Vagrant and CI tests for Ubuntu 22.04

[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 361b67d46c8411eb0ec2d4da28f6c84ce1573cc0..035b6698511035fbaf6dfed1f137aeb8e911cce1 100644 (file)
--- a/nominatim/tokenizer/icu_rule_loader.py
+++ b/nominatim/tokenizer/icu_rule_loader.py
@@ -1,3 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# This file is part of Nominatim. (https://nominatim.org)
+#
+# Copyright (C) 2022 by the Nominatim developer community.
+# For a full list of authors see the git log.
 """
 Helper class to create ICU rules from a configuration file.
 """
@@ -11,6 +17,7 @@ from nominatim.db.properties import set_property, get_property
 from nominatim.errors import UsageError
 from nominatim.tokenizer.place_sanitizer import PlaceSanitizer
 from nominatim.tokenizer.icu_token_analysis import ICUTokenAnalysis
+import nominatim.data.country_info
 
 LOG = logging.getLogger()
 
@@ -38,6 +45,9 @@ class ICURuleLoader:
         rules = config.load_sub_configuration('icu_tokenizer.yaml',
                                               config='TOKENIZER_CONFIG')
 
+        # Make sure country information is available to analyzers and sanitizers.
+        nominatim.data.country_info.setup_country_config(config)
+
         self.normalization_rules = self._cfg_to_icu_rules(rules, 'normalization')
         self.transliteration_rules = self._cfg_to_icu_rules(rules, 'transliteration')
         self.analysis_rules = _get_section(rules, 'token-analysis')
@@ -120,7 +130,7 @@ class ICURuleLoader:
                 else:
                     LOG.fatal("ICU tokenizer configuration has two token "
                               "analyzers with id '%s'.", name)
-                UsageError("Syntax error in ICU tokenizer config.")
+                raise UsageError("Syntax error in ICU tokenizer config.")
             self.analysis[name] = TokenAnalyzerRule(section, self.normalization_rules)