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 Analyser
+
+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.
"""
- 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:]+ > ' '"
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]) -> Analyser:
+ """ 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]