From: Sarah Hoffmann <lonvia@denofr.de>
Date: Mon, 2 May 2022 14:06:02 +0000 (+0200)
Subject: Merge remote-tracking branch 'upstream/master'
X-Git-Tag: deploy~112
X-Git-Url: https://git.openstreetmap.org/nominatim.git/commitdiff_plain/b8d41cf38cb9abead17f53fc42c28b65e0ae62b7?hp=e941a3f00b2944e0d624f395e9a252d29ad4c95c

Merge remote-tracking branch 'upstream/master'
---

diff --git a/docs/admin/Migration.md b/docs/admin/Migration.md
index bc649918..11ee7f05 100644
--- a/docs/admin/Migration.md
+++ b/docs/admin/Migration.md
@@ -15,6 +15,15 @@ breaking changes. **Please read them before running the migration.**
     If you are migrating from a version <3.6, then you still have to follow
     the manual migration steps up to 3.6.
 
+## 4.0.0 -> master
+
+### geocodejson output changed
+
+The `type` field of the geocodejson output has changed. It now contains
+the address class of the object instead of the value of the OSM tag. If
+your client has used the `type` field, switch them to read `osm_value`
+instead.
+
 ## 3.7.0 -> 4.0.0
 
 ### NOMINATIM_PHRASE_CONFIG removed
diff --git a/docs/api/Output.md b/docs/api/Output.md
index 07525a98..d59f75dd 100644
--- a/docs/api/Output.md
+++ b/docs/api/Output.md
@@ -98,7 +98,10 @@ The GeocodeJSON format follows the
 The following feature attributes are implemented:
 
  * `osm_type`, `osm_id` - reference to the OSM object (unofficial extension, [see notes](#osm-reference))
- * `type` - value of the main tag of the object (e.g. residential, restaurant, ...)
+ * `type` - the 'address level' of the object ('house', 'street', `district`, `city`,
+            `county`, `state`, `country`, `locality`)
+ * `osm_key`- key of the main tag of the OSM object (e.g. boundary, highway, amenity)
+ * `osm_value` - value of the main tag of the OSM object (e.g. residential, restaurant)
  * `label` - full comma-separated address
  * `name` - localised name of the place
  * `housenumber`, `street`, `locality`, `district`, `postcode`, `city`,
diff --git a/lib-php/lib.php b/lib-php/lib.php
index 9babe5ed..d17c9d72 100644
--- a/lib-php/lib.php
+++ b/lib-php/lib.php
@@ -206,6 +206,36 @@ function parseLatLon($sQuery)
     return array($sFound, $fQueryLat, $fQueryLon);
 }
 
+function addressRankToGeocodeJsonType($iAddressRank)
+{
+    if ($iAddressRank >= 29 && $iAddressRank <= 30) {
+        return 'house';
+    }
+    if ($iAddressRank >= 26 && $iAddressRank < 28) {
+        return 'street';
+    }
+    if ($iAddressRank >= 22 && $iAddressRank < 26) {
+        return 'locality';
+    }
+    if ($iAddressRank >= 17 && $iAddressRank < 22) {
+        return 'district';
+    }
+    if ($iAddressRank >= 13 && $iAddressRank < 17) {
+        return 'city';
+    }
+    if ($iAddressRank >= 10 && $iAddressRank < 13) {
+        return 'county';
+    }
+    if ($iAddressRank >= 5 && $iAddressRank < 10) {
+        return 'state';
+    }
+    if ($iAddressRank >= 4 && $iAddressRank < 5) {
+        return 'country';
+    }
+
+    return 'locality';
+}
+
 if (!function_exists('array_key_last')) {
     function array_key_last(array $array)
     {
diff --git a/lib-php/template/search-geocodejson.php b/lib-php/template/search-geocodejson.php
index b8727719..5439e3cf 100644
--- a/lib-php/template/search-geocodejson.php
+++ b/lib-php/template/search-geocodejson.php
@@ -25,8 +25,10 @@ foreach ($aSearchResults as $iResNum => $aPointDetails) {
         $aPlace['properties']['geocoding']['osm_type'] = $sOSMType;
         $aPlace['properties']['geocoding']['osm_id'] = $aPointDetails['osm_id'];
     }
+    $aPlace['properties']['geocoding']['osm_key'] = $aPointDetails['class'];
+    $aPlace['properties']['geocoding']['osm_value'] = $aPointDetails['type'];
 
-    $aPlace['properties']['geocoding']['type'] = $aPointDetails['type'];
+    $aPlace['properties']['geocoding']['type'] = addressRankToGeocodeJsonType($aPointDetails['rank_address']);
 
     $aPlace['properties']['geocoding']['label'] = $aPointDetails['langaddress'];
 
diff --git a/nominatim/tools/check_database.py b/nominatim/tools/check_database.py
index 3640197b..7ac31271 100644
--- a/nominatim/tools/check_database.py
+++ b/nominatim/tools/check_database.py
@@ -23,6 +23,7 @@ class CheckState(Enum):
     FAIL = 1
     FATAL = 2
     NOT_APPLICABLE = 3
+    WARN = 4
 
 def _check(hint=None):
     """ Decorator for checks. It adds the function to the list of
@@ -40,6 +41,11 @@ def _check(hint=None):
                 params = {}
             if ret == CheckState.OK:
                 print('\033[92mOK\033[0m')
+            elif ret == CheckState.WARN:
+                print('\033[93mWARNING\033[0m')
+                if hint:
+                    print('')
+                    print(dedent(hint.format(**params)))
             elif ret == CheckState.NOT_APPLICABLE:
                 print('not applicable')
             else:
@@ -180,6 +186,23 @@ def check_tokenizer(_, config):
     return CheckState.FAIL, dict(msg=result)
 
 
+@_check(hint="""\
+             Wikipedia/Wikidata importance tables missing.
+             Quality of search results may be degraded. Reverse geocoding is unaffected.
+             See https://nominatim.org/release-docs/latest/admin/Import/#wikipediawikidata-rankings
+             """)
+def check_existance_wikipedia(conn, _):
+    """ Checking for wikipedia/wikidata data
+    """
+    if not conn.table_exists('search_name'):
+        return CheckState.NOT_APPLICABLE
+
+    with conn.cursor() as cur:
+        cnt = cur.scalar('SELECT count(*) FROM wikipedia_article')
+
+        return CheckState.WARN if cnt == 0 else CheckState.OK
+
+
 @_check(hint="""\
              The indexing didn't finish. {count} entries are not yet indexed.