Installation docs - link to Kubernetes install project

As reported by @robjuz in https://github.com/osm-search/Nominatim/discussions/2412

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,4 @@
+contact_links:
+  - name: Nominatim Discussions
+    url: https://github.com/osm-search/Nominatim/discussions
+    about: Ask questions, get support, share ideas and discuss with community members.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,22 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+<!-- Before opening a new feature request, please search through the open issue to check that your request hasn't been reported already. -->
+
+**Is your feature request related to a problem? Please describe.**
+<!-- A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] -->
+
+**Describe the solution you'd like**
+<!-- A clear and concise description of what you want to happen. -->
+
+**Describe alternatives you've considered**
+<!-- A clear and concise description of any alternative solutions or features you've considered. -->
+
+**Additional context**
+<!-- Add any other context or screenshots about the feature request here. -->

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

@@ -0,0 +1,37 @@
+---
+name: Report issues with search results
+about: You have searched something with Nominatim and did not get the expected result.
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+## What did you search for?
+
+<!-- Please try to provide a link to your search. You  can go to https://nominatim.openstreetmap.org and repeat your search there. If you originally found the issue somewhere else, please tell us what software/website you were using. -->
+
+## What result did you get?
+
+## What result did you expect?
+
+**Is the result in the right place and just named wrongly?** 
+
+<!-- Please tell us the display name you expected. -->
+
+**Is the result missing completely?**
+
+<!-- Make sure that the data you are looking for is in OpenStreetMap. Provide a link to the OpenStreetMap object or if you cannot get it, a link to the map on https://openstreetmap.org where you expect the result to be.
+
+To get the link to the OSM object, you can try the following:
+
+ * Go to [https://openstreetmap.org](https://openstreetmap.org).
+ * Move to the area of the map where you expect the result and then zoom in as much as possible.
+ * Click on the question mark on the right side of the map. You get a question cursor. Use it to click on the map where your object is located.
+ * Find the object of interest in the list that appears on the left side.
+ * Click on the object and report back the URL that the browser shows.
+-->
+
+## Further details
+
+<!-- Anything else we should know about the search. Particularities with addresses in the area etc. -->

.github/ISSUE_TEMPLATE/report-problems-with-the-software.md

@@ -0,0 +1,36 @@
+---
+name: Report problems with the software
+about: You have your own installation of Nominatim and found a bug.
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+<!-- Note: if you are installing Nominatim through a docker image, you should report issues with the installation process with the docker repository first. -->
+
+**Describe the bug**
+<!-- A clear and concise description of what the bug is. -->
+
+**To Reproduce**
+<!-- Please describe what you did to get to the issue. -->
+
+**Software Environment (please complete the following information):**
+- Nominatim version: 
+- Postgresql version: 
+- Postgis version:
+- OS: 
+
+**Hardware Configuration (please complete the following information):**
+- RAM: 
+- number of CPUs:
+- type and size of disks:
+- bare metal/AWS/other cloud service: 
+
+**Postgresql Configuration:**
+
+<!-- List any configuration items you changed in your postgresql configuration. -->
+
+**Additional context**
+
+<!-- Add any other context about the problem here. -->

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

@@ -0,0 +1,42 @@
+name: 'Build Nominatim'
+
+inputs:
+    ubuntu:
+        description: 'Version of Ubuntu to install on'
+        required: false
+        default: '20'
+
+runs:
+    using: "composite"
+
+    steps:
+        - name: Install prerequisites
+          run: |
+            sudo apt-get install -y -qq libboost-system-dev libboost-filesystem-dev libexpat1-dev zlib1g-dev libbz2-dev libpq-dev libproj-dev libicu-dev
+            if [ "x$UBUNTUVER" == "x18" ]; then
+                pip3 install python-dotenv psycopg2==2.7.7 jinja2==2.8 psutil==5.4.2 pyicu osmium PyYAML==5.1 datrie
+            else
+                sudo apt-get install -y -qq python3-icu python3-datrie python3-pyosmium python3-jinja2 python3-psutil python3-psycopg2 python3-dotenv python3-yaml
+            fi
+          shell: bash
+          env:
+            UBUNTUVER: ${{ inputs.ubuntu }}
+
+        - name: Download dependencies
+          run: |
+              if [ ! -f country_grid.sql.gz ]; then
+                  wget --no-verbose https://www.nominatim.org/data/country_grid.sql.gz
+              fi
+              cp country_grid.sql.gz Nominatim/data/country_osm_grid.sql.gz
+          shell: bash
+
+        - name: Configure
+          run: mkdir build && cd build && cmake ../Nominatim
+          shell: bash
+
+        - name: Build
+          run: |
+              make -j2 all
+              sudo make install
+          shell: bash
+          working-directory: build

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

@@ -0,0 +1,47 @@
+name: 'Setup Postgresql and Postgis'
+
+inputs:
+    postgresql-version:
+        description: 'Version of PostgreSQL to install'
+        required: true
+    postgis-version:
+        description: 'Version of Postgis to install'
+        required: true
+
+runs:
+    using: "composite"
+
+    steps:
+        - name: Remove existing PostgreSQL
+          run: |
+              sudo apt-get purge -yq postgresql*
+              sudo sh -c 'echo "deb http://apt.postgresql.org/pub/repos/apt $(lsb_release -cs)-pgdg main" > /etc/apt/sources.list.d/pgdg.list'
+              sudo apt-get update -qq
+
+          shell: bash
+
+        - name: Install PostgreSQL
+          run: |
+              sudo apt-get install -y -qq --no-install-suggests --no-install-recommends postgresql-client-${PGVER} postgresql-${PGVER}-postgis-${POSTGISVER} postgresql-${PGVER}-postgis-${POSTGISVER}-scripts postgresql-contrib-${PGVER} postgresql-${PGVER} postgresql-server-dev-${PGVER}
+          shell: bash
+          env:
+              PGVER: ${{ inputs.postgresql-version }}
+              POSTGISVER: ${{ inputs.postgis-version }}
+
+        - name: Adapt postgresql configuration
+          run: |
+              echo 'fsync = off' | sudo tee /etc/postgresql/${PGVER}/main/conf.d/local.conf
+              echo 'synchronous_commit = off' | sudo tee -a /etc/postgresql/${PGVER}/main/conf.d/local.conf
+              echo 'full_page_writes = off' | sudo tee -a /etc/postgresql/${PGVER}/main/conf.d/local.conf
+              echo 'shared_buffers = 1GB' | sudo tee -a /etc/postgresql/${PGVER}/main/conf.d/local.conf
+              echo 'port = 5432' | sudo tee -a /etc/postgresql/${PGVER}/main/conf.d/local.conf
+          shell: bash
+          env:
+              PGVER: ${{ inputs.postgresql-version }}
+
+        - name: Setup database
+          run: |
+              sudo systemctl restart postgresql
+              sudo -u postgres createuser -S www-data
+              sudo -u postgres createuser -s runner
+          shell: bash

.github/workflows/ci-tests.yml

@@ -0,0 +1,217 @@
+name: CI Tests
+
+on: [ push, pull_request ]
+
+jobs:
+    tests:
+        strategy:
+            matrix:
+                ubuntu: [18, 20]
+                include:
+                    - ubuntu: 18
+                      postgresql: 9.5
+                      postgis: 2.5
+                      pytest: pytest
+                      php: 7.2
+                    - ubuntu: 20
+                      postgresql: 13
+                      postgis: 3
+                      pytest: py.test-3
+                      php: 7.4
+
+        runs-on: ubuntu-${{ matrix.ubuntu }}.04
+
+        steps:
+            - uses: actions/checkout@v2
+              with:
+                  submodules: true
+                  path: Nominatim
+
+            - name: Setup PHP
+              uses: shivammathur/setup-php@v2
+              with:
+                  php-version: ${{ matrix.php }}
+                  coverage: xdebug
+                  tools: phpunit, phpcs, composer
+
+            - uses: actions/setup-python@v2
+              with:
+                python-version: 3.6
+              if: matrix.ubuntu == 18
+
+            - name: Get Date
+              id: get-date
+              run: |
+                  echo "::set-output name=date::$(/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 }}
+                  postgis-version: ${{ matrix.postgis }}
+
+            - uses: ./Nominatim/.github/actions/build-nominatim
+              with:
+                  ubuntu: ${{ matrix.ubuntu }}
+
+            - name: Install test prerequsites
+              run: sudo apt-get install -y -qq pylint python3-pytest python3-behave python3-pytest-cov php-codecoverage
+              if: matrix.ubuntu == 20
+
+            - name: Install test prerequsites
+              run: |
+                   pip3 install pylint==2.6.0 pytest pytest-cov behave==1.2.6
+              if: matrix.ubuntu == 18
+
+            - name: PHP linting
+              run: phpcs --report-width=120 .
+              working-directory: Nominatim
+
+            - name: Python linting
+              run: pylint nominatim
+              working-directory: Nominatim
+
+            - name: PHP unit tests
+              run: phpunit --coverage-clover ../../coverage-php.xml ./
+              working-directory: Nominatim/test/php
+              if: matrix.ubuntu == 20
+
+            - name: Python unit tests
+              run: $PYTEST --cov=nominatim --cov-report=xml test/python
+              working-directory: Nominatim
+              env:
+                PYTEST: ${{ matrix.pytest }}
+
+            - name: BDD tests
+              run: |
+                  mkdir cov
+                  behave -DREMOVE_TEMPLATE=1 -DBUILDDIR=$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-${{ matrix.ubuntu }}.04
+
+        steps:
+            - uses: actions/checkout@v2
+              with:
+                  submodules: true
+                  path: Nominatim
+
+            - name: Get Date
+              id: get-date
+              run: |
+                  echo "::set-output name=date::$(/bin/date -u "+%Y%W")"
+              shell: bash
+
+            - uses: actions/cache@v2
+              with:
+                  path: |
+                     country_grid.sql.gz
+                  key: nominatim-country-data-${{ steps.get-date.outputs.date }}
+
+            - uses: actions/cache@v2
+              with:
+                  path: |
+                     monaco-latest.osm.pbf
+                  key: nominatim-test-data-${{ steps.get-date.outputs.date }}
+
+            - uses: actions/setup-python@v2
+              with:
+                python-version: 3.6
+              if: matrix.ubuntu == 18
+
+            - uses: ./Nominatim/.github/actions/setup-postgresql
+              with:
+                  postgresql-version: ${{ matrix.postgresql }}
+                  postgis-version: ${{ matrix.postgis }}
+            - uses: ./Nominatim/.github/actions/build-nominatim
+              with:
+                  ubuntu: ${{ matrix.ubuntu }}
+
+            - name: Clean installation
+              run: rm -rf Nominatim build
+              shell: bash
+
+            - name: Prepare import environment
+              run: |
+                  if [ ! -f monaco-latest.osm.pbf ]; then
+                      wget --no-verbose https://download.geofabrik.de/europe/monaco-latest.osm.pbf
+                  fi
+                  mkdir data-env
+                  cd data-env
+              shell: bash
+
+            - name: Import
+              run: nominatim import --osm-file ../monaco-latest.osm.pbf
+              shell: bash
+              working-directory: data-env
+
+            - name: Import special phrases
+              run: nominatim special-phrases --import-from-wiki
+              working-directory: data-env
+
+            - name: Check full import
+              run: nominatim admin --check-database
+              working-directory: data-env
+
+            - name: Warm up database
+              run: nominatim admin --warm
+              working-directory: data-env
+
+            - name: Run update
+              run: |
+                   nominatim replication --init
+                   nominatim replication --once
+              working-directory: data-env
+
+            - name: Run reverse-only import
+              run : nominatim import --osm-file ../monaco-latest.osm.pbf --reverse-only --no-updates
+              working-directory: data-env
+              env:
+                  NOMINATIM_DATABASE_DSN: pgsql:dbname=reverse
+
+            - name: Check reverse import
+              run: nominatim admin --check-database
+              working-directory: data-env

.gitignore

@@ -9,3 +9,4 @@ data/wiki_specialphrases.sql
 data/osmosischange.osc
 
 .vagrant
+data/country_osm_grid.sql.gz

.pylintrc

@@ -0,0 +1,15 @@
+[MASTER]
+
+extension-pkg-whitelist=osmium
+ignored-modules=icu,datrie
+
+[MESSAGES CONTROL]
+
+[TYPECHECK]
+
+# closing added here because it sometimes triggers a false positive with
+# 'with' statements.
+ignored-classes=NominatimArgs,closing
+disable=too-few-public-methods,duplicate-code
+
+good-names=i,x,y,fd,db

.travis.yml

@@ -1,39 +0,0 @@
----
-os: linux
-dist: bionic
-language: python
-python:
-  - "3.6"
-addons:
-  postgresql: "9.6"
-  apt:
-    packages:
-      postgresql-server-dev-9.6
-      postgresql-client-9.6
-git:
-  depth: 3
-env:
-  - TEST_SUITE=tests
-  - TEST_SUITE=monaco
-before_install:
-  - phpenv global 7.1
-install:
-  - vagrant/install-on-travis-ci.sh
-before_script:
-  - psql -U postgres -c "create extension postgis"
-script:
-  - cd $TRAVIS_BUILD_DIR/
-  - if [[ $TEST_SUITE == "tests" ]]; then phpcs --report-width=120 . ; fi
-  - cd $TRAVIS_BUILD_DIR/test/php
-  - if [[ $TEST_SUITE == "tests" ]]; then /usr/bin/phpunit ./ ; fi
-  - cd $TRAVIS_BUILD_DIR/test/bdd
-  - # behave --format=progress3 api
-  - if [[ $TEST_SUITE == "tests" ]]; then behave -DREMOVE_TEMPLATE=1 --format=progress3 db ; fi
-  - if [[ $TEST_SUITE == "tests" ]]; then behave --format=progress3 osm2pgsql ; fi
-  - cd $TRAVIS_BUILD_DIR/build
-  - if [[ $TEST_SUITE == "monaco" ]]; then wget --no-verbose --output-document=../data/monaco.osm.pbf http://download.geofabrik.de/europe/monaco-latest.osm.pbf; fi
-  - if [[ $TEST_SUITE == "monaco" ]]; then /usr/bin/env php ./utils/setup.php --osm-file ../data/monaco.osm.pbf --osm2pgsql-cache 1000 --all 2>&1 | grep -v 'ETA (seconds)'; fi
-  - if [[ $TEST_SUITE == "monaco" ]]; then /usr/bin/env php ./utils/specialphrases.php --wiki-import | psql -d test_api_nominatim >/dev/null; fi
-  - if [[ $TEST_SUITE == "monaco" ]]; then /usr/bin/env php ./utils/check_import_finished.php; fi
-notifications:
-  email: false

CMakeLists.txt

@@ -6,7 +6,7 @@
 #
 #-----------------------------------------------------------------------------
 
-cmake_minimum_required(VERSION 2.8 FATAL_ERROR)
+cmake_minimum_required(VERSION 3.0 FATAL_ERROR)
 list(APPEND CMAKE_MODULE_PATH "${CMAKE_SOURCE_DIR}/cmake")
 
 
@@ -19,8 +19,8 @@ list(APPEND CMAKE_MODULE_PATH "${CMAKE_SOURCE_DIR}/cmake")
 project(nominatim)
 
 set(NOMINATIM_VERSION_MAJOR 3)
-set(NOMINATIM_VERSION_MINOR 5)
-set(NOMINATIM_VERSION_PATCH 1)
+set(NOMINATIM_VERSION_MINOR 7)
+set(NOMINATIM_VERSION_PATCH 0)
 
 set(NOMINATIM_VERSION "${NOMINATIM_VERSION_MAJOR}.${NOMINATIM_VERSION_MINOR}.${NOMINATIM_VERSION_PATCH}")
 
@@ -36,6 +36,7 @@ set(BUILD_API on CACHE BOOL "Build everything for the API server")
 set(BUILD_MODULE on CACHE BOOL "Build PostgreSQL module")
 set(BUILD_TESTS on CACHE BOOL "Build test suite")
 set(BUILD_DOCS on CACHE BOOL "Build documentation")
+set(BUILD_MANPAGE on CACHE BOOL "Build Manual Page")
 set(BUILD_OSM2PGSQL on CACHE BOOL "Build osm2pgsql (expert only)")
 
 #-----------------------------------------------------------------------------
@@ -57,20 +58,11 @@ endif()
 
 
 #-----------------------------------------------------------------------------
-#  python and pyosmium (imports/updates only)
+#  python (imports/updates only)
 #-----------------------------------------------------------------------------
 
 if (BUILD_IMPORTER)
-    find_package(PythonInterp 3)
-
-    find_program(PYOSMIUM pyosmium-get-changes)
-    if (NOT EXISTS "${PYOSMIUM}")
-        set(PYOSMIUM_PATH "")
-            message(WARNING "pyosmium-get-changes not found (required for updates)")
-    else()
-        set(PYOSMIUM_PATH "${PYOSMIUM}")
-        message(STATUS "Using pyosmium-get-changes at ${PYOSMIUM_PATH}")
-    endif()
+    find_package(PythonInterp 3.6 REQUIRED)
 endif()
 
 #-----------------------------------------------------------------------------
@@ -79,75 +71,48 @@ endif()
 
 # Setting PHP binary variable as to command line (prevailing) or auto detect
 
-if (NOT PHP_BIN)
-     find_program (PHP_BIN php)
+if (BUILD_API OR BUILD_IMPORTER)
+    if (NOT PHP_BIN)
+         find_program (PHP_BIN php)
+    endif()
+    # sanity check if PHP binary exists
+    if (NOT EXISTS ${PHP_BIN})
+        message(FATAL_ERROR "PHP binary not found. Install php or provide location with -DPHP_BIN=/path/php ")
+    else()
+        message (STATUS "Using PHP binary " ${PHP_BIN})
+    endif()
+    if (NOT PHPCGI_BIN)
+        find_program (PHPCGI_BIN php-cgi)
+    endif()
+    # sanity check if PHP binary exists
+    if (NOT EXISTS ${PHPCGI_BIN})
+        message(WARNING "php-cgi binary not found. nominatim tool will not provide query functions.")
+        set (PHPCGI_BIN "")
+    else()
+        message (STATUS "Using php-cgi binary " ${PHPCGI_BIN})
+    endif()
 endif()
-# sanity check if PHP binary exists
-if (NOT EXISTS ${PHP_BIN})
-    message(FATAL_ERROR "PHP binary not found. Install php or provide location with -DPHP_BIN=/path/php ")
-endif()
-message (STATUS "Using PHP binary " ${PHP_BIN})
 
 #-----------------------------------------------------------------------------
 # import scripts and utilities (importer only)
 #-----------------------------------------------------------------------------
 
 if (BUILD_IMPORTER)
-   set(CUSTOMSCRIPTS
-       utils/check_import_finished.php
-       utils/country_languages.php
-       utils/importWikipedia.php
-       utils/export.php
-       utils/query.php
-       utils/setup.php
-       utils/specialphrases.php
-       utils/update.php
-       utils/warm.php
-      )
+   find_file(COUNTRY_GRID_FILE country_osm_grid.sql.gz
+             PATHS ${PROJECT_SOURCE_DIR}/data
+             NO_DEFAULT_PATH
+             DOC "Location of the country grid file."
+            )
 
-   foreach (script_source ${CUSTOMSCRIPTS})
-       configure_file(${PROJECT_SOURCE_DIR}/cmake/script.tmpl
-                      ${PROJECT_BINARY_DIR}/${script_source})
-   endforeach()
+   if (NOT COUNTRY_GRID_FILE)
+       message(FATAL_ERROR "\nYou need to download the country_osm_grid first:\n"
+                           "    wget -O ${PROJECT_SOURCE_DIR}/data/country_osm_grid.sql.gz https://www.nominatim.org/data/country_grid.sql.gz")
+   endif()
+
+   configure_file(${PROJECT_SOURCE_DIR}/cmake/tool.tmpl
+                  ${PROJECT_BINARY_DIR}/nominatim)
 endif()
 
-#-----------------------------------------------------------------------------
-# webserver scripts (API only)
-#-----------------------------------------------------------------------------
-
-if (BUILD_API)
-   set(WEBSITESCRIPTS
-       website/deletable.php
-       website/details.php
-       website/hierarchy.php
-       website/lookup.php
-       website/polygons.php
-       website/reverse.php
-       website/search.php
-       website/status.php
-   )
-
-   foreach (script_source ${WEBSITESCRIPTS})
-       configure_file(${PROJECT_SOURCE_DIR}/cmake/website.tmpl
-                      ${PROJECT_BINARY_DIR}/${script_source})
-   endforeach()
-
-   set(WEBPATHS css images js)
-
-   foreach (wp ${WEBPATHS})
-       execute_process(
-           COMMAND ln -sf ${PROJECT_SOURCE_DIR}/website/${wp} ${PROJECT_BINARY_DIR}/website/
-       )
-   endforeach()
-endif()
-
-#-----------------------------------------------------------------------------
-# default settings
-#-----------------------------------------------------------------------------
-
-configure_file(${PROJECT_SOURCE_DIR}/settings/defaults.php
-               ${PROJECT_BINARY_DIR}/settings/settings.php)
-
 #-----------------------------------------------------------------------------
 # Tests
 #-----------------------------------------------------------------------------
@@ -157,21 +122,60 @@ if (BUILD_TESTS)
 
     set(TEST_BDD db osm2pgsql api)
 
-    foreach (test ${TEST_BDD})
-        add_test(NAME bdd_${test}
-                 COMMAND behave ${test}
-                 WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}/test/bdd)
-        set_tests_properties(bdd_${test}
-            PROPERTIES ENVIRONMENT "NOMINATIM_DIR=${PROJECT_BINARY_DIR}")
-    endforeach()
+    find_program(PYTHON_BEHAVE behave)
+    find_program(PYLINT NAMES pylint3 pylint)
+    find_program(PYTEST NAMES pytest py.test-3 py.test)
+    find_program(PHPCS phpcs)
+    find_program(PHPUNIT phpunit)
 
-    add_test(NAME php
-             COMMAND phpunit ./
-             WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}/test/php)
+    if (PYTHON_BEHAVE)
+        message(STATUS "Using Python behave binary ${PYTHON_BEHAVE}")
+        foreach (test ${TEST_BDD})
+            add_test(NAME bdd_${test}
+                     COMMAND ${PYTHON_BEHAVE} ${test}
+                     WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}/test/bdd)
+            set_tests_properties(bdd_${test}
+                PROPERTIES ENVIRONMENT "NOMINATIM_DIR=${PROJECT_BINARY_DIR}")
+        endforeach()
+    else()
+        message(WARNING "behave not found. BDD tests disabled." )
+    endif()
 
-    add_test(NAME phpcs
-             COMMAND phpcs --report-width=120 --colors lib website utils
-             WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})
+    if (PHPUNIT)
+        message(STATUS "Using phpunit binary ${PHPUNIT}")
+        add_test(NAME php
+                 COMMAND ${PHPUNIT} ./
+                 WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}/test/php)
+    else()
+        message(WARNING "phpunit not found. PHP unit tests disabled." )
+    endif()
+
+    if (PHPCS)
+        message(STATUS "Using phpcs binary ${PHPCS}")
+        add_test(NAME phpcs
+                 COMMAND ${PHPCS} --report-width=120 --colors lib website utils
+                 WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})
+    else()
+        message(WARNING "phpcs not found. PHP linting tests disabled." )
+    endif()
+
+    if (PYLINT)
+        message(STATUS "Using pylint binary ${PYLINT}")
+        add_test(NAME pylint
+                 COMMAND ${PYLINT} nominatim
+                 WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})
+    else()
+        message(WARNING "pylint not found. Python linting tests disabled.")
+    endif()
+
+    if (PYTEST)
+        message(STATUS "Using pytest binary ${PYTEST}")
+        add_test(NAME pytest
+                 COMMAND ${PYTEST} test/python
+                 WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})
+    else()
+        message(WARNING "pytest not found. Python tests disabled." )
+    endif()
 endif()
 
 #-----------------------------------------------------------------------------
@@ -189,3 +193,71 @@ endif()
 if (BUILD_DOCS)
    add_subdirectory(docs)
 endif()
+
+#-----------------------------------------------------------------------------
+# Manual page
+#-----------------------------------------------------------------------------
+
+if (BUILD_MANPAGE)
+   add_subdirectory(manual)
+endif()
+
+#-----------------------------------------------------------------------------
+# Installation
+#-----------------------------------------------------------------------------
+
+
+include(GNUInstallDirs)
+set(NOMINATIM_DATADIR ${CMAKE_INSTALL_FULL_DATADIR}/${PROJECT_NAME})
+set(NOMINATIM_LIBDIR ${CMAKE_INSTALL_FULL_LIBDIR}/${PROJECT_NAME})
+set(NOMINATIM_CONFIGDIR ${CMAKE_INSTALL_FULL_SYSCONFDIR}/${PROJECT_NAME})
+
+if (BUILD_IMPORTER)
+    configure_file(${PROJECT_SOURCE_DIR}/cmake/tool-installed.tmpl installed.bin)
+    install(PROGRAMS ${PROJECT_BINARY_DIR}/installed.bin
+            DESTINATION ${CMAKE_INSTALL_BINDIR}
+            RENAME nominatim)
+
+    install(DIRECTORY nominatim
+            DESTINATION ${NOMINATIM_LIBDIR}/lib-python
+            FILES_MATCHING PATTERN "*.py"
+            PATTERN __pycache__ EXCLUDE)
+    install(DIRECTORY lib-sql DESTINATION ${NOMINATIM_LIBDIR})
+
+    install(FILES data/country_name.sql
+                  ${COUNTRY_GRID_FILE}
+                  data/words.sql
+            DESTINATION ${NOMINATIM_DATADIR})
+endif()
+
+if (BUILD_OSM2PGSQL)
+    if (${CMAKE_VERSION} VERSION_LESS 3.13)
+        # Installation of subdirectory targets was only introduced in 3.13.
+        # So just copy the osm2pgsql file for older versions.
+        install(PROGRAMS ${PROJECT_BINARY_DIR}/osm2pgsql/osm2pgsql
+                DESTINATION ${NOMINATIM_LIBDIR})
+    else()
+        install(TARGETS osm2pgsql RUNTIME DESTINATION ${NOMINATIM_LIBDIR})
+    endif()
+endif()
+
+if (BUILD_MODULE)
+    install(PROGRAMS ${PROJECT_BINARY_DIR}/module/nominatim.so
+            DESTINATION ${NOMINATIM_LIBDIR}/module)
+endif()
+
+if (BUILD_API)
+    install(DIRECTORY lib-php DESTINATION ${NOMINATIM_LIBDIR})
+endif()
+
+install(FILES settings/env.defaults
+              settings/address-levels.json
+              settings/phrase-settings.json
+              settings/import-admin.style
+              settings/import-street.style
+              settings/import-address.style
+              settings/import-full.style
+              settings/import-extratags.style
+              settings/legacy_icu_tokenizer.yaml
+              settings/icu-rules/extended-unicode-to-asccii.yaml
+        DESTINATION ${NOMINATIM_CONFIGDIR})

CONTRIBUTING.md

@@ -7,41 +7,6 @@ Please always open a separate issue for each problem. In particular, do
 not add your bugs to closed issues. They may looks similar to you but
 often are completely different from the maintainer's point of view.
 
-### When Reporting Bad Search Results...
-
-Please make sure to add the following information:
-
- * the URL of the query that produces the bad result
- * the result you are getting
- * the expected result, preferably a link to the OSM object you want to find,
-   otherwise an address that is as precise as possible
-
-To get the link to the OSM object, you can try the following:
-
- * go to https://openstreetmap.org
- * zoom to the area of the map where you expect the result and
-   zoom in as much as possible
- * click on the question mark on the right side of the map,
-   then with the queston cursor on the map where your object is located
- * find the object of interest in the list that appears on the left side
- * click on the object and report the URL back that the browser shows
-
-### When Reporting Bugs...
-
-Please add the following information to your issue:
-
- * hardware configuration: RAM size, CPUs, kind and size of disks
- * Operating system (also mention if you are running on a cloud service)
- * Postgres and Postgis version
- * list of settings you changed in your Postgres configuration
- * Nominatim version (release version or,
-   if you run from the git repo, the output of `git rev-parse HEAD`)
- * (if applicable) exact command line of the command that was causing the issue
-
-Bug reports that do not include extensive information about your system,
-about the problem and about what you have been trying to debug the problem
-will be closed.
-
 ## Workflow for Pull Requests
 
 We love to get pull requests from you. We operate the "Fork & Pull" model
@@ -84,22 +49,18 @@ are in process of consolidating the style. The following rules apply:
  * for PHP variables use CamelCase with a prefixing letter indicating the type
    (i - integer, f - float, a - array, s - string, o - object)
 
-The coding style is enforced with PHPCS and can be tested with:
+The coding style is enforced with PHPCS and pylint. It can be tested with:
 
 ```
-  phpcs --report-width=120 --colors .
+phpcs --report-width=120 --colors .
+pylint3 --extension-pkg-whitelist=osmium nominatim
 ```
 
 ## Testing
 
-Before submitting a pull request make sure that the following tests pass:
+Before submitting a pull request make sure that the tests pass:
 
 ```
-  cd test/bdd
-  behave -DBUILDDIR=<builddir> db osm2pgsql
-```
-
-```
-  cd test/php
-  phpunit ./
+  cd build
+  make test
 ```

ChangeLog

@@ -1,3 +1,67 @@
+3.7.0
+
+ * switch to dotenv for configuration file
+ * introduce 'make install' (reorganising most of the code)
+ * introduce nominatim tool as replacement for various php scripts
+ * introduce project directories and allow multiple installations from same build
+ * clean up BDD tests: drop nose, reorganise step code
+ * simplify test database for API BDD tests and autoinstall database
+ * port most of the code for command-line tools to Python
+   (thanks to @darkshredder and @AntoJvlt)
+ * add tests for all tooling
+ * replace pyosmium-get-changes with custom internal implementation using
+   pyosmium
+ * improve search for queries with housenumber and partial terms
+ * add database versioning
+ * use jinja2 for preprocessing SQL files
+ * introduce automatic migrations
+ * reverse fix preference of interpolations over housenumbers
+ * parallelize indexing of postcodes
+ * add non-key indexes to speed up housenumber + street searches
+ * switch housenumber field in placex to save transliterated names
+
+
+3.6.0
+
+ * add full support for searching by and displaying of addr:* tags
+ * improve address output for large-area objects
+ * better use of country names from OSM data for search and display
+ * better debug output for reverse call
+ * add support for addr:place links without an place equivalent in OSM
+ * improve finding postcodes with normalisation artefacts
+ * batch object to index for rank 30, avoiding a wrap-around of transaction
+   IDs in PostgreSQL
+ * introduce dynamic address rank computation for administrative boundaries
+   depending on linked objects and their place in the admin level hierarchy
+ * add country-specific address ranking for Indonesia, Russia, Belgium and
+   the Netherlands (thanks @hendrikmoree)
+ * make sure wikidata/wikipedia tags are imported for all styles
+ * make POIs searchable by name and housenumber (thanks @joy-yyd)
+ * reverse geocoding now ignores places without an address rank (rivers etc.)
+ * installation of a webserver is no longer mandatory, for development
+   use the php internal webserver via 'make serve
+ * reduce the influence of place nodes in addresses
+ * drop support for the unspecific is_in tag
+ * various minor tweaks to supplied styles
+ * move HTML web frontend into its own project
+ * move scripts for processing external data sources into separate directories
+ * introduce separate configuration for website (thanks @krahulreddy)
+ * update documentation, in particular, clean up development docs
+ * update osm2pgsql to 1.4.0
+
+3.5.2
+
+ * ensure that wikipedia tags are imported for all styles
+ * reinstate verbosity for indexing during updates
+ * make house number reappear in display name on named POIs
+ * introduce batch processing in indexer to avoid transaction ID overrun
+ * increase splitting for large geometries to improve indexing speed
+ * remove deprecated get_magic_quotes_gpc() function
+ * make sure that all postcodes have an entry in word and are thus searchable
+ * remove use of ST_Covers in conjunction woth ST_Intersects,
+   causes bad query planning and slow updates in Postgis3
+ * update osm2pgsql
+
 3.5.1
 
  * disable jit and parallel processing in PostgreSQL for osm2pgsql
@@ -17,7 +81,7 @@
  * cleanup of partition function
  * improve parenting for large POIs
  * add support for Postgresql 12 and Postgis 3
- * add earlier cleanup when --drop is given, to reduce meory usage
+ * add earlier cleanup when --drop is given, to reduce memory usage
  * remove use of place_id in URLs
  * replace C nominatim indexer with a simpler Python implementation
  * split up the huge sql/functions.sql file

README.md

@@ -1,4 +1,5 @@
-[![Build Status](https://travis-ci.org/osm-search/Nominatim.svg?branch=master)](https://travis-ci.org/osm-search/Nominatim)
+[![Build Status](https://github.com/osm-search/Nominatim/workflows/CI%20Tests/badge.svg)](https://github.com/osm-search/Nominatim/actions?query=workflow%3A%22CI+Tests%22)
+[![codecov](https://codecov.io/gh/osm-search/Nominatim/branch/master/graph/badge.svg?token=8P1LXrhCMy)](https://codecov.io/gh/osm-search/Nominatim)
 
 Nominatim
 =========
@@ -24,15 +25,14 @@ 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. You can ask questions on the mailing list
-(see below) or on [help.openstreetmap.org](https://help.openstreetmap.org/).**
+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/).
 
-Detailed installation instructions for the development version can be
-found at [nominatim.org](https://nominatim.org/release-docs/develop/admin/Installation)
-as well.
+[Detailed installation instructions for current master](https://nominatim.org/release-docs/develop/admin/Installation)
+can be found at nominatim.org as well.
 
 A quick summary of the necessary steps:
 
@@ -42,12 +42,15 @@ A quick summary of the necessary steps:
         cd build
         cmake ..
         make
+        sudo make install
 
-2. Get OSM data and import:
+2. Create a project directory, get OSM data and import:
 
-        ./build/utils/setup.php --osm-file <your planet file> --all
+        mkdir nominatim-project
+        cd nominatim-project
+        nominatim import --osm-file <your planet file>
 
-3. Point your webserver to the ./build/website directory.
+3. Point your webserver to the nominatim-project/website directory.
 
 
 License
@@ -59,13 +62,14 @@ The source code is available under a GPLv2 license.
 Contributing
 ============
 
-Contributions are welcome. For details see [contribution guide](CONTRIBUTING.md).
-
-Both bug reports and pull requests are welcome.
+Contributions, bugreport and pull requests are welcome.
+For details see [contribution guide](CONTRIBUTING.md).
 
 
-Mailing list
-============
+Questions and help
+==================
 
-For questions you can join the geocoding mailing list, see
-https://lists.openstreetmap.org/listinfo/geocoding
+For questions, community help and discussions you can use the
+[Github discussions forum](https://github.com/osm-search/Nominatim/discussions)
+or join the
+[geocoding mailing list](https://lists.openstreetmap.org/listinfo/geocoding).

SECURITY.md

@@ -0,0 +1,39 @@
+# Security Policy
+
+## Supported Versions
+
+All Nominatim releases receive security updates for two years.
+
+The following table lists the end of support for all currently supported
+versions.
+
+| Version | End of support for security updates |
+| ------- | ----------------------------------- |
+| 3.7.x   | 2023-04-05                          |
+| 3.6.x   | 2022-12-12                          |
+| 3.5.x   | 2022-06-05                          |
+| 3.4.x   | 2021-10-24                          |
+
+## Reporting a Vulnerability
+
+If you believe, you have found an issue in Nominatim that has implications on
+security, please send a description of the issue to **security@nominatim.org**.
+You will receive an acknowledgement of your mail within 3 work days where we
+also notify you of the next steps.
+
+## How we Disclose Security Issues
+
+** The following section only applies to security issues found in released
+versions. Issues that concern the master development branch only will be
+fixed immediately on the branch with the corresponding PR containing the
+description of the nature and severity of the issue. **
+
+Patches for identified security issues are applied to all affected versions and
+new minor versions are released. At the same time we release a statement at
+the [Nominatim blog](https://nominatim.org/blog/) describing the nature of the
+incident. Announcements will also be published at the
+[geocoding mailinglist](https://lists.openstreetmap.org/listinfo/geocoding).
+
+## List of Previous Incidents
+
+* 2020-05-04 - [SQL injection issue on /details endpoint](https://lists.openstreetmap.org/pipermail/geocoding/2020-May/002012.html)

VAGRANT.md

@@ -160,9 +160,9 @@ You can configure/download other Vagrant boxes from [https://app.vagrantup.com/b
 
 Let's say you have a Postgres database named `nominatim_it` on server `your-server.com` and port `5432`. The Postgres username is `postgres`. You can edit `settings/local.php` and point Nominatim to it.
 
-    pgsql://postgres@your-server.com:5432/nominatim_it
+    pgsql:host=your-server.com;port=5432;user=postgres;dbname=nominatim_it
     
-No data import necessary or restarting necessary.
+No data import or restarting necessary.
 
 If the Postgres installation is behind a firewall, you can try
 

Vagrantfile

@@ -4,18 +4,38 @@
 Vagrant.configure("2") do |config|
   # Apache webserver
   config.vm.network "forwarded_port", guest: 80, host: 8089
+  config.vm.network "forwarded_port", guest: 8088, host: 8088
 
   # If true, then any SSH connections made will enable agent forwarding.
   config.ssh.forward_agent = true
 
+  # Never sync the current directory to /vagrant.
+  config.vm.synced_folder ".", "/vagrant", disabled: true
+
   checkout = "yes"
   if ENV['CHECKOUT'] != 'y' then
-      config.vm.synced_folder ".", "/home/vagrant/Nominatim"
-      checkout = "no"
+    checkout = "no"
+  end
+
+  config.vm.provider "virtualbox" do |vb, override|
+    vb.gui = false
+    vb.memory = 2048
+    vb.customize ["setextradata", :id, "VBoxInternal2/SharedFoldersEnableSymlinksCreate//vagrant","0"]
+    if ENV['CHECKOUT'] != 'y' then
+      override.vm.synced_folder ".", "/home/vagrant/Nominatim"
+    end
+  end
+
+  config.vm.provider "libvirt" do |lv, override|
+    lv.memory = 2048
+    lv.nested = true
+    if ENV['CHECKOUT'] != 'y' then
+      override.vm.synced_folder ".", "/home/vagrant/Nominatim", type: 'nfs'
+    end
   end
 
   config.vm.define "ubuntu", primary: true do |sub|
-      sub.vm.box = "bento/ubuntu-20.04"
+      sub.vm.box = "generic/ubuntu2004"
       sub.vm.provision :shell do |s|
         s.path = "vagrant/Install-on-Ubuntu-20.sh"
         s.privileged = false
@@ -23,8 +43,26 @@ Vagrant.configure("2") do |config|
       end
   end
 
-  config.vm.define "ubuntu18", primary: true do |sub|
-      sub.vm.box = "bento/ubuntu-18.04"
+  config.vm.define "ubuntu-apache" do |sub|
+      sub.vm.box = "generic/ubuntu2004"
+      sub.vm.provision :shell do |s|
+        s.path = "vagrant/Install-on-Ubuntu-20.sh"
+        s.privileged = false
+        s.args = [checkout, "install-apache"]
+      end
+  end
+
+  config.vm.define "ubuntu-nginx" do |sub|
+      sub.vm.box = "generic/ubuntu2004"
+      sub.vm.provision :shell do |s|
+        s.path = "vagrant/Install-on-Ubuntu-20.sh"
+        s.privileged = false
+        s.args = [checkout, "install-nginx"]
+      end
+  end
+
+  config.vm.define "ubuntu18" do |sub|
+      sub.vm.box = "generic/ubuntu1804"
       sub.vm.provision :shell do |s|
         s.path = "vagrant/Install-on-Ubuntu-18.sh"
         s.privileged = false
@@ -32,60 +70,41 @@ Vagrant.configure("2") do |config|
       end
   end
 
-  config.vm.define "ubuntu18nginx" do |sub|
-      sub.vm.box = "bento/ubuntu-18.04"
+  config.vm.define "ubuntu18-apache" do |sub|
+      sub.vm.box = "generic/ubuntu1804"
       sub.vm.provision :shell do |s|
-        s.path = "vagrant/Install-on-Ubuntu-18-nginx.sh"
+        s.path = "vagrant/Install-on-Ubuntu-18.sh"
         s.privileged = false
-        s.args = [checkout]
+        s.args = [checkout, "install-apache"]
       end
   end
 
-  config.vm.define "ubuntu16" do |sub|
-      sub.vm.box = "bento/ubuntu-16.04"
+  config.vm.define "ubuntu18-nginx" do |sub|
+      sub.vm.box = "generic/ubuntu1804"
       sub.vm.provision :shell do |s|
-        s.path = "vagrant/Install-on-Ubuntu-16.sh"
+        s.path = "vagrant/Install-on-Ubuntu-18.sh"
         s.privileged = false
-        s.args = [checkout]
+        s.args = [checkout, "install-nginx"]
       end
   end
 
-  config.vm.define "travis" do |sub|
-      sub.vm.box = "bento/ubuntu-14.04"
+  config.vm.define "centos7" do |sub|
+      sub.vm.box = "centos/7"
       sub.vm.provision :shell do |s|
-        s.path = "vagrant/install-on-travis-ci.sh"
+        s.path = "vagrant/Install-on-Centos-7.sh"
         s.privileged = false
         s.args = [checkout]
       end
   end
 
   config.vm.define "centos" do |sub|
-      sub.vm.box = "centos/7"
-      sub.vm.provision :shell do |s|
-        s.path = "vagrant/Install-on-Centos-7.sh"
-        s.privileged = false
-        s.args = "yes"
-      end
-      sub.vm.synced_folder ".", "/home/vagrant/Nominatim", disabled: true
-      sub.vm.synced_folder ".", "/vagrant", disabled: true
-  end
-
-  config.vm.define "centos8" do |sub|
       sub.vm.box = "generic/centos8"
       sub.vm.provision :shell do |s|
         s.path = "vagrant/Install-on-Centos-8.sh"
         s.privileged = false
-        s.args = "yes"
+        s.args = [checkout]
       end
-      sub.vm.synced_folder ".", "/home/vagrant/Nominatim", disabled: true
-      sub.vm.synced_folder ".", "/vagrant", disabled: true
   end
 
 
-  config.vm.provider "virtualbox" do |vb|
-    vb.gui = false
-    vb.memory = 2048
-    vb.customize ["setextradata", :id, "VBoxInternal2/SharedFoldersEnableSymlinksCreate//vagrant","0"]
-  end
-
 end

cmake/script.tmpl

@@ -1,4 +0,0 @@
-#!@PHP_BIN@ -Cq
-<?php
-require_once(dirname(dirname(__FILE__)).'/settings/settings.php');
-require_once(CONST_BasePath.'/@script_source@');

cmake/tool-installed.tmpl

@@ -0,0 +1,17 @@
+#!/usr/bin/env python3
+import sys
+import os
+
+sys.path.insert(1, '@NOMINATIM_LIBDIR@/lib-python')
+
+os.environ['NOMINATIM_NOMINATIM_TOOL'] = os.path.abspath(__file__)
+
+from nominatim import cli
+
+exit(cli.nominatim(module_dir='@NOMINATIM_LIBDIR@/module',
+                   osm2pgsql_path='@NOMINATIM_LIBDIR@/osm2pgsql',
+                   phplib_dir='@NOMINATIM_LIBDIR@/lib-php',
+                   sqllib_dir='@NOMINATIM_LIBDIR@/lib-sql',
+                   data_dir='@NOMINATIM_DATADIR@',
+                   config_dir='@NOMINATIM_CONFIGDIR@',
+                   phpcgi_path='@PHPCGI_BIN@'))

cmake/tool.tmpl

@@ -0,0 +1,17 @@
+#!/usr/bin/env python3
+import sys
+import os
+
+sys.path.insert(1, '@CMAKE_SOURCE_DIR@')
+
+os.environ['NOMINATIM_NOMINATIM_TOOL'] = os.path.abspath(__file__)
+
+from nominatim import cli
+
+exit(cli.nominatim(module_dir='@CMAKE_BINARY_DIR@/module',
+                   osm2pgsql_path='@CMAKE_BINARY_DIR@/osm2pgsql/osm2pgsql',
+                   phplib_dir='@CMAKE_SOURCE_DIR@/lib-php',
+                   sqllib_dir='@CMAKE_SOURCE_DIR@/lib-sql',
+                   data_dir='@CMAKE_SOURCE_DIR@/data',
+                   config_dir='@CMAKE_SOURCE_DIR@/settings',
+                   phpcgi_path='@PHPCGI_BIN@'))

cmake/website.tmpl

@@ -1,3 +0,0 @@
-<?php
-require_once(dirname(dirname(__FILE__)).'/settings/settings.php');
-require_once(CONST_BasePath.'/@script_source@');

codecov.yml

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

data-sources/country-grid/README.md

@@ -1,77 +0,0 @@
-# Fallback Country Boundaries
-
-Each place is assigned a `country_code` and partition. Partitions derive from `country_code`.
-
-Nominatim imports two pre-generated files
-
-   * `data/country_name.sql` (country code, name, default language, partition)
-   * `data/country_osm_grid.sql` (country code, geometry)
-
-before creating places in the database. This helps with fast lookups and missing data (e.g. if the data the user wants to import doesn't contain any country places).
-
-The number of countries in the world can change (South Sudan created 2011, Germany reunification), so can their boundaries. This document explain how the pre-generated files can be updated.
-
-
-
-## Country code
-
-Each place is assigned a two letter country_code based on its location, e.g. `gb` for Great Britain. Or `NULL` if no suitable country is found (usually it's in open water then).
-
-In `sql/functions.sql: get_country_code(geometry)` the place's center is checked against
-
-   1. country places already imported from the user's data file. Places are imported by rank low-to-high. Lowest rank 2 is countries so most places should be matched. Still the data file might be incomplete.
-   2. if unmatched: OSM grid boundaries
-   3. if still unmatched: OSM grid boundaries, but allow a small distance
-
-
-
-## Partitions
-
-Each place is assigned partition, which is a number 0..250. 0 is fallback/other.
-
-During place indexing (`sql/functions.sql: placex_insert()`) a place is assigned the partition based on its country code (`sql/functions.sql: get_partition(country_code)`). It checks in the `country_name` table.
-
-Most countries have their own partition, some share a partition. Thus partition counts vary greatly.
-
-Several database tables are split by partition to allow queries to run against less indices and improve caching.
-
-   * `location_area_large_<partition>`
-   * `search_name_<partition>`
-   * `location_road_<partition>`
-
-
-
-
-
-## Data files
-
-### data/country_name.sql
-
-Export from existing database table plus manual changes. `country_default_language_code` most taken from [https://wiki.openstreetmap.org/wiki/Nominatim/Country_Codes](), see `utils/country_languages.php`.
-
-
-
-### data/country_osm_grid.sql
-
-`country_grid.sql` merges territories by country. Then uses `function.sql: quad_split_geometry` to split each country into multiple [Quadtree](https://en.wikipedia.org/wiki/Quadtree) polygons for faster point-in-polygon lookups.
-
-To visualize one country as geojson feature collection, e.g. for loading into [geojson.io](http://geojson.io/):
-
-```
--- http://www.postgresonline.com/journal/archives/267-Creating-GeoJSON-Feature-Collections-with-JSON-and-PostGIS-functions.html
-
-SELECT row_to_json(fc)
-FROM (
-  SELECT 'FeatureCollection' As type, array_to_json(array_agg(f)) As features
-  FROM (
-    SELECT 'Feature' As type,
-    ST_AsGeoJSON(lg.geometry)::json As geometry,
-    row_to_json((country_code, area)) As properties
-    FROM country_osm_grid As lg where country_code='mx'
-  ) As f
-) As fc;
-```
-
-`cat /tmp/query.sql | psql -At nominatim > /tmp/mexico.quad.geojson`
-
-![mexico](mexico.quad.png)

data-sources/country-grid/country_grid.sql

@@ -1,33 +0,0 @@
--- Script to build a calculated country grid from existing tables
-DROP TABLE IF EXISTS tmp_country_osm_grid;
-CREATE TABLE tmp_country_osm_grid as select country_name.country_code,st_union(placex.geometry) as geometry from country_name,
-  placex
-  where (lower(placex.country_code) = country_name.country_code)
-    and placex.rank_search < 16 and st_area(placex.geometry) > 0 
-  group by country_name.country_code;
-ALTER TABLE tmp_country_osm_grid add column area double precision;
-UPDATE tmp_country_osm_grid set area = st_area(geometry::geography);
-
--- compare old and new
-select country_code, round, round(log(area)) from (select distinct country_code,round(log(area)) from country_osm_grid order by country_code) as x 
-  left outer join tmp_country_osm_grid using (country_code) where area is null or round(log(area)) != round;
-
-DROP TABLE IF EXISTS new_country_osm_grid;
-CREATE TABLE new_country_osm_grid as select country_code,area,quad_split_geometry(geometry,0.5,20) as geometry from tmp_country_osm_grid;
-CREATE INDEX new_idx_country_osm_grid_geometry ON new_country_osm_grid USING GIST (geometry);
-
--- Sometimes there are problems calculating area due to invalid data - optionally recalc
-UPDATE new_country_osm_grid set area = sum from (select country_code,sum(case when st_area(geometry::geography) = 'NaN' THEN 0 ELSE st_area(geometry::geography) END) 
- from new_country_osm_grid group by country_code) as x where x.country_code = new_country_osm_grid.country_code;
-
--- compare old and new
-select country_code, x.round, y.round from (select distinct country_code,round(log(area)) from country_osm_grid order by country_code) as x
-  left outer join (select distinct country_code,round(log(area)) from new_country_osm_grid order by country_code) as y
-    using (country_code) where x.round != y.round;
-
--- Flip the new table in
-BEGIN;
-DROP TABLE IF EXISTS country_osm_grid;
-ALTER TABLE new_country_osm_grid rename to country_osm_grid;
-ALTER INDEX new_idx_country_osm_grid_geometry RENAME TO idx_country_osm_grid_geometry;
-COMMIT;

data-sources/gb-postcodes/README.md

@@ -1,56 +0,0 @@
-# GB Postcodes
-
-
-The server [importing instructions](https://www.nominatim.org/release-docs/latest/admin/Import-and-Update/) allow optionally download [`gb_postcode_data.sql.gz`](https://www.nominatim.org/data/gb_postcode_data.sql.gz). This document explains how the file got created.
-
-## GB vs UK
-
-GB (Great Britain) is more correct as the Ordnance Survey dataset doesn't contain postcodes from Northern Ireland.
-
-## Importing separately after the initial import
-
-If you forgot to download the file, or have a new version, you can import it separately:
-
-1. Import the downloaded `gb_postcode_data.sql.gz` file.
-
-2. Run the SQL query `SELECT count(getorcreate_postcode_id(postcode)) FROM gb_postcode;`. This will update the search index.
-
-3. Run `utils/setup.php --calculate-postcodes` from the build directory. This will copy data form the `gb_postcode` table to the `location_postcodes` table.
-
-
-
-## Converting Code-Point Open data
-
-1. Download from [Code-Point® Open](https://www.ordnancesurvey.co.uk/business-and-government/products/code-point-open.html). It requires an email address where a download link will be send to.
-
-2. `unzip codepo_gb.zip`
-
-    Unpacked you'll see a directory of CSV files.
-
-        $ more codepo_gb/Data/CSV/n.csv
-        "N1 0AA",10,530626,183961,"E92000001","E19000003","E18000007","","E09000019","E05000368"
-        "N1 0AB",10,530559,183978,"E92000001","E19000003","E18000007","","E09000019","E05000368"
-
-    The coordinates are "Northings" and "Eastings" in [OSGB 1936](http://epsg.io/1314) projection. They can be projected to WGS84 like this
-
-        SELECT ST_AsText(ST_Transform(ST_SetSRID('POINT(530626 183961)'::geometry,27700), 4326));
-        POINT(-0.117872733220225 51.5394424719303)
-
-    [-0.117872733220225 51.5394424719303 on OSM map](https://www.openstreetmap.org/?mlon=-0.117872733220225&mlat=51.5394424719303&zoom=16)
-
-
-
-3. Create database, import CSV files, add geometry column, dump into file
-
-        DBNAME=create_gb_postcode_file
-        createdb $DBNAME
-        echo 'CREATE EXTENSION postgis' | psql $DBNAME
-
-        cat data/gb_postcode_table.sql | psql $DBNAME      
-        cat codepo_gb/Data/CSV/*.csv | ./data-sources/gb-postcodes/convert_codepoint.php | psql $DBNAME
-        cat codepo_gb/Doc/licence.txt | iconv -f iso-8859-1 -t utf-8 | dos2unix | sed 's/^/-- /g' > gb_postcode_data.sql
-        pg_dump -a -t gb_postcode $DBNAME | grep -v '^--' >> gb_postcode_data.sql
-      
-        gzip -9 -f gb_postcode_data.sql
-        ls -lah gb_postcode_data.*
-        # dropdb $DBNAME

data-sources/gb-postcodes/convert_codepoint.php

@@ -1,37 +0,0 @@
-#!/usr/bin/env php
-<?php
-
-echo <<< EOT
-
-ALTER TABLE gb_postcode ADD COLUMN easting bigint;
-ALTER TABLE gb_postcode ADD COLUMN northing bigint;
-
-TRUNCATE gb_postcode;
-
-COPY gb_postcode (id, postcode, easting, northing) FROM stdin;
-
-EOT;
-
-$iCounter = 0;
-while ($sLine = fgets(STDIN)) {
-    $aColumns = str_getcsv($sLine);
-
-    // insert space before the third last position
-    // https://stackoverflow.com/a/9144834
-    $postcode = $aColumns[0];
-    $postcode = preg_replace('/\s*(...)$/', ' $1', $postcode);
-
-    echo join("\t", array($iCounter, $postcode, $aColumns[2], $aColumns[3]))."\n";
-
-    $iCounter = $iCounter + 1;
-}
-
-echo <<< EOT
-\.
-
-UPDATE gb_postcode SET geometry=ST_Transform(ST_SetSRID(CONCAT('POINT(', easting, ' ', northing, ')')::geometry, 27700), 4326);
-
-ALTER TABLE gb_postcode DROP COLUMN easting;
-ALTER TABLE gb_postcode DROP COLUMN northing;
-
-EOT;

data-sources/us-tiger/README.md

@@ -1,26 +0,0 @@
-# US TIGER address data
-
-Convert [TIGER](https://www.census.gov/geographies/mapping-files/time-series/geo/tiger-line-file.html)/Line dataset of the US Census Bureau to SQL files which can be imported by Nominatim. The created tables in the Nominatim database are separate from OpenStreetMap tables and get queried at search time separately.
-
-The dataset gets updated once per year. Downloading is prone to be slow (can take a full day) and converting them can take hours as well.
-
-Replace '2019' with the current year throughout.
-
-  1. Install the GDAL library and python bindings and the unzip tool
-
-        # Ubuntu:
-        sudo apt-get install python3-gdal unzip
-
-  2. Get the TIGER 2019 data. You will need the EDGES files
-     (3,233 zip files, 11GB total).
-
-         wget -r ftp://ftp2.census.gov/geo/tiger/TIGER2019/EDGES/
-
-  3. Convert the data into SQL statements. Adjust the file paths in the scripts as needed
-
-        cd data-sources/us-tiger
-        ./convert.sh <input-path> <output-path>
-
-  4. Maybe: package the created files
-  
-        tar -czf tiger2019-nominatim-preprocessed.tar.gz tiger

data-sources/us-tiger/convert.sh

@@ -1,48 +0,0 @@
-#!/bin/bash
-
-INPATH=$1
-OUTPATH=$2
-
-if [[ ! -d "$INPATH" ]]; then
-    echo "input path does not exist"
-    exit 1
-fi
-
-if [[ ! -d "$OUTPATH" ]]; then
-    echo "output path does not exist"
-    exit 1
-fi
-
-INREGEX='_([0-9]{5})_edges.zip'
-WORKPATH="$OUTPATH/tmp-workdir/"
-mkdir -p "$WORKPATH"
-
-
-
-INFILES=($INPATH/*.zip)
-echo "Found ${#INFILES[*]} files."
-
-for F in ${INFILES[*]}; do
-    # echo $F
-
-    if [[ "$F" =~ $INREGEX ]]; then
-        COUNTYID=${BASH_REMATCH[1]}
-        SHAPEFILE="$WORKPATH/$(basename $F '.zip').shp"
-        SQLFILE="$OUTPATH/$COUNTYID.sql"
-
-        unzip -o -q -d "$WORKPATH" "$F"
-        if [[ ! -e "$SHAPEFILE" ]]; then
-            echo "Unzip failed. $SHAPEFILE not found."
-            exit 1
-        fi
-
-        ./tiger_address_convert.py "$SHAPEFILE" "$SQLFILE"
-
-        rm $WORKPATH/*
-    fi
-done
-
-OUTFILES=($OUTPATH/*.sql)
-echo "Wrote ${#OUTFILES[*]} files."
-
-rmdir $WORKPATH

data-sources/us-tiger/tiger_address_convert.py

@@ -1,620 +0,0 @@
-#!/usr/bin/python3
-# Tiger road data to OSM conversion script
-# Creates Karlsruhe-style address ways beside the main way
-# based on the Massachusetts GIS script by christopher schmidt
-
-#BUGS:
-# On very tight curves, a loop may be generated in the address way.
-# It would be nice if the ends of the address ways were not pulled back from dead ends
-
-
-# Ways that include these mtfccs should not be uploaded
-# H1100 Connector
-# H3010 Stream/River
-# H3013 Braided Stream
-# H3020 Canal, Ditch or Aqueduct
-# L4130 Point-to-Point Line
-# L4140 Property/Parcel Line (Including PLSS)
-# P0001 Nonvisible Linear Legal/Statistical Boundary
-# P0002 Perennial Shoreline
-# P0003 Intermittent Shoreline
-# P0004 Other non-visible bounding Edge (e.g., Census water boundary, boundary of an areal feature)
-ignoremtfcc = [ "H1100", "H3010", "H3013", "H3020", "L4130", "L4140", "P0001", "P0002", "P0003", "P0004" ]
-
-# Sets the distance that the address ways should be from the main way, in feet.
-address_distance = 30
-
-# Sets the distance that the ends of the address ways should be pulled back from the ends of the main way, in feet
-address_pullback = 45
-
-import sys, os.path, json
-try:
-    from osgeo import ogr
-    from osgeo import osr
-except:
-    import ogr
-    import osr
-
-# https://www.census.gov/geo/reference/codes/cou.html 
-# tiger_county_fips.json was generated from the following:
-# wget https://www2.census.gov/geo/docs/reference/codes/files/national_county.txt
-# cat national_county.txt | perl -F, -naE'($F[0] ne 'AS') && $F[3] =~ s/ ((city|City|County|District|Borough|City and Borough|Municipio|Municipality|Parish|Island|Census Area)(?:, |\Z))+//; say qq(  "$F[1]$F[2]": "$F[3], $F[0]",)'
-json_fh = open(os.path.dirname(sys.argv[0]) + "/tiger_county_fips.json")
-county_fips_data = json.load(json_fh)
-
-def parse_shp_for_geom_and_tags( filename ):
-    #ogr.RegisterAll()
-
-    dr = ogr.GetDriverByName("ESRI Shapefile")
-    poDS = dr.Open( filename )
-
-    if poDS == None:
-        raise "Open failed."
-
-    poLayer = poDS.GetLayer( 0 )
-
-    fieldNameList = []
-    layerDefinition = poLayer.GetLayerDefn()
-    for i in range(layerDefinition.GetFieldCount()):
-        fieldNameList.append(layerDefinition.GetFieldDefn(i).GetName())
-    # sys.stderr.write(",".join(fieldNameList))
-
-    poLayer.ResetReading()
-
-    ret = []
-
-    poFeature = poLayer.GetNextFeature()
-    while poFeature:
-        tags = {}
-        
-        # WAY ID
-        tags["tiger:way_id"] = int( poFeature.GetField("TLID") )
-        
-        # FEATURE IDENTIFICATION
-        mtfcc = poFeature.GetField("MTFCC");
-        if mtfcc != None:
-
-            if mtfcc == "L4010":        #Pipeline
-                tags["man_made"] = "pipeline"
-            if mtfcc == "L4020":        #Powerline
-                tags["power"] = "line"
-            if mtfcc == "L4031":        #Aerial Tramway/Ski Lift
-                tags["aerialway"] = "cable_car"
-            if mtfcc == "L4110":        #Fence Line
-                tags["barrier"] = "fence"
-            if mtfcc == "L4125":        #Cliff/Escarpment
-                tags["natural"] = "cliff"
-            if mtfcc == "L4165":        #Ferry Crossing
-                tags["route"] = "ferry"
-            if mtfcc == "R1011":        #Railroad Feature (Main, Spur, or Yard)
-                tags["railway"] = "rail"
-                ttyp = poFeature.GetField("TTYP")
-                if ttyp != None:
-                    if ttyp == "S":
-                        tags["service"] = "spur"
-                    if ttyp == "Y":
-                        tags["service"] = "yard"
-                    tags["tiger:ttyp"] = ttyp
-            if mtfcc == "R1051":        #Carline, Streetcar Track, Monorail, Other Mass Transit Rail)
-                tags["railway"] = "light_rail"
-            if mtfcc == "R1052":        #Cog Rail Line, Incline Rail Line, Tram
-                tags["railway"] = "incline"
-            if mtfcc == "S1100":
-                tags["highway"] = "primary"
-            if mtfcc == "S1200":
-                tags["highway"] = "secondary"
-            if mtfcc == "S1400":
-                tags["highway"] = "residential"
-            if mtfcc == "S1500":
-                tags["highway"] = "track"
-            if mtfcc == "S1630":        #Ramp
-                tags["highway"] = "motorway_link"
-            if mtfcc == "S1640":        #Service Drive usually along a limited access highway
-                tags["highway"] = "service"
-            if mtfcc == "S1710":        #Walkway/Pedestrian Trail
-                tags["highway"] = "path"
-            if mtfcc == "S1720":
-                tags["highway"] = "steps"
-            if mtfcc == "S1730":        #Alley
-                tags["highway"] = "service"
-                tags["service"] = "alley"
-            if mtfcc == "S1740":        #Private Road for service vehicles (logging, oil, fields, ranches, etc.)
-                tags["highway"] = "service"
-                tags["access"] = "private"
-            if mtfcc == "S1750":        #Private Driveway
-                tags["highway"] = "service"
-                tags["access"] = "private"
-                tags["service"] = "driveway"
-            if mtfcc == "S1780":        #Parking Lot Road
-                tags["highway"] = "service"
-                tags["service"] = "parking_aisle"
-            if mtfcc == "S1820":        #Bike Path or Trail
-                tags["highway"] = "cycleway"
-            if mtfcc == "S1830":        #Bridle Path
-                tags["highway"] = "bridleway"
-            tags["tiger:mtfcc"] = mtfcc
-
-        # FEATURE NAME
-        if poFeature.GetField("FULLNAME"):
-            #capitalizes the first letter of each word
-            name = poFeature.GetField( "FULLNAME" )
-            tags["name"] = name
-
-            #Attempt to guess highway grade
-            if name[0:2] == "I-":
-                tags["highway"] = "motorway"
-            if name[0:3] == "US ":
-                tags["highway"] = "primary"
-            if name[0:3] == "US-":
-                tags["highway"] = "primary"
-            if name[0:3] == "Hwy":
-                if tags["highway"] != "primary":
-                    tags["highway"] = "secondary"
-
-        # TIGER 2017 no longer contains this field
-        if 'DIVROAD' in fieldNameList:
-            divroad = poFeature.GetField("DIVROAD")
-            if divroad != None:
-                if divroad == "Y" and "highway" in tags and tags["highway"] == "residential":
-                    tags["highway"] = "tertiary"
-                tags["tiger:separated"] = divroad
-
-        statefp = poFeature.GetField("STATEFP")
-        countyfp = poFeature.GetField("COUNTYFP")
-        if (statefp != None) and (countyfp != None):
-            county_name = county_fips_data.get(statefp + '' + countyfp)
-            if county_name:
-                tags["tiger:county"] = county_name
-
-        # tlid = poFeature.GetField("TLID")
-        # if tlid != None:
-        #     tags["tiger:tlid"] = tlid
-
-        lfromadd = poFeature.GetField("LFROMADD")
-        if lfromadd != None:
-            tags["tiger:lfromadd"] = lfromadd
-
-        rfromadd = poFeature.GetField("RFROMADD")
-        if rfromadd != None:
-            tags["tiger:rfromadd"] = rfromadd
-
-        ltoadd = poFeature.GetField("LTOADD")
-        if ltoadd != None:
-            tags["tiger:ltoadd"] = ltoadd
-
-        rtoadd = poFeature.GetField("RTOADD")
-        if rtoadd != None:
-            tags["tiger:rtoadd"] = rtoadd
-
-        zipl = poFeature.GetField("ZIPL")
-        if zipl != None:
-            tags["tiger:zip_left"] = zipl
-
-        zipr = poFeature.GetField("ZIPR")
-        if zipr != None:
-            tags["tiger:zip_right"] = zipr
-
-        if mtfcc not in ignoremtfcc:
-            # COPY DOWN THE GEOMETRY
-            geom = []
-            
-            rawgeom = poFeature.GetGeometryRef()
-            for i in range( rawgeom.GetPointCount() ):
-                geom.append( (rawgeom.GetX(i), rawgeom.GetY(i)) )
-    
-            ret.append( (geom, tags) )
-        poFeature = poLayer.GetNextFeature()
-        
-    return ret
-
-
-# ====================================
-# to do read .prj file for this data
-# Change the Projcs_wkt to match your datas prj file.
-# ====================================
-projcs_wkt = \
-"""GEOGCS["GCS_North_American_1983",
-        DATUM["D_North_American_1983",
-        SPHEROID["GRS_1980",6378137,298.257222101]],
-        PRIMEM["Greenwich",0],
-        UNIT["Degree",0.017453292519943295]]"""
-
-from_proj = osr.SpatialReference()
-from_proj.ImportFromWkt( projcs_wkt )
-
-# output to WGS84
-to_proj = osr.SpatialReference()
-to_proj.SetWellKnownGeogCS( "EPSG:4326" )
-
-tr = osr.CoordinateTransformation( from_proj, to_proj )
-
-import math
-def length(segment, nodelist):
-    '''Returns the length (in feet) of a segment'''
-    first = True
-    distance = 0
-    lat_feet = 364613  #The approximate number of feet in one degree of latitude
-    for point in segment:
-        pointid, (lat, lon) = nodelist[ round_point( point ) ]
-        if first:
-            first = False
-        else:
-            #The approximate number of feet in one degree of longitute
-            lrad = math.radians(lat)
-            lon_feet = 365527.822 * math.cos(lrad) - 306.75853 * math.cos(3 * lrad) + 0.3937 * math.cos(5 * lrad)
-            distance += math.sqrt(((lat - previous[0])*lat_feet)**2 + ((lon - previous[1])*lon_feet)**2)
-        previous = (lat, lon)
-    return distance
-
-def addressways(waylist, nodelist, first_id):
-    id = first_id
-    lat_feet = 364613  #The approximate number of feet in one degree of latitude
-    distance = float(address_distance)
-    ret = []
-
-    for waykey, segments in waylist.items():
-        waykey = dict(waykey)
-        rsegments = []
-        lsegments = []
-        for segment in segments:
-            lsegment = []
-            rsegment = []
-            lastpoint = None
-
-            # Don't pull back the ends of very short ways too much
-            seglength = length(segment, nodelist)
-            if seglength < float(address_pullback) * 3.0:
-                pullback = seglength / 3.0
-            else:
-                pullback = float(address_pullback)
-            if "tiger:lfromadd" in waykey:
-                lfromadd = waykey["tiger:lfromadd"]
-            else:
-                lfromadd = None
-            if "tiger:ltoadd" in waykey:
-                ltoadd = waykey["tiger:ltoadd"]
-            else:
-                ltoadd = None
-            if "tiger:rfromadd" in waykey:
-                rfromadd = waykey["tiger:rfromadd"]
-            else: 
-                rfromadd = None
-            if "tiger:rtoadd" in waykey:
-                rtoadd = waykey["tiger:rtoadd"]
-            else:
-                rtoadd = None
-            if rfromadd != None and rtoadd != None:
-                right = True
-            else:
-                right = False
-            if lfromadd != None and ltoadd != None:
-                left = True
-            else:
-                left = False
-            if left or right:
-                first = True
-                firstpointid, firstpoint = nodelist[ round_point( segment[0] ) ]
-
-                finalpointid, finalpoint = nodelist[ round_point( segment[len(segment) - 1] ) ]
-                for point in segment:
-                    pointid, (lat, lon) = nodelist[ round_point( point ) ]
-
-                    #The approximate number of feet in one degree of longitute
-                    lrad = math.radians(lat)
-                    lon_feet = 365527.822 * math.cos(lrad) - 306.75853 * math.cos(3 * lrad) + 0.3937 * math.cos(5 * lrad)
-
-#Calculate the points of the offset ways
-                    if lastpoint != None:
-                        #Skip points too close to start
-                        if math.sqrt((lat * lat_feet - firstpoint[0] * lat_feet)**2 + (lon * lon_feet - firstpoint[1] * lon_feet)**2) < pullback:
-                            #Preserve very short ways (but will be rendered backwards)
-                            if pointid != finalpointid:
-                                continue
-                        #Skip points too close to end
-                        if math.sqrt((lat * lat_feet - finalpoint[0] * lat_feet)**2 + (lon * lon_feet - finalpoint[1] * lon_feet)**2) < pullback:
-                            #Preserve very short ways (but will be rendered backwards)
-                            if (pointid != firstpointid) and (pointid != finalpointid):
-                                continue
-
-                        X = (lon - lastpoint[1]) * lon_feet
-                        Y = (lat - lastpoint[0]) * lat_feet
-                        if Y != 0:
-                            theta = math.pi/2 - math.atan( X / Y)
-                            Xp = math.sin(theta) * distance
-                            Yp = math.cos(theta) * distance
-                        else:
-                            Xp = 0
-                            if X > 0:
-                                Yp = -distance
-                            else:
-                                Yp = distance
-
-                        if Y > 0:
-                            Xp = -Xp
-                        else:
-                            Yp = -Yp
-                                
-                        if first:
-                            first = False
-                            dX =  - (Yp * (pullback / distance)) / lon_feet #Pull back the first point
-                            dY = (Xp * (pullback / distance)) / lat_feet
-                            if left:
-                                lpoint = (lastpoint[0] + (Yp / lat_feet) - dY, lastpoint[1] + (Xp / lon_feet) - dX)
-                                lsegment.append( (id, lpoint) )
-                                id += 1
-                            if right:
-                                rpoint = (lastpoint[0] - (Yp / lat_feet) - dY, lastpoint[1] - (Xp / lon_feet) - dX)
-                                rsegment.append( (id, rpoint) )
-                                id += 1
-
-                        else:
-                            #round the curves
-                            if delta[1] != 0:
-                                theta = abs(math.atan(delta[0] / delta[1]))
-                            else:
-                                theta = math.pi / 2
-                            if Xp != 0:
-                                theta = theta - abs(math.atan(Yp / Xp))
-                            else: theta = theta - math.pi / 2
-                            r = 1 + abs(math.tan(theta/2))
-                            if left:
-                                lpoint = (lastpoint[0] + (Yp + delta[0]) * r / (lat_feet * 2), lastpoint[1] + (Xp + delta[1]) * r / (lon_feet * 2))
-                                lsegment.append( (id, lpoint) )
-                                id += 1
-                            if right:
-                                rpoint = (lastpoint[0] - (Yp + delta[0]) * r / (lat_feet * 2), lastpoint[1] - (Xp + delta[1]) * r / (lon_feet * 2))
-                                
-                                rsegment.append( (id, rpoint) )
-                                id += 1
-
-                        delta = (Yp, Xp)
-
-                    lastpoint = (lat, lon)
-
-
-#Add in the last node
-                dX =  - (Yp * (pullback / distance)) / lon_feet
-                dY = (Xp * (pullback / distance)) / lat_feet
-                if left:
-                    lpoint = (lastpoint[0] + (Yp + delta[0]) / (lat_feet * 2) + dY, lastpoint[1] + (Xp + delta[1]) / (lon_feet * 2) + dX )
-                    lsegment.append( (id, lpoint) )
-                    id += 1
-                if right:
-                    rpoint = (lastpoint[0] - Yp / lat_feet + dY, lastpoint[1] - Xp / lon_feet + dX)
-                    rsegment.append( (id, rpoint) )
-                    id += 1
-
-#Generate the tags for ways and nodes
-                zipr = ''
-                zipl = ''
-                name = ''
-                county = ''
-                if "tiger:zip_right" in waykey:
-                    zipr = waykey["tiger:zip_right"]
-                if "tiger:zip_left" in waykey:
-                    zipl = waykey["tiger:zip_left"]
-                if "name" in waykey:
-                    name = waykey["name"]
-                if "tiger:county" in waykey:
-                    county = waykey["tiger:county"]
-                if "tiger:separated" in waykey: # No longer set in Tiger-2017
-                    separated = waykey["tiger:separated"]
-                else:
-                    separated = "N"
-
-#Write the nodes of the offset ways
-                if right:
-                    rlinestring = [];
-                    for i, point in rsegment:
-                        rlinestring.append( "%f %f" % (point[1], point[0]) )
-                if left:
-                    llinestring = [];
-                    for i, point in lsegment:
-                        llinestring.append( "%f %f" % (point[1], point[0]) )
-                if right:
-                    rsegments.append( rsegment )
-                if left:
-                    lsegments.append( lsegment )
-                rtofromint = right        #Do the addresses convert to integers?
-                ltofromint = left        #Do the addresses convert to integers?
-                if right:
-                    try: rfromint = int(rfromadd)
-                    except:
-                        print("Non integer address: %s" % rfromadd)
-                        rtofromint = False
-                    try: rtoint = int(rtoadd)
-                    except:
-                        print("Non integer address: %s" % rtoadd)
-                        rtofromint = False
-                if left:
-                    try: lfromint = int(lfromadd)
-                    except:
-                        print("Non integer address: %s" % lfromadd)
-                        ltofromint = False
-                    try: ltoint = int(ltoadd)
-                    except:
-                        print("Non integer address: %s" % ltoadd)
-                        ltofromint = False
-                if right:
-                    id += 1
-
-                    interpolationtype = "all";
-                    if rtofromint:
-                        if (rfromint % 2) == 0 and (rtoint % 2) == 0:
-                            if separated == "Y":        #Doesn't matter if there is another side
-                                interpolationtype = "even";
-                            elif ltofromint and (lfromint % 2) == 1 and (ltoint % 2) == 1:
-                                interpolationtype = "even";
-                        elif (rfromint % 2) == 1 and (rtoint % 2) == 1:
-                            if separated == "Y":        #Doesn't matter if there is another side
-                                interpolationtype = "odd";
-                            elif ltofromint and (lfromint % 2) == 0 and (ltoint % 2) == 0:
-                                interpolationtype = "odd";
-
-                    ret.append( "SELECT tiger_line_import(ST_GeomFromText('LINESTRING(%s)',4326), %s, %s, %s, %s, %s, %s);" %
-                                ( ",".join(rlinestring), sql_quote(rfromadd), sql_quote(rtoadd), sql_quote(interpolationtype), sql_quote(name), sql_quote(county), sql_quote(zipr) ) )
-
-                if left:
-                    id += 1
-
-                    interpolationtype = "all";
-                    if ltofromint:
-                        if (lfromint % 2) == 0 and (ltoint % 2) == 0:
-                            if separated == "Y":
-                                interpolationtype = "even";
-                            elif rtofromint and (rfromint % 2) == 1 and (rtoint % 2) == 1:
-                                interpolationtype = "even";
-                        elif (lfromint % 2) == 1 and (ltoint % 2) == 1:
-                            if separated == "Y":
-                                interpolationtype = "odd";
-                            elif rtofromint and (rfromint %2 ) == 0 and (rtoint % 2) == 0:
-                                interpolationtype = "odd";
-
-                    ret.append( "SELECT tiger_line_import(ST_GeomFromText('LINESTRING(%s)',4326), %s, %s, %s, %s, %s, %s);" %
-                                ( ",".join(llinestring), sql_quote(lfromadd), sql_quote(ltoadd), sql_quote(interpolationtype), sql_quote(name), sql_quote(county), sql_quote(zipl) ) )
-
-    return ret
-
-def sql_quote( string ):
-    return "'" + string.replace("'", "''") + "'"
-
-def unproject( point ):
-    pt = tr.TransformPoint( point[0], point[1] )
-    return (pt[1], pt[0])
-
-def round_point( point, accuracy=8 ):
-    return tuple( [ round(x,accuracy) for x in point ] )
-
-def compile_nodelist( parsed_gisdata, first_id=1 ):
-    nodelist = {}
-    
-    i = first_id
-    for geom, tags in parsed_gisdata:
-        if len( geom )==0:
-            continue
-        
-        for point in geom:
-            r_point = round_point( point )
-            if r_point not in nodelist:
-                nodelist[ r_point ] = (i, unproject( point ))
-                i += 1
-            
-    return (i, nodelist)
-
-def adjacent( left, right ):
-    left_left = round_point(left[0])
-    left_right = round_point(left[-1])
-    right_left = round_point(right[0])
-    right_right = round_point(right[-1])
-    
-    return ( left_left == right_left or
-             left_left == right_right or
-             left_right == right_left or
-             left_right == right_right )
-             
-def glom( left, right ):
-    left = list( left )
-    right = list( right )
-    
-    left_left = round_point(left[0])
-    left_right = round_point(left[-1])
-    right_left = round_point(right[0])
-    right_right = round_point(right[-1])
-    
-    if left_left == right_left:
-        left.reverse()
-        return left[0:-1] + right
-        
-    if left_left == right_right:
-        return right[0:-1] + left
-        
-    if left_right == right_left:
-        return left[0:-1] + right
-        
-    if left_right == right_right:
-        right.reverse()
-        return left[0:-1] + right
-        
-    raise 'segments are not adjacent'
-
-def glom_once( segments ):
-    if len(segments)==0:
-        return segments
-    
-    unsorted = list( segments )
-    x = unsorted.pop(0)
-    
-    while len( unsorted ) > 0:
-        n = len( unsorted )
-        
-        for i in range(0, n):
-            y = unsorted[i]
-            if adjacent( x, y ):
-                y = unsorted.pop(i)
-                x = glom( x, y )
-                break
-                
-        # Sorted and unsorted lists have no adjacent segments
-        if len( unsorted ) == n:
-            break
-            
-    return x, unsorted
-    
-def glom_all( segments ):
-    unsorted = segments
-    chunks = []
-    
-    while unsorted != []:
-        chunk, unsorted = glom_once( unsorted )
-        chunks.append( chunk )
-        
-    return chunks
-        
-                
-
-def compile_waylist( parsed_gisdata ):
-    waylist = {}
-    
-    #Group by tiger:way_id
-    for geom, tags in parsed_gisdata:
-        way_key = tags.copy()
-        way_key = ( way_key['tiger:way_id'], tuple( [(k,v) for k,v in way_key.items()] ) )
-        
-        if way_key not in waylist:
-            waylist[way_key] = []
-            
-        waylist[way_key].append( geom )
-    
-    ret = {}
-    for (way_id, way_key), segments in waylist.items():
-        ret[way_key] = glom_all( segments )
-    return ret
-            
-
-def shape_to_sql( shp_filename, sql_filename ):
-    
-    print("parsing shpfile %s" % shp_filename)
-    parsed_features = parse_shp_for_geom_and_tags( shp_filename )
-    
-    print("compiling nodelist")
-    i, nodelist = compile_nodelist( parsed_features )
-    
-    print("compiling waylist")
-    waylist = compile_waylist( parsed_features )
-
-    print("preparing address ways")
-    sql_lines = addressways(waylist, nodelist, i)
-
-    print("writing %s" % sql_filename)
-    fp = open( sql_filename, "w" )
-    fp.write( "\n".join( sql_lines ) )
-    fp.close()
-    
-if __name__ == '__main__':
-    import sys, os.path
-    if len(sys.argv) < 3:
-        print("%s input.shp output.sql" % sys.argv[0])
-        sys.exit()
-    shp_filename = sys.argv[1]
-    sql_filename = sys.argv[2]
-    shape_to_sql(shp_filename, sql_filename)

data-sources/wikipedia-wikidata/README.md

@@ -1,58 +0,0 @@
-## Add Wikipedia and Wikidata to Nominatim
-
-OSM contributors frequently tag items with links to Wikipedia and Wikidata. Nominatim can use the page ranking of Wikipedia pages to help indicate the relative importance of osm features. This is done by calculating an importance score between 0 and 1 based on the number of inlinks to an article for a location. If two places have the same name and one is more important than the other, the wikipedia score often points to the correct place. 
-
-These scripts extract and prepare both Wikipedia page rank and Wikidata links for use in Nominatim.  
-
-#### Create a new postgres DB for Processing
-
-Due to the size of initial and intermediate tables, processing can be done in an external database:
-```
-CREATE DATABASE wikiprocessingdb;
-```
----
-Wikipedia
----  
-
-Processing these data requires a large amount of disk space (~1TB) and considerable time (>24 hours).
-
-#### Import & Process Wikipedia tables
-
-This step downloads and converts [Wikipedia](https://dumps.wikimedia.org/) page data SQL dumps to postgreSQL files which can be imported and processed with pagelink information from Wikipedia language sites to calculate importance scores.
-
-- The script will processes data from whatever set of Wikipedia languages are specified in the initial languages array
-
-- Note that processing the top 40 Wikipedia languages can take over a day, and will add nearly 1TB to the processing database. The final output tables will be approximately 11GB and 2GB in size
-
-To download, convert, and import the data, then process summary statistics and compute importance scores, run:
-```
-./import_wikipedia.sh
-```
----
-Wikidata
----
-
-This script downloads and processes Wikidata to enrich the previously created Wikipedia tables for use in Nominatim.
-
-#### Import & Process Wikidata
-
-This step downloads and converts [Wikidata](https://dumps.wikimedia.org/wikidatawiki/) page data SQL dumps to postgreSQL files which can be processed and imported into Nominatim database. Also utilizes Wikidata Query Service API to discover and include place types.
-
-- Script presumes that the user has already processed Wikipedia tables as specified above
-
-- Script requires wikidata_place_types.txt and wikidata_place_type_levles.csv
-
-- script requires the [jq json parser](https://stedolan.github.io/jq/)
-
-- Script processes data from whatever set of Wikipedia languages are specified in the initial languages array
-
-- Script queries Wikidata Query Service API and imports all instances of place types listed in wikidata_place_types.txt
-
-- Script updates wikipedia_articles table with extracted wikidata 
-
-By including Wikidata in the wikipedia_articles table, new connections can be made on the fly from the Nominatim placex table to wikipedia_article importance scores. 
-
-To download, convert, and import the data, then process required items, run:
-``` 
-./import_wikidata.sh
-```

data-sources/wikipedia-wikidata/import_wikidata.sh

@@ -1,274 +0,0 @@
-#!/bin/bash
-
-psqlcmd() {
-     psql --quiet wikiprocessingdb
-}
-
-mysql2pgsqlcmd() {
-     ./mysql2pgsql.perl /dev/stdin /dev/stdout
-}
-
-download() {
-     echo "Downloading $1"
-     wget --quiet --no-clobber --tries 3 "$1"
-}
-
-# languages to process (refer to List of Wikipedias here: https://en.wikipedia.org/wiki/List_of_Wikipedias)
-# requires Bash 4.0
-readarray -t LANGUAGES < languages.txt
-
-
-
-echo "====================================================================="
-echo "Download wikidata dump tables"
-echo "====================================================================="
-
-# 114M  wikidatawiki-latest-geo_tags.sql.gz
-# 1.7G  wikidatawiki-latest-page.sql.gz
-# 1.2G  wikidatawiki-latest-wb_items_per_site.sql.gz
-download https://dumps.wikimedia.org/wikidatawiki/latest/wikidatawiki-latest-geo_tags.sql.gz
-download https://dumps.wikimedia.org/wikidatawiki/latest/wikidatawiki-latest-page.sql.gz
-download https://dumps.wikimedia.org/wikidatawiki/latest/wikidatawiki-latest-wb_items_per_site.sql.gz
-
-
-
-
-echo "====================================================================="
-echo "Import wikidata dump tables"
-echo "====================================================================="
-
-echo "Importing wikidatawiki-latest-geo_tags"
-gzip -dc wikidatawiki-latest-geo_tags.sql.gz          | mysql2pgsqlcmd | psqlcmd
-
-echo "Importing wikidatawiki-latest-page"
-gzip -dc wikidatawiki-latest-page.sql.gz              | mysql2pgsqlcmd | psqlcmd
-
-echo "Importing wikidatawiki-latest-wb_items_per_site"
-gzip -dc wikidatawiki-latest-wb_items_per_site.sql.gz | mysql2pgsqlcmd | psqlcmd
-
-
-
-
-
-
-echo "====================================================================="
-echo "Get wikidata places from wikidata query API"
-echo "====================================================================="
-
-echo "Number of place types:"
-wc -l wikidata_place_types.txt
-
-while read F  ; do
-    echo "Querying for place type $F..."
-    wget --quiet "https://query.wikidata.org/bigdata/namespace/wdq/sparql?format=json&query=SELECT ?item WHERE{?item wdt:P31*/wdt:P279*wd:$F;}" -O $F.json
-    jq -r '.results | .[] | .[] | [.item.value] | @csv' $F.json >> $F.txt
-    awk -v qid=$F '{print $0 ","qid}' $F.txt | sed -e 's!"http://www.wikidata.org/entity/!!' | sed 's/"//g' >> $F.csv
-    cat $F.csv >> wikidata_place_dump.csv
-    rm $F.json $F.txt $F.csv
-done < wikidata_place_types.txt
-
-
-
-
-echo "====================================================================="
-echo "Import wikidata places"
-echo "====================================================================="
-
-echo "CREATE TABLE wikidata_place_dump (
-        item        text,
-        instance_of text
-      );"  | psqlcmd
-
-echo "COPY wikidata_place_dump (item, instance_of)
-      FROM '/srv/nominatim/Nominatim/data-sources/wikipedia-wikidata/wikidata_place_dump.csv'
-      DELIMITER ','
-      CSV
-      ;"  | psqlcmd
-
-echo "CREATE TABLE wikidata_place_type_levels (
-        place_type text,
-        level      integer
-      );" | psqlcmd
-
-echo "COPY wikidata_place_type_levels (place_type, level)
-      FROM '/srv/nominatim/Nominatim/data-sources/wikipedia-wikidata/wikidata_place_type_levels.csv'
-      DELIMITER ','
-      CSV
-      HEADER
-      ;" | psqlcmd
-
-
-
-
-echo "====================================================================="
-echo "Create derived tables"
-echo "====================================================================="
-
-echo "CREATE TABLE geo_earth_primary AS
-      SELECT gt_page_id,
-             gt_lat,
-             gt_lon
-      FROM geo_tags
-      WHERE gt_globe = 'earth'
-        AND gt_primary = 1
-        AND NOT(    gt_lat < -90
-                 OR gt_lat > 90
-                 OR gt_lon < -180
-                 OR gt_lon > 180
-                 OR gt_lat=0
-                 OR gt_lon=0)
-      ;" | psqlcmd
-
-echo "CREATE TABLE geo_earth_wikidata AS
-      SELECT DISTINCT geo_earth_primary.gt_page_id,
-                      geo_earth_primary.gt_lat,
-                      geo_earth_primary.gt_lon,
-                      page.page_title,
-                      page.page_namespace
-      FROM geo_earth_primary
-      LEFT OUTER JOIN page
-                   ON (geo_earth_primary.gt_page_id = page.page_id)
-      ORDER BY geo_earth_primary.gt_page_id
-      ;" | psqlcmd
-
-echo "ALTER TABLE wikidata_place_dump
-      ADD COLUMN ont_level integer,
-      ADD COLUMN lat numeric(11,8),
-      ADD COLUMN lon numeric(11,8)
-      ;" | psqlcmd
-
-echo "UPDATE wikidata_place_dump
-      SET ont_level = wikidata_place_type_levels.level
-      FROM wikidata_place_type_levels
-      WHERE wikidata_place_dump.instance_of = wikidata_place_type_levels.place_type
-      ;" | psqlcmd
-
-echo "CREATE TABLE wikidata_places
-      AS
-      SELECT DISTINCT ON (item) item,
-                                instance_of,
-                                MAX(ont_level) AS ont_level,
-                                lat,
-                                lon
-      FROM wikidata_place_dump
-      GROUP BY item,
-               instance_of,
-               ont_level,
-               lat,
-               lon
-      ORDER BY item
-      ;" | psqlcmd
-
-echo "UPDATE wikidata_places
-      SET lat = geo_earth_wikidata.gt_lat,
-          lon = geo_earth_wikidata.gt_lon
-      FROM geo_earth_wikidata
-      WHERE wikidata_places.item = geo_earth_wikidata.page_title
-      ;" | psqlcmd
-
-
-
-
-echo "====================================================================="
-echo "Process language pages"
-echo "====================================================================="
-
-
-echo "CREATE TABLE wikidata_pages (
-        item          text,
-        instance_of   text,
-        lat           numeric(11,8),
-        lon           numeric(11,8),
-        ips_site_page text,
-        language      text
-      );" | psqlcmd
-
-for i in "${LANGUAGES[@]}"
-do
-   echo "CREATE TABLE wikidata_${i}_pages AS
-         SELECT wikidata_places.item,
-                wikidata_places.instance_of,
-                wikidata_places.lat,
-                wikidata_places.lon,
-                wb_items_per_site.ips_site_page
-         FROM wikidata_places
-         LEFT JOIN wb_items_per_site
-                ON (CAST (( LTRIM(wikidata_places.item, 'Q')) AS INTEGER) = wb_items_per_site.ips_item_id)
-         WHERE ips_site_id = '${i}wiki'
-           AND LEFT(wikidata_places.item,1) = 'Q'
-         ORDER BY wikidata_places.item
-         ;" | psqlcmd
-
-   echo "ALTER TABLE wikidata_${i}_pages
-         ADD COLUMN language text
-         ;" | psqlcmd
-
-   echo "UPDATE wikidata_${i}_pages
-         SET language = '${i}'
-         ;" | psqlcmd
-
-   echo "INSERT INTO wikidata_pages
-         SELECT item,
-                instance_of,
-                lat,
-                lon,
-                ips_site_page,
-                language
-         FROM wikidata_${i}_pages
-         ;" | psqlcmd
-done
-
-echo "ALTER TABLE wikidata_pages
-      ADD COLUMN wp_page_title text
-      ;" | psqlcmd
-echo "UPDATE wikidata_pages
-      SET wp_page_title = REPLACE(ips_site_page, ' ', '_')
-      ;" | psqlcmd
-echo "ALTER TABLE wikidata_pages
-      DROP COLUMN ips_site_page
-      ;" | psqlcmd
-
-
-
-
-echo "====================================================================="
-echo "Add wikidata to wikipedia_article table"
-echo "====================================================================="
-
-echo "UPDATE wikipedia_article
-      SET lat = wikidata_pages.lat,
-          lon = wikidata_pages.lon,
-          wd_page_title = wikidata_pages.item,
-          instance_of = wikidata_pages.instance_of
-      FROM wikidata_pages
-      WHERE wikipedia_article.language = wikidata_pages.language
-        AND wikipedia_article.title  = wikidata_pages.wp_page_title
-      ;" | psqlcmd
-
-echo "CREATE TABLE wikipedia_article_slim
-      AS
-      SELECT * FROM wikipedia_article
-      WHERE wikidata_id IS NOT NULL
-      ;" | psqlcmd
-
-echo "ALTER TABLE wikipedia_article
-      RENAME TO wikipedia_article_full
-      ;" | psqlcmd
-
-echo "ALTER TABLE wikipedia_article_slim
-      RENAME TO wikipedia_article
-      ;" | psqlcmd
-
-
-
-
-echo "====================================================================="
-echo "Dropping intermediate tables"
-echo "====================================================================="
-
-echo "DROP TABLE wikidata_place_dump;" | psqlcmd
-echo "DROP TABLE geo_earth_primary;" | psqlcmd
-for i in "${LANGUAGES[@]}"
-do
-    echo "DROP TABLE wikidata_${i}_pages;" | psqlcmd
-done

data-sources/wikipedia-wikidata/import_wikipedia.sh

@@ -1,297 +0,0 @@
-#!/bin/bash
-
-psqlcmd() {
-     psql --quiet wikiprocessingdb |& \
-     grep -v 'does not exist, skipping' |& \
-     grep -v 'violates check constraint' |& \
-     grep -vi 'Failing row contains'
-}
-
-mysql2pgsqlcmd() {
-     ./mysql2pgsql.perl --nodrop /dev/stdin /dev/stdout
-}
-
-download() {
-     echo "Downloading $1"
-     wget --quiet --no-clobber --tries=3 "$1"
-}
-
-
-# languages to process (refer to List of Wikipedias here: https://en.wikipedia.org/wiki/List_of_Wikipedias)
-# requires Bash 4.0
-readarray -t LANGUAGES < languages.txt
-
-
-
-echo "====================================================================="
-echo "Create wikipedia calculation tables"
-echo "====================================================================="
-
-echo "CREATE TABLE linkcounts (
-        language text,
-        title    text,
-        count    integer,
-        sumcount integer,
-        lat      double precision,
-        lon      double precision
-     );"  | psqlcmd
-
-echo "CREATE TABLE wikipedia_article (
-        language    text NOT NULL,
-        title       text NOT NULL,
-        langcount   integer,
-        othercount  integer,
-        totalcount  integer,
-        lat double  precision,
-        lon double  precision,
-        importance  double precision,
-        title_en    text,
-        osm_type    character(1),
-        osm_id      bigint
-      );" | psqlcmd
-
-echo "CREATE TABLE wikipedia_redirect (
-        language   text,
-        from_title text,
-        to_title   text
-     );" | psqlcmd
-
-
-
-
-
-echo "====================================================================="
-echo "Download individual wikipedia language tables"
-echo "====================================================================="
-
-
-for i in "${LANGUAGES[@]}"
-do
-    echo "Language: $i"
-
-    # english is the largest
-    # 1.7G  enwiki-latest-page.sql.gz
-    # 6.2G  enwiki-latest-pagelinks.sql.gz
-    # 355M  enwiki-latest-langlinks.sql.gz
-    # 128M  enwiki-latest-redirect.sql.gz
-
-    # example of smaller languge turkish
-    #  53M  trwiki-latest-page.sql.gz
-    # 176M  trwiki-latest-pagelinks.sql.gz
-    # 106M  trwiki-latest-langlinks.sql.gz
-    # 3.2M  trwiki-latest-redirect.sql.gz
-
-    download https://dumps.wikimedia.org/${i}wiki/latest/${i}wiki-latest-page.sql.gz
-    download https://dumps.wikimedia.org/${i}wiki/latest/${i}wiki-latest-pagelinks.sql.gz
-    download https://dumps.wikimedia.org/${i}wiki/latest/${i}wiki-latest-langlinks.sql.gz
-    download https://dumps.wikimedia.org/${i}wiki/latest/${i}wiki-latest-redirect.sql.gz
-done
-
-
-
-
-
-echo "====================================================================="
-echo "Import individual wikipedia language tables"
-echo "====================================================================="
-
-for i in "${LANGUAGES[@]}"
-do
-    echo "Language: $i"
-
-    # We pre-create the table schema. This allows us to
-    # 1. Skip index creation. Most queries we do are full table scans
-    # 2. Add constrain to only import namespace=0 (wikipedia articles)
-    # Both cuts down data size considerably (50%+)
-
-    echo "Importing ${i}wiki-latest-pagelinks"
-
-    echo "DROP TABLE IF EXISTS ${i}pagelinks;" | psqlcmd
-    echo "CREATE TABLE ${i}pagelinks (
-       pl_from            int  NOT NULL DEFAULT '0',
-       pl_namespace       int  NOT NULL DEFAULT '0',
-       pl_title           text NOT NULL DEFAULT '',
-       pl_from_namespace  int  NOT NULL DEFAULT '0'
-    );" | psqlcmd
-
-    time \
-      gzip -dc ${i}wiki-latest-pagelinks.sql.gz | \
-      sed "s/\`pagelinks\`/\`${i}pagelinks\`/g" | \
-      mysql2pgsqlcmd | \
-      grep -v '^CREATE INDEX ' | \
-      psqlcmd
-
-
-
-
-    echo "Importing ${i}wiki-latest-page"
-
-    # autoincrement serial8 4byte
-    echo "DROP TABLE IF EXISTS ${i}page;" | psqlcmd
-    echo "CREATE TABLE ${i}page (
-       page_id             int NOT NULL,
-       page_namespace      int NOT NULL DEFAULT '0',
-       page_title          text NOT NULL DEFAULT '',
-       page_restrictions   text NOT NULL,
-       page_is_redirect    smallint NOT NULL DEFAULT '0',
-       page_is_new         smallint NOT NULL DEFAULT '0',
-       page_random         double precision NOT NULL DEFAULT '0',
-       page_touched        text NOT NULL DEFAULT '',
-       page_links_updated  text DEFAULT NULL,
-       page_latest         int NOT NULL DEFAULT '0',
-       page_len            int NOT NULL DEFAULT '0',
-       page_content_model  text DEFAULT NULL,
-       page_lang           text DEFAULT NULL
-     );" | psqlcmd
-
-    time \
-      gzip -dc ${i}wiki-latest-page.sql.gz | \
-      sed "s/\`page\`/\`${i}page\`/g" | \
-      mysql2pgsqlcmd | \
-      grep -v '^CREATE INDEX ' | \
-      psqlcmd
-
-
-
-
-    echo "Importing ${i}wiki-latest-langlinks"
-
-    echo "DROP TABLE IF EXISTS ${i}langlinks;" | psqlcmd
-    echo "CREATE TABLE ${i}langlinks (
-       ll_from   int  NOT NULL DEFAULT '0',
-       ll_lang   text NOT NULL DEFAULT '',
-       ll_title  text NOT NULL DEFAULT ''
-    );" | psqlcmd
-
-    time \
-      gzip -dc ${i}wiki-latest-langlinks.sql.gz | \
-      sed "s/\`langlinks\`/\`${i}langlinks\`/g" | \
-      mysql2pgsqlcmd | \
-      grep -v '^CREATE INDEX ' | \
-      psqlcmd
-
-
-
-
-
-    echo "Importing ${i}wiki-latest-redirect"
-
-    echo "DROP TABLE IF EXISTS ${i}redirect;" | psqlcmd
-    echo "CREATE TABLE ${i}redirect (
-       rd_from       int   NOT NULL DEFAULT '0',
-       rd_namespace  int   NOT NULL DEFAULT '0',
-       rd_title      text  NOT NULL DEFAULT '',
-       rd_interwiki  text  DEFAULT NULL,
-       rd_fragment   text  DEFAULT NULL
-    );" | psqlcmd
-
-    time \
-      gzip -dc ${i}wiki-latest-redirect.sql.gz | \
-      sed "s/\`redirect\`/\`${i}redirect\`/g" | \
-      mysql2pgsqlcmd | \
-      grep -v '^CREATE INDEX ' | \
-      psqlcmd
-done
-
-
-
-
-
-echo "====================================================================="
-echo "Process language tables and associated pagelink counts"
-echo "====================================================================="
-
-
-for i in "${LANGUAGES[@]}"
-do
-    echo "Language: $i"
-
-    echo "CREATE TABLE ${i}pagelinkcount
-          AS
-          SELECT pl_title AS title,
-                 COUNT(*) AS count,
-                 0::bigint as othercount
-          FROM ${i}pagelinks
-          WHERE pl_namespace = 0
-          GROUP BY pl_title
-          ;" | psqlcmd
-
-    echo "INSERT INTO linkcounts
-          SELECT '${i}',
-                 pl_title,
-                 COUNT(*)
-          FROM ${i}pagelinks
-          WHERE pl_namespace = 0
-          GROUP BY pl_title
-          ;" | psqlcmd
-
-    echo "INSERT INTO wikipedia_redirect
-          SELECT '${i}',
-                 page_title,
-                 rd_title
-          FROM ${i}redirect
-          JOIN ${i}page ON (rd_from = page_id)
-          WHERE page_namespace = 0
-            AND rd_namespace = 0
-          ;" | psqlcmd
-
-done
-
-
-for i in "${LANGUAGES[@]}"
-do
-    for j in "${LANGUAGES[@]}"
-    do
-        echo "UPDATE ${i}pagelinkcount
-              SET othercount = ${i}pagelinkcount.othercount + x.count
-              FROM (
-                SELECT page_title AS title,
-                       count
-                FROM ${i}langlinks
-                JOIN ${i}page ON (ll_from = page_id)
-                JOIN ${j}pagelinkcount ON (ll_lang = '${j}' AND ll_title = title)
-              ) AS x
-              WHERE x.title = ${i}pagelinkcount.title
-              ;" | psqlcmd
-    done
-
-    echo "INSERT INTO wikipedia_article
-          SELECT '${i}',
-                 title,
-                 count,
-                 othercount,
-                 count + othercount
-          FROM ${i}pagelinkcount
-          ;" | psqlcmd
-done
-
-
-
-
-
-echo "====================================================================="
-echo "Calculate importance score for each wikipedia page"
-echo "====================================================================="
-
-echo "UPDATE wikipedia_article
-      SET importance = LOG(totalcount)/LOG((SELECT MAX(totalcount) FROM wikipedia_article))
-      ;" | psqlcmd
-
-
-
-
-
-echo "====================================================================="
-echo "Clean up intermediate tables to conserve space"
-echo "====================================================================="
-
-for i in "${LANGUAGES[@]}"
-do
-    echo "DROP TABLE ${i}pagelinks;"     | psqlcmd
-    echo "DROP TABLE ${i}page;"          | psqlcmd
-    echo "DROP TABLE ${i}langlinks;"     | psqlcmd
-    echo "DROP TABLE ${i}redirect;"      | psqlcmd
-    echo "DROP TABLE ${i}pagelinkcount;" | psqlcmd
-done
-
-echo "all done."

data-sources/wikipedia-wikidata/languages.txt

@@ -1,39 +0,0 @@
-ar
-bg
-ca
-cs
-da
-de
-en
-es
-eo
-eu
-fa
-fr
-ko
-hi
-hr
-id
-it
-he
-lt
-hu
-ms
-nl
-ja
-no
-pl
-pt
-kk
-ro
-ru
-sk
-sl
-sr
-fi
-sv
-tr
-uk
-vi
-war
-zh

data-sources/wikipedia-wikidata/mysql2pgsql.perl

@@ -1,951 +0,0 @@
-#!/usr/bin/perl -w
-# mysql2pgsql
-# MySQL to PostgreSQL dump file converter
-#
-# For usage: perl mysql2pgsql.perl --help
-#
-# ddl statments are changed but none or only minimal real data
-# formatting are done.
-# data consistency is up to the DBA.
-#
-# (c) 2004-2007 Jose M Duarte and Joseph Speigle ... gborg
-#
-# (c) 2000-2004 Maxim Rudensky  <fonin@omnistaronline.com>
-# (c) 2000 Valentine Danilchuk  <valdan@ziet.zhitomir.ua>
-# All rights reserved.
-#
-# Redistribution and use in source and binary forms, with or without
-# modification, are permitted provided that the following conditions
-# are met:
-# 1. Redistributions of source code must retain the above copyright
-#    notice, this list of conditions and the following disclaimer.
-# 2. Redistributions in binary form must reproduce the above copyright
-#    notice, this list of conditions and the following disclaimer in the
-#    documentation and/or other materials provided with the distribution.
-# 3. All advertising materials mentioning features or use of this software
-#    must display the following acknowledgement:
-# This product includes software developed by the Max Rudensky
-# and its contributors.
-# 4. Neither the name of the author nor the names of its contributors
-#    may be used to endorse or promote products derived from this software
-#    without specific prior written permission.
-# THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
-# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
-# ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
-# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
-# OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
-# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
-# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
-# OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
-# SUCH DAMAGE.
-
-use Getopt::Long;
-
-use POSIX;
-
-use strict;
-use warnings;
-
-
-# main sections
-# -------------
-# 1 variable declarations
-# 2 subroutines
-# 3 get commandline options and specify help statement
-# 4 loop through file and process
-# 5. print_plpgsql function prototype
-
-#################################################################
-#  1.  variable declarations
-#################################################################
-# command line options
-my( $ENC_IN, $ENC_OUT, $PRESERVE_CASE, $HELP, $DEBUG, $SCHEMA, $LOWERCASE, $CHAR2VARCHAR, $NODROP, $SEP_FILE, $opt_debug, $opt_help, $opt_schema, $opt_preserve_case, $opt_char2varchar, $opt_nodrop, $opt_sepfile, $opt_enc_in, $opt_enc_out );
-# variables for constructing pre-create-table entities
-my $pre_create_sql='';    # comments, 'enum' constraints preceding create table statement
-my $auto_increment_seq= '';    # so we can easily substitute it if we need a default value
-my $create_sql='';    # all the datatypes in the create table section
-my $post_create_sql='';   # create indexes, foreign keys, table comments
-my $function_create_sql = '';  # for the set (function,trigger) and CURRENT_TIMESTAMP ( function,trigger )
-#  constraints
-my ($type, $column_valuesStr, @column_values, $value );
-my %constraints=(); #  holds values constraints used to emulate mysql datatypes (e.g. year, set)
-# datatype conversion variables
-my ( $index,$seq);
-my ( $column_name, $col, $quoted_column);
-my ( @year_holder, $year, $constraint_table_name);
-my $table="";   # table_name for create sql statements
-my $table_no_quotes="";   # table_name for create sql statements
-my $sl = '^\s+\w+\s+';  # matches the column name
-my $tables_first_timestamp_column= 1;  #  decision to print warnings about default_timestamp not being in postgres
-my $mysql_numeric_datatypes = "TINYINT|SMALLINT|MEDIUMINT|INT|INTEGER|BIGINT|REAL|DOUBLE|FLOAT|DECIMAL|NUMERIC";
-my $mysql_datetime_datatypes = "|DATE|TIME|TIMESTAMP|DATETIME|YEAR";
-my $mysql_text_datatypes = "CHAR|VARCHAR|BINARY|VARBINARY|TINYBLOB|BLOB|MEDIUMBLOB|LONGBLOB|TINYTEXT|TEXT|MEDIUMTEXT|LONGTEXT|ENUM|SET";
-my $mysql_datatypesStr =  $mysql_numeric_datatypes . "|". $mysql_datetime_datatypes . "|". $mysql_text_datatypes ;
-# handling INSERT INTO statements
-my $rowRe = qr{
-    \(                  # opening parens
-        (               #  (start capture)
-            (?:         #  (start group)
-            '           # string start
-                [^'\\]*     # up to string-end or backslash (escape)
-                (?:     #  (start group)
-                \\.     # gobble escaped character
-                [^'\\]*     # up to string-end of backslash
-                )*      #  (end group, repeat zero or more)
-            '           # string end
-            |           #  (OR)
-            .*?         # everything else (not strings)
-            )*          #  (end group, repeat zero or more)
-        )               #  (end capture)
-    \)                  # closing parent
-}x;
-
-my ($insert_table, $valueString);
-#
-########################################################
-# 2.  subroutines
-#
-# get_identifier
-# print_post_create_sql()
-# quote_and_lc()
-# make_plpgsql($table,$column_name) -- at end of file
-########################################################
-
-# returns an identifier with the given suffix doing controlled
-# truncation if necessary
-sub get_identifier($$$) {
-    my ($table, $col, $suffix) = @_;
-    my $name = '';
-    $table=~s/\"//g; # make sure that $table doesn't have quotes so we don't end up with redundant quoting
-    # in the case of multiple columns
-    my @cols = split(/,/,$col);
-    $col =~ s/,//g;
-    # in case all columns together too long we have to truncate them
-    if (length($col) > 55) {
-        my $totaltocut = length($col)-55;
-        my $tocut = ceil($totaltocut / @cols);
-        @cols = map {substr($_,0,abs(length($_)-$tocut))} @cols;
-        $col="";
-        foreach (@cols){
-            $col.=$_;
-        }
-    }
-
-    my $max_table_length = 63 - length("_${col}_$suffix");
-
-    if (length($table) > $max_table_length) {
-        $table = substr($table, length($table) - $max_table_length, $max_table_length);
-    }
-    return quote_and_lc("${table}_${col}_${suffix}");
-}
-
-
-#
-#
-# called when we encounter next CREATE TABLE statement
-# also called at EOF to print out for last table
-# prints comments, indexes, foreign key constraints (the latter 2 possibly to a separate file)
-sub print_post_create_sql() {
-    my ( @create_idx_comments_constraints_commandsArr, $stmts, $table_field_combination);
-    my %stmts;
-    # loop to check for duplicates in $post_create_sql
-    # Needed because of duplicate key declarations ( PRIMARY KEY and KEY), auto_increment columns
-
-    @create_idx_comments_constraints_commandsArr = split(';\n?', $post_create_sql);
-    if ($SEP_FILE) {
-        open(SEP_FILE, ">>:encoding($ENC_OUT)", $SEP_FILE) or die "Unable to open $SEP_FILE for output: $!\n";
-    }
-
-    foreach (@create_idx_comments_constraints_commandsArr) {
-        if (m/CREATE INDEX "*(\S+)"*\s/i) {  #  CREATE INDEX korean_english_wordsize_idx ON korean_english USING btree  (wordsize);
-            $table_field_combination =  $1;
-            # if this particular table_field_combination was already used do not print the statement:
-            if ($SEP_FILE) {
-                print SEP_FILE "$_;\n" if !defined($stmts{$table_field_combination});
-            } else {
-                print OUT "$_;\n" if !defined($stmts{$table_field_combination});
-            }
-            $stmts{$table_field_combination} = 1;
-        }
-        elsif (m/COMMENT/i) {  # COMMENT ON object IS 'text'; but comment may be part of table name so use 'elsif'
-            print OUT "$_;\n"
-        } else {  # foreign key constraint  or comments (those preceded by -- )
-            if ($SEP_FILE) {
-                print SEP_FILE "$_;\n";
-            } else {
-                print OUT "$_;\n"
-            }
-        }
-    }
-
-    if ($SEP_FILE) {
-        close SEP_FILE;
-    }
-    $post_create_sql='';
-    # empty %constraints for next " create table" statement
-}
-
-# quotes a string or a multicolumn string (comma separated)
-# and optionally lowercase (if LOWERCASE is set)
-# lowercase .... if user wants default postgres behavior
-# quotes .... to preserve keywords and to preserve case when case-sensitive tables are to be used
-sub quote_and_lc($)
-{
-    my $col = shift;
-    if ($LOWERCASE) {
-        $col = lc($col);
-    }
-    if ($col =~ m/,/) {
-        my @cols = split(/,\s?/, $col);
-        @cols = map {"\"$_\""} @cols;
-        return join(', ', @cols);
-    } else {
-        return "\"$col\"";
-    }
-}
-
-########################################################
-# 3.  get commandline options and maybe print help
-########################################################
-
-GetOptions("help", "debug"=> \$opt_debug, "schema=s" => \$SCHEMA, "preserve_case" => \$opt_preserve_case, "char2varchar" => \$opt_char2varchar, "nodrop" => \$opt_nodrop, "sepfile=s" => \$opt_sepfile, "enc_in=s" => \$opt_enc_in, "enc_out=s" => \$opt_enc_out );
-
-$HELP = $opt_help || 0;
-$DEBUG = $opt_debug || 0;
-$PRESERVE_CASE = $opt_preserve_case || 0;
-if ($PRESERVE_CASE == 1) { $LOWERCASE = 0; }
-else { $LOWERCASE = 1; }
-$CHAR2VARCHAR = $opt_char2varchar || 0;
-$NODROP = $opt_nodrop || 0;
-$SEP_FILE = $opt_sepfile || 0;
-$ENC_IN = $opt_enc_in || 'utf8';
-$ENC_OUT = $opt_enc_out || 'utf8';
-
-if (($HELP) || ! defined($ARGV[0]) || ! defined($ARGV[1])) {
-    print "\n\nUsage: perl $0 {--help --debug --preserve_case --char2varchar --nodrop --schema --sepfile --enc_in --enc_out } mysql.sql pg.sql\n";
-    print "\t* OPTIONS WITHOUT ARGS\n";
-    print "\t--help:  prints this message \n";
-    print "\t--debug: output the commented-out mysql line above the postgres line in pg.sql \n";
-    print "\t--preserve_case: prevents automatic case-lowering of column and table names\n";
-    print "\t\tIf you want to preserve case, you must set this flag. For example,\n";
-    print "\t\tIf your client application quotes table and column-names and they have cases in them, set this flag\n";
-    print "\t--char2varchar: converts all char fields to varchar\n";
-    print "\t--nodrop: strips out DROP TABLE statements\n";
-    print "\t\totherise harmless warnings are printed by psql when the dropped table does not exist\n";
-    print "\n\t* OPTIONS WITH ARGS\n";
-    print "\t--schema: outputs a line into the postgres sql file setting search_path \n";
-    print "\t--sepfile: output foreign key constraints and indexes to a separate file so that it can be\n";
-    print "\t\timported after large data set is inserted from another dump file\n";
-    print "\t--enc_in: encoding of mysql in file (default utf8) \n";
-    print "\t--enc_out: encoding of postgres out file (default utf8) \n";
-    print "\n\t* REQUIRED ARGUMENTS\n";
-    if (defined ($ARGV[0])) {
-        print "\tmysql.sql ($ARGV[0])\n";
-    } else {
-        print "\tmysql.sql (undefined)\n";
-    }
-    if (defined ($ARGV[1])) {
-        print "\tpg.sql ($ARGV[1])\n";
-    } else {
-        print "\tpg.sql (undefined)\n";
-    }
-    print "\n";
-    exit 1;
-}
-########################################################
-# 4.  process through mysql_dump.sql file
-# in a big loop
-########################################################
-
-# open in and out files
-open(IN,"<:encoding($ENC_IN)", $ARGV[0]) || die "can't open mysql dump file $ARGV[0]";
-open(OUT,">:encoding($ENC_OUT)", $ARGV[1]) || die "can't open pg dump file $ARGV[1]";
-
-# output header
-print OUT "--\n";
-print OUT "-- Generated from mysql2pgsql.perl\n";
-print OUT "-- http://gborg.postgresql.org/project/mysql2psql/\n";
-print OUT "-- (c) 2001 - 2007 Jose M. Duarte, Joseph Speigle\n";
-print OUT "--\n";
-print OUT "\n";
-print OUT "-- warnings are printed for drop tables if they do not exist\n";
-print OUT "-- please see http://archives.postgresql.org/pgsql-novice/2004-10/msg00158.php\n\n";
-print OUT "-- ##############################################################\n";
-
-if ($SCHEMA ) {
-    print OUT "set search_path='" . $SCHEMA . "'\\g\n" ;
-}
-
-# loop through mysql file  on a per-line basis
-while(<IN>) {
-
-##############     flow     #########################
-# (the lines are directed to different string variables at different times)
-#
-# handle drop table , unlock, connect statements
-# if ( start of create table)   {
-#   print out post_create table (indexes, foreign key constraints, comments from previous table)
-#   add drop table statement if !$NODROP to pre_create_sql
-#   next;
-# }
-# else if ( inside create table) {
-#   add comments in this portion to create_sql
-#   if ( end of create table) {
-#      delete mysql-unique CREATE TABLE commands
-#      print pre_create_sql
-#      print the constraint tables for set and year datatypes
-#      print create_sql
-#      print function_create_sql (this is for the enum columns only)
-#      next;
-#   }
-#   do substitutions
-#    -- NUMERIC DATATYPES
-#    -- CHARACTER DATATYPES
-#    -- DATE AND TIME DATATYPES
-#    -- KEY AND UNIQUE CREATIONS
-#    and append them to create_sql
-# } else {
-#   print inserts on-the-spot (this script only changes default timestamp of 0000-00-00)
-# }
-# LOOP until EOF
-#
-########################################################
-
-
-if (!/^\s*insert into/i) { # not inside create table so don't worry about data corruption
-    s/`//g;  #  '`pgsql uses no backticks to denote table name (CREATE TABLE `sd`) or around field
-            # and table names like  mysql
-            # doh!  we hope all dashes and special chars are caught by the regular expressions :)
-}
-if (/^\s*USE\s*([^;]*);/) {
-    print OUT "\\c ". $1;
-    next;
-}
-if (/^(UN)?LOCK TABLES/i  || /drop\s+table/i ) {
-
-    # skip
-    # DROP TABLE is added when we see the CREATE TABLE
-    next;
-}
-if (/(create\s+table\s+)([-_\w]+)\s/i) { #  example: CREATE TABLE `english_english`
-    print_post_create_sql();   # for last table
-    $tables_first_timestamp_column= 1;  #  decision to print warnings about default_timestamp not being in postgres
-    $create_sql = '';
-    $table_no_quotes = $2 ;
-    $table=quote_and_lc($2);
-    if ( !$NODROP )  {  # always print drop table if user doesn't explicitly say not to
-        #  to drop a table that is referenced by a view or a foreign-key constraint of another table,
-        #  CASCADE must be specified. (CASCADE will remove a dependent view entirely, but in the
-        #  in the foreign-key case it will only remove the foreign-key constraint, not the other table entirely.)
-        #  (source: 8.1.3 docs, section "drop table")
-        warn "table $table will be dropped CASCADE\n";
-        $pre_create_sql .= "DROP TABLE $table CASCADE;\n";    # custom dumps may be missing the 'dump' commands
-    }
-
-    s/(create\s+table\s+)([-_\w]+)\s/$1 $table /i;
-    if ($DEBUG) {
-        $create_sql .=  '-- ' . $_;
-    }
-    $create_sql .= $_;
-    next;
-}
-if ($create_sql ne "") {         # we are inside create table statement so lets process datatypes
-    # print out comments or empty lines in context
-    if ($DEBUG) {
-        $create_sql .=  '-- ' . $_;
-    }
-    if (/^#/ || /^$/ || /^\s*--/) {
-        s/^#/--/;   #  Two hyphens (--) is the SQL-92 standard indicator for comments
-        $create_sql.=$_;
-        next;
-    }
-
-    if (/\).*;/i) {    # end of create table squence
-
-        s/INSERT METHOD[=\s+][^;\s]+//i;
-        s/PASSWORD=[^;\s]+//i;
-        s/ROW_FORMAT=(?:DEFAULT|DYNAMIC|FIXED|COMPRESSED|REDUNDANT|COMPACT)+//i;
-        s/KEY_BLOCK_SIZE=8//i;
-        s/DELAY KEY WRITE=[^;\s]+//i;
-        s/INDEX DIRECTORY[=\s+][^;\s]+//i;
-        s/DATA DIRECTORY=[^;\s]+//i;
-        s/CONNECTION=[^;\s]+//i;
-        s/CHECKSUM=[^;\s]+//i;
-        s/Type=[^;\s]+//i; # ISAM ,   # older versions
-        s/COLLATE=[^;\s]+//i;         # table's collate
-        s/COLLATE\s+[^;\s]+//i;         # table's collate
-        # possible AUTO_INCREMENT starting index, it is used in mysql 5.0.26, not sure since which version
-        if (/AUTO_INCREMENT=(\d+)/i) {
-        # should take < ----  ) ENGINE=MyISAM AUTO_INCREMENT=16 DEFAULT CHARSET=latin1;
-        # and should ouput --->  CREATE SEQUENCE "rhm_host_info_id_seq" START WITH 16;
-        my $start_value = $1;
-        print $auto_increment_seq . "--\n";
-        # print $pre_create_sql . "--\n";
-        $pre_create_sql =~ s/(CREATE SEQUENCE $auto_increment_seq )/$1 START WITH $start_value /;
-    }
-        s/AUTO_INCREMENT=\d+//i;
-        s/PACK_KEYS=\d//i;            # mysql 5.0.22
-        s/DEFAULT CHARSET=[^;\s]+//i; #  my mysql version is 4.1.11
-        s/ENGINE\s*=\s*[^;\s]+//i;   #  my mysql version is 4.1.11
-        s/ROW_FORMAT=[^;\s]+//i;   #  my mysql version is 5.0.22
-        s/KEY_BLOCK_SIZE=8//i; 
-        s/MIN_ROWS=[^;\s]+//i;
-        s/MAX_ROWS=[^;\s]+//i;
-        s/AVG_ROW_LENGTH=[^;\s]+//i;
-        if (/COMMENT='([^']*)'/) {  # ) ENGINE=MyISAM DEFAULT CHARSET=utf8 COMMENT='must be country zones';
-            $post_create_sql.="COMMENT ON TABLE $table IS '$1'\;"; # COMMENT ON table_name IS 'text';
-            s/COMMENT='[^']*'//i;
-        }
-        $create_sql =~ s/,$//g;    # strip last , inside create table
-        # make sure we end in a comma, as KEY statments are turned
-        # into post_create_sql indices
-        # they often are the last line so leaving a 'hanging comma'
-        my @array = split("\n", $create_sql);
-        for (my $a = $#array; $a >= 0; $a--) {  #loop backwards
-            if ($a == $#array  && $array[$a] =~ m/,\s*$/) {    # for last line
-                $array[$a] =~ s/,\s*$//;
-                next;
-            }
-            if ($array[$a] !~ m/create table/i) {  # i.e. if there was more than one column in table
-                if ($a != $#array  && $array[$a] !~ m/,\s*$/  ) {  # for second to last
-                    $array[$a] =~ s/$/,/;
-                    last;
-                }
-                elsif ($a != $#array  && $array[$a] =~ m/,\s*$/ ) {  # for second to last
-                    last;
-                }
-            }
-        }
-        $create_sql = join("\n", @array) . "\n";
-        $create_sql .=  $_;
-
-        # put comments out first
-        print OUT $pre_create_sql;
-
-        # create separate table to reference and to hold mysql's possible set data-type
-        # values.  do that table's creation before create table
-        # definition
-        foreach $column_name (keys %constraints) {
-            $type=$constraints{$column_name}{'type'};
-            $column_valuesStr = $constraints{$column_name}{'values'};
-            $constraint_table_name = get_identifier(${table},${column_name} ,"constraint_table");
-            if ($type eq 'set') {
-                print OUT qq~DROP TABLE $constraint_table_name  CASCADE\\g\n~ ;
-                print OUT qq~create table $constraint_table_name  ( set_values varchar UNIQUE)\\g\n~ ;
-                $function_create_sql .= make_plpgsql($table,$column_name);
-            } elsif ($type eq 'year')  {
-                print OUT qq~DROP TABLE $constraint_table_name  CASCADE\\g\n~ ;
-                print OUT qq~create table $constraint_table_name  ( year_values varchar UNIQUE)\\g\n~ ;
-            }
-            @column_values = split /,/, $column_valuesStr;
-            foreach $value (@column_values) {
-                print OUT qq~insert into $constraint_table_name   values (  $value  )\\g\n~; # ad ' for ints and varchars
-            }
-        }
-
-        $create_sql =~ s/double double/double precision/g;
-
-        # print create table and reset create table vars
-        # when moving from each "create table" to "insert" part of dump
-        print OUT $create_sql;
-        print OUT $function_create_sql;
-        $pre_create_sql="";
-        $auto_increment_seq="";
-        $create_sql="";
-        $function_create_sql='';
-        %constraints=();
-        # the post_create_sql for this table is output at the beginning of the next table def
-        # in case we want to make indexes after doing inserting
-        next;
-    }
-    if (/^\s*(\w+)\s+.*COMMENT\s*'([^']*)'/) {  #`zone_country_id` int(11) COMMENT 'column comment here',
-        $quoted_column=quote_and_lc($1);
-        $post_create_sql.="COMMENT ON COLUMN $table"."."." $quoted_column IS '$2'\;"; # COMMENT ON table_name.column_name IS 'text';
-        s/COMMENT\s*'[^']*'//i;
-    }
-
-
-    # NUMERIC DATATYPES
-    #
-    # auto_increment -> sequences
-    # UNSIGNED conversions
-    # TINYINT
-    # SMALLINT
-    # MEDIUMINT
-    # INT, INTEGER
-    # BIGINT
-    #
-    # DOUBLE [PRECISION], REAL
-    # DECIMAL(M,D), NUMERIC(M,D)
-    # FLOAT(p)
-    # FLOAT
-
-    s/(\w*int)\(\d+\)/$1/g;  # hack of the (n) stuff for e.g. mediumint(2) int(3)
-
-    if (/^(\s*)(\w+)\s*.*numeric.*auto_increment/i) {         # int,auto_increment -> serial
-        $seq = get_identifier($table, $2, 'seq');
-        $quoted_column=quote_and_lc($2);
-        # Smash datatype to int8 and autogenerate the sequence.
-        s/^(\s*)(\w+)\s*.*NUMERIC(.*)auto_increment([^,]*)/$1 $quoted_column serial8 $4/ig;
-        $create_sql.=$_;
-        next;
-    }
-    if (/^\s*(\w+)\s+.*int.*auto_increment/i) {  #  example: data_id mediumint(8) unsigned NOT NULL auto_increment,
-        $seq = get_identifier($table, $1, 'seq');
-        $quoted_column=quote_and_lc($1);
-        s/(\s*)(\w+)\s+.*int.*auto_increment([^,]*)/$1 $quoted_column serial8 $3/ig;
-        $create_sql.=$_;
-        next;
-    }
-
-
-
-
-    # convert UNSIGNED to CHECK constraints
-    if (m/^(\s*)(\w+)\s+((float|double precision|double|real|decimal|numeric))(.*)unsigned/i) {
-        $quoted_column = quote_and_lc($2);
-        s/^(\s*)(\w+)\s+((float|double precision|double|real|decimal|numeric))(.*)unsigned/$1 $quoted_column $3 $4 CHECK ($quoted_column >= 0)/i;
-    }
-    # example:  `wordsize` tinyint(3) unsigned default NULL,
-    if (m/^(\s+)(\w+)\s+(\w+)\s+unsigned/i) {
-        $quoted_column=quote_and_lc($2);
-        s/^(\s+)(\w+)\s+(\w+)\s+unsigned/$1 $quoted_column $3 CHECK ($quoted_column >= 0)/i;
-    }
-    if (m/^(\s*)(\w+)\s+(bigint.*)unsigned/) {
-        $quoted_column=quote_and_lc($2);
-        #  see http://archives.postgresql.org/pgsql-general/2005-07/msg01178.php
-        #  and see http://www.postgresql.org/docs/8.2/interactive/datatype-numeric.html
-        # see  http://dev.mysql.com/doc/refman/5.1/en/numeric-types.html  max size == 20 digits
-        s/^(\s*)(\w+)\s+bigint(.*)unsigned/$1 $quoted_column NUMERIC (20,0) CHECK ($quoted_column >= 0)/i;
-
-    }
-
-    # int type conversion
-    # TINYINT    (signed) -128 to 127 (unsigned) 0   255
-    #  SMALLINT A small integer. The signed range is -32768 to 32767. The unsigned range is 0 to 65535.
-    #  MEDIUMINT  A medium-sized integer. The signed range is -8388608 to 8388607. The unsigned range is 0 to 16777215.
-    #  INT A normal-size integer. The signed range is -2147483648 to 2147483647. The unsigned range is 0 to 4294967295.
-    # BIGINT The signed range is -9223372036854775808 to 9223372036854775807. The unsigned range is 0 to 18446744073709551615
-    # for postgres see http://www.postgresql.org/docs/8.2/static/datatype-numeric.html#DATATYPE-INT
-    s/^(\s+"*\w+"*\s+)tinyint/$1 smallint/i;
-    s/^(\s+"*\w+"*\s+)mediumint/$1 integer/i;
-
-    # the floating point types
-    #   double -> double precision
-    #   double(n,m) -> double precision
-    #   float - no need for conversion
-    #   float(n) - no need for conversion
-    #   float(n,m) -> double precision
-
-    s/(^\s*\w+\s+)double(\(\d+,\d+\))?/$1float/i;
-    s/float(\(\d+,\d+\))/float/i;
-
-    #
-    # CHARACTER TYPES
-    #
-    # set
-    # enum
-    # binary(M), VARBINARy(M), tinyblob, tinytext,
-    # bit
-    # char(M), varchar(M)
-    # blob -> text
-    # mediumblob
-    # longblob, longtext
-    # text -> text
-    # mediumtext
-    # longtext
-    #  mysql docs: A BLOB is a binary large object that can hold a variable amount of data.
-
-    # set
-    # For example, a column specified as SET('one', 'two') NOT NULL can have any of these values:
-    # ''
-    # 'one'
-    # 'two'
-    # 'one,two'
-    if (/(\w*)\s+set\(((?:['"]\w+['"]\s*,*)+(?:['"]\w+['"])*)\)(.*)$/i) { # example:  `au_auth` set('r','w','d') NOT NULL default '',
-        $column_name = $1;
-        $constraints{$column_name}{'values'} = $2;  # 'abc','def', ...
-        $constraints{$column_name}{'type'} = "set";  # 'abc','def', ...
-        $_ =  qq~ $column_name varchar , ~;
-        $column_name = quote_and_lc($1);
-        $create_sql.=$_;
-        next;
-
-    }
-    if (/(\S*)\s+enum\(((?:['"][^'"]+['"]\s*,)+['"][^'"]+['"])\)(.*)$/i) { # enum handling
-        #  example:  `test` enum('?','+','-') NOT NULL default '?'
-        # $2  is the values of the enum 'abc','def', ...
-        $quoted_column=quote_and_lc($1);
-        #  "test" NOT NULL default '?' CONSTRAINT test_test_constraint CHECK ("test" IN ('?','+','-'))
-        $_ = qq~ $quoted_column varchar CHECK ($quoted_column IN ( $2 ))$3\n~;  # just assume varchar?
-        $create_sql.=$_;
-        next;
-    }
-    # Take care of "binary" option for char and varchar
-    # (pre-4.1.2, it indicated a byte array; from 4.1.2, indicates
-    # a binary collation)
-    s/(?:var)?char(?:\(\d+\))? (?:byte|binary)/text/i;
-    if (m/(?:var)?binary\s*\(\d+\)/i) {   #  c varBINARY(3) in Mysql
-        warn "WARNING in table '$table' '$_':  binary type is converted to bytea (unsized) for Postgres\n";
-    }
-    s/(?:var)?binary(?:\(\d+\))?/text/i;   #  c varBINARY(3) in Mysql
-    s/bit(?:\(\d+\))?/bytea/i;   #  bit datatype -> bytea
-
-    # large datatypes
-    s/\w*blob/bytea/gi;
-    s/tinytext/text/gi;
-    s/mediumtext/text/gi;
-    s/longtext/text/gi;
-
-    # char -> varchar -- if specified as a command line option
-    # PostgreSQL would otherwise pad with spaces as opposed
-    # to MySQL! Your user interface may depend on this!
-    if ($CHAR2VARCHAR) {
-        s/(^\s+\S+\s+)char/${1}varchar/gi;
-    }
-
-    # nuke column's collate and character set
-    s/(\S+)\s+character\s+set\s+\w+/$1/gi;
-    s/(\S+)\s+collate\s+\w+/$1/gi;
-
-    #
-    # DATE AND TIME TYPES
-    #
-    # date  time
-    # year
-    # datetime
-    # timestamp
-
-    # date  time
-    # these are the same types in postgres, just do the replacement of 0000-00-00 date
-
-    if (m/default '(\d+)-(\d+)-(\d+)([^']*)'/i) { # we grab the year, month and day
-        # NOTE: times of 00:00:00 are possible and are okay
-        my $time = '';
-        my $year=$1;
-        my $month= $2;
-        my $day = $3;
-        if ($4) {
-            $time = $4;
-        }
-        if ($year eq "0000") { $year = '1970'; }
-        if ($month eq "00") { $month = '01'; }
-        if ($day eq "00") { $day = '01'; }
-        s/default '[^']+'/default '$year-$month-$day$time'/i; # finally we replace with $datetime
-    }
-
-    # convert mysql's year datatype to a constraint
-    if (/(\w*)\s+year\(4\)(.*)$/i) { # can be integer OR string 1901-2155
-        $constraint_table_name = get_identifier($table,$1 ,"constraint_table");
-        $column_name=quote_and_lc($1);
-        @year_holder = ();
-        $year='';
-        for (1901 .. 2155) {
-                $year = "'$_'";
-            unless ($year =~ /2155/) { $year .= ','; }
-             push( @year_holder, $year);
-        }
-        $constraints{$column_name}{'values'} = join('','',@year_holder);   # '1901','1902', ...
-        $constraints{$column_name}{'type'} = "year";
-        $_ =  qq~ $column_name varchar CONSTRAINT ${table}_${column_name}_constraint REFERENCES $constraint_table_name ("year_values") $2\n~;
-        $create_sql.=$_;
-        next;
-    } elsif (/(\w*)\s+year\(2\)(.*)$/i) { # same for a 2-integer string
-        $constraint_table_name = get_identifier($table,$1 ,"constraint_table");
-        $column_name=quote_and_lc($1);
-        @year_holder = ();
-        $year='';
-        for (1970 .. 2069) {
-            $year = "'$_'";
-            if ($year =~ /2069/) { next; }
-            push( @year_holder, $year);
-        }
-        push( @year_holder, '0000');
-        $constraints{$column_name}{'values'} = join(',',@year_holder);   # '1971','1972', ...
-        $constraints{$column_name}{'type'} = "year";  # 'abc','def', ...
-        $_ =  qq~ $1 varchar CONSTRAINT ${table}_${column_name}_constraint REFERENCES $constraint_table_name ("year_values") $2\n~;
-        $create_sql.=$_;
-        next;
-    }
-
-    # datetime
-    # Default on a dump from MySQL 5.0.22 is in the same form as datetime so let it flow down
-    # to the timestamp section and deal with it there
-    s/(${sl})datetime /$1timestamp without time zone /i;
-
-    # change not null datetime field to null valid ones
-    # (to support remapping of "zero time" to null
-    # s/($sl)datetime not null/$1timestamp without time zone/i;
-
-
-    # timestamps
-    #
-    # nuke datetime representation (not supported in PostgreSQL)
-    # change default time of 0000-00-00 to 1970-01-01
-
-    # we may possibly need to create a trigger to provide
-    # equal functionality with ON UPDATE CURRENT TIMESTAMP
-
-
-    if (m/${sl}timestamp/i) {
-        if ( m/ON UPDATE CURRENT_TIMESTAMP/i )  {  # the ... default CURRENT_TIMESTAMP  only applies for blank inserts, not updates
-            s/ON UPDATE CURRENT_TIMESTAMP//i ;
-            m/^\s*(\w+)\s+timestamp/i ;
-            # automatic trigger creation
-            $table_no_quotes =~ s/"//g;
-$function_create_sql .= " CREATE OR REPLACE FUNCTION update_". $table_no_quotes . "() RETURNS trigger AS '
-BEGIN
-    NEW.$1 := CURRENT_TIMESTAMP;
-    RETURN NEW;
-END;
-' LANGUAGE 'plpgsql';
-
--- before INSERT is handled by 'default CURRENT_TIMESTAMP'
-CREATE TRIGGER add_current_date_to_".$table_no_quotes." BEFORE UPDATE ON ". $table . " FOR EACH ROW EXECUTE PROCEDURE
-update_".$table_no_quotes."();\n";
-
-        }
-        if ($tables_first_timestamp_column && m/DEFAULT NULL/i) {
-            # DEFAULT NULL is the same as DEFAULT CURRENT_TIMESTAMP for the first TIMESTAMP  column. (MYSQL manual)
-            s/($sl)(timestamp\s+)default null/$1 $2 DEFAULT CURRENT_TIMESTAMP/i;
-        }
-        $tables_first_timestamp_column= 0;
-        if (m/${sl}timestamp\s*\(\d+\)/i) {   # fix for timestamps with width spec not handled (ID: 1628)
-            warn "WARNING for in table '$table' '$_': your default timestamp width is being ignored for table $table \n";
-            s/($sl)timestamp(?:\(\d+\))/$1datetime/i;
-        }
-    } # end timestamp section
-
-    # KEY AND UNIQUE CREATIONS
-    #
-    # unique
-    if ( /^\s+unique\s+\(([^(]+)\)/i ) { #  example    UNIQUE `name` (`name`), same as UNIQUE KEY
-        #  POSTGRESQL:  treat same as mysql unique
-        $quoted_column = quote_and_lc($1);
-        s/\s+unique\s+\(([^(]+)\)/ unique ($quoted_column) /i;
-            $create_sql.=$_;
-        next;
-        } elsif ( /^\s+unique\s+key\s*(\w+)\s*\(([^(]+)\)/i ) { #  example    UNIQUE KEY `name` (`name`)
-            #  MYSQL: unique  key: allows null=YES, allows duplicates=NO (*)
-            #  ... new ... UNIQUE KEY `unique_fullname` (`fullname`)  in my mysql v. Ver 14.12 Distrib 5.1.7-beta
-            #  POSTGRESQL:  treat same as mysql unique
-        # just quote columns
-        $quoted_column = quote_and_lc($2);
-            s/\s+unique\s+key\s*(\w+)\s*\(([^(]+)\)/ unique ($quoted_column) /i;
-            $create_sql.=$_;
-        # the index corresponding to the 'key' is automatically created
-            next;
-    }
-    # keys
-    if ( /^\s+fulltext key\s+/i) { # example:  FULLTEXT KEY `commenttext` (`commenttext`)
-    # that is key as a word in the first check for a match
-        # the tsvector datatype is made for these types of things
-        # example mysql file:
-        #  what is tsvector datatype?
-        #  http://www.sai.msu.su/~megera/postgres/gist/tsearch/V2/docs/tsearch-V2-intro.html
-        warn "dba must do fulltext key transformation for $table\n";
-        next;
-    }
-    if ( /^(\s+)constraint (\S+) foreign key \((\S+)\) references (\S+) \((\S+)\)(.*)/i ) {
-        $quoted_column =quote_and_lc($3);
-        $col=quote_and_lc($5);
-        $post_create_sql .= "ALTER TABLE $table ADD FOREIGN KEY ($quoted_column) REFERENCES " . quote_and_lc($4) . " ($col);\n";
-        next;
-    }
-    if ( /^\s*primary key\s*\(([^)]+)\)([,\s]+)/i ) { #  example    PRIMARY KEY (`name`)
-        # MYSQL: primary key: allows null=NO , allows duplicates=NO
-        #  POSTGRESQL: When an index is declared unique, multiple table rows with equal indexed values will not be
-        #       allowed. Null values are not considered equal.
-        #  POSTGRESQL quote's source: 8.1.3 docs section 11.5 "unique indexes"
-        #  so, in postgres, we need to add a NOT NULL to the UNIQUE constraint
-        # and, primary key (mysql) == primary key (postgres) so that we *really* don't need change anything
-        $quoted_column = quote_and_lc($1);
-        s/(\s*)primary key\s+\(([^)]+)\)([,\s]+)/$1 primary key ($quoted_column)$3/i;
-        # indexes are automatically created for unique columns
-        $create_sql.=$_;
-        next;
-    } elsif (m/^\s+key\s[-_\s\w]+\((.+)\)/i    ) {     # example:   KEY `idx_mod_english_def_word` (`word`),
-        # regular key: allows null=YES, allows duplicates=YES
-        # MYSQL:   KEY is normally a synonym for INDEX.  http://dev.mysql.com/doc/refman/5.1/en/create-table.html
-        #
-        #  * MySQL: ALTER TABLE {$table} ADD KEY $column ($column)
-        #  * PostgreSQL: CREATE INDEX {$table}_$column_idx ON {$table}($column) // Please note the _idx "extension"
-        #    PRIMARY KEY (`postid`),
-        #    KEY `ownerid` (`ownerid`)
-        # create an index for everything which has a key listed for it.
-        my $col = $1;
-        # TODO we don't have a translation for the substring syntax in text columns in MySQL (e.g. "KEY my_idx (mytextcol(20))")
-        # for now just getting rid of the brackets and numbers (the substring specifier):
-        $col=~s/\(\d+\)//g;
-        $quoted_column = quote_and_lc($col);
-        if ($col =~ m/,/) {
-            $col =  s/,/_/;
-        }
-        $index = get_identifier($table, $col, 'idx');
-        $post_create_sql.="CREATE INDEX $index ON $table USING btree ($quoted_column)\;";
-        # just create index do not add to create table statement
-        next;
-    }
-
-    # handle 'key' declared at end of column
-    if (/\w+.*primary key/i) {   # mysql: key is normally just a synonym for index
-    # just leave as is ( postgres has primary key type)
-
-
-    } elsif (/(\w+\s+(?:$mysql_datatypesStr)\s+.*)key/i) {   # mysql: key is normally just a synonym for index
-    # I can't find a reference for 'key' in a postgres command without using the word 'primary key'
-        s/$1key/$1/i ;
-        $index = get_identifier($table, $1, 'idx');
-        $quoted_column =quote_and_lc($1);
-        $post_create_sql.="CREATE INDEX $index ON $table USING btree ($quoted_column) \;";
-        $create_sql.=$_;
-    }
-
-
-
-    # do we really need this anymore?
-    # remap colums with names of existing system attribute
-    if (/"oid"/i) {
-        s/"oid"/"_oid"/g;
-        print STDERR "WARNING: table $table uses column \"oid\" which is renamed to \"_oid\"\nYou should fix application manually! Press return to continue.";
-        my $wait=<STDIN>;
-    }
-
-    s/oid/_oid/i if (/key/i && /oid/i); # fix oid in key
-
-    # FINAL QUOTING OF ALL COLUMNS
-    # quote column names which were not already quoted
-    # perhaps they were not quoted because they were not explicitly handled
-    if (!/^\s*"(\w+)"(\s+)/i) {
-        /^(\s*)(\w+)(\s+)(.*)$/i ;
-        $quoted_column= quote_and_lc($2);
-        s/^(\s*)(\w+)(\s+)(.*)$/$1 $quoted_column $3 $4 /;
-    }
-    $create_sql.=$_;
-    #  END of if ($create_sql ne "") i.e. were inside create table statement so processed datatypes
-}
-# add "not in create table" comments or empty lines to pre_create_sql
-elsif (/^#/ || /^$/ || /^\s*--/) {
-    s/^#/--/;   #  Two hyphens (--) is the SQL-92 standard indicator for comments
-    $pre_create_sql .=  $_ ;  # printed above create table statement
-    next;
-}
-elsif (/^\s*insert into/i) { # not inside create table and doing insert
-    # fix mysql's zero/null value for timestamps
-    s/'0000-00-00/'1970-01-01/gi;
-    # commented out to fix bug "Field contents interpreted as a timestamp", what was the point of this line anyway?
-    #s/([12]\d\d\d)([01]\d)([0-3]\d)([0-2]\d)([0-6]\d)([0-6]\d)/'$1-$2-$3 $4:$5:$6'/;
-
-    #---- fix data in inserted data: (from MS world)
-    s!\x96!-!g;    # --
-    s!\x93!"!g;    # ``
-    s!\x94!"!g;    # ''
-    s!\x85!... !g;    # \ldots
-    s!\x92!`!g;
-
-    print OUT $pre_create_sql;    # print comments preceding the insert section
-    $pre_create_sql="";
-    $auto_increment_seq = "";
-
-    s/'((?:[^'\\]++|\\.)*+)'(?=[),])/E'$1'/g;
-    # for the E'' see http://www.postgresql.org/docs/8.2/interactive/release-8-1.html
-    s!\\\\!\\\\\\\\!g;      # replace \\ with ]\\\\
-
-    # split 'extended' INSERT INTO statements to something PostgreSQL can  understand
-    ( $insert_table,  $valueString) = $_ =~ m/^INSERT\s+INTO\s+['`"]*(.*?)['`"]*\s+VALUES\s*(.*)/i;
-    $insert_table = quote_and_lc($insert_table);
-
-    s/^INSERT INTO.*?\);//i;  # hose the statement which is to be replaced whether a run-on or not
-    # guarantee table names are quoted
-    print OUT qq(INSERT INTO $insert_table VALUES $valueString \n);
-
-} else {
-    print OUT $_ ;  #  example: /*!40101 SET @OLD_CHARACTER_SET_CLIENT=@@CHARACTER_SET_CLIENT */;
-}
-#  keep looping and get next line of IN file
-
-} # END while(<IN>)
-
-print_post_create_sql();   # in case there is extra from the last table
-
-#################################################################
-#  5.  print_plgsql function prototype
-#      emulate the set datatype with the following plpgsql function
-#      looks ugly so putting at end of file
-#################################################################
-#
-sub make_plpgsql {
-my ($table,$column_name) = ($_[0],$_[1]);
-$table=~s/\"//g; # make sure that $table doesn't have quotes so we don't end up with redundant quoting
-my $constraint_table = get_identifier($table,$column_name ,"constraint_table");
-return "
--- this function is called by the insert/update trigger
--- it checks if the INSERT/UPDATE for the 'set' column
--- contains members which comprise a valid mysql set
--- this TRIGGER function therefore acts like a constraint
---  provided limited functionality for mysql's set datatype
--- just verifies and matches for string representations of the set at this point
--- though the set datatype uses bit comparisons, the only supported arguments to our
--- set datatype are VARCHAR arguments
--- to add a member to the set add it to the ".$table."_".$column_name." table
-CREATE OR REPLACE FUNCTION check_".$table."_".$column_name."_set(  ) RETURNS TRIGGER AS \$\$\n
-DECLARE
-----
-arg_str VARCHAR ;
-argx VARCHAR := '';
-nobreak INT := 1;
-rec_count INT := 0;
-psn INT := 0;
-str_in VARCHAR := NEW.$column_name;
-----
-BEGIN
-----
-IF str_in IS NULL THEN RETURN NEW ; END IF;
-arg_str := REGEXP_REPLACE(str_in, '\\',\\'', ',');  -- str_in is CONSTANT
-arg_str := REGEXP_REPLACE(arg_str, '^\\'', '');
-arg_str := REGEXP_REPLACE(arg_str, '\\'\$', '');
--- RAISE NOTICE 'arg_str %',arg_str;
-psn := POSITION(',' in arg_str);
-IF psn > 0 THEN
-    psn := psn - 1; -- minus-1 from comma position
-    -- RAISE NOTICE 'psn %',psn;
-    argx := SUBSTRING(arg_str FROM 1 FOR psn);  -- get one set member
-    psn := psn + 2; -- go to first starting letter
-    arg_str := SUBSTRING(arg_str FROM psn);   -- hack it off
-ELSE
-    psn := 0; -- minus-1 from comma position
-    argx := arg_str;
-END IF;
--- RAISE NOTICE 'argx %',argx;
--- RAISE NOTICE 'new arg_str: %',arg_str;
-WHILE nobreak LOOP
-    EXECUTE 'SELECT count(*) FROM $constraint_table WHERE set_values = ' || quote_literal(argx) INTO rec_count;
-    IF rec_count = 0 THEN RAISE EXCEPTION 'one of the set values was not found';
-    END IF;
-    IF psn > 0 THEN
-        psn := psn - 1; -- minus-1 from comma position
-        -- RAISE NOTICE 'psn %',psn;
-        argx := SUBSTRING(arg_str FROM 1 FOR psn);  -- get one set member
-        psn := psn + 2; -- go to first starting letter
-        arg_str := SUBSTRING(arg_str FROM psn);   -- hack it off
-        psn := POSITION(',' in arg_str);
-    ELSE nobreak = 0;
-    END IF;
-    -- RAISE NOTICE 'next argx % and next arg_str %', argx, arg_str;
-END LOOP;
-RETURN NEW;
-----
-END;
-\$\$ LANGUAGE 'plpgsql' VOLATILE;
-
-drop trigger set_test ON $table;
--- make a trigger for each set field
--- make trigger and hard-code in column names
--- see http://archives.postgresql.org/pgsql-interfaces/2005-02/msg00020.php
-CREATE   TRIGGER    set_test
-BEFORE   INSERT OR   UPDATE  ON $table   FOR  EACH  ROW
-EXECUTE  PROCEDURE  check_".$table."_".$column_name."_set();\n";
-} #  end sub make_plpgsql();
-

data-sources/wikipedia-wikidata/wikidata_place_type_levels.csv

@@ -1,199 +0,0 @@
-place_type,level
-Q9842,4
-Q9430,3
-Q928830,4
-Q9259,1
-Q91028,5
-Q8514,2
-Q8502,2
-Q83405,3
-Q82794,2
-Q820477,1
-Q811979,1
-Q8072,2
-Q79007,2
-Q786014,3
-Q75848,2
-Q75520,2
-Q728937,4
-Q7275,2
-Q719456,3
-Q7075,3
-Q697295,4
-Q6852233,2
-Q682943,3
-Q665487,5
-Q655686,3
-Q643589,5
-Q641226,2
-Q631305,2
-Q6256,2
-Q6023295,2
-Q5773747,5
-Q56061,1
-Q55659167,4
-Q55488,4
-Q55465477,3
-Q54050,2
-Q532,3
-Q53060,2
-Q52177058,4
-Q515716,5
-Q5153984,4
-Q515,3
-Q5144960,5
-Q5119,4
-Q5119,4
-Q5107,2
-Q5084,4
-Q5031071,4
-Q5003624,2
-Q4989906,1
-Q4976993,3
-Q486972,1
-Q486972,2
-Q483110,3
-Q4830453,4
-Q47521,3
-Q473972,1
-Q46831,2
-Q46614560,5
-Q44782,3
-Q44613,4
-Q44539,4
-Q44494,2
-Q44377,2
-Q4421,2
-Q43501,2
-Q4286337,3
-Q42523,3
-Q41176,2
-Q40357,3
-Q4022,4
-Q40080,2
-Q39816,2
-Q39715,3
-Q39614,1
-Q3957,3
-Q3947,4
-Q3914,3
-Q38723,2
-Q38720,3
-Q3623867,5
-Q35666,2
-Q355304,3
-Q35509,2
-Q35112127,3
-Q34985575,4
-Q34876,5
-Q34763,2
-Q34627,4
-Q3455524,3
-Q34442,4
-Q33837,2
-Q33506,3
-Q32815,4
-Q3257686,2
-Q3240715,2
-Q3191695,5
-Q3153117,2
-Q30198,2
-Q30139652,3
-Q294422,3
-Q2870166,3
-Q27686,3
-Q274153,3
-Q271669,1
-Q2659904,2
-Q24529780,2
-Q24354,3
-Q2354973,4
-Q23442,2
-Q23413,3
-Q23397,3
-Q2327515,4
-Q2311958,5
-Q22927291,6
-Q22698,1
-Q2175765,4
-Q205495,4
-Q204832,3
-Q2042028,2
-Q202216,6
-Q1970725,3
-Q194203,5
-Q194195,2
-Q190429,2
-Q185187,3
-Q185113,2
-Q183366,2
-Q1799794,1
-Q1788454,4
-Q1785071,3
-Q1777138,3
-Q177634,2
-Q177380,2
-Q174814,4
-Q174782,2
-Q17350442,2
-Q17343829,3
-Q17334923,0
-Q17018380,3
-Q16970,4
-Q16917,3
-Q16831714,4
-Q165,3
-Q160742,4
-Q159719,3
-Q159334,4
-Q15640612,5
-Q15324,2
-Q15284,5
-Q15243209,6
-Q152081,1
-Q15195406,4
-Q1500350,5
-Q149621,5
-Q14757767,4
-Q14350,3
-Q1410668,3
-Q1394476,3
-Q1377575,2
-Q1353183,3
-Q134447,4
-Q133215,3
-Q133056,2
-Q13221722,3
-Q13220204,2
-Q1311958,4
-Q1303167,3
-Q130003,3
-Q12518,2
-Q12516,3
-Q1248784,3
-Q123705,3
-Q12323,3
-Q12284,4
-Q12280,4
-Q121359,2
-Q1210950,2
-Q11755880,3
-Q11707,3
-Q11315,3
-Q11303,3
-Q1115575,4
-Q1107656,1
-Q10864048,1
-Q1076486,2
-Q105731,3
-Q105190,3
-Q1048525,3
-Q102496,5
-Q28872924,1
-Q15617994,1
-Q159313,2
-Q24398318,3
-Q327333,2
-Q43229,1
-Q860861,1
-Q4989906,1

data-sources/wikipedia-wikidata/wikidata_place_types.txt

@@ -1,195 +0,0 @@
-Q9842
-Q9430
-Q928830
-Q9259
-Q91028
-Q8514
-Q8502
-Q83405
-Q82794
-Q820477
-Q811979
-Q8072
-Q79007
-Q786014
-Q75848
-Q75520
-Q728937
-Q7275
-Q719456
-Q7075
-Q697295
-Q6852233
-Q682943
-Q665487
-Q655686
-Q643589
-Q641226
-Q631305
-Q6256
-Q6023295
-Q5773747
-Q56061
-Q55659167
-Q55488
-Q55465477
-Q54050
-Q532
-Q53060
-Q52177058
-Q515716
-Q5153984
-Q515
-Q5144960
-Q5119
-Q5107
-Q5084
-Q5031071
-Q5003624
-Q4989906
-Q4976993
-Q486972
-Q483110
-Q4830453
-Q47521
-Q473972
-Q46831
-Q46614560
-Q44782
-Q44613
-Q44539
-Q44494
-Q44377
-Q4421
-Q43501
-Q4286337
-Q42523
-Q41176
-Q40357
-Q4022
-Q40080
-Q39816
-Q39715
-Q39614
-Q3957
-Q3947
-Q3914
-Q38723
-Q38720
-Q3623867
-Q35666
-Q355304
-Q35509
-Q35112127
-Q34985575
-Q34876
-Q34763
-Q34627
-Q3455524
-Q34442
-Q33837
-Q33506
-Q32815
-Q3257686
-Q3240715
-Q3191695
-Q3153117
-Q30198
-Q30139652
-Q294422
-Q2870166
-Q27686
-Q274153
-Q271669
-Q2659904
-Q24529780
-Q24354
-Q2354973
-Q23442
-Q23413
-Q23397
-Q2327515
-Q2311958
-Q22927291
-Q22698
-Q2175765
-Q205495
-Q204832
-Q2042028
-Q202216
-Q1970725
-Q194203
-Q194195
-Q190429
-Q185187
-Q185113
-Q183366
-Q1799794
-Q1788454
-Q1785071
-Q1777138
-Q177634
-Q177380
-Q174814
-Q174782
-Q17350442
-Q17343829
-Q17334923
-Q17018380
-Q16970
-Q16917
-Q16831714
-Q165
-Q160742
-Q159719
-Q159334
-Q15640612
-Q15324
-Q15284
-Q15243209
-Q152081
-Q15195406
-Q1500350
-Q149621
-Q14757767
-Q14350
-Q1410668
-Q1394476
-Q1377575
-Q1353183
-Q134447
-Q133215
-Q133056
-Q13221722
-Q13220204
-Q1311958
-Q1303167
-Q130003
-Q12518
-Q12516
-Q1248784
-Q123705
-Q12323
-Q12284
-Q12280
-Q121359
-Q1210950
-Q11755880
-Q11707
-Q11315
-Q11303
-Q1115575
-Q1107656
-Q10864048
-Q1076486
-Q105731
-Q105190
-Q1048525
-Q102496
-Q28872924
-Q15617994
-Q159313
-Q24398318
-Q327333
-Q43229
-Q860861

data-sources/wikipedia-wikidata/wikidata_places.md

@@ -1,200 +0,0 @@
-
-## Wikidata place types and related OSM Tags
-
-Wikidata does not have any official ontologies, however the [DBpedia project](https://wiki.dbpedia.org/) has created an [ontology](https://wiki.dbpedia.org/services-resources/ontology) that covered [place types](http://mappings.dbpedia.org/server/ontology/classes/#Place). The table below used the DBpedia place ontology as a starting point, and is provided as a cross-reference to the relevant OSM tags.
-
-The Wikidata place types listed in the table below can be used in conjunction with the [Wikidata Query Service](https://query.wikidata.org/) to retrieve instances of those place types from the Wikidata knowledgebase. 
-
-```
-SELECT ?item ?lat ?lon
-WHERE {
-  ?item wdt:P31*/wdt:P279*wd:Q9430; wdt:P625 ?pt.
-  ?item p:P625?loc.
-  ?loc psv:P625?cnode.
-  ?cnode wikibase:geoLatitude?lat.
-  ?cnode wikibase:geoLongitude?lon.
-}
-```
-
-An example json return for all instances of the Wikidata item "Q9430" (Ocean) can be seen at [json](https://query.wikidata.org/bigdata/namespace/wdq/sparql?format=json&query=SELECT?item?lat?lon%20WHERE{?item%20wdt:P31*/wdt:P279*wd:Q9430;wdt:P625?pt.?item%20p:P625?loc.?loc%20psv:P625?cnode.?cnode%20wikibase:geoLatitude?lat.?cnode%20wikibase:geoLongitude?lon.})
-
-**NOTE** the OSM tags listed are those listed in the wikidata entries, and not all the possible matches for tags within OSM.
-
-
-   title   |             concept                   |       OSM Tag     | 
------------|---------------------------------------|------------------|
-[Q17334923](https://www.wikidata.org/entity/Q17334923)  | Location | | 
-[Q811979](https://www.wikidata.org/entity/Q811979)           | Architectural Structure | | 
-[Q194195](https://www.wikidata.org/entity/Q194195)   | Amusement park | 
-[Q204832](https://www.wikidata.org/entity/Q204832)   | Roller coaster | [attraction=roller_coaster](https://wiki.openstreetmap.org/wiki/Tag:attraction=roller_coaster) | 
-[Q2870166](https://www.wikidata.org/entity/Q2870166)   | Water ride | |
-[Q641226](https://www.wikidata.org/entity/Q641226)    | Arena | [amenity=events_centre](https://wiki.openstreetmap.org/wiki/Tag:amenity=events_centre) | 
-[Q41176](https://www.wikidata.org/entity/Q41176)     | Building | [building=yes](https://wiki.openstreetmap.org/wiki/Key:building) |
-[Q1303167](https://www.wikidata.org/entity/Q1303167)   | Barn | [building=barn](https://wiki.openstreetmap.org/wiki/Tag:building=barn) |
-[Q655686](https://www.wikidata.org/entity/Q655686)   | Commercial building | [building=commercial](https://wiki.openstreetmap.org/wiki/Tag:building=commercial) | 
-[Q4830453](https://www.wikidata.org/entity/Q4830453)   | Business | |
-[Q7075](https://www.wikidata.org/entity/Q7075)     | Library | [amenity=library](https://wiki.openstreetmap.org/wiki/Tag:amenity=library) |
-[Q133215](https://www.wikidata.org/entity/Q133215)   | Casino | [amenity=casino](https://wiki.openstreetmap.org/wiki/Tag:amenity=casino) | 
-[Q23413](https://www.wikidata.org/entity/Q23413)     | Castle | [historic=castle](https://wiki.openstreetmap.org/wiki/Tag:historic=castle) |
-[Q83405](https://www.wikidata.org/entity/Q83405)     | Factory | | 
-[Q53060](https://www.wikidata.org/entity/Q53060)     | Gate  | [barrier=gate](https://wiki.openstreetmap.org/wiki/Tag:barrier=gate) |cnode%20wikibase:geoLatitude?lat.?cnode%20wikibase:geoLongitude?lon.})
-[Q11755880](https://www.wikidata.org/entity/Q11755880)           | Residential Building  | [building=residential](https://wiki.openstreetmap.org/wiki/Tag:building=residential) | 
-[Q3947](https://www.wikidata.org/entity/Q3947)      | House  | [building=house](https://wiki.openstreetmap.org/wiki/Tag:building=house) |
-[Q35112127](https://www.wikidata.org/entity/Q35112127)           | Historic Building  | |
-[Q5773747](https://www.wikidata.org/entity/Q5773747)   | Historic house  | | 
-[Q38723](https://www.wikidata.org/entity/Q38723)           | Higher Education Institution  | 
-[Q3914](https://www.wikidata.org/entity/Q3914)      | School  | [amenity=school](https://wiki.openstreetmap.org/wiki/Tag:amenity=school) | 
-[Q9842](https://www.wikidata.org/entity/Q9842)      | Primary school  | | 
-[Q159334](https://www.wikidata.org/entity/Q159334)    | Secondary school  | | 
-[Q16917](https://www.wikidata.org/entity/Q16917)     | Hospital  | [amenity=hospital](https://wiki.openstreetmap.org/wiki/Tag:amenity=hospital), [healthcare=hospital](https://wiki.openstreetmap.org/wiki/Tag:healthcare=hospital), [building=hospital](https://wiki.openstreetmap.org/wiki/Tag:building=hospital) |
-[Q27686](https://www.wikidata.org/entity/Q27686)     | Hotel  | [tourism=hotel](https://wiki.openstreetmap.org/wiki/Tag:tourism=hotel), [building=hotel](https://wiki.openstreetmap.org/wiki/Tag:building=hotel) |
-[Q33506](https://www.wikidata.org/entity/Q33506)     | Museum  | [tourism=museum](https://wiki.openstreetmap.org/wiki/Tag:tourism=museum) |
-[Q40357](https://www.wikidata.org/entity/Q40357)     | Prison  | [amenity=prison](https://wiki.openstreetmap.org/wiki/Tag:amenity=prison) |
-[Q24398318](https://www.wikidata.org/entity/Q24398318)           | Religious Building  | |
-[Q160742](https://www.wikidata.org/entity/Q160742)    | Abbey  | |
-[Q16970](https://www.wikidata.org/entity/Q16970)     | Church (building)  | [building=church](https://wiki.openstreetmap.org/wiki/Tag:building=church) |
-[Q44613](https://www.wikidata.org/entity/Q44613)     | Monastery  | [amenity=monastery](https://wiki.openstreetmap.org/wiki/Tag:amenity=monastery) | 
-[Q32815](https://www.wikidata.org/entity/Q32815)     | Mosque  | [building=mosque](https://wiki.openstreetmap.org/wiki/Tag:building=mosque) | 
-[Q697295](https://www.wikidata.org/entity/Q697295)    | Shrine  | [building=shrine](https://wiki.openstreetmap.org/wiki/Tag:building=shrine) |
-[Q34627](https://www.wikidata.org/entity/Q34627)     | Synagogue  | [building=synagogue](https://wiki.openstreetmap.org/wiki/Tag:building=synagogue) |
-[Q44539](https://www.wikidata.org/entity/Q44539)     | Temple  | [building=temple](https://wiki.openstreetmap.org/wiki/Tag:building=temple) | 
-[Q11707](https://www.wikidata.org/entity/Q11707)     | Restaurant  | [amenity=restaurant](https://wiki.openstreetmap.org/wiki/Tag:amenity=restaurant) |
-[Q11315](https://www.wikidata.org/entity/Q11315)     | Shopping mall  | [shop=mall](https://wiki.openstreetmap.org/wiki/Tag:shop=mall), [shop=shopping_centre](https://wiki.openstreetmap.org/wiki/Tag:shop=shopping_centre) | 
-[Q11303](https://www.wikidata.org/entity/Q11303)     | Skyscraper  | |
-[Q17350442](https://www.wikidata.org/entity/Q17350442)           | Venue  | |
-[Q41253](https://www.wikidata.org/entity/Q41253)           | Movie Theater  | [amenity=cinema](https://wiki.openstreetmap.org/wiki/Tag:amenity=cinema) | 
-[Q483110](https://www.wikidata.org/entity/Q483110)    | Stadium  | [leisure=stadium](https://wiki.openstreetmap.org/wiki/Tag:leisure=stadium), [building=stadium](https://wiki.openstreetmap.org/wiki/Tag:building=stadium) |
-[Q24354](https://www.wikidata.org/entity/Q24354)     | Theater (structure)  | [amenity=theatre](https://wiki.openstreetmap.org/wiki/Tag:amenity=theatre) |
-[Q121359](https://www.wikidata.org/entity/Q121359)    | Infrastructure  | |
-[Q1248784](https://www.wikidata.org/entity/Q1248784)   | Airport  | |
-[Q12323](https://www.wikidata.org/entity/Q12323)     | Dam  | [waterway=dam](https://wiki.openstreetmap.org/wiki/Tag:waterway=dam) |
-[Q1353183](https://www.wikidata.org/entity/Q1353183)   | Launch pad  | | 
-[Q105190](https://www.wikidata.org/entity/Q105190)   | Levee  | [man_made=dyke](https://wiki.openstreetmap.org/wiki/Tag:man_made=dyke) |
-[Q105731](https://www.wikidata.org/entity/Q105731)    | Lock (water navigation)   | [lock=yes](https://wiki.openstreetmap.org/wiki/Key:lock) |
-[Q44782](https://www.wikidata.org/entity/Q44782)     | Port  | |
-[Q159719](https://www.wikidata.org/entity/Q159719)    | Power station  | [power=plant](https://wiki.openstreetmap.org/wiki/Tag:power=plant) |
-[Q174814](https://www.wikidata.org/entity/Q174814)    | Electrical substation   |  |
-[Q134447](https://www.wikidata.org/entity/Q134447)    | Nuclear power plant  | [plant:source=nuclear](https://wiki.openstreetmap.org/wiki/Tag:plant:source=nuclear) |
-[Q786014](https://www.wikidata.org/entity/Q786014)   | Rest area  | [highway=rest_area](https://wiki.openstreetmap.org/wiki/Tag:highway=rest_area), [highway=services](https://wiki.openstreetmap.org/wiki/Tag:highway=services) |
-[Q12280](https://www.wikidata.org/entity/Q12280)     | Bridge  | [bridge=* ](https://wiki.openstreetmap.org/wiki/Key:bridge), [man_made=bridge](https://wiki.openstreetmap.org/wiki/Tag:man_made=bridge) |
-[Q728937](https://www.wikidata.org/entity/Q728937)           | Railroad Line  | [railway=rail](https://wiki.openstreetmap.org/wiki/Tag:railway=rail) | 
-[Q1311958](https://www.wikidata.org/entity/Q1311958)           | Railway Tunnel  | | 
-[Q34442](https://www.wikidata.org/entity/Q34442)     | Road  | [highway=* ](https://wiki.openstreetmap.org/wiki/Key:highway), [route=road](https://wiki.openstreetmap.org/wiki/Tag:route=road) |
-[Q1788454](https://www.wikidata.org/entity/Q1788454)   | Road junction  |  | 
-[Q44377](https://www.wikidata.org/entity/Q44377)     | Tunnel  | [tunnel=* ](https://wiki.openstreetmap.org/wiki/Key:tunnel) |
-[Q5031071](https://www.wikidata.org/entity/Q5031071)  | Canal tunnel  | |
-[Q719456](https://www.wikidata.org/entity/Q719456)    | Station  | [public_transport=station](https://wiki.openstreetmap.org/wiki/Tag:public_transport=station) |
-[Q205495](https://www.wikidata.org/entity/Q205495)    | Filling station  | [amenity=fuel](https://wiki.openstreetmap.org/wiki/Tag:amenity=fuel) |
-[Q928830](https://www.wikidata.org/entity/Q928830)    | Metro station  | [station=subway](https://wiki.openstreetmap.org/wiki/Tag:station=subway) |
-[Q55488](https://www.wikidata.org/entity/Q55488)     | Train station  | [railway=station](https://wiki.openstreetmap.org/wiki/Tag:railway=station) |
-[Q2175765](https://www.wikidata.org/entity/Q2175765)   | Tram stop  | [railway=tram_stop](https://wiki.openstreetmap.org/wiki/Tag:railway=tram_stop), [public_transport=stop_position](https://wiki.openstreetmap.org/wiki/Tag:public_transport=stop_position) |
-[Q6852233](https://www.wikidata.org/entity/Q6852233)   | Military building  | |
-[Q44494](https://www.wikidata.org/entity/Q44494)     | Mill (grinding)  | |
-[Q185187](https://www.wikidata.org/entity/Q185187)    | Watermill  | [man_made=watermill](https://wiki.openstreetmap.org/wiki/Tag:man_made=watermill) |
-[Q38720](https://www.wikidata.org/entity/Q38720)     | Windmill  | [man_made=windmill](https://wiki.openstreetmap.org/wiki/Tag:man_made=windmill) | 
-[Q4989906](https://www.wikidata.org/entity/Q4989906)   | Monument  | [historic=monument](https://wiki.openstreetmap.org/wiki/Tag:historic=monument) |
-[Q5003624](https://www.wikidata.org/entity/Q5003624)   | Memorial  | [historic=memorial](https://wiki.openstreetmap.org/wiki/Tag:historic=memorial) |
-[Q271669](https://www.wikidata.org/entity/Q271669)   | Landform  | |
-[Q190429](https://www.wikidata.org/entity/Q190429)    | Depression (geology)  | |
-[Q17018380](https://www.wikidata.org/entity/Q17018380)  | Bight (geography)  | | 
-[Q54050](https://www.wikidata.org/entity/Q54050)     | Hill  | |
-[Q1210950](https://www.wikidata.org/entity/Q1210950)   | Channel (geography)  | |
-[Q23442](https://www.wikidata.org/entity/Q23442)    | Island  | [place=island](https://wiki.openstreetmap.org/wiki/Tag:place=island) | 
-[Q42523](https://www.wikidata.org/entity/Q42523)    | Atoll  | |
-[Q34763](https://www.wikidata.org/entity/Q34763)    | Peninsula  | | 
-[Q355304](https://www.wikidata.org/entity/Q355304)   | Watercourse  | |
-[Q30198](https://www.wikidata.org/entity/Q30198)    | Marsh  | [wetland=marsh](https://wiki.openstreetmap.org/wiki/Tag:wetland=marsh) |
-[Q75520](https://www.wikidata.org/entity/Q75520)    | Plateau  | |
-[Q2042028](https://www.wikidata.org/entity/Q2042028)  | Ravine  | |
-[Q631305](https://www.wikidata.org/entity/Q631305)   | Rock formation  | | 
-[Q12516](https://www.wikidata.org/entity/Q12516)    | Pyramid  | |
-[Q1076486](https://www.wikidata.org/entity/Q1076486) | Sports venue  |  |
-[Q682943](https://www.wikidata.org/entity/Q682943)   | Cricket field  | [sport=cricket](https://wiki.openstreetmap.org/wiki/Tag:sport=cricket) | 
-[Q1048525](https://www.wikidata.org/entity/Q1048525)  | Golf course  | [leisure=golf_course](https://wiki.openstreetmap.org/wiki/Tag:leisure=golf_course) |
-[Q1777138](https://www.wikidata.org/entity/Q1777138)  | Race track  | [highway=raceway](https://wiki.openstreetmap.org/wiki/Tag:highway=raceway) | 
-[Q130003](https://www.wikidata.org/entity/Q130003)   | Ski resort  | |
-[Q174782](https://www.wikidata.org/entity/Q174782)   | Town square  | [place=square](https://wiki.openstreetmap.org/wiki/Tag:place=square) |
-[Q12518](https://www.wikidata.org/entity/Q12518)    | Tower  | [building=tower](https://wiki.openstreetmap.org/wiki/Tag:building=tower), [man_made=tower](https://wiki.openstreetmap.org/wiki/Tag:man_made=tower) |
-[Q39715](https://www.wikidata.org/entity/Q39715)    | Lighthouse  | [man_made=lighthouse](https://wiki.openstreetmap.org/wiki/Tag:man_made=lighthouse) |
-[Q274153](https://www.wikidata.org/entity/Q274153)   | Water tower | [building=water_tower](https://wiki.openstreetmap.org/wiki/Tag:building=water_tower), [man_made=water_tower](https://wiki.openstreetmap.org/wiki/Tag:man_made=water_tower) |
-[Q43501](https://www.wikidata.org/entity/Q43501)    | Zoo  | [tourism=zoo](https://wiki.openstreetmap.org/wiki/Tag:tourism=zoo) | 
-[Q39614](https://www.wikidata.org/entity/Q39614)    | Cemetery  | [amenity=grave_yard](https://wiki.openstreetmap.org/wiki/Tag:amenity=grave_yard), [landuse=cemetery](https://wiki.openstreetmap.org/wiki/Tag:landuse=cemetery) |
-[Q152081](https://www.wikidata.org/entity/Q152081)   | Concentration camp  | |
-[Q1107656](https://www.wikidata.org/entity/Q1107656)  | Garden  | [leisure=garden](https://wiki.openstreetmap.org/wiki/Tag:leisure=garden) |
-[Q820477](https://www.wikidata.org/entity/Q820477)   | Mine |  | 
-[Q33837](https://www.wikidata.org/entity/Q33837) | Archipelago  | [place=archipelago](https://wiki.openstreetmap.org/wiki/Tag:place=archipelago) | 
-[Q40080](https://www.wikidata.org/entity/Q40080)    | Beach  | [natural=beach](https://wiki.openstreetmap.org/wiki/Tag:natural=beach) |
-[Q15324](https://www.wikidata.org/entity/Q15324)    | Body of water | [natural=water](https://wiki.openstreetmap.org/wiki/Tag:natural=water) | 
-[Q23397](https://www.wikidata.org/entity/Q23397)    | Lake  | [water=lake](https://wiki.openstreetmap.org/wiki/Tag:water=lake) | 
-[Q9430](https://www.wikidata.org/entity/Q9430)     | Ocean  | |
-[Q165](https://www.wikidata.org/entity/Q165)    | Sea  | |
-[Q47521](https://www.wikidata.org/entity/Q47521)    | Stream  | | 
-[Q12284](https://www.wikidata.org/entity/Q12284)    | Canal  | [waterway=canal](https://wiki.openstreetmap.org/wiki/Tag:waterway=canal) |
-[Q4022](https://www.wikidata.org/entity/Q4022)     | River  | [waterway=river](https://wiki.openstreetmap.org/wiki/Tag:waterway=river), [type=waterway](https://wiki.openstreetmap.org/wiki/Relation:waterway) |
-[Q185113](https://www.wikidata.org/entity/Q185113)   | Cape | [natural=cape](https://wiki.openstreetmap.org/wiki/Tag:natural=cape) | 
-[Q35509](https://www.wikidata.org/entity/Q35509)    | Cave  | [natural=cave_entrance](https://wiki.openstreetmap.org/wiki/Tag:natural=cave_entrance) | 
-[Q8514](https://www.wikidata.org/entity/Q8514)     | Desert  | | 
-[Q4421](https://www.wikidata.org/entity/Q4421)     | Forest  | [natural=wood](https://wiki.openstreetmap.org/wiki/Tag:natural=wood) |
-[Q35666](https://www.wikidata.org/entity/Q35666)    | Glacier  | [natural=glacier](https://wiki.openstreetmap.org/wiki/Tag:natural=glacier) |
-[Q177380](https://www.wikidata.org/entity/Q177380)   | Hot spring | | 
-[Q8502](https://www.wikidata.org/entity/Q8502)     | Mountain  | [natural=peak](https://wiki.openstreetmap.org/wiki/Tag:natural=peak) | 
-[Q133056](https://www.wikidata.org/entity/Q133056)   | Mountain pass  | | 
-[Q46831](https://www.wikidata.org/entity/Q46831)    | Mountain range  | |
-[Q39816](https://www.wikidata.org/entity/Q39816)    | Valley  | [natural=valley](https://wiki.openstreetmap.org/wiki/Tag:natural=valley) |
-[Q8072](https://www.wikidata.org/entity/Q8072)     | Volcano  | [natural=volcano](https://wiki.openstreetmap.org/wiki/Tag:natural=volcano) |
-[Q43229](https://www.wikidata.org/entity/Q43229)    | Organization  |  | 
-[Q327333](https://www.wikidata.org/entity/Q327333)   | Government agency  | [office=government](https://wiki.openstreetmap.org/wiki/Tag:office=government)|
-[Q22698](https://www.wikidata.org/entity/Q22698)    | Park | [leisure=park](https://wiki.openstreetmap.org/wiki/Tag:leisure=park) | 
-[Q159313](https://www.wikidata.org/entity/Q159313)   | Urban agglomeration | |
-[Q177634](https://www.wikidata.org/entity/Q177634)   | Community  | |
-[Q5107](https://www.wikidata.org/entity/Q5107)    | Continent | [place=continent](https://wiki.openstreetmap.org/wiki/Tag:place=continent) |
-[Q6256](https://www.wikidata.org/entity/Q6256)     | Country  | [place=country](https://wiki.openstreetmap.org/wiki/Tag:place=country) | 
-[Q75848](https://www.wikidata.org/entity/Q75848)    | Gated community | | 
-[Q3153117](https://www.wikidata.org/entity/Q3153117) | Intercommunality  | |
-[Q82794](https://www.wikidata.org/entity/Q82794)    | Region  | | 
-[Q56061](https://www.wikidata.org/entity/Q56061)    | Administrative division  | [boundary=administrative](https://wiki.openstreetmap.org/wiki/Tag:boundary=administrative)  | 
-[Q665487](https://www.wikidata.org/entity/Q665487)   | Diocese | | 
-[Q4976993](https://www.wikidata.org/entity/Q4976993)  | Parish | [boundary=civil_parish](https://wiki.openstreetmap.org/wiki/Tag:boundary=civil_parish) |
-[Q194203](https://www.wikidata.org/entity/Q194203)   | Arrondissements of France  | |
-[Q91028](https://www.wikidata.org/entity/Q91028)    | Arrondissements of Belgium  | | 
-[Q3623867](https://www.wikidata.org/entity/Q3623867)  | Arrondissements of Benin  | | 
-[Q2311958](https://www.wikidata.org/entity/Q2311958)  | Canton (country subdivision) | [political_division=canton](https://wiki.openstreetmap.org/wiki/FR:Cantons_in_France) |
-[Q643589](https://www.wikidata.org/entity/Q643589)   | Department |  | 
-[Q202216](https://www.wikidata.org/entity/Q202216)   | Overseas department and region  | |
-[Q149621](https://www.wikidata.org/entity/Q149621)   | District  | [place=district](https://wiki.openstreetmap.org/wiki/Tag:place=district) |
-[Q15243209](https://www.wikidata.org/wiki/Q15243209) | Historic district  | |
-[Q5144960](https://www.wikidata.org/entity/Q5144960)  | Microregion  | | 
-[Q15284](https://www.wikidata.org/entity/Q15284)    | Municipality  | |
-[Q515716](https://www.wikidata.org/entity/Q515716)   | Prefecture  | |
-[Q34876](https://www.wikidata.org/entity/Q34876)    | Province  | |
-[Q3191695](https://www.wikidata.org/entity/Q3191695)  | Regency (Indonesia)  | |
-[Q1970725](https://www.wikidata.org/entity/Q1970725)  | Natural region  | |
-[Q486972](https://www.wikidata.org/entity/Q486972)   | Human settlement  | | 
-[Q515](https://www.wikidata.org/entity/Q515)      | City  | [place=city](https://wiki.openstreetmap.org/wiki/Tag:place=city) |
-[Q5119](https://www.wikidata.org/entity/Q5119)     | Capital city | [capital=yes](https://wiki.openstreetmap.org/wiki/Key:capital) |
-[Q4286337](https://www.wikidata.org/entity/Q4286337)  | City district  | | 
-[Q1394476](https://www.wikidata.org/entity/Q1394476)  | Civil township  | | 
-[Q1115575](https://www.wikidata.org/entity/Q1115575)  | Civil parish  | [designation=civil_parish](https://wiki.openstreetmap.org/wiki/Tag:designation=civil_parish) |
-[Q5153984](https://www.wikidata.org/entity/Q5153984)  | Commune-level subdivisions  | |
-[Q123705](https://www.wikidata.org/entity/Q123705)   | Neighbourhood  | [place=neighbourhood](https://wiki.openstreetmap.org/wiki/Tag:place=neighbourhood) |
-[Q1500350](https://www.wikidata.org/entity/Q1500350)  | Townships of China  | |
-[Q17343829](https://www.wikidata.org/entity/Q17343829)           | Unincorporated Community  | |
-[Q3957](https://www.wikidata.org/entity/Q3957)     | Town  | [place=town](https://wiki.openstreetmap.org/wiki/Tag:place=town) | 
-[Q532](https://www.wikidata.org/entity/Q532)      | Village  | [place=village](https://wiki.openstreetmap.org/wiki/Tag:place=village) |
-[Q5084](https://www.wikidata.org/entity/Q5084)     | Hamlet   | [place=hamlet](https://wiki.openstreetmap.org/wiki/Tag:place=hamlet) | 
-[Q7275](https://www.wikidata.org/entity/Q7275)     | State  | | 
-[Q79007](https://www.wikidata.org/entity/Q79007)    | Street  | |
-[Q473972](https://www.wikidata.org/entity/Q473972)   | Protected area  | [boundary=protected_area](https://wiki.openstreetmap.org/wiki/Tag:boundary=protected_area) |
-[Q1377575](https://www.wikidata.org/entity/Q1377575)  | Wildlife refuge  | | 
-[Q1410668](https://www.wikidata.org/entity/Q1410668)  | National Wildlife Refuge  | [protection_title=National Wildlife Refuge](ownership=national), [ownership=national](https://wiki.openstreetmap.org/wiki/Tag:ownership=national)|
-[Q9259](https://www.wikidata.org/entity/Q9259)     | World Heritage Site  | |
-
----
-
-### Future Work
-
-The Wikidata improvements to Nominatim can be further enhanced by:
-
-- continuing to add new Wikidata links to OSM objects
-- increasing the number of place types accounted for in the wikipedia_articles table
-- working to use place types in the wikipedia_article matching process

data/gb_postcode_table.sql

@@ -1,26 +0,0 @@
--- This data contains Ordnance Survey data © Crown copyright and database right 2010. 
--- Code-Point Open contains Royal Mail data © Royal Mail copyright and database right 2010.
--- OS data may be used under the terms of the OS OpenData licence:
--- http://www.ordnancesurvey.co.uk/oswebsite/opendata/licence/docs/licence.pdf
-
-SET statement_timeout = 0;
-SET client_encoding = 'UTF8';
-SET standard_conforming_strings = off;
-SET check_function_bodies = false;
-SET client_min_messages = warning;
-SET escape_string_warning = off;
-
-SET search_path = public, pg_catalog;
-
-SET default_tablespace = '';
-
-SET default_with_oids = false;
-
-CREATE TABLE gb_postcode (
-    id integer,
-    postcode character varying(9),
-    geometry geometry,
-    CONSTRAINT enforce_dims_geometry CHECK ((st_ndims(geometry) = 2)),
-    CONSTRAINT enforce_srid_geometry CHECK ((st_srid(geometry) = 4326))
-);
-

data/us_postcode_table.sql

@@ -1,16 +0,0 @@
-SET statement_timeout = 0;
-SET client_encoding = 'UTF8';
-SET check_function_bodies = false;
-SET client_min_messages = warning;
-
-SET search_path = public, pg_catalog;
-
-SET default_tablespace = '';
-
-SET default_with_oids = false;
-
-CREATE TABLE us_postcode (
-    postcode text,
-    x double precision,
-    y double precision
-);

data/words.sql

@@ -29787,7 +29787,7 @@ st	5557484
 
 -- prefill word table
 
-select count(make_keywords(v)) from (select distinct svals(name) as v from place) as w where v is not null;
+select count(precompute_words(v)) from (select distinct svals(name) as v from place) as w where v is not null;
 select count(getorcreate_housenumber_id(make_standard_name(v))) from (select distinct address->'housenumber' as v from place where address ? 'housenumber') as w;
 
 -- copy the word frequencies

docs/CMakeLists.txt

@@ -5,7 +5,6 @@
 
 configure_file(mkdocs.yml ../mkdocs.yml)
 file(MAKE_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/appendix)
-file(MAKE_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/data-sources)
 
 set (DOC_SOURCES
      admin
@@ -14,7 +13,6 @@ set (DOC_SOURCES
      index.md
      extra.css
      styles.css
-     data-sources/overview.md
     )
 
 foreach (src ${DOC_SOURCES})
@@ -23,22 +21,6 @@ foreach (src ${DOC_SOURCES})
     )
 endforeach()
 
-execute_process(
-   COMMAND ${CMAKE_COMMAND} -E create_symlink ${PROJECT_SOURCE_DIR}/data-sources/us-tiger/README.md ${CMAKE_CURRENT_BINARY_DIR}/data-sources/US-Tiger.md
-)
-execute_process(
-   COMMAND ${CMAKE_COMMAND} -E create_symlink ${PROJECT_SOURCE_DIR}/data-sources/gb-postcodes/README.md ${CMAKE_CURRENT_BINARY_DIR}/data-sources/GB-Postcodes.md
-)
-execute_process(
-   COMMAND ${CMAKE_COMMAND} -E create_symlink ${PROJECT_SOURCE_DIR}/data-sources/country-grid/README.md ${CMAKE_CURRENT_BINARY_DIR}/data-sources/Country-Grid.md
-)
-execute_process(
-   COMMAND ${CMAKE_COMMAND} -E create_symlink ${PROJECT_SOURCE_DIR}/data-sources/country-grid/mexico.quad.png ${CMAKE_CURRENT_BINARY_DIR}/data-sources/mexico.quad.png
-)
-execute_process(
-   COMMAND ${CMAKE_COMMAND} -E create_symlink ${PROJECT_SOURCE_DIR}/data-sources/wikipedia-wikidata/README.md  ${CMAKE_CURRENT_BINARY_DIR}/data-sources/Wikipedia-Wikidata.md
-)
-
 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

docs/admin/Advanced-Installations.md

@@ -47,14 +47,16 @@ The file `import_multiple_regions.sh` needs to be edited as per your requirement
     
         BASEURL="https://download.geofabrik.de"
         DOWNCOUNTRYPOSTFIX="-latest.osm.pbf"
- 
-!!! 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 2>&1`.
 
 ### 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.
+
 Run the following command from your Nominatim directory after configuring the file.
 
     bash ./utils/import_multiple_regions.sh
@@ -63,7 +65,7 @@ Run the following command from your Nominatim directory after configuring the fi
         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
+### 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.   
@@ -103,7 +105,69 @@ Run the following command from your Nominatim directory after configuring the fi
 
 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.
 
-## Verification and further setup
+## Importing Nominatim to an external PostgreSQL database
 
-Instructions for import verification and other details like importing Wikidata can be found in [import and update page](Import-and-Update.md)
+You can install Nominatim using a database that runs on a different server when
+you have physical access to the file system on the other server. Nominatim
+uses a custom normalization library that needs to be made accessible to the
+PostgreSQL server. This section explains how to set up the normalization
+library.
 
+### Option 1: Compiling the library on the database server
+
+The most sure way to get a working library is to compile it on the database
+server. From the prerequisites you need at least cmake, gcc and the
+PostgreSQL server package.
+
+Clone or unpack the Nominatim source code, enter the source directory and
+create and enter a build directory.
+
+```sh
+cd Nominatim
+mkdir build
+cd build
+```
+
+Now configure cmake to only build the PostgreSQL module and build it:
+
+```
+cmake -DBUILD_IMPORTER=off -DBUILD_API=off -DBUILD_TESTS=off -DBUILD_DOCS=off -DBUILD_OSM2PGSQL=off ..
+make
+```
+
+When done, you find the normalization library in `build/module/nominatim.so`.
+Copy it to a place where it is readable and executable by the PostgreSQL server
+process.
+
+### Option 2: Compiling the library on the import machine
+
+You can also compile the normalization library on the machine from where you
+run the import.
+
+!!! important
+    You can only do this when the database server and the import machine have
+    the same architecture and run the same version of Linux. Otherwise there is
+    no guarantee that the compiled library is compatible with the PostgreSQL
+    server running on the database server.
+
+Make sure that the PostgreSQL server package is installed on the machine
+**with the same version as on the database server**. You do not need to install
+the PostgreSQL server itself.
+
+Download and compile Nominatim as per standard instructions. Once done, you find
+the normalization library in `build/module/nominatim.so`. Copy the file to
+the database server at a location where it is readable and executable by the
+PostgreSQL server process.
+
+### Running the import
+
+On the client side you now need to configure the import to point to the
+correct location of the library **on the database server**. Add the following
+line to your your `.env` file:
+
+```php
+NOMINATIM_DATABASE_MODULE_PATH="<directory on the database server where nominatim.so resides>"
+```
+
+Now change the `NOMINATIM_DATABASE_DSN` to point to your remote server and continue
+to follow the [standard instructions for importing](/admin/Import).

docs/admin/Customization.md

@@ -0,0 +1,101 @@
+# 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

@@ -0,0 +1,142 @@
+# Deploying Nominatim
+
+The Nominatim API is implemented as a PHP application. The `website/` directory
+in the project directory contains the configured website. You can serve this
+in a production environment with any web server that is capable to run
+PHP scripts.
+
+This section gives a quick overview on how to configure Apache and Nginx to
+serve Nominatim. It is not meant as a full system administration guide on how
+to run a web service. Please refer to the documentation of
+[Apache](http://httpd.apache.org/docs/current/) and
+[Nginx](https://nginx.org/en/docs/)
+for background information on configuring the services.
+
+!!! Note
+    Throughout this page, we assume that your Nominatim project directory is
+    located in `/srv/nominatim-project` and that you have installed Nominatim
+    using the default installation prefix `/usr/local`. If you have put it
+    somewhere else, you need to adjust the commands and configuration
+    accordingly.
+
+    We further assume that your web server runs as user `www-data`. Older
+    versions of CentOS may still use the user name `apache`. You also need
+    to adapt the instructions in this case.
+
+## Making the website directory accessible
+
+You need to make sure that the `website` directory is accessible for the
+web server user. You can check that the permissions are correct by accessing
+on of the php files as the web server user:
+
+``` sh
+sudo -u www-data head -n 1 /srv/nominatim-project/website/search.php
+```
+
+If this shows a permission error, then you need to adapt the permissions of
+each directory in the path so that it is executable for `www-data`.
+
+If you have SELinux enabled, further adjustments may be necessary to give the
+web server access. At a minimum the following SELinux labelling should be done
+for Nominatim:
+
+``` sh
+sudo semanage fcontext -a -t httpd_sys_content_t "/usr/local/nominatim/lib/lib-php(/.*)?"
+sudo semanage fcontext -a -t httpd_sys_content_t "/srv/nominatim-project/website(/.*)?"
+sudo semanage fcontext -a -t lib_t "/srv/nominatim-project/module/nominatim.so"
+sudo restorecon -R -v /usr/local/lib/nominatim
+sudo restorecon -R -v /srv/nominatim-project
+```
+
+## Nominatim with Apache
+
+### Installing the required packages
+
+With Apache you can use the PHP module to run Nominatim.
+
+Under Ubuntu/Debian install them with:
+
+``` sh
+sudo apt install apache2 libapache2-mod-php
+```
+
+### Configuring Apache
+
+Make sure your Apache configuration contains the required permissions for the
+directory and create an alias:
+
+``` apache
+<Directory "/srv/nominatim-project/website">
+  Options FollowSymLinks MultiViews
+  AddType text/html   .php
+  DirectoryIndex search.php
+  Require all granted
+</Directory>
+Alias /nominatim /srv/nominatim-project/website
+```
+
+After making changes in the apache config you need to restart apache.
+The website should now be available on `http://localhost/nominatim`.
+
+## Nominatim with Nginx
+
+### Installing the required packages
+
+Nginx has no built-in PHP interpreter. You need to use php-fpm as a deamon for
+serving PHP cgi.
+
+On Ubuntu/Debian install nginx and php-fpm with:
+
+``` sh
+sudo apt install nginx php-fpm
+```
+
+### Configure php-fpm and Nginx
+
+By default php-fpm listens on a network socket. If you want it to listen to a
+Unix socket instead, change the pool configuration
+(`/etc/php/<php version>/fpm/pool.d/www.conf`) as follows:
+
+``` ini
+; Replace the tcp listener and add the unix socket
+listen = /var/run/php-fpm.sock
+
+; Ensure that the daemon runs as the correct user
+listen.owner = www-data
+listen.group = www-data
+listen.mode = 0666
+```
+
+Tell nginx that php files are special and to fastcgi_pass to the php-fpm
+unix socket by adding the location definition to the default configuration.
+
+``` nginx
+root /srv/nominatim-project/website;
+index search.php;
+location / {
+    try_files $uri $uri/ @php;
+}
+
+location @php {
+    fastcgi_param SCRIPT_FILENAME "$document_root$uri.php";
+    fastcgi_param PATH_TRANSLATED "$document_root$uri.php";
+    fastcgi_param QUERY_STRING    $args;
+    fastcgi_pass unix:/var/run/php-fpm.sock;
+    fastcgi_index index.php;
+    include fastcgi_params;
+}
+
+location ~ [^/]\.php(/|$) {
+    fastcgi_split_path_info ^(.+?\.php)(/.*)$;
+    if (!-f $document_root$fastcgi_script_name) {
+        return 404;
+    }
+    fastcgi_pass unix:/var/run/php-fpm.sock;
+    fastcgi_index search.php;
+    include fastcgi.conf;
+}
+```
+
+Restart the nginx and php-fpm services and the website should now be available
+at `http://localhost/`.
+

docs/admin/Faq.md

@@ -16,12 +16,27 @@ was killed. If it looks like this:
 then you can resume with the following command:
 
 ```sh
-./utils/setup.php --index --create-search-indices --create-country-names
+nominatim import --continue indexing
 ```
 
 If the reported rank is 26 or higher, you can also safely add `--index-noanalyse`.
 
 
+### PostgreSQL crashed "invalid page in block"
+
+Usually serious problem, can be a hardware issue, not all data written to disc
+for example. Check PostgreSQL log file and search PostgreSQL issues/mailing
+list for hints.
+
+If it happened during index creation you can try rerunning the step with
+
+```sh
+nominatim import --continue indexing
+```
+
+Otherwise it's best to start the full setup from the beginning.
+
+
 ### PHP "open_basedir restriction in effect" warnings
 
     PHP Warning:  file_get_contents(): open_basedir restriction in effect.
@@ -38,7 +53,7 @@ by adding ";" at the beginning of the line. Don't forget to enable this setting
 again once you are done with the PHP command line operations.
 
 
-### PHP timzeone warnings
+### PHP timezeone warnings
 
 The Apache log may contain lots of PHP warnings like this:
     `PHP Warning:  date_default_timezone_set() function.`
@@ -78,7 +93,7 @@ on a non-managed machine.
 
 ### I see the error: "function transliteration(text) does not exist"
 
-Reinstall the nominatim functions with `setup.php --create--functions`
+Reinstall the nominatim functions with `nominatim refresh --functions`
 and check for any errors, e.g. a missing `nominatim.so` file.
 
 ### I see the error: "ERROR: mmap (remap) failed"
@@ -98,7 +113,8 @@ Double-check clang is installed. Instead of `make` try running `make CLANG=true`
 
 ### nominatim UPDATE failed: ERROR: buffer 179261 is not owned by resource owner Portal
 
-Several users [reported this](https://github.com/openstreetmap/Nominatim/issues/1168) during the initial import of the database. It's
+Several users [reported this](https://github.com/openstreetmap/Nominatim/issues/1168)
+during the initial import of the database. It's
 something PostgreSQL internal Nominatim doesn't control. And PostgreSQL forums
 suggest it's threading related but definitely some kind of crash of a process.
 Users reported either rebooting the server, different hardware or just trying
@@ -156,7 +172,8 @@ Example error message
 
 The PostgreSQL database, i.e. user `postgres`, needs to have access to that file.
 
-The permission need to be read & executable by everybody, e.g.
+The permission need to be read & executable by everybody, but not writeable
+by everybody, e.g.
 
 ```
    -rwxr-xr-x 1 nominatim nominatim 297984 build/module/nominatim.so
@@ -167,6 +184,16 @@ 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
+
+```
+   cd build
+   rm -r module/
+   cmake $main_Nominatim_path && make
+```
+
 ### Setup.php fails with "DB Error: extension not found"
 
 Make sure you have the PostgreSQL extensions "hstore" and "postgis" installed.
@@ -176,7 +203,7 @@ See the installation instructions for a full list of required packages.
 ### I forgot to delete the flatnodes file before starting an import.
 
 That's fine. For each import the flatnodes file get overwritten.
-See [https://help.openstreetmap.org/questions/52419/nominatim-flatnode-storage]()
+See [https://help.openstreetmap.org/questions/52419/nominatim-flatnode-storage](https://help.openstreetmap.org/questions/52419/nominatim-flatnode-storage)
 for more information.
 
 
@@ -185,11 +212,3 @@ for more information.
 ### Can I import negative OSM ids into Nominatim?
 
 See [this question of Stackoverflow](https://help.openstreetmap.org/questions/64662/nominatim-flatnode-with-negative-id).
-
-### Missing XML or text declaration
-
-The website might show: `XML Parsing Error: XML or text declaration not at start of entity Location.`
-
-Make sure there are no spaces at the beginning of your `settings/local.php` file.
-
-

docs/admin/Import-and-Update.md

@@ -1,322 +0,0 @@
-# Importing and Updating the Database
-
-The following instructions explain how to create a Nominatim database
-from an OSM planet file and how to keep the database up to date. It
-is assumed that you have already successfully installed the Nominatim
-software itself, if not return to the [installation page](Installation.md).
-
-## Configuration setup in settings/local.php
-
-The Nominatim server can be customized via the file `settings/local.php`
-in the build directory. Note that this is a PHP file, so it must always
-start like this:
-
-    <?php
-
-without any leading spaces.
-
-There are lots of configuration settings you can tweak. Have a look
-at `settings/default.php` for a full list. Most should have a sensible default.
-
-#### Flatnode files
-
-If you plan to import a large dataset (e.g. Europe, North America, planet),
-you should also enable flatnode storage of node locations. With this
-setting enabled, node coordinates are stored in a simple file instead
-of the database. This will save you import time and disk storage.
-Add to your `settings/local.php`:
-
-    @define('CONST_Osm2pgsql_Flatnode_File', '/path/to/flatnode.file');
-
-Replace the second part with a suitable path on your system and make sure
-the directory exists. There should be at least 64GB of free space.
-
-## Downloading additional data
-
-### Wikipedia/Wikidata rankings
-
-Wikipedia can be used as an optional auxiliary data source to help indicate
-the importance of OSM features. Nominatim will work without this information
-but it will improve the quality of the results if this is installed.
-This data is available as a binary download:
-
-    cd $NOMINATIM_SOURCE_DIR/data
-    wget https://www.nominatim.org/data/wikimedia-importance.sql.gz
-
-The file is about 400MB and adds around 4GB to Nominatim database.
-
-!!! tip
-    If you forgot to download the wikipedia rankings, you can also add
-    importances after the import. Download the files, then run
-    `./utils/setup.php --import-wikipedia-articles`
-    and `./utils/update.php --recompute-importance`.
-
-### Great Britain, USA postcodes
-
-Nominatim can use postcodes from an external source to improve searches that
-involve a GB or US postcode. This data can be optionally downloaded:
-
-    cd $NOMINATIM_SOURCE_DIR/data
-    wget https://www.nominatim.org/data/gb_postcode_data.sql.gz
-    wget https://www.nominatim.org/data/us_postcode_data.sql.gz
-
-## Choosing the Data to Import
-
-In its default setup Nominatim is configured to import the full OSM data
-set for the entire planet. Such a setup requires a powerful machine with
-at least 64GB of RAM and around 800GB of SSD hard disks. Depending on your
-use case there are various ways to reduce the amount of data imported. This
-section discusses these methods. They can also be combined.
-
-### Using an extract
-
-If you only need geocoding for a smaller region, then precomputed 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
-below. 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
-boundaries. As a result some parts of the boundary may be missing which means
-that Nominatim cannot compute the areas for some administrative areas.
-
-### Dropping Data Required for Dynamic Updates
-
-About half of the data in Nominatim's database is not really used for serving
-the API. It is only there to allow the data to be updated from the latest
-changes from OSM. For many uses these dynamic updates are not really required.
-If you don't plan to apply updates, the dynamic part of the database can be
-safely dropped using the following command:
-
-```
-./utils/setup.php --drop
-```
-
-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.
-
-### 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
-without search indexes. Add `--reverse-only` to your setup command above.
-
-This saves about 5% of disk space.
-
-### Filtering Imported Data
-
-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**
-  Only import administrative boundaries and places.
-* **settings/import-street.style**
-  Like the admin style but also adds streets.
-* **settings/import-address.style**
-  Import all data necessary to compute addresses down to house number level.
-* **settings/import-full.style**
-  Default style that also includes points of interest.
-* **settings/import-extratags.style**
-  Like the full style but also adds most of the OSM tags into the extratags
-  column.
-
-The style can be changed with the configuration `CONST_Import_Style`.
-
-To give you an idea of the impact of using the different styles, the table
-below gives rough estimates of the final database size after import of a
-2018 planet and after using the `--drop` option. It also shows the time
-needed for the import on a machine with 64GB RAM, 4 CPUS and SSDs. Note that
-the given sizes are just an estimate meant for comparison of style requirements.
-Your planet import is likely to be larger as the OSM data grows with time.
-
-style     | Import time  |  DB size   |  after drop
-----------|--------------|------------|------------
-admin     |    5h        |  190 GB    |   20 GB
-street    |   42h        |  400 GB    |  180 GB
-address   |   59h        |  500 GB    |  260 GB
-full      |   80h        |  575 GB    |  300 GB
-extratags |   80h        |  585 GB    |  310 GB
-
-You can also customize the styles further. For a description of the
-style format see [the development section](../develop/Import.md).
-
-## Initial import of the data
-
-!!! danger "Important"
-    First try the import with a small extract, for example from
-    [Geofabrik](https://download.geofabrik.de).
-
-Download the data to import and load the data with the following command
-from the build directory:
-
-```sh
-./utils/setup.php --osm-file <data file> --all 2>&1 | tee setup.log
-```
-
-***Note for full planet imports:*** Even on a perfectly configured machine
-the import of a full planet takes at least 2 days. Once you see messages
-with `Rank .. ETA` appear, the indexing process has started. This part takes
-the most time. There are 30 ranks to process. Rank 26 and 30 are the most complex.
-They take each about a third of the total import time. If you have not reached
-rank 26 after two days of import, it is worth revisiting your system
-configuration as it may not be optimal for the import.
-
-### Notes on memory usage
-
-In the first step of the import Nominatim uses osm2pgsql 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)
-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
-of this cache can be configured with the parameter `--osm2pgsql-cache`.
-
-When importing with a flatnode file, it is best to disable the node cache
-completely and leave the memory for the flatnode file. Nominatim will do this
-by default, so you do not need to configure anything in this case.
-
-For imports without a flatnode file, set `--osm2pgsql-cache` approximately to
-the size of the OSM pbf file (in MB) you are importing. Make sure you leave
-enough RAM for PostgreSQL and osm2pgsql as mentioned above. If the system starts
-swapping or you are getting out-of-memory errors, reduce the cache size or
-even consider using a flatnode file.
-
-### Verify import finished
-
-Run this script to verify all required tables and indices got created successfully.
-
-```sh
-./utils/check_import_finished.php
-```
-
-
-## 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
-./utils/update.php --recompute-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.
-
-If you want to be able to search for places by their type through
-[special key phrases](https://wiki.openstreetmap.org/wiki/Nominatim/Special_Phrases)
-you also need to enable these key phrases like this:
-
-    ./utils/specialphrases.php --wiki-import > specialphrases.sql
-    psql -d nominatim -f specialphrases.sql
-
-Note that this command downloads the phrases from the wiki link above. You
-need internet access for the step.
-
-
-## Installing Tiger housenumber data for the US
-
-Nominatim is able to use the official [TIGER](https://www.census.gov/geographies/mapping-files/time-series/geo/tiger-line-file.html)
-address set to complement the OSM house number data in the US. You can add
-TIGER data to your own Nominatim instance by following these steps. The
-entire US adds about 10GB to your database.
-
-  1. Get preprocessed TIGER 2019 data and unpack it into the
-     data directory in your Nominatim sources:
-
-        cd Nominatim/data
-        wget https://nominatim.org/data/tiger2019-nominatim-preprocessed.tar.gz
-        tar xf tiger2019-nominatim-preprocessed.tar.gz
-
-    `data-source/us-tiger/README.md` explains how the data got preprocessed.
-
-  2. Import the data into your Nominatim database:
-
-        ./utils/setup.php --import-tiger-data
-
-  3. Enable use of the Tiger data in your `settings/local.php` by adding:
-
-         @define('CONST_Use_US_Tiger_Data', true);
-
-  4. Apply the new settings:
-
-```sh
-    ./utils/setup.php --create-functions --enable-diff-updates --create-partition-functions
-```
-
-
-## Updates
-
-There are many different ways to update your Nominatim database.
-The following section describes how to keep it up-to-date with Pyosmium.
-For a list of other methods see the output of `./utils/update.php --help`.
-
-!!! warning
-    If you have configured a flatnode file for the import, then you
-    need to keep this flatnode file around for updates as well.
-
-#### Installing the newest version of Pyosmium
-
-It is recommended to install Pyosmium via pip. Make sure to use python3.
-Run (as the same user who will later run the updates):
-
-```sh
-pip3 install --user osmium
-```
-
-Nominatim needs a tool called `pyosmium-get-updates` which comes with
-Pyosmium. You need to tell Nominatim where to find it. Add the
-following line to your `settings/local.php`:
-
-    @define('CONST_Pyosmium_Binary', '/home/user/.local/bin/pyosmium-get-changes');
-
-The path above is fine if you used the `--user` parameter with pip.
-Replace `user` with your user name.
-
-#### Setting up the update process
-
-Next the update needs to be initialised. By default Nominatim is configured
-to update using the global minutely diffs.
-
-If you want a different update source you will need to add some settings
-to `settings/local.php`. For example, to use the daily country extracts
-diffs for Ireland from Geofabrik add the following:
-
-    // base URL of the replication service
-    @define('CONST_Replication_Url', 'https://download.geofabrik.de/europe/ireland-and-northern-ireland-updates');
-    // How often upstream publishes diffs
-    @define('CONST_Replication_Update_Interval', '86400');
-    // How long to sleep if no update found yet
-    @define('CONST_Replication_Recheck_Interval', '900');
-
-To set up the update process now run the following command:
-
-    ./utils/update.php --init-updates
-
-It outputs the date where updates will start. Recheck that this date is
-what you expect.
-
-The `--init-updates` command needs to be rerun whenever the replication service
-is changed.
-
-#### Updating Nominatim
-
-The following command will keep your database constantly up to date:
-
-    ./utils/update.php --import-osmosis-all
-
-(Note that even though the old name "import-osmosis-all" has been kept for
-compatibility reasons, Osmosis is not required to run this - it uses pyosmium
-behind the scenes.)
-
-If you have imported multiple country extracts and want to keep them
-up-to-date, [Advanced installations section](Advanced-Installations.md) contains instructions 
-to set up and update multiple country extracts.

docs/admin/Import.md

@@ -0,0 +1,291 @@
+# Importing the Database
+
+The following instructions explain how to create a Nominatim database
+from an OSM planet file. It is assumed that you have already successfully
+installed the Nominatim software itself and the `nominatim` tool can be found
+in your `PATH`. If this is not the case, return to the
+[installation page](Installation.md).
+
+## Creating the project directory
+
+Before you start the import, you should create a project directory for your
+new database installation. This directory receives all data that is related
+to a single Nominatim setup: configuration, extra data, etc. Create a project
+directory apart from the Nominatim software and change into the directory:
+
+```
+mkdir ~/nominatim-planet
+cd ~/nominatim-planet
+```
+
+In the following, we refer to the project directory as `$PROJECT_DIR`. To be
+able to copy&paste instructions, you can export the appropriate variable:
+
+```
+export PROJECT_DIR=~/nominatim-planet
+```
+
+The Nominatim tool assumes per default that the current working directory is
+the project directory but you may explicitly state a different directory using
+the `--project-dir` parameter. The following instructions assume that you run
+all commands from the project directory.
+
+!!! tip "Migration Tip"
+
+    Nominatim used to be run directly from the build directory until version 3.6.
+    Essentially, the build directory functioned as the project directory
+    for the database installation. This setup still works and can be useful for
+    development purposes. It is not recommended anymore for production setups.
+    Create a project directory that is separate from the Nominatim software.
+
+### Configuration setup in `.env`
+
+The Nominatim server can be customized via an `.env` configuration file in the 
+project directory. This is a file in [dotenv](https://github.com/theskumar/python-dotenv)
+format which looks the same as variable settings in a standard shell environment.
+You can also set the same configuration via environment variables. All
+settings have a `NOMINATIM_` prefix to avoid conflicts with other environment
+variables.
+
+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.
+
+#### Flatnode files
+
+If you plan to import a large dataset (e.g. Europe, North America, planet),
+you should also enable flatnode storage of node locations. With this
+setting enabled, node coordinates are stored in a simple file instead
+of the database. This will save you import time and disk storage.
+Add to your `.env`:
+
+    NOMINATIM_FLATNODE_FILE="/path/to/flatnode.file"
+
+Replace the second part with a suitable path on your system and make sure
+the directory exists. There should be at least 75GB of free space.
+
+## Downloading additional data
+
+### Wikipedia/Wikidata rankings
+
+Wikipedia can be used as an optional auxiliary data source to help indicate
+the importance of OSM features. Nominatim will work without this information
+but it will improve the quality of the results if this is installed.
+This data is available as a binary download. Put it into your project directory:
+
+    cd $PROJECT_DIR
+    wget https://www.nominatim.org/data/wikimedia-importance.sql.gz
+
+The file is about 400MB and adds around 4GB to the Nominatim database.
+
+!!! tip
+    If you forgot to download the wikipedia rankings, you can also add
+    importances after the import. Download the files, then run
+    `nominatim refresh --wiki-data --importance`. Updating importances for
+    a planet can take a couple of hours.
+
+### External postcodes
+
+Nominatim can use postcodes from an external source to improve searching with
+postcodes. We provide precomputed postcodes sets for the US (using TIGER data)
+and the UK (using the [CodePoint OpenData set](https://osdatahub.os.uk/downloads/open/CodePointOpen).
+This data can be optionally downloaded into the project directory:
+
+    cd $PROJECT_DIR
+    wget https://www.nominatim.org/data/gb_postcodes.csv.gz
+    wget https://www.nominatim.org/data/us_postcodes.csv.gz
+
+You can also add your own custom postcode sources, see
+[Customization of postcodes](Customization.md#external-postcode-data).
+
+## Choosing the data to import
+
+In its default setup Nominatim is configured to import the full OSM data
+set for the entire planet. Such a setup requires a powerful machine with
+at least 64GB of RAM and around 900GB of SSD hard disks. Depending on your
+use case there are various ways to reduce the amount of data imported. This
+section discusses these methods. They can also be combined.
+
+### Using an extract
+
+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
+[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
+boundaries. As a result some parts of the boundary may be missing which means
+that Nominatim cannot compute the areas for some administrative areas.
+
+### Dropping Data Required for Dynamic Updates
+
+About half of the data in Nominatim's database is not really used for serving
+the API. It is only there to allow the data to be updated from the latest
+changes from OSM. For many uses these dynamic updates are not really required.
+If you don't plan to apply updates, you can run the import with the
+`--no-updates` parameter. This will drop the dynamic part of the database as
+soon as it is not required anymore.
+
+You can also drop the dynamic part later using the following command:
+
+```
+nominatim freeze
+```
+
+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.
+
+### 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
+without search indexes. Add `--reverse-only` to your setup command above.
+
+This saves about 5% of disk space.
+
+### Filtering Imported Data
+
+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**
+  Only import administrative boundaries and places.
+* **settings/import-street.style**
+  Like the admin style but also adds streets.
+* **settings/import-address.style**
+  Import all data necessary to compute addresses down to house number level.
+* **settings/import-full.style**
+  Default style that also includes points of interest.
+* **settings/import-extratags.style**
+  Like the full style but also adds most of the OSM tags into the extratags
+  column.
+
+The style can be changed with the configuration `NOMINATIM_IMPORT_STYLE`.
+
+To give you an idea of the impact of using the different styles, the table
+below gives rough estimates of the final database size after import of a
+2020 planet and after using the `--drop` option. It also shows the time
+needed for the import on a machine with 64GB RAM, 4 CPUS and NVME disks.
+Note that the given sizes are just an estimate meant for comparison of
+style requirements. Your planet import is likely to be larger as the
+OSM data grows with time.
+
+style     | Import time  |  DB size   |  after drop
+----------|--------------|------------|------------
+admin     |    4h        |  215 GB    |   20 GB
+street    |   22h        |  440 GB    |  185 GB
+address   |   36h        |  545 GB    |  260 GB
+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.
+
+## Initial import of the data
+
+!!! danger "Important"
+    First try the import with a small extract, for example from
+    [Geofabrik](https://download.geofabrik.de).
+
+Download the data to import. Then issue the following command
+from the **project directory** to start the import:
+
+```sh
+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).
+
+### Notes on full planet imports
+
+Even on a perfectly configured machine
+the import of a full planet takes around 2 days. Once you see messages
+with `Rank .. ETA` appear, the indexing process has started. This part takes
+the most time. There are 30 ranks to process. Rank 26 and 30 are the most complex.
+They take each about a third of the total import time. If you have not reached
+rank 26 after two days of import, it is worth revisiting your system
+configuration as it may not be optimal for the import.
+
+### Notes on memory usage
+
+In the first step of the import Nominatim uses [osm2pgsql](https://osm2pgsql.org)
+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)
+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
+of this cache can be configured with the parameter `--osm2pgsql-cache`.
+
+When importing with a flatnode file, it is best to disable the node cache
+completely and leave the memory for the flatnode file. Nominatim will do this
+by default, so you do not need to configure anything in this case.
+
+For imports without a flatnode file, set `--osm2pgsql-cache` approximately to
+the size of the OSM pbf file you are importing. The size needs to be given in
+MB. Make sure you leave enough RAM for PostgreSQL and osm2pgsql as mentioned
+above. If the system starts swapping or you are getting out-of-memory errors,
+reduce the cache size or even consider using a flatnode file.
+
+
+### Testing the installation
+
+Run this script to verify all required tables and indices got created successfully.
+
+```sh
+nominatim admin --check-database
+```
+
+Now you can try out your installation by running:
+
+```sh
+nominatim serve
+```
+
+This runs a small test server normally used for development. You can use it
+to verify that your installation is working. Go to
+`http://localhost:8088/status.php` and you should see the message `OK`.
+You can also run a search query, e.g. `http://localhost:8088/search.php?q=Berlin`.
+
+Note that search query is not supported for reverse-only imports. You can run a
+reverse query, e.g. `http://localhost:8088/reverse.php?lat=27.1750090510034&lon=78.04209025`.
+
+To run Nominatim via webservers like Apache or nginx, please read the
+[Deployment chapter](Deployment.md).
+
+## 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.
+
+If you want to be able to search for places by their type through
+[special key phrases](https://wiki.openstreetmap.org/wiki/Nominatim/Special_Phrases)
+you also need to import these key phrases like this:
+
+```sh
+nominatim special-phrases --import-from-wiki
+```
+
+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).

docs/admin/Installation.md

@@ -17,6 +17,7 @@ and can't offer support.
 
   * [Docker](https://github.com/mediagis/nominatim-docker)
   * [Docker on Kubernetes](https://github.com/peter-evans/nominatim-k8s)
+  * [Kubernetes with Helm](https://github.com/robjuz/helm-charts/blob/master/charts/nominatim/README.md)
   * [Ansible](https://github.com/synthesio/infra-ansible-nominatim)
 
 ## Prerequisites
@@ -30,30 +31,34 @@ For compiling:
   * [proj](https://proj.org/)
   * [bzip2](http://www.bzip.org/)
   * [zlib](https://www.zlib.net/)
+  * [ICU](http://site.icu-project.org/)
   * [Boost libraries](https://www.boost.org/), including system and filesystem
   * PostgreSQL client libraries
   * a recent C++ compiler (gcc 5+ or Clang 3.8+)
 
 For running Nominatim:
 
-  * [PostgreSQL](https://www.postgresql.org) (9.3+)
-  * [PostGIS](https://postgis.org) (2.2+)
-  * [Python 3](https://www.python.org/)
-  * [Psycopg2](https://initd.org/psycopg)
+  * [PostgreSQL](https://www.postgresql.org) (9.5+ will work, 11+ strongly recommended)
+  * [PostGIS](https://postgis.net) (2.2+)
+  * [Python 3](https://www.python.org/) (3.6+)
+  * [Psycopg2](https://www.psycopg.org) (2.7+)
+  * [Python Dotenv](https://github.com/theskumar/python-dotenv)
+  * [psutil](https://github.com/giampaolo/psutil)
+  * [Jinja2](https://palletsprojects.com/p/jinja/)
+  * [PyICU](https://pypi.org/project/PyICU/)
+  * [PyYaml](https://pyyaml.org/) (5.1+)
+  * [datrie](https://github.com/pytries/datrie)
   * [PHP](https://php.net) (7.0 or later)
   * PHP-pgsql
   * PHP-intl (bundled with PHP)
-  * a webserver (apache or nginx are recommended)
+  * PHP-cgi (for running queries from the command line)
 
 For running continuous updates:
 
-  * [pyosmium](https://osmcode.org/pyosmium/) (with Python 3)
+  * [pyosmium](https://osmcode.org/pyosmium/)
 
-For running tests:
-
-  * [behave](http://pythonhosted.org/behave/)
-  * [nose](https://nose.readthedocs.io)
-  * [phpunit](https://phpunit.de) >= 7.3
+For dependencies for running tests and building documentation, see
+the [Development section](../develop/Development-Environment.md).
 
 ### Hardware
 
@@ -61,16 +66,14 @@ 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
 out of memory problems if you have less than 64GB RAM.
 
-For a full planet install you will need at least 800GB of hard disk space
-(take into account that the OSM database is growing fast). SSD disks
-will help considerably to speed up import and queries.
+For a full planet install you will need at least 900GB of hard disk space.
+Take into account that the OSM database is growing fast.
+Fast disks are essential. Using NVME disks is recommended.
 
 Even on a well configured machine the import of a full planet takes
-at least 2 days. Without SSDs 7-8 days are more realistic.
+around 2 days. On traditional spinning disks, 7-8 days are more realistic.
 
-## Setup of the server
-
-### PostgreSQL tuning
+## Tuning the PostgreSQL database
 
 You might want to tune your PostgreSQL installation so that the later steps
 make best use of your hardware. You should tune the following parameters in
@@ -110,82 +113,54 @@ Don't forget to reenable them after the initial import or you risk database
 corruption.
 
 
-### Webserver setup
+## Downloading and building Nominatim
 
-The `website/` directory in the build directory contains the configured
-website. Include the directory into your webbrowser to serve php files
-from there.
+### Downloading the latest release
 
-#### Configure for use with Apache
+You can download the [latest release from nominatim.org](https://nominatim.org/downloads/).
+The release contains all necessary files. Just unpack it.
 
-Make sure your Apache configuration contains the required permissions for the
-directory and create an alias:
+### Downloading the latest development version
 
-``` apache
-<Directory "/srv/nominatim/build/website">
-  Options FollowSymLinks MultiViews
-  AddType text/html   .php
-  DirectoryIndex search.php
-  Require all granted
-</Directory>
-Alias /nominatim /srv/nominatim/build/website
+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
 ```
 
-`/srv/nominatim/build` should be replaced with the location of your
-build directory.
+The development version does not include the country grid. Download it separately:
 
-After making changes in the apache config you need to restart apache.
-The website should now be available on http://localhost/nominatim.
-
-#### Configure for use with Nginx
-
-Use php-fpm as a deamon for serving PHP cgi. Install php-fpm together with nginx.
-
-By default php listens on a network socket. If you want it to listen to a
-Unix socket instead, change the pool configuration (`pool.d/www.conf`) as
-follows:
-
-    ; Comment out the tcp listener and add the unix socket
-    ;listen = 127.0.0.1:9000
-    listen = /var/run/php5-fpm.sock
-
-    ; Ensure that the daemon runs as the correct user
-    listen.owner = www-data
-    listen.group = www-data
-    listen.mode = 0666
-
-Tell nginx that php files are special and to fastcgi_pass to the php-fpm
-unix socket by adding the location definition to the default configuration.
-
-``` nginx
-root /srv/nominatim/build/website;
-index search.php;
-location / {
-    try_files $uri $uri/ @php;
-}
-
-location @php {
-    fastcgi_param SCRIPT_FILENAME "$document_root$uri.php";
-    fastcgi_param PATH_TRANSLATED "$document_root$uri.php";
-    fastcgi_param QUERY_STRING    $args;
-    fastcgi_pass unix:/var/run/php/php7.3-fpm.sock;
-    fastcgi_index index.php;
-    include fastcgi_params;
-}
-
-location ~ [^/]\.php(/|$) {
-    fastcgi_split_path_info ^(.+?\.php)(/.*)$;
-    if (!-f $document_root$fastcgi_script_name) {
-        return 404;
-    }
-    fastcgi_pass unix:/var/run/php7.3-fpm.sock;
-    fastcgi_index search.php;
-    include fastcgi.conf;
-}
+```
+wget -O Nominatim/data/country_osm_grid.sql.gz https://www.nominatim.org/data/country_grid.sql.gz
 ```
 
-Restart the nginx and php5-fpm services and the website should now be available
-at `http://localhost/`.
+### Building Nominatim
 
+The code must be built in a separate directory. Create the directory and
+change into it.
 
-Now continue with [importing the database](Import-and-Update.md).
+```
+mkdir build
+cd build
+```
+
+Nominatim uses cmake and make for building. Assuming that you have created the
+build at the same level as the Nominatim source directory run:
+
+```
+cmake ../Nominatim
+make
+sudo make install
+```
+
+Nominatim installs itself into `/usr/local` per default. To choose a different
+installation directory add `-DCMAKE_INSTALL_PREFIX=<install root>` to the
+cmake command. Make sure that the `bin` directory is available in your path
+in that case, e.g.
+
+```
+export PATH=<install root>/bin:$PATH
+```
+
+Now continue with [importing the database](Import.md).

docs/admin/Migration.md

@@ -1,10 +1,136 @@
 # Database Migrations
 
-This page describes database migrations necessary to update existing databases
-to newer versions of Nominatim.
+Since version 3.7.0 Nominatim offers automatic migrations. Please follow
+the following steps:
 
-SQL statements should be executed from the PostgreSQL commandline. Execute
-`psql nominatim` to enter command line mode.
+* stop any updates that are potentially running
+* update Nominatim to the newer version
+* go to your project directory and run `nominatim admin --migrate`
+* (optionally) restart updates
+
+Below you find additional migrations and hints about other structural and
+breaking changes. **Please read them before running the migration.**
+
+!!! note
+    If you are migrating from a version <3.6, then you still have to follow
+    the manual migration steps up to 3.6.
+
+## 3.6.0 -> 3.7.0
+
+### New format and name of configuration file
+
+The configuration for an import is now saved in a `.env` file in the project
+directory. This file follows the dotenv format. For more information, see
+the [installation chapter](Import.md#configuration-setup-in-env).
+
+To migrate to the new system, create a new project directory, add the `.env`
+file and port your custom configuration from `settings/local.php`. Most
+settings are named similar and only have received a `NOMINATIM_` prefix.
+Use the default settings in `settings/env.defaults` as a reference.
+
+### New location for data files
+
+External data files for Wikipedia importance, postcodes etc. are no longer
+expected to reside in the source tree by default. Instead they will be searched
+in the project directory. If you have an automated setup script you must
+either adapt the download location or explicitly set the location of the
+files to the old place in your `.env`.
+
+### Introducing `nominatim` command line tool
+
+The various php utilities have been replaced with a single `nominatim`
+command line tool. Make sure to adapt any scripts. There is no direct 1:1
+matching between the old utilities and the commands of nominatim CLI. The
+following list gives you a list of nominatim sub-commands that contain
+functionality of each script:
+
+* ./utils/setup.php: `import`, `freeze`, `refresh`
+* ./utils/update.php: `replication`, `add-data`, `index`, `refresh`
+* ./utils/specialphrases.php: `special-phrases`
+* ./utils/check_import_finished.php: `admin`
+* ./utils/warm.php: `admin`
+* ./utils/export.php: `export`
+
+Try `nominatim <command> --help` for more information about each subcommand.
+
+`./utils/query.php` no longer exists in its old form. `nominatim search`
+provides a replacement but returns different output.
+
+### Switch to normalized house numbers
+
+The housenumber column in the placex table uses now normalized version.
+The automatic migration step will convert the column but this may take a
+very long time. It is advisable to take the machine offline while doing that.
+
+## 3.5.0 -> 3.6.0
+
+### Change of layout of search_name_* tables
+
+The table need a different index for nearest place lookup. Recreate the
+indexes using the following shell script:
+
+```bash
+for table in `psql -d nominatim -c "SELECT tablename FROM pg_tables WHERE tablename LIKE 'search_name_%'" -tA | grep -v search_name_blank`;
+do
+    psql -d nominatim -c "DROP INDEX idx_${table}_centroid_place; CREATE INDEX idx_${table}_centroid_place ON ${table} USING gist (centroid) WHERE ((address_rank >= 2) AND (address_rank <= 25)); DROP INDEX idx_${table}_centroid_street; CREATE INDEX idx_${table}_centroid_street ON ${table} USING gist (centroid) WHERE ((address_rank >= 26) AND (address_rank <= 27))";
+done
+```
+
+### Removal of html output
+
+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
+set up the UI.
+
+The icons served together with the API responses have been moved to the
+nominatim-ui project as well. If you want to keep the `icon` field in the
+response, you need to set `CONST_MapIcon_URL` to the URL of the `/mapicon`
+directory of nominatim-ui.
+
+### Change order during indexing
+
+When reindexing places during updates, there is now a different order used
+which needs a different database index. Create it with the following SQL command:
+
+```sql
+CREATE INDEX idx_placex_pendingsector_rank_address
+  ON placex
+  USING BTREE (rank_address, geometry_sector)
+  WHERE indexed_status > 0;
+```
+
+You can then drop the old index with:
+
+```sql
+DROP INDEX idx_placex_pendingsector;
+```
+
+### Unused index
+
+This index has been unused ever since the query using it was changed two years ago. Saves about 12GB on a planet installation.
+
+```sql
+DROP INDEX idx_placex_geometry_reverse_lookupPoint;
+```
+
+### Switching to dotenv
+
+As part of the work changing the configuration format, the configuration for
+the website is now using a separate configuration file. To create the
+configuration file, run the following command after updating:
+
+```sh
+./utils/setup.php --setup-website
+```
+
+### Update SQL code
+
+To update the SQL code to the leatest version run:
+
+```
+./utils/setup.php --create-functions --enable-diff-updates --create-partition-functions
+```
 
 ## 3.4.0 -> 3.5.0
 
@@ -17,10 +143,32 @@ follows:
   * download the new Wikipedia tables as described in the import section
   * reimport the tables: `./utils/setup.php --import-wikipedia-articles`
   * update the functions: `./utils/setup.php --create-functions --enable-diff-updates`
+  * create a new lookup index:
+```sql
+CREATE INDEX idx_placex_wikidata
+  ON placex
+  USING BTREE ((extratags -> 'wikidata'))
+  WHERE extratags ? 'wikidata'
+    AND class = 'place'
+    AND osm_type = 'N'
+    AND rank_search < 26;
+```
   * compute importance: `./utils/update.php --recompute-importance`
 
 The last step takes about 10 hours on the full planet.
 
+Remove one function (it will be recreated in the next step):
+
+```sql
+DROP FUNCTION create_country(hstore,character varying);
+```
+
+Finally, update all SQL functions:
+
+```sh
+./utils/setup.php --create-functions --enable-diff-updates --create-partition-functions
+```
+
 ## 3.3.0 -> 3.4.0
 
 ### Reorganisation of location_area_country table
@@ -38,6 +186,12 @@ CREATE INDEX idx_location_area_country_geometry ON location_area_country USING G
 CREATE INDEX idx_location_area_country_place_id ON location_area_country USING BTREE (place_id);
 ```
 
+Finally, update all SQL functions:
+
+```sh
+./utils/setup.php --create-functions --enable-diff-updates --create-partition-functions
+```
+
 ## 3.2.0 -> 3.3.0
 
 ### New database connection string (DSN) format
@@ -54,7 +208,7 @@ The new format is
 
 ### Natural Earth country boundaries no longer needed as fallback
 
-```
+```sql
 DROP TABLE country_naturalearthdata;
 ```
 
@@ -80,27 +234,37 @@ following command:
 The reverse algorithm has changed and requires new indexes. Run the following
 SQL statements to create the indexes:
 
-```
+```sql
 CREATE INDEX idx_placex_geometry_reverse_lookupPoint
-  ON placex USING gist (geometry)
-  WHERE (name is not null or housenumber is not null or rank_address between 26 and 27)
-    AND class not in ('railway','tunnel','bridge','man_made')
-    AND rank_address >= 26 AND indexed_status = 0 AND linked_place_id is null;
+  ON placex
+  USING gist (geometry)
+  WHERE (name IS NOT null or housenumber IS NOT null or rank_address BETWEEN 26 AND 27)
+    AND class NOT IN ('railway','tunnel','bridge','man_made')
+    AND rank_address >= 26
+    AND indexed_status = 0
+    AND linked_place_id IS null;
 CREATE INDEX idx_placex_geometry_reverse_lookupPolygon
   ON placex USING gist (geometry)
   WHERE St_GeometryType(geometry) in ('ST_Polygon', 'ST_MultiPolygon')
-    AND rank_address between 4 and 25 AND type != 'postcode'
-    AND name is not null AND indexed_status = 0 AND linked_place_id is null;
+    AND rank_address between 4 and 25
+    AND type != 'postcode'
+    AND name is not null
+    AND indexed_status = 0
+    AND linked_place_id is null;
 CREATE INDEX idx_placex_geometry_reverse_placeNode
   ON placex USING gist (geometry)
-  WHERE osm_type = 'N' AND rank_search between 5 and 25
-    AND class = 'place' AND type != 'postcode'
-    AND name is not null AND indexed_status = 0 AND linked_place_id is null;
+  WHERE osm_type = 'N'
+    AND rank_search between 5 and 25
+    AND class = 'place'
+    AND type != 'postcode'
+    AND name is not null
+    AND indexed_status = 0
+    AND linked_place_id is null;
 ```
 
 You also need to grant the website user access to the `country_osm_grid` table:
 
-```
+```sql
 GRANT SELECT ON table country_osm_grid to "www-user";
 ```
 
@@ -108,7 +272,7 @@ Replace the `www-user` with the user name of your website server if necessary.
 
 You can now drop the unused indexes:
 
-```
+```sql
 DROP INDEX idx_placex_reverse_geometry;
 ```
 
@@ -137,8 +301,8 @@ CREATE INDEX idx_postcode_geometry ON location_postcode USING GIST (geometry);
 CREATE UNIQUE INDEX idx_postcode_id ON location_postcode USING BTREE (place_id);
 CREATE INDEX idx_postcode_postcode ON location_postcode USING BTREE (postcode);
 GRANT SELECT ON location_postcode TO "www-data";
-drop type if exists nearfeaturecentr cascade;
-create type nearfeaturecentr as (
+DROP TYPE IF EXISTS nearfeaturecentr CASCADE;
+CREATE TYPE nearfeaturecentr AS (
   place_id BIGINT,
   keywords int[],
   rank_address smallint,

docs/admin/Setup-Nominatim-UI.md

@@ -0,0 +1,184 @@
+# Setting up the Nominatim UI
+
+Nominatim is a search API, it does not provide a website interface on its
+own. [nominatim-ui](https://github.com/osm-search/nominatim-ui) offers a
+small website for testing your setup and inspecting the database content.
+
+This section provides a quick start how to use nominatim-ui with your
+installation. For more details, please also have a look at the
+[README of nominatim-ui](https://github.com/osm-search/nominatim-ui/blob/master/README.md).
+
+## Installing nominatim-ui
+
+We provide regular releases of nominatim-ui that contain the packaged website.
+They do not need any special installation. Just download, configure
+and run it. Grab the latest release from
+[nominatim-ui's Github release page](https://github.com/osm-search/nominatim-ui/releases)
+and unpack it. You can use `nominatim-ui-x.x.x.tar.gz` or `nominatim-ui-x.x.x.zip`.
+
+Copy the example configuration into the right place:
+
+    cd nominatim-ui
+    cp dist/config.example.js dist/config.js
+
+Now adapt the configuration to your needs. You need at least
+to change the `Nominatim_API_Endpoint` to point to your Nominatim installation.
+
+Then you can just test it locally by spinning up a webserver in the `dist`
+directory. For example, with Python:
+
+    cd nominatim-ui/dist
+    python3 -m http.server 8765
+
+The website is now available at `http://localhost:8765`.
+
+## Forwarding searches to nominatim-ui
+
+Nominatim used to provide the search interface directly by itself when
+`format=html` was requested. For all endpoints except for `/reverse` and
+`/lookup` this even used to be the default.
+
+The following section describes how to set up Apache or nginx, so that your
+users are forwarded to nominatim-ui when they go to URL that formerly presented
+the UI.
+
+### Setting up forwarding in Nginx
+
+First of all make nominatim-ui available under `/ui` on your webserver:
+
+``` nginx
+server {
+
+    # Here is the Nominatim setup as described in the Installation section
+
+    location /ui/ {
+        alias <full path to the nominatim-ui directory>/dist/;
+        index index.html;
+    }
+}
+```
+
+Now we need to find out if a URL should be forwarded to the UI. Add the
+following `map` commands *outside* the server section:
+
+``` nginx
+# Inspect the format parameter in the query arguments. We are interested
+# if it is set to html or something else or if it is missing completely.
+map $args $format {
+    default                  default;
+    ~(^|&)format=html(&|$)   html;
+    ~(^|&)format=            other;
+}
+
+# Determine from the URI and the format parameter above if forwarding is needed.
+map $uri/$format $forward_to_ui {
+    default               1;   # The default is to forward.
+    ~^/ui                 0;   # If the URI point to the UI already, we are done.
+    ~/other$              0;   # An explicit non-html format parameter. No forwarding.
+    ~/reverse.*/default   0;   # Reverse and lookup assume xml format when
+    ~/lookup.*/default    0;   #   no format parameter is given. No forwarding.
+}
+```
+
+The `$forward_to_ui` parameter can now be used to conditionally forward the
+calls:
+
+```
+# When no endpoint is given, default to search.
+# Need to add a rewrite so that the rewrite rules below catch it correctly.
+rewrite ^/$ /search;
+
+location @php {
+    # fastcgi stuff..
+    if ($forward_to_ui) {
+        rewrite ^(/[^/]*) https://yourserver.com/ui$1.html redirect;
+    }
+}
+
+location ~ [^/]\.php(/|$) {
+    # fastcgi stuff..
+    if ($forward_to_ui) {
+        rewrite (.*).php https://yourserver.com/ui$1.html redirect;
+    }
+}
+```
+
+!!! warning
+    Be aware that the rewrite commands are slightly different for URIs with and
+    without the .php suffix.
+
+Reload nginx and the UI should be available.
+
+### Setting up forwarding in Apache
+
+First of all make nominatim-ui available in the `ui/` subdirectory where
+Nominatim is installed. For example, given you have set up an alias under
+`nominatim` like this:
+
+``` apache
+Alias /nominatim /home/vagrant/build/website
+```
+
+you need to insert the following rules for nominatim-ui before that alias:
+
+```
+<Directory "/home/vagrant/nominatim-ui/dist">
+  DirectoryIndex search.html
+  Require all granted
+</Directory>
+
+Alias /nominatim/ui /home/vagrant/nominatim-ui/dist
+```
+
+Replace `/home/vagrant/nominatim-ui` with the directory where you have cloned
+nominatim-ui.
+
+!!! important
+    The alias for nominatim-ui must come before the alias for the Nominatim
+    website directory.
+
+To set up forwarding, the Apache rewrite module is needed. Enable it with:
+
+``` sh
+sudo a2enmod rewrite
+```
+
+Then add rewrite rules to the `Directory` directive of the Nominatim website
+directory like this:
+
+``` apache
+<Directory "/home/vagrant/build/website">
+  Options FollowSymLinks MultiViews
+  AddType text/html   .php
+  Require all granted
+
+  RewriteEngine On
+
+  # This must correspond to the URL where nominatim can be found.
+  RewriteBase "/nominatim/"
+
+  # If no endpoint is given, then use search.
+  RewriteRule ^(/|$)   "search.php"
+
+  # If format-html is explicity 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]
+
+  # 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]
+</Directory>
+```
+
+Restart Apache and the UI should be available.

docs/admin/Tokenizers.md

@@ -0,0 +1,205 @@
+# 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

@@ -0,0 +1,56 @@
+# Updating the Database
+
+There are many different ways to update your Nominatim database.
+The following section describes how to keep it up-to-date using
+an [online replication service for OpenStreetMap data](https://wiki.openstreetmap.org/wiki/Planet.osm/diffs)
+For a list of other methods to add or update data see the output of
+`nominatim add-data --help`.
+
+!!! important
+    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
+
+It is recommended to install Pyosmium via pip. Make sure to use python3.
+Run (as the same user who will later run the updates):
+
+```sh
+pip3 install --user osmium
+```
+
+#### Setting up the update process
+
+Next the update needs to be initialised. By default Nominatim is configured
+to update using the global minutely diffs.
+
+If you want a different update source you will need to add some settings
+to `.env`. For example, to use the daily country extracts
+diffs for Ireland from Geofabrik add the following:
+
+    # base URL of the replication service
+    NOMINATIM_REPLICATION_URL="https://download.geofabrik.de/europe/ireland-and-northern-ireland-updates"
+    # How often upstream publishes diffs (in seconds)
+    NOMINATIM_REPLICATION_UPDATE_INTERVAL=86400
+    # How long to sleep if no update found yet (in seconds)
+    NOMINATIM_REPLICATION_RECHECK_INTERVAL=900
+
+To set up the update process now run the following command:
+
+    nominatim replication --init
+
+It outputs the date where updates will start. Recheck that this date is
+what you expect.
+
+The `replication --init` command needs to be rerun whenever the replication
+service is changed.
+
+#### Updating Nominatim
+
+The following command will keep your database constantly up to date:
+
+    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.

docs/api/Details.md

@@ -1,19 +1,22 @@
 # Place details
 
-Lookup details about a single place by id. The default output is HTML for debugging search logic and results.
+Show all details about a single place saved in the database.
 
-**The details page (including JSON output) exists for debugging only and must not be downloaded automatically**, see [Nominatim Usage Policy](https://operations.osmfoundation.org/policies/nominatim/).
+!!! warning
+    The details page exists for debugging only. You may not use it in scripts
+    or to automatically query details about a result.
+    See [Nominatim Usage Policy](https://operations.osmfoundation.org/policies/nominatim/).
 
 
 ## Parameters
 
 The details API supports the following two request formats:
 
-```
-  https://nominatim.openstreetmap.org/details?osmtype=[N|W|R]&osmid=<value>&class=<value>
+``` xml
+https://nominatim.openstreetmap.org/details?osmtype=[N|W|R]&osmid=<value>&class=<value>
 ```
 
-`osmtype` and `osmid` are required parameter. The type is one of node (N), way (W)
+`osmtype` and `osmid` are required parameters. The type is one of node (N), way (W)
 or relation (R). The id must be a number. The `class` parameter is optional and
 allows to distinguish between entries, when the corresponding OSM object has more
 than one main tag. For example, when a place is tagged with `tourism=hotel` and
@@ -23,36 +26,34 @@ to get exactly the one you want. If there are multiple places in the database
 but the `class` parameter is left out, then one of the places will be chosen
 at random and displayed.
 
-```
-  https://nominatim.openstreetmap.org/details?place_id=<value>
+``` xml
+https://nominatim.openstreetmap.org/details?place_id=<value>
 ```
 
-Placeids are assigned sequentially during Nominatim data import. The id for a place is different between Nominatim installation (servers) and changes when data gets reimported. Therefore it can't be used as permanent id and shouldn't be used in bug reports.
+Place IDs are assigned sequentially during Nominatim data import. The ID
+for a place is different between Nominatim installation (servers) and
+changes when data gets reimported. Therefore it cannot be used as
+a permanent id and shouldn't be used in bug reports.
 
 
 Additional optional parameters are explained below.
 
 ### Output format
 
-* `format=[html|json]`
-
-See [Place Output Formats](Output.md) for details on each format. (Default: html)
-
 * `json_callback=<string>`
 
 Wrap JSON output in a callback function (JSONP) i.e. `<string>(<json>)`.
-Only has an effect for JSON output formats.
 
 * `pretty=[0|1]`
 
-For JSON output will add indentation to make it more human-readable. (Default: 0)
+Add indentation to make it more human-readable. (Default: 0)
 
 
 ### Output details
 
 * `addressdetails=[0|1]`
 
-Include a breakdown of the address into elements. (Default for JSON: 0, for HTML: 1)
+Include a breakdown of the address into elements. (Default: 0)
 
 * `keywords=[0|1]`
 
@@ -60,11 +61,16 @@ Include a list of name keywords and address keywords (word ids). (Default: 0)
 
 * `linkedplaces=[0|1]`
 
-Include details of places higher in the address hierarchy. E.g. for a street this is usually the city, state, postal code, country. (Default: 1)
+Include a details of places that are linked with this one. Places get linked
+together when they are different forms of the same physical object. Nominatim
+links two kinds of objects together: place nodes get linked with the
+corresponding administrative boundaries. Waterway relations get linked together with their
+members.
+(Default: 1)
 
 * `hierarchy=[0|1]`
 
-Include details of places lower in the address hierarchy. E.g. for a city this usually a list of streets, suburbs, rivers. (Default for JSON: 0, for HTML: 1)
+Include details of places lower in the address hierarchy. (Default: 0)
 
 * `group_hierarchy=[0|1]`
 
@@ -72,7 +78,7 @@ For JSON output will group the places by type. (Default: 0)
 
 * `polygon_geojson=[0|1]`
 
-Include geometry of result. (Default for JSON: 0, for HTML: 1)
+Include geometry of result. (Default: 0)
 
 ### Language of results
 
@@ -86,10 +92,6 @@ comma-separated list of language codes.
 
 ## Examples
 
-##### HTML
-
-[https://nominatim.openstreetmap.org/details.php?osmtype=W&osmid=38210407](https://nominatim.openstreetmap.org/details.php?osmtype=W&osmid=38210407)
-
 ##### JSON
 
 [https://nominatim.openstreetmap.org/details.php?osmtype=W&osmid=38210407&format=json](https://nominatim.openstreetmap.org/details.php?osmtype=W&osmid=38210407&format=json)

docs/api/Faq.md

@@ -58,4 +58,4 @@ The [Overpass API](https://wiki.openstreetmap.org/wiki/Overpass_API) is more
 suited for these kinds of queries.
 
 That said if you installed your own Nominatim instance you can use the
-`/utils/export.php` PHP script as basis to return such lists.
+`nominatim export` PHP script as basis to return such lists.

docs/api/Lookup.md

@@ -56,6 +56,21 @@ specified in the "Accept-Language" HTTP header.
 Either use a standard RFC2616 accept-language string or a simple
 comma-separated list of language codes.
 
+### Polygon output
+
+* `polygon_geojson=1`
+* `polygon_kml=1`
+* `polygon_svg=1`
+* `polygon_text=1`
+
+Output geometry of results as a GeoJSON, KML, SVG or WKT. Only one of these
+options can be used at a time. (Default: 0)
+
+* `polygon_threshold=0.0`
+
+Return a simplified version of the output geometry. The parameter is the
+tolerance in degrees with which the geometry may differ from the original
+geometry. Topology is preserved in the result. (Default: 0.0)
 
 ### Other
 

docs/api/Output.md

@@ -2,12 +2,10 @@
 
 The [/reverse](Reverse.md), [/search](Search.md) and [/lookup](Lookup.md)
 API calls produce very similar output which is explained in this section.
-There is one section for each format which is selectable via the `format`
-parameter.
+There is one section for each format. The format correspond to what was
+selected via the `format` parameter.
 
-## Formats
-
-### JSON
+## JSON
 
 The JSON format returns an array of places (for search and lookup) or
 a single place (for reverse) of the following format:
@@ -41,13 +39,13 @@ a single place (for reverse) of the following format:
       "wikipedia": "en:London",
       "population": "8416535"
     }
-  },
+  }
 ```
 
 The possible fields are:
 
  * `place_id` - reference to the Nominatim internal database ID ([see notes](#place_id-is-not-a-persistent-id))
- * `osm_type`, `osm_id` - reference to the OSM object
+ * `osm_type`, `osm_id` - reference to the OSM object ([see notes](#osm-reference))
  * `boundingbox` - area of corner coordinates ([see notes](#boundingbox))
  * `lat`, `lon` - latitude and longitude of the centroid of the object
  * `display_name` - full comma-separated address
@@ -62,22 +60,22 @@ The possible fields are:
  * `geojson`, `svg`, `geotext`, `geokml` - full geometry
    (only with the appropriate `polygon_*` parameter)
 
-### JSONv2
+## JSONv2
 
 This is the same as the JSON format with two changes:
 
  * `class` renamed to `category`
  * additional field `place_rank` with the search rank of the object
 
-### GeoJSON
+## GeoJSON
 
 This format follows the [RFC7946](https://geojson.org). Every feature includes
 a bounding box (`bbox`).
 
-The feature list has the following fields:
+The properties object has the following fields:
 
  * `place_id` - reference to the Nominatim internal database ID ([see notes](#place_id-is-not-a-persistent-id))
- * `osm_type`, `osm_id` - reference to the OSM object
+ * `osm_type`, `osm_id` - reference to the OSM object ([see notes](#osm-reference))
  * `category`, `type` - key and value of the main OSM tag
  * `display_name` - full comma-separated address
  * `place_rank` - class search rank
@@ -92,13 +90,13 @@ The feature list has the following fields:
 Use `polygon_geojson` to output the full geometry of the object instead
 of the centroid.
 
-### GeocodeJSON
+## GeocodeJSON
 
 The GeocodeJSON format follows the
 [GeocodeJSON spec 0.1.0](https://github.com/geocoders/geocodejson-spec).
 The following feature attributes are implemented:
 
- * `osm_type`, `osm_id` - reference to the OSM object (unofficial extension)
+ * `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, ...)
  * `label` - full comma-separated address
  * `name` - localised name of the place
@@ -110,18 +108,18 @@ The following feature attributes are implemented:
 Use `polygon_geojson` to output the full geometry of the object instead
 of the centroid.
 
-### XML
+## XML
 
 The XML response returns one or more place objects in slightly different
 formats depending on the API call.
 
-#### Reverse
+### Reverse
 
 ```
 <reversegeocode timestamp="Sat, 11 Aug 18 11:53:21 +0000"
                 attribution="Data © OpenStreetMap contributors, ODbL 1.0. https://www.openstreetmap.org/copyright"
                 querystring="lat=48.400381&lon=11.745876&zoom=5&format=xml">
-  <result place_id="179509537" osm_type="relation" osm_id="2145268" ref="BY"
+  <result place_id="179509537" osm_type="relation" osm_id="2145268" ref="BY" place_rank="15" address_rank="15"
           lat="48.9467562" lon="11.4038717"
           boundingbox="47.2701114,50.5647142,8.9763497,13.8396373">
        Bavaria, Germany
@@ -148,7 +146,7 @@ attribution to OSM and the original querystring.
 The place information can be found in the `result` element. The attributes of that element contain:
 
  * `place_id` - reference to the Nominatim internal database ID ([see notes](#place_id-is-not-a-persistent-id))
- * `osm_type`, `osm_id` - reference to the OSM object
+ * `osm_type`, `osm_id` - reference to the OSM object ([see notes](#osm-reference))
  * `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))
@@ -159,14 +157,14 @@ The full address of the result can be found in the content of the
 Additional information requested with `addressdetails=1`, `extratags=1` and
 `namedetails=1` can be found in extra elements.
 
-#### Search and Lookup
+### Search and Lookup
 
 ```
 <searchresults timestamp="Sat, 11 Aug 18 11:55:35 +0000"
                attribution="Data © OpenStreetMap contributors, ODbL 1.0. https://www.openstreetmap.org/copyright"
                querystring="london" polygon="false" exclude_place_ids="100149"
                more_url="https://nominatim.openstreetmap.org/search.php?q=london&addressdetails=1&extratags=1&exclude_place_ids=100149&format=xml&accept-language=en-US%2Cen%3Bq%3D0.7%2Cde%3Bq%3D0.3">
-  <place place_id="100149" osm_type="node" osm_id="107775" place_rank="15"
+  <place place_id="100149" osm_type="node" osm_id="107775" place_rank="15" address_rank="15"
          boundingbox="51.3473219,51.6673219,-0.2876474,0.0323526" lat="51.5073219" lon="-0.1276474"
          display_name="London, Greater London, England, SW1A 2DU, United Kingdom"
          class="place" type="city" importance="0.9654895765402"
@@ -203,11 +201,12 @@ The place information can be found in the `place` elements, of which there may
 be more than one. The attributes of that element contain:
 
  * `place_id` - reference to the Nominatim internal database ID ([see notes](#place_id-is-not-a-persistent-id))
- * `osm_type`, `osm_id` - reference to the OSM object
+ * `osm_type`, `osm_id` - reference to the OSM object ([see notes](#osm-reference))
  * `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
+ * `place_rank` - class [search rank](../develop/Ranking#search-rank)
+ * `address_rank` - place [address rank](../develop/Ranking#address-rank)
  * `display_name` - full comma-separated address
  * `class`, `type` - key and value of the main OSM tag
  * `importance` - computed importance rank
@@ -217,17 +216,19 @@ When `addressdetails=1` is requested, the localised address parts appear
 as subelements with the type of the address part.
 
 Additional information requested with `extratags=1` and `namedetails=1` can
-be found in extra elements as sub-element of each place.
+be found in extra elements as sub-element of `extratags` and `namedetails`
+respectively.
 
 
 ## Notes on field values
 
 ### place_id is not a persistent id
 
-The `place_id` is created when a Nominatim database gets installed. A
-single place will have a different value on another server or even when
-the same data gets re-imported. It's thus not useful to treat it as
-permanent for later use.
+The `place_id` is an internal identifier that is assigned data is imported
+into a Nominatim database. The same OSM object will have a different value
+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
 OpenStreetMap mappers can delete, split, recreate places (and those
@@ -236,20 +237,40 @@ Places can also change their meaning without changing their `osm_id`,
 e.g. when a restaurant is retagged as supermarket. For a more in-depth
 discussion see [Permanent ID](https://wiki.openstreetmap.org/wiki/Permanent_ID).
 
-Nominatim merges some places (e.g. center node of a city with the boundary
-relation) so `osm_type`+`osm_id`+`class_name` would be more unique.
+If you need an ID that is consistent over multiple installations of Nominatim,
+then you should use the combination of `osm_type`+`osm_id`+`class`.
+
+### OSM reference
+
+Nominatim may sometimes return special objects that do not correspond directly
+to an object in OpenStreetMap. These are:
+
+* **Postcodes**. Nominatim returns an postcode point created from all mapped
+  postcodes of the same name. The class and type of these object is `place=postcdode`.
+  No `osm_type` and `osm_id` are included in the result.
+* **Housenumber interpolations**. Nominatim returns a single interpolated
+  housenumber from the interpolation way. The class and type are `place=house`
+  and `osm_type` and `osm_id` correspond to the interpolation way in OSM.
+* **TIGER housenumber.** Nominatim returns a single interpolated housenumber
+  from the TIGER data. The class and type are `place=house`
+  and `osm_type` and `osm_id` correspond to the street mentioned in the result.
+
+Please note that the `osm_type` and `osm_id` returned may be changed in the
+future. You should not expect to only find `node`, `way` and `relation` for
+the type.
 
 ### boundingbox
 
 Comma separated list of min latitude, max latitude, min longitude, max longitude.
 The whole planet would be `-90,90,-180,180`.
 
-Can we used to pan and center the map on the result, for example with leafletjs
+Can be used to pan and center the map on the result, for example with leafletjs
 mapping library
 `map.fitBounds([[bbox[0],bbox[2]],[bbox[1],bbox[3]]], {padding: [20, 20], maxzoom: 16});`
 
 Bounds crossing the antimeridian have a min latitude -180 and max latitude 180,
-essentially covering the planet (See [issue 184](https://github.com/openstreetmap/Nominatim/issues/184)).
+essentially covering the entire planet
+(see [issue 184](https://github.com/openstreetmap/Nominatim/issues/184)).
 
 ### addressdetails
 

docs/api/Reverse.md

@@ -1,36 +1,48 @@
 # Reverse Geocoding
 
-Reverse geocoding generates an address from a latitude and longitude or from
-an OSM object.
+Reverse geocoding generates an address from a latitude and longitude.
+
+## How it works
+
+The reverse geocoding API does not exactly compute the address for the
+coordinate it receives. It works by finding the closest suitable OSM object
+and returning its address information. This may occasionally lead to
+unexpected results.
+
+First of all, Nominatim only includes OSM objects in
+its index that are suitable for searching. Small, unnamed paths for example
+are missing from the database and can therefore not be used for reverse
+geocoding either.
+
+The other issue to be aware of is that the closest OSM object may not always
+have a similar enough address to the coordinate you were requesting. For
+example, in dense city areas it may belong to a completely different street.
+
 
 ## Parameters
 
 The main format of the reverse API is
 
 ```
-https://nominatim.openstreetmap.org/reverse?<query>
+https://nominatim.openstreetmap.org/reverse?lat=<value>&lon=<value>&<params>
 ```
 
-There are two ways how the requested location can be specified:
+where `lat` and `lon` are latitude and longitutde of a coordinate in WGS84
+projection. The API returns exactly one result or an error when the coordinate
+is in an area with no OSM data coverage.
 
-* `lat=<value>` `lon=<value>`
+Additional paramters are accepted as listed below.
 
-    A geographic location to generate an address for. The coordiantes must be
-    in WGS84 format.
-
-* `osm_type=[N|W|R]` `osm_id=<value>`
-
-    A specific OSM node(N), way(W) or relation(R) to return an address for.
-
-In both cases exactly one object is returned. The two input parameters cannot
-be used at the same time. Both accept the additional optional parameters 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)
+    instead.
 
 ### Output format
 
 * `format=[xml|json|jsonv2|geojson|geocodejson]`
 
-See [Place Output Formats](Output.md) for details on each format. (Default: html)
+See [Place Output Formats](Output.md) for details on each format. (Default: xml)
 
 * `json_callback=<string>`
 
@@ -69,8 +81,9 @@ comma-separated list of language codes.
 
 * `zoom=[0-18]`
 
-Level of detail required for the address. Default: 18. This is a number that corresponds
-roughly to the zoom level used in map frameworks like Leaflet.js, Openlayers etc.
+Level of detail required for the address. Default: 18. This is a number that
+corresponds roughly to the zoom level used in XYZ tile sources in frameworks
+like Leaflet.js, Openlayers etc.
 In terms of address details the zoom levels are as follows:
 
  zoom | address detail
@@ -97,7 +110,7 @@ options can be used at a time. (Default: 0)
 
 * `polygon_threshold=0.0`
 
-Simplify the output geometry before returning. The parameter is the
+Return a simplified version of the output geometry. The parameter is the
 tolerance in degrees with which the geometry may differ from the original
 geometry. Topology is preserved in the result. (Default: 0.0)
 
@@ -149,7 +162,7 @@ This overrides the specified machine readable format. (Default: 0)
   "licence":"Data © OpenStreetMap contributors, ODbL 1.0. https:\/\/www.openstreetmap.org\/copyright",
   "osm_type":"way",
   "osm_id":"280940520",
-"lat":"-34.4391708",
+  "lat":"-34.4391708",
   "lon":"-58.7064573",
   "place_rank":"26",
   "category":"highway",

docs/api/Search.md

@@ -1,30 +1,27 @@
 # Search queries
 
-The search API allows you to look up a location from a textual description.
-Nominatim supports structured as well as free-form search queries.
+The search API allows you to look up a location from a textual description
+or address. Nominatim supports structured and free-form search queries.
 
 The search query may also contain
 [special phrases](https://wiki.openstreetmap.org/wiki/Nominatim/Special_Phrases)
 which are translated into specific OpenStreetMap (OSM) tags (e.g. Pub => `amenity=pub`).
-Note that this only limits the items to be found, it's not suited to return complete
-lists of OSM objects of a specific type. For those use [Overpass API](https://overpass-api.de/).
+This can be used to narrow down the kind of objects to be returned.
+
+!!! warning
+    Special phrases are not suitable to query all objects of a certain type in an
+    area. Nominatim will always just return a collection of the best matches. To
+    download OSM data by object type, use the [Overpass API](https://overpass-api.de/).
 
 ## Parameters
 
-The search API has the following two formats:
-
-```
-   https://nominatim.openstreetmap.org/search/<query>?<params>
-```
-
-This format only accepts a free-form query string where the
-parts of the query are separated by slashes.
+The search API has the following format:
 
 ```
    https://nominatim.openstreetmap.org/search?<params>
 ```
 
-In this form, the query may be given through two different sets of parameters:
+The search term may be specified with two different sets of parameters:
 
 * `q=<query>`
 
@@ -46,13 +43,13 @@ In this form, the query may be given through two different sets of parameters:
     Structured requests are faster but are less robust against alternative
     OSM tagging schemas. **Do not combine with** `q=<query>` **parameter**.
 
-All three query forms accept the additional parameters listed below.
+Both query forms accept the additional parameters listed below.
 
 ### Output format
 
-* `format=[html|xml|json|jsonv2|geojson|geocodejson]`
+* `format=[xml|json|jsonv2|geojson|geocodejson]`
 
-See [Place Output Formats](Output.md) for details on each format. (Default: html)
+See [Place Output Formats](Output.md) for details on each format. (Default: jsonv2)
 
 * `json_callback=<string>`
 
@@ -96,16 +93,16 @@ Limit search results to one or more countries. `<countrycode>` must be the
 e.g. `gb` for the United Kingdom, `de` for Germany.
 
 Each place in Nominatim is assigned to one country code based
-on `admin_level=2` tags, in rare cases to none (for example in
-international waters outside any country).
+on OSM country boundaries. In rare cases a place may not be in any country
+at all, for example, in international waters.
 
 * `exclude_place_ids=<place_id,[place_id],[place_id]`
 
 If you do not want certain OSM objects to appear in the search
 result, give a comma separated list of the `place_id`s you want to skip.
-This can be used to broaden search results. For example, if a previous
-query only returned a few results, then including those here would cause
-the search to return other, less accurate, matches (if possible).
+This can be used to retrieve additional search results. For example, if a
+previous query only returned a few results, then including those here would
+cause the search to return other, less accurate, matches (if possible).
 
 
 * `limit=<integer>`
@@ -116,16 +113,17 @@ Limit the number of returned results. (Default: 10, Maximum: 50)
 * `viewbox=<x1>,<y1>,<x2>,<y2>`
 
 The preferred area to find search results. Any two corner points of the box
-are accepted in any order as long as they span a real box. `x` is longitude,
+are accepted as long as they span a real box. `x` is longitude,
 `y` is latitude.
 
 
 * `bounded=[0|1]`
 
-When a viewbox is given, restrict the result to items contained with that
+When a viewbox is given, restrict the result to items contained within that
 viewbox (see above). When `viewbox` and `bounded=1` are given, an amenity
-only search is allowed. In this case, give the special keyword for the
-amenity in square brackets, e.g. `[pub]`. (Default: 0)
+only search is allowed. Give the special keyword for the amenity in square
+brackets, e.g. `[pub]` and a selection of objects of this type is returned.
+There is no guarantee that the result is complete. (Default: 0)
 
 
 ### Polygon output
@@ -140,7 +138,7 @@ options can be used at a time. (Default: 0)
 
 * `polygon_threshold=0.0`
 
-Simplify the output geometry before returning. The parameter is the
+Return a simplified version of the output geometry. The parameter is the
 tolerance in degrees with which the geometry may differ from the original
 geometry. Topology is preserved in the result. (Default: 0.0)
 
@@ -154,13 +152,11 @@ address to identify your requests. See Nominatim's [Usage Policy](https://operat
 * `dedupe=[0|1]`
 
 Sometimes you have several objects in OSM identifying the same place or
-object in reality. The simplest case is a street being split in many
+object in reality. The simplest case is a street being split into many
 different OSM ways due to different characteristics. Nominatim will
 attempt to detect such duplicates and only return one match unless
 this parameter is set to 0. (Default: 1)
 
-
-
 * `debug=[0|1]`
 
 Output assorted developer debug information. Data on internals of Nominatim's

docs/api/Status.md

@@ -35,10 +35,16 @@ will return HTTP code 200 and a structure
   {
       "status": 0,
       "message": "OK",
-      "data_updated": "2020-05-04T14:47:00+00:00"
+      "data_updated": "2020-05-04T14:47:00+00:00",
+      "software_version": "3.6.0-0",
+      "database_version": "3.6.0-0"
   }
 ```
 
+The `software_version` field contains the version of Nominatim used to serve
+the API. The `database_version` field contains the version of the data format
+in the database.
+
 On error will also return HTTP status code 200 and a structure with error
 code and message, e.g.
 

docs/data-sources/overview.md

@@ -1,4 +0,0 @@
-# Additional Data Sources
-
-This guide explains how data sources other than OpenStreetMap mentioned in
-the install instructions got obtained and converted.

docs/develop/Development-Environment.md

@@ -0,0 +1,128 @@
+# Setting up Nominatim for Development
+
+This chapter gives an overview how to set up Nominatim for developement
+and how to run tests.
+
+!!! Important
+    This guide assumes that you develop under the latest version of Ubuntu. You
+    can of course also use your favourite distribution. You just might have to
+    adapt the commands below slightly, in particular the commands for installing
+    additional software.
+
+## Installing Nominatim
+
+The first step is to install Nominatim itself. Please follow the installation
+instructions in the [Admin section](../admin/Installation.md). You don't need
+to set up a webserver for development, the webserver that is included with PHP
+is sufficient.
+
+If you want to run Nominatim in a VM via Vagrant, use the default `ubuntu` setup.
+Vagrant's libvirt provider runs out-of-the-box under Ubuntu. You also need to
+install an NFS daemon to enable directory sharing between host and guest. The
+following packages should get you started:
+
+    sudo apt install vagrant vagrant-libvirt libvirt-daemon nfs-kernel-server
+
+## Prerequisites for testing and documentation
+
+The Nominatim test suite consists of behavioural tests (using behave) and
+unit tests (using PHPUnit for PHP code and pytest for Python code).
+It has the following additional requirements:
+
+* [behave test framework](https://behave.readthedocs.io) >= 1.2.6
+* [phpunit](https://phpunit.de) >= 7.3
+* [PHP CodeSniffer](https://github.com/squizlabs/PHP_CodeSniffer)
+* [Pylint](https://pylint.org/) (2.6.0 is used for the CI)
+* [pytest](https://pytest.org)
+
+The documentation is built with mkdocs:
+
+* [mkdocs](https://www.mkdocs.org/) >= 1.1.2
+
+### Installing prerequisites on Ubuntu/Debian
+
+Some of the Python packages require the newest version which is not yet
+available with the current distributions. Therefore it is recommended to
+install pip to get the newest versions.
+
+To install all necessary packages run:
+
+```sh
+sudo apt install php-cgi phpunit php-codesniffer \
+                 python3-pip python3-setuptools python3-dev pylint
+
+pip3 install --user behave mkdocs pytest
+```
+
+The `mkdocs` executable will be located in `.local/bin`. You may have to add
+this directory to your path, for example by running:
+
+```
+echo 'export PATH=~/.local/bin:$PATH' > ~/.profile
+```
+
+If your distribution does not have PHPUnit 7.3+, you can install it (as well
+as CodeSniffer) via composer:
+
+```
+sudo apt-get install composer
+composer global require "squizlabs/php_codesniffer=*"
+composer global require "phpunit/phpunit=8.*"
+```
+
+The binaries are found in `.config/composer/vendor/bin`. You need to add this
+to your PATH as well:
+
+```
+echo 'export PATH=~/.config/composer/vendor/bin:$PATH' > ~/.profile
+```
+
+
+## Executing Tests
+
+All tests are located in the `/test` directory.
+
+To run all tests just go to the build directory and run make:
+
+```sh
+cd build
+make test
+```
+
+For more information about the structure of the tests and how to change and
+extend the test suite, see the [Testing chapter](Testing.md).
+
+## Documentation Pages
+
+The [Nominatim documentation](https://nominatim.org/release-docs/develop/) is
+built using the [MkDocs](https://www.mkdocs.org/) static site generation
+framework. The master branch is automatically deployed every night on
+[https://nominatim.org/release-docs/develop/](https://nominatim.org/release-docs/develop/)
+
+To build the documentation, go to the build directory and run
+
+```
+make doc
+INFO - Cleaning site directory
+INFO - Building documentation to directory: /home/vagrant/build/site-html
+```
+
+This runs `mkdocs build` plus extra transformation of some files and adds
+symlinks (see `CMakeLists.txt` for the exact steps).
+
+Now you can start webserver for local testing
+
+```
+build> mkdocs serve
+[server:296] Serving on http://127.0.0.1:8000
+[handlers:62] Start watching changes
+```
+
+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
+[server:296] Serving on http://0.0.0.0:8088
+[handlers:62] Start watching changes
+```

docs/develop/Documentation.md

@@ -1,36 +0,0 @@
-# Documentation Pages
-
-The [Nominatim documentation](https://nominatim.org/release-docs/develop/) is built using the [MkDocs](https://www.mkdocs.org/) static site generation framework. The master branch is automatically deployed every night on under [https://nominatim.org/release-docs/develop/](https://nominatim.org/release-docs/develop/)
-
-To preview local changes, first install MkDocs
-
-```
-pip3 install --user mkdocs
-```
-
-
-Then go to the build directory and run
-
-```
-make doc
-INFO - Cleaning site directory
-INFO - Building documentation to directory: /home/vagrant/build/site-html
-```
-
-This runs `mkdocs build` plus extra transformation of some files and adds
-symlinks (see `CMakeLists.txt` for the exact steps).
-
-Now you can start webserver for local testing
-
-```
-build> mkdocs serve
-[server:296] Serving on http://127.0.0.1:8000
-[handlers:62] Start watching changes
-```
-
-If you develop inside a Vagrant virtual machine:
-
- * add port forwarding to your Vagrantfile,
-   e.g. `config.vm.network "forwarded_port", guest: 8000, host: 8000`
- * use `mkdocs serve --dev-addr 0.0.0.0:8000` because the default localhost
-   IP does not get forwarded.

docs/develop/Import.md

@@ -1,8 +1,8 @@
 # OSM Data Import
 
-OSM data is initially imported using osm2pgsql. Nominatim uses its own data
-output style 'gazetteer', which differs from the output style created for
-map rendering.
+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
 
@@ -29,7 +29,7 @@ once with `class` of `highway` and once with a `class` of `bridge`. Thus the
 ## Configuring the Import
 
 How tags are interpreted and assigned to the different `place` columns can be
-configured via the import style configuration file (`CONST_Import_style`). This
+configured via the import style configuration file (`NOMINATIM_IMPORT_STYLE`). This
 is a JSON file which contains a list of rules which are matched against every
 tag of every object and then assign the tag its specific role.
 

docs/develop/Postcodes.md

@@ -14,7 +14,7 @@ country's format, e.g. if Swiss postcodes are 4 digits.
 ## Regular updating calculated postcodes
 
 The script to rerun the calculation is
-`build/utils/update.php --calculate-postcodes`
+`nominatim refresh --postcodes`
 and runs once per night on nominatim.openstreetmap.org.
 
 

docs/develop/Ranking.md

@@ -7,24 +7,74 @@ different purposes, which are explained in this chapter.
 ## Search rank
 
 The search rank describes the extent and importance of a place. It is used
-when ranking search result. Simply put, if there are two results for a
+when ranking search results. Simply put, if there are two results for a
 search query which are otherwise equal, then the result with the _lower_
 search rank will be appear higher in the result list.
 
 Search ranks are not so important these days because many well-known
 places use the Wikipedia importance ranking instead.
 
+The following table gives an overview of the kind of features that Nominatim
+expects for each rank:
+
+rank   | typical place types             | extent
+-------|---------------------------------|-------
+1-3    | oceans, continents              | -
+4      | countries                       | -
+5-9    | states, regions, provinces      | -
+10-12  | counties                        | -
+13-16  | cities, municipalities, islands | 15 km
+17-18  | towns, boroughs                 | 4 km
+19     | villages, suburbs               | 2 km
+20     | hamlets, farms, neighbourhoods  |  1 km
+21-25  | isolated dwellings, city blocks | 500 m
+
+The extent column describes how far a feature is assumed to reach when it
+is mapped only as a point. Larger features like countries and states are usually
+available with their exact area in the OpenStreetMap data. That is why no extent
+is given.
+
 ## Address rank
 
 The address rank describes where a place shows up in an address hierarchy.
 Usually only administrative boundaries and place nodes and areas are
-eligible to be part of an address. All other objects have an address rank
-of 0.
+eligible to be part of an address. Places that should not appear in the
+address must have an address rank of 0.
 
-Note that the search rank of a place plays a role in the address computation
-as well. When collecting the places that should make up the address parts
-then only places are taken into account that have a lower address rank than
-the search rank of the base object.
+The following table gives an overview how ranks are mapped to address parts:
+
+ rank        | address part
+-------------|-------------
+ 1-3         | _unused_
+ 4           | country
+ 5-9         | state
+ 10-12       | county
+ 13-16       | city
+ 17-21       | suburb
+ 22-24       | neighbourhood
+ 25          | squares, farms, localities
+ 26-27       | street
+ 28-30       | POI/house number
+
+The country rank 4 usually doesn't show up in the address parts of an object.
+The country is determined indirectly from the country code.
+
+Ranks 5-24 can be assigned more or less freely. They make up the major part
+of the address.
+
+Rank 25 is also an addressing rank but it is special because while it can be
+the parent to a POI with an addr:place of the same name, it cannot be a parent
+to streets. Use it for place features that are technically on the same level
+as a street (e.g. squares, city blocks) or for places that should not normally
+appear in an address unless explicitly tagged so (e.g place=locality which
+should be uninhabited and as such not addressable).
+
+The street ranks 26 and 27 are handled slightly differently. Only one object
+from these ranks shows up in an address.
+
+For POI level objects like shops, buildings or house numbers always use rank 30.
+Ranks 28 is reserved for house number interpolations. 29 is for internal use
+only.
 
 ## Rank configuration
 
@@ -37,9 +87,9 @@ into the database. There are a few hard-coded rules for the assignment:
     * highway nodes
     * landuse that is not an area
 
-Other than that, the ranks can be freely assigned via the JSON file
-defined with `CONST_Address_Level_Config` according to their type and
-the country they are in.
+Other than that, the ranks can be freely assigned via the JSON file according
+to their type and the country they are in. The name of the config file to be
+used can be changed with the setting `NOMINATIM_ADDRESS_LEVEL_CONFIG`.
 
 The address level configuration must consist of an array of configuration
 entries, each containing a tag definition and an optional country array:
@@ -84,7 +134,7 @@ Then the rank is used when no more specific value is found for the given
 key.
 
 Countries and key/value combination may appear in multiple definitions. Just
-make sure that each combination of counrty/key/value appears only once per
+make sure that each combination of country/key/value appears only once per
 file. Otherwise the import will fail with a UNIQUE INDEX constraint violation
 on import.
 

docs/develop/Testing.md

@@ -1,22 +1,10 @@
-This directory contains functional and unit tests for the Nominatim API.
+# Nominatim Test Suite
 
-Prerequisites
-=============
+This chapter describes the tests in the `/test` directory, how they are
+structured and how to extend them. For a quick introduction on how to run
+the tests, see the [Development setup chapter](Development-Environment.md).
 
- * Python 3 (https://www.python.org/)
- * behave test framework >= 1.2.5 (https://github.com/behave/behave)
- * nose (https://nose.readthedocs.org)
- * pytidylib (http://countergram.com/open-source/pytidylib)
- * psycopg2 (http://initd.org/psycopg/)
-
-To get the prerequisites on a a fresh Ubuntu LTS 16.04 run:
-
-     [sudo] apt-get install python3-dev python3-pip python3-psycopg2 python3-tidylib phpunit php-cgi
-     pip3 install --user behave nose
-
-
-Overall structure
-=================
+## Overall structure
 
 There are two kind of tests in this test suite. There are functional tests
 which test the API interface using a BDD test framework and there are unit
@@ -33,15 +21,15 @@ This test directory is sturctured as follows:
   | +-  api        Tests for API endpoints (search, reverse, etc.)
   |
   +-   php         PHP unit tests
+  +-   python      Python unit tests
   +-   scenes      Geometry test data
   +-   testdb      Base data for generating API test database
 ```
 
-PHP Unit Tests
-==============
+## PHP Unit Tests (`test/php`)
 
-Unit tests can be found in the php/ directory and tests selected php functions.
-Very low coverage.
+Unit tests for PHP code can be found in the `php/` directory. They test selected
+PHP functions. Very low coverage.
 
 To execute the test suite run
 
@@ -49,19 +37,39 @@ To execute the test suite run
     UNIT_TEST_DSN='pgsql:dbname=nominatim_unit_tests' phpunit ../
 
 It will read phpunit.xml which points to the library, test path, bootstrap
-strip and set other parameters.
+strip and sets other parameters.
 
 It will use (and destroy) a local database 'nominatim_unit_tests'. You can set
 a different connection string with e.g. UNIT_TEST_DSN='pgsql:dbname=foo_unit_tests'.
 
-BDD Functional Tests
-====================
+## Python Unit Tests (`test/python`)
+
+Unit tests for Python code can be found in the `python/` directory. The goal is
+to have complete coverage of the Python library in `nominatim`.
+
+To execute the tests run
+
+    py.test-3 test/python
+
+or
+
+    pytest test/python
+
+The name of the pytest binary depends on your installation.
+
+## BDD Functional Tests (`test/bdd`)
 
 Functional tests are written as BDD instructions. For more information on
-the philosophy of BDD testing, see http://pythonhosted.org/behave/philosophy.html
+the philosophy of BDD testing, see the
+[Behave manual](http://pythonhosted.org/behave/philosophy.html).
 
-Usage
------
+The following explanation assume that the reader is familiar with the BDD
+notations of features, scenarios and steps.
+
+All possible steps can be found in the `steps` directory and should ideally
+be documented.
+
+### General Usage
 
 To run the functional tests, do
 
@@ -75,65 +83,42 @@ The tests can be configured with a set of environment variables (`behave -D key=
                    the test databases (db tests)
  * `TEST_DB` - name of test database (db tests)
  * `API_TEST_DB` - name of the database containing the API test data (api tests)
+ * `API_TEST_FILE` - OSM file to be imported into the API test database (api tests)
  * `DB_HOST` - (optional) hostname of database host
  * `DB_PORT` - (optional) port of database on host
  * `DB_USER` - (optional) username of database login
  * `DB_PASS` - (optional) password for database login
  * `SERVER_MODULE_PATH` - (optional) path on the Postgres server to Nominatim
                           module shared library file
- * `TEST_SETTINGS_TEMPLATE` - file to write temporary Nominatim settings to
- * `REMOVE_TEMPLATE` - if true, the template database will not be reused during
-                       the next run. Reusing the base templates speeds up tests
-                       considerably but might lead to outdated errors for some
-                       changes in the database layout.
+ * `REMOVE_TEMPLATE` - if true, the template and API database will not be reused
+                       during the next run. Reusing the base templates speeds
+                       up tests considerably but might lead to outdated errors
+                       for some changes in the database layout.
  * `KEEP_TEST_DB` - if true, the test database will not be dropped after a test
                     is finished. Should only be used if one single scenario is
                     run, otherwise the result is undefined.
 
 Logging can be defined through command line parameters of behave itself. Check
-out `behave --help` for details. Also keep an eye out for the 'work-in-progress'
+out `behave --help` for details. Also have a look at the 'work-in-progress'
 feature of behave which comes in handy when writing new tests.
 
-Writing Tests
--------------
-
-The following explanation assume that the reader is familiar with the BDD
-notations of features, scenarios and steps.
-
-All possible steps can be found in the `steps` directory and should ideally
-be documented.
-
 ### API Tests (`test/bdd/api`)
 
 These tests are meant to test the different API endpoints and their parameters.
-They require a preimported test database, which consists of the import of a
-planet extract. A precompiled PBF with the necessary data can be downloaded from
-https://www.nominatim.org/data/test/nominatim-api-testdata.pbf
+They require to import several datasets into a test database. This is normally
+done automatically during setup of the test. The API test database is then
+kept around and reused in subsequent runs of behave. Use `behave -DREMOVE_TEMPLATE`
+to force a reimport of the database.
 
-You need at least 2GB RAM and 10GB discspace.
+The official test dataset is saved in the file `test/testdb/apidb-test-data.pbf`
+and compromises the following data:
 
-The polygons defining the extract can be found in the test/testdb
-directory. There is also a reduced set of wikipedia data for this extract,
-which you need to import as well. For Tiger tests the data of South Dakota
-is required. Get the Tiger files `46*`.
+ * Geofabrik extract of Liechtenstein
+ * extract of Autauga country, Alabama, US (for tests against Tiger data)
+ * additional data from `test/testdb/additional_api_test.data.osm`
 
-    cd Nominatim/data
-    wget https://nominatim.org/data/tiger2018-nominatim-preprocessed.tar.gz
-    tar xvf tiger2018-nominatim-preprocessed.tar.gz --wildcards --no-anchored '46*'
-    rm tiger2018-nominatim-preprocessed.tar.gz
-
-The official test dataset is derived from the 180924 planet. Newer
-planets are likely to work as well but you may see isolated test
-failures where the data has changed. To recreate the input data
-for the test database run:
-
-    wget https://ftp5.gwdg.de/pub/misc/openstreetmap/planet.openstreetmap.org/pbf/planet-180924.osm.pbf
-    osmconvert planet-180924.osm.pbf -B=test/testdb/testdb.polys -o=testdb.pbf
-
-Before importing make sure to add the following to your local settings:
-
-    @define('CONST_Database_DSN', 'pgsql://@/test_api_nominatim');
-    @define('CONST_Wikipedia_Data_Path', CONST_BasePath.'/test/testdb');
+API tests should only be testing the functionality of the website PHP code.
+Most tests should be formulated as BDD DB creation tests (see below) instead.
 
 #### Code Coverage
 
@@ -143,7 +128,7 @@ On Debian/Ubuntu run:
 
     apt-get install php-codecoverage php-xdebug
 
-The run the API tests as follows:
+Then run the API tests as follows:
 
     behave api -DPHPCOV=<coverage output dir>
 
@@ -152,11 +137,11 @@ the [phpcov](https://github.com/sebastianbergmann/phpcov) tool:
 
     phpcov merge --html=<report output dir> <coverage output dir>
 
-### Indexing Tests (`test/bdd/db`)
+### DB Creation Tests (`test/bdd/db`)
 
 These tests check the import and update of the Nominatim database. They do not
 test the correctness of osm2pgsql. Each test will write some data into the `place`
-table (and optionally `the planet_osm_*` tables if required) and then run
+table (and optionally the `planet_osm_*` tables if required) and then run
 Nominatim's processing functions on that.
 
 These tests need to create their own test databases. By default they will be
@@ -167,4 +152,8 @@ needs superuser rights for postgres.
 ### Import Tests (`test/bdd/osm2pgsql`)
 
 These tests check that data is imported correctly into the place table. They
-use the same template database as the Indexing tests, so the same remarks apply.
+use the same template database as the DB Creation tests, so the same remarks apply.
+
+Note that most testing of the gazetteer output of osm2pgsql is done in the tests
+of osm2pgsql itself. The BDD tests are just there to ensure compatibility of
+the osm2pgsql and Nominatim code.

docs/develop/data-sources.md

@@ -0,0 +1,34 @@
+# Additional Data Sources
+
+This guide explains how data sources other than OpenStreetMap mentioned in
+the install instructions got obtained and converted.
+
+## Country grid
+
+Nominatim uses pre-generated country borders data. In case one imports only
+a subset of a country. And to assign each place a partition. Nominatim
+database tables are split into partitions for performance.
+
+More details in [osm-search/country-grid-data](https://github.com/osm-search/country-grid-data).
+
+## US Census TIGER
+
+For the United States you can choose to import additonal street-level data.
+The data isn't mixed into OSM data but queried as fallback when no OSM
+result can be found.
+
+More details in [osm-search/TIGER-data](https://github.com/osm-search/TIGER-data).
+
+## GB postcodes
+
+For Great Britain you can choose to import Royalmail postcode centroids.
+
+More details in [osm-search/gb-postcode-data](https://github.com/osm-search/gb-postcode-data).
+
+
+## Wikipedia & Wikidata rankings
+
+Nominatim can import "importance" data of place names. This greatly
+improves ranking of results.
+
+More details in [osm-search/wikipedia-wikidata](https://github.com/osm-search/wikipedia-wikidata).

docs/develop/overview.md

@@ -9,14 +9,14 @@ the address computation and the search frontend.
 The __data import__ stage reads the raw OSM data and extracts all information
 that is useful for geocoding. This part is done by osm2pgsql, the same tool
 that can also be used to import a rendering database. It uses the special
-gazetteer output plugin in `osm2pgsql/output-gazetter.[ch]pp`. The result of
+gazetteer output plugin in `osm2pgsql/src/output-gazetter.[ch]pp`. The result of
 the import can be found in the database table `place`.
 
 The __address computation__ or __indexing__ stage takes the data from `place`
 and adds additional information needed for geocoding. It ranks the places by
 importance, links objects that belong together and computes addresses and
 the search index. Most of this work is done in PL/pgSQL via database triggers
-and can be found in the file `sql/functions.sql`.
+and can be found in the files in the `sql/functions/` directory.
 
 The __search frontend__ implements the actual API. It takes search
 and reverse geocoding queries from the user, looks up the data and

docs/extra.css

@@ -1,3 +1,15 @@
 .toctree-l3 {
     display: none!important
 }
+
+table {
+    margin-bottom: 12pt
+}
+
+th, td {
+    padding: 1pt 12pt;
+}
+
+th {
+    background-color: #eee;
+}

docs/mkdocs.yml

@@ -16,22 +16,23 @@ pages:
         - 'FAQ': 'api/Faq.md'
     - 'Administration Guide':
         - 'Basic Installation': 'admin/Installation.md'
-        - 'Importing and Updating' : 'admin/Import-and-Update.md'
+        - 'Import' : 'admin/Import.md'
+        - 'Update' : 'admin/Update.md'
+        - 'Deploy' : 'admin/Deployment.md'
+        - 'Customize Imports' : 'admin/Customization.md'
+        - 'Tokenizers' : 'admin/Tokenizers.md'
+        - 'Nominatim UI'  : 'admin/Setup-Nominatim-UI.md'
         - 'Advanced Installations' : 'admin/Advanced-Installations.md'
         - 'Migration from older Versions' : 'admin/Migration.md'
         - 'Troubleshooting' : 'admin/Faq.md'
     - 'Developers Guide':
-        - 'Overview' : 'develop/overview.md'
+        - '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'
-        - 'Documentation' : 'develop/Documentation.md'
-    - 'External Data Sources':
-        - 'Overview' : 'data-sources/overview.md'
-        - 'US Census (Tiger)': 'data-sources/US-Tiger.md'
-        - 'GB Postcodes': 'data-sources/GB-Postcodes.md'
-        - 'Country Grid': 'data-sources/Country-Grid.md'
-        - 'Wikipedia & Wikidata': 'data-sources/Wikipedia-Wikidata.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'

lib-php/AddressDetails.php

@@ -2,7 +2,7 @@
 
 namespace Nominatim;
 
-require_once(CONST_BasePath.'/lib/ClassTypes.php');
+require_once(CONST_LibDir.'/ClassTypes.php');
 
 /**
  * Detailed list of address parts for a single result
@@ -61,7 +61,7 @@ class AddressDetails
         return join(', ', $aParts);
     }
 
-    public function getAddressNames($sCountry = null)
+    public function getAddressNames()
     {
         $aAddress = array();
 
@@ -79,13 +79,11 @@ class AddressDetails
                 $sName = $aLine['housenumber'];
             }
 
-            if (isset($sName)) {
-                $sTypeLabel = strtolower(str_replace(' ', '_', $sTypeLabel));
-                if (!isset($aAddress[$sTypeLabel])
-                    || $aLine['class'] == 'place'
-                ) {
-                    $aAddress[$sTypeLabel] = $sName;
-                }
+            if (isset($sName)
+                && (!isset($aAddress[$sTypeLabel])
+                    || $aLine['class'] == 'place')
+            ) {
+                $aAddress[$sTypeLabel] = $sName;
             }
         }
 

lib-php/ClassTypes.php

@@ -18,6 +18,8 @@ function getLabelTag($aPlace, $sCountry = null)
         $sLabel = $aPlace['place_type'];
     } elseif ($aPlace['class'] == 'boundary' && $aPlace['type'] == 'administrative') {
         $sLabel = getBoundaryLabel($iRank/2, $sCountry);
+    } elseif ($aPlace['type'] == 'postal_code') {
+        $sLabel = 'postcode';
     } elseif ($iRank < 26) {
         $sLabel = $aPlace['type'];
     } elseif ($iRank < 28) {
@@ -84,7 +86,8 @@ function getBoundaryLabel($iAdminLevel, $sCountry, $sFallback = 'Administrative'
                                            8 => 'City',
                                            9 => 'City District',
                                            10 => 'Suburb',
-                                           11 => 'Neighbourhood'
+                                           11 => 'Neighbourhood',
+                                           12 => 'City Block'
                                           ),
                              'no' => array (
                                       3 => 'State',
@@ -249,13 +252,17 @@ function getIcon($aPlace)
  */
 function getIconFile($aPlace)
 {
+    if (CONST_MapIcon_URL === false) {
+        return null;
+    }
+
     $sIcon = getIcon($aPlace);
 
     if (!isset($sIcon)) {
         return null;
     }
 
-    return CONST_Website_BaseURL.'images/mapicons/'.$sIcon.'.p.20.png';
+    return CONST_MapIcon_URL.'/'.$sIcon.'.p.20.png';
 }
 
 /**
@@ -272,6 +279,7 @@ function getImportance($aPlace)
 
     if ($aWithImportance === null) {
         $aWithImportance = array_flip(array(
+                                           'boundary:administrative',
                                            'place:country',
                                            'place:state',
                                            'place:province',

lib-php/DB.php

@@ -2,7 +2,7 @@
 
 namespace Nominatim;
 
-require_once(CONST_BasePath.'/lib/DatabaseError.php');
+require_once(CONST_LibDir.'/DatabaseError.php');
 
 /**
  * Uses PDO to access the database specified in the CONST_Database_DSN
@@ -12,9 +12,9 @@ class DB
 {
     protected $connection;
 
-    public function __construct($sDSN = CONST_Database_DSN)
+    public function __construct($sDSN = null)
     {
-        $this->sDSN = $sDSN;
+        $this->sDSN = $sDSN ?? getSetting('DATABASE_DSN');
     }
 
     public function connect($bNew = false, $bPersistent = true)
@@ -39,7 +39,9 @@ class DB
         $conn->exec("SET DateStyle TO 'sql,european'");
         $conn->exec("SET client_encoding TO 'utf-8'");
         $iMaxExecution = ini_get('max_execution_time');
-        if ($iMaxExecution > 0) $conn->setAttribute(\PDO::ATTR_TIMEOUT, $iMaxExecution); // seconds
+        if ($iMaxExecution > 0) {
+            $conn->setAttribute(\PDO::ATTR_TIMEOUT, $iMaxExecution); // seconds
+        }
 
         $this->connection = $conn;
         return true;
@@ -95,7 +97,9 @@ class DB
         try {
             $stmt = $this->getQueryStatement($sSQL, $aInputVars, $sErrMessage);
             $row = $stmt->fetch(\PDO::FETCH_NUM);
-            if ($row === false) return false;
+            if ($row === false) {
+                return false;
+            }
         } catch (\PDOException $e) {
             throw new \Nominatim\DatabaseError($sErrMessage, 500, null, $e, $sSQL);
         }
@@ -240,16 +244,6 @@ class DB
         return ($this->getOne($sSQL, array(':tablename' => $sTableName)) == 1);
     }
 
-    /**
-    * Returns a list of table names in the database
-    *
-    * @return array[]
-    */
-    public function getListOfTables()
-    {
-        return $this->getCol("SELECT tablename FROM pg_tables WHERE schemaname='public'");
-    }
-
     /**
      * Deletes a table. Returns true if deleted or didn't exist.
      *
@@ -262,76 +256,6 @@ class DB
         return $this->exec('DROP TABLE IF EXISTS '.$sTableName.' CASCADE') == 0;
     }
 
-    /**
-    * Check if an index exists in the database. Optional filtered by tablename
-    *
-    * @param string  $sTableName
-    *
-    * @return boolean
-    */
-    public function indexExists($sIndexName, $sTableName = null)
-    {
-        return in_array($sIndexName, $this->getListOfIndices($sTableName));
-    }
-
-    /**
-    * Returns a list of index names in the database, optional filtered by tablename
-    *
-    * @param string  $sTableName
-    *
-    * @return array
-    */
-    public function getListOfIndices($sTableName = null)
-    {
-        //  table_name            | index_name                      | column_name
-        // -----------------------+---------------------------------+--------------
-        //  country_name          | idx_country_name_country_code   | country_code
-        //  country_osm_grid      | idx_country_osm_grid_geometry   | geometry
-        //  import_polygon_delete | idx_import_polygon_delete_osmid | osm_id
-        //  import_polygon_delete | idx_import_polygon_delete_osmid | osm_type
-        //  import_polygon_error  | idx_import_polygon_error_osmid  | osm_id
-        //  import_polygon_error  | idx_import_polygon_error_osmid  | osm_type
-        $sSql = <<< END
-SELECT
-    t.relname as table_name,
-    i.relname as index_name,
-    a.attname as column_name
-FROM
-    pg_class t,
-    pg_class i,
-    pg_index ix,
-    pg_attribute a
-WHERE
-    t.oid = ix.indrelid
-    and i.oid = ix.indexrelid
-    and a.attrelid = t.oid
-    and a.attnum = ANY(ix.indkey)
-    and t.relkind = 'r'
-    and i.relname NOT LIKE 'pg_%'
-    FILTERS
- ORDER BY
-    t.relname,
-    i.relname,
-    a.attname
-END;
-
-        $aRows = null;
-        if ($sTableName) {
-            $sSql = str_replace('FILTERS', 'and t.relname = :tablename', $sSql);
-            $aRows = $this->getAll($sSql, array(':tablename' => $sTableName));
-        } else {
-            $sSql = str_replace('FILTERS', '', $sSql);
-            $aRows = $this->getAll($sSql);
-        }
-
-        $aIndexNames = array_unique(array_map(function ($aRow) {
-            return $aRow['index_name'];
-        }, $aRows));
-        sort($aIndexNames);
-
-        return $aIndexNames;
-    }
-
     /**
      * Tries to connect to the database but on failure doesn't throw an exception.
      *
@@ -386,9 +310,13 @@ END;
         if (preg_match('/^pgsql:(.+)$/', $sDSN, $aMatches)) {
             foreach (explode(';', $aMatches[1]) as $sKeyVal) {
                 list($sKey, $sVal) = explode('=', $sKeyVal, 2);
-                if ($sKey == 'host') $sKey = 'hostspec';
-                if ($sKey == 'dbname') $sKey = 'database';
-                if ($sKey == 'user') $sKey = 'username';
+                if ($sKey == 'host') {
+                    $sKey = 'hostspec';
+                } elseif ($sKey == 'dbname') {
+                    $sKey = 'database';
+                } elseif ($sKey == 'user') {
+                    $sKey = 'username';
+                }
                 $aInfo[$sKey] = $sVal;
             }
         }

lib-php/DatabaseError.php

@@ -5,7 +5,7 @@ namespace Nominatim;
 class DatabaseError extends \Exception
 {
 
-    public function __construct($message, $code = 500, Exception $previous = null, $oPDOErr, $sSql = null)
+    public function __construct($message, $code, $previous, $oPDOErr, $sSql = null)
     {
         parent::__construct($message, $code, $previous);
         // https://secure.php.net/manual/en/class.pdoexception.php

lib-php/DebugHtml.php

@@ -78,7 +78,7 @@ class Debug
         echo '<th>Address Tokens</th><th>Address Not</th>';
         echo '<th>country</th><th>operator</th>';
         echo '<th>class</th><th>type</th><th>postcode</th><th>housenumber</th></tr>';
-        foreach ($aSearches as $iRank => $aRankedSet) {
+        foreach ($aSearches as $aRankedSet) {
             foreach ($aRankedSet as $aRow) {
                 $aRow->dumpAsHtmlTableRow($aWordsIDs);
             }

lib-php/Geocode.php

@@ -2,23 +2,25 @@
 
 namespace Nominatim;
 
-require_once(CONST_BasePath.'/lib/PlaceLookup.php');
-require_once(CONST_BasePath.'/lib/Phrase.php');
-require_once(CONST_BasePath.'/lib/ReverseGeocode.php');
-require_once(CONST_BasePath.'/lib/SearchDescription.php');
-require_once(CONST_BasePath.'/lib/SearchContext.php');
-require_once(CONST_BasePath.'/lib/TokenList.php');
+require_once(CONST_LibDir.'/PlaceLookup.php');
+require_once(CONST_LibDir.'/Phrase.php');
+require_once(CONST_LibDir.'/ReverseGeocode.php');
+require_once(CONST_LibDir.'/SearchDescription.php');
+require_once(CONST_LibDir.'/SearchContext.php');
+require_once(CONST_LibDir.'/SearchPosition.php');
+require_once(CONST_LibDir.'/TokenList.php');
+require_once(CONST_TokenizerDir.'/tokenizer.php');
 
 class Geocode
 {
     protected $oDB;
 
     protected $oPlaceLookup;
+    protected $oTokenizer;
 
     protected $aLangPrefOrder = array();
 
     protected $aExcludePlaceIDs = array();
-    protected $bReverseInPlan = false;
 
     protected $iLimit = 20;
     protected $iFinalLimit = 10;
@@ -42,28 +44,12 @@ class Geocode
     protected $sQuery = false;
     protected $aStructuredQuery = false;
 
-    protected $oNormalizer = null;
-
 
     public function __construct(&$oDB)
     {
         $this->oDB =& $oDB;
         $this->oPlaceLookup = new PlaceLookup($this->oDB);
-        $this->oNormalizer = \Transliterator::createFromRules(CONST_Term_Normalization_Rules);
-    }
-
-    private function normTerm($sTerm)
-    {
-        if ($this->oNormalizer === null) {
-            return $sTerm;
-        }
-
-        return $this->oNormalizer->transliterate($sTerm);
-    }
-
-    public function setReverseInPlan($bReverse)
-    {
-        $this->bReverseInPlan = $bReverse;
+        $this->oTokenizer = new \Nominatim\Tokenizer($this->oDB);
     }
 
     public function setLanguagePreference($aLangPref)
@@ -85,7 +71,9 @@ class Geocode
             $aParams['exclude_place_ids'] = implode(',', $this->aExcludePlaceIDs);
         }
 
-        if ($this->bBoundedSearch) $aParams['bounded'] = '1';
+        if ($this->bBoundedSearch) {
+            $aParams['bounded'] = '1';
+        }
 
         if ($this->aCountryCodes) {
             $aParams['countrycodes'] = implode(',', $this->aCountryCodes);
@@ -100,8 +88,11 @@ class Geocode
 
     public function setLimit($iLimit = 10)
     {
-        if ($iLimit > 50) $iLimit = 50;
-        if ($iLimit < 1) $iLimit = 1;
+        if ($iLimit > 50) {
+            $iLimit = 50;
+        } elseif ($iLimit < 1) {
+            $iLimit = 1;
+        }
 
         $this->iFinalLimit = $iLimit;
         $this->iLimit = $iLimit + min($iLimit, 10);
@@ -196,18 +187,24 @@ class Geocode
         if ($sExcluded) {
             foreach ($sExcluded as $iExcludedPlaceID) {
                 $iExcludedPlaceID = (int)$iExcludedPlaceID;
-                if ($iExcludedPlaceID)
+                if ($iExcludedPlaceID) {
                     $aExcludePlaceIDs[$iExcludedPlaceID] = $iExcludedPlaceID;
+                }
             }
 
-            if (isset($aExcludePlaceIDs))
+            if (isset($aExcludePlaceIDs)) {
                 $this->aExcludePlaceIDs = $aExcludePlaceIDs;
+            }
         }
 
         // Only certain ranks of feature
         $sFeatureType = $oParams->getString('featureType');
-        if (!$sFeatureType) $sFeatureType = $oParams->getString('featuretype');
-        if ($sFeatureType) $this->setFeatureType($sFeatureType);
+        if (!$sFeatureType) {
+            $sFeatureType = $oParams->getString('featuretype');
+        }
+        if ($sFeatureType) {
+            $this->setFeatureType($sFeatureType);
+        }
 
         // Country code list
         $sCountries = $oParams->getStringList('countrycodes');
@@ -217,8 +214,9 @@ class Geocode
                     $aCountries[] = strtolower($sCountryCode);
                 }
             }
-            if (isset($aCountries))
+            if (isset($aCountries)) {
                 $this->aCountryCodes = $aCountries;
+            }
         }
 
         $aViewbox = $oParams->getStringList('viewboxlbrt');
@@ -262,7 +260,6 @@ class Geocode
                 $oParams->getString('country'),
                 $oParams->getString('postalcode')
             );
-            $this->setReverseInPlan(false);
         } else {
             $this->setQuery($sQuery);
         }
@@ -271,13 +268,17 @@ class Geocode
     public function loadStructuredAddressElement($sValue, $sKey, $iNewMinAddressRank, $iNewMaxAddressRank, $aItemListValues)
     {
         $sValue = trim($sValue);
-        if (!$sValue) return false;
+        if (!$sValue) {
+            return false;
+        }
         $this->aStructuredQuery[$sKey] = $sValue;
         if ($this->iMinAddressRank == 0 && $this->iMaxAddressRank == 30) {
             $this->iMinAddressRank = $iNewMinAddressRank;
             $this->iMaxAddressRank = $iNewMaxAddressRank;
         }
-        if ($aItemListValues) $this->aAddressRankList = array_merge($this->aAddressRankList, $aItemListValues);
+        if ($aItemListValues) {
+            $this->aAddressRankList = array_merge($this->aAddressRankList, $aItemListValues);
+        }
         return true;
     }
 
@@ -311,11 +312,11 @@ class Geocode
 
     public function fallbackStructuredQuery()
     {
-        if (!$this->aStructuredQuery) return false;
-
         $aParams = $this->aStructuredQuery;
 
-        if (count($aParams) == 1) return false;
+        if (!$aParams || count($aParams) == 1) {
+            return false;
+        }
 
         $aOrderToFallback = array('postalcode', 'street', 'city', 'county', 'state');
 
@@ -330,7 +331,7 @@ class Geocode
         return false;
     }
 
-    public function getGroupedSearches($aSearches, $aPhrases, $oValidTokens, $bIsStructured)
+    public function getGroupedSearches($aSearches, $aPhrases, $oValidTokens)
     {
         /*
              Calculate all searches using oValidTokens i.e.
@@ -345,52 +346,26 @@ class Geocode
          */
         foreach ($aPhrases as $iPhrase => $oPhrase) {
             $aNewPhraseSearches = array();
-            $sPhraseType = $bIsStructured ? $oPhrase->getPhraseType() : '';
+            $oPosition = new SearchPosition(
+                $oPhrase->getPhraseType(),
+                $iPhrase,
+                count($aPhrases)
+            );
 
             foreach ($oPhrase->getWordSets() as $aWordset) {
                 $aWordsetSearches = $aSearches;
 
                 // Add all words from this wordset
                 foreach ($aWordset as $iToken => $sToken) {
-                    //echo "<br><b>$sToken</b>";
                     $aNewWordsetSearches = array();
+                    $oPosition->setTokenPosition($iToken, count($aWordset));
 
                     foreach ($aWordsetSearches as $oCurrentSearch) {
-                        //echo "<i>";
-                        //var_dump($oCurrentSearch);
-                        //echo "</i>";
-
-                        // Tokens with full name matches.
-                        foreach ($oValidTokens->get(' '.$sToken) as $oSearchTerm) {
-                            $aNewSearches = $oCurrentSearch->extendWithFullTerm(
-                                $oSearchTerm,
-                                $oValidTokens->contains($sToken)
-                                  && strpos($sToken, ' ') === false,
-                                $sPhraseType,
-                                $iToken == 0 && $iPhrase == 0,
-                                $iPhrase == 0,
-                                $iToken + 1 == count($aWordset)
-                                  && $iPhrase + 1 == count($aPhrases)
-                            );
-
-                            foreach ($aNewSearches as $oSearch) {
-                                if ($oSearch->getRank() < $this->iMaxRank) {
-                                    $aNewWordsetSearches[] = $oSearch;
-                                }
-                            }
-                        }
-                        // Look for partial matches.
-                        // Note that there is no point in adding country terms here
-                        // because country is omitted in the address.
-                        if ($sPhraseType != 'country') {
-                            // Allow searching for a word - but at extra cost
-                            foreach ($oValidTokens->get($sToken) as $oSearchTerm) {
-                                $aNewSearches = $oCurrentSearch->extendWithPartialTerm(
-                                    $sToken,
-                                    $oSearchTerm,
-                                    $bIsStructured,
-                                    $iPhrase,
-                                    $oValidTokens->get(' '.$sToken)
+                        foreach ($oValidTokens->get($sToken) as $oSearchTerm) {
+                            if ($oSearchTerm->isExtendable($oCurrentSearch, $oPosition)) {
+                                $aNewSearches = $oSearchTerm->extendSearch(
+                                    $oCurrentSearch,
+                                    $oPosition
                                 );
 
                                 foreach ($aNewSearches as $oSearch) {
@@ -405,7 +380,6 @@ class Geocode
                     usort($aNewWordsetSearches, array('Nominatim\SearchDescription', 'bySearchRank'));
                     $aWordsetSearches = array_slice($aNewWordsetSearches, 0, 50);
                 }
-                //var_Dump('<hr>',count($aWordsetSearches)); exit;
 
                 $aNewPhraseSearches = array_merge($aNewPhraseSearches, $aNewWordsetSearches);
                 usort($aNewPhraseSearches, array('Nominatim\SearchDescription', 'bySearchRank'));
@@ -413,8 +387,11 @@ class Geocode
                 $aSearchHash = array();
                 foreach ($aNewPhraseSearches as $iSearch => $aSearch) {
                     $sHash = serialize($aSearch);
-                    if (isset($aSearchHash[$sHash])) unset($aNewPhraseSearches[$iSearch]);
-                    else $aSearchHash[$sHash] = 1;
+                    if (isset($aSearchHash[$sHash])) {
+                        unset($aNewPhraseSearches[$iSearch]);
+                    } else {
+                        $aSearchHash[$sHash] = 1;
+                    }
                 }
 
                 $aNewPhraseSearches = array_slice($aNewPhraseSearches, 0, 50);
@@ -435,10 +412,12 @@ class Geocode
 
             $iSearchCount = 0;
             $aSearches = array();
-            foreach ($aGroupedSearches as $iScore => $aNewSearches) {
+            foreach ($aGroupedSearches as $aNewSearches) {
                 $iSearchCount += count($aNewSearches);
                 $aSearches = array_merge($aSearches, $aNewSearches);
-                if ($iSearchCount > 50) break;
+                if ($iSearchCount > 50) {
+                    break;
+                }
             }
         }
 
@@ -495,7 +474,9 @@ class Geocode
     public function lookup()
     {
         Debug::newFunction('Geocode::lookup');
-        if (!$this->sQuery && !$this->aStructuredQuery) return array();
+        if (!$this->sQuery && !$this->aStructuredQuery) {
+            return array();
+        }
 
         Debug::printDebugArray('Geocode', $this);
 
@@ -517,16 +498,10 @@ class Geocode
         if ($this->aCountryCodes) {
             $oCtx->setCountryList($this->aCountryCodes);
         }
+        $this->oTokenizer->setCountryRestriction($this->aCountryCodes);
 
         Debug::newSection('Query Preprocessing');
 
-        $sNormQuery = $this->normTerm($this->sQuery);
-        Debug::printVar('Normalized query', $sNormQuery);
-
-        $sLanguagePrefArraySQL = $this->oDB->getArraySQL(
-            $this->oDB->getDBQuotedList($this->aLangPrefOrder)
-        );
-
         $sQuery = $this->sQuery;
         if (!preg_match('//u', $sQuery)) {
             userError('Query string is not UTF-8 encoded.');
@@ -576,121 +551,62 @@ class Geocode
             }
 
             if ($sSpecialTerm && !$aSearches[0]->hasOperator()) {
-                $sSpecialTerm = pg_escape_string($sSpecialTerm);
-                $sToken = $this->oDB->getOne(
-                    'SELECT make_standard_name(:term)',
-                    array(':term' => $sSpecialTerm),
-                    'Cannot decode query. Wrong encoding?'
-                );
-                $sSQL = 'SELECT class, type FROM word ';
-                $sSQL .= '   WHERE word_token in (\' '.$sToken.'\')';
-                $sSQL .= '   AND class is not null AND class not in (\'place\')';
+                $aTokens = $this->oTokenizer->tokensForSpecialTerm($sSpecialTerm);
 
-                Debug::printSQL($sSQL);
-                $aSearchWords = $this->oDB->getAll($sSQL);
-                $aNewSearches = array();
-                foreach ($aSearches as $oSearch) {
-                    foreach ($aSearchWords as $aSearchTerm) {
-                        $oNewSearch = clone $oSearch;
-                        $oNewSearch->setPoiSearch(
-                            Operator::TYPE,
-                            $aSearchTerm['class'],
-                            $aSearchTerm['type']
-                        );
-                        $aNewSearches[] = $oNewSearch;
+                if (!empty($aTokens)) {
+                    $aNewSearches = array();
+                    $oPosition = new SearchPosition('', 0, 1);
+                    $oPosition->setTokenPosition(0, 1);
+
+                    foreach ($aSearches as $oSearch) {
+                        foreach ($aTokens as $oToken) {
+                            $aNewSearches = array_merge(
+                                $aNewSearches,
+                                $oToken->extendSearch($oSearch, $oPosition)
+                            );
+                        }
                     }
+                    $aSearches = $aNewSearches;
                 }
-                $aSearches = $aNewSearches;
             }
 
             // Split query into phrases
             // Commas are used to reduce the search space by indicating where phrases split
+            $aPhrases = array();
             if ($this->aStructuredQuery) {
-                $aInPhrases = $this->aStructuredQuery;
-                $bStructuredPhrases = true;
+                foreach ($this->aStructuredQuery as $iPhrase => $sPhrase) {
+                    $aPhrases[] = new Phrase($sPhrase, $iPhrase);
+                }
             } else {
-                $aInPhrases = explode(',', $sQuery);
-                $bStructuredPhrases = false;
+                foreach (explode(',', $sQuery) as $sPhrase) {
+                    $aPhrases[] = new Phrase($sPhrase, '');
+                }
             }
 
             Debug::printDebugArray('Search context', $oCtx);
             Debug::printDebugArray('Base search', empty($aSearches) ? null : $aSearches[0]);
-            Debug::printVar('Final query phrases', $aInPhrases);
 
-            // Convert each phrase to standard form
-            // Create a list of standard words
-            // Get all 'sets' of words
-            // Generate a complete list of all
             Debug::newSection('Tokenization');
-            $aTokens = array();
-            $aPhrases = array();
-            foreach ($aInPhrases as $iPhrase => $sPhrase) {
-                $sPhrase = $this->oDB->getOne(
-                    'SELECT make_standard_name(:phrase)',
-                    array(':phrase' => $sPhrase),
-                    'Cannot normalize query string (is it a UTF-8 string?)'
-                );
-                if (trim($sPhrase)) {
-                    $oPhrase = new Phrase($sPhrase, is_string($iPhrase) ? $iPhrase : '');
-                    $oPhrase->addTokens($aTokens);
-                    $aPhrases[] = $oPhrase;
-                }
-            }
+            $oValidTokens = $this->oTokenizer->extractTokensFromPhrases($aPhrases);
 
-            Debug::printVar('Tokens', $aTokens);
+            if ($oValidTokens->count() > 0) {
+                $oCtx->setFullNameWords($oValidTokens->getFullWordIDs());
 
-            $oValidTokens = new TokenList();
-
-            if (!empty($aTokens)) {
-                $sSQL = 'SELECT word_id, word_token, word, class, type, country_code, operator, search_name_count';
-                $sSQL .= ' FROM word ';
-                $sSQL .= ' WHERE word_token in ('.join(',', $this->oDB->getDBQuotedList($aTokens)).')';
-
-                Debug::printSQL($sSQL);
-
-                $oValidTokens->addTokensFromDB(
-                    $this->oDB,
-                    $aTokens,
-                    $this->aCountryCodes,
-                    $sNormQuery,
-                    $this->oNormalizer
-                );
-
-                // Try more interpretations for Tokens that could not be matched.
-                foreach ($aTokens as $sToken) {
-                    if ($sToken[0] == ' ' && !$oValidTokens->contains($sToken)) {
-                        if (preg_match('/^ ([0-9]{5}) [0-9]{4}$/', $sToken, $aData)) {
-                            // US ZIP+4 codes - merge in the 5-digit ZIP code
-                            $oValidTokens->addToken(
-                                $sToken,
-                                new Token\Postcode(null, $aData[1], 'us')
-                            );
-                        } elseif (preg_match('/^ [0-9]+$/', $sToken)) {
-                            // Unknown single word token with a number.
-                            // Assume it is a house number.
-                            $oValidTokens->addToken(
-                                $sToken,
-                                new Token\HouseNumber(null, trim($sToken))
-                            );
-                        }
-                    }
-                }
+                $aPhrases = array_filter($aPhrases, function ($oPhrase) {
+                    return $oPhrase->getWordSets() !== null;
+                });
 
                 // Any words that have failed completely?
                 // TODO: suggestions
 
                 Debug::printGroupTable('Valid Tokens', $oValidTokens->debugInfo());
-
-                foreach ($aPhrases as $oPhrase) {
-                    $oPhrase->computeWordSets($oValidTokens);
-                }
                 Debug::printDebugTable('Phrases', $aPhrases);
 
                 Debug::newSection('Search candidates');
 
-                $aGroupedSearches = $this->getGroupedSearches($aSearches, $aPhrases, $oValidTokens, $bStructuredPhrases);
+                $aGroupedSearches = $this->getGroupedSearches($aSearches, $aPhrases, $oValidTokens);
 
-                if ($this->bReverseInPlan) {
+                if (!$this->aStructuredQuery) {
                     // Reverse phrase array and also reverse the order of the wordsets in
                     // the first and final phrase. Don't bother about phrases in the middle
                     // because order in the address doesn't matter.
@@ -699,7 +615,7 @@ class Geocode
                     if (count($aPhrases) > 1) {
                         $aPhrases[count($aPhrases)-1]->invertWordSets();
                     }
-                    $aReverseGroupedSearches = $this->getGroupedSearches($aSearches, $aPhrases, $oValidTokens, false);
+                    $aReverseGroupedSearches = $this->getGroupedSearches($aSearches, $aPhrases, $oValidTokens);
 
                     foreach ($aGroupedSearches as $aSearches) {
                         foreach ($aSearches as $aSearch) {
@@ -718,7 +634,9 @@ class Geocode
                 $aGroupedSearches = array();
                 foreach ($aSearches as $aSearch) {
                     if ($aSearch->getRank() < $this->iMaxRank) {
-                        if (!isset($aGroupedSearches[$aSearch->getRank()])) $aGroupedSearches[$aSearch->getRank()] = array();
+                        if (!isset($aGroupedSearches[$aSearch->getRank()])) {
+                            $aGroupedSearches[$aSearch->getRank()] = array();
+                        }
                         $aGroupedSearches[$aSearch->getRank()][] = $aSearch;
                     }
                 }
@@ -732,7 +650,9 @@ class Geocode
                     $sHash = serialize($aSearch);
                     if (isset($aSearchHash[$sHash])) {
                         unset($aGroupedSearches[$iGroup][$iSearch]);
-                        if (empty($aGroupedSearches[$iGroup])) unset($aGroupedSearches[$iGroup]);
+                        if (empty($aGroupedSearches[$iGroup])) {
+                            unset($aGroupedSearches[$iGroup]);
+                        }
                     } else {
                         $aSearchHash[$sHash] = 1;
                     }
@@ -776,20 +696,27 @@ class Geocode
                         }
                     }
 
-                    if ($iQueryLoop > 20) break;
+                    if ($iQueryLoop > 20) {
+                        break;
+                    }
                 }
 
                 if (!empty($aResults)) {
                     $aSplitResults = Result::splitResults($aResults);
                     Debug::printVar('Split results', $aSplitResults);
-                    if ($iGroupLoop <= 4 && empty($aSplitResults['tail'])
-                        && reset($aSplitResults['head'])->iResultRank > 0) {
+                    if ($iGroupLoop <= 4
+                        && reset($aSplitResults['head'])->iResultRank > 0
+                        && $iGroupedRank !== array_key_last($aGroupedSearches)) {
                         // Haven't found an exact match for the query yet.
                         // Therefore add result from the next group level.
                         $aNextResults = $aSplitResults['head'];
                         foreach ($aNextResults as $oRes) {
                             $oRes->iResultRank--;
                         }
+                        foreach ($aSplitResults['tail'] as $oRes) {
+                            $oRes->iResultRank--;
+                            $aNextResults[$oRes->iId] = $oRes;
+                        }
                         $aResults = array();
                     } else {
                         $aResults = $aSplitResults['head'];
@@ -837,7 +764,6 @@ class Geocode
                     foreach ($aResults as $oResult) {
                         if (($this->iMaxAddressRank == 30 &&
                              ($oResult->iTable == Result::TABLE_OSMLINE
-                              || $oResult->iTable == Result::TABLE_AUX
                               || $oResult->iTable == Result::TABLE_TIGER))
                             || in_array($oResult->iId, $aFilteredIDs)
                         ) {
@@ -847,9 +773,9 @@ class Geocode
                     $aResults = $tempIDs;
                 }
 
-                if (!empty($aResults)) break;
-                if ($iGroupLoop > 4) break;
-                if ($iQueryLoop > 30) break;
+                if (!empty($aResults) || $iGroupLoop > 4 || $iQueryLoop > 30) {
+                    break;
+                }
             }
         } else {
             // Just interpret as a reverse geocode
@@ -867,10 +793,8 @@ class Geocode
 
         // No results? Done
         if (empty($aResults)) {
-            if ($this->bFallback) {
-                if ($this->fallbackStructuredQuery()) {
-                    return $this->lookup();
-                }
+            if ($this->bFallback && $this->fallbackStructuredQuery()) {
+                return $this->lookup();
             }
 
             return array();
@@ -889,7 +813,9 @@ class Geocode
 
         $aRecheckWords = preg_split('/\b[\s,\\-]*/u', $sQuery);
         foreach ($aRecheckWords as $i => $sWord) {
-            if (!preg_match('/[\pL\pN]/', $sWord)) unset($aRecheckWords[$i]);
+            if (!preg_match('/[\pL\pN]/', $sWord)) {
+                unset($aRecheckWords[$i]);
+            }
         }
 
         Debug::printVar('Recheck words', $aRecheckWords);
@@ -923,21 +849,14 @@ class Geocode
                     $aResult['lon'],
                     $aResult['lat']
                 );
-                // Adjust importance for the number of exact string matches in the result
-                $iCountWords = 0;
-                $sAddress = $aResult['langaddress'];
-                foreach ($aRecheckWords as $i => $sWord) {
-                    if (stripos($sAddress, $sWord)!==false) {
-                        $iCountWords++;
-                        if (preg_match('/(^|,)\s*'.preg_quote($sWord, '/').'\s*(,|$)/', $sAddress)) $iCountWords += 0.1;
-                    }
-                }
-
-                $aResult['importance'] = $aResult['importance'] + ($iCountWords*0.1); // 0.1 is a completely arbitrary number but something in the range 0.1 to 0.5 would seem right
 
                 // secondary ordering (for results with same importance (the smaller the better):
                 // - approximate importance of address parts
-                $aResult['foundorder'] = -$aResult['addressimportance']/10;
+                if (isset($aResult['addressimportance']) && $aResult['addressimportance']) {
+                    $aResult['foundorder'] = -$aResult['addressimportance']/10;
+                } else {
+                    $aResult['foundorder'] = -$aResult['importance'];
+                }
                 // - number of exact matches from the query
                 $aResult['foundorder'] -= $aResults[$aResult['place_id']]->iExactMatches;
                 // - importance of the class/type
@@ -947,6 +866,23 @@ class Geocode
                 } else {
                     $aResult['foundorder'] += 0.01;
                 }
+                // - rank
+                $aResult['foundorder'] -= 0.00001 * (30 - $aResult['rank_search']);
+
+                // Adjust importance for the number of exact string matches in the result
+                $iCountWords = 0;
+                $sAddress = $aResult['langaddress'];
+                foreach ($aRecheckWords as $i => $sWord) {
+                    if (stripos($sAddress, $sWord)!==false) {
+                        $iCountWords++;
+                        if (preg_match('/(^|,)\s*'.preg_quote($sWord, '/').'\s*(,|$)/', $sAddress)) {
+                            $iCountWords += 0.1;
+                        }
+                    }
+                }
+
+                // 0.1 is a completely arbitrary number but something in the range 0.1 to 0.5 would seem right
+                $aResult['importance'] = $aResult['importance'] + ($iCountWords*0.1);
             }
             $aSearchResults[$iIdx] = $aResult;
         }
@@ -958,15 +894,8 @@ class Geocode
         $aToFilter = $aSearchResults;
         $aSearchResults = array();
 
-        $bFirst = true;
         foreach ($aToFilter as $aResult) {
             $this->aExcludePlaceIDs[$aResult['place_id']] = $aResult['place_id'];
-            if ($bFirst) {
-                $fLat = $aResult['lat'];
-                $fLon = $aResult['lon'];
-                if (isset($aResult['zoom'])) $iZoom = $aResult['zoom'];
-                $bFirst = false;
-            }
             if (!$this->oPlaceLookup->doDeDupe() || (!isset($aOSMIDDone[$aResult['osm_type'].$aResult['osm_id']])
                 && !isset($aClassTypeNameDone[$aResult['osm_type'].$aResult['class'].$aResult['type'].$aResult['name'].$aResult['admin_level']]))
             ) {
@@ -976,7 +905,9 @@ class Geocode
             }
 
             // Absolute limit on number of results
-            if (count($aSearchResults) >= $this->iFinalLimit) break;
+            if (count($aSearchResults) >= $this->iFinalLimit) {
+                break;
+            }
         }
 
         Debug::printVar('Post-filter results', $aSearchResults);
@@ -990,7 +921,6 @@ class Geocode
                 'Structured query' => $this->aStructuredQuery,
                 'Name keys' => Debug::fmtArrayVals($this->aLangPrefOrder),
                 'Excluded place IDs' => Debug::fmtArrayVals($this->aExcludePlaceIDs),
-                'Try reversed query'=> $this->bReverseInPlan,
                 'Limit (for searches)' => $this->iLimit,
                 'Limit (for results)'=> $this->iFinalLimit,
                 'Country codes' => Debug::fmtArrayVals($this->aCountryCodes),

lib-php/ParameterParser.php

@@ -90,14 +90,16 @@ class ParameterParser
         $aLanguages = array();
         $sLangString = $this->getString('accept-language', $sFallback);
 
-        if ($sLangString) {
-            if (preg_match_all('/(([a-z]{1,8})([-_][a-z]{1,8})?)\s*(;\s*q\s*=\s*(1|0\.[0-9]+))?/i', $sLangString, $aLanguagesParse, PREG_SET_ORDER)) {
-                foreach ($aLanguagesParse as $iLang => $aLanguage) {
-                    $aLanguages[$aLanguage[1]] = isset($aLanguage[5])?(float)$aLanguage[5]:1 - ($iLang/100);
-                    if (!isset($aLanguages[$aLanguage[2]])) $aLanguages[$aLanguage[2]] = $aLanguages[$aLanguage[1]]/10;
+        if ($sLangString
+            && preg_match_all('/(([a-z]{1,8})([-_][a-z]{1,8})?)\s*(;\s*q\s*=\s*(1|0\.[0-9]+))?/i', $sLangString, $aLanguagesParse, PREG_SET_ORDER)
+        ) {
+            foreach ($aLanguagesParse as $iLang => $aLanguage) {
+                $aLanguages[$aLanguage[1]] = isset($aLanguage[5])?(float)$aLanguage[5]:1 - ($iLang/100);
+                if (!isset($aLanguages[$aLanguage[2]])) {
+                    $aLanguages[$aLanguage[2]] = $aLanguages[$aLanguage[1]]/10;
                 }
-                arsort($aLanguages);
             }
+            arsort($aLanguages);
         }
         if (empty($aLanguages) && CONST_Default_Language) {
             $aLanguages[CONST_Default_Language] = 1;

lib-php/Phrase.php

@@ -16,8 +16,6 @@ class Phrase
     private $sPhrase;
     // Element type for structured searches.
     private $sPhraseType;
-    // Space-separated words of the phrase.
-    private $aWords;
     // Possible segmentations of the phrase.
     private $aWordSets;
 
@@ -38,7 +36,14 @@ class Phrase
     {
         $this->sPhrase = trim($sPhrase);
         $this->sPhraseType = $sPhraseType;
-        $this->aWords = explode(' ', $this->sPhrase);
+    }
+
+    /**
+     * Get the orginal phrase of the string.
+     */
+    public function getPhrase()
+    {
+        return $this->sPhrase;
     }
 
     /**
@@ -63,30 +68,6 @@ class Phrase
         return $this->aWordSets;
     }
 
-    /**
-     * Add the tokens from this phrase to the given list of tokens.
-     *
-     * @param string[] $aTokens List of tokens to append.
-     *
-     * @return void
-     */
-    public function addTokens(&$aTokens)
-    {
-        $iNumWords = count($this->aWords);
-
-        for ($i = 0; $i < $iNumWords; $i++) {
-            $sPhrase = $this->aWords[$i];
-            $aTokens[' '.$sPhrase] = ' '.$sPhrase;
-            $aTokens[$sPhrase] = $sPhrase;
-
-            for ($j = $i + 1; $j < $iNumWords; $j++) {
-                $sPhrase .= ' '.$this->aWords[$j];
-                $aTokens[' '.$sPhrase] = ' '.$sPhrase;
-                $aTokens[$sPhrase] = $sPhrase;
-            }
-        }
-    }
-
     /**
      * Invert the set of possible segmentations.
      *
@@ -99,21 +80,27 @@ class Phrase
         }
     }
 
-    public function computeWordSets($oTokens)
+    public function computeWordSets($aWords, $oTokens)
     {
-        $iNumWords = count($this->aWords);
+        $iNumWords = count($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 ($oTokens->containsAny($this->aWords[0])) {
-            $aSetCache[0][] = array($this->aWords[0]);
+        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 ? $this->aWords[$j] : $this->aWords[$j].' '.$sPartial;
+                $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) {
@@ -136,7 +123,7 @@ class Phrase
             }
 
             // finally the current full phrase
-            $sPartial = $this->aWords[0].' '.$sPartial;
+            $sPartial = $aWords[0].' '.$sPartial;
             if ($oTokens->containsAny($sPartial)) {
                 $aSetCache[$i][] = array($sPartial);
             }
@@ -153,7 +140,6 @@ class Phrase
         return array(
                 'Type' => $this->sPhraseType,
                 'Phrase' => $this->sPhrase,
-                'Words' => $this->aWords,
                 'WordSets' => $this->aWordSets
                );
     }

lib-php/PlaceLookup.php

@@ -2,8 +2,8 @@
 
 namespace Nominatim;
 
-require_once(CONST_BasePath.'/lib/AddressDetails.php');
-require_once(CONST_BasePath.'/lib/Result.php');
+require_once(CONST_LibDir.'/AddressDetails.php');
+require_once(CONST_LibDir.'/Result.php');
 
 class PlaceLookup
 {
@@ -89,20 +89,36 @@ class PlaceLookup
     {
         $aParams = array();
 
-        if ($this->bAddressDetails) $aParams['addressdetails'] = '1';
-        if ($this->bExtraTags) $aParams['extratags'] = '1';
-        if ($this->bNameDetails) $aParams['namedetails'] = '1';
+        if ($this->bAddressDetails) {
+            $aParams['addressdetails'] = '1';
+        }
+        if ($this->bExtraTags) {
+            $aParams['extratags'] = '1';
+        }
+        if ($this->bNameDetails) {
+            $aParams['namedetails'] = '1';
+        }
 
-        if ($this->bIncludePolygonAsText) $aParams['polygon_text'] = '1';
-        if ($this->bIncludePolygonAsGeoJSON) $aParams['polygon_geojson'] = '1';
-        if ($this->bIncludePolygonAsKML) $aParams['polygon_kml'] = '1';
-        if ($this->bIncludePolygonAsSVG) $aParams['polygon_svg'] = '1';
+        if ($this->bIncludePolygonAsText) {
+            $aParams['polygon_text'] = '1';
+        }
+        if ($this->bIncludePolygonAsGeoJSON) {
+            $aParams['polygon_geojson'] = '1';
+        }
+        if ($this->bIncludePolygonAsKML) {
+            $aParams['polygon_kml'] = '1';
+        }
+        if ($this->bIncludePolygonAsSVG) {
+            $aParams['polygon_svg'] = '1';
+        }
 
         if ($this->fPolygonSimplificationThreshold > 0.0) {
             $aParams['polygon_threshold'] = $this->fPolygonSimplificationThreshold;
         }
 
-        if (!$this->bDeDupe) $aParams['dedupe'] = '0';
+        if (!$this->bDeDupe) {
+            $aParams['dedupe'] = '0';
+        }
 
         return $aParams;
     }
@@ -147,8 +163,9 @@ class PlaceLookup
 
     private function langAddressSql($sHousenumber)
     {
-        if ($this->bAddressDetails)
+        if ($this->bAddressDetails) {
             return ''; // langaddress will be computed from address details
+        }
 
         return 'get_address_by_language(place_id,'.$sHousenumber.','.$this->aLangPrefOrderSql.') AS langaddress,';
     }
@@ -234,12 +251,20 @@ class PlaceLookup
             $sSQL .= '     housenumber,';
             $sSQL .= '     country_code, ';
             $sSQL .= '     importance, ';
-            if (!$this->bDeDupe) $sSQL .= 'place_id,';
-            if (!$this->bAddressDetails) $sSQL .= 'langaddress, ';
+            if (!$this->bDeDupe) {
+                $sSQL .= 'place_id,';
+            }
+            if (!$this->bAddressDetails) {
+                $sSQL .= 'langaddress, ';
+            }
             $sSQL .= '     placename, ';
             $sSQL .= '     ref, ';
-            if ($this->bExtraTags) $sSQL .= 'extratags, ';
-            if ($this->bNameDetails) $sSQL .= 'name, ';
+            if ($this->bExtraTags) {
+                $sSQL .= 'extratags, ';
+            }
+            if ($this->bNameDetails) {
+                $sSQL .= 'name, ';
+            }
             $sSQL .= '     extra_place ';
 
             $aSubSelects[] = $sSQL;
@@ -260,8 +285,12 @@ class PlaceLookup
             $sSQL .= $this->langAddressSql('-1');
             $sSQL .= '  postcode as placename,';
             $sSQL .= '  postcode as ref,';
-            if ($this->bExtraTags) $sSQL .= 'null::text AS extra,';
-            if ($this->bNameDetails) $sSQL .= 'null::text AS names,';
+            if ($this->bExtraTags) {
+                $sSQL .= 'null::text AS extra,';
+            }
+            if ($this->bNameDetails) {
+                $sSQL .= 'null::text AS names,';
+            }
             $sSQL .= '  ST_x(geometry) AS lon, ST_y(geometry) AS lat,';
             $sSQL .= '  (0.75-(rank_search::float/40)) AS importance, ';
             $sSQL .= $this->addressImportanceSql('geometry', 'lp.parent_place_id');
@@ -298,8 +327,12 @@ class PlaceLookup
                     $sSQL .= $this->langAddressSql('housenumber_for_place');
                     $sSQL .= '     null::text AS placename, ';
                     $sSQL .= '     null::text AS ref, ';
-                    if ($this->bExtraTags) $sSQL .= 'null::text AS extra,';
-                    if ($this->bNameDetails) $sSQL .= 'null::text AS names,';
+                    if ($this->bExtraTags) {
+                        $sSQL .= 'null::text AS extra,';
+                    }
+                    if ($this->bNameDetails) {
+                        $sSQL .= 'null::text AS names,';
+                    }
                     $sSQL .= '     st_x(centroid) AS lon, ';
                     $sSQL .= '     st_y(centroid) AS lat,';
                     $sSQL .= '     -1.15 AS importance, ';
@@ -344,8 +377,12 @@ class PlaceLookup
                 $sSQL .= $this->langAddressSql('housenumber_for_place');
                 $sSQL .= '  null::text AS placename, ';
                 $sSQL .= '  null::text AS ref, ';
-                if ($this->bExtraTags) $sSQL .= 'null::text AS extra, ';
-                if ($this->bNameDetails) $sSQL .= 'null::text AS names, ';
+                if ($this->bExtraTags) {
+                    $sSQL .= 'null::text AS extra, ';
+                }
+                if ($this->bNameDetails) {
+                    $sSQL .= 'null::text AS names, ';
+                }
                 $sSQL .= '  st_x(centroid) AS lon, ';
                 $sSQL .= '  st_y(centroid) AS lat, ';
                 // slightly smaller than the importance for normal houses
@@ -373,42 +410,6 @@ class PlaceLookup
 
                 $aSubSelects[] = $sSQL;
             }
-
-            if (CONST_Use_Aux_Location_data) {
-                $sPlaceIDs = Result::joinIdsByTable($aResults, Result::TABLE_AUX);
-                if ($sPlaceIDs) {
-                    $sHousenumbers = Result::sqlHouseNumberTable($aResults, Result::TABLE_AUX);
-                    $sSQL = '  SELECT ';
-                    $sSQL .= "     'L' AS osm_type, ";
-                    $sSQL .= '     place_id AS osm_id, ';
-                    $sSQL .= "     'place' AS class,";
-                    $sSQL .= "     'house' AS type, ";
-                    $sSQL .= '     null::smallint AS admin_level, ';
-                    $sSQL .= '     30 AS rank_search,';
-                    $sSQL .= '     30 AS rank_address, ';
-                    $sSQL .= '     place_id,';
-                    $sSQL .= '     parent_place_id, ';
-                    $sSQL .= '     housenumber,';
-                    $sSQL .= "     'us' AS country_code, ";
-                    $sSQL .= $this->langAddressSql('-1');
-                    $sSQL .= '     null::text AS placename, ';
-                    $sSQL .= '     null::text AS ref, ';
-                    if ($this->bExtraTags) $sSQL .= 'null::text AS extra, ';
-                    if ($this->bNameDetails) $sSQL .= 'null::text AS names, ';
-                    $sSQL .= '     ST_X(centroid) AS lon, ';
-                    $sSQL .= '     ST_Y(centroid) AS lat, ';
-                    $sSQL .= '     -1.10 AS importance, ';
-                    $sSQL .= $this->addressImportanceSql(
-                        'centroid',
-                        'location_property_aux.parent_place_id'
-                    );
-                    $sSQL .= '     null::text AS extra_place ';
-                    $sSQL .= '  FROM location_property_aux ';
-                    $sSQL .= "  WHERE place_id in ($sPlaceIDs) ";
-
-                    $aSubSelects[] = $sSQL;
-                }
-            }
         }
 
         if (empty($aSubSelects)) {
@@ -452,11 +453,20 @@ class PlaceLookup
                 $aPlace,
                 $aPlace['country_code']
             );
+
+            $aResults[$aPlace['place_id']] = $aPlace;
         }
 
-        Debug::printVar('Places', $aPlaces);
+        $aResults = array_filter(
+            $aResults,
+            function ($v) {
+                return !($v instanceof Result);
+            }
+        );
 
-        return $aPlaces;
+        Debug::printVar('Places', $aResults);
+
+        return $aResults;
     }
 
     /* returns an array which will contain the keys
@@ -475,67 +485,83 @@ class PlaceLookup
     {
 
         $aOutlineResult = array();
-        if (!$iPlaceID) return $aOutlineResult;
+        if (!$iPlaceID) {
+            return $aOutlineResult;
+        }
 
-        if (CONST_Search_AreaPolygons) {
-            // Get the bounding box and outline polygon
-            $sSQL = 'select place_id,0 as numfeatures,st_area(geometry) as area,';
-            if ($fLonReverse != null && $fLatReverse != null) {
-                $sSQL .= ' ST_Y(closest_point) as centrelat,';
-                $sSQL .= ' ST_X(closest_point) as centrelon,';
-            } else {
-                $sSQL .= ' ST_Y(centroid) as centrelat, ST_X(centroid) as centrelon,';
-            }
-            $sSQL .= ' ST_YMin(geometry) as minlat,ST_YMax(geometry) as maxlat,';
-            $sSQL .= ' ST_XMin(geometry) as minlon,ST_XMax(geometry) as maxlon';
-            if ($this->bIncludePolygonAsGeoJSON) $sSQL .= ',ST_AsGeoJSON(geometry) as asgeojson';
-            if ($this->bIncludePolygonAsKML) $sSQL .= ',ST_AsKML(geometry) as askml';
-            if ($this->bIncludePolygonAsSVG) $sSQL .= ',ST_AsSVG(geometry) as assvg';
-            if ($this->bIncludePolygonAsText) $sSQL .= ',ST_AsText(geometry) as astext';
-            if ($fLonReverse != null && $fLatReverse != null) {
-                $sFrom = ' from (SELECT * , CASE WHEN (class = \'highway\') AND (ST_GeometryType(geometry) = \'ST_LineString\') THEN ';
-                $sFrom .=' ST_ClosestPoint(geometry, ST_SetSRID(ST_Point('.$fLatReverse.','.$fLonReverse.'),4326))';
-                $sFrom .=' ELSE centroid END AS closest_point';
-                $sFrom .= ' from placex where place_id = '.$iPlaceID.') as plx';
-            } else {
-                $sFrom = ' from placex where place_id = '.$iPlaceID;
-            }
-            if ($this->fPolygonSimplificationThreshold > 0) {
-                $sSQL .= ' from (select place_id,centroid,ST_SimplifyPreserveTopology(geometry,'.$this->fPolygonSimplificationThreshold.') as geometry'.$sFrom.') as plx';
-            } else {
-                $sSQL .= $sFrom;
+        // Get the bounding box and outline polygon
+        $sSQL = 'select place_id,0 as numfeatures,st_area(geometry) as area,';
+        if ($fLonReverse != null && $fLatReverse != null) {
+            $sSQL .= ' ST_Y(closest_point) as centrelat,';
+            $sSQL .= ' ST_X(closest_point) as centrelon,';
+        } else {
+            $sSQL .= ' ST_Y(centroid) as centrelat, ST_X(centroid) as centrelon,';
+        }
+        $sSQL .= ' ST_YMin(geometry) as minlat,ST_YMax(geometry) as maxlat,';
+        $sSQL .= ' ST_XMin(geometry) as minlon,ST_XMax(geometry) as maxlon';
+        if ($this->bIncludePolygonAsGeoJSON) {
+            $sSQL .= ',ST_AsGeoJSON(geometry) as asgeojson';
+        }
+        if ($this->bIncludePolygonAsKML) {
+            $sSQL .= ',ST_AsKML(geometry) as askml';
+        }
+        if ($this->bIncludePolygonAsSVG) {
+            $sSQL .= ',ST_AsSVG(geometry) as assvg';
+        }
+        if ($this->bIncludePolygonAsText) {
+            $sSQL .= ',ST_AsText(geometry) as astext';
+        }
+        if ($fLonReverse != null && $fLatReverse != null) {
+            $sFrom = ' from (SELECT * , CASE WHEN (class = \'highway\') AND (ST_GeometryType(geometry) = \'ST_LineString\') THEN ';
+            $sFrom .=' ST_ClosestPoint(geometry, ST_SetSRID(ST_Point('.$fLatReverse.','.$fLonReverse.'),4326))';
+            $sFrom .=' ELSE centroid END AS closest_point';
+            $sFrom .= ' from placex where place_id = '.$iPlaceID.') as plx';
+        } else {
+            $sFrom = ' from placex where place_id = '.$iPlaceID;
+        }
+        if ($this->fPolygonSimplificationThreshold > 0) {
+            $sSQL .= ' from (select place_id,centroid,ST_SimplifyPreserveTopology(geometry,'.$this->fPolygonSimplificationThreshold.') as geometry'.$sFrom.') as plx';
+        } else {
+            $sSQL .= $sFrom;
+        }
+
+        $aPointPolygon = $this->oDB->getRow($sSQL, null, 'Could not get outline');
+
+        if ($aPointPolygon && $aPointPolygon['place_id']) {
+            if ($aPointPolygon['centrelon'] !== null && $aPointPolygon['centrelat'] !== null) {
+                $aOutlineResult['lat'] = $aPointPolygon['centrelat'];
+                $aOutlineResult['lon'] = $aPointPolygon['centrelon'];
             }
 
-            $aPointPolygon = $this->oDB->getRow($sSQL, null, 'Could not get outline');
-
-            if ($aPointPolygon && $aPointPolygon['place_id']) {
-                if ($aPointPolygon['centrelon'] !== null && $aPointPolygon['centrelat'] !== null) {
-                    $aOutlineResult['lat'] = $aPointPolygon['centrelat'];
-                    $aOutlineResult['lon'] = $aPointPolygon['centrelon'];
-                }
-
-                if ($this->bIncludePolygonAsGeoJSON) $aOutlineResult['asgeojson'] = $aPointPolygon['asgeojson'];
-                if ($this->bIncludePolygonAsKML) $aOutlineResult['askml'] = $aPointPolygon['askml'];
-                if ($this->bIncludePolygonAsSVG) $aOutlineResult['assvg'] = $aPointPolygon['assvg'];
-                if ($this->bIncludePolygonAsText) $aOutlineResult['astext'] = $aPointPolygon['astext'];
-
-                if (abs($aPointPolygon['minlat'] - $aPointPolygon['maxlat']) < 0.0000001) {
-                    $aPointPolygon['minlat'] = $aPointPolygon['minlat'] - $fRadius;
-                    $aPointPolygon['maxlat'] = $aPointPolygon['maxlat'] + $fRadius;
-                }
-
-                if (abs($aPointPolygon['minlon'] - $aPointPolygon['maxlon']) < 0.0000001) {
-                    $aPointPolygon['minlon'] = $aPointPolygon['minlon'] - $fRadius;
-                    $aPointPolygon['maxlon'] = $aPointPolygon['maxlon'] + $fRadius;
-                }
-
-                $aOutlineResult['aBoundingBox'] = array(
-                                                   (string)$aPointPolygon['minlat'],
-                                                   (string)$aPointPolygon['maxlat'],
-                                                   (string)$aPointPolygon['minlon'],
-                                                   (string)$aPointPolygon['maxlon']
-                                                  );
+            if ($this->bIncludePolygonAsGeoJSON) {
+                $aOutlineResult['asgeojson'] = $aPointPolygon['asgeojson'];
             }
+            if ($this->bIncludePolygonAsKML) {
+                $aOutlineResult['askml'] = $aPointPolygon['askml'];
+            }
+            if ($this->bIncludePolygonAsSVG) {
+                $aOutlineResult['assvg'] = $aPointPolygon['assvg'];
+            }
+            if ($this->bIncludePolygonAsText) {
+                $aOutlineResult['astext'] = $aPointPolygon['astext'];
+            }
+
+            if (abs($aPointPolygon['minlat'] - $aPointPolygon['maxlat']) < 0.0000001) {
+                $aPointPolygon['minlat'] = $aPointPolygon['minlat'] - $fRadius;
+                $aPointPolygon['maxlat'] = $aPointPolygon['maxlat'] + $fRadius;
+            }
+
+            if (abs($aPointPolygon['minlon'] - $aPointPolygon['maxlon']) < 0.0000001) {
+                $aPointPolygon['minlon'] = $aPointPolygon['minlon'] - $fRadius;
+                $aPointPolygon['maxlon'] = $aPointPolygon['maxlon'] + $fRadius;
+            }
+
+            $aOutlineResult['aBoundingBox'] = array(
+                                               (string)$aPointPolygon['minlat'],
+                                               (string)$aPointPolygon['maxlat'],
+                                               (string)$aPointPolygon['minlon'],
+                                               (string)$aPointPolygon['maxlon']
+                                              );
         }
 
         // as a fallback we generate a bounding box without knowing the size of the geometry

lib-php/Result.php

@@ -13,8 +13,7 @@ class Result
     const TABLE_PLACEX = 0;
     const TABLE_POSTCODE = 1;
     const TABLE_OSMLINE = 2;
-    const TABLE_AUX = 3;
-    const TABLE_TIGER = 4;
+    const TABLE_TIGER = 3;
 
     /// Database table that contains the result.
     public $iTable;
@@ -26,6 +25,8 @@ class Result
     public $iExactMatches = 0;
     /// Subranking within the results (the higher the worse).
     public $iResultRank = 0;
+    /// Address rank of the result.
+    public $iAddressRank;
 
     public function debugInfo()
     {
@@ -54,6 +55,27 @@ class Result
             }
         )));
     }
+
+    public static function joinIdsByTableMinRank($aResults, $iTable, $iMinAddressRank)
+    {
+        return join(',', array_keys(array_filter(
+            $aResults,
+            function ($aValue) use ($iTable, $iMinAddressRank) {
+                return $aValue->iTable == $iTable && $aValue->iAddressRank >= $iMinAddressRank;
+            }
+        )));
+    }
+
+    public static function joinIdsByTableMaxRank($aResults, $iTable, $iMaxAddressRank)
+    {
+        return join(',', array_keys(array_filter(
+            $aResults,
+            function ($aValue) use ($iTable, $iMaxAddressRank) {
+                return $aValue->iTable == $iTable && $aValue->iAddressRank <= $iMaxAddressRank;
+            }
+        )));
+    }
+
     public static function sqlHouseNumberTable($aResults, $iTable)
     {
         $sHousenumbers = '';
@@ -84,7 +106,7 @@ class Result
 
         foreach ($aResults as $oRes) {
             if ($oRes->iResultRank < $iMinRank) {
-                $aTail = array_merge($aTail, $aHead);
+                $aTail += $aHead;
                 $aHead = array($oRes->iId => $oRes);
                 $iMinRank = $oRes->iResultRank;
             } elseif ($oRes->iResultRank == $iMinRank) {

lib-php/ReverseGeocode.php

@@ -2,7 +2,7 @@
 
 namespace Nominatim;
 
-require_once(CONST_BasePath.'/lib/Result.php');
+require_once(CONST_LibDir.'/Result.php');
 
 class ReverseGeocode
 {
@@ -54,6 +54,7 @@ class ReverseGeocode
      */
     protected function lookupInterpolation($sPointSQL, $fSearchDiam)
     {
+        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,';
@@ -62,6 +63,7 @@ class ReverseGeocode
         $sSQL .= ' WHERE ST_DWithin('.$sPointSQL.', linegeo, '.$fSearchDiam.')';
         $sSQL .= ' and indexed_status = 0 and startnumber is not NULL ';
         $sSQL .= ' ORDER BY distance ASC limit 1';
+        Debug::printSQL($sSQL);
 
         return $this->oDB->getRow(
             $sSQL,
@@ -72,8 +74,6 @@ class ReverseGeocode
 
     protected function lookupLargeArea($sPointSQL, $iMaxRank)
     {
-        $oResult = null;
-
         if ($iMaxRank > 4) {
             $aPlace = $this->lookupPolygon($sPointSQL, $iMaxRank);
             if ($aPlace) {
@@ -88,16 +88,20 @@ class ReverseGeocode
 
     protected function lookupInCountry($sPointSQL, $iMaxRank)
     {
+        Debug::newFunction('lookupInCountry');
         // searches for polygon in table country_osm_grid which contains the searchpoint
         // and searches for the nearest place node to the searchpoint in this polygon
         $sSQL = 'SELECT country_code FROM country_osm_grid';
         $sSQL .= ' WHERE ST_CONTAINS(geometry, '.$sPointSQL.') LIMIT 1';
+        Debug::printSQL($sSQL);
 
         $sCountryCode = $this->oDB->getOne(
             $sSQL,
             null,
             'Could not determine country polygon containing the point.'
         );
+        Debug::printVar('Country code', $sCountryCode);
+
         if ($sCountryCode) {
             if ($iMaxRank > 4) {
                 // look for place nodes with the given country code
@@ -115,9 +119,11 @@ class ReverseGeocode
                 $sSQL .= 'WHERE distance <= reverse_place_diameter(rank_search)';
                 $sSQL .= ' ORDER BY rank_search DESC, distance ASC';
                 $sSQL .= ' LIMIT 1';
+                Debug::printSQL($sSQL);
 
-                if (CONST_Debug) var_dump($sSQL);
                 $aPlace = $this->oDB->getRow($sSQL, null, 'Could not determine place node.');
+                Debug::printVar('Country node', $aPlace);
+
                 if ($aPlace) {
                     return new Result($aPlace['place_id']);
                 }
@@ -131,9 +137,10 @@ class ReverseGeocode
             $sSQL .= ' AND class in (\'boundary\',  \'place\')';
             $sSQL .= ' AND linked_place_id is null';
             $sSQL .= ' ORDER BY distance ASC';
+            Debug::printSQL($sSQL);
 
-            if (CONST_Debug) var_dump($sSQL);
             $aPlace = $this->oDB->getRow($sSQL, null, 'Could not determine place node.');
+            Debug::printVar('Country place', $aPlace);
             if ($aPlace) {
                 return new Result($aPlace['place_id']);
             }
@@ -156,10 +163,15 @@ class ReverseGeocode
      */
     protected function lookupPolygon($sPointSQL, $iMaxRank)
     {
+        Debug::newFunction('lookupPolygon');
         // polygon search begins at suburb-level
-        if ($iMaxRank > 25) $iMaxRank = 25;
+        if ($iMaxRank > 25) {
+            $iMaxRank = 25;
+        }
         // no polygon search over country-level
-        if ($iMaxRank < 5) $iMaxRank = 5;
+        if ($iMaxRank < 5) {
+            $iMaxRank = 5;
+        }
         // search for polygon
         $sSQL = 'SELECT place_id, parent_place_id, rank_address, rank_search FROM';
         $sSQL .= '(select place_id, parent_place_id, rank_address, rank_search, country_code, geometry';
@@ -173,12 +185,13 @@ class ReverseGeocode
         $sSQL .= ' ORDER BY rank_address DESC LIMIT 50 ) as a';
         $sSQL .= ' WHERE ST_CONTAINS(geometry, '.$sPointSQL.' )';
         $sSQL .= ' ORDER BY rank_address DESC LIMIT 1';
+        Debug::printSQL($sSQL);
 
         $aPoly = $this->oDB->getRow($sSQL, null, 'Could not determine polygon containing the point.');
+        Debug::printVar('Polygon result', $aPoly);
 
         if ($aPoly) {
         // if a polygon is found, search for placenodes begins ...
-            $iParentPlaceID = $aPoly['parent_place_id'];
             $iRankAddress = $aPoly['rank_address'];
             $iRankSearch = $aPoly['rank_search'];
             $iPlaceID = $aPoly['place_id'];
@@ -193,6 +206,7 @@ class ReverseGeocode
                 // for place nodes at rank_address 16
                 $sSQL .= ' AND rank_search > '.$iRankSearch;
                 $sSQL .= ' AND rank_search <= '.$iMaxRank;
+                $sSQL .= ' AND rank_address > 0';
                 $sSQL .= ' AND class = \'place\'';
                 $sSQL .= ' AND type != \'postcode\'';
                 $sSQL .= ' AND name IS NOT NULL ';
@@ -205,11 +219,12 @@ class ReverseGeocode
                 $sSQL .= ' AND distance <= reverse_place_diameter(rank_search)';
                 $sSQL .= ' ORDER BY distance ASC, rank_search DESC';
                 $sSQL .= ' LIMIT 1';
+                Debug::printSQL($sSQL);
 
-                if (CONST_Debug) var_dump($sSQL);
-                $aPlacNode = $this->oDB->getRow($sSQL, null, 'Could not determine place node.');
-                if ($aPlacNode) {
-                    return $aPlacNode;
+                $aPlaceNode = $this->oDB->getRow($sSQL, null, 'Could not determine place node.');
+                Debug::printVar('Nearest place node', $aPlaceNode);
+                if ($aPlaceNode) {
+                    return $aPlaceNode;
                 }
             }
         }
@@ -227,26 +242,25 @@ class ReverseGeocode
 
     public function lookupPoint($sPointSQL, $bDoInterpolation = true)
     {
-        // starts if the search is on POI or street level,
-        // searches for the nearest POI or street,
-        // if a street is found and a POI is searched for,
-        // the nearest POI which the found street is a parent of is choosen.
-        $iMaxRank = $this->iMaxRank;
-
+        Debug::newFunction('lookupPoint');
         // Find the nearest point
         $fSearchDiam = 0.006;
         $oResult = null;
         $aPlace = null;
 
         // for POI or street level
-        if ($iMaxRank >= 26) {
+        if ($this->iMaxRank >= 26) {
+            // starts if the search is on POI or street level,
+            // searches for the nearest POI or street,
+            // if a street is found and a POI is searched for,
+            // the nearest POI which the found street is a parent of is choosen.
             $sSQL = 'select place_id,parent_place_id,rank_address,country_code,';
             $sSQL .= ' ST_distance('.$sPointSQL.', geometry) as distance';
             $sSQL .= ' FROM ';
             $sSQL .= ' placex';
             $sSQL .= '   WHERE ST_DWithin('.$sPointSQL.', geometry, '.$fSearchDiam.')';
             $sSQL .= '   AND';
-            $sSQL .= ' rank_address between 26 and '.$iMaxRank;
+            $sSQL .= ' rank_address between 26 and '.$this->iMaxRank;
             $sSQL .= ' and (name is not null or housenumber is not null';
             $sSQL .= ' or rank_address between 26 and 27)';
             $sSQL .= ' and (rank_address between 26 and 27';
@@ -256,41 +270,20 @@ class ReverseGeocode
             $sSQL .= ' and (ST_GeometryType(geometry) not in (\'ST_Polygon\',\'ST_MultiPolygon\') ';
             $sSQL .= ' OR ST_DWithin('.$sPointSQL.', centroid, '.$fSearchDiam.'))';
             $sSQL .= ' ORDER BY distance ASC limit 1';
-            if (CONST_Debug) var_dump($sSQL);
+            Debug::printSQL($sSQL);
+
             $aPlace = $this->oDB->getRow($sSQL, null, 'Could not determine closest place.');
 
-            if (CONST_Debug) var_dump($aPlace);
+            Debug::printVar('POI/street level result', $aPlace);
             if ($aPlace) {
                 $iPlaceID = $aPlace['place_id'];
                 $oResult = new Result($iPlaceID);
                 $iRankAddress = $aPlace['rank_address'];
-                $iParentPlaceID = $aPlace['parent_place_id'];
-            }
-
-            if ($bDoInterpolation && $iMaxRank >= 30) {
-                $fDistance = $fSearchDiam;
-                if ($aPlace) {
-                    // We can't reliably go from the closest street to an
-                    // interpolation line because the closest interpolation
-                    // may have a different street segments as a parent.
-                    // Therefore allow an interpolation line to take precendence
-                    // even when the street is closer.
-                    $fDistance = $iRankAddress < 28 ? 0.001 : $aPlace['distance'];
-                }
-
-                $aHouse = $this->lookupInterpolation($sPointSQL, $fDistance);
-
-                if ($aHouse) {
-                    $oResult = new Result($aHouse['place_id'], Result::TABLE_OSMLINE);
-                    $oResult->iHouseNumber = closestHouseNumber($aHouse);
-                    $aPlace = $aHouse;
-                    $iRankAddress = 30;
-                }
             }
 
             if ($aPlace) {
                 // if street and maxrank > streetlevel
-                if ($iRankAddress <= 27 && $iMaxRank > 27) {
+                if ($iRankAddress <= 27 && $this->iMaxRank > 27) {
                     // find the closest object (up to a certain radius) of which the street is a parent of
                     $sSQL = ' select place_id,';
                     $sSQL .= ' ST_distance('.$sPointSQL.', geometry) as distance';
@@ -305,11 +298,15 @@ class ReverseGeocode
                     $sSQL .= ' and class not in (\'boundary\')';
                     $sSQL .= ' and indexed_status = 0 and linked_place_id is null';
                     $sSQL .= ' ORDER BY distance ASC limit 1';
-                    if (CONST_Debug) var_dump($sSQL);
+                    Debug::printSQL($sSQL);
+
                     $aStreet = $this->oDB->getRow($sSQL, null, 'Could not determine closest place.');
+                    Debug::printVar('Closest POI result', $aStreet);
+
                     if ($aStreet) {
-                        if (CONST_Debug) var_dump($aStreet);
+                        $aPlace = $aStreet;
                         $oResult = new Result($aStreet['place_id']);
+                        $iRankAddress = 30;
                     }
                 }
 
@@ -326,22 +323,51 @@ class ReverseGeocode
                     $sSQL .= ' FROM location_property_tiger WHERE parent_place_id = '.$oResult->iId;
                     $sSQL .= ' AND ST_DWithin('.$sPointSQL.', linegeo, 0.001)';
                     $sSQL .= ' ORDER BY distance ASC limit 1';
-                    if (CONST_Debug) var_dump($sSQL);
+                    Debug::printSQL($sSQL);
+
                     $aPlaceTiger = $this->oDB->getRow($sSQL, null, 'Could not determine closest Tiger place.');
+                    Debug::printVar('Tiger house number result', $aPlaceTiger);
+
                     if ($aPlaceTiger) {
-                        if (CONST_Debug) var_dump('found Tiger housenumber', $aPlaceTiger);
+                        $aPlace = $aPlaceTiger;
                         $oResult = new Result($aPlaceTiger['place_id'], Result::TABLE_TIGER);
                         $oResult->iHouseNumber = closestHouseNumber($aPlaceTiger);
+                        $iRankAddress = 30;
                     }
                 }
-            } else {
+            }
+
+            if ($bDoInterpolation && $this->iMaxRank >= 30) {
+                $fDistance = $fSearchDiam;
+                if ($aPlace) {
+                    // We can't reliably go from the closest street to an
+                    // interpolation line because the closest interpolation
+                    // may have a different street segments as a parent.
+                    // Therefore allow an interpolation line to take precendence
+                    // even when the street is closer.
+                    $fDistance = $iRankAddress < 28 ? 0.001 : $aPlace['distance'];
+                }
+
+                $aHouse = $this->lookupInterpolation($sPointSQL, $fDistance);
+                Debug::printVar('Interpolation result', $aPlace);
+
+                if ($aHouse) {
+                    $oResult = new Result($aHouse['place_id'], Result::TABLE_OSMLINE);
+                    $oResult->iHouseNumber = closestHouseNumber($aHouse);
+                    $aPlace = $aHouse;
+                }
+            }
+
+            if (!$aPlace) {
                 // if no POI or street is found ...
                 $oResult = $this->lookupLargeArea($sPointSQL, 25);
             }
         } else {
             // lower than street level ($iMaxRank < 26 )
-            $oResult = $this->lookupLargeArea($sPointSQL, $iMaxRank);
+            $oResult = $this->lookupLargeArea($sPointSQL, $this->iMaxRank);
         }
+
+        Debug::printVar('Final result', $oResult);
         return $oResult;
     }
 }

lib-php/SearchContext.php

@@ -2,7 +2,7 @@
 
 namespace Nominatim;
 
-require_once(CONST_BasePath.'/lib/lib.php');
+require_once(CONST_LibDir.'/lib.php');
 
 
 /**
@@ -32,7 +32,18 @@ class SearchContext
     public $sqlCountryList = '';
     /// List of place IDs to exclude (as SQL).
     private $sqlExcludeList = '';
+    /// Subset of word ids of full words in the query.
+    private $aFullNameWords = array();
 
+    public function setFullNameWords($aWordList)
+    {
+        $this->aFullNameWords = $aWordList;
+    }
+
+    public function getFullNameTerms()
+    {
+        return $this->aFullNameWords;
+    }
 
     /**
      * Check if a reference point is defined.

lib-php/SearchDescription.php

@@ -2,9 +2,9 @@
 
 namespace Nominatim;
 
-require_once(CONST_BasePath.'/lib/SpecialSearchOperator.php');
-require_once(CONST_BasePath.'/lib/SearchContext.php');
-require_once(CONST_BasePath.'/lib/Result.php');
+require_once(CONST_LibDir.'/SpecialSearchOperator.php');
+require_once(CONST_LibDir.'/SearchContext.php');
+require_once(CONST_LibDir.'/Result.php');
 
 /**
  * Description of a single interpretation of a search query.
@@ -21,8 +21,6 @@ class SearchDescription
     private $bRareName = false;
     /// List of word ids making up the address of the object.
     private $aAddress = array();
-    /// Subset of word ids of full words making up the address.
-    private $aFullNameAddress = array();
     /// List of word ids that appear in the name but should be ignored.
     private $aNameNonSearch = array();
     /// List of word ids that appear in the address but should be ignored.
@@ -69,47 +67,6 @@ class SearchDescription
         return $this->iSearchRank;
     }
 
-    /**
-     * Make this search a POI search.
-     *
-     * In a POI search, objects are not (only) searched by their name
-     * but also by the primary OSM key/value pair (class and type in Nominatim).
-     *
-     * @param integer $iOperator Type of POI search
-     * @param string  $sClass    Class (or OSM tag key) of POI.
-     * @param string  $sType     Type (or OSM tag value) of POI.
-     *
-     * @return void
-     */
-    public function setPoiSearch($iOperator, $sClass, $sType)
-    {
-        $this->iOperator = $iOperator;
-        $this->sClass = $sClass;
-        $this->sType = $sType;
-    }
-
-    /**
-     * Check if this might be a full address search.
-     *
-     * @return bool True if the search contains name, address and housenumber.
-     */
-    public function looksLikeFullAddress()
-    {
-        return (!empty($this->aName))
-               && (!empty($this->aAddress) || $this->sCountryCode)
-               && preg_match('/[0-9]+/', $this->sHouseNumber);
-    }
-
-    /**
-     * Check if any operator is set.
-     *
-     * @return bool True, if this is a special search operation.
-     */
-    public function hasOperator()
-    {
-        return $this->iOperator != Operator::NONE;
-    }
-
     /**
      * Extract key/value pairs from a query.
      *
@@ -162,240 +119,234 @@ class SearchDescription
 
     /////////// Search building functions
 
-
     /**
-     * Derive new searches by adding a full term to the existing search.
+     * Create a copy of this search description adding to search rank.
      *
-     * @param object $oSearchTerm  Description of the token.
-     * @param bool   $bHasPartial  True if there are also tokens of partial terms
-     *                             with the same name.
-     * @param string $sPhraseType  Type of phrase the token is contained in.
-     * @param bool   $bFirstToken  True if the token is at the beginning of the
-     *                             query.
-     * @param bool   $bFirstPhrase True if the token is in the first phrase of
-     *                             the query.
-     * @param bool   $bLastToken   True if the token is at the end of the query.
+     * @param integer $iTermCost  Cost to add to the current search rank.
      *
-     * @return SearchDescription[] List of derived search descriptions.
+     * @return object Cloned search description.
      */
-    public function extendWithFullTerm($oSearchTerm, $bHasPartial, $sPhraseType, $bFirstToken, $bFirstPhrase, $bLastToken)
+    public function clone($iTermCost)
     {
-        $aNewSearches = array();
+        $oSearch = clone $this;
+        $oSearch->iSearchRank += $iTermCost;
 
-        if (($sPhraseType == '' || $sPhraseType == 'country')
-            && is_a($oSearchTerm, '\Nominatim\Token\Country')
-        ) {
-            if (!$this->sCountryCode) {
-                $oSearch = clone $this;
-                $oSearch->iSearchRank++;
-                $oSearch->sCountryCode = $oSearchTerm->sCountryCode;
-                // Country is almost always at the end of the string
-                // - increase score for finding it anywhere else (optimisation)
-                if (!$bLastToken) {
-                    $oSearch->iSearchRank += 5;
-                }
-                $aNewSearches[] = $oSearch;
-            }
-        } elseif (($sPhraseType == '' || $sPhraseType == 'postalcode')
-                  && is_a($oSearchTerm, '\Nominatim\Token\Postcode')
-        ) {
-            // We need to try the case where the postal code is the primary element
-            // (i.e. no way to tell if it is (postalcode, city) OR (city, postalcode)
-            // so try both.
-            if (!$this->sPostcode) {
-                // If we have structured search or this is the first term,
-                // make the postcode the primary search element.
-                if ($this->iOperator == Operator::NONE
-                    && ($sPhraseType == 'postalcode' || $bFirstToken)
-                ) {
-                    $oSearch = clone $this;
-                    $oSearch->iSearchRank++;
-                    $oSearch->iOperator = Operator::POSTCODE;
-                    $oSearch->aAddress = array_merge($this->aAddress, $this->aName);
-                    $oSearch->aName =
-                        array($oSearchTerm->iId => $oSearchTerm->sPostcode);
-                    $aNewSearches[] = $oSearch;
-                }
-
-                // If we have a structured search or this is not the first term,
-                // add the postcode as an addendum.
-                if ($this->iOperator != Operator::POSTCODE
-                    && ($sPhraseType == 'postalcode' || !empty($this->aName))
-                ) {
-                    $oSearch = clone $this;
-                    $oSearch->iSearchRank++;
-                    $oSearch->sPostcode = $oSearchTerm->sPostcode;
-                    $aNewSearches[] = $oSearch;
-                }
-            }
-        } elseif (($sPhraseType == '' || $sPhraseType == 'street')
-                 && is_a($oSearchTerm, '\Nominatim\Token\HouseNumber')
-        ) {
-            if (!$this->sHouseNumber && $this->iOperator != Operator::POSTCODE) {
-                $oSearch = clone $this;
-                $oSearch->iSearchRank++;
-                $oSearch->sHouseNumber = $oSearchTerm->sToken;
-                // sanity check: if the housenumber is not mainly made
-                // up of numbers, add a penalty
-                if (preg_match('/\\d/', $oSearch->sHouseNumber) === 0
-                    || preg_match_all('/[^0-9]/', $oSearch->sHouseNumber, $aMatches) > 2) {
-                    $oSearch->iSearchRank++;
-                }
-                if (empty($oSearchTerm->iId)) {
-                    $oSearch->iSearchRank++;
-                }
-                // also must not appear in the middle of the address
-                if (!empty($this->aAddress)
-                    || (!empty($this->aAddressNonSearch))
-                    || $this->sPostcode
-                ) {
-                    $oSearch->iSearchRank++;
-                }
-                $aNewSearches[] = $oSearch;
-            }
-        } elseif ($sPhraseType == ''
-                  && is_a($oSearchTerm, '\Nominatim\Token\SpecialTerm')
-        ) {
-            if ($this->iOperator == Operator::NONE) {
-                $oSearch = clone $this;
-                $oSearch->iSearchRank++;
-
-                $iOp = $oSearchTerm->iOperator;
-                if ($iOp == Operator::NONE) {
-                    if (!empty($this->aName) || $this->oContext->isBoundedSearch()) {
-                        $iOp = Operator::NAME;
-                    } else {
-                        $iOp = Operator::NEAR;
-                    }
-                    $oSearch->iSearchRank += 2;
-                }
-
-                $oSearch->setPoiSearch(
-                    $iOp,
-                    $oSearchTerm->sClass,
-                    $oSearchTerm->sType
-                );
-                $aNewSearches[] = $oSearch;
-            }
-        } elseif ($sPhraseType != 'country'
-                  && is_a($oSearchTerm, '\Nominatim\Token\Word')
-        ) {
-            $iWordID = $oSearchTerm->iId;
-            // Full words can only be a name if they appear at the beginning
-            // of the phrase. In structured search the name must forcably in
-            // the first phrase. In unstructured search it may be in a later
-            // phrase when the first phrase is a house number.
-            if (!empty($this->aName) || !($bFirstPhrase || $sPhraseType == '')) {
-                if (($sPhraseType == '' || !$bFirstPhrase) && !$bHasPartial) {
-                    $oSearch = clone $this;
-                    $oSearch->iSearchRank += 2;
-                    $oSearch->aAddress[$iWordID] = $iWordID;
-                    $aNewSearches[] = $oSearch;
-                } else {
-                    $this->aFullNameAddress[$iWordID] = $iWordID;
-                }
-            } else {
-                $oSearch = clone $this;
-                $oSearch->iSearchRank++;
-                $oSearch->aName = array($iWordID => $iWordID);
-                if (CONST_Search_NameOnlySearchFrequencyThreshold) {
-                    $oSearch->bRareName =
-                        $oSearchTerm->iSearchNameCount
-                          < CONST_Search_NameOnlySearchFrequencyThreshold;
-                }
-                $aNewSearches[] = $oSearch;
-            }
-        }
-
-        return $aNewSearches;
+        return $oSearch;
     }
 
     /**
-     * Derive new searches by adding a partial term to the existing search.
+     * Check if the search currently includes a name.
      *
-     * @param string  $sToken             Term for the token.
-     * @param object  $oSearchTerm        Description of the token.
-     * @param bool    $bStructuredPhrases True if the search is structured.
-     * @param integer $iPhrase            Number of the phrase the token is in.
-     * @param array[] $aFullTokens        List of full term tokens with the
-     *                                    same name.
+     * @param bool bIncludeNonNames  If true stop-word tokens are taken into
+     *                               account, too.
      *
-     * @return SearchDescription[] List of derived search descriptions.
+     * @return bool True, if search has a name.
      */
-    public function extendWithPartialTerm($sToken, $oSearchTerm, $bStructuredPhrases, $iPhrase, $aFullTokens)
+    public function hasName($bIncludeNonNames = false)
     {
-        // Only allow name terms.
-        if (!(is_a($oSearchTerm, '\Nominatim\Token\Word'))) {
-            return array();
+        return !empty($this->aName)
+               || (!empty($this->aNameNonSearch) && $bIncludeNonNames);
+    }
+
+    /**
+     * Check if the search currently includes an address term.
+     *
+     * @return bool True, if any address term is included, including stop-word
+     *              terms.
+     */
+    public function hasAddress()
+    {
+        return !empty($this->aAddress) || !empty($this->aAddressNonSearch);
+    }
+
+    /**
+     * Check if a country restriction is currently included in the search.
+     *
+     * @return bool True, if a country restriction is set.
+     */
+    public function hasCountry()
+    {
+        return $this->sCountryCode !== '';
+    }
+
+    /**
+     * Check if a postcode is currently included in the search.
+     *
+     * @return bool True, if a postcode is set.
+     */
+    public function hasPostcode()
+    {
+        return $this->sPostcode !== '';
+    }
+
+    /**
+     * Check if a house number is set for the search.
+     *
+     * @return bool True, if a house number is set.
+     */
+    public function hasHousenumber()
+    {
+        return $this->sHouseNumber !== '';
+    }
+
+    /**
+     * Check if a special type of place is requested.
+     *
+     * param integer iOperator  When set, check for the particular
+     *                          operator used for the special type.
+     *
+     * @return bool True, if speial type is requested or, if requested,
+     *              a special type with the given operator.
+     */
+    public function hasOperator($iOperator = null)
+    {
+        return $iOperator === null ? $this->iOperator != Operator::NONE : $this->iOperator == $iOperator;
+    }
+
+    /**
+     * Add the given token to the list of terms to search for in the address.
+     *
+     * @param integer iID       ID of term to add.
+     * @param bool bSearchable  Term should be used to search for result
+     *                          (i.e. term is not a stop word).
+     */
+    public function addAddressToken($iId, $bSearchable = true)
+    {
+        if ($bSearchable) {
+            $this->aAddress[$iId] = $iId;
+        } else {
+            $this->aAddressNonSearch[$iId] = $iId;
         }
+    }
 
-        $aNewSearches = array();
-        $iWordID = $oSearchTerm->iId;
+    /**
+     * Add the given full-word token to the list of terms to search for in the
+     * name.
+     *
+     * @param interger iId    ID of term to add.
+     * @param bool bRareName  True if the term is infrequent enough to not
+     *                        require other constraints for efficient search.
+     */
+    public function addNameToken($iId, $bRareName)
+    {
+        $this->aName[$iId] = $iId;
+        $this->bRareName = $bRareName;
+    }
 
-        if ((!$bStructuredPhrases || $iPhrase > 0)
-            && (!empty($this->aName))
-            && strpos($sToken, ' ') === false
-        ) {
-            if ($oSearchTerm->iSearchNameCount < CONST_Max_Word_Frequency) {
-                $oSearch = clone $this;
-                $oSearch->iSearchRank += 2;
-                $oSearch->aAddress[$iWordID] = $iWordID;
-                $aNewSearches[] = $oSearch;
-            } else {
-                $oSearch = clone $this;
-                $oSearch->iSearchRank++;
-                $oSearch->aAddressNonSearch[$iWordID] = $iWordID;
-                if (preg_match('#^[0-9]+$#', $sToken)) {
-                    $oSearch->iSearchRank += 2;
-                }
-                if (!empty($aFullTokens)) {
-                    $oSearch->iSearchRank++;
-                }
-                $aNewSearches[] = $oSearch;
-
-                // revert to the token version?
-                foreach ($aFullTokens as $oSearchTermToken) {
-                    if (is_a($oSearchTermToken, '\Nominatim\Token\Word')) {
-                        $oSearch = clone $this;
-                        $oSearch->iSearchRank++;
-                        $oSearch->aAddress[$oSearchTermToken->iId]
-                            = $oSearchTermToken->iId;
-                        $aNewSearches[] = $oSearch;
-                    }
-                }
-            }
+    /**
+     * Add the given partial token to the list of terms to search for in
+     * the name.
+     *
+     * @param integer iID            ID of term to add.
+     * @param bool bSearchable       Term should be used to search for result
+     *                               (i.e. term is not a stop word).
+     * @param integer iPhraseNumber  Index of phrase, where the partial term
+     *                               appears.
+     */
+    public function addPartialNameToken($iId, $bSearchable, $iPhraseNumber)
+    {
+        if ($bSearchable) {
+            $this->aName[$iId] = $iId;
+        } else {
+            $this->aNameNonSearch[$iId] = $iId;
         }
+        $this->iNamePhrase = $iPhraseNumber;
+    }
 
-        if ((!$this->sPostcode && !$this->aAddress && !$this->aAddressNonSearch)
-            && (empty($this->aName) || $this->iNamePhrase == $iPhrase)
-        ) {
-            $oSearch = clone $this;
-            $oSearch->iSearchRank += 2;
-            if (empty($this->aName)) {
-                $oSearch->iSearchRank += 1;
-            }
-            if (preg_match('#^[0-9]+$#', $sToken)) {
-                $oSearch->iSearchRank += 2;
-            }
-            if ($oSearchTerm->iSearchNameCount < CONST_Max_Word_Frequency) {
-                if (empty($this->aName)
-                    && CONST_Search_NameOnlySearchFrequencyThreshold
-                ) {
-                    $oSearch->bRareName =
-                        $oSearchTerm->iSearchNameCount
-                          < CONST_Search_NameOnlySearchFrequencyThreshold;
-                } else {
-                    $oSearch->bRareName = false;
-                }
-                $oSearch->aName[$iWordID] = $iWordID;
-            } else {
-                $oSearch->aNameNonSearch[$iWordID] = $iWordID;
-            }
-            $oSearch->iNamePhrase = $iPhrase;
-            $aNewSearches[] = $oSearch;
-        }
+    /**
+     * Set country restriction for the search.
+     *
+     * @param string sCountryCode  Country code of country to restrict search to.
+     */
+    public function setCountry($sCountryCode)
+    {
+        $this->sCountryCode = $sCountryCode;
+        $this->iNamePhrase = -1;
+    }
 
-        return $aNewSearches;
+    /**
+     * Set postcode search constraint.
+     *
+     * @param string sPostcode  Postcode the result should have.
+     */
+    public function setPostcode($sPostcode)
+    {
+        $this->sPostcode = $sPostcode;
+        $this->iNamePhrase = -1;
+    }
+
+    /**
+     * Make this search a search for a postcode object.
+     *
+     * @param integer iId       Token Id for the postcode.
+     * @param string sPostcode  Postcode to look for.
+     */
+    public function setPostcodeAsName($iId, $sPostcode)
+    {
+        $this->iOperator = Operator::POSTCODE;
+        $this->aAddress = array_merge($this->aAddress, $this->aName);
+        $this->aName = array($iId => $sPostcode);
+        $this->bRareName = true;
+        $this->iNamePhrase = -1;
+    }
+
+    /**
+     * Set house number search cnstraint.
+     *
+     * @param string sNumber  House number the result should have.
+     */
+    public function setHousenumber($sNumber)
+    {
+        $this->sHouseNumber = $sNumber;
+        $this->iNamePhrase = -1;
+    }
+
+    /**
+     * Make this search a search for a house number.
+     *
+     * @param integer iId  Token Id for the house number.
+     */
+    public function setHousenumberAsName($iId)
+    {
+        $this->aAddress = array_merge($this->aAddress, $this->aName);
+        $this->bRareName = false;
+        $this->aName = array($iId => $iId);
+        $this->iNamePhrase = -1;
+    }
+
+    /**
+     * Make this search a POI search.
+     *
+     * In a POI search, objects are not (only) searched by their name
+     * but also by the primary OSM key/value pair (class and type in Nominatim).
+     *
+     * @param integer $iOperator Type of POI search
+     * @param string  $sClass    Class (or OSM tag key) of POI.
+     * @param string  $sType     Type (or OSM tag value) of POI.
+     *
+     * @return void
+     */
+    public function setPoiSearch($iOperator, $sClass, $sType)
+    {
+        $this->iOperator = $iOperator;
+        $this->sClass = $sClass;
+        $this->sType = $sType;
+        $this->iNamePhrase = -1;
+    }
+
+    public function getNamePhrase()
+    {
+        return $this->iNamePhrase;
+    }
+
+    /**
+     * Get the global search context.
+     *
+     * @return object  Objects of global search constraints.
+     */
+    public function getContext()
+    {
+        return $this->oContext;
     }
 
     /////////// Query functions
@@ -416,7 +367,6 @@ class SearchDescription
     public function query(&$oDB, $iMinRank, $iMaxRank, $iLimit)
     {
         $aResults = array();
-        $iHousenumber = -1;
 
         if ($this->sCountryCode
             && empty($this->aName)
@@ -449,19 +399,24 @@ class SearchDescription
 
             // Now search for housenumber, if housenumber provided. Can be zero.
             if (($this->sHouseNumber || $this->sHouseNumber === '0') && !empty($aResults)) {
-                // Downgrade the rank of the street results, they are missing
-                // the housenumber.
-                foreach ($aResults as $oRes) {
-                    $oRes->iResultRank++;
-                }
-
                 $aHnResults = $this->queryHouseNumber($oDB, $aResults);
 
-                if (!empty($aHnResults)) {
-                    foreach ($aHnResults as $oRes) {
-                        $aResults[$oRes->iId] = $oRes;
+                // Downgrade the rank of the street results, they are missing
+                // the housenumber. Also drop POI places (rank 30) here, they
+                // cannot be a parent place and therefore must not be shown
+                // as a result for a search with a missing housenumber.
+                foreach ($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
@@ -613,14 +568,14 @@ class SearchDescription
         // too many results are expected for the street, i.e. if the result
         // will be narrowed down by an address. Remeber that with ordering
         // every single result has to be checked.
-        if ($this->sHouseNumber && (!empty($this->aAddress) || $this->sPostcode)) {
+        if ($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';
-            $aOrder[0] .= "    AND transliteration(housenumber) ~* E'".$sHouseNumberRegex."'";
+            $aOrder[0] .= "    AND housenumber ~* E'".$sHouseNumberRegex."'";
             $aOrder[0] .= '  LIMIT 1';
             $aOrder[0] .= ') ';
             // also housenumbers from interpolation lines table are needed
@@ -657,7 +612,7 @@ class SearchDescription
         }
 
         if ($this->sHouseNumber) {
-            $aTerms[] = 'address_rank between 16 and 27';
+            $aTerms[] = 'address_rank between 16 and 30';
         } elseif (!$this->sClass || $this->iOperator == Operator::NAME) {
             if ($iMinAddressRank > 0) {
                 $aTerms[] = "((address_rank between $iMinAddressRank and $iMaxAddressRank) or (search_rank between $iMinAddressRank and $iMaxAddressRank))";
@@ -696,10 +651,11 @@ class SearchDescription
         $sImportanceSQL .= $this->oContext->viewboxImportanceSQL('centroid');
         $aOrder[] = "$sImportanceSQL DESC";
 
-        if (!empty($this->aFullNameAddress)) {
+        $aFullNameAddress = $this->oContext->getFullNameTerms();
+        if (!empty($aFullNameAddress)) {
             $sExactMatchSQL = ' ( ';
             $sExactMatchSQL .= ' SELECT count(*) FROM ( ';
-            $sExactMatchSQL .= '  SELECT unnest('.$oDB->getArraySQL($this->aFullNameAddress).')';
+            $sExactMatchSQL .= '  SELECT unnest('.$oDB->getArraySQL($aFullNameAddress).')';
             $sExactMatchSQL .= '    INTERSECT ';
             $sExactMatchSQL .= '  SELECT unnest(nameaddress_vector)';
             $sExactMatchSQL .= ' ) s';
@@ -716,7 +672,7 @@ class SearchDescription
         $aResults = array();
 
         if (!empty($aTerms)) {
-            $sSQL = 'SELECT place_id,'.$sExactMatchSQL;
+            $sSQL = 'SELECT place_id, address_rank,'.$sExactMatchSQL;
             $sSQL .= ' FROM search_name';
             $sSQL .= ' WHERE '.join(' and ', $aTerms);
             $sSQL .= ' ORDER BY '.join(', ', $aOrder);
@@ -729,6 +685,7 @@ class SearchDescription
             foreach ($aDBResults as $aResult) {
                 $oResult = new Result($aResult['place_id']);
                 $oResult->iExactMatches = $aResult['exactmatch'];
+                $oResult->iAddressRank = $aResult['address_rank'];
                 $aResults[$aResult['place_id']] = $oResult;
             }
         }
@@ -739,16 +696,33 @@ class SearchDescription
     private function queryHouseNumber(&$oDB, $aRoadPlaceIDs)
     {
         $aResults = array();
-        $sPlaceIDs = Result::joinIdsByTable($aRoadPlaceIDs, Result::TABLE_PLACEX);
+        $sRoadPlaceIDs = Result::joinIdsByTableMaxRank(
+            $aRoadPlaceIDs,
+            Result::TABLE_PLACEX,
+            27
+        );
+        $sPOIPlaceIDs = Result::joinIdsByTableMinRank(
+            $aRoadPlaceIDs,
+            Result::TABLE_PLACEX,
+            30
+        );
 
-        if (!$sPlaceIDs) {
+        $aIDCondition = array();
+        if ($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 ';
-        $sSQL .= 'WHERE parent_place_id in ('.$sPlaceIDs.')';
-        $sSQL .= "  AND transliteration(housenumber) ~* E'".$sHouseNumberRegex."'";
+        $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);
@@ -760,11 +734,11 @@ class SearchDescription
 
         $bIsIntHouseNumber= (bool) preg_match('/[0-9]+/', $this->sHouseNumber);
         $iHousenumber = intval($this->sHouseNumber);
-        if ($bIsIntHouseNumber && empty($aResults)) {
+        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';
-            $sSQL .= '  AND parent_place_id in ('.$sPlaceIDs.') AND (';
+            $sSQL .= '  AND parent_place_id in ('.$sRoadPlaceIDs.') AND (';
             if ($iHousenumber % 2 == 0) {
                 // If housenumber is even, look for housenumber in streets
                 // with interpolationtype even or all.
@@ -787,24 +761,10 @@ class SearchDescription
             }
         }
 
-        // If nothing found try the aux fallback table
-        if (CONST_Use_Aux_Location_data && empty($aResults)) {
-            $sSQL = 'SELECT place_id FROM location_property_aux';
-            $sSQL .= ' WHERE parent_place_id in ('.$sPlaceIDs.')';
-            $sSQL .= " AND housenumber = '".$this->sHouseNumber."'";
-            $sSQL .= $this->oContext->excludeSQL(' AND place_id');
-
-            Debug::printSQL($sSQL);
-
-            foreach ($oDB->getCol($sSQL) as $iPlaceId) {
-                $aResults[$iPlaceId] = new Result($iPlaceId, Result::TABLE_AUX);
-            }
-        }
-
         // If nothing found then search in Tiger data (location_property_tiger)
-        if (CONST_Use_US_Tiger_Data && $bIsIntHouseNumber && empty($aResults)) {
+        if (CONST_Use_US_Tiger_Data && $sRoadPlaceIDs && $bIsIntHouseNumber && empty($aResults)) {
             $sSQL = 'SELECT place_id FROM location_property_tiger';
-            $sSQL .= ' WHERE parent_place_id in ('.$sPlaceIDs.') and (';
+            $sSQL .= ' WHERE parent_place_id in ('.$sRoadPlaceIDs.') and (';
             if ($iHousenumber % 2 == 0) {
                 $sSQL .= "interpolationtype='even'";
             } else {
@@ -1016,7 +976,7 @@ class SearchDescription
                 'Name terms (stop words)' => $this->aNameNonSearch,
                 'Address terms' => $this->aAddress,
                 'Address terms (stop words)' => $this->aAddressNonSearch,
-                'Address terms (full words)' => $this->aFullNameAddress,
+                'Address terms (full words)' => $this->aFullNameAddress ?? '',
                 'Special search' => $this->iOperator,
                 'Class' => $this->sClass,
                 'Type' => $this->sType,
@@ -1028,7 +988,7 @@ class SearchDescription
     public function dumpAsHtmlTableRow(&$aWordIDs)
     {
         $kf = function ($k) use (&$aWordIDs) {
-            return $aWordIDs[$k];
+            return $aWordIDs[$k] ?? '['.$k.']';
         };
 
         echo '<tr>';

lib-php/SearchPosition.php

@@ -0,0 +1,87 @@
+<?php
+
+namespace Nominatim;
+
+/**
+ * Description of the position of a token within a query.
+ */
+class SearchPosition
+{
+    private $sPhraseType;
+
+    private $iPhrase;
+    private $iNumPhrases;
+
+    private $iToken;
+    private $iNumTokens;
+
+
+    public function __construct($sPhraseType, $iPhrase, $iNumPhrases)
+    {
+        $this->sPhraseType = $sPhraseType;
+        $this->iPhrase = $iPhrase;
+        $this->iNumPhrases = $iNumPhrases;
+    }
+
+    public function setTokenPosition($iToken, $iNumTokens)
+    {
+        $this->iToken = $iToken;
+        $this->iNumTokens = $iNumTokens;
+    }
+
+    /**
+     * Check if the phrase can be of the given type.
+     *
+     * @param string  $sType  Type of phrse requested.
+     *
+     * @return True if the phrase is untyped or of the given type.
+     */
+    public function maybePhrase($sType)
+    {
+        return $this->sPhraseType == '' || $this->sPhraseType == $sType;
+    }
+
+    /**
+     * Check if the phrase is exactly of the given type.
+     *
+     * @param string  $sType  Type of phrse requested.
+     *
+     * @return True if the phrase of the given type.
+     */
+    public function isPhrase($sType)
+    {
+        return $this->sPhraseType == $sType;
+    }
+
+    /**
+     * Return true if the token is the very first in the query.
+     */
+    public function isFirstToken()
+    {
+        return $this->iPhrase == 0 && $this->iToken == 0;
+    }
+
+    /**
+     * Check if the token is the final one in the query.
+     */
+    public function isLastToken()
+    {
+        return $this->iToken + 1 == $this->iNumTokens && $this->iPhrase + 1 == $this->iNumPhrases;
+    }
+
+    /**
+     * Check if the current token is part of the first phrase in the query.
+     */
+    public function isFirstPhrase()
+    {
+        return $this->iPhrase == 0;
+    }
+
+    /**
+     * Get the phrase position in the query.
+     */
+    public function getPhrase()
+    {
+        return $this->iPhrase;
+    }
+}

lib-php/Shell.php

@@ -7,7 +7,7 @@ class Shell
     public function __construct($sBaseCmd, ...$aParams)
     {
         if (!$sBaseCmd) {
-            throw new Exception('Command missing in new() call');
+            throw new \Exception('Command missing in new() call');
         }
         $this->baseCmd = $sBaseCmd;
         $this->aParams = array();
@@ -33,7 +33,9 @@ class Shell
     public function addEnvPair($sKey, $sVal)
     {
         if (isset($sKey) && $sKey && isset($sVal)) {
-            if (!isset($this->aEnv)) $this->aEnv = $_ENV;
+            if (!isset($this->aEnv)) {
+                $this->aEnv = $_ENV;
+            }
             $this->aEnv = array_merge($this->aEnv, array($sKey => $sVal), $_ENV);
         }
         return $this;
@@ -48,7 +50,7 @@ class Shell
         return join(' ', $aEscaped);
     }
 
-    public function run()
+    public function run($bExitOnFail = false)
     {
         $sCmd = $this->escapedCmd();
         // $aEnv does not need escaping, proc_open seems to handle it fine
@@ -67,14 +69,16 @@ class Shell
         fclose($aPipes[0]); // no stdin
 
         $iStat = proc_close($hProc);
+
+        if ($iStat != 0 && $bExitOnFail) {
+            exit($iStat);
+        }
+
         return $iStat;
     }
 
-
-
     private function escapeParam($sParam)
     {
-        if (preg_match('/^-*\w+$/', $sParam)) return $sParam;
-        return escapeshellarg($sParam);
+        return (preg_match('/^-*\w+$/', $sParam)) ? $sParam : escapeshellarg($sParam);
     }
 }

lib-php/Status.php

@@ -0,0 +1,51 @@
+<?php
+
+namespace Nominatim;
+
+require_once(CONST_TokenizerDir.'/tokenizer.php');
+
+use Exception;
+
+class Status
+{
+    protected $oDB;
+
+    public function __construct(&$oDB)
+    {
+        $this->oDB =& $oDB;
+    }
+
+    public function status()
+    {
+        if (!$this->oDB) {
+            throw new Exception('No database', 700);
+        }
+
+        try {
+            $this->oDB->connect();
+        } catch (\Nominatim\DatabaseError $e) {
+            throw new Exception('Database connection failed', 700);
+        }
+
+        $oTokenizer = new \Nominatim\Tokenizer($this->oDB);
+        $oTokenizer->checkStatus();
+    }
+
+    public function dataDate()
+    {
+        $sSQL = 'SELECT EXTRACT(EPOCH FROM lastimportdate) FROM import_status LIMIT 1';
+        $iDataDateEpoch = $this->oDB->getOne($sSQL);
+
+        if ($iDataDateEpoch === false) {
+            throw new Exception('Import date is not available', 705);
+        }
+
+        return $iDataDateEpoch;
+    }
+
+    public function databaseVersion()
+    {
+        $sSQL = 'SELECT value FROM nominatim_properties WHERE property = \'database_version\'';
+        return $this->oDB->getOne($sSQL);
+    }
+}

lib-php/TokenCountry.php

@@ -0,0 +1,72 @@
+<?php
+
+namespace Nominatim\Token;
+
+/**
+ * A country token.
+ */
+class Country
+{
+    /// Database word id, if available.
+    private $iId;
+    /// Two-letter country code (lower-cased).
+    private $sCountryCode;
+
+    public function __construct($iId, $sCountryCode)
+    {
+        $this->iId = $iId;
+        $this->sCountryCode = $sCountryCode;
+    }
+
+    public function getId()
+    {
+        return $this->iId;
+    }
+
+    /**
+     * Check if the token can be added to the given search.
+     * Derive new searches by adding this token to an existing search.
+     *
+     * @param object  $oSearch      Partial search description derived so far.
+     * @param object  $oPosition    Description of the token position within
+                                    the query.
+     *
+     * @return True if the token is compatible with the search configuration
+     *         given the position.
+     */
+    public function isExtendable($oSearch, $oPosition)
+    {
+        return !$oSearch->hasCountry() && $oPosition->maybePhrase('country');
+    }
+
+    /**
+     * Derive new searches by adding this token to an existing search.
+     *
+     * @param object  $oSearch      Partial search description derived so far.
+     * @param object  $oPosition    Description of the token position within
+                                    the query.
+     *
+     * @return SearchDescription[] List of derived search descriptions.
+     */
+    public function extendSearch($oSearch, $oPosition)
+    {
+        $oNewSearch = $oSearch->clone($oPosition->isLastToken() ? 1 : 6);
+        $oNewSearch->setCountry($this->sCountryCode);
+
+        return array($oNewSearch);
+    }
+
+    public function debugInfo()
+    {
+        return array(
+                'ID' => $this->iId,
+                'Type' => 'country',
+                'Info' => $this->sCountryCode
+               );
+    }
+
+    public function debugCode()
+    {
+        return 'C';
+    }
+}

lib-php/TokenHousenumber.php

@@ -0,0 +1,108 @@
+<?php
+
+namespace Nominatim\Token;
+
+/**
+ * A house number token.
+ */
+class HouseNumber
+{
+    /// Database word id, if available.
+    private $iId;
+    /// Normalized house number.
+    private $sToken;
+
+    public function __construct($iId, $sToken)
+    {
+        $this->iId = $iId;
+        $this->sToken = $sToken;
+    }
+
+    public function getId()
+    {
+        return $this->iId;
+    }
+
+    /**
+     * Check if the token can be added to the given search.
+     * Derive new searches by adding this token to an existing search.
+     *
+     * @param object  $oSearch      Partial search description derived so far.
+     * @param object  $oPosition    Description of the token position within
+                                    the query.
+     *
+     * @return True if the token is compatible with the search configuration
+     *         given the position.
+     */
+    public function isExtendable($oSearch, $oPosition)
+    {
+        return !$oSearch->hasHousenumber()
+               && !$oSearch->hasOperator(\Nominatim\Operator::POSTCODE)
+               && $oPosition->maybePhrase('street');
+    }
+
+    /**
+     * Derive new searches by adding this token to an existing search.
+     *
+     * @param object  $oSearch      Partial search description derived so far.
+     * @param object  $oPosition    Description of the token position within
+                                    the query.
+     *
+     * @return SearchDescription[] List of derived search descriptions.
+     */
+    public function extendSearch($oSearch, $oPosition)
+    {
+        $aNewSearches = array();
+
+        // sanity check: if the housenumber is not mainly made
+        // up of numbers, add a penalty
+        $iSearchCost = 1;
+        if (preg_match('/\\d/', $this->sToken) === 0
+            || preg_match_all('/[^0-9]/', $this->sToken, $aMatches) > 2) {
+            $iSearchCost++;
+        }
+        if (!$oSearch->hasOperator(\Nominatim\Operator::NONE)) {
+            $iSearchCost++;
+        }
+        if (empty($this->iId)) {
+            $iSearchCost++;
+        }
+        // also must not appear in the middle of the address
+        if ($oSearch->hasAddress() || $oSearch->hasPostcode()) {
+            $iSearchCost++;
+        }
+
+        $oNewSearch = $oSearch->clone($iSearchCost);
+        $oNewSearch->setHousenumber($this->sToken);
+        $aNewSearches[] = $oNewSearch;
+
+        // Housenumbers may appear in the name when the place has its own
+        // address terms.
+        if ($this->iId !== null
+            && ($oSearch->getNamePhrase() >= 0 || !$oSearch->hasName())
+            && !$oSearch->hasAddress()
+        ) {
+            $oNewSearch = $oSearch->clone($iSearchCost);
+            $oNewSearch->setHousenumberAsName($this->iId);
+
+            $aNewSearches[] = $oNewSearch;
+        }
+
+        return $aNewSearches;
+    }
+
+
+    public function debugInfo()
+    {
+        return array(
+                'ID' => $this->iId,
+                'Type' => 'house number',
+                'Info' => array('nr' => $this->sToken)
+               );
+    }
+
+    public function debugCode()
+    {
+        return 'H';
+    }
+}

lib-php/TokenList.php

@@ -0,0 +1,126 @@
+<?php
+
+namespace Nominatim;
+
+require_once(CONST_LibDir.'/TokenCountry.php');
+require_once(CONST_LibDir.'/TokenHousenumber.php');
+require_once(CONST_LibDir.'/TokenPostcode.php');
+require_once(CONST_LibDir.'/TokenSpecialTerm.php');
+require_once(CONST_LibDir.'/TokenWord.php');
+require_once(CONST_LibDir.'/TokenPartial.php');
+require_once(CONST_LibDir.'/SpecialSearchOperator.php');
+
+/**
+ * Saves information about the tokens that appear in a search query.
+ *
+ * Tokens are sorted by their normalized form, the token word. There are different
+ * kinds of tokens, represented by different Token* classes. Note that
+ * tokens do not have a common base class. All tokens need to have a field
+ * with the word id that points to an entry in the `word` database table
+ * but otherwise the information saved about a token can be very different.
+ */
+class TokenList
+{
+    // List of list of tokens indexed by their word_token.
+    private $aTokens = array();
+
+
+    /**
+     * Return total number of tokens.
+     *
+     * @return Integer
+     */
+    public function count()
+    {
+        return count($this->aTokens);
+    }
+
+    /**
+     * Check if there are tokens for the given token word.
+     *
+     * @param string $sWord Token word to look for.
+     *
+     * @return bool True if there is one or more token for the token word.
+     */
+    public function contains($sWord)
+    {
+        return isset($this->aTokens[$sWord]);
+    }
+
+    /**
+     * Check if there are partial or full tokens for the given word.
+     *
+     * @param string $sWord Token word to look for.
+     *
+     * @return bool True if there is one or more token for the token word.
+     */
+    public function containsAny($sWord)
+    {
+        return isset($this->aTokens[$sWord]);
+    }
+
+    /**
+     * Get the list of tokens for the given token word.
+     *
+     * @param string $sWord Token word to look for.
+     *
+     * @return object[] Array of tokens for the given token word or an
+     *                  empty array if no tokens could be found.
+     */
+    public function get($sWord)
+    {
+        return isset($this->aTokens[$sWord]) ? $this->aTokens[$sWord] : array();
+    }
+
+    public function getFullWordIDs()
+    {
+        $ids = array();
+
+        foreach ($this->aTokens as $aTokenList) {
+            foreach ($aTokenList as $oToken) {
+                if (is_a($oToken, '\Nominatim\Token\Word')) {
+                    $ids[$oToken->getId()] = $oToken->getId();
+                }
+            }
+        }
+
+        return $ids;
+    }
+
+    /**
+     * Add a new token for the given word.
+     *
+     * @param string $sWord  Word the token describes.
+     * @param object $oToken Token object to add.
+     *
+     * @return void
+     */
+    public function addToken($sWord, $oToken)
+    {
+        if (isset($this->aTokens[$sWord])) {
+            $this->aTokens[$sWord][] = $oToken;
+        } else {
+            $this->aTokens[$sWord] = array($oToken);
+        }
+    }
+
+    public function debugTokenByWordIdList()
+    {
+        $aWordsIDs = array();
+        foreach ($this->aTokens as $sToken => $aWords) {
+            foreach ($aWords as $aToken) {
+                $iId = $aToken->getId();
+                if ($iId !== null) {
+                    $aWordsIDs[$iId] = '#'.$sToken.'('.$aToken->debugCode().' '.$iId.')#';
+                }
+            }
+        }
+
+        return $aWordsIDs;
+    }
+
+    public function debugInfo()
+    {
+        return $this->aTokens;
+    }
+}

lib-php/TokenPartial.php

@@ -0,0 +1,118 @@
+<?php
+
+namespace Nominatim\Token;
+
+/**
+ * A standard word token.
+ */
+class Partial
+{
+    /// Database word id, if applicable.
+    private $iId;
+    /// Number of appearances in the database.
+    private $iSearchNameCount;
+    /// True, if the token consists exclusively of digits and spaces.
+    private $bNumberToken;
+
+    public function __construct($iId, $sToken, $iSearchNameCount)
+    {
+        $this->iId = $iId;
+        $this->bNumberToken = (bool) preg_match('#^[0-9 ]+$#', $sToken);
+        $this->iSearchNameCount = $iSearchNameCount;
+    }
+
+    public function getId()
+    {
+        return $this->iId;
+    }
+
+    /**
+     * Check if the token can be added to the given search.
+     * Derive new searches by adding this token to an existing search.
+     *
+     * @param object  $oSearch      Partial search description derived so far.
+     * @param object  $oPosition    Description of the token position within
+                                    the query.
+     *
+     * @return True if the token is compatible with the search configuration
+     *         given the position.
+     */
+    public function isExtendable($oSearch, $oPosition)
+    {
+        return !$oPosition->isPhrase('country');
+    }
+
+    /**
+     * Derive new searches by adding this token to an existing search.
+     *
+     * @param object  $oSearch      Partial search description derived so far.
+     * @param object  $oPosition    Description of the token position within
+                                    the query.
+     *
+     * @return SearchDescription[] List of derived search descriptions.
+     */
+    public function extendSearch($oSearch, $oPosition)
+    {
+        $aNewSearches = array();
+
+        // Partial token in Address.
+        if (($oPosition->isPhrase('') || !$oPosition->isFirstPhrase())
+            && $oSearch->hasName()
+        ) {
+            $iSearchCost = $this->bNumberToken ? 2 : 1;
+            if ($this->iSearchNameCount >= CONST_Max_Word_Frequency) {
+                $iSearchCost += 1;
+            }
+
+            $oNewSearch = $oSearch->clone($iSearchCost);
+            $oNewSearch->addAddressToken(
+                $this->iId,
+                $this->iSearchNameCount < CONST_Max_Word_Frequency
+            );
+
+            $aNewSearches[] = $oNewSearch;
+        }
+
+        // Partial token in Name.
+        if ((!$oSearch->hasPostcode() && !$oSearch->hasAddress())
+            && (!$oSearch->hasName(true)
+                || $oSearch->getNamePhrase() == $oPosition->getPhrase())
+        ) {
+            $iSearchCost = 1;
+            if (!$oSearch->hasName(true)) {
+                $iSearchCost += 1;
+            }
+            if ($this->bNumberToken) {
+                $iSearchCost += 1;
+            }
+
+            $oNewSearch = $oSearch->clone($iSearchCost);
+            $oNewSearch->addPartialNameToken(
+                $this->iId,
+                $this->iSearchNameCount < CONST_Max_Word_Frequency,
+                $oPosition->getPhrase()
+            );
+
+            $aNewSearches[] = $oNewSearch;
+        }
+
+        return $aNewSearches;
+    }
+
+
+    public function debugInfo()
+    {
+        return array(
+                'ID' => $this->iId,
+                'Type' => 'partial',
+                'Info' => array(
+                           'count' => $this->iSearchNameCount
+                          )
+               );
+    }
+
+    public function debugCode()
+    {
+        return 'w';
+    }
+}

lib-php/TokenPostcode.php

@@ -0,0 +1,98 @@
+<?php
+
+namespace Nominatim\Token;
+
+/**
+ * A postcode token.
+ */
+class Postcode
+{
+    /// Database word id, if available.
+    private $iId;
+    /// Full nomralized postcode (upper cased).
+    private $sPostcode;
+    // Optional country code the postcode belongs to (currently unused).
+    private $sCountryCode;
+
+    public function __construct($iId, $sPostcode, $sCountryCode = '')
+    {
+        $this->iId = $iId;
+        $this->sPostcode = $sPostcode;
+        $this->sCountryCode = empty($sCountryCode) ? '' : $sCountryCode;
+    }
+
+    public function getId()
+    {
+        return $this->iId;
+    }
+
+    /**
+     * Check if the token can be added to the given search.
+     * Derive new searches by adding this token to an existing search.
+     *
+     * @param object  $oSearch      Partial search description derived so far.
+     * @param object  $oPosition    Description of the token position within
+                                    the query.
+     *
+     * @return True if the token is compatible with the search configuration
+     *         given the position.
+     */
+    public function isExtendable($oSearch, $oPosition)
+    {
+        return !$oSearch->hasPostcode() && $oPosition->maybePhrase('postalcode');
+    }
+
+    /**
+     * Derive new searches by adding this token to an existing search.
+     *
+     * @param object  $oSearch      Partial search description derived so far.
+     * @param object  $oPosition    Description of the token position within
+                                    the query.
+     *
+     * @return SearchDescription[] List of derived search descriptions.
+     */
+    public function extendSearch($oSearch, $oPosition)
+    {
+        $aNewSearches = array();
+
+        // If we have structured search or this is the first term,
+        // make the postcode the primary search element.
+        if ($oSearch->hasOperator(\Nominatim\Operator::NONE) && $oPosition->isFirstToken()) {
+            $oNewSearch = $oSearch->clone(1);
+            $oNewSearch->setPostcodeAsName($this->iId, $this->sPostcode);
+
+            $aNewSearches[] = $oNewSearch;
+        }
+
+        // If we have a structured search or this is not the first term,
+        // add the postcode as an addendum.
+        if (!$oSearch->hasOperator(\Nominatim\Operator::POSTCODE)
+            && ($oPosition->isPhrase('postalcode') || $oSearch->hasName())
+        ) {
+            $iPenalty = 1;
+            if (strlen($this->sPostcode) < 4) {
+                $iPenalty += 4 - strlen($this->sPostcode);
+            }
+            $oNewSearch = $oSearch->clone($iPenalty);
+            $oNewSearch->setPostcode($this->sPostcode);
+
+            $aNewSearches[] = $oNewSearch;
+        }
+
+        return $aNewSearches;
+    }
+
+    public function debugInfo()
+    {
+        return array(
+                'ID' => $this->iId,
+                'Type' => 'postcode',
+                'Info' => $this->sPostcode.'('.$this->sCountryCode.')'
+               );
+    }
+
+    public function debugCode()
+    {
+        return 'P';
+    }
+}

lib-php/TokenSpecialTerm.php

@@ -0,0 +1,102 @@
+<?php
+
+namespace Nominatim\Token;
+
+require_once(CONST_LibDir.'/SpecialSearchOperator.php');
+
+/**
+ * A word token describing a place type.
+ */
+class SpecialTerm
+{
+    /// Database word id, if applicable.
+    private $iId;
+    /// Class (or OSM tag key) of the place to look for.
+    private $sClass;
+    /// Type (or OSM tag value) of the place to look for.
+    private $sType;
+    /// Relationship of the operator to the object (see Operator class).
+    private $iOperator;
+
+    public function __construct($iID, $sClass, $sType, $iOperator)
+    {
+        $this->iId = $iID;
+        $this->sClass = $sClass;
+        $this->sType = $sType;
+        $this->iOperator = $iOperator;
+    }
+
+    public function getId()
+    {
+        return $this->iId;
+    }
+
+    /**
+     * Check if the token can be added to the given search.
+     * Derive new searches by adding this token to an existing search.
+     *
+     * @param object  $oSearch      Partial search description derived so far.
+     * @param object  $oPosition    Description of the token position within
+                                    the query.
+     *
+     * @return True if the token is compatible with the search configuration
+     *         given the position.
+     */
+    public function isExtendable($oSearch, $oPosition)
+    {
+        return !$oSearch->hasOperator() && $oPosition->isPhrase('');
+    }
+
+    /**
+     * Derive new searches by adding this token to an existing search.
+     *
+     * @param object  $oSearch      Partial search description derived so far.
+     * @param object  $oPosition    Description of the token position within
+                                    the query.
+     *
+     * @return SearchDescription[] List of derived search descriptions.
+     */
+    public function extendSearch($oSearch, $oPosition)
+    {
+        $iSearchCost = 2;
+
+        $iOp = $this->iOperator;
+        if ($iOp == \Nominatim\Operator::NONE) {
+            if ($oSearch->hasName() || $oSearch->getContext()->isBoundedSearch()) {
+                $iOp = \Nominatim\Operator::NAME;
+            } else {
+                $iOp = \Nominatim\Operator::NEAR;
+            }
+            $iSearchCost += 2;
+        } elseif (!$oPosition->isFirstToken() && !$oPosition->isLastToken()) {
+            $iSearchCost += 2;
+        }
+        if ($oSearch->hasHousenumber()) {
+            $iSearchCost ++;
+        }
+
+        $oNewSearch = $oSearch->clone($iSearchCost);
+        $oNewSearch->setPoiSearch($iOp, $this->sClass, $this->sType);
+
+        return array($oNewSearch);
+    }
+
+
+    public function debugInfo()
+    {
+        return array(
+                'ID' => $this->iId,
+                'Type' => 'special term',
+                'Info' => array(
+                           'class' => $this->sClass,
+                           'type' => $this->sType,
+                           'operator' => \Nominatim\Operator::toString($this->iOperator)
+                          )
+               );
+    }
+
+    public function debugCode()
+    {
+        return 'S';
+    }
+}

lib-php/TokenWord.php

@@ -0,0 +1,102 @@
+<?php
+
+namespace Nominatim\Token;
+
+/**
+ * A standard word token.
+ */
+class Word
+{
+    /// Database word id, if applicable.
+    private $iId;
+    /// Number of appearances in the database.
+    private $iSearchNameCount;
+    /// Number of terms in the word.
+    private $iTermCount;
+
+    public function __construct($iId, $iSearchNameCount, $iTermCount)
+    {
+        $this->iId = $iId;
+        $this->iSearchNameCount = $iSearchNameCount;
+        $this->iTermCount = $iTermCount;
+    }
+
+    public function getId()
+    {
+        return $this->iId;
+    }
+
+    /**
+     * Check if the token can be added to the given search.
+     * Derive new searches by adding this token to an existing search.
+     *
+     * @param object  $oSearch      Partial search description derived so far.
+     * @param object  $oPosition    Description of the token position within
+                                    the query.
+     *
+     * @return True if the token is compatible with the search configuration
+     *         given the position.
+     */
+    public function isExtendable($oSearch, $oPosition)
+    {
+        return !$oPosition->isPhrase('country');
+    }
+
+    /**
+     * Derive new searches by adding this token to an existing search.
+     *
+     * @param object  $oSearch      Partial search description derived so far.
+     * @param object  $oPosition    Description of the token position within
+                                    the query.
+     *
+     * @return SearchDescription[] List of derived search descriptions.
+     */
+    public function extendSearch($oSearch, $oPosition)
+    {
+        // Full words can only be a name if they appear at the beginning
+        // of the phrase. In structured search the name must forcably in
+        // the first phrase. In unstructured search it may be in a later
+        // phrase when the first phrase is a house number.
+        if ($oSearch->hasName()
+            || !($oPosition->isFirstPhrase() || $oPosition->isPhrase(''))
+        ) {
+            if ($this->iTermCount > 1
+                && ($oPosition->isPhrase('') || !$oPosition->isFirstPhrase())
+            ) {
+                $oNewSearch = $oSearch->clone(1);
+                $oNewSearch->addAddressToken($this->iId);
+
+                return array($oNewSearch);
+            }
+        } elseif (!$oSearch->hasName(true)) {
+            $oNewSearch = $oSearch->clone(1);
+            $oNewSearch->addNameToken(
+                $this->iId,
+                CONST_Search_NameOnlySearchFrequencyThreshold
+                && $this->iSearchNameCount
+                          < CONST_Search_NameOnlySearchFrequencyThreshold
+            );
+
+            return array($oNewSearch);
+        }
+
+        return array();
+    }
+
+    public function debugInfo()
+    {
+        return array(
+                'ID' => $this->iId,
+                'Type' => 'word',
+                'Info' => array(
+                           'count' => $this->iSearchNameCount,
+                           'terms' => $this->iTermCount
+                          )
+               );
+    }
+
+    public function debugCode()
+    {
+        return 'W';
+    }
+}

lib-php/admin/country_languages.php

@@ -1,6 +1,7 @@
 <?php
+@define('CONST_LibDir', dirname(dirname(__FILE__)));
 
-require_once(CONST_BasePath.'/lib/init-cmd.php');
+require_once(CONST_LibDir.'/init-cmd.php');
 
 ini_set('memory_limit', '800M');
 ini_set('display_errors', 'stderr');
@@ -11,10 +12,12 @@ $aCMDOptions
     array('help', 'h', 0, 1, 0, 0, false, 'Show Help'),
     array('quiet', 'q', 0, 1, 0, 0, 'bool', 'Quiet output'),
     array('verbose', 'v', 0, 1, 0, 0, 'bool', 'Verbose output'),
+    array('project-dir', '', 0, 1, 1, 1, 'realpath', 'Base directory of the Nominatim installation (default: .)'),
    );
 getCmdOpt($_SERVER['argv'], $aCMDOptions, $aCMDResult, true, true);
 
-include(CONST_Phrase_Config);
+loadSettings($aCMDResult['project-dir'] ?? getcwd());
+setupHTTPProxy();
 
 if (true) {
     $sURL = 'https://wiki.openstreetmap.org/wiki/Special:Export/Nominatim/Country_Codes';

lib-php/admin/export.php

@@ -1,10 +1,11 @@
 <?php
+    @define('CONST_LibDir', dirname(dirname(__FILE__)));
     // Script to extract structured city and street data
     // from a running nominatim instance as CSV data
 
 
-    require_once(CONST_BasePath.'/lib/init-cmd.php');
-    require_once(CONST_BasePath.'/lib/ParameterParser.php');
+    require_once(CONST_LibDir.'/init-cmd.php');
+    require_once(CONST_LibDir.'/ParameterParser.php');
     ini_set('memory_limit', '800M');
 
     $aCMDOptions = array(
@@ -21,6 +22,7 @@
                     array('restrict-to-osm-node', '', 0, 1, 1, 1, 'int', 'Export only objects that are children of this OSM node'),
                     array('restrict-to-osm-way', '', 0, 1, 1, 1, 'int', 'Export only objects that are children of this OSM way'),
                     array('restrict-to-osm-relation', '', 0, 1, 1, 1, 'int', 'Export only objects that are children of this OSM relation'),
+                    array('project-dir', '', 0, 1, 1, 1, 'realpath', 'Base directory of the Nominatim installation (default: .)'),
                     "\nAddress ranks: continent, country, state, county, city, suburb, street, path",
                     'Additional output types: postcode, placeid (placeid for each object)',
                     "\noutput-format must be a semicolon-separated list of address ranks. Multiple ranks",
@@ -30,6 +32,8 @@
                    );
     getCmdOpt($_SERVER['argv'], $aCMDOptions, $aCMDResult, true, true);
 
+    loadSettings($aCMDResult['project-dir'] ?? getcwd());
+
     $aRankmap = array(
                  'continent' => 1,
                  'country' => 4,
@@ -45,7 +49,9 @@
     $oDB->connect();
 
     if (isset($aCMDResult['output-type'])) {
-        if (!isset($aRankmap[$aCMDResult['output-type']])) fail('unknown output-type: '.$aCMDResult['output-type']);
+        if (!isset($aRankmap[$aCMDResult['output-type']])) {
+            fail('unknown output-type: '.$aCMDResult['output-type']);
+        }
         $iOutputRank = $aRankmap[$aCMDResult['output-type']];
     } else {
         $iOutputRank = $aRankmap['street'];
@@ -54,14 +60,18 @@
 
     // Preferred language
     $oParams = new Nominatim\ParameterParser();
-    if (!isset($aCMDResult['language'])) $aCMDResult['language'] = 'xx';
+    if (!isset($aCMDResult['language'])) {
+        $aCMDResult['language'] = 'xx';
+    }
     $aLangPrefOrder = $oParams->getPreferredLanguages($aCMDResult['language']);
     $sLanguagePrefArraySQL = $oDB->getArraySQL($oDB->getDBQuotedList($aLangPrefOrder));
 
     // output formatting: build up a lookup table that maps address ranks to columns
     $aColumnMapping = array();
     $iNumCol = 0;
-    if (!isset($aCMDResult['output-format'])) $aCMDResult['output-format'] = 'street;suburb;city;county;state;country';
+    if (!isset($aCMDResult['output-format'])) {
+        $aCMDResult['output-format'] = 'street;suburb;city;county;state;country';
+    }
     foreach (preg_split('/\s*;\s*/', $aCMDResult['output-format']) as $sColumn) {
         $bHasData = false;
         foreach (preg_split('/\s*,\s*/', $sColumn) as $sRank) {
@@ -76,7 +86,9 @@
                 }
             }
         }
-        if ($bHasData) $iNumCol++;
+        if ($bHasData) {
+            $iNumCol++;
+        }
     }
 
     // build the query for objects
@@ -118,7 +130,9 @@
     if ($sOsmType) {
         $sSQL = 'select place_id from placex where osm_type = :osm_type and osm_id = :osm_id';
         $sParentId = $oDB->getOne($sSQL, array('osm_type' => $sOsmType, 'osm_id' => $sOsmId));
-        if (!$sParentId) fail('Could not find place '.$sOsmType.' '.$sOsmId);
+        if (!$sParentId) {
+            fail('Could not find place '.$sOsmType.' '.$sOsmId);
+        }
     }
     if ($sParentId) {
         $sPlacexSQL .= ' and place_id in (select place_id from place_addressline where address_place_id = '.$sParentId.' and isaddress)';
@@ -132,7 +146,6 @@
     $oResults = $oDB->getQueryStatement($sPlacexSQL);
     $fOutstream = fopen('php://output', 'w');
     while ($aRow = $oResults->fetch()) {
-        //var_dump($aRow);
         $iPlaceID = $aRow['place_id'];
         $sSQL = "select rank_address,get_name_by_language(name,$sLanguagePrefArraySQL) as localname from get_addressdata(:place_id, -1)";
         $sSQL .= ' WHERE isaddress';