correctly quote strings when copying in data

[nominatim.git] / nominatim / tokenizer / icu_rule_loader.py

diff --git a/nominatim/tokenizer/icu_rule_loader.py b/nominatim/tokenizer/icu_rule_loader.py
index a11b9bd86e0140b97d4fd189e2d44b6b79adc13b..269faed981abbbb9ffc530bd32d6b38ae0c30df4 100644 (file)
--- a/nominatim/tokenizer/icu_rule_loader.py
+++ b/nominatim/tokenizer/icu_rule_loader.py
@@ -93,7 +93,7 @@ class ICURuleLoader:
 
 
     def _load_from_yaml(self):
-        rules = yaml.load(self.configfile.read_text())
+        rules = yaml.safe_load(self.configfile.read_text())
 
         self.normalization_rules = self._cfg_to_icu_rules(rules, 'normalization')
         self.transliteration_rules = self._cfg_to_icu_rules(rules, 'transliteration')
@@ -122,6 +122,9 @@ class ICURuleLoader:
         """
         content = self._get_section(rules, section)
 
+        if content is None:
+            return ''
+
         if isinstance(content, str):
             return (self.configfile.parent / content).read_text().replace('\n', ' ')
 
@@ -160,4 +163,5 @@ class ICURuleLoader:
             abbrterms = (norm.transliterate(t.strip()) for t in parts[1].split(','))
 
             for full, abbr in itertools.product(fullterms, abbrterms):
-                self.abbreviations[full].append(abbr)
+                if full and abbr:
+                    self.abbreviations[full].append(abbr)