Fix occurence regex

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

diff --git a/nominatim/tools/special_phrases.py b/nominatim/tools/special_phrases.py
index fd46a18d827810aaf11a380a9cee659d3187a3fb..d172498a13fdc6fb7268e7c71a02d2ce0989e2a5 100644 (file)
--- a/nominatim/tools/special_phrases.py
+++ b/nominatim/tools/special_phrases.py
@@ -27,7 +27,7 @@ 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",
@@ -80,7 +80,7 @@ class SpecialPhrasesImporter():
             'et', 'eu', 'fa', 'fi', 'fr', 'gl', 'hr', 'hu',
             'ia', 'is', 'it', 'ja', 'mk', 'nl', 'no', 'pl',
             'ps', 'pt', 'ru', 'sk', 'sl', 'sv', 'uk', 'vi']
-        return self.config.LANGUAGES or default_languages
+        return self.config.LANGUAGES.split(',') if self.config.LANGUAGES else default_languages
 
     @staticmethod
     def _get_wiki_content(lang):