prepare release 4.2.2

The full style should only save the necessary tags needed for
processing.

.github/FUNDING.yml

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

.github/ISSUE_TEMPLATE/report-issues-with-search-results.md

@@ -7,6 +7,8 @@ assignees: ''
 
 ---
 
+<!-- Note: this template is for reporting problems with searching. If you have found an issue with the data, you need to report/fix the issue directly in OpenStreetMap. See https://www.openstreetmap.org/fixthemap for details. -->
+
 ## What did you search for?
 
 <!-- Please try to provide a link to your search. You  can go to https://nominatim.openstreetmap.org and repeat your search there. If you originally found the issue somewhere else, please tell us what software/website you were using. -->
@@ -15,11 +17,11 @@ assignees: ''
 
 ## What result did you expect?
 
-**Is the result 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. -->
 
-**Is the result 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.
 

.github/actions/build-nominatim/action.yml

@@ -5,34 +5,43 @@ inputs:
         description: 'Version of Ubuntu to install on'
         required: false
         default: '20'
+    cmake-args:
+        description: 'Additional options to hand to cmake'
+        required: false
+        default: ''
+    lua:
+        description: 'Version of Lua to use'
+        required: false
+        default: '5.3'
 
 runs:
     using: "composite"
 
     steps:
+        - name: Clean out the disk
+          run: |
+            sudo rm -rf /opt/hostedtoolcache/go /opt/hostedtoolcache/CodeQL /usr/lib/jvm /usr/local/share/chromium /usr/local/lib/android
+            df -h
+          shell: bash
         - name: Install prerequisites
           run: |
-            sudo apt-get install -y -qq libboost-system-dev libboost-filesystem-dev libexpat1-dev zlib1g-dev libbz2-dev libpq-dev libproj-dev libicu-dev
+            sudo apt-get install -y -qq libboost-system-dev libboost-filesystem-dev libexpat1-dev zlib1g-dev libbz2-dev libpq-dev libproj-dev libicu-dev liblua${LUA_VERSION}-dev lua${LUA_VERSION}
             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
+                pip3 install python-dotenv psycopg2==2.7.7 jinja2==2.8 psutil==5.4.2 pyicu==2.9 osmium PyYAML==5.1 datrie
             else
                 sudo apt-get install -y -qq python3-icu python3-datrie python3-pyosmium python3-jinja2 python3-psutil python3-psycopg2 python3-dotenv python3-yaml
             fi
           shell: bash
           env:
             UBUNTUVER: ${{ inputs.ubuntu }}
-
-        - name: Download dependencies
-          run: |
-              if [ ! -f country_grid.sql.gz ]; then
-                  wget --no-verbose https://www.nominatim.org/data/country_grid.sql.gz
-              fi
-              cp country_grid.sql.gz Nominatim/data/country_osm_grid.sql.gz
-          shell: bash
+            CMAKE_ARGS: ${{ inputs.cmake-args }}
+            LUA_VERSION: ${{ inputs.lua }}
 
         - name: Configure
-          run: mkdir build && cd build && cmake ../Nominatim
+          run: mkdir build && cd build && cmake $CMAKE_ARGS ../Nominatim
           shell: bash
+          env:
+            CMAKE_ARGS: ${{ inputs.cmake-args }}
 
         - name: Build
           run: |

.github/actions/setup-postgresql/action.yml

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

.github/workflows/ci-tests.yml

@@ -3,13 +3,44 @@ name: CI Tests
 on: [ push, pull_request ]
 
 jobs:
+    create-archive:
+        runs-on: ubuntu-latest
+
+        steps:
+            - uses: actions/checkout@v3
+              with:
+                submodules: true
+
+            - uses: actions/cache@v3
+              with:
+                  path: |
+                     data/country_osm_grid.sql.gz
+                  key: nominatim-country-data-1
+
+            - name: Package tarball
+              run: |
+                  if [ ! -f data/country_osm_grid.sql.gz ]; then
+                      wget --no-verbose -O data/country_osm_grid.sql.gz https://www.nominatim.org/data/country_grid.sql.gz
+                  fi
+                  cd ..
+                  tar czf nominatim-src.tar.bz2 Nominatim
+                  mv nominatim-src.tar.bz2 Nominatim
+
+            - name: 'Upload Artifact'
+              uses: actions/upload-artifact@v3
+              with:
+                  name: full-source
+                  path: nominatim-src.tar.bz2
+                  retention-days: 1
+
     tests:
+        needs: create-archive
         strategy:
             matrix:
-                ubuntu: [18, 20]
+                ubuntu: [18, 20, 22]
                 include:
                     - ubuntu: 18
-                      postgresql: 9.5
+                      postgresql: 9.6
                       postgis: 2.5
                       pytest: pytest
                       php: 7.2
@@ -18,39 +49,36 @@ jobs:
                       postgis: 3
                       pytest: py.test-3
                       php: 7.4
+                    - ubuntu: 22
+                      postgresql: 15
+                      postgis: 3
+                      pytest: py.test-3
+                      php: 8.1
 
         runs-on: ubuntu-${{ matrix.ubuntu }}.04
 
         steps:
-            - uses: actions/checkout@v2
+            - uses: actions/download-artifact@v3
               with:
-                  submodules: true
-                  path: Nominatim
+                  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 }}
-                  coverage: xdebug
-                  tools: phpunit, phpcs, composer
+                  tools: phpunit:9, phpcs, composer
+                  ini-values: opcache.jit=disable
+              env:
+                  GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
-            - uses: actions/setup-python@v2
+            - uses: actions/setup-python@v4
               with:
                 python-version: 3.6
               if: matrix.ubuntu == 18
 
-            - name: Get Date
-              id: get-date
-              run: |
-                  echo "::set-output name=date::$(/bin/date -u "+%Y%W")"
-              shell: bash
-
-            - uses: actions/cache@v2
-              with:
-                  path: |
-                     country_grid.sql.gz
-                  key: nominatim-country-data-${{ steps.get-date.outputs.date }}
-
             - uses: ./Nominatim/.github/actions/setup-postgresql
               with:
                   postgresql-version: ${{ matrix.postgresql }}
@@ -61,157 +89,234 @@ jobs:
                   ubuntu: ${{ matrix.ubuntu }}
 
             - name: Install test prerequsites
-              run: sudo apt-get install -y -qq pylint python3-pytest python3-behave python3-pytest-cov php-codecoverage
+              run: sudo apt-get install -y -qq python3-pytest python3-behave
               if: matrix.ubuntu == 20
 
             - name: Install test prerequsites
-              run: |
-                   pip3 install pylint==2.6.0 pytest pytest-cov behave==1.2.6
-              if: matrix.ubuntu == 18
+              run: pip3 install pylint pytest behave==1.2.6
+              if: ${{ (matrix.ubuntu == 18) || (matrix.ubuntu == 22) }}
+
+            - name: Install test prerequsites
+              run: sudo apt-get install -y -qq python3-pytest
+              if: matrix.ubuntu == 22
+
+            - name: Install latest pylint/mypy
+              run: pip3 install -U pylint mypy types-PyYAML types-jinja2 types-psycopg2 types-psutil types-requests typing-extensions
+              if: matrix.ubuntu == 22
 
             - name: PHP linting
               run: phpcs --report-width=120 .
               working-directory: Nominatim
+              if: matrix.ubuntu == 22
 
             - name: Python linting
               run: pylint nominatim
               working-directory: Nominatim
+              if: matrix.ubuntu == 22
+
+            - name: Python static typechecking
+              run: mypy --strict nominatim
+              working-directory: Nominatim
+              if: matrix.ubuntu == 22
+
 
             - name: PHP unit tests
-              run: phpunit --coverage-clover ../../coverage-php.xml ./
+              run: phpunit ./
               working-directory: Nominatim/test/php
-              if: matrix.ubuntu == 20
+              if: ${{ (matrix.ubuntu == 20) || (matrix.ubuntu == 22) }}
 
             - name: Python unit tests
-              run: $PYTEST --cov=nominatim --cov-report=xml test/python
+              run: $PYTEST test/python
               working-directory: Nominatim
               env:
                 PYTEST: ${{ matrix.pytest }}
 
-            - name: BDD tests
-              run: |
-                  mkdir cov
-                  behave -DREMOVE_TEMPLATE=1 -DBUILDDIR=$GITHUB_WORKSPACE/build --format=progress3 -DPHPCOV=./cov
-                  composer require phpunit/phpcov:7.0.2
-                  vendor/bin/phpcov merge --clover ../../coverage-bdd.xml ./cov
-              working-directory: Nominatim/test/bdd
-              if: matrix.ubuntu == 20
-
             - name: BDD tests
               run: |
                   behave -DREMOVE_TEMPLATE=1 -DBUILDDIR=$GITHUB_WORKSPACE/build --format=progress3
               working-directory: Nominatim/test/bdd
-              if: matrix.ubuntu == 18
 
-            - name: BDD tests (legacy_icu tokenizer)
-              run: |
-                  behave -DREMOVE_TEMPLATE=1 -DBUILDDIR=$GITHUB_WORKSPACE/build -DTOKENIZER=legacy_icu --format=progress3
-              working-directory: Nominatim/test/bdd
 
-            - name: Upload coverage to Codecov
-              uses: codecov/codecov-action@v1
-              with:
-                files: ./Nominatim/coverage*.xml
-                directory: ./
-                name: codecov-umbrella
-                fail_ci_if_error: false
-                path_to_write_report: ./coverage/codecov_report.txt
-                verbose: true
-              if: matrix.ubuntu == 20
-
-    import:
-        strategy:
-            matrix:
-                ubuntu: [18, 20]
-                include:
-                    - ubuntu: 18
-                      postgresql: 9.5
-                      postgis: 2.5
-                    - ubuntu: 20
-                      postgresql: 13
-                      postgis: 3
-
-        runs-on: ubuntu-${{ matrix.ubuntu }}.04
+    legacy-test:
+        needs: create-archive
+        runs-on: ubuntu-20.04
 
         steps:
-            - uses: actions/checkout@v2
+            - uses: actions/download-artifact@v3
               with:
-                  submodules: true
-                  path: Nominatim
+                  name: full-source
 
-            - name: Get Date
-              id: get-date
-              run: |
-                  echo "::set-output name=date::$(/bin/date -u "+%Y%W")"
-              shell: bash
+            - name: Unpack Nominatim
+              run: tar xf nominatim-src.tar.bz2
 
-            - uses: actions/cache@v2
+            - name: Setup PHP
+              uses: shivammathur/setup-php@v2
               with:
-                  path: |
-                     country_grid.sql.gz
-                  key: nominatim-country-data-${{ steps.get-date.outputs.date }}
-
-            - uses: actions/cache@v2
-              with:
-                  path: |
-                     monaco-latest.osm.pbf
-                  key: nominatim-test-data-${{ steps.get-date.outputs.date }}
-
-            - uses: actions/setup-python@v2
-              with:
-                python-version: 3.6
-              if: matrix.ubuntu == 18
+                  php-version: 7.4
 
             - uses: ./Nominatim/.github/actions/setup-postgresql
               with:
-                  postgresql-version: ${{ matrix.postgresql }}
-                  postgis-version: ${{ matrix.postgis }}
+                  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: ${{ matrix.ubuntu }}
+                  ubuntu: 20
+                  cmake-args: -DBUILD_MODULE=on
 
-            - name: Clean installation
-              run: rm -rf Nominatim build
+            - 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
+        needs: create-archive
+
+        strategy:
+            matrix:
+                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
+
+        container:
+            image: ${{ matrix.image }}
+            env:
+                LANG: en_US.UTF-8
+
+        defaults:
+            run:
+                shell: sudo -Hu nominatim bash --noprofile --norc -eo pipefail {0}
+
+        steps:
+            - name: Prepare container (Ubuntu)
+              run: |
+                  export APT_LISTCHANGES_FRONTEND=none
+                  export DEBIAN_FRONTEND=noninteractive
+                  apt-get update -qq
+                  apt-get install -y git sudo wget
+                  ln -snf /usr/share/zoneinfo/$CONTAINER_TIMEZONE /etc/localtime && echo $CONTAINER_TIMEZONE > /etc/timezone
               shell: bash
+              if: matrix.flavour == 'ubuntu'
+
+            - name: Prepare container (CentOS)
+              run: |
+                  dnf update -y
+                  dnf install -y sudo glibc-langpack-en
+              shell: bash
+              if: matrix.flavour == 'centos'
+
+            - name: Setup import user
+              run: |
+                  useradd -m nominatim
+                  echo 'nominatim   ALL=(ALL:ALL) NOPASSWD: ALL' > /etc/sudoers.d/nominiatim
+                  echo "/home/nominatim/Nominatim/vagrant/Install-on-${OS}.sh no $INSTALL_MODE" > /home/nominatim/vagrant.sh
+              shell: bash
+              env:
+                OS: ${{ matrix.name }}
+                INSTALL_MODE: ${{ matrix.install_mode }}
+
+            - uses: actions/download-artifact@v3
+              with:
+                  name: full-source
+                  path: /home/nominatim
+
+            - name: Install Nominatim
+              run: |
+                export USERNAME=nominatim
+                export USERHOME=/home/nominatim
+                export NOSYSTEMD=yes
+                export HAVE_SELINUX=no
+                tar xf nominatim-src.tar.bz2
+                . vagrant.sh
+              working-directory: /home/nominatim
 
             - name: Prepare import environment
               run: |
-                  if [ ! -f monaco-latest.osm.pbf ]; then
-                      wget --no-verbose https://download.geofabrik.de/europe/monaco-latest.osm.pbf
-                  fi
-                  mkdir data-env
-                  cd data-env
-              shell: bash
+                  mv Nominatim/test/testdb/apidb-test-data.pbf test.pbf
+                  rm -rf Nominatim
+                  mkdir data-env-reverse
+              working-directory: /home/nominatim
 
+            - name: Prepare import environment (CentOS)
+              run: |
+                  sudo ln -s /usr/local/bin/nominatim /usr/bin/nominatim
+                  echo NOMINATIM_DATABASE_WEBUSER="apache" > nominatim-project/.env
+                  cp nominatim-project/.env data-env-reverse/.env
+              working-directory: /home/nominatim
+              if: matrix.flavour == 'centos'
+
+            - name: Print version
+              run: nominatim --version
+              working-directory: /home/nominatim/nominatim-project
+
+            - name: Collect host OS information
+              run: nominatim admin --collect-os-info
+              working-directory: /home/nominatim/nominatim-project
+              
             - name: Import
-              run: nominatim import --osm-file ../monaco-latest.osm.pbf
-              shell: bash
-              working-directory: data-env
+              run: nominatim import --osm-file ../test.pbf
+              working-directory: /home/nominatim/nominatim-project
 
             - name: Import special phrases
               run: nominatim special-phrases --import-from-wiki
-              working-directory: data-env
+              working-directory: /home/nominatim/nominatim-project
 
             - name: Check full import
               run: nominatim admin --check-database
-              working-directory: data-env
+              working-directory: /home/nominatim/nominatim-project
 
             - name: Warm up database
               run: nominatim admin --warm
-              working-directory: data-env
+              working-directory: /home/nominatim/nominatim-project
+
+            - name: Prepare update (Ubuntu)
+              run: apt-get install -y python3-pip
+              shell: bash
+              if: matrix.flavour == 'ubuntu'
 
             - name: Run update
               run: |
-                   nominatim replication --init
-                   nominatim replication --once
-              working-directory: data-env
+                  pip3 install --user osmium
+                  nominatim replication --init
+                  NOMINATIM_REPLICATION_MAX_DIFF=1 nominatim replication --once
+              working-directory: /home/nominatim/nominatim-project
+
+            - name: Clean up database
+              run: nominatim refresh --postcodes --word-tokens
+              working-directory: /home/nominatim/nominatim-project
 
             - name: Run reverse-only import
-              run : nominatim import --osm-file ../monaco-latest.osm.pbf --reverse-only --no-updates
-              working-directory: data-env
-              env:
-                  NOMINATIM_DATABASE_DSN: pgsql:dbname=reverse
+              run : |
+                  echo 'NOMINATIM_DATABASE_DSN="pgsql:dbname=reverse"' >> .env
+                  nominatim import --osm-file ../test.pbf --reverse-only --no-updates
+              working-directory: /home/nominatim/data-env-reverse
 
-            - name: Check reverse import
+            - name: Check reverse-only import
               run: nominatim admin --check-database
-              working-directory: data-env
+              working-directory: /home/nominatim/data-env-reverse
+
+            - name: Clean up database (reverse-only import)
+              run: nominatim refresh --postcodes --word-tokens
+              working-directory: /home/nominatim/nominatim-project

.gitignore

@@ -1,12 +1,9 @@
 *.log
 *.pyc
 
-build
-settings/local.php
+docs/develop/*.png
 
-data/wiki_import.sql
-data/wiki_specialphrases.sql
-data/osmosischange.osc
+build
 
 .vagrant
 data/country_osm_grid.sql.gz

.mypy.ini

@@ -0,0 +1,13 @@
+[mypy]
+
+[mypy-icu.*]
+ignore_missing_imports = True
+
+[mypy-osmium.*]
+ignore_missing_imports = True
+
+[mypy-datrie.*]
+ignore_missing_imports = True
+
+[mypy-dotenv.*]
+ignore_missing_imports = True

.pylintrc

@@ -10,6 +10,9 @@ ignored-modules=icu,datrie
 # closing added here because it sometimes triggers a false positive with
 # 'with' statements.
 ignored-classes=NominatimArgs,closing
-disable=too-few-public-methods,duplicate-code
+# 'too-many-ancestors' is triggered already by deriving from UserDict
+# 'not-context-manager' disabled because it causes false positives once
+#   typed Python is enabled. See also https://github.com/PyCQA/pylint/issues/5273
+disable=too-few-public-methods,duplicate-code,too-many-ancestors,bad-option-value,no-self-use,not-context-manager,use-dict-literal
 
-good-names=i,x,y,fd,db
+good-names=i,x,y,m,fd,db,cc

AUTHORS

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

CMakeLists.txt

@@ -18,14 +18,25 @@ list(APPEND CMAKE_MODULE_PATH "${CMAKE_SOURCE_DIR}/cmake")
 
 project(nominatim)
 
-set(NOMINATIM_VERSION_MAJOR 3)
-set(NOMINATIM_VERSION_MINOR 7)
-set(NOMINATIM_VERSION_PATCH 0)
+set(NOMINATIM_VERSION_MAJOR 4)
+set(NOMINATIM_VERSION_MINOR 2)
+set(NOMINATIM_VERSION_PATCH 2)
 
 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
@@ -33,11 +44,12 @@ add_definitions(-DNOMINATIM_VERSION="${NOMINATIM_VERSION}")
 
 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 on CACHE BOOL "Build PostgreSQL module")
+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)
@@ -51,7 +63,6 @@ if (BUILD_IMPORTER AND BUILD_OSM2PGSQL)
     endif()
     set(BUILD_TESTS_SAVED "${BUILD_TESTS}")
     set(BUILD_TESTS off)
-    set(WITH_LUA off CACHE BOOL "")
     add_subdirectory(osm2pgsql)
     set(BUILD_TESTS ${BUILD_TESTS_SAVED})
 endif()
@@ -153,7 +164,7 @@ if (BUILD_TESTS)
     if (PHPCS)
         message(STATUS "Using phpcs binary ${PHPCS}")
         add_test(NAME phpcs
-                 COMMAND ${PHPCS} --report-width=120 --colors lib website utils
+                 COMMAND ${PHPCS} --report-width=120 --colors lib-php
                  WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})
     else()
         message(WARNING "phpcs not found. PHP linting tests disabled." )
@@ -199,7 +210,7 @@ endif()
 #-----------------------------------------------------------------------------
 
 if (BUILD_MANPAGE)
-   add_subdirectory(manual)
+   add_subdirectory(man)
 endif()
 
 #-----------------------------------------------------------------------------
@@ -211,6 +222,7 @@ 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)
@@ -224,8 +236,7 @@ if (BUILD_IMPORTER)
             PATTERN __pycache__ EXCLUDE)
     install(DIRECTORY lib-sql DESTINATION ${NOMINATIM_LIBDIR})
 
-    install(FILES data/country_name.sql
-                  ${COUNTRY_GRID_FILE}
+    install(FILES ${COUNTRY_GRID_FILE}
                   data/words.sql
             DESTINATION ${NOMINATIM_DATADIR})
 endif()
@@ -258,6 +269,24 @@ install(FILES settings/env.defaults
               settings/import-address.style
               settings/import-full.style
               settings/import-extratags.style
-              settings/legacy_icu_tokenizer.yaml
-              settings/icu-rules/extended-unicode-to-asccii.yaml
+              settings/import-admin.lua
+              settings/import-street.lua
+              settings/import-address.lua
+              settings/import-full.lua
+              settings/import-extratags.lua
+              settings/flex-base.lua
+              settings/icu_tokenizer.yaml
+              settings/country_settings.yaml
         DESTINATION ${NOMINATIM_CONFIGDIR})
+
+install(DIRECTORY settings/icu-rules
+        DESTINATION ${NOMINATIM_CONFIGDIR})
+install(DIRECTORY settings/country-names
+        DESTINATION ${NOMINATIM_CONFIGDIR})
+
+if (INSTALL_MUNIN_PLUGINS)
+    install(FILES munin/nominatim_importlag
+                  munin/nominatim_query_speed
+                  munin/nominatim_requests
+            DESTINATION ${NOMINATIM_MUNINDIR})
+endif()

CONTRIBUTING.md

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

ChangeLog

@@ -1,3 +1,147 @@
+4.2.2
+
+ * extend flex-style library to fully support all default styles
+ * fix handling of Hebrew aleph
+ * do not assign postcodes to rivers
+ * fix string matching in PHP code
+ * update osm2pgsql (various updates to flex)
+ * fix slow query when deleting places on update
+ * fix CLI details query
+ * fix recalculation of importance values
+ * fix polygon simplification in reverse results
+ * add class/type information to reverse geocodejson result
+ * minor improvements to default tokenizer configuration
+ * various smaller fixes to documentation
+
+4.2.1
+
+ * fix XSS vulnerability in debug view
+
+4.2.0
+
+ * add experimental support for osm2pgsql flex style
+ * introduce secondary importance value to be retrieved from a raster data file
+   (currently still unused, to replace address importance, thanks to @tareqpi)
+ * add new report tool `nominatim admin --collect-os-info`
+   (thanks @micahcochran, @tareqpi)
+ * reorganise index to improve lookup performance and size
+ * run index creation after import in parallel
+ * run ANALYZE more selectively to speed up continuation of indexing
+ * fix crash on update when addr:interpolation receives an illegal value
+ * fix minimum number of retrieved results to be at least 10
+ * fix search for combinations of special term + name (e.g Hotel Bellevue)
+ * do not return interpolations without a parent street on reverse search
+ * improve invalidation of linked places on updates
+ * fix address parsing for interpolation lines
+ * make sure socket timeouts are respected during replication
+   (working around a bug in some versions of pyosmium)
+ * update bundled osm2pgsql to 1.7.1
+ * add support for PostgreSQL 15
+ * typing fixes to work with latest type annotations from typeshed
+ * smaller improvements to documentation (thanks to @mausch)
+
+4.1.1
+
+ * fix XSS vulnerability in debug view
+
+4.1.0
+
+ * switch to ICU tokenizer as default
+ * add housenumber normalization and support optional spaces during search
+ * add postcode format checking and support optional spaces during search
+ * add function for cleaning housenumbers in word table
+ * add updates/deletion of country names imported from OSM
+ * linked places no longer overwrite names from a place permanently
+ * move default country name configuration into yaml file (thanks @tareqpi)
+ * more compact layout for interpolation and TIGER tables
+ * introduce mutations to ICU tokenizer (used for German umlauts)
+ * support reinitializing a full project directory with refresh --website
+ * fix various issues with linked places on updates
+ * add support for external sanitizers and token analyzers
+ * add CLI commands for forced indexing
+ * add CLI command for version report
+ * add offline import mode
+ * change geocodejson to return a feature class in the 'type' field
+ * add ISO3166-2 to address output (thanks @I70l0teN4ik)
+ * improve parsing and matching of addr: tags
+ * support relations as street members of associatedStreet
+ * better ranking for address results from TIGER data
+ * adapt rank classification to changed tag usage in OSM
+ * update bundled osm2pgsql to 1.6.0
+ * add typing information to Python code
+ * improve unit test coverage
+ * reorganise and speed up code for BDD tests, drop support for scenes
+ * move PHP unit tests to PHP 9.5
+ * extensive typo fixes in documentation (thanks @woodpeck,@StephanGeorg,
+   @amandasaurus, @nslxndr, @stefkiourk, @Luflosi, @kianmeng)
+ * drop official support for installation on CentOS
+ * add installation instructions for Ubuntu 22.04
+ * add support for PHP8
+ * add setup instructions for updates and systemd
+ * drop support for PostgreSQL 9.5
+
+4.0.2
+
+ * fix XSS vulnerability in debug view
+
+4.0.1
+
+ * fix initialisation error in replication script
+ * ICU tokenizer: avoid any special characters in word tokens
+ * better error message when API php script does not exist
+ * fix quoting of house numbers in SQL queries
+ * small fixes and improvements in search query parsing
+ * add documentation for moving the database to a different machine
+
+4.0.0
+
+ * refactor name token computation and introduce ICU tokenizer
+   * name processing now happens in the indexer outside the DB
+   * reorganizes abbreviation handling and moves it to the indexing phases
+   * adds preprocessing of names
+ * add country-specific ranking for Spain, Slovakia
+ * partially switch to using SP-GIST indexes
+ * better updating of dependent addresses for name changes in streets
+ * remove unused/broken tables for external housenumbers
+ * move external postcodes to CSV format and no longer save them in tables
+   (adds support for postcodes for arbitrary countries)
+ * remove postcode helper entries from placex (thanks @AntoJvlt)
+ * change required format for TIGER data to CSV
+ * move configuration of default languages from wiki into config file
+ * expect customized configuration files in project directory by default
+ * disable search API for reverse-only import (thanks @darkshredder)
+ * port most of maintenance/import code to Python and remove PHP utils
+ * add catch-up mode for replication
+ * add updating of special phrases (thanks @AntoJvlt)
+ * add support for special phrases in CSV files (thanks @AntoJvlt)
+ * switch to case-independent matching between place and boundary names
+ * remove disabling of reverse query parsing
+ * minor tweaks to search algorithm to avoid more false positives
+ * major overhaul of the administrator and developer documentation
+ * add security disclosure policy
+ * 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
+ * do not error out in status API result when import date is missing
+ * add array_key_last function for PHP < 7.3 (thanks to @woodpeck)
+ * fix more url when server name is unknown (thanks to @mogita)
+ * commit changes to replication log table
+
+3.7.1
+
+ * fix smaller issues with special phrases import (thanks @AntoJvlt)
+ * add index to speed up continued indexing during import
+ * fix index on location_property_tiger(parent_place_id) (thanks @changpingc)
+ * make sure Python code is backward-compatible with Python 3.5
+ * various documentation fixes
+
 3.7.0
 
  * switch to dotenv for configuration file
@@ -20,7 +164,6 @@
  * add non-key indexes to speed up housenumber + street searches
  * switch housenumber field in placex to save transliterated names
 
-
 3.6.0
 
  * add full support for searching by and displaying of addr:* tags

README.md

@@ -20,14 +20,6 @@ https://nominatim.org/release-docs/develop/ .
 Installation
 ============
 
-**Nominatim is a complex piece of software and runs in a complex environment.
-Installing and running Nominatim is something for experienced system
-administrators only who can do some trouble-shooting themselves. We are sorry,
-but we can not provide installation support. We are all doing this in our free
-time and there is just so much of that time to go around. Do not open issues in
-our bug tracker if you need help. Use the discussions forum
-or ask for help on [help.openstreetmap.org](https://help.openstreetmap.org/).**
-
 The latest stable release can be downloaded from https://nominatim.org.
 There you can also find [installation instructions for the release](https://nominatim.org/release-docs/latest/admin/Installation), as well as an extensive [Troubleshooting/FAQ section](https://nominatim.org/release-docs/latest/admin/Faq/).
 

SECURITY.md

@@ -9,10 +9,11 @@ versions.
 
 | Version | End of support for security updates |
 | ------- | ----------------------------------- |
+| 4.2.x   | 2024-11-24                          |
+| 4.1.x   | 2024-08-05                          |
+| 4.0.x   | 2023-11-02                          |
 | 3.7.x   | 2023-04-05                          |
 | 3.6.x   | 2022-12-12                          |
-| 3.5.x   | 2022-06-05                          |
-| 3.4.x   | 2021-10-24                          |
 
 ## Reporting a Vulnerability
 

VAGRANT.md

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

cmake/tool-installed.tmpl

@@ -7,6 +7,9 @@ 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',

cmake/tool.tmpl

@@ -7,6 +7,9 @@ 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',

codecov.yml

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

docs/CMakeLists.txt

@@ -10,6 +10,7 @@ set (DOC_SOURCES
      admin
      develop
      api
+     customize
      index.md
      extra.css
      styles.css
@@ -22,11 +23,13 @@ foreach (src ${DOC_SOURCES})
 endforeach()
 
 ADD_CUSTOM_TARGET(doc
-   COMMAND ${CMAKE_CURRENT_SOURCE_DIR}/bash2md.sh ${PROJECT_SOURCE_DIR}/vagrant/Install-on-Centos-7.sh ${CMAKE_CURRENT_BINARY_DIR}/appendix/Install-on-Centos-7.md
-   COMMAND ${CMAKE_CURRENT_SOURCE_DIR}/bash2md.sh ${PROJECT_SOURCE_DIR}/vagrant/Install-on-Centos-8.sh ${CMAKE_CURRENT_BINARY_DIR}/appendix/Install-on-Centos-8.md
    COMMAND ${CMAKE_CURRENT_SOURCE_DIR}/bash2md.sh ${PROJECT_SOURCE_DIR}/vagrant/Install-on-Ubuntu-18.sh ${CMAKE_CURRENT_BINARY_DIR}/appendix/Install-on-Ubuntu-18.md
    COMMAND ${CMAKE_CURRENT_SOURCE_DIR}/bash2md.sh ${PROJECT_SOURCE_DIR}/vagrant/Install-on-Ubuntu-20.sh ${CMAKE_CURRENT_BINARY_DIR}/appendix/Install-on-Ubuntu-20.md
-   COMMAND mkdocs build -d ${CMAKE_CURRENT_BINARY_DIR}/../site-html -f ${CMAKE_CURRENT_BINARY_DIR}/../mkdocs.yml
+   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}
+)

docs/admin/Advanced-Installations.md

@@ -5,9 +5,34 @@ 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 multiple regions
+## Importing multiple regions (without updates)
 
-To import multiple regions in your database, you need to configure and run `utils/import_multiple_regions.sh` file. This script will set up the update directory which has the following structure:
+To import multiple regions in your database you can simply give multiple
+OSM files to the import command:
+
+```
+nominatim import --osm-file file1.pbf --osm-file file2.pbf
+```
+
+If you already have imported a file and want to add another one, you can
+use the add-data function to import the additional data as follows:
+
+```
+nominatim add-data --file <FILE>
+nominatim refresh --postcodes
+nominatim index -j <NUMBER OF THREADS>
+```
+
+Please note that adding additional data is always significantly slower than
+the original import.
+
+## Importing multiple regions (with updates)
+
+If you want to import multiple regions _and_ be able to keep them up-to-date
+with updates, then you can use the scripts provided in the `utils` directory.
+
+These scripts will set up an `update` directory in your project directory,
+which has the following structure:
 
 ```bash
 update
@@ -17,7 +42,6 @@ update
     │   └── monaco
     │       └── sequence.state
     └── tmp
-        ├── combined.osm.pbf
         └── europe
                 ├── andorra-latest.osm.pbf
                 └── monaco-latest.osm.pbf
@@ -25,87 +49,59 @@ update
 
 ```
 
-The `sequence.state` files will contain the sequence ID, which will be used by pyosmium to get updates. The tmp folder is used for import dump.
+The `sequence.state` files contain the sequence ID for each region. They will
+be used by pyosmium to get updates. The `tmp` folder is used for import dump and
+can be deleted once the import is complete.
 
-### Configuring multiple regions
-
-The file `import_multiple_regions.sh` needs to be edited as per your requirement:
-
-1. List of countries. eg:
-
-        COUNTRIES="europe/monaco europe/andorra"
-
-2. Path to Build directory. eg:
-
-        NOMINATIMBUILD="/srv/nominatim/build"
-
-3. Path to Update directory. eg:
-        
-        UPDATEDIR="/srv/nominatim/update"
-
-4. Replication URL. eg:
-    
-        BASEURL="https://download.geofabrik.de"
-        DOWNCOUNTRYPOSTFIX="-latest.osm.pbf"
 
 ### Setting up multiple regions
 
-!!! tip
-    If your database already exists and you want to add more countries,
-    replace the setting up part
-    `${SETUPFILE} --osm-file ${UPDATEDIR}/tmp/combined.osm.pbf --all 2>&1`
-    with `${UPDATEFILE} --import-file ${UPDATEDIR}/tmp/combined.osm.pbf --index --index-instances N 2>&1`
-    where N is the numbers of CPUs in your system.
+Create a project directory as described for the
+[simple import](Import.md#creating-the-project-directory). If necessary,
+you can also add an `.env` configuration with customized options. In particular,
+you need to make sure that `NOMINATIM_REPLICATION_UPDATE_INTERVAL` and
+`NOMINATIM_REPLICATION_RECHECK_INTERVAL` are set according to the update
+interval of the extract server you use.
 
-Run the following command from your Nominatim directory after configuring the file.
+Copy the scripts `utils/import_multiple_regions.sh` and `utils/update_database.sh`
+into the project directory.
 
-    bash ./utils/import_multiple_regions.sh
+Now customize both files as per your requirements
 
-!!! danger "Important"
-        This file uses osmium-tool. It must be installed before executing the import script.
-        Installation instructions can be found [here](https://osmcode.org/osmium-tool/manual.html#installation).
-
-### Updating multiple regions
-
-To import multiple regions in your database, you need to configure and run ```utils/update_database.sh```.
-This uses the update directory set up while setting up the DB.   
-
-### Configuring multiple regions
-
-The file `update_database.sh` needs to be edited as per your requirement:
-
-1. List of countries. eg:
+1. List of countries. e.g.
 
         COUNTRIES="europe/monaco europe/andorra"
 
-2. Path to Build directory. eg:
+2. URL to the service providing the extracts and updates. eg:
 
-        NOMINATIMBUILD="/srv/nominatim/build"
-
-3. Path to Update directory. eg:
-        
-        UPDATEDIR="/srv/nominatim/update"
-
-4. Replication URL. eg:
-    
         BASEURL="https://download.geofabrik.de"
-        DOWNCOUNTRYPOSTFIX="-updates"
+        DOWNCOUNTRYPOSTFIX="-latest.osm.pbf"
 
-5. Followup can be set according to your installation. eg: For Photon,
+5. Followup in the update script can be set according to your installation.
+   E.g. for Photon,
 
         FOLLOWUP="curl http://localhost:2322/nominatim-update"
 
     will handle the indexing.
 
+
+To start the initial import, change into the project directory and run
+
+```
+    bash import_multiple_regions.sh
+```
+
 ### Updating the database
 
-Run the following command from your Nominatim directory after configuring the file.
+Change into the project directory and run the following command:
 
-    bash ./utils/update_database.sh
+    bash update_database.sh
 
-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.
+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.
 
-## Importing Nominatim to an external PostgreSQL database
+## Using an external PostgreSQL database
 
 You can install Nominatim using a database that runs on a different server when
 you have physical access to the file system on the other server. Nominatim
@@ -113,6 +109,11 @@ 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
@@ -170,4 +171,46 @@ NOMINATIM_DATABASE_MODULE_PATH="<directory on the database server where nominati
 ```
 
 Now change the `NOMINATIM_DATABASE_DSN` to point to your remote server and continue
-to follow the [standard instructions for importing](/admin/Import).
+to follow the [standard instructions for importing](Import.md).
+
+
+## Moving the database to another machine
+
+For some configurations it may be useful to run the import on one machine, then
+move the database to another machine and run the Nominatim service from there.
+For example, you might want to use a large machine to be able to run the import
+quickly but only want a smaller machine for production because there is not so
+much load. Or you might want to do the import once and then replicate the
+database to many machines.
+
+The important thing to keep in mind when transferring the Nominatim installation
+is that you need to transfer the database _and the project directory_. Both
+parts are essential for your installation.
+
+The Nominatim database can be transferred using the `pg_dump`/`pg_restore` tool.
+Make sure to use the same version of PostgreSQL and PostGIS on source and
+target machine.
+
+!!! note
+    Before creating a dump of your Nominatim database, consider running
+    `nominatim freeze` first. Your database looses the ability to receive further
+    data updates but the resulting database is only about a third of the size
+    of a full database.
+
+Next install Nominatim on the target machine by following the standard installation
+instructions. Again, make sure to use the same version as the source machine.
+
+Create a project directory on your destination machine and set up the `.env`
+file to match the configuration on the source machine. Finally run
+
+    nominatim refresh --website
+
+to make sure that the local installation of Nominatim will be used.
+
+If you are using the legacy tokenizer you might also have to switch to the
+PostgreSQL module that was compiled on your target machine. If you get errors
+that PostgreSQL cannot find or access `nominatim.so` then rerun
+
+   nominatim refresh --functions
+
+on the target machine to update the the location of the module.

docs/admin/Customization.md

@@ -1,101 +0,0 @@
-# Customization of the Database
-
-This section explains in detail how to configure a Nominatim import and
-the various means to use external data.
-
-## External postcode data
-
-Nominatim creates a table of known postcode centroids during import. This table
-is used for searches of postcodes and for adding postcodes to places where the
-OSM data does not provide one. These postcode centroids are mainly computed
-from the OSM data itself. In addition, Nominatim supports reading postcode
-information from an external CSV file, to supplement the postcodes that are
-missing in OSM.
-
-To enable external postcode support, simply put one CSV file per country into
-your project directory and name it `<CC>_postcodes.csv`. `<CC>` must be the
-two-letter country code for which to apply the file. The file may also be
-gzipped. Then it must be called `<CC>_postcodes.csv.gz`.
-
-The CSV file must use commas as a delimiter and have a header line. Nominatim
-expects three columns to be present: `postcode`, `lat` and `lon`. All other
-columns are ignored. `lon` and `lat` must describe the x and y coordinates of the
-postcode centroids in WGS84.
-
-The postcode files are loaded only when there is data for the given country
-in your database. For example, if there is a `us_postcodes.csv` file in your
-project directory but you import only an excerpt of Italy, then the US postcodes
-will simply be ignored.
-
-As a rule, the external postcode data should be put into the project directory
-**before** starting the initial import. Still, you can add, remove and update the
-external postcode data at any time. Simply
-run:
-
-```
-nominatim refresh --postcodes
-```
-
-to make the changes visible in your database. Be aware, however, that the changes
-only have an immediate effect on searches for postcodes. Postcodes that were
-added to places are only updated, when they are reindexed. That usually happens
-only during replication updates.
-
-## Installing Tiger housenumber data for the US
-
-Nominatim is able to use the official [TIGER](https://www.census.gov/geographies/mapping-files/time-series/geo/tiger-line-file.html)
-address set to complement the OSM house number data in the US. You can add
-TIGER data to your own Nominatim instance by following these steps. The
-entire US adds about 10GB to your database.
-
-  1. Get preprocessed TIGER 2020 data:
-
-        cd $PROJECT_DIR
-        wget https://nominatim.org/data/tiger2020-nominatim-preprocessed.csv.tar.gz
-
-  2. Import the data into your Nominatim database:
-
-        nominatim add-data --tiger-data tiger2020-nominatim-preprocessed.csv.tar.gz
-
-  3. Enable use of the Tiger data in your `.env` by adding:
-
-        echo NOMINATIM_USE_US_TIGER_DATA=yes >> .env
-
-  4. Apply the new settings:
-
-        nominatim refresh --functions
-
-
-See the [developer's guide](../develop/data-sources.md#us-census-tiger) for more
-information on how the data got preprocessed.
-
-## Special phrases import
-
-As described in the [Importation chapter](Import.md), it is possible to
-import special phrases from the wiki with the following command:
-
-```sh
-nominatim special-phrases --import-from-wiki
-```
-
-But, it is also possible to import some phrases from a csv file. 
-To do so, you have access to the following command:
-
-```sh
-nominatim special-phrases --import-from-csv <csv file>
-```
-
-Note that the two previous import commands will update the phrases from your database.
-This means that if you import some phrases from a csv file, only the phrases
-present in the csv file will be kept into the database. All other phrases will
-be removed.
-
-If you want to only add new phrases and not update the other ones you can add
-the argument `--no-replace` to the import command. For example:
-
-```sh
-nominatim special-phrases --import-from-csv <csv file> --no-replace
-```
-
-This will add the phrases present in the csv file into the database without
-removing the other ones.

docs/admin/Deployment.md

@@ -82,7 +82,7 @@ The website should now be available on `http://localhost/nominatim`.
 
 ### Installing the required packages
 
-Nginx has no built-in PHP interpreter. You need to use php-fpm as a deamon for
+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:
@@ -99,7 +99,7 @@ Unix socket instead, change the pool configuration
 
 ``` ini
 ; Replace the tcp listener and add the unix socket
-listen = /var/run/php-fpm.sock
+listen = /var/run/php-fpm-nominatim.sock
 
 ; Ensure that the daemon runs as the correct user
 listen.owner = www-data
@@ -121,7 +121,7 @@ location @php {
     fastcgi_param SCRIPT_FILENAME "$document_root$uri.php";
     fastcgi_param PATH_TRANSLATED "$document_root$uri.php";
     fastcgi_param QUERY_STRING    $args;
-    fastcgi_pass unix:/var/run/php-fpm.sock;
+    fastcgi_pass unix:/var/run/php-fpm-nominatim.sock;
     fastcgi_index index.php;
     include fastcgi_params;
 }
@@ -131,7 +131,7 @@ location ~ [^/]\.php(/|$) {
     if (!-f $document_root$fastcgi_script_name) {
         return 404;
     }
-    fastcgi_pass unix:/var/run/php-fpm.sock;
+    fastcgi_pass unix:/var/run/php-fpm-nominatim.sock;
     fastcgi_index search.php;
     include fastcgi.conf;
 }
@@ -140,3 +140,9 @@ location ~ [^/]\.php(/|$) {
 Restart the nginx and php-fpm services and the website should now be available
 at `http://localhost/`.
 
+## Nominatim with other webservers
+
+Users have created instructions for other webservers:
+
+* [Caddy](https://github.com/osm-search/Nominatim/discussions/2580)
+

docs/admin/Faq.md

@@ -79,7 +79,7 @@ When running the import you may get a version mismatch:
 
 pg_config seems to use bad includes sometimes when multiple versions
 of PostgreSQL are available in the system. Make sure you remove the
-server development libraries (`postgresql-server-dev-9.5` on Ubuntu)
+server development libraries (`postgresql-server-dev-13` on Ubuntu)
 and recompile (`cmake .. && make`).
 
 
@@ -106,11 +106,6 @@ If you are using a flatnode file, then it may also be that the underlying
 filesystem does not fully support 'mmap'. A notable candidate is virtualbox's
 vboxfs.
 
-### I see the error: "clang: Command not found" on CentOS
-
-On CentOS 7 users reported `/opt/rh/llvm-toolset-7/root/usr/bin/clang: Command not found`.
-Double-check clang is installed. Instead of `make` try running `make CLANG=true`.
-
 ### nominatim UPDATE failed: ERROR: buffer 179261 is not owned by resource owner Portal
 
 Several users [reported this](https://github.com/openstreetmap/Nominatim/issues/1168)
@@ -126,22 +121,6 @@ The server cannot access your database. Add `&debug=1` to your URL
 to get the full error message.
 
 
-### On CentOS the website shows "Could not connect to server"
-
-`could not connect to server: No such file or directory`
-
-On CentOS v7 the PostgreSQL server is started with `systemd`. Check if
-`/usr/lib/systemd/system/httpd.service` contains a line `PrivateTmp=true`. If
-so then Apache cannot see the `/tmp/.s.PGSQL.5432` file. It's a good security
-feature, so use the
-[preferred solution](../appendix/Install-on-Centos-7/#adding-selinux-security-settings).
-
-However, you can solve this the quick and dirty way by commenting out that line and then run
-
-    sudo systemctl daemon-reload
-    sudo systemctl restart httpd
-
-
 ### Website reports "DB Error: insufficient permissions"
 
 The user the webserver, e.g. Apache, runs under needs to have access to the
@@ -181,9 +160,6 @@ by everybody, e.g.
 
 Try `chmod a+r nominatim.so; chmod a+x nominatim.so`.
 
-When running SELinux, make sure that the
-[context is set up correctly](../appendix/Install-on-Centos-7/#adding-selinux-security-settings).
-
 When you recently updated your operating system, updated PostgreSQL to
 a new version or moved files (e.g. the build directory) you should
 recreate `nominatim.so`. Try

docs/admin/Import.md

@@ -47,8 +47,9 @@ You can also set the same configuration via environment variables. All
 settings have a `NOMINATIM_` prefix to avoid conflicts with other environment
 variables.
 
-There are lots of configuration settings you can tweak. Have a look
-at `Nominatim/settings/env.default` for a full list. Most should have a sensible default.
+There are lots of configuration settings you can tweak. A full reference
+can be found in the chapter [Configuration Settings](../customize/Settings.md).
+Most should have a sensible default.
 
 #### Flatnode files
 
@@ -73,15 +74,15 @@ but it will improve the quality of the results if this is installed.
 This data is available as a binary download. Put it into your project directory:
 
     cd $PROJECT_DIR
-    wget https://www.nominatim.org/data/wikimedia-importance.sql.gz
+    wget https://nominatim.org/data/wikimedia-importance.sql.gz
 
 The file is about 400MB and adds around 4GB to the Nominatim database.
 
 !!! tip
-    If you forgot to download the wikipedia rankings, you can also add
-    importances after the import. Download the files, then run
-    `nominatim refresh --wiki-data --importance`. Updating importances for
-    a planet can take a couple of hours.
+    If you forgot to download the wikipedia rankings, then you can
+    also add importances after the import. Download the SQL files, then
+    run `nominatim refresh --wiki-data --importance`. Updating
+    importances for a planet will take a couple of hours.
 
 ### External postcodes
 
@@ -91,11 +92,11 @@ and the UK (using the [CodePoint OpenData set](https://osdatahub.os.uk/downloads
 This data can be optionally downloaded into the project directory:
 
     cd $PROJECT_DIR
-    wget https://www.nominatim.org/data/gb_postcodes.csv.gz
-    wget https://www.nominatim.org/data/us_postcodes.csv.gz
+    wget https://nominatim.org/data/gb_postcodes.csv.gz
+    wget https://nominatim.org/data/us_postcodes.csv.gz
 
 You can also add your own custom postcode sources, see
-[Customization of postcodes](Customization.md#external-postcode-data).
+[Customization of postcodes](../customize/Postcodes.md).
 
 ## Choosing the data to import
 
@@ -111,7 +112,7 @@ If you only need geocoding for a smaller region, then precomputed OSM extracts
 are a good way to reduce the database size and import time.
 [Geofabrik](https://download.geofabrik.de) offers extracts for most countries.
 They even have daily updates which can be used with the update process described
-[in the next section](../Update). There are also
+[in the next section](Update.md). There are also
 [other providers for extracts](https://wiki.openstreetmap.org/wiki/Planet.osm#Downloading).
 
 Please be aware that some extracts are not cut exactly along the country
@@ -137,11 +138,19 @@ Note that you still need to provide for sufficient disk space for the initial
 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
+    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
+    everything run `nominatim freeze`.
+
+
 ### Reverse-only Imports
 
 If you only want to use the Nominatim database for reverse lookups or
 if you plan to use the installation only for exports to a
-[photon](https://photon.komoot.de/) database, then you can set up a database
+[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.
@@ -152,15 +161,15 @@ Nominatim normally sets up a full search database containing administrative
 boundaries, places, streets, addresses and POI data. There are also other
 import styles available which only read selected data:
 
-* **settings/import-admin.style**
+* **admin**
   Only import administrative boundaries and places.
-* **settings/import-street.style**
+* **street**
   Like the admin style but also adds streets.
-* **settings/import-address.style**
+* **address**
   Import all data necessary to compute addresses down to house number level.
-* **settings/import-full.style**
+* **full**
   Default style that also includes points of interest.
-* **settings/import-extratags.style**
+* **extratags**
   Like the full style but also adds most of the OSM tags into the extratags
   column.
 
@@ -183,8 +192,8 @@ full      |   54h        |  640 GB    |  330 GB
 extratags |   54h        |  650 GB    |  340 GB
 
 You can also customize the styles further.
-A [description of the style format](../develop/Import.md#configuring-the-import) 
-can be found in the development section.
+A [description of the style format](../customize/Import-Styles.md)
+can be found in the customization guide.
 
 ## Initial import of the data
 
@@ -200,7 +209,7 @@ nominatim import --osm-file <data file> 2>&1 | tee setup.log
 ```
 
 The **project directory** is the one that you have set up at the beginning.
-See [creating the project directory](Import#creating-the-project-directory).
+See [creating the project directory](#creating-the-project-directory).
 
 ### Notes on full planet imports
 
@@ -219,7 +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#postgresql-tuning)
+[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
@@ -238,7 +247,8 @@ reduce the cache size or even consider using a flatnode file.
 
 ### Testing the installation
 
-Run this script to verify all required tables and indices got created successfully.
+Run this script to verify that all required tables and indices got created
+successfully.
 
 ```sh
 nominatim admin --check-database
@@ -261,23 +271,10 @@ reverse query, e.g. `http://localhost:8088/reverse.php?lat=27.1750090510034&lon=
 To run Nominatim via webservers like Apache or nginx, please read the
 [Deployment chapter](Deployment.md).
 
-## Tuning the database
-
-Accurate word frequency information for search terms helps PostgreSQL's query
-planner to make the right decisions. Recomputing them can improve the performance
-of forward geocoding in particular under high load. To recompute word counts run:
-
-```sh
-nominatim refresh --word-counts
-```
-
-This will take a couple of hours for a full planet installation. You can
-also defer that step to a later point in time when you realise that
-performance becomes an issue. Just make sure that updates are stopped before
-running this function.
+## Adding search through category phrases
 
 If you want to be able to search for places by their type through
-[special key phrases](https://wiki.openstreetmap.org/wiki/Nominatim/Special_Phrases)
+[special phrases](https://wiki.openstreetmap.org/wiki/Nominatim/Special_Phrases)
 you also need to import these key phrases like this:
 
 ```sh
@@ -288,4 +285,4 @@ Note that this command downloads the phrases from the wiki link above. You
 need internet access for the step.
 
 You can also import special phrases from a csv file, for more 
-information please read the [Customization chapter](Customization.md).
+information please see the [Customization part](../customize/Special-Phrases.md).

docs/admin/Installation.md

@@ -4,10 +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 22.04](../appendix/Install-on-Ubuntu-22.md)
   * [Ubuntu 20.04](../appendix/Install-on-Ubuntu-20.md)
   * [Ubuntu 18.04](../appendix/Install-on-Ubuntu-18.md)
-  * [CentOS 8](../appendix/Install-on-Centos-8.md)
-  * [CentOS 7.2](../appendix/Install-on-Centos-7.md)
 
 These OS-specific instructions can also be found in executable form
 in the `vagrant/` directory.
@@ -24,6 +23,11 @@ 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/)
@@ -38,8 +42,8 @@ For compiling:
 
 For running Nominatim:
 
-  * [PostgreSQL](https://www.postgresql.org) (9.5+ will work, 11+ strongly recommended)
-  * [PostGIS](https://postgis.net) (2.2+)
+  * [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)
@@ -63,10 +67,10 @@ the [Development section](../develop/Development-Environment.md).
 ### Hardware
 
 A minimum of 2GB of RAM is required or installation will fail. For a full
-planet import 64GB of RAM or more are strongly recommended. Do not report
+planet import 128GB of RAM or more are strongly recommended. Do not report
 out of memory problems if you have less than 64GB RAM.
 
-For a full planet install you will need at least 900GB of hard disk space.
+For a full planet install you will need at least 1TB of hard disk space.
 Take into account that the OSM database is growing fast.
 Fast disks are essential. Using NVME disks is recommended.
 
@@ -85,8 +89,7 @@ your `postgresql.conf` file.
     work_mem = (50MB)
     effective_cache_size = (24GB)
     synchronous_commit = off
-    checkpoint_segments = 100 # only for postgresql <= 9.4
-    max_wal_size = 1GB # postgresql > 9.4
+    max_wal_size = 1GB
     checkpoint_timeout = 10min
     checkpoint_completion_target = 0.9
 
@@ -109,7 +112,7 @@ For the initial import, you should also set:
     fsync = off
     full_page_writes = off
 
-Don't forget to reenable them after the initial import or you risk database
+Don't forget to re-enable them after the initial import or you risk database
 corruption.
 
 
@@ -126,13 +129,13 @@ If you want to install latest development version from github, make sure to
 also check out the osm2pgsql subproject:
 
 ```
-git clone --recursive git://github.com/openstreetmap/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://www.nominatim.org/data/country_grid.sql.gz
+wget -O Nominatim/data/country_osm_grid.sql.gz https://nominatim.org/data/country_grid.sql.gz
 ```
 
 ### Building Nominatim
@@ -154,6 +157,17 @@ 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

docs/admin/Maintenance.md

@@ -0,0 +1,75 @@
+This chapter describes the various operations the Nominatim database administrator
+may use to clean and maintain the database. None of these operations is mandatory
+but they may help improve the performance and accuracy of results.
+
+
+## Updating postcodes
+
+Command: `nominatim refresh --postcodes`
+
+Postcode centroids (aka 'calculated postcodes') are generated by looking at all
+postcodes of a country, grouping them and calculating the geometric centroid.
+There is currently no logic to deal with extreme outliers (typos or other
+mistakes in OSM data). There is also no check if a postcodes adheres to a
+country's format, e.g. if Swiss postcodes are 4 digits.
+
+When running regular updates, postcodes results can be improved by running
+this command on a regular basis. Note that only the postcode table and the
+postcode search terms are updated. The postcode that is assigned to each place
+is only updated when the place is updated.
+
+The command takes around 70min to run on the planet and needs ca. 40GB of
+temporary disk space.
+
+
+## Updating word counts
+
+Command: `nominatim refresh --word-counts`
+
+Nominatim keeps frequency statistics about all search terms it indexes. These
+statistics are currently used to optimise queries to the database. Thus better
+statistics mean better performance. Word counts are created once after import
+and are usually sufficient even when running regular updates. You might want
+to rerun the statistics computation when adding larger amounts of new data,
+for example, when adding an additional country via `nominatim add-data`.
+
+
+## Forcing recomputation of places and areas
+
+Command: `nominatim refresh --data-object [NWR]<id> --data-area [NWR]<id>`
+
+When running replication updates, Nominatim tries to recompute the search
+and address information for all places that are affected by a change. But it
+needs to restrict the total number of changes to make sure it can keep up
+with the minutely updates. Therefore it will refrain from propagating changes
+that affect a lot of objects.
+
+The administrator may force an update of places in the database.
+`nominatim refresh --data-object` invalidates a single OSM object.
+`nominatim refresh --data-area` invalidates an OSM object and all dependent
+objects. That are usually the places that inside its area or around the
+center of the object. Both commands expect the OSM object as an argument
+of the form OSM type + OSM id. The type must be `N` (node), `W` (way) or
+`R` (relation).
+
+After invalidating the object, indexing must be run again. If continuous
+update are running in the background, the objects will be recomputed together
+with the next round of updates. Otherwise you need to run `nominatim index`
+to finish the recomputation.
+
+
+## Removing large deleted objects
+
+Nominatim refuses to delete very large areas because often these deletions are
+accidental and are reverted within hours. Instead the deletions are logged in
+the `import_polygon_delete` table and left to the administrator to clean up.
+
+There is currently no command to do that. You can use the following SQL
+query to force a deletion on all objects that have been deleted more than
+a certain timespan ago (here: 1 month):
+
+```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
+```

docs/admin/Migration.md

@@ -15,6 +15,44 @@ breaking changes. **Please read them before running the migration.**
     If you are migrating from a version <3.6, then you still have to follow
     the manual migration steps up to 3.6.
 
+## 4.0.0 -> 4.1.0
+
+### ICU tokenizer is the new default
+
+Nominatim now installs the [ICU tokenizer](../customize/Tokenizers.md#icu-tokenizer)
+by default. This only has an effect on newly installed databases. When
+updating older databases, it keeps its installed tokenizer. If you still
+run with the legacy tokenizer, make sure to compile Nominatim with the
+PostgreSQL module, see [Installation](Installation.md#building-nominatim).
+
+### geocodejson output changed
+
+The `type` field of the geocodejson output has changed. It now contains
+the address class of the object instead of the value of the OSM tag. If
+your client has used the `type` field, switch them to read `osm_value`
+instead.
+
+## 3.7.0 -> 4.0.0
+
+### NOMINATIM_PHRASE_CONFIG removed
+
+Custom blacklist configurations for special phrases now need to be handed
+with the `--config` parameter to `nominatim special-phrases`. Alternatively
+you can put your custom configuration in the project directory in a file
+named `phrase-settings.json`.
+
+Version 3.8 also removes the automatic converter for the php format of
+the configuration in older versions. If you are updating from Nominatim < 3.7
+and still work with a custom `phrase-settings.php`, you need to manually
+convert it into a json format.
+
+### PHP utils removed
+
+The old PHP utils have now been removed completely. You need to switch to
+the appropriate functions of the nominatim  command line tool. See
+[Introducing `nominatim` command line tool](#introducing-nominatim-command-line-tool)
+below.
+
 ## 3.6.0 -> 3.7.0
 
 ### New format and name of configuration file
@@ -80,7 +118,7 @@ done
 
 The debugging UI is no longer directly provided with Nominatim. Instead we
 now provide a simple Javascript application. Please refer to
-[Setting up the Nominatim UI](../Setup-Nominatim-UI) for details on how to
+[Setting up the Nominatim UI](Setup-Nominatim-UI.md) for details on how to
 set up the UI.
 
 The icons served together with the API responses have been moved to the

docs/admin/Setup-Nominatim-UI.md

@@ -16,13 +16,14 @@ and run it. Grab the latest release from
 [nominatim-ui's Github release page](https://github.com/osm-search/nominatim-ui/releases)
 and unpack it. You can use `nominatim-ui-x.x.x.tar.gz` or `nominatim-ui-x.x.x.zip`.
 
-Copy the example configuration into the right place:
+Next you need to adapt the UI to your installation. Custom settings need to be
+put into `dist/theme/config.theme.js`. At a minimum you need to
+set `Nominatim_API_Endpoint` to point to your Nominatim installation:
 
     cd nominatim-ui
-    cp dist/config.example.js dist/config.js
+    echo "Nominatim_Config.Nominatim_API_Endpoint='https://myserver.org/nominatim/';" > dist/theme/config.theme.js
 
-Now adapt the configuration to your needs. You need at least
-to change the `Nominatim_API_Endpoint` to point to your Nominatim installation.
+For the full set of available settings, have a look at `dist/config.defaults.js`.
 
 Then you can just test it locally by spinning up a webserver in the `dist`
 directory. For example, with Python:
@@ -160,24 +161,16 @@ directory like this:
   # If no endpoint is given, then use search.
   RewriteRule ^(/|$)   "search.php"
 
-  # If format-html is explicity requested, forward to the UI.
+  # If format-html is explicitly requested, forward to the UI.
   RewriteCond %{QUERY_STRING} "format=html"
-  RewriteRule ^([^/]+).php ui/$1.html [R,END]
-  # Same but .php suffix is missing.
-  RewriteCond %{QUERY_STRING} "format=html"
-  RewriteRule ^([^/]+) ui/$1.html [R,END]
+  RewriteRule ^([^/]+)(.php)? ui/$1.html [R,END]
 
   # If no format parameter is there then forward anything
   # but /reverse and /lookup to the UI.
   RewriteCond %{QUERY_STRING} "!format="
   RewriteCond %{REQUEST_URI}  "!/lookup"
   RewriteCond %{REQUEST_URI}  "!/reverse"
-  RewriteRule ^([^/]+).php ui/$1.html [R,END]
-  # Same but .php suffix is missing.
-  RewriteCond %{QUERY_STRING} "!format="
-  RewriteCond %{REQUEST_URI}  "!/lookup"
-  RewriteCond %{REQUEST_URI}  "!/reverse"
-  RewriteRule ^([^/]+) ui/$1.html [R,END]
+  RewriteRule ^([^/]+)(.php)? ui/$1.html [R,END]
 </Directory>
 ```
 

docs/admin/Tokenizers.md

@@ -1,205 +0,0 @@
-# Tokenizers
-
-The tokenizer module in Nominatim is responsible for analysing the names given
-to OSM objects and the terms of an incoming query in order to make sure, they
-can be matched appropriately.
-
-Nominatim offers different tokenizer modules, which behave differently and have
-different configuration options. This sections describes the tokenizers and how
-they can be configured.
-
-!!! important
-    The use of a tokenizer is tied to a database installation. You need to choose
-    and configure the tokenizer before starting the initial import. Once the import
-    is done, you cannot switch to another tokenizer anymore. Reconfiguring the
-    chosen tokenizer is very limited as well. See the comments in each tokenizer
-    section.
-
-## Legacy tokenizer
-
-The legacy tokenizer implements the analysis algorithms of older Nominatim
-versions. It uses a special Postgresql module to normalize names and queries.
-This tokenizer is currently the default.
-
-To enable the tokenizer add the following line to your project configuration:
-
-```
-NOMINATIM_TOKENIZER=legacy
-```
-
-The Postgresql module for the tokenizer is available in the `module` directory
-and also installed with the remainder of the software under
-`lib/nominatim/module/nominatim.so`. You can specify a custom location for
-the module with
-
-```
-NOMINATIM_DATABASE_MODULE_PATH=<path to directory where nominatim.so resides>
-```
-
-This is in particular useful when the database runs on a different server.
-See [Advanced installations](Advanced-Installations.md#importing-nominatim-to-an-external-postgresql-database) for details.
-
-There are no other configuration options for the legacy tokenizer. All
-normalization functions are hard-coded.
-
-## ICU tokenizer
-
-!!! danger
-    This tokenizer is currently in active development and still subject
-    to backwards-incompatible changes.
-
-The ICU tokenizer uses the [ICU library](http://site.icu-project.org/) to
-normalize names and queries. It also offers configurable decomposition and
-abbreviation handling.
-
-### How it works
-
-On import the tokenizer processes names in the following four stages:
-
-1. The **Normalization** part removes all non-relevant information from the
-   input.
-2. Incoming names are now converted to **full names**. This process is currently
-   hard coded and mostly serves to handle name tags from OSM that contain
-   multiple names (e.g. [Biel/Bienne](https://www.openstreetmap.org/node/240097197)).
-3. Next the tokenizer creates **variants** from the full names. These variants
-   cover decomposition and abbreviation handling. Variants are saved to the
-   database, so that it is not necessary to create the variants for a search
-   query.
-4. The final **Tokenization** step converts the names to a simple ASCII form,
-   potentially removing further spelling variants for better matching.
-
-At query time only stage 1) and 4) are used. The query is normalized and
-tokenized and the resulting string used for searching in the database.
-
-### Configuration
-
-The ICU tokenizer is configured using a YAML file which can be configured using
-`NOMINATIM_TOKENIZER_CONFIG`. The configuration is read on import and then
-saved as part of the internal database status. Later changes to the variable
-have no effect.
-
-Here is an example configuration file:
-
-``` yaml
-normalization:
-    - ":: lower ()"
-    - "ß > 'ss'" # German szet is unimbigiously equal to double ss
-transliteration:
-    - !include /etc/nominatim/icu-rules/extended-unicode-to-asccii.yaml
-    - ":: Ascii ()"
-variants:
-    - language: de
-      words:
-        - ~haus => haus
-        - ~strasse -> str
-    - language: en
-      words: 
-        - road -> rd
-        - bridge -> bdge,br,brdg,bri,brg
-```
-
-The configuration file contains three sections:
-`normalization`, `transliteration`, `variants`.
-
-The normalization and transliteration sections each must contain a list of
-[ICU transformation rules](https://unicode-org.github.io/icu/userguide/transforms/general/rules.html).
-The rules are applied in the order in which they appear in the file.
-You can also include additional rules from external yaml file using the
-`!include` tag. The included file must contain a valid YAML list of ICU rules
-and may again include other files.
-
-!!! warning
-    The ICU rule syntax contains special characters that conflict with the
-    YAML syntax. You should therefore always enclose the ICU rules in
-    double-quotes.
-
-The variants section defines lists of replacements which create alternative
-spellings of a name. To create the variants, a name is scanned from left to
-right and the longest matching replacement is applied until the end of the
-string is reached.
-
-The variants section must contain a list of replacement groups. Each group
-defines a set of properties that describes where the replacements are
-applicable. In addition, the word section defines the list of replacements
-to be made. The basic replacement description is of the form:
-
-```
-<source>[,<source>[...]] => <target>[,<target>[...]]
-```
-
-The left side contains one or more `source` terms to be replaced. The right side
-lists one or more replacements. Each source is replaced with each replacement
-term.
-
-!!! tip
-    The source and target terms are internally normalized using the
-    normalization rules given in the configuration. This ensures that the
-    strings match as expected. In fact, it is better to use unnormalized
-    words in the configuration because then it is possible to change the
-    rules for normalization later without having to adapt the variant rules.
-
-#### Decomposition
-
-In its standard form, only full words match against the source. There
-is a special notation to match the prefix and suffix of a word:
-
-``` yaml
-- ~strasse => str  # matches "strasse" as full word and in suffix position
-- hinter~ => hntr  # matches "hinter" as full word and in prefix position
-```
-
-There is no facility to match a string in the middle of the word. The suffix
-and prefix notation automatically trigger the decomposition mode: two variants
-are created for each replacement, one with the replacement attached to the word
-and one separate. So in above example, the tokenization of "hauptstrasse" will
-create the variants "hauptstr" and "haupt str". Similarly, the name "rote strasse"
-triggers the variants "rote str" and "rotestr". By having decomposition work
-both ways, it is sufficient to create the variants at index time. The variant
-rules are not applied at query time.
-
-To avoid automatic decomposition, use the '|' notation:
-
-``` yaml
-- ~strasse |=> str
-```
-
-simply changes "hauptstrasse" to "hauptstr" and "rote strasse" to "rote str".
-
-#### Initial and final terms
-
-It is also possible to restrict replacements to the beginning and end of a
-name:
-
-``` yaml
-- ^south => s  # matches only at the beginning of the name
-- road$ => rd  # matches only at the end of the name
-```
-
-So the first example would trigger a replacement for "south 45th street" but
-not for "the south beach restaurant".
-
-#### Replacements vs. variants
-
-The replacement syntax `source => target` works as a pure replacement. It changes
-the name instead of creating a variant. To create an additional version, you'd
-have to write `source => source,target`. As this is a frequent case, there is
-a shortcut notation for it:
-
-```
-<source>[,<source>[...]] -> <target>[,<target>[...]]
-```
-
-The simple arrow causes an additional variant to be added. Note that
-decomposition has an effect here on the source as well. So a rule
-
-``` yaml
-- "~strasse -> str"
-```
-
-means that for a word like `hauptstrasse` four variants are created:
-`hauptstrasse`, `haupt strasse`, `hauptstr` and `haupt str`.
-
-### Reconfiguration
-
-Changing the configuration after the import is currently not possible, although
-this feature may be added at a later time.

docs/admin/Update.md

@@ -10,18 +10,21 @@ For a list of other methods to add or update data see the output of
     If you have configured a flatnode file for the import, then you
     need to keep this flatnode file around for updates.
 
-#### Installing the newest version of Pyosmium
+### Installing the newest version of Pyosmium
 
-It is recommended to install Pyosmium via pip. Make sure to use python3.
+The replication process uses
+[Pyosmium](https://docs.osmcode.org/pyosmium/latest/updating_osm_data.html)
+to download update data from the server.
+It is recommended to install Pyosmium via pip.
 Run (as the same user who will later run the updates):
 
 ```sh
 pip3 install --user osmium
 ```
 
-#### Setting up the update process
+### Setting up the update process
 
-Next the update needs to be initialised. By default Nominatim is configured
+Next the update process needs to be initialised. By default Nominatim is configured
 to update using the global minutely diffs.
 
 If you want a different update source you will need to add some settings
@@ -45,12 +48,176 @@ what you expect.
 The `replication --init` command needs to be rerun whenever the replication
 service is changed.
 
-#### Updating Nominatim
+### Updating Nominatim
 
-The following command will keep your database constantly up to date:
+Nominatim supports different modes how to retrieve the update data from the
+server. Which one you want to use depends on your exact setup and how often you
+want to retrieve updates.
+
+These instructions are for using a single source of updates. If you have
+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
 
-If you have 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.
+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
+batch of updates and then exit. This one-time mode still respects the
+`NOMINATIM_REPLICATION_UPDATE_INTERVAL` that you have set. If according to
+the update interval no new data has been published yet, it will go to sleep
+until the next expected update and only then attempt to download the next batch.
+
+The one-time mode is particularly useful if you want to run updates continuously
+but need to schedule other work in between updates. For example, the main
+service at osm.org uses it, to regularly recompute postcodes -- a process that
+must not be run while updates are in progress. Its update script
+looks like this:
+
+```sh
+#!/bin/bash
+
+# Switch to your project directory.
+cd /srv/nominatim
+
+while true; do
+  nominatim replication --once
+  if [ -f "/srv/nominatim/schedule-maintenance" ]; then
+    rm /srv/nominatim/schedule-maintenance
+    nominatim refresh --postcodes
+  fi
+done
+```
+
+A cron job then creates the file `/srv/nominatim/schedule-maintenance` once per night.
+
+##### One-time mode with systemd
+
+You can run the one-time mode with a systemd timer & service.
+
+Create a timer description like `/etc/systemd/system/nominatim-updates.timer`:
+
+```
+[Unit]
+Description=Timer to start updates of Nominatim
+
+[Timer]
+OnActiveSec=2
+OnUnitActiveSec=1min
+Unit=nominatim-updates.service
+
+[Install]
+WantedBy=multi-user.target
+```
+
+And then a similar service definition: `/etc/systemd/system/nominatim-updates.service`:
+
+```
+[Unit]
+Description=Single updates of Nominatim
+
+[Service]
+WorkingDirectory=/srv/nominatim
+ExecStart=nominatim replication --once
+StandardOutput=append:/var/log/nominatim-updates.log
+StandardError=append:/var/log/nominatim-updates.error.log
+User=nominatim
+Group=nominatim
+Type=simple
+
+[Install]
+WantedBy=multi-user.target
+```
+
+Replace the `WorkingDirectory` with your project directory. Also adapt user and
+group names as required. `OnUnitActiveSec` defines how often the individual
+update command is run.
+
+Now activate the service and start the updates:
+
+```
+sudo systemctl daemon-reload
+sudo systemctl enable nominatim-updates.timer
+sudo systemctl start nominatim-updates.timer
+```
+
+You can stop future data updates, while allowing any current, in-progress
+update steps to finish, by running `sudo systemctl stop
+nominatim-updates.timer` and waiting until `nominatim-updates.service` isn't
+running (`sudo systemctl is-active nominatim-updates.service`). Current output
+from the update can be seen like above (`systemctl status
+nominatim-updates.service`).
+
+
+#### Catch-up mode
+
+With the `--catch-up` parameter, Nominatim will immediately try to download
+all changes from the server until the database is up-to-date. The catch-up mode
+still respects the parameter `NOMINATIM_REPLICATION_MAX_DIFF`. It downloads and
+applies the changes in appropriate batches until all is done.
+
+The catch-up mode is foremost useful to bring the database up to speed after the
+initial import. Give that the service usually is not in production at this
+point, you can temporarily be a bit more generous with the batch size and
+number of threads you use for the updates by running catch-up like this:
+
+```
+cd /srv/nominatim
+NOMINATIM_REPLICATION_MAX_DIFF=5000 nominatim replication --catch-up --threads 15
+```
+
+The catch-up mode is also useful when you want to apply updates at a lower
+frequency than what the source publishes. You can set up a cron job to run
+replication catch-up at whatever interval you desire.
+
+!!! hint
+    When running scheduled updates with catch-up, it is a good idea to choose
+    a replication source with an update frequency that is an order of magnitude
+    lower. For example, if you want to update once a day, use an hourly updated
+    source. This makes sure that you don't miss an entire day of updates when
+    the source is unexpectedly late to publish its update.
+
+    If you want to use the source with the same update frequency (e.g. a daily
+    updated source with daily updates), use the
+    continuous update mode. It ensures to re-request the newest update until it
+    is published.

docs/api/Faq.md

@@ -35,7 +35,7 @@ it contains the county/state/country across the border.
 #### 3. I get different counties/states/countries when I change the zoom parameter in the reverse query. How is that possible?
 
 This is basically the same problem as in the previous answer.
-The zoom level influences at which [search rank](https://wiki.openstreetmap.org/wiki/Nominatim/Development_overview#Country_to_street_level) Nominatim starts looking
+The zoom level influences at which [search rank](../customize/Ranking.md#search-rank) Nominatim starts looking
 for the closest object. So the closest house number maybe on one side of the
 border while the closest street is on the other. As the address details contain
 the address of the closest object found, you might sometimes get one result,
@@ -59,3 +59,27 @@ suited for these kinds of queries.
 
 That said if you installed your own Nominatim instance you can use the
 `nominatim export` PHP script as basis to return such lists.
+
+#### 7. My result has a wrong postcode. Where does it come from?
+
+Most places in OSM don't have a postcode, so Nominatim tries to interpolate
+one. It first look at all the places that make up the address of the place.
+If one of them has a postcode defined, this is the one to be used. When
+none of the address parts has a postcode either, Nominatim interpolates one
+from the surrounding objects. If the postcode is for your result is one, then
+most of the time there is an OSM object with the wrong postcode nearby.
+
+To find the bad postcode, go to
+[https://nominatim.openstreetmap.org](https://nominatim.openstreetmap.org)
+and search for your place. When you have found it, click on the 'details' link
+under the result to go to the details page. There is a field 'Computed Postcode'
+which should display the bad postcode. Click on the 'how?' link. A small
+explanation text appears. It contains a link to a query for Overpass Turbo.
+Click on that and you get a map with all places in the area that have the bad
+postcode. If none is displayed, zoom the map out a bit and then click on 'Run'.
+
+Now go to [OpenStreetMap](https://openstreetmap.org) and fix the error you
+have just found. It will take at least a day for Nominatim to catch up with
+your data fix. Sometimes longer, depending on how much editing activity is in
+the area.
+

docs/api/Lookup.md

@@ -90,11 +90,11 @@ This overrides the specified machine readable format. (Default: 0)
 
 ##### XML
 
-[https://nominatim.openstreetmap.org/lookup?osm_ids=R146656,W104393803,N240109189](https://nominatim.openstreetmap.org/lookup?osm_ids=R146656,W104393803,N240109189)
+[https://nominatim.openstreetmap.org/lookup?osm_ids=R146656,W104393803,N240109189](https://nominatim.openstreetmap.org/lookup?osm_ids=R146656,W50637691,N240109189)
 
 ```xml
-  <lookupresults timestamp="Mon, 29 Jun 15 18:01:33 +0000" attribution="Data © OpenStreetMap contributors, ODbL 1.0. https://www.openstreetmap.org/copyright" querystring="R146656,W104393803,N240109189" polygon="false">
-    <place place_id="127761056" osm_type="relation" osm_id="146656" place_rank="16" lat="53.4791466" lon="-2.2447445" display_name="Manchester, Greater Manchester, North West England, England, United Kingdom" class="boundary" type="administrative" importance="0.704893333438333">
+  <lookupresults timestamp="Mon, 28 Mar 22 14:38:54 +0000" attribution="Data &#xA9; OpenStreetMap contributors, ODbL 1.0. http://www.openstreetmap.org/copyright" querystring="R146656,W50637691,N240109189" more_url="">
+    <place place_id="282236157" osm_type="relation" osm_id="146656" place_rank="16" address_rank="16" boundingbox="53.3401044,53.5445923,-2.3199185,-2.1468288" lat="53.44246175" lon="-2.2324547359718547" display_name="Manchester, Greater Manchester, North West England, England, United Kingdom" class="boundary" type="administrative" importance="0.35">
       <city>Manchester</city>
       <county>Greater Manchester</county>
       <state_district>North West England</state_district>
@@ -102,21 +102,20 @@ This overrides the specified machine readable format. (Default: 0)
       <country>United Kingdom</country>
       <country_code>gb</country_code>
     </place>
-    <place place_id="77769745" osm_type="way" osm_id="104393803" place_rank="30" lat="52.5162024" lon="13.3777343363579" display_name="Brandenburg Gate, 1, Pariser Platz, Mitte, Berlin, 10117, Germany" class="tourism" type="attraction" importance="0.443472858361592">
-      <attraction>Brandenburg Gate</attraction>
-      <house_number>1</house_number>
-      <pedestrian>Pariser Platz</pedestrian>
-      <suburb>Mitte</suburb>
-      <city_district>Mitte</city_district>
-      <city>Berlin</city>
-      <state>Berlin</state>
-      <postcode>10117</postcode>
+    <place place_id="115462561" osm_type="way" osm_id="50637691" place_rank="30" address_rank="30" boundingbox="52.3994612,52.3996426,13.0479574,13.0481754" lat="52.399550700000006" lon="13.048066846939687" display_name="Brandenburger Tor, Brandenburger Stra&#xDF;e, Historische Innenstadt, Innenstadt, Potsdam, Brandenburg, 14467, Germany" class="tourism" type="attraction" importance="0.29402874005524">
+      <tourism>Brandenburger Tor</tourism>
+      <road>Brandenburger Stra&#xDF;e</road>
+      <suburb>Historische Innenstadt</suburb>
+      <city>Potsdam</city>
+      <state>Brandenburg</state>
+      <postcode>14467</postcode>
       <country>Germany</country>
       <country_code>de</country_code>
     </place>
-    <place place_id="2570600569" osm_type="node" osm_id="240109189" place_rank="15" lat="52.5170365" lon="13.3888599" display_name="Berlin, Germany" class="place" type="city" importance="0.822149797630868">
+    <place place_id="567505" osm_type="node" osm_id="240109189" place_rank="15" address_rank="16" boundingbox="52.3586925,52.6786925,13.2396024,13.5596024" lat="52.5186925" lon="13.3996024" display_name="Berlin, 10178, Germany" class="place" type="city" importance="0.78753902824914">
       <city>Berlin</city>
       <state>Berlin</state>
+      <postcode>10178</postcode>
       <country>Germany</country>
       <country_code>de</country_code>
     </place>
@@ -125,38 +124,50 @@ This overrides the specified machine readable format. (Default: 0)
 
 ##### JSON with extratags
 
-[https://nominatim.openstreetmap.org/lookup?osm_ids=W50637691&format=json](https://nominatim.openstreetmap.org/lookup?osm_ids=W50637691&format=json)
+[https://nominatim.openstreetmap.org/lookup?osm_ids=W50637691&format=json&extratags=1](https://nominatim.openstreetmap.org/lookup?osm_ids=W50637691&format=json&extratags=1)
 
 ```json
 [
-  {
-    "place_id": "84271358",
-    "licence": "Data © OpenStreetMap contributors, ODbL 1.0. https://osm.org/copyright",
-    "osm_type": "way",
-    "osm_id": "50637691",
-    "lat": "52.39955055",
-    "lon": "13.04806574678",
-    "display_name": "Brandenburger Tor, Brandenburger Straße, Nördliche Innenstadt, Innenstadt, Potsdam, Brandenburg, 14467, Germany",
-    "class": "historic",
-    "type": "city_gate",
-    "importance": "0.221233780277011",
-    "address": {
-      "address29": "Brandenburger Tor",
-      "pedestrian": "Brandenburger Straße",
-      "suburb": "Nördliche Innenstadt",
-      "city": "Potsdam",
-      "state": "Brandenburg",
-      "postcode": "14467",
-      "country": "Germany",
-      "country_code": "de"
-    },
-    "extratags": {
-      "image": "http://commons.wikimedia.org/wiki/File:Potsdam_brandenburger_tor.jpg",
-      "wikidata": "Q695045",
-      "wikipedia": "de:Brandenburger Tor (Potsdam)",
-      "wheelchair": "yes",
-      "description": "Kleines Brandenburger Tor in Potsdam"
-    }
-  }
+   {
+      "place_id": 115462561,
+      "licence": "Data © OpenStreetMap contributors, ODbL 1.0. https://osm.org/copyright",
+      "osm_type": "way",
+      "osm_id": 50637691,
+      "boundingbox": [
+        "52.3994612",
+        "52.3996426",
+        "13.0479574",
+        "13.0481754"
+      ],
+      "lat": "52.399550700000006",
+      "lon": "13.048066846939687",
+      "display_name": "Brandenburger Tor, Brandenburger Straße, Historische Innenstadt, Innenstadt, Potsdam, Brandenburg, 14467, Germany",
+      "class": "tourism",
+      "type": "attraction",
+      "importance": 0.2940287400552381,
+      "address": {
+        "tourism": "Brandenburger Tor",
+        "road": "Brandenburger Straße",
+        "suburb": "Historische Innenstadt",
+        "city": "Potsdam",
+        "state": "Brandenburg",
+        "postcode": "14467",
+        "country": "Germany",
+        "country_code": "de"
+      },
+      "extratags": {
+        "image": "http://commons.wikimedia.org/wiki/File:Potsdam_brandenburger_tor.jpg",
+        "heritage": "4",
+        "wikidata": "Q695045",
+        "architect": "Carl von Gontard;Georg Christian Unger",
+        "wikipedia": "de:Brandenburger Tor (Potsdam)",
+        "wheelchair": "yes",
+        "description": "Kleines Brandenburger Tor in Potsdam",
+        "heritage:website": "http://www.bldam-brandenburg.de/images/stories/PDF/DML%202012/04-p-internet-13.pdf",
+        "heritage:operator": "bldam",
+        "architect:wikidata": "Q68768;Q95223",
+        "year_of_construction": "1771"
+      }
+   }
 ]
 ```

docs/api/Output.md

@@ -28,6 +28,7 @@ a single place (for reverse) of the following format:
       "city": "London",
       "state_district": "Greater London",
       "state": "England",
+      "ISO3166-2-lvl4": "GB-ENG",
       "postcode": "SW1A 2DU",
       "country": "United Kingdom",
       "country_code": "gb"
@@ -97,7 +98,10 @@ The GeocodeJSON format follows the
 The following feature attributes are implemented:
 
  * `osm_type`, `osm_id` - reference to the OSM object (unofficial extension, [see notes](#osm-reference))
- * `type` - value of the main tag of the object (e.g. residential, restaurant, ...)
+ * `type` - the 'address level' of the object ('house', 'street', `district`, `city`,
+            `county`, `state`, `country`, `locality`)
+ * `osm_key`- key of the main tag of the OSM object (e.g. boundary, highway, amenity)
+ * `osm_value` - value of the main tag of the OSM object (e.g. residential, restaurant)
  * `label` - full comma-separated address
  * `name` - localised name of the place
  * `housenumber`, `street`, `locality`, `district`, `postcode`, `city`,
@@ -126,6 +130,7 @@ formats depending on the API call.
   </result>
   <addressparts>
      <state>Bavaria</state>
+     <ISO3166-2-lvl4>DE-BY</ISO3166-2-lvl4>
      <country>Germany</country>
      <country_code>de</country_code>
   </addressparts>
@@ -179,6 +184,7 @@ Additional information requested with `addressdetails=1`, `extratags=1` and
     <city>London</city>
     <state_district>Greater London</state_district>
     <state>England</state>
+    <ISO3166-2-lvl4>GB-ENG</ISO3166-2-lvl4>
     <postcode>SW1A 2DU</postcode>
     <country>United Kingdom</country>
     <country_code>gb</country_code>
@@ -205,8 +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](../develop/Ranking#search-rank)
- * `address_rank` - place [address rank](../develop/Ranking#address-rank)
+ * `place_rank` - class [search rank](../customize/Ranking.md#search-rank)
+ * `address_rank` - place [address rank](../customize/Ranking.md#address-rank)
  * `display_name` - full comma-separated address
  * `class`, `type` - key and value of the main OSM tag
  * `importance` - computed importance rank
@@ -230,7 +236,7 @@ on another server. It may even change its ID on the same server when it is
 removed and reimported while updating the database with fresh OSM data.
 It is thus not useful to treat it as permanent for later use.
 
-The combination `osm_type`+`osm_id` is slighly better but remember in
+The combination `osm_type`+`osm_id` is slightly better but remember in
 OpenStreetMap mappers can delete, split, recreate places (and those
 get a new `osm_id`), there is no link between those old and new ids.
 Places can also change their meaning without changing their `osm_id`,
@@ -279,17 +285,18 @@ with a designation label. Per default the following labels may appear:
 
  * continent
  * country, country_code
- * region, state, state_district, county
+ * region, state, state_district, county, ISO3166-2-lvl<admin_level>
  * municipality, city, town, village
  * city_district, district, borough, suburb, subdivision
  * hamlet, croft, isolated_dwelling
  * neighbourhood, allotments, quarter
- * city_block, residental, farm, farmyard, industrial, commercial, retail
+ * city_block, residential, farm, farmyard, industrial, commercial, retail
  * road
  * house_number, house_name
  * emergency, historic, military, natural, landuse, place, railway,
    man_made, aerialway, boundary, amenity, aeroway, club, craft, leisure,
    office, mountain_pass, shop, tourism, bridge, tunnel, waterway
+ * postcode
 
 They roughly correspond to the classification of the OpenStreetMap data
 according to either the `place` tag or the main key of the object.

docs/api/Reverse.md

@@ -27,15 +27,15 @@ The main format of the reverse API is
 https://nominatim.openstreetmap.org/reverse?lat=<value>&lon=<value>&<params>
 ```
 
-where `lat` and `lon` are latitude and longitutde of a coordinate in WGS84
+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 paramters are accepted as listed below.
+Additional parameters are accepted as listed below.
 
 !!! 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)
+    its OSM id. This use is now deprecated. Use the [Address Lookup API](Lookup.md)
     instead.
 
 ### Output format
@@ -118,7 +118,7 @@ geometry. Topology is preserved in the result. (Default: 0.0)
 
 * `email=<valid email address>`
 
-If you are making large numbers of request please include an appropriate email
+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.
 
 

docs/api/Search.md

@@ -27,8 +27,8 @@ The search term may be specified with two different sets of parameters:
 
     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](//nominatim.openstreetmap.org/search?q=pilkington+avenue,birmingham) as well as for
-    [birmingham, pilkington avenue](//nominatim.openstreetmap.org/search?q=birmingham,+pilkington+avenue).
+    [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.
 
 
@@ -51,6 +51,12 @@ Both query forms accept the additional parameters listed below.
 
 See [Place Output Formats](Output.md) for details on each format. (Default: jsonv2)
 
+!!! note
+    The Nominatim service at
+    [https://nominatim.openstreetmap.org](https://nominatim.openstreetmap.org)
+    has a different default behaviour for historical reasons. When the
+    `format` parameter is omitted, the request will be forwarded to the Web UI.
+
 * `json_callback=<string>`
 
 Wrap JSON output in a callback function ([JSONP](https://en.wikipedia.org/wiki/JSONP)) i.e. `<string>(<json>)`.

docs/api/Status.md

@@ -57,10 +57,11 @@ code and message, e.g.
 
 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         |
+|     | 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                         |
+| 705 | "Import date is not available" | No import dates were returned (enabling replication can fix this) |

docs/customize/Country-Settings.md

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

docs/customize/Import-Styles.md

@@ -1,38 +1,24 @@
-# OSM Data Import
-
-OSM data is initially imported using [osm2pgsql](https://osm2pgsql.org).
-Nominatim uses its own data output style 'gazetteer', which differs from the
-output style created for map rendering.
-
-## Database Layout
-
-The gazetteer style produces a single table `place` with the following rows:
-
- * `osm_type` - kind of OSM object (**N** - node, **W** - way, **R** - relation)
- * `osm_id` - original OSM ID
- * `class` - key of principal tag defining the object type
- * `type` - value of principal tag defining the object type
- * `name` - collection of tags that contain a name or reference
- * `admin_level` - numerical value of the tagged administrative level
- * `address` - collection of tags defining the address of an object
- * `extratags` - collection of additional interesting tags that are not
-                 directly relevant for searching
- * `geometry` - geometry of the object (in WGS84)
-
-A single OSM object may appear multiple times in this table when it is tagged
-with multiple tags that may constitute a principal tag. Take for example a
-motorway bridge. In OSM, this would be a way which is tagged with
-`highway=motorway` and `bridge=yes`. This way would appear in the `place` table
-once with `class` of `highway` and once with a `class` of `bridge`. Thus the
-*unique key* for `place` is (`osm_type`, `osm_id`, `class`).
-
 ## Configuring the Import
 
-How tags are interpreted and assigned to the different `place` columns can be
-configured via the import style configuration file (`NOMINATIM_IMPORT_STYLE`). This
+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.
 
+The style to use is given by the `NOMINATIM_IMPORT_STYLE` configuration
+option. There are a number of default styles, which are explained in detail
+in the [Import section](../admin/Import.md#filtering-imported-data). These
+standard styles may be referenced by their name.
+
+You can also create your own custom style. Put the style file into your
+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 remainder of the page describes the format of the file.
+
 ### Configuration Rules
 
 A single rule looks like this:
@@ -159,9 +145,6 @@ 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.
 
-There are a number of pre-defined styles in the `settings/` directory. It is
-advisable to start from one of these styles when defining your own.
-
 ### Changing the Style of Existing Databases
 
 There is normally no issue changing the style of a database that is already

docs/customize/Importance.md

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

docs/customize/Overview.md

@@ -0,0 +1,20 @@
+Nominatim comes with a predefined set of configuration options that should
+work for most standard installations. If you have special requirements, there
+are many places where the configuration can be adapted. This chapter describes
+the following configurable parts:
+
+* [Global Settings](Settings.md) has a detailed description of all parameters that
+  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
+* [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
+  responsible for analysing and indexing names
+* [Special Phrases](Special-Phrases.md) are common nouns or phrases that
+  can be used in search to identify a class of places
+
+There are also guides for adding the following external data:
+
+* [US house numbers from the TIGER dataset](Tiger.md)
+* [External postcodes](Postcodes.md)

docs/customize/Postcodes.md

@@ -0,0 +1,37 @@
+# External postcode data
+
+Nominatim creates a table of known postcode centroids during import. This table
+is used for searches of postcodes and for adding postcodes to places where the
+OSM data does not provide one. These postcode centroids are mainly computed
+from the OSM data itself. In addition, Nominatim supports reading postcode
+information from an external CSV file, to supplement the postcodes that are
+missing in OSM.
+
+To enable external postcode support, simply put one CSV file per country into
+your project directory and name it `<CC>_postcodes.csv`. `<CC>` must be the
+two-letter country code for which to apply the file. The file may also be
+gzipped. Then it must be called `<CC>_postcodes.csv.gz`.
+
+The CSV file must use commas as a delimiter and have a header line. Nominatim
+expects three columns to be present: `postcode`, `lat` and `lon`. All other
+columns are ignored. `lon` and `lat` must describe the x and y coordinates of the
+postcode centroids in WGS84.
+
+The postcode files are loaded only when there is data for the given country
+in your database. For example, if there is a `us_postcodes.csv` file in your
+project directory but you import only an excerpt of Italy, then the US postcodes
+will simply be ignored.
+
+As a rule, the external postcode data should be put into the project directory
+**before** starting the initial import. Still, you can add, remove and update the
+external postcode data at any time. Simply
+run:
+
+```
+nominatim refresh --postcodes
+```
+
+to make the changes visible in your database. Be aware, however, that the changes
+only have an immediate effect on searches for postcodes. Postcodes that were
+added to places are only updated, when they are reindexed. That usually happens
+only during replication updates.

docs/customize/Ranking.md

@@ -1,8 +1,7 @@
 # Place Ranking in Nominatim
 
 Nominatim uses two metrics to rank a place: search rank and address rank.
-Both can be assigned a value between 0 and 30. They serve slightly
-different purposes, which are explained in this chapter.
+This chapter explains what place ranking means and how it can be customized.
 
 ## Search rank
 

docs/customize/Settings.md

@@ -0,0 +1,672 @@
+This section provides a reference of all configuration parameters that can
+be used with Nominatim.
+
+# Configuring Nominatim
+
+Nominatim uses [dotenv](https://github.com/theskumar/python-dotenv) to manage
+its configuration settings. There are two means to set configuration
+variables: through an `.env` configuration file or through an environment
+variable.
+
+The `.env` configuration file needs to be placed into the
+[project directory](../admin/Import.md#creating-the-project-directory). It
+must contain configuration parameters in `<parameter>=<value>` format.
+Please refer to the dotenv documentation for details.
+
+The configuration options may also be set in the form of shell environment
+variables. This is particularly useful, when you want to temporarily change
+a configuration option. For example, to force the replication serve to
+download the next change, you can temporarily disable the update interval:
+
+    NOMINATIM_REPLICATION_UPDATE_INTERVAL=0 nominatim replication --once
+
+If a configuration option is defined through .env file and environment
+variable, then the latter takes precedence. 
+
+## Configuration Parameter Reference
+
+### Import and Database Settings
+
+#### NOMINATIM_DATABASE_DSN
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Database connection string |
+| **Format:**        | string: `pgsql:<param1>=<value1>;<param2>=<value2>;...` |
+| **Default:**       | pgsql:dbname=nominatim |
+| **After Changes:** | run `nominatim refresh --website` |
+
+Sets the connection parameters for the Nominatim database. At a minimum
+the name of the database (`dbname`) is required. You can set any additional
+parameter that is understood by libpq. See the [Postgres documentation](https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-PARAMKEYWORDS) for a full list.
+
+!!! note
+    It is usually recommended not to set the password directly in this
+    configuration parameter. Use a
+    [password file](https://www.postgresql.org/docs/current/libpq-pgpass.html)
+    instead.
+
+
+#### NOMINATIM_DATABASE_WEBUSER
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Database query user |
+| **Format:**        | string  |
+| **Default:**       | www-data |
+| **After Changes:** | cannot be changed after import |
+
+Defines the name of the database user that will run search queries. Usually
+this is the user under which the webserver is executed. When running Nominatim
+via php-fpm, you can also define a separate query user. The Postgres user
+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:**       | legacy |
+| **After Changes:** | cannot be changed after import |
+
+Sets the tokenizer type to use for the import. For more information on
+available tokenizers and how they are configured, see
+[Tokenizers](../customize/Tokenizers.md).
+
+
+#### NOMINATIM_TOKENIZER_CONFIG
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Configuration file for the tokenizer |
+| **Format:**        | path |
+| **Default:**       | _empty_ (default file depends on tokenizer) |
+| **After Changes:** | see documentation for each tokenizer |
+
+Points to the file with additional configuration for the tokenizer.
+See the [Tokenizer](../customize/Tokenizers.md) descriptions for details
+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
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Avoid invalidating large areas |
+| **Format:**        | bool |
+| **Default:**       | yes |
+
+Nominatim computes the address of each place at indexing time. This has the
+advantage to make search faster but also means that more objects needs to
+be invalidated when the data changes. For example, changing the name of
+the state of Florida would require recomputing every single address point
+in the state to make the new name searchable in conjunction with addresses.
+
+Setting this option to 'yes' means that Nominatim skips reindexing of contained
+objects when the area becomes too large.
+
+
+#### NOMINATIM_UPDATE_FORWARD_DEPENDENCIES
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Forward geometry changes to dependet objects |
+| **Format:**        | bool |
+| **Default:**       | no |
+| **Comment:**       | EXPERT ONLY. Must not be enabled after import. |
+
+The geometry of OSM ways and relations may change when a node that is part
+of the object is moved around. These changes are not propagated per default.
+The geometry of ways/relations is only updated the next time that the object
+itself is touched. When enabling this option, then dependent objects will
+be marked for update when one of its member objects changes.
+
+Enabling this option may slow down updates significantly.
+
+!!! warning
+    If you want to enable this option, it must be set already on import.
+    Do not enable this option on an existing database that was imported with
+    NOMINATIM_UPDATE_FORWARD_DEPENDENCIES=no.
+    Updates will become unusably slow.
+
+#### NOMINATIM_LANGUAGES
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Restrict search languages |
+| **Format:**        | string: comma-separated list of language codes |
+| **Default:**       | _empty_ |
+
+Normally Nominatim will include all language variants of name:XX
+in the search index. Set this to a comma separated list of language
+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            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Enable searching for Tiger house number data |
+| **Format:**        | boolean |
+| **Default:**       | no |
+| **After Changes:** | run `nominatim refresh --functions` |
+
+When this setting is enabled, search and reverse queries also take data
+from [Tiger house number data](Tiger.md) into account.
+
+
+#### NOMINATIM_USE_AUX_LOCATION_DATA
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Enable searching in external house number tables |
+| **Format:**        | boolean |
+| **Default:**       | no |
+| **After Changes:** | run `nominatim refresh --functions` |
+| **Comment:**       | Do not use. |
+
+When this setting is enabled, search queries also take data from external
+house number tables into account.
+
+*Warning:* This feature is currently unmaintained and should not be used.
+
+
+#### NOMINATIM_HTTP_PROXY
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Use HTTP proxy when downloading data |
+| **Format:**        | boolean |
+| **Default:**       | no |
+
+When this setting is enabled and at least
+[NOMINATIM_HTTP_PROXY_HOST](#nominatim_http_proxy_host) and
+[NOMINATIM_HTTP_PROXY_PORT](#nominatim_http_proxy_port) are set, the
+configured proxy will be used, when downloading external data like
+replication diffs.
+
+
+#### NOMINATIM_HTTP_PROXY_HOST
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Host name of the proxy to use |
+| **Format:**        | string |
+| **Default:**       | _empty_ |
+
+When [NOMINATIM_HTTP_PROXY](#nominatim_http_proxy) is enabled, this setting
+configures the proxy host name.
+
+
+#### NOMINATIM_HTTP_PROXY_PORT
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Port number of the proxy to use |
+| **Format:**        | integer |
+| **Default:**       | 3128 |
+
+When [NOMINATIM_HTTP_PROXY](#nominatim_http_proxy) is enabled, this setting
+configures the port number to use with the proxy.
+
+
+#### NOMINATIM_HTTP_PROXY_LOGIN
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Username for proxies that require login |
+| **Format:**        | string |
+| **Default:**       | _empty_ |
+
+When [NOMINATIM_HTTP_PROXY](#nominatim_http_proxy) is enabled, use this
+setting to define the username for proxies that require a login.
+
+
+#### NOMINATIM_HTTP_PROXY_PASSWORD
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Password for proxies that require login |
+| **Format:**        | string |
+| **Default:**       | _empty_ |
+
+When [NOMINATIM_HTTP_PROXY](#nominatim_http_proxy) is enabled, use this
+setting to define the password for proxies that require a login.
+
+
+#### NOMINATIM_OSM2PGSQL_BINARY
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Location of the osm2pgsql binary |
+| **Format:**        | path |
+| **Default:**       | _empty_ (use binary shipped with Nominatim) |
+| **Comment:**       | EXPERT ONLY |
+
+Nominatim uses [osm2pgsql](https://osm2pgsql.org) to load the OSM data
+initially into the database. Nominatim comes bundled with a version of
+osm2pgsql that is guaranteed to be compatible. Use this setting to use
+a different binary instead. You should do this only when you know exactly
+what you are doing. If the osm2pgsql version is not compatible, then the
+result is undefined.
+
+
+#### NOMINATIM_WIKIPEDIA_DATA_PATH
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Directory with the wikipedia importance data |
+| **Format:**        | path |
+| **Default:**       | _empty_ (project directory) |
+
+Set a custom location for the
+[wikipedia ranking file](../admin/Import.md#wikipediawikidata-rankings). When
+unset, Nominatim expects the data to be saved in the project directory.
+
+#### NOMINATIM_ADDRESS_LEVEL_CONFIG
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Configuration file for rank assignments |
+| **Format:**        | path |
+| **Default:**       | address-levels.json |
+
+The _address level configuration_ defines the rank assignments for places. See
+[Place Ranking](Ranking.md) for a detailed explanation what rank assignments
+are and what the configuration file must look like.
+
+When a relative path is given, then the file is searched first relative to the
+project directory and then in the global settings directory.
+
+
+#### NOMINATIM_IMPORT_STYLE
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Configuration to use for the initial OSM data import |
+| **Format:**        | string or path |
+| **Default:**       | extratags |
+
+The _style configuration_ describes which OSM objects and tags are taken
+into consideration for the search database. Nominatim comes with a set
+of pre-configured styles, that may be configured here.
+
+You can also write your own custom style and point the setting to the file
+with the style. When a relative path is given, then the style file is searched
+first relative to the project directory and then in the global settings
+directory.
+
+See [Import Styles](Import-Styles.md)
+for more information on the available internal styles and the format of the
+configuration file.
+
+#### NOMINATIM_FLATNODE_FILE
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Location of osm2pgsql flatnode file |
+| **Format:**        | path |
+| **Default:**       | _empty_ (do not use a flatnote file) |
+| **After Changes:** | Only change when moving the file physically. |
+
+The `osm2pgsql flatnode file` is file that efficiently stores geographic
+location for OSM nodes. For larger imports it can significantly speed up
+the import. When this option is unset, then osm2pgsql uses a PsotgreSQL table
+to store the locations.
+
+When a relative path is given, then the flatnode file is created/searched
+relative to the project directory.
+
+!!! warning
+
+    The flatnode file is not only used during the initial import but also
+    when adding new data with `nominatim add-data` or `nominatim replication`.
+    Make sure you keep the flatnode file around and this setting unmodified,
+    if you plan to add more data or run regular updates.
+
+
+#### NOMINATIM_TABLESPACE_*
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Group of settings for distributing the database over tablespaces |
+| **Format:**        | string |
+| **Default:**       | _empty_ (do not use a table space) |
+| **After Changes:** | no effect after initial import |
+
+Nominatim allows to distribute the search database over up to 10 different
+[PostgreSQL tablespaces](https://www.postgresql.org/docs/current/manage-ag-tablespaces.html).
+If you use this option, make sure that the tablespaces exist before starting
+the import.
+
+The available tablespace groups are:
+
+NOMINATIM_TABLESPACE_SEARCH_DATA
+:    Data used by the geocoding frontend.
+
+NOMINATIM_TABLESPACE_SEARCH_INDEX
+:    Indexes used by the geocoding frontend.
+
+NOMINATIM_TABLESPACE_OSM_DATA
+:    Raw OSM data cache used for import and updates.
+
+NOMINATIM_TABLESPACE_OSM_DATA
+:    Indexes on the raw OSM data cache.
+
+NOMINATIM_TABLESPACE_PLACE_DATA
+:    Data table with the pre-filtered but still unprocessed OSM data.
+     Used only during imports and updates.
+
+NOMINATIM_TABLESPACE_PLACE_INDEX
+:    Indexes on raw data table. Used only during imports and updates.
+
+NOMINATIM_TABLESPACE_ADDRESS_DATA
+:    Data tables used for computing search terms and addresses of places
+     during import and updates.
+
+NOMINATIM_TABLESPACE_ADDRESS_INDEX
+:    Indexes on the data tables for search term and address computation.
+     Used only for import and updates.
+
+NOMINATIM_TABLESPACE_AUX_DATA
+:    Auxiliary data tables for non-OSM data, e.g. for Tiger house number data.
+
+NOMINATIM_TABLESPACE_AUX_INDEX
+:    Indexes on auxiliary data tables.
+
+
+### Replication Update Settings
+
+#### NOMINATIM_REPLICATION_URL
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Base URL of the replication service |
+| **Format:**        | url |
+| **Default:**       | https://planet.openstreetmap.org/replication/minute |
+| **After Changes:** | run `nominatim replication --init` |
+
+Replication services deliver updates to OSM data. Use this setting to choose
+which replication service to use. See [Updates](../admin/Update.md) for more
+information on how to set up regular updates.
+
+#### NOMINATIM_REPLICATION_MAX_DIFF
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Maximum amount of data to download per update cycle (in MB) |
+| **Format:**        | integer |
+| **Default:**       | 50 |
+| **After Changes:** | restart the replication process |
+
+At each update cycle Nominatim downloads diffs until either no more diffs
+are available on the server (i.e. the database is up-to-date) or the limit
+given in this setting is exceeded. Nominatim guarantees to downloads at least
+one diff, if one is available, no matter how small the setting.
+
+The default for this setting is fairly conservative because Nominatim keeps
+all data downloaded in one cycle in RAM. Using large values in a production
+server may interfere badly with the search frontend because it evicts data
+from RAM that is needed for speedy answers to incoming requests. It is usually
+a better idea to keep this setting lower and run multiple update cycles
+to catch up with updates.
+
+When catching up in non-production mode, for example after the initial import,
+the setting can easily be changed temporarily on the command line:
+
+    NOMINATIM_REPLICATION_MAX_DIFF=3000 nominatim replication
+
+
+#### NOMINATIM_REPLICATION_UPDATE_INTERVAL
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Publication interval of the replication service (in seconds) |
+| **Format:**        | integer |
+| **Default:**       | 75 |
+| **After Changes:** | restart the replication process |
+
+This setting determines when Nominatim will attempt to download again a new
+update. The time is computed from the publication date of the last diff
+downloaded. Setting this to a slightly higher value than the actual
+publication interval avoids unnecessary rechecks.
+
+
+#### NOMINATIM_REPLICATION_RECHECK_INTERVAL
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Wait time to recheck for a pending update (in seconds)  |
+| **Format:**        | integer |
+| **Default:**       | 60 |
+| **After Changes:** | restart the replication process |
+
+When replication updates are run in continuous mode (using `nominatim replication`),
+this setting determines how long Nominatim waits until it looks for updates
+again when updates were not available on the server.
+
+Note that this is different from
+[NOMINATIM_REPLICATION_UPDATE_INTERVAL](#nominatim_replication_update_interval).
+Nominatim will never attempt to query for new updates for UPDATE_INTERVAL
+seconds after the current database date. Only after the update interval has
+passed it asks for new data. If then no new data is found, it waits for
+RECHECK_INTERVAL seconds before it attempts again.
+
+### API Settings
+
+#### NOMINATIM_CORS_NOACCESSCONTROL
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Send permissive CORS access headers |
+| **Format:**        | boolean |
+| **Default:**       | yes |
+| **After Changes:** | run `nominatim refresh --website` |
+
+When this setting is enabled, API HTTP responses include the HTTP
+[CORS](https://en.wikipedia.org/wiki/CORS) headers
+`access-control-allow-origin: *` and `access-control-allow-methods: OPTIONS,GET`.
+
+#### NOMINATIM_MAPICON_URL
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | URL prefix for static icon images |
+| **Format:**        | url |
+| **Default:**       | _empty_ |
+| **After Changes:** | run `nominatim refresh --website` |
+
+When a mapicon URL is configured, then Nominatim includes an additional `icon`
+field in the responses, pointing to an appropriate icon for the place type.
+
+Map icons used to be included in Nominatim itself but now have moved to the
+[nominatim-ui](https://github.com/osm-search/nominatim-ui/) project. If you
+want the URL to be included in API responses, make the `/mapicon`
+directory of the project available under a public URL and point this setting
+to the directory.
+
+
+#### NOMINATIM_DEFAULT_LANGUAGE
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Language of responses when no language is requested |
+| **Format:**        | language code |
+| **Default:**       | _empty_ (use the local language of the feature) |
+| **After Changes:** | run `nominatim refresh --website` |
+
+Nominatim localizes the place names in responses when the corresponding
+translation is available. Users can request a custom language setting through
+the HTTP accept-languages header or through the explicit parameter
+[accept-languages](../api/Search.md#language-of-results). If neither is
+given, it falls back to this setting. If the setting is also empty, then
+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            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Maximum number of OSM ids accepted by /lookup |
+| **Format:**        | integer |
+| **Default:**       | 50 |
+| **After Changes:** | run `nominatim refresh --website` |
+
+The /lookup point accepts list of ids to look up address details for. This
+setting restricts the number of places a user may look up with a single
+request.
+
+
+#### NOMINATIM_POLYGON_OUTPUT_MAX_TYPES
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Number of different geometry formats that may be returned |
+| **Format:**        | integer |
+| **Default:**       | 1 |
+| **After Changes:** | run `nominatim refresh --website` |
+
+Nominatim supports returning full geometries of places. The geometries may
+be requested in different formats with one of the
+[`polygon_*` parameters](../api/Search.md#polygon-output). Use this
+setting to restrict the number of geometry types that may be requested
+with a single query.
+
+Setting this parameter to 0 disables polygon output completely.
+
+### Logging Settings
+
+#### NOMINATIM_LOG_DB
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **Description:**   | Log requests into the database |
+| **Format:**        | boolean |
+| **Default:**       | no |
+| **After Changes:** | run `nominatim refresh --website` |
+
+Enable logging requests into a database table with this setting. The logs
+can be found in the table `new_query_log`.
+
+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.
+
+Can be used as the same time as NOMINATIM_LOG_FILE.
+
+#### NOMINATIM_LOG_FILE
+
+| Summary            |                                                     |
+| --------------     | --------------------------------------------------- |
+| **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 entries in the log file have the following format:
+
+    <request time> <execution time in s> <number of results> <type> "<query string>"
+
+Request time is the time when the request was started. The execution time is
+given in seconds and corresponds to the time the query took executing in PHP.
+type contains the name of the endpoint used.
+
+Can be used as the same time as NOMINATIM_LOG_DB.

docs/customize/Special-Phrases.md

@@ -0,0 +1,34 @@
+# Special phrases
+
+## Importing OSM user-maintained special phrases
+
+As described in the [Import section](../admin/Import.md), it is possible to
+import special phrases from the wiki with the following command:
+
+```sh
+nominatim special-phrases --import-from-wiki
+```
+
+## Importing custom special phrases
+
+But, it is also possible to import some phrases from a csv file. 
+To do so, you have access to the following command:
+
+```sh
+nominatim special-phrases --import-from-csv <csv file>
+```
+
+Note that the two previous import commands will update the phrases from your database.
+This means that if you import some phrases from a csv file, only the phrases
+present in the csv file will be kept into the database. All other phrases will
+be removed.
+
+If you want to only add new phrases and not update the other ones you can add
+the argument `--no-replace` to the import command. For example:
+
+```sh
+nominatim special-phrases --import-from-csv <csv file> --no-replace
+```
+
+This will add the phrases present in the csv file into the database without
+removing the other ones.

docs/customize/Tiger.md

@@ -0,0 +1,28 @@
+# Installing TIGER housenumber data for the US
+
+Nominatim is able to use the official [TIGER](https://www.census.gov/geographies/mapping-files/time-series/geo/tiger-line-file.html)
+address set to complement the OSM house number data in the US. You can add
+TIGER data to your own Nominatim instance by following these steps. The
+entire US adds about 10GB to your database.
+
+  1. Get preprocessed TIGER data:
+
+        cd $PROJECT_DIR
+        wget https://nominatim.org/data/tiger-nominatim-preprocessed-latest.csv.tar.gz
+
+  2. Import the data into your Nominatim database:
+
+        nominatim add-data --tiger-data tiger-nominatim-preprocessed-latest.csv.tar.gz
+
+  3. Enable use of the Tiger data in your existing `.env` file by adding:
+
+        echo NOMINATIM_USE_US_TIGER_DATA=yes >> .env
+
+  4. Apply the new settings:
+
+        nominatim refresh --functions --website
+
+
+See the [TIGER-data project](https://github.com/osm-search/TIGER-data) for more
+information on how the data got preprocessed.
+

docs/customize/Tokenizers.md

@@ -0,0 +1,391 @@
+# Tokenizers
+
+The tokenizer module in Nominatim is responsible for analysing the names given
+to OSM objects and the terms of an incoming query in order to make sure, they
+can be matched appropriately.
+
+Nominatim offers different tokenizer modules, which behave differently and have
+different configuration options. This sections describes the tokenizers and how
+they can be configured.
+
+!!! important
+    The use of a tokenizer is tied to a database installation. You need to choose
+    and configure the tokenizer before starting the initial import. Once the import
+    is done, you cannot switch to another tokenizer anymore. Reconfiguring the
+    chosen tokenizer is very limited as well. See the comments in each tokenizer
+    section.
+
+## Legacy tokenizer
+
+The legacy tokenizer implements the analysis algorithms of older Nominatim
+versions. It uses a special Postgresql module to normalize names and queries.
+This tokenizer is 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
+normalize names and queries. It also offers configurable decomposition and
+abbreviation handling.
+This tokenizer is currently the default.
+
+To enable the tokenizer add the following line to your project configuration:
+
+```
+NOMINATIM_TOKENIZER=icu
+```
+
+### How it works
+
+On import the tokenizer processes names in the following three stages:
+
+1. During the **Sanitizer step** incoming names are cleaned up and converted to
+   **full names**. This step can be used to regularize spelling, split multi-name
+   tags into their parts and tag names with additional attributes. See the
+   [Sanitizers section](#sanitizers) below for available cleaning routines.
+2. The **Normalization** part removes all information from the full names
+   that are not relevant for search.
+3. The **Token analysis** step takes the normalized full names and creates
+   all transliterated variants under which the name should be searchable.
+   See the [Token analysis](#token-analysis) section below for more
+   information.
+
+During query time, only normalization and transliteration are relevant.
+An incoming query is first split into name chunks (this usually means splitting
+the string at the commas) and the each part is normalised and transliterated.
+The result is used to look up places in the search index.
+
+### Configuration
+
+The ICU tokenizer is configured using a YAML file which can be configured using
+`NOMINATIM_TOKENIZER_CONFIG`. The configuration is read on import and then
+saved as part of the internal database status. Later changes to the variable
+have no effect.
+
+Here is an example configuration file:
+
+``` yaml
+normalization:
+    - ":: lower ()"
+    - "ß > 'ss'" # German szet is unimbigiously equal to double ss
+transliteration:
+    - !include /etc/nominatim/icu-rules/extended-unicode-to-asccii.yaml
+    - ":: Ascii ()"
+sanitizers:
+    - step: split-name-list
+token-analysis:
+    - analyzer: generic
+      variants:
+          - !include icu-rules/variants-ca.yaml
+          - words:
+              - road -> rd
+              - bridge -> bdge,br,brdg,bri,brg
+      mutations:
+          - pattern: 'ä'
+            replacements: ['ä', 'ae']
+```
+
+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 **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.
+
+The **transliteration** rules are applied at the end of the tokenization
+process to transfer the name into an ASCII representation. Transliteration can
+be useful to allow for further fuzzy matching, especially between different
+scripts.
+
+Each section must contain a list of
+[ICU transformation rules](https://unicode-org.github.io/icu/userguide/transforms/general/rules.html).
+The rules are applied in the order in which they appear in the file.
+You can also include additional rules from external yaml file using the
+`!include` tag. The included file must contain a valid YAML list of ICU rules
+and may again include other files.
+
+!!! warning
+    The ICU rule syntax contains special characters that conflict with the
+    YAML syntax. You should therefore always enclose the ICU rules in
+    double-quotes.
+
+#### Sanitizers
+
+The sanitizers section defines an ordered list of functions that are applied
+to the name and address tags before they are further processed by the tokenizer.
+They allows to clean up the tagging and bring it to a standardized form more
+suitable for building the search index.
+
+!!! hint
+    Sanitizers only have an effect on how the search index is built. They
+    do not change the information about each place that is saved in the
+    database. In particular, they have no influence on how the results are
+    displayed. The returned results always show the original information as
+    stored in the OpenStreetMap database.
+
+Each entry contains information of a sanitizer to be applied. It has a
+mandatory parameter `step` which gives the name of the sanitizer. Depending
+on the type, it may have additional parameters to configure its operation.
+
+The order of the list matters. The sanitizers are applied exactly in the order
+that is configured. Each sanitizer works on the results of the previous one.
+
+The following is a list of sanitizers that are shipped with Nominatim.
+
+##### split-name-list
+
+::: nominatim.tokenizer.sanitizers.split_name_list
+    selection:
+        members: False
+    rendering:
+        heading_level: 6
+
+##### strip-brace-terms
+
+::: nominatim.tokenizer.sanitizers.strip_brace_terms
+    selection:
+        members: False
+    rendering:
+        heading_level: 6
+
+##### tag-analyzer-by-language
+
+::: nominatim.tokenizer.sanitizers.tag_analyzer_by_language
+    selection:
+        members: False
+    rendering:
+        heading_level: 6
+
+##### clean-housenumbers
+
+::: nominatim.tokenizer.sanitizers.clean_housenumbers
+    selection:
+        members: False
+    rendering:
+        heading_level: 6
+
+##### clean-postcodes
+
+::: nominatim.tokenizer.sanitizers.clean_postcodes
+    selection:
+        members: False
+    rendering:
+        heading_level: 6
+
+##### clean-tiger-tags
+
+::: nominatim.tokenizer.sanitizers.clean_tiger_tags
+    selection:
+        members: False
+    rendering:
+        heading_level: 6
+
+
+
+#### Token Analysis
+
+Token analyzers take a full name and transform it into one or more normalized
+form that are then saved in the search index. In its simplest form, the
+analyzer only applies the transliteration rules. More complex analyzers
+create additional spelling variants of a name. This is useful to handle
+decomposition and abbreviation.
+
+The ICU tokenizer may use different analyzers for different names. To select
+the analyzer to be used, the name must be tagged with the `analyzer` attribute
+by a sanitizer (see for example the
+[tag-analyzer-by-language sanitizer](#tag-analyzer-by-language)).
+
+The token-analysis section contains the list of configured analyzers. Each
+analyzer must have an `id` parameter that uniquely identifies the analyzer.
+The only exception is the default analyzer that is used when no special
+analyzer was selected. There are analysers with special ids:
+
+ * '@housenumber'. If an analyzer with that name is present, it is used
+   for normalization of house numbers.
+ * '@potcode'. If an analyzer with that name is present, it is used
+   for normalization of postcodes.
+
+Different analyzer implementations may exist. To select the implementation,
+the `analyzer` parameter must be set. The different implementations are
+described in the following.
+
+##### Generic token analyzer
+
+The generic analyzer `generic` is able to create variants from a list of given
+abbreviation and decomposition replacements and introduce spelling variations.
+
+###### Variants
+
+The optional 'variants' section defines lists of replacements which create alternative
+spellings of a name. To create the variants, a name is scanned from left to
+right and the longest matching replacement is applied until the end of the
+string is reached.
+
+The variants section must contain a list of replacement groups. Each group
+defines a set of properties that describes where the replacements are
+applicable. In addition, the word section defines the list of replacements
+to be made. The basic replacement description is of the form:
+
+```
+<source>[,<source>[...]] => <target>[,<target>[...]]
+```
+
+The left side contains one or more `source` terms to be replaced. The right side
+lists one or more replacements. Each source is replaced with each replacement
+term.
+
+!!! tip
+    The source and target terms are internally normalized using the
+    normalization rules given in the configuration. This ensures that the
+    strings match as expected. In fact, it is better to use unnormalized
+    words in the configuration because then it is possible to change the
+    rules for normalization later without having to adapt the variant rules.
+
+###### Decomposition
+
+In its standard form, only full words match against the source. There
+is a special notation to match the prefix and suffix of a word:
+
+``` yaml
+- ~strasse => str  # matches "strasse" as full word and in suffix position
+- hinter~ => hntr  # matches "hinter" as full word and in prefix position
+```
+
+There is no facility to match a string in the middle of the word. The suffix
+and prefix notation automatically trigger the decomposition mode: two variants
+are created for each replacement, one with the replacement attached to the word
+and one separate. So in above example, the tokenization of "hauptstrasse" will
+create the variants "hauptstr" and "haupt str". Similarly, the name "rote strasse"
+triggers the variants "rote str" and "rotestr". By having decomposition work
+both ways, it is sufficient to create the variants at index time. The variant
+rules are not applied at query time.
+
+To avoid automatic decomposition, use the '|' notation:
+
+``` yaml
+- ~strasse |=> str
+```
+
+simply changes "hauptstrasse" to "hauptstr" and "rote strasse" to "rote str".
+
+###### Initial and final terms
+
+It is also possible to restrict replacements to the beginning and end of a
+name:
+
+``` yaml
+- ^south => s  # matches only at the beginning of the name
+- road$ => rd  # matches only at the end of the name
+```
+
+So the first example would trigger a replacement for "south 45th street" but
+not for "the south beach restaurant".
+
+###### Replacements vs. variants
+
+The replacement syntax `source => target` works as a pure replacement. It changes
+the name instead of creating a variant. To create an additional version, you'd
+have to write `source => source,target`. As this is a frequent case, there is
+a shortcut notation for it:
+
+```
+<source>[,<source>[...]] -> <target>[,<target>[...]]
+```
+
+The simple arrow causes an additional variant to be added. Note that
+decomposition has an effect here on the source as well. So a rule
+
+``` yaml
+- "~strasse -> str"
+```
+
+means that for a word like `hauptstrasse` four variants are created:
+`hauptstrasse`, `haupt strasse`, `hauptstr` and `haupt str`.
+
+###### Mutations
+
+The 'mutation' section in the configuration describes an additional set of
+replacements to be applied after the variants have been computed.
+
+Each mutation is described by two parameters: `pattern` and `replacements`.
+The pattern must contain a single regular expression to search for in the
+variant name. The regular expressions need to follow the syntax for
+[Python regular expressions](file:///usr/share/doc/python3-doc/html/library/re.html#regular-expression-syntax).
+Capturing groups are not permitted.
+`replacements` must contain a list of strings that the pattern
+should be replaced with. Each occurrence of the pattern is replaced with
+all given replacements. Be mindful of combinatorial explosion of variants.
+
+###### Modes
+
+The generic analyser supports a special mode `variant-only`. When configured
+then it consumes the input token and emits only variants (if any exist). Enable
+the mode by adding:
+
+```
+  mode: variant-only
+```
+
+to the analyser configuration.
+
+##### Housenumber token analyzer
+
+The analyzer `housenumbers` is purpose-made to analyze house numbers. It
+creates variants with optional spaces between numbers and letters. Thus,
+house numbers of the form '3 a', '3A', '3-A' etc. are all considered equivalent.
+
+The analyzer cannot be customized.
+
+##### Postcode token analyzer
+
+The analyzer `postcodes` is pupose-made to analyze postcodes. It supports
+a 'lookup' varaint of the token, which produces variants with optional
+spaces. Use together with the clean-postcodes sanitizer.
+
+The analyzer cannot be customized.
+
+### Reconfiguration
+
+Changing the configuration after the import is currently not possible, although
+this feature may be added at a later time.

docs/develop/Database-Layout.md

@@ -0,0 +1,167 @@
+# Database Layout
+
+### Import tables
+
+OSM data is initially imported using [osm2pgsql](https://osm2pgsql.org).
+Nominatim uses its own data output style 'gazetteer', which differs from the
+output style created for map rendering.
+
+The import process creates the following tables:
+
+![osm2pgsql tables](osm2pgsql-tables.svg)
+
+The `planet_osm_*` tables are the usual backing tables for OSM data. Note
+that Nominatim uses them to look up special relations and to find nodes on
+ways.
+
+The gazetteer style produces a single table `place` as output with the following
+columns:
+
+ * `osm_type` - kind of OSM object (**N** - node, **W** - way, **R** - relation)
+ * `osm_id` - original OSM ID
+ * `class` - key of principal tag defining the object type
+ * `type` - value of principal tag defining the object type
+ * `name` - collection of tags that contain a name or reference
+ * `admin_level` - numerical value of the tagged administrative level
+ * `address` - collection of tags defining the address of an object
+ * `extratags` - collection of additional interesting tags that are not
+                 directly relevant for searching
+ * `geometry` - geometry of the object (in WGS84)
+
+A single OSM object may appear multiple times in this table when it is tagged
+with multiple tags that may constitute a principal tag. Take for example a
+motorway bridge. In OSM, this would be a way which is tagged with
+`highway=motorway` and `bridge=yes`. This way would appear in the `place` table
+once with `class` of `highway` and once with a `class` of `bridge`. Thus the
+*unique key* for `place` is (`osm_type`, `osm_id`, `class`).
+
+How raw OSM tags are mapped to the columns in the place table is to a certain
+degree configurable. See [Customizing Import Styles](../customize/Import-Styles.md)
+for more information.
+
+### Search tables
+
+The following tables carry all information needed to do the search:
+
+![search tables](search-tables.svg)
+
+The **placex** table is the central table that saves all information about the
+searchable places in Nominatim. The basic columns are the same as for the
+place table and have the same meaning. The placex tables adds the following
+additional columns:
+
+ * `place_id` - the internal unique ID to identify the place
+ * `partition` - the id to use with partitioned tables (see below)
+ * `geometry_sector` - a location hash used for geographically close ordering
+ * `parent_place_id` - the next higher place in the address hierarchy, only
+   relevant for POI-type places (with rank 30)
+ * `linked_place_id` - place ID of the place this object has been merged with.
+   When this ID is set, then the place is invisible for search.
+ * `importance` - measure how well known the place is
+ * `rank_search`, `rank_address` - search and address rank (see [Customizing ranking](../customize/Ranking.md)
+ * `wikipedia` - the wikipedia page used for computing the importance of the place
+ * `country_code` - the country the place is located in
+ * `housenumber` - normalized housenumber, if the place has one
+ * `postcode` - computed postcode for the place
+ * `indexed_status` - processing status of the place (0 - ready, 1 - freshly inserted, 2 - needs updating, 100 - needs deletion)
+ * `indexed_date` - timestamp when the place was processed last
+ * `centroid` - a point feature for the place
+
+The **location_property_osmline** table is a special table for
+[address interpolations](https://wiki.openstreetmap.org/wiki/Addresses#Using_interpolation).
+The columns have the same meaning and use as the columns with the same name in
+the placex table. Only three columns are special:
+
+ * `startnumber` and `endnumber` - beginning and end of the number range
+    for the interpolation
+ * `interpolationtype` - a string `odd`, `even` or `all` to indicate
+    the interval between the numbers
+
+Address interpolations are always ways in OSM, which is why there is no column
+`osm_type`.
+
+The **location_postcode** table holds computed centroids of all postcodes that
+can be found in the OSM data. The meaning of the columns is again the same
+as that of the placex table.
+
+Every place needs an address, a set of surrounding places that describe the
+location of the place. The set of address places is made up of OSM places
+themselves. The **place_addressline** table cross-references for each place
+all the places that make up its address. Two columns define the address
+relation:
+
+  * `place_id` - reference to the place being addressed
+  * `address_place_id` - reference to the place serving as an address part
+
+The most of the columns cache information from the placex entry of the address
+part. The exceptions are:
+
+  * `fromarea` - is true if the address part has an area geometry and can
+    therefore be considered preceise
+  * `isaddress` - is true if the address part should show up in the address
+    output. Sometimes there are multiple places competing for for same address
+    type (e.g. multiple cities) and this field resolves the tie.
+
+The **search_name** table contains the search index proper. It saves for each
+place the terms with which the place can be found. The terms are split into
+the name itself and all terms that make up the address. The table mirrors some
+of the columns from placex for faster lookup.
+
+Search terms are not saved as strings. Each term is assigned an integer and those
+integers are saved in the name and address vectors of the search_name table. The
+**word** table serves as the lookup table from string to such a word ID. The
+exact content of the word table depends on the [tokenizer](Tokenizers.md) used.
+
+## Address computation tables
+
+Next to the main search tables, there is a set of secondary helper tables used
+to compute the address relations between places. These tables are partitioned.
+Each country is assigned a partition number in the country_name table (see
+below) and the data is then split between a set of tables, one for each
+partition. Note that Nominatim still manually manages partitioned tables.
+Native support for partitions in PostgreSQL only became usable with version 13.
+It will be a little while before Nominatim drops support for older versions.
+
+![address tables](address-tables.svg)
+
+The **search_name_X** tables are used to look up streets that appear in the
+`addr:street` tag.
+
+The **location_area_large_X** tables are used to look up larger areas
+(administrative boundaries and place nodes) either through their geographic
+closeness or through `addr:*` entries.
+
+The **location_road_X** tables are used to find the closest street for a
+dependent place.
+
+All three table cache specific information from the placex table for their
+selected subset of places:
+
+ * `keywords` and `name_vector` contain lists of term ids (from the word table)
+   that the full name of the place should match against
+ * `isguess` is true for places that are not described by an area
+
+All other columns reflect their counterpart in the placex table.
+
+## Static data tables
+
+Nominatim also creates a number of static tables at import:
+
+ * `nominatim_properties` saves settings that must not be changed after
+    import
+ * `address_levels` save the rank information from the
+   [ranking configuration](../customize/Ranking.md)
+ * `country_name` contains a fallback of names for all countries, their
+   default languages and saves the assignment of countries to partitions.
+ * `country_osm_grid` provides a fallback for country geometries
+
+## Auxiliary data tables
+
+Finally there are some table for auxiliary data:
+
+ * `location_property_tiger` - saves housenumber from the Tiger import. Its
+   layout is similar to that of `location_propoerty_osmline`.
+ * `place_class_*` tables are helper tables to facilitate lookup of POIs
+   by their class and type. They exist because it is not possible to create
+   combined indexes with geometries.
+

docs/develop/Development-Environment.md

@@ -1,6 +1,6 @@
 # Setting up Nominatim for Development
 
-This chapter gives an overview how to set up Nominatim for developement
+This chapter gives an overview how to set up Nominatim for development
 and how to run tests.
 
 !!! Important
@@ -30,14 +30,18 @@ unit tests (using PHPUnit for PHP code and pytest for Python code).
 It has the following additional requirements:
 
 * [behave test framework](https://behave.readthedocs.io) >= 1.2.6
-* [phpunit](https://phpunit.de) >= 7.3
+* [phpunit](https://phpunit.de) (9.5 is known to work)
 * [PHP CodeSniffer](https://github.com/squizlabs/PHP_CodeSniffer)
-* [Pylint](https://pylint.org/) (2.6.0 is used for the CI)
+* [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)
 
 The documentation is built with mkdocs:
 
 * [mkdocs](https://www.mkdocs.org/) >= 1.1.2
+* [mkdocstrings](https://mkdocstrings.github.io/) >= 0.16
+* [mkdocstrings-python-legacy](https://mkdocstrings.github.io/python-legacy/)
 
 ### Installing prerequisites on Ubuntu/Debian
 
@@ -49,9 +53,10 @@ To install all necessary packages run:
 
 ```sh
 sudo apt install php-cgi phpunit php-codesniffer \
-                 python3-pip python3-setuptools python3-dev pylint
+                 python3-pip python3-setuptools python3-dev
 
-pip3 install --user behave mkdocs pytest
+pip3 install --user behave mkdocs mkdocstrings pytest pylint \
+                    mypy types-PyYAML types-jinja2 types-psycopg2 types-psutil
 ```
 
 The `mkdocs` executable will be located in `.local/bin`. You may have to add
@@ -113,7 +118,7 @@ symlinks (see `CMakeLists.txt` for the exact steps).
 Now you can start webserver for local testing
 
 ```
-build> mkdocs serve
+build> make serve-doc
 [server:296] Serving on http://127.0.0.1:8000
 [handlers:62] Start watching changes
 ```
@@ -122,7 +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
 ```

docs/develop/ICU-Tokenizer-Modules.md

@@ -0,0 +1,227 @@
+# Writing custom sanitizer and token analysis modules for the ICU tokenizer
+
+The [ICU tokenizer](../customize/Tokenizers.md#icu-tokenizer) provides a
+highly customizable method to pre-process and normalize the name information
+of the input data before it is added to the search index. It comes with a
+selection of sanitizers and token analyzers which you can use to adapt your
+installation to your needs. If the provided modules are not enough, you can
+also provide your own implementations. This section describes the API
+of sanitizers and token analysis.
+
+!!! warning
+    This API is currently in early alpha status. While this API is meant to
+    be a public API on which other sanitizers and token analyzers may be
+    implemented, it is not guaranteed to be stable at the moment.
+
+
+## Using non-standard sanitizers and token analyzers
+
+Sanitizer names (in the `step` property) and token analysis names (in the
+`analyzer`) may refer to externally supplied modules. There are two ways
+to include external modules: through a library or from the project directory.
+
+To include a module from a library, use the absolute import path as name and
+make sure the library can be found in your PYTHONPATH.
+
+To use a custom module without creating a library, you can put the module
+somewhere in your project directory and then use the relative path to the
+file. Include the whole name of the file including the `.py` ending.
+
+## Custom sanitizer modules
+
+A sanitizer module must export a single factory function `create` with the
+following signature:
+
+``` python
+def create(config: SanitizerConfig) -> Callable[[ProcessInfo], None]
+```
+
+The function receives the custom configuration for the sanitizer and must
+return a callable (function or class) that transforms the name and address
+terms of a place. When a place is processed, then a `ProcessInfo` object
+is created from the information that was queried from the database. This
+object is sequentially handed to each configured sanitizer, so that each
+sanitizer receives the result of processing from the previous sanitizer.
+After the last sanitizer is finished, the resulting name and address lists
+are forwarded to the token analysis module.
+
+Sanitizer functions are instantiated once and then called for each place
+that is imported or updated. They don't need to be thread-safe.
+If multi-threading is used, each thread creates their own instance of
+the function.
+
+### Sanitizer configuration
+
+::: nominatim.tokenizer.sanitizers.config.SanitizerConfig
+    rendering:
+        show_source: no
+        heading_level: 6
+
+### The main filter function of the sanitizer
+
+The filter function receives a single object of type `ProcessInfo`
+which has with three members:
+
+ * `place`: read-only information about the place being processed.
+   See PlaceInfo below.
+ * `names`: The current list of names for the place. Each name is a
+   PlaceName object.
+ * `address`: The current list of address names for the place. Each name
+   is a PlaceName object.
+
+While the `place` member is provided for information only, the `names` and
+`address` lists are meant to be manipulated by the sanitizer. It may add and
+remove entries, change information within a single entry (for example by
+adding extra attributes) or completely replace the list with a different one.
+
+#### PlaceInfo - information about the place
+
+::: nominatim.data.place_info.PlaceInfo
+    rendering:
+        show_source: no
+        heading_level: 6
+
+
+#### PlaceName - extended naming information
+
+::: nominatim.data.place_name.PlaceName
+    rendering:
+        show_source: no
+        heading_level: 6
+
+
+### Example: Filter for US street prefixes
+
+The following sanitizer removes the directional prefixes from street names
+in the US:
+
+``` python
+import re
+
+def _filter_function(obj):
+    if obj.place.country_code == 'us' \
+       and obj.place.rank_address >= 26 and obj.place.rank_address <= 27:
+        for name in obj.names:
+            name.name = re.sub(r'^(north|south|west|east) ',
+                               '',
+                               name.name,
+                               flags=re.IGNORECASE)
+
+def create(config):
+    return _filter_function
+```
+
+This is the most simple form of a sanitizer module. If defines a single
+filter function and implements the required `create()` function by returning
+the filter.
+
+The filter function first checks if the object is interesting for the
+sanitizer. Namely it checks if the place is in the US (through `country_code`)
+and it the place is a street (a `rank_address` of 26 or 27). If the
+conditions are met, then it goes through all available names and
+removes any leading directional prefix using a simple regular expression.
+
+Save the source code in a file in your project directory, for example as
+`us_streets.py`. Then you can use the sanitizer in your `icu_tokenizer.yaml`:
+
+``` yaml
+...
+sanitizers:
+    - step: us_streets.py
+...
+```
+
+!!! warning
+    This example is just a simplified show case on how to create a sanitizer.
+    It is not really read for real-world use: while the sanitizer would
+    correcly transform `West 5th Street` into `5th Street`. it would also
+    shorten a simple `North Street` to `Street`.
+
+For more sanitizer examples, have a look at the sanitizers provided by Nominatim.
+They can be found in the directory
+[`nominatim/tokenizer/sanitizers`](https://github.com/osm-search/Nominatim/tree/master/nominatim/tokenizer/sanitizers).
+
+
+## Custom token analysis module
+
+::: nominatim.tokenizer.token_analysis.base.AnalysisModule
+    rendering:
+        show_source: no
+        heading_level: 6
+
+
+::: nominatim.tokenizer.token_analysis.base.Analyzer
+    rendering:
+        show_source: no
+        heading_level: 6
+
+### Example: Creating acronym variants for long names
+
+The following example of a token analysis module creates acronyms from
+very long names and adds them as a variant:
+
+``` python
+class AcronymMaker:
+    """ This class is the actual analyzer.
+    """
+    def __init__(self, norm, trans):
+        self.norm = norm
+        self.trans = trans
+
+
+    def get_canonical_id(self, name):
+        # In simple cases, the normalized name can be used as a canonical id.
+        return self.norm.transliterate(name.name).strip()
+
+
+    def compute_variants(self, name):
+        # The transliterated form of the name always makes up a variant.
+        variants = [self.trans.transliterate(name)]
+
+        # Only create acronyms from very long words.
+        if len(name) > 20:
+            # Take the first letter from each word to form the acronym.
+            acronym = ''.join(w[0] for w in name.split())
+            # If that leds to an acronym with at least three letters,
+            # add the resulting acronym as a variant.
+            if len(acronym) > 2:
+                # Never forget to transliterate the variants before returning them.
+                variants.append(self.trans.transliterate(acronym))
+
+        return variants
+
+# The following two functions are the module interface.
+
+def configure(rules, normalizer, transliterator):
+    # There is no configuration to parse and no data to set up.
+    # Just return an empty configuration.
+    return None
+
+
+def create(normalizer, transliterator, config):
+    # Return a new instance of our token analysis class above.
+    return AcronymMaker(normalizer, transliterator)
+```
+
+Given the name `Trans-Siberian Railway`, the code above would return the full
+name `Trans-Siberian Railway` and the acronym `TSR` as variant, so that
+searching would work for both.
+
+## Sanitizers vs. Token analysis - what to use for variants?
+
+It is not always clear when to implement variations in the sanitizer and
+when to write a token analysis module. Just take the acronym example
+above: it would also have been possible to write a sanitizer which adds the
+acronym as an additional name to the name list. The result would have been
+similar. So which should be used when?
+
+The most important thing to keep in mind is that variants created by the
+token analysis are only saved in the word lookup table. They do not need
+extra space in the search index. If there are many spelling variations, this
+can mean quite a significant amount of space is saved.
+
+When creating additional names with a sanitizer, these names are completely
+independent. In particular, they can be fed into different token analysis
+modules. This gives a much greater flexibility but at the price that the
+additional names increase the size of the search index.
+

docs/develop/Indexing.md

@@ -0,0 +1,152 @@
+# Indexing Places
+
+In Nominatim, the word __indexing__ refers to the process that takes the raw
+OpenStreetMap data from the place table, enriches it with address information
+and creates the search indexes. This section explains the basic data flow.
+
+
+## Initial import
+
+After osm2pgsql has loaded the raw OSM data into the place table,
+the data is copied to the final search tables placex and location_property_osmline.
+While they are copied, some basic properties are added:
+
+ * country_code, geometry_sector and partition
+ * initial search and address rank
+
+In addition the column `indexed_status` is set to `1` marking the place as one
+that needs to be indexed.
+
+All this happens in the triggers `placex_insert` and `osmline_insert`.
+
+## Indexing
+
+The main work horse of the data import is the indexing step, where Nominatim
+takes every place from the placex and location_property_osmline tables where
+the indexed_status != 0 and computes the search terms and the address parts
+of the place.
+
+The indexing happens in three major steps:
+
+1. **Data preparation** - The indexer gets the data for the place to be indexed
+   from the database.
+
+2. **Search name processing** - The prepared data is given to the
+   tokenizer which computes the search terms from the names
+   and potentially other information.
+
+3. **Address processing** - The indexer then hands the prepared data and the
+   tokenizer information back to the database via an `INSERT` statement which
+   also sets the indexed_status to `0`. This triggers the update triggers
+   `placex_update`/`osmline_update` which do the work of computing address
+   parts and filling all the search tables.
+
+When computing the address terms of a place, Nominatim relies on the processed
+search names of all the address parts. That is why places are processed in rank
+order, from smallest rank to largest. To ensure correct handling of linked
+place nodes, administrative boundaries are processed before all other places.
+
+Apart from these restrictions, each place can be indexed independently
+from the others. This allows a large degree of parallelization during the indexing.
+It also means that the indexing process can be interrupted at any time and
+will simply pick up where it left of when restarted.
+
+### Data preparation
+
+The data preparation step computes and retrieves all data for a place that
+might be needed for the next step of processing the search name. That includes
+
+* location information (country code)
+* place classification (class, type, ranks)
+* names (including names of linked places)
+* address information (`addr:*` tags)
+
+Data preparation is implemented in pl/PgSQL mostly in the functions
+`placex_indexing_prepare()` and `get_interpolation_address()`.
+
+#### `addr:*` tag inheritance
+
+Nominatim has limited support for inheriting address tags from a building
+to POIs inside the building. This only works when the address tags are on the
+building outline. Any rank 30 object inside such a building or on its outline
+inherits all address tags when it does not have any address tags of its own.
+
+The inheritance is computed in the data preparation step.
+
+### Search name processing
+
+The prepared place information is handed to the tokenizer next. This is a
+Python module responsible for processing the names  from both name and address
+terms and building up the word index from them. The process is explained in
+more detail in the [Tokenizer chapter](Tokenizers.md).
+
+### Address processing
+
+Finally, the preprocessed place information and the results of the search name
+processing are written back to the database. At this point the update trigger
+of the placex/location_property_osmline tables take over and fill all the
+dependent tables. This makes up the most work-intensive part of the indexing.
+
+Nominatim distinguishes between dependent and independent places.
+**Dependent places** are all places on rank 30: house numbers, POIs etc. These
+places don't have a full address of their own. Instead they are attached to
+a parent street or place and use the information of the parent for searching
+and displaying information. Everything else are **independent places**: streets,
+parks, water bodies, suburbs, cities, states etc.  They receive a full address
+on their own.
+
+The address processing for both types of places is very different.
+
+#### Independent places
+
+To compute the address of an independent place Nominatim searches for all
+places that cover the place to compute the address for at least partially.
+For places with an area, that area is used to check for coverage. For place
+nodes an artificial square area is computed according to the rank of
+the place. The lower the rank the lager the area. The `location_area_large_X`
+tables are there to facilitate the lookup. All places that can function as
+the address of another place are saved in those tables.
+
+`addr:*` and `isin:*` tags are taken into account to compute the address, too.
+Nominatim will give preference to places with the same name as in these tags
+when looking for places in the vicinity. If there are no matching place names
+at all, then the tags are at least added to the search index. That means that
+the names will not be shown in the result as the 'address' of the place, but
+searching by them still works.
+
+Independent places are always added to the global search index `search_name`.
+
+#### Dependent places
+
+Dependent places skip the full address computation for performance reasons.
+Instead they just find a parent place to attach themselves to.
+
+![parenting of dependent places](parenting-flow.svg)
+
+By default a POI
+or house number will be attached to the closest street. That can be any major
+or minor street indexed by Nominatim. In the default configuration that means
+that it can attach itself to a footway but only when it has a name.
+
+When the dependent place has an `addr:street` tag, then Nominatim will first
+try to find a street with the same name before falling back to the closest
+street.
+
+There are also addresses in OSM, where the housenumber does not belong
+to a street at all. These have an `addr:place` tag. For these places, Nominatim
+tries to find a place with the given name in the indexed places with an
+address rank between 16 and 25. If none is found, then the dependent place
+is attached to the closest place in that category and the addr:place name is
+added as *unlisted* place, which indicates to Nominatim that it needs to add
+it to the address output, no matter what. This special case is necessary to
+cover addresses that don't really refer to an existing object.
+
+When an address has both the `addr:street` and `addr:place` tag, then Nominatim
+assumes that the `addr:place` tag in fact should be the city part of the address
+and give the POI the usual street number address.
+
+Dependent places are only added to the global search index `search_name` when
+they have either a name themselves or when they have address tags that are not
+covered by the places that make up their address. The latter ensures that
+addresses are always searchable by those address tags.
+

docs/develop/Postcodes.md

@@ -1,45 +0,0 @@
-# Postcodes in Nominatim
-
-The blog post
-[Nominatim and Postcodes](https://www.openstreetmap.org/user/lonvia/diary/43143)
-describes the handling implemented since Nominatim 3.1.
-
-Postcode centroids (aka 'calculated postcodes') are generated by looking at all
-postcodes of a country, grouping them and calculating the geometric centroid.
-There is currently no logic to deal with extreme outliers (typos or other
-mistakes in OSM data). There is also no check if a postcodes adheres to a
-country's format, e.g. if Swiss postcodes are 4 digits.
-
-
-## Regular updating calculated postcodes
-
-The script to rerun the calculation is
-`nominatim refresh --postcodes`
-and runs once per night on nominatim.openstreetmap.org.
-
-
-## Finding places that share a specific postcode
-
-In the Nominatim database run
-
-```sql
-SELECT address->'postcode' as pc,
-       osm_type, osm_id, class, type,
-       st_x(centroid) as lon, st_y(centroid) as lat
-FROM placex
-WHERE country_code='fr'
-  AND upper(trim (both ' ' from address->'postcode')) = '33210';
-```
-
-Alternatively on [Overpass](https://overpass-turbo.eu/) run the following query
-
-```
-[out:json][timeout:250];
-area["name"="France"]->.boundaryarea;
-(
-nwr(area.boundaryarea)["addr:postcode"="33210"];
-);
-out body;
->;
-out skel qt;
-```

docs/develop/Testing.md

@@ -22,8 +22,8 @@ This test directory is sturctured as follows:
   |
   +-   php         PHP unit tests
   +-   python      Python unit tests
-  +-   scenes      Geometry test data
   +-   testdb      Base data for generating API test database
+  +-   testdata    Additional test data used by unit tests
 ```
 
 ## PHP Unit Tests (`test/php`)

docs/develop/Tokenizers.md

@@ -0,0 +1,332 @@
+# Tokenizers
+
+The tokenizer is the component of Nominatim that is responsible for
+analysing names of OSM objects and queries. Nominatim provides different
+tokenizers that use different strategies for normalisation. This page describes
+how tokenizers are expected to work and the public API that needs to be
+implemented when creating a new tokenizer. For information on how to configure
+a specific tokenizer for a database see the
+[tokenizer chapter in the Customization Guide](../customize/Tokenizers.md).
+
+## Generic Architecture
+
+### About Search Tokens
+
+Search in Nominatim is organised around search tokens. Such a token represents
+string that can be part of the search query. Tokens are used so that the search
+index does not need to be organised around strings. Instead the database saves
+for each place which tokens match this place's name, address, house number etc.
+To be able to distinguish between these different types of information stored
+with the place, a search token also always has a certain type: name, house number,
+postcode etc.
+
+During search an incoming query is transformed into a ordered list of such
+search tokens (or rather many lists, see below) and this list is then converted
+into a database query to find the right place.
+
+It is the core task of the tokenizer to create, manage and assign the search
+tokens. The tokenizer is involved in two distinct operations:
+
+* __at import time__: scanning names of OSM objects, normalizing them and
+  building up the list of search tokens.
+* __at query time__: scanning the query and returning the appropriate search
+  tokens.
+
+
+### Importing
+
+The indexer is responsible to enrich an OSM object (or place) with all data
+required for geocoding. It is split into two parts: the controller collects
+the places that require updating, enriches the place information as required
+and hands the place to Postgresql. The collector is part of the Nominatim
+library written in Python. Within Postgresql, the `placex_update`
+trigger is responsible to fill out all secondary tables with extra geocoding
+information. This part is written in PL/pgSQL.
+
+The tokenizer is involved in both parts. When the indexer prepares a place,
+it hands it over to the tokenizer to inspect the names and create all the
+search tokens applicable for the place. This usually involves updating the
+tokenizer's internal token lists and creating a list of all token IDs for
+the specific place. This list is later needed in the PL/pgSQL part where the
+indexer needs to add the token IDs to the appropriate search tables. To be
+able to communicate the list between the Python part and the pl/pgSQL trigger,
+the `placex` table contains a special JSONB column `token_info` which is there
+for the exclusive use of the tokenizer.
+
+The Python part of the tokenizer returns a structured information about the
+tokens of a place to the indexer which converts it to JSON and inserts it into
+the `token_info` column. The content of the column is then handed to the PL/pqSQL
+callbacks of the tokenizer which extracts the required information. Usually
+the tokenizer then removes all information from the `token_info` structure,
+so that no information is ever persistently saved in the table. All information
+that went in should have been processed after all and put into secondary tables.
+This is however not a hard requirement. If the tokenizer needs to store
+additional information about a place permanently, it may do so in the
+`token_info` column. It just may never execute searches over it and
+consequently not create any special indexes on it.
+
+### Querying
+
+At query time, Nominatim builds up multiple _interpretations_ of the search
+query. Each of these interpretations is tried against the database in order
+of the likelihood with which they match to the search query. The first
+interpretation that yields results wins.
+
+The interpretations are encapsulated in the `SearchDescription` class. An
+instance of this class is created by applying a sequence of
+_search tokens_ to an initially empty SearchDescription. It is the
+responsibility of the tokenizer to parse the search query and derive all
+possible sequences of search tokens. To that end the tokenizer needs to parse
+the search query and look up matching words in its own data structures.
+
+## Tokenizer API
+
+The following section describes the functions that need to be implemented
+for a custom tokenizer implementation.
+
+!!! warning
+    This API is currently in early alpha status. While this API is meant to
+    be a public API on which other tokenizers may be implemented, the API is
+    far away from being stable at the moment.
+
+### Directory Structure
+
+Nominatim expects two files for a tokenizer:
+
+* `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
+
+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
+the `settings/<NAME>_tokenizer.<SUFFIX>`.
+
+### Configuration and Persistence
+
+Tokenizers may define custom settings for their configuration. All settings
+must be prefixed with `NOMINATIM_TOKENIZER_`. Settings may be transient or
+persistent. Transient settings are loaded from the configuration file when
+Nominatim is started and may thus be changed at any time. Persistent settings
+are tied to a database installation and must only be read during installation
+time. If they are needed for the runtime then they must be saved into the
+`nominatim_properties` table and later loaded from there.
+
+### The Python module
+
+The Python module is expect to export a single factory function:
+
+```python
+def create(dsn: str, data_dir: Path) -> AbstractTokenizer
+```
+
+The `dsn` parameter contains the DSN of the Nominatim database. The `data_dir`
+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.
+
+### Python Tokenizer Class
+
+All tokenizers must inherit from `nominatim.tokenizer.base.AbstractTokenizer`
+and implement the abstract functions defined there.
+
+::: nominatim.tokenizer.base.AbstractTokenizer
+    rendering:
+        heading_level: 4
+
+### Python Analyzer Class
+
+::: nominatim.tokenizer.base.AbstractAnalyzer
+    rendering:
+        heading_level: 4
+
+### PL/pgSQL Functions
+
+The tokenizer must provide access functions for the `token_info` column
+to the indexer which extracts the necessary information for the global
+search tables. If the tokenizer needs additional SQL functions for private
+use, then these functions must be prefixed with `token_` in order to ensure
+that there are no naming conflicts with the SQL indexer code.
+
+The following functions are expected:
+
+```sql
+FUNCTION token_get_name_search_tokens(info JSONB) RETURNS INTEGER[]
+```
+
+Return an array of token IDs of search terms that should match
+the name(s) for the given place. These tokens are used to look up the place
+by name and, where the place functions as part of an address for another place,
+by address. Must return NULL when the place has no name.
+
+```sql
+FUNCTION token_get_name_match_tokens(info JSONB) RETURNS INTEGER[]
+```
+
+Return an array of token IDs of full names of the place that should be used
+to match addresses. The list of match tokens is usually more strict than
+search tokens as it is used to find a match between two OSM tag values which
+are expected to contain matching full names. Partial terms should not be
+used for match tokens. Must return NULL when the place has no name.
+
+```sql
+FUNCTION token_get_housenumber_search_tokens(info JSONB) RETURNS INTEGER[]
+```
+
+Return an array of token IDs of house number tokens that apply to the place.
+Note that a place may have multiple house numbers, for example when apartments
+each have their own number. Must be NULL when the place has no house numbers.
+
+```sql
+FUNCTION token_normalized_housenumber(info JSONB) RETURNS TEXT
+```
+
+Return the house number(s) in the normalized form that can be matched against
+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_matches_street(info JSONB, street_tokens INTEGER[]) RETURNS BOOLEAN
+```
+
+Check if the given tokens (previously saved from `token_get_name_match_tokens()`)
+match against the `addr:street` tag name. Must return either NULL or FALSE
+when the place has no `addr:street` tag.
+
+```sql
+FUNCTION token_matches_place(info JSONB, place_tokens INTEGER[]) RETURNS BOOLEAN
+```
+
+Check if the given tokens (previously saved from `token_get_name_match_tokens()`)
+match against the `addr:place` tag name. Must return either NULL or FALSE
+when the place has no `addr:place` tag.
+
+
+```sql
+FUNCTION token_addr_place_search_tokens(info JSONB) RETURNS INTEGER[]
+```
+
+Return the search token IDs extracted from the `addr:place` tag. These tokens
+are used for searches by address when no matching place can be found in the
+database. Must be NULL when the place has no `addr:place` tag.
+
+```sql
+FUNCTION token_get_address_keys(info JSONB) RETURNS SETOF TEXT
+```
+
+Return the set of keys for which address information is provided. This
+should correspond to the list of (relevant) `addr:*` tags with the `addr:`
+prefix removed or the keys used in the `address` dictionary of the place info.
+
+```sql
+FUNCTION token_get_address_search_tokens(info JSONB, key TEXT) RETURNS INTEGER[]
+```
+
+Return the array of search tokens for the given address part. `key` can be
+expected to be one of those returned with `token_get_address_keys()`. The
+search tokens are added to the address search vector of the place, when no
+corresponding OSM object could be found for the given address part from which
+to copy the name information.
+
+```sql
+FUNCTION token_matches_address(info JSONB, key TEXT, tokens INTEGER[])
+```
+
+Check if the given tokens match against the address part `key`.
+
+__Warning:__ the tokens that are handed in are the lists previously saved
+from `token_get_name_search_tokens()`, _not_ from the match token list. This
+is an historical oddity which will be fixed at some point in the future.
+Currently, tokenizers are encouraged to make sure that matching works against
+both the search token list and the match token list.
+
+```sql
+FUNCTION token_get_postcode(info JSONB) RETURNS TEXT
+```
+
+Return the postcode for the object, if any exists. The postcode must be in
+the form that should also be presented to the end-user.
+
+```sql
+FUNCTION token_strip_info(info JSONB) RETURNS JSONB
+```
+
+Return the part of the `token_info` field that should be stored in the database
+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.
+

docs/develop/address-tables.plantuml

@@ -0,0 +1,35 @@
+@startuml
+skinparam monochrome true
+skinparam ObjectFontStyle bold
+
+map search_name_X {
+  place_id => BIGINT
+  address_rank => SMALLINT
+  name_vector => INT[]
+  centroid => GEOMETRY
+}
+
+map location_area_large_X {
+  place_id => BIGINT
+  keywords => INT[]
+  partition => SMALLINT
+  rank_search => SMALLINT
+  rank_address => SMALLINT
+  country_code => VARCHR(2)
+  isguess => BOOLEAN
+  postcode => TEXT
+  centroid => POINT
+  geometry => GEOMETRY
+}
+
+map location_road_X {
+  place_id => BIGINT
+  partition => SMALLINT
+  country_code => VARCHR(2)
+  geometry => GEOMETRY
+}
+
+search_name_X -[hidden]> location_area_large_X
+location_area_large_X -[hidden]> location_road_X
+
+@enduml

docs/develop/data-sources.md

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

docs/develop/osm2pgsql-tables.plantuml

@@ -0,0 +1,44 @@
+@startuml
+skinparam monochrome true
+skinparam ObjectFontStyle bold
+
+map planet_osm_nodes #eee {
+  id => BIGINT
+  lat => INT
+  lon => INT
+}
+
+map planet_osm_ways #eee {
+  id => BIGINT
+  nodes => BIGINT[]
+  tags => TEXT[]
+}
+
+map planet_osm_rels #eee {
+  id => BIGINT
+  parts => BIGINT[]
+  members => TEXT[]
+  tags => TEXT[]
+  way_off => SMALLINT
+  rel_off => SMALLINT
+}
+
+map place {
+  osm_type => CHAR(1)
+  osm_id => BIGINT
+  class => TEXT
+  type => TEXT
+  name => HSTORE
+  address => HSTORE
+  extratags => HSTORE
+  admin_level => SMALLINT
+  geometry => GEOMETRY
+}
+
+planet_osm_nodes  -[hidden]> planet_osm_ways
+planet_osm_ways  -[hidden]> planet_osm_rels
+planet_osm_ways -[hidden]-> place
+
+planet_osm_nodes::id <- planet_osm_ways::nodes
+
+@enduml

docs/develop/parenting-flow.plantuml

@@ -0,0 +1,31 @@
+@startuml
+skinparam monochrome true
+
+start
+
+if (has 'addr:street'?) then (yes)
+  if (street with that name\n nearby?) then (yes)
+    :**Use closest street**
+     **with same name**;
+     kill
+  else (no)
+    :** Use closest**\n**street**;
+     kill
+  endif
+elseif (has 'addr:place'?) then (yes)
+  if (place with that name\n nearby?) then (yes)
+    :**Use closest place**
+     **with same name**;
+     kill
+  else (no)
+    :add addr:place to adress;
+    :**Use closest place**\n**rank 16 to 25**;
+     kill
+  endif
+else (otherwise)
+ :**Use closest**\n**street**;
+ kill
+endif
+
+
+@enduml

docs/develop/search-tables.plantuml

@@ -0,0 +1,99 @@
+@startuml
+skinparam monochrome true
+skinparam ObjectFontStyle bold
+
+left to right direction
+
+map placex {
+  place_id => BIGINT
+  osm_type => CHAR(1)
+  osm_id => BIGINT
+  class => TEXT
+  type => TEXT
+  name => HSTORE
+  address => HSTORE
+  extratags => HSTORE
+  admin_level => SMALLINT
+  partition => SMALLINT
+  geometry_sector => INT
+  parent_place_id => BIGINT
+  linked_place_id => BIGINT
+  importance => DOUBLE
+  rank_search => SMALLINT
+  rank_address => SMALLINT
+  wikipedia => TEXT
+  country_code => VARCHAR(2)
+  housenumber => TEXT
+  postcode => TEXT
+  indexed_status => SMALLINT
+  indexed_date => TIMESTAMP
+  centroid => GEOMETRY
+  geometry => GEOMETRY
+}
+
+map search_name {
+  place_id => BIGINT
+  importance => DOUBLE
+  search_rank => SMALLINT
+  address_rank => SMALLINT
+  name_vector => INT[]
+  nameaddress_vector => INT[]
+  country_code => VARCHAR(2)
+  centroid => GEOMETRY
+}
+
+map word {
+  word_id => INT
+  word_token => TEXT
+  ... =>
+}
+
+map location_property_osmline {
+  place_id => BIGINT
+  osm_id => BIGINT
+  startnumber => INT
+  endnumber => INT
+  interpolationtype => TEXT
+  address => HSTORE
+  partition => SMALLINT
+  geometry_sector => INT
+  parent_place_id => BIGINT
+  country_code => VARCHAR(2)
+  postcode => text
+  indexed_status => SMALLINT
+  indexed_date => TIMESTAMP
+  linegeo => GEOMETRY
+}
+
+map place_addressline {
+  place_id => BIGINT
+  address_place_id => BIGINT
+  distance => DOUBLE
+  cached_rank_address => SMALLINT
+  fromarea => BOOLEAN
+  isaddress => BOOLEAN
+}
+
+map location_postcode {
+  place_id => BIGINT
+  postcode => TEXT
+  parent_place_id => BIGINT
+  rank_search => SMALLINT
+  rank_address => SMALLINT
+  indexed_status => SMALLINT
+  indexed_date => TIMESTAMP
+  geometry => GEOMETRY
+}
+
+placex::place_id <-- search_name::place_id
+placex::place_id <-- place_addressline::place_id
+placex::place_id <-- place_addressline::address_place_id
+
+search_name::name_vector --> word::word_id
+search_name::nameaddress_vector --> word::word_id
+
+place_addressline -[hidden]> location_property_osmline
+search_name -[hidden]> place_addressline
+location_property_osmline -[hidden]-> location_postcode
+
+@enduml

docs/extra.css

@@ -13,3 +13,12 @@ th, td {
 th {
     background-color: #eee;
 }
+
+.doc-object h6 {
+    margin-bottom: 0.8em;
+    font-size: 120%;
+}
+
+.doc-object {
+    margin-bottom: 1.3em;
+}

docs/index.md

@@ -1,8 +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).
 
-This guide comes in three 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
  * __[Developer's Guide](develop/overview.md)__ for developers of the software

docs/mkdocs.yml

@@ -3,7 +3,7 @@ theme: readthedocs
 docs_dir: ${CMAKE_CURRENT_BINARY_DIR}
 site_url: https://nominatim.org
 repo_url: https://github.com/openstreetmap/Nominatim
-pages:
+nav:
     - 'Introduction' : 'index.md'
     - 'API Reference':
         - 'Overview': 'api/Overview.md'
@@ -19,28 +19,47 @@ pages:
         - 'Import' : 'admin/Import.md'
         - 'Update' : 'admin/Update.md'
         - 'Deploy' : 'admin/Deployment.md'
-        - 'Customize Imports' : 'admin/Customization.md'
-        - 'Tokenizers' : 'admin/Tokenizers.md'
         - 'Nominatim UI'  : 'admin/Setup-Nominatim-UI.md'
         - 'Advanced Installations' : 'admin/Advanced-Installations.md'
+        - 'Maintenance' : 'admin/Maintenance.md'
         - 'Migration from older Versions' : 'admin/Migration.md'
         - 'Troubleshooting' : 'admin/Faq.md'
+    - 'Customization Guide':
+        - 'Overview': 'customize/Overview.md'
+        - 'Import Styles': 'customize/Import-Styles.md'
+        - 'Configuration Settings': 'customize/Settings.md'
+        - 'Per-Country Data': 'customize/Country-Settings.md'
+        - 'Place Ranking' : 'customize/Ranking.md'
+        - 'Importance' : 'customize/Importance.md'
+        - 'Tokenizers' : 'customize/Tokenizers.md'
+        - 'Special Phrases': 'customize/Special-Phrases.md'
+        - 'External data: US housenumbers from TIGER': 'customize/Tiger.md'
+        - 'External data: Postcodes': 'customize/Postcodes.md'
     - 'Developers Guide':
-        - 'Setup for Development' : 'develop/Development-Environment.md'
         - 'Architecture Overview' : 'develop/overview.md'
-        - 'OSM Data Import' : 'develop/Import.md'
-        - 'Place Ranking' : 'develop/Ranking.md'
-        - 'Postcodes' : 'develop/Postcodes.md'
+        - 'Database Layout' : 'develop/Database-Layout.md'
+        - 'Indexing' : 'develop/Indexing.md'
+        - 'Tokenizers' : 'develop/Tokenizers.md'
+        - 'Custom modules for ICU tokenizer': 'develop/ICU-Tokenizer-Modules.md'
+        - 'Setup for Development' : 'develop/Development-Environment.md'
         - 'Testing' : 'develop/Testing.md'
         - 'External Data Sources': 'develop/data-sources.md'
     - 'Appendix':
-        - 'Installation on CentOS 7' : 'appendix/Install-on-Centos-7.md'
-        - 'Installation on CentOS 8' : 'appendix/Install-on-Centos-8.md'
         - 'Installation on Ubuntu 18' : 'appendix/Install-on-Ubuntu-18.md'
         - 'Installation on Ubuntu 20' : 'appendix/Install-on-Ubuntu-20.md'
+        - 'Installation on Ubuntu 22' : 'appendix/Install-on-Ubuntu-22.md'
 markdown_extensions:
     - codehilite
     - admonition
+    - def_list
     - toc:
         permalink: 
 extra_css: [extra.css, styles.css]
+plugins:
+    - search
+    - mkdocstrings:
+        handlers:
+          python-legacy:
+            rendering:
+              show_source: false
+              show_signature_annotations: false

lib-php/AddressDetails.php

@@ -1,4 +1,12 @@
 <?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;
 
@@ -84,6 +92,10 @@ class AddressDetails
                     || $aLine['class'] == 'place')
             ) {
                 $aAddress[$sTypeLabel] = $sName;
+
+                if (!empty($aLine['name'])) {
+                    $this->addSubdivisionCode($aAddress, $aLine['admin_level'], $aLine['name']);
+                }
             }
         }
 
@@ -166,4 +178,14 @@ class AddressDetails
     {
         return $this->aAddressLines;
     }
+
+    private function addSubdivisionCode(&$aAddress, $iAdminLevel, $nameDetails)
+    {
+        if (is_string($nameDetails)) {
+            $nameDetails = json_decode('{' . str_replace('"=>"', '":"', $nameDetails) . '}', true);
+        }
+        if (!empty($nameDetails['ISO3166-2'])) {
+            $aAddress["ISO3166-2-lvl$iAdminLevel"] = $nameDetails['ISO3166-2'];
+        }
+    }
 }

lib-php/ClassTypes.php

@@ -1,4 +1,12 @@
 <?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;
 

lib-php/DB.php

@@ -1,4 +1,12 @@
 <?php
+/**
+ * SPDX-License-Identifier: GPL-2.0-only
+ *
+ * This file is part of Nominatim. (https://nominatim.org)
+ *
+ * Copyright (C) 2022 by the Nominatim developer community.
+ * For a full list of authors see the git log.
+ */
 
 namespace Nominatim;
 
@@ -38,6 +46,9 @@ class DB
 
         $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

lib-php/DatabaseError.php

@@ -1,4 +1,12 @@
 <?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;
 

lib-php/DebugHtml.php

@@ -1,4 +1,12 @@
 <?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;
 
@@ -127,7 +135,7 @@ class Debug
 
     public static function printSQL($sSQL)
     {
-        echo '<p><tt><font color="#aaa">'.$sSQL.'</font></tt></p>'."\n";
+        echo '<p><tt><font color="#aaa">'.htmlspecialchars($sSQL, ENT_QUOTES | ENT_SUBSTITUTE | ENT_HTML401).'</font></tt></p>'."\n";
     }
 
     private static function outputVar($mVar, $sPreNL)
@@ -170,11 +178,12 @@ class Debug
         }
 
         if (is_string($mVar)) {
-            echo "'$mVar'";
-            return strlen($mVar) + 2;
+            $sOut = "'$mVar'";
+        } else {
+            $sOut = (string)$mVar;
         }
 
-        echo (string)$mVar;
-        return strlen((string)$mVar);
+        echo htmlspecialchars($sOut, ENT_QUOTES | ENT_SUBSTITUTE | ENT_HTML401);
+        return strlen($sOut);
     }
 }

lib-php/DebugNone.php

@@ -1,4 +1,12 @@
 <?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;
 

lib-php/Geocode.php

@@ -1,4 +1,12 @@
 <?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;
 
@@ -95,7 +103,7 @@ class Geocode
         }
 
         $this->iFinalLimit = $iLimit;
-        $this->iLimit = $iLimit + min($iLimit, 10);
+        $this->iLimit = $iLimit + max($iLimit, 10);
     }
 
     public function setFeatureType($sFeatureType)
@@ -182,7 +190,7 @@ class Geocode
 
         $this->bFallback = $oParams->getBool('fallback', $this->bFallback);
 
-        // List of excluded Place IDs - used for more acurate pageing
+        // List of excluded Place IDs - used for more accurate pageing
         $sExcluded = $oParams->getStringList('exclude_place_ids');
         if ($sExcluded) {
             foreach ($sExcluded as $iExcludedPlaceID) {
@@ -498,7 +506,6 @@ class Geocode
         if ($this->aCountryCodes) {
             $oCtx->setCountryList($this->aCountryCodes);
         }
-        $this->oTokenizer->setCountryRestriction($this->aCountryCodes);
 
         Debug::newSection('Query Preprocessing');
 
@@ -507,13 +514,6 @@ class Geocode
             userError('Query string is not UTF-8 encoded.');
         }
 
-        // Conflicts between US state abreviations and various words for 'the' in different languages
-        if (isset($this->aLangPrefOrder['name:en'])) {
-            $sQuery = preg_replace('/(^|,)\s*il\s*(,|$)/i', '\1illinois\2', $sQuery);
-            $sQuery = preg_replace('/(^|,)\s*al\s*(,|$)/i', '\1alabama\2', $sQuery);
-            $sQuery = preg_replace('/(^|,)\s*la\s*(,|$)/i', '\1louisiana\2', $sQuery);
-        }
-
         // Do we have anything that looks like a lat/lon pair?
         $sQuery = $oCtx->setNearPointFromQuery($sQuery);
 
@@ -617,16 +617,15 @@ class Geocode
                     }
                     $aReverseGroupedSearches = $this->getGroupedSearches($aSearches, $aPhrases, $oValidTokens);
 
-                    foreach ($aGroupedSearches as $aSearches) {
+                    foreach ($aReverseGroupedSearches as $aSearches) {
                         foreach ($aSearches as $aSearch) {
-                            if (!isset($aReverseGroupedSearches[$aSearch->getRank()])) {
-                                $aReverseGroupedSearches[$aSearch->getRank()] = array();
+                            if (!isset($aGroupedSearches[$aSearch->getRank()])) {
+                                $aGroupedSearches[$aSearch->getRank()] = array();
                             }
-                            $aReverseGroupedSearches[$aSearch->getRank()][] = $aSearch;
+                            $aGroupedSearches[$aSearch->getRank()][] = $aSearch;
                         }
                     }
 
-                    $aGroupedSearches = $aReverseGroupedSearches;
                     ksort($aGroupedSearches);
                 }
             } else {
@@ -844,7 +843,9 @@ class Geocode
                 $aResult['importance'] = 0.001;
                 $aResult['foundorder'] = $aResult['addressimportance'];
             } else {
-                $aResult['importance'] = max(0.001, $aResult['importance']);
+                if ($aResult['importance'] == 0) {
+                    $aResult['importance'] = 0.0001;
+                }
                 $aResult['importance'] *= $this->viewboxImportanceFactor(
                     $aResult['lon'],
                     $aResult['lat']
@@ -873,7 +874,7 @@ class Geocode
                 $iCountWords = 0;
                 $sAddress = $aResult['langaddress'];
                 foreach ($aRecheckWords as $i => $sWord) {
-                    if (stripos($sAddress, $sWord)!==false) {
+                    if (grapheme_stripos($sAddress, $sWord)!==false) {
                         $iCountWords++;
                         if (preg_match('/(^|,)\s*'.preg_quote($sWord, '/').'\s*(,|$)/', $sAddress)) {
                             $iCountWords += 0.1;

lib-php/ParameterParser.php

@@ -1,4 +1,12 @@
 <?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;
 
@@ -14,7 +22,10 @@ class ParameterParser
 
     public function getBool($sName, $bDefault = false)
     {
-        if (!isset($this->aParams[$sName]) || strlen($this->aParams[$sName]) == 0) {
+        if (!isset($this->aParams[$sName])
+            || !is_string($this->aParams[$sName])
+            || strlen($this->aParams[$sName]) == 0
+        ) {
             return $bDefault;
         }
 
@@ -23,7 +34,7 @@ class ParameterParser
 
     public function getInt($sName, $bDefault = false)
     {
-        if (!isset($this->aParams[$sName])) {
+        if (!isset($this->aParams[$sName]) || is_array($this->aParams[$sName])) {
             return $bDefault;
         }
 
@@ -36,7 +47,7 @@ class ParameterParser
 
     public function getFloat($sName, $bDefault = false)
     {
-        if (!isset($this->aParams[$sName])) {
+        if (!isset($this->aParams[$sName]) || is_array($this->aParams[$sName])) {
             return $bDefault;
         }
 
@@ -49,7 +60,10 @@ class ParameterParser
 
     public function getString($sName, $bDefault = false)
     {
-        if (!isset($this->aParams[$sName]) || strlen($this->aParams[$sName]) == 0) {
+        if (!isset($this->aParams[$sName])
+            || !is_string($this->aParams[$sName])
+            || strlen($this->aParams[$sName]) == 0
+        ) {
             return $bDefault;
         }
 
@@ -58,11 +72,14 @@ class ParameterParser
 
     public function getSet($sName, $aValues, $sDefault = false)
     {
-        if (!isset($this->aParams[$sName]) || strlen($this->aParams[$sName]) == 0) {
+        if (!isset($this->aParams[$sName])
+            || !is_string($this->aParams[$sName])
+            || strlen($this->aParams[$sName]) == 0
+        ) {
             return $sDefault;
         }
 
-        if (!in_array($this->aParams[$sName], $aValues)) {
+        if (!in_array($this->aParams[$sName], $aValues, true)) {
             userError("Parameter '$sName' must be one of: ".join(', ', $aValues));
         }
 
@@ -106,21 +123,27 @@ class ParameterParser
         }
 
         foreach ($aLanguages as $sLanguage => $fLanguagePref) {
-            $aLangPrefOrder['name:'.$sLanguage] = 'name:'.$sLanguage;
+            $this->addNameTag($aLangPrefOrder, 'name:'.$sLanguage);
         }
-        $aLangPrefOrder['name'] = 'name';
-        $aLangPrefOrder['brand'] = 'brand';
+        $this->addNameTag($aLangPrefOrder, 'name');
+        $this->addNameTag($aLangPrefOrder, 'brand');
         foreach ($aLanguages as $sLanguage => $fLanguagePref) {
-            $aLangPrefOrder['official_name:'.$sLanguage] = 'official_name:'.$sLanguage;
-            $aLangPrefOrder['short_name:'.$sLanguage] = 'short_name:'.$sLanguage;
+            $this->addNameTag($aLangPrefOrder, 'official_name:'.$sLanguage);
+            $this->addNameTag($aLangPrefOrder, 'short_name:'.$sLanguage);
         }
-        $aLangPrefOrder['official_name'] = 'official_name';
-        $aLangPrefOrder['short_name'] = 'short_name';
-        $aLangPrefOrder['ref'] = 'ref';
-        $aLangPrefOrder['type'] = 'type';
+        $this->addNameTag($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) {

lib-php/Phrase.php

@@ -1,4 +1,12 @@
 <?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;
 
@@ -9,29 +17,14 @@ namespace Nominatim;
  */
 class Phrase
 {
-    const MAX_WORDSET_LEN = 20;
-    const MAX_WORDSETS = 100;
-
-    // Complete phrase as a string.
+    // 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 static function cmpByArraylen($aA, $aB)
-    {
-        $iALen = count($aA);
-        $iBLen = count($aB);
-
-        if ($iALen == $iBLen) {
-            return 0;
-        }
-
-        return ($iALen < $iBLen) ? -1 : 1;
-    }
-
-
     public function __construct($sPhrase, $sPhraseType)
     {
         $this->sPhrase = trim($sPhrase);
@@ -39,7 +32,7 @@ class Phrase
     }
 
     /**
-     * Get the orginal phrase of the string.
+     * Get the original phrase of the string.
      */
     public function getPhrase()
     {
@@ -57,6 +50,11 @@ class Phrase
         return $this->sPhraseType;
     }
 
+    public function setWordSets($aWordSets)
+    {
+        $this->aWordSets = $aWordSets;
+    }
+
     /**
      * Return the array of possible segmentations of the phrase.
      *
@@ -80,61 +78,6 @@ class Phrase
         }
     }
 
-    public function computeWordSets($aWords, $oTokens)
-    {
-        $iNumWords = count($aWords);
-
-        if ($iNumWords == 0) {
-            $this->aWordSets = null;
-            return;
-        }
-
-        // Caches the word set for the partial phrase up to word i.
-        $aSetCache = array_fill(0, $iNumWords, array());
-
-        // Initialise first element of cache. There can only be the word.
-        if ($oTokens->containsAny($aWords[0])) {
-            $aSetCache[0][] = array($aWords[0]);
-        }
-
-        // Now do the next elements using what we already have.
-        for ($i = 1; $i < $iNumWords; $i++) {
-            for ($j = $i; $j > 0; $j--) {
-                $sPartial = $j == $i ? $aWords[$j] : $aWords[$j].' '.$sPartial;
-                if (!empty($aSetCache[$j - 1]) && $oTokens->containsAny($sPartial)) {
-                    $aPartial = array($sPartial);
-                    foreach ($aSetCache[$j - 1] as $aSet) {
-                        if (count($aSet) < Phrase::MAX_WORDSET_LEN) {
-                            $aSetCache[$i][] = array_merge($aSet, $aPartial);
-                        }
-                    }
-                    if (count($aSetCache[$i]) > 2 * Phrase::MAX_WORDSETS) {
-                        usort(
-                            $aSetCache[$i],
-                            array('\Nominatim\Phrase', 'cmpByArraylen')
-                        );
-                        $aSetCache[$i] = array_slice(
-                            $aSetCache[$i],
-                            0,
-                            Phrase::MAX_WORDSETS
-                        );
-                    }
-                }
-            }
-
-            // finally the current full phrase
-            $sPartial = $aWords[0].' '.$sPartial;
-            if ($oTokens->containsAny($sPartial)) {
-                $aSetCache[$i][] = array($sPartial);
-            }
-        }
-
-        $this->aWordSets = $aSetCache[$iNumWords - 1];
-        usort($this->aWordSets, array('\Nominatim\Phrase', 'cmpByArraylen'));
-        $this->aWordSets = array_slice($this->aWordSets, 0, Phrase::MAX_WORDSETS);
-    }
-
-
     public function debugInfo()
     {
         return array(

lib-php/PlaceLookup.php

@@ -1,4 +1,12 @@
 <?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;
 
@@ -179,12 +187,12 @@ class PlaceLookup
             return null;
         }
 
-        $aResults = $this->lookup(array($iPlaceID => new Result($iPlaceID)));
+        $aResults = $this->lookup(array($iPlaceID => new Result($iPlaceID)), 0, 30, true);
 
         return empty($aResults) ? null : reset($aResults);
     }
 
-    public function lookup($aResults, $iMinRank = 0, $iMaxRank = 30)
+    public function lookup($aResults, $iMinRank = 0, $iMaxRank = 30, $bAllowLinked = false)
     {
         Debug::newFunction('Place lookup');
 
@@ -239,7 +247,9 @@ class PlaceLookup
             if ($this->sAllowedTypesSQLList) {
                 $sSQL .= 'AND placex.class in '.$this->sAllowedTypesSQLList;
             }
-            $sSQL .= '    AND linked_place_id is null ';
+            if (!$bAllowLinked) {
+                $sSQL .= '    AND linked_place_id is null ';
+            }
             $sSQL .= ' GROUP BY ';
             $sSQL .= '     osm_type, ';
             $sSQL .= '     osm_id, ';
@@ -340,7 +350,9 @@ class PlaceLookup
                     $sSQL .= '     null::text AS extra_place ';
                     $sSQL .= ' FROM (';
                     $sSQL .= '     SELECT place_id, ';    // interpolate the Tiger housenumbers here
-                    $sSQL .= '         ST_LineInterpolatePoint(linegeo, (housenumber_for_place-startnumber::float)/(endnumber-startnumber)::float) AS centroid, ';
+                    $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 (';
@@ -397,7 +409,7 @@ class PlaceLookup
                 $sSQL .= '         CASE ';             // interpolate the housenumbers here
                 $sSQL .= '           WHEN startnumber != endnumber ';
                 $sSQL .= '           THEN ST_LineInterpolatePoint(linegeo, (housenumber_for_place-startnumber::float)/(endnumber-startnumber)::float) ';
-                $sSQL .= '           ELSE ST_LineInterpolatePoint(linegeo, 0.5) ';
+                $sSQL .= '           ELSE linegeo ';
                 $sSQL .= '         END as centroid, ';
                 $sSQL .= '         parent_place_id, ';
                 $sSQL .= '         housenumber_for_place ';
@@ -435,18 +447,14 @@ class PlaceLookup
 
             if ($this->bExtraTags) {
                 if ($aPlace['extra']) {
-                    $aPlace['sExtraTags'] = json_decode($aPlace['extra']);
+                    $aPlace['sExtraTags'] = json_decode($aPlace['extra'], true);
                 } else {
                     $aPlace['sExtraTags'] = (object) array();
                 }
             }
 
             if ($this->bNameDetails) {
-                if ($aPlace['names']) {
-                    $aPlace['sNameDetails'] = json_decode($aPlace['names']);
-                } else {
-                    $aPlace['sNameDetails'] = (object) array();
-                }
+                $aPlace['sNameDetails'] = $this->extractNames($aPlace['names']);
             }
 
             $aPlace['addresstype'] = ClassTypes\getLabelTag(
@@ -469,6 +477,33 @@ class PlaceLookup
         return $aResults;
     }
 
+
+    private function extractNames($sNames)
+    {
+        if (!$sNames) {
+            return (object) array();
+        }
+
+        $aFullNames = json_decode($sNames, true);
+        $aNames = array();
+
+        foreach ($aFullNames as $sKey => $sValue) {
+            if (strpos($sKey, '_place_') === 0) {
+                $sSubKey = substr($sKey, 7);
+                if (array_key_exists($sSubKey, $aFullNames)) {
+                    $aNames[$sKey] = $sValue;
+                } else {
+                    $aNames[$sSubKey] = $sValue;
+                }
+            } else {
+                $aNames[$sKey] = $sValue;
+            }
+        }
+
+        return $aNames;
+    }
+
+
     /* returns an array which will contain the keys
      *   aBoundingBox
      * and may also contain one or more of the keys
@@ -479,8 +514,6 @@ class PlaceLookup
      *   lat
      *   lon
      */
-
-
     public function getOutlines($iPlaceID, $fLon = null, $fLat = null, $fRadius = null, $fLonReverse = null, $fLatReverse = null)
     {
 
@@ -491,12 +524,7 @@ class PlaceLookup
 
         // Get the bounding box and outline polygon
         $sSQL = 'select place_id,0 as numfeatures,st_area(geometry) as area,';
-        if ($fLonReverse != null && $fLatReverse != null) {
-            $sSQL .= ' ST_Y(closest_point) as centrelat,';
-            $sSQL .= ' ST_X(closest_point) as centrelon,';
-        } else {
-            $sSQL .= ' ST_Y(centroid) as centrelat, ST_X(centroid) as centrelon,';
-        }
+        $sSQL .= ' ST_Y(centroid) as centrelat, ST_X(centroid) as centrelon,';
         $sSQL .= ' ST_YMin(geometry) as minlat,ST_YMax(geometry) as maxlat,';
         $sSQL .= ' ST_XMin(geometry) as minlon,ST_XMax(geometry) as maxlon';
         if ($this->bIncludePolygonAsGeoJSON) {
@@ -511,19 +539,21 @@ class PlaceLookup
         if ($this->bIncludePolygonAsText) {
             $sSQL .= ',ST_AsText(geometry) as astext';
         }
+
+        $sSQL .= ' FROM (SELECT place_id';
         if ($fLonReverse != null && $fLatReverse != null) {
-            $sFrom = ' from (SELECT * , CASE WHEN (class = \'highway\') AND (ST_GeometryType(geometry) = \'ST_LineString\') THEN ';
-            $sFrom .=' ST_ClosestPoint(geometry, ST_SetSRID(ST_Point('.$fLatReverse.','.$fLonReverse.'),4326))';
-            $sFrom .=' ELSE centroid END AS closest_point';
-            $sFrom .= ' from placex where place_id = '.$iPlaceID.') as plx';
+            $sSQL .= ',CASE WHEN (class = \'highway\') AND (ST_GeometryType(geometry) = \'ST_LineString\') THEN ';
+            $sSQL .=' ST_ClosestPoint(geometry, ST_SetSRID(ST_Point('.$fLatReverse.','.$fLonReverse.'),4326))';
+            $sSQL .=' ELSE centroid END AS centroid';
         } else {
-            $sFrom = ' from placex where place_id = '.$iPlaceID;
+            $sSQL .= ',centroid';
         }
         if ($this->fPolygonSimplificationThreshold > 0) {
-            $sSQL .= ' from (select place_id,centroid,ST_SimplifyPreserveTopology(geometry,'.$this->fPolygonSimplificationThreshold.') as geometry'.$sFrom.') as plx';
+            $sSQL .= ',ST_SimplifyPreserveTopology(geometry,'.$this->fPolygonSimplificationThreshold.') as geometry';
         } else {
-            $sSQL .= $sFrom;
+            $sSQL .= ',geometry';
         }
+        $sSQL .= ' FROM placex where place_id = '.$iPlaceID.') as plx';
 
         $aPointPolygon = $this->oDB->getRow($sSQL, null, 'Could not get outline');
 

lib-php/Result.php

@@ -1,4 +1,12 @@
 <?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;
 

lib-php/ReverseGeocode.php

@@ -1,4 +1,12 @@
 <?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;
 
@@ -56,12 +64,15 @@ class ReverseGeocode
     {
         Debug::newFunction('lookupInterpolation');
         $sSQL = 'SELECT place_id, parent_place_id, 30 as rank_search,';
-        $sSQL .= '  ST_LineLocatePoint(linegeo,'.$sPointSQL.') as fraction,';
-        $sSQL .= '  startnumber, endnumber, interpolationtype,';
+        $sSQL .= '  (CASE WHEN endnumber != startnumber';
+        $sSQL .= '        THEN (endnumber - startnumber) * ST_LineLocatePoint(linegeo,'.$sPointSQL.')';
+        $sSQL .= '        ELSE startnumber END) as fhnr,';
+        $sSQL .= '  startnumber, endnumber, step,';
         $sSQL .= '  ST_Distance(linegeo,'.$sPointSQL.') as distance';
         $sSQL .= ' FROM location_property_osmline';
         $sSQL .= ' WHERE ST_DWithin('.$sPointSQL.', linegeo, '.$fSearchDiam.')';
-        $sSQL .= ' and indexed_status = 0 and startnumber is not NULL ';
+        $sSQL .= '       and indexed_status = 0 and startnumber is not NULL ';
+        $sSQL .= '       and parent_place_id != 0';
         $sSQL .= ' ORDER BY distance ASC limit 1';
         Debug::printSQL($sSQL);
 
@@ -111,6 +122,7 @@ class ReverseGeocode
                 $sSQL .= ' FROM placex';
                 $sSQL .= ' WHERE osm_type = \'N\'';
                 $sSQL .= ' AND country_code = \''.$sCountryCode.'\'';
+                $sSQL .= ' AND rank_search < 26 '; // needed to select right index
                 $sSQL .= ' AND rank_search between 5 and ' .min(25, $iMaxRank);
                 $sSQL .= ' AND class = \'place\' AND type != \'postcode\'';
                 $sSQL .= ' AND name IS NOT NULL ';
@@ -177,14 +189,16 @@ class ReverseGeocode
         $sSQL .= '(select place_id, parent_place_id, rank_address, rank_search, country_code, geometry';
         $sSQL .= ' FROM placex';
         $sSQL .= ' WHERE ST_GeometryType(geometry) in (\'ST_Polygon\', \'ST_MultiPolygon\')';
-        $sSQL .= ' AND rank_address Between 5 AND ' .$iMaxRank;
+        // Ensure that query planner doesn't use the index on rank_search.
+        $sSQL .= ' AND coalesce(rank_search, 0) between 5 and ' .$iMaxRank;
+        $sSQL .= ' AND rank_address between 4 and 25'; // needed for index selection
         $sSQL .= ' AND geometry && '.$sPointSQL;
         $sSQL .= ' AND type != \'postcode\' ';
         $sSQL .= ' AND name is not null';
         $sSQL .= ' AND indexed_status = 0 and linked_place_id is null';
-        $sSQL .= ' ORDER BY rank_address DESC LIMIT 50 ) as a';
-        $sSQL .= ' WHERE ST_CONTAINS(geometry, '.$sPointSQL.' )';
-        $sSQL .= ' ORDER BY rank_address DESC LIMIT 1';
+        $sSQL .= ' ORDER BY rank_search DESC LIMIT 50 ) as a';
+        $sSQL .= ' WHERE ST_Contains(geometry, '.$sPointSQL.' )';
+        $sSQL .= ' ORDER BY rank_search DESC LIMIT 1';
         Debug::printSQL($sSQL);
 
         $aPoly = $this->oDB->getRow($sSQL, null, 'Could not determine polygon containing the point.');
@@ -196,7 +210,7 @@ class ReverseGeocode
             $iRankSearch = $aPoly['rank_search'];
             $iPlaceID = $aPoly['place_id'];
 
-            if ($iRankAddress != $iMaxRank) {
+            if ($iRankSearch != $iMaxRank) {
                 $sSQL = 'SELECT place_id FROM ';
                 $sSQL .= '(SELECT place_id, rank_search, country_code, geometry,';
                 $sSQL .= ' ST_distance('.$sPointSQL.', geometry) as distance';
@@ -206,6 +220,7 @@ class ReverseGeocode
                 // 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\'';
@@ -253,7 +268,7 @@ class ReverseGeocode
             // starts if the search is on POI or street level,
             // searches for the nearest POI or street,
             // if a street is found and a POI is searched for,
-            // the nearest POI which the found street is a parent of is choosen.
+            // 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 ';
@@ -317,9 +332,9 @@ class ReverseGeocode
                     && $this->iMaxRank >= 28
                 ) {
                     $sSQL = 'SELECT place_id,parent_place_id,30 as rank_search,';
-                    $sSQL .= 'ST_LineLocatePoint(linegeo,'.$sPointSQL.') as fraction,';
-                    $sSQL .= 'ST_distance('.$sPointSQL.', linegeo) as distance,';
-                    $sSQL .= 'startnumber,endnumber,interpolationtype';
+                    $sSQL .= '      (endnumber - startnumber) * ST_LineLocatePoint(linegeo,'.$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)';
                     $sSQL .= ' ORDER BY distance ASC limit 1';
@@ -331,7 +346,11 @@ class ReverseGeocode
                     if ($aPlaceTiger) {
                         $aPlace = $aPlaceTiger;
                         $oResult = new Result($aPlaceTiger['place_id'], Result::TABLE_TIGER);
-                        $oResult->iHouseNumber = closestHouseNumber($aPlaceTiger);
+                        $iRndNum = max(0, round($aPlaceTiger['fhnr'] / $aPlaceTiger['step']) * $aPlaceTiger['step']);
+                        $oResult->iHouseNumber = $aPlaceTiger['startnumber'] + $iRndNum;
+                        if ($oResult->iHouseNumber > $aPlaceTiger['endnumber']) {
+                            $oResult->iHouseNumber = $aPlaceTiger['endnumber'];
+                        }
                         $iRankAddress = 30;
                     }
                 }
@@ -343,7 +362,7 @@ class ReverseGeocode
                     // We can't reliably go from the closest street to an
                     // interpolation line because the closest interpolation
                     // may have a different street segments as a parent.
-                    // Therefore allow an interpolation line to take precendence
+                    // Therefore allow an interpolation line to take precedence
                     // even when the street is closer.
                     $fDistance = $iRankAddress < 28 ? 0.001 : $aPlace['distance'];
                 }
@@ -353,7 +372,11 @@ class ReverseGeocode
 
                 if ($aHouse) {
                     $oResult = new Result($aHouse['place_id'], Result::TABLE_OSMLINE);
-                    $oResult->iHouseNumber = closestHouseNumber($aHouse);
+                    $iRndNum = max(0, round($aHouse['fhnr'] / $aHouse['step']) * $aHouse['step']);
+                    $oResult->iHouseNumber = $aHouse['startnumber'] + $iRndNum;
+                    if ($oResult->iHouseNumber > $aHouse['endnumber']) {
+                        $oResult->iHouseNumber = $aHouse['endnumber'];
+                    }
                     $aPlace = $aHouse;
                 }
             }

lib-php/SearchContext.php

@@ -1,4 +1,12 @@
 <?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;
 
@@ -28,6 +36,8 @@ class SearchContext
     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 $sqlCountryList = '';
     /// List of place IDs to exclude (as SQL).
@@ -187,6 +197,7 @@ class SearchContext
     public function setCountryList($aCountries)
     {
         $this->sqlCountryList = '('.join(',', array_map('addQuotes', $aCountries)).')';
+        $this->aCountryList = $aCountries;
     }
 
     /**
@@ -279,6 +290,19 @@ class SearchContext
         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(

lib-php/SearchDescription.php

@@ -1,4 +1,12 @@
 <?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;
 
@@ -19,6 +27,8 @@ class SearchDescription
     private $aName = array();
     /// True if the name is rare enough to force index use on name.
     private $bRareName = false;
+    /// True if the name requires to be accompanied by address terms.
+    private $bNameNeedsAddress = false;
     /// List of word ids making up the address of the object.
     private $aAddress = array();
     /// List of word ids that appear in the name but should be ignored.
@@ -113,6 +123,9 @@ class SearchDescription
                 return false;
             }
         }
+        if ($this->bNameNeedsAddress && empty($this->aAddress)) {
+            return false;
+        }
 
         return true;
     }
@@ -223,7 +236,7 @@ class SearchDescription
      * Add the given full-word token to the list of terms to search for in the
      * name.
      *
-     * @param interger iId    ID of term to add.
+     * @param integer iId    ID of term to add.
      * @param bool bRareName  True if the term is infrequent enough to not
      *                        require other constraints for efficient search.
      */
@@ -231,6 +244,7 @@ class SearchDescription
     {
         $this->aName[$iId] = $iId;
         $this->bRareName = $bRareName;
+        $this->bNameNeedsAddress = false;
     }
 
     /**
@@ -240,11 +254,21 @@ class SearchDescription
      * @param integer iID            ID of term to add.
      * @param bool bSearchable       Term should be used to search for result
      *                               (i.e. term is not a stop word).
+     * @param bool bNeedsAddress     True if the term is too unspecific to be used
+     *                               in a stand-alone search without an address
+     *                               to narrow down the search.
      * @param integer iPhraseNumber  Index of phrase, where the partial term
      *                               appears.
      */
-    public function addPartialNameToken($iId, $bSearchable, $iPhraseNumber)
+    public function addPartialNameToken($iId, $bSearchable, $bNeedsAddress, $iPhraseNumber)
     {
+        if (empty($this->aName)) {
+            $this->bNameNeedsAddress = $bNeedsAddress;
+        } elseif ($bSearchable && count($this->aName) >= 2) {
+            $this->bNameNeedsAddress = false;
+        } else {
+            $this->bNameNeedsAddress &= $bNeedsAddress;
+        }
         if ($bSearchable) {
             $this->aName[$iId] = $iId;
         } else {
@@ -310,6 +334,7 @@ class SearchDescription
     {
         $this->aAddress = array_merge($this->aAddress, $this->aName);
         $this->bRareName = false;
+        $this->bNameNeedsAddress = true;
         $this->aName = array($iId => $iId);
         $this->iNamePhrase = -1;
     }
@@ -362,7 +387,7 @@ class SearchDescription
      *
      * @return mixed[] An array with two fields: IDs contains the list of
      *                 matching place IDs and houseNumber the houseNumber
-     *                 if appicable or -1 if not.
+     *                 if applicable or -1 if not.
      */
     public function query(&$oDB, $iMinRank, $iMaxRank, $iLimit)
     {
@@ -397,28 +422,6 @@ class SearchDescription
                 $iLimit
             );
 
-            // Now search for housenumber, if housenumber provided. Can be zero.
-            if (($this->sHouseNumber || $this->sHouseNumber === '0') && !empty($aResults)) {
-                $aHnResults = $this->queryHouseNumber($oDB, $aResults);
-
-                // Downgrade the rank of the street results, they are missing
-                // the housenumber. Also drop POI places (rank 30) here, they
-                // cannot be a parent place and therefore must not be shown
-                // as a result for a search with a missing housenumber.
-                foreach ($aResults as $oRes) {
-                    if ($oRes->iAddressRank < 28) {
-                        if ($oRes->iAddressRank >= 26) {
-                            $oRes->iResultRank++;
-                        } else {
-                            $oRes->iResultRank += 2;
-                        }
-                        $aHnResults[$oRes->iId] = $oRes;
-                    }
-                }
-
-                $aResults = $aHnResults;
-            }
-
             // finally get POIs if requested
             if ($this->sClass && !empty($aResults)) {
                 $aResults = $this->queryPoiByOperator($oDB, $aResults, $iLimit);
@@ -564,36 +567,6 @@ class SearchDescription
         $aTerms = array();
         $aOrder = array();
 
-        // Sort by existence of the requested house number but only if not
-        // too many results are expected for the street, i.e. if the result
-        // will be narrowed down by an address. Remeber that with ordering
-        // every single result has to be checked.
-        if ($this->sHouseNumber && ($this->bRareName || !empty($this->aAddress) || $this->sPostcode)) {
-            $sHouseNumberRegex = '\\\\m'.$this->sHouseNumber.'\\\\M';
-            $aOrder[] = ' (';
-            $aOrder[0] .= 'EXISTS(';
-            $aOrder[0] .= '  SELECT place_id';
-            $aOrder[0] .= '  FROM placex';
-            $aOrder[0] .= '  WHERE parent_place_id = search_name.place_id';
-            $aOrder[0] .= "    AND housenumber ~* E'".$sHouseNumberRegex."'";
-            $aOrder[0] .= '  LIMIT 1';
-            $aOrder[0] .= ') ';
-            // also housenumbers from interpolation lines table are needed
-            if (preg_match('/[0-9]+/', $this->sHouseNumber)) {
-                $iHouseNumber = intval($this->sHouseNumber);
-                $aOrder[0] .= 'OR EXISTS(';
-                $aOrder[0] .= '  SELECT place_id ';
-                $aOrder[0] .= '  FROM location_property_osmline ';
-                $aOrder[0] .= '  WHERE parent_place_id = search_name.place_id';
-                $aOrder[0] .= '    AND startnumber is not NULL';
-                $aOrder[0] .= '    AND '.$iHouseNumber.'>=startnumber ';
-                $aOrder[0] .= '    AND '.$iHouseNumber.'<=endnumber ';
-                $aOrder[0] .= '  LIMIT 1';
-                $aOrder[0] .= ')';
-            }
-            $aOrder[0] .= ') DESC';
-        }
-
         if (!empty($this->aName)) {
             $aTerms[] = 'name_vector @> '.$oDB->getArraySQL($this->aName);
         }
@@ -624,7 +597,7 @@ class SearchDescription
             $aOrder[] = $this->oContext->distanceSQL('centroid');
         } elseif ($this->sPostcode) {
             if (empty($this->aAddress)) {
-                $aTerms[] = "EXISTS(SELECT place_id FROM location_postcode p WHERE p.postcode = '".$this->sPostcode."' AND ST_DWithin(search_name.centroid, p.geometry, 0.1))";
+                $aTerms[] = "EXISTS(SELECT place_id FROM location_postcode p WHERE p.postcode = '".$this->sPostcode."' AND ST_DWithin(search_name.centroid, p.geometry, 0.12))";
             } else {
                 $aOrder[] = "(SELECT min(ST_Distance(search_name.centroid, p.geometry)) FROM location_postcode p WHERE p.postcode = '".$this->sPostcode."')";
             }
@@ -639,10 +612,6 @@ class SearchDescription
             $aTerms[] = 'centroid && '.$this->oContext->sqlViewboxSmall;
         }
 
-        if ($this->oContext->hasNearPoint()) {
-            $aOrder[] = $this->oContext->distanceSQL('centroid');
-        }
-
         if ($this->sHouseNumber) {
             $sImportanceSQL = '- abs(26 - address_rank) + 3';
         } else {
@@ -665,122 +634,128 @@ class SearchDescription
             $sExactMatchSQL = '0::int as exactmatch';
         }
 
-        if ($this->sHouseNumber || $this->sClass) {
-            $iLimit = 40;
+        if (empty($aTerms)) {
+            return array();
         }
 
-        $aResults = array();
+        if ($this->hasHousenumber()) {
+            $sHouseNumberRegex = $oDB->getDBQuoted('\\\\m'.$this->sHouseNumber.'\\\\M');
 
-        if (!empty($aTerms)) {
-            $sSQL = 'SELECT place_id, address_rank,'.$sExactMatchSQL;
+            // Housenumbers on streets and places.
+            $sPlacexSql = 'SELECT array_agg(place_id) FROM placex';
+            $sPlacexSql .= ' WHERE parent_place_id = sin.place_id AND sin.address_rank < 30';
+            $sPlacexSql .= $this->oContext->excludeSQL(' AND place_id');
+            $sPlacexSql .= '       and housenumber ~* E'.$sHouseNumberRegex;
+
+            // Interpolations on streets and places.
+            $sInterpolSql = 'null';
+            $sTigerSql = 'null';
+            if (preg_match('/^[0-9]+$/', $this->sHouseNumber)) {
+                $sIpolHnr = 'WHERE parent_place_id = sin.place_id ';
+                $sIpolHnr .= '  AND startnumber is not NULL AND sin.address_rank < 30';
+                $sIpolHnr .= '  AND '.$this->sHouseNumber.' between startnumber and endnumber';
+                $sIpolHnr .= '  AND ('.$this->sHouseNumber.' - startnumber) % step = 0';
+
+                $sInterpolSql = 'SELECT array_agg(place_id) FROM location_property_osmline '.$sIpolHnr;
+                if (CONST_Use_US_Tiger_Data) {
+                    $sTigerSql = 'SELECT array_agg(place_id) FROM location_property_tiger '.$sIpolHnr;
+                    $sTigerSql .= "      and sin.country_code = 'us'";
+                }
+            }
+
+            if ($this->sClass) {
+                $iLimit = 40;
+            }
+
+            $sSelfHnr = 'SELECT * FROM placex WHERE place_id = search_name.place_id';
+            $sSelfHnr .= '    AND housenumber ~* E'.$sHouseNumberRegex;
+
+            $aTerms[] = '(address_rank < 30 or exists('.$sSelfHnr.'))';
+
+
+            $sSQL = 'SELECT sin.*, ';
+            $sSQL .=        '('.$sPlacexSql.') as placex_hnr, ';
+            $sSQL .=        '('.$sInterpolSql.') as interpol_hnr, ';
+            $sSQL .=        '('.$sTigerSql.') as tiger_hnr ';
+            $sSQL .= ' FROM (';
+            $sSQL .= '    SELECT place_id, address_rank, country_code,'.$sExactMatchSQL.',';
+            $sSQL .= '            CASE WHEN importance = 0 OR importance IS NULL';
+            $sSQL .= '               THEN 0.75001-(search_rank::float/40) ELSE importance END as importance';
+            $sSQL .= '     FROM search_name';
+            $sSQL .= '     WHERE '.join(' and ', $aTerms);
+            $sSQL .= '     ORDER BY '.join(', ', $aOrder);
+            $sSQL .= '     LIMIT 40000';
+            $sSQL .= ') as sin';
+            $sSQL .= ' ORDER BY address_rank = 30 desc, placex_hnr, interpol_hnr, tiger_hnr,';
+            $sSQL .= '          importance';
+            $sSQL .= ' LIMIT '.$iLimit;
+        } else {
+            if ($this->sClass) {
+                $iLimit = 40;
+            }
+
+            $sSQL = 'SELECT place_id, address_rank, '.$sExactMatchSQL;
             $sSQL .= ' FROM search_name';
             $sSQL .= ' WHERE '.join(' and ', $aTerms);
             $sSQL .= ' ORDER BY '.join(', ', $aOrder);
             $sSQL .= ' LIMIT '.$iLimit;
-
-            Debug::printSQL($sSQL);
-
-            $aDBResults = $oDB->getAll($sSQL, null, 'Could not get places for search terms.');
-
-            foreach ($aDBResults as $aResult) {
-                $oResult = new Result($aResult['place_id']);
-                $oResult->iExactMatches = $aResult['exactmatch'];
-                $oResult->iAddressRank = $aResult['address_rank'];
-                $aResults[$aResult['place_id']] = $oResult;
-            }
         }
 
-        return $aResults;
-    }
-
-    private function queryHouseNumber(&$oDB, $aRoadPlaceIDs)
-    {
-        $aResults = array();
-        $sRoadPlaceIDs = Result::joinIdsByTableMaxRank(
-            $aRoadPlaceIDs,
-            Result::TABLE_PLACEX,
-            27
-        );
-        $sPOIPlaceIDs = Result::joinIdsByTableMinRank(
-            $aRoadPlaceIDs,
-            Result::TABLE_PLACEX,
-            30
-        );
-
-        $aIDCondition = array();
-        if ($sRoadPlaceIDs) {
-            $aIDCondition[] = 'parent_place_id in ('.$sRoadPlaceIDs.')';
-        }
-        if ($sPOIPlaceIDs) {
-            $aIDCondition[] = 'place_id in ('.$sPOIPlaceIDs.')';
-        }
-
-        if (empty($aIDCondition)) {
-            return $aResults;
-        }
-
-        $sHouseNumberRegex = '\\\\m'.$this->sHouseNumber.'\\\\M';
-        $sSQL = 'SELECT place_id FROM placex WHERE';
-        $sSQL .= "  housenumber ~* E'".$sHouseNumberRegex."'";
-        $sSQL .= ' AND ('.join(' OR ', $aIDCondition).')';
-        $sSQL .= $this->oContext->excludeSQL(' AND place_id');
-
         Debug::printSQL($sSQL);
 
-        // XXX should inherit the exactMatches from its parent
-        foreach ($oDB->getCol($sSQL) as $iPlaceId) {
-            $aResults[$iPlaceId] = new Result($iPlaceId);
-        }
+        $aDBResults = $oDB->getAll($sSQL, null, 'Could not get places for search terms.');
 
-        $bIsIntHouseNumber= (bool) preg_match('/[0-9]+/', $this->sHouseNumber);
-        $iHousenumber = intval($this->sHouseNumber);
-        if ($bIsIntHouseNumber && $sRoadPlaceIDs && empty($aResults)) {
-            // if nothing found, search in the interpolation line table
-            $sSQL = 'SELECT distinct place_id FROM location_property_osmline';
-            $sSQL .= ' WHERE startnumber is not NULL';
-            $sSQL .= '  AND parent_place_id in ('.$sRoadPlaceIDs.') AND (';
-            if ($iHousenumber % 2 == 0) {
-                // If housenumber is even, look for housenumber in streets
-                // with interpolationtype even or all.
-                $sSQL .= "interpolationtype='even'";
-            } else {
-                // Else look for housenumber with interpolationtype odd or all.
-                $sSQL .= "interpolationtype='odd'";
+        $aResults = array();
+
+        foreach ($aDBResults as $aResult) {
+            $oResult = new Result($aResult['place_id']);
+            $oResult->iExactMatches = $aResult['exactmatch'];
+            $oResult->iAddressRank = $aResult['address_rank'];
+
+            $bNeedResult = true;
+            if ($this->hasHousenumber() && $aResult['address_rank'] < 30) {
+                if ($aResult['placex_hnr']) {
+                    foreach (explode(',', substr($aResult['placex_hnr'], 1, -1)) as $sPlaceID) {
+                        $iPlaceID = intval($sPlaceID);
+                        $oHnrResult = new Result($iPlaceID);
+                        $oHnrResult->iExactMatches = $aResult['exactmatch'];
+                        $oHnrResult->iAddressRank = 30;
+                        $aResults[$iPlaceID] = $oHnrResult;
+                        $bNeedResult = false;
+                    }
+                }
+                if ($aResult['interpol_hnr']) {
+                    foreach (explode(',', substr($aResult['interpol_hnr'], 1, -1)) as $sPlaceID) {
+                        $iPlaceID = intval($sPlaceID);
+                        $oHnrResult = new Result($iPlaceID, Result::TABLE_OSMLINE);
+                        $oHnrResult->iExactMatches = $aResult['exactmatch'];
+                        $oHnrResult->iAddressRank = 30;
+                        $oHnrResult->iHouseNumber = intval($this->sHouseNumber);
+                        $aResults[$iPlaceID] = $oHnrResult;
+                        $bNeedResult = false;
+                    }
+                }
+                if ($aResult['tiger_hnr']) {
+                    foreach (explode(',', substr($aResult['tiger_hnr'], 1, -1)) as $sPlaceID) {
+                        $iPlaceID = intval($sPlaceID);
+                        $oHnrResult = new Result($iPlaceID, Result::TABLE_TIGER);
+                        $oHnrResult->iExactMatches = $aResult['exactmatch'];
+                        $oHnrResult->iAddressRank = 30;
+                        $oHnrResult->iHouseNumber = intval($this->sHouseNumber);
+                        $aResults[$iPlaceID] = $oHnrResult;
+                        $bNeedResult = false;
+                    }
+                }
+
+                if ($aResult['address_rank'] < 26) {
+                    $oResult->iResultRank += 2;
+                } else {
+                    $oResult->iResultRank++;
+                }
             }
-            $sSQL .= " or interpolationtype='all') and ";
-            $sSQL .= $iHousenumber.'>=startnumber and ';
-            $sSQL .= $iHousenumber.'<=endnumber';
-            $sSQL .= $this->oContext->excludeSQL(' AND place_id');
 
-            Debug::printSQL($sSQL);
-
-            foreach ($oDB->getCol($sSQL) as $iPlaceId) {
-                $oResult = new Result($iPlaceId, Result::TABLE_OSMLINE);
-                $oResult->iHouseNumber = $iHousenumber;
-                $aResults[$iPlaceId] = $oResult;
-            }
-        }
-
-        // If nothing found then search in Tiger data (location_property_tiger)
-        if (CONST_Use_US_Tiger_Data && $sRoadPlaceIDs && $bIsIntHouseNumber && empty($aResults)) {
-            $sSQL = 'SELECT place_id FROM location_property_tiger';
-            $sSQL .= ' WHERE parent_place_id in ('.$sRoadPlaceIDs.') and (';
-            if ($iHousenumber % 2 == 0) {
-                $sSQL .= "interpolationtype='even'";
-            } else {
-                $sSQL .= "interpolationtype='odd'";
-            }
-            $sSQL .= " or interpolationtype='all') and ";
-            $sSQL .= $iHousenumber.'>=startnumber and ';
-            $sSQL .= $iHousenumber.'<=endnumber';
-            $sSQL .= $this->oContext->excludeSQL(' AND place_id');
-
-            Debug::printSQL($sSQL);
-
-            foreach ($oDB->getCol($sSQL) as $iPlaceId) {
-                $oResult = new Result($iPlaceId, Result::TABLE_TIGER);
-                $oResult->iHouseNumber = $iHousenumber;
-                $aResults[$iPlaceId] = $oResult;
+            if ($bNeedResult) {
+                $aResults[$aResult['place_id']] = $oResult;
             }
         }
 
@@ -832,6 +807,7 @@ class SearchDescription
                 $sSQL = 'SELECT geometry FROM placex';
                 $sSQL .= " WHERE place_id in ($sPlaceIDs)";
                 $sSQL .= "   AND rank_search < $iMaxRank + 5";
+                $sSQL .= '   AND ST_Area(Box2d(geometry)) < 20';
                 $sSQL .= "   AND ST_GeometryType(geometry) in ('ST_Polygon','ST_MultiPolygon')";
                 $sSQL .= ' ORDER BY rank_search ASC ';
                 $sSQL .= ' LIMIT 1';

lib-php/SearchPosition.php

@@ -1,4 +1,12 @@
 <?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;
 

lib-php/Shell.php

@@ -1,4 +1,12 @@
 <?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;
 

lib-php/SimpleWordList.php

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

lib-php/SpecialSearchOperator.php

@@ -1,4 +1,12 @@
 <?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;
 

lib-php/Status.php

@@ -1,4 +1,12 @@
 <?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;
 

lib-php/TokenCountry.php

@@ -1,4 +1,12 @@
 <?php
+/**
+ * SPDX-License-Identifier: GPL-2.0-only
+ *
+ * This file is part of Nominatim. (https://nominatim.org)
+ *
+ * Copyright (C) 2022 by the Nominatim developer community.
+ * For a full list of authors see the git log.
+ */
 
 namespace Nominatim\Token;
 
@@ -36,7 +44,9 @@ class Country
      */
     public function isExtendable($oSearch, $oPosition)
     {
-        return !$oSearch->hasCountry() && $oPosition->maybePhrase('country');
+        return !$oSearch->hasCountry()
+               && $oPosition->maybePhrase('country')
+               && $oSearch->getContext()->isCountryApplicable($this->sCountryCode);
     }
 
     /**

lib-php/TokenHousenumber.php

@@ -1,4 +1,12 @@
 <?php
+/**
+ * SPDX-License-Identifier: GPL-2.0-only
+ *
+ * This file is part of Nominatim. (https://nominatim.org)
+ *
+ * Copyright (C) 2022 by the Nominatim developer community.
+ * For a full list of authors see the git log.
+ */
 
 namespace Nominatim\Token;
 
@@ -58,8 +66,8 @@ class HouseNumber
         // up of numbers, add a penalty
         $iSearchCost = 1;
         if (preg_match('/\\d/', $this->sToken) === 0
-            || preg_match_all('/[^0-9]/', $this->sToken, $aMatches) > 2) {
-            $iSearchCost++;
+            || preg_match_all('/[^0-9 ]/', $this->sToken, $aMatches) > 3) {
+            $iSearchCost += strlen($this->sToken) - 1;
         }
         if (!$oSearch->hasOperator(\Nominatim\Operator::NONE)) {
             $iSearchCost++;

lib-php/TokenList.php

@@ -1,4 +1,12 @@
 <?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;
 

lib-php/TokenPartial.php

@@ -1,4 +1,12 @@
 <?php
+/**
+ * SPDX-License-Identifier: GPL-2.0-only
+ *
+ * This file is part of Nominatim. (https://nominatim.org)
+ *
+ * Copyright (C) 2022 by the Nominatim developer community.
+ * For a full list of authors see the git log.
+ */
 
 namespace Nominatim\Token;
 
@@ -90,6 +98,7 @@ class Partial
             $oNewSearch->addPartialNameToken(
                 $this->iId,
                 $this->iSearchNameCount < CONST_Max_Word_Frequency,
+                $this->iSearchNameCount > CONST_Search_NameOnlySearchFrequencyThreshold,
                 $oPosition->getPhrase()
             );
 

lib-php/TokenPostcode.php

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

lib-php/TokenSpecialTerm.php

@@ -1,4 +1,12 @@
 <?php
+/**
+ * SPDX-License-Identifier: GPL-2.0-only
+ *
+ * This file is part of Nominatim. (https://nominatim.org)
+ *
+ * Copyright (C) 2022 by the Nominatim developer community.
+ * For a full list of authors see the git log.
+ */
 
 namespace Nominatim\Token;
 
@@ -44,7 +52,10 @@ class SpecialTerm
      */
     public function isExtendable($oSearch, $oPosition)
     {
-        return !$oSearch->hasOperator() && $oPosition->isPhrase('');
+        return !$oSearch->hasOperator()
+               && $oPosition->isPhrase('')
+               && ($this->iOperator != \Nominatim\Operator::NONE
+                  || (!$oSearch->hasAddress() && !$oSearch->hasHousenumber() && !$oSearch->hasCountry()));
     }
 
     /**
@@ -58,19 +69,31 @@ class SpecialTerm
      */
     public function extendSearch($oSearch, $oPosition)
     {
-        $iSearchCost = 2;
+        $iSearchCost = 0;
 
         $iOp = $this->iOperator;
         if ($iOp == \Nominatim\Operator::NONE) {
-            if ($oSearch->hasName() || $oSearch->getContext()->isBoundedSearch()) {
+            if ($oPosition->isFirstToken()
+                || $oSearch->hasName()
+                || $oSearch->getContext()->isBoundedSearch()
+            ) {
                 $iOp = \Nominatim\Operator::NAME;
+                $iSearchCost += 3;
             } else {
                 $iOp = \Nominatim\Operator::NEAR;
+                $iSearchCost += 4;
+                if (!$oPosition->isFirstToken()) {
+                    $iSearchCost += 3;
+                }
             }
+        } elseif ($oPosition->isFirstToken()) {
             $iSearchCost += 2;
-        } elseif (!$oPosition->isFirstToken() && !$oPosition->isLastToken()) {
-            $iSearchCost += 2;
+        } elseif ($oPosition->isLastToken()) {
+            $iSearchCost += 4;
+        } else {
+            $iSearchCost += 6;
         }
+
         if ($oSearch->hasHousenumber()) {
             $iSearchCost ++;
         }

lib-php/TokenWord.php

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

lib-php/admin/country_languages.php

@@ -1,34 +0,0 @@
-<?php
-@define('CONST_LibDir', dirname(dirname(__FILE__)));
-
-require_once(CONST_LibDir.'/init-cmd.php');
-
-ini_set('memory_limit', '800M');
-ini_set('display_errors', 'stderr');
-
-$aCMDOptions
- = array(
-    'Import country language data from osm wiki',
-    array('help', 'h', 0, 1, 0, 0, false, 'Show Help'),
-    array('quiet', 'q', 0, 1, 0, 0, 'bool', 'Quiet output'),
-    array('verbose', 'v', 0, 1, 0, 0, 'bool', 'Verbose output'),
-    array('project-dir', '', 0, 1, 1, 1, 'realpath', 'Base directory of the Nominatim installation (default: .)'),
-   );
-getCmdOpt($_SERVER['argv'], $aCMDOptions, $aCMDResult, true, true);
-
-loadSettings($aCMDResult['project-dir'] ?? getcwd());
-setupHTTPProxy();
-
-if (true) {
-    $sURL = 'https://wiki.openstreetmap.org/wiki/Special:Export/Nominatim/Country_Codes';
-    $sWikiPageXML = file_get_contents($sURL);
-    if (preg_match_all('#\\| ([a-z]{2}) \\|\\| [^|]+\\|\\| ([a-z,]+)#', $sWikiPageXML, $aMatches, PREG_SET_ORDER)) {
-        foreach ($aMatches as $aMatch) {
-            $aLanguages = explode(',', $aMatch[2]);
-            foreach ($aLanguages as $i => $s) {
-                $aLanguages[$i] = '"'.pg_escape_string($s).'"';
-            }
-            echo "UPDATE country_name set country_default_language_codes = '{".join(',', $aLanguages)."}' where country_code = '".pg_escape_string($aMatch[1])."';\n";
-        }
-    }
-}

lib-php/admin/export.php

@@ -1,4 +1,12 @@
 <?php
+/**
+ * SPDX-License-Identifier: GPL-2.0-only
+ *
+ * This file is part of Nominatim. (https://nominatim.org)
+ *
+ * Copyright (C) 2022 by the Nominatim developer community.
+ * For a full list of authors see the git log.
+ */
     @define('CONST_LibDir', dirname(dirname(__FILE__)));
     // Script to extract structured city and street data
     // from a running nominatim instance as CSV data

lib-php/admin/warm.php

@@ -1,4 +1,12 @@
 <?php
+/**
+ * SPDX-License-Identifier: GPL-2.0-only
+ *
+ * This file is part of Nominatim. (https://nominatim.org)
+ *
+ * Copyright (C) 2022 by the Nominatim developer community.
+ * For a full list of authors see the git log.
+ */
 @define('CONST_LibDir', dirname(dirname(__FILE__)));
 
 require_once(CONST_LibDir.'/init-cmd.php');
@@ -86,8 +94,13 @@ if (!$aResult['reverse-only']) {
     if ($bVerbose) {
         echo "\n";
     }
+
+    $oTokenizer = new \Nominatim\Tokenizer($oDB);
+
+    $aWords = $oTokenizer->mostFrequentWords(1000);
+
     $sSQL = 'SELECT word FROM word WHERE word is not null ORDER BY search_name_count DESC LIMIT 1000';
-    foreach ($oDB->getCol($sSQL) as $sWord) {
+    foreach ($aWords as $sWord) {
         if ($bVerbose) {
             echo "$sWord = ";
         }

lib-php/cmd.php

@@ -1,4 +1,12 @@
 <?php
+/**
+ * SPDX-License-Identifier: GPL-2.0-only
+ *
+ * This file is part of Nominatim. (https://nominatim.org)
+ *
+ * Copyright (C) 2022 by the Nominatim developer community.
+ * For a full list of authors see the git log.
+ */
 
 require_once(CONST_LibDir.'/Shell.php');
 
@@ -98,7 +106,7 @@ function getCmdOpt($aArg, $aSpec, &$aResult, $bExitOnError = false, $bExitOnUnkn
                 showUsage($aSpec, $bExitOnError, 'Option \''.$aLine[0].'\' is missing');
             }
             if ($aCounts[$aLine[0]] > $aLine[3]) {
-                showUsage($aSpec, $bExitOnError, 'Option \''.$aLine[0].'\' is pressent too many times');
+                showUsage($aSpec, $bExitOnError, 'Option \''.$aLine[0].'\' is present too many times');
             }
             if ($aLine[6] == 'bool' && !array_key_exists($aLine[0], $aResult)) {
                 $aResult[$aLine[0]] = false;

lib-php/dotenv_loader.php

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

lib-php/init-cmd.php

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

lib-php/init-website.php

@@ -1,4 +1,12 @@
 <?php
+/**
+ * SPDX-License-Identifier: GPL-2.0-only
+ *
+ * This file is part of Nominatim. (https://nominatim.org)
+ *
+ * Copyright (C) 2022 by the Nominatim developer community.
+ * For a full list of authors see the git log.
+ */
 
 require_once('init.php');
 require_once('ParameterParser.php');
@@ -18,7 +26,7 @@ function userError($sMsg)
 
 function exception_handler_json($exception)
 {
-    http_response_code($exception->getCode());
+    http_response_code($exception->getCode() == 0 ? 500 : $exception->getCode());
     header('Content-type: application/json; charset=utf-8');
     include(CONST_LibDir.'/template/error-json.php');
     exit();
@@ -26,7 +34,7 @@ function exception_handler_json($exception)
 
 function exception_handler_xml($exception)
 {
-    http_response_code($exception->getCode());
+    http_response_code($exception->getCode() == 0 ? 500 : $exception->getCode());
     header('Content-type: text/xml; charset=utf-8');
     echo '<?xml version="1.0" encoding="UTF-8" ?>'."\n";
     include(CONST_LibDir.'/template/error-xml.php');

lib-php/init.php

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