reintroduce cutoffs when searching for very frequent words

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

diff --git a/nominatim/tokenizer/icu_token_analysis.py b/nominatim/tokenizer/icu_token_analysis.py
index f27a2fbe96e9a849912e9ea41304857ce22907b0..7ea31e8ea1eb21b20f3e8dd8b3c3f12cdc7cee83 100644 (file)
--- a/nominatim/tokenizer/icu_token_analysis.py
+++ b/nominatim/tokenizer/icu_token_analysis.py
@@ -1,16 +1,29 @@
+# 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.
 """
 Container class collecting all components required to transform an OSM name
 into a Nominatim token.
 """
-
+from typing import Mapping, Optional, TYPE_CHECKING
 from icu import Transliterator
 
+from nominatim.tokenizer.token_analysis.base import Analyzer
+
+if TYPE_CHECKING:
+    from typing import Any
+    from nominatim.tokenizer.icu_rule_loader import TokenAnalyzerRule # pylint: disable=cyclic-import
+
 class ICUTokenAnalysis:
     """ Container class collecting the transliterators and token analysis
-        modules for a single NameAnalyser instance.
+        modules for a single Analyser instance.
     """
 
-    def __init__(self, norm_rules, trans_rules, analysis_rules):
+    def __init__(self, norm_rules: str, trans_rules: str,
+                 analysis_rules: Mapping[Optional[str], 'TokenAnalyzerRule']):
         self.normalizer = Transliterator.createFromRules("icu_normalization",
                                                          norm_rules)
         trans_rules += ";[:Space:]+ > ' '"
@@ -19,5 +32,12 @@ class ICUTokenAnalysis:
         self.search = Transliterator.createFromRules("icu_search",
                                                      norm_rules + trans_rules)
 
-        self.analysis = {name: arules.create(self.to_ascii, arules.config)
+        self.analysis = {name: arules.create(self.normalizer, self.to_ascii)
                          for name, arules in analysis_rules.items()}
+
+
+    def get_analyzer(self, name: Optional[str]) -> Analyzer:
+        """ Return the given named analyzer. If no analyzer with that
+            name exists, return the default analyzer.
+        """
+        return self.analysis.get(name) or self.analysis[None]