Compare commits

..

4 Commits

Author SHA1 Message Date
Sarah Hoffmann
a3343ab048 fix package name in Centos 7 vagrant script
Fixes #2531.
2021-12-06 15:45:09 +01:00
Sarah Hoffmann
517eb52352 prepare 4.0.1 release 2021-11-22 16:23:19 +01:00
Sarah Hoffmann
02bd1bad2d add a section about moving the database to another machine 2021-11-22 16:17:47 +01:00
Sarah Hoffmann
8d7afbfd4f adapt to release 4.0.0 2021-11-02 20:58:07 +01:00
706 changed files with 10284 additions and 63366 deletions

2
.github/FUNDING.yml vendored
View File

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

View File

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

View File

@@ -1,48 +1,38 @@
name: 'Build Nominatim'
inputs:
flavour:
ubuntu:
description: 'Version of Ubuntu to install on'
required: false
default: 'ubuntu-20'
cmake-args:
description: 'Additional options to hand to cmake'
required: false
default: ''
lua:
description: 'Version of Lua to use'
required: false
default: '5.3'
default: '20'
runs:
using: "composite"
steps:
- name: Clean out the disk
- name: Install prerequisites
run: |
sudo rm -rf /opt/hostedtoolcache/go /opt/hostedtoolcache/CodeQL /usr/lib/jvm /usr/local/share/chromium /usr/local/lib/android
df -h
shell: bash
- name: Install${{ matrix.flavour }} prerequisites
run: |
sudo apt-get install -y -qq libboost-system-dev libboost-filesystem-dev libexpat1-dev zlib1g-dev libbz2-dev libpq-dev libproj-dev libicu-dev liblua${LUA_VERSION}-dev lua${LUA_VERSION} lua-dkjson nlohmann-json3-dev
if [ "$FLAVOUR" == "oldstuff" ]; then
pip3 install MarkupSafe==2.0.1 python-dotenv psycopg2==2.7.7 jinja2==2.8 psutil==5.4.2 pyicu==2.9 osmium PyYAML==5.1 sqlalchemy==1.4.31 datrie asyncpg
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
pip3 install sqlalchemy psycopg
fi
shell: bash
env:
FLAVOUR: ${{ inputs.flavour }}
CMAKE_ARGS: ${{ inputs.cmake-args }}
LUA_VERSION: ${{ inputs.lua }}
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
shell: bash
- name: Configure
run: mkdir build && cd build && cmake $CMAKE_ARGS ../Nominatim
run: mkdir build && cd build && cmake ../Nominatim
shell: bash
env:
CMAKE_ARGS: ${{ inputs.cmake-args }}
- name: Build
run: |

View File

@@ -15,16 +15,14 @@ runs:
- name: Remove existing PostgreSQL
run: |
sudo apt-get purge -yq postgresql*
sudo apt install curl ca-certificates gnupg
curl https://www.postgresql.org/media/keys/ACCC4CF8.asc | gpg --dearmor | sudo tee /etc/apt/trusted.gpg.d/apt.postgresql.org.gpg >/dev/null
sudo sh -c 'echo "deb https://apt.postgresql.org/pub/repos/apt $(lsb_release -cs)-pgdg main" > /etc/apt/sources.list.d/pgdg.list'
sudo sh -c 'echo "deb http://apt.postgresql.org/pub/repos/apt $(lsb_release -cs)-pgdg main" > /etc/apt/sources.list.d/pgdg.list'
sudo apt-get update -qq
shell: bash
- name: Install PostgreSQL
run: |
sudo apt-get install -y -qq --no-install-suggests --no-install-recommends postgresql-client-${PGVER} postgresql-${PGVER}-postgis-${POSTGISVER} postgresql-${PGVER}-postgis-${POSTGISVER}-scripts postgresql-contrib-${PGVER} postgresql-${PGVER}
sudo apt-get install -y -qq --no-install-suggests --no-install-recommends postgresql-client-${PGVER} postgresql-${PGVER}-postgis-${POSTGISVER} postgresql-${PGVER}-postgis-${POSTGISVER}-scripts postgresql-contrib-${PGVER} postgresql-${PGVER} postgresql-server-dev-${PGVER}
shell: bash
env:
PGVER: ${{ inputs.postgresql-version }}

View File

@@ -7,11 +7,11 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/checkout@v2
with:
submodules: true
- uses: actions/cache@v3
- uses: actions/cache@v2
with:
path: |
data/country_osm_grid.sql.gz
@@ -27,7 +27,7 @@ jobs:
mv nominatim-src.tar.bz2 Nominatim
- name: 'Upload Artifact'
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v2
with:
name: full-source
path: nominatim-src.tar.bz2
@@ -37,31 +37,23 @@ jobs:
needs: create-archive
strategy:
matrix:
flavour: [oldstuff, "ubuntu-20", "ubuntu-22"]
ubuntu: [18, 20]
include:
- flavour: oldstuff
ubuntu: 20
postgresql: '9.6'
postgis: '2.5'
php: '7.3'
lua: '5.1'
- flavour: ubuntu-20
ubuntu: 20
- ubuntu: 18
postgresql: 9.5
postgis: 2.5
pytest: pytest
php: 7.2
- ubuntu: 20
postgresql: 13
postgis: 3
php: '7.4'
lua: '5.3'
- flavour: ubuntu-22
ubuntu: 22
postgresql: 15
postgis: 3
php: '8.1'
lua: '5.3'
pytest: py.test-3
php: 7.4
runs-on: ubuntu-${{ matrix.ubuntu }}.04
steps:
- uses: actions/download-artifact@v3
- uses: actions/download-artifact@v2
with:
name: full-source
@@ -72,15 +64,13 @@ jobs:
uses: shivammathur/setup-php@v2
with:
php-version: ${{ matrix.php }}
tools: phpunit:9, phpcs, composer
ini-values: opcache.jit=disable
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
coverage: xdebug
tools: phpunit, phpcs, composer
- uses: actions/setup-python@v4
- uses: actions/setup-python@v2
with:
python-version: 3.7
if: matrix.flavour == 'oldstuff'
python-version: 3.6
if: matrix.ubuntu == 18
- uses: ./Nominatim/.github/actions/setup-postgresql
with:
@@ -89,71 +79,78 @@ jobs:
- uses: ./Nominatim/.github/actions/build-nominatim
with:
flavour: ${{ matrix.flavour }}
lua: ${{ matrix.lua }}
ubuntu: ${{ matrix.ubuntu }}
- name: Install test prerequsites (behave from apt)
run: sudo apt-get install -y -qq python3-behave
if: matrix.flavour == 'ubuntu-20'
- 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
- name: Install test prerequsites (behave from pip)
run: pip3 install behave==1.2.6
if: (matrix.flavour == 'oldstuff') || (matrix.flavour == 'ubuntu-22')
- name: Install test prerequsites (from apt for Ununtu 2x)
run: sudo apt-get install -y -qq python3-pytest python3-pytest-asyncio uvicorn
if: matrix.flavour != 'oldstuff'
- name: Install newer pytest-asyncio
run: pip3 install -U pytest-asyncio
if: matrix.flavour == 'ubuntu-20'
- name: Install test prerequsites (from pip for Ubuntu 18)
run: pip3 install pytest pytest-asyncio uvicorn
if: matrix.flavour == 'oldstuff'
- name: Install Python webservers
run: pip3 install falcon starlette
- name: Install latest pylint
run: pip3 install -U pylint asgi_lifespan
- name: Install test prerequsites
run: pip3 install pylint==2.6.0 pytest pytest-cov behave==1.2.6
if: matrix.ubuntu == 18
- name: PHP linting
run: phpcs --report-width=120 .
working-directory: Nominatim
- name: Python linting
run: python3 -m pylint nominatim
run: pylint nominatim
working-directory: Nominatim
- name: PHP unit tests
run: phpunit ./
run: phpunit --coverage-clover ../../coverage-php.xml ./
working-directory: Nominatim/test/php
if: matrix.ubuntu == 20
- name: Python unit tests
run: python3 -m pytest test/python
run: $PYTEST --cov=nominatim --cov-report=xml test/python
working-directory: Nominatim
env:
PYTEST: ${{ matrix.pytest }}
- name: BDD tests
run: |
python3 -m behave -DREMOVE_TEMPLATE=1 -DBUILDDIR=$GITHUB_WORKSPACE/build --format=progress3
mkdir cov
behave -DREMOVE_TEMPLATE=1 -DBUILDDIR=$GITHUB_WORKSPACE/build --format=progress3 -DPHPCOV=./cov
composer require phpunit/phpcov:7.0.2
vendor/bin/phpcov merge --clover ../../coverage-bdd.xml ./cov
working-directory: Nominatim/test/bdd
if: matrix.ubuntu == 20
- name: Install mypy and typechecking info
run: pip3 install -U mypy osmium uvicorn types-PyYAML types-jinja2 types-psycopg2 types-psutil types-requests types-ujson types-Pygments typing-extensions
if: matrix.flavour != 'oldstuff'
- name: BDD tests
run: |
behave -DREMOVE_TEMPLATE=1 -DBUILDDIR=$GITHUB_WORKSPACE/build --format=progress3
working-directory: Nominatim/test/bdd
if: matrix.ubuntu == 18
- name: Python static typechecking
run: python3 -m mypy --strict nominatim
working-directory: Nominatim
if: matrix.flavour != 'oldstuff'
- 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
legacy-test:
icu-test:
needs: create-archive
runs-on: ubuntu-20.04
strategy:
matrix:
ubuntu: [20]
include:
- ubuntu: 20
postgresql: 13
postgis: 3
pytest: py.test-3
php: 7.4
runs-on: ubuntu-${{ matrix.ubuntu }}.04
steps:
- uses: actions/download-artifact@v3
- uses: actions/download-artifact@v2
with:
name: full-source
@@ -163,59 +160,35 @@ jobs:
- name: Setup PHP
uses: shivammathur/setup-php@v2
with:
php-version: '7.4'
php-version: ${{ matrix.php }}
coverage: xdebug
tools: phpunit, phpcs, composer
- uses: actions/setup-python@v2
with:
python-version: 3.6
if: matrix.ubuntu == 18
- uses: ./Nominatim/.github/actions/setup-postgresql
with:
postgresql-version: 13
postgis-version: 3
- name: Install Postgresql server dev
run: sudo apt-get install postgresql-server-dev-13
postgresql-version: ${{ matrix.postgresql }}
postgis-version: ${{ matrix.postgis }}
- uses: ./Nominatim/.github/actions/build-nominatim
with:
cmake-args: -DBUILD_MODULE=on
ubuntu: ${{ matrix.ubuntu }}
- name: Install test prerequsites
run: sudo apt-get install -y -qq python3-behave
- name: BDD tests (legacy tokenizer)
run: |
python3 -m behave -DREMOVE_TEMPLATE=1 -DBUILDDIR=$GITHUB_WORKSPACE/build -DTOKENIZER=legacy --format=progress3
working-directory: Nominatim/test/bdd
python-api-test:
needs: create-archive
runs-on: ubuntu-22.04
steps:
- uses: actions/download-artifact@v3
with:
name: full-source
- name: Unpack Nominatim
run: tar xf nominatim-src.tar.bz2
- uses: ./Nominatim/.github/actions/setup-postgresql
with:
postgresql-version: 15
postgis-version: 3
- uses: ./Nominatim/.github/actions/build-nominatim
with:
flavour: 'ubuntu-22'
if: matrix.ubuntu == 20
- name: Install test prerequsites
run: sudo apt-get install -y -qq python3-behave
run: pip3 install behave==1.2.6
if: matrix.ubuntu == 18
- name: Install Python webservers
run: pip3 install starlette asgi_lifespan httpx
- name: BDD tests (starlette)
- name: BDD tests (icu tokenizer)
run: |
python3 -m behave -DREMOVE_TEMPLATE=1 -DBUILDDIR=$GITHUB_WORKSPACE/build -DAPI_ENGINE=starlette --format=progress3
behave -DREMOVE_TEMPLATE=1 -DBUILDDIR=$GITHUB_WORKSPACE/build -DTOKENIZER=icu --format=progress3
working-directory: Nominatim/test/bdd
@@ -225,16 +198,21 @@ jobs:
strategy:
matrix:
name: [Ubuntu-20, Ubuntu-22]
name: [Ubuntu-18, Ubuntu-20, Centos-8]
include:
- name: Ubuntu-18
flavour: ubuntu
image: "ubuntu:18.04"
ubuntu: 18
install_mode: install-nginx
- name: Ubuntu-20
flavour: ubuntu
image: "ubuntu:20.04"
ubuntu: 20
install_mode: install-apache
- name: Ubuntu-22
image: "ubuntu:22.04"
ubuntu: 22
install_mode: install-apache
- name: Centos-8
flavour: centos
image: "centos:8"
container:
image: ${{ matrix.image }}
@@ -254,6 +232,14 @@ jobs:
apt-get install -y git sudo wget
ln -snf /usr/share/zoneinfo/$CONTAINER_TIMEZONE /etc/localtime && echo $CONTAINER_TIMEZONE > /etc/timezone
shell: bash
if: matrix.flavour == 'ubuntu'
- name: Prepare container (CentOS)
run: |
dnf update -y
dnf install -y sudo glibc-langpack-en
shell: bash
if: matrix.flavour == 'centos'
- name: Setup import user
run: |
@@ -265,7 +251,7 @@ jobs:
OS: ${{ matrix.name }}
INSTALL_MODE: ${{ matrix.install_mode }}
- uses: actions/download-artifact@v3
- uses: actions/download-artifact@v2
with:
name: full-source
path: /home/nominatim
@@ -283,24 +269,17 @@ jobs:
- name: Prepare import environment
run: |
mv Nominatim/test/testdb/apidb-test-data.pbf test.pbf
mv Nominatim/settings/flex-base.lua flex-base.lua
mv Nominatim/settings/import-extratags.lua import-extratags.lua
mv Nominatim/settings/taginfo.lua taginfo.lua
rm -rf Nominatim
mkdir data-env-reverse
working-directory: /home/nominatim
- name: Print version
run: nominatim --version
working-directory: /home/nominatim/nominatim-project
- name: Print taginfo
run: lua taginfo.lua
- name: Prepare import environment (CentOS)
run: |
sudo ln -s /usr/local/bin/nominatim /usr/bin/nominatim
echo NOMINATIM_DATABASE_WEBUSER="apache" > nominatim-project/.env
cp nominatim-project/.env data-env-reverse/.env
working-directory: /home/nominatim
- name: Collect host OS information
run: nominatim admin --collect-os-info
working-directory: /home/nominatim/nominatim-project
if: matrix.flavour == 'centos'
- name: Import
run: nominatim import --osm-file ../test.pbf
@@ -321,6 +300,7 @@ jobs:
- name: Prepare update (Ubuntu)
run: apt-get install -y python3-pip
shell: bash
if: matrix.flavour == 'ubuntu'
- name: Run update
run: |
@@ -329,20 +309,12 @@ jobs:
NOMINATIM_REPLICATION_MAX_DIFF=1 nominatim replication --once
working-directory: /home/nominatim/nominatim-project
- name: Clean up database
run: nominatim refresh --postcodes --word-tokens
working-directory: /home/nominatim/nominatim-project
- name: Run reverse-only import
run : |
echo 'NOMINATIM_DATABASE_DSN="pgsql:dbname=reverse"' >> .env
nominatim import --osm-file ../test.pbf --reverse-only --no-updates
working-directory: /home/nominatim/data-env-reverse
- name: Check reverse-only import
- name: Check reverse import
run: nominatim admin --check-database
working-directory: /home/nominatim/data-env-reverse
- name: Clean up database (reverse-only import)
run: nominatim refresh --postcodes --word-tokens
working-directory: /home/nominatim/nominatim-project

View File

@@ -1,23 +0,0 @@
[mypy]
plugins = sqlalchemy.ext.mypy.plugin
[mypy-sanic_cors.*]
ignore_missing_imports = True
[mypy-icu.*]
ignore_missing_imports = True
[mypy-asyncpg.*]
ignore_missing_imports = True
[mypy-datrie.*]
ignore_missing_imports = True
[mypy-dotenv.*]
ignore_missing_imports = True
[mypy-falcon.*]
ignore_missing_imports = True
[mypy-geoalchemy2.*]
ignore_missing_imports = True

View File

@@ -1,6 +1,6 @@
[MASTER]
extension-pkg-whitelist=osmium,falcon
extension-pkg-whitelist=osmium
ignored-modules=icu,datrie
[MESSAGES CONTROL]
@@ -10,9 +10,6 @@ ignored-modules=icu,datrie
# closing added here because it sometimes triggers a false positive with
# 'with' statements.
ignored-classes=NominatimArgs,closing
# 'too-many-ancestors' is triggered already by deriving from UserDict
# 'not-context-manager' disabled because it causes false positives once
# typed Python is enabled. See also https://github.com/PyCQA/pylint/issues/5273
disable=too-few-public-methods,duplicate-code,too-many-ancestors,bad-option-value,no-self-use,not-context-manager,use-dict-literal,chained-comparison,attribute-defined-outside-init
disable=too-few-public-methods,duplicate-code
good-names=i,j,x,y,m,t,fd,db,cc,x1,x2,y1,y2,pt,k,v,nr
good-names=i,x,y,fd,db

16
AUTHORS
View File

@@ -1,15 +1,15 @@
Nominatim was written by:
* Brian Quinion
* Sarah Hoffmann
* Marc Tobias Metten
Brian Quinion
Sarah Hoffmann
Marc Tobias Metten
* markigail
* AntoJvlt
* gemo1011
* darkshredder
markigail
gemo1011
IrlJidel
Frederik Ramm
and many more.
For a full list of contributors see the Git logs or visit
For a full list of contributors see
https://github.com/openstreetmap/Nominatim/graphs/contributors

View File

@@ -19,24 +19,13 @@ list(APPEND CMAKE_MODULE_PATH "${CMAKE_SOURCE_DIR}/cmake")
project(nominatim)
set(NOMINATIM_VERSION_MAJOR 4)
set(NOMINATIM_VERSION_MINOR 3)
set(NOMINATIM_VERSION_PATCH 1)
set(NOMINATIM_VERSION_MINOR 0)
set(NOMINATIM_VERSION_PATCH 0)
set(NOMINATIM_VERSION "${NOMINATIM_VERSION_MAJOR}.${NOMINATIM_VERSION_MINOR}.${NOMINATIM_VERSION_PATCH}")
add_definitions(-DNOMINATIM_VERSION="${NOMINATIM_VERSION}")
# Setting GIT_HASH
find_package(Git)
if (GIT_FOUND)
execute_process(
COMMAND "${GIT_EXECUTABLE}" log -1 --format=%h
WORKING_DIRECTORY ${CMAKE_CURRENT_LIST_DIR}
OUTPUT_VARIABLE GIT_HASH
OUTPUT_STRIP_TRAILING_WHITESPACE
ERROR_QUIET
)
endif()
#-----------------------------------------------------------------------------
# Configuration
@@ -44,7 +33,7 @@ endif()
set(BUILD_IMPORTER on CACHE BOOL "Build everything for importing/updating the database")
set(BUILD_API on CACHE BOOL "Build everything for the API server")
set(BUILD_MODULE off CACHE BOOL "Build PostgreSQL module for legacy tokenizer")
set(BUILD_MODULE on CACHE BOOL "Build PostgreSQL module")
set(BUILD_TESTS on CACHE BOOL "Build test suite")
set(BUILD_DOCS on CACHE BOOL "Build documentation")
set(BUILD_MANPAGE on CACHE BOOL "Build Manual Page")
@@ -63,6 +52,7 @@ if (BUILD_IMPORTER AND BUILD_OSM2PGSQL)
endif()
set(BUILD_TESTS_SAVED "${BUILD_TESTS}")
set(BUILD_TESTS off)
set(WITH_LUA off CACHE BOOL "")
add_subdirectory(osm2pgsql)
set(BUILD_TESTS ${BUILD_TESTS_SAVED})
endif()
@@ -73,7 +63,7 @@ endif()
#-----------------------------------------------------------------------------
if (BUILD_IMPORTER)
find_package(PythonInterp 3.7 REQUIRED)
find_package(PythonInterp 3.6 REQUIRED)
endif()
#-----------------------------------------------------------------------------
@@ -92,6 +82,16 @@ if (BUILD_API OR BUILD_IMPORTER)
else()
message (STATUS "Using PHP binary " ${PHP_BIN})
endif()
if (NOT PHPCGI_BIN)
find_program (PHPCGI_BIN php-cgi)
endif()
# sanity check if PHP binary exists
if (NOT EXISTS ${PHPCGI_BIN})
message(WARNING "php-cgi binary not found. nominatim tool will not provide query functions.")
set (PHPCGI_BIN "")
else()
message (STATUS "Using php-cgi binary " ${PHPCGI_BIN})
endif()
endif()
#-----------------------------------------------------------------------------
@@ -223,17 +223,11 @@ if (BUILD_IMPORTER)
install(DIRECTORY nominatim
DESTINATION ${NOMINATIM_LIBDIR}/lib-python
FILES_MATCHING PATTERN "*.py"
PATTERN "paths.py" EXCLUDE
PATTERN __pycache__ EXCLUDE)
configure_file(${PROJECT_SOURCE_DIR}/cmake/paths-py.tmpl paths-py.installed)
install(FILES ${PROJECT_BINARY_DIR}/paths-py.installed
DESTINATION ${NOMINATIM_LIBDIR}/lib-python/nominatim
RENAME paths.py)
install(DIRECTORY lib-sql DESTINATION ${NOMINATIM_LIBDIR})
install(FILES ${COUNTRY_GRID_FILE}
install(FILES data/country_name.sql
${COUNTRY_GRID_FILE}
data/words.sql
DESTINATION ${NOMINATIM_DATADIR})
endif()
@@ -261,20 +255,17 @@ endif()
install(FILES settings/env.defaults
settings/address-levels.json
settings/phrase-settings.json
settings/import-admin.lua
settings/import-street.lua
settings/import-address.lua
settings/import-full.lua
settings/import-extratags.lua
settings/flex-base.lua
settings/import-admin.style
settings/import-street.style
settings/import-address.style
settings/import-full.style
settings/import-extratags.style
settings/icu_tokenizer.yaml
settings/country_settings.yaml
DESTINATION ${NOMINATIM_CONFIGDIR})
install(DIRECTORY settings/icu-rules
DESTINATION ${NOMINATIM_CONFIGDIR})
install(DIRECTORY settings/country-names
DESTINATION ${NOMINATIM_CONFIGDIR})
if (INSTALL_MUNIN_PLUGINS)
install(FILES munin/nominatim_importlag

View File

@@ -36,7 +36,7 @@ Nominatim historically hasn't followed a particular coding style but we
are in process of consolidating the style. The following rules apply:
* Python code uses the official Python style
* indentation
* indention
* SQL use 2 spaces
* all other file types use 4 spaces
* [BSD style](https://en.wikipedia.org/wiki/Indent_style#Allman_style) for braces
@@ -64,39 +64,3 @@ Before submitting a pull request make sure that the tests pass:
cd build
make test
```
## Releases
Nominatim follows semantic versioning. Major releases are done for large changes
that require (or at least strongly recommend) a reimport of the databases.
Minor releases can usually be applied to exisiting databases. Patch releases
contain bug fixes only and are released from a separate branch where the
relevant changes are cherry-picked from the master branch.
Checklist for releases:
* [ ] increase version in `nominatim/version.py` and CMakeLists.txt
* [ ] update `ChangeLog` (copy information from patch releases from release branch)
* [ ] complete `docs/admin/Migration.md`
* [ ] update EOL dates in `SECURITY.md`
* [ ] commit and make sure CI tests pass
* [ ] test migration
* download, build and import previous version
* migrate using master version
* run updates using master version
* [ ] prepare tarball:
* `git clone --recursive https://github.com/osm-search/Nominatim` (switch to right branch!)
* `rm -r .git* osm2pgsql/.git*`
* copy country data into `data/`
* add version to base directory and package
* [ ] upload tarball to https://nominatim.org
* [ ] prepare documentation
* check out new docs branch
* change git checkout instructions to tarball download instructions or adapt version on existing ones
* build documentation and copy to https://github.com/osm-search/nominatim-org-site
* add new version to history
* [ ] check release tarball
* download tarball as per new documentation instructions
* compile and import Nominatim
* run `nominatim --version` to confirm correct version
* [ ] tag new release and add a release on github.com

144
ChangeLog
View File

@@ -1,143 +1,3 @@
4.3.1
* reintroduce result rematching
* improve search of multi-part names
* fix accidentally switched meaning of --reverse-only and --search-only in
warm command
4.3.0
* fix failing importance recalculation command
* fix merging of linked names into unnamed boundaries
* fix a number of corner cases with interpolation splitting resulting in
invalid geometries
* fix failure in website generation when password contains curly brackets
* fix broken use of ST_Project in PostGIS 3.4
* new NOMINATIM_SEARCH_WITHIN_COUNTRIES setting to restrict reverse lookups
to known countries (thanks @alfmarcua)
* allow negative OSM IDs (thanks @alfmarcua)
* disallow import of Tiger data in a frozen DB
* avoid UPDATE to change settings to be compatible with r/o DBs (thanks @t-tomek)
* update bundled osm2pgsql to 1.9.2
* reorganise osm2pgsql flex style and make it the default
* exclude names ending in :wikipedia from indexing
* no longer accept comma as a list separator in name tags
* process forward dependencies on update to catch updates in geometries
of ways and relations
* fix handling of isolated silent letters during transliteration
* no longer assign postcodes to large linear features like rivers
* introduce nominatim.paths module for finding data and libraries
* documentation layout changed to material theme
* new documentation section for library
* various smaller fixes to existing documentation
(thanks @woodpeck, @bloom256, @biswajit-k)
* updates to vagrant install scripts, drop support for Ubunut 18
(thanks @n-timofeev)
* removed obsolete configuration variables from env.defaults
* add script for generating a taginfo description (thanks @biswajit-k)
* modernize Python code around BDD test and add testing of Python frontend
* lots of new BDD tests for API output
4.2.3
* fix deletion handling for 'nominatim add-data'
* adapt place_force_delete() to new deletion handling
* flex style: avoid dropping of postcode areas
* fix update errors on address interpolation handling
4.2.2
* extend flex-style library to fully support all default styles
* fix handling of Hebrew aleph
* do not assign postcodes to rivers
* fix string matching in PHP code
* update osm2pgsql (various updates to flex)
* fix slow query when deleting places on update
* fix CLI details query
* fix recalculation of importance values
* fix polygon simplification in reverse results
* add class/type information to reverse geocodejson result
* minor improvements to default tokenizer configuration
* various smaller fixes to documentation
4.2.1
* fix XSS vulnerability in debug view
4.2.0
* add experimental support for osm2pgsql flex style
* introduce secondary importance value to be retrieved from a raster data file
(currently still unused, to replace address importance, thanks to @tareqpi)
* add new report tool `nominatim admin --collect-os-info`
(thanks @micahcochran, @tareqpi)
* reorganise index to improve lookup performance and size
* run index creation after import in parallel
* run ANALYZE more selectively to speed up continuation of indexing
* fix crash on update when addr:interpolation receives an illegal value
* fix minimum number of retrieved results to be at least 10
* fix search for combinations of special term + name (e.g Hotel Bellevue)
* do not return interpolations without a parent street on reverse search
* improve invalidation of linked places on updates
* fix address parsing for interpolation lines
* make sure socket timeouts are respected during replication
(working around a bug in some versions of pyosmium)
* update bundled osm2pgsql to 1.7.1
* add support for PostgreSQL 15
* typing fixes to work with latest type annotations from typeshed
* smaller improvements to documentation (thanks to @mausch)
4.1.1
* fix XSS vulnerability in debug view
4.1.0
* switch to ICU tokenizer as default
* add housenumber normalization and support optional spaces during search
* add postcode format checking and support optional spaces during search
* add function for cleaning housenumbers in word table
* add updates/deletion of country names imported from OSM
* linked places no longer overwrite names from a place permanently
* move default country name configuration into yaml file (thanks @tareqpi)
* more compact layout for interpolation and TIGER tables
* introduce mutations to ICU tokenizer (used for German umlauts)
* support reinitializing a full project directory with refresh --website
* fix various issues with linked places on updates
* add support for external sanitizers and token analyzers
* add CLI commands for forced indexing
* add CLI command for version report
* add offline import mode
* change geocodejson to return a feature class in the 'type' field
* add ISO3166-2 to address output (thanks @I70l0teN4ik)
* improve parsing and matching of addr: tags
* support relations as street members of associatedStreet
* better ranking for address results from TIGER data
* adapt rank classification to changed tag usage in OSM
* update bundled osm2pgsql to 1.6.0
* add typing information to Python code
* improve unit test coverage
* reorganise and speed up code for BDD tests, drop support for scenes
* move PHP unit tests to PHP 9.5
* extensive typo fixes in documentation (thanks @woodpeck,@StephanGeorg,
@amandasaurus, @nslxndr, @stefkiourk, @Luflosi, @kianmeng)
* drop official support for installation on CentOS
* add installation instructions for Ubuntu 22.04
* add support for PHP8
* add setup instructions for updates and systemd
* drop support for PostgreSQL 9.5
4.0.2
* fix XSS vulnerability in debug view
4.0.1
* fix initialisation error in replication script
* ICU tokenizer: avoid any special characters in word tokens
* better error message when API php script does not exist
* fix quoting of house numbers in SQL queries
* small fixes and improvements in search query parsing
* add documentation for moving the database to a different machine
4.0.0
* refactor name token computation and introduce ICU tokenizer
@@ -167,10 +27,6 @@
* add testing of installation scripts via CI
* drop support for Python < 3.6 and Postgresql < 9.5
3.7.3
* fix XSS vulnerability in debug view
3.7.2
* fix database check for reverse-only imports

View File

@@ -9,10 +9,10 @@ versions.
| Version | End of support for security updates |
| ------- | ----------------------------------- |
| 4.3.x | 2025-09-07 |
| 4.2.x | 2024-11-24 |
| 4.1.x | 2024-08-05 |
| 4.0.x | 2023-11-02 |
| 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
@@ -37,4 +37,3 @@ incident. Announcements will also be published at the
## List of Previous Incidents
* 2020-05-04 - [SQL injection issue on /details endpoint](https://lists.openstreetmap.org/pipermail/geocoding/2020-May/002012.html)
* 2023-02-21 - [cross-site scripting vulnerability](https://nominatim.org/2023/02/21/release-421.html)

View File

@@ -1,6 +1,6 @@
# Install Nominatim in a virtual machine for development and testing
This document describes how you can install Nominatim inside a Ubuntu 22
This document describes how you can install Nominatim inside a Ubuntu 16
virtual machine on your desktop/laptop (host machine). The goal is to give
you a development environment to easily edit code and run the test suite
without affecting the rest of your system.
@@ -42,9 +42,9 @@ is.
```
# inside the virtual machine:
cd nominatim-project
wget --no-verbose --output-document=monaco.osm.pbf http://download.geofabrik.de/europe/monaco-latest.osm.pbf
nominatim import --osm-file monaco.osm.pbf 2>&1 | tee monaco.$$.log
cd build
wget --no-verbose --output-document=/tmp/monaco.osm.pbf http://download.geofabrik.de/europe/monaco-latest.osm.pbf
./utils/setup.php --osm-file /tmp/monaco.osm.pbf --osm2pgsql-cache 1000 --all 2>&1 | tee monaco.$$.log
```
To repeat an import you'd need to delete the database first
@@ -56,7 +56,7 @@ is.
## Development
Vagrant maps the virtual machine's port 8089 to your host machine. Thus you can
see Nominatim in action on [localhost:8089](http://localhost:8089/nominatim/).
see Nominatim in action on [locahost:8089](http://localhost:8089/nominatim/).
You edit code on your host machine in any editor you like. There is no need to
restart any software: just refresh your browser window.
@@ -69,7 +69,8 @@ installation.
PHP errors are written to `/var/log/apache2/error.log`.
With `echo` and `var_dump()` you write into the output (HTML/XML/JSON) when
you either add `&debug=1` to the URL.
you either add `&debug=1` to the URL (preferred) or set
`@define('CONST_Debug', true);` in `settings/local.php`.
In the Python BDD test you can use `logger.info()` for temporary debug
statements.
@@ -129,10 +130,6 @@ and then
Yes, Vagrant and Virtualbox can be installed on MS Windows just fine. You need a 64bit
version of Windows.
##### Will it run on Apple Silicon?
You might need to replace Virtualbox with [Parallels](https://www.parallels.com/products/desktop/).
There is no free/open source version of Parallels.
##### Why Monaco, can I use another country?
@@ -144,12 +141,11 @@ No. Long running Nominatim installations will differ once new import features (o
bug fixes) get added since those usually only get applied to new/changed data.
Also this document skips the optional Wikipedia data import which affects ranking
of search results. See [Nominatim installation](https://nominatim.org/release-docs/latest/admin/Installation)
for details.
of search results. See [Nominatim installation](https://nominatim.org/release-docs/latest/admin/Installation) for details.
##### Why Ubuntu? Can I test CentOS/Fedora/CoreOS/FreeBSD?
There used to be a Vagrant script for CentOS available, but the Nominatim directory
There is a Vagrant script for CentOS available, but the Nominatim directory
isn't symlinked/mounted to the host which makes development trickier. We used
it mainly for debugging installation with SELinux.
@@ -158,17 +154,14 @@ are slightly different, e.g. the name of the package manager, Apache2 package
name, location of files. We chose Ubuntu because that is closest to the
nominatim.openstreetmap.org production environment.
You can configure/download other Vagrant boxes from
[https://app.vagrantup.com/boxes/search](https://app.vagrantup.com/boxes/search).
You can configure/download other Vagrant boxes from [https://app.vagrantup.com/boxes/search](https://app.vagrantup.com/boxes/search).
##### How can I connect to an existing database?
Let's say you have a Postgres database named `nominatim_it` on server `your-server.com`
and port `5432`. The Postgres username is `postgres`. You can edit the `.env` in your
project directory and point Nominatim to it.
NOMINATIM_DATABASE_DSN="pgsql:host=your-server.com;port=5432;user=postgres;dbname=nominatim_it
Let's say you have a Postgres database named `nominatim_it` on server `your-server.com` and port `5432`. The Postgres username is `postgres`. You can edit `settings/local.php` and point Nominatim to it.
pgsql:host=your-server.com;port=5432;user=postgres;dbname=nominatim_it
No data import or restarting necessary.
If the Postgres installation is behind a firewall, you can try
@@ -176,12 +169,11 @@ If the Postgres installation is behind a firewall, you can try
ssh -L 9999:localhost:5432 your-username@your-server.com
inside the virtual machine. It will map the port to `localhost:9999` and then
you edit `.env` file with
you edit `settings/local.php` with
NOMINATIM_DATABASE_DSN="pgsql:host=localhost;port=9999;user=postgres;dbname=nominatim_it"
@define('CONST_Database_DSN', 'pgsql:host=localhost;port=9999;user=postgres;dbname=nominatim_it');
To access postgres directly remember to specify the hostname,
e.g. `psql --host localhost --port 9999 nominatim_it`
To access postgres directly remember to specify the hostname, e.g. `psql --host localhost --port 9999 nominatim_it`
##### My computer is slow and the import takes too long. Can I start the virtual machine "in the cloud"?

88
Vagrantfile vendored
View File

@@ -17,14 +17,6 @@ Vagrant.configure("2") do |config|
checkout = "no"
end
config.vm.provider "hyperv" do |hv, override|
hv.memory = 2048
hv.linked_clone = true
if ENV['CHECKOUT'] != 'y' then
override.vm.synced_folder ".", "/home/vagrant/Nominatim", type: "smb", smb_host: ENV['SMB_HOST'] || ENV['COMPUTERNAME']
end
end
config.vm.provider "virtualbox" do |vb, override|
vb.gui = false
vb.memory = 2048
@@ -42,34 +34,7 @@ Vagrant.configure("2") do |config|
end
end
config.vm.define "ubuntu22", primary: true do |sub|
sub.vm.box = "generic/ubuntu2204"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Ubuntu-22.sh"
s.privileged = false
s.args = [checkout]
end
end
config.vm.define "ubuntu22-apache" do |sub|
sub.vm.box = "generic/ubuntu2204"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Ubuntu-22.sh"
s.privileged = false
s.args = [checkout, "install-apache"]
end
end
config.vm.define "ubuntu22-nginx" do |sub|
sub.vm.box = "generic/ubuntu2204"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Ubuntu-22.sh"
s.privileged = false
s.args = [checkout, "install-nginx"]
end
end
config.vm.define "ubuntu20" do |sub|
config.vm.define "ubuntu", primary: true do |sub|
sub.vm.box = "generic/ubuntu2004"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Ubuntu-20.sh"
@@ -78,7 +43,7 @@ Vagrant.configure("2") do |config|
end
end
config.vm.define "ubuntu20-apache" do |sub|
config.vm.define "ubuntu-apache" do |sub|
sub.vm.box = "generic/ubuntu2004"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Ubuntu-20.sh"
@@ -87,7 +52,7 @@ Vagrant.configure("2") do |config|
end
end
config.vm.define "ubuntu20-nginx" do |sub|
config.vm.define "ubuntu-nginx" do |sub|
sub.vm.box = "generic/ubuntu2004"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Ubuntu-20.sh"
@@ -95,4 +60,51 @@ Vagrant.configure("2") do |config|
s.args = [checkout, "install-nginx"]
end
end
config.vm.define "ubuntu18" do |sub|
sub.vm.box = "generic/ubuntu1804"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Ubuntu-18.sh"
s.privileged = false
s.args = [checkout]
end
end
config.vm.define "ubuntu18-apache" do |sub|
sub.vm.box = "generic/ubuntu1804"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Ubuntu-18.sh"
s.privileged = false
s.args = [checkout, "install-apache"]
end
end
config.vm.define "ubuntu18-nginx" do |sub|
sub.vm.box = "generic/ubuntu1804"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Ubuntu-18.sh"
s.privileged = false
s.args = [checkout, "install-nginx"]
end
end
config.vm.define "centos7" do |sub|
sub.vm.box = "centos/7"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Centos-7.sh"
s.privileged = false
s.args = [checkout]
end
end
config.vm.define "centos" do |sub|
sub.vm.box = "generic/centos8"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Centos-8.sh"
s.privileged = false
s.args = [checkout]
end
end
end

View File

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

View File

@@ -4,10 +4,14 @@ import os
sys.path.insert(1, '@NOMINATIM_LIBDIR@/lib-python')
from nominatim import cli
from nominatim import version
os.environ['NOMINATIM_NOMINATIM_TOOL'] = os.path.abspath(__file__)
version.GIT_COMMIT_HASH = '@GIT_HASH@'
from nominatim import cli
exit(cli.nominatim(module_dir='@NOMINATIM_LIBDIR@/module',
osm2pgsql_path='@NOMINATIM_LIBDIR@/osm2pgsql'))
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@'))

View File

@@ -4,10 +4,14 @@ import os
sys.path.insert(1, '@CMAKE_SOURCE_DIR@')
from nominatim import cli
from nominatim import version
os.environ['NOMINATIM_NOMINATIM_TOOL'] = os.path.abspath(__file__)
version.GIT_COMMIT_HASH = '@GIT_HASH@'
from nominatim import cli
exit(cli.nominatim(module_dir='@CMAKE_BINARY_DIR@/module',
osm2pgsql_path='@CMAKE_BINARY_DIR@/osm2pgsql/osm2pgsql'))
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@'))

14
codecov.yml Normal file
View File

@@ -0,0 +1,14 @@
codecov:
require_ci_to_pass: yes
coverage:
status:
project: off
patch: off
comment:
require_changes: true
after_n_builds: 2
fixes:
- "Nominatim/::"

265
data/country_name.sql Normal file

File diff suppressed because one or more lines are too long

View File

@@ -11,7 +11,6 @@ set (DOC_SOURCES
develop
api
customize
library
index.md
extra.css
styles.css
@@ -24,12 +23,14 @@ foreach (src ${DOC_SOURCES})
endforeach()
ADD_CUSTOM_TARGET(doc
COMMAND ${CMAKE_CURRENT_SOURCE_DIR}/bash2md.sh ${PROJECT_SOURCE_DIR}/vagrant/Install-on-Centos-7.sh ${CMAKE_CURRENT_BINARY_DIR}/appendix/Install-on-Centos-7.md
COMMAND ${CMAKE_CURRENT_SOURCE_DIR}/bash2md.sh ${PROJECT_SOURCE_DIR}/vagrant/Install-on-Centos-8.sh ${CMAKE_CURRENT_BINARY_DIR}/appendix/Install-on-Centos-8.md
COMMAND ${CMAKE_CURRENT_SOURCE_DIR}/bash2md.sh ${PROJECT_SOURCE_DIR}/vagrant/Install-on-Ubuntu-18.sh ${CMAKE_CURRENT_BINARY_DIR}/appendix/Install-on-Ubuntu-18.md
COMMAND ${CMAKE_CURRENT_SOURCE_DIR}/bash2md.sh ${PROJECT_SOURCE_DIR}/vagrant/Install-on-Ubuntu-20.sh ${CMAKE_CURRENT_BINARY_DIR}/appendix/Install-on-Ubuntu-20.md
COMMAND ${CMAKE_CURRENT_SOURCE_DIR}/bash2md.sh ${PROJECT_SOURCE_DIR}/vagrant/Install-on-Ubuntu-22.sh ${CMAKE_CURRENT_BINARY_DIR}/appendix/Install-on-Ubuntu-22.md
COMMAND mkdocs build -d ${CMAKE_CURRENT_BINARY_DIR}/../site-html -f ${CMAKE_CURRENT_BINARY_DIR}/../mkdocs.yml
COMMAND PYTHONPATH=${PROJECT_SOURCE_DIR} mkdocs build -d ${CMAKE_CURRENT_BINARY_DIR}/../site-html -f ${CMAKE_CURRENT_BINARY_DIR}/../mkdocs.yml
)
ADD_CUSTOM_TARGET(serve-doc
COMMAND mkdocs serve -f ${CMAKE_CURRENT_BINARY_DIR}/../mkdocs.yml
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}
COMMAND PYTHONPATH=${PROJECT_SOURCE_DIR} mkdocs serve
WORKING_DIRECTORY ${PROJECT_BINARY_DIR}
)

View File

@@ -36,15 +36,16 @@ which has the following structure:
```bash
update
├── europe
├── andorra
│ │ └── sequence.state
└── monaco
└── sequence.state
└── tmp
└── europe
├── andorra-latest.osm.pbf
└── monaco-latest.osm.pbf
   ├── europe
   │   ├── andorra
   │   │   └── sequence.state
   │   └── monaco
   │   └── sequence.state
   └── tmp
└── europe
├── andorra-latest.osm.pbf
└── monaco-latest.osm.pbf
```
@@ -98,7 +99,7 @@ Change into the project directory and run the following command:
This will get diffs from the replication server, import diffs and index
the database. The default replication server in the
script ([Geofabrik](https://download.geofabrik.de)) provides daily updates.
script([Geofabrik](https://download.geofabrik.de)) provides daily updates.
## Using an external PostgreSQL database
@@ -110,7 +111,7 @@ library.
!!! note
The external module is only needed when using the legacy tokenizer.
If you have chosen the ICU tokenizer, then you can ignore this section
If you have choosen the ICU tokenizer, then you can ignore this section
and follow the standard import documentation.
### Option 1: Compiling the library on the database server
@@ -197,10 +198,11 @@ target machine.
of a full database.
Next install Nominatim on the target machine by following the standard installation
instructions. Again, make sure to use the same version as the source machine.
instructions. Again make sure to use the same version as the source machine.
Create a project directory on your destination machine and set up the `.env`
file to match the configuration on the source machine. Finally run
You can now copy the project directory from the source machine to the new machine.
If necessary, edit the `.env` file to point it to the restored database.
Finally run
nominatim refresh --website
@@ -208,8 +210,6 @@ to make sure that the local installation of Nominatim will be used.
If you are using the legacy tokenizer you might also have to switch to the
PostgreSQL module that was compiled on your target machine. If you get errors
that PostgreSQL cannot find or access `nominatim.so` then rerun
nominatim refresh --functions
on the target machine to update the the location of the module.
that PostgreSQL cannot find or access `nominatim.so` then copy the installed
version into the `module` directory of your project directory. The installed
copy can usually be found under `/usr/local/lib/nominatim/module/nominatim.so`.

View File

@@ -1,122 +0,0 @@
# Deploying the Nominatim Python frontend
The Nominatim can be run as a Python-based
[ASGI web application](https://asgi.readthedocs.io/en/latest/). You have the
choice between [Falcon](https://falcon.readthedocs.io/en/stable/)
and [Starlette](https://www.starlette.io/) as the ASGI framework.
This section gives a quick overview on how to configure Nginx to serve
Nominatim. Please refer to the documentation of
[Nginx](https://nginx.org/en/docs/) for background information on how
to configure it.
!!! Note
Throughout this page, we assume your Nominatim project directory is
located in `/srv/nominatim-project` and you have installed Nominatim
using the default installation prefix `/usr/local`. If you have put it
somewhere else, you need to adjust the commands and configuration
accordingly.
We further assume that your web server runs as user `www-data`. Older
versions of CentOS may still use the user name `apache`. You also need
to adapt the instructions in this case.
### Installing the required packages
The recommended way to deploy a Python ASGI application is to run
the ASGI runner [uvicorn](https://uvicorn.org/)
together with [gunicorn](https://gunicorn.org/) HTTP server. We use
Falcon here as the web framework.
Create a virtual environment for the Python packages and install the necessary
dependencies:
``` sh
sudo apt install virtualenv
virtualenv /srv/nominatim-venv
/srv/nominatim-venv/bin/pip install SQLAlchemy PyICU psycopg[binary] \
psycopg2-binary python-dotenv PyYAML falcon uvicorn gunicorn
```
### Setting up Nominatim as a systemd job
Next you need to set up the service that runs the Nominatim frontend. This is
easiest done with a systemd job.
Create the following file `/etc/systemd/system/nominatim.service`:
``` systemd
[Unit]
Description=Nominatim running as a gunicorn application
After=network.target
Requires=nominatim.socket
[Service]
Type=simple
Environment="PYTHONPATH=/usr/local/lib/nominatim/lib-python/"
User=www-data
Group=www-data
WorkingDirectory=/srv/nominatim-project
ExecStart=/srv/nominatim-venv/bin/gunicorn -b unix:/run/nominatim.sock -w 4 -k uvicorn.workers.UvicornWorker nominatim.server.falcon.server:run_wsgi
ExecReload=/bin/kill -s HUP $MAINPID
StandardOutput=append:/var/log/gunicorn-nominatim.log
StandardError=inherit
PrivateTmp=true
TimeoutStopSec=5
KillMode=mixed
[Install]
WantedBy=multi-user.target
```
This sets up gunicorn with 4 workers (`-w 4` in ExecStart). Each worker runs
its own Python process using
[`NOMINATIM_API_POOL_SIZE`](../customize/Settings.md#nominatim_api_pool_size)
connections to the database to serve requests in parallel.
Make the new service known to systemd and start it:
``` sh
sudo systemctl daemon-reload
sudo systemctl enable nominatim
sudo systemctl start nominatim
```
This sets the service up, so that Nominatim is automatically started
on reboot.
### Configuring nginx
To make the service available to the world, you need to proxy it through
nginx. Add the following definition to the default configuration:
``` nginx
upstream nominatim_service {
server unix:/run/nominatim.sock fail_timeout=0;
}
server {
listen 80;
listen [::]:80;
root /var/www/html;
index /search;
location / {
proxy_set_header Host $http_host;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
proxy_redirect off;
proxy_pass http://nominatim_service;
}
}
```
Reload nginx with
```
sudo systemctl reload nginx
```
and you should be able to see the status of your server under
`http://localhost/status`.

View File

@@ -1,4 +1,4 @@
# Deploying Nominatim using the PHP frontend
# 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
@@ -8,13 +8,13 @@ PHP scripts.
This section gives a quick overview on how to configure Apache and Nginx to
serve Nominatim. It is not meant as a full system administration guide on how
to run a web service. Please refer to the documentation of
[Apache](https://httpd.apache.org/docs/current/) and
[Apache](http://httpd.apache.org/docs/current/) and
[Nginx](https://nginx.org/en/docs/)
for background information on configuring the services.
!!! Note
Throughout this page, we assume your Nominatim project directory is
located in `/srv/nominatim-project` and you have installed Nominatim
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.
@@ -82,7 +82,7 @@ The website should now be available on `http://localhost/nominatim`.
### Installing the required packages
Nginx has no built-in PHP interpreter. You need to use php-fpm as a daemon for
Nginx has no built-in PHP interpreter. You need to use php-fpm as a deamon for
serving PHP cgi.
On Ubuntu/Debian install nginx and php-fpm with:
@@ -99,7 +99,7 @@ Unix socket instead, change the pool configuration
``` ini
; Replace the tcp listener and add the unix socket
listen = /var/run/php-fpm-nominatim.sock
listen = /var/run/php-fpm.sock
; Ensure that the daemon runs as the correct user
listen.owner = www-data
@@ -121,7 +121,7 @@ location @php {
fastcgi_param SCRIPT_FILENAME "$document_root$uri.php";
fastcgi_param PATH_TRANSLATED "$document_root$uri.php";
fastcgi_param QUERY_STRING $args;
fastcgi_pass unix:/var/run/php-fpm-nominatim.sock;
fastcgi_pass unix:/var/run/php-fpm.sock;
fastcgi_index index.php;
include fastcgi_params;
}
@@ -131,7 +131,7 @@ location ~ [^/]\.php(/|$) {
if (!-f $document_root$fastcgi_script_name) {
return 404;
}
fastcgi_pass unix:/var/run/php-fpm-nominatim.sock;
fastcgi_pass unix:/var/run/php-fpm.sock;
fastcgi_index search.php;
include fastcgi.conf;
}
@@ -140,9 +140,3 @@ location ~ [^/]\.php(/|$) {
Restart the nginx and php-fpm services and the website should now be available
at `http://localhost/`.
## Nominatim with other webservers
Users have created instructions for other webservers:
* [Caddy](https://github.com/osm-search/Nominatim/discussions/2580)

View File

@@ -79,7 +79,7 @@ When running the import you may get a version mismatch:
pg_config seems to use bad includes sometimes when multiple versions
of PostgreSQL are available in the system. Make sure you remove the
server development libraries (`postgresql-server-dev-13` on Ubuntu)
server development libraries (`postgresql-server-dev-9.5` on Ubuntu)
and recompile (`cmake .. && make`).
@@ -106,6 +106,11 @@ If you are using a flatnode file, then it may also be that the underlying
filesystem does not fully support 'mmap'. A notable candidate is virtualbox's
vboxfs.
### I see the error: "clang: Command not found" on CentOS
On CentOS 7 users reported `/opt/rh/llvm-toolset-7/root/usr/bin/clang: Command not found`.
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)
@@ -121,6 +126,22 @@ The server cannot access your database. Add `&debug=1` to your URL
to get the full error message.
### On CentOS the website shows "Could not connect to server"
`could not connect to server: No such file or directory`
On CentOS v7 the PostgreSQL server is started with `systemd`. Check if
`/usr/lib/systemd/system/httpd.service` contains a line `PrivateTmp=true`. If
so then Apache cannot see the `/tmp/.s.PGSQL.5432` file. It's a good security
feature, so use the
[preferred solution](../appendix/Install-on-Centos-7.md#adding-selinux-security-settings).
However, you can solve this the quick and dirty way by commenting out that line and then run
sudo systemctl daemon-reload
sudo systemctl restart httpd
### Website reports "DB Error: insufficient permissions"
The user the webserver, e.g. Apache, runs under needs to have access to the
@@ -160,6 +181,9 @@ by everybody, e.g.
Try `chmod a+r nominatim.so; chmod a+x nominatim.so`.
When running SELinux, make sure that the
[context is set up correctly](../appendix/Install-on-Centos-7.md#adding-selinux-security-settings).
When you recently updated your operating system, updated PostgreSQL to
a new version or moved files (e.g. the build directory) you should
recreate `nominatim.so`. Try

View File

@@ -74,15 +74,15 @@ but it will improve the quality of the results if this is installed.
This data is available as a binary download. Put it into your project directory:
cd $PROJECT_DIR
wget https://nominatim.org/data/wikimedia-importance.sql.gz
wget https://www.nominatim.org/data/wikimedia-importance.sql.gz
The file is about 400MB and adds around 4GB to the Nominatim database.
!!! tip
If you forgot to download the wikipedia rankings, then you can
also add importances after the import. Download the SQL files, then
run `nominatim refresh --wiki-data --importance`. Updating
importances for a planet will take a couple of hours.
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.
### External postcodes
@@ -92,8 +92,8 @@ and the UK (using the [CodePoint OpenData set](https://osdatahub.os.uk/downloads
This data can be optionally downloaded into the project directory:
cd $PROJECT_DIR
wget https://nominatim.org/data/gb_postcodes.csv.gz
wget https://nominatim.org/data/us_postcodes.csv.gz
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](../customize/Postcodes.md).
@@ -139,7 +139,7 @@ import. So this option is particularly interesting if you plan to transfer the
database or reuse the space later.
!!! warning
The data structure for updates are also required when adding additional data
The datastructure for updates are also required when adding additional data
after the import, for example [TIGER housenumber data](../customize/Tiger.md).
If you plan to use those, you must not use the `--no-updates` parameter.
Do a normal import, add the external data and once you are done with
@@ -150,7 +150,7 @@ database or reuse the space later.
If you only want to use the Nominatim database for reverse lookups or
if you plan to use the installation only for exports to a
[photon](https://photon.komoot.io/) database, then you can set up a database
[photon](https://photon.komoot.de/) database, then you can set up a database
without search indexes. Add `--reverse-only` to your setup command above.
This saves about 5% of disk space.
@@ -254,70 +254,26 @@ successfully.
nominatim admin --check-database
```
Now you can try out your installation by executing a simple query on the
command line:
``` sh
nominatim search --query Berlin
```
or, when you have a reverse-only installation:
``` sh
nominatim reverse --lat 51 --lon 45
```
If you want to run Nominatim as a service, you need to make a choice between
running the traditional PHP frontend or the new experimental Python frontend.
Make sure you have installed the right packages as per
[Installation](Installation.md#software).
#### Testing the PHP frontend
You can run a small test server with the PHP frontend like this:
Now you can try out your installation by running:
```sh
nominatim serve
```
Go to `http://localhost:8088/status.php` and you should see the message `OK`.
You can also run a search query, e.g. `http://localhost:8088/search.php?q=Berlin`
or, for reverse-only installations a reverse query,
e.g. `http://localhost:8088/reverse.php?lat=27.1750090510034&lon=78.04209025`.
This runs a small test server normally used for development. You can use it
to verify that your installation is working. Go to
`http://localhost:8088/status.php` and you should see the message `OK`.
You can also run a search query, e.g. `http://localhost:8088/search.php?q=Berlin`.
Do not use this test server in production.
To run Nominatim via webservers like Apache or nginx, please continue reading
[Deploy the PHP frontend](Deployment-PHP.md).
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`.
#### Testing the Python frontend
To run Nominatim via webservers like Apache or nginx, please read the
[Deployment chapter](Deployment.md).
To run the test server against the Python frontend, you must choose a
web framework to use, either starlette or falcon. Make sure the appropriate
packages are installed. Then run
## Adding search through category phrases
``` sh
nominatim serve --engine falcon
```
or
``` sh
nominatim serve --engine starlette
```
Go to `http://localhost:8088/status.php` and you should see the message `OK`.
You can also run a search query, e.g. `http://localhost:8088/search.php?q=Berlin`
or, for reverse-only installations a reverse query,
e.g. `http://localhost:8088/reverse.php?lat=27.1750090510034&lon=78.04209025`.
Do not use this test server in production.
To run Nominatim via webservers like Apache or nginx, please continue reading
[Deploy the Python frontend](Deployment-Python.md).
## Enabling search by category phrases
To be able to search for places by their type using
If you want to be able to search for places by their type through
[special phrases](https://wiki.openstreetmap.org/wiki/Nominatim/Special_Phrases)
you also need to import these key phrases like this:

View File

@@ -4,8 +4,10 @@ This page contains generic installation instructions for Nominatim and its
prerequisites. There are also step-by-step instructions available for
the following operating systems:
* [Ubuntu 22.04](../appendix/Install-on-Ubuntu-22.md)
* [Ubuntu 20.04](../appendix/Install-on-Ubuntu-20.md)
* [Ubuntu 18.04](../appendix/Install-on-Ubuntu-18.md)
* [CentOS 8](../appendix/Install-on-Centos-8.md)
* [CentOS 7.2](../appendix/Install-on-Centos-7.md)
These OS-specific instructions can also be found in executable form
in the `vagrant/` directory.
@@ -23,9 +25,8 @@ and can't offer support.
### Software
!!! Warning
For larger installations you **must have** PostgreSQL 11+ and PostGIS 3+
For larger installations you **must have** PostgreSQL 11+ and Postgis 3+
otherwise import and queries will be slow to the point of being unusable.
Query performance has marked improvements with PostgreSQL 13+ and PostGIS 3.2+.
For compiling:
@@ -35,58 +36,46 @@ For compiling:
* [bzip2](http://www.bzip.org/)
* [zlib](https://www.zlib.net/)
* [ICU](http://site.icu-project.org/)
* [nlohmann/json](https://json.nlohmann.me/)
* [Boost libraries](https://www.boost.org/), including system and filesystem
* PostgreSQL client libraries
* a recent C++ compiler (gcc 5+ or Clang 3.8+)
For running Nominatim:
* [PostgreSQL](https://www.postgresql.org) (9.6+ will work, 11+ strongly recommended)
* [PostgreSQL](https://www.postgresql.org) (9.5+ will work, 11+ strongly recommended)
* [PostGIS](https://postgis.net) (2.2+ will work, 3.0+ strongly recommended)
* [Python 3](https://www.python.org/) (3.7+)
* [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/)
* [SQLAlchemy](https://www.sqlalchemy.org/) (1.4.31+ with greenlet support)
* [asyncpg](https://magicstack.github.io/asyncpg) (0.8+)
* [PyICU](https://pypi.org/project/PyICU/)
* [PyYaml](https://pyyaml.org/) (5.1+)
* [datrie](https://github.com/pytries/datrie)
When running the PHP frontend:
* [PHP](https://php.net) (7.3+)
* [PHP](https://php.net) (7.0 or later)
* PHP-pgsql
* PHP-intl (bundled with PHP)
* PHP-cgi (for running queries from the command line)
For running continuous updates:
* [pyosmium](https://osmcode.org/pyosmium/)
For running the experimental Python frontend:
* one of the following web frameworks:
* [falcon](https://falconframework.org/) (3.0+)
* [starlette](https://www.starlette.io/)
* [uvicorn](https://www.uvicorn.org/)
For dependencies for running tests and building documentation, see
the [Development section](../develop/Development-Environment.md).
### Hardware
A minimum of 2GB of RAM is required or installation will fail. For a full
planet import 128GB of RAM or more are strongly recommended. Do not report
planet import 64GB of RAM or more are strongly recommended. Do not report
out of memory problems if you have less than 64GB RAM.
For a full planet install you will need at least 1TB of hard disk space.
For a full planet install you will need at least 900GB of hard disk space.
Take into account that the OSM database is growing fast.
Fast disks are essential. Using NVME disks is recommended.
Even on a well configured machine the import of a full planet takes
around 2 days. When using traditional SSDs, 4-5 days are more realistic.
around 2 days. On traditional spinning disks, 7-8 days are more realistic.
## Tuning the PostgreSQL database
@@ -100,7 +89,8 @@ your `postgresql.conf` file.
work_mem = (50MB)
effective_cache_size = (24GB)
synchronous_commit = off
max_wal_size = 1GB
checkpoint_segments = 100 # only for postgresql <= 9.4
max_wal_size = 1GB # postgresql > 9.4
checkpoint_timeout = 10min
checkpoint_completion_target = 0.9
@@ -118,6 +108,15 @@ you might consider setting:
and even reduce `autovacuum_work_mem` further. This will reduce the amount
of memory that autovacuum takes away from the import process.
For the initial import, you should also set:
fsync = off
full_page_writes = off
Don't forget to reenable them after the initial import or you risk database
corruption.
## Downloading and building Nominatim
### Downloading the latest release
@@ -131,13 +130,13 @@ If you want to install latest development version from github, make sure to
also check out the osm2pgsql subproject:
```
git clone --recursive https://github.com/openstreetmap/Nominatim.git
git clone --recursive git://github.com/openstreetmap/Nominatim.git
```
The development version does not include the country grid. Download it separately:
```
wget -O Nominatim/data/country_osm_grid.sql.gz https://nominatim.org/data/country_grid.sql.gz
wget -O Nominatim/data/country_osm_grid.sql.gz https://www.nominatim.org/data/country_grid.sql.gz
```
### Building Nominatim
@@ -159,17 +158,6 @@ make
sudo make install
```
!!! warning
The default installation no longer compiles the PostgreSQL module that
is needed for the legacy tokenizer from older Nominatim versions. If you
are upgrading an older database or want to run the
[legacy tokenizer](../customize/Tokenizers.md#legacy-tokenizer) for
some other reason, you need to enable the PostgreSQL module via
cmake: `cmake -DBUILD_MODULE=on ../Nominatim`. To compile the module
you need to have the server development headers for PostgreSQL installed.
On Ubuntu/Debian run: `sudo apt install postgresql-server-dev-<postgresql version>`
Nominatim installs itself into `/usr/local` per default. To choose a different
installation directory add `-DCMAKE_INSTALL_PREFIX=<install root>` to the
cmake command. Make sure that the `bin` directory is available in your path

View File

@@ -34,30 +34,6 @@ to rerun the statistics computation when adding larger amounts of new data,
for example, when adding an additional country via `nominatim add-data`.
## Forcing recomputation of places and areas
Command: `nominatim refresh --data-object [NWR]<id> --data-area [NWR]<id>`
When running replication updates, Nominatim tries to recompute the search
and address information for all places that are affected by a change. But it
needs to restrict the total number of changes to make sure it can keep up
with the minutely updates. Therefore it will refrain from propagating changes
that affect a lot of objects.
The administrator may force an update of places in the database.
`nominatim refresh --data-object` invalidates a single OSM object.
`nominatim refresh --data-area` invalidates an OSM object and all dependent
objects. That are usually the places that inside its area or around the
center of the object. Both commands expect the OSM object as an argument
of the form OSM type + OSM id. The type must be `N` (node), `W` (way) or
`R` (relation).
After invalidating the object, indexing must be run again. If continuous
update are running in the background, the objects will be recomputed together
with the next round of updates. Otherwise you need to run `nominatim index`
to finish the recomputation.
## Removing large deleted objects
Nominatim refuses to delete very large areas because often these deletions are

View File

@@ -15,42 +15,6 @@ breaking changes. **Please read them before running the migration.**
If you are migrating from a version <3.6, then you still have to follow
the manual migration steps up to 3.6.
## 4.2.0 -> 4.3.0
### New indexes for reverse lookup
The reverse lookup algorithm has changed slightly to improve performance.
This change needs a different index in the database. The required index
will be automatically build during migration. Until the new index is available
performance of the /reverse endpoint is significantly reduced. You should
therefore either remove traffic from the machine before attempting a
version update or create the index manually **before** starting the update
using the following SQL:
```sql
CREATE INDEX IF NOT EXISTS idx_placex_geometry_reverse_lookupPlaceNode
ON placex USING gist (ST_Buffer(geometry, reverse_place_diameter(rank_search)))
WHERE rank_address between 4 and 25 AND type != 'postcode'
AND name is not null AND linked_place_id is null AND osm_type = 'N';
```
## 4.0.0 -> 4.1.0
### ICU tokenizer is the new default
Nominatim now installs the [ICU tokenizer](../customize/Tokenizers.md#icu-tokenizer)
by default. This only has an effect on newly installed databases. When
updating older databases, it keeps its installed tokenizer. If you still
run with the legacy tokenizer, make sure to compile Nominatim with the
PostgreSQL module, see [Installation](Installation.md#building-nominatim).
### geocodejson output changed
The `type` field of the geocodejson output has changed. It now contains
the address class of the object instead of the value of the OSM tag. If
your client has used the `type` field, switch them to read `osm_value`
instead.
## 3.7.0 -> 4.0.0
### NOMINATIM_PHRASE_CONFIG removed

View File

@@ -16,12 +16,12 @@ 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`.
Next you need to adapt the UI to your installation. Custom settings need to be
Next you need to adapt the UI yo your installation. Custom settings need to be
put into `dist/theme/config.theme.js`. At a minimum you need to
set `Nominatim_API_Endpoint` to point to your Nominatim installation:
cd nominatim-ui
echo "Nominatim_Config.Nominatim_API_Endpoint='https://myserver.org/nominatim/';" > dist/theme/config.theme.js
echo "Nominatim_Config.Nominatim_API_Endpoint='https:\\myserver.org\nominatim';" > dist/theme/config.theme.js
For the full set of available settings, have a look at `dist/config.defaults.js`.
@@ -161,16 +161,24 @@ directory like this:
# If no endpoint is given, then use search.
RewriteRule ^(/|$) "search.php"
# If format-html is explicitly requested, forward to the UI.
# If format-html is explicity requested, forward to the UI.
RewriteCond %{QUERY_STRING} "format=html"
RewriteRule ^([^/]+)(.php)? ui/$1.html [R,END]
RewriteRule ^([^/]+).php ui/$1.html [R,END]
# Same but .php suffix is missing.
RewriteCond %{QUERY_STRING} "format=html"
RewriteRule ^([^/]+) ui/$1.html [R,END]
# If no format parameter is there then forward anything
# but /reverse and /lookup to the UI.
RewriteCond %{QUERY_STRING} "!format="
RewriteCond %{REQUEST_URI} "!/lookup"
RewriteCond %{REQUEST_URI} "!/reverse"
RewriteRule ^([^/]+)(.php)? ui/$1.html [R,END]
RewriteRule ^([^/]+).php ui/$1.html [R,END]
# Same but .php suffix is missing.
RewriteCond %{QUERY_STRING} "!format="
RewriteCond %{REQUEST_URI} "!/lookup"
RewriteCond %{REQUEST_URI} "!/reverse"
RewriteRule ^([^/]+) ui/$1.html [R,END]
</Directory>
```

View File

@@ -59,137 +59,8 @@ imported multiple country extracts and want to keep them
up-to-date, [Advanced installations section](Advanced-Installations.md)
contains instructions to set up and update multiple country extracts.
#### One-time mode
When the `--once` parameter is given, then Nominatim will download exactly one
batch of updates and then exit. This one-time mode still respects the
`NOMINATIM_REPLICATION_UPDATE_INTERVAL` that you have set. If according to
the update interval no new data has been published yet, it will go to sleep
until the next expected update and only then attempt to download the next batch.
The one-time mode is particularly useful if you want to run updates continuously
but need to schedule other work in between updates. For example, the main
service at osm.org uses it, to regularly recompute postcodes -- a process that
must not be run while updates are in progress. Its update script
looks like this:
```sh
#!/bin/bash
# Switch to your project directory.
cd /srv/nominatim
while true; do
nominatim replication --once
if [ -f "/srv/nominatim/schedule-maintenance" ]; then
rm /srv/nominatim/schedule-maintenance
nominatim refresh --postcodes
fi
done
```
A cron job then creates the file `/srv/nominatim/schedule-maintenance` once per night.
##### One-time mode with systemd
You can run the one-time mode with a systemd timer & service.
Create a timer description like `/etc/systemd/system/nominatim-updates.timer`:
```
[Unit]
Description=Timer to start updates of Nominatim
[Timer]
OnActiveSec=2
OnUnitActiveSec=1min
Unit=nominatim-updates.service
[Install]
WantedBy=multi-user.target
```
And then a similar service definition: `/etc/systemd/system/nominatim-updates.service`:
```
[Unit]
Description=Single updates of Nominatim
[Service]
WorkingDirectory=/srv/nominatim
ExecStart=nominatim replication --once
StandardOutput=append:/var/log/nominatim-updates.log
StandardError=append:/var/log/nominatim-updates.error.log
User=nominatim
Group=nominatim
Type=simple
[Install]
WantedBy=multi-user.target
```
Replace the `WorkingDirectory` with your project directory. Also adapt user and
group names as required. `OnUnitActiveSec` defines how often the individual
update command is run.
Now activate the service and start the updates:
```
sudo systemctl daemon-reload
sudo systemctl enable nominatim-updates.timer
sudo systemctl start nominatim-updates.timer
```
You can stop future data updates, while allowing any current, in-progress
update steps to finish, by running `sudo systemctl stop
nominatim-updates.timer` and waiting until `nominatim-updates.service` isn't
running (`sudo systemctl is-active nominatim-updates.service`). Current output
from the update can be seen like above (`systemctl status
nominatim-updates.service`).
#### Catch-up mode
With the `--catch-up` parameter, Nominatim will immediately try to download
all changes from the server until the database is up-to-date. The catch-up mode
still respects the parameter `NOMINATIM_REPLICATION_MAX_DIFF`. It downloads and
applies the changes in appropriate batches until all is done.
The catch-up mode is foremost useful to bring the database up to speed after the
initial import. Give that the service usually is not in production at this
point, you can temporarily be a bit more generous with the batch size and
number of threads you use for the updates by running catch-up like this:
```
cd /srv/nominatim
NOMINATIM_REPLICATION_MAX_DIFF=5000 nominatim replication --catch-up --threads 15
```
The catch-up mode is also useful when you want to apply updates at a lower
frequency than what the source publishes. You can set up a cron job to run
replication catch-up at whatever interval you desire.
!!! hint
When running scheduled updates with catch-up, it is a good idea to choose
a replication source with an update frequency that is an order of magnitude
lower. For example, if you want to update once a day, use an hourly updated
source. This makes sure that you don't miss an entire day of updates when
the source is unexpectedly late to publish its update.
If you want to use the source with the same update frequency (e.g. a daily
updated source with daily updates), use the
continuous update mode. It ensures to re-request the newest update until it
is published.
#### Continuous updates
!!! danger
This mode is no longer recommended to use and will removed in future
releases. systemd is much better
suited for running regular updates. Please refer to the setup
instructions for running one-time mode with systemd above.
This is the easiest mode. Simply run the replication command without any
parameters:
@@ -199,7 +70,7 @@ The update application keeps running forever and retrieves and applies
new updates from the server as they are published.
You can run this command as a simple systemd service. Create a service
description like that in `/etc/systemd/system/nominatim-updates.service`:
description like that in `/etc/systemd/system/nominatim-update.service`:
```
[Unit]
@@ -229,4 +100,67 @@ sudo systemctl enable nominatim-updates
sudo systemctl start nominatim-updates
```
#### One-time mode
When the `--once` parameter is given, then Nominatim will download exactly one
batch of updates and then exit. This one-time mode still respects the
`NOMINATIM_REPLICATION_UPDATE_INTERVAL` that you have set. If according to
the update interval no new data has been published yet, it will go to sleep
until the next expected update and only then attempt to download the next batch.
The one-time mode is particularly useful if you want to run updates continuously
but need to schedule other work in between updates. For example, the main
service at osm.org uses it, to regularly recompute postcodes -- a process that
must not be run while updates are in progress. Its update script
looks like this:
```sh
#!/bin/bash
# Switch to your project directory.
cd /srv/nominatim
while true; do
nominatim replication --once
if [ -f "/srv/nominatim/schedule-mainenance" ]; then
rm /srv/nominatim/schedule-mainenance
nominatim refresh --postcodes
fi
done
```
A cron job then creates the file `/srv/nominatim/need-mainenance` once per night.
#### Catch-up mode
With the `--catch-up` parameter, Nominatim will immediately try to download
all changes from the server until the database is up-to-date. The catch-up mode
still respects the parameter `NOMINATIM_REPLICATION_MAX_DIFF`. It downloads and
applies the changes in appropriate batches until all is done.
The catch-up mode is foremost useful to bring the database up to speed after the
initial import. Give that the service usually is not in production at this
point, you can temporarily be a bit more generous with the batch size and
number of threads you use for the updates by running catch-up like this:
```
cd /srv/nominatim
NOMINATIM_REPLICATION_MAX_DIFF=5000 nominatim replication --catch-up --threads 15
```
The catch-up mode is also useful when you want to apply updates at a lower
frequency than what the source publishes. You can set up a cron job to run
replication catch-up at whatever interval you desire.
!!! hint
When running scheduled updates with catch-up, it is a good idea to choose
a replication source with an update frequency that is an order of magnitude
lower. For example, if you want to update once a day, use an hourly updated
source. This makes sure that you don't miss an entire day of updates when
the source is unexpectely late to publish its update.
If you want to use the source with the same update frequency (e.g. a daily
updated source with daily updates), use the
continuous update mode. It ensures to re-request the newest update until it
is published.

View File

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

View File

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

View File

@@ -3,7 +3,7 @@
The lookup API allows to query the address and other details of one or
multiple OSM objects like node, way or relation.
## Endpoint
## Parameters
The lookup API has the following format:
@@ -15,140 +15,86 @@ The lookup API has the following format:
prefixed with its type, one of node(N), way(W) or relation(R). Up to 50 ids
can be queried at the same time.
!!! danger "Deprecation warning"
The API can also be used with the URL
`https://nominatim.openstreetmap.org/lookup.php`. This is now deprecated
and will be removed in future versions.
## Parameters
This section lists additional optional parameters.
Additional optional parameters are explained below.
### Output format
| Parameter | Value | Default |
|-----------| ----- | ------- |
| format | one of: `xml`, `json`, `jsonv2`, `geojson`, `geocodejson` | `jsonv2` |
* `format=[xml|json|jsonv2|geojson|geocodejson]`
See [Place Output Formats](Output.md) for details on each format.
See [Place Output Formats](Output.md) for details on each format. (Default: xml)
* `json_callback=<string>`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| json_callback | function name | _unset_ |
When given, then JSON output will be wrapped in a callback function with
the given name. See [JSONP](https://en.wikipedia.org/wiki/JSONP) for more
information.
Wrap JSON output in a callback function (JSONP) i.e. `<string>(<json>)`.
Only has an effect for JSON output formats.
### Output details
| Parameter | Value | Default |
|-----------| ----- | ------- |
| addressdetails | 0 or 1 | 0 |
* `addressdetails=[0|1]`
When set to 1, include a breakdown of the address into elements.
The exact content of the address breakdown depends on the output format.
!!! tip
If you are interested in a stable classification of address categories
(suburb, city, state, etc), have a look at the `geocodejson` format.
All other formats return classifications according to OSM tagging.
There is a much larger set of categories and they are not always consistent,
which makes them very hard to work with.
Include a breakdown of the address into elements. (Default: 0)
| Parameter | Value | Default |
|-----------| ----- | ------- |
| extratags | 0 or 1 | 0 |
* `extratags=[0|1]`
When set to 1, the response include any additional information in the result
that is available in the database, e.g. wikipedia link, opening hours.
Include additional information in the result if available,
e.g. wikipedia link, opening hours. (Default: 0)
| Parameter | Value | Default |
|-----------| ----- | ------- |
| namedetails | 0 or 1 | 0 |
* `namedetails=[0|1]`
When set to 1, include a full list of names for the result. These may include
language variants, older names, references and brand.
Include a list of alternative names in the results. These may include
language variants, references, operator and brand. (Default: 0)
### Language of results
| Parameter | Value | Default |
|-----------| ----- | ------- |
| accept-language | browser language string | content of "Accept-Language" HTTP header |
Preferred language order for showing search results. This may either be
a simple comma-separated list of language codes or have the same format
as the ["Accept-Language" HTTP header](https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Accept-Language).
!!! tip
First-time users of Nominatim tend to be confused that they get different
results when using Nominatim in the browser versus in a command-line tool
like wget or curl. The command-line tools
usually don't send any Accept-Language header, prompting Nominatim
to show results in the local language. Browsers on the contratry always
send the currently chosen browser language.
* `accept-language=<browser language string>`
Preferred language order for showing search results, overrides the value
specified in the "Accept-Language" HTTP header.
Either use a standard RFC2616 accept-language string or a simple
comma-separated list of language codes.
### Polygon output
| Parameter | Value | Default |
|-----------| ----- | ------- |
| polygon_geojson | 0 or 1 | 0 |
| polygon_kml | 0 or 1 | 0 |
| polygon_svg | 0 or 1 | 0 |
| polygon_text | 0 or 1 | 0 |
* `polygon_geojson=1`
* `polygon_kml=1`
* `polygon_svg=1`
* `polygon_text=1`
Add the full geometry of the place to the result output. Output formats
in GeoJSON, KML, SVG or WKT are supported. Only one of these
options can be used at a time.
Output geometry of results as a GeoJSON, KML, SVG or WKT. Only one of these
options can be used at a time. (Default: 0)
| Parameter | Value | Default |
|-----------| ----- | ------- |
| polygon_threshold | floating-point number | 0.0 |
* `polygon_threshold=0.0`
When one of the polygon_* outputs is chosen, return a simplified version
of the output geometry. The parameter describes the
Return a simplified version of the output geometry. The parameter is the
tolerance in degrees with which the geometry may differ from the original
geometry. Topology is preserved in the geometry.
geometry. Topology is preserved in the result. (Default: 0.0)
### Other
| Parameter | Value | Default |
|-----------| ----- | ------- |
| email | valid email address | _unset_ |
* `email=<valid email address>`
If you are making large numbers of request please include an appropriate email
address to identify your requests. See Nominatim's
[Usage Policy](https://operations.osmfoundation.org/policies/nominatim/) for more details.
address to identify your requests. See Nominatim's [Usage Policy](https://operations.osmfoundation.org/policies/nominatim/) for more details.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| debug | 0 or 1 | 0 |
* `debug=[0|1]`
Output assorted developer debug information. Data on internals of Nominatim's
"search loop" logic, and SQL queries. The output is HTML format.
This overrides the specified machine readable format.
"Search Loop" logic, and SQL queries. The output is (rough) HTML format.
This overrides the specified machine readable format. (Default: 0)
## Examples
##### XML
[https://nominatim.openstreetmap.org/lookup?osm_ids=R146656,W104393803,N240109189](https://nominatim.openstreetmap.org/lookup?osm_ids=R146656,W50637691,N240109189)
[https://nominatim.openstreetmap.org/lookup?osm_ids=R146656,W104393803,N240109189](https://nominatim.openstreetmap.org/lookup?osm_ids=R146656,W104393803,N240109189)
```xml
<lookupresults timestamp="Mon, 28 Mar 22 14:38:54 +0000" attribution="Data &#xA9; OpenStreetMap contributors, ODbL 1.0. http://www.openstreetmap.org/copyright" querystring="R146656,W50637691,N240109189" more_url="">
<place place_id="282236157" osm_type="relation" osm_id="146656" place_rank="16" address_rank="16" boundingbox="53.3401044,53.5445923,-2.3199185,-2.1468288" lat="53.44246175" lon="-2.2324547359718547" display_name="Manchester, Greater Manchester, North West England, England, United Kingdom" class="boundary" type="administrative" importance="0.35">
<lookupresults timestamp="Mon, 29 Jun 15 18:01:33 +0000" attribution="Data © OpenStreetMap contributors, ODbL 1.0. https://www.openstreetmap.org/copyright" querystring="R146656,W104393803,N240109189" polygon="false">
<place place_id="127761056" osm_type="relation" osm_id="146656" place_rank="16" lat="53.4791466" lon="-2.2447445" display_name="Manchester, Greater Manchester, North West England, England, United Kingdom" class="boundary" type="administrative" importance="0.704893333438333">
<city>Manchester</city>
<county>Greater Manchester</county>
<state_district>North West England</state_district>
@@ -156,20 +102,21 @@ This overrides the specified machine readable format.
<country>United Kingdom</country>
<country_code>gb</country_code>
</place>
<place place_id="115462561" osm_type="way" osm_id="50637691" place_rank="30" address_rank="30" boundingbox="52.3994612,52.3996426,13.0479574,13.0481754" lat="52.399550700000006" lon="13.048066846939687" display_name="Brandenburger Tor, Brandenburger Stra&#xDF;e, Historische Innenstadt, Innenstadt, Potsdam, Brandenburg, 14467, Germany" class="tourism" type="attraction" importance="0.29402874005524">
<tourism>Brandenburger Tor</tourism>
<road>Brandenburger Stra&#xDF;e</road>
<suburb>Historische Innenstadt</suburb>
<city>Potsdam</city>
<state>Brandenburg</state>
<postcode>14467</postcode>
<place place_id="77769745" osm_type="way" osm_id="104393803" place_rank="30" lat="52.5162024" lon="13.3777343363579" display_name="Brandenburg Gate, 1, Pariser Platz, Mitte, Berlin, 10117, Germany" class="tourism" type="attraction" importance="0.443472858361592">
<attraction>Brandenburg Gate</attraction>
<house_number>1</house_number>
<pedestrian>Pariser Platz</pedestrian>
<suburb>Mitte</suburb>
<city_district>Mitte</city_district>
<city>Berlin</city>
<state>Berlin</state>
<postcode>10117</postcode>
<country>Germany</country>
<country_code>de</country_code>
</place>
<place place_id="567505" osm_type="node" osm_id="240109189" place_rank="15" address_rank="16" boundingbox="52.3586925,52.6786925,13.2396024,13.5596024" lat="52.5186925" lon="13.3996024" display_name="Berlin, 10178, Germany" class="place" type="city" importance="0.78753902824914">
<place place_id="2570600569" osm_type="node" osm_id="240109189" place_rank="15" lat="52.5170365" lon="13.3888599" display_name="Berlin, Germany" class="place" type="city" importance="0.822149797630868">
<city>Berlin</city>
<state>Berlin</state>
<postcode>10178</postcode>
<country>Germany</country>
<country_code>de</country_code>
</place>
@@ -178,50 +125,38 @@ This overrides the specified machine readable format.
##### JSON with extratags
[https://nominatim.openstreetmap.org/lookup?osm_ids=W50637691&format=json&extratags=1](https://nominatim.openstreetmap.org/lookup?osm_ids=W50637691&format=json&extratags=1)
[https://nominatim.openstreetmap.org/lookup?osm_ids=W50637691&format=json](https://nominatim.openstreetmap.org/lookup?osm_ids=W50637691&format=json)
```json
[
{
"place_id": 115462561,
"licence": "Data © OpenStreetMap contributors, ODbL 1.0. https://osm.org/copyright",
"osm_type": "way",
"osm_id": 50637691,
"boundingbox": [
"52.3994612",
"52.3996426",
"13.0479574",
"13.0481754"
],
"lat": "52.399550700000006",
"lon": "13.048066846939687",
"display_name": "Brandenburger Tor, Brandenburger Straße, Historische Innenstadt, Innenstadt, Potsdam, Brandenburg, 14467, Germany",
"class": "tourism",
"type": "attraction",
"importance": 0.2940287400552381,
"address": {
"tourism": "Brandenburger Tor",
"road": "Brandenburger Straße",
"suburb": "Historische Innenstadt",
"city": "Potsdam",
"state": "Brandenburg",
"postcode": "14467",
"country": "Germany",
"country_code": "de"
},
"extratags": {
"image": "http://commons.wikimedia.org/wiki/File:Potsdam_brandenburger_tor.jpg",
"heritage": "4",
"wikidata": "Q695045",
"architect": "Carl von Gontard;Georg Christian Unger",
"wikipedia": "de:Brandenburger Tor (Potsdam)",
"wheelchair": "yes",
"description": "Kleines Brandenburger Tor in Potsdam",
"heritage:website": "http://www.bldam-brandenburg.de/images/stories/PDF/DML%202012/04-p-internet-13.pdf",
"heritage:operator": "bldam",
"architect:wikidata": "Q68768;Q95223",
"year_of_construction": "1771"
}
}
{
"place_id": "84271358",
"licence": "Data © OpenStreetMap contributors, ODbL 1.0. https://osm.org/copyright",
"osm_type": "way",
"osm_id": "50637691",
"lat": "52.39955055",
"lon": "13.04806574678",
"display_name": "Brandenburger Tor, Brandenburger Straße, Nördliche Innenstadt, Innenstadt, Potsdam, Brandenburg, 14467, Germany",
"class": "historic",
"type": "city_gate",
"importance": "0.221233780277011",
"address": {
"address29": "Brandenburger Tor",
"pedestrian": "Brandenburger Straße",
"suburb": "Nördliche Innenstadt",
"city": "Potsdam",
"state": "Brandenburg",
"postcode": "14467",
"country": "Germany",
"country_code": "de"
},
"extratags": {
"image": "http://commons.wikimedia.org/wiki/File:Potsdam_brandenburger_tor.jpg",
"wikidata": "Q695045",
"wikipedia": "de:Brandenburger Tor (Potsdam)",
"wheelchair": "yes",
"description": "Kleines Brandenburger Tor in Potsdam"
}
}
]
```

View File

@@ -28,7 +28,6 @@ a single place (for reverse) of the following format:
"city": "London",
"state_district": "Greater London",
"state": "England",
"ISO3166-2-lvl4": "GB-ENG",
"postcode": "SW1A 2DU",
"country": "United Kingdom",
"country_code": "gb"
@@ -98,10 +97,7 @@ The GeocodeJSON format follows the
The following feature attributes are implemented:
* `osm_type`, `osm_id` - reference to the OSM object (unofficial extension, [see notes](#osm-reference))
* `type` - the 'address level' of the object ('house', 'street', `district`, `city`,
`county`, `state`, `country`, `locality`)
* `osm_key`- key of the main tag of the OSM object (e.g. boundary, highway, amenity)
* `osm_value` - value of the main tag of the OSM object (e.g. residential, restaurant)
* `type` - value of the main tag of the object (e.g. residential, restaurant, ...)
* `label` - full comma-separated address
* `name` - localised name of the place
* `housenumber`, `street`, `locality`, `district`, `postcode`, `city`,
@@ -130,7 +126,6 @@ formats depending on the API call.
</result>
<addressparts>
<state>Bavaria</state>
<ISO3166-2-lvl4>DE-BY</ISO3166-2-lvl4>
<country>Germany</country>
<country_code>de</country_code>
</addressparts>
@@ -184,7 +179,6 @@ Additional information requested with `addressdetails=1`, `extratags=1` and
<city>London</city>
<state_district>Greater London</state_district>
<state>England</state>
<ISO3166-2-lvl4>GB-ENG</ISO3166-2-lvl4>
<postcode>SW1A 2DU</postcode>
<country>United Kingdom</country>
<country_code>gb</country_code>
@@ -211,8 +205,8 @@ be more than one. The attributes of that element contain:
* `ref` - content of `ref` tag if it exists
* `lat`, `lon` - latitude and longitude of the centroid of the object
* `boundingbox` - comma-separated list of corner coordinates ([see notes](#boundingbox))
* `place_rank` - class [search rank](../customize/Ranking.md#search-rank)
* `address_rank` - place [address rank](../customize/Ranking.md#address-rank)
* `place_rank` - class [search rank](../develop/Ranking#search-rank)
* `address_rank` - place [address rank](../develop/Ranking#address-rank)
* `display_name` - full comma-separated address
* `class`, `type` - key and value of the main OSM tag
* `importance` - computed importance rank
@@ -236,7 +230,7 @@ on another server. It may even change its ID on the same server when it is
removed and reimported while updating the database with fresh OSM data.
It is thus not useful to treat it as permanent for later use.
The combination `osm_type`+`osm_id` is slightly better but remember in
The combination `osm_type`+`osm_id` is slighly better but remember in
OpenStreetMap mappers can delete, split, recreate places (and those
get a new `osm_id`), there is no link between those old and new ids.
Places can also change their meaning without changing their `osm_id`,
@@ -285,12 +279,12 @@ with a designation label. Per default the following labels may appear:
* continent
* country, country_code
* region, state, state_district, county, ISO3166-2-lvl<admin_level>
* region, state, state_district, county
* municipality, city, town, village
* city_district, district, borough, suburb, subdivision
* hamlet, croft, isolated_dwelling
* neighbourhood, allotments, quarter
* city_block, residential, farm, farmyard, industrial, commercial, retail
* city_block, residental, farm, farmyard, industrial, commercial, retail
* road
* house_number, house_name
* emergency, historic, military, natural, landuse, place, railway,

View File

@@ -1,16 +1,8 @@
### Nominatim API
!!! Attention
The current version of Nominatim implements two different search frontends:
the old PHP frontend and the new Python frontend. They have a very similar
API but differ in some implementation details. These are marked in the
documentation as `[Python-only]` or `[PHP-only]`.
Nominatim indexes named (or numbered) features within the OpenStreetMap (OSM) dataset and a subset of other unnamed features (pubs, hotels, churches, etc).
`https://nominatim.openstreetmap.org` implements the **Python frontend**.
So users should refer to the **`[Python-only]`** comments.
This section describes the API V1 of the Nominatim web service. The
service offers the following endpoints:
Its API has the following endpoints for querying the data:
* __[/search](Search.md)__ - search OSM objects by name or type
* __[/reverse](Reverse.md)__ - search OSM object by their location
@@ -20,6 +12,3 @@ service offers the following endpoints:
back in Nominatim in case the deletion was accidental
* __/polygons__ - list of broken polygons detected by Nominatim
* __[/details](Details.md)__ - show internal details for an object (for debugging only)

View File

@@ -1,7 +1,6 @@
# Reverse Geocoding
Reverse geocoding generates an address from a coordinate given as
latitude and longitude.
Reverse geocoding generates an address from a latitude and longitude.
## How it works
@@ -19,7 +18,8 @@ The other issue to be aware of is that the closest OSM object may not always
have a similar enough address to the coordinate you were requesting. For
example, in dense city areas it may belong to a completely different street.
## Endpoint
## Parameters
The main format of the reverse API is
@@ -27,105 +27,61 @@ The main format of the reverse API is
https://nominatim.openstreetmap.org/reverse?lat=<value>&lon=<value>&<params>
```
where `lat` and `lon` are latitude and longitude of a coordinate in WGS84
where `lat` and `lon` are latitude and longitutde of a coordinate in WGS84
projection. The API returns exactly one result or an error when the coordinate
is in an area with no OSM data coverage.
Additional paramters are accepted as listed below.
!!! danger "Deprecation warning"
!!! warning "Deprecation warning"
The reverse API used to allow address lookup for a single OSM object by
its OSM id for `[PHP-only]`. The use is considered deprecated.
Use the [Address Lookup API](Lookup.md) instead.
!!! danger "Deprecation warning"
The API can also be used with the URL
`https://nominatim.openstreetmap.org/reverse.php`. This is now deprecated
and will be removed in future versions.
## Parameters
This section lists additional parameters to further influence the output.
its OSM id. This use is now deprecated. Use the [Address Lookup API](../Lookup)
instead.
### Output format
| Parameter | Value | Default |
|-----------| ----- | ------- |
| format | one of: `xml`, `json`, `jsonv2`, `geojson`, `geocodejson` | `xml` |
* `format=[xml|json|jsonv2|geojson|geocodejson]`
See [Place Output Formats](Output.md) for details on each format.
See [Place Output Formats](Output.md) for details on each format. (Default: xml)
* `json_callback=<string>`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| json_callback | function name | _unset_ |
When given, then JSON output will be wrapped in a callback function with
the given name. See [JSONP](https://en.wikipedia.org/wiki/JSONP) for more
information.
Wrap JSON output in a callback function ([JSONP](https://en.wikipedia.org/wiki/JSONP)) i.e. `<string>(<json>)`.
Only has an effect for JSON output formats.
### Output details
| Parameter | Value | Default |
|-----------| ----- | ------- |
| addressdetails | 0 or 1 | 1 |
* `addressdetails=[0|1]`
When set to 1, include a breakdown of the address into elements.
The exact content of the address breakdown depends on the output format.
!!! tip
If you are interested in a stable classification of address categories
(suburb, city, state, etc), have a look at the `geocodejson` format.
All other formats return classifications according to OSM tagging.
There is a much larger set of categories and they are not always consistent,
which makes them very hard to work with.
Include a breakdown of the address into elements. (Default: 1)
| Parameter | Value | Default |
|-----------| ----- | ------- |
| extratags | 0 or 1 | 0 |
* `extratags=[0|1]`
When set to 1, the response include any additional information in the result
that is available in the database, e.g. wikipedia link, opening hours.
Include additional information in the result if available,
e.g. wikipedia link, opening hours. (Default: 0)
| Parameter | Value | Default |
|-----------| ----- | ------- |
| namedetails | 0 or 1 | 0 |
* `namedetails=[0|1]`
When set to 1, include a full list of names for the result. These may include
language variants, older names, references and brand.
Include a list of alternative names in the results. These may include
language variants, references, operator and brand. (Default: 0)
### Language of results
| Parameter | Value | Default |
|-----------| ----- | ------- |
| accept-language | browser language string | content of "Accept-Language" HTTP header |
* `accept-language=<browser language string>`
Preferred language order for showing search results. This may either be
a simple comma-separated list of language codes or have the same format
as the ["Accept-Language" HTTP header](https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Accept-Language).
Preferred language order for showing search results, overrides the value
specified in the "Accept-Language" HTTP header.
Either use a standard RFC2616 accept-language string or a simple
comma-separated list of language codes.
!!! tip
First-time users of Nominatim tend to be confused that they get different
results when using Nominatim in the browser versus in a command-line tool
like wget or curl. The command-line tools
usually don't send any Accept-Language header, prompting Nominatim
to show results in the local language. Browsers on the contratry always
send the currently chosen browser language.
### Result limitation
* `zoom=[0-18]`
### Result restriction
| Parameter | Value | Default |
|-----------| ----- | ------- |
| zoom | 0-18 | 18 |
Level of detail required for the address. This is a number that
Level of detail required for the address. Default: 18. This is a number that
corresponds roughly to the zoom level used in XYZ tile sources in frameworks
like Leaflet.js, Openlayers etc.
In terms of address details the zoom levels are as follows:
@@ -136,79 +92,41 @@ In terms of address details the zoom levels are as follows:
5 | state
8 | county
10 | city
12 | town / borough
13 | village / suburb
14 | neighbourhood
15 | any settlement
14 | suburb
16 | major streets
17 | major and minor streets
18 | building
| Parameter | Value | Default |
|-----------| ----- | ------- |
| layer | comma-separated list of: `address`, `poi`, `railway`, `natural`, `manmade` | _unset_ (no restriction) |
The layer filter allows to select places by themes.
The `address` layer contains all places that make up an address:
address points with house numbers, streets, inhabited places (suburbs, villages,
cities, states etc.) and administrative boundaries.
The `poi` layer selects all point of interest. This includes classic points
of interest like restaurants, shops, hotels but also less obvious features
like recycling bins, guideposts or benches.
The `railway` layer includes railway infrastructure like tracks.
Note that in Nominatim's standard configuration, only very few railway
features are imported into the database.
The `natural` layer collects feautures like rivers, lakes and mountains while
the `manmade` layer functions as a catch-all for features not covered by the
other layers.
### Polygon output
| Parameter | Value | Default |
|-----------| ----- | ------- |
| polygon_geojson | 0 or 1 | 0 |
| polygon_kml | 0 or 1 | 0 |
| polygon_svg | 0 or 1 | 0 |
| polygon_text | 0 or 1 | 0 |
* `polygon_geojson=1`
* `polygon_kml=1`
* `polygon_svg=1`
* `polygon_text=1`
Add the full geometry of the place to the result output. Output formats
in GeoJSON, KML, SVG or WKT are supported. Only one of these
options can be used at a time.
Output geometry of results as a GeoJSON, KML, SVG or WKT. Only one of these
options can be used at a time. (Default: 0)
| Parameter | Value | Default |
|-----------| ----- | ------- |
| polygon_threshold | floating-point number | 0.0 |
* `polygon_threshold=0.0`
When one of the polygon_* outputs is chosen, return a simplified version
of the output geometry. The parameter describes the
Return a simplified version of the output geometry. The parameter is the
tolerance in degrees with which the geometry may differ from the original
geometry. Topology is preserved in the geometry.
geometry. Topology is preserved in the result. (Default: 0.0)
### Other
| Parameter | Value | Default |
|-----------| ----- | ------- |
| email | valid email address | _unset_ |
* `email=<valid email address>`
If you are making large numbers of request please include an appropriate email
address to identify your requests. See Nominatim's
[Usage Policy](https://operations.osmfoundation.org/policies/nominatim/) for more details.
address to identify your requests. See Nominatim's [Usage Policy](https://operations.osmfoundation.org/policies/nominatim/) for more details.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| debug | 0 or 1 | 0 |
* `debug=[0|1]`
Output assorted developer debug information. Data on internals of Nominatim's
"search loop" logic, and SQL queries. The output is HTML format.
This overrides the specified machine readable format.
"Search Loop" logic, and SQL queries. The output is (rough) HTML format.
This overrides the specified machine readable format. (Default: 0)
## Examples

View File

@@ -8,12 +8,12 @@ The search query may also contain
which are translated into specific OpenStreetMap (OSM) tags (e.g. Pub => `amenity=pub`).
This can be used to narrow down the kind of objects to be returned.
!!! note
!!! warning
Special phrases are not suitable to query all objects of a certain type in an
area. Nominatim will always just return a collection of the best matches. To
download OSM data by object type, use the [Overpass API](https://overpass-api.de/).
## Endpoint
## Parameters
The search API has the following format:
@@ -21,211 +21,82 @@ The search API has the following format:
https://nominatim.openstreetmap.org/search?<params>
```
!!! danger "Deprecation warning"
The API can also be used with the URL
`https://nominatim.openstreetmap.org/search.php`. This is now deprecated
and will be removed in future versions.
The search term may be specified with two different sets of parameters:
The query term can be given in two different forms: free-form or structured.
* `q=<query>`
### Free-form query
Free-form query string to search for.
Free-form queries are processed first left-to-right and then right-to-left if that fails. So you may search for
[pilkington avenue, birmingham](https://nominatim.openstreetmap.org/search?q=pilkington+avenue,birmingham) as well as for
[birmingham, pilkington avenue](https://nominatim.openstreetmap.org/search?q=birmingham,+pilkington+avenue).
Commas are optional, but improve performance by reducing the complexity of the search.
| Parameter | Value |
|-----------| ----- |
| q | Free-form query string to search for |
In this form, the query can be unstructured.
Free-form queries are processed first left-to-right and then right-to-left if that fails. So you may search for
[pilkington avenue, birmingham](https://nominatim.openstreetmap.org/search?q=pilkington+avenue,birmingham) as well as for
[birmingham, pilkington avenue](https://nominatim.openstreetmap.org/search?q=birmingham,+pilkington+avenue).
Commas are optional, but improve performance by reducing the complexity of the search.
* `street=<housenumber> <streetname>`
* `city=<city>`
* `county=<county>`
* `state=<state>`
* `country=<country>`
* `postalcode=<postalcode>`
The free-form may also contain special phrases to describe the type of
place to be returned or a coordinate to search close to a position.
Alternative query string format split into several parameters for structured requests.
Structured requests are faster but are less robust against alternative
OSM tagging schemas. **Do not combine with** `q=<query>` **parameter**.
### Structured query
| Parameter | Value |
|----------- | ----- |
| amenity | name and/or type of POI |
| street | housenumber and streetname |
| city | city |
| county | county |
| state | state |
| country | country |
| postalcode | postal code |
The structured form of the search query allows to lookup up an address
that is already split into its components. Each parameter represents a field
of the address. All parameters are optional. You should only use the ones
that are relevant for the address you want to geocode.
!!! Attention
Cannot be combined with the `q=<query>` parameter. Newer versions of
the API will return an error if you do so. Older versions simply return
unexpected results.
## Parameters
The following parameters can be used to further restrict the search and
change the output. They are usable for both forms of the search query.
Both query forms accept the additional parameters listed below.
### Output format
| Parameter | Value | Default |
|-----------| ----- | ------- |
| format | one of: `xml`, `json`, `jsonv2`, `geojson`, `geocodejson` | `jsonv2` |
* `format=[xml|json|jsonv2|geojson|geocodejson]`
See [Place Output Formats](Output.md) for details on each format.
See [Place Output Formats](Output.md) for details on each format. (Default: jsonv2)
!!! note
The Nominatim service at
[https://nominatim.openstreetmap.org](https://nominatim.openstreetmap.org)
has a different default behaviour for historical reasons. When the
`format` parameter is omitted, the request will be forwarded to the Web UI.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| json_callback | function name | _unset_ |
When given, then JSON output will be wrapped in a callback function with
the given name. See [JSONP](https://en.wikipedia.org/wiki/JSONP) for more
information.
* `json_callback=<string>`
Wrap JSON output in a callback function ([JSONP](https://en.wikipedia.org/wiki/JSONP)) i.e. `<string>(<json>)`.
Only has an effect for JSON output formats.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| limit | number | 10 |
Limit the maximum number of returned results. Cannot be more than 40.
Nominatim may decide to return less results than given, if additional
results do not sufficiently match the query.
### Output details
| Parameter | Value | Default |
|-----------| ----- | ------- |
| addressdetails | 0 or 1 | 0 |
* `addressdetails=[0|1]`
When set to 1, include a breakdown of the address into elements.
The exact content of the address breakdown depends on the output format.
!!! tip
If you are interested in a stable classification of address categories
(suburb, city, state, etc), have a look at the `geocodejson` format.
All other formats return classifications according to OSM tagging.
There is a much larger set of categories and they are not always consistent,
which makes them very hard to work with.
Include a breakdown of the address into elements. (Default: 0)
| Parameter | Value | Default |
|-----------| ----- | ------- |
| extratags | 0 or 1 | 0 |
* `extratags=[0|1]`
When set to 1, the response include any additional information in the result
that is available in the database, e.g. wikipedia link, opening hours.
Include additional information in the result if available,
e.g. wikipedia link, opening hours. (Default: 0)
| Parameter | Value | Default |
|-----------| ----- | ------- |
| namedetails | 0 or 1 | 0 |
* `namedetails=[0|1]`
When set to 1, include a full list of names for the result. These may include
language variants, older names, references and brand.
Include a list of alternative names in the results. These may include
language variants, references, operator and brand. (Default: 0)
### Language of results
| Parameter | Value | Default |
|-----------| ----- | ------- |
| accept-language | browser language string | content of "Accept-Language" HTTP header |
* `accept-language=<browser language string>`
Preferred language order for showing search results. This may either be
a simple comma-separated list of language codes or have the same format
as the ["Accept-Language" HTTP header](https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Accept-Language).
Preferred language order for showing search results, overrides the value
specified in the ["Accept-Language" HTTP header](https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Accept-Language).
Either use a standard RFC2616 accept-language string or a simple
comma-separated list of language codes.
!!! tip
First-time users of Nominatim tend to be confused that they get different
results when using Nominatim in the browser versus in a command-line tool
like wget or curl. The command-line tools
usually don't send any Accept-Language header, prompting Nominatim
to show results in the local language. Browsers on the contratry always
send the currently chosen browser language.
### Result limitation
### Result restriction
* `countrycodes=<countrycode>[,<countrycode>][,<countrycode>]...`
There are two ways to influence the results. *Filters* exclude certain
kinds of results completely. *Boost parameters* only change the order of the
results and thus give a preference to some results over others.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| countrycodes | comma-separated list of country codes | _unset_ |
Filer that limits the search results to one or more countries.
The country code must be the
[ISO 3166-1alpha2](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) code
of the country, e.g. `gb` for the United Kingdom, `de` for Germany.
Limit search results to one or more countries. `<countrycode>` must be the
[ISO 3166-1alpha2](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) code,
e.g. `gb` for the United Kingdom, `de` for Germany.
Each place in Nominatim is assigned to one country code based
on OSM country boundaries. In rare cases a place may not be in any country
at all, for example, when it is in international waters. These places are
also excluded when the filter is set.
at all, for example, in international waters.
!!! Note
This parameter should not be confused with the 'country' parameter of
the structured query. The 'country' parameter contains a search term
and will be handled with some fuzziness. The `countrycodes` parameter
is a hard filter and as such should be prefered. Having both parameters
in the same query will work. If the parameters contradict each other,
the search will come up empty.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| layer | comma-separated list of: `address`, `poi`, `railway`, `natural`, `manmade` | _unset_ (no restriction) |
The layer filter allows to select places by themes.
The `address` layer contains all places that make up an address:
address points with house numbers, streets, inhabited places (suburbs, villages,
cities, states tec.) and administrative boundaries.
The `poi` layer selects all point of interest. This includes classic POIs like
restaurants, shops, hotels but also less obvious features like recycling bins,
guideposts or benches.
The `railway` layer includes railway infrastructure like tracks.
Note that in Nominatim's standard configuration, only very few railway
features are imported into the database.
The `natural` layer collects feautures like rivers, lakes and mountains while
the `manmade` layer functions as a catch-all for features not covered by the
other layers.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| featureType | one of: `country`, `state`, `city`, `settlement` | _unset_ |
The featureType allows to have a more fine-grained selection for places
from the address layer. Results can be restricted to places that make up
the 'state', 'country' or 'city' part of an address. A featureType of
settlement selects any human inhabited feature from 'state' down to
'neighbourhood'.
When featureType ist set, then results are automatically restricted
to the address layer (see above).
!!! tip
Instead of using the featureType filters `country`, `state` or `city`,
you can also use a structured query without the finer-grained parameters
amenity or street.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| exclude_place_ids | comma-separeted list of place ids |
* `exclude_place_ids=<place_id,[place_id],[place_id]`
If you do not want certain OSM objects to appear in the search
result, give a comma separated list of the `place_id`s you want to skip.
@@ -233,212 +104,180 @@ This can be used to retrieve additional search results. For example, if a
previous query only returned a few results, then including those here would
cause the search to return other, less accurate, matches (if possible).
| Parameter | Value | Default |
|-----------| ----- | ------- |
| viewbox | `<x1>,<y1>,<x2>,<y2>` | _unset_ |
Boost parameter which focuses the search on the given area.
Any two corner points of the box are accepted as long as they make a proper
box. `x` is longitude, `y` is latitude.
* `limit=<integer>`
| Parameter | Value | Default |
|-----------| ----- | ------- |
| bounded | 0 or 1 | 0 |
Limit the number of returned results. (Default: 10, Maximum: 50)
When set to 1, then it turns the 'viewbox' parameter (see above) into
a filter paramter, excluding any results outside the viewbox.
When `bounded=1` is given and the viewbox is small enough, then an amenity-only
search is allowed. Give the special keyword for the amenity in square
* `viewbox=<x1>,<y1>,<x2>,<y2>`
The preferred area to find search results. Any two corner points of the box
are accepted as long as they span a real box. `x` is longitude,
`y` is latitude.
* `bounded=[0|1]`
When a viewbox is given, restrict the result to items contained within that
viewbox (see above). When `viewbox` and `bounded=1` are given, an amenity
only search is allowed. Give the special keyword for the amenity in square
brackets, e.g. `[pub]` and a selection of objects of this type is returned.
There is no guarantee that the result returns all objects in the area.
There is no guarantee that the result is complete. (Default: 0)
### Polygon output
| Parameter | Value | Default |
|-----------| ----- | ------- |
| polygon_geojson | 0 or 1 | 0 |
| polygon_kml | 0 or 1 | 0 |
| polygon_svg | 0 or 1 | 0 |
| polygon_text | 0 or 1 | 0 |
* `polygon_geojson=1`
* `polygon_kml=1`
* `polygon_svg=1`
* `polygon_text=1`
Add the full geometry of the place to the result output. Output formats
in GeoJSON, KML, SVG or WKT are supported. Only one of these
options can be used at a time.
Output geometry of results as a GeoJSON, KML, SVG or WKT. Only one of these
options can be used at a time. (Default: 0)
| Parameter | Value | Default |
|-----------| ----- | ------- |
| polygon_threshold | floating-point number | 0.0 |
* `polygon_threshold=0.0`
When one of the polygon_* outputs is chosen, return a simplified version
of the output geometry. The parameter describes the
Return a simplified version of the output geometry. The parameter is the
tolerance in degrees with which the geometry may differ from the original
geometry. Topology is preserved in the geometry.
geometry. Topology is preserved in the result. (Default: 0.0)
### Other
| Parameter | Value | Default |
|-----------| ----- | ------- |
| email | valid email address | _unset_ |
* `email=<valid email address>`
If you are making large numbers of request please include an appropriate email
address to identify your requests. See Nominatim's
[Usage Policy](https://operations.osmfoundation.org/policies/nominatim/) for more details.
address to identify your requests. See Nominatim's [Usage Policy](https://operations.osmfoundation.org/policies/nominatim/) for more details.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| dedupe | 0 or 1 | 1 |
* `dedupe=[0|1]`
Sometimes you have several objects in OSM identifying the same place or
object in reality. The simplest case is a street being split into many
different OSM ways due to different characteristics. Nominatim will
attempt to detect such duplicates and only return one match. Setting
this parameter to 0 disables this deduplication mechanism and
ensures that all results are returned.
attempt to detect such duplicates and only return one match unless
this parameter is set to 0. (Default: 1)
| Parameter | Value | Default |
|-----------| ----- | ------- |
| debug | 0 or 1 | 0 |
* `debug=[0|1]`
Output assorted developer debug information. Data on internals of Nominatim's
"search loop" logic, and SQL queries. The output is HTML format.
This overrides the specified machine readable format.
"Search Loop" logic, and SQL queries. The output is (rough) HTML format.
This overrides the specified machine readable format. (Default: 0)
## Examples
##### XML with KML polygon
##### XML with kml polygon
* [https://nominatim.openstreetmap.org/search?q=135+pilkington+avenue,+birmingham&format=xml&polygon_kml=1&addressdetails=1](https://nominatim.openstreetmap.org/search?q=135+pilkington+avenue,+birmingham&format=xml&polygon_kml=1&addressdetails=1)
* [https://nominatim.openstreetmap.org/search?q=135+pilkington+avenue,+birmingham&format=xml&polygon_geojson=1&addressdetails=1](https://nominatim.openstreetmap.org/search?q=135+pilkington+avenue,+birmingham&format=xml&polygon_geojson=1&addressdetails=1)
```xml
<?xml version="1.0" encoding="UTF-8" ?>
<searchresults timestamp="Tue, 08 Aug 2023 15:45:41 +00:00"
attribution="Data © OpenStreetMap contributors, ODbL 1.0. http://osm.org/copyright"
querystring="135 pilkington avenue, birmingham"
more_url="https://nominatim.openstreetmap.org/search?q=135+pilkington+avenue%2C+birmingham&amp;polygon_kml=1&amp;addressdetails=1&amp;limit=20&amp;exclude_place_ids=125279639&amp;format=xml"
exclude_place_ids="125279639">
<place place_id="125279639"
osm_type="way"
osm_id="90394480"
lat="52.5487921"
lon="-1.8164308"
boundingbox="52.5487473,52.5488481,-1.8165130,-1.8163464"
place_rank="30"
address_rank="30"
display_name="135, Pilkington Avenue, Maney, Sutton Coldfield, Wylde Green, Birmingham, West Midlands Combined Authority, England, B72 1LH, United Kingdom"
class="building"
type="residential"
importance="9.999999994736442e-08">
<geokml>
<Polygon>
<outerBoundaryIs>
<LinearRing>
<coordinates>-1.816513,52.5487566 -1.816434,52.5487473 -1.816429,52.5487629 -1.8163717,52.5487561 -1.8163464,52.5488346 -1.8164599,52.5488481 -1.8164685,52.5488213 -1.8164913,52.548824 -1.816513,52.5487566</coordinates>
</LinearRing>
</outerBoundaryIs>
</Polygon>
</geokml>
<house_number>135</house_number>
<road>Pilkington Avenue</road>
<hamlet>Maney</hamlet>
<town>Sutton Coldfield</town>
<village>Wylde Green</village>
<city>Birmingham</city>
<ISO3166-2-lvl8>GB-BIR</ISO3166-2-lvl8>
<state_district>West Midlands Combined Authority</state_district>
<state>England</state>
<ISO3166-2-lvl4>GB-ENG</ISO3166-2-lvl4>
<postcode>B72 1LH</postcode>
<country>United Kingdom</country>
<country_code>gb</country_code>
</place>
</searchresults>
<searchresults timestamp="Sat, 07 Nov 09 14:42:10 +0000" querystring="135 pilkington, avenue birmingham" polygon="true">
<place
place_id="1620612" osm_type="node" osm_id="452010817"
boundingbox="52.548641204834,52.5488433837891,-1.81612110137939,-1.81592094898224"
lat="52.5487429714954" lon="-1.81602098644987"
display_name="135, Pilkington Avenue, Wylde Green, City of Birmingham, West Midlands (county), B72, United Kingdom"
class="place" type="house">
<geokml>
<Polygon>
<outerBoundaryIs>
<LinearRing>
<coordinates>-1.816513,52.548756599999997 -1.816434,52.548747300000002 -1.816429,52.5487629 -1.8163717,52.548756099999999 -1.8163464,52.548834599999999 -1.8164599,52.548848100000001 -1.8164685,52.5488213 -1.8164913,52.548824000000003 -1.816513,52.548756599999997</coordinates>
</LinearRing>
</outerBoundaryIs>
</Polygon>
</geokml>
<house_number>135</house_number>
<road>Pilkington Avenue</road>
<village>Wylde Green</village>
<town>Sutton Coldfield</town>
<city>City of Birmingham</city>
<county>West Midlands (county)</county>
<postcode>B72</postcode>
<country>United Kingdom</country>
<country_code>gb</country_code>
</place>
</searchresults>
```
##### JSON with SVG polygon
[https://nominatim.openstreetmap.org/search?q=Unter%20den%20Linden%201%20Berlin&format=json&addressdetails=1&limit=1&polygon_svg=1](https://nominatim.openstreetmap.org/search?q=Unter%20den%20Linden%201%20Berlin&format=json&addressdetails=1&limit=1&polygon_svg=1)
[https://nominatim.openstreetmap.org/search/Unter%20den%20Linden%201%20Berlin?format=json&addressdetails=1&limit=1&polygon_svg=1](https://nominatim.openstreetmap.org/search/Unter%20den%20Linden%201%20Berlin?format=json&addressdetails=1&limit=1&polygon_svg=1)
```json
[
{
"address": {
"ISO3166-2-lvl4": "DE-BE",
"borough": "Mitte",
"city": "Berlin",
"country": "Deutschland",
"country_code": "de",
"historic": "Kommandantenhaus",
"house_number": "1",
"neighbourhood": "Friedrichswerder",
"postcode": "10117",
"road": "Unter den Linden",
"suburb": "Mitte"
},
"boundingbox": [
"52.5170798",
"52.5173311",
"13.3975116",
"13.3981577"
],
"class": "historic",
"display_name": "Kommandantenhaus, 1, Unter den Linden, Friedrichswerder, Mitte, Berlin, 10117, Deutschland",
"importance": 0.8135042058306902,
"lat": "52.51720765",
"licence": "Data © OpenStreetMap contributors, ODbL 1.0. https://osm.org/copyright",
"lon": "13.397834399325466",
"osm_id": 15976890,
"osm_type": "way",
"place_id": 108681845,
"svg": "M 13.3975116 -52.5172905 L 13.397549 -52.5170798 13.397715 -52.5170906 13.3977122 -52.5171064 13.3977392 -52.5171086 13.3977417 -52.5170924 13.3979655 -52.5171069 13.3979623 -52.5171233 13.3979893 -52.5171248 13.3979922 -52.5171093 13.3981577 -52.5171203 13.398121 -52.5173311 13.3978115 -52.5173103 Z",
"type": "house"
}
]
{
"address": {
"city": "Berlin",
"city_district": "Mitte",
"construction": "Unter den Linden",
"continent": "European Union",
"country": "Deutschland",
"country_code": "de",
"house_number": "1",
"neighbourhood": "Scheunenviertel",
"postcode": "10117",
"public_building": "Kommandantenhaus",
"state": "Berlin",
"suburb": "Mitte"
},
"boundingbox": [
"52.5170783996582",
"52.5173187255859",
"13.3975105285645",
"13.3981599807739"
],
"class": "amenity",
"display_name": "Kommandantenhaus, 1, Unter den Linden, Scheunenviertel, Mitte, Berlin, 10117, Deutschland, European Union",
"importance": 0.73606775332943,
"lat": "52.51719785",
"licence": "Data \u00a9 OpenStreetMap contributors, ODbL 1.0. https://www.openstreetmap.org/copyright",
"lon": "13.3978352028938",
"osm_id": "15976890",
"osm_type": "way",
"place_id": "30848715",
"svg": "M 13.397511 -52.517283599999999 L 13.397829400000001 -52.517299800000004 13.398131599999999 -52.517315099999998 13.398159400000001 -52.517112099999999 13.3975388 -52.517080700000001 Z",
"type": "public_building"
}
```
##### JSON with address details
[https://nominatim.openstreetmap.org/search?addressdetails=1&q=bakery+in+berlin+wedding&format=jsonv2&limit=1](https://nominatim.openstreetmap.org/search?addressdetails=1&q=bakery+in+berlin+wedding&format=jsonv2&limit=1)
[https://nominatim.openstreetmap.org/?addressdetails=1&q=bakery+in+berlin+wedding&format=json&limit=1](https://nominatim.openstreetmap.org/?addressdetails=1&q=bakery+in+berlin+wedding&format=json&limit=1)
```json
[
{
"address": {
"ISO3166-2-lvl4": "DE-BE",
"borough": "Mitte",
"city": "Berlin",
"country": "Deutschland",
"country_code": "de",
"neighbourhood": "Sprengelkiez",
"postcode": "13347",
"road": "Lindower Straße",
"shop": "Ditsch",
"suburb": "Wedding"
},
"addresstype": "shop",
"boundingbox": [
"52.5427201",
"52.5427654",
"13.3668619",
"13.3669442"
],
"category": "shop",
"display_name": "Ditsch, Lindower Straße, Sprengelkiez, Wedding, Mitte, Berlin, 13347, Deutschland",
"importance": 9.99999999995449e-06,
"lat": "52.54274275",
"licence": "Data © OpenStreetMap contributors, ODbL 1.0. http://osm.org/copyright",
"lon": "13.36690305710228",
"name": "Ditsch",
"osm_id": 437595031,
"osm_type": "way",
"place_id": 204751033,
"place_rank": 30,
"type": "bakery"
}
]
{
"address": {
"bakery": "B\u00e4cker Kamps",
"city_district": "Mitte",
"continent": "European Union",
"country": "Deutschland",
"country_code": "de",
"footway": "Bahnsteig U6",
"neighbourhood": "Sprengelkiez",
"postcode": "13353",
"state": "Berlin",
"suburb": "Wedding"
},
"boundingbox": [
"52.5460929870605",
"52.5460968017578",
"13.3591794967651",
"13.3591804504395"
],
"class": "shop",
"display_name": "B\u00e4cker Kamps, Bahnsteig U6, Sprengelkiez, Wedding, Mitte, Berlin, 13353, Deutschland, European Union",
"icon": "https://nominatim.openstreetmap.org/images/mapicons/shopping_bakery.p.20.png",
"importance": 0.201,
"lat": "52.5460941",
"licence": "Data \u00a9 OpenStreetMap contributors, ODbL 1.0. https://www.openstreetmap.org/copyright",
"lon": "13.35918",
"osm_id": "317179427",
"osm_type": "node",
"place_id": "1453068",
"type": "bakery"
}
```
##### GeoJSON

View File

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

View File

@@ -1,149 +0,0 @@
# Customizing Per-Country Data
Whenever an OSM is imported into Nominatim, the object is first assigned
a country. Nominatim can use this information to adapt various aspects of
the address computation to the local customs of the country. This section
explains how country assignment works and the principal per-country
localizations.
## Country assignment
Countries are assigned on the basis of country data from the OpenStreetMap
input data itself. Countries are expected to be tagged according to the
[administrative boundary schema](https://wiki.openstreetmap.org/wiki/Tag:boundary%3Dadministrative):
a OSM relation with `boundary=administrative` and `admin_level=2`. Nominatim
uses the country code to distinguish the countries.
If there is no country data available for a point, then Nominatim uses the
fallback data imported from `data/country_osm_grid.sql.gz`. This was computed
from OSM data as well but is guaranteed to cover all countries.
Some OSM objects may also be located outside any country, for example a buoy
in the middle of the ocean. These object do not get any country assigned and
get a default treatment when it comes to localized handling of data.
## Per-country settings
### Global country settings
The main place to configure settings per country is the file
`settings/country_settings.yaml`. This file has one section per country that
is recognised by Nominatim. Each section is tagged with the country code
(in lower case) and contains the different localization information. Only
countries which are listed in this file are taken into account for computations.
For example, the section for Andorra looks like this:
```
partition: 35
languages: ca
names: !include country-names/ad.yaml
postcode:
pattern: "(ddd)"
output: AD\1
```
The individual settings are described below.
#### `partition`
Nominatim internally splits the data into multiple tables to improve
performance. The partition number tells Nominatim into which table to put
the country. This is purely internal management and has no effect on the
output data.
The default is to have one partition per country.
#### `languages`
A comma-separated list of ISO-639 language codes of default languages in the
country. These are the languages used in name tags without a language suffix.
Note that this is not necessarily the same as the list of official languages
in the country. There may be officially recognised languages in a country
which are only ever used in name tags with the appropriate language suffixes.
Conversely, a non-official language may appear a lot in the name tags, for
example when used as an unofficial Lingua Franca.
List the languages in order of frequency of appearance with the most frequently
used language first. It is not recommended to add languages when there are only
very few occurrences.
If only one language is listed, then Nominatim will 'auto-complete' the
language of names without an explicit language-suffix.
#### `names`
List of names of the country and its translations. These names are used as
a baseline. It is always possible to search countries by the given names, no
matter what other names are in the OSM data. They are also used as a fallback
when a needed translation is not available.
!!! Note
The list of names per country is currently fairly large because Nominatim
supports translations in many languages per default. That is why the
name lists have been separated out into extra files. You can find the
name lists in the file `settings/country-names/<country code>.yaml`.
The names section in the main country settings file only refers to these
files via the special `!include` directive.
#### `postcode`
Describes the format of the postcode that is in use in the country.
When a country has no official postcodes, set this to no. Example:
```
ae:
postcode: no
```
When a country has a postcode, you need to state the postcode pattern and
the default output format. Example:
```
bm:
postcode:
pattern: "(ll)[ -]?(dd)"
output: \1 \2
```
The **pattern** is a regular expression that describes the possible formats
accepted as a postcode. The pattern follows the standard syntax for
[regular expressions in Python](https://docs.python.org/3/library/re.html#regular-expression-syntax)
with two extra shortcuts: `d` is a shortcut for a single digit([0-9])
and `l` for a single ASCII letter ([A-Z]).
Use match groups to indicate groups in the postcode that may optionally be
separated with a space or a hyphen.
For example, the postcode for Bermuda above always consists of two letters
and two digits. They may optionally be separated by a space or hyphen. That
means that Nominatim will consider `AB56`, `AB 56` and `AB-56` spelling variants
for one and the same postcode.
Never add the country code in front of the postcode pattern. Nominatim will
automatically accept variants with a country code prefix for all postcodes.
The **output** field is an optional field that describes what the canonical
spelling of the postcode should be. The format is the
[regular expression expand syntax](https://docs.python.org/3/library/re.html#re.Match.expand) referring back to the bracket groups in the pattern.
Most simple postcodes only have one spelling variant. In that case, the
**output** can be omitted. The postcode will simply be used as is.
In the Bermuda example above, the canonical spelling would be to have a space
between letters and digits.
!!! Warning
When your postcode pattern covers multiple variants of the postcode, then
you must explicitly state the canonical output or Nominatim will not
handle the variations correctly.
### Other country-specific configuration
There are some other configuration files where you can set localized settings
according to the assigned country. These are:
* [Place ranking configuration](Ranking.md)
Please see the linked documentation sections for more information.

View File

@@ -1,439 +1,149 @@
## Configuring the Import
In the very first step of a Nominatim import, OSM data is loaded into the
database. Nominatim uses [osm2pgsql](https://osm2pgsql.org) for this task.
It comes with a [flex style](https://osm2pgsql.org/doc/manual.html#the-flex-output)
specifically tailored to filter and convert OSM data into Nominatim's
internal data representation.
Which OSM objects are added to the database and which of the tags are used
can be configured via the import style configuration file. This
is a JSON file which contains a list of rules which are matched against every
tag of every object and then assign the tag its specific role.
There are a number of default configurations for the flex style which
result in geocoding databases of different detail. The
[Import section](../admin/Import.md#filtering-imported-data) explains
these default configurations in detail.
The style to use is given by the `NOMINATIM_IMPORT_STYLE` configuration
option. There are a number of default styles, which are explained in detail
in the [Import section](../admin/Import.md#filtering-imported-data). These
standard styles may be referenced by their name.
You can also create your own custom style. Put the style file into your
You can also create your own custom syle. Put the style file into your
project directory and then set `NOMINATIM_IMPORT_STYLE` to the name of the file.
It is always recommended to start with one of the standard styles and customize
those. You find the standard styles under the name `import-<stylename>.lua`
those. You find the standard styles under the name `import-<stylename>.style`
in the standard Nominatim configuration path (usually `/etc/nominatim` or
`/usr/local/etc/nominatim`).
The remainder of the page describes how the flex style works and how to
customize it.
The remainder of the page describes the format of the file.
### The `flex-base.lua` module
### Configuration Rules
The core of Nominatim's flex import configuration is the `flex-base` module.
It defines the table layout used by Nominatim and provides standard
implementations for the import callbacks that make it easy to customize
how OSM tags are used by Nominatim.
Every custom style should include this module to make sure that the correct
tables are created. Thus start your custom style as follows:
``` lua
local flex = require('flex-base')
A single rule looks like this:
```json
{
"keys" : ["key1", "key2", ...],
"values" : {
"value1" : "prop",
"value2" : "prop1,prop2"
}
}
```
The following sections explain how the module can be customized.
### Changing the recognized tags
If you just want to change which OSM tags are recognized during import,
then there are a number of convenience functions to set the tag lists used
during the processing.
!!! warning
There are no built-in defaults for the tag lists, so all the functions
need to be called from your style script to fully process the data.
Make sure you start from one of the default style and only modify
the data you are interested in. You can also derive your style from an
existing style by importing the appropriate module, e.g.
`local flex = require('import-street')`.
Many of the following functions take _key match lists_. These lists can
contain three kinds of strings to match against tag keys:
A string that ends in an asterisk `*` is a prefix match and accordingly matches
against any key that starts with the given string (minus the `*`).
A suffix match can be defined similarly with a string that starts with a `*`.
Any other string is matched exactly against tag keys.
#### `set_main_tags()` - principal tags
If a principal or main tag is found on an OSM object, then the object
is included in Nominatim's search index. A single object may also have
multiple main tags. In that case, the object will be included multiple
times in the index, once for each main tag.
The flex script distinguishes between four types of main tags:
* __always__: a main tag that is used unconditionally
* __named__: consider this main tag only, if the object has a proper name
(a reference is not enough, see below).
* __named_with_key__: consider this main tag only, when the object has
a proper name with a domain prefix. For example, if the main tag is
`bridge=yes`, then it will only be added as an extra row, if there is
a tag `bridge:name[:XXX]` for the same object. If this property is set,
all other names that are not domain-specific are ignored.
* __fallback__: use this main tag only, if there is no other main tag.
Fallback always implied `named`, i.e. fallbacks are only tried for
named objects.
The `set_main_tags()` function takes exactly one table parameter which
defines the keys and key/value combinations to include and the kind of
main tag. Each lua table key defines an OSM tag key. The value may
be a string defining the kind of main key as described above. Then the tag will
be considered a main tag for any possible value. To further restrict
which values are acceptable, give a table with the permitted values
and their kind of main tag. If the table contains a simple value without
key, then this is used as default for values that are not listed.
!!! example
``` lua
local flex = require('import-full')
flex.set_main_tags{
boundary = {administrative = 'named'},
highway = {'always', street_lamp = 'named'},
landuse = 'fallback'
}
```
In this example an object with a `boundary` tag will only be included
when it has a value of `administrative`. Objects with `highway` tags are
always included. However when the value is `street_lamp` then the object
must have a name, too. With any other value, the object is included
independently of the name. Finally, if a `landuse` tag is present then
it will be used independely of the concrete value if neither boundary
nor highway tags were found and the object is named.
#### `set_prefilters()` - ignoring tags
Pre-filtering of tags allows to ignore them for any further processing.
Thus pre-filtering takes precedence over any other tag processing. This is
useful when some specific key/value combinations need to be excluded from
processing. When tags are filtered, they may either be deleted completely
or moved to `extratags`. Extra tags are saved with the object and returned
to the user when requested, but are not used otherwise.
`set_prefilters()` takes a table with four optional fields:
* __delete_keys__ is a _key match list_ for tags that should be deleted
* __delete_tags__ contains a table of tag keys pointing to a list of tag
values. Tags with matching key/value pairs are deleted.
* __extra_keys__ is a _key match list_ for tags which should be saved into
extratags
* __extra_tags__ contains a table of tag keys pointing to a list of tag
values. Tags with matching key/value pairs are moved to extratags.
Key list may contain three kinds of strings:
A string that ends in an asterisk `*` is a prefix match and accordingly matches
against any key that starts with the given string (minus the `*`).
A suffix match can be defined similarly with a string that starts with a `*`.
Any other string is matched exactly against tag keys.
!!! example
``` lua
local flex = require('import-full')
flex.set_prefilters{
delete_keys = {'source', 'source:*'},
extra_tags = {amenity = {'yes', 'no'}}
}
flex.set_main_tags{
amenity = 'always'
}
```
In this example any tags `source` and tags that begin with `source:` are
deleted before any other processing is done. Getting rid of frequent tags
this way can speed up the import.
Tags with `amenity=yes` or `amenity=no` are moved to extratags. Later
all tags with an `amenity` key are made a main tag. This effectively means
that Nominatim will use all amenity tags except for those with value
yes and no.
#### `set_name_tags()` - defining names
The flex script distinguishes between two kinds of names:
* __main__: the primary names make an object fully searchable.
Main tags of type _named_ will only cause the object to be included when
such a primary name is present. Primary names are usually those found
in the `name` tag and its variants.
* __extra__: extra names are still added to the search index but they are
alone not sufficient to make an object named.
`set_name_tags()` takes a table with two optional fields `main` and `extra`.
They take _key match lists_ for main and extra names respectively.
!!! example
``` lua
local flex = require('flex-base')
flex.set_main_tags{highway = {traffic_light = 'named'}}
flex.set_name_tags{main = {'name', 'name:*'},
extra = {'ref'}
}
```
This example creates a search index over traffic lights but will
only include those that have a common name and not those which just
have some reference ID from the city.
#### `set_address_tags()` - defining address parts
Address tags will be used to build up the address of an object.
`set_address_tags()` takes a table with arbitrary fields pointing to
_key match lists_. To fields have a special meaning:
* __main__: defines
the tags that make a full address object out of the OSM object. This
is usually the housenumber or variants thereof. If a main address tag
appears, then the object will always be included, if necessary with a
fallback of `place=house`. If the key has a prefix of `addr:` or `is_in:`
this will be stripped.
* __extra__: defines all supplementary tags for addresses, tags like `addr:street`, `addr:city` etc. If the key has a prefix of `addr:` or `is_in:` this will be stripped.
All other fields will be handled as summary fields. If a key matches the
key match list, then its value will be added to the address tags with the
name of the field as key. If multiple tags match, then an arbitrary one
wins.
Country tags are handled slightly special. Only tags with a two-letter code
are accepted, all other values are discarded.
!!! example
``` lua
local flex = require('import-full')
flex.set_address_tags{
main = {'addr:housenumber'},
extra = {'addr:*'},
postcode = {'postal_code', 'postcode', 'addr:postcode'},
country = {'country-code', 'ISO3166-1'}
}
```
In this example all tags which begin with `addr:` will be saved in
the address tag list. If one of the tags is `addr:housenumber`, the
object will fall back to be entered as a `place=house` in the database
unless there is another interested main tag to be found.
Tags with keys `country-code` and `ISO3166-1` are saved with their
value under `country` in the address tag list. The same thing happens
to postcodes, they will always be saved under the key `postcode` thus
normalizing the multitude of keys that are used in the OSM database.
#### `set_unused_handling()` - processing remaining tags
This function defines what to do with tags that remain after all tags
have been classified using the functions above. There are two ways in
which the function can be used:
`set_unused_handling(delete_keys = ..., delete_tags = ...)` deletes all
keys that match the descriptions in the parameters and moves all remaining
tags into the extratags list.
`set_unused_handling(extra_keys = ..., extra_tags = ...)` moves all tags
matching the parameters into the extratags list and then deletes the remaining
tags. For the format of the parameters see the description in `set_prefilters()`
above.
A rule first defines a list of keys to apply the rule to. This is always a list
of strings. The string may have four forms. An empty string matches against
any key. A string that ends in an asterisk `*` is a prefix match and accordingly
matches against any key that starts with the given string (minus the `*`). A
suffix match can be defined similarly with a string that starts with a `*`. Any
other string constitutes an exact match.
!!! example
``` lua
local flex = require('import-full')
The second part of the rules defines a list of values and the properties that
apply to a successful match. Value strings may be either empty, which
means that they match any value, or describe an exact match. Prefix
or suffix matching of values is not possible.
flex.set_address_tags{
main = {'addr:housenumber'},
extra = {'addr:*', 'tiger:county'}
}
flex.set_unused_handling{delete_keys = {'tiger:*'}}
```
For a rule to match, it has to find a valid combination of keys and values. The
resulting property is that of the matched values.
In this example all remaining tags except those beginning with `tiger:`
are moved to the extratags list. Note that it is not possible to
already delete the tiger tags with `set_prefilters()` because that
would remove tiger:county before the address tags are processed.
### Customizing osm2pgsql callbacks
The rules in a configuration file are processed sequentially and the first
match for each tag wins.
osm2pgsql expects the flex style to implement three callbacks, one process
function per OSM type. If you want to implement special handling for
certain OSM types, you can override the default implementations provided
by the flex-base module.
A rule where key and value are the empty string is special. This defines the
fallback when none of the rules match. The fallback is always used as a last
resort when nothing else matches, no matter where the rule appears in the file.
Defining multiple fallback rules is not allowed. What happens in this case,
is undefined.
#### Changing the relation types to be handled
### Tag Properties
The default scripts only allows relations of type `multipolygon`, `boundary`
and `waterway`. To add other types relations, set `RELATION_TYPES` for
the type to the kind of geometry that should be created. The following
kinds of geometries can be used:
* __relation_as_multipolygon__ creates a (Multi)Polygon from the ways in
the relation. If the ways do not form a valid area, then the object is
silently discarded.
* __relation_as_multiline__ creates a (Mutli)LineString from the ways in
the relations. Ways are combined as much as possible without any regards
to their order in the relation.
!!! Example
``` lua
local flex = require('import-full')
flex.RELATION_TYPES['site'] = flex.relation_as_multipolygon
```
With this line relations of `type=site` will be included in the index
according to main tags found. This only works when the site relation
resolves to a valid area. Nodes in the site relation are not part of the
geometry.
#### Adding additional logic to processing functions
The default processing functions are also exported by the flex-base module
as `process_node`, `process_way` and `process_relation`. These can be used
to implement your own processing functions with some additional processing
logic.
!!! Example
``` lua
local flex = require('import-full')
function osm2pgsql.process_relation(object)
if object.tags.boundary ~= 'administrative' or object.tags.admin_level ~= '2' then
flex.process_relation(object)
end
end
```
This example discards all country-level boundaries and uses standard
handling for everything else. This can be useful if you want to use
your own custom country boundaries.
### Customizing the main processing function
The main processing function of the flex style can be found in the function
`process_tags`. This function is called for all OSM object kinds and is
responsible for filtering the tags and writing out the rows into Postgresql.
!!! Example
``` lua
local flex = require('import-full')
local original_process_tags = flex.process_tags
function flex.process_tags(o)
if o.object.tags.highway ~= nil and o.object.tags.access == 'no' then
return
end
original_process_tags(o)
end
```
This example shows the most simple customization of the process_tags function.
It simply adds some additional processing before running the original code.
To do that, first save the original function and then overwrite process_tags
from the module. In this example all highways which are not accessible
by anyone will be ignored.
#### The `Place` class
The `process_tags` function receives a Lua object of `Place` type which comes
with some handy functions to collect the data necessary for geocoding and
writing it into the place table. Always use this object to fill the table.
The Place class has some attributes which you may access read-only:
* __object__ is the original OSM object data handed in by osm2pgsql
* __admin_level__ is the content of the admin_level tag, parsed into an
integer and normalized to a value between 0 and 15
* __has_name__ is a boolean indicating if the object has a full name
* __names__ is a table with the collected list of name tags
* __address__ is a table with the collected list of address tags
* __extratags__ is a table with the collected list of additional tags to save
There are a number of functions to fill these fields. All functions expect
a table parameter with fields as indicated in the description.
Many of these functions expect match functions which are described in detail
further below.
* __delete{match=...}__ removes all tags that match the match function given
in _match_.
* __grab_extratags{match=...}__ moves all tags that match the match function
given in _match_ into extratags. Returns the number of tags moved.
* __clean{delete=..., extra=...}__ deletes all tags that match _delete_ and
moves the ones that match _extra_ into extratags
* __grab_address_parts{groups=...}__ moves matching tags into the address table.
_groups_ must be a group match function. Tags of the group `main` and
`extra` are added to the address table as is but with `addr:` and `is_in:`
prefixes removed from the tag key. All other groups are added with the
group name as key and the value from the tag. Multiple values of the same
group overwrite each other. The function returns the number of tags saved
from the main group.
* __grab_main_parts{groups=...}__ moves matching tags into the name table.
_groups_ must be a group match function. If a tags of the group `main` is
present, the object will be marked as having a name. Tags of group `house`
produce a fallback to `place=house`. This fallback is return by the function
if present.
There are two functions to write a row into the place table. Both functions
expect the main tag (key and value) for the row and then use the collected
information from the name, address, extratags etc. fields to complete the row.
They also have a boolean parameter `save_extra_mains` which defines how any
unprocessed tags are handled: when True, the tags will be saved as extratags,
when False, they will be simply discarded.
* __write_row(key, value, save_extra_mains)__ creates a new table row from
the current state of the Place object.
* __write_place(key, value, mtype, save_extra_mains)__ creates a new row
conditionally. When value is nil, the function will attempt to look up the
value in the object tags. If value is still nil or mtype is nil, the row
is ignored. An mtype of `always` will then always write out the row,
a mtype of `named` only, when the object has a full name. When mtype
is `named_with_key`, the function checks for a domain name, i.e. a name
tag prefixed with the name of the main key. Only if at least one is found,
the row will be written. The names are replaced with the domain names found.
#### Match functions
The Place functions usually expect either a _match function_ or a
_group match function_ to find the tags to apply their function to.
The __match function__ is a Lua function which takes two parameters,
key and value, and returns a boolean to indicate that a tag matches. The
flex-base module has a convenience function `tag_match()` to create such a
function. It takes a table with two optional fields: `keys` takes a key match
list (see above), `tags` takes a table with keys that point to a list of
possible values, thus defining key/value matches.
The __group match function__ is a Lua function which also takes two parameters,
key and value, and returns a string indicating to which group or type they
belong to. The `tag_group()` can be used to create such a function. It expects
a table where the group names are the keys and the values are a key match list.
### Using the gazetteer output of osm2pgsql
Nominatim still allows you to configure the gazetteer output to remain
backwards compatible with older imports. It will be automatically used
when the style file name ends in `.style`. For documentation of the
old import style, please refer to the documentation of older releases
of Nominatim. Do not use the gazetteer output for new imports. There is no
guarantee that new versions of Nominatim are fully compatible with the
gazetteer output.
One or more of the following properties may be given for each tag:
* `main`
A principal tag. A new row will be added for the object with key and value
as `class` and `type`.
* `with_name`
When the tag is a principal tag (`main` property set): only really add a new
row, if there is any name tag found (a reference tag is not sufficient, see
below).
* `with_name_key`
When the tag is a principal tag (`main` property set): only really add a new
row, if there is also a name tag that matches the key of the principal tag.
For example, if the main tag is `bridge=yes`, then it will only be added as
an extra row, if there is a tag `bridge:name[:XXX]` for the same object.
If this property is set, all other names that are not domain-specific are
ignored.
* `fallback`
When the tag is a principal tag (`main` property set): only really add a new
row, when no other principal tags for this object have been found. Only one
fallback tag can win for an object.
* `operator`
When the tag is a principal tag (`main` property set): also include the
`operator` tag in the list of names. This is a special construct for an
out-dated tagging practise in OSM. Fuel stations and chain restaurants
in particular used to have the name of the chain tagged as `operator`.
These days the chain can be more commonly found in the `brand` tag but
there is still enough old data around to warrant this special case.
* `name`
Add tag to the list of names.
* `ref`
Add tag to the list of names as a reference. At the moment this only means
that the object is not considered to be named for `with_name`.
* `address`
Add tag to the list of address tags. If the tag starts with `addr:` or
`is_in:`, then this prefix is cut off before adding it to the list.
* `postcode`
Add the value as a postcode to the address tags. If multiple tags are
candidate for postcodes, one wins out and the others are dropped.
* `country`
Add the value as a country code to the address tags. The value must be a
two letter country code, otherwise it is ignored. If there are multiple
tags that match, then one wins out and the others are dropped.
* `house`
If no principle tags can be found for the object, still add the object with
`class`=`place` and `type`=`house`. Use this for address nodes that have no
other function.
* `interpolation`
Add this object as an address interpolation (appears as `class`=`place` and
`type`=`houses` in the database).
* `extra`
Add tag to the list of extra tags.
* `skip`
Skip the tag completely. Useful when a custom default fallback is defined
or to define exceptions to rules.
A rule can define as many of these properties for one match as it likes. For
example, if the property is `"main,extra"` then the tag will open a new row
but also have the tag appear in the list of extra tags.
### Changing the Style of Existing Databases

View File

@@ -1,49 +0,0 @@
## Importance
Search requests can yield multiple results which match equally well with
the original query. In such case Nominatim needs to order the results
according to a different criterion: importance. This is a measure for how
likely it is that a user will search for a given place. This section explains
the sources Nominatim uses for computing importance of a place and how to
customize them.
### How importance is computed
The main value for importance is derived from page ranking values for Wikipedia
pages for a place. For places that do not have their own
Wikipedia page, a formula is used that derives a static importance from the
places [search rank](../customize/Ranking.md#search-rank).
In a second step, a secondary importance value is added which is meant to
represent how well-known the general area is where the place is located. It
functions as a tie-breaker between places with very similar primary
importance values.
nominatim.org has preprocessed importance tables for the
[primary Wikipedia rankings](https://nominatim.org/data/wikimedia-importance.sql.gz)
and for a secondary importance based on the number of tile views on openstreetmap.org.
### Customizing secondary importance
The secondary importance is implemented as a simple
[Postgis raster](https://postgis.net/docs/raster.html) table, where Nominatim
looks up the value for the coordinates of the centroid of a place. You can
provide your own secondary importance raster in form of an SQL file named
`secondary_importance.sql.gz` in your project directory.
The SQL file needs to drop and (re)create a table `secondary_importance` which
must as a minimum contain a column `rast` of type `raster`. The raster must
be in EPSG:4326 and contain 16bit unsigned ints
(`raster_constraint_pixel_types(rast) = '{16BUI}'). Any other columns in the
table will be ignored. You must furthermore create an index as follows:
```
CREATE INDEX ON secondary_importance USING gist(ST_ConvexHull(gist))
```
The following raster2pgsql command will create a table that conforms to
the requirements:
```
raster2pgsql -I -C -Y -d -t 128x128 input.tiff public.secondary_importance
```

View File

@@ -91,7 +91,7 @@ The option is only used by the Legacy tokenizer and ignored otherwise.
| -------------- | --------------------------------------------------- |
| **Description:** | Tokenizer used for normalizing and parsing queries and names |
| **Format:** | string |
| **Default:** | icu |
| **Default:** | legacy |
| **After Changes:** | cannot be changed after import |
Sets the tokenizer type to use for the import. For more information on
@@ -189,7 +189,7 @@ will be used.
| **Description:** | Enable searching for Tiger house number data |
| **Format:** | boolean |
| **Default:** | no |
| **After Changes:** | run `nominatim refresh --functions` |
| **After Changes:** | run `nominatim --refresh --functions` |
When this setting is enabled, search and reverse queries also take data
from [Tiger house number data](Tiger.md) into account.
@@ -202,7 +202,7 @@ from [Tiger house number data](Tiger.md) into account.
| **Description:** | Enable searching in external house number tables |
| **Format:** | boolean |
| **Default:** | no |
| **After Changes:** | run `nominatim refresh --functions` |
| **After Changes:** | run `nominatim --refresh --functions` |
| **Comment:** | Do not use. |
When this setting is enabled, search queries also take data from external
@@ -552,8 +552,6 @@ used.
| **Format:** | boolean |
| **Default:** | no |
| **After Changes:** | run `nominatim refresh --website` |
| **Comment:** | PHP frontend only |
This feature is currently undocumented and potentially broken.
@@ -566,7 +564,6 @@ This feature is currently undocumented and potentially broken.
| **Format:** | integer |
| **Default:** | 500 |
| **After Changes:** | run `nominatim refresh --website` |
| **Comment:** | PHP frontend only |
This setting defines the threshold over which a name is no longer considered
as rare. When searching for places with rare names, only the name is used
@@ -607,88 +604,6 @@ with a single query.
Setting this parameter to 0 disables polygon output completely.
#### NOMINATIM_SEARCH_WITHIN_COUNTRIES
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Disable search for elements that are not in the country grid |
| **Format:** | boolean |
| **Default:** | no |
| **After Changes:** | run `nominatim refresh --website` |
| **Comment:** | PHP frontend only |
Enable to search elements just within countries.
When enabled, if, despite not finding a point within the static grid of countries, it
finds a geometry of a region, do not return the geometry.
Return "Unable to geocode" instead.
#### NOMINATIM_SERVE_LEGACY_URLS
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Enable serving via URLs with a .php suffix |
| **Format:** | boolean |
| **Default:** | yes |
| **Comment:** | Python frontend only |
When enabled, then endpoints are reachable as `/<name>` as well as `/<name>.php`.
This can be useful when you want to be backwards-compatible with previous
versions of Nominatim.
#### NOMINATIM_API_POOL_SIZE
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Number of parallel database connections per worker |
| **Format:** | number |
| **Default:** | 10 |
| **Comment:** | Python frontend only |
Sets the maximum number of database connections available for a single instance
of Nominatim. When configuring the maximum number of connections that your
PostgreSQL database can handle, you need at least
`NOMINATIM_API_POOL_SIZE` * `<number of configured workers>` connections.
For configuring the number of workers, refer to the section about
[Deploying the Python frontend](../admin/Deployment-Python.md).
#### NOMINATIM_QUERY_TIMEOUT
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Timeout for SQL queries to the database |
| **Format:** | number (seconds) |
| **Default:** | 10 |
| **Comment:** | Python frontend only |
When this timeout is set, then all SQL queries that run longer than the
specified numbers of seconds will be cancelled and the user receives a
timeout exceptions. Users of the API see a 503 HTTP error.
The timeout does ont apply when using the
[low-level DB access](../library/Low-Level-DB-Access.md)
of the library. A timeout can be manually set, if required.
#### NOMINATIM_REQUEST_TIMEOUT
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Timeout for search queries |
| **Format:** | number (seconds) |
| **Default:** | 60 |
| **Comment:** | Python frontend only |
When this timeout is set, a search query will finish sending queries
to the database after the timeout has passed and immediately return the
results gathered so far.
Note that under high load you may observe that users receive different results
than usual without seeing an error. This may cause some confusion.
### Logging Settings
#### NOMINATIM_LOG_DB
@@ -728,24 +643,7 @@ The entries in the log file have the following format:
<request time> <execution time in s> <number of results> <type> "<query string>"
Request time is the time when the request was started. The execution time is
given in seconds and corresponds to the time the query took executing in PHP.
given in ms and corresponds to the time the query took executing in PHP.
type contains the name of the endpoint used.
Can be used as the same time as NOMINATIM_LOG_DB.
#### NOMINATIM_DEBUG_SQL
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Enable printing of raw SQL by SQLAlchemy |
| **Format:** | boolean |
| **Default:** | no |
| **Comment:** | **For developers only.** |
This settings enables
[SQL debugging](https://docs.sqlalchemy.org/en/20/core/engines.html#dbengine-logging)
by SQLAlchemy. This can be helpful when debugging some bugs with internal
query handling. It should only be used together with the CLI query functions.
Enabling it for server mode may have unintended consequences. Use the `debug`
parameter instead, which prints information on how the search is executed
including SQL statements.

View File

@@ -5,22 +5,22 @@ 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 data:
1. Get preprocessed TIGER 2021 data:
cd $PROJECT_DIR
wget https://nominatim.org/data/tiger-nominatim-preprocessed-latest.csv.tar.gz
wget https://nominatim.org/data/tiger2021-nominatim-preprocessed.csv.tar.gz
2. Import the data into your Nominatim database:
nominatim add-data --tiger-data tiger-nominatim-preprocessed-latest.csv.tar.gz
nominatim add-data --tiger-data tiger2021-nominatim-preprocessed.csv.tar.gz
3. Enable use of the Tiger data in your existing `.env` file by adding:
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 --website
nominatim refresh --functions
See the [TIGER-data project](https://github.com/osm-search/TIGER-data) for more

View File

@@ -19,22 +19,7 @@ they can be configured.
The legacy tokenizer implements the analysis algorithms of older Nominatim
versions. It uses a special Postgresql module to normalize names and queries.
This tokenizer is automatically installed and used when upgrading an older
database. It should not be used for new installations anymore.
### Compiling the PostgreSQL module
The tokeinzer needs a special C module for PostgreSQL which is not compiled
by default. If you need the legacy tokenizer, compile Nominatim as follows:
```
mkdir build
cd build
cmake -DBUILD_MODULE=on
make
```
### Enabling the tokenizer
This tokenizer is currently the default.
To enable the tokenizer add the following line to your project configuration:
@@ -62,7 +47,6 @@ normalization functions are hard-coded.
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.
This tokenizer is currently the default.
To enable the tokenizer add the following line to your project configuration:
@@ -102,7 +86,7 @@ Here is an example configuration file:
``` yaml
normalization:
- ":: lower ()"
- "ß > 'ss'" # German szet is unambiguously equal to double ss
- "ß > 'ss'" # German szet is unimbigiously equal to double ss
transliteration:
- !include /etc/nominatim/icu-rules/extended-unicode-to-asccii.yaml
- ":: Ascii ()"
@@ -115,9 +99,6 @@ token-analysis:
- words:
- road -> rd
- bridge -> bdge,br,brdg,bri,brg
mutations:
- pattern: 'ä'
replacements: ['ä', 'ae']
```
The configuration file contains four sections:
@@ -128,7 +109,7 @@ The configuration file contains four sections:
The normalization and transliteration sections each define a set of
ICU rules that are applied to the names.
The **normalization** rules are applied after sanitation. They should remove
The **normalisation** rules are applied after sanitation. They should remove
any information that is not relevant for search at all. Usual rules to be
applied here are: lower-casing, removing of special characters, cleanup of
spaces.
@@ -176,66 +157,28 @@ The following is a list of sanitizers that are shipped with Nominatim.
##### split-name-list
::: nominatim.tokenizer.sanitizers.split_name_list
options:
selection:
members: False
rendering:
heading_level: 6
docstring_section_style: spacy
##### strip-brace-terms
::: nominatim.tokenizer.sanitizers.strip_brace_terms
options:
selection:
members: False
rendering:
heading_level: 6
docstring_section_style: spacy
##### tag-analyzer-by-language
::: nominatim.tokenizer.sanitizers.tag_analyzer_by_language
options:
selection:
members: False
rendering:
heading_level: 6
docstring_section_style: spacy
##### clean-housenumbers
::: nominatim.tokenizer.sanitizers.clean_housenumbers
options:
members: False
heading_level: 6
docstring_section_style: spacy
##### clean-postcodes
::: nominatim.tokenizer.sanitizers.clean_postcodes
options:
members: False
heading_level: 6
docstring_section_style: spacy
##### clean-tiger-tags
::: nominatim.tokenizer.sanitizers.clean_tiger_tags
options:
members: False
heading_level: 6
docstring_section_style: spacy
#### delete-tags
::: nominatim.tokenizer.sanitizers.delete_tags
options:
members: False
heading_level: 6
docstring_section_style: spacy
#### tag-japanese
::: nominatim.tokenizer.sanitizers.tag_japanese
options:
members: False
heading_level: 6
docstring_section_style: spacy
#### Token Analysis
@@ -253,25 +196,21 @@ by a sanitizer (see for example the
The token-analysis section contains the list of configured analyzers. Each
analyzer must have an `id` parameter that uniquely identifies the analyzer.
The only exception is the default analyzer that is used when no special
analyzer was selected. There are analysers with special ids:
* '@housenumber'. If an analyzer with that name is present, it is used
for normalization of house numbers.
* '@potcode'. If an analyzer with that name is present, it is used
for normalization of postcodes.
analyzer was selected.
Different analyzer implementations may exist. To select the implementation,
the `analyzer` parameter must be set. The different implementations are
described in the following.
the `analyzer` parameter must be set. Currently there is only one implementation
`generic` which is described in the following.
##### Generic token analyzer
The generic analyzer `generic` is able to create variants from a list of given
abbreviation and decomposition replacements and introduce spelling variations.
The generic analyzer is able to create variants from a list of given
abbreviation and decomposition replacements. It takes one optional parameter
`variants` which lists the replacements to apply. If the section is
omitted, then the generic analyzer becomes a simple analyzer that only
applies the transliteration.
###### Variants
The optional 'variants' section defines lists of replacements which create alternative
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.
@@ -357,48 +296,6 @@ decomposition has an effect here on the source as well. So a rule
means that for a word like `hauptstrasse` four variants are created:
`hauptstrasse`, `haupt strasse`, `hauptstr` and `haupt str`.
###### Mutations
The 'mutation' section in the configuration describes an additional set of
replacements to be applied after the variants have been computed.
Each mutation is described by two parameters: `pattern` and `replacements`.
The pattern must contain a single regular expression to search for in the
variant name. The regular expressions need to follow the syntax for
[Python regular expressions](file:///usr/share/doc/python3-doc/html/library/re.html#regular-expression-syntax).
Capturing groups are not permitted.
`replacements` must contain a list of strings that the pattern
should be replaced with. Each occurrence of the pattern is replaced with
all given replacements. Be mindful of combinatorial explosion of variants.
###### Modes
The generic analyser supports a special mode `variant-only`. When configured
then it consumes the input token and emits only variants (if any exist). Enable
the mode by adding:
```
mode: variant-only
```
to the analyser configuration.
##### Housenumber token analyzer
The analyzer `housenumbers` is purpose-made to analyze house numbers. It
creates variants with optional spaces between numbers and letters. Thus,
house numbers of the form '3 a', '3A', '3-A' etc. are all considered equivalent.
The analyzer cannot be customized.
##### Postcode token analyzer
The analyzer `postcodes` is pupose-made to analyze postcodes. It supports
a 'lookup' varaint of the token, which produces variants with optional
spaces. Use together with the clean-postcodes sanitizer.
The analyzer cannot be customized.
### Reconfiguration
Changing the configuration after the import is currently not possible, although

View File

@@ -119,7 +119,7 @@ to compute the address relations between places. These tables are partitioned.
Each country is assigned a partition number in the country_name table (see
below) and the data is then split between a set of tables, one for each
partition. Note that Nominatim still manually manages partitioned tables.
Native support for partitions in PostgreSQL only became usable with version 13.
Native support for partitions in PostgreSQL only became useable with version 13.
It will be a little while before Nominatim drops support for older versions.
![address tables](address-tables.svg)
@@ -155,9 +155,9 @@ Nominatim also creates a number of static tables at import:
default languages and saves the assignment of countries to partitions.
* `country_osm_grid` provides a fallback for country geometries
## Auxiliary data tables
## Auxilary data tables
Finally there are some table for auxiliary data:
Finally there are some table for auxillary data:
* `location_property_tiger` - saves housenumber from the Tiger import. Its
layout is similar to that of `location_propoerty_osmline`.

View File

@@ -1,6 +1,6 @@
# Setting up Nominatim for Development
This chapter gives an overview how to set up Nominatim for development
This chapter gives an overview how to set up Nominatim for developement
and how to run tests.
!!! Important
@@ -30,25 +30,15 @@ unit tests (using PHPUnit for PHP code and pytest for Python code).
It has the following additional requirements:
* [behave test framework](https://behave.readthedocs.io) >= 1.2.6
* [phpunit](https://phpunit.de) (9.5 is known to work)
* [phpunit](https://phpunit.de) >= 7.3
* [PHP CodeSniffer](https://github.com/squizlabs/PHP_CodeSniffer)
* [Pylint](https://pylint.org/) (CI always runs the latest version from pip)
* [mypy](http://mypy-lang.org/) (plus typing information for external libs)
* [Python Typing Extensions](https://github.com/python/typing_extensions) (for Python < 3.9)
* [Pylint](https://pylint.org/) (2.6.0 is used for the CI)
* [pytest](https://pytest.org)
* [pytest-asyncio](https://pytest-asyncio.readthedocs.io)
For testing the Python search frontend, you need to install extra dependencies
depending on your choice of webserver framework:
* [httpx](https://www.python-httpx.org/) (starlette only)
* [asgi-lifespan](https://github.com/florimondmanca/asgi-lifespan) (starlette only)
The documentation is built with mkdocs:
* [mkdocs](https://www.mkdocs.org/) >= 1.1.2
* [mkdocstrings](https://mkdocstrings.github.io/) >= 0.18
* [mkdocstrings-python](https://mkdocstrings.github.io/python/)
* [mkdocstrings](https://mkdocstrings.github.io/)
### Installing prerequisites on Ubuntu/Debian
@@ -60,12 +50,9 @@ To install all necessary packages run:
```sh
sudo apt install php-cgi phpunit php-codesniffer \
python3-pip python3-setuptools python3-dev
python3-pip python3-setuptools python3-dev pylint
pip3 install --user behave mkdocs mkdocstrings pytest pytest-asyncio pylint \
mypy types-PyYAML types-jinja2 types-psycopg2 types-psutil \
types-ujson types-requests types-Pygments typing-extensions\
httpx asgi-lifespan
pip3 install --user behave mkdocs mkdocstrings pytest
```
The `mkdocs` executable will be located in `.local/bin`. You may have to add

View File

@@ -1,220 +0,0 @@
# Writing custom sanitizer and token analysis modules for the ICU tokenizer
The [ICU tokenizer](../customize/Tokenizers.md#icu-tokenizer) provides a
highly customizable method to pre-process and normalize the name information
of the input data before it is added to the search index. It comes with a
selection of sanitizers and token analyzers which you can use to adapt your
installation to your needs. If the provided modules are not enough, you can
also provide your own implementations. This section describes the API
of sanitizers and token analysis.
!!! warning
This API is currently in early alpha status. While this API is meant to
be a public API on which other sanitizers and token analyzers may be
implemented, it is not guaranteed to be stable at the moment.
## Using non-standard sanitizers and token analyzers
Sanitizer names (in the `step` property) and token analysis names (in the
`analyzer`) may refer to externally supplied modules. There are two ways
to include external modules: through a library or from the project directory.
To include a module from a library, use the absolute import path as name and
make sure the library can be found in your PYTHONPATH.
To use a custom module without creating a library, you can put the module
somewhere in your project directory and then use the relative path to the
file. Include the whole name of the file including the `.py` ending.
## Custom sanitizer modules
A sanitizer module must export a single factory function `create` with the
following signature:
``` python
def create(config: SanitizerConfig) -> Callable[[ProcessInfo], None]
```
The function receives the custom configuration for the sanitizer and must
return a callable (function or class) that transforms the name and address
terms of a place. When a place is processed, then a `ProcessInfo` object
is created from the information that was queried from the database. This
object is sequentially handed to each configured sanitizer, so that each
sanitizer receives the result of processing from the previous sanitizer.
After the last sanitizer is finished, the resulting name and address lists
are forwarded to the token analysis module.
Sanitizer functions are instantiated once and then called for each place
that is imported or updated. They don't need to be thread-safe.
If multi-threading is used, each thread creates their own instance of
the function.
### Sanitizer configuration
::: nominatim.tokenizer.sanitizers.config.SanitizerConfig
options:
heading_level: 6
### The main filter function of the sanitizer
The filter function receives a single object of type `ProcessInfo`
which has with three members:
* `place: PlaceInfo`: read-only information about the place being processed.
See PlaceInfo below.
* `names: List[PlaceName]`: The current list of names for the place.
* `address: List[PlaceName]`: The current list of address names for the place.
While the `place` member is provided for information only, the `names` and
`address` lists are meant to be manipulated by the sanitizer. It may add and
remove entries, change information within a single entry (for example by
adding extra attributes) or completely replace the list with a different one.
#### PlaceInfo - information about the place
::: nominatim.data.place_info.PlaceInfo
options:
heading_level: 6
#### PlaceName - extended naming information
::: nominatim.data.place_name.PlaceName
options:
heading_level: 6
### Example: Filter for US street prefixes
The following sanitizer removes the directional prefixes from street names
in the US:
``` python
import re
def _filter_function(obj):
if obj.place.country_code == 'us' \
and obj.place.rank_address >= 26 and obj.place.rank_address <= 27:
for name in obj.names:
name.name = re.sub(r'^(north|south|west|east) ',
'',
name.name,
flags=re.IGNORECASE)
def create(config):
return _filter_function
```
This is the most simple form of a sanitizer module. If defines a single
filter function and implements the required `create()` function by returning
the filter.
The filter function first checks if the object is interesting for the
sanitizer. Namely it checks if the place is in the US (through `country_code`)
and it the place is a street (a `rank_address` of 26 or 27). If the
conditions are met, then it goes through all available names and
removes any leading directional prefix using a simple regular expression.
Save the source code in a file in your project directory, for example as
`us_streets.py`. Then you can use the sanitizer in your `icu_tokenizer.yaml`:
``` yaml
...
sanitizers:
- step: us_streets.py
...
```
!!! warning
This example is just a simplified show case on how to create a sanitizer.
It is not really read for real-world use: while the sanitizer would
correcly transform `West 5th Street` into `5th Street`. it would also
shorten a simple `North Street` to `Street`.
For more sanitizer examples, have a look at the sanitizers provided by Nominatim.
They can be found in the directory
[`nominatim/tokenizer/sanitizers`](https://github.com/osm-search/Nominatim/tree/master/nominatim/tokenizer/sanitizers).
## Custom token analysis module
::: nominatim.tokenizer.token_analysis.base.AnalysisModule
options:
heading_level: 6
::: nominatim.tokenizer.token_analysis.base.Analyzer
options:
heading_level: 6
### Example: Creating acronym variants for long names
The following example of a token analysis module creates acronyms from
very long names and adds them as a variant:
``` python
class AcronymMaker:
""" This class is the actual analyzer.
"""
def __init__(self, norm, trans):
self.norm = norm
self.trans = trans
def get_canonical_id(self, name):
# In simple cases, the normalized name can be used as a canonical id.
return self.norm.transliterate(name.name).strip()
def compute_variants(self, name):
# The transliterated form of the name always makes up a variant.
variants = [self.trans.transliterate(name)]
# Only create acronyms from very long words.
if len(name) > 20:
# Take the first letter from each word to form the acronym.
acronym = ''.join(w[0] for w in name.split())
# If that leds to an acronym with at least three letters,
# add the resulting acronym as a variant.
if len(acronym) > 2:
# Never forget to transliterate the variants before returning them.
variants.append(self.trans.transliterate(acronym))
return variants
# The following two functions are the module interface.
def configure(rules, normalizer, transliterator):
# There is no configuration to parse and no data to set up.
# Just return an empty configuration.
return None
def create(normalizer, transliterator, config):
# Return a new instance of our token analysis class above.
return AcronymMaker(normalizer, transliterator)
```
Given the name `Trans-Siberian Railway`, the code above would return the full
name `Trans-Siberian Railway` and the acronym `TSR` as variant, so that
searching would work for both.
## Sanitizers vs. Token analysis - what to use for variants?
It is not always clear when to implement variations in the sanitizer and
when to write a token analysis module. Just take the acronym example
above: it would also have been possible to write a sanitizer which adds the
acronym as an additional name to the name list. The result would have been
similar. So which should be used when?
The most important thing to keep in mind is that variants created by the
token analysis are only saved in the word lookup table. They do not need
extra space in the search index. If there are many spelling variations, this
can mean quite a significant amount of space is saved.
When creating additional names with a sanitizer, these names are completely
independent. In particular, they can be fed into different token analysis
modules. This gives a much greater flexibility but at the price that the
additional names increase the size of the search index.

View File

@@ -78,7 +78,7 @@ The inheritance is computed in the data preparation step.
The prepared place information is handed to the tokenizer next. This is a
Python module responsible for processing the names from both name and address
terms and building up the word index from them. The process is explained in
more detail in the [Tokenizer chapter](Tokenizers.md).
more detail in the [Tokenizer chapter](Tokenizer.md).
### Address processing

View File

@@ -22,8 +22,8 @@ This test directory is sturctured as follows:
|
+- php PHP unit tests
+- python Python unit tests
+- scenes Geometry test data
+- testdb Base data for generating API test database
+- testdata Additional test data used by unit tests
```
## PHP Unit Tests (`test/php`)
@@ -84,8 +84,6 @@ The tests can be configured with a set of environment variables (`behave -D key=
* `TEST_DB` - name of test database (db tests)
* `API_TEST_DB` - name of the database containing the API test data (api tests)
* `API_TEST_FILE` - OSM file to be imported into the API test database (api tests)
* `API_ENGINE` - webframe to use for running search queries, same values as
`nominatim serve --engine` parameter
* `DB_HOST` - (optional) hostname of database host
* `DB_PORT` - (optional) port of database on host
* `DB_USER` - (optional) username of database login
@@ -122,7 +120,7 @@ and compromises the following data:
API tests should only be testing the functionality of the website PHP code.
Most tests should be formulated as BDD DB creation tests (see below) instead.
#### Code Coverage (PHP engine only)
#### Code Coverage
The API tests also support code coverage tests. You need to install
[PHP_CodeCoverage](https://github.com/sebastianbergmann/php-code-coverage).
@@ -155,3 +153,7 @@ needs superuser rights for postgres.
These tests check that data is imported correctly into the place table. They
use the same template database as the DB Creation tests, so the same remarks apply.
Note that most testing of the gazetteer output of osm2pgsql is done in the tests
of osm2pgsql itself. The BDD tests are just there to ensure compatibility of
the osm2pgsql and Nominatim code.

View File

@@ -93,7 +93,7 @@ for a custom tokenizer implementation.
Nominatim expects two files for a tokenizer:
* `nominatim/tokenizer/<NAME>_tokenizer.py` containing the Python part of the
* `nominiatim/tokenizer/<NAME>_tokenizer.py` containing the Python part of the
implementation
* `lib-php/tokenizer/<NAME>_tokenizer.php` with the PHP part of the
implementation
@@ -105,7 +105,7 @@ functions. By convention, these should be placed in `lib-sql/tokenizer`.
If the tokenizer has a default configuration file, this should be saved in
the `settings/<NAME>_tokenizer.<SUFFIX>`.
### Configuration and Persistence
### Configuration and Persistance
Tokenizers may define custom settings for their configuration. All settings
must be prefixed with `NOMINATIM_TOKENIZER_`. Settings may be transient or
@@ -134,14 +134,14 @@ All tokenizers must inherit from `nominatim.tokenizer.base.AbstractTokenizer`
and implement the abstract functions defined there.
::: nominatim.tokenizer.base.AbstractTokenizer
options:
heading_level: 6
rendering:
heading_level: 4
### Python Analyzer Class
::: nominatim.tokenizer.base.AbstractAnalyzer
options:
heading_level: 6
rendering:
heading_level: 4
### PL/pgSQL Functions
@@ -189,28 +189,6 @@ a house number token text. If a place has multiple house numbers they must
be listed with a semicolon as delimiter. Must be NULL when the place has no
house numbers.
```sql
FUNCTION token_is_street_address(info JSONB) RETURNS BOOLEAN
```
Return true if this is an object that should be parented against a street.
Only relevant for objects with address rank 30.
```sql
FUNCTION token_has_addr_street(info JSONB) RETURNS BOOLEAN
```
Return true if there are street names to match against for finding the
parent of the object.
```sql
FUNCTION token_has_addr_place(info JSONB) RETURNS BOOLEAN
```
Return true if there are place names to match against for finding the
parent of the object.
```sql
FUNCTION token_matches_street(info JSONB, street_tokens INTEGER[]) RETURNS BOOLEAN
```
@@ -267,11 +245,11 @@ Currently, tokenizers are encouraged to make sure that matching works against
both the search token list and the match token list.
```sql
FUNCTION token_get_postcode(info JSONB) RETURNS TEXT
FUNCTION token_normalized_postcode(postcode TEXT) RETURNS TEXT
```
Return the postcode for the object, if any exists. The postcode must be in
the form that should also be presented to the end-user.
Return the normalized version of the given postcode. This function must return
the same value as the Python function `AbstractAnalyzer->normalize_postcode()`.
```sql
FUNCTION token_strip_info(info JSONB) RETURNS JSONB

View File

@@ -13,7 +13,7 @@ More details in [osm-search/country-grid-data](https://github.com/osm-search/cou
## US Census TIGER
For the United States you can choose to import additional street-level data.
For the United States you can choose to import additonal street-level data.
The data isn't mixed into OSM data but queried as fallback when no OSM
result can be found.

View File

@@ -2,10 +2,6 @@
display: none!important
}
.wy-nav-content {
max-width: 900px!important
}
table {
margin-bottom: 12pt
}
@@ -18,19 +14,10 @@ th {
background-color: #eee;
}
.doc-object h6 {
margin-bottom: 0.8em;
font-size: 130%;
}
/* Indentation for mkdocstrings.
div.doc-contents:not(.first) {
padding-left: 25px;
border-left: 4px solid rgba(230, 230, 230);
margin-bottom: 60px;
}*/
.doc-object {
margin-bottom: 1.3em;
}
.doc-children .doc-contents {
margin-left: 3em;
}
.md-footer__inner {
display: none;
}

View File

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

View File

@@ -1,31 +0,0 @@
# Configuration
When using Nominatim through the library, it can be configured in exactly
the same way as when running as a service. This means that you should have
created a [project directory](../admin/Import.md#creating-the-project-directory)
which contains all files belonging to the Nominatim instance. It can also contain
an `.env` file with configuration options. Setting configuration parameters
via environment variables works as well.
Configuration options are resolved in the following order:
* from the OS environment (or the dictionary given in `environ`,
(see NominatimAPI.md#nominatim.api.core.NominatimAPI.__init__)
* from the .env file in the project directory of the installation
* from the default installation in the configuration directory
For more information on configuration via dotenv and a list of possible
configuration parameters, see the [Configuration page](../customize/Settings.md).
## `Configuration` class
::: nominatim.config.Configuration
options:
members:
- get_bool
- get_int
- get_str_list
- get_path
heading_level: 6
show_signature_annotations: True

View File

@@ -1,248 +0,0 @@
# Getting Started
The Nominatim search frontend can directly be used as a Python library in
scripts and applications. When you have imported your own Nominatim database,
then it is no longer necessary to run a full web service for it and access
the database through http requests. There are
also less constraints on the kinds of data that can be accessed. The library
allows to get access to more detailed information about the objects saved
in the database.
!!! danger
The library interface is currently in an experimental stage. There might
be some smaller adjustments to the public interface until the next version.
The library also misses a proper installation routine, so some manipulation
of the PYTHONPATH is required. At the moment, use is only recommended for
developers wit some experience in Python.
## Installation
To use the Nominatim library, you need access to a local Nominatim database.
Follow the [installation](../admin/Installation.md) and
[import](../admin/Import.md) instructions to set up your database.
It is not yet possible to install it in the usual way via pip or inside a
virtualenv. To get access to the library you need to set an appropriate
`PYTHONPATH`. With the default installation, the python library can be found
under `/usr/local/share/nominatim/lib-python`. If you have installed
Nominatim under a different prefix, adapt the `/usr/local/` part accordingly.
You can also point the `PYTHONPATH` to the Nominatim source code.
### A simple search example
To query the Nominatim database you need to first set up a connection. This
is done by creating an Nominatim API object. This object exposes all the
search functions of Nominatim that are also known from its web API.
This code snippet implements a simple search for the town of 'Brugge':
!!! example
=== "NominatimAPIAsync"
``` python
from pathlib import Path
import asyncio
import nominatim.api as napi
async def search(query):
api = napi.NominatimAPIAsync(Path('.'))
return await api.search(query)
results = asyncio.run(search('Brugge'))
if not results:
print('Cannot find Brugge')
else:
print(f'Found a place at {results[0].centroid.x},{results[0].centroid.y}')
```
=== "NominatimAPI"
``` python
from pathlib import Path
import nominatim.api as napi
api = napi.NominatimAPI(Path('.'))
results = api.search('Brugge')
if not results:
print('Cannot find Brugge')
else:
print(f'Found a place at {results[0].centroid.x},{results[0].centroid.y}')
```
The Nominatim library is designed around
[asyncio](https://docs.python.org/3/library/asyncio.html). `NominatimAPIAsync`
provides you with an interface of coroutines.
If you have many requests to make, coroutines can speed up your applications
significantly.
For smaller scripts there is also a synchronous wrapper around the API. By
using `NominatimAPI`, you get exactly the same interface using classic functions.
The examples in this chapter will always show-case both
implementations. The documentation itself will usually refer only to
'Nominatim API class' when both flavours are meant. If a functionality is
available only for the synchronous or asynchronous version, this will be
explicitly mentioned.
### Defining which database to use
The [Configuration](../admin/Import.md#configuration-setup-in-env)
section explains how Nominatim is configured using the
[dotenv](https://github.com/theskumar/python-dotenv) library.
The same configuration mechanism is used with the
Nominatim API library. You should therefore be sure you are familiar with
the section.
The constructor of the 'Nominatim API class' takes one mandatory parameter:
the path to the [project directory](../admin/Import.md#creating-the-project-directory).
You should have set up this directory as part of the Nominatim import.
Any configuration found in the `.env` file in this directory will automatically
used.
Yo may also configure Nominatim be setting environment variables.
Normally, Nominatim will check the operating system environment. This can be
overwritten by giving the constructor a dictionary of configuration parameters.
Let us look up 'Brugge' in the special database named 'belgium' instead of the
standard 'nominatim' database:
!!! example
=== "NominatimAPIAsync"
``` python
from pathlib import Path
import asyncio
import nominatim.api as napi
config_params = {
'NOMINATIM_DATABASE_DSN': 'pgsql:dbname=belgium'
}
async def search(query):
api = napi.NominatimAPIAsync(Path('.'), environ=config_params)
return await api.search(query)
results = asyncio.run(search('Brugge'))
```
=== "NominatimAPI"
``` python
from pathlib import Path
import nominatim.api as napi
config_params = {
'NOMINATIM_DATABASE_DSN': 'pgsql:dbname=belgium'
}
api = napi.NominatimAPI(Path('.'), environ=config_params)
results = api.search('Brugge')
```
### Presenting results to humans
All search functions return the raw results from the database. There is no
full human-readable label. To create such a label, you need two things:
* the address details of the place
* adapt the result to the language you wish to use for display
Again searching for 'Brugge', this time with a nicely formatted result:
!!! example
=== "NominatimAPIAsync"
``` python
from pathlib import Path
import asyncio
import nominatim.api as napi
async def search(query):
api = napi.NominatimAPIAsync(Path('.'))
return await api.search(query, address_details=True)
results = asyncio.run(search('Brugge'))
locale = napi.Locales(['fr', 'en'])
for i, result in enumerate(results):
address_parts = result.address_rows.localize(locale)
print(f"{i + 1}. {', '.join(address_parts)}")
```
=== "NominatimAPI"
``` python
from pathlib import Path
import nominatim.api as napi
api = napi.NominatimAPI(Path('.'))
results = api.search('Brugge', address_details=True)
locale = napi.Locales(['fr', 'en'])
for i, result in enumerate(results):
address_parts = result.address_rows.localize(locale)
print(f"{i + 1}. {', '.join(address_parts)}")
```
To request information about the address of a result, add the optional
parameter 'address_details' to your search:
``` python
>>> results = api.search('Brugge', address_details=True)
```
An additional field `address_rows` will set in results that are returned.
It contains a list of all places that make up the address of the place. For
simplicity, this includes name and house number of the place itself. With
the names in this list it is possible to create a human-readable description
of the result. To do that, you first need to decide in which language the
results should be presented. As with the names in the result itself, the
places in `address_rows` contain all possible name translation for each row.
The library has a helper class `Locale` which helps extracting a name of a
place in the preferred language. It takes a single parameter with a list
of language codes in the order of preference. So
``` python
locale = napi.Locale(['fr', 'en'])
```
creates a helper class that returns the name preferably in French. If that is
not possible, it tries English and eventually falls back to the default `name`
or `ref`.
The `Locale` object can be applied to a name dictionary to return the best-matching
name out of it:
``` python
>>> print(locale.display_name(results[0].names))
'Brugges'
```
The `address_row` field has a helper function to apply the function to all
its members and save the result in the `local_name` field. It also returns
all the localized names as a convenient simple list. This list can be used
to create a human-readable output:
``` python
>>> address_parts = results[0].address_rows.localize(locale)
>>> print(', '.join(address_parts))
Bruges, Flandre-Occidentale, Flandre, Belgique
```
This is a fairly simple way to create a human-readable description. The
place information in `address_rows` contains further information about each
place. For example, which OSM `adlin_level` was used, what category the place
belongs to or what rank Nominatim has assigned. Use this to adapt the output
to local address formats.
For more information on address rows, see
[detailed address description](Result-Handling.md#detailed-address-description).

View File

@@ -1,62 +0,0 @@
# Input Parameter Types
This page describes in more detail some of the input parameter types used
in the query functions of the API object.
## Place identification
The [details](NominatimAPI.md#nominatim.api.core.NominatimAPI.details) and
[lookup](NominatimAPI.md#nominatim.api.core.NominatimAPI.lookup) functions
require references to places in the database. Below the possible
types for place identification are listed. All types are dataclasses.
### PlaceID
::: nominatim.api.PlaceID
options:
heading_level: 6
### OsmID
::: nominatim.api.OsmID
options:
heading_level: 6
## Geometry types
::: nominatim.api.GeometryFormat
options:
heading_level: 6
members_order: source
## Geometry input
### Point
::: nominatim.api.Point
options:
heading_level: 6
show_signature_annotations: True
### Bbox
::: nominatim.api.Bbox
options:
heading_level: 6
show_signature_annotations: True
members_order: source
group_by_category: False
## Layers
Layers allow to restrict the search result to thematic groups. This is
orthogonal to restriction by address ranks, which groups places by their
geographic extent.
::: nominatim.api.DataLayer
options:
heading_level: 6
members_order: source

View File

@@ -1,56 +0,0 @@
# Low-level connections
The `NominatimAPIAsync` class allows to directly access the underlying
database connection to explore the raw data. Nominatim uses
[SQLAlchemy](https://docs.sqlalchemy.org/) for building queries. Please
refer to the documentation of the library to understand how to write SQL.
To get access to a search connection, use the `begin()` function of your
API object. This returns a `SearchConnection` object described below
wrapped in a context manager. Its
`t` property has definitions for all Nominatim search tables. For an
overview of available tables, refer to the
[Development Layout](../develop/Database-Layout.md) in in the development
chapter. Note that only tables that are needed for search are accessible
as SQLAlchemy tables.
!!! warning
The database layout is not part of the API definition and may change
without notice. If you play with the low-level access functions, you
need to be prepared for such changes.
Here is a simple example, which prints how many places are available in
the placex table:
```
import asyncio
from pathlib import Path
import sqlalchemy as sa
from nominatim.api import NominatimAPIAsync
async def print_table_size():
api = NominatimAPIAsync(Path('.'))
async with api.begin() as conn:
cnt = await conn.scalar(sa.select(sa.func.count()).select_from(conn.t.placex))
print(f'placex table has {cnt} rows.')
asyncio.run(print_table_size())
```
!!! warning
Low-level connections may only be used to read data from the database.
Do not use it to add or modify data or you might break Nominatim's
normal functions.
## SearchConnection class
::: nominatim.api.SearchConnection
options:
members:
- scalar
- execute
- get_class_table
- get_db_property
- get_property
heading_level: 6

View File

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

View File

@@ -1,58 +0,0 @@
# Result handling
The search functions of the Nominatim API always return a result object
with the raw information about the place that is available in the
database. This section discusses data types used in the results and utility
functions that allow further processing of the results.
## Result fields
### Sources
Nominatim takes the result data from multiple sources. The `source_table` field
in the result describes, from which source the result was retrieved.
::: nominatim.api.SourceTable
options:
heading_level: 6
members_order: source
### Detailed address description
When the `address_details` parameter is set, then functions return not
only information about the result place but also about the place that
make up the address. This information is almost always required when you
want to present the user with a human-readable description of the result.
See also [Localization](#localization) below.
The address details are available in the `address_rows` field as a ordered
list of `AddressLine` objects with the country information last. The list also
contains the result place itself and some artificial entries, for example,
for the house number or the country code. This makes processing and creating
a full address easier.
::: nominatim.api.AddressLine
options:
heading_level: 6
members_order: source
### Detailed search terms
The `details` function can return detailed information about which search terms
may be used to find a place, when the `keywords` parameter is set. Search
terms are split into terms for the name of the place and search terms for
its address.
::: nominatim.api.WordInfo
options:
heading_level: 6
## Localization
Results are always returned with the full list of available names.
### Locale
::: nominatim.api.Locales
options:
heading_level: 6

View File

@@ -1,13 +1,9 @@
site_name: Nominatim Manual
theme:
name: material
features:
- navigation.tabs
copyright: Copyright &copy; Nominatim developer community
site_name: Nominatim 4.0.1
theme: readthedocs
docs_dir: ${CMAKE_CURRENT_BINARY_DIR}
site_url: https://nominatim.org
repo_url: https://github.com/openstreetmap/Nominatim
nav:
pages:
- 'Introduction' : 'index.md'
- 'API Reference':
- 'Overview': 'api/Overview.md'
@@ -22,8 +18,7 @@ nav:
- 'Basic Installation': 'admin/Installation.md'
- 'Import' : 'admin/Import.md'
- 'Update' : 'admin/Update.md'
- 'Deploy (PHP frontend)' : 'admin/Deployment-PHP.md'
- 'Deploy (Python frontend)' : 'admin/Deployment-Python.md'
- 'Deploy' : 'admin/Deployment.md'
- 'Nominatim UI' : 'admin/Setup-Nominatim-UI.md'
- 'Advanced Installations' : 'admin/Advanced-Installations.md'
- 'Maintenance' : 'admin/Maintenance.md'
@@ -33,38 +28,27 @@ nav:
- 'Overview': 'customize/Overview.md'
- 'Import Styles': 'customize/Import-Styles.md'
- 'Configuration Settings': 'customize/Settings.md'
- 'Per-Country Data': 'customize/Country-Settings.md'
- 'Place Ranking' : 'customize/Ranking.md'
- 'Importance' : 'customize/Importance.md'
- 'Tokenizers' : 'customize/Tokenizers.md'
- 'Special Phrases': 'customize/Special-Phrases.md'
- 'External data: US housenumbers from TIGER': 'customize/Tiger.md'
- 'External data: Postcodes': 'customize/Postcodes.md'
- 'Library Guide':
- 'Getting Started': 'library/Getting-Started.md'
- 'Nominatim API class': 'library/NominatimAPI.md'
- 'Configuration': 'library/Configuration.md'
- 'Input Parameter Types': 'library/Input-Parameter-Types.md'
- 'Result Handling': 'library/Result-Handling.md'
- 'Low-level DB Access': 'library/Low-Level-DB-Access.md'
- 'Developers Guide':
- 'Architecture Overview' : 'develop/overview.md'
- 'Database Layout' : 'develop/Database-Layout.md'
- 'Indexing' : 'develop/Indexing.md'
- 'Tokenizers' : 'develop/Tokenizers.md'
- 'Custom modules for ICU tokenizer': 'develop/ICU-Tokenizer-Modules.md'
- 'Setup for Development' : 'develop/Development-Environment.md'
- 'Testing' : 'develop/Testing.md'
- 'External Data Sources': 'develop/data-sources.md'
- 'Appendix':
- 'Installation on CentOS 7' : 'appendix/Install-on-Centos-7.md'
- 'Installation on CentOS 8' : 'appendix/Install-on-Centos-8.md'
- 'Installation on Ubuntu 18' : 'appendix/Install-on-Ubuntu-18.md'
- 'Installation on Ubuntu 20' : 'appendix/Install-on-Ubuntu-20.md'
- 'Installation on Ubuntu 22' : 'appendix/Install-on-Ubuntu-22.md'
markdown_extensions:
- codehilite
- admonition
- pymdownx.superfences
- pymdownx.tabbed:
alternate_style: true
- def_list
- toc:
permalink:
@@ -74,7 +58,6 @@ plugins:
- mkdocstrings:
handlers:
python:
paths: ["${PROJECT_SOURCE_DIR}"]
options:
show_source: False
show_bases: False
rendering:
show_source: false
show_signature_annotations: false

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
@@ -92,10 +84,6 @@ class AddressDetails
|| $aLine['class'] == 'place')
) {
$aAddress[$sTypeLabel] = $sName;
if (!empty($aLine['name'])) {
$this->addSubdivisionCode($aAddress, $aLine['admin_level'], $aLine['name']);
}
}
}
@@ -178,14 +166,4 @@ class AddressDetails
{
return $this->aAddressLines;
}
private function addSubdivisionCode(&$aAddress, $iAdminLevel, $nameDetails)
{
if (is_string($nameDetails)) {
$nameDetails = json_decode('{' . str_replace('"=>"', '":"', $nameDetails) . '}', true);
}
if (!empty($nameDetails['ISO3166-2'])) {
$aAddress["ISO3166-2-lvl$iAdminLevel"] = $nameDetails['ISO3166-2'];
}
}
}

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim\ClassTypes;

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
@@ -38,25 +30,20 @@ class DB
// https://secure.php.net/manual/en/ref.pdo-pgsql.connection.php
try {
$this->connection = new \PDO($this->sDSN, null, null, $aConnOptions);
$conn = new \PDO($this->sDSN, null, null, $aConnOptions);
} catch (\PDOException $e) {
$sMsg = 'Failed to establish database connection:' . $e->getMessage();
throw new \Nominatim\DatabaseError($sMsg, 500, null, $e->getMessage());
}
$this->connection->exec("SET DateStyle TO 'sql,european'");
$this->connection->exec("SET client_encoding TO 'utf-8'");
// Disable JIT and parallel workers. They interfere badly with search SQL.
$this->connection->exec('SET max_parallel_workers_per_gather TO 0');
if ($this->getPostgresVersion() >= 11) {
$this->connection->exec('SET jit_above_cost TO -1');
}
$conn->exec("SET DateStyle TO 'sql,european'");
$conn->exec("SET client_encoding TO 'utf-8'");
$iMaxExecution = ini_get('max_execution_time');
if ($iMaxExecution > 0) {
$this->connection->setAttribute(\PDO::ATTR_TIMEOUT, $iMaxExecution); // seconds
$conn->setAttribute(\PDO::ATTR_TIMEOUT, $iMaxExecution); // seconds
}
$this->connection = $conn;
return true;
}

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
@@ -135,7 +127,7 @@ class Debug
public static function printSQL($sSQL)
{
echo '<p><tt><b>'.date('c').'</b> <font color="#aaa">'.htmlspecialchars($sSQL, ENT_QUOTES | ENT_SUBSTITUTE | ENT_HTML401).'</font></tt></p>'."\n";
echo '<p><tt><font color="#aaa">'.$sSQL.'</font></tt></p>'."\n";
}
private static function outputVar($mVar, $sPreNL)
@@ -178,12 +170,11 @@ class Debug
}
if (is_string($mVar)) {
$sOut = "'$mVar'";
} else {
$sOut = (string)$mVar;
echo "'$mVar'";
return strlen($mVar) + 2;
}
echo htmlspecialchars($sOut, ENT_QUOTES | ENT_SUBSTITUTE | ENT_HTML401);
return strlen($sOut);
echo (string)$mVar;
return strlen((string)$mVar);
}
}

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
@@ -103,7 +95,7 @@ class Geocode
}
$this->iFinalLimit = $iLimit;
$this->iLimit = $iLimit + max($iLimit, 10);
$this->iLimit = $iLimit + min($iLimit, 10);
}
public function setFeatureType($sFeatureType)
@@ -190,7 +182,7 @@ class Geocode
$this->bFallback = $oParams->getBool('fallback', $this->bFallback);
// List of excluded Place IDs - used for more accurate pageing
// List of excluded Place IDs - used for more acurate pageing
$sExcluded = $oParams->getStringList('exclude_place_ids');
if ($sExcluded) {
foreach ($sExcluded as $iExcludedPlaceID) {
@@ -617,15 +609,16 @@ class Geocode
}
$aReverseGroupedSearches = $this->getGroupedSearches($aSearches, $aPhrases, $oValidTokens);
foreach ($aReverseGroupedSearches as $aSearches) {
foreach ($aGroupedSearches as $aSearches) {
foreach ($aSearches as $aSearch) {
if (!isset($aGroupedSearches[$aSearch->getRank()])) {
$aGroupedSearches[$aSearch->getRank()] = array();
if (!isset($aReverseGroupedSearches[$aSearch->getRank()])) {
$aReverseGroupedSearches[$aSearch->getRank()] = array();
}
$aGroupedSearches[$aSearch->getRank()][] = $aSearch;
$aReverseGroupedSearches[$aSearch->getRank()][] = $aSearch;
}
}
$aGroupedSearches = $aReverseGroupedSearches;
ksort($aGroupedSearches);
}
} else {
@@ -843,9 +836,7 @@ class Geocode
$aResult['importance'] = 0.001;
$aResult['foundorder'] = $aResult['addressimportance'];
} else {
if ($aResult['importance'] == 0) {
$aResult['importance'] = 0.0001;
}
$aResult['importance'] = max(0.001, $aResult['importance']);
$aResult['importance'] *= $this->viewboxImportanceFactor(
$aResult['lon'],
$aResult['lat']
@@ -874,7 +865,7 @@ class Geocode
$iCountWords = 0;
$sAddress = $aResult['langaddress'];
foreach ($aRecheckWords as $i => $sWord) {
if (grapheme_stripos($sAddress, $sWord)!==false) {
if (stripos($sAddress, $sWord)!==false) {
$iCountWords++;
if (preg_match('/(^|,)\s*'.preg_quote($sWord, '/').'\s*(,|$)/', $sAddress)) {
$iCountWords += 0.1;

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
@@ -22,10 +14,7 @@ class ParameterParser
public function getBool($sName, $bDefault = false)
{
if (!isset($this->aParams[$sName])
|| !is_string($this->aParams[$sName])
|| strlen($this->aParams[$sName]) == 0
) {
if (!isset($this->aParams[$sName]) || strlen($this->aParams[$sName]) == 0) {
return $bDefault;
}
@@ -34,7 +23,7 @@ class ParameterParser
public function getInt($sName, $bDefault = false)
{
if (!isset($this->aParams[$sName]) || is_array($this->aParams[$sName])) {
if (!isset($this->aParams[$sName])) {
return $bDefault;
}
@@ -47,7 +36,7 @@ class ParameterParser
public function getFloat($sName, $bDefault = false)
{
if (!isset($this->aParams[$sName]) || is_array($this->aParams[$sName])) {
if (!isset($this->aParams[$sName])) {
return $bDefault;
}
@@ -60,10 +49,7 @@ class ParameterParser
public function getString($sName, $bDefault = false)
{
if (!isset($this->aParams[$sName])
|| !is_string($this->aParams[$sName])
|| strlen($this->aParams[$sName]) == 0
) {
if (!isset($this->aParams[$sName]) || strlen($this->aParams[$sName]) == 0) {
return $bDefault;
}
@@ -72,14 +58,11 @@ class ParameterParser
public function getSet($sName, $aValues, $sDefault = false)
{
if (!isset($this->aParams[$sName])
|| !is_string($this->aParams[$sName])
|| strlen($this->aParams[$sName]) == 0
) {
if (!isset($this->aParams[$sName]) || strlen($this->aParams[$sName]) == 0) {
return $sDefault;
}
if (!in_array($this->aParams[$sName], $aValues, true)) {
if (!in_array($this->aParams[$sName], $aValues)) {
userError("Parameter '$sName' must be one of: ".join(', ', $aValues));
}
@@ -123,27 +106,21 @@ class ParameterParser
}
foreach ($aLanguages as $sLanguage => $fLanguagePref) {
$this->addNameTag($aLangPrefOrder, 'name:'.$sLanguage);
$aLangPrefOrder['name:'.$sLanguage] = 'name:'.$sLanguage;
}
$this->addNameTag($aLangPrefOrder, 'name');
$this->addNameTag($aLangPrefOrder, 'brand');
$aLangPrefOrder['name'] = 'name';
$aLangPrefOrder['brand'] = 'brand';
foreach ($aLanguages as $sLanguage => $fLanguagePref) {
$this->addNameTag($aLangPrefOrder, 'official_name:'.$sLanguage);
$this->addNameTag($aLangPrefOrder, 'short_name:'.$sLanguage);
$aLangPrefOrder['official_name:'.$sLanguage] = 'official_name:'.$sLanguage;
$aLangPrefOrder['short_name:'.$sLanguage] = 'short_name:'.$sLanguage;
}
$this->addNameTag($aLangPrefOrder, 'official_name');
$this->addNameTag($aLangPrefOrder, 'short_name');
$this->addNameTag($aLangPrefOrder, 'ref');
$this->addNameTag($aLangPrefOrder, 'type');
$aLangPrefOrder['official_name'] = 'official_name';
$aLangPrefOrder['short_name'] = 'short_name';
$aLangPrefOrder['ref'] = 'ref';
$aLangPrefOrder['type'] = 'type';
return $aLangPrefOrder;
}
private function addNameTag(&$aLangPrefOrder, $sTag)
{
$aLangPrefOrder[$sTag] = $sTag;
$aLangPrefOrder['_place_'.$sTag] = '_place_'.$sTag;
}
public function hasSetAny($aParamNames)
{
foreach ($aParamNames as $sName) {

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
@@ -32,7 +24,7 @@ class Phrase
}
/**
* Get the original phrase of the string.
* Get the orginal phrase of the string.
*/
public function getPhrase()
{

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
@@ -86,7 +78,7 @@ class PlaceLookup
($this->bIncludePolygonAsSVG ? 1 : 0);
if ($iWantedTypes > CONST_PolygonOutput_MaximumTypes) {
if (CONST_PolygonOutput_MaximumTypes) {
userError('Select only '.CONST_PolygonOutput_MaximumTypes.' polygon output option');
userError('Select only '.CONST_PolygonOutput_MaximumTypes.' polgyon output option');
} else {
userError('Polygon output is disabled');
}
@@ -187,12 +179,12 @@ class PlaceLookup
return null;
}
$aResults = $this->lookup(array($iPlaceID => new Result($iPlaceID)), 0, 30, true);
$aResults = $this->lookup(array($iPlaceID => new Result($iPlaceID)));
return empty($aResults) ? null : reset($aResults);
}
public function lookup($aResults, $iMinRank = 0, $iMaxRank = 30, $bAllowLinked = false)
public function lookup($aResults, $iMinRank = 0, $iMaxRank = 30)
{
Debug::newFunction('Place lookup');
@@ -247,9 +239,7 @@ class PlaceLookup
if ($this->sAllowedTypesSQLList) {
$sSQL .= 'AND placex.class in '.$this->sAllowedTypesSQLList;
}
if (!$bAllowLinked) {
$sSQL .= ' AND linked_place_id is null ';
}
$sSQL .= ' AND linked_place_id is null ';
$sSQL .= ' GROUP BY ';
$sSQL .= ' osm_type, ';
$sSQL .= ' osm_id, ';
@@ -350,9 +340,7 @@ class PlaceLookup
$sSQL .= ' null::text AS extra_place ';
$sSQL .= ' FROM (';
$sSQL .= ' SELECT place_id, '; // interpolate the Tiger housenumbers here
$sSQL .= ' CASE WHEN startnumber != endnumber';
$sSQL .= ' THEN ST_LineInterpolatePoint(linegeo, (housenumber_for_place-startnumber::float)/(endnumber-startnumber)::float)';
$sSQL .= ' ELSE ST_LineInterpolatePoint(linegeo, 0.5) END AS centroid, ';
$sSQL .= ' ST_LineInterpolatePoint(linegeo, (housenumber_for_place-startnumber::float)/(endnumber-startnumber)::float) AS centroid, ';
$sSQL .= ' parent_place_id, ';
$sSQL .= ' housenumber_for_place';
$sSQL .= ' FROM (';
@@ -409,7 +397,7 @@ class PlaceLookup
$sSQL .= ' CASE '; // interpolate the housenumbers here
$sSQL .= ' WHEN startnumber != endnumber ';
$sSQL .= ' THEN ST_LineInterpolatePoint(linegeo, (housenumber_for_place-startnumber::float)/(endnumber-startnumber)::float) ';
$sSQL .= ' ELSE linegeo ';
$sSQL .= ' ELSE ST_LineInterpolatePoint(linegeo, 0.5) ';
$sSQL .= ' END as centroid, ';
$sSQL .= ' parent_place_id, ';
$sSQL .= ' housenumber_for_place ';
@@ -447,14 +435,18 @@ class PlaceLookup
if ($this->bExtraTags) {
if ($aPlace['extra']) {
$aPlace['sExtraTags'] = json_decode($aPlace['extra'], true);
$aPlace['sExtraTags'] = json_decode($aPlace['extra']);
} else {
$aPlace['sExtraTags'] = (object) array();
}
}
if ($this->bNameDetails) {
$aPlace['sNameDetails'] = $this->extractNames($aPlace['names']);
if ($aPlace['names']) {
$aPlace['sNameDetails'] = json_decode($aPlace['names']);
} else {
$aPlace['sNameDetails'] = (object) array();
}
}
$aPlace['addresstype'] = ClassTypes\getLabelTag(
@@ -477,33 +469,6 @@ class PlaceLookup
return $aResults;
}
private function extractNames($sNames)
{
if (!$sNames) {
return (object) array();
}
$aFullNames = json_decode($sNames, true);
$aNames = array();
foreach ($aFullNames as $sKey => $sValue) {
if (strpos($sKey, '_place_') === 0) {
$sSubKey = substr($sKey, 7);
if (array_key_exists($sSubKey, $aFullNames)) {
$aNames[$sKey] = $sValue;
} else {
$aNames[$sSubKey] = $sValue;
}
} else {
$aNames[$sKey] = $sValue;
}
}
return $aNames;
}
/* returns an array which will contain the keys
* aBoundingBox
* and may also contain one or more of the keys
@@ -514,6 +479,8 @@ class PlaceLookup
* lat
* lon
*/
public function getOutlines($iPlaceID, $fLon = null, $fLat = null, $fRadius = null, $fLonReverse = null, $fLatReverse = null)
{
@@ -524,7 +491,12 @@ class PlaceLookup
// Get the bounding box and outline polygon
$sSQL = 'select place_id,0 as numfeatures,st_area(geometry) as area,';
$sSQL .= ' ST_Y(centroid) as centrelat, ST_X(centroid) as centrelon,';
if ($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) {
@@ -539,21 +511,19 @@ class PlaceLookup
if ($this->bIncludePolygonAsText) {
$sSQL .= ',ST_AsText(geometry) as astext';
}
$sSQL .= ' FROM (SELECT place_id';
if ($fLonReverse != null && $fLatReverse != null) {
$sSQL .= ',CASE WHEN (class = \'highway\') AND (ST_GeometryType(geometry) = \'ST_LineString\') THEN ';
$sSQL .=' ST_ClosestPoint(geometry, ST_SetSRID(ST_Point('.$fLatReverse.','.$fLonReverse.'),4326))';
$sSQL .=' ELSE centroid END AS centroid';
$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 {
$sSQL .= ',centroid';
$sFrom = ' from placex where place_id = '.$iPlaceID;
}
if ($this->fPolygonSimplificationThreshold > 0) {
$sSQL .= ',ST_SimplifyPreserveTopology(geometry,'.$this->fPolygonSimplificationThreshold.') as geometry';
$sSQL .= ' from (select place_id,centroid,ST_SimplifyPreserveTopology(geometry,'.$this->fPolygonSimplificationThreshold.') as geometry'.$sFrom.') as plx';
} else {
$sSQL .= ',geometry';
$sSQL .= $sFrom;
}
$sSQL .= ' FROM placex where place_id = '.$iPlaceID.') as plx';
$aPointPolygon = $this->oDB->getRow($sSQL, null, 'Could not get outline');

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
@@ -40,10 +32,10 @@ class ReverseGeocode
9 => 12,
10 => 17, // City
11 => 17,
12 => 18, // Town
13 => 19, // Village
14 => 22, // Neighbourhood
15 => 25, // Locality
12 => 18, // Town / Village
13 => 18,
14 => 22, // Suburb
15 => 22,
16 => 26, // major street
17 => 27, // minor street
18 => 30, // or >, Building
@@ -64,15 +56,12 @@ class ReverseGeocode
{
Debug::newFunction('lookupInterpolation');
$sSQL = 'SELECT place_id, parent_place_id, 30 as rank_search,';
$sSQL .= ' (CASE WHEN endnumber != startnumber';
$sSQL .= ' THEN (endnumber - startnumber) * ST_LineLocatePoint(linegeo,'.$sPointSQL.')';
$sSQL .= ' ELSE startnumber END) as fhnr,';
$sSQL .= ' startnumber, endnumber, step,';
$sSQL .= ' ST_LineLocatePoint(linegeo,'.$sPointSQL.') as fraction,';
$sSQL .= ' startnumber, endnumber, interpolationtype,';
$sSQL .= ' ST_Distance(linegeo,'.$sPointSQL.') as distance';
$sSQL .= ' FROM location_property_osmline';
$sSQL .= ' WHERE ST_DWithin('.$sPointSQL.', linegeo, '.$fSearchDiam.')';
$sSQL .= ' and indexed_status = 0 and startnumber is not NULL ';
$sSQL .= ' and parent_place_id != 0';
$sSQL .= ' and indexed_status = 0 and startnumber is not NULL ';
$sSQL .= ' ORDER BY distance ASC limit 1';
Debug::printSQL($sSQL);
@@ -85,11 +74,6 @@ class ReverseGeocode
protected function lookupLargeArea($sPointSQL, $iMaxRank)
{
$sCountryCode = $this->getCountryCode($sPointSQL);
if (CONST_Search_WithinCountries and $sCountryCode == null) {
return null;
}
if ($iMaxRank > 4) {
$aPlace = $this->lookupPolygon($sPointSQL, $iMaxRank);
if ($aPlace) {
@@ -99,12 +83,12 @@ class ReverseGeocode
// If no polygon which contains the searchpoint is found,
// searches in the country_osm_grid table for a polygon.
return $this->lookupInCountry($sPointSQL, $iMaxRank, $sCountryCode);
return $this->lookupInCountry($sPointSQL, $iMaxRank);
}
protected function getCountryCode($sPointSQL)
protected function lookupInCountry($sPointSQL, $iMaxRank)
{
Debug::newFunction('getCountryCode');
Debug::newFunction('lookupInCountry');
// searches for polygon in table country_osm_grid which contains the searchpoint
// and searches for the nearest place node to the searchpoint in this polygon
$sSQL = 'SELECT country_code FROM country_osm_grid';
@@ -116,12 +100,8 @@ class ReverseGeocode
null,
'Could not determine country polygon containing the point.'
);
return $sCountryCode;
}
Debug::printVar('Country code', $sCountryCode);
protected function lookupInCountry($sPointSQL, $iMaxRank, $sCountryCode)
{
Debug::newFunction('lookupInCountry');
if ($sCountryCode) {
if ($iMaxRank > 4) {
// look for place nodes with the given country code
@@ -131,13 +111,12 @@ class ReverseGeocode
$sSQL .= ' FROM placex';
$sSQL .= ' WHERE osm_type = \'N\'';
$sSQL .= ' AND country_code = \''.$sCountryCode.'\'';
$sSQL .= ' AND rank_address between 4 and 25'; // needed to select right index
$sSQL .= ' AND rank_search < 26 '; // needed to select right index
$sSQL .= ' AND rank_search between 5 and ' .min(25, $iMaxRank);
$sSQL .= ' AND type != \'postcode\'';
$sSQL .= ' AND class = \'place\' AND type != \'postcode\'';
$sSQL .= ' AND name IS NOT NULL ';
$sSQL .= ' and indexed_status = 0 and linked_place_id is null';
$sSQL .= ' AND ST_Buffer(geometry, reverse_place_diameter(rank_search)) && '.$sPointSQL;
$sSQL .= ') as a ';
$sSQL .= ' AND ST_DWithin('.$sPointSQL.', geometry, 1.8)) p ';
$sSQL .= 'WHERE distance <= reverse_place_diameter(rank_search)';
$sSQL .= ' ORDER BY rank_search DESC, distance ASC';
$sSQL .= ' LIMIT 1';
@@ -199,16 +178,14 @@ class ReverseGeocode
$sSQL .= '(select place_id, parent_place_id, rank_address, rank_search, country_code, geometry';
$sSQL .= ' FROM placex';
$sSQL .= ' WHERE ST_GeometryType(geometry) in (\'ST_Polygon\', \'ST_MultiPolygon\')';
// Ensure that query planner doesn't use the index on rank_search.
$sSQL .= ' AND coalesce(rank_search, 0) between 5 and ' .$iMaxRank;
$sSQL .= ' AND rank_address between 4 and 25'; // needed for index selection
$sSQL .= ' AND rank_address Between 5 AND ' .$iMaxRank;
$sSQL .= ' AND geometry && '.$sPointSQL;
$sSQL .= ' AND type != \'postcode\' ';
$sSQL .= ' AND name is not null';
$sSQL .= ' AND indexed_status = 0 and linked_place_id is null';
$sSQL .= ' ORDER BY rank_search DESC LIMIT 50 ) as a';
$sSQL .= ' WHERE ST_Contains(geometry, '.$sPointSQL.' )';
$sSQL .= ' ORDER BY rank_search DESC LIMIT 1';
$sSQL .= ' ORDER BY rank_address DESC LIMIT 50 ) as a';
$sSQL .= ' WHERE ST_CONTAINS(geometry, '.$sPointSQL.' )';
$sSQL .= ' ORDER BY rank_address DESC LIMIT 1';
Debug::printSQL($sSQL);
$aPoly = $this->oDB->getRow($sSQL, null, 'Could not determine polygon containing the point.');
@@ -220,24 +197,29 @@ class ReverseGeocode
$iRankSearch = $aPoly['rank_search'];
$iPlaceID = $aPoly['place_id'];
if ($iRankSearch != $iMaxRank) {
if ($iRankAddress != $iMaxRank) {
$sSQL = 'SELECT place_id FROM ';
$sSQL .= '(SELECT place_id, rank_search, country_code, geometry,';
$sSQL .= ' ST_distance('.$sPointSQL.', geometry) as distance';
$sSQL .= ' FROM placex';
$sSQL .= ' WHERE osm_type = \'N\'';
// using rank_search because of a better differentiation
// for place nodes at rank_address 16
$sSQL .= ' AND rank_search > '.$iRankSearch;
$sSQL .= ' AND rank_search <= '.$iMaxRank;
$sSQL .= ' AND rank_address between 4 and 25'; // needed to select right index
$sSQL .= ' AND rank_search < 26 '; // needed to select right index
$sSQL .= ' AND rank_address > 0';
$sSQL .= ' AND class = \'place\'';
$sSQL .= ' AND type != \'postcode\'';
$sSQL .= ' AND name IS NOT NULL ';
$sSQL .= ' AND indexed_status = 0 AND linked_place_id is null';
$sSQL .= ' AND ST_Buffer(geometry, reverse_place_diameter(rank_search)) && '.$sPointSQL;
$sSQL .= ' ORDER BY rank_search DESC, distance ASC';
$sSQL .= ' limit 100) as a';
$sSQL .= ' WHERE ST_Contains((SELECT geometry FROM placex WHERE place_id = '.$iPlaceID.'), geometry )';
$sSQL .= ' AND ST_DWithin('.$sPointSQL.', geometry, reverse_place_diameter('.$iRankSearch.'::smallint))';
$sSQL .= ' ORDER BY distance ASC,';
$sSQL .= ' rank_address DESC';
$sSQL .= ' limit 500) as a';
$sSQL .= ' WHERE ST_CONTAINS((SELECT geometry FROM placex WHERE place_id = '.$iPlaceID.'), geometry )';
$sSQL .= ' AND distance <= reverse_place_diameter(rank_search)';
$sSQL .= ' ORDER BY rank_search DESC, distance ASC';
$sSQL .= ' ORDER BY distance ASC, rank_search DESC';
$sSQL .= ' LIMIT 1';
Debug::printSQL($sSQL);
@@ -273,7 +255,7 @@ class ReverseGeocode
// starts if the search is on POI or street level,
// searches for the nearest POI or street,
// if a street is found and a POI is searched for,
// the nearest POI which the found street is a parent of is chosen.
// the nearest POI which the found street is a parent of is choosen.
$sSQL = 'select place_id,parent_place_id,rank_address,country_code,';
$sSQL .= ' ST_distance('.$sPointSQL.', geometry) as distance';
$sSQL .= ' FROM ';
@@ -337,9 +319,9 @@ class ReverseGeocode
&& $this->iMaxRank >= 28
) {
$sSQL = 'SELECT place_id,parent_place_id,30 as rank_search,';
$sSQL .= ' (endnumber - startnumber) * ST_LineLocatePoint(linegeo,'.$sPointSQL.') as fhnr,';
$sSQL .= ' startnumber, endnumber, step,';
$sSQL .= ' ST_Distance('.$sPointSQL.', linegeo) as distance';
$sSQL .= 'ST_LineLocatePoint(linegeo,'.$sPointSQL.') as fraction,';
$sSQL .= 'ST_distance('.$sPointSQL.', linegeo) as distance,';
$sSQL .= 'startnumber,endnumber,interpolationtype';
$sSQL .= ' FROM location_property_tiger WHERE parent_place_id = '.$oResult->iId;
$sSQL .= ' AND ST_DWithin('.$sPointSQL.', linegeo, 0.001)';
$sSQL .= ' ORDER BY distance ASC limit 1';
@@ -351,11 +333,7 @@ class ReverseGeocode
if ($aPlaceTiger) {
$aPlace = $aPlaceTiger;
$oResult = new Result($aPlaceTiger['place_id'], Result::TABLE_TIGER);
$iRndNum = max(0, round($aPlaceTiger['fhnr'] / $aPlaceTiger['step']) * $aPlaceTiger['step']);
$oResult->iHouseNumber = $aPlaceTiger['startnumber'] + $iRndNum;
if ($oResult->iHouseNumber > $aPlaceTiger['endnumber']) {
$oResult->iHouseNumber = $aPlaceTiger['endnumber'];
}
$oResult->iHouseNumber = closestHouseNumber($aPlaceTiger);
$iRankAddress = 30;
}
}
@@ -367,7 +345,7 @@ class ReverseGeocode
// We can't reliably go from the closest street to an
// interpolation line because the closest interpolation
// may have a different street segments as a parent.
// Therefore allow an interpolation line to take precedence
// Therefore allow an interpolation line to take precendence
// even when the street is closer.
$fDistance = $iRankAddress < 28 ? 0.001 : $aPlace['distance'];
}
@@ -377,11 +355,7 @@ class ReverseGeocode
if ($aHouse) {
$oResult = new Result($aHouse['place_id'], Result::TABLE_OSMLINE);
$iRndNum = max(0, round($aHouse['fhnr'] / $aHouse['step']) * $aHouse['step']);
$oResult->iHouseNumber = $aHouse['startnumber'] + $iRndNum;
if ($oResult->iHouseNumber > $aHouse['endnumber']) {
$oResult->iHouseNumber = $aHouse['endnumber'];
}
$oResult->iHouseNumber = closestHouseNumber($aHouse);
$aPlace = $aHouse;
}
}

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
@@ -236,7 +228,7 @@ class SearchDescription
* Add the given full-word token to the list of terms to search for in the
* name.
*
* @param integer iId ID of term to add.
* @param 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.
*/
@@ -264,10 +256,8 @@ class SearchDescription
{
if (empty($this->aName)) {
$this->bNameNeedsAddress = $bNeedsAddress;
} elseif ($bSearchable && count($this->aName) >= 2) {
$this->bNameNeedsAddress = false;
} else {
$this->bNameNeedsAddress &= $bNeedsAddress;
$this->bNameNeedsAddress |= $bNeedsAddress;
}
if ($bSearchable) {
$this->aName[$iId] = $iId;
@@ -387,7 +377,7 @@ class SearchDescription
*
* @return mixed[] An array with two fields: IDs contains the list of
* matching place IDs and houseNumber the houseNumber
* if applicable or -1 if not.
* if appicable or -1 if not.
*/
public function query(&$oDB, $iMinRank, $iMaxRank, $iLimit)
{
@@ -422,6 +412,28 @@ class SearchDescription
$iLimit
);
// Now search for housenumber, if housenumber provided. Can be zero.
if (($this->sHouseNumber || $this->sHouseNumber === '0') && !empty($aResults)) {
$aHnResults = $this->queryHouseNumber($oDB, $aResults);
// Downgrade the rank of the street results, they are missing
// the housenumber. Also drop POI places (rank 30) here, they
// cannot be a parent place and therefore must not be shown
// as a result for a search with a missing housenumber.
foreach ($aResults as $oRes) {
if ($oRes->iAddressRank < 28) {
if ($oRes->iAddressRank >= 26) {
$oRes->iResultRank++;
} else {
$oRes->iResultRank += 2;
}
$aHnResults[$oRes->iId] = $oRes;
}
}
$aResults = $aHnResults;
}
// finally get POIs if requested
if ($this->sClass && !empty($aResults)) {
$aResults = $this->queryPoiByOperator($oDB, $aResults, $iLimit);
@@ -567,6 +579,41 @@ class SearchDescription
$aTerms = array();
$aOrder = array();
// Sort by existence of the requested house number but only if not
// too many results are expected for the street, i.e. if the result
// will be narrowed down by an address. Remember that with ordering
// every single result has to be checked.
if ($this->sHouseNumber && ($this->bRareName || !empty($this->aAddress) || $this->sPostcode)) {
$sHouseNumberRegex = '\\\\m'.$this->sHouseNumber.'\\\\M';
// Housenumbers on streets and places.
$sChildHnr = 'SELECT * FROM placex WHERE parent_place_id = search_name.place_id';
$sChildHnr .= " AND housenumber ~* E'".$sHouseNumberRegex."'";
// Interpolations on streets and places.
if (preg_match('/^[0-9]+$/', $this->sHouseNumber)) {
$sIpolHnr = 'SELECT * FROM location_property_osmline ';
$sIpolHnr .= 'WHERE parent_place_id = search_name.place_id ';
$sIpolHnr .= ' AND startnumber is not NULL';
$sIpolHnr .= ' AND '.$this->sHouseNumber.'>=startnumber ';
$sIpolHnr .= ' AND '.$this->sHouseNumber.'<=endnumber ';
} else {
$sIpolHnr = false;
}
// Housenumbers on the object iteself for unlisted places.
$sSelfHnr = 'SELECT * FROM placex WHERE place_id = search_name.place_id';
$sSelfHnr .= " AND housenumber ~* E'".$sHouseNumberRegex."'";
$sSql = '(CASE WHEN address_rank = 30 THEN EXISTS('.$sSelfHnr.') ';
$sSql .= ' ELSE EXISTS('.$sChildHnr.') ';
if ($sIpolHnr) {
$sSql .= 'OR EXISTS('.$sIpolHnr.') ';
}
$sSql .= 'END) DESC';
$aOrder[] = $sSql;
}
if (!empty($this->aName)) {
$aTerms[] = 'name_vector @> '.$oDB->getArraySQL($this->aName);
}
@@ -612,6 +659,10 @@ class SearchDescription
$aTerms[] = 'centroid && '.$this->oContext->sqlViewboxSmall;
}
if ($this->oContext->hasNearPoint()) {
$aOrder[] = $this->oContext->distanceSQL('centroid');
}
if ($this->sHouseNumber) {
$sImportanceSQL = '- abs(26 - address_rank) + 3';
} else {
@@ -634,128 +685,122 @@ class SearchDescription
$sExactMatchSQL = '0::int as exactmatch';
}
if (empty($aTerms)) {
return array();
if ($this->sHouseNumber || $this->sClass) {
$iLimit = 40;
}
if ($this->hasHousenumber()) {
$sHouseNumberRegex = $oDB->getDBQuoted('\\\\m'.$this->sHouseNumber.'\\\\M');
$aResults = array();
// Housenumbers on streets and places.
$sPlacexSql = 'SELECT array_agg(place_id) FROM placex';
$sPlacexSql .= ' WHERE parent_place_id = sin.place_id AND sin.address_rank < 30';
$sPlacexSql .= $this->oContext->excludeSQL(' AND place_id');
$sPlacexSql .= ' and housenumber ~* E'.$sHouseNumberRegex;
// Interpolations on streets and places.
$sInterpolSql = 'null';
$sTigerSql = 'null';
if (preg_match('/^[0-9]+$/', $this->sHouseNumber)) {
$sIpolHnr = 'WHERE parent_place_id = sin.place_id ';
$sIpolHnr .= ' AND startnumber is not NULL AND sin.address_rank < 30';
$sIpolHnr .= ' AND '.$this->sHouseNumber.' between startnumber and endnumber';
$sIpolHnr .= ' AND ('.$this->sHouseNumber.' - startnumber) % step = 0';
$sInterpolSql = 'SELECT array_agg(place_id) FROM location_property_osmline '.$sIpolHnr;
if (CONST_Use_US_Tiger_Data) {
$sTigerSql = 'SELECT array_agg(place_id) FROM location_property_tiger '.$sIpolHnr;
$sTigerSql .= " and sin.country_code = 'us'";
}
}
if ($this->sClass) {
$iLimit = 40;
}
$sSelfHnr = 'SELECT * FROM placex WHERE place_id = search_name.place_id';
$sSelfHnr .= ' AND housenumber ~* E'.$sHouseNumberRegex;
$aTerms[] = '(address_rank < 30 or exists('.$sSelfHnr.'))';
$sSQL = 'SELECT sin.*, ';
$sSQL .= '('.$sPlacexSql.') as placex_hnr, ';
$sSQL .= '('.$sInterpolSql.') as interpol_hnr, ';
$sSQL .= '('.$sTigerSql.') as tiger_hnr ';
$sSQL .= ' FROM (';
$sSQL .= ' SELECT place_id, address_rank, country_code,'.$sExactMatchSQL.',';
$sSQL .= ' CASE WHEN importance = 0 OR importance IS NULL';
$sSQL .= ' THEN 0.75001-(search_rank::float/40) ELSE importance END as importance';
$sSQL .= ' FROM search_name';
$sSQL .= ' WHERE '.join(' and ', $aTerms);
$sSQL .= ' ORDER BY '.join(', ', $aOrder);
$sSQL .= ' LIMIT 40000';
$sSQL .= ') as sin';
$sSQL .= ' ORDER BY address_rank = 30 desc, placex_hnr, interpol_hnr, tiger_hnr,';
$sSQL .= ' importance';
$sSQL .= ' LIMIT '.$iLimit;
} else {
if ($this->sClass) {
$iLimit = 40;
}
$sSQL = 'SELECT place_id, address_rank, '.$sExactMatchSQL;
if (!empty($aTerms)) {
$sSQL = 'SELECT place_id, address_rank,'.$sExactMatchSQL;
$sSQL .= ' FROM search_name';
$sSQL .= ' WHERE '.join(' and ', $aTerms);
$sSQL .= ' ORDER BY '.join(', ', $aOrder);
$sSQL .= ' LIMIT '.$iLimit;
Debug::printSQL($sSQL);
$aDBResults = $oDB->getAll($sSQL, null, 'Could not get places for search terms.');
foreach ($aDBResults as $aResult) {
$oResult = new Result($aResult['place_id']);
$oResult->iExactMatches = $aResult['exactmatch'];
$oResult->iAddressRank = $aResult['address_rank'];
$aResults[$aResult['place_id']] = $oResult;
}
}
return $aResults;
}
private function queryHouseNumber(&$oDB, $aRoadPlaceIDs)
{
$aResults = array();
$sRoadPlaceIDs = Result::joinIdsByTableMaxRank(
$aRoadPlaceIDs,
Result::TABLE_PLACEX,
27
);
$sPOIPlaceIDs = Result::joinIdsByTableMinRank(
$aRoadPlaceIDs,
Result::TABLE_PLACEX,
30
);
$aIDCondition = array();
if ($sRoadPlaceIDs) {
$aIDCondition[] = 'parent_place_id in ('.$sRoadPlaceIDs.')';
}
if ($sPOIPlaceIDs) {
$aIDCondition[] = 'place_id in ('.$sPOIPlaceIDs.')';
}
if (empty($aIDCondition)) {
return $aResults;
}
$sHouseNumberRegex = '\\\\m'.$this->sHouseNumber.'\\\\M';
$sSQL = 'SELECT place_id FROM placex WHERE';
$sSQL .= " housenumber ~* E'".$sHouseNumberRegex."'";
$sSQL .= ' AND ('.join(' OR ', $aIDCondition).')';
$sSQL .= $this->oContext->excludeSQL(' AND place_id');
Debug::printSQL($sSQL);
$aDBResults = $oDB->getAll($sSQL, null, 'Could not get places for search terms.');
// XXX should inherit the exactMatches from its parent
foreach ($oDB->getCol($sSQL) as $iPlaceId) {
$aResults[$iPlaceId] = new Result($iPlaceId);
}
$aResults = array();
foreach ($aDBResults as $aResult) {
$oResult = new Result($aResult['place_id']);
$oResult->iExactMatches = $aResult['exactmatch'];
$oResult->iAddressRank = $aResult['address_rank'];
$bNeedResult = true;
if ($this->hasHousenumber() && $aResult['address_rank'] < 30) {
if ($aResult['placex_hnr']) {
foreach (explode(',', substr($aResult['placex_hnr'], 1, -1)) as $sPlaceID) {
$iPlaceID = intval($sPlaceID);
$oHnrResult = new Result($iPlaceID);
$oHnrResult->iExactMatches = $aResult['exactmatch'];
$oHnrResult->iAddressRank = 30;
$aResults[$iPlaceID] = $oHnrResult;
$bNeedResult = false;
}
}
if ($aResult['interpol_hnr']) {
foreach (explode(',', substr($aResult['interpol_hnr'], 1, -1)) as $sPlaceID) {
$iPlaceID = intval($sPlaceID);
$oHnrResult = new Result($iPlaceID, Result::TABLE_OSMLINE);
$oHnrResult->iExactMatches = $aResult['exactmatch'];
$oHnrResult->iAddressRank = 30;
$oHnrResult->iHouseNumber = intval($this->sHouseNumber);
$aResults[$iPlaceID] = $oHnrResult;
$bNeedResult = false;
}
}
if ($aResult['tiger_hnr']) {
foreach (explode(',', substr($aResult['tiger_hnr'], 1, -1)) as $sPlaceID) {
$iPlaceID = intval($sPlaceID);
$oHnrResult = new Result($iPlaceID, Result::TABLE_TIGER);
$oHnrResult->iExactMatches = $aResult['exactmatch'];
$oHnrResult->iAddressRank = 30;
$oHnrResult->iHouseNumber = intval($this->sHouseNumber);
$aResults[$iPlaceID] = $oHnrResult;
$bNeedResult = false;
}
}
if ($aResult['address_rank'] < 26) {
$oResult->iResultRank += 2;
} else {
$oResult->iResultRank++;
}
$bIsIntHouseNumber= (bool) preg_match('/[0-9]+/', $this->sHouseNumber);
$iHousenumber = intval($this->sHouseNumber);
if ($bIsIntHouseNumber && $sRoadPlaceIDs && empty($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 (';
if ($iHousenumber % 2 == 0) {
// If housenumber is even, look for housenumber in streets
// with interpolationtype even or all.
$sSQL .= "interpolationtype='even'";
} else {
// Else look for housenumber with interpolationtype odd or all.
$sSQL .= "interpolationtype='odd'";
}
$sSQL .= " or interpolationtype='all') and ";
$sSQL .= $iHousenumber.'>=startnumber and ';
$sSQL .= $iHousenumber.'<=endnumber';
$sSQL .= $this->oContext->excludeSQL(' AND place_id');
if ($bNeedResult) {
$aResults[$aResult['place_id']] = $oResult;
Debug::printSQL($sSQL);
foreach ($oDB->getCol($sSQL) as $iPlaceId) {
$oResult = new Result($iPlaceId, Result::TABLE_OSMLINE);
$oResult->iHouseNumber = $iHousenumber;
$aResults[$iPlaceId] = $oResult;
}
}
// If nothing found then search in Tiger data (location_property_tiger)
if (CONST_Use_US_Tiger_Data && $sRoadPlaceIDs && $bIsIntHouseNumber && empty($aResults)) {
$sSQL = 'SELECT place_id FROM location_property_tiger';
$sSQL .= ' WHERE parent_place_id in ('.$sRoadPlaceIDs.') and (';
if ($iHousenumber % 2 == 0) {
$sSQL .= "interpolationtype='even'";
} else {
$sSQL .= "interpolationtype='odd'";
}
$sSQL .= " or interpolationtype='all') and ";
$sSQL .= $iHousenumber.'>=startnumber and ';
$sSQL .= $iHousenumber.'<=endnumber';
$sSQL .= $this->oContext->excludeSQL(' AND place_id');
Debug::printSQL($sSQL);
foreach ($oDB->getCol($sSQL) as $iPlaceId) {
$oResult = new Result($iPlaceId, Result::TABLE_TIGER);
$oResult->iHouseNumber = $iHousenumber;
$aResults[$iPlaceId] = $oResult;
}
}
@@ -807,7 +852,6 @@ class SearchDescription
$sSQL = 'SELECT geometry FROM placex';
$sSQL .= " WHERE place_id in ($sPlaceIDs)";
$sSQL .= " AND rank_search < $iMaxRank + 5";
$sSQL .= ' AND ST_Area(Box2d(geometry)) < 20';
$sSQL .= " AND ST_GeometryType(geometry) in ('ST_Polygon','ST_MultiPolygon')";
$sSQL .= ' ORDER BY rank_search ASC ';
$sSQL .= ' LIMIT 1';

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
@@ -120,18 +112,13 @@ class SimpleWordList
return array_slice($aWordSets, 0, SimpleWordList::MAX_WORDSETS);
}
/**
* Custom search routine which takes two arrays. The array with the fewest
* items wins. If same number of items then the one with the longest first
* element wins.
*/
public static function cmpByArraylen($aA, $aB)
{
$iALen = count($aA);
$iBLen = count($aB);
if ($iALen == $iBLen) {
return strlen($aB[0]) <=> strlen($aA[0]);
return 0;
}
return ($iALen < $iBLen) ? -1 : 1;

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim\Token;

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim\Token;
@@ -66,7 +58,7 @@ class HouseNumber
// up of numbers, add a penalty
$iSearchCost = 1;
if (preg_match('/\\d/', $this->sToken) === 0
|| preg_match_all('/[^0-9 ]/', $this->sToken, $aMatches) > 3) {
|| preg_match_all('/[^0-9]/', $this->sToken, $aMatches) > 2) {
$iSearchCost += strlen($this->sToken) - 1;
}
if (!$oSearch->hasOperator(\Nominatim\Operator::NONE)) {

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim\Token;

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim\Token;
@@ -17,7 +9,7 @@ class Postcode
{
/// Database word id, if available.
private $iId;
/// Full normalized postcode (upper cased).
/// Full nomralized postcode (upper cased).
private $sPostcode;
// Optional country code the postcode belongs to (currently unused).
private $sCountryCode;
@@ -25,12 +17,7 @@ class Postcode
public function __construct($iId, $sPostcode, $sCountryCode = '')
{
$this->iId = $iId;
$iSplitPos = strpos($sPostcode, '@');
if ($iSplitPos === false) {
$this->sPostcode = $sPostcode;
} else {
$this->sPostcode = substr($sPostcode, 0, $iSplitPos);
}
$this->sPostcode = $sPostcode;
$this->sCountryCode = empty($sCountryCode) ? '' : $sCountryCode;
}

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim\Token;
@@ -69,31 +61,19 @@ class SpecialTerm
*/
public function extendSearch($oSearch, $oPosition)
{
$iSearchCost = 0;
$iSearchCost = 2;
$iOp = $this->iOperator;
if ($iOp == \Nominatim\Operator::NONE) {
if ($oPosition->isFirstToken()
|| $oSearch->hasName()
|| $oSearch->getContext()->isBoundedSearch()
) {
if ($oSearch->hasName() || $oSearch->getContext()->isBoundedSearch()) {
$iOp = \Nominatim\Operator::NAME;
$iSearchCost += 3;
} else {
$iOp = \Nominatim\Operator::NEAR;
$iSearchCost += 4;
if (!$oPosition->isFirstToken()) {
$iSearchCost += 3;
}
$iSearchCost += 2;
}
} elseif ($oPosition->isFirstToken()) {
} elseif (!$oPosition->isFirstToken() && !$oPosition->isLastToken()) {
$iSearchCost += 2;
} elseif ($oPosition->isLastToken()) {
$iSearchCost += 4;
} else {
$iSearchCost += 6;
}
if ($oSearch->hasHousenumber()) {
$iSearchCost ++;
}

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim\Token;
@@ -62,7 +54,7 @@ class Word
public function extendSearch($oSearch, $oPosition)
{
// Full words can only be a name if they appear at the beginning
// of the phrase. In structured search the name must forcibly in
// of the phrase. In structured search the name must forcably in
// the first phrase. In unstructured search it may be in a later
// phrase when the first phrase is a house number.
if ($oSearch->hasName()

182
lib-php/admin/export.php Normal file
View File

@@ -0,0 +1,182 @@
<?php
@define('CONST_LibDir', dirname(dirname(__FILE__)));
// Script to extract structured city and street data
// from a running nominatim instance as CSV data
require_once(CONST_LibDir.'/init-cmd.php');
require_once(CONST_LibDir.'/ParameterParser.php');
ini_set('memory_limit', '800M');
$aCMDOptions = array(
'Export addresses as CSV file from a Nominatim database',
array('help', 'h', 0, 1, 0, 0, false, 'Show Help'),
array('quiet', 'q', 0, 1, 0, 0, 'bool', 'Quiet output'),
array('verbose', 'v', 0, 1, 0, 0, 'bool', 'Verbose output'),
array('output-type', '', 0, 1, 1, 1, 'str', 'Type of places to output (see below)'),
array('output-format', '', 0, 1, 1, 1, 'str', 'Column mapping (see below)'),
array('output-all-postcodes', '', 0, 1, 0, 0, 'bool', 'List all postcodes for address instead of just the most likely one'),
array('language', '', 0, 1, 1, 1, 'str', 'Preferred language for output (local name, if omitted)'),
array('restrict-to-country', '', 0, 1, 1, 1, 'str', 'Export only objects within country (country code)'),
array('restrict-to-osm-node', '', 0, 1, 1, 1, 'int', 'Export only objects that are children of this OSM node'),
array('restrict-to-osm-way', '', 0, 1, 1, 1, 'int', 'Export only objects that are children of this OSM way'),
array('restrict-to-osm-relation', '', 0, 1, 1, 1, 'int', 'Export only objects that are children of this OSM relation'),
array('project-dir', '', 0, 1, 1, 1, 'realpath', 'Base directory of the Nominatim installation (default: .)'),
"\nAddress ranks: continent, country, state, county, city, suburb, street, path",
'Additional output types: postcode, placeid (placeid for each object)',
"\noutput-format must be a semicolon-separated list of address ranks. Multiple ranks",
'can be merged into one column by simply using a comma-separated list.',
"\nDefault output-type: street",
'Default output format: street;suburb;city;county;state;country'
);
getCmdOpt($_SERVER['argv'], $aCMDOptions, $aCMDResult, true, true);
loadSettings($aCMDResult['project-dir'] ?? getcwd());
$aRankmap = array(
'continent' => 1,
'country' => 4,
'state' => 8,
'county' => 12,
'city' => 16,
'suburb' => 20,
'street' => 26,
'path' => 27
);
$oDB = new Nominatim\DB();
$oDB->connect();
if (isset($aCMDResult['output-type'])) {
if (!isset($aRankmap[$aCMDResult['output-type']])) {
fail('unknown output-type: '.$aCMDResult['output-type']);
}
$iOutputRank = $aRankmap[$aCMDResult['output-type']];
} else {
$iOutputRank = $aRankmap['street'];
}
// Preferred language
$oParams = new Nominatim\ParameterParser();
if (!isset($aCMDResult['language'])) {
$aCMDResult['language'] = 'xx';
}
$aLangPrefOrder = $oParams->getPreferredLanguages($aCMDResult['language']);
$sLanguagePrefArraySQL = $oDB->getArraySQL($oDB->getDBQuotedList($aLangPrefOrder));
// output formatting: build up a lookup table that maps address ranks to columns
$aColumnMapping = array();
$iNumCol = 0;
if (!isset($aCMDResult['output-format'])) {
$aCMDResult['output-format'] = 'street;suburb;city;county;state;country';
}
foreach (preg_split('/\s*;\s*/', $aCMDResult['output-format']) as $sColumn) {
$bHasData = false;
foreach (preg_split('/\s*,\s*/', $sColumn) as $sRank) {
if ($sRank == 'postcode' || $sRank == 'placeid') {
$aColumnMapping[$sRank] = $iNumCol;
$bHasData = true;
} elseif (isset($aRankmap[$sRank])) {
$iRank = $aRankmap[$sRank];
if ($iRank <= $iOutputRank) {
$aColumnMapping[(string)$iRank] = $iNumCol;
$bHasData = true;
}
}
}
if ($bHasData) {
$iNumCol++;
}
}
// build the query for objects
$sPlacexSQL = 'select min(place_id) as place_id, ';
$sPlacexSQL .= 'array_agg(place_id) as place_ids, ';
$sPlacexSQL .= 'country_code as cc, ';
$sPlacexSQL .= 'postcode, ';
// get the address places excluding postcodes
$sPlacexSQL .= 'array(select address_place_id from place_addressline a';
$sPlacexSQL .= ' where a.place_id = placex.place_id and isaddress';
$sPlacexSQL .= ' and address_place_id != placex.place_id';
$sPlacexSQL .= ' and not cached_rank_address in (5,11)';
$sPlacexSQL .= ' and cached_rank_address > 2 order by cached_rank_address)';
$sPlacexSQL .= ' as address';
$sPlacexSQL .= ' from placex where name is not null and linked_place_id is null';
$sPlacexSQL .= ' and rank_address = '.$iOutputRank;
if (isset($aCMDResult['restrict-to-country'])) {
$sPlacexSQL .= ' and country_code = '.$oDB->getDBQuoted($aCMDResult['restrict-to-country']);
}
// restriction to parent place id
$sParentId = false;
$sOsmType = false;
if (isset($aCMDResult['restrict-to-osm-node'])) {
$sOsmType = 'N';
$sOsmId = $aCMDResult['restrict-to-osm-node'];
}
if (isset($aCMDResult['restrict-to-osm-way'])) {
$sOsmType = 'W';
$sOsmId = $aCMDResult['restrict-to-osm-way'];
}
if (isset($aCMDResult['restrict-to-osm-relation'])) {
$sOsmType = 'R';
$sOsmId = $aCMDResult['restrict-to-osm-relation'];
}
if ($sOsmType) {
$sSQL = 'select place_id from placex where osm_type = :osm_type and osm_id = :osm_id';
$sParentId = $oDB->getOne($sSQL, array('osm_type' => $sOsmType, 'osm_id' => $sOsmId));
if (!$sParentId) {
fail('Could not find place '.$sOsmType.' '.$sOsmId);
}
}
if ($sParentId) {
$sPlacexSQL .= ' and place_id in (select place_id from place_addressline where address_place_id = '.$sParentId.' and isaddress)';
}
$sPlacexSQL .= " group by name->'name', address, postcode, country_code, placex.place_id";
// Iterate over placeids
// to get further hierarchical information
//var_dump($sPlacexSQL);
$oResults = $oDB->getQueryStatement($sPlacexSQL);
$fOutstream = fopen('php://output', 'w');
while ($aRow = $oResults->fetch()) {
$iPlaceID = $aRow['place_id'];
$sSQL = "select rank_address,get_name_by_language(name,$sLanguagePrefArraySQL) as localname from get_addressdata(:place_id, -1)";
$sSQL .= ' WHERE isaddress';
$sSQL .= ' order by rank_address desc,isaddress desc';
$aAddressLines = $oDB->getAll($sSQL, array('place_id' => $iPlaceID));
$aOutput = array_fill(0, $iNumCol, '');
// output address parts
foreach ($aAddressLines as $aAddress) {
if (isset($aColumnMapping[$aAddress['rank_address']])) {
$aOutput[$aColumnMapping[$aAddress['rank_address']]] = $aAddress['localname'];
}
}
// output postcode
if (isset($aColumnMapping['postcode'])) {
if ($aCMDResult['output-all-postcodes']) {
$sSQL = 'select array_agg(px.postcode) from placex px join place_addressline pa ';
$sSQL .= 'on px.place_id = pa.address_place_id ';
$sSQL .= 'where pa.cached_rank_address in (5,11) ';
$sSQL .= 'and pa.place_id in (select place_id from place_addressline where address_place_id in (:first_place_id)) ';
$sSQL .= 'group by postcode order by count(*) desc limit 1';
$sRes = $oDB->getOne($sSQL, array('first_place_id' => substr($aRow['place_ids'], 1, -1)));
$aOutput[$aColumnMapping['postcode']] = substr($sRes, 1, -1);
} else {
$aOutput[$aColumnMapping['postcode']] = $aRow['postcode'];
}
}
if (isset($aColumnMapping['placeid'])) {
$aOutput[$aColumnMapping['placeid']] = substr($aRow['place_ids'], 1, -1);
}
fputcsv($fOutstream, $aOutput);
}
fclose($fOutstream);

106
lib-php/admin/warm.php Normal file
View File

@@ -0,0 +1,106 @@
<?php
@define('CONST_LibDir', dirname(dirname(__FILE__)));
require_once(CONST_LibDir.'/init-cmd.php');
require_once(CONST_LibDir.'/log.php');
require_once(CONST_LibDir.'/PlaceLookup.php');
require_once(CONST_LibDir.'/ReverseGeocode.php');
ini_set('memory_limit', '800M');
$aCMDOptions = array(
'Tools to warm nominatim db',
array('help', 'h', 0, 1, 0, 0, false, 'Show Help'),
array('quiet', 'q', 0, 1, 0, 0, 'bool', 'Quiet output'),
array('verbose', 'v', 0, 1, 0, 0, 'bool', 'Verbose output'),
array('reverse-only', '', 0, 1, 0, 0, 'bool', 'Warm reverse only'),
array('search-only', '', 0, 1, 0, 0, 'bool', 'Warm search only'),
array('project-dir', '', 0, 1, 1, 1, 'realpath', 'Base directory of the Nominatim installation (default: .)'),
);
getCmdOpt($_SERVER['argv'], $aCMDOptions, $aResult, true, true);
loadSettings($aCMDResult['project-dir'] ?? getcwd());
@define('CONST_Database_DSN', getSetting('DATABASE_DSN'));
@define('CONST_Default_Language', getSetting('DEFAULT_LANGUAGE', false));
@define('CONST_Log_DB', getSettingBool('LOG_DB'));
@define('CONST_Log_File', getSetting('LOG_FILE', false));
@define('CONST_NoAccessControl', getSettingBool('CORS_NOACCESSCONTROL'));
@define('CONST_Places_Max_ID_count', getSetting('LOOKUP_MAX_COUNT'));
@define('CONST_PolygonOutput_MaximumTypes', getSetting('POLYGON_OUTPUT_MAX_TYPES'));
@define('CONST_Search_BatchMode', getSettingBool('SEARCH_BATCH_MODE'));
@define('CONST_Search_NameOnlySearchFrequencyThreshold', getSetting('SEARCH_NAME_ONLY_THRESHOLD'));
@define('CONST_Use_US_Tiger_Data', getSettingBool('USE_US_TIGER_DATA'));
@define('CONST_MapIcon_URL', getSetting('MAPICON_URL', false));
@define('CONST_TokenizerDir', CONST_InstallDir.'/tokenizer');
require_once(CONST_LibDir.'/Geocode.php');
$oDB = new Nominatim\DB();
$oDB->connect();
$bVerbose = $aResult['verbose'];
function print_results($aResults, $bVerbose)
{
if ($bVerbose) {
if ($aResults && count($aResults)) {
echo $aResults[0]['langaddress']."\n";
} else {
echo "<not found>\n";
}
} else {
echo '.';
}
}
if (!$aResult['search-only']) {
$oReverseGeocode = new Nominatim\ReverseGeocode($oDB);
$oReverseGeocode->setZoom(20);
$oPlaceLookup = new Nominatim\PlaceLookup($oDB);
$oPlaceLookup->setIncludeAddressDetails(true);
$oPlaceLookup->setLanguagePreference(array('en'));
echo 'Warm reverse: ';
if ($bVerbose) {
echo "\n";
}
for ($i = 0; $i < 1000; $i++) {
$fLat = rand(-9000, 9000) / 100;
$fLon = rand(-18000, 18000) / 100;
if ($bVerbose) {
echo "$fLat, $fLon = ";
}
$oLookup = $oReverseGeocode->lookup($fLat, $fLon);
$aSearchResults = $oLookup ? $oPlaceLookup->lookup(array($oLookup->iId => $oLookup)) : null;
print_results($aSearchResults, $bVerbose);
}
echo "\n";
}
if (!$aResult['reverse-only']) {
$oGeocode = new Nominatim\Geocode($oDB);
echo 'Warm search: ';
if ($bVerbose) {
echo "\n";
}
$oTokenizer = new \Nominatim\Tokenizer($oDB);
$aWords = $oTokenizer->mostFrequentWords(1000);
$sSQL = 'SELECT word FROM word WHERE word is not null ORDER BY search_name_count DESC LIMIT 1000';
foreach ($aWords as $sWord) {
if ($bVerbose) {
echo "$sWord = ";
}
$oGeocode->setLanguagePreference(array('en'));
$oGeocode->setQuery($sWord);
$aSearchResults = $oGeocode->lookup();
print_results($aSearchResults, $bVerbose);
}
echo "\n";
}

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
require_once(CONST_LibDir.'/Shell.php');
@@ -106,7 +98,7 @@ function getCmdOpt($aArg, $aSpec, &$aResult, $bExitOnError = false, $bExitOnUnkn
showUsage($aSpec, $bExitOnError, 'Option \''.$aLine[0].'\' is missing');
}
if ($aCounts[$aLine[0]] > $aLine[3]) {
showUsage($aSpec, $bExitOnError, 'Option \''.$aLine[0].'\' is present too many times');
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;

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
require('Symfony/Component/Dotenv/autoload.php');

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
require_once('init.php');
require_once('cmd.php');

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
require_once('init.php');
require_once('ParameterParser.php');
@@ -26,7 +18,7 @@ function userError($sMsg)
function exception_handler_json($exception)
{
http_response_code($exception->getCode() == 0 ? 500 : $exception->getCode());
http_response_code($exception->getCode());
header('Content-type: application/json; charset=utf-8');
include(CONST_LibDir.'/template/error-json.php');
exit();
@@ -34,7 +26,7 @@ function exception_handler_json($exception)
function exception_handler_xml($exception)
{
http_response_code($exception->getCode() == 0 ? 500 : $exception->getCode());
http_response_code($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');

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
require_once(CONST_LibDir.'/lib.php');
require_once(CONST_LibDir.'/DB.php');

View File

@@ -1,17 +1,9 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
function loadSettings($sProjectDir)
{
@define('CONST_InstallDir', $sProjectDir);
// Temporary hack to set the directory via environment instead of
// 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', $_SERVER['NOMINATIM_CONFIGDIR']);
@@ -206,34 +198,24 @@ function parseLatLon($sQuery)
return array($sFound, $fQueryLat, $fQueryLon);
}
function addressRankToGeocodeJsonType($iAddressRank)
function closestHouseNumber($aRow)
{
if ($iAddressRank >= 29 && $iAddressRank <= 30) {
return 'house';
}
if ($iAddressRank >= 26 && $iAddressRank < 28) {
return 'street';
}
if ($iAddressRank >= 22 && $iAddressRank < 26) {
return 'locality';
}
if ($iAddressRank >= 17 && $iAddressRank < 22) {
return 'district';
}
if ($iAddressRank >= 13 && $iAddressRank < 17) {
return 'city';
}
if ($iAddressRank >= 10 && $iAddressRank < 13) {
return 'county';
}
if ($iAddressRank >= 5 && $iAddressRank < 10) {
return 'state';
}
if ($iAddressRank >= 4 && $iAddressRank < 5) {
return 'country';
$fHouse = $aRow['startnumber']
+ ($aRow['endnumber'] - $aRow['startnumber']) * $aRow['fraction'];
switch ($aRow['interpolationtype']) {
case 'odd':
$iHn = (int)($fHouse/2) * 2 + 1;
break;
case 'even':
$iHn = (int)(round($fHouse/2)) * 2;
break;
default:
$iHn = (int)(round($fHouse));
break;
}
return 'locality';
return max(min($aRow['endnumber'], $iHn), $aRow['startnumber']);
}
if (!function_exists('array_key_last')) {

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
function logStart(&$oDB, $sType = '', $sQuery = '', $aLanguageList = array())
@@ -78,7 +70,7 @@ function logEnd(&$oDB, $hLog, $iNumResults)
if (CONST_Log_DB) {
$aEndTime = explode('.', $fEndTime);
if (!isset($aEndTime[1])) {
if (!$aEndTime[1]) {
$aEndTime[1] = '0';
}
$sEndTime = date('Y-m-d H:i:s', $aEndTime[0]).'.'.$aEndTime[1];

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
function formatOSMType($sType, $bIncludeExternal = true)

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
function getOsm2pgsqlBinary()
{

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
// https://github.com/geocoders/geocodejson-spec/
@@ -36,10 +28,7 @@ if (empty($aPlace)) {
$aFilteredPlaces['properties']['geocoding']['osm_id'] = $aPlace['osm_id'];
}
$aFilteredPlaces['properties']['geocoding']['osm_key'] = $aPlace['class'];
$aFilteredPlaces['properties']['geocoding']['osm_value'] = $aPlace['type'];
$aFilteredPlaces['properties']['geocoding']['type'] = addressRankToGeocodeJsonType($aPlace['rank_address']);
$aFilteredPlaces['properties']['geocoding']['type'] = $aPlace['type'];
$aFilteredPlaces['properties']['geocoding']['accuracy'] = (int) $fDistance;
@@ -59,7 +48,7 @@ if (empty($aPlace)) {
}
if (isset($aPlace['asgeojson'])) {
$aFilteredPlaces['geometry'] = json_decode($aPlace['asgeojson'], true);
$aFilteredPlaces['geometry'] = json_decode($aPlace['asgeojson']);
} else {
$aFilteredPlaces['geometry'] = array(
'type' => 'Point',

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
$aFilteredPlaces = array();
@@ -65,7 +57,7 @@ if (empty($aPlace)) {
}
if (isset($aPlace['asgeojson'])) {
$aFilteredPlaces['geometry'] = json_decode($aPlace['asgeojson'], true);
$aFilteredPlaces['geometry'] = json_decode($aPlace['asgeojson']);
} else {
$aFilteredPlaces['geometry'] = array(
'type' => 'Point',

View File

@@ -1,12 +1,4 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
$aFilteredPlaces = array();
@@ -63,7 +55,7 @@ if (empty($aPlace)) {
}
if (isset($aPlace['asgeojson'])) {
$aFilteredPlaces['geojson'] = json_decode($aPlace['asgeojson'], true);
$aFilteredPlaces['geojson'] = json_decode($aPlace['asgeojson']);
}
if (isset($aPlace['assvg'])) {

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