do not check for extra housenumber index for reverse-only

[nominatim.git] / nominatim / tools / special_phrases.py

diff --git a/nominatim/tools/special_phrases.py b/nominatim/tools/special_phrases.py
index 0c1258fefb0b9cece4c4e7ca88869b39fd97ab0e..f4eec260c529c13e3a1d0235eaa5230669f2f16f 100644 (file)
--- a/nominatim/tools/special_phrases.py
+++ b/nominatim/tools/special_phrases.py
@@ -3,20 +3,21 @@
 """
 import logging
 import os
+from os.path import isfile
 from pathlib import Path
 import re
 import subprocess
 import json
-from os.path import isfile
+
 from icu import Transliterator
 from psycopg2.sql import Identifier, Literal, SQL
+
 from nominatim.tools.exec_utils import get_url
 from nominatim.errors import UsageError
 
 LOG = logging.getLogger()
 class SpecialPhrasesImporter():
     # pylint: disable-msg=too-many-instance-attributes
-    # pylint: disable-msg=too-few-public-methods
     """
         Class handling the process of special phrases importations.
     """
@@ -27,7 +28,7 @@ class SpecialPhrasesImporter():
         self.black_list, self.white_list = self._load_white_and_black_lists()
         #Compile the regex here to increase performances.
         self.occurence_pattern = re.compile(
-            r'\| ([^\|]+) \|\| ([^\|]+) \|\| ([^\|]+) \|\| ([^\|]+) \|\| ([\-YN])'
+            r'\| *([^\|]+) *\|\| *([^\|]+) *\|\| *([^\|]+) *\|\| *([^\|]+) *\|\| *([\-YN])'
         )
         self.sanity_check_pattern = re.compile(r'^\w+$')
         self.transliterator = Transliterator.createFromRules("special-phrases normalizer",
@@ -116,7 +117,7 @@ class SpecialPhrasesImporter():
         if self.config.PHRASE_CONFIG:
             settings_path = self._convert_php_settings_if_needed(self.config.PHRASE_CONFIG)
 
-        with open(settings_path, "r") as json_settings:
+        with settings_path.open("r") as json_settings:
             settings = json.load(json_settings)
         return settings['blackList'], settings['whiteList']
 
@@ -152,9 +153,11 @@ class SpecialPhrasesImporter():
         type_matchs = self.sanity_check_pattern.findall(phrase_type)
         class_matchs = self.sanity_check_pattern.findall(phrase_class)
 
-        if len(class_matchs) < 1 or len(type_matchs) < 1:
-            raise UsageError("Bad class/type for language {}: {}={}".format(
-                lang, phrase_class, phrase_type))
+        if not class_matchs or not type_matchs:
+            LOG.warning("Bad class/type for language %s: %s=%s. It will not be imported",
+                        lang, phrase_class, phrase_type)
+            return False
+        return True
 
     def _process_xml_content(self, xml_content, lang):
         """
@@ -205,7 +208,8 @@ class SpecialPhrasesImporter():
                 continue
 
             #sanity check, in case somebody added garbage in the wiki
-            self._check_sanity(lang, phrase_class, phrase_type)
+            if not self._check_sanity(lang, phrase_class, phrase_type):
+                continue
 
             class_type_pairs.add((phrase_class, phrase_type))