function getListOfIndices($sTableName = null)
|
||||
{
|
||||
// table_name | index_name | column_name
|
||||
// -----------------------+---------------------------------+--------------
|
||||
// country_name | idx_country_name_country_code | country_code
|
||||
// country_osm_grid | idx_country_osm_grid_geometry | geometry
|
||||
// import_polygon_delete | idx_import_polygon_delete_osmid | osm_id
|
||||
// import_polygon_delete | idx_import_polygon_delete_osmid | osm_type
|
||||
// import_polygon_error | idx_import_polygon_error_osmid | osm_id
|
||||
// import_polygon_error | idx_import_polygon_error_osmid | osm_type
|
||||
$sSql = <<< END
|
||||
SELECT
|
||||
t.relname as table_name,
|
||||
i.relname as index_name,
|
||||
a.attname as column_name
|
||||
FROM
|
||||
pg_class t,
|
||||
pg_class i,
|
||||
pg_index ix,
|
||||
pg_attribute a
|
||||
WHERE
|
||||
t.oid = ix.indrelid
|
||||
and i.oid = ix.indexrelid
|
||||
and a.attrelid = t.oid
|
||||
and a.attnum = ANY(ix.indkey)
|
||||
and t.relkind = 'r'
|
||||
and i.relname NOT LIKE 'pg_%'
|
||||
FILTERS
|
||||
ORDER BY
|
||||
t.relname,
|
||||
i.relname,
|
||||
a.attname
|
||||
END;
|
||||
|
||||
$aRows = null;
|
||||
if ($sTableName) {
|
||||
$sSql = str_replace('FILTERS', 'and t.relname = :tablename', $sSql);
|
||||
$aRows = $this->getAll($sSql, array(':tablename' => $sTableName));
|
||||
} else {
|
||||
$sSql = str_replace('FILTERS', '', $sSql);
|
||||
$aRows = $this->getAll($sSql);
|
||||
}
|
||||
|
||||
$aIndexNames = array_unique(array_map(function ($aRow) {
|
||||
return $aRow['index_name'];
|
||||
}, $aRows));
|
||||
sort($aIndexNames);
|
||||
|
||||
return $aIndexNames;
|
||||
}
|
||||
|
||||
/**
|
||||
* Tries to connect to the database but on failure doesn't throw an exception.
|
||||
*
|
||||
@@ -310,13 +386,9 @@ class DB
|
||||
if (preg_match('/^pgsql:(.+)$/', $sDSN, $aMatches)) {
|
||||
foreach (explode(';', $aMatches[1]) as $sKeyVal) {
|
||||
list($sKey, $sVal) = explode('=', $sKeyVal, 2);
|
||||
if ($sKey == 'host') {
|
||||
$sKey = 'hostspec';
|
||||
} elseif ($sKey == 'dbname') {
|
||||
$sKey = 'database';
|
||||
} elseif ($sKey == 'user') {
|
||||
$sKey = 'username';
|
||||
}
|
||||
if ($sKey == 'host') $sKey = 'hostspec';
|
||||
if ($sKey == 'dbname') $sKey = 'database';
|
||||
if ($sKey == 'user') $sKey = 'username';
|
||||
$aInfo[$sKey] = $sVal;
|
||||
}
|
||||
}
|
||||
@@ -5,7 +5,7 @@ namespace Nominatim;
|
||||
class DatabaseError extends \Exception
|
||||
{
|
||||
|
||||
public function __construct($message, $code, $previous, $oPDOErr, $sSql = null)
|
||||
public function __construct($message, $code = 500, Exception $previous = null, $oPDOErr, $sSql = null)
|
||||
{
|
||||
parent::__construct($message, $code, $previous);
|
||||
// https://secure.php.net/manual/en/class.pdoexception.php
|
||||
@@ -78,7 +78,7 @@ class Debug
|
||||
echo '<th>Address Tokens</th><th>Address Not</th>';
|
||||
echo '<th>country</th><th>operator</th>';
|
||||
echo '<th>class</th><th>type</th><th>postcode</th><th>housenumber</th></tr>';
|
||||
foreach ($aSearches as $aRankedSet) {
|
||||
foreach ($aSearches as $iRank => $aRankedSet) {
|
||||
foreach ($aRankedSet as $aRow) {
|
||||
$aRow->dumpAsHtmlTableRow($aWordsIDs);
|
||||
}
|
||||
@@ -2,25 +2,23 @@
|
||||
|
||||
namespace Nominatim;
|
||||
|
||||
require_once(CONST_LibDir.'/PlaceLookup.php');
|
||||
require_once(CONST_LibDir.'/Phrase.php');
|
||||
require_once(CONST_LibDir.'/ReverseGeocode.php');
|
||||
require_once(CONST_LibDir.'/SearchDescription.php');
|
||||
require_once(CONST_LibDir.'/SearchContext.php');
|
||||
require_once(CONST_LibDir.'/SearchPosition.php');
|
||||
require_once(CONST_LibDir.'/TokenList.php');
|
||||
require_once(CONST_TokenizerDir.'/tokenizer.php');
|
||||
require_once(CONST_BasePath.'/lib/PlaceLookup.php');
|
||||
require_once(CONST_BasePath.'/lib/Phrase.php');
|
||||
require_once(CONST_BasePath.'/lib/ReverseGeocode.php');
|
||||
require_once(CONST_BasePath.'/lib/SearchDescription.php');
|
||||
require_once(CONST_BasePath.'/lib/SearchContext.php');
|
||||
require_once(CONST_BasePath.'/lib/TokenList.php');
|
||||
|
||||
class Geocode
|
||||
{
|
||||
protected $oDB;
|
||||
|
||||
protected $oPlaceLookup;
|
||||
protected $oTokenizer;
|
||||
|
||||
protected $aLangPrefOrder = array();
|
||||
|
||||
protected $aExcludePlaceIDs = array();
|
||||
protected $bReverseInPlan = false;
|
||||
|
||||
protected $iLimit = 20;
|
||||
protected $iFinalLimit = 10;
|
||||
@@ -44,12 +42,28 @@ class Geocode
|
||||
protected $sQuery = false;
|
||||
protected $aStructuredQuery = false;
|
||||
|
||||
protected $oNormalizer = null;
|
||||
|
||||
|
||||
public function __construct(&$oDB)
|
||||
{
|
||||
$this->oDB =& $oDB;
|
||||
$this->oPlaceLookup = new PlaceLookup($this->oDB);
|
||||
$this->oTokenizer = new \Nominatim\Tokenizer($this->oDB);
|
||||
$this->oNormalizer = \Transliterator::createFromRules(CONST_Term_Normalization_Rules);
|
||||
}
|
||||
|
||||
private function normTerm($sTerm)
|
||||
{
|
||||
if ($this->oNormalizer === null) {
|
||||
return $sTerm;
|
||||
}
|
||||
|
||||
return $this->oNormalizer->transliterate($sTerm);
|
||||
}
|
||||
|
||||
public function setReverseInPlan($bReverse)
|
||||
{
|
||||
$this->bReverseInPlan = $bReverse;
|
||||
}
|
||||
|
||||
public function setLanguagePreference($aLangPref)
|
||||
@@ -71,9 +85,7 @@ class Geocode
|
||||
$aParams['exclude_place_ids'] = implode(',', $this->aExcludePlaceIDs);
|
||||
}
|
||||
|
||||
if ($this->bBoundedSearch) {
|
||||
$aParams['bounded'] = '1';
|
||||
}
|
||||
if ($this->bBoundedSearch) $aParams['bounded'] = '1';
|
||||
|
||||
if ($this->aCountryCodes) {
|
||||
$aParams['countrycodes'] = implode(',', $this->aCountryCodes);
|
||||
@@ -88,11 +100,8 @@ class Geocode
|
||||
|
||||
public function setLimit($iLimit = 10)
|
||||
{
|
||||
if ($iLimit > 50) {
|
||||
$iLimit = 50;
|
||||
} elseif ($iLimit < 1) {
|
||||
$iLimit = 1;
|
||||
}
|
||||
if ($iLimit > 50) $iLimit = 50;
|
||||
if ($iLimit < 1) $iLimit = 1;
|
||||
|
||||
$this->iFinalLimit = $iLimit;
|
||||
$this->iLimit = $iLimit + min($iLimit, 10);
|
||||
@@ -187,24 +196,18 @@ class Geocode
|
||||
if ($sExcluded) {
|
||||
foreach ($sExcluded as $iExcludedPlaceID) {
|
||||
$iExcludedPlaceID = (int)$iExcludedPlaceID;
|
||||
if ($iExcludedPlaceID) {
|
||||
if ($iExcludedPlaceID)
|
||||
$aExcludePlaceIDs[$iExcludedPlaceID] = $iExcludedPlaceID;
|
||||
}
|
||||
}
|
||||
|
||||
if (isset($aExcludePlaceIDs)) {
|
||||
if (isset($aExcludePlaceIDs))
|
||||
$this->aExcludePlaceIDs = $aExcludePlaceIDs;
|
||||
}
|
||||
}
|
||||
|
||||
// Only certain ranks of feature
|
||||
$sFeatureType = $oParams->getString('featureType');
|
||||
if (!$sFeatureType) {
|
||||
$sFeatureType = $oParams->getString('featuretype');
|
||||
}
|
||||
if ($sFeatureType) {
|
||||
$this->setFeatureType($sFeatureType);
|
||||
}
|
||||
if (!$sFeatureType) $sFeatureType = $oParams->getString('featuretype');
|
||||
if ($sFeatureType) $this->setFeatureType($sFeatureType);
|
||||
|
||||
// Country code list
|
||||
$sCountries = $oParams->getStringList('countrycodes');
|
||||
@@ -214,9 +217,8 @@ class Geocode
|
||||
$aCountries[] = strtolower($sCountryCode);
|
||||
}
|
||||
}
|
||||
if (isset($aCountries)) {
|
||||
if (isset($aCountries))
|
||||
$this->aCountryCodes = $aCountries;
|
||||
}
|
||||
}
|
||||
|
||||
$aViewbox = $oParams->getStringList('viewboxlbrt');
|
||||
@@ -260,6 +262,7 @@ class Geocode
|
||||
$oParams->getString('country'),
|
||||
$oParams->getString('postalcode')
|
||||
);
|
||||
$this->setReverseInPlan(false);
|
||||
} else {
|
||||
$this->setQuery($sQuery);
|
||||
}
|
||||
@@ -268,17 +271,13 @@ class Geocode
|
||||
public function loadStructuredAddressElement($sValue, $sKey, $iNewMinAddressRank, $iNewMaxAddressRank, $aItemListValues)
|
||||
{
|
||||
$sValue = trim($sValue);
|
||||
if (!$sValue) {
|
||||
return false;
|
||||
}
|
||||
if (!$sValue) return false;
|
||||
$this->aStructuredQuery[$sKey] = $sValue;
|
||||
if ($this->iMinAddressRank == 0 && $this->iMaxAddressRank == 30) {
|
||||
$this->iMinAddressRank = $iNewMinAddressRank;
|
||||
$this->iMaxAddressRank = $iNewMaxAddressRank;
|
||||
}
|
||||
if ($aItemListValues) {
|
||||
$this->aAddressRankList = array_merge($this->aAddressRankList, $aItemListValues);
|
||||
}
|
||||
if ($aItemListValues) $this->aAddressRankList = array_merge($this->aAddressRankList, $aItemListValues);
|
||||
return true;
|
||||
}
|
||||
|
||||
@@ -312,11 +311,11 @@ class Geocode
|
||||
|
||||
public function fallbackStructuredQuery()
|
||||
{
|
||||
if (!$this->aStructuredQuery) return false;
|
||||
|
||||
$aParams = $this->aStructuredQuery;
|
||||
|
||||
if (!$aParams || count($aParams) == 1) {
|
||||
return false;
|
||||
}
|
||||
if (count($aParams) == 1) return false;
|
||||
|
||||
$aOrderToFallback = array('postalcode', 'street', 'city', 'county', 'state');
|
||||
|
||||
@@ -331,7 +330,7 @@ class Geocode
|
||||
return false;
|
||||
}
|
||||
|
||||
public function getGroupedSearches($aSearches, $aPhrases, $oValidTokens)
|
||||
public function getGroupedSearches($aSearches, $aPhrases, $oValidTokens, $bIsStructured)
|
||||
{
|
||||
/*
|
||||
Calculate all searches using oValidTokens i.e.
|
||||
@@ -346,26 +345,52 @@ class Geocode
|
||||
*/
|
||||
foreach ($aPhrases as $iPhrase => $oPhrase) {
|
||||
$aNewPhraseSearches = array();
|
||||
$oPosition = new SearchPosition(
|
||||
$oPhrase->getPhraseType(),
|
||||
$iPhrase,
|
||||
count($aPhrases)
|
||||
);
|
||||
$sPhraseType = $bIsStructured ? $oPhrase->getPhraseType() : '';
|
||||
|
||||
foreach ($oPhrase->getWordSets() as $aWordset) {
|
||||
$aWordsetSearches = $aSearches;
|
||||
|
||||
// Add all words from this wordset
|
||||
foreach ($aWordset as $iToken => $sToken) {
|
||||
//echo "<br><b>$sToken</b>";
|
||||
$aNewWordsetSearches = array();
|
||||
$oPosition->setTokenPosition($iToken, count($aWordset));
|
||||
|
||||
foreach ($aWordsetSearches as $oCurrentSearch) {
|
||||
foreach ($oValidTokens->get($sToken) as $oSearchTerm) {
|
||||
if ($oSearchTerm->isExtendable($oCurrentSearch, $oPosition)) {
|
||||
$aNewSearches = $oSearchTerm->extendSearch(
|
||||
$oCurrentSearch,
|
||||
$oPosition
|
||||
//echo "<i>";
|
||||
//var_dump($oCurrentSearch);
|
||||
//echo "</i>";
|
||||
|
||||
// Tokens with full name matches.
|
||||
foreach ($oValidTokens->get(' '.$sToken) as $oSearchTerm) {
|
||||
$aNewSearches = $oCurrentSearch->extendWithFullTerm(
|
||||
$oSearchTerm,
|
||||
$oValidTokens->contains($sToken)
|
||||
&& strpos($sToken, ' ') === false,
|
||||
$sPhraseType,
|
||||
$iToken == 0 && $iPhrase == 0,
|
||||
$iPhrase == 0,
|
||||
$iToken + 1 == count($aWordset)
|
||||
&& $iPhrase + 1 == count($aPhrases)
|
||||
);
|
||||
|
||||
foreach ($aNewSearches as $oSearch) {
|
||||
if ($oSearch->getRank() < $this->iMaxRank) {
|
||||
$aNewWordsetSearches[] = $oSearch;
|
||||
}
|
||||
}
|
||||
}
|
||||
// Look for partial matches.
|
||||
// Note that there is no point in adding country terms here
|
||||
// because country is omitted in the address.
|
||||
if ($sPhraseType != 'country') {
|
||||
// Allow searching for a word - but at extra cost
|
||||
foreach ($oValidTokens->get($sToken) as $oSearchTerm) {
|
||||
$aNewSearches = $oCurrentSearch->extendWithPartialTerm(
|
||||
$sToken,
|
||||
$oSearchTerm,
|
||||
$bIsStructured,
|
||||
$iPhrase,
|
||||
$oValidTokens->get(' '.$sToken)
|
||||
);
|
||||
|
||||
foreach ($aNewSearches as $oSearch) {
|
||||
@@ -380,6 +405,7 @@ class Geocode
|
||||
usort($aNewWordsetSearches, array('Nominatim\SearchDescription', 'bySearchRank'));
|
||||
$aWordsetSearches = array_slice($aNewWordsetSearches, 0, 50);
|
||||
}
|
||||
//var_Dump('<hr>',count($aWordsetSearches)); exit;
|
||||
|
||||
$aNewPhraseSearches = array_merge($aNewPhraseSearches, $aNewWordsetSearches);
|
||||
usort($aNewPhraseSearches, array('Nominatim\SearchDescription', 'bySearchRank'));
|
||||
@@ -387,11 +413,8 @@ class Geocode
|
||||
$aSearchHash = array();
|
||||
foreach ($aNewPhraseSearches as $iSearch => $aSearch) {
|
||||
$sHash = serialize($aSearch);
|
||||
if (isset($aSearchHash[$sHash])) {
|
||||
unset($aNewPhraseSearches[$iSearch]);
|
||||
} else {
|
||||
$aSearchHash[$sHash] = 1;
|
||||
}
|
||||
if (isset($aSearchHash[$sHash])) unset($aNewPhraseSearches[$iSearch]);
|
||||
else $aSearchHash[$sHash] = 1;
|
||||
}
|
||||
|
||||
$aNewPhraseSearches = array_slice($aNewPhraseSearches, 0, 50);
|
||||
@@ -412,12 +435,10 @@ class Geocode
|
||||
|
||||
$iSearchCount = 0;
|
||||
$aSearches = array();
|
||||
foreach ($aGroupedSearches as $aNewSearches) {
|
||||
foreach ($aGroupedSearches as $iScore => $aNewSearches) {
|
||||
$iSearchCount += count($aNewSearches);
|
||||
$aSearches = array_merge($aSearches, $aNewSearches);
|
||||
if ($iSearchCount > 50) {
|
||||
break;
|
||||
}
|
||||
if ($iSearchCount > 50) break;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -474,9 +495,7 @@ class Geocode
|
||||
public function lookup()
|
||||
{
|
||||
Debug::newFunction('Geocode::lookup');
|
||||
if (!$this->sQuery && !$this->aStructuredQuery) {
|
||||
return array();
|
||||
}
|
||||
if (!$this->sQuery && !$this->aStructuredQuery) return array();
|
||||
|
||||
Debug::printDebugArray('Geocode', $this);
|
||||
|
||||
@@ -498,10 +517,16 @@ class Geocode
|
||||
if ($this->aCountryCodes) {
|
||||
$oCtx->setCountryList($this->aCountryCodes);
|
||||
}
|
||||
$this->oTokenizer->setCountryRestriction($this->aCountryCodes);
|
||||
|
||||
Debug::newSection('Query Preprocessing');
|
||||
|
||||
$sNormQuery = $this->normTerm($this->sQuery);
|
||||
Debug::printVar('Normalized query', $sNormQuery);
|
||||
|
||||
$sLanguagePrefArraySQL = $this->oDB->getArraySQL(
|
||||
$this->oDB->getDBQuotedList($this->aLangPrefOrder)
|
||||
);
|
||||
|
||||
$sQuery = $this->sQuery;
|
||||
if (!preg_match('//u', $sQuery)) {
|
||||
userError('Query string is not UTF-8 encoded.');
|
||||
@@ -551,62 +576,117 @@ class Geocode
|
||||
}
|
||||
|
||||
if ($sSpecialTerm && !$aSearches[0]->hasOperator()) {
|
||||
$aTokens = $this->oTokenizer->tokensForSpecialTerm($sSpecialTerm);
|
||||
$sSpecialTerm = pg_escape_string($sSpecialTerm);
|
||||
$sToken = $this->oDB->getOne(
|
||||
'SELECT make_standard_name(:term)',
|
||||
array(':term' => $sSpecialTerm),
|
||||
'Cannot decode query. Wrong encoding?'
|
||||
);
|
||||
$sSQL = 'SELECT class, type FROM word ';
|
||||
$sSQL .= ' WHERE word_token in (\' '.$sToken.'\')';
|
||||
$sSQL .= ' AND class is not null AND class not in (\'place\')';
|
||||
|
||||
if (!empty($aTokens)) {
|
||||
$aNewSearches = array();
|
||||
$oPosition = new SearchPosition('', 0, 1);
|
||||
$oPosition->setTokenPosition(0, 1);
|
||||
|
||||
foreach ($aSearches as $oSearch) {
|
||||
foreach ($aTokens as $oToken) {
|
||||
$aNewSearches = array_merge(
|
||||
$aNewSearches,
|
||||
$oToken->extendSearch($oSearch, $oPosition)
|
||||
);
|
||||
}
|
||||
Debug::printSQL($sSQL);
|
||||
$aSearchWords = $this->oDB->getAll($sSQL);
|
||||
$aNewSearches = array();
|
||||
foreach ($aSearches as $oSearch) {
|
||||
foreach ($aSearchWords as $aSearchTerm) {
|
||||
$oNewSearch = clone $oSearch;
|
||||
$oNewSearch->setPoiSearch(
|
||||
Operator::TYPE,
|
||||
$aSearchTerm['class'],
|
||||
$aSearchTerm['type']
|
||||
);
|
||||
$aNewSearches[] = $oNewSearch;
|
||||
}
|
||||
$aSearches = $aNewSearches;
|
||||
}
|
||||
$aSearches = $aNewSearches;
|
||||
}
|
||||
|
||||
// Split query into phrases
|
||||
// Commas are used to reduce the search space by indicating where phrases split
|
||||
$aPhrases = array();
|
||||
if ($this->aStructuredQuery) {
|
||||
foreach ($this->aStructuredQuery as $iPhrase => $sPhrase) {
|
||||
$aPhrases[] = new Phrase($sPhrase, $iPhrase);
|
||||
}
|
||||
$aInPhrases = $this->aStructuredQuery;
|
||||
$bStructuredPhrases = true;
|
||||
} else {
|
||||
foreach (explode(',', $sQuery) as $sPhrase) {
|
||||
$aPhrases[] = new Phrase($sPhrase, '');
|
||||
}
|
||||
$aInPhrases = explode(',', $sQuery);
|
||||
$bStructuredPhrases = false;
|
||||
}
|
||||
|
||||
Debug::printDebugArray('Search context', $oCtx);
|
||||
Debug::printDebugArray('Base search', empty($aSearches) ? null : $aSearches[0]);
|
||||
Debug::printVar('Final query phrases', $aInPhrases);
|
||||
|
||||
// Convert each phrase to standard form
|
||||
// Create a list of standard words
|
||||
// Get all 'sets' of words
|
||||
// Generate a complete list of all
|
||||
Debug::newSection('Tokenization');
|
||||
$oValidTokens = $this->oTokenizer->extractTokensFromPhrases($aPhrases);
|
||||
$aTokens = array();
|
||||
$aPhrases = array();
|
||||
foreach ($aInPhrases as $iPhrase => $sPhrase) {
|
||||
$sPhrase = $this->oDB->getOne(
|
||||
'SELECT make_standard_name(:phrase)',
|
||||
array(':phrase' => $sPhrase),
|
||||
'Cannot normalize query string (is it a UTF-8 string?)'
|
||||
);
|
||||
if (trim($sPhrase)) {
|
||||
$oPhrase = new Phrase($sPhrase, is_string($iPhrase) ? $iPhrase : '');
|
||||
$oPhrase->addTokens($aTokens);
|
||||
$aPhrases[] = $oPhrase;
|
||||
}
|
||||
}
|
||||
|
||||
Debug::printVar('Tokens', $aTokens);
|
||||
|
||||
$oValidTokens = new TokenList();
|
||||
|
||||
if (!empty($aTokens)) {
|
||||
$oValidTokens->addTokensFromDB(
|
||||
$this->oDB,
|
||||
$aTokens,
|
||||
$this->aCountryCodes,
|
||||
$sNormQuery,
|
||||
$this->oNormalizer
|
||||
);
|
||||
|
||||
if ($oValidTokens->count() > 0) {
|
||||
$oCtx->setFullNameWords($oValidTokens->getFullWordIDs());
|
||||
|
||||
$aPhrases = array_filter($aPhrases, function ($oPhrase) {
|
||||
return $oPhrase->getWordSets() !== null;
|
||||
});
|
||||
// Try more interpretations for Tokens that could not be matched.
|
||||
foreach ($aTokens as $sToken) {
|
||||
if ($sToken[0] == ' ' && !$oValidTokens->contains($sToken)) {
|
||||
if (preg_match('/^ ([0-9]{5}) [0-9]{4}$/', $sToken, $aData)) {
|
||||
// US ZIP+4 codes - merge in the 5-digit ZIP code
|
||||
$oValidTokens->addToken(
|
||||
$sToken,
|
||||
new Token\Postcode(null, $aData[1], 'us')
|
||||
);
|
||||
} elseif (preg_match('/^ [0-9]+$/', $sToken)) {
|
||||
// Unknown single word token with a number.
|
||||
// Assume it is a house number.
|
||||
$oValidTokens->addToken(
|
||||
$sToken,
|
||||
new Token\HouseNumber(null, trim($sToken))
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Any words that have failed completely?
|
||||
// TODO: suggestions
|
||||
|
||||
Debug::printGroupTable('Valid Tokens', $oValidTokens->debugInfo());
|
||||
|
||||
foreach ($aPhrases as $oPhrase) {
|
||||
$oPhrase->computeWordSets($oValidTokens);
|
||||
}
|
||||
Debug::printDebugTable('Phrases', $aPhrases);
|
||||
|
||||
Debug::newSection('Search candidates');
|
||||
|
||||
$aGroupedSearches = $this->getGroupedSearches($aSearches, $aPhrases, $oValidTokens);
|
||||
$aGroupedSearches = $this->getGroupedSearches($aSearches, $aPhrases, $oValidTokens, $bStructuredPhrases);
|
||||
|
||||
if (!$this->aStructuredQuery) {
|
||||
if ($this->bReverseInPlan) {
|
||||
// Reverse phrase array and also reverse the order of the wordsets in
|
||||
// the first and final phrase. Don't bother about phrases in the middle
|
||||
// because order in the address doesn't matter.
|
||||
@@ -615,7 +695,7 @@ class Geocode
|
||||
if (count($aPhrases) > 1) {
|
||||
$aPhrases[count($aPhrases)-1]->invertWordSets();
|
||||
}
|
||||
$aReverseGroupedSearches = $this->getGroupedSearches($aSearches, $aPhrases, $oValidTokens);
|
||||
$aReverseGroupedSearches = $this->getGroupedSearches($aSearches, $aPhrases, $oValidTokens, false);
|
||||
|
||||
foreach ($aGroupedSearches as $aSearches) {
|
||||
foreach ($aSearches as $aSearch) {
|
||||
@@ -634,9 +714,7 @@ class Geocode
|
||||
$aGroupedSearches = array();
|
||||
foreach ($aSearches as $aSearch) {
|
||||
if ($aSearch->getRank() < $this->iMaxRank) {
|
||||
if (!isset($aGroupedSearches[$aSearch->getRank()])) {
|
||||
$aGroupedSearches[$aSearch->getRank()] = array();
|
||||
}
|
||||
if (!isset($aGroupedSearches[$aSearch->getRank()])) $aGroupedSearches[$aSearch->getRank()] = array();
|
||||
$aGroupedSearches[$aSearch->getRank()][] = $aSearch;
|
||||
}
|
||||
}
|
||||
@@ -650,9 +728,7 @@ class Geocode
|
||||
$sHash = serialize($aSearch);
|
||||
if (isset($aSearchHash[$sHash])) {
|
||||
unset($aGroupedSearches[$iGroup][$iSearch]);
|
||||
if (empty($aGroupedSearches[$iGroup])) {
|
||||
unset($aGroupedSearches[$iGroup]);
|
||||
}
|
||||
if (empty($aGroupedSearches[$iGroup])) unset($aGroupedSearches[$iGroup]);
|
||||
} else {
|
||||
$aSearchHash[$sHash] = 1;
|
||||
}
|
||||
@@ -696,27 +772,20 @@ class Geocode
|
||||
}
|
||||
}
|
||||
|
||||
if ($iQueryLoop > 20) {
|
||||
break;
|
||||
}
|
||||
if ($iQueryLoop > 20) break;
|
||||
}
|
||||
|
||||
if (!empty($aResults)) {
|
||||
$aSplitResults = Result::splitResults($aResults);
|
||||
Debug::printVar('Split results', $aSplitResults);
|
||||
if ($iGroupLoop <= 4
|
||||
&& reset($aSplitResults['head'])->iResultRank > 0
|
||||
&& $iGroupedRank !== array_key_last($aGroupedSearches)) {
|
||||
if ($iGroupLoop <= 4 && empty($aSplitResults['tail'])
|
||||
&& reset($aSplitResults['head'])->iResultRank > 0) {
|
||||
// Haven't found an exact match for the query yet.
|
||||
// Therefore add result from the next group level.
|
||||
$aNextResults = $aSplitResults['head'];
|
||||
foreach ($aNextResults as $oRes) {
|
||||
$oRes->iResultRank--;
|
||||
}
|
||||
foreach ($aSplitResults['tail'] as $oRes) {
|
||||
$oRes->iResultRank--;
|
||||
$aNextResults[$oRes->iId] = $oRes;
|
||||
}
|
||||
$aResults = array();
|
||||
} else {
|
||||
$aResults = $aSplitResults['head'];
|
||||
@@ -764,6 +833,7 @@ class Geocode
|
||||
foreach ($aResults as $oResult) {
|
||||
if (($this->iMaxAddressRank == 30 &&
|
||||
($oResult->iTable == Result::TABLE_OSMLINE
|
||||
|| $oResult->iTable == Result::TABLE_AUX
|
||||
|| $oResult->iTable == Result::TABLE_TIGER))
|
||||
|| in_array($oResult->iId, $aFilteredIDs)
|
||||
) {
|
||||
@@ -773,9 +843,9 @@ class Geocode
|
||||
$aResults = $tempIDs;
|
||||
}
|
||||
|
||||
if (!empty($aResults) || $iGroupLoop > 4 || $iQueryLoop > 30) {
|
||||
break;
|
||||
}
|
||||
if (!empty($aResults)) break;
|
||||
if ($iGroupLoop > 4) break;
|
||||
if ($iQueryLoop > 30) break;
|
||||
}
|
||||
} else {
|
||||
// Just interpret as a reverse geocode
|
||||
@@ -793,8 +863,10 @@ class Geocode
|
||||
|
||||
// No results? Done
|
||||
if (empty($aResults)) {
|
||||
if ($this->bFallback && $this->fallbackStructuredQuery()) {
|
||||
return $this->lookup();
|
||||
if ($this->bFallback) {
|
||||
if ($this->fallbackStructuredQuery()) {
|
||||
return $this->lookup();
|
||||
}
|
||||
}
|
||||
|
||||
return array();
|
||||
@@ -813,9 +885,7 @@ class Geocode
|
||||
|
||||
$aRecheckWords = preg_split('/\b[\s,\\-]*/u', $sQuery);
|
||||
foreach ($aRecheckWords as $i => $sWord) {
|
||||
if (!preg_match('/[\pL\pN]/', $sWord)) {
|
||||
unset($aRecheckWords[$i]);
|
||||
}
|
||||
if (!preg_match('/[\pL\pN]/', $sWord)) unset($aRecheckWords[$i]);
|
||||
}
|
||||
|
||||
Debug::printVar('Recheck words', $aRecheckWords);
|
||||
@@ -875,9 +945,7 @@ class Geocode
|
||||
foreach ($aRecheckWords as $i => $sWord) {
|
||||
if (stripos($sAddress, $sWord)!==false) {
|
||||
$iCountWords++;
|
||||
if (preg_match('/(^|,)\s*'.preg_quote($sWord, '/').'\s*(,|$)/', $sAddress)) {
|
||||
$iCountWords += 0.1;
|
||||
}
|
||||
if (preg_match('/(^|,)\s*'.preg_quote($sWord, '/').'\s*(,|$)/', $sAddress)) $iCountWords += 0.1;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -894,8 +962,15 @@ class Geocode
|
||||
$aToFilter = $aSearchResults;
|
||||
$aSearchResults = array();
|
||||
|
||||
$bFirst = true;
|
||||
foreach ($aToFilter as $aResult) {
|
||||
$this->aExcludePlaceIDs[$aResult['place_id']] = $aResult['place_id'];
|
||||
if ($bFirst) {
|
||||
$fLat = $aResult['lat'];
|
||||
$fLon = $aResult['lon'];
|
||||
if (isset($aResult['zoom'])) $iZoom = $aResult['zoom'];
|
||||
$bFirst = false;
|
||||
}
|
||||
if (!$this->oPlaceLookup->doDeDupe() || (!isset($aOSMIDDone[$aResult['osm_type'].$aResult['osm_id']])
|
||||
&& !isset($aClassTypeNameDone[$aResult['osm_type'].$aResult['class'].$aResult['type'].$aResult['name'].$aResult['admin_level']]))
|
||||
) {
|
||||
@@ -905,9 +980,7 @@ class Geocode
|
||||
}
|
||||
|
||||
// Absolute limit on number of results
|
||||
if (count($aSearchResults) >= $this->iFinalLimit) {
|
||||
break;
|
||||
}
|
||||
if (count($aSearchResults) >= $this->iFinalLimit) break;
|
||||
}
|
||||
|
||||
Debug::printVar('Post-filter results', $aSearchResults);
|
||||
@@ -921,6 +994,7 @@ class Geocode
|
||||
'Structured query' => $this->aStructuredQuery,
|
||||
'Name keys' => Debug::fmtArrayVals($this->aLangPrefOrder),
|
||||
'Excluded place IDs' => Debug::fmtArrayVals($this->aExcludePlaceIDs),
|
||||
'Try reversed query'=> $this->bReverseInPlan,
|
||||
'Limit (for searches)' => $this->iLimit,
|
||||
'Limit (for results)'=> $this->iFinalLimit,
|
||||
'Country codes' => Debug::fmtArrayVals($this->aCountryCodes),
|
||||
@@ -90,16 +90,14 @@ class ParameterParser
|
||||
$aLanguages = array();
|
||||
$sLangString = $this->getString('accept-language', $sFallback);
|
||||
|
||||
if ($sLangString
|
||||
&& preg_match_all('/(([a-z]{1,8})([-_][a-z]{1,8})?)\s*(;\s*q\s*=\s*(1|0\.[0-9]+))?/i', $sLangString, $aLanguagesParse, PREG_SET_ORDER)
|
||||
) {
|
||||
foreach ($aLanguagesParse as $iLang => $aLanguage) {
|
||||
$aLanguages[$aLanguage[1]] = isset($aLanguage[5])?(float)$aLanguage[5]:1 - ($iLang/100);
|
||||
if (!isset($aLanguages[$aLanguage[2]])) {
|
||||
$aLanguages[$aLanguage[2]] = $aLanguages[$aLanguage[1]]/10;
|
||||
if ($sLangString) {
|
||||
if (preg_match_all('/(([a-z]{1,8})([-_][a-z]{1,8})?)\s*(;\s*q\s*=\s*(1|0\.[0-9]+))?/i', $sLangString, $aLanguagesParse, PREG_SET_ORDER)) {
|
||||
foreach ($aLanguagesParse as $iLang => $aLanguage) {
|
||||
$aLanguages[$aLanguage[1]] = isset($aLanguage[5])?(float)$aLanguage[5]:1 - ($iLang/100);
|
||||
if (!isset($aLanguages[$aLanguage[2]])) $aLanguages[$aLanguage[2]] = $aLanguages[$aLanguage[1]]/10;
|
||||
}
|
||||
arsort($aLanguages);
|
||||
}
|
||||
arsort($aLanguages);
|
||||
}
|
||||
if (empty($aLanguages) && CONST_Default_Language) {
|
||||
$aLanguages[CONST_Default_Language] = 1;
|
||||
@@ -16,6 +16,8 @@ class Phrase
|
||||
private $sPhrase;
|
||||
// Element type for structured searches.
|
||||
private $sPhraseType;
|
||||
// Space-separated words of the phrase.
|
||||
private $aWords;
|
||||
// Possible segmentations of the phrase.
|
||||
private $aWordSets;
|
||||
|
||||
@@ -36,14 +38,7 @@ class Phrase
|
||||
{
|
||||
$this->sPhrase = trim($sPhrase);
|
||||
$this->sPhraseType = $sPhraseType;
|
||||
}
|
||||
|
||||
/**
|
||||
* Get the orginal phrase of the string.
|
||||
*/
|
||||
public function getPhrase()
|
||||
{
|
||||
return $this->sPhrase;
|
||||
$this->aWords = explode(' ', $this->sPhrase);
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -68,6 +63,30 @@ class Phrase
|
||||
return $this->aWordSets;
|
||||
}
|
||||
|
||||
/**
|
||||
* Add the tokens from this phrase to the given list of tokens.
|
||||
*
|
||||
* @param string[] $aTokens List of tokens to append.
|
||||
*
|
||||
* @return void
|
||||
*/
|
||||
public function addTokens(&$aTokens)
|
||||
{
|
||||
$iNumWords = count($this->aWords);
|
||||
|
||||
for ($i = 0; $i < $iNumWords; $i++) {
|
||||
$sPhrase = $this->aWords[$i];
|
||||
$aTokens[' '.$sPhrase] = ' '.$sPhrase;
|
||||
$aTokens[$sPhrase] = $sPhrase;
|
||||
|
||||
for ($j = $i + 1; $j < $iNumWords; $j++) {
|
||||
$sPhrase .= ' '.$this->aWords[$j];
|
||||
$aTokens[' '.$sPhrase] = ' '.$sPhrase;
|
||||
$aTokens[$sPhrase] = $sPhrase;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Invert the set of possible segmentations.
|
||||
*
|
||||
@@ -80,27 +99,21 @@ class Phrase
|
||||
}
|
||||
}
|
||||
|
||||
public function computeWordSets($aWords, $oTokens)
|
||||
public function computeWordSets($oTokens)
|
||||
{
|
||||
$iNumWords = count($aWords);
|
||||
|
||||
if ($iNumWords == 0) {
|
||||
$this->aWordSets = null;
|
||||
return;
|
||||
}
|
||||
|
||||
$iNumWords = count($this->aWords);
|
||||
// Caches the word set for the partial phrase up to word i.
|
||||
$aSetCache = array_fill(0, $iNumWords, array());
|
||||
|
||||
// Initialise first element of cache. There can only be the word.
|
||||
if ($oTokens->containsAny($aWords[0])) {
|
||||
$aSetCache[0][] = array($aWords[0]);
|
||||
if ($oTokens->containsAny($this->aWords[0])) {
|
||||
$aSetCache[0][] = array($this->aWords[0]);
|
||||
}
|
||||
|
||||
// Now do the next elements using what we already have.
|
||||
for ($i = 1; $i < $iNumWords; $i++) {
|
||||
for ($j = $i; $j > 0; $j--) {
|
||||
$sPartial = $j == $i ? $aWords[$j] : $aWords[$j].' '.$sPartial;
|
||||
$sPartial = $j == $i ? $this->aWords[$j] : $this->aWords[$j].' '.$sPartial;
|
||||
if (!empty($aSetCache[$j - 1]) && $oTokens->containsAny($sPartial)) {
|
||||
$aPartial = array($sPartial);
|
||||
foreach ($aSetCache[$j - 1] as $aSet) {
|
||||
@@ -123,7 +136,7 @@ class Phrase
|
||||
}
|
||||
|
||||
// finally the current full phrase
|
||||
$sPartial = $aWords[0].' '.$sPartial;
|
||||
$sPartial = $this->aWords[0].' '.$sPartial;
|
||||
if ($oTokens->containsAny($sPartial)) {
|
||||
$aSetCache[$i][] = array($sPartial);
|
||||
}
|
||||
@@ -140,6 +153,7 @@ class Phrase
|
||||
return array(
|
||||
'Type' => $this->sPhraseType,
|
||||
'Phrase' => $this->sPhrase,
|
||||
'Words' => $this->aWords,
|
||||
'WordSets' => $this->aWordSets
|
||||
);
|
||||
}
|
||||
@@ -2,8 +2,8 @@
|
||||
|
||||
namespace Nominatim;
|
||||
|
||||
require_once(CONST_LibDir.'/AddressDetails.php');
|
||||
require_once(CONST_LibDir.'/Result.php');
|
||||
require_once(CONST_BasePath.'/lib/AddressDetails.php');
|
||||
require_once(CONST_BasePath.'/lib/Result.php');
|
||||
|
||||
class PlaceLookup
|
||||
{
|
||||
@@ -89,36 +89,20 @@ class PlaceLookup
|
||||
{
|
||||
$aParams = array();
|
||||
|
||||
if ($this->bAddressDetails) {
|
||||
$aParams['addressdetails'] = '1';
|
||||
}
|
||||
if ($this->bExtraTags) {
|
||||
$aParams['extratags'] = '1';
|
||||
}
|
||||
if ($this->bNameDetails) {
|
||||
$aParams['namedetails'] = '1';
|
||||
}
|
||||
if ($this->bAddressDetails) $aParams['addressdetails'] = '1';
|
||||
if ($this->bExtraTags) $aParams['extratags'] = '1';
|
||||
if ($this->bNameDetails) $aParams['namedetails'] = '1';
|
||||
|
||||
if ($this->bIncludePolygonAsText) {
|
||||
$aParams['polygon_text'] = '1';
|
||||
}
|
||||
if ($this->bIncludePolygonAsGeoJSON) {
|
||||
$aParams['polygon_geojson'] = '1';
|
||||
}
|
||||
if ($this->bIncludePolygonAsKML) {
|
||||
$aParams['polygon_kml'] = '1';
|
||||
}
|
||||
if ($this->bIncludePolygonAsSVG) {
|
||||
$aParams['polygon_svg'] = '1';
|
||||
}
|
||||
if ($this->bIncludePolygonAsText) $aParams['polygon_text'] = '1';
|
||||
if ($this->bIncludePolygonAsGeoJSON) $aParams['polygon_geojson'] = '1';
|
||||
if ($this->bIncludePolygonAsKML) $aParams['polygon_kml'] = '1';
|
||||
if ($this->bIncludePolygonAsSVG) $aParams['polygon_svg'] = '1';
|
||||
|
||||
if ($this->fPolygonSimplificationThreshold > 0.0) {
|
||||
$aParams['polygon_threshold'] = $this->fPolygonSimplificationThreshold;
|
||||
}
|
||||
|
||||
if (!$this->bDeDupe) {
|
||||
$aParams['dedupe'] = '0';
|
||||
}
|
||||
if (!$this->bDeDupe) $aParams['dedupe'] = '0';
|
||||
|
||||
return $aParams;
|
||||
}
|
||||
@@ -163,9 +147,8 @@ class PlaceLookup
|
||||
|
||||
private function langAddressSql($sHousenumber)
|
||||
{
|
||||
if ($this->bAddressDetails) {
|
||||
if ($this->bAddressDetails)
|
||||
return ''; // langaddress will be computed from address details
|
||||
}
|
||||
|
||||
return 'get_address_by_language(place_id,'.$sHousenumber.','.$this->aLangPrefOrderSql.') AS langaddress,';
|
||||
}
|
||||
@@ -251,20 +234,12 @@ class PlaceLookup
|
||||
$sSQL .= ' housenumber,';
|
||||
$sSQL .= ' country_code, ';
|
||||
$sSQL .= ' importance, ';
|
||||
if (!$this->bDeDupe) {
|
||||
$sSQL .= 'place_id,';
|
||||
}
|
||||
if (!$this->bAddressDetails) {
|
||||
$sSQL .= 'langaddress, ';
|
||||
}
|
||||
if (!$this->bDeDupe) $sSQL .= 'place_id,';
|
||||
if (!$this->bAddressDetails) $sSQL .= 'langaddress, ';
|
||||
$sSQL .= ' placename, ';
|
||||
$sSQL .= ' ref, ';
|
||||
if ($this->bExtraTags) {
|
||||
$sSQL .= 'extratags, ';
|
||||
}
|
||||
if ($this->bNameDetails) {
|
||||
$sSQL .= 'name, ';
|
||||
}
|
||||
if ($this->bExtraTags) $sSQL .= 'extratags, ';
|
||||
if ($this->bNameDetails) $sSQL .= 'name, ';
|
||||
$sSQL .= ' extra_place ';
|
||||
|
||||
$aSubSelects[] = $sSQL;
|
||||
@@ -285,12 +260,8 @@ class PlaceLookup
|
||||
$sSQL .= $this->langAddressSql('-1');
|
||||
$sSQL .= ' postcode as placename,';
|
||||
$sSQL .= ' postcode as ref,';
|
||||
if ($this->bExtraTags) {
|
||||
$sSQL .= 'null::text AS extra,';
|
||||
}
|
||||
if ($this->bNameDetails) {
|
||||
$sSQL .= 'null::text AS names,';
|
||||
}
|
||||
if ($this->bExtraTags) $sSQL .= 'null::text AS extra,';
|
||||
if ($this->bNameDetails) $sSQL .= 'null::text AS names,';
|
||||
$sSQL .= ' ST_x(geometry) AS lon, ST_y(geometry) AS lat,';
|
||||
$sSQL .= ' (0.75-(rank_search::float/40)) AS importance, ';
|
||||
$sSQL .= $this->addressImportanceSql('geometry', 'lp.parent_place_id');
|
||||
@@ -327,12 +298,8 @@ class PlaceLookup
|
||||
$sSQL .= $this->langAddressSql('housenumber_for_place');
|
||||
$sSQL .= ' null::text AS placename, ';
|
||||
$sSQL .= ' null::text AS ref, ';
|
||||
if ($this->bExtraTags) {
|
||||
$sSQL .= 'null::text AS extra,';
|
||||
}
|
||||
if ($this->bNameDetails) {
|
||||
$sSQL .= 'null::text AS names,';
|
||||
}
|
||||
if ($this->bExtraTags) $sSQL .= 'null::text AS extra,';
|
||||
if ($this->bNameDetails) $sSQL .= 'null::text AS names,';
|
||||
$sSQL .= ' st_x(centroid) AS lon, ';
|
||||
$sSQL .= ' st_y(centroid) AS lat,';
|
||||
$sSQL .= ' -1.15 AS importance, ';
|
||||
@@ -377,12 +344,8 @@ class PlaceLookup
|
||||
$sSQL .= $this->langAddressSql('housenumber_for_place');
|
||||
$sSQL .= ' null::text AS placename, ';
|
||||
$sSQL .= ' null::text AS ref, ';
|
||||
if ($this->bExtraTags) {
|
||||
$sSQL .= 'null::text AS extra, ';
|
||||
}
|
||||
if ($this->bNameDetails) {
|
||||
$sSQL .= 'null::text AS names, ';
|
||||
}
|
||||
if ($this->bExtraTags) $sSQL .= 'null::text AS extra, ';
|
||||
if ($this->bNameDetails) $sSQL .= 'null::text AS names, ';
|
||||
$sSQL .= ' st_x(centroid) AS lon, ';
|
||||
$sSQL .= ' st_y(centroid) AS lat, ';
|
||||
// slightly smaller than the importance for normal houses
|
||||
@@ -410,6 +373,42 @@ class PlaceLookup
|
||||
|
||||
$aSubSelects[] = $sSQL;
|
||||
}
|
||||
|
||||
if (CONST_Use_Aux_Location_data) {
|
||||
$sPlaceIDs = Result::joinIdsByTable($aResults, Result::TABLE_AUX);
|
||||
if ($sPlaceIDs) {
|
||||
$sHousenumbers = Result::sqlHouseNumberTable($aResults, Result::TABLE_AUX);
|
||||
$sSQL = ' SELECT ';
|
||||
$sSQL .= " 'L' AS osm_type, ";
|
||||
$sSQL .= ' place_id AS osm_id, ';
|
||||
$sSQL .= " 'place' AS class,";
|
||||
$sSQL .= " 'house' AS type, ";
|
||||
$sSQL .= ' null::smallint AS admin_level, ';
|
||||
$sSQL .= ' 30 AS rank_search,';
|
||||
$sSQL .= ' 30 AS rank_address, ';
|
||||
$sSQL .= ' place_id,';
|
||||
$sSQL .= ' parent_place_id, ';
|
||||
$sSQL .= ' housenumber,';
|
||||
$sSQL .= " 'us' AS country_code, ";
|
||||
$sSQL .= $this->langAddressSql('-1');
|
||||
$sSQL .= ' null::text AS placename, ';
|
||||
$sSQL .= ' null::text AS ref, ';
|
||||
if ($this->bExtraTags) $sSQL .= 'null::text AS extra, ';
|
||||
if ($this->bNameDetails) $sSQL .= 'null::text AS names, ';
|
||||
$sSQL .= ' ST_X(centroid) AS lon, ';
|
||||
$sSQL .= ' ST_Y(centroid) AS lat, ';
|
||||
$sSQL .= ' -1.10 AS importance, ';
|
||||
$sSQL .= $this->addressImportanceSql(
|
||||
'centroid',
|
||||
'location_property_aux.parent_place_id'
|
||||
);
|
||||
$sSQL .= ' null::text AS extra_place ';
|
||||
$sSQL .= ' FROM location_property_aux ';
|
||||
$sSQL .= " WHERE place_id in ($sPlaceIDs) ";
|
||||
|
||||
$aSubSelects[] = $sSQL;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (empty($aSubSelects)) {
|
||||
@@ -485,83 +484,67 @@ class PlaceLookup
|
||||
{
|
||||
|
||||
$aOutlineResult = array();
|
||||
if (!$iPlaceID) {
|
||||
return $aOutlineResult;
|
||||
}
|
||||
if (!$iPlaceID) return $aOutlineResult;
|
||||
|
||||
// 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_YMin(geometry) as minlat,ST_YMax(geometry) as maxlat,';
|
||||
$sSQL .= ' ST_XMin(geometry) as minlon,ST_XMax(geometry) as maxlon';
|
||||
if ($this->bIncludePolygonAsGeoJSON) {
|
||||
$sSQL .= ',ST_AsGeoJSON(geometry) as asgeojson';
|
||||
}
|
||||
if ($this->bIncludePolygonAsKML) {
|
||||
$sSQL .= ',ST_AsKML(geometry) as askml';
|
||||
}
|
||||
if ($this->bIncludePolygonAsSVG) {
|
||||
$sSQL .= ',ST_AsSVG(geometry) as assvg';
|
||||
}
|
||||
if ($this->bIncludePolygonAsText) {
|
||||
$sSQL .= ',ST_AsText(geometry) as astext';
|
||||
}
|
||||
if ($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';
|
||||
} else {
|
||||
$sFrom = ' from placex where place_id = '.$iPlaceID;
|
||||
}
|
||||
if ($this->fPolygonSimplificationThreshold > 0) {
|
||||
$sSQL .= ' from (select place_id,centroid,ST_SimplifyPreserveTopology(geometry,'.$this->fPolygonSimplificationThreshold.') as geometry'.$sFrom.') as plx';
|
||||
} else {
|
||||
$sSQL .= $sFrom;
|
||||
}
|
||||
|
||||
$aPointPolygon = $this->oDB->getRow($sSQL, null, 'Could not get outline');
|
||||
|
||||
if ($aPointPolygon && $aPointPolygon['place_id']) {
|
||||
if ($aPointPolygon['centrelon'] !== null && $aPointPolygon['centrelat'] !== null) {
|
||||
$aOutlineResult['lat'] = $aPointPolygon['centrelat'];
|
||||
$aOutlineResult['lon'] = $aPointPolygon['centrelon'];
|
||||
if (CONST_Search_AreaPolygons) {
|
||||
// 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_YMin(geometry) as minlat,ST_YMax(geometry) as maxlat,';
|
||||
$sSQL .= ' ST_XMin(geometry) as minlon,ST_XMax(geometry) as maxlon';
|
||||
if ($this->bIncludePolygonAsGeoJSON) $sSQL .= ',ST_AsGeoJSON(geometry) as asgeojson';
|
||||
if ($this->bIncludePolygonAsKML) $sSQL .= ',ST_AsKML(geometry) as askml';
|
||||
if ($this->bIncludePolygonAsSVG) $sSQL .= ',ST_AsSVG(geometry) as assvg';
|
||||
if ($this->bIncludePolygonAsText) $sSQL .= ',ST_AsText(geometry) as astext';
|
||||
if ($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';
|
||||
} else {
|
||||
$sFrom = ' from placex where place_id = '.$iPlaceID;
|
||||
}
|
||||
if ($this->fPolygonSimplificationThreshold > 0) {
|
||||
$sSQL .= ' from (select place_id,centroid,ST_SimplifyPreserveTopology(geometry,'.$this->fPolygonSimplificationThreshold.') as geometry'.$sFrom.') as plx';
|
||||
} else {
|
||||
$sSQL .= $sFrom;
|
||||
}
|
||||
|
||||
if ($this->bIncludePolygonAsGeoJSON) {
|
||||
$aOutlineResult['asgeojson'] = $aPointPolygon['asgeojson'];
|
||||
}
|
||||
if ($this->bIncludePolygonAsKML) {
|
||||
$aOutlineResult['askml'] = $aPointPolygon['askml'];
|
||||
}
|
||||
if ($this->bIncludePolygonAsSVG) {
|
||||
$aOutlineResult['assvg'] = $aPointPolygon['assvg'];
|
||||
}
|
||||
if ($this->bIncludePolygonAsText) {
|
||||
$aOutlineResult['astext'] = $aPointPolygon['astext'];
|
||||
}
|
||||
$aPointPolygon = $this->oDB->getRow($sSQL, null, 'Could not get outline');
|
||||
|
||||
if (abs($aPointPolygon['minlat'] - $aPointPolygon['maxlat']) < 0.0000001) {
|
||||
$aPointPolygon['minlat'] = $aPointPolygon['minlat'] - $fRadius;
|
||||
$aPointPolygon['maxlat'] = $aPointPolygon['maxlat'] + $fRadius;
|
||||
}
|
||||
if ($aPointPolygon && $aPointPolygon['place_id']) {
|
||||
if ($aPointPolygon['centrelon'] !== null && $aPointPolygon['centrelat'] !== null) {
|
||||
$aOutlineResult['lat'] = $aPointPolygon['centrelat'];
|
||||
$aOutlineResult['lon'] = $aPointPolygon['centrelon'];
|
||||
}
|
||||
|
||||
if (abs($aPointPolygon['minlon'] - $aPointPolygon['maxlon']) < 0.0000001) {
|
||||
$aPointPolygon['minlon'] = $aPointPolygon['minlon'] - $fRadius;
|
||||
$aPointPolygon['maxlon'] = $aPointPolygon['maxlon'] + $fRadius;
|
||||
}
|
||||
if ($this->bIncludePolygonAsGeoJSON) $aOutlineResult['asgeojson'] = $aPointPolygon['asgeojson'];
|
||||
if ($this->bIncludePolygonAsKML) $aOutlineResult['askml'] = $aPointPolygon['askml'];
|
||||
if ($this->bIncludePolygonAsSVG) $aOutlineResult['assvg'] = $aPointPolygon['assvg'];
|
||||
if ($this->bIncludePolygonAsText) $aOutlineResult['astext'] = $aPointPolygon['astext'];
|
||||
|
||||
$aOutlineResult['aBoundingBox'] = array(
|
||||
(string)$aPointPolygon['minlat'],
|
||||
(string)$aPointPolygon['maxlat'],
|
||||
(string)$aPointPolygon['minlon'],
|
||||
(string)$aPointPolygon['maxlon']
|
||||
);
|
||||
if (abs($aPointPolygon['minlat'] - $aPointPolygon['maxlat']) < 0.0000001) {
|
||||
$aPointPolygon['minlat'] = $aPointPolygon['minlat'] - $fRadius;
|
||||
$aPointPolygon['maxlat'] = $aPointPolygon['maxlat'] + $fRadius;
|
||||
}
|
||||
|
||||
if (abs($aPointPolygon['minlon'] - $aPointPolygon['maxlon']) < 0.0000001) {
|
||||
$aPointPolygon['minlon'] = $aPointPolygon['minlon'] - $fRadius;
|
||||
$aPointPolygon['maxlon'] = $aPointPolygon['maxlon'] + $fRadius;
|
||||
}
|
||||
|
||||
$aOutlineResult['aBoundingBox'] = array(
|
||||
(string)$aPointPolygon['minlat'],
|
||||
(string)$aPointPolygon['maxlat'],
|
||||
(string)$aPointPolygon['minlon'],
|
||||
(string)$aPointPolygon['maxlon']
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
// as a fallback we generate a bounding box without knowing the size of the geometry
|
||||
@@ -13,7 +13,8 @@ class Result
|
||||
const TABLE_PLACEX = 0;
|
||||
const TABLE_POSTCODE = 1;
|
||||
const TABLE_OSMLINE = 2;
|
||||
const TABLE_TIGER = 3;
|
||||
const TABLE_AUX = 3;
|
||||
const TABLE_TIGER = 4;
|
||||
|
||||
/// Database table that contains the result.
|
||||
public $iTable;
|
||||
@@ -25,8 +26,6 @@ class Result
|
||||
public $iExactMatches = 0;
|
||||
/// Subranking within the results (the higher the worse).
|
||||
public $iResultRank = 0;
|
||||
/// Address rank of the result.
|
||||
public $iAddressRank;
|
||||
|
||||
public function debugInfo()
|
||||
{
|
||||
@@ -55,27 +54,6 @@ class Result
|
||||
}
|
||||
)));
|
||||
}
|
||||
|
||||
public static function joinIdsByTableMinRank($aResults, $iTable, $iMinAddressRank)
|
||||
{
|
||||
return join(',', array_keys(array_filter(
|
||||
$aResults,
|
||||
function ($aValue) use ($iTable, $iMinAddressRank) {
|
||||
return $aValue->iTable == $iTable && $aValue->iAddressRank >= $iMinAddressRank;
|
||||
}
|
||||
)));
|
||||
}
|
||||
|
||||
public static function joinIdsByTableMaxRank($aResults, $iTable, $iMaxAddressRank)
|
||||
{
|
||||
return join(',', array_keys(array_filter(
|
||||
$aResults,
|
||||
function ($aValue) use ($iTable, $iMaxAddressRank) {
|
||||
return $aValue->iTable == $iTable && $aValue->iAddressRank <= $iMaxAddressRank;
|
||||
}
|
||||
)));
|
||||
}
|
||||
|
||||
public static function sqlHouseNumberTable($aResults, $iTable)
|
||||
{
|
||||
$sHousenumbers = '';
|
||||
@@ -106,7 +84,7 @@ class Result
|
||||
|
||||
foreach ($aResults as $oRes) {
|
||||
if ($oRes->iResultRank < $iMinRank) {
|
||||
$aTail += $aHead;
|
||||
$aTail = array_merge($aTail, $aHead);
|
||||
$aHead = array($oRes->iId => $oRes);
|
||||
$iMinRank = $oRes->iResultRank;
|
||||
} elseif ($oRes->iResultRank == $iMinRank) {
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
namespace Nominatim;
|
||||
|
||||
require_once(CONST_LibDir.'/Result.php');
|
||||
require_once(CONST_BasePath.'/lib/Result.php');
|
||||
|
||||
class ReverseGeocode
|
||||
{
|
||||
@@ -74,6 +74,8 @@ class ReverseGeocode
|
||||
|
||||
protected function lookupLargeArea($sPointSQL, $iMaxRank)
|
||||
{
|
||||
$oResult = null;
|
||||
|
||||
if ($iMaxRank > 4) {
|
||||
$aPlace = $this->lookupPolygon($sPointSQL, $iMaxRank);
|
||||
if ($aPlace) {
|
||||
@@ -165,13 +167,9 @@ class ReverseGeocode
|
||||
{
|
||||
Debug::newFunction('lookupPolygon');
|
||||
// polygon search begins at suburb-level
|
||||
if ($iMaxRank > 25) {
|
||||
$iMaxRank = 25;
|
||||
}
|
||||
if ($iMaxRank > 25) $iMaxRank = 25;
|
||||
// no polygon search over country-level
|
||||
if ($iMaxRank < 5) {
|
||||
$iMaxRank = 5;
|
||||
}
|
||||
if ($iMaxRank < 5) $iMaxRank = 5;
|
||||
// search for polygon
|
||||
$sSQL = 'SELECT place_id, parent_place_id, rank_address, rank_search FROM';
|
||||
$sSQL .= '(select place_id, parent_place_id, rank_address, rank_search, country_code, geometry';
|
||||
@@ -192,6 +190,7 @@ class ReverseGeocode
|
||||
|
||||
if ($aPoly) {
|
||||
// if a polygon is found, search for placenodes begins ...
|
||||
$iParentPlaceID = $aPoly['parent_place_id'];
|
||||
$iRankAddress = $aPoly['rank_address'];
|
||||
$iRankSearch = $aPoly['rank_search'];
|
||||
$iPlaceID = $aPoly['place_id'];
|
||||
@@ -243,24 +242,26 @@ class ReverseGeocode
|
||||
public function lookupPoint($sPointSQL, $bDoInterpolation = true)
|
||||
{
|
||||
Debug::newFunction('lookupPoint');
|
||||
// starts if the search is on POI or street level,
|
||||
// searches for the nearest POI or street,
|
||||
// if a street is found and a POI is searched for,
|
||||
// the nearest POI which the found street is a parent of is choosen.
|
||||
$iMaxRank = $this->iMaxRank;
|
||||
|
||||
// Find the nearest point
|
||||
$fSearchDiam = 0.006;
|
||||
$oResult = null;
|
||||
$aPlace = null;
|
||||
|
||||
// for POI or street level
|
||||
if ($this->iMaxRank >= 26) {
|
||||
// starts if the search is on POI or street level,
|
||||
// searches for the nearest POI or street,
|
||||
// if a street is found and a POI is searched for,
|
||||
// the nearest POI which the found street is a parent of is choosen.
|
||||
if ($iMaxRank >= 26) {
|
||||
$sSQL = 'select place_id,parent_place_id,rank_address,country_code,';
|
||||
$sSQL .= ' ST_distance('.$sPointSQL.', geometry) as distance';
|
||||
$sSQL .= ' FROM ';
|
||||
$sSQL .= ' placex';
|
||||
$sSQL .= ' WHERE ST_DWithin('.$sPointSQL.', geometry, '.$fSearchDiam.')';
|
||||
$sSQL .= ' AND';
|
||||
$sSQL .= ' rank_address between 26 and '.$this->iMaxRank;
|
||||
$sSQL .= ' rank_address between 26 and '.$iMaxRank;
|
||||
$sSQL .= ' and (name is not null or housenumber is not null';
|
||||
$sSQL .= ' or rank_address between 26 and 27)';
|
||||
$sSQL .= ' and (rank_address between 26 and 27';
|
||||
@@ -279,11 +280,34 @@ class ReverseGeocode
|
||||
$iPlaceID = $aPlace['place_id'];
|
||||
$oResult = new Result($iPlaceID);
|
||||
$iRankAddress = $aPlace['rank_address'];
|
||||
$iParentPlaceID = $aPlace['parent_place_id'];
|
||||
}
|
||||
|
||||
if ($bDoInterpolation && $iMaxRank >= 30) {
|
||||
$fDistance = $fSearchDiam;
|
||||
if ($aPlace) {
|
||||
// We can't reliably go from the closest street to an
|
||||
// interpolation line because the closest interpolation
|
||||
// may have a different street segments as a parent.
|
||||
// Therefore allow an interpolation line to take precendence
|
||||
// even when the street is closer.
|
||||
$fDistance = $iRankAddress < 28 ? 0.001 : $aPlace['distance'];
|
||||
}
|
||||
|
||||
$aHouse = $this->lookupInterpolation($sPointSQL, $fDistance);
|
||||
Debug::printVar('Interpolation result', $aPlace);
|
||||
|
||||
if ($aHouse) {
|
||||
$oResult = new Result($aHouse['place_id'], Result::TABLE_OSMLINE);
|
||||
$oResult->iHouseNumber = closestHouseNumber($aHouse);
|
||||
$aPlace = $aHouse;
|
||||
$iRankAddress = 30;
|
||||
}
|
||||
}
|
||||
|
||||
if ($aPlace) {
|
||||
// if street and maxrank > streetlevel
|
||||
if ($iRankAddress <= 27 && $this->iMaxRank > 27) {
|
||||
if ($iRankAddress <= 27 && $iMaxRank > 27) {
|
||||
// find the closest object (up to a certain radius) of which the street is a parent of
|
||||
$sSQL = ' select place_id,';
|
||||
$sSQL .= ' ST_distance('.$sPointSQL.', geometry) as distance';
|
||||
@@ -304,9 +328,7 @@ class ReverseGeocode
|
||||
Debug::printVar('Closest POI result', $aStreet);
|
||||
|
||||
if ($aStreet) {
|
||||
$aPlace = $aStreet;
|
||||
$oResult = new Result($aStreet['place_id']);
|
||||
$iRankAddress = 30;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -329,42 +351,17 @@ class ReverseGeocode
|
||||
Debug::printVar('Tiger house number result', $aPlaceTiger);
|
||||
|
||||
if ($aPlaceTiger) {
|
||||
$aPlace = $aPlaceTiger;
|
||||
$oResult = new Result($aPlaceTiger['place_id'], Result::TABLE_TIGER);
|
||||
$oResult->iHouseNumber = closestHouseNumber($aPlaceTiger);
|
||||
$iRankAddress = 30;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if ($bDoInterpolation && $this->iMaxRank >= 30) {
|
||||
$fDistance = $fSearchDiam;
|
||||
if ($aPlace) {
|
||||
// We can't reliably go from the closest street to an
|
||||
// interpolation line because the closest interpolation
|
||||
// may have a different street segments as a parent.
|
||||
// Therefore allow an interpolation line to take precendence
|
||||
// even when the street is closer.
|
||||
$fDistance = $iRankAddress < 28 ? 0.001 : $aPlace['distance'];
|
||||
}
|
||||
|
||||
$aHouse = $this->lookupInterpolation($sPointSQL, $fDistance);
|
||||
Debug::printVar('Interpolation result', $aPlace);
|
||||
|
||||
if ($aHouse) {
|
||||
$oResult = new Result($aHouse['place_id'], Result::TABLE_OSMLINE);
|
||||
$oResult->iHouseNumber = closestHouseNumber($aHouse);
|
||||
$aPlace = $aHouse;
|
||||
}
|
||||
}
|
||||
|
||||
if (!$aPlace) {
|
||||
} else {
|
||||
// if no POI or street is found ...
|
||||
$oResult = $this->lookupLargeArea($sPointSQL, 25);
|
||||
}
|
||||
} else {
|
||||
// lower than street level ($iMaxRank < 26 )
|
||||
$oResult = $this->lookupLargeArea($sPointSQL, $this->iMaxRank);
|
||||
$oResult = $this->lookupLargeArea($sPointSQL, $iMaxRank);
|
||||
}
|
||||
|
||||
Debug::printVar('Final result', $oResult);
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
namespace Nominatim;
|
||||
|
||||
require_once(CONST_LibDir.'/lib.php');
|
||||
require_once(CONST_BasePath.'/lib/lib.php');
|
||||
|
||||
|
||||
/**
|
||||
@@ -2,9 +2,9 @@
|
||||
|
||||
namespace Nominatim;
|
||||
|
||||
require_once(CONST_LibDir.'/SpecialSearchOperator.php');
|
||||
require_once(CONST_LibDir.'/SearchContext.php');
|
||||
require_once(CONST_LibDir.'/Result.php');
|
||||
require_once(CONST_BasePath.'/lib/SpecialSearchOperator.php');
|
||||
require_once(CONST_BasePath.'/lib/SearchContext.php');
|
||||
require_once(CONST_BasePath.'/lib/Result.php');
|
||||
|
||||
/**
|
||||
* Description of a single interpretation of a search query.
|
||||
@@ -67,6 +67,47 @@ class SearchDescription
|
||||
return $this->iSearchRank;
|
||||
}
|
||||
|
||||
/**
|
||||
* Make this search a POI search.
|
||||
*
|
||||
* In a POI search, objects are not (only) searched by their name
|
||||
* but also by the primary OSM key/value pair (class and type in Nominatim).
|
||||
*
|
||||
* @param integer $iOperator Type of POI search
|
||||
* @param string $sClass Class (or OSM tag key) of POI.
|
||||
* @param string $sType Type (or OSM tag value) of POI.
|
||||
*
|
||||
* @return void
|
||||
*/
|
||||
public function setPoiSearch($iOperator, $sClass, $sType)
|
||||
{
|
||||
$this->iOperator = $iOperator;
|
||||
$this->sClass = $sClass;
|
||||
$this->sType = $sType;
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if this might be a full address search.
|
||||
*
|
||||
* @return bool True if the search contains name, address and housenumber.
|
||||
*/
|
||||
public function looksLikeFullAddress()
|
||||
{
|
||||
return (!empty($this->aName))
|
||||
&& (!empty($this->aAddress) || $this->sCountryCode)
|
||||
&& preg_match('/[0-9]+/', $this->sHouseNumber);
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if any operator is set.
|
||||
*
|
||||
* @return bool True, if this is a special search operation.
|
||||
*/
|
||||
public function hasOperator()
|
||||
{
|
||||
return $this->iOperator != Operator::NONE;
|
||||
}
|
||||
|
||||
/**
|
||||
* Extract key/value pairs from a query.
|
||||
*
|
||||
@@ -119,234 +160,252 @@ class SearchDescription
|
||||
|
||||
/////////// Search building functions
|
||||
|
||||
/**
|
||||
* Create a copy of this search description adding to search rank.
|
||||
*
|
||||
* @param integer $iTermCost Cost to add to the current search rank.
|
||||
*
|
||||
* @return object Cloned search description.
|
||||
*/
|
||||
public function clone($iTermCost)
|
||||
{
|
||||
$oSearch = clone $this;
|
||||
$oSearch->iSearchRank += $iTermCost;
|
||||
|
||||
return $oSearch;
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if the search currently includes a name.
|
||||
* Derive new searches by adding a full term to the existing search.
|
||||
*
|
||||
* @param bool bIncludeNonNames If true stop-word tokens are taken into
|
||||
* account, too.
|
||||
* @param object $oSearchTerm Description of the token.
|
||||
* @param bool $bHasPartial True if there are also tokens of partial terms
|
||||
* with the same name.
|
||||
* @param string $sPhraseType Type of phrase the token is contained in.
|
||||
* @param bool $bFirstToken True if the token is at the beginning of the
|
||||
* query.
|
||||
* @param bool $bFirstPhrase True if the token is in the first phrase of
|
||||
* the query.
|
||||
* @param bool $bLastToken True if the token is at the end of the query.
|
||||
*
|
||||
* @return bool True, if search has a name.
|
||||
* @return SearchDescription[] List of derived search descriptions.
|
||||
*/
|
||||
public function hasName($bIncludeNonNames = false)
|
||||
public function extendWithFullTerm($oSearchTerm, $bHasPartial, $sPhraseType, $bFirstToken, $bFirstPhrase, $bLastToken)
|
||||
{
|
||||
return !empty($this->aName)
|
||||
|| (!empty($this->aNameNonSearch) && $bIncludeNonNames);
|
||||
}
|
||||
$aNewSearches = array();
|
||||
|
||||
/**
|
||||
* Check if the search currently includes an address term.
|
||||
*
|
||||
* @return bool True, if any address term is included, including stop-word
|
||||
* terms.
|
||||
*/
|
||||
public function hasAddress()
|
||||
{
|
||||
return !empty($this->aAddress) || !empty($this->aAddressNonSearch);
|
||||
}
|
||||
if (($sPhraseType == '' || $sPhraseType == 'country')
|
||||
&& is_a($oSearchTerm, '\Nominatim\Token\Country')
|
||||
) {
|
||||
if (!$this->sCountryCode) {
|
||||
$oSearch = clone $this;
|
||||
$oSearch->iSearchRank++;
|
||||
$oSearch->sCountryCode = $oSearchTerm->sCountryCode;
|
||||
// Country is almost always at the end of the string
|
||||
// - increase score for finding it anywhere else (optimisation)
|
||||
if (!$bLastToken) {
|
||||
$oSearch->iSearchRank += 5;
|
||||
}
|
||||
$aNewSearches[] = $oSearch;
|
||||
}
|
||||
} elseif (($sPhraseType == '' || $sPhraseType == 'postalcode')
|
||||
&& is_a($oSearchTerm, '\Nominatim\Token\Postcode')
|
||||
) {
|
||||
if (!$this->sPostcode) {
|
||||
// If we have structured search or this is the first term,
|
||||
// make the postcode the primary search element.
|
||||
if ($this->iOperator == Operator::NONE && $bFirstToken) {
|
||||
$oSearch = clone $this;
|
||||
$oSearch->iSearchRank++;
|
||||
$oSearch->iOperator = Operator::POSTCODE;
|
||||
$oSearch->aAddress = array_merge($this->aAddress, $this->aName);
|
||||
$oSearch->aName =
|
||||
array($oSearchTerm->iId => $oSearchTerm->sPostcode);
|
||||
$aNewSearches[] = $oSearch;
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if a country restriction is currently included in the search.
|
||||
*
|
||||
* @return bool True, if a country restriction is set.
|
||||
*/
|
||||
public function hasCountry()
|
||||
{
|
||||
return $this->sCountryCode !== '';
|
||||
}
|
||||
// If we have a structured search or this is not the first term,
|
||||
// add the postcode as an addendum.
|
||||
if ($this->iOperator != Operator::POSTCODE
|
||||
&& ($sPhraseType == 'postalcode' || !empty($this->aName))
|
||||
) {
|
||||
$oSearch = clone $this;
|
||||
$oSearch->iSearchRank++;
|
||||
if (strlen($oSearchTerm->sPostcode) < 4) {
|
||||
$oSearch->iSearchRank += 4 - strlen($oSearchTerm->sPostcode);
|
||||
}
|
||||
$oSearch->sPostcode = $oSearchTerm->sPostcode;
|
||||
$aNewSearches[] = $oSearch;
|
||||
}
|
||||
}
|
||||
} elseif (($sPhraseType == '' || $sPhraseType == 'street')
|
||||
&& is_a($oSearchTerm, '\Nominatim\Token\HouseNumber')
|
||||
) {
|
||||
if (!$this->sHouseNumber && $this->iOperator != Operator::POSTCODE) {
|
||||
$oSearch = clone $this;
|
||||
$oSearch->iSearchRank++;
|
||||
$oSearch->sHouseNumber = $oSearchTerm->sToken;
|
||||
// sanity check: if the housenumber is not mainly made
|
||||
// up of numbers, add a penalty
|
||||
if (preg_match('/\\d/', $oSearch->sHouseNumber) === 0
|
||||
|| preg_match_all('/[^0-9]/', $oSearch->sHouseNumber, $aMatches) > 2) {
|
||||
$oSearch->iSearchRank++;
|
||||
}
|
||||
if (empty($oSearchTerm->iId)) {
|
||||
$oSearch->iSearchRank++;
|
||||
}
|
||||
// also must not appear in the middle of the address
|
||||
if (!empty($this->aAddress)
|
||||
|| (!empty($this->aAddressNonSearch))
|
||||
|| $this->sPostcode
|
||||
) {
|
||||
$oSearch->iSearchRank++;
|
||||
}
|
||||
$aNewSearches[] = $oSearch;
|
||||
// Housenumbers may appear in the name when the place has its own
|
||||
// address terms.
|
||||
if ($oSearchTerm->iId !== null
|
||||
&& ($this->iNamePhrase >= 0 || empty($this->aName))
|
||||
&& empty($this->aAddress)
|
||||
) {
|
||||
$oSearch = clone $this;
|
||||
$oSearch->iSearchRank++;
|
||||
$oSearch->aAddress = $this->aName;
|
||||
$oSearch->bRareName = false;
|
||||
$oSearch->aName = array($oSearchTerm->iId => $oSearchTerm->iId);
|
||||
$aNewSearches[] = $oSearch;
|
||||
}
|
||||
}
|
||||
} elseif ($sPhraseType == ''
|
||||
&& is_a($oSearchTerm, '\Nominatim\Token\SpecialTerm')
|
||||
) {
|
||||
if ($this->iOperator == Operator::NONE) {
|
||||
$oSearch = clone $this;
|
||||
$oSearch->iSearchRank++;
|
||||
|
||||
/**
|
||||
* Check if a postcode is currently included in the search.
|
||||
*
|
||||
* @return bool True, if a postcode is set.
|
||||
*/
|
||||
public function hasPostcode()
|
||||
{
|
||||
return $this->sPostcode !== '';
|
||||
}
|
||||
$iOp = $oSearchTerm->iOperator;
|
||||
if ($iOp == Operator::NONE) {
|
||||
if (!empty($this->aName) || $this->oContext->isBoundedSearch()) {
|
||||
$iOp = Operator::NAME;
|
||||
} else {
|
||||
$iOp = Operator::NEAR;
|
||||
}
|
||||
$oSearch->iSearchRank += 2;
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if a house number is set for the search.
|
||||
*
|
||||
* @return bool True, if a house number is set.
|
||||
*/
|
||||
public function hasHousenumber()
|
||||
{
|
||||
return $this->sHouseNumber !== '';
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if a special type of place is requested.
|
||||
*
|
||||
* param integer iOperator When set, check for the particular
|
||||
* operator used for the special type.
|
||||
*
|
||||
* @return bool True, if speial type is requested or, if requested,
|
||||
* a special type with the given operator.
|
||||
*/
|
||||
public function hasOperator($iOperator = null)
|
||||
{
|
||||
return $iOperator === null ? $this->iOperator != Operator::NONE : $this->iOperator == $iOperator;
|
||||
}
|
||||
|
||||
/**
|
||||
* Add the given token to the list of terms to search for in the address.
|
||||
*
|
||||
* @param integer iID ID of term to add.
|
||||
* @param bool bSearchable Term should be used to search for result
|
||||
* (i.e. term is not a stop word).
|
||||
*/
|
||||
public function addAddressToken($iId, $bSearchable = true)
|
||||
{
|
||||
if ($bSearchable) {
|
||||
$this->aAddress[$iId] = $iId;
|
||||
} else {
|
||||
$this->aAddressNonSearch[$iId] = $iId;
|
||||
$oSearch->setPoiSearch(
|
||||
$iOp,
|
||||
$oSearchTerm->sClass,
|
||||
$oSearchTerm->sType
|
||||
);
|
||||
$aNewSearches[] = $oSearch;
|
||||
}
|
||||
} elseif ($sPhraseType != 'country'
|
||||
&& is_a($oSearchTerm, '\Nominatim\Token\Word')
|
||||
) {
|
||||
$iWordID = $oSearchTerm->iId;
|
||||
// Full words can only be a name if they appear at the beginning
|
||||
// of the phrase. In structured search the name must forcably in
|
||||
// the first phrase. In unstructured search it may be in a later
|
||||
// phrase when the first phrase is a house number.
|
||||
if (!empty($this->aName) || !($bFirstPhrase || $sPhraseType == '')) {
|
||||
if (($sPhraseType == '' || !$bFirstPhrase) && !$bHasPartial) {
|
||||
$oSearch = clone $this;
|
||||
$oSearch->iSearchRank += 3 * $oSearchTerm->iTermCount;
|
||||
$oSearch->aAddress[$iWordID] = $iWordID;
|
||||
$aNewSearches[] = $oSearch;
|
||||
}
|
||||
} else {
|
||||
$oSearch = clone $this;
|
||||
$oSearch->iSearchRank++;
|
||||
$oSearch->aName = array($iWordID => $iWordID);
|
||||
if (CONST_Search_NameOnlySearchFrequencyThreshold) {
|
||||
$oSearch->bRareName =
|
||||
$oSearchTerm->iSearchNameCount
|
||||
< CONST_Search_NameOnlySearchFrequencyThreshold;
|
||||
}
|
||||
$aNewSearches[] = $oSearch;
|
||||
}
|
||||
}
|
||||
|
||||
return $aNewSearches;
|
||||
}
|
||||
|
||||
/**
|
||||
* Add the given full-word token to the list of terms to search for in the
|
||||
* name.
|
||||
* Derive new searches by adding a partial term to the existing search.
|
||||
*
|
||||
* @param interger iId ID of term to add.
|
||||
* @param bool bRareName True if the term is infrequent enough to not
|
||||
* require other constraints for efficient search.
|
||||
*/
|
||||
public function addNameToken($iId, $bRareName)
|
||||
{
|
||||
$this->aName[$iId] = $iId;
|
||||
$this->bRareName = $bRareName;
|
||||
}
|
||||
|
||||
/**
|
||||
* Add the given partial token to the list of terms to search for in
|
||||
* the name.
|
||||
* @param string $sToken Term for the token.
|
||||
* @param object $oSearchTerm Description of the token.
|
||||
* @param bool $bStructuredPhrases True if the search is structured.
|
||||
* @param integer $iPhrase Number of the phrase the token is in.
|
||||
* @param array[] $aFullTokens List of full term tokens with the
|
||||
* same name.
|
||||
*
|
||||
* @param integer iID ID of term to add.
|
||||
* @param bool bSearchable Term should be used to search for result
|
||||
* (i.e. term is not a stop word).
|
||||
* @param integer iPhraseNumber Index of phrase, where the partial term
|
||||
* appears.
|
||||
* @return SearchDescription[] List of derived search descriptions.
|
||||
*/
|
||||
public function addPartialNameToken($iId, $bSearchable, $iPhraseNumber)
|
||||
public function extendWithPartialTerm($sToken, $oSearchTerm, $bStructuredPhrases, $iPhrase, $aFullTokens)
|
||||
{
|
||||
if ($bSearchable) {
|
||||
$this->aName[$iId] = $iId;
|
||||
} else {
|
||||
$this->aNameNonSearch[$iId] = $iId;
|
||||
// Only allow name terms.
|
||||
if (!(is_a($oSearchTerm, '\Nominatim\Token\Word'))) {
|
||||
return array();
|
||||
}
|
||||
$this->iNamePhrase = $iPhraseNumber;
|
||||
}
|
||||
|
||||
/**
|
||||
* Set country restriction for the search.
|
||||
*
|
||||
* @param string sCountryCode Country code of country to restrict search to.
|
||||
*/
|
||||
public function setCountry($sCountryCode)
|
||||
{
|
||||
$this->sCountryCode = $sCountryCode;
|
||||
$this->iNamePhrase = -1;
|
||||
}
|
||||
$aNewSearches = array();
|
||||
$iWordID = $oSearchTerm->iId;
|
||||
|
||||
/**
|
||||
* Set postcode search constraint.
|
||||
*
|
||||
* @param string sPostcode Postcode the result should have.
|
||||
*/
|
||||
public function setPostcode($sPostcode)
|
||||
{
|
||||
$this->sPostcode = $sPostcode;
|
||||
$this->iNamePhrase = -1;
|
||||
}
|
||||
if ((!$bStructuredPhrases || $iPhrase > 0)
|
||||
&& (!empty($this->aName))
|
||||
&& strpos($sToken, ' ') === false
|
||||
) {
|
||||
if ($oSearchTerm->iSearchNameCount < CONST_Max_Word_Frequency) {
|
||||
$oSearch = clone $this;
|
||||
$oSearch->iSearchRank += $oSearchTerm->iTermCount + 1;
|
||||
if (empty($this->aName)) {
|
||||
$oSearch->iSearchRank++;
|
||||
}
|
||||
if (preg_match('#^[0-9]+$#', $sToken)) {
|
||||
$oSearch->iSearchRank++;
|
||||
}
|
||||
$oSearch->aAddress[$iWordID] = $iWordID;
|
||||
$aNewSearches[] = $oSearch;
|
||||
} else {
|
||||
$oSearch = clone $this;
|
||||
$oSearch->iSearchRank += $oSearchTerm->iTermCount + 1;
|
||||
$oSearch->aAddressNonSearch[$iWordID] = $iWordID;
|
||||
if (!empty($aFullTokens)) {
|
||||
$oSearch->iSearchRank++;
|
||||
}
|
||||
$aNewSearches[] = $oSearch;
|
||||
|
||||
/**
|
||||
* Make this search a search for a postcode object.
|
||||
*
|
||||
* @param integer iId Token Id for the postcode.
|
||||
* @param string sPostcode Postcode to look for.
|
||||
*/
|
||||
public function setPostcodeAsName($iId, $sPostcode)
|
||||
{
|
||||
$this->iOperator = Operator::POSTCODE;
|
||||
$this->aAddress = array_merge($this->aAddress, $this->aName);
|
||||
$this->aName = array($iId => $sPostcode);
|
||||
$this->bRareName = true;
|
||||
$this->iNamePhrase = -1;
|
||||
}
|
||||
// revert to the token version?
|
||||
foreach ($aFullTokens as $oSearchTermToken) {
|
||||
if (is_a($oSearchTermToken, '\Nominatim\Token\Word')) {
|
||||
$oSearch = clone $this;
|
||||
$oSearch->iSearchRank += 3;
|
||||
$oSearch->aAddress[$oSearchTermToken->iId]
|
||||
= $oSearchTermToken->iId;
|
||||
$aNewSearches[] = $oSearch;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Set house number search cnstraint.
|
||||
*
|
||||
* @param string sNumber House number the result should have.
|
||||
*/
|
||||
public function setHousenumber($sNumber)
|
||||
{
|
||||
$this->sHouseNumber = $sNumber;
|
||||
$this->iNamePhrase = -1;
|
||||
}
|
||||
if ((!$this->sPostcode && !$this->aAddress && !$this->aAddressNonSearch)
|
||||
&& (empty($this->aName) || $this->iNamePhrase == $iPhrase)
|
||||
) {
|
||||
$oSearch = clone $this;
|
||||
$oSearch->iSearchRank += 2;
|
||||
if (empty($this->aName)) {
|
||||
$oSearch->iSearchRank += 1;
|
||||
}
|
||||
if (preg_match('#^[0-9]+$#', $sToken)) {
|
||||
$oSearch->iSearchRank += 2;
|
||||
}
|
||||
if ($oSearchTerm->iSearchNameCount < CONST_Max_Word_Frequency) {
|
||||
if (empty($this->aName)
|
||||
&& CONST_Search_NameOnlySearchFrequencyThreshold
|
||||
) {
|
||||
$oSearch->bRareName =
|
||||
$oSearchTerm->iSearchNameCount
|
||||
< CONST_Search_NameOnlySearchFrequencyThreshold;
|
||||
} else {
|
||||
$oSearch->bRareName = false;
|
||||
}
|
||||
$oSearch->aName[$iWordID] = $iWordID;
|
||||
} else {
|
||||
$oSearch->aNameNonSearch[$iWordID] = $iWordID;
|
||||
}
|
||||
$oSearch->iNamePhrase = $iPhrase;
|
||||
$aNewSearches[] = $oSearch;
|
||||
}
|
||||
|
||||
/**
|
||||
* Make this search a search for a house number.
|
||||
*
|
||||
* @param integer iId Token Id for the house number.
|
||||
*/
|
||||
public function setHousenumberAsName($iId)
|
||||
{
|
||||
$this->aAddress = array_merge($this->aAddress, $this->aName);
|
||||
$this->bRareName = false;
|
||||
$this->aName = array($iId => $iId);
|
||||
$this->iNamePhrase = -1;
|
||||
}
|
||||
|
||||
/**
|
||||
* Make this search a POI search.
|
||||
*
|
||||
* In a POI search, objects are not (only) searched by their name
|
||||
* but also by the primary OSM key/value pair (class and type in Nominatim).
|
||||
*
|
||||
* @param integer $iOperator Type of POI search
|
||||
* @param string $sClass Class (or OSM tag key) of POI.
|
||||
* @param string $sType Type (or OSM tag value) of POI.
|
||||
*
|
||||
* @return void
|
||||
*/
|
||||
public function setPoiSearch($iOperator, $sClass, $sType)
|
||||
{
|
||||
$this->iOperator = $iOperator;
|
||||
$this->sClass = $sClass;
|
||||
$this->sType = $sType;
|
||||
$this->iNamePhrase = -1;
|
||||
}
|
||||
|
||||
public function getNamePhrase()
|
||||
{
|
||||
return $this->iNamePhrase;
|
||||
}
|
||||
|
||||
/**
|
||||
* Get the global search context.
|
||||
*
|
||||
* @return object Objects of global search constraints.
|
||||
*/
|
||||
public function getContext()
|
||||
{
|
||||
return $this->oContext;
|
||||
return $aNewSearches;
|
||||
}
|
||||
|
||||
/////////// Query functions
|
||||
@@ -367,6 +426,7 @@ class SearchDescription
|
||||
public function query(&$oDB, $iMinRank, $iMaxRank, $iLimit)
|
||||
{
|
||||
$aResults = array();
|
||||
$iHousenumber = -1;
|
||||
|
||||
if ($this->sCountryCode
|
||||
&& empty($this->aName)
|
||||
@@ -399,24 +459,19 @@ class SearchDescription
|
||||
|
||||
// Now search for housenumber, if housenumber provided. Can be zero.
|
||||
if (($this->sHouseNumber || $this->sHouseNumber === '0') && !empty($aResults)) {
|
||||
$aHnResults = $this->queryHouseNumber($oDB, $aResults);
|
||||
|
||||
// Downgrade the rank of the street results, they are missing
|
||||
// the housenumber. Also drop POI places (rank 30) here, they
|
||||
// cannot be a parent place and therefore must not be shown
|
||||
// as a result for a search with a missing housenumber.
|
||||
// the housenumber.
|
||||
foreach ($aResults as $oRes) {
|
||||
if ($oRes->iAddressRank < 28) {
|
||||
if ($oRes->iAddressRank >= 26) {
|
||||
$oRes->iResultRank++;
|
||||
} else {
|
||||
$oRes->iResultRank += 2;
|
||||
}
|
||||
$aHnResults[$oRes->iId] = $oRes;
|
||||
}
|
||||
$oRes->iResultRank++;
|
||||
}
|
||||
|
||||
$aResults = $aHnResults;
|
||||
$aHnResults = $this->queryHouseNumber($oDB, $aResults);
|
||||
|
||||
if (!empty($aHnResults)) {
|
||||
foreach ($aHnResults as $oRes) {
|
||||
$aResults[$oRes->iId] = $oRes;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// finally get POIs if requested
|
||||
@@ -568,14 +623,14 @@ class SearchDescription
|
||||
// too many results are expected for the street, i.e. if the result
|
||||
// will be narrowed down by an address. Remeber that with ordering
|
||||
// every single result has to be checked.
|
||||
if ($this->sHouseNumber && ($this->bRareName || !empty($this->aAddress) || $this->sPostcode)) {
|
||||
if ($this->sHouseNumber && (!empty($this->aAddress) || $this->sPostcode)) {
|
||||
$sHouseNumberRegex = '\\\\m'.$this->sHouseNumber.'\\\\M';
|
||||
$aOrder[] = ' (';
|
||||
$aOrder[0] .= 'EXISTS(';
|
||||
$aOrder[0] .= ' SELECT place_id';
|
||||
$aOrder[0] .= ' FROM placex';
|
||||
$aOrder[0] .= ' WHERE parent_place_id = search_name.place_id';
|
||||
$aOrder[0] .= " AND housenumber ~* E'".$sHouseNumberRegex."'";
|
||||
$aOrder[0] .= " AND transliteration(housenumber) ~* E'".$sHouseNumberRegex."'";
|
||||
$aOrder[0] .= ' LIMIT 1';
|
||||
$aOrder[0] .= ') ';
|
||||
// also housenumbers from interpolation lines table are needed
|
||||
@@ -672,7 +727,7 @@ class SearchDescription
|
||||
$aResults = array();
|
||||
|
||||
if (!empty($aTerms)) {
|
||||
$sSQL = 'SELECT place_id, address_rank,'.$sExactMatchSQL;
|
||||
$sSQL = 'SELECT place_id,'.$sExactMatchSQL;
|
||||
$sSQL .= ' FROM search_name';
|
||||
$sSQL .= ' WHERE '.join(' and ', $aTerms);
|
||||
$sSQL .= ' ORDER BY '.join(', ', $aOrder);
|
||||
@@ -685,7 +740,6 @@ class SearchDescription
|
||||
foreach ($aDBResults as $aResult) {
|
||||
$oResult = new Result($aResult['place_id']);
|
||||
$oResult->iExactMatches = $aResult['exactmatch'];
|
||||
$oResult->iAddressRank = $aResult['address_rank'];
|
||||
$aResults[$aResult['place_id']] = $oResult;
|
||||
}
|
||||
}
|
||||
@@ -696,33 +750,16 @@ class SearchDescription
|
||||
private function queryHouseNumber(&$oDB, $aRoadPlaceIDs)
|
||||
{
|
||||
$aResults = array();
|
||||
$sRoadPlaceIDs = Result::joinIdsByTableMaxRank(
|
||||
$aRoadPlaceIDs,
|
||||
Result::TABLE_PLACEX,
|
||||
27
|
||||
);
|
||||
$sPOIPlaceIDs = Result::joinIdsByTableMinRank(
|
||||
$aRoadPlaceIDs,
|
||||
Result::TABLE_PLACEX,
|
||||
30
|
||||
);
|
||||
$sPlaceIDs = Result::joinIdsByTable($aRoadPlaceIDs, Result::TABLE_PLACEX);
|
||||
|
||||
$aIDCondition = array();
|
||||
if ($sRoadPlaceIDs) {
|
||||
$aIDCondition[] = 'parent_place_id in ('.$sRoadPlaceIDs.')';
|
||||
}
|
||||
if ($sPOIPlaceIDs) {
|
||||
$aIDCondition[] = 'place_id in ('.$sPOIPlaceIDs.')';
|
||||
}
|
||||
|
||||
if (empty($aIDCondition)) {
|
||||
if (!$sPlaceIDs) {
|
||||
return $aResults;
|
||||
}
|
||||
|
||||
$sHouseNumberRegex = '\\\\m'.$this->sHouseNumber.'\\\\M';
|
||||
$sSQL = 'SELECT place_id FROM placex WHERE';
|
||||
$sSQL .= " housenumber ~* E'".$sHouseNumberRegex."'";
|
||||
$sSQL .= ' AND ('.join(' OR ', $aIDCondition).')';
|
||||
$sSQL = 'SELECT place_id FROM placex ';
|
||||
$sSQL .= 'WHERE parent_place_id in ('.$sPlaceIDs.')';
|
||||
$sSQL .= " AND transliteration(housenumber) ~* E'".$sHouseNumberRegex."'";
|
||||
$sSQL .= $this->oContext->excludeSQL(' AND place_id');
|
||||
|
||||
Debug::printSQL($sSQL);
|
||||
@@ -734,11 +771,11 @@ class SearchDescription
|
||||
|
||||
$bIsIntHouseNumber= (bool) preg_match('/[0-9]+/', $this->sHouseNumber);
|
||||
$iHousenumber = intval($this->sHouseNumber);
|
||||
if ($bIsIntHouseNumber && $sRoadPlaceIDs && empty($aResults)) {
|
||||
if ($bIsIntHouseNumber && empty($aResults)) {
|
||||
// if nothing found, search in the interpolation line table
|
||||
$sSQL = 'SELECT distinct place_id FROM location_property_osmline';
|
||||
$sSQL .= ' WHERE startnumber is not NULL';
|
||||
$sSQL .= ' AND parent_place_id in ('.$sRoadPlaceIDs.') AND (';
|
||||
$sSQL .= ' AND parent_place_id in ('.$sPlaceIDs.') AND (';
|
||||
if ($iHousenumber % 2 == 0) {
|
||||
// If housenumber is even, look for housenumber in streets
|
||||
// with interpolationtype even or all.
|
||||
@@ -761,10 +798,24 @@ class SearchDescription
|
||||
}
|
||||
}
|
||||
|
||||
// If nothing found try the aux fallback table
|
||||
if (CONST_Use_Aux_Location_data && empty($aResults)) {
|
||||
$sSQL = 'SELECT place_id FROM location_property_aux';
|
||||
$sSQL .= ' WHERE parent_place_id in ('.$sPlaceIDs.')';
|
||||
$sSQL .= " AND housenumber = '".$this->sHouseNumber."'";
|
||||
$sSQL .= $this->oContext->excludeSQL(' AND place_id');
|
||||
|
||||
Debug::printSQL($sSQL);
|
||||
|
||||
foreach ($oDB->getCol($sSQL) as $iPlaceId) {
|
||||
$aResults[$iPlaceId] = new Result($iPlaceId, Result::TABLE_AUX);
|
||||
}
|
||||
}
|
||||
|
||||
// If nothing found then search in Tiger data (location_property_tiger)
|
||||
if (CONST_Use_US_Tiger_Data && $sRoadPlaceIDs && $bIsIntHouseNumber && empty($aResults)) {
|
||||
if (CONST_Use_US_Tiger_Data && $bIsIntHouseNumber && empty($aResults)) {
|
||||
$sSQL = 'SELECT place_id FROM location_property_tiger';
|
||||
$sSQL .= ' WHERE parent_place_id in ('.$sRoadPlaceIDs.') and (';
|
||||
$sSQL .= ' WHERE parent_place_id in ('.$sPlaceIDs.') and (';
|
||||
if ($iHousenumber % 2 == 0) {
|
||||
$sSQL .= "interpolationtype='even'";
|
||||
} else {
|
||||
@@ -976,7 +1027,7 @@ class SearchDescription
|
||||
'Name terms (stop words)' => $this->aNameNonSearch,
|
||||
'Address terms' => $this->aAddress,
|
||||
'Address terms (stop words)' => $this->aAddressNonSearch,
|
||||
'Address terms (full words)' => $this->aFullNameAddress ?? '',
|
||||
'Address terms (full words)' => $this->aFullNameAddress,
|
||||
'Special search' => $this->iOperator,
|
||||
'Class' => $this->sClass,
|
||||
'Type' => $this->sType,
|
||||
@@ -988,7 +1039,7 @@ class SearchDescription
|
||||
public function dumpAsHtmlTableRow(&$aWordIDs)
|
||||
{
|
||||
$kf = function ($k) use (&$aWordIDs) {
|
||||
return $aWordIDs[$k] ?? '['.$k.']';
|
||||
return $aWordIDs[$k];
|
||||
};
|
||||
|
||||
echo '<tr>';
|
||||
@@ -7,7 +7,7 @@ class Shell
|
||||
public function __construct($sBaseCmd, ...$aParams)
|
||||
{
|
||||
if (!$sBaseCmd) {
|
||||
throw new \Exception('Command missing in new() call');
|
||||
throw new Exception('Command missing in new() call');
|
||||
}
|
||||
$this->baseCmd = $sBaseCmd;
|
||||
$this->aParams = array();
|
||||
@@ -33,9 +33,7 @@ class Shell
|
||||
public function addEnvPair($sKey, $sVal)
|
||||
{
|
||||
if (isset($sKey) && $sKey && isset($sVal)) {
|
||||
if (!isset($this->aEnv)) {
|
||||
$this->aEnv = $_ENV;
|
||||
}
|
||||
if (!isset($this->aEnv)) $this->aEnv = $_ENV;
|
||||
$this->aEnv = array_merge($this->aEnv, array($sKey => $sVal), $_ENV);
|
||||
}
|
||||
return $this;
|
||||
@@ -50,7 +48,7 @@ class Shell
|
||||
return join(' ', $aEscaped);
|
||||
}
|
||||
|
||||
public function run($bExitOnFail = false)
|
||||
public function run()
|
||||
{
|
||||
$sCmd = $this->escapedCmd();
|
||||
// $aEnv does not need escaping, proc_open seems to handle it fine
|
||||
@@ -69,16 +67,14 @@ class Shell
|
||||
fclose($aPipes[0]); // no stdin
|
||||
|
||||
$iStat = proc_close($hProc);
|
||||
|
||||
if ($iStat != 0 && $bExitOnFail) {
|
||||
exit($iStat);
|
||||
}
|
||||
|
||||
return $iStat;
|
||||
}
|
||||
|
||||
|
||||
|
||||
private function escapeParam($sParam)
|
||||
{
|
||||
return (preg_match('/^-*\w+$/', $sParam)) ? $sParam : escapeshellarg($sParam);
|
||||
if (preg_match('/^-*\w+$/', $sParam)) return $sParam;
|
||||
return escapeshellarg($sParam);
|
||||
}
|
||||
}
|
||||
59
lib/Status.php
Normal file
59
lib/Status.php
Normal file
@@ -0,0 +1,59 @@
|
||||
<?php
|
||||
|
||||
namespace Nominatim;
|
||||
|
||||
use Exception;
|
||||
|
||||
class Status
|
||||
{
|
||||
protected $oDB;
|
||||
|
||||
public function __construct(&$oDB)
|
||||
{
|
||||
$this->oDB =& $oDB;
|
||||
}
|
||||
|
||||
public function status()
|
||||
{
|
||||
if (!$this->oDB) {
|
||||
throw new Exception('No database', 700);
|
||||
}
|
||||
|
||||
try {
|
||||
$this->oDB->connect();
|
||||
} catch (\Nominatim\DatabaseError $e) {
|
||||
throw new Exception('Database connection failed', 700);
|
||||
}
|
||||
|
||||
$sStandardWord = $this->oDB->getOne("SELECT make_standard_name('a')");
|
||||
if ($sStandardWord === false) {
|
||||
throw new Exception('Module failed', 701);
|
||||
}
|
||||
|
||||
if ($sStandardWord != 'a') {
|
||||
throw new Exception('Module call failed', 702);
|
||||
}
|
||||
|
||||
$sSQL = 'SELECT word_id, word_token, word, class, type, country_code, ';
|
||||
$sSQL .= "operator, search_name_count FROM word WHERE word_token IN (' a')";
|
||||
$iWordID = $this->oDB->getOne($sSQL);
|
||||
if ($iWordID === false) {
|
||||
throw new Exception('Query failed', 703);
|
||||
}
|
||||
if (!$iWordID) {
|
||||
throw new Exception('No value', 704);
|
||||
}
|
||||
}
|
||||
|
||||
public function dataDate()
|
||||
{
|
||||
$sSQL = 'SELECT EXTRACT(EPOCH FROM lastimportdate) FROM import_status LIMIT 1';
|
||||
$iDataDateEpoch = $this->oDB->getOne($sSQL);
|
||||
|
||||
if ($iDataDateEpoch === false) {
|
||||
throw Exception('Data date query failed '.$iDataDateEpoch->getMessage(), 705);
|
||||
}
|
||||
|
||||
return $iDataDateEpoch;
|
||||
}
|
||||
}
|
||||
29
lib/TokenCountry.php
Normal file
29
lib/TokenCountry.php
Normal file
@@ -0,0 +1,29 @@
|
||||
<?php
|
||||
|
||||
namespace Nominatim\Token;
|
||||
|
||||
/**
|
||||
* A country token.
|
||||
*/
|
||||
class Country
|
||||
{
|
||||
/// Database word id, if available.
|
||||
public $iId;
|
||||
/// Two-letter country code (lower-cased).
|
||||
public $sCountryCode;
|
||||
|
||||
public function __construct($iId, $sCountryCode)
|
||||
{
|
||||
$this->iId = $iId;
|
||||
$this->sCountryCode = $sCountryCode;
|
||||
}
|
||||
|
||||
public function debugInfo()
|
||||
{
|
||||
return array(
|
||||
'ID' => $this->iId,
|
||||
'Type' => 'country',
|
||||
'Info' => $this->sCountryCode
|
||||
);
|
||||
}
|
||||
}
|
||||
29
lib/TokenHousenumber.php
Normal file
29
lib/TokenHousenumber.php
Normal file
@@ -0,0 +1,29 @@
|
||||
<?php
|
||||
|
||||
namespace Nominatim\Token;
|
||||
|
||||
/**
|
||||
* A house number token.
|
||||
*/
|
||||
class HouseNumber
|
||||
{
|
||||
/// Database word id, if available.
|
||||
public $iId;
|
||||
/// Normalized house number.
|
||||
public $sToken;
|
||||
|
||||
public function __construct($iId, $sToken)
|
||||
{
|
||||
$this->iId = $iId;
|
||||
$this->sToken = $sToken;
|
||||
}
|
||||
|
||||
public function debugInfo()
|
||||
{
|
||||
return array(
|
||||
'ID' => $this->iId,
|
||||
'Type' => 'house number',
|
||||
'Info' => array('nr' => $this->sToken)
|
||||
);
|
||||
}
|
||||
}
|
||||
216
lib/TokenList.php
Normal file
216
lib/TokenList.php
Normal file
@@ -0,0 +1,216 @@
|
||||
<?php
|
||||
|
||||
namespace Nominatim;
|
||||
|
||||
require_once(CONST_BasePath.'/lib/TokenCountry.php');
|
||||
require_once(CONST_BasePath.'/lib/TokenHousenumber.php');
|
||||
require_once(CONST_BasePath.'/lib/TokenPostcode.php');
|
||||
require_once(CONST_BasePath.'/lib/TokenSpecialTerm.php');
|
||||
require_once(CONST_BasePath.'/lib/TokenWord.php');
|
||||
require_once(CONST_BasePath.'/lib/SpecialSearchOperator.php');
|
||||
|
||||
/**
|
||||
* Saves information about the tokens that appear in a search query.
|
||||
*
|
||||
* Tokens are sorted by their normalized form, the token word. There are different
|
||||
* kinds of tokens, represented by different Token* classes. Note that
|
||||
* tokens do not have a common base class. All tokens need to have a field
|
||||
* with the word id that points to an entry in the `word` database table
|
||||
* but otherwise the information saved about a token can be very different.
|
||||
*
|
||||
* There are two different kinds of token words: full words and partial terms.
|
||||
*
|
||||
* Full words start with a space. They represent a complete name of a place.
|
||||
* All special tokens are normally full words.
|
||||
*
|
||||
* Partial terms have no space at the beginning. They may represent a part of
|
||||
* a name of a place (e.g. in the name 'World Trade Center' a partial term
|
||||
* would be 'Trade' or 'Trade Center'). They are only used in TokenWord.
|
||||
*/
|
||||
class TokenList
|
||||
{
|
||||
// List of list of tokens indexed by their word_token.
|
||||
private $aTokens = array();
|
||||
|
||||
|
||||
/**
|
||||
* Return total number of tokens.
|
||||
*
|
||||
* @return Integer
|
||||
*/
|
||||
public function count()
|
||||
{
|
||||
return count($this->aTokens);
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if there are tokens for the given token word.
|
||||
*
|
||||
* @param string $sWord Token word to look for.
|
||||
*
|
||||
* @return bool True if there is one or more token for the token word.
|
||||
*/
|
||||
public function contains($sWord)
|
||||
{
|
||||
return isset($this->aTokens[$sWord]);
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if there are partial or full tokens for the given word.
|
||||
*
|
||||
* @param string $sWord Token word to look for.
|
||||
*
|
||||
* @return bool True if there is one or more token for the token word.
|
||||
*/
|
||||
public function containsAny($sWord)
|
||||
{
|
||||
return isset($this->aTokens[$sWord]) || isset($this->aTokens[' '.$sWord]);
|
||||
}
|
||||
|
||||
/**
|
||||
* Get the list of tokens for the given token word.
|
||||
*
|
||||
* @param string $sWord Token word to look for.
|
||||
*
|
||||
* @return object[] Array of tokens for the given token word or an
|
||||
* empty array if no tokens could be found.
|
||||
*/
|
||||
public function get($sWord)
|
||||
{
|
||||
return isset($this->aTokens[$sWord]) ? $this->aTokens[$sWord] : array();
|
||||
}
|
||||
|
||||
public function getFullWordIDs()
|
||||
{
|
||||
$ids = array();
|
||||
|
||||
foreach ($this->aTokens as $aTokenList) {
|
||||
foreach ($aTokenList as $oToken) {
|
||||
if (is_a($oToken, '\Nominatim\Token\Word') && !$oToken->bPartial) {
|
||||
$ids[$oToken->iId] = $oToken->iId;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return $ids;
|
||||
}
|
||||
|
||||
/**
|
||||
* Add token information from the word table in the database.
|
||||
*
|
||||
* @param object $oDB Nominatim::DB instance.
|
||||
* @param string[] $aTokens List of tokens to look up in the database.
|
||||
* @param string[] $aCountryCodes List of country restrictions.
|
||||
* @param string $sNormQuery Normalized query string.
|
||||
* @param object $oNormalizer Normalizer function to use on tokens.
|
||||
*
|
||||
* @return void
|
||||
*/
|
||||
public function addTokensFromDB(&$oDB, &$aTokens, &$aCountryCodes, $sNormQuery, $oNormalizer)
|
||||
{
|
||||
// Check which tokens we have, get the ID numbers
|
||||
$sSQL = 'SELECT word_id, word_token, word, class, type, country_code,';
|
||||
$sSQL .= ' operator, coalesce(search_name_count, 0) as count';
|
||||
$sSQL .= ' FROM word WHERE word_token in (';
|
||||
$sSQL .= join(',', $oDB->getDBQuotedList($aTokens)).')';
|
||||
|
||||
Debug::printSQL($sSQL);
|
||||
|
||||
$aDBWords = $oDB->getAll($sSQL, null, 'Could not get word tokens.');
|
||||
|
||||
foreach ($aDBWords as $aWord) {
|
||||
$oToken = null;
|
||||
$iId = (int) $aWord['word_id'];
|
||||
|
||||
if ($aWord['class']) {
|
||||
// Special terms need to appear in their normalized form.
|
||||
if ($aWord['word']) {
|
||||
$sNormWord = $aWord['word'];
|
||||
if ($oNormalizer != null) {
|
||||
$sNormWord = $oNormalizer->transliterate($aWord['word']);
|
||||
}
|
||||
if (strpos($sNormQuery, $sNormWord) === false) {
|
||||
continue;
|
||||
}
|
||||
}
|
||||
|
||||
if ($aWord['class'] == 'place' && $aWord['type'] == 'house') {
|
||||
$oToken = new Token\HouseNumber($iId, trim($aWord['word_token']));
|
||||
} elseif ($aWord['class'] == 'place' && $aWord['type'] == 'postcode') {
|
||||
if ($aWord['word']
|
||||
&& pg_escape_string($aWord['word']) == $aWord['word']
|
||||
) {
|
||||
$oToken = new Token\Postcode(
|
||||
$iId,
|
||||
$aWord['word'],
|
||||
$aWord['country_code']
|
||||
);
|
||||
}
|
||||
} else {
|
||||
// near and in operator the same at the moment
|
||||
$oToken = new Token\SpecialTerm(
|
||||
$iId,
|
||||
$aWord['class'],
|
||||
$aWord['type'],
|
||||
$aWord['operator'] ? Operator::NEAR : Operator::NONE
|
||||
);
|
||||
}
|
||||
} elseif ($aWord['country_code']) {
|
||||
// Filter country tokens that do not match restricted countries.
|
||||
if (!$aCountryCodes
|
||||
|| in_array($aWord['country_code'], $aCountryCodes)
|
||||
) {
|
||||
$oToken = new Token\Country($iId, $aWord['country_code']);
|
||||
}
|
||||
} else {
|
||||
$oToken = new Token\Word(
|
||||
$iId,
|
||||
$aWord['word_token'][0] != ' ',
|
||||
(int) $aWord['count'],
|
||||
substr_count($aWord['word_token'], ' ')
|
||||
);
|
||||
}
|
||||
|
||||
if ($oToken) {
|
||||
$this->addToken($aWord['word_token'], $oToken);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Add a new token for the given word.
|
||||
*
|
||||
* @param string $sWord Word the token describes.
|
||||
* @param object $oToken Token object to add.
|
||||
*
|
||||
* @return void
|
||||
*/
|
||||
public function addToken($sWord, $oToken)
|
||||
{
|
||||
if (isset($this->aTokens[$sWord])) {
|
||||
$this->aTokens[$sWord][] = $oToken;
|
||||
} else {
|
||||
$this->aTokens[$sWord] = array($oToken);
|
||||
}
|
||||
}
|
||||
|
||||
public function debugTokenByWordIdList()
|
||||
{
|
||||
$aWordsIDs = array();
|
||||
foreach ($this->aTokens as $sToken => $aWords) {
|
||||
foreach ($aWords as $aToken) {
|
||||
if ($aToken->iId !== null) {
|
||||
$aWordsIDs[$aToken->iId] =
|
||||
'#'.$sToken.'('.$aToken->iId.')#';
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return $aWordsIDs;
|
||||
}
|
||||
|
||||
public function debugInfo()
|
||||
{
|
||||
return $this->aTokens;
|
||||
}
|
||||
}
|
||||
32
lib/TokenPostcode.php
Normal file
32
lib/TokenPostcode.php
Normal file
@@ -0,0 +1,32 @@
|
||||
<?php
|
||||
|
||||
namespace Nominatim\Token;
|
||||
|
||||
/**
|
||||
* A postcode token.
|
||||
*/
|
||||
class Postcode
|
||||
{
|
||||
/// Database word id, if available.
|
||||
public $iId;
|
||||
/// Full nomralized postcode (upper cased).
|
||||
public $sPostcode;
|
||||
// Optional country code the postcode belongs to (currently unused).
|
||||
public $sCountryCode;
|
||||
|
||||
public function __construct($iId, $sPostcode, $sCountryCode = '')
|
||||
{
|
||||
$this->iId = $iId;
|
||||
$this->sPostcode = $sPostcode;
|
||||
$this->sCountryCode = empty($sCountryCode) ? '' : $sCountryCode;
|
||||
}
|
||||
|
||||
public function debugInfo()
|
||||
{
|
||||
return array(
|
||||
'ID' => $this->iId,
|
||||
'Type' => 'postcode',
|
||||
'Info' => $this->sPostcode.'('.$this->sCountryCode.')'
|
||||
);
|
||||
}
|
||||
}
|
||||
41
lib/TokenSpecialTerm.php
Normal file
41
lib/TokenSpecialTerm.php
Normal file
@@ -0,0 +1,41 @@
|
||||
<?php
|
||||
|
||||
namespace Nominatim\Token;
|
||||
|
||||
require_once(CONST_BasePath.'/lib/SpecialSearchOperator.php');
|
||||
|
||||
/**
|
||||
* A word token describing a place type.
|
||||
*/
|
||||
class SpecialTerm
|
||||
{
|
||||
/// Database word id, if applicable.
|
||||
public $iId;
|
||||
/// Class (or OSM tag key) of the place to look for.
|
||||
public $sClass;
|
||||
/// Type (or OSM tag value) of the place to look for.
|
||||
public $sType;
|
||||
/// Relationship of the operator to the object (see Operator class).
|
||||
public $iOperator;
|
||||
|
||||
public function __construct($iID, $sClass, $sType, $iOperator)
|
||||
{
|
||||
$this->iId = $iID;
|
||||
$this->sClass = $sClass;
|
||||
$this->sType = $sType;
|
||||
$this->iOperator = $iOperator;
|
||||
}
|
||||
|
||||
public function debugInfo()
|
||||
{
|
||||
return array(
|
||||
'ID' => $this->iId,
|
||||
'Type' => 'special term',
|
||||
'Info' => array(
|
||||
'class' => $this->sClass,
|
||||
'type' => $this->sType,
|
||||
'operator' => \Nominatim\Operator::toString($this->iOperator)
|
||||
)
|
||||
);
|
||||
}
|
||||
}
|
||||
38
lib/TokenWord.php
Normal file
38
lib/TokenWord.php
Normal file
@@ -0,0 +1,38 @@
|
||||
<?php
|
||||
|
||||
namespace Nominatim\Token;
|
||||
|
||||
/**
|
||||
* A standard word token.
|
||||
*/
|
||||
class Word
|
||||
{
|
||||
/// Database word id, if applicable.
|
||||
public $iId;
|
||||
/// If true, the word may represent only part of a place name.
|
||||
public $bPartial;
|
||||
/// Number of appearances in the database.
|
||||
public $iSearchNameCount;
|
||||
/// Number of terms in the word.
|
||||
public $iTermCount;
|
||||
|
||||
public function __construct($iId, $bPartial, $iSearchNameCount, $iTermCount)
|
||||
{
|
||||
$this->iId = $iId;
|
||||
$this->bPartial = $bPartial;
|
||||
$this->iSearchNameCount = $iSearchNameCount;
|
||||
$this->iTermCount = $iTermCount;
|
||||
}
|
||||
|
||||
public function debugInfo()
|
||||
{
|
||||
return array(
|
||||
'ID' => $this->iId,
|
||||
'Type' => 'word',
|
||||
'Info' => array(
|
||||
'partial' => $this->bPartial,
|
||||
'count' => $this->iSearchNameCount
|
||||
)
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -1,6 +1,6 @@
|
||||
<?php
|
||||
|
||||
require_once(CONST_LibDir.'/Shell.php');
|
||||
require_once(CONST_BasePath.'/lib/Shell.php');
|
||||
|
||||
function getCmdOpt($aArg, $aSpec, &$aResult, $bExitOnError = false, $bExitOnUnknown = false)
|
||||
{
|
||||
@@ -9,12 +9,8 @@ function getCmdOpt($aArg, $aSpec, &$aResult, $bExitOnError = false, $bExitOnUnkn
|
||||
|
||||
foreach ($aSpec as $aLine) {
|
||||
if (is_array($aLine)) {
|
||||
if ($aLine[0]) {
|
||||
$aQuick['--'.$aLine[0]] = $aLine;
|
||||
}
|
||||
if ($aLine[1]) {
|
||||
$aQuick['-'.$aLine[1]] = $aLine;
|
||||
}
|
||||
if ($aLine[0]) $aQuick['--'.$aLine[0]] = $aLine;
|
||||
if ($aLine[1]) $aQuick['-'.$aLine[1]] = $aLine;
|
||||
$aCounts[$aLine[0]] = 0;
|
||||
}
|
||||
}
|
||||
@@ -32,9 +28,7 @@ function getCmdOpt($aArg, $aSpec, &$aResult, $bExitOnError = false, $bExitOnUnkn
|
||||
$xVal = array();
|
||||
for ($n = $aLine[4]; $i < $iSize && $n; $n--) {
|
||||
$i++;
|
||||
if ($i >= $iSize || $aArg[$i][0] == '-') {
|
||||
showUsage($aSpec, $bExitOnError, 'Parameter of \''.$aLine[0].'\' is missing');
|
||||
}
|
||||
if ($i >= $iSize || $aArg[$i][0] == '-') showUsage($aSpec, $bExitOnError, 'Parameter of \''.$aLine[0].'\' is missing');
|
||||
|
||||
switch ($aLine[6]) {
|
||||
case 'realpath':
|
||||
@@ -62,9 +56,7 @@ function getCmdOpt($aArg, $aSpec, &$aResult, $bExitOnError = false, $bExitOnUnkn
|
||||
break;
|
||||
}
|
||||
}
|
||||
if ($aLine[4] == 1) {
|
||||
$xVal = $xVal[0];
|
||||
}
|
||||
if ($aLine[4] == 1) $xVal = $xVal[0];
|
||||
} else {
|
||||
$xVal = true;
|
||||
}
|
||||
@@ -73,9 +65,7 @@ function getCmdOpt($aArg, $aSpec, &$aResult, $bExitOnError = false, $bExitOnUnkn
|
||||
}
|
||||
|
||||
if ($aLine[3] > 1) {
|
||||
if (!array_key_exists($aLine[0], $aResult)) {
|
||||
$aResult[$aLine[0]] = array();
|
||||
}
|
||||
if (!array_key_exists($aLine[0], $aResult)) $aResult[$aLine[0]] = array();
|
||||
$aResult[$aLine[0]][] = $xVal;
|
||||
} else {
|
||||
$aResult[$aLine[0]] = $xVal;
|
||||
@@ -85,23 +75,18 @@ function getCmdOpt($aArg, $aSpec, &$aResult, $bExitOnError = false, $bExitOnUnkn
|
||||
}
|
||||
}
|
||||
|
||||
if (array_key_exists('help', $aResult)) {
|
||||
showUsage($aSpec);
|
||||
}
|
||||
if ($bUnknown && $bExitOnUnknown) {
|
||||
showUsage($aSpec, $bExitOnError, 'Unknown option \''.$bUnknown.'\'');
|
||||
}
|
||||
if (array_key_exists('help', $aResult)) showUsage($aSpec);
|
||||
if ($bUnknown && $bExitOnUnknown) showUsage($aSpec, $bExitOnError, 'Unknown option \''.$bUnknown.'\'');
|
||||
|
||||
foreach ($aSpec as $aLine) {
|
||||
if (is_array($aLine)) {
|
||||
if ($aCounts[$aLine[0]] < $aLine[2]) {
|
||||
showUsage($aSpec, $bExitOnError, 'Option \''.$aLine[0].'\' is missing');
|
||||
}
|
||||
if ($aCounts[$aLine[0]] > $aLine[3]) {
|
||||
showUsage($aSpec, $bExitOnError, 'Option \''.$aLine[0].'\' is pressent too many times');
|
||||
}
|
||||
if ($aLine[6] == 'bool' && !array_key_exists($aLine[0], $aResult)) {
|
||||
$aResult[$aLine[0]] = false;
|
||||
if ($aCounts[$aLine[0]] < $aLine[2]) showUsage($aSpec, $bExitOnError, 'Option \''.$aLine[0].'\' is missing');
|
||||
if ($aCounts[$aLine[0]] > $aLine[3]) showUsage($aSpec, $bExitOnError, 'Option \''.$aLine[0].'\' is pressent too many times');
|
||||
switch ($aLine[6]) {
|
||||
case 'bool':
|
||||
if (!array_key_exists($aLine[0], $aResult))
|
||||
$aResult[$aLine[0]] = false;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -124,12 +109,8 @@ function showUsage($aSpec, $bExit = false, $sError = false)
|
||||
echo "\n";
|
||||
}
|
||||
$aNames = array();
|
||||
if ($aLine[1]) {
|
||||
$aNames[] = '-'.$aLine[1];
|
||||
}
|
||||
if ($aLine[0]) {
|
||||
$aNames[] = '--'.$aLine[0];
|
||||
}
|
||||
if ($aLine[1]) $aNames[] = '-'.$aLine[1];
|
||||
if ($aLine[0]) $aNames[] = '--'.$aLine[0];
|
||||
$sName = join(', ', $aNames);
|
||||
echo ' '.$sName.str_repeat(' ', 30-strlen($sName)).$aLine[7]."\n";
|
||||
} else {
|
||||
@@ -163,29 +144,54 @@ function repeatWarnings()
|
||||
}
|
||||
|
||||
|
||||
function setupHTTPProxy()
|
||||
function runSQLScript($sScript, $bfatal = true, $bVerbose = false, $bIgnoreErrors = false)
|
||||
{
|
||||
if (!getSettingBool('HTTP_PROXY')) {
|
||||
return;
|
||||
// Convert database DSN to psql parameters
|
||||
$aDSNInfo = \Nominatim\DB::parseDSN(CONST_Database_DSN);
|
||||
if (!isset($aDSNInfo['port']) || !$aDSNInfo['port']) $aDSNInfo['port'] = 5432;
|
||||
|
||||
$oCmd = new \Nominatim\Shell('psql');
|
||||
$oCmd->addParams('--port', $aDSNInfo['port']);
|
||||
$oCmd->addParams('--dbname', $aDSNInfo['database']);
|
||||
if (isset($aDSNInfo['hostspec']) && $aDSNInfo['hostspec']) {
|
||||
$oCmd->addParams('--host', $aDSNInfo['hostspec']);
|
||||
}
|
||||
if (isset($aDSNInfo['username']) && $aDSNInfo['username']) {
|
||||
$oCmd->addParams('--username', $aDSNInfo['username']);
|
||||
}
|
||||
if (isset($aDSNInfo['password'])) {
|
||||
$oCmd->addEnvPair('PGPASSWORD', $aDSNInfo['password']);
|
||||
}
|
||||
if (!$bVerbose) {
|
||||
$oCmd->addParams('--quiet');
|
||||
}
|
||||
if ($bfatal && !$bIgnoreErrors) {
|
||||
$oCmd->addParams('-v', 'ON_ERROR_STOP=1');
|
||||
}
|
||||
|
||||
$sProxy = 'tcp://'.getSetting('HTTP_PROXY_HOST').':'.getSetting('HTTP_PROXY_PROT');
|
||||
$aHeaders = array();
|
||||
|
||||
$sLogin = getSetting('HTTP_PROXY_LOGIN');
|
||||
$sPassword = getSetting('HTTP_PROXY_PASSWORD');
|
||||
|
||||
if ($sLogin && $sPassword) {
|
||||
$sAuth = base64_encode($sLogin.':'.$sPassword);
|
||||
$aHeaders = array('Proxy-Authorization: Basic '.$sAuth);
|
||||
}
|
||||
|
||||
$aProxyHeader = array(
|
||||
'proxy' => $sProxy,
|
||||
'request_fulluri' => true,
|
||||
'header' => $aHeaders
|
||||
$aDescriptors = array(
|
||||
0 => array('pipe', 'r'),
|
||||
1 => STDOUT,
|
||||
2 => STDERR
|
||||
);
|
||||
$ahPipes = null;
|
||||
$hProcess = @proc_open($oCmd->escapedCmd(), $aDescriptors, $ahPipes, null, $oCmd->aEnv);
|
||||
if (!is_resource($hProcess)) {
|
||||
fail('unable to start pgsql');
|
||||
}
|
||||
|
||||
$aContext = array('http' => $aProxyHeader, 'https' => $aProxyHeader);
|
||||
stream_context_set_default($aContext);
|
||||
if (!$bVerbose) {
|
||||
fwrite($ahPipes[0], 'set client_min_messages to WARNING;');
|
||||
}
|
||||
|
||||
while (strlen($sScript)) {
|
||||
$iWritten = fwrite($ahPipes[0], $sScript);
|
||||
if ($iWritten <= 0) break;
|
||||
$sScript = substr($sScript, $iWritten);
|
||||
}
|
||||
fclose($ahPipes[0]);
|
||||
$iReturn = proc_close($hProcess);
|
||||
if ($bfatal && $iReturn > 0) {
|
||||
fail("pgsql returned with error code ($iReturn)");
|
||||
}
|
||||
}
|
||||
28
lib/init-cmd.php
Normal file
28
lib/init-cmd.php
Normal file
@@ -0,0 +1,28 @@
|
||||
<?php
|
||||
|
||||
require_once('init.php');
|
||||
require_once('cmd.php');
|
||||
require_once('DebugNone.php');
|
||||
|
||||
// handle http proxy when using file_get_contents
|
||||
if (CONST_HTTP_Proxy) {
|
||||
$proxy = 'tcp://' . CONST_HTTP_Proxy_Host . ':' . CONST_HTTP_Proxy_Port;
|
||||
$aHeaders = array();
|
||||
if (CONST_HTTP_Proxy_Login != null && CONST_HTTP_Proxy_Login != '' && CONST_HTTP_Proxy_Password != null && CONST_HTTP_Proxy_Password != '') {
|
||||
$auth = base64_encode(CONST_HTTP_Proxy_Login . ':' . CONST_HTTP_Proxy_Password);
|
||||
$aHeaders = array("Proxy-Authorization: Basic $auth");
|
||||
}
|
||||
$aContext = array(
|
||||
'http' => array(
|
||||
'proxy' => $proxy,
|
||||
'request_fulluri' => true,
|
||||
'header' => $aHeaders
|
||||
),
|
||||
'https' => array(
|
||||
'proxy' => $proxy,
|
||||
'request_fulluri' => true,
|
||||
'header' => $aHeaders
|
||||
)
|
||||
);
|
||||
stream_context_set_default($aContext);
|
||||
}
|
||||
@@ -12,7 +12,7 @@ require_once(CONST_Debug ? 'DebugHtml.php' : 'DebugNone.php');
|
||||
|
||||
function userError($sMsg)
|
||||
{
|
||||
throw new \Exception($sMsg, 400);
|
||||
throw new Exception($sMsg, 400);
|
||||
}
|
||||
|
||||
|
||||
@@ -20,7 +20,7 @@ function exception_handler_json($exception)
|
||||
{
|
||||
http_response_code($exception->getCode());
|
||||
header('Content-type: application/json; charset=utf-8');
|
||||
include(CONST_LibDir.'/template/error-json.php');
|
||||
include(CONST_BasePath.'/lib/template/error-json.php');
|
||||
exit();
|
||||
}
|
||||
|
||||
@@ -29,7 +29,7 @@ function exception_handler_xml($exception)
|
||||
http_response_code($exception->getCode());
|
||||
header('Content-type: text/xml; charset=utf-8');
|
||||
echo '<?xml version="1.0" encoding="UTF-8" ?>'."\n";
|
||||
include(CONST_LibDir.'/template/error-xml.php');
|
||||
include(CONST_BasePath.'/lib/template/error-xml.php');
|
||||
exit();
|
||||
}
|
||||
|
||||
@@ -37,7 +37,7 @@ function shutdown_exception_handler_xml()
|
||||
{
|
||||
$error = error_get_last();
|
||||
if ($error !== null && $error['type'] === E_ERROR) {
|
||||
exception_handler_xml(new \Exception($error['message'], 500));
|
||||
exception_handler_xml(new Exception($error['message'], 500));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -45,7 +45,7 @@ function shutdown_exception_handler_json()
|
||||
{
|
||||
$error = error_get_last();
|
||||
if ($error !== null && $error['type'] === E_ERROR) {
|
||||
exception_handler_json(new \Exception($error['message'], 500));
|
||||
exception_handler_json(new Exception($error['message'], 500));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -81,10 +81,6 @@ if (CONST_NoAccessControl) {
|
||||
header('Access-Control-Allow-Headers: '.$_SERVER['HTTP_ACCESS_CONTROL_REQUEST_HEADERS']);
|
||||
}
|
||||
}
|
||||
if (isset($_SERVER['REQUEST_METHOD']) && $_SERVER['REQUEST_METHOD'] == 'OPTIONS') {
|
||||
exit;
|
||||
}
|
||||
if (isset($_SERVER['REQUEST_METHOD']) && $_SERVER['REQUEST_METHOD'] == 'OPTIONS') exit;
|
||||
|
||||
if (CONST_Debug) {
|
||||
header('Content-type: text/html; charset=utf-8');
|
||||
}
|
||||
if (CONST_Debug) header('Content-type: text/html; charset=utf-8');
|
||||
4
lib/init.php
Normal file
4
lib/init.php
Normal file
@@ -0,0 +1,4 @@
|
||||
<?php
|
||||
|
||||
require_once(CONST_BasePath.'/lib/lib.php');
|
||||
require_once(CONST_BasePath.'/lib/DB.php');
|
||||
@@ -1,42 +1,10 @@
|
||||
<?php
|
||||
|
||||
function loadSettings($sProjectDir)
|
||||
{
|
||||
@define('CONST_InstallDir', $sProjectDir);
|
||||
// Temporary hack to set the direcory via environment instead of
|
||||
// the installed scripts. Neither setting is part of the official
|
||||
// set of settings.
|
||||
defined('CONST_ConfigDir') or define('CONST_ConfigDir', $_SERVER['NOMINATIM_CONFIGDIR']);
|
||||
}
|
||||
|
||||
function getSetting($sConfName, $sDefault = null)
|
||||
{
|
||||
$sValue = $_SERVER['NOMINATIM_'.$sConfName];
|
||||
|
||||
if ($sDefault !== null && !$sValue) {
|
||||
return $sDefault;
|
||||
}
|
||||
|
||||
return $sValue;
|
||||
}
|
||||
|
||||
function getSettingBool($sConfName)
|
||||
{
|
||||
$sVal = strtolower(getSetting($sConfName));
|
||||
|
||||
return strcmp($sVal, 'yes') == 0
|
||||
|| strcmp($sVal, 'true') == 0
|
||||
|| strcmp($sVal, '1') == 0;
|
||||
}
|
||||
|
||||
function fail($sError, $sUserError = false)
|
||||
{
|
||||
if (!$sUserError) {
|
||||
$sUserError = $sError;
|
||||
}
|
||||
if (!$sUserError) $sUserError = $sError;
|
||||
error_log('ERROR: '.$sError);
|
||||
var_dump($sUserError);
|
||||
echo "\n";
|
||||
var_dump($sUserError)."\n";
|
||||
exit(-1);
|
||||
}
|
||||
|
||||
@@ -84,9 +52,8 @@ function getDatabaseDate(&$oDB)
|
||||
|
||||
function byImportance($a, $b)
|
||||
{
|
||||
if ($a['importance'] != $b['importance']) {
|
||||
if ($a['importance'] != $b['importance'])
|
||||
return ($a['importance'] > $b['importance']?-1:1);
|
||||
}
|
||||
|
||||
return $a['foundorder'] <=> $b['foundorder'];
|
||||
}
|
||||
@@ -198,6 +165,17 @@ function parseLatLon($sQuery)
|
||||
return array($sFound, $fQueryLat, $fQueryLon);
|
||||
}
|
||||
|
||||
function createPointsAroundCenter($fLon, $fLat, $fRadius)
|
||||
{
|
||||
$iSteps = max(8, min(100, ($fRadius * 40000)^2));
|
||||
$fStepSize = (2*pi())/$iSteps;
|
||||
$aPolyPoints = array();
|
||||
for ($f = 0; $f < 2*pi(); $f += $fStepSize) {
|
||||
$aPolyPoints[] = array('', $fLon+($fRadius*sin($f)), $fLat+($fRadius*cos($f)) );
|
||||
}
|
||||
return $aPolyPoints;
|
||||
}
|
||||
|
||||
function closestHouseNumber($aRow)
|
||||
{
|
||||
$fHouse = $aRow['startnumber']
|
||||
@@ -218,11 +196,24 @@ function closestHouseNumber($aRow)
|
||||
return max(min($aRow['endnumber'], $iHn), $aRow['startnumber']);
|
||||
}
|
||||
|
||||
if (!function_exists('array_key_last')) {
|
||||
function array_key_last(array $array)
|
||||
{
|
||||
if (!empty($array)) {
|
||||
return key(array_slice($array, -1, 1, true));
|
||||
}
|
||||
}
|
||||
function getSearchRankLabel($iRank)
|
||||
{
|
||||
if (!isset($iRank)) return 'unknown';
|
||||
if ($iRank < 2) return 'continent';
|
||||
if ($iRank < 4) return 'sea';
|
||||
if ($iRank < 8) return 'country';
|
||||
if ($iRank < 12) return 'state';
|
||||
if ($iRank < 16) return 'county';
|
||||
if ($iRank == 16) return 'city';
|
||||
if ($iRank == 17) return 'town / island';
|
||||
if ($iRank == 18) return 'village / hamlet';
|
||||
if ($iRank == 20) return 'suburb';
|
||||
if ($iRank == 21) return 'postcode area';
|
||||
if ($iRank == 22) return 'croft / farm / locality / islet';
|
||||
if ($iRank == 23) return 'postcode area';
|
||||
if ($iRank == 25) return 'postcode point';
|
||||
if ($iRank == 26) return 'street / major landmark';
|
||||
if ($iRank == 27) return 'minory street / path';
|
||||
if ($iRank == 28) return 'house / building';
|
||||
return 'other: ' . $iRank;
|
||||
}
|
||||
@@ -5,23 +5,15 @@ function logStart(&$oDB, $sType = '', $sQuery = '', $aLanguageList = array())
|
||||
{
|
||||
$fStartTime = microtime(true);
|
||||
$aStartTime = explode('.', $fStartTime);
|
||||
if (!isset($aStartTime[1])) {
|
||||
$aStartTime[1] = '0';
|
||||
}
|
||||
if (!isset($aStartTime[1])) $aStartTime[1] = '0';
|
||||
|
||||
$sOutputFormat = '';
|
||||
if (isset($_GET['format'])) {
|
||||
$sOutputFormat = $_GET['format'];
|
||||
}
|
||||
if (isset($_GET['format'])) $sOutputFormat = $_GET['format'];
|
||||
|
||||
if ($sType == 'reverse') {
|
||||
$sOutQuery = (isset($_GET['lat'])?$_GET['lat']:'').'/';
|
||||
if (isset($_GET['lon'])) {
|
||||
$sOutQuery .= $_GET['lon'];
|
||||
}
|
||||
if (isset($_GET['zoom'])) {
|
||||
$sOutQuery .= '/'.$_GET['zoom'];
|
||||
}
|
||||
if (isset($_GET['lon'])) $sOutQuery .= $_GET['lon'];
|
||||
if (isset($_GET['zoom'])) $sOutQuery .= '/'.$_GET['zoom'];
|
||||
} else {
|
||||
$sOutQuery = $sQuery;
|
||||
}
|
||||
@@ -36,15 +28,13 @@ function logStart(&$oDB, $sType = '', $sQuery = '', $aLanguageList = array())
|
||||
);
|
||||
|
||||
if (CONST_Log_DB) {
|
||||
if (isset($_GET['email'])) {
|
||||
if (isset($_GET['email']))
|
||||
$sUserAgent = $_GET['email'];
|
||||
} elseif (isset($_SERVER['HTTP_REFERER'])) {
|
||||
elseif (isset($_SERVER['HTTP_REFERER']))
|
||||
$sUserAgent = $_SERVER['HTTP_REFERER'];
|
||||
} elseif (isset($_SERVER['HTTP_USER_AGENT'])) {
|
||||
elseif (isset($_SERVER['HTTP_USER_AGENT']))
|
||||
$sUserAgent = $_SERVER['HTTP_USER_AGENT'];
|
||||
} else {
|
||||
$sUserAgent = '';
|
||||
}
|
||||
else $sUserAgent = '';
|
||||
$sSQL = 'insert into new_query_log (type,starttime,query,ipaddress,useragent,language,format,searchterm)';
|
||||
$sSQL .= ' values (';
|
||||
$sSQL .= join(',', $oDB->getDBQuotedList(array(
|
||||
@@ -70,9 +60,7 @@ function logEnd(&$oDB, $hLog, $iNumResults)
|
||||
|
||||
if (CONST_Log_DB) {
|
||||
$aEndTime = explode('.', $fEndTime);
|
||||
if (!$aEndTime[1]) {
|
||||
$aEndTime[1] = '0';
|
||||
}
|
||||
if (!$aEndTime[1]) $aEndTime[1] = '0';
|
||||
$sEndTime = date('Y-m-d H:i:s', $aEndTime[0]).'.'.$aEndTime[1];
|
||||
|
||||
$sSQL = 'update new_query_log set endtime = '.$oDB->getDBQuoted($sEndTime).', results = '.$iNumResults;
|
||||
73
lib/output.php
Normal file
73
lib/output.php
Normal file
@@ -0,0 +1,73 @@
|
||||
<?php
|
||||
|
||||
|
||||
function formatOSMType($sType, $bIncludeExternal = true)
|
||||
{
|
||||
if ($sType == 'N') return 'node';
|
||||
if ($sType == 'W') return 'way';
|
||||
if ($sType == 'R') return 'relation';
|
||||
|
||||
if (!$bIncludeExternal) return '';
|
||||
|
||||
if ($sType == 'T') return 'way';
|
||||
if ($sType == 'I') return 'way';
|
||||
|
||||
// not handled: P, L
|
||||
|
||||
return '';
|
||||
}
|
||||
|
||||
function osmLink($aFeature, $sRefText = false)
|
||||
{
|
||||
$sOSMType = formatOSMType($aFeature['osm_type'], false);
|
||||
if ($sOSMType) {
|
||||
return '<a href="//www.openstreetmap.org/'.$sOSMType.'/'.$aFeature['osm_id'].'">'.$sOSMType.' '.($sRefText?$sRefText:$aFeature['osm_id']).'</a>';
|
||||
}
|
||||
return '';
|
||||
}
|
||||
|
||||
function wikipediaLink($aFeature)
|
||||
{
|
||||
if ($aFeature['wikipedia']) {
|
||||
list($sLanguage, $sArticle) = explode(':', $aFeature['wikipedia']);
|
||||
return '<a href="https://'.$sLanguage.'.wikipedia.org/wiki/'.urlencode($sArticle).'" target="_blank">'.$aFeature['wikipedia'].'</a>';
|
||||
}
|
||||
return '';
|
||||
}
|
||||
|
||||
function detailsLink($aFeature, $sTitle = false, $sExtraProperties = false)
|
||||
{
|
||||
if (!$aFeature['place_id']) return '';
|
||||
|
||||
$sHtml = '<a ';
|
||||
if ($sExtraProperties) {
|
||||
$sHtml .= $sExtraProperties.' ';
|
||||
}
|
||||
|
||||
$sHtml .= 'href="details.php?place_id='.$aFeature['place_id'].'">'.($sTitle?$sTitle:$aFeature['place_id']).'</a>';
|
||||
|
||||
return $sHtml;
|
||||
}
|
||||
|
||||
function detailsPermaLink($aFeature, $sRefText = false, $sExtraProperties = false)
|
||||
{
|
||||
$sOSMType = formatOSMType($aFeature['osm_type'], false);
|
||||
|
||||
if ($sOSMType) {
|
||||
$sHtml = '<a ';
|
||||
if ($sExtraProperties) {
|
||||
$sHtml .= $sExtraProperties.' ';
|
||||
}
|
||||
$sHtml .= 'href="details.php?osmtype='.$aFeature['osm_type']
|
||||
.'&osmid='.$aFeature['osm_id'].'&class='.$aFeature['class'].'">';
|
||||
|
||||
if ($sRefText) {
|
||||
$sHtml .= $sRefText.'</a>';
|
||||
} else {
|
||||
$sHtml .= $sOSMType.' '.$aFeature['osm_id'].'</a>';
|
||||
}
|
||||
|
||||
return $sHtml;
|
||||
}
|
||||
return detailsLink($aFeature, $sRefText, $sExtraProperties);
|
||||
}
|
||||
98
lib/setup/AddressLevelParser.php
Normal file
98
lib/setup/AddressLevelParser.php
Normal file
@@ -0,0 +1,98 @@
|
||||
<?php
|
||||
|
||||
namespace Nominatim\Setup;
|
||||
|
||||
/**
|
||||
* Parses an address level description.
|
||||
*/
|
||||
class AddressLevelParser
|
||||
{
|
||||
private $aLevels;
|
||||
|
||||
public function __construct($sDescriptionFile)
|
||||
{
|
||||
$sJson = file_get_contents($sDescriptionFile);
|
||||
$this->aLevels = json_decode($sJson, true);
|
||||
if (!$this->aLevels) {
|
||||
switch (json_last_error()) {
|
||||
case JSON_ERROR_NONE:
|
||||
break;
|
||||
case JSON_ERROR_DEPTH:
|
||||
fail('JSON error - Maximum stack depth exceeded');
|
||||
break;
|
||||
case JSON_ERROR_STATE_MISMATCH:
|
||||
fail('JSON error - Underflow or the modes mismatch');
|
||||
break;
|
||||
case JSON_ERROR_CTRL_CHAR:
|
||||
fail('JSON error - Unexpected control character found');
|
||||
break;
|
||||
case JSON_ERROR_SYNTAX:
|
||||
fail('JSON error - Syntax error, malformed JSON');
|
||||
break;
|
||||
case JSON_ERROR_UTF8:
|
||||
fail('JSON error - Malformed UTF-8 characters, possibly incorrectly encoded');
|
||||
break;
|
||||
default:
|
||||
fail('JSON error - Unknown error');
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Dump the description into a database table.
|
||||
*
|
||||
* @param object $oDB Database conneciton to use.
|
||||
* @param string $sTable Name of table to create.
|
||||
*
|
||||
* @return null
|
||||
*
|
||||
* A new table is created. Any previously existing table is dropped.
|
||||
* The table has the following columns:
|
||||
* country, class, type, rank_search, rank_address.
|
||||
*/
|
||||
public function createTable($oDB, $sTable)
|
||||
{
|
||||
$oDB->exec('DROP TABLE IF EXISTS '.$sTable);
|
||||
$sSql = 'CREATE TABLE '.$sTable;
|
||||
$sSql .= '(country_code varchar(2), class TEXT, type TEXT,';
|
||||
$sSql .= ' rank_search SMALLINT, rank_address SMALLINT)';
|
||||
$oDB->exec($sSql);
|
||||
|
||||
$sSql = 'CREATE UNIQUE INDEX ON '.$sTable.' (country_code, class, type)';
|
||||
$oDB->exec($sSql);
|
||||
|
||||
$sSql = 'INSERT INTO '.$sTable.' VALUES ';
|
||||
foreach ($this->aLevels as $aLevel) {
|
||||
$aCountries = array();
|
||||
if (isset($aLevel['countries'])) {
|
||||
foreach ($aLevel['countries'] as $sCountry) {
|
||||
$aCountries[$sCountry] = $oDB->getDBQuoted($sCountry);
|
||||
}
|
||||
} else {
|
||||
$aCountries['NULL'] = 'NULL';
|
||||
}
|
||||
foreach ($aLevel['tags'] as $sKey => $aValues) {
|
||||
foreach ($aValues as $sValue => $mRanks) {
|
||||
$aFields = array(
|
||||
$oDB->getDBQuoted($sKey),
|
||||
$sValue ? $oDB->getDBQuoted($sValue) : 'NULL'
|
||||
);
|
||||
if (is_array($mRanks)) {
|
||||
$aFields[] = (string) $mRanks[0];
|
||||
$aFields[] = (string) $mRanks[1];
|
||||
} else {
|
||||
$aFields[] = (string) $mRanks;
|
||||
$aFields[] = (string) $mRanks;
|
||||
}
|
||||
$sLine = ','.join(',', $aFields).'),';
|
||||
|
||||
foreach ($aCountries as $sCountries) {
|
||||
$sSql .= '('.$sCountries.$sLine;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
$oDB->exec(rtrim($sSql, ','));
|
||||
}
|
||||
}
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user