Compare commits

..

9 Commits

Author SHA1 Message Date
Sarah Hoffmann
b3796b9e25 remove download instructions for country grid 2022-11-19 17:07:18 +01:00
Sarah Hoffmann
4efd5f6444 adapt to 4.1.1 release 2022-11-19 16:21:26 +01:00
Marc Tobias
75f2efaf49 Tiger install doc: add -refresh website- step 2022-11-19 16:18:35 +01:00
marc tobias
4f82a9a789 Documentation: remove year from TIGER filename 2022-11-19 16:18:15 +01:00
Mauricio Scheffer
ebfdee62d7 docs: fix links to rank docs 2022-11-19 16:18:06 +01:00
Sarah Hoffmann
912db1cbc4 docs: add types-psutil requirement 2022-11-19 16:17:47 +01:00
Sarah Hoffmann
456520750e Merge pull request #2827 from mtmail/docs-4.1.x
Documentation: Add missing wget to Ubuntu install instructions
2022-09-25 12:42:51 +02:00
marc tobias
2950fa6ad5 Documentation: Add missing wget to Ubuntu install instructions 2022-09-23 20:49:14 +02:00
Sarah Hoffmann
d259f01d62 adapt to 4.1.0 release 2022-08-05 15:30:06 +02:00
859 changed files with 32614 additions and 43894 deletions

View File

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

11
.flake8
View File

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

2
.github/FUNDING.yml vendored
View File

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

View File

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

View File

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

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

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

View File

@@ -1,10 +1,14 @@
name: 'Build Nominatim'
inputs:
dependencies:
description: 'Where to install dependencies from (pip/apt)'
ubuntu:
description: 'Version of Ubuntu to install on'
required: false
default: 'pip'
default: '20'
cmake-args:
description: 'Additional options to hand to cmake'
required: false
default: ''
runs:
using: "composite"
@@ -15,30 +19,28 @@ runs:
sudo rm -rf /opt/hostedtoolcache/go /opt/hostedtoolcache/CodeQL /usr/lib/jvm /usr/local/share/chromium /usr/local/lib/android
df -h
shell: bash
- name: Install general prerequisites
- name: Install prerequisites
run: |
sudo apt-get install -y -qq libspatialite-dev libsqlite3-mod-spatialite libicu-dev virtualenv python3-dev osm2pgsql
sudo apt-get install -y -qq libboost-system-dev libboost-filesystem-dev libexpat1-dev zlib1g-dev libbz2-dev libpq-dev libproj-dev libicu-dev
if [ "x$UBUNTUVER" == "x18" ]; then
pip3 install python-dotenv psycopg2==2.7.7 jinja2==2.8 psutil==5.4.2 pyicu osmium PyYAML==5.1 datrie
else
sudo apt-get install -y -qq python3-icu python3-datrie python3-pyosmium python3-jinja2 python3-psutil python3-psycopg2 python3-dotenv python3-yaml
fi
shell: bash
env:
UBUNTUVER: ${{ inputs.ubuntu }}
CMAKE_ARGS: ${{ inputs.cmake-args }}
- name: Install prerequisites from apt
- name: Configure
run: mkdir build && cd build && cmake $CMAKE_ARGS ../Nominatim
shell: bash
env:
CMAKE_ARGS: ${{ inputs.cmake-args }}
- name: Build
run: |
sudo apt-get install -y -qq python3-icu python3-datrie python3-jinja2 python3-psutil python3-dotenv python3-yaml python3-sqlalchemy python3-psycopg python3-asyncpg python3-mwparserfromhell
shell: bash
if: inputs.dependencies == 'apt'
- name: Setup virtual environment (for pip)
run: |
virtualenv venv
./venv/bin/pip install -U pip
shell: bash
if: inputs.dependencies == 'pip'
- name: Setup virtual environment (for apt)
run: |
virtualenv venv --system-site-packages
shell: bash
if: inputs.dependencies == 'apt'
- name: Build nominatim
run: ./venv/bin/pip install Nominatim/packaging/nominatim-{api,db}
make -j2 all
sudo make install
shell: bash
working-directory: build

View File

@@ -4,6 +4,9 @@ inputs:
postgresql-version:
description: 'Version of PostgreSQL to install'
required: true
postgis-version:
description: 'Version of Postgis to install'
required: true
runs:
using: "composite"
@@ -11,18 +14,19 @@ runs:
steps:
- name: Remove existing PostgreSQL
run: |
sudo /usr/share/postgresql-common/pgdg/apt.postgresql.org.sh -y
sudo apt-get purge -yq postgresql*
sudo 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-${PGVER}-postgis-3 postgresql-${PGVER}-postgis-3-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}
shell: bash
env:
PGVER: ${{ inputs.postgresql-version }}
POSTGISVER: ${{ inputs.postgis-version }}
- name: Adapt postgresql configuration
run: |

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@v4
- 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@v4
uses: actions/upload-artifact@v2
with:
name: full-source
path: nominatim-src.tar.bz2
@@ -37,108 +37,138 @@ jobs:
needs: create-archive
strategy:
matrix:
flavour: ["ubuntu-22", "ubuntu-24"]
ubuntu: [18, 20, 22]
include:
- flavour: ubuntu-22
ubuntu: 22
postgresql: 12
lua: '5.1'
dependencies: pip
python: '3.9'
- flavour: ubuntu-24
ubuntu: 24
postgresql: 18
lua: '5.3'
dependencies: apt
python: 'builtin'
- ubuntu: 18
postgresql: 9.6
postgis: 2.5
pytest: pytest
php: 7.2
- ubuntu: 20
postgresql: 13
postgis: 3
pytest: py.test-3
php: 7.4
- ubuntu: 22
postgresql: 14
postgis: 3
pytest: py.test-3
php: 8.1
runs-on: ubuntu-${{ matrix.ubuntu }}.04
steps:
- uses: actions/download-artifact@v4
- uses: actions/download-artifact@v2
with:
name: full-source
- name: Unpack Nominatim
run: tar xf nominatim-src.tar.bz2
- name: Setup PHP
uses: shivammathur/setup-php@v2
with:
php-version: ${{ matrix.php }}
tools: phpunit, phpcs, composer
ini-values: opcache.jit=disable
- uses: actions/setup-python@v2
with:
python-version: 3.6
if: matrix.ubuntu == 18
- uses: ./Nominatim/.github/actions/setup-postgresql
with:
postgresql-version: ${{ matrix.postgresql }}
postgis-version: ${{ matrix.postgis }}
- uses: ./Nominatim/.github/actions/build-nominatim
with:
dependencies: ${{ matrix.dependencies }}
ubuntu: ${{ matrix.ubuntu }}
- uses: actions/cache@v4
with:
path: |
/usr/local/bin/osm2pgsql
key: osm2pgsql-bin-22-1
if: matrix.ubuntu == '22'
- name: Install test prerequsites
run: sudo apt-get install -y -qq python3-pytest python3-behave
if: matrix.ubuntu == 20
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python }}
if: matrix.python != 'builtin'
- name: Install test prerequsites
run: pip3 install pylint pytest behave==1.2.6
if: ${{ (matrix.ubuntu == 18) || (matrix.ubuntu == 22) }}
- name: Compile osm2pgsql
run: |
if [ ! -f /usr/local/bin/osm2pgsql ]; then
sudo apt-get install -y -qq libboost-system-dev libboost-filesystem-dev libexpat1-dev zlib1g-dev libbz2-dev libpq-dev libproj-dev libicu-dev liblua${LUA_VERSION}-dev lua-dkjson nlohmann-json3-dev
mkdir osm2pgsql-build
cd osm2pgsql-build
git clone https://github.com/osm2pgsql-dev/osm2pgsql
mkdir build
cd build
cmake ../osm2pgsql
make
sudo make install
cd ../..
rm -rf osm2pgsql-build
else
sudo apt-get install -y -qq libexpat1 liblua${LUA_VERSION}
fi
if: matrix.ubuntu == '22'
env:
LUA_VERSION: ${{ matrix.lua }}
- name: Install test prerequsites
run: sudo apt-get install -y -qq python3-pytest
if: matrix.ubuntu == 22
- name: Install test prerequisites (apt)
run: sudo apt-get install -y -qq python3-pytest python3-pytest-asyncio uvicorn python3-falcon python3-aiosqlite python3-pyosmium
if: matrix.dependencies == 'apt'
- name: Install latest pylint/mypy
run: pip3 install -U pylint mypy types-PyYAML types-jinja2 types-psycopg2 types-psutil typing-extensions
- name: Install test prerequisites (pip)
run: ./venv/bin/pip install pytest-asyncio falcon starlette asgi_lifespan aiosqlite osmium uvicorn
if: matrix.dependencies == 'pip'
- name: Install test prerequisites
run: ./venv/bin/pip install pytest-bdd
- name: Install latest flake8
run: ./venv/bin/pip install -U flake8
- name: PHP linting
run: phpcs --report-width=120 .
working-directory: Nominatim
- name: Python linting
run: ../venv/bin/python -m flake8 src test/python test/bdd
run: pylint nominatim
working-directory: Nominatim
- name: Install mypy and typechecking info
run: ./venv/bin/pip install -U mypy types-PyYAML types-jinja2 types-psutil types-requests types-ujson types-Pygments typing-extensions
if: matrix.dependencies == 'pip'
- name: Python static typechecking
run: ../venv/bin/python -m mypy --strict --python-version 3.9 src
run: mypy --strict nominatim
working-directory: Nominatim
if: matrix.dependencies == 'pip'
- name: PHP unit tests
run: phpunit ./
working-directory: Nominatim/test/php
if: ${{ (matrix.ubuntu == 20) || (matrix.ubuntu == 22) }}
- name: Python unit tests
run: ../venv/bin/python -m pytest test/python
run: $PYTEST test/python
working-directory: Nominatim
env:
PYTEST: ${{ matrix.pytest }}
- name: BDD tests
run: |
../venv/bin/python -m pytest test/bdd --nominatim-purge
working-directory: Nominatim
behave -DREMOVE_TEMPLATE=1 -DBUILDDIR=$GITHUB_WORKSPACE/build --format=progress3
working-directory: Nominatim/test/bdd
legacy-test:
needs: create-archive
runs-on: ubuntu-20.04
steps:
- uses: actions/download-artifact@v2
with:
name: full-source
- name: Unpack Nominatim
run: tar xf nominatim-src.tar.bz2
- name: Setup PHP
uses: shivammathur/setup-php@v2
with:
php-version: 7.4
- uses: ./Nominatim/.github/actions/setup-postgresql
with:
postgresql-version: 13
postgis-version: 3
- name: Install Postgresql server dev
run: sudo apt-get install postgresql-server-dev-13
- uses: ./Nominatim/.github/actions/build-nominatim
with:
ubuntu: 20
cmake-args: -DBUILD_MODULE=on
- name: Install test prerequsites
run: sudo apt-get install -y -qq python3-behave
- name: BDD tests (legacy tokenizer)
run: |
behave -DREMOVE_TEMPLATE=1 -DBUILDDIR=$GITHUB_WORKSPACE/build -DTOKENIZER=legacy --format=progress3
working-directory: Nominatim/test/bdd
install:
runs-on: ubuntu-latest
@@ -146,16 +176,23 @@ jobs:
strategy:
matrix:
name: [Ubuntu-22, Ubuntu-24]
name: [Ubuntu-18, Ubuntu-20, Ubuntu-22]
include:
- name: Ubuntu-18
flavour: ubuntu
image: "ubuntu:18.04"
ubuntu: 18
install_mode: install-nginx
- name: Ubuntu-20
flavour: ubuntu
image: "ubuntu:20.04"
ubuntu: 20
install_mode: install-apache
- name: Ubuntu-22
flavour: ubuntu
image: "ubuntu:22.04"
ubuntu: 22
install_mode: install-apache
- name: Ubuntu-24
image: "ubuntu:24.04"
ubuntu: 24
install_mode: install-apache
container:
image: ${{ matrix.image }}
@@ -175,6 +212,14 @@ jobs:
apt-get install -y git sudo wget
ln -snf /usr/share/zoneinfo/$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: |
@@ -186,7 +231,7 @@ jobs:
OS: ${{ matrix.name }}
INSTALL_MODE: ${{ matrix.install_mode }}
- uses: actions/download-artifact@v4
- uses: actions/download-artifact@v2
with:
name: full-source
path: /home/nominatim
@@ -208,26 +253,18 @@ jobs:
mkdir data-env-reverse
working-directory: /home/nominatim
- name: Add nominatim to path
- name: Prepare import environment (CentOS)
run: |
sudo ln -s /home/nominatim/nominatim-venv/bin/nominatim /usr/local/bin/nominatim
- name: Need lua binary
run: |
sudo apt-get install -y lua5.4 lua-dkjson
sudo ln -s /usr/local/bin/nominatim /usr/bin/nominatim
echo NOMINATIM_DATABASE_WEBUSER="apache" > nominatim-project/.env
cp nominatim-project/.env data-env-reverse/.env
working-directory: /home/nominatim
if: matrix.flavour == 'centos'
- name: Print version
run: nominatim --version
working-directory: /home/nominatim/nominatim-project
- name: Print taginfo
run: lua ./nominatim-venv/lib/*/site-packages/nominatim_db/resources/lib-lua/taginfo.lua
working-directory: /home/nominatim
- name: Collect host OS information
run: nominatim admin --collect-os-info
working-directory: /home/nominatim/nominatim-project
- name: Import
run: nominatim import --osm-file ../test.pbf
working-directory: /home/nominatim/nominatim-project
@@ -244,12 +281,14 @@ jobs:
run: nominatim admin --warm
working-directory: /home/nominatim/nominatim-project
- name: Install osmium
run: |
/home/nominatim/nominatim-venv/bin/pip install osmium
- name: Prepare update (Ubuntu)
run: apt-get install -y python3-pip
shell: bash
if: matrix.flavour == 'ubuntu'
- name: Run update
run: |
pip3 install --user osmium
nominatim replication --init
NOMINATIM_REPLICATION_MAX_DIFF=1 nominatim replication --once
working-directory: /home/nominatim/nominatim-project
@@ -271,91 +310,3 @@ jobs:
- name: Clean up database (reverse-only import)
run: nominatim refresh --postcodes --word-tokens
working-directory: /home/nominatim/nominatim-project
install-no-superuser:
runs-on: ubuntu-24.04
needs: create-archive
steps:
- uses: actions/download-artifact@v4
with:
name: full-source
- name: Unpack Nominatim
run: tar xf nominatim-src.tar.bz2
- uses: ./Nominatim/.github/actions/setup-postgresql
with:
postgresql-version: 16
- uses: ./Nominatim/.github/actions/build-nominatim
- name: Prepare import environment
run: |
mv Nominatim/test/testdb/apidb-test-data.pbf test.pbf
rm -rf Nominatim
- name: Prepare Database
run: |
./venv/bin/nominatim import --prepare-database
- name: Create import user
run: |
sudo -u postgres createuser osm-import
psql -d nominatim -c "ALTER USER \"osm-import\" WITH PASSWORD 'osm-import'"
psql -d nominatim -c 'GRANT CREATE ON SCHEMA public TO "osm-import"'
- name: Run import
run: |
NOMINATIM_DATABASE_DSN="pgsql:host=127.0.0.1;dbname=nominatim;user=osm-import;password=osm-import" ./venv/bin/nominatim import --continue import-from-file --osm-file test.pbf
- name: Check full import
run: ./venv/bin/nominatim admin --check-database
migrate:
runs-on: ubuntu-24.04
needs: create-archive
steps:
- uses: actions/download-artifact@v4
with:
name: full-source
- name: Unpack Nominatim
run: tar xf nominatim-src.tar.bz2
- uses: ./Nominatim/.github/actions/setup-postgresql
with:
postgresql-version: 18
- name: Install Python dependencies
run: |
sudo apt-get install --no-install-recommends virtualenv osm2pgsql
- name: Install Nominatim master version
run: |
virtualenv master
cd Nominatim
../master/bin/pip install packaging/nominatim-db
- name: Install Nominatim from pypi
run: |
virtualenv release
./release/bin/pip install nominatim-db
- name: Import Nominatim database using release
run: |
./release/bin/nominatim import --osm-file Nominatim/test/testdb/apidb-test-data.pbf
./release/bin/nominatim add-data --file Nominatim/test/testdb/additional_api_test.data.osm
- name: Migrate to master version
run: |
./master/bin/nominatim admin --migrate
./release/bin/nominatim add-data --file Nominatim/test/testdb/additional_api_test.data.osm
codespell:
runs-on: ubuntu-latest
steps:
- uses: codespell-project/actions-codespell@v2
with:
only_warn: 1

4
.gitignore vendored
View File

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

4
.gitmodules vendored
View File

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

View File

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

18
.pylintrc Normal file
View File

@@ -0,0 +1,18 @@
[MASTER]
extension-pkg-whitelist=osmium
ignored-modules=icu,datrie
[MESSAGES CONTROL]
[TYPECHECK]
# closing added here because it sometimes triggers a false positive with
# 'with' statements.
ignored-classes=NominatimArgs,closing
# '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
good-names=i,x,y,fd,db,cc

287
CMakeLists.txt Normal file
View File

@@ -0,0 +1,287 @@
#-----------------------------------------------------------------------------
#
# CMake Config
#
# Nominatim
#
#-----------------------------------------------------------------------------
cmake_minimum_required(VERSION 3.0 FATAL_ERROR)
list(APPEND CMAKE_MODULE_PATH "${CMAKE_SOURCE_DIR}/cmake")
#-----------------------------------------------------------------------------
#
# Project version
#
#-----------------------------------------------------------------------------
project(nominatim)
set(NOMINATIM_VERSION_MAJOR 4)
set(NOMINATIM_VERSION_MINOR 1)
set(NOMINATIM_VERSION_PATCH 0)
set(NOMINATIM_VERSION "${NOMINATIM_VERSION_MAJOR}.${NOMINATIM_VERSION_MINOR}.${NOMINATIM_VERSION_PATCH}")
add_definitions(-DNOMINATIM_VERSION="${NOMINATIM_VERSION}")
# Setting GIT_HASH
find_package(Git)
if (GIT_FOUND)
execute_process(
COMMAND "${GIT_EXECUTABLE}" log -1 --format=%h
WORKING_DIRECTORY ${CMAKE_CURRENT_LIST_DIR}
OUTPUT_VARIABLE GIT_HASH
OUTPUT_STRIP_TRAILING_WHITESPACE
ERROR_QUIET
)
endif()
#-----------------------------------------------------------------------------
# Configuration
#-----------------------------------------------------------------------------
set(BUILD_IMPORTER on CACHE BOOL "Build everything for importing/updating the database")
set(BUILD_API on CACHE BOOL "Build everything for the API server")
set(BUILD_MODULE off CACHE BOOL "Build PostgreSQL module for legacy tokenizer")
set(BUILD_TESTS on CACHE BOOL "Build test suite")
set(BUILD_DOCS on CACHE BOOL "Build documentation")
set(BUILD_MANPAGE on CACHE BOOL "Build Manual Page")
set(BUILD_OSM2PGSQL on CACHE BOOL "Build osm2pgsql (expert only)")
set(INSTALL_MUNIN_PLUGINS on CACHE BOOL "Install Munin plugins for supervising Nominatim")
#-----------------------------------------------------------------------------
# osm2pgsql (imports/updates only)
#-----------------------------------------------------------------------------
if (BUILD_IMPORTER AND BUILD_OSM2PGSQL)
if (NOT EXISTS "${CMAKE_SOURCE_DIR}/osm2pgsql/CMakeLists.txt")
message(FATAL_ERROR "The osm2pgsql directory is empty.\
Did you forget to check out Nominatim recursively?\
\nTry updating submodules with: git submodule update --init")
endif()
set(BUILD_TESTS_SAVED "${BUILD_TESTS}")
set(BUILD_TESTS off)
set(WITH_LUA off CACHE BOOL "")
add_subdirectory(osm2pgsql)
set(BUILD_TESTS ${BUILD_TESTS_SAVED})
endif()
#-----------------------------------------------------------------------------
# python (imports/updates only)
#-----------------------------------------------------------------------------
if (BUILD_IMPORTER)
find_package(PythonInterp 3.6 REQUIRED)
endif()
#-----------------------------------------------------------------------------
# PHP
#-----------------------------------------------------------------------------
# Setting PHP binary variable as to command line (prevailing) or auto detect
if (BUILD_API OR BUILD_IMPORTER)
if (NOT PHP_BIN)
find_program (PHP_BIN php)
endif()
# sanity check if PHP binary exists
if (NOT EXISTS ${PHP_BIN})
message(FATAL_ERROR "PHP binary not found. Install php or provide location with -DPHP_BIN=/path/php ")
else()
message (STATUS "Using PHP binary " ${PHP_BIN})
endif()
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()
#-----------------------------------------------------------------------------
# import scripts and utilities (importer only)
#-----------------------------------------------------------------------------
if (BUILD_IMPORTER)
find_file(COUNTRY_GRID_FILE country_osm_grid.sql.gz
PATHS ${PROJECT_SOURCE_DIR}/data
NO_DEFAULT_PATH
DOC "Location of the country grid file."
)
if (NOT COUNTRY_GRID_FILE)
message(FATAL_ERROR "\nYou need to download the country_osm_grid first:\n"
" wget -O ${PROJECT_SOURCE_DIR}/data/country_osm_grid.sql.gz https://www.nominatim.org/data/country_grid.sql.gz")
endif()
configure_file(${PROJECT_SOURCE_DIR}/cmake/tool.tmpl
${PROJECT_BINARY_DIR}/nominatim)
endif()
#-----------------------------------------------------------------------------
# Tests
#-----------------------------------------------------------------------------
if (BUILD_TESTS)
include(CTest)
set(TEST_BDD db osm2pgsql api)
find_program(PYTHON_BEHAVE behave)
find_program(PYLINT NAMES pylint3 pylint)
find_program(PYTEST NAMES pytest py.test-3 py.test)
find_program(PHPCS phpcs)
find_program(PHPUNIT phpunit)
if (PYTHON_BEHAVE)
message(STATUS "Using Python behave binary ${PYTHON_BEHAVE}")
foreach (test ${TEST_BDD})
add_test(NAME bdd_${test}
COMMAND ${PYTHON_BEHAVE} ${test}
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}/test/bdd)
set_tests_properties(bdd_${test}
PROPERTIES ENVIRONMENT "NOMINATIM_DIR=${PROJECT_BINARY_DIR}")
endforeach()
else()
message(WARNING "behave not found. BDD tests disabled." )
endif()
if (PHPUNIT)
message(STATUS "Using phpunit binary ${PHPUNIT}")
add_test(NAME php
COMMAND ${PHPUNIT} ./
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}/test/php)
else()
message(WARNING "phpunit not found. PHP unit tests disabled." )
endif()
if (PHPCS)
message(STATUS "Using phpcs binary ${PHPCS}")
add_test(NAME phpcs
COMMAND ${PHPCS} --report-width=120 --colors lib-php
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})
else()
message(WARNING "phpcs not found. PHP linting tests disabled." )
endif()
if (PYLINT)
message(STATUS "Using pylint binary ${PYLINT}")
add_test(NAME pylint
COMMAND ${PYLINT} nominatim
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})
else()
message(WARNING "pylint not found. Python linting tests disabled.")
endif()
if (PYTEST)
message(STATUS "Using pytest binary ${PYTEST}")
add_test(NAME pytest
COMMAND ${PYTEST} test/python
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})
else()
message(WARNING "pytest not found. Python tests disabled." )
endif()
endif()
#-----------------------------------------------------------------------------
# Postgres module
#-----------------------------------------------------------------------------
if (BUILD_MODULE)
add_subdirectory(module)
endif()
#-----------------------------------------------------------------------------
# Documentation
#-----------------------------------------------------------------------------
if (BUILD_DOCS)
add_subdirectory(docs)
endif()
#-----------------------------------------------------------------------------
# Manual page
#-----------------------------------------------------------------------------
if (BUILD_MANPAGE)
add_subdirectory(man)
endif()
#-----------------------------------------------------------------------------
# Installation
#-----------------------------------------------------------------------------
include(GNUInstallDirs)
set(NOMINATIM_DATADIR ${CMAKE_INSTALL_FULL_DATADIR}/${PROJECT_NAME})
set(NOMINATIM_LIBDIR ${CMAKE_INSTALL_FULL_LIBDIR}/${PROJECT_NAME})
set(NOMINATIM_CONFIGDIR ${CMAKE_INSTALL_FULL_SYSCONFDIR}/${PROJECT_NAME})
set(NOMINATIM_MUNINDIR ${CMAKE_INSTALL_FULL_DATADIR}/munin/plugins)
if (BUILD_IMPORTER)
configure_file(${PROJECT_SOURCE_DIR}/cmake/tool-installed.tmpl installed.bin)
install(PROGRAMS ${PROJECT_BINARY_DIR}/installed.bin
DESTINATION ${CMAKE_INSTALL_BINDIR}
RENAME nominatim)
install(DIRECTORY nominatim
DESTINATION ${NOMINATIM_LIBDIR}/lib-python
FILES_MATCHING PATTERN "*.py"
PATTERN __pycache__ EXCLUDE)
install(DIRECTORY lib-sql DESTINATION ${NOMINATIM_LIBDIR})
install(FILES ${COUNTRY_GRID_FILE}
data/words.sql
DESTINATION ${NOMINATIM_DATADIR})
endif()
if (BUILD_OSM2PGSQL)
if (${CMAKE_VERSION} VERSION_LESS 3.13)
# Installation of subdirectory targets was only introduced in 3.13.
# So just copy the osm2pgsql file for older versions.
install(PROGRAMS ${PROJECT_BINARY_DIR}/osm2pgsql/osm2pgsql
DESTINATION ${NOMINATIM_LIBDIR})
else()
install(TARGETS osm2pgsql RUNTIME DESTINATION ${NOMINATIM_LIBDIR})
endif()
endif()
if (BUILD_MODULE)
install(PROGRAMS ${PROJECT_BINARY_DIR}/module/nominatim.so
DESTINATION ${NOMINATIM_LIBDIR}/module)
endif()
if (BUILD_API)
install(DIRECTORY lib-php DESTINATION ${NOMINATIM_LIBDIR})
endif()
install(FILES settings/env.defaults
settings/address-levels.json
settings/phrase-settings.json
settings/import-admin.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
munin/nominatim_query_speed
munin/nominatim_requests
DESTINATION ${NOMINATIM_MUNINDIR})
endif()

View File

@@ -30,19 +30,6 @@ feature pull requests. If you plan to make larger changes, please open
an issue first or comment on the appropriate issue already existing so
that duplicate work can be avoided.
### Using AI-assisted code generators
PRs that include AI-generated content, may that be in code, in the PR
description or in documentation need to
1. clearly mark the AI-generated sections as such, for example, by
mentioning all use of AI in the PR description, and
2. include proof that you have run the generated code on an actual
installation of Nominatim. Adding and excuting tests will not be
sufficient. You need to show that the code actually solves the problem
the PR claims to solve.
## Coding style
Nominatim historically hasn't followed a particular coding style but we
@@ -59,11 +46,14 @@ are in process of consolidating the style. The following rules apply:
* no spaces after opening and before closing bracket
* leave out space between a function name and bracket
but add one between control statement(if, while, etc.) and bracket
* for PHP variables use CamelCase with a prefixing letter indicating the type
(i - integer, f - float, a - array, s - string, o - object)
The coding style is enforced with flake8. It can be tested with:
The coding style is enforced with PHPCS and pylint. It can be tested with:
```
make lint
phpcs --report-width=120 --colors .
pylint3 --extension-pkg-whitelist=osmium nominatim
```
## Testing
@@ -71,47 +61,6 @@ make lint
Before submitting a pull request make sure that the tests pass:
```
make tests
cd build
make test
```
## Releases
Nominatim follows semantic versioning. Major releases are done for large changes
that require (or at least strongly recommend) a reimport of the databases.
Minor releases can usually be applied to existing databases. Patch releases
contain bug fixes only and are released from a separate branch where the
relevant changes are cherry-picked from the master branch.
Checklist for releases:
* [ ] increase versions in
* `src/nominatim_api/version.py`
* `src/nominatim_db/version.py`
* [ ] update `ChangeLog` (copy information from patch releases from release branch)
* [ ] complete `docs/admin/Migration.md`
* [ ] update EOL dates in `SECURITY.md`
* [ ] commit and make sure CI tests pass
* [ ] update OSMF production repo and release new version -post1 there
* [ ] test migration
* download, build and import previous version
* migrate using master version
* run updates using master version
* [ ] prepare tarball:
* `git clone https://github.com/osm-search/Nominatim` (switch to right branch!)
* `rm -r .git*`
* copy country data into `data/`
* add version to base directory and package
* [ ] upload tarball to https://nominatim.org
* [ ] prepare documentation
* check out new docs branch
* change git checkout instructions to tarball download instructions or adapt version on existing ones
* build documentation and copy to https://github.com/osm-search/nominatim-org-site
* add new version to history
* [ ] check release tarball
* download tarball as per new documentation instructions
* compile and import Nominatim
* run `nominatim --version` to confirm correct version
* [ ] tag new release and add a release on github.com
* [ ] build pip packages and upload to pypi
* `make build`
* `twine upload dist/*`

557
COPYING
View File

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

258
ChangeLog
View File

@@ -1,243 +1,3 @@
5.2.0
* increase minimum required Python to 3.9
* index and output entrances of buildings and areas (thanks @emlove)
* name tags used for creating display names are now configurable
(thanks @astridx)
* new pattern-replacement query preprocessor (thanks @TuringVerified)
* special phrases can now be filtered by presence of tags (thanks @anqixxx)
* lua import style now always includes tags required by Nominatim
* improved query time reporting and logging
* improve word matching for languages with no word boundaries
* POIs with addresses inherited from surrounding building are no
longer returned in the address layer
* avoid creating a directory for the tokenizer when not needed
* replace behave with pytest-bdd for BDD testing
* refactoring and performance improvements to query parsing
* various smaller updates to styles
* remove English as default language for South Korea
* remove Japanese word variants
* updated country names for Norwegians (thanks @Johannes-Andersen)
* remove support for deprecated osm2pgsql gazetteer style
* fix updating of importances (also needs to update search_name table)
* fix query for deletable endpoint to use index again
* fix reindexing of contained places when a boundary is deleted and reinstated
* fix difference computation error when updating postcodes
* bracket handling sanitizer no longer strips bracket terms in the middle of
name
* reduce precision of stored coordinates to 7-digits everywhere
* avoid ST_Relate as it seems buggy on some systems
* remove setting for logging queries in DB, no longer functional
* postcode updates no longer require a project directory (needed for tests)
* refactor locale handling code (thanks @anqixxx)
* code updates for newer Python (thanks @emmanuel-ferdman)
* better test coverage (thanks @asharmalik19)
* various fixes and improvements to documentation
(thanks @anqixxx, @dave-meyer, @hasandiwan)
5.1.0
* replace datrie with simple internal trie implementation
* add pattern-based postcode parser for queries,
postcodes no longer need to be present in OSM to be found
* take variants into account when computing token similarity
* add extratags output to geocodejson format
* fix default layer setting used for structured queries
* update abbreviation lists for Russian and English
(thanks @shoorick, @IvanShift, @mhsrn21)
* fix variant generation for Norwegian
* fix normalization around space-like characters
* improve postcode search and handling of postcodes in queries
* reorganise internal query structure and get rid of slow enums
* enable code linting for tests
* various code moderinsations in test code (thanks @eumiro)
* remove setting osm2pgsql location via config.lib_dir
* make SQL functions parallel save as far as possible (thanks @otbutz)
* various fixes and improvements to documentation (thanks @TuringVerified)
5.0.0
* increase required versions for PostgreSQL (12+), PostGIS (3.0+)
* remove installation via cmake and debundle osm2pgsql
* remove deprecated PHP frontend
* remove deprecated legacy tokenizer
* add configurable pre-processing of queries
* add query pre-processor to split up Japanese addresses
* rewrite of osm2pgsql style implementation
(also adds support for osm2pgsql-themepark)
* reduce the number of SQL queries needed to complete a 'lookup' call
* improve computation of centroid for lines with only two points
* improve bbox output for postcode areas
* improve result order by returning the largest object when other things are
equal
* add fallback for reverse geocoding to default country tables
* exclude postcode areas from reverse geocoding
* disable search endpoint when database is reverse-only (regression)
* minor performance improvements to area split algorithm
* switch table and index creation to use autocommit mode to avoid deadlocks
* drop overly long ways during import
* restrict automatic migrations to versions 4.3+
* switch linting from pylint to flake8
* switch tests to use a wikimedia test file in the new CSV style
* various fixes and improvements to documentation
4.5.0
* allow building Nominatim as a pip package
* make osm2pgsql building optional
* switch importer to psycopg3
* allow output format of web search to be customized in self-installations
* look up potential postcode areas for postcode results
* add word usage statistics for address terms
* implement more light-weight CSV format for wiki importance tables
* rewrite SQL for place search to use window functions
* increase search radius when filtering by postcode
* prefer POI points over POI areas
* reintroduce full terms for address terms in search_name table
* reindex postcodes when their parent is deleted
* indexing: precompute counts of affected rows
* ensure consistent country assignments for overlapping countries
* make Nominatim[Async]API context manager to ensure proper calling of
close()
* make usage of project dir optional for library
* drop interpolations when no parent can be found
* style tweaks to reflect OSM usage (man_made, highway and others)
* deprecation of: bundled osm2pgsql, legacy tokenizer, PHP frontend
* make documentation buildable without CMake
* various fixes and improvements to documentation
4.4.1
* fix geocodejson output: admin level output should only print boundaries
* updating: restrict invalidation of child objects on large street features
* restrict valid interpolation house numbers to 0-999999
* fix import error when SQLAlchemy 1.4 and psycopg3 are installed
* various typo fixes in the documentation
4.4.0
* add export to SQLite database and SQLite support for the frontend
* switch to Python frontend as the default frontend
* update to osm2pgsql 1.11.0
* add support for new osm2pgsql middle table format
* simplify geometry for large polygon objects not used in addresses
* various performance tweaks for search in Python frontend
* fix regression in search with categories where it was confused with near
search
* partially roll back use of SQLAlchemy lambda statements due to bugs
in SQLAlchemy
* fix handling of timezones for timestamps from the database
* fix handling of full address searches in connection with a viewbox
* fix postcode computation of highway areas
* fix handling of timeout errors for Python <= 3.10
* fix address computation for postcode areas
* fix variable shadowing in osm2pgsql flex script, causing bugs with LuaJIT
* make sure extratags are always null when empty
* reduce importance of places without wikipedia reference
* improve performance of word count computations
* drop support for wikipedia tags with full URLs
* replace get_addressdata() SQL implementation with a Python function
* improve display name for non-address features
* fix postcode validation for postcodes with country code
(thanks @pawel-wroniszewski)
* add possibility to run imports without superuser database rights
(thanks @robbe-haesendonck)
* new CLI command for cleaning deleted relations (thanks @lujoh)
* add check for database version in the CLI check command
* updates to import styles ignoring more unused objects
* various typo fixes (thanks @kumarUjjawal)
4.3.2
* fix potential SQL injection issue for 'nominatim admin --collect-os-info'
* PHP frontend: fix on-the-fly lookup of postcode areas near boundaries
* Python frontend: improve handling of viewbox
* Python frontend: correct deployment instructions
4.3.1
* reintroduce result rematching
* improve search of multi-part names
* fix accidentally switched meaning of --reverse-only and --search-only in
warm command
4.3.0
* fix failing importance recalculation command
* fix merging of linked names into unnamed boundaries
* fix a number of corner cases with interpolation splitting resulting in
invalid geometries
* fix failure in website generation when password contains curly brackets
* fix broken use of ST_Project in PostGIS 3.4
* new NOMINATIM_SEARCH_WITHIN_COUNTRIES setting to restrict reverse lookups
to known countries (thanks @alfmarcua)
* allow negative OSM IDs (thanks @alfmarcua)
* disallow import of Tiger data in a frozen DB
* avoid UPDATE to change settings to be compatible with r/o DBs (thanks @t-tomek)
* update bundled osm2pgsql to 1.9.2
* reorganise osm2pgsql flex style and make it the default
* exclude names ending in :wikipedia from indexing
* no longer accept comma as a list separator in name tags
* process forward dependencies on update to catch updates in geometries
of ways and relations
* fix handling of isolated silent letters during transliteration
* no longer assign postcodes to large linear features like rivers
* introduce nominatim.paths module for finding data and libraries
* documentation layout changed to material theme
* new documentation section for library
* various smaller fixes to existing documentation
(thanks @woodpeck, @bloom256, @biswajit-k)
* updates to vagrant install scripts, drop support for Ubuntu 18
(thanks @n-timofeev)
* removed obsolete configuration variables from env.defaults
* add script for generating a taginfo description (thanks @biswajit-k)
* modernize Python code around BDD test and add testing of Python frontend
* lots of new BDD tests for API output
4.2.3
* fix deletion handling for 'nominatim add-data'
* adapt place_force_delete() to new deletion handling
* flex style: avoid dropping of postcode areas
* fix update errors on address interpolation handling
4.2.2
* extend flex-style library to fully support all default styles
* fix handling of Hebrew aleph
* do not assign postcodes to rivers
* fix string matching in PHP code
* update osm2pgsql (various updates to flex)
* fix slow query when deleting places on update
* fix CLI details query
* fix recalculation of importance values
* fix polygon simplification in reverse results
* add class/type information to reverse geocodejson result
* minor improvements to default tokenizer configuration
* various smaller fixes to documentation
4.2.1
* fix XSS vulnerability in debug view
4.2.0
* 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
@@ -274,10 +34,6 @@
* 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
@@ -316,10 +72,6 @@
* 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
@@ -395,7 +147,7 @@
* increase splitting for large geometries to improve indexing speed
* remove deprecated get_magic_quotes_gpc() function
* make sure that all postcodes have an entry in word and are thus searchable
* remove use of ST_Covers in conjunction with ST_Intersects,
* remove use of ST_Covers in conjunction woth ST_Intersects,
causes bad query planning and slow updates in Postgis3
* update osm2pgsql
@@ -452,7 +204,7 @@
* exclude postcode ranges separated by colon from centre point calculation
* update osm2pgsql, better handling of imports without flatnode file
* switch to more efficient algorithm for word set computation
* use only boundaries for country and state parts of addresses
* use only boundries for country and state parts of addresses
* improve updates of addresses with housenumbers and interpolations
* remove country from place_addressline table and use country_code instead
* optimise indexes on search_name partition tables
@@ -491,7 +243,7 @@
* complete rewrite of reverse search algorithm
* add new geojson and geocodejson output formats
* add simple export script to export addresses to CSV
* add simple export script to exprot addresses to CSV
* remove is_in terms from address computation
* remove unused search_name_country tables
* various smaller fixes to query parsing
@@ -556,7 +308,7 @@
* move installation documentation into this repo
* add self-documenting vagrant scripts
* remove --create-website, recommend to use website directory in build
* add accessor functions for URL parameters and improve error checking
* add accessor functions for URL parameters and improve erro checking
* remove IP blocking and rate-limiting code
* enable CI via travis
* reformatting for more consistent coding style
@@ -567,7 +319,7 @@
* update to refactored osm2pgsql which use libosmium based types
* switch from osmosis to pyosmium for updates
* be more strict when matching against special search terms
* handle postcode entries with multiple values correctly
* handle postcode entries with mutliple values correctly
2.5

View File

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

View File

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

View File

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

View File

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

View File

@@ -9,11 +9,10 @@ versions.
| Version | End of support for security updates |
| ------- | ----------------------------------- |
| 5.2.x | 2027-10-29 |
| 5.1.x | 2027-04-01 |
| 5.0.x | 2027-02-06 |
| 4.5.x | 2026-09-12 |
| 4.4.x | 2026-03-07 |
| 4.0.x | 2023-11-02 |
| 3.7.x | 2023-04-05 |
| 3.6.x | 2022-12-12 |
| 3.5.x | 2022-06-05 |
## Reporting a Vulnerability
@@ -32,10 +31,9 @@ description of the nature and severity of the issue. **
Patches for identified security issues are applied to all affected versions and
new minor versions are released. At the same time we release a statement at
the [Nominatim blog](https://nominatim.org/blog/) describing the nature of the
incident.
incident. Announcements will also be published at the
[geocoding mailinglist](https://lists.openstreetmap.org/listinfo/geocoding).
## List of Previous Incidents
* 2023-11-20 - [SQL injection vulnerability](https://nominatim.org/2023/11/20/release-432.html)
* 2023-02-21 - [cross-site scripting vulnerability](https://nominatim.org/2023/02/21/release-421.html)
* 2020-05-04 - [SQL injection issue on /details endpoint](https://lists.openstreetmap.org/pipermail/geocoding/2020-May/002012.html)

View File

@@ -1,6 +1,6 @@
# Install Nominatim in a virtual machine for development and testing
This document describes how you can install Nominatim inside a Ubuntu 24
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.
@@ -15,22 +15,29 @@ is.
2. [Vagrant](https://www.vagrantup.com/downloads.html)
3. Nominatim
3. Nominatim
git clone --recursive https://github.com/openstreetmap/Nominatim.git
If you forgot `--recursive`, it you can later load the submodules using
git submodule init
git submodule update
git clone https://github.com/openstreetmap/Nominatim.git
## Installation
1. Start the virtual machine
vagrant up ubuntu24-nginx
vagrant up ubuntu
2. Log into the virtual machine
vagrant ssh ubuntu24-nginx
vagrant ssh ubuntu
3. Import a small country (Monaco)
See the FAQ how to skip this step and point Nominatim to an existing database.
```
@@ -54,44 +61,91 @@ see Nominatim in action on [localhost:8089](http://localhost:8089/nominatim/).
You edit code on your host machine in any editor you like. There is no need to
restart any software: just refresh your browser window.
Use the functions of the `log()` object to create temporary debug output.
Add `&debug=1` to the URL to see the output.
Note that the webserver uses files from the /build directory. If you change
files in Nominatim/website or Nominatim/utils for example you first need to
copy them into the /build directory by running the `cmake` step from the
installation.
PHP errors are written to `/var/log/apache2/error.log`.
With `echo` and `var_dump()` you write into the output (HTML/XML/JSON) when
you either add `&debug=1` to the URL (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.
For more information on running tests, see
https://nominatim.org/release-docs/develop/develop/Testing/
## Running unit tests
cd ~/Nominatim/tests/php
phpunit ./
## Running PHP code style tests
cd ~/Nominatim
phpcs --colors .
## Running functional tests
Tests in `test/bdd/db` and `test/bdd/osm2pgsql` have to pass 100%. Other
tests might require full planet-wide data. Sadly even if you have your own
planet-wide data there will be enough differences to the openstreetmap.org
installation to cause false positives in the other tests (see FAQ).
To run the full test suite
cd ~/Nominatim/test/bdd
behave -DBUILDDIR=/home/vagrant/build/ db osm2pgsql
To run a single file
behave -DBUILDDIR=/home/vagrant/build/ api/lookup/simple.feature
Or a single test by line number
behave -DBUILDDIR=/home/vagrant/build/ api/lookup/simple.feature:34
To run specific groups of tests you can add tags just before the `Scenario line`, e.g.
@bug-34
Scenario: address lookup for non-existing or invalid node, way, relation
and then
behave -DBUILDDIR=/home/vagrant/build/ --tags @bug-34
## FAQ
##### Will it run on Windows?
Yes, Vagrant and Virtualbox can be installed on MS Windows just fine. You need
a 64bit version of Windows.
Yes, Vagrant and Virtualbox can be installed on MS Windows just fine. You need a 64bit
version of Windows.
##### Will it run on Apple Silicon?
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?
Of course! The Monaco import takes less than 10 minutes and works with 2GB RAM.
Of course! The Monaco import takes less than 30 minutes and works with 2GB RAM.
##### Will the results be the same as those from nominatim.openstreetmap.org?
No. Long-running Nominatim installations will differ once new import features (or
No. Long running Nominatim installations will differ once new import features (or
bug fixes) get added since those usually only get applied to new/changed data.
Also this document skips the optional Wikipedia data import which affects ranking
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.
@@ -100,17 +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
@@ -118,15 +169,18 @@ 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"?
Yes. It's possible to start the virtual machine on [Amazon AWS (plugin)](https://github.com/mitchellh/vagrant-aws)
or [DigitalOcean (plugin)](https://github.com/smdahlen/vagrant-digitalocean).

78
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
@@ -34,77 +26,85 @@ Vagrant.configure("2") do |config|
end
end
config.vm.provider "parallels" do |prl, override|
prl.update_guest_tools = false
prl.memory = 2048
if ENV['CHECKOUT'] != 'y' then
override.vm.synced_folder ".", "/home/vagrant/Nominatim"
end
end
config.vm.provider "libvirt" do |lv, override|
lv.memory = 2048
lv.nested = true
if ENV['CHECKOUT'] != 'y' then
override.vm.synced_folder ".", "/home/vagrant/Nominatim", type: 'nfs', nfs_udp: false
override.vm.synced_folder ".", "/home/vagrant/Nominatim", type: 'nfs'
end
end
config.vm.define "ubuntu22", primary: true do |sub|
sub.vm.box = "generic/ubuntu2204"
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-22.sh"
s.path = "vagrant/Install-on-Ubuntu-20.sh"
s.privileged = false
s.args = [checkout]
end
end
config.vm.define "ubuntu22-apache" do |sub|
sub.vm.box = "generic/ubuntu2204"
config.vm.define "ubuntu-apache" do |sub|
sub.vm.box = "generic/ubuntu2004"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Ubuntu-22.sh"
s.path = "vagrant/Install-on-Ubuntu-20.sh"
s.privileged = false
s.args = [checkout, "install-apache"]
end
end
config.vm.define "ubuntu22-nginx" do |sub|
sub.vm.box = "generic/ubuntu2204"
config.vm.define "ubuntu-nginx" do |sub|
sub.vm.box = "generic/ubuntu2004"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Ubuntu-22.sh"
s.path = "vagrant/Install-on-Ubuntu-20.sh"
s.privileged = false
s.args = [checkout, "install-nginx"]
end
end
config.vm.define "ubuntu24" do |sub|
sub.vm.box = "bento/ubuntu-24.04"
if RUBY_PLATFORM.include?('darwin') && RUBY_PLATFORM.include?('arm64')
# Apple M processor
sub.vm.box = 'gutehall/ubuntu24-04'
end
config.vm.define "ubuntu18" do |sub|
sub.vm.box = "generic/ubuntu1804"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Ubuntu-24.sh"
s.path = "vagrant/Install-on-Ubuntu-18.sh"
s.privileged = false
s.args = [checkout]
end
end
config.vm.define "ubuntu24-apache" do |sub|
sub.vm.box = "bento/ubuntu-24.04"
config.vm.define "ubuntu18-apache" do |sub|
sub.vm.box = "generic/ubuntu1804"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Ubuntu-24.sh"
s.path = "vagrant/Install-on-Ubuntu-18.sh"
s.privileged = false
s.args = [checkout, "install-apache"]
end
end
config.vm.define "ubuntu24-nginx" do |sub|
sub.vm.box = "bento/ubuntu-24.04"
config.vm.define "ubuntu18-nginx" do |sub|
sub.vm.box = "generic/ubuntu1804"
sub.vm.provision :shell do |s|
s.path = "vagrant/Install-on-Ubuntu-24.sh"
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

20
cmake/tool-installed.tmpl Normal file
View File

@@ -0,0 +1,20 @@
#!/usr/bin/env python3
import sys
import os
sys.path.insert(1, '@NOMINATIM_LIBDIR@/lib-python')
os.environ['NOMINATIM_NOMINATIM_TOOL'] = os.path.abspath(__file__)
from nominatim import cli
from nominatim import version
version.GIT_COMMIT_HASH = '@GIT_HASH@'
exit(cli.nominatim(module_dir='@NOMINATIM_LIBDIR@/module',
osm2pgsql_path='@NOMINATIM_LIBDIR@/osm2pgsql',
phplib_dir='@NOMINATIM_LIBDIR@/lib-php',
sqllib_dir='@NOMINATIM_LIBDIR@/lib-sql',
data_dir='@NOMINATIM_DATADIR@',
config_dir='@NOMINATIM_CONFIGDIR@',
phpcgi_path='@PHPCGI_BIN@'))

20
cmake/tool.tmpl Executable file
View File

@@ -0,0 +1,20 @@
#!/usr/bin/env python3
import sys
import os
sys.path.insert(1, '@CMAKE_SOURCE_DIR@')
os.environ['NOMINATIM_NOMINATIM_TOOL'] = os.path.abspath(__file__)
from nominatim import cli
from nominatim import version
version.GIT_COMMIT_HASH = '@GIT_HASH@'
exit(cli.nominatim(module_dir='@CMAKE_BINARY_DIR@/module',
osm2pgsql_path='@CMAKE_BINARY_DIR@/osm2pgsql/osm2pgsql',
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@'))

35
docs/CMakeLists.txt Normal file
View File

@@ -0,0 +1,35 @@
# Auto-generated vagrant install documentation
# build the actual documentation
configure_file(mkdocs.yml ../mkdocs.yml)
file(MAKE_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/appendix)
set (DOC_SOURCES
admin
develop
api
customize
index.md
extra.css
styles.css
)
foreach (src ${DOC_SOURCES})
execute_process(
COMMAND ${CMAKE_COMMAND} -E create_symlink ${CMAKE_CURRENT_SOURCE_DIR}/${src} ${CMAKE_CURRENT_BINARY_DIR}/${src}
)
endforeach()
ADD_CUSTOM_TARGET(doc
COMMAND ${CMAKE_CURRENT_SOURCE_DIR}/bash2md.sh ${PROJECT_SOURCE_DIR}/vagrant/Install-on-Ubuntu-18.sh ${CMAKE_CURRENT_BINARY_DIR}/appendix/Install-on-Ubuntu-18.md
COMMAND ${CMAKE_CURRENT_SOURCE_DIR}/bash2md.sh ${PROJECT_SOURCE_DIR}/vagrant/Install-on-Ubuntu-20.sh ${CMAKE_CURRENT_BINARY_DIR}/appendix/Install-on-Ubuntu-20.md
COMMAND ${CMAKE_CURRENT_SOURCE_DIR}/bash2md.sh ${PROJECT_SOURCE_DIR}/vagrant/Install-on-Ubuntu-22.sh ${CMAKE_CURRENT_BINARY_DIR}/appendix/Install-on-Ubuntu-22.md
COMMAND PYTHONPATH=${PROJECT_SOURCE_DIR} mkdocs build -d ${CMAKE_CURRENT_BINARY_DIR}/../site-html -f ${CMAKE_CURRENT_BINARY_DIR}/../mkdocs.yml
)
ADD_CUSTOM_TARGET(serve-doc
COMMAND PYTHONPATH=${PROJECT_SOURCE_DIR} mkdocs serve
WORKING_DIRECTORY ${PROJECT_BINARY_DIR}
)

View File

@@ -5,35 +5,6 @@ your Nominatim database. It is assumed that you have already successfully
installed the Nominatim software itself, if not return to the
[installation page](Installation.md).
## Importing with a database user without superuser rights
Nominatim usually creates its own PostgreSQL database at the beginning of the
import process. This makes usage easier for the user but means that the
database user doing the import needs the appropriate rights.
If you prefer to run the import with a database user with limited rights,
you can do so by changing the import process as follows:
1. Run the command for database preparation with a database user with
superuser rights. For example, to use a db user 'dbadmin' for a
database 'nominatim', execute:
```
NOMINATIM_DATABASE_DSN="pgsql:dbname=nominatim;user=dbadmin" nominatim import --prepare-database
```
2. Grant the import user the right to create tables. For example, foe user 'import-user':
```
psql -d nominatim -c 'GRANT CREATE ON SCHEMA public TO "import-user"'
```
3. Now run the reminder of the import with the import user:
```
NOMINATIM_DATABASE_DSN="pgsql:dbname=nominatim;user=import-user" nominatim import --continue import-from-file --osm-file file.pbf
```
## Importing multiple regions (without updates)
To import multiple regions in your database you can simply give multiple
@@ -65,15 +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
```
@@ -127,17 +99,80 @@ 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
You can install Nominatim using a database that runs on a different server.
Simply point the configuration variable `NOMINATIM_DATABASE_DSN` to the
server and follow the standard import documentation.
You can install Nominatim using a database that runs on a different server when
you have physical access to the file system on the other server. Nominatim
uses a custom normalization library that needs to be made accessible to the
PostgreSQL server. This section explains how to set up the normalization
library.
!!! note
The external module is only needed when using the legacy tokenizer.
If you have chosen the ICU tokenizer, then you can ignore this section
and follow the standard import documentation.
### Option 1: Compiling the library on the database server
The most sure way to get a working library is to compile it on the database
server. From the prerequisites you need at least cmake, gcc and the
PostgreSQL server package.
Clone or unpack the Nominatim source code, enter the source directory and
create and enter a build directory.
```sh
cd Nominatim
mkdir build
cd build
```
Now configure cmake to only build the PostgreSQL module and build it:
```
cmake -DBUILD_IMPORTER=off -DBUILD_API=off -DBUILD_TESTS=off -DBUILD_DOCS=off -DBUILD_OSM2PGSQL=off ..
make
```
When done, you find the normalization library in `build/module/nominatim.so`.
Copy it to a place where it is readable and executable by the PostgreSQL server
process.
### Option 2: Compiling the library on the import machine
You can also compile the normalization library on the machine from where you
run the import.
!!! important
You can only do this when the database server and the import machine have
the same architecture and run the same version of Linux. Otherwise there is
no guarantee that the compiled library is compatible with the PostgreSQL
server running on the database server.
Make sure that the PostgreSQL server package is installed on the machine
**with the same version as on the database server**. You do not need to install
the PostgreSQL server itself.
Download and compile Nominatim as per standard instructions. Once done, you find
the normalization library in `build/module/nominatim.so`. Copy the file to
the database server at a location where it is readable and executable by the
PostgreSQL server process.
### Running the import
On the client side you now need to configure the import to point to the
correct location of the library **on the database server**. Add the following
line to your your `.env` file:
```php
NOMINATIM_DATABASE_MODULE_PATH="<directory on the database server where nominatim.so resides>"
```
Now change the `NOMINATIM_DATABASE_DSN` to point to your remote server and continue
to follow the [standard instructions for importing](Import.md).
The import will be faster, if the import is run directly from the database
machine. You can easily switch to a different machine for the query frontend
after the import.
## Moving the database to another machine
@@ -162,9 +197,20 @@ target machine.
data updates but the resulting database is only about a third of the size
of a full database.
Next install nominatim-api on the target machine by following the standard
installation instructions. Again, make sure to use the same version as the
source machine.
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.
Create a project directory on your destination machine and set up the `.env`
file to match the configuration on the source machine. That's all.
file to match the configuration on the source machine. Finally run
nominatim refresh --website
to make sure that the local installation of Nominatim will be used.
If you are using the legacy tokenizer you might also have to switch to the
PostgreSQL module that was compiled on your target machine. If you get errors
that PostgreSQL cannot find or access `nominatim.so` then rerun
nominatim refresh --functions
on the target machine to update the the location of the module.

View File

@@ -1,148 +0,0 @@
# Deploying the Nominatim Python frontend
Nominatim can be run as a Python-based
[ASGI web application](https://asgi.readthedocs.io/en/latest/). You have the
choice between [Falcon](https://falcon.readthedocs.io/en/stable/)
and [Starlette](https://www.starlette.io/) as the ASGI framework.
This section gives a quick overview on how to configure Nginx to serve
Nominatim. Please refer to the documentation of
[Nginx](https://nginx.org/en/docs/) for background information on how
to configure it.
!!! Note
Throughout this page, we assume your Nominatim project directory is
located in `/srv/nominatim-project`. If you have put it somewhere else,
you need to adjust the commands and configuration accordingly.
### Installing the required packages
The Nominatim frontend is best run from its own virtual environment. If
you have already created one for the database backend during the
[installation](Installation.md#building-nominatim), you can use that. Otherwise
create one now with:
```sh
sudo apt-get install virtualenv
virtualenv /srv/nominatim-venv
```
The Nominatim frontend is contained in the 'nominatim-api' package. To
install directly from the source tree run:
```sh
cd Nominatim
/srv/nominatim-venv/bin/pip install packaging/nominatim-api
```
The recommended way to deploy a Python ASGI application is to run
the ASGI runner [uvicorn](https://www.uvicorn.org/)
together with [gunicorn](https://gunicorn.org/) HTTP server. We use
Falcon here as the web framework.
Add the necessary packages to your virtual environment:
``` sh
/srv/nominatim-venv/bin/pip install falcon uvicorn gunicorn
```
### Setting up Nominatim as a systemd job
Next you need to set up the service that runs the Nominatim frontend. This is
easiest done with a systemd job.
First you need to tell systemd to create a socket file to be used by
hunicorn. Create the following file `/etc/systemd/system/nominatim.socket`:
``` systemd
[Unit]
Description=Gunicorn socket for Nominatim
[Socket]
ListenStream=/run/nominatim.sock
SocketUser=www-data
[Install]
WantedBy=multi-user.target
```
Now you can add the systemd service for Nominatim itself.
Create the following file `/etc/systemd/system/nominatim.service`:
``` systemd
[Unit]
Description=Nominatim running as a gunicorn application
After=network.target
Requires=nominatim.socket
[Service]
Type=simple
User=www-data
Group=www-data
WorkingDirectory=/srv/nominatim-project
ExecStart=/srv/nominatim-venv/bin/gunicorn -b unix:/run/nominatim.sock -w 4 -k uvicorn.workers.UvicornWorker "nominatim_api.server.falcon.server:run_wsgi()"
ExecReload=/bin/kill -s HUP $MAINPID
StandardOutput=append:/var/log/gunicorn-nominatim.log
StandardError=inherit
PrivateTmp=true
TimeoutStopSec=5
KillMode=mixed
[Install]
WantedBy=multi-user.target
```
This sets up gunicorn with 4 workers (`-w 4` in ExecStart). Each worker runs
its own Python process using
[`NOMINATIM_API_POOL_SIZE`](../customize/Settings.md#nominatim_api_pool_size)
connections to the database to serve requests in parallel.
Make the new services known to systemd and start it:
``` sh
sudo systemctl daemon-reload
sudo systemctl enable nominatim.socket
sudo systemctl start nominatim.socket
sudo systemctl enable nominatim.service
sudo systemctl start nominatim.service
```
This sets the service up, so that Nominatim is automatically started
on reboot.
### Configuring nginx
To make the service available to the world, you need to proxy it through
nginx. Add the following definition to the default configuration:
``` nginx
upstream nominatim_service {
server unix:/run/nominatim.sock fail_timeout=0;
}
server {
listen 80;
listen [::]:80;
root /var/www/html;
index /search;
location / {
proxy_set_header Host $http_host;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
proxy_redirect off;
proxy_pass http://nominatim_service;
}
}
```
Reload nginx with
```
sudo systemctl reload nginx
```
and you should be able to see the status of your server under
`http://localhost/status`.

148
docs/admin/Deployment.md Normal file
View File

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

View File

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

View File

@@ -14,15 +14,15 @@ to a single Nominatim setup: configuration, extra data, etc. Create a project
directory apart from the Nominatim software and change into the directory:
```
mkdir ~/nominatim-project
cd ~/nominatim-project
mkdir ~/nominatim-planet
cd ~/nominatim-planet
```
In the following, we refer to the project directory as `$PROJECT_DIR`. To be
able to copy&paste instructions, you can export the appropriate variable:
```
export PROJECT_DIR=~/nominatim-project
export PROJECT_DIR=~/nominatim-planet
```
The Nominatim tool assumes per default that the current working directory is
@@ -74,18 +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.csv.gz
wget -O secondary_importance.sql.gz https://nominatim.org/data/wikimedia-secondary-importance.sql.gz
wget https://www.nominatim.org/data/wikimedia-importance.sql.gz
The files are about 400MB and add around 4GB to the Nominatim database. For
more information about importance,
see [Importance Customization](../customize/Importance.md).
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 --secondary-importance --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
@@ -95,8 +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).
@@ -142,7 +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
@@ -156,7 +153,7 @@ if you plan to use the installation only for exports to a
[photon](https://photon.komoot.io/) database, then you can set up a database
without search indexes. Add `--reverse-only` to your setup command above.
This saves about 5% of disk space, import time won't be significant faster.
This saves about 5% of disk space.
### Filtering Imported Data
@@ -231,7 +228,7 @@ to load the OSM data into the PostgreSQL database. This step is very demanding
in terms of RAM usage. osm2pgsql and PostgreSQL are running in parallel at
this point. PostgreSQL blocks at least the part of RAM that has been configured
with the `shared_buffers` parameter during
[PostgreSQL tuning](Installation.md#tuning-the-postgresql-database)
[PostgreSQL tuning](Installation.md#postgresql-tuning)
and needs some memory on top of that. osm2pgsql needs at least 2GB of RAM for
its internal data structures, potentially more when it has to process very large
relations. In addition it needs to maintain a cache for node locations. The size
@@ -257,51 +254,26 @@ successfully.
nominatim admin --check-database
```
If you have installed the `nominatim-api` package, then you can try out
your installation by executing a simple query on the command line:
Now you can try out your installation by running:
``` 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, make sure you have installed
the right packages as per [Installation](Installation.md#software).
#### Testing the Python frontend
To run the test server against the Python frontend, you must choose a
web framework to use, either starlette or falcon. Make sure the appropriate
packages are installed. Then run
``` sh
```sh
nominatim serve
```
or, if you prefer to use Starlette instead of Falcon as webserver,
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`.
``` sh
nominatim serve --engine starlette
```
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`.
Go to `http://localhost:8088/status` and you should see the message `OK`.
You can also run a search query, e.g. `http://localhost:8088/search?q=Berlin`
or, for reverse-only installations a reverse query,
e.g. `http://localhost:8088/reverse?lat=27.1750090510034&lon=78.04209025`.
To run Nominatim via webservers like Apache or nginx, please read the
[Deployment chapter](Deployment.md).
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).
## Adding search through category phrases
## 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 +4,9 @@ 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 24.04](Install-on-Ubuntu-24.md)
* [Ubuntu 22.04](Install-on-Ubuntu-22.md)
* [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)
These OS-specific instructions can also be found in executable form
in the `vagrant/` directory.
@@ -22,38 +23,44 @@ and can't offer support.
### Software
!!! Warning
For larger installations you **must have** PostgreSQL 11+ and PostGIS 3+
otherwise import and queries will be slow to the point of being unusable.
Query performance has marked improvements with PostgreSQL 13+ and PostGIS 3.2+.
For compiling:
* [cmake](https://cmake.org/)
* [expat](https://libexpat.github.io/)
* [proj](https://proj.org/)
* [bzip2](http://www.bzip.org/)
* [zlib](https://www.zlib.net/)
* [ICU](http://site.icu-project.org/)
* [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) (12+ will work, 13+ strongly recommended)
* [PostGIS](https://postgis.net) (3.0+ will work, 3.2+ strongly recommended)
* [osm2pgsql](https://osm2pgsql.org) (1.8+)
* [Python 3](https://www.python.org/) (3.9+)
Furthermore the following Python libraries are required:
* [Psycopg3](https://www.psycopg.org)
* [PostgreSQL](https://www.postgresql.org) (9.6+ will work, 11+ strongly recommended)
* [PostGIS](https://postgis.net) (2.2+ will work, 3.0+ strongly recommended)
* [Python 3](https://www.python.org/) (3.6+)
* [Psycopg2](https://www.psycopg.org) (2.7+)
* [Python Dotenv](https://github.com/theskumar/python-dotenv)
* [psutil](https://github.com/giampaolo/psutil)
* [Jinja2](https://palletsprojects.com/p/jinja/)
* [PyICU](https://pypi.org/project/PyICU/)
* [PyYaml](https://pyyaml.org/) (5.1+)
* [mwparserfromhell](https://github.com/earwig/mwparserfromhell/)
These will be installed automatically when using pip installation.
* [datrie](https://github.com/pytries/datrie)
* [PHP](https://php.net) (7.0 or later)
* PHP-pgsql
* PHP-intl (bundled with PHP)
* PHP-cgi (for running queries from the command line)
For running continuous updates:
* [pyosmium](https://osmcode.org/pyosmium/)
For running the Python frontend:
* [SQLAlchemy](https://www.sqlalchemy.org/) (1.4.31+ with greenlet support)
* [asyncpg](https://magicstack.github.io/asyncpg) (0.8+, only when using SQLAlchemy < 2.0)
* one of the following web frameworks:
* [falcon](https://falconframework.org/) (3.0+)
* [starlette](https://www.starlette.io/)
* [uvicorn](https://www.uvicorn.org/)
For dependencies for running tests and building documentation, see
the [Development section](../develop/Development-Environment.md).
@@ -68,7 +75,7 @@ Take into account that the OSM database is growing fast.
Fast disks are essential. Using NVME disks is recommended.
Even on a well configured machine the import of a full planet takes
around 2.5 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
@@ -80,16 +87,14 @@ your `postgresql.conf` file.
maintenance_work_mem = (10GB)
autovacuum_work_mem = 2GB
work_mem = (50MB)
effective_cache_size = (24GB)
synchronous_commit = off
max_wal_size = 1GB
checkpoint_timeout = 60min
checkpoint_timeout = 10min
checkpoint_completion_target = 0.9
random_page_cost = 1.0
wal_level = minimal
max_wal_senders = 0
The numbers in brackets behind some parameters seem to work fine for
128GB RAM machine. Adjust to your setup. A higher number for `max_wal_size`
64GB RAM machine. Adjust to your setup. A higher number for `max_wal_size`
means that PostgreSQL needs to run checkpoints less often but it does require
the additional space on your disk.
@@ -102,14 +107,14 @@ you might consider setting:
and even reduce `autovacuum_work_mem` further. This will reduce the amount
of memory that autovacuum takes away from the import process.
## Installing the latest release
For the initial import, you should also set:
Nominatim is easiest installed directly from Pypi. Make sure you have installed
osm2pgsql, PostgreSQL/PostGIS and libICU together with its header files.
fsync = off
full_page_writes = off
Then you can install Nominatim with:
Don't forget to re-enable them after the initial import or you risk database
corruption.
pip install nominatim-db nominatim-api
## Downloading and building Nominatim
@@ -120,28 +125,56 @@ The release contains all necessary files. Just unpack it.
### Downloading the latest development version
If you want to install latest development version from github:
If you want to install latest development version from github, make sure to
also check out the osm2pgsql subproject:
```
git clone https://github.com/osm-search/Nominatim.git
git clone --recursive https://github.com/openstreetmap/Nominatim.git
```
The development version does not include the country grid. Download it separately:
```
wget -O Nominatim/data/country_osm_grid.sql.gz https://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
Nominatim is easiest to run from its own virtual environment. To create one, run:
The code must be built in a separate directory. Create the directory and
change into it.
sudo apt-get install virtualenv
virtualenv /srv/nominatim-venv
```
mkdir build
cd build
```
To install Nominatim directly from the source tree into the virtual environment, run:
Nominatim uses cmake and make for building. Assuming that you have created the
build at the same level as the Nominatim source directory run:
/srv/nominatim-venv/bin/pip install packaging/nominatim-{db,api}
```
cmake ../Nominatim
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
in that case, e.g.
```
export PATH=<install root>/bin:$PATH
```
Now continue with [importing the database](Import.md).

View File

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

View File

@@ -1,116 +1,19 @@
# Database Migrations
Nominatim offers automatic migrations for versions 4.3+. Please follow
Since version 3.7.0 Nominatim offers automatic migrations. Please follow
the following steps:
* Stop any updates that are potentially running
* Update the backend: `pip install -U nominatim-db`
* Go to your project directory and run `nominatim admin --migrate`
* Update the frontend: `pip install -U nominatim-api`
* (optionally) Restart updates
* stop any updates that are potentially running
* update Nominatim to the newer version
* go to your project directory and run `nominatim admin --migrate`
* (optionally) restart updates
Below you find additional migrations and hints about other structural and
breaking changes. **Please read them before running the migration.**
!!! note
If you are migrating from a version <4.3, you need to install 4.3
and migrate to 4.3 first. Then you can migrate to the current
version. It is strongly recommended to do a reimport instead.
## 5.1.0 -> 5.2.0
### Lua import style: required extratags removed
Tags that are required by Nominatim as extratags are now always included
independent of what is defined in the style. The line
flex.add_for_extratags('required')
is no longer required in custom styles and will throw an error. Simply
remove the line from your style.
## 4.5.0 -> 5.0.0
### PHP frontend removed
The PHP frontend has been completely removed. Please switch to the Python
frontend.
Without the PHP code, the `nominatim refresh --website` command is no longer
needed. It currently omits a warning and does otherwise nothing. It will be
removed in later versions of Nominatim. So make sure you remove it from your
scripts.
### CMake building removed
Nominatim can now only be installed via pip. Please follow the installation
instructions for the current version to change to pip.
### osm2pgsql no longer vendored in
Nominatim no longer ships its own version of osm2pgsql. Please install a
stock version of osm2pgsql from your distribution. See the
[installation instruction for osm2pgsql](https://osm2pgsql.org/doc/install.html)
for details. A minimum version of 1.8 is required. The current stable versions
of Ubuntu and Debian already ship with an appropriate versions. For older
installation, you may have to compile a newer osm2pgsql yourself.
### Legacy tokenizer removed
The `legacy` tokenizer is no longer enabled. This tokenizer has been superseded
by the `ICU` tokenizer a long time ago. In the unlikely case that your database
still uses the `legacy` tokenizer, you must reimport your database.
### osm2pgsql style overhauled
There are some fundamental changes to how customized osm2pgsql styles should
be written. The changes are mostly backwards compatible, i.e. custom styles
should still work with the new implementation. The only exception is a
customization of the `process_tags()` function. This function is no longer
considered public and neither are the helper functions used in it.
They currently still work but will be removed at some point. If you have
been making changes to `process_tags`, please review your style and try
to switch to the new convenience functions.
For more information on the changes, see the
[pull request](https://github.com/osm-search/Nominatim/pull/3615)
and read the new
[customization documentation](https://nominatim.org/release-docs/latest/customize/Import-Styles/).
## 4.4.0 -> 4.5.0
### New structure for Python packages
The nominatim Python package has been split into `nominatim-db` and `nominatim-api`.
Any imports need to be adapted accordingly.
If you are running the Python frontend, change the server module from
`nominatim.server.falcon.server` to `nominatim_api.server.falcon.server`.
If you are using the Nominatim library, all imports need to be changed
from `nominatim.api.<module>` to `nominatim_api.<module>`.
If you have written custom tokenizers or sanitizers, the appropriate modules
are now found in `nominatim_db`.
## 4.2.0 -> 4.3.0
### 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';
```
If you are migrating from a version <3.6, then you still have to follow
the manual migration steps up to 3.6.
## 4.0.0 -> 4.1.0

View File

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

View File

@@ -59,6 +59,47 @@ imported multiple country extracts and want to keep them
up-to-date, [Advanced installations section](Advanced-Installations.md)
contains instructions to set up and update multiple country extracts.
#### Continuous updates
This is the easiest mode. Simply run the replication command without any
parameters:
nominatim replication
The update application keeps running forever and retrieves and applies
new updates from the server as they are published.
You can run this command as a simple systemd service. Create a service
description like that in `/etc/systemd/system/nominatim-updates.service`:
```
[Unit]
Description=Continuous updates of Nominatim
[Service]
WorkingDirectory=/srv/nominatim
ExecStart=nominatim replication
StandardOutput=append:/var/log/nominatim-updates.log
StandardError=append:/var/log/nominatim-updates.error.log
User=nominatim
Group=nominatim
Type=simple
[Install]
WantedBy=multi-user.target
```
Replace the `WorkingDirectory` with your project directory. Also adapt user
and group names as required.
Now activate the service and start the updates:
```
sudo systemctl daemon-reload
sudo systemctl enable nominatim-updates
sudo systemctl start nominatim-updates
```
#### One-time mode
When the `--once` parameter is given, then Nominatim will download exactly one
@@ -68,10 +109,10 @@ the update interval no new data has been published yet, it will go to sleep
until the next expected update and only then attempt to download the next batch.
The one-time mode is particularly useful if you want to run updates continuously
but need to schedule other work in between updates. For example, you might
want to regularly recompute postcodes -- a process that
must not be run while updates are in progress. An update script refreshing
postcodes regularly might look like this:
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
@@ -109,19 +150,17 @@ Unit=nominatim-updates.service
WantedBy=multi-user.target
```
`OnUnitActiveSec` defines how often the individual update command is run.
Then add a service definition for the timer in `/etc/systemd/system/nominatim-updates.service`:
And then a similar service definition: `/etc/systemd/system/nominatim-updates.service`:
```
[Unit]
Description=Single updates of Nominatim
[Service]
WorkingDirectory=/srv/nominatim-project
ExecStart=/srv/nominatim-venv/bin/nominatim replication --once
StandardOutput=journald
StandardError=inherit
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
@@ -130,9 +169,9 @@ Type=simple
WantedBy=multi-user.target
```
Replace the `WorkingDirectory` with your project directory. `ExecStart` points
to the nominatim binary that was installed in your virtualenv earlier.
Finally, you might need to adapt user and group names as required.
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:
@@ -142,13 +181,12 @@ sudo systemctl enable nominatim-updates.timer
sudo systemctl start nominatim-updates.timer
```
You can stop future data updates while allowing any current, in-progress
You can stop future data updates, while allowing any current, in-progress
update steps to finish, by running `sudo systemctl stop
nominatim-updates.timer` and waiting until `nominatim-updates.service` isn't
running (`sudo systemctl is-active nominatim-updates.service`).
To check the output from the update process, use journalctl: `journalctl -u
nominatim-updates.service`
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
@@ -158,13 +196,13 @@ all changes from the server until the database is up-to-date. The catch-up mode
still respects the parameter `NOMINATIM_REPLICATION_MAX_DIFF`. It downloads and
applies the changes in appropriate batches until all is done.
The catch-up mode is foremost useful to bring the database up to date after the
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-project
cd /srv/nominatim
NOMINATIM_REPLICATION_MAX_DIFF=5000 nominatim replication --catch-up --threads 15
```
@@ -176,27 +214,10 @@ replication catch-up at whatever interval you desire.
When running scheduled updates with catch-up, it is a good idea to choose
a replication source with an update frequency that is an order of magnitude
lower. For example, if you want to update once a day, use an hourly updated
source. This ensures that you don't miss an entire day of updates when
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
once mode together with a frequently run systemd script as described above.
It ensures to re-request the newest update until they have been published.
#### Continuous updates
!!! danger
This mode is no longer recommended to use and will removed in future
releases. systemd is much better
suited for running regular updates. Please refer to the setup
instructions for running one-time mode with systemd above.
This is the easiest mode. Simply run the replication command without any
parameters:
nominatim replication
The update application keeps running forever and retrieves and applies
new updates from the server as they are published.
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:
@@ -39,95 +35,66 @@ 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>`
Wrap JSON output in a callback function (JSONP) i.e. `<string>(<json>)`.
* `pretty=[0|1]`
Add indentation to make it more human-readable. (Default: 0)
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.
### 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 POIs and address that depend on the place. Only POIs
that use this place to determine their address will be returned.
Include details of places lower in the address hierarchy. (Default: 0)
| Parameter | Value | Default |
|-----------| ----- | ------- |
| group_hierarchy | 0 or 1 | 0 |
* `group_hierarchy=[0|1]`
When set to 1, the output of the address hierarchy will be
grouped by type.
For JSON output will group the places by type. (Default: 0)
| Parameter | Value | Default |
|-----------| ----- | ------- |
| polygon_geojson | 0 or 1 | 0 |
Include geometry of result.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| entrances | 0 or 1 | 0 |
When set to 1, include the tagged entrances in the result.
* `polygon_geojson=[0|1]`
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
##### JSON
[https://nominatim.openstreetmap.org/details?osmtype=W&osmid=38210407&format=json](https://nominatim.openstreetmap.org/details?osmtype=W&osmid=38210407&format=json)
[https://nominatim.openstreetmap.org/details.php?osmtype=W&osmid=38210407&format=json](https://nominatim.openstreetmap.org/details.php?osmtype=W&osmid=38210407&format=json)
```json

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:
@@ -15,135 +15,75 @@ 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 | 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: 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.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| entrances | 0 or 1 | 0 |
When set to 1, include the tagged entrances in the result.
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 contrary 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

View File

@@ -12,7 +12,7 @@ a single place (for reverse) of the following format:
```
{
"place_id": 100149,
"place_id": "100149",
"licence": "Data © OpenStreetMap contributors, ODbL 1.0. https://osm.org/copyright",
"osm_type": "node",
"osm_id": "107775",
@@ -60,8 +60,6 @@ The possible fields are:
* `namedetails` - dictionary with full list of available names including ref etc.
* `geojson`, `svg`, `geotext`, `geokml` - full geometry
(only with the appropriate `polygon_*` parameter)
* `entrances` - array of objects representing tagged entrances for the object, or
null if none are found (only with `entrances=1`)
## JSONv2
@@ -89,8 +87,6 @@ The properties object has the following fields:
* `extratags` - dictionary with additional useful tags like `website` or `maxspeed`
(only with `extratags=1`)
* `namedetails` - dictionary with full list of available names including ref etc.
* `entrances` - array of objects representing tagged entrances for the object, or
null if none are found (only with `entrances=1`)
Use `polygon_geojson` to output the full geometry of the object instead
of the centroid.
@@ -110,13 +106,8 @@ The following feature attributes are implemented:
* `name` - localised name of the place
* `housenumber`, `street`, `locality`, `district`, `postcode`, `city`,
`county`, `state`, `country` -
provided when it can be determined from the address (only with `addressdetails=1`)
provided when it can be determined from the address
* `admin` - list of localised names of administrative boundaries (only with `addressdetails=1`)
* `extra` - dictionary with additional useful tags like `website` or `maxspeed`
(only with `extratags=1`)
* `entrances` - array of objects representing tagged entrances for the object, or
null if none are found (only with `entrances=1`)
Use `polygon_geojson` to output the full geometry of the object instead
of the centroid.
@@ -168,8 +159,8 @@ The place information can be found in the `result` element. The attributes of th
The full address of the result can be found in the content of the
`result` element as a comma-separated list.
Additional information requested with `addressdetails=1`, `extratags=1`,
`namedetails=1`, and `entrances=1` can be found in extra elements.
Additional information requested with `addressdetails=1`, `extratags=1` and
`namedetails=1` can be found in extra elements.
### Search and Lookup
@@ -177,7 +168,7 @@ Additional information requested with `addressdetails=1`, `extratags=1`,
<searchresults timestamp="Sat, 11 Aug 18 11:55:35 +0000"
attribution="Data © OpenStreetMap contributors, ODbL 1.0. https://www.openstreetmap.org/copyright"
querystring="london" polygon="false" exclude_place_ids="100149"
more_url="https://nominatim.openstreetmap.org/search?q=london&addressdetails=1&extratags=1&exclude_place_ids=100149&format=xml&accept-language=en-US%2Cen%3Bq%3D0.7%2Cde%3Bq%3D0.3">
more_url="https://nominatim.openstreetmap.org/search.php?q=london&addressdetails=1&extratags=1&exclude_place_ids=100149&format=xml&accept-language=en-US%2Cen%3Bq%3D0.7%2Cde%3Bq%3D0.3">
<place place_id="100149" osm_type="node" osm_id="107775" place_rank="15" address_rank="15"
boundingbox="51.3473219,51.6673219,-0.2876474,0.0323526" lat="51.5073219" lon="-0.1276474"
display_name="London, Greater London, England, SW1A 2DU, United Kingdom"
@@ -220,8 +211,8 @@ be more than one. The attributes of that element contain:
* `ref` - content of `ref` tag if it exists
* `lat`, `lon` - latitude and longitude of the centroid of the object
* `boundingbox` - comma-separated list of corner coordinates ([see notes](#boundingbox))
* `place_rank` - class [search rank](../customize/Ranking.md#search-rank)
* `address_rank` - place [address rank](../customize/Ranking.md#address-rank)
* `place_rank` - class [search rank](../customize/Ranking#search-rank)
* `address_rank` - place [address rank](../customize/Ranking#address-rank)
* `display_name` - full comma-separated address
* `class`, `type` - key and value of the main OSM tag
* `importance` - computed importance rank
@@ -230,9 +221,9 @@ be more than one. The attributes of that element contain:
When `addressdetails=1` is requested, the localised address parts appear
as subelements with the type of the address part.
Additional information requested with `extratags=1`, `namedetails=1`, and
`entrances=1` can be found in extra elements as sub-element of `extratags`,
`namedetails`, and `entrances` respectively.
Additional information requested with `extratags=1` and `namedetails=1` can
be found in extra elements as sub-element of `extratags` and `namedetails`
respectively.
## Notes on field values
@@ -309,78 +300,3 @@ with a designation label. Per default the following labels may appear:
They roughly correspond to the classification of the OpenStreetMap data
according to either the `place` tag or the main key of the object.
### entrances
Entrance details in the xml and json formats return the latitude and longitude
of the entrance, the osm node ID, the [type of
entrance](https://wiki.openstreetmap.org/wiki/Key:entrance), and any extra tags
associated with the entrance node.
* osm_id
* type
* lat
* lon
* extratags
They roughly correspond to the classification of the OpenStreetMap data
according to either the `place` tag or the main key of the object.
#### Example
##### JSON
[https://nominatim.openstreetmap.org/details?osmtype=W&osmid=32619803&entrances=1&format=json](https://nominatim.openstreetmap.org/details?osmtype=W&osmid=32619803&entrances=1&format=json)
```json
{
"place_id": 124325848,
"parent_place_id": 123936289,
"osm_type": "W",
"osm_id": 32619803,
"category": "shop",
"type": "supermarket",
"admin_level": 15,
"localname": "PENNY",
...
"entrances": [
{
"osm_id": 1733488238,
"type": "yes",
"lat": "51.0466704",
"lon": "12.8077106",
"extratags": {
"foot": "yes"
}
},
{
"osm_id": 1733488256,
"type": "main",
"lat": "51.0467197",
"lon": "12.8078448",
"extratags": {
"foot": "yes"
}
},
{
"osm_id": 1733498087,
"type": "exit",
"lat": "51.0467081",
"lon": "12.8078131",
"extratags": {
"foot": "yes"
}
},
{
"osm_id": 7914950851,
"type": "service",
"lat": "51.0468487",
"lon": "12.8075876",
"extratags": {
"access": "delivery"
}
}
]
}
```

View File

@@ -1,5 +1,8 @@
This section describes the API V1 of the Nominatim web service. The
service offers the following endpoints:
### Nominatim API
Nominatim indexes named (or numbered) features within the OpenStreetMap (OSM) dataset and a subset of other unnamed features (pubs, hotels, churches, etc).
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
@@ -9,6 +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
@@ -31,106 +31,57 @@ where `lat` and `lon` are latitude and longitude of a coordinate in WGS84
projection. The API returns exactly one result or an error when the coordinate
is in an area with no OSM data coverage.
Additional parameters are accepted as listed below.
!!! tip
The reverse API allows a lookup of object by coordinate. If you want
to look up an object by ID, use the [Address Lookup API](Lookup.md) instead.
!!! danger "Deprecation warning"
The API can also be used with the URL
`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.
!!! warning "Deprecation warning"
The reverse API used to allow address lookup for a single OSM object by
its OSM id. This use is now deprecated. Use the [Address Lookup API](../Lookup)
instead.
### 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.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| entrances | 0 or 1 | 0 |
When set to 1, include the tagged entrances in the result.
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 contrary 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:
@@ -141,84 +92,46 @@ 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` | `address,poi` |
The layer filter allows to select places by themes.
The `address` layer contains all places that make up an address:
address points with house numbers, streets, inhabited places (suburbs, villages,
cities, states etc.) and administrative boundaries.
The `poi` layer selects all point of interest. This includes classic points
of interest like restaurants, shops, hotels but also less obvious features
like recycling bins, guideposts or benches.
The `railway` layer includes railway infrastructure like tracks.
Note that in Nominatim's standard configuration, only very few railway
features are imported into the database.
The `natural` layer collects features like rivers, lakes and mountains while
the `manmade` layer functions as a catch-all for features not covered by the
other layers.
### Polygon output
| 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.
If you are making a large number of requests, please include an appropriate email
address to identify your requests. See Nominatim's [Usage Policy](https://operations.osmfoundation.org/policies/nominatim/) for more details.
| 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
* [https://nominatim.openstreetmap.org/reverse?format=xml&lat=52.5487429714954&lon=-1.81602098644987&zoom=18&addressdetails=1&layer=address](https://nominatim.openstreetmap.org/reverse?format=xml&lat=52.5487429714954&lon=-1.81602098644987&zoom=18&addressdetails=1&layer=address)
* [https://nominatim.openstreetmap.org/reverse?format=xml&lat=52.5487429714954&lon=-1.81602098644987&zoom=18&addressdetails=1](https://nominatim.openstreetmap.org/reverse?format=xml&lat=52.5487429714954&lon=-1.81602098644987&zoom=18&addressdetails=1)
```xml
<reversegeocode timestamp="Fri, 06 Nov 09 16:33:54 +0000" querystring="...">
@@ -241,7 +154,7 @@ This overrides the specified machine readable format.
##### Example with `format=jsonv2`
* [https://nominatim.openstreetmap.org/reverse?format=jsonv2&lat=-34.44076&lon=-58.70521&layer=address](https://nominatim.openstreetmap.org/reverse?format=jsonv2&lat=-34.44076&lon=-58.70521&layer=address)
* [https://nominatim.openstreetmap.org/reverse?format=jsonv2&lat=-34.44076&lon=-58.70521](https://nominatim.openstreetmap.org/reverse?format=jsonv2&lat=-34.44076&lon=-58.70521)
```json
{
@@ -273,7 +186,7 @@ This overrides the specified machine readable format.
##### Example with `format=geojson`
* [https://nominatim.openstreetmap.org/reverse?format=geojson&lat=44.50155&lon=11.33989&layer=address](https://nominatim.openstreetmap.org/reverse?format=geojson&lat=44.50155&lon=11.33989&layer=address)
* [https://nominatim.openstreetmap.org/reverse?format=geojson&lat=44.50155&lon=11.33989](https://nominatim.openstreetmap.org/reverse?format=geojson&lat=44.50155&lon=11.33989)
```json
{
@@ -325,7 +238,7 @@ This overrides the specified machine readable format.
##### Example with `format=geocodejson`
[https://nominatim.openstreetmap.org/reverse?format=geocodejson&lat=60.2299&lon=11.1663&layer=address](https://nominatim.openstreetmap.org/reverse?format=geocodejson&lat=60.2299&lon=11.1663&layer=address)
[https://nominatim.openstreetmap.org/reverse?format=geocodejson&lat=60.2299&lon=11.1663](https://nominatim.openstreetmap.org/reverse?format=geocodejson&lat=60.2299&lon=11.1663)
```json
{

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:
@@ -21,62 +21,35 @@ 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
@@ -84,154 +57,52 @@ See [Place Output Formats](Output.md) for details on each format.
has a different default behaviour for historical reasons. When the
`format` parameter is omitted, the request will be forwarded to the Web UI.
* `json_callback=<string>`
| 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.
| 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.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| entrances | 0 or 1 | 0 |
When set to 1, include the tagged entrances in the result.
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 contrary 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_ |
Filter that limits the search results to one or more countries.
The country code must be the
[ISO 3166-1alpha2](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) code
of the country, e.g. `gb` for the United Kingdom, `de` for Germany.
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 preferred. Having both parameters
in the same query will work. If the parameters contradict each other,
the search will come up empty.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| layer | comma-separated list of: `address`, `poi`, `railway`, `natural`, `manmade` | _unset_ (no restriction) |
The layer filter allows to select places by themes.
The `address` layer contains all places that make up an address:
address points with house numbers, streets, inhabited places (suburbs, villages,
cities, states tec.) and administrative boundaries.
The `poi` layer selects all point of interest. This includes classic POIs like
restaurants, shops, hotels but also less obvious features like recycling bins,
guideposts or benches.
The `railway` layer includes railway infrastructure like tracks.
Note that in Nominatim's standard configuration, only very few railway
features are imported into the database.
The `natural` layer collects features like rivers, lakes and mountains while
the `manmade` layer functions as a catch-all for features not covered by the
other layers.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| featureType | one of: `country`, `state`, `city`, `settlement` | _unset_ |
The featureType allows to have a more fine-grained selection for places
from the address layer. Results can be restricted to places that make up
the 'state', 'country' or 'city' part of an address. A featureType of
`settlement` selects any human inhabited feature from 'state' down to
'neighbourhood'.
When featureType is set, then results are automatically restricted
to the address layer (see above).
!!! tip
Instead of using the featureType filters `country`, `state` or `city`,
you can also use a structured query without the finer-grained parameters
amenity or street.
| Parameter | Value | Default |
|-----------| ----- | ------- |
| exclude_place_ids | comma-separated list of place ids |
* `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.
@@ -239,212 +110,180 @@ 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 parameter, excluding any results outside the viewbox.
When `bounded=1` is given and the viewbox is small enough, then an amenity-only
search is allowed. Give the special keyword for the amenity in square
* `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 |

7
docs/bash2md.sh Executable file
View File

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

View File

@@ -1,623 +1,153 @@
# Configuring the Import of OSM data
## 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. Nominatim ships with a few preset
configurations for this import, each results in a geocoding database of
different detail. The
[Import section](../admin/Import.md#filtering-imported-data) explains
these default configurations in detail.
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.
If you want to have more control over which OSM data is added to the database,
you can also create your own custom style. Create a new lua style file, put it
into your project directory and then set `NOMINATIM_IMPORT_STYLE` to the name
of the file. Custom style files can be used to modify the existing preset
configurations or to implement your own configuration from scratch.
The 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.
The remainder of the page describes how the flex style works and how to
customize it.
You can also create your own custom style. Put the style file into your
project directory and then set `NOMINATIM_IMPORT_STYLE` to the name of the file.
It is always recommended to start with one of the standard styles and customize
those. You find the standard styles under the name `import-<stylename>.style`
in the standard Nominatim configuration path (usually `/etc/nominatim` or
`/usr/local/etc/nominatim`).
## The `flex-base` lua module
The remainder of the page describes the format of the file.
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 help with customizing
how OSM tags are used by Nominatim.
### Configuration Rules
Every custom style must include this module to make sure that the correct
tables are created. Thus start your custom style as follows:
A single rule looks like this:
``` lua
local flex = require('flex-base')
```
### Using preset configurations
If you want to start with one of the existing presets, then you can import
its settings using the `load_topic()` function:
``` lua
local flex = require('flex-base')
flex.load_topic('streets')
```
The `load_topic` function takes an optional second configuration
parameter. The available options are explained in the
[themepark section](#using-osm2pgsql-themepark).
Available topics are: `admin`, `street`, `address`, `full`. These topic
correspond to the [import styles](../admin/Import.md#filtering-imported-data)
you can choose during import. To start with the 'extratags' style, use the
`full` topic with the appropriate config parameter:
``` lua
flex.load_topic('full', {with_extratags = true})
```
!!! note
You can also directly import the preset style files, e.g.
`local flex = require('import-street')`. It is not possible to
set extra configuration this way.
### How processing works
When Nominatim processes an OSM object, it looks for four kinds of tags:
The _main tags_ classify what kind of place the OSM object represents. One
OSM object can have more than one main tag. In such case one database entry
is created for each main tag. _Name tags_ represent searchable names of the
place. _Address tags_ are used to compute the address information of the place.
Address tags are used for searching and for creating a display name of the place.
_Extra tags_ are any tags that are not directly related to search but
contain interesting additional information. These are just saved in the database
and may be returned with the result [on request](../api/Search.md#output-details).
!!! danger
Some tags in the extratags category are used by Nominatim to better
classify the place. These tags will always be added, independent of
any settings in the style.
Configuring the style means deciding which key and/or key/value is used
in which category.
## Changing the recognized tags
The flex style offers a number of functions to set the classification of
each OSM tag. Most of these functions can also take a preset string instead
of a tag description. These presets describe common configurations that
are also used in the definition of the predefined styles. This section
lists the configuration functions and the accepted presets.
#### Key match lists
Some of the following functions take _key match lists_. These lists can
contain three kinds of strings to match against tag keys:
A string that ends in an asterisk `*` is a prefix match and accordingly matches
against any key that starts with the given string (minus the `*`).
A suffix match can be defined similarly with a string that starts with a `*`.
Any other string is matched exactly against tag keys.
### Main tags
`set/modify_main_tags()` allow to define which tags are used as main tags. It
takes a lua table parameter which defines for keys and key/value
combinations, how they are classified.
The following classifications are recognized:
| classification | meaning |
| :-------------- | :------ |
| always | Unconditionally use this tag as a main tag. |
| named | Consider as main tag, when the object has a primary name (see [names](#name-tags) below) |
| named_with_key | Consider as main tag, when the object has a primary name with a domain prefix. For example, if the main tag is `bridge=yes`, then it will only be added as an extra entry, if there is a tag `bridge:name[:XXX]` for the same object. If this property is set, all names that are not domain-specific are ignored. |
| fallback | Consider as main tag only when no other main tag was found. Fallback always implies `named`, i.e. fallbacks are only tried for objects with primary names. |
| postcode_area | Tag indicates a postcode area. Copy area into the table of postcodes but only when the object is a relation and has a postcode tagged. |
| delete | Completely ignore the tag in any further processing |
| extra | Move the tag to extratags and then ignore it for further processing |
| `<function>`| Advanced handling, see [below](#advanced-main-tag-handling) |
Each key in the table parameter defines an OSM tag key. The value may
be directly a classification as described above. Then the tag will
be considered a main tag for any possible value that is not further defined.
To further restrict which values are acceptable, give a table with the
permitted values and their kind of main tag. If the table contains a simple
value without key, then this is used as default for values that are not listed.
`set_main_tags()` will completely replace the current main tag configuration
with the new configuration. `modify_main_tags()` will merge the new
configuration with the existing one. Merging is done at value level.
For example, when the current setting is `highway = {'always', primary = 'named'}`,
then `set_main_tags{highway = 'delete'}` will result in a rule
`highway = {'delete', primary = 'named'}`.
!!! example
``` lua
local flex = require('import-full')
flex.set_main_tags{
boundary = {administrative = 'named'},
highway = {'always', street_lamp = 'named', no = 'delete'},
landuse = 'fallback'
```json
{
"keys" : ["key1", "key2", ...],
"values" : {
"value1" : "prop",
"value2" : "prop1,prop2"
}
```
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 with two exceptions: the troll tag `highway=no` is
deleted on the spot. And when the value is `street_lamp` then the object
must also have a name, to be included. Finally, if a `landuse` tag is
present then it will be used independently of the concrete value when
neither boundary nor highway tags were found and the object is named.
##### Presets
| Name | Description |
| :----- | :---------- |
| admin | Basic tag set collecting places and administrative boundaries. This set is needed also to ensure proper address computation and should therefore always be present. You can disable selected place types like `place=locality` after adding this set, if they are not relevant for your use case. |
| all_boundaries | Extends the set of recognized boundaries and places to all available ones. |
| natural | Tags for natural features like rivers and mountain peaks. |
| street/default | Tags for streets. Major streets are always included, minor ones only when they have a name. |
| street/car | Tags for all streets that can be used by a motor vehicle. |
| street/all | Includes all highway features named and unnamed. |
| poi/delete | Adds most POI features with and without name. Some frequent but very domain-specific values are excluded by deleting them. |
| poi/extra | Like 'poi/delete' but excluded values are moved to extratags. |
##### Advanced main tag handling
The groups described above are in fact only a preset for a filtering function
that is used to make the final decision how a pre-selected main tag is entered
into Nominatim's internal table. To further customize handling you may also
supply your own filtering function.
The function takes up to three parameters: a Place object of the object
being processed, the key of the main tag and the value of the main tag.
The function may return one of three values:
* `nil` or `false` causes the entry to be ignored
* the Place object causes the place to be added as is
* `Place.copy(names=..., address=..., extratags=...) causes the
place to be enter into the database but with name/address/extratags
set to the given different values.
The Place object has some read-only values that can be used to determine
the handling:
* **object** is the original OSM object data handed in by osm2pgsql
* **admin_level** is the content of the admin_level tag, parsed into an integer and normalized to a value between 0 and 15
* **has_name** is a boolean indicating if the object has a primary name tag
* **names** is a table with the collected list of name tags
* **address** is a table with the collected list of address tags
* **extratags** is a table with the collected list of additional tags to save
!!! example
``` lua
local flex = require('flex-base')
flex.add_topic('street')
local function no_sidewalks(place, k, v)
if place.object.tags.footway == 'sidewalk' then
return false
end
-- default behaviour is to have all footways
return place
end
flex.modify_main_tags(highway = {'footway' = no_sidewalks}
```
This script adds a custom handler for `highway=footway`. It only includes
them in the database, when the object doesn't have a tag `footway=sidewalk`
indicating that it is just part of a larger street which should already
be indexed. Note that it is not necessary to check the key and value
of the main tag because the function is only used for the specific
main tag.
### Ignored tags
The function `ignore_keys()` sets the `delete` classification for keys.
This function takes a _key match list_ so that it is possible to exclude
groups of keys.
Note that full matches always take precedence over suffix matches, which
in turn take precedence over prefix matches.
!!! example
``` lua
local flex = require('flex-base')
flex.add_topic('admin')
flex.ignore_keys{'old_name', 'old_name:*'}
```
This example uses the `admin` preset with the exception that names
that are no longer are in current use, are ignored.
##### Presets
| Name | Description |
| :----- | :---------- |
| metatags | Tags with meta information about the OSM tag like source, notes and import sources. |
| name | Non-names that actually describe properties or name parts. These names can throw off search and should always be removed. |
| address | Extra `addr:*` tags that are not useful for Nominatim. |
### Tags for `extratags`
The function `add_for_extratags()` sets the `extra` classification for keys.
This function takes a
_key match list_ so that it is possible to move groups of keys to extratags.
Note that full matches always take precedence over suffix matches, which
in turn take precedence over prefix matches.
!!! example
``` lua
local flex = require('flex-base')
flex.add_topic('street')
flex.add_for_extratags{'surface', 'access', 'vehicle', 'maxspeed'}
```
This example uses the `street` preset but adds a couple of tags that
are of interest about the condition of the street.
##### Presets
Accepts all [presets from ignored tags](#presets_1).
### General pre-filtering
_(deprecated)_ `set_prefilters()` allows to set the `delete` and `extra`
classification for main tags.
This function removes all previously set main tags with `delete` and `extra`
classification and then adds the newly defined tags.
`set_prefilters()` takes a table with four optional fields:
* __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.
!!! danger "Deprecation warning"
Use of this function should be replaced with `modify_main_tags()` to
set the data from `delete_tags` and `extra_tags`, with `ignore_keys()`
for the `delete_keys` parameter and with `add_for_extratags()` for the
`extra_keys` parameter.
### Name tags
`set/modify_name_tags()` allow to define the tags used for naming places. Name tags
can only be selected by their keys. The import script distinguishes
between primary and auxiliary names. A primary name is the given name of
a place. Having a primary name makes a place _named_. This is important
for main tags that are only included when a name is present. Auxiliary names
are identifiers like references. They may be searched for but should not
be included on their own.
The functions take a table with two optional fields `main` and `extra`.
They take _key match lists_ for primary and auxiliary names respectively.
A third field `house` can contain tags for names that appear in place of
house numbers in addresses. This field can only contain complete key names.
'house tags' are special in that they cause the OSM object to be added to
the database independently of the presence of other main tags.
`set_name_tags()` overwrites the current configuration, while
`modify_name_tags()` replaces the fields that are given. (Be aware that
the fields are replaced as a whole. `main = {'foo_name'}` will cause
`foo_name` to become the only recognized primary name. Any previously
defined primary names are forgotten.)
!!! example
``` lua
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.
##### Presets
| Name | Description |
| :----- | :---------- |
| core | Basic set of recognized names for all places. |
| address | Additional names useful when indexing full addresses. |
| poi | Extended set of recognized names for pois. Use on top of the core set. |
### Address tags
`set/modify_address_tags()` defines the tags that will be used to build
up the address of an object. Address tags can only be chosen by their key.
The functions take a table with arbitrary fields, each defining
a key list or _key match list_. Some fields have a special meaning:
| Field | Type | Description |
| :---------| :-------- | :-----------|
| main | key list | Tags that make a full address object out of the OSM object. This is usually the house number or variants thereof. If a main address tag appears, then the object will always be included, if necessary with a fallback of `place=house`. If the key has a prefix of `addr:` or `is_in:` this will be stripped. |
| extra | key match list | Supplementary tags for addresses, tags like `addr:street`, `addr:city` etc. If the key has a prefix of `addr:` or `is_in:` this will be stripped. |
| interpolation | key list | Tags that identify address interpolation lines. |
| country | key match list | Tags that may contain the country the place is in. The first found value with a two-letter code will be accepted, all other values are discarded. |
| _other_ | key match list | Summary field. If a key matches the key match list, then its value will be added to the address tags with the name of the field as key. If multiple tags match, then an arbitrary one wins. |
`set_address_tags()` overwrites the current configuration, while
`modify_address_tags()` replaces the fields that are given. (Be aware that
the fields are replaced as a whole.)
!!! example
``` lua
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.
##### Presets
| Name | Description |
| :----- | :---------- |
| core | Basic set of tags needed to recognize address relationship for any place. Always include this. |
| houses | Additional set of tags needed to recognize proper addresses |
### Handling of unclassified tags
`set_unused_handling()` defines what to do with tags that remain after all tags
have been classified using the functions above. There are two ways in
which the function can be used:
`set_unused_handling(delete_keys = ..., delete_tags = ...)` deletes all
keys that match the descriptions in the parameters and moves all remaining
tags into the extratags list.
`set_unused_handling(extra_keys = ..., extra_tags = ...)` moves all tags
matching the parameters into the extratags list and then deletes the remaining
tags. For the format of the parameters see the description in `set_prefilters()`
above.
When no special handling is set, then unused tags will be discarded with one
exception: place tags are kept in extratags for administrative boundaries.
When using a custom setting, you should also make sure that the place tag
is added for extratags.
!!! example
``` lua
local flex = require('import-full')
flex.set_address_tags{
main = {'addr:housenumber'},
extra = {'addr:*', 'tiger:county'}
}
flex.set_unused_handling{delete_keys = {'tiger:*'}}
```
In this example all remaining tags except those beginning with `tiger:`
are moved to the extratags list. Note that it is not possible to
already delete the tiger tags with `set_prefilters()` because that
would remove tiger:county before the address tags are processed.
## Filling additional tables
Most of the OSM objects are saved in the main `place` table for further
processing. In addition to that, there are some smaller tables that save
specialised information. The content of these tables can be customized as
well.
### Entrance table
The table `place_entrance` saves information about OSM nodes that represent
an entrance. This data is later mingled with buildings and other areas and
can be returned [on request](../api/Search.md#output-details). The table
saves the type of entrance as well as a set of custom extra tags.
The function `set_entrance_filter()` can be used to customize the table's
content.
When called without any parameter, then filling the entrance table will be
disabled. When called with a preset name, the appropriate preset will be
applied.
To create a custom configuration, call the function
with a table with the following fields:
* __main_tags__ is a list of tags that mark an entrance node. The value of the
first tag found in the list will be used as the entrance type.
* __extra_include__ is an optional list of tags to be added to the extratags
for this entrance. When left out, all tags except for the ones defined
in 'main_tags' will be included. To disable saving of extra tags, set
this to the empty list.
* __extra_exclude__ defines an optional list of tags to drop before including
the remaining tags as extratags. Note that the tags defined in 'main_tags'
will always be excluded, independently of this setting.
To have even more fine-grained control over the output, you can also hand
in a callback for processing entrance information. The callback function
receives a single parameter, the
[osm2pgsql object](https://osm2pgsql.org/doc/manual.html#processing-callbacks).
This object itself must not be modified. The callback should return either
`nil` when the object is not an entrance. Or it returns a table with a
mandatory `entrance` field containing a string with the type of entrance
and an optional `extratags` field with a simple key-value table of extra
information.
##### Presets
| Name | Description |
| :----- | :---------- |
| default | Standard configuration used with `full` and `extratags` styles. |
## Customizing osm2pgsql callbacks
osm2pgsql expects the flex style to implement three callbacks, one process
function per OSM type. If you want to implement special handling for
certain OSM types, you can override the default implementations provided
by the flex-base module.
### Enabling additional relation types
OSM relations can represent very diverse
[types of real-world objects](https://wiki.openstreetmap.org/wiki/Key:type). To
be able to process them correctly, Nominatim needs to understand how to
create a geometry for each type. By default, the script knows how to
process relations of type `multipolygon`, `boundary` and `waterway`. All
other relation types are ignored.
To add other types relations, set `RELATION_TYPES` for
the type to the kind of geometry that should be created. The following
kinds of geometries can be used:
* __relation_as_multipolygon__ creates a (Multi)Polygon from the ways in
the relation. If the ways do not form a valid area, then the object is
silently discarded.
* __relation_as_multiline__ creates a (Multi)LineString from the ways in
the relations. Ways are combined as much as possible without any regards
to their order in the relation.
!!! Example
``` lua
local flex = require('import-full')
flex.RELATION_TYPES['site'] = flex.relation_as_multipolygon
```
With this line relations of `type=site` will be included in the index
according to main tags found. This only works when the site relation
resolves to a valid area. Nodes in the site relation are not part of the
geometry.
### Adding additional logic to processing functions
The default processing functions are also exported by the flex-base module
as `process_node`, `process_way` and `process_relation`. These can be used
to implement your own processing functions with some additional processing
logic.
!!! Example
``` lua
local flex = require('import-full')
function osm2pgsql.process_relation(object)
if object.tags.boundary ~= 'administrative' or object.tags.admin_level ~= '2' then
flex.process_relation(object)
end
end
```
This example discards all country-level boundaries and uses standard
handling for everything else. This can be useful if you want to use
your own custom country boundaries.
### Customizing the main processing function
!!! danger "Deprecation Warning"
The style used to allow overwriting the internal processing function
`process_tags()`. While this is currently still possible, it is no longer
encouraged and may stop working in future versions. The internal
`Place` class should now be considered read-only.
## Using osm2pgsql-themepark
The Nominatim osm2pgsql style is designed so that it can also be used as
a theme for [osm2pgsql-themepark](https://osm2pgsql.org/themepark/). This
makes it easy to combine Nominatim with other projects like
[openstreetmap-carto](https://github.com/gravitystorm/openstreetmap-carto)
in the same database.
To set up one of the preset styles, simply include a topic with the same name:
```
local themepark = require('themepark')
themepark:add_topic('nominatim/address')
}
```
Themepark topics offer two configuration options:
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.
* **street_theme** allows to choose one of the sub topics for streets:
* _default_ - include all major streets and named minor paths
* _car_ - include all streets physically usable by cars
* _all_ - include all major streets and minor paths
* **with_extratags**, when set to a truthy value, then tags that are
not specifically used for address or naming are added to the
extratags column
The 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.
The customization functions described in the
[Changing recognized tags](#changing-the-recognized-tags) section
are available from the theme. To access the theme you need to explicitly initialize it.
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.
!!! Example
``` lua
local themepark = require('themepark')
The rules in a configuration file are processed sequentially and the first
match for each tag wins.
themepark:add_topic('nominatim/full', {with_extratags = true})
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.
local flex = themepark:init_theme('nominatim')
### Tag Properties
flex.modify_main_tags{'amenity' = {
'waste_basket' = 'delete'}
}
```
This example uses the full Nominatim configuration but disables
importing waste baskets.
One or more of the following properties may be given for each tag:
You may also write a new configuration from scratch. Simply omit including
a Nominatim topic and only call the required customization functions.
* `main`
Customizing the osm2pgsql processing functions as explained
[above](#adding-additional-logic-to-processing-functions) is not possible
when running under themepark. Instead include other topics that make the
necessary modifications or add an additional processor before including
the Nominatim topic.
A principal tag. A new row will be added for the object with key and value
as `class` and `type`.
!!! Example
``` lua
local themepark = require('themepark')
* `with_name`
local function discard_country_boundaries(object)
if object.tags.boundary == 'administrative' and object.tags.admin_level == '2' then
return 'stop'
end
end
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).
themepark:add_proc('relation', discard_country_boundaries)
-- Order matters here. The topic needs to be added after the custom callback.
themepark:add_topic('nominatim/full', {with_extratags = true})
```
Discarding country-level boundaries when running under themepark.
* `with_name_key`
## Changing the style of existing databases
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.
There is usually no issue changing the style of a database that is already
* `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
There is normally no issue changing the style of a database that is already
imported and now kept up-to-date with change files. Just be aware that any
change in the style applies to updates only. If you want to change the data
that is already in the database, then a reimport is necessary.

View File

@@ -1,55 +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
place's [search rank](../customize/Ranking.md#search-rank).
In a second step, a secondary importance value is added which is meant to
represent how well-known the general area is where the place is located. It
functions as a tie-breaker between places with very similar primary
importance values.
nominatim.org has preprocessed importance tables for the
[primary Wikipedia rankings](https://nominatim.org/data/wikimedia-importance.sql.gz)
and for [secondary importance](https://nominatim.org/data/wikimedia-secondary-importance.sql.gz)
based on Wikipedia importance of the administrative areas.
The source code for creating these files is available in the Github projects
[osm-search/wikipedia-wikidata](https://github.com/osm-search/wikipedia-wikidata)
and
[osm-search/secondary-importance](https://github.com/osm-search/secondary-importance).
### Customizing secondary importance
The secondary importance is implemented as a simple
[Postgis raster](https://postgis.net/docs/raster.html) table, where Nominatim
looks up the value for the coordinates of the centroid of a place. You can
provide your own secondary importance raster in form of an SQL file named
`secondary_importance.sql.gz` in your project directory.
The SQL file needs to drop and (re)create a table `secondary_importance` which
must as a minimum contain a column `rast` of type `raster`. The raster must
be in EPSG:4326 and contain 16bit unsigned ints
(`raster_constraint_pixel_types(rast) = '{16BUI}'). Any other columns in the
table will be ignored. You must furthermore create an index as follows:
```
CREATE INDEX ON secondary_importance USING gist(ST_ConvexHull(gist))
```
The following raster2pgsql command will create a table from a tiff file
that conforms to the requirements:
```
raster2pgsql -I -C -Y -d -t 128x128 input.tiff public.secondary_importance
```

View File

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

View File

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

View File

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

View File

@@ -57,20 +57,41 @@ parameter that is understood by libpq. See the [Postgres documentation](https://
| **After Changes:** | cannot be changed after import |
Defines the name of the database user that will run search queries. Usually
this is the user under which the webserver is executed. The Postgres user
this is the user under which the webserver is executed. When running Nominatim
via php-fpm, you can also define a separate query user. The Postgres user
needs to be set up before starting the import.
Nominatim grants minimal rights to this user to all tables that are needed
for running geocoding queries.
#### NOMINATIM_DATABASE_MODULE_PATH
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Directory where to find the PostgreSQL server module |
| **Format:** | path |
| **Default:** | _empty_ (use `<project_directory>/module`) |
| **After Changes:** | run `nominatim refresh --functions` |
| **Comment:** | Legacy tokenizer only |
Defines the directory in which the PostgreSQL server module `nominatim.so`
is stored. The directory and module must be accessible by the PostgreSQL
server.
For information on how to use this setting when working with external databases,
see [Advanced Installations](../admin/Advanced-Installations.md).
The option is only used by the Legacy tokenizer and ignored otherwise.
#### NOMINATIM_TOKENIZER
| Summary | |
| -------------- | --------------------------------------------------- |
| **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
@@ -94,6 +115,20 @@ on the file format.
If a relative path is given, then the file is searched first relative to the
project directory and then in the global settings directory.
#### NOMINATIM_MAX_WORD_FREQUENCY
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Number of occurrences before a word is considered frequent |
| **Format:** | int |
| **Default:** | 50000 |
| **After Changes:** | cannot be changed after import |
| **Comment:** | Legacy tokenizer only |
The word frequency count is used by the Legacy tokenizer to automatically
identify _stop words_. Any partial term that occurs more often then what
is defined in this setting, is effectively ignored during search.
#### NOMINATIM_LIMIT_REINDEXING
@@ -128,6 +163,25 @@ codes, to restrict import to a subset of languages.
Currently only affects the initial import of country names and special phrases.
#### NOMINATIM_TERM_NORMALIZATION
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Rules for normalizing terms for comparisons |
| **Format:** | string: semicolon-separated list of ICU rules |
| **Default:** | :: NFD (); [[:Nonspacing Mark:] [:Cf:]] >; :: lower (); [[:Punctuation:][:Space:]]+ > ' '; :: NFC (); |
| **Comment:** | Legacy tokenizer only |
[Special phrases](Special-Phrases.md) have stricter matching requirements than
normal search terms. They must appear exactly in the query after this term
normalization has been applied.
Only has an effect on the Legacy tokenizer. For the ICU tokenizer the rules
defined in the
[normalization section](Tokenizers.md#normalization-and-transliteration)
will be used.
#### NOMINATIM_USE_US_TIGER_DATA
| Summary | |
@@ -336,7 +390,7 @@ NOMINATIM_TABLESPACE_SEARCH_INDEX
NOMINATIM_TABLESPACE_OSM_DATA
: Raw OSM data cache used for import and updates.
NOMINATIM_TABLESPACE_OSM_INDEX
NOMINATIM_TABLESPACE_OSM_DATA
: Indexes on the raw OSM data cache.
NOMINATIM_TABLESPACE_PLACE_DATA
@@ -490,6 +544,35 @@ the local languages (in OSM: the name tag without any language suffix) is
used.
#### NOMINATIM_SEARCH_BATCH_MODE
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Enable a special batch query mode |
| **Format:** | boolean |
| **Default:** | no |
| **After Changes:** | run `nominatim refresh --website` |
This feature is currently undocumented and potentially broken.
#### NOMINATIM_SEARCH_NAME_ONLY_THRESHOLD
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Threshold for switching the search index lookup strategy |
| **Format:** | integer |
| **Default:** | 500 |
| **After Changes:** | run `nominatim refresh --website` |
This setting defines the threshold over which a name is no longer considered
as rare. When searching for places with rare names, only the name is used
for place lookups. Otherwise the name and any address information is used.
This setting only has an effect after `nominatim refresh --word-counts` has
been called to compute the word frequencies.
#### NOMINATIM_LOOKUP_MAX_COUNT
| Summary | |
@@ -521,125 +604,25 @@ with a single query.
Setting this parameter to 0 disables polygon output completely.
### Logging Settings
#### NOMINATIM_SEARCH_WITHIN_COUNTRIES
#### NOMINATIM_LOG_DB
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Disable search for elements that are not in the country grid |
| **Description:** | Log requests into the database |
| **Format:** | boolean |
| **Default:** | no |
| **After Changes:** | run `nominatim refresh --website` |
Enable to search elements just within countries.
Enable logging requests into a database table with this setting. The logs
can be found in the table `new_query_log`.
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.
When using this logging method, it is advisable to set up a job that
regularly clears out old logging information. Nominatim will not do that
on its own.
#### 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.
#### NOMINATIM_OUTPUT_NAMES
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Specifies order of name tags |
| **Format:** | string: comma-separated list of tag names |
| **Default:** | name:XX,name,brand,official_name:XX,short_name:XX,official_name,short_name,ref |
Specifies the order in which different name tags are used.
The values in this list determine the preferred order of name variants,
including language-specific names (in OSM: the name tag with and without any language suffix).
Comma-separated list, where :XX stands for language suffix
(e.g. name:en) and no :XX stands for general tags (e.g. name).
See also [NOMINATIM_DEFAULT_LANGUAGE](#nominatim_default_language).
!!! note
If NOMINATIM_OUTPUT_NAMES = `name:XX,name,short_name:XX,short_name` the search follows
```
'name', 'short_name'
```
if we have no preferred language order for showing search results.
For languages ['en', 'es'] the search follows
```
'name:en', 'name:es',
'name',
'short_name:en', 'short_name:es',
'short_name'
```
For those familiar with the internal implementation, the `_place_*` expansion is added, but to simplify, it is not included in this example.
### Logging Settings
Can be used as the same time as NOMINATIM_LOG_FILE.
#### NOMINATIM_LOG_FILE
@@ -648,67 +631,19 @@ See also [NOMINATIM_DEFAULT_LANGUAGE](#nominatim_default_language).
| **Description:** | Log requests into a file |
| **Format:** | path |
| **Default:** | _empty_ (logging disabled) |
| **After Changes:** | run `nominatim refresh --website` |
Enable logging of requests into a file with this setting by setting the log
file where to log to. A relative file name is assumed to be relative to
the project directory. The format of the log output can be set
with NOMINATIM_LOG_FORMAT.
#### NOMINATIM_LOG_FORMAT
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Log requests into a file |
| **Format:** | [Python String Format](https://docs.python.org/3/library/string.html#formatstrings) string |
| **Default:** | `[{start}] {total_time:.4f} {results_total} {endpoint} "{query_string}"` |
Describes the content of a log line for a single request. The format
must be readable by Python's format function. Nominatim provides a number
of metrics than can be logged. The default set of metrics is the following:
/// html | div.simple-table
| name | type | Description |
| --------------- | ------ | ------------|
| start | time | Point in time when the request arrived. |
| end | time | Point in time when the request was done. |
| query_start | time | Point in time when processing started. |
| total_time | float | Total time in seconds to handle the request. |
| wait_time | float | Time in seconds the request waited for a database connection to be available. |
| query_time | float | Total time in seconds to process the request once a connection was available. |
| results_total | int | Number of results found. |
| endpoint | string | API endpoint used. |
| query_string | string | Raw query string received. |
///
Variables of type 'time' contain a UTC timestamp string in ISO format.
Nominatim also exposes additional metrics to help with development. These
are subject to change between versions:
/// html | div.simple-table
| name | type | Description |
| ------------------------- | ------ | ------------|
| search_rounds | int | Total number of searches executed for the request. |
| search_min_penalty | float | Minimal possible penalty for the request. |
| search_first_result_round | int | Number of first search to yield any result. |
| search_min_result_penalty | float | Minimal penalty by a result found. |
| search_best_penalty_round | int | Search round that yielded the best penalty result. |
///
the project directory.
#### NOMINATIM_DEBUG_SQL
The entries in the log file have the following format:
| Summary | |
| -------------- | --------------------------------------------------- |
| **Description:** | Enable printing of raw SQL by SQLAlchemy |
| **Format:** | boolean |
| **Default:** | no |
| **Comment:** | **For developers only.** |
<request time> <execution time in s> <number of results> <type> "<query string>"
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.
Request time is the time when the request was started. The execution time is
given in ms and corresponds to the time the query took executing in PHP.
type contains the name of the endpoint used.
Can be used as the same time as NOMINATIM_LOG_DB.

View File

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

View File

@@ -4,16 +4,59 @@ The tokenizer module in Nominatim is responsible for analysing the names given
to OSM objects and the terms of an incoming query in order to make sure, they
can be matched appropriately.
Nominatim currently offers only one tokenizer module, the ICU tokenizer. This section
describes the tokenizer and how it can be configured.
Nominatim offers different tokenizer modules, which behave differently and have
different configuration options. This sections describes the tokenizers and how
they can be configured.
!!! important
The selection of tokenizer is tied to a database installation. You need to choose
The use of a tokenizer is tied to a database installation. You need to choose
and configure the tokenizer before starting the initial import. Once the import
is done, you cannot switch to another tokenizer anymore. Reconfiguring the
chosen tokenizer is very limited as well. See the comments in each tokenizer
section.
## Legacy tokenizer
The legacy tokenizer implements the analysis algorithms of older Nominatim
versions. It uses a special Postgresql module to normalize names and queries.
This tokenizer is automatically installed and used when upgrading an older
database. It should not be used for new installations anymore.
### Compiling the PostgreSQL module
The tokeinzer needs a special C module for PostgreSQL which is not compiled
by default. If you need the legacy tokenizer, compile Nominatim as follows:
```
mkdir build
cd build
cmake -DBUILD_MODULE=on
make
```
### Enabling the tokenizer
To enable the tokenizer add the following line to your project configuration:
```
NOMINATIM_TOKENIZER=legacy
```
The Postgresql module for the tokenizer is available in the `module` directory
and also installed with the remainder of the software under
`lib/nominatim/module/nominatim.so`. You can specify a custom location for
the module with
```
NOMINATIM_DATABASE_MODULE_PATH=<path to directory where nominatim.so resides>
```
This is in particular useful when the database runs on a different server.
See [Advanced installations](../admin/Advanced-Installations.md#importing-nominatim-to-an-external-postgresql-database) for details.
There are no other configuration options for the legacy tokenizer. All
normalization functions are hard-coded.
## ICU tokenizer
The ICU tokenizer uses the [ICU library](http://site.icu-project.org/) to
@@ -42,19 +85,10 @@ On import the tokenizer processes names in the following three stages:
See the [Token analysis](#token-analysis) section below for more
information.
During query time, the tokeinzer is responsible for processing incoming
queries. This happens in two stages:
1. During **query preprocessing** the incoming text is split into name
chunks and normalised. This usually means applying the same normalisation
as during the import process but may involve other processing like,
for example, word break detection.
2. The **token analysis** step breaks down the query parts into tokens,
looks them up in the database and assigns them possible functions and
probabilities.
Query processing can be further customized while the rest of the analysis
is hard-coded.
During query time, only normalization and transliteration are relevant.
An incoming query is first split into name chunks (this usually means splitting
the string at the commas) and the each part is normalised and transliterated.
The result is used to look up places in the search index.
### Configuration
@@ -66,17 +100,9 @@ have no effect.
Here is an example configuration file:
``` yaml
query-preprocessing:
- step: split_japanese_phrases
- step: regex_replace
replacements:
- pattern: https?://[^\s]* # Filter URLs starting with http or https
replace: ''
- step: normalize
normalization:
- ":: lower ()"
- "ß > 'ss'" # German szet is unambiguously equal to double ss
- "ß > 'ss'" # German szet is unimbigiously equal to double ss
transliteration:
- !include /etc/nominatim/icu-rules/extended-unicode-to-asccii.yaml
- ":: Ascii ()"
@@ -94,44 +120,15 @@ token-analysis:
replacements: ['ä', 'ae']
```
The configuration file contains five sections:
`query-preprocessing`, `normalization`, `transliteration`, `sanitizers` and `token-analysis`.
#### Query preprocessing
The section for `query-preprocessing` defines an ordered list of functions
that are applied to the query before the token analysis.
The following is a list of preprocessors that are shipped with Nominatim.
##### normalize
::: nominatim_api.query_preprocessing.normalize
options:
members: False
heading_level: 6
docstring_section_style: spacy
##### regex-replace
::: nominatim_api.query_preprocessing.regex_replace
options:
members: False
heading_level: 6
docstring_section_style: spacy
description:
This option runs any given regex pattern on the input and replaces values accordingly
replacements:
- pattern: regex pattern
replace: string to replace with
The configuration file contains four sections:
`normalization`, `transliteration`, `sanitizers` and `token-analysis`.
#### Normalization and Transliteration
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.
@@ -178,67 +175,44 @@ The following is a list of sanitizers that are shipped with Nominatim.
##### split-name-list
::: nominatim_db.tokenizer.sanitizers.split_name_list
options:
::: nominatim.tokenizer.sanitizers.split_name_list
selection:
members: False
rendering:
heading_level: 6
docstring_section_style: spacy
##### strip-brace-terms
::: nominatim_db.tokenizer.sanitizers.strip_brace_terms
options:
::: nominatim.tokenizer.sanitizers.strip_brace_terms
selection:
members: False
rendering:
heading_level: 6
docstring_section_style: spacy
##### tag-analyzer-by-language
::: nominatim_db.tokenizer.sanitizers.tag_analyzer_by_language
options:
::: nominatim.tokenizer.sanitizers.tag_analyzer_by_language
selection:
members: False
rendering:
heading_level: 6
docstring_section_style: spacy
##### clean-housenumbers
::: nominatim_db.tokenizer.sanitizers.clean_housenumbers
options:
::: nominatim.tokenizer.sanitizers.clean_housenumbers
selection:
members: False
rendering:
heading_level: 6
docstring_section_style: spacy
##### clean-postcodes
::: nominatim_db.tokenizer.sanitizers.clean_postcodes
options:
::: nominatim.tokenizer.sanitizers.clean_postcodes
selection:
members: False
rendering:
heading_level: 6
docstring_section_style: spacy
##### clean-tiger-tags
::: nominatim_db.tokenizer.sanitizers.clean_tiger_tags
options:
members: False
heading_level: 6
docstring_section_style: spacy
#### delete-tags
::: nominatim_db.tokenizer.sanitizers.delete_tags
options:
members: False
heading_level: 6
docstring_section_style: spacy
#### tag-japanese
::: nominatim_db.tokenizer.sanitizers.tag_japanese
options:
members: False
heading_level: 6
docstring_section_style: spacy
#### Token Analysis
@@ -397,7 +371,7 @@ The analyzer cannot be customized.
##### Postcode token analyzer
The analyzer `postcodes` is pupose-made to analyze postcodes. It supports
a 'lookup' variant of the token, which produces variants with optional
a 'lookup' varaint of the token, which produces variants with optional
spaces. Use together with the clean-postcodes sanitizer.
The analyzer cannot be customized.

View File

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

View File

@@ -4,19 +4,19 @@ This chapter gives an overview how to set up Nominatim for development
and how to run tests.
!!! Important
This guide assumes you develop under the latest version of Debian/Ubuntu.
You can of course also use your favourite distribution. You just might have
to adapt the commands below slightly, in particular the commands for
installing additional software.
This guide assumes that you develop under the latest version of Ubuntu. You
can of course also use your favourite distribution. You just might have to
adapt the commands below slightly, in particular the commands for installing
additional software.
## Installing Nominatim
The first step is to install Nominatim itself. Please follow the installation
instructions in the [Admin section](../admin/Installation.md). You don't need
to set up a webserver for development, the webserver that can be started
via `nominatim serve` is sufficient.
to set up a webserver for development, the webserver that is included with PHP
is sufficient.
If you want to run Nominatim in a VM via Vagrant, use the default `ubuntu24` setup.
If you want to run Nominatim in a VM via Vagrant, use the default `ubuntu` setup.
Vagrant's libvirt provider runs out-of-the-box under Ubuntu. You also need to
install an NFS daemon to enable directory sharing between host and guest. The
following packages should get you started:
@@ -25,98 +25,75 @@ following packages should get you started:
## Prerequisites for testing and documentation
The Nominatim test suite consists of behavioural tests (using pytest-bdd) and
unit tests (using pytest). It has the following additional requirements:
The Nominatim test suite consists of behavioural tests (using behave) and
unit tests (using PHPUnit for PHP code and pytest for Python code).
It has the following additional requirements:
* [flake8](https://flake8.pycqa.org/en/stable/) (CI always runs the latest version from pip)
* [behave test framework](https://behave.readthedocs.io) >= 1.2.6
* [phpunit](https://phpunit.de) (9.5 is known to work)
* [PHP CodeSniffer](https://github.com/squizlabs/PHP_CodeSniffer)
* [Pylint](https://pylint.org/) (CI always runs the latest version from pip)
* [mypy](http://mypy-lang.org/) (plus typing information for external libs)
* [Python Typing Extensions](https://github.com/python/typing_extensions) (for Python < 3.9)
* [pytest](https://pytest.org)
* [pytest-asyncio](https://pytest-asyncio.readthedocs.io)
* [pytest-bdd](https://pytest-bdd.readthedocs.io)
For testing the Python search frontend, you need to install extra dependencies
depending on your choice of webserver framework:
* [httpx](https://www.python-httpx.org/) (Starlette only)
* [asgi-lifespan](https://github.com/florimondmanca/asgi-lifespan) (Starlette only)
The documentation is built with mkdocs:
* [mkdocs](https://www.mkdocs.org/) >= 1.1.2
* [mkdocstrings](https://mkdocstrings.github.io/) >= 0.25
* [mkdocs-material](https://squidfunk.github.io/mkdocs-material/)
* [mkdocs-gen-files](https://oprypin.github.io/mkdocs-gen-files/)
* [mkdocstrings](https://mkdocstrings.github.io/) >= 0.16
* [mkdocstrings-python-legacy](https://mkdocstrings.github.io/python-legacy/)
### Installing prerequisites on Ubuntu/Debian
The Python tools should always be run with the most recent version.
The easiest way, to handle these Python dependencies is to run your
development from within a virtual environment.
Some of the Python packages require the newest version which is not yet
available with the current distributions. Therefore it is recommended to
install pip to get the newest versions.
To install all necessary packages run:
```sh
sudo apt install libsqlite3-mod-spatialite osm2pgsql \
postgresql-postgis postgresql-postgis-scripts \
pkg-config libicu-dev virtualenv
sudo apt install php-cgi phpunit php-codesniffer \
python3-pip python3-setuptools python3-dev
pip3 install --user behave mkdocs mkdocstrings pytest pylint \
mypy types-PyYAML types-jinja2 types-psycopg2 types-psutil
```
To set up the virtual environment with all necessary packages run:
```sh
virtualenv ~/nominatim-dev-venv
~/nominatim-dev-venv/bin/pip install\
psutil 'psycopg[binary]' PyICU SQLAlchemy \
python-dotenv jinja2 pyYAML \
mkdocs 'mkdocstrings[python]' mkdocs-gen-files \
pytest pytest-asyncio pytest-bdd flake8 \
types-jinja2 types-markupsafe types-psutil types-psycopg2 \
types-pygments types-pyyaml types-requests types-ujson \
types-urllib3 typing-extensions unicorn falcon starlette \
uvicorn mypy osmium aiosqlite mwparserfromhell
```
Now enter the virtual environment whenever you want to develop:
```sh
. ~/nominatim-dev-venv/bin/activate
```
### Running Nominatim during development
The source code for Nominatim can be found in the `src` directory and can
be run in-place. The source directory features a special script
`nominatim-cli.py` which does the same as the installed 'nominatim' binary
but executes against the code in the source tree. For example:
The `mkdocs` executable will be located in `.local/bin`. You may have to add
this directory to your path, for example by running:
```
me@machine:~$ cd Nominatim
me@machine:~Nominatim$ ./nominatim-cli.py --version
Nominatim version 5.1.0-0
echo 'export PATH=~/.local/bin:$PATH' > ~/.profile
```
If your distribution does not have PHPUnit 7.3+, you can install it (as well
as CodeSniffer) via composer:
```
sudo apt-get install composer
composer global require "squizlabs/php_codesniffer=*"
composer global require "phpunit/phpunit=8.*"
```
The binaries are found in `.config/composer/vendor/bin`. You need to add this
to your PATH as well:
```
echo 'export PATH=~/.config/composer/vendor/bin:$PATH' > ~/.profile
```
Make sure you have activated the virtual environment holding all
necessary dependencies.
## Executing Tests
All tests are located in the `/test` directory.
To run all tests, run make from the source root:
To run all tests just go to the build directory and run make:
```sh
make tests
cd build
make test
```
There are also make targets for executing only parts of the test suite.
For example to run linting only use:
```sh
make lint
```
The possible testing targets are: mypy, lint, pytest, bdd.
For more information about the structure of the tests and how to change and
extend the test suite, see the [Testing chapter](Testing.md).
@@ -127,14 +104,18 @@ built using the [MkDocs](https://www.mkdocs.org/) static site generation
framework. The master branch is automatically deployed every night on
[https://nominatim.org/release-docs/develop/](https://nominatim.org/release-docs/develop/)
To build the documentation run
To build the documentation, go to the build directory and run
```
make doc
INFO - Cleaning site directory
INFO - Building documentation to directory: /home/vagrant/build/site-html
```
This runs `mkdocs build` plus extra transformation of some files and adds
symlinks (see `CMakeLists.txt` for the exact steps).
For local testing, you can start webserver:
Now you can start webserver for local testing
```
build> make serve-doc
@@ -146,7 +127,7 @@ If you develop inside a Vagrant virtual machine, use a port that is forwarded
to your host:
```
build> mkdocs serve --dev-addr 0.0.0.0:8088
build> PYTHONPATH=$SRCDIR mkdocs serve --dev-addr 0.0.0.0:8088
[server:296] Serving on http://0.0.0.0:8088
[handlers:62] Start watching changes
```

View File

@@ -14,11 +14,10 @@ of sanitizers and token analysis.
implemented, it is not guaranteed to be stable at the moment.
## Using non-standard modules
## Using non-standard sanitizers and token analyzers
Sanitizer names (in the `step` property), token analysis names (in the
`analyzer`) and query preprocessor names (in the `step` property)
may refer to externally supplied modules. There are two ways
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
@@ -28,53 +27,6 @@ To use a custom module without creating a library, you can put the module
somewhere in your project directory and then use the relative path to the
file. Include the whole name of the file including the `.py` ending.
## Custom query preprocessors
A query preprocessor must export a single factory function `create` with
the following signature:
``` python
create(self, config: QueryConfig) -> Callable[[list[Phrase]], list[Phrase]]
```
The function receives the custom configuration for the preprocessor and
returns a callable (function or class) with the actual preprocessing
code. When a query comes in, then the callable gets a list of phrases
and needs to return the transformed list of phrases. The list and phrases
may be changed in place or a completely new list may be generated.
The `QueryConfig` is a simple dictionary which contains all configuration
options given in the yaml configuration of the ICU tokenizer. It is up to
the function to interpret the values.
A `nominatim_api.search.Phrase` describes a part of the query that contains one or more independent
search terms. Breaking a query into phrases helps reducing the number of
possible tokens Nominatim has to take into account. However a phrase break
is definitive: a multi-term search word cannot go over a phrase break.
A Phrase object has two fields:
* `ptype` further refines the type of phrase (see list below)
* `text` contains the query text for the phrase
The order of phrases matters to Nominatim when doing further processing.
Thus, while you may split or join phrases, you should not reorder them
unless you really know what you are doing.
Phrase types can further help narrowing down how the tokens in the phrase
are interpreted. The following phrase types are known:
| Name | Description |
|----------------|-------------|
| PHRASE_ANY | No specific designation (i.e. source is free-form query) |
| PHRASE_AMENITY | Contains name or type of a POI |
| PHRASE_STREET | Contains a street name optionally with a housenumber |
| PHRASE_CITY | Contains the postal city |
| PHRASE_COUNTY | Contains the equivalent of a county |
| PHRASE_STATE | Contains a state or province |
| PHRASE_POSTCODE| Contains a postal code |
| PHRASE_COUNTRY | Contains the country name or code |
## Custom sanitizer modules
A sanitizer module must export a single factory function `create` with the
@@ -100,8 +52,9 @@ the function.
### Sanitizer configuration
::: nominatim_db.tokenizer.sanitizers.config.SanitizerConfig
options:
::: nominatim.tokenizer.sanitizers.config.SanitizerConfig
rendering:
show_source: no
heading_level: 6
### The main filter function of the sanitizer
@@ -109,10 +62,12 @@ the function.
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.
* `place`: 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.
* `names`: The current list of names for the place. Each name is a
PlaceName object.
* `address`: The current list of address names for the place. Each name
is a PlaceName object.
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
@@ -121,15 +76,17 @@ adding extra attributes) or completely replace the list with a different one.
#### PlaceInfo - information about the place
::: nominatim_db.data.place_info.PlaceInfo
options:
::: nominatim.data.place_info.PlaceInfo
rendering:
show_source: no
heading_level: 6
#### PlaceName - extended naming information
::: nominatim_db.data.place_name.PlaceName
options:
::: nominatim.data.place_name.PlaceName
rendering:
show_source: no
heading_level: 6
@@ -138,22 +95,21 @@ adding extra attributes) or completely replace the list with a different one.
The following sanitizer removes the directional prefixes from street names
in the US:
!!! example
``` python
import re
``` python
import re
def _filter_function(obj):
if obj.place.country_code == 'us' \
and obj.place.rank_address >= 26 and obj.place.rank_address <= 27:
for name in obj.names:
name.name = re.sub(r'^(north|south|west|east) ',
'',
name.name,
flags=re.IGNORECASE)
def _filter_function(obj):
if obj.place.country_code == 'us' \
and obj.place.rank_address >= 26 and obj.place.rank_address <= 27:
for name in obj.names:
name.name = re.sub(r'^(north|south|west|east) ',
'',
name.name,
flags=re.IGNORECASE)
def create(config):
return _filter_function
```
def create(config):
return _filter_function
```
This is the most simple form of a sanitizer module. If defines a single
filter function and implements the required `create()` function by returning
@@ -177,24 +133,26 @@ sanitizers:
!!! warning
This example is just a simplified show case on how to create a sanitizer.
It is not really meant for real-world use: while the sanitizer would
correctly transform `West 5th Street` into `5th Street`. it would also
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
[`src/nominatim_db/tokenizer/sanitizers`](https://github.com/osm-search/Nominatim/tree/master/src/nominatim_db/tokenizer/sanitizers).
[`nominatim/tokenizer/sanitizers`](https://github.com/osm-search/Nominatim/tree/master/nominatim/tokenizer/sanitizers).
## Custom token analysis module
::: nominatim_db.tokenizer.token_analysis.base.AnalysisModule
options:
::: nominatim.tokenizer.token_analysis.base.AnalysisModule
rendering:
show_source: no
heading_level: 6
::: nominatim_db.tokenizer.token_analysis.base.Analyzer
options:
::: nominatim.tokenizer.token_analysis.base.Analyzer
rendering:
show_source: no
heading_level: 6
### Example: Creating acronym variants for long names

View File

@@ -8,9 +8,9 @@ the tests, see the [Development setup chapter](Development-Environment.md).
There are two kind of tests in this test suite. There are functional tests
which test the API interface using a BDD test framework and there are unit
tests for the Python code.
tests for specific PHP functions.
This test directory is structured as follows:
This test directory is sturctured as follows:
```
-+- bdd Functional API tests
@@ -20,11 +20,28 @@ This test directory is structured as follows:
| +- db Tests for internal data processing on import and update
| +- api Tests for API endpoints (search, reverse, etc.)
|
+- php PHP unit tests
+- python Python unit tests
+- testdb Base data for generating API test database
+- testdata Additional test data used by unit tests
```
## PHP Unit Tests (`test/php`)
Unit tests for PHP code can be found in the `php/` directory. They test selected
PHP functions. Very low coverage.
To execute the test suite run
cd test/php
UNIT_TEST_DSN='pgsql:dbname=nominatim_unit_tests' phpunit ../
It will read phpunit.xml which points to the library, test path, bootstrap
strip and sets other parameters.
It will use (and destroy) a local database 'nominatim_unit_tests'. You can set
a different connection string with e.g. UNIT_TEST_DSN='pgsql:dbname=foo_unit_tests'.
## Python Unit Tests (`test/python`)
Unit tests for Python code can be found in the `python/` directory. The goal is
@@ -43,62 +60,54 @@ The name of the pytest binary depends on your installation.
## BDD Functional Tests (`test/bdd`)
Functional tests are written as BDD instructions. For more information on
the philosophy of BDD testing, read the Wikipedia article on
[Behaviour-driven development](https://en.wikipedia.org/wiki/Behavior-driven_development).
the philosophy of BDD testing, see the
[Behave manual](http://pythonhosted.org/behave/philosophy.html).
The following explanation assume that the reader is familiar with the BDD
notations of features, scenarios and steps.
All possible steps can be found in the `steps` directory and should ideally
be documented.
### General Usage
To run the functional tests, do
pytest test/bdd
cd test/bdd
behave
You can run a single feature file using expression matching:
The tests can be configured with a set of environment variables (`behave -D key=val`):
pytest test/bdd -k osm2pgsql/import/entrances.feature
This even works for running single tests by adding the line number of the
scenario header like that:
pytest test/bdd -k 'osm2pgsql/import/entrances.feature and L4'
The BDD tests create databases for the tests. You can set name of the databases
through configuration variables in your `pytest.ini`:
* `nominatim_test_db` defines the name of the temporary database created for
a single test (default: `test_nominatim`)
* `nominatim_api_test_db` defines the name of the database containing
the API test data, see also below (default: `test_api_nominatim`)
* `nominatim_template_db` defines the name of the template database used
for creating the temporary test databases. It contains some static setup
which usually doesn't change between imports of OSM data
(default: `test_template_nominatim`)
To change other connection parameters for the PostgreSQL database, use
the [libpq enivronment variables](https://www.postgresql.org/docs/current/libpq-envars.html).
Never set a password through these variables. Use a
[password file](https://www.postgresql.org/docs/current/libpq-pgpass.html) instead.
The API test database and the template database are only created once and then
left untouched. This is usually what you want because it speeds up subsequent
runs of BDD tests. If you do change code that has an influence on the content
of these databases, you can run pytest with the `--nominatim-purge` parameter
and the databases will be dropped and recreated from scratch.
When running the BDD tests with make (using `make tests` or `make bdd`), then
the databases will always be purged.
The temporary test database is usually dropped directly after the test, so
it does not take up unnecessary space. If you want to keep the database around,
for example while debugging a specific BDD test, use the parameter
`--nominatim-keep-db`.
* `BUILDDIR` - build directory of Nominatim installation to test
* `TEMPLATE_DB` - name of template database used as a skeleton for
the test databases (db tests)
* `TEST_DB` - name of test database (db tests)
* `API_TEST_DB` - name of the database containing the API test data (api tests)
* `API_TEST_FILE` - OSM file to be imported into the API test database (api tests)
* `DB_HOST` - (optional) hostname of database host
* `DB_PORT` - (optional) port of database on host
* `DB_USER` - (optional) username of database login
* `DB_PASS` - (optional) password for database login
* `SERVER_MODULE_PATH` - (optional) path on the Postgres server to Nominatim
module shared library file
* `REMOVE_TEMPLATE` - if true, the template and API database will not be reused
during the next run. Reusing the base templates speeds
up tests considerably but might lead to outdated errors
for some changes in the database layout.
* `KEEP_TEST_DB` - if true, the test database will not be dropped after a test
is finished. Should only be used if one single scenario is
run, otherwise the result is undefined.
Logging can be defined through command line parameters of behave itself. Check
out `behave --help` for details. Also have a look at the 'work-in-progress'
feature of behave which comes in handy when writing new tests.
### API Tests (`test/bdd/api`)
These tests are meant to test the different API endpoints and their parameters.
They require to import several datasets into a test database. This is normally
done automatically during setup of the test. The API test database is then
kept around and reused in subsequent runs of behave. Use `--nominatim-purge`
kept around and reused in subsequent runs of behave. Use `behave -DREMOVE_TEMPLATE`
to force a reimport of the database.
The official test dataset is saved in the file `test/testdb/apidb-test-data.pbf`
@@ -108,9 +117,26 @@ and compromises the following data:
* extract of Autauga country, Alabama, US (for tests against Tiger data)
* additional data from `test/testdb/additional_api_test.data.osm`
API tests should only be testing the functionality of the website frontend code.
API tests should only be testing the functionality of the website PHP code.
Most tests should be formulated as BDD DB creation tests (see below) instead.
#### Code Coverage
The API tests also support code coverage tests. You need to install
[PHP_CodeCoverage](https://github.com/sebastianbergmann/php-code-coverage).
On Debian/Ubuntu run:
apt-get install php-codecoverage php-xdebug
Then run the API tests as follows:
behave api -DPHPCOV=<coverage output dir>
The output directory must be an absolute path. To generate reports, you can use
the [phpcov](https://github.com/sebastianbergmann/phpcov) tool:
phpcov merge --html=<report output dir> <coverage output dir>
### DB Creation Tests (`test/bdd/db`)
These tests check the import and update of the Nominatim database. They do not
@@ -118,12 +144,16 @@ test the correctness of osm2pgsql. Each test will write some data into the `plac
table (and optionally the `planet_osm_*` tables if required) and then run
Nominatim's processing functions on that.
These tests use the template database and create temporary test databases for
each test.
These tests need to create their own test databases. By default they will be
called `test_template_nominatim` and `test_nominatim`. Names can be changed with
the environment variables `TEMPLATE_DB` and `TEST_DB`. The user running the tests
needs superuser rights for postgres.
### Import Tests (`test/bdd/osm2pgsql`)
These tests check that data is imported correctly into the place table.
These tests check that data is imported correctly into the place table. They
use the same template database as the DB Creation tests, so the same remarks apply.
These tests also use the template database and create temporary test databases
for each test.
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

@@ -91,19 +91,19 @@ for a custom tokenizer implementation.
### Directory Structure
Nominatim expects two files containing the Python part of the implementation:
Nominatim expects two files for a tokenizer:
* `src/nominatim_db/tokenizer/<NAME>_tokenizer.py` contains the tokenizer
code used during import and
* `src/nominatim_api/search/<NAME>_tokenizer.py` has the code used during
query time.
* `nominatim/tokenizer/<NAME>_tokenizer.py` containing the Python part of the
implementation
* `lib-php/tokenizer/<NAME>_tokenizer.php` with the PHP part of the
implementation
`<NAME>` is a unique name for the tokenizer consisting of only lower-case
where `<NAME>` is a unique name for the tokenizer consisting of only lower-case
letters, digits and underscore. A tokenizer also needs to install some SQL
functions. By convention, these should be placed in `lib-sql/tokenizer`.
If the tokenizer has a default configuration file, this should be saved in
`settings/<NAME>_tokenizer.<SUFFIX>`.
the `settings/<NAME>_tokenizer.<SUFFIX>`.
### Configuration and Persistence
@@ -115,11 +115,9 @@ are tied to a database installation and must only be read during installation
time. If they are needed for the runtime then they must be saved into the
`nominatim_properties` table and later loaded from there.
### The Python modules
### The Python module
#### `src/nominatim_db/tokenizer/`
The import Python module is expected to export a single factory function:
The Python module is expect to export a single factory function:
```python
def create(dsn: str, data_dir: Path) -> AbstractTokenizer
@@ -130,41 +128,20 @@ is a directory in the project directory that the tokenizer may use to save
database-specific data. The function must return the instance of the tokenizer
class as defined below.
#### `src/nominatim_api/search/`
The query-time Python module must also export a factory function:
``` python
def create_query_analyzer(conn: SearchConnection) -> AbstractQueryAnalyzer
```
The `conn` parameter contains the current search connection. See the
[library documentation](../library/Low-Level-DB-Access.md#searchconnection-class)
for details on the class. The function must return the instance of the tokenizer
class as defined below.
### Python Tokenizer Class
All tokenizers must inherit from `nominatim_db.tokenizer.base.AbstractTokenizer`
All tokenizers must inherit from `nominatim.tokenizer.base.AbstractTokenizer`
and implement the abstract functions defined there.
::: nominatim_db.tokenizer.base.AbstractTokenizer
options:
heading_level: 6
::: nominatim.tokenizer.base.AbstractTokenizer
rendering:
heading_level: 4
### Python Analyzer Class
::: nominatim_db.tokenizer.base.AbstractAnalyzer
options:
heading_level: 6
### Python Query Analyzer Class
::: nominatim_api.search.query_analyzer_factory.AbstractQueryAnalyzer
options:
heading_level: 6
::: nominatim.tokenizer.base.AbstractAnalyzer
rendering:
heading_level: 4
### PL/pgSQL Functions
@@ -212,28 +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
```
@@ -305,3 +260,73 @@ permanently. The indexer calls this function when all processing is done and
replaces the content of the `token_info` column with the returned value before
the trigger stores the information in the database. May return NULL if no
information should be stored permanently.
### PHP Tokenizer class
The PHP tokenizer class is instantiated once per request and responsible for
analyzing the incoming query. Multiple requests may be in flight in
parallel.
The class is expected to be found under the
name of `\Nominatim\Tokenizer`. To find the class the PHP code includes the file
`tokenizer/tokenizer.php` in the project directory. This file must be created
when the tokenizer is first set up on import. The file should initialize any
configuration variables by setting PHP constants and then require the file
with the actual implementation of the tokenizer.
The tokenizer class must implement the following functions:
```php
public function __construct(object &$oDB)
```
The constructor of the class receives a database connection that can be used
to query persistent data in the database.
```php
public function checkStatus()
```
Check that the tokenizer can access its persistent data structures. If there
is an issue, throw an `\Exception`.
```php
public function normalizeString(string $sTerm) : string
```
Normalize string to a form to be used for comparisons when reordering results.
Nominatim reweighs results how well the final display string matches the actual
query. Before comparing result and query, names and query are normalised against
this function. The tokenizer can thus remove all properties that should not be
taken into account for reweighing, e.g. special characters or case.
```php
public function tokensForSpecialTerm(string $sTerm) : array
```
Return the list of special term tokens that match the given term.
```php
public function extractTokensFromPhrases(array &$aPhrases) : TokenList
```
Parse the given phrases, splitting them into word lists and retrieve the
matching tokens.
The phrase array may take on two forms. In unstructured searches (using `q=`
parameter) the search query is split at the commas and the elements are
put into a sorted list. For structured searches the phrase array is an
associative array where the key designates the type of the term (street, city,
county etc.) The tokenizer may ignore the phrase type at this stage in parsing.
Matching phrase type and appropriate search token type will be done later
when the SearchDescription is built.
For each phrase in the list of phrases, the function must analyse the phrase
string and then call `setWordSets()` to communicate the result of the analysis.
A word set is a list of strings, where each string refers to a search token.
A phrase may have multiple interpretations. Therefore a list of word sets is
usually attached to the phrase. The search tokens themselves are returned
by the function in an associative array, where the key corresponds to the
strings given in the word sets. The value is a list of search tokens. Thus
a single string in the list of word sets may refer to multiple search tokens.

View File

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

View File

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

File diff suppressed because one or more lines are too long

Before

Width:  |  Height:  |  Size: 9.8 KiB

After

Width:  |  Height:  |  Size: 9.8 KiB

View File

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

View File

@@ -2,10 +2,6 @@
display: none!important
}
.md-content {
max-width: 800px
}
table {
margin-bottom: 12pt
}
@@ -20,28 +16,9 @@ th {
.doc-object h6 {
margin-bottom: 0.8em;
font-size: 130%;
font-size: 120%;
}
.doc-object {
margin-bottom: 1.3em;
}
.doc-children .doc-contents {
margin-left: 3em;
}
.md-footer__inner {
display: none;
}
.headerlink {
filter: grayscale(100%);
font-size: 80%;
}
.simple-table table:not([class]) th,
.simple-table table:not([class]) td {
padding: 2px 4px;
background: white;
}

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

@@ -1,33 +0,0 @@
# Configuration
When using Nominatim through the library, it can be configured in exactly
the same way as when running as a service. You may instantiate the library
against the [project directory](../admin/Import.md#creating-the-project-directory)
of your Nominatim installation. It contains all files belonging to the
Nominatim instance. This may include an `.env` file with configuration options.
Setting configuration parameters via environment variables works as well.
Alternatively to using the operating system's environment, a set of
configuration parameters may also be passed to the Nomiantim API object.
Configuration options are resolved in the following order:
* from the OS environment (or the dictionary given in `environ`,
(see NominatimAPI.md#nominatim.api.core.NominatimAPI.__init__)
* from the .env file in the project directory of the installation
* from the default installation in the configuration directory
For more information on configuration via dotenv and a list of possible
configuration parameters, see the [Configuration page](../customize/Settings.md).
## `Configuration` class
::: nominatim_api.Configuration
options:
members:
- get_bool
- get_int
- get_str_list
- get_path
heading_level: 6
show_signature_annotations: True

View File

@@ -1,293 +0,0 @@
# Getting Started
The Nominatim search frontend is implemented as a Python library and can as
such directly be used in Python scripts and applications. You don't need to
set up a web frontend and access it through HTTP calls. The library gives
direct access to the Nominatim database through similar search functions as
offered by the web API. In addition, it will give you a more complete and
detailed view on the search objects stored in the database.
!!! warning
The Nominatim library is used for accessing a local Nominatim database.
It is not meant to be used against web services of Nominatim like the
one on https://nominatim.openstreetmap.org. If you need a Python library
to access these web services, have a look at
[GeoPy](https://geopy.readthedocs.io). Don't forget to consult the
usage policy of the service you want to use before accessing such
a web service.
## Installation
To use the Nominatim library, you need access to a local Nominatim database.
Follow the [installation](../admin/Installation.md) and
[import](../admin/Import.md) instructions to set up your database.
The Nominatim frontend library is contained in the Python package `nominatim-api`.
You can install the latest released version directly from pip:
pip install nominatim-api
To install the package from the source tree directly, run:
pip install packaging/nominatim-api
Usually you would want to run this in a virtual environment.
## A simple search example
To query the Nominatim database you need to first set up a connection. This
is done by creating an Nominatim API object. This object exposes all the
search functions of Nominatim that are also known from its web API.
This code snippet implements a simple search for the town of 'Brugge':
!!! example
=== "NominatimAPIAsync"
``` python
import asyncio
import nominatim_api as napi
async def search(query):
async with napi.NominatimAPIAsync() as api:
return await api.search(query)
results = asyncio.run(search('Brugge'))
if not results:
print('Cannot find Brugge')
else:
print(f'Found a place at {results[0].centroid.x},{results[0].centroid.y}')
```
=== "NominatimAPI"
``` python
import nominatim_api as napi
with napi.NominatimAPI() as api:
results = api.search('Brugge')
if not results:
print('Cannot find Brugge')
else:
print(f'Found a place at {results[0].centroid.x},{results[0].centroid.y}')
```
The Nominatim library is designed around
[asyncio](https://docs.python.org/3/library/asyncio.html). `NominatimAPIAsync`
provides you with an interface of coroutines.
If you have many requests to make, coroutines can speed up your applications
significantly.
For smaller scripts there is also a synchronous wrapper around the API. By
using `NominatimAPI`, you get exactly the same interface using classic functions.
The examples in this chapter will always show-case both
implementations. The documentation itself will usually refer only to
'Nominatim API class' when both flavours are meant. If a functionality is
available only for the synchronous or asynchronous version, this will be
explicitly mentioned.
## Defining which database to use
The [Configuration](../admin/Import.md#configuration-setup-in-env)
section explains how Nominatim is configured using the
[dotenv](https://github.com/theskumar/python-dotenv) library.
The same configuration mechanism is used with the
Nominatim API library. You should therefore be sure you are familiar with
the section.
There are three different ways, how configuration options can be set for
a 'Nominatim API class'. When you have set up your Nominatim database, you
have normally created a [project directory](../admin/Import.md#creating-the-project-directory)
which stores the various configuration and customization files that Nominatim
needs. You may pass the location of the project directory to your
'Nominatim API class' constructor and it will read the .env file in the
directory and set the configuration accordingly. Here is the simple search
example, using the configuration from a pre-defined project directory in
`/srv/nominatim-project`:
!!! example
=== "NominatimAPIAsync"
``` python
import asyncio
import nominatim_api as napi
async def search(query):
async with napi.NominatimAPIAsync('/srv/nominatim-project') as api:
return await api.search(query)
results = asyncio.run(search('Brugge'))
if not results:
print('Cannot find Brugge')
else:
print(f'Found a place at {results[0].centroid.x},{results[0].centroid.y}')
```
=== "NominatimAPI"
``` python
import nominatim_api as napi
with napi.NominatimAPI('/srv/nominatim-project') as api:
results = api.search('Brugge')
if not results:
print('Cannot find Brugge')
else:
print(f'Found a place at {results[0].centroid.x},{results[0].centroid.y}')
```
You may also configure Nominatim by setting environment variables.
Normally Nominatim will check the operating system environment. Lets
say you want to look up 'Brugge' in the special database named 'belgium' instead of the
standard 'nominatim' database. You can run the example script above like this:
```
NOMINATIM_DATABASE_DSN=pgsql:dbname=belgium python3 example.py
```
The third option to configure the library is to hand in the configuration
parameters into the 'Nominatim API class'. Changing the database would look
like this:
!!! example
=== "NominatimAPIAsync"
``` python
import asyncio
import nominatim_api as napi
config_params = {
'NOMINATIM_DATABASE_DSN': 'pgsql:dbname=belgium'
}
async def search(query):
async with napi.NominatimAPIAsync(environ=config_params) as api:
return await api.search(query)
results = asyncio.run(search('Brugge'))
```
=== "NominatimAPI"
``` python
import nominatim_api as napi
config_params = {
'NOMINATIM_DATABASE_DSN': 'pgsql:dbname=belgium'
}
with napi.NominatimAPI(environ=config_params) as api:
results = api.search('Brugge')
```
When the `environ` parameter is given, then only configuration variables
from this dictionary will be used. The operating system's environment
variables will be ignored.
## Presenting results to humans
All search functions return full result objects from the database. Such a
result object contains lots of details: names, address information, OSM tags etc.
This gives you lots of flexibility what to do with the results.
One of the most common things to get is some kind of human-readable label
that describes the result in a compact form. Usually this would be the name
of the object and some parts of the address to explain where in the world
it is. To create such a label, you need two things:
* the address details of the place
* all names for the label adapted to the language you wish to use for display
Again searching for 'Brugge', this time with a nicely formatted result:
!!! example
=== "NominatimAPIAsync"
``` python
import asyncio
import nominatim_api as napi
async def search(query):
async with napi.NominatimAPIAsync() as api:
return await api.search(query, address_details=True)
results = asyncio.run(search('Brugge'))
locale = napi.Locales(['fr', 'en'])
for i, result in enumerate(results):
address_parts = result.address_rows.localize(locale)
print(f"{i + 1}. {', '.join(address_parts)}")
```
=== "NominatimAPI"
``` python
import nominatim_api as napi
with napi.NominatimAPI() as api:
results = api.search('Brugge', address_details=True)
locale = napi.Locales(['fr', 'en'])
for i, result in enumerate(results):
address_parts = result.address_rows.localize(locale)
print(f"{i + 1}. {', '.join(address_parts)}")
```
To request information about the address of a result, add the optional
parameter 'address_details' to your search:
``` python
>>> results = api.search('Brugge', address_details=True)
```
An additional field `address_rows` will set in results that are returned.
It contains a list of all places that make up the address of the place. For
simplicity, this includes name and house number of the place itself. With
the names in this list it is possible to create a human-readable description
of the result. To do that, you first need to decide in which language the
results should be presented. As with the names in the result itself, the
places in `address_rows` contain all possible name translation for each row.
The library has a helper class `Locales` which helps extracting a name of a
place in the preferred language. It takes a single parameter with a list
of language codes in the order of preference. So
``` python
locale = napi.Locales(['fr', 'en'])
```
creates a helper class that returns the name preferably in French. If that is
not possible, it tries English and eventually falls back to the default `name`
or `ref`.
The `Locales` 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 compute the display name for each Address Line
component based on its `local_name` field. This is then utilized by the overall `result` object,
which has a helper function to apply the function to all its address_row members and saves
the result in the `locale_name` field.
However, in order to set this `local_name` field in a preferred language, you must use the `Locales`
object which contains the function `localize_results`, which explicitly sets each `local_name field`.
``` python
>>> Locales().localize_results(results)
>>> address_parts = results[0].address_rows
>>> print(', '.join(address_parts))
Bruges, Flandre-Occidentale, Flandre, Belgique
```
This is a fairly simple way to create a human-readable description. The
place information in `address_rows` contains further information about each
place. For example, which OSM `admin_level` was used, what category the place
belongs to or what rank Nominatim has assigned. Use this to adapt the output
to local address formats.
For more information on address rows, see
[detailed address description](Result-Handling.md#detailed-address-description).

View File

@@ -1,60 +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.NominatimAPI.details) and
[lookup](NominatimAPI.md#nominatim_api.NominatimAPI.lookup) functions
require references to places in the database. Below the possible
types for place identification are listed. All types are dataclasses.
### PlaceID
::: nominatim_api.PlaceID
options:
heading_level: 6
### OsmID
::: nominatim_api.OsmID
options:
heading_level: 6
## Geometry types
::: nominatim_api.GeometryFormat
options:
heading_level: 6
members_order: source
## Geometry input
### Point
::: nominatim_api.Point
options:
heading_level: 6
show_signature_annotations: True
### Bbox
::: nominatim_api.Bbox
options:
heading_level: 6
show_signature_annotations: True
members_order: source
group_by_category: False
## Layers
Layers allow to restrict the search result to thematic groups. This is
orthogonal to restriction by address ranks, which groups places by their
geographic extent.
::: nominatim_api.DataLayer
options:
heading_level: 6
members_order: source

View File

@@ -1,55 +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
import sqlalchemy as sa
from nominatim_api import NominatimAPIAsync
async def print_table_size():
api = NominatimAPIAsync()
async with api.begin() as conn:
cnt = await conn.scalar(sa.select(sa.func.count()).select_from(conn.t.placex))
print(f'placex table has {cnt} rows.')
asyncio.run(print_table_size())
```
!!! warning
Low-level connections may only be used to read data from the database.
Do not use it to add or modify data or you might break Nominatim's
normal functions.
## SearchConnection class
::: nominatim_api.SearchConnection
options:
members:
- scalar
- execute
- get_class_table
- get_db_property
- get_property
heading_level: 6

View File

@@ -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

@@ -1,62 +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. However, the
default `locale_name` must be explicitly set using the `localize` function within
`Locales`. This parses through the full list of available names to find the one
most preferred by the user. Once this is set, the user can simply use the
`display_name` field within a `Result` object to retrive the localized name.
### Locale
::: nominatim_api.Locales
options:
heading_level: 6

View File

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

View File

@@ -1,14 +1,6 @@
site_name: Nominatim Manual
theme:
font: false
name: material
features:
- navigation.tabs
- toc.integrate
plugins:
- privacy
copyright: Copyright &copy; Nominatim developer community
docs_dir: docs
site_name: Nominatim 4.1.1
theme: readthedocs
docs_dir: ${CMAKE_CURRENT_BINARY_DIR}
site_url: https://nominatim.org
repo_url: https://github.com/openstreetmap/Nominatim
nav:
@@ -26,34 +18,22 @@ nav:
- 'Basic Installation': 'admin/Installation.md'
- 'Import' : 'admin/Import.md'
- 'Update' : 'admin/Update.md'
- 'Deploy' : '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'
- 'Migration from older Versions' : 'admin/Migration.md'
- 'Troubleshooting' : 'admin/Faq.md'
- 'Installation on Ubuntu 22' : 'admin/Install-on-Ubuntu-22.md'
- 'Installation on Ubuntu 24' : 'admin/Install-on-Ubuntu-24.md'
- 'Customization Guide':
- 'Overview': 'customize/Overview.md'
- 'Import Styles': 'customize/Import-Styles.md'
- 'Configuration Settings': 'customize/Settings.md'
- 'API Result Formatting': 'customize/Result-Formatting.md'
- 'Per-Country Data': 'customize/Country-Settings.md'
- 'Place Ranking' : 'customize/Ranking.md'
- 'Importance' : 'customize/Importance.md'
- 'Tokenizers' : 'customize/Tokenizers.md'
- 'Special Phrases': 'customize/Special-Phrases.md'
- 'External data: US housenumbers from TIGER': 'customize/Tiger.md'
- 'External data: Postcodes': 'customize/Postcodes.md'
- 'Conversion to SQLite': 'customize/SQLite.md'
- 'Library Guide':
- 'Getting Started': 'library/Getting-Started.md'
- 'Nominatim API class': 'library/NominatimAPI.md'
- 'Configuration': 'library/Configuration.md'
- 'Input Parameter Types': 'library/Input-Parameter-Types.md'
- 'Result Handling': 'library/Result-Handling.md'
- 'Low-level DB Access': 'library/Low-Level-DB-Access.md'
- 'Developers Guide':
- 'Architecture Overview' : 'develop/overview.md'
- 'Database Layout' : 'develop/Database-Layout.md'
@@ -63,30 +43,22 @@ nav:
- 'Setup for Development' : 'develop/Development-Environment.md'
- 'Testing' : 'develop/Testing.md'
- 'External Data Sources': 'develop/data-sources.md'
- 'Appendix':
- 'Installation on Ubuntu 18' : 'appendix/Install-on-Ubuntu-18.md'
- 'Installation on Ubuntu 20' : 'appendix/Install-on-Ubuntu-20.md'
- 'Installation on Ubuntu 22' : 'appendix/Install-on-Ubuntu-22.md'
markdown_extensions:
- codehilite
- admonition
- pymdownx.superfences
- pymdownx.blocks.html
- pymdownx.tabbed:
alternate_style: true
- def_list
- toc:
toc_depth: 4
permalink: 🔗
permalink:
extra_css: [extra.css, styles.css]
exclude_docs: |
mk_install_instructions.py
site_dir: site-html
plugins:
- search
- mkdocstrings:
handlers:
python:
paths: ["src"]
options:
show_source: False
show_bases: False
- gen-files:
scripts:
- docs/mk_install_instructions.py
python-legacy:
rendering:
show_source: false
show_signature_annotations: false

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

File diff suppressed because it is too large Load Diff

View File

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

View File

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

View File

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

View File

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

View File

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

191
lib-php/AddressDetails.php Normal file
View File

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

576
lib-php/ClassTypes.php Normal file
View File

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

360
lib-php/DB.php Normal file
View File

@@ -0,0 +1,360 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
require_once(CONST_LibDir.'/DatabaseError.php');
/**
* Uses PDO to access the database specified in the CONST_Database_DSN
* setting.
*/
class DB
{
protected $connection;
public function __construct($sDSN = null)
{
$this->sDSN = $sDSN ?? getSetting('DATABASE_DSN');
}
public function connect($bNew = false, $bPersistent = true)
{
if (isset($this->connection) && !$bNew) {
return true;
}
$aConnOptions = array(
\PDO::ATTR_ERRMODE => \PDO::ERRMODE_EXCEPTION,
\PDO::ATTR_DEFAULT_FETCH_MODE => \PDO::FETCH_ASSOC,
\PDO::ATTR_PERSISTENT => $bPersistent
);
// https://secure.php.net/manual/en/ref.pdo-pgsql.connection.php
try {
$conn = new \PDO($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());
}
$conn->exec("SET DateStyle TO 'sql,european'");
$conn->exec("SET client_encoding TO 'utf-8'");
// Disable JIT and parallel workers. They interfere badly with search SQL.
$conn->exec("UPDATE pg_settings SET setting = -1 WHERE name = 'jit_above_cost'");
$conn->exec("UPDATE pg_settings SET setting = 0 WHERE name = 'max_parallel_workers_per_gather'");
$iMaxExecution = ini_get('max_execution_time');
if ($iMaxExecution > 0) {
$conn->setAttribute(\PDO::ATTR_TIMEOUT, $iMaxExecution); // seconds
}
$this->connection = $conn;
return true;
}
// returns the number of rows that were modified or deleted by the SQL
// statement. If no rows were affected returns 0.
public function exec($sSQL, $aInputVars = null, $sErrMessage = 'Database query failed')
{
$val = null;
try {
if (isset($aInputVars)) {
$stmt = $this->connection->prepare($sSQL);
$stmt->execute($aInputVars);
} else {
$val = $this->connection->exec($sSQL);
}
} catch (\PDOException $e) {
throw new \Nominatim\DatabaseError($sErrMessage, 500, null, $e, $sSQL);
}
return $val;
}
/**
* Executes query. Returns first row as array.
* Returns false if no result found.
*
* @param string $sSQL
*
* @return array[]
*/
public function getRow($sSQL, $aInputVars = null, $sErrMessage = 'Database query failed')
{
try {
$stmt = $this->getQueryStatement($sSQL, $aInputVars, $sErrMessage);
$row = $stmt->fetch();
} catch (\PDOException $e) {
throw new \Nominatim\DatabaseError($sErrMessage, 500, null, $e, $sSQL);
}
return $row;
}
/**
* Executes query. Returns first value of first result.
* Returns false if no results found.
*
* @param string $sSQL
*
* @return array[]
*/
public function getOne($sSQL, $aInputVars = null, $sErrMessage = 'Database query failed')
{
try {
$stmt = $this->getQueryStatement($sSQL, $aInputVars, $sErrMessage);
$row = $stmt->fetch(\PDO::FETCH_NUM);
if ($row === false) {
return false;
}
} catch (\PDOException $e) {
throw new \Nominatim\DatabaseError($sErrMessage, 500, null, $e, $sSQL);
}
return $row[0];
}
/**
* Executes query. Returns array of results (arrays).
* Returns empty array if no results found.
*
* @param string $sSQL
*
* @return array[]
*/
public function getAll($sSQL, $aInputVars = null, $sErrMessage = 'Database query failed')
{
try {
$stmt = $this->getQueryStatement($sSQL, $aInputVars, $sErrMessage);
$rows = $stmt->fetchAll();
} catch (\PDOException $e) {
throw new \Nominatim\DatabaseError($sErrMessage, 500, null, $e, $sSQL);
}
return $rows;
}
/**
* Executes query. Returns array of the first value of each result.
* Returns empty array if no results found.
*
* @param string $sSQL
*
* @return array[]
*/
public function getCol($sSQL, $aInputVars = null, $sErrMessage = 'Database query failed')
{
$aVals = array();
try {
$stmt = $this->getQueryStatement($sSQL, $aInputVars, $sErrMessage);
while (($val = $stmt->fetchColumn(0)) !== false) { // returns first column or false
$aVals[] = $val;
}
} catch (\PDOException $e) {
throw new \Nominatim\DatabaseError($sErrMessage, 500, null, $e, $sSQL);
}
return $aVals;
}
/**
* Executes query. Returns associate array mapping first value to second value of each result.
* Returns empty array if no results found.
*
* @param string $sSQL
*
* @return array[]
*/
public function getAssoc($sSQL, $aInputVars = null, $sErrMessage = 'Database query failed')
{
try {
$stmt = $this->getQueryStatement($sSQL, $aInputVars, $sErrMessage);
$aList = array();
while ($aRow = $stmt->fetch(\PDO::FETCH_NUM)) {
$aList[$aRow[0]] = $aRow[1];
}
} catch (\PDOException $e) {
throw new \Nominatim\DatabaseError($sErrMessage, 500, null, $e, $sSQL);
}
return $aList;
}
/**
* Executes query. Returns a PDO statement to iterate over.
*
* @param string $sSQL
*
* @return PDOStatement
*/
public function getQueryStatement($sSQL, $aInputVars = null, $sErrMessage = 'Database query failed')
{
try {
if (isset($aInputVars)) {
$stmt = $this->connection->prepare($sSQL);
$stmt->execute($aInputVars);
} else {
$stmt = $this->connection->query($sSQL);
}
} catch (\PDOException $e) {
throw new \Nominatim\DatabaseError($sErrMessage, 500, null, $e, $sSQL);
}
return $stmt;
}
/**
* St. John's Way => 'St. John\'s Way'
*
* @param string $sVal Text to be quoted.
*
* @return string
*/
public function getDBQuoted($sVal)
{
return $this->connection->quote($sVal);
}
/**
* Like getDBQuoted, but takes an array.
*
* @param array $aVals List of text to be quoted.
*
* @return array[]
*/
public function getDBQuotedList($aVals)
{
return array_map(function ($sVal) {
return $this->getDBQuoted($sVal);
}, $aVals);
}
/**
* [1,2,'b'] => 'ARRAY[1,2,'b']''
*
* @param array $aVals List of text to be quoted.
*
* @return string
*/
public function getArraySQL($a)
{
return 'ARRAY['.join(',', $a).']';
}
/**
* Check if a table exists in the database. Returns true if it does.
*
* @param string $sTableName
*
* @return boolean
*/
public function tableExists($sTableName)
{
$sSQL = 'SELECT count(*) FROM pg_tables WHERE tablename = :tablename';
return ($this->getOne($sSQL, array(':tablename' => $sTableName)) == 1);
}
/**
* Deletes a table. Returns true if deleted or didn't exist.
*
* @param string $sTableName
*
* @return boolean
*/
public function deleteTable($sTableName)
{
return $this->exec('DROP TABLE IF EXISTS '.$sTableName.' CASCADE') == 0;
}
/**
* Tries to connect to the database but on failure doesn't throw an exception.
*
* @return boolean
*/
public function checkConnection()
{
$bExists = true;
try {
$this->connect(true);
} catch (\Nominatim\DatabaseError $e) {
$bExists = false;
}
return $bExists;
}
/**
* e.g. 9.6, 10, 11.2
*
* @return float
*/
public function getPostgresVersion()
{
$sVersionString = $this->getOne('SHOW server_version_num');
preg_match('#([0-9]?[0-9])([0-9][0-9])[0-9][0-9]#', $sVersionString, $aMatches);
return (float) ($aMatches[1].'.'.$aMatches[2]);
}
/**
* e.g. 2, 2.2
*
* @return float
*/
public function getPostgisVersion()
{
$sVersionString = $this->getOne('select postgis_lib_version()');
preg_match('#^([0-9]+)[.]([0-9]+)[.]#', $sVersionString, $aMatches);
return (float) ($aMatches[1].'.'.$aMatches[2]);
}
/**
* Returns an associate array of postgresql database connection settings. Keys can
* be 'database', 'hostspec', 'port', 'username', 'password'.
* Returns empty array on failure, thus check if at least 'database' is set.
*
* @return array[]
*/
public static function parseDSN($sDSN)
{
// https://secure.php.net/manual/en/ref.pdo-pgsql.connection.php
$aInfo = array();
if (preg_match('/^pgsql:(.+)$/', $sDSN, $aMatches)) {
foreach (explode(';', $aMatches[1]) as $sKeyVal) {
list($sKey, $sVal) = explode('=', $sKeyVal, 2);
if ($sKey == 'host') {
$sKey = 'hostspec';
} elseif ($sKey == 'dbname') {
$sKey = 'database';
} elseif ($sKey == 'user') {
$sKey = 'username';
}
$aInfo[$sKey] = $sVal;
}
}
return $aInfo;
}
/**
* Takes an array of settings and return the DNS string. Key names can be
* 'database', 'hostspec', 'port', 'username', 'password' but aliases
* 'dbname', 'host' and 'user' are also supported.
*
* @return string
*
*/
public static function generateDSN($aInfo)
{
$sDSN = sprintf(
'pgsql:host=%s;port=%s;dbname=%s;user=%s;password=%s;',
$aInfo['host'] ?? $aInfo['hostspec'] ?? '',
$aInfo['port'] ?? '',
$aInfo['dbname'] ?? $aInfo['database'] ?? '',
$aInfo['user'] ?? '',
$aInfo['password'] ?? ''
);
$sDSN = preg_replace('/\b\w+=;/', '', $sDSN);
$sDSN = preg_replace('/;\Z/', '', $sDSN);
return $sDSN;
}
}

42
lib-php/DatabaseError.php Normal file
View File

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

188
lib-php/DebugHtml.php Normal file
View File

@@ -0,0 +1,188 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
class Debug
{
public static function newFunction($sHeading)
{
echo "<pre><h2>Debug output for $sHeading</h2></pre>\n";
}
public static function newSection($sHeading)
{
echo "<hr><pre><h3>$sHeading</h3></pre>\n";
}
public static function printVar($sHeading, $mVar)
{
echo '<pre><b>'.$sHeading. ':</b> ';
Debug::outputVar($mVar, str_repeat(' ', strlen($sHeading) + 3));
echo "</pre>\n";
}
public static function fmtArrayVals($aArr)
{
return array('__debug_format' => 'array_vals', 'data' => $aArr);
}
public static function printDebugArray($sHeading, $oVar)
{
if ($oVar === null) {
Debug::printVar($sHeading, 'null');
} else {
Debug::printVar($sHeading, $oVar->debugInfo());
}
}
public static function printDebugTable($sHeading, $aVar)
{
echo '<b>'.$sHeading.":</b>\n";
echo "<table border='1'>\n";
if (!empty($aVar)) {
echo " <tr>\n";
$aKeys = array();
$aInfo = reset($aVar);
if (!is_array($aInfo)) {
$aInfo = $aInfo->debugInfo();
}
foreach ($aInfo as $sKey => $mVal) {
echo ' <th><small>'.$sKey.'</small></th>'."\n";
$aKeys[] = $sKey;
}
echo " </tr>\n";
foreach ($aVar as $oRow) {
$aInfo = $oRow;
if (!is_array($oRow)) {
$aInfo = $oRow->debugInfo();
}
echo " <tr>\n";
foreach ($aKeys as $sKey) {
echo ' <td><pre>';
if (isset($aInfo[$sKey])) {
Debug::outputVar($aInfo[$sKey], '');
}
echo '</pre></td>'."\n";
}
echo " </tr>\n";
}
}
echo "</table>\n";
}
public static function printGroupedSearch($aSearches, $aWordsIDs)
{
echo '<table border="1">';
echo '<tr><th>rank</th><th>Name Tokens</th><th>Name Not</th>';
echo '<th>Address Tokens</th><th>Address Not</th>';
echo '<th>country</th><th>operator</th>';
echo '<th>class</th><th>type</th><th>postcode</th><th>housenumber</th></tr>';
foreach ($aSearches as $aRankedSet) {
foreach ($aRankedSet as $aRow) {
$aRow->dumpAsHtmlTableRow($aWordsIDs);
}
}
echo '</table>';
}
public static function printGroupTable($sHeading, $aVar)
{
echo '<b>'.$sHeading.":</b>\n";
echo "<table border='1'>\n";
if (!empty($aVar)) {
echo " <tr>\n";
echo ' <th><small>Group</small></th>'."\n";
$aKeys = array();
$aInfo = reset($aVar)[0];
if (!is_array($aInfo)) {
$aInfo = $aInfo->debugInfo();
}
foreach ($aInfo as $sKey => $mVal) {
echo ' <th><small>'.$sKey.'</small></th>'."\n";
$aKeys[] = $sKey;
}
echo " </tr>\n";
foreach ($aVar as $sGrpKey => $aGroup) {
foreach ($aGroup as $oRow) {
$aInfo = $oRow;
if (!is_array($oRow)) {
$aInfo = $oRow->debugInfo();
}
echo " <tr>\n";
echo ' <td><pre>'.$sGrpKey.'</pre></td>'."\n";
foreach ($aKeys as $sKey) {
echo ' <td><pre>';
if (!empty($aInfo[$sKey])) {
Debug::outputVar($aInfo[$sKey], '');
}
echo '</pre></td>'."\n";
}
echo " </tr>\n";
}
}
}
echo "</table>\n";
}
public static function printSQL($sSQL)
{
echo '<p><tt><font color="#aaa">'.$sSQL.'</font></tt></p>'."\n";
}
private static function outputVar($mVar, $sPreNL)
{
if (is_array($mVar) && !isset($mVar['__debug_format'])) {
$sPre = '';
foreach ($mVar as $mKey => $aValue) {
echo $sPre;
$iKeyLen = Debug::outputSimpleVar($mKey);
echo ' => ';
Debug::outputVar(
$aValue,
$sPreNL.str_repeat(' ', $iKeyLen + 4)
);
$sPre = "\n".$sPreNL;
}
} elseif (is_array($mVar) && isset($mVar['__debug_format'])) {
if (!empty($mVar['data'])) {
$sPre = '';
foreach ($mVar['data'] as $mValue) {
echo $sPre;
Debug::outputSimpleVar($mValue);
$sPre = ', ';
}
}
} elseif (is_object($mVar) && method_exists($mVar, 'debugInfo')) {
Debug::outputVar($mVar->debugInfo(), $sPreNL);
} elseif (is_a($mVar, 'stdClass')) {
Debug::outputVar(json_decode(json_encode($mVar), true), $sPreNL);
} else {
Debug::outputSimpleVar($mVar);
}
}
private static function outputSimpleVar($mVar)
{
if (is_bool($mVar)) {
echo '<i>'.($mVar ? 'True' : 'False').'</i>';
return $mVar ? 4 : 5;
}
if (is_string($mVar)) {
echo "'$mVar'";
return strlen($mVar) + 2;
}
echo (string)$mVar;
return strlen((string)$mVar);
}
}

19
lib-php/DebugNone.php Normal file
View File

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

938
lib-php/Geocode.php Normal file
View File

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

157
lib-php/ParameterParser.php Normal file
View File

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

89
lib-php/Phrase.php Normal file
View File

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

616
lib-php/PlaceLookup.php Normal file
View File

@@ -0,0 +1,616 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
require_once(CONST_LibDir.'/AddressDetails.php');
require_once(CONST_LibDir.'/Result.php');
class PlaceLookup
{
protected $oDB;
protected $aLangPrefOrderSql = "''";
protected $bAddressDetails = false;
protected $bExtraTags = false;
protected $bNameDetails = false;
protected $bIncludePolygonAsText = false;
protected $bIncludePolygonAsGeoJSON = false;
protected $bIncludePolygonAsKML = false;
protected $bIncludePolygonAsSVG = false;
protected $fPolygonSimplificationThreshold = 0.0;
protected $sAnchorSql = null;
protected $sAddressRankListSql = null;
protected $sAllowedTypesSQLList = null;
protected $bDeDupe = true;
public function __construct(&$oDB)
{
$this->oDB =& $oDB;
}
public function doDeDupe()
{
return $this->bDeDupe;
}
public function setIncludeAddressDetails($b)
{
$this->bAddressDetails = $b;
}
public function loadParamArray($oParams, $sGeomType = null)
{
$aLangs = $oParams->getPreferredLanguages();
$this->aLangPrefOrderSql =
'ARRAY['.join(',', $this->oDB->getDBQuotedList($aLangs)).']';
$this->bExtraTags = $oParams->getBool('extratags', false);
$this->bNameDetails = $oParams->getBool('namedetails', false);
$this->bDeDupe = $oParams->getBool('dedupe', $this->bDeDupe);
if ($sGeomType === null || $sGeomType == 'geojson') {
$this->bIncludePolygonAsGeoJSON = $oParams->getBool('polygon_geojson');
}
if ($oParams->getString('format', '') !== 'geojson') {
if ($sGeomType === null || $sGeomType == 'text') {
$this->bIncludePolygonAsText = $oParams->getBool('polygon_text');
}
if ($sGeomType === null || $sGeomType == 'kml') {
$this->bIncludePolygonAsKML = $oParams->getBool('polygon_kml');
}
if ($sGeomType === null || $sGeomType == 'svg') {
$this->bIncludePolygonAsSVG = $oParams->getBool('polygon_svg');
}
}
$this->fPolygonSimplificationThreshold
= $oParams->getFloat('polygon_threshold', 0.0);
$iWantedTypes =
($this->bIncludePolygonAsText ? 1 : 0) +
($this->bIncludePolygonAsGeoJSON ? 1 : 0) +
($this->bIncludePolygonAsKML ? 1 : 0) +
($this->bIncludePolygonAsSVG ? 1 : 0);
if ($iWantedTypes > CONST_PolygonOutput_MaximumTypes) {
if (CONST_PolygonOutput_MaximumTypes) {
userError('Select only '.CONST_PolygonOutput_MaximumTypes.' polgyon output option');
} else {
userError('Polygon output is disabled');
}
}
}
public function getMoreUrlParams()
{
$aParams = array();
if ($this->bAddressDetails) {
$aParams['addressdetails'] = '1';
}
if ($this->bExtraTags) {
$aParams['extratags'] = '1';
}
if ($this->bNameDetails) {
$aParams['namedetails'] = '1';
}
if ($this->bIncludePolygonAsText) {
$aParams['polygon_text'] = '1';
}
if ($this->bIncludePolygonAsGeoJSON) {
$aParams['polygon_geojson'] = '1';
}
if ($this->bIncludePolygonAsKML) {
$aParams['polygon_kml'] = '1';
}
if ($this->bIncludePolygonAsSVG) {
$aParams['polygon_svg'] = '1';
}
if ($this->fPolygonSimplificationThreshold > 0.0) {
$aParams['polygon_threshold'] = $this->fPolygonSimplificationThreshold;
}
if (!$this->bDeDupe) {
$aParams['dedupe'] = '0';
}
return $aParams;
}
public function setAnchorSql($sPoint)
{
$this->sAnchorSql = $sPoint;
}
public function setAddressRankList($aList)
{
$this->sAddressRankListSql = '('.join(',', $aList).')';
}
public function setAllowedTypesSQLList($sSql)
{
$this->sAllowedTypesSQLList = $sSql;
}
public function setLanguagePreference($aLangPrefOrder)
{
$this->aLangPrefOrderSql = $this->oDB->getArraySQL(
$this->oDB->getDBQuotedList($aLangPrefOrder)
);
}
private function addressImportanceSql($sGeometry, $sPlaceId)
{
if ($this->sAnchorSql) {
$sSQL = 'ST_Distance('.$this->sAnchorSql.','.$sGeometry.')';
} else {
$sSQL = '(SELECT max(ai_p.importance * (ai_p.rank_address + 2))';
$sSQL .= ' FROM place_addressline ai_s, placex ai_p';
$sSQL .= ' WHERE ai_s.place_id = '.$sPlaceId;
$sSQL .= ' AND ai_p.place_id = ai_s.address_place_id ';
$sSQL .= ' AND ai_s.isaddress ';
$sSQL .= ' AND ai_p.importance is not null)';
}
return $sSQL.' AS addressimportance,';
}
private function langAddressSql($sHousenumber)
{
if ($this->bAddressDetails) {
return ''; // langaddress will be computed from address details
}
return 'get_address_by_language(place_id,'.$sHousenumber.','.$this->aLangPrefOrderSql.') AS langaddress,';
}
public function lookupOSMID($sType, $iID)
{
$sSQL = 'select place_id from placex where osm_type = :type and osm_id = :id';
$iPlaceID = $this->oDB->getOne($sSQL, array(':type' => $sType, ':id' => $iID));
if (!$iPlaceID) {
return null;
}
$aResults = $this->lookup(array($iPlaceID => new Result($iPlaceID)));
return empty($aResults) ? null : reset($aResults);
}
public function lookup($aResults, $iMinRank = 0, $iMaxRank = 30)
{
Debug::newFunction('Place lookup');
if (empty($aResults)) {
return array();
}
$aSubSelects = array();
$sPlaceIDs = Result::joinIdsByTable($aResults, Result::TABLE_PLACEX);
if ($sPlaceIDs) {
Debug::printVar('Ids from placex', $sPlaceIDs);
$sSQL = 'SELECT ';
$sSQL .= ' osm_type,';
$sSQL .= ' osm_id,';
$sSQL .= ' class,';
$sSQL .= ' type,';
$sSQL .= ' admin_level,';
$sSQL .= ' rank_search,';
$sSQL .= ' rank_address,';
$sSQL .= ' min(place_id) AS place_id,';
$sSQL .= ' min(parent_place_id) AS parent_place_id,';
$sSQL .= ' -1 as housenumber,';
$sSQL .= ' country_code,';
$sSQL .= $this->langAddressSql('-1');
$sSQL .= ' get_name_by_language(name,'.$this->aLangPrefOrderSql.') AS placename,';
$sSQL .= " get_name_by_language(name, ARRAY['ref']) AS ref,";
if ($this->bExtraTags) {
$sSQL .= 'hstore_to_json(extratags)::text AS extra,';
}
if ($this->bNameDetails) {
$sSQL .= 'hstore_to_json(name)::text AS names,';
}
$sSQL .= ' avg(ST_X(centroid)) AS lon, ';
$sSQL .= ' avg(ST_Y(centroid)) AS lat, ';
$sSQL .= ' COALESCE(importance,0.75-(rank_search::float/40)) AS importance, ';
$sSQL .= $this->addressImportanceSql(
'ST_Collect(centroid)',
'min(CASE WHEN placex.rank_search < 28 THEN placex.place_id ELSE placex.parent_place_id END)'
);
$sSQL .= " COALESCE(extratags->'place', extratags->'linked_place') AS extra_place ";
$sSQL .= ' FROM placex';
$sSQL .= " WHERE place_id in ($sPlaceIDs) ";
$sSQL .= ' AND (';
$sSQL .= " placex.rank_address between $iMinRank and $iMaxRank ";
if (14 >= $iMinRank && 14 <= $iMaxRank) {
$sSQL .= " OR (extratags->'place') = 'city'";
}
if ($this->sAddressRankListSql) {
$sSQL .= ' OR placex.rank_address in '.$this->sAddressRankListSql;
}
$sSQL .= ' ) ';
if ($this->sAllowedTypesSQLList) {
$sSQL .= 'AND placex.class in '.$this->sAllowedTypesSQLList;
}
$sSQL .= ' AND linked_place_id is null ';
$sSQL .= ' GROUP BY ';
$sSQL .= ' osm_type, ';
$sSQL .= ' osm_id, ';
$sSQL .= ' class, ';
$sSQL .= ' type, ';
$sSQL .= ' admin_level, ';
$sSQL .= ' rank_search, ';
$sSQL .= ' rank_address, ';
$sSQL .= ' housenumber,';
$sSQL .= ' country_code, ';
$sSQL .= ' importance, ';
if (!$this->bDeDupe) {
$sSQL .= 'place_id,';
}
if (!$this->bAddressDetails) {
$sSQL .= 'langaddress, ';
}
$sSQL .= ' placename, ';
$sSQL .= ' ref, ';
if ($this->bExtraTags) {
$sSQL .= 'extratags, ';
}
if ($this->bNameDetails) {
$sSQL .= 'name, ';
}
$sSQL .= ' extra_place ';
$aSubSelects[] = $sSQL;
}
// postcode table
$sPlaceIDs = Result::joinIdsByTable($aResults, Result::TABLE_POSTCODE);
if ($sPlaceIDs) {
Debug::printVar('Ids from location_postcode', $sPlaceIDs);
$sSQL = 'SELECT';
$sSQL .= " 'P' as osm_type,";
$sSQL .= ' (SELECT osm_id from placex p WHERE p.place_id = lp.parent_place_id) as osm_id,';
$sSQL .= " 'place' as class, 'postcode' as type,";
$sSQL .= ' null::smallint as admin_level, rank_search, rank_address,';
$sSQL .= ' place_id, parent_place_id,';
$sSQL .= ' -1 as housenumber,';
$sSQL .= ' country_code,';
$sSQL .= $this->langAddressSql('-1');
$sSQL .= ' postcode as placename,';
$sSQL .= ' postcode as ref,';
if ($this->bExtraTags) {
$sSQL .= 'null::text AS extra,';
}
if ($this->bNameDetails) {
$sSQL .= 'null::text AS names,';
}
$sSQL .= ' ST_x(geometry) AS lon, ST_y(geometry) AS lat,';
$sSQL .= ' (0.75-(rank_search::float/40)) AS importance, ';
$sSQL .= $this->addressImportanceSql('geometry', 'lp.parent_place_id');
$sSQL .= ' null::text AS extra_place ';
$sSQL .= 'FROM location_postcode lp';
$sSQL .= " WHERE place_id in ($sPlaceIDs) ";
$sSQL .= " AND lp.rank_address between $iMinRank and $iMaxRank";
$aSubSelects[] = $sSQL;
}
// All other tables are rank 30 only.
if ($iMaxRank == 30) {
// TIGER table
if (CONST_Use_US_Tiger_Data) {
$sPlaceIDs = Result::joinIdsByTable($aResults, Result::TABLE_TIGER);
if ($sPlaceIDs) {
Debug::printVar('Ids from Tiger table', $sPlaceIDs);
$sHousenumbers = Result::sqlHouseNumberTable($aResults, Result::TABLE_TIGER);
// Tiger search only if a housenumber was searched and if it was found
// (realized through a join)
$sSQL = ' SELECT ';
$sSQL .= " 'T' AS osm_type, ";
$sSQL .= ' (SELECT osm_id from placex p WHERE p.place_id=blub.parent_place_id) as osm_id, ';
$sSQL .= " 'place' AS class, ";
$sSQL .= " 'house' AS type, ";
$sSQL .= ' null::smallint AS admin_level, ';
$sSQL .= ' 30 AS rank_search, ';
$sSQL .= ' 30 AS rank_address, ';
$sSQL .= ' place_id, ';
$sSQL .= ' parent_place_id, ';
$sSQL .= ' housenumber_for_place as housenumber,';
$sSQL .= " 'us' AS country_code, ";
$sSQL .= $this->langAddressSql('housenumber_for_place');
$sSQL .= ' null::text AS placename, ';
$sSQL .= ' null::text AS ref, ';
if ($this->bExtraTags) {
$sSQL .= 'null::text AS extra,';
}
if ($this->bNameDetails) {
$sSQL .= 'null::text AS names,';
}
$sSQL .= ' st_x(centroid) AS lon, ';
$sSQL .= ' st_y(centroid) AS lat,';
$sSQL .= ' -1.15 AS importance, ';
$sSQL .= $this->addressImportanceSql('centroid', 'blub.parent_place_id');
$sSQL .= ' null::text AS extra_place ';
$sSQL .= ' FROM (';
$sSQL .= ' SELECT place_id, '; // interpolate the Tiger housenumbers here
$sSQL .= ' CASE WHEN startnumber != endnumber';
$sSQL .= ' THEN ST_LineInterpolatePoint(linegeo, (housenumber_for_place-startnumber::float)/(endnumber-startnumber)::float)';
$sSQL .= ' ELSE ST_LineInterpolatePoint(linegeo, 0.5) END AS centroid, ';
$sSQL .= ' parent_place_id, ';
$sSQL .= ' housenumber_for_place';
$sSQL .= ' FROM (';
$sSQL .= ' location_property_tiger ';
$sSQL .= ' JOIN (values '.$sHousenumbers.') AS housenumbers(place_id, housenumber_for_place) USING(place_id)) ';
$sSQL .= ' WHERE ';
$sSQL .= ' housenumber_for_place >= startnumber';
$sSQL .= ' AND housenumber_for_place <= endnumber';
$sSQL .= ' ) AS blub'; //postgres wants an alias here
$aSubSelects[] = $sSQL;
}
}
// osmline - interpolated housenumbers
$sPlaceIDs = Result::joinIdsByTable($aResults, Result::TABLE_OSMLINE);
if ($sPlaceIDs) {
Debug::printVar('Ids from interpolation', $sPlaceIDs);
$sHousenumbers = Result::sqlHouseNumberTable($aResults, Result::TABLE_OSMLINE);
// interpolation line search only if a housenumber was searched
// (realized through a join)
$sSQL = 'SELECT ';
$sSQL .= " 'W' AS osm_type, ";
$sSQL .= ' osm_id, ';
$sSQL .= " 'place' AS class, ";
$sSQL .= " 'house' AS type, ";
$sSQL .= ' null::smallint AS admin_level, ';
$sSQL .= ' 30 AS rank_search, ';
$sSQL .= ' 30 AS rank_address, ';
$sSQL .= ' place_id, ';
$sSQL .= ' parent_place_id, ';
$sSQL .= ' housenumber_for_place as housenumber,';
$sSQL .= ' country_code, ';
$sSQL .= $this->langAddressSql('housenumber_for_place');
$sSQL .= ' null::text AS placename, ';
$sSQL .= ' null::text AS ref, ';
if ($this->bExtraTags) {
$sSQL .= 'null::text AS extra, ';
}
if ($this->bNameDetails) {
$sSQL .= 'null::text AS names, ';
}
$sSQL .= ' st_x(centroid) AS lon, ';
$sSQL .= ' st_y(centroid) AS lat, ';
// slightly smaller than the importance for normal houses
$sSQL .= ' -0.1 AS importance, ';
$sSQL .= $this->addressImportanceSql('centroid', 'blub.parent_place_id');
$sSQL .= ' null::text AS extra_place ';
$sSQL .= ' FROM (';
$sSQL .= ' SELECT ';
$sSQL .= ' osm_id, ';
$sSQL .= ' place_id, ';
$sSQL .= ' country_code, ';
$sSQL .= ' CASE '; // interpolate the housenumbers here
$sSQL .= ' WHEN startnumber != endnumber ';
$sSQL .= ' THEN ST_LineInterpolatePoint(linegeo, (housenumber_for_place-startnumber::float)/(endnumber-startnumber)::float) ';
$sSQL .= ' ELSE linegeo ';
$sSQL .= ' END as centroid, ';
$sSQL .= ' parent_place_id, ';
$sSQL .= ' housenumber_for_place ';
$sSQL .= ' FROM (';
$sSQL .= ' location_property_osmline ';
$sSQL .= ' JOIN (values '.$sHousenumbers.') AS housenumbers(place_id, housenumber_for_place) USING(place_id)';
$sSQL .= ' ) ';
$sSQL .= ' WHERE housenumber_for_place >= 0 ';
$sSQL .= ' ) as blub'; //postgres wants an alias here
$aSubSelects[] = $sSQL;
}
}
if (empty($aSubSelects)) {
return array();
}
$sSQL = join(' UNION ', $aSubSelects);
Debug::printSQL($sSQL);
$aPlaces = $this->oDB->getAll($sSQL, null, 'Could not lookup place');
foreach ($aPlaces as &$aPlace) {
$aPlace['importance'] = (float) $aPlace['importance'];
if ($this->bAddressDetails) {
// to get addressdetails for tiger data, the housenumber is needed
$aPlace['address'] = new AddressDetails(
$this->oDB,
$aPlace['place_id'],
$aPlace['housenumber'],
$this->aLangPrefOrderSql
);
$aPlace['langaddress'] = $aPlace['address']->getLocaleAddress();
}
if ($this->bExtraTags) {
if ($aPlace['extra']) {
$aPlace['sExtraTags'] = json_decode($aPlace['extra'], true);
} else {
$aPlace['sExtraTags'] = (object) array();
}
}
if ($this->bNameDetails) {
$aPlace['sNameDetails'] = $this->extractNames($aPlace['names']);
}
$aPlace['addresstype'] = ClassTypes\getLabelTag(
$aPlace,
$aPlace['country_code']
);
$aResults[$aPlace['place_id']] = $aPlace;
}
$aResults = array_filter(
$aResults,
function ($v) {
return !($v instanceof Result);
}
);
Debug::printVar('Places', $aResults);
return $aResults;
}
private function extractNames($sNames)
{
if (!$sNames) {
return (object) array();
}
$aFullNames = json_decode($sNames, true);
$aNames = array();
foreach ($aFullNames as $sKey => $sValue) {
if (strpos($sKey, '_place_') === 0) {
$sSubKey = substr($sKey, 7);
if (array_key_exists($sSubKey, $aFullNames)) {
$aNames[$sKey] = $sValue;
} else {
$aNames[$sSubKey] = $sValue;
}
} else {
$aNames[$sKey] = $sValue;
}
}
return $aNames;
}
/* returns an array which will contain the keys
* aBoundingBox
* and may also contain one or more of the keys
* asgeojson
* askml
* assvg
* astext
* lat
* lon
*/
public function getOutlines($iPlaceID, $fLon = null, $fLat = null, $fRadius = null, $fLonReverse = null, $fLatReverse = null)
{
$aOutlineResult = array();
if (!$iPlaceID) {
return $aOutlineResult;
}
// Get the bounding box and outline polygon
$sSQL = 'select place_id,0 as numfeatures,st_area(geometry) as area,';
if ($fLonReverse != null && $fLatReverse != null) {
$sSQL .= ' ST_Y(closest_point) as centrelat,';
$sSQL .= ' ST_X(closest_point) as centrelon,';
} else {
$sSQL .= ' ST_Y(centroid) as centrelat, ST_X(centroid) as centrelon,';
}
$sSQL .= ' ST_YMin(geometry) as minlat,ST_YMax(geometry) as maxlat,';
$sSQL .= ' ST_XMin(geometry) as minlon,ST_XMax(geometry) as maxlon';
if ($this->bIncludePolygonAsGeoJSON) {
$sSQL .= ',ST_AsGeoJSON(geometry) as asgeojson';
}
if ($this->bIncludePolygonAsKML) {
$sSQL .= ',ST_AsKML(geometry) as askml';
}
if ($this->bIncludePolygonAsSVG) {
$sSQL .= ',ST_AsSVG(geometry) as assvg';
}
if ($this->bIncludePolygonAsText) {
$sSQL .= ',ST_AsText(geometry) as astext';
}
if ($fLonReverse != null && $fLatReverse != null) {
$sFrom = ' from (SELECT * , CASE WHEN (class = \'highway\') AND (ST_GeometryType(geometry) = \'ST_LineString\') THEN ';
$sFrom .=' ST_ClosestPoint(geometry, ST_SetSRID(ST_Point('.$fLatReverse.','.$fLonReverse.'),4326))';
$sFrom .=' ELSE centroid END AS closest_point';
$sFrom .= ' from placex where place_id = '.$iPlaceID.') as plx';
} else {
$sFrom = ' from placex where place_id = '.$iPlaceID;
}
if ($this->fPolygonSimplificationThreshold > 0) {
$sSQL .= ' from (select place_id,centroid,ST_SimplifyPreserveTopology(geometry,'.$this->fPolygonSimplificationThreshold.') as geometry'.$sFrom.') as plx';
} else {
$sSQL .= $sFrom;
}
$aPointPolygon = $this->oDB->getRow($sSQL, null, 'Could not get outline');
if ($aPointPolygon && $aPointPolygon['place_id']) {
if ($aPointPolygon['centrelon'] !== null && $aPointPolygon['centrelat'] !== null) {
$aOutlineResult['lat'] = $aPointPolygon['centrelat'];
$aOutlineResult['lon'] = $aPointPolygon['centrelon'];
}
if ($this->bIncludePolygonAsGeoJSON) {
$aOutlineResult['asgeojson'] = $aPointPolygon['asgeojson'];
}
if ($this->bIncludePolygonAsKML) {
$aOutlineResult['askml'] = $aPointPolygon['askml'];
}
if ($this->bIncludePolygonAsSVG) {
$aOutlineResult['assvg'] = $aPointPolygon['assvg'];
}
if ($this->bIncludePolygonAsText) {
$aOutlineResult['astext'] = $aPointPolygon['astext'];
}
if (abs($aPointPolygon['minlat'] - $aPointPolygon['maxlat']) < 0.0000001) {
$aPointPolygon['minlat'] = $aPointPolygon['minlat'] - $fRadius;
$aPointPolygon['maxlat'] = $aPointPolygon['maxlat'] + $fRadius;
}
if (abs($aPointPolygon['minlon'] - $aPointPolygon['maxlon']) < 0.0000001) {
$aPointPolygon['minlon'] = $aPointPolygon['minlon'] - $fRadius;
$aPointPolygon['maxlon'] = $aPointPolygon['maxlon'] + $fRadius;
}
$aOutlineResult['aBoundingBox'] = array(
(string)$aPointPolygon['minlat'],
(string)$aPointPolygon['maxlat'],
(string)$aPointPolygon['minlon'],
(string)$aPointPolygon['maxlon']
);
}
// as a fallback we generate a bounding box without knowing the size of the geometry
if ((!isset($aOutlineResult['aBoundingBox'])) && isset($fLon)) {
$aBounds = array(
'minlat' => $fLat - $fRadius,
'maxlat' => $fLat + $fRadius,
'minlon' => $fLon - $fRadius,
'maxlon' => $fLon + $fRadius
);
$aOutlineResult['aBoundingBox'] = array(
(string)$aBounds['minlat'],
(string)$aBounds['maxlat'],
(string)$aBounds['minlon'],
(string)$aBounds['maxlon']
);
}
return $aOutlineResult;
}
}

129
lib-php/Result.php Normal file
View File

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

393
lib-php/ReverseGeocode.php Normal file
View File

@@ -0,0 +1,393 @@
<?php
/**
* SPDX-License-Identifier: GPL-2.0-only
*
* This file is part of Nominatim. (https://nominatim.org)
*
* Copyright (C) 2022 by the Nominatim developer community.
* For a full list of authors see the git log.
*/
namespace Nominatim;
require_once(CONST_LibDir.'/Result.php');
class ReverseGeocode
{
protected $oDB;
protected $iMaxRank = 28;
public function __construct(&$oDB)
{
$this->oDB =& $oDB;
}
public function setZoom($iZoom)
{
// Zoom to rank, this could probably be calculated but a lookup gives fine control
$aZoomRank = array(
0 => 2, // Continent / Sea
1 => 2,
2 => 2,
3 => 4, // Country
4 => 4,
5 => 8, // State
6 => 10, // Region
7 => 10,
8 => 12, // County
9 => 12,
10 => 17, // City
11 => 17,
12 => 18, // Town / Village
13 => 18,
14 => 22, // Suburb
15 => 22,
16 => 26, // major street
17 => 27, // minor street
18 => 30, // or >, Building
19 => 30, // or >, Building
);
$this->iMaxRank = (isset($iZoom) && isset($aZoomRank[$iZoom]))?$aZoomRank[$iZoom]:28;
}
/**
* Find the closest interpolation with the given search diameter.
*
* @param string $sPointSQL Reverse geocoding point as SQL
* @param float $fSearchDiam Search diameter
*
* @return Record of the interpolation or null.
*/
protected function lookupInterpolation($sPointSQL, $fSearchDiam)
{
Debug::newFunction('lookupInterpolation');
$sSQL = 'SELECT place_id, parent_place_id, 30 as rank_search,';
$sSQL .= ' (CASE WHEN endnumber != startnumber';
$sSQL .= ' THEN (endnumber - startnumber) * ST_LineLocatePoint(linegeo,'.$sPointSQL.')';
$sSQL .= ' ELSE startnumber END) as fhnr,';
$sSQL .= ' startnumber, endnumber, step,';
$sSQL .= ' ST_Distance(linegeo,'.$sPointSQL.') as distance';
$sSQL .= ' FROM location_property_osmline';
$sSQL .= ' WHERE ST_DWithin('.$sPointSQL.', linegeo, '.$fSearchDiam.')';
$sSQL .= ' and indexed_status = 0 and startnumber is not NULL ';
$sSQL .= ' ORDER BY distance ASC limit 1';
Debug::printSQL($sSQL);
return $this->oDB->getRow(
$sSQL,
null,
'Could not determine closest housenumber on an osm interpolation line.'
);
}
protected function lookupLargeArea($sPointSQL, $iMaxRank)
{
if ($iMaxRank > 4) {
$aPlace = $this->lookupPolygon($sPointSQL, $iMaxRank);
if ($aPlace) {
return new Result($aPlace['place_id']);
}
}
// If no polygon which contains the searchpoint is found,
// searches in the country_osm_grid table for a polygon.
return $this->lookupInCountry($sPointSQL, $iMaxRank);
}
protected function lookupInCountry($sPointSQL, $iMaxRank)
{
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';
$sSQL .= ' WHERE ST_CONTAINS(geometry, '.$sPointSQL.') LIMIT 1';
Debug::printSQL($sSQL);
$sCountryCode = $this->oDB->getOne(
$sSQL,
null,
'Could not determine country polygon containing the point.'
);
Debug::printVar('Country code', $sCountryCode);
if ($sCountryCode) {
if ($iMaxRank > 4) {
// look for place nodes with the given country code
$sSQL = 'SELECT place_id FROM';
$sSQL .= ' (SELECT place_id, rank_search,';
$sSQL .= ' ST_distance('.$sPointSQL.', geometry) as distance';
$sSQL .= ' FROM placex';
$sSQL .= ' WHERE osm_type = \'N\'';
$sSQL .= ' AND country_code = \''.$sCountryCode.'\'';
$sSQL .= ' AND rank_search < 26 '; // needed to select right index
$sSQL .= ' AND rank_search between 5 and ' .min(25, $iMaxRank);
$sSQL .= ' AND class = \'place\' AND type != \'postcode\'';
$sSQL .= ' AND name IS NOT NULL ';
$sSQL .= ' and indexed_status = 0 and linked_place_id is null';
$sSQL .= ' AND ST_DWithin('.$sPointSQL.', geometry, 1.8)) p ';
$sSQL .= 'WHERE distance <= reverse_place_diameter(rank_search)';
$sSQL .= ' ORDER BY rank_search DESC, distance ASC';
$sSQL .= ' LIMIT 1';
Debug::printSQL($sSQL);
$aPlace = $this->oDB->getRow($sSQL, null, 'Could not determine place node.');
Debug::printVar('Country node', $aPlace);
if ($aPlace) {
return new Result($aPlace['place_id']);
}
}
// still nothing, then return the country object
$sSQL = 'SELECT place_id, ST_distance('.$sPointSQL.', centroid) as distance';
$sSQL .= ' FROM placex';
$sSQL .= ' WHERE country_code = \''.$sCountryCode.'\'';
$sSQL .= ' AND rank_search = 4 AND rank_address = 4';
$sSQL .= ' AND class in (\'boundary\', \'place\')';
$sSQL .= ' AND linked_place_id is null';
$sSQL .= ' ORDER BY distance ASC';
Debug::printSQL($sSQL);
$aPlace = $this->oDB->getRow($sSQL, null, 'Could not determine place node.');
Debug::printVar('Country place', $aPlace);
if ($aPlace) {
return new Result($aPlace['place_id']);
}
}
return null;
}
/**
* Search for areas or nodes for areas or nodes between state and suburb level.
*
* @param string $sPointSQL Search point as SQL string.
* @param int $iMaxRank Maximum address rank of the feature.
*
* @return Record of the found feature or null.
*
* Searches first for polygon that contains the search point.
* If such a polygon is found, place nodes with a higher rank are
* searched inside the polygon.
*/
protected function lookupPolygon($sPointSQL, $iMaxRank)
{
Debug::newFunction('lookupPolygon');
// polygon search begins at suburb-level
if ($iMaxRank > 25) {
$iMaxRank = 25;
}
// no polygon search over country-level
if ($iMaxRank < 5) {
$iMaxRank = 5;
}
// search for polygon
$sSQL = 'SELECT place_id, parent_place_id, rank_address, rank_search FROM';
$sSQL .= '(select place_id, parent_place_id, rank_address, rank_search, country_code, geometry';
$sSQL .= ' FROM placex';
$sSQL .= ' WHERE ST_GeometryType(geometry) in (\'ST_Polygon\', \'ST_MultiPolygon\')';
$sSQL .= ' AND rank_address Between 5 AND ' .$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_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.');
Debug::printVar('Polygon result', $aPoly);
if ($aPoly) {
// if a polygon is found, search for placenodes begins ...
$iRankAddress = $aPoly['rank_address'];
$iRankSearch = $aPoly['rank_search'];
$iPlaceID = $aPoly['place_id'];
if ($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_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';
$sSQL .= ' AND ST_DWithin('.$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 distance ASC, rank_search DESC';
$sSQL .= ' LIMIT 1';
Debug::printSQL($sSQL);
$aPlaceNode = $this->oDB->getRow($sSQL, null, 'Could not determine place node.');
Debug::printVar('Nearest place node', $aPlaceNode);
if ($aPlaceNode) {
return $aPlaceNode;
}
}
}
return $aPoly;
}
public function lookup($fLat, $fLon, $bDoInterpolation = true)
{
return $this->lookupPoint(
'ST_SetSRID(ST_Point('.$fLon.','.$fLat.'),4326)',
$bDoInterpolation
);
}
public function lookupPoint($sPointSQL, $bDoInterpolation = true)
{
Debug::newFunction('lookupPoint');
// Find the nearest point
$fSearchDiam = 0.006;
$oResult = null;
$aPlace = null;
// for POI or street level
if ($this->iMaxRank >= 26) {
// starts if the search is on POI or street level,
// searches for the nearest POI or street,
// if a street is found and a POI is searched for,
// the nearest POI which the found street is a parent of is chosen.
$sSQL = 'select place_id,parent_place_id,rank_address,country_code,';
$sSQL .= ' ST_distance('.$sPointSQL.', geometry) as distance';
$sSQL .= ' FROM ';
$sSQL .= ' placex';
$sSQL .= ' WHERE ST_DWithin('.$sPointSQL.', geometry, '.$fSearchDiam.')';
$sSQL .= ' AND';
$sSQL .= ' rank_address between 26 and '.$this->iMaxRank;
$sSQL .= ' and (name is not null or housenumber is not null';
$sSQL .= ' or rank_address between 26 and 27)';
$sSQL .= ' and (rank_address between 26 and 27';
$sSQL .= ' or ST_GeometryType(geometry) != \'ST_LineString\')';
$sSQL .= ' and class not in (\'boundary\')';
$sSQL .= ' and indexed_status = 0 and linked_place_id is null';
$sSQL .= ' and (ST_GeometryType(geometry) not in (\'ST_Polygon\',\'ST_MultiPolygon\') ';
$sSQL .= ' OR ST_DWithin('.$sPointSQL.', centroid, '.$fSearchDiam.'))';
$sSQL .= ' ORDER BY distance ASC limit 1';
Debug::printSQL($sSQL);
$aPlace = $this->oDB->getRow($sSQL, null, 'Could not determine closest place.');
Debug::printVar('POI/street level result', $aPlace);
if ($aPlace) {
$iPlaceID = $aPlace['place_id'];
$oResult = new Result($iPlaceID);
$iRankAddress = $aPlace['rank_address'];
}
if ($aPlace) {
// if street and maxrank > streetlevel
if ($iRankAddress <= 27 && $this->iMaxRank > 27) {
// find the closest object (up to a certain radius) of which the street is a parent of
$sSQL = ' select place_id,';
$sSQL .= ' ST_distance('.$sPointSQL.', geometry) as distance';
$sSQL .= ' FROM ';
$sSQL .= ' placex';
// radius ?
$sSQL .= ' WHERE ST_DWithin('.$sPointSQL.', geometry, 0.001)';
$sSQL .= ' AND parent_place_id = '.$iPlaceID;
$sSQL .= ' and rank_address > 28';
$sSQL .= ' and ST_GeometryType(geometry) != \'ST_LineString\'';
$sSQL .= ' and (name is not null or housenumber is not null)';
$sSQL .= ' and class not in (\'boundary\')';
$sSQL .= ' and indexed_status = 0 and linked_place_id is null';
$sSQL .= ' ORDER BY distance ASC limit 1';
Debug::printSQL($sSQL);
$aStreet = $this->oDB->getRow($sSQL, null, 'Could not determine closest place.');
Debug::printVar('Closest POI result', $aStreet);
if ($aStreet) {
$aPlace = $aStreet;
$oResult = new Result($aStreet['place_id']);
$iRankAddress = 30;
}
}
// In the US we can check TIGER data for nearest housenumber
if (CONST_Use_US_Tiger_Data
&& $iRankAddress <= 27
&& $aPlace['country_code'] == 'us'
&& $this->iMaxRank >= 28
) {
$sSQL = 'SELECT place_id,parent_place_id,30 as rank_search,';
$sSQL .= ' (endnumber - startnumber) * ST_LineLocatePoint(linegeo,'.$sPointSQL.') as fhnr,';
$sSQL .= ' startnumber, endnumber, step,';
$sSQL .= ' ST_Distance('.$sPointSQL.', linegeo) as distance';
$sSQL .= ' FROM location_property_tiger WHERE parent_place_id = '.$oResult->iId;
$sSQL .= ' AND ST_DWithin('.$sPointSQL.', linegeo, 0.001)';
$sSQL .= ' ORDER BY distance ASC limit 1';
Debug::printSQL($sSQL);
$aPlaceTiger = $this->oDB->getRow($sSQL, null, 'Could not determine closest Tiger place.');
Debug::printVar('Tiger house number result', $aPlaceTiger);
if ($aPlaceTiger) {
$aPlace = $aPlaceTiger;
$oResult = new Result($aPlaceTiger['place_id'], Result::TABLE_TIGER);
$iRndNum = max(0, round($aPlaceTiger['fhnr'] / $aPlaceTiger['step']) * $aPlaceTiger['step']);
$oResult->iHouseNumber = $aPlaceTiger['startnumber'] + $iRndNum;
if ($oResult->iHouseNumber > $aPlaceTiger['endnumber']) {
$oResult->iHouseNumber = $aPlaceTiger['endnumber'];
}
$iRankAddress = 30;
}
}
}
if ($bDoInterpolation && $this->iMaxRank >= 30) {
$fDistance = $fSearchDiam;
if ($aPlace) {
// We can't reliably go from the closest street to an
// interpolation line because the closest interpolation
// may have a different street segments as a parent.
// Therefore allow an interpolation line to take precedence
// even when the street is closer.
$fDistance = $iRankAddress < 28 ? 0.001 : $aPlace['distance'];
}
$aHouse = $this->lookupInterpolation($sPointSQL, $fDistance);
Debug::printVar('Interpolation result', $aPlace);
if ($aHouse) {
$oResult = new Result($aHouse['place_id'], Result::TABLE_OSMLINE);
$iRndNum = max(0, round($aHouse['fhnr'] / $aHouse['step']) * $aHouse['step']);
$oResult->iHouseNumber = $aHouse['startnumber'] + $iRndNum;
if ($oResult->iHouseNumber > $aHouse['endnumber']) {
$oResult->iHouseNumber = $aHouse['endnumber'];
}
$aPlace = $aHouse;
}
}
if (!$aPlace) {
// if no POI or street is found ...
$oResult = $this->lookupLargeArea($sPointSQL, 25);
}
} else {
// lower than street level ($iMaxRank < 26 )
$oResult = $this->lookupLargeArea($sPointSQL, $this->iMaxRank);
}
Debug::printVar('Final result', $oResult);
return $oResult;
}
}

319
lib-php/SearchContext.php Normal file
View File

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

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