keep break indicators [:-] during normalisation

All punctuation will be converted to '-'. Soft breaks : may be
added by preprocessors. The break signs are only used during
query analysis and are ignored during import token analysis.

diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml
index 530df1a63397e423355ec7a75dc36178e2c2418e..437319fab801d53fbd5b2cb5581e1dd88a0ff79a 100644 (file)
--- a/settings/icu_tokenizer.yaml
+++ b/settings/icu_tokenizer.yaml
@@ -9,16 +9,17 @@ normalization:
     - "'nº' > 'no'"
     - "ª > a"
     - "º > o"
-    - "[[:Punctuation:][:Symbol:]\u02bc]  > ' '"
+    - "[[:Punctuation:][:Symbol:][\u02bc] - [-:]]+  > '-'"
     - "ß > 'ss'" # German szet is unambiguously equal to double ss
-    - "[^[:alnum:] [:Canonical_Combining_Class=Virama:] [:Space:]] >"
+    - "[^[:alnum:] [:Canonical_Combining_Class=Virama:] [:Space:] [-:]] >"
     - "[:Lm:] >"
     - ":: [[:Number:]] Latin ()"
     - ":: [[:Number:]] Ascii ();"
     - ":: [[:Number:]] NFD ();"
     - "[[:Nonspacing Mark:] [:Cf:]] >;"
-    - "[:Space:]+ > ' '"
+    - "[-:]?[:Space:]+[-:]? > ' '"
 transliteration:
+    - "[-:]  > ' '"
     - ":: Latin ()"
     - !include icu-rules/extended-unicode-to-asccii.yaml
     - ":: Ascii ()"

diff --git a/src/nominatim_api/search/geocoder.py b/src/nominatim_api/search/geocoder.py
index efe5b7216853ba64c4983cd31801999c750c1512..69455d77a0d3c14aa79d168fd053e045e80ad39a 100644 (file)
--- a/src/nominatim_api/search/geocoder.py
+++ b/src/nominatim_api/search/geocoder.py
@@ -133,7 +133,7 @@ class ForwardGeocoder:
         """
         assert self.query_analyzer is not None
         qwords = [word for phrase in query.source
-                  for word in re.split('[, ]+', phrase.text) if word]
+                  for word in re.split('[-,: ]+', phrase.text) if word]
         if not qwords:
             return
 
@@ -146,7 +146,7 @@ class ForwardGeocoder:
             distance = 0.0
             norm = self.query_analyzer.normalize_text(' '.join((result.display_name,
                                                                 result.country_code or '')))
-            words = set((w for w in norm.split(' ') if w))
+            words = set((w for w in re.split('[-,: ]+', norm) if w))
             if not words:
                 continue
             for qword in qwords:

diff --git a/src/nominatim_db/tokenizer/icu_token_analysis.py b/src/nominatim_db/tokenizer/icu_token_analysis.py
index a3cdcb7afdb9a008ee4c19f642b18542da369ac0..c1ba106c48775498ad7b2596ef460be8f85bc299 100644 (file)
--- a/src/nominatim_db/tokenizer/icu_token_analysis.py
+++ b/src/nominatim_db/tokenizer/icu_token_analysis.py
@@ -25,6 +25,8 @@ class ICUTokenAnalysis:
 
     def __init__(self, norm_rules: str, trans_rules: str,
                  analysis_rules: Mapping[Optional[str], 'TokenAnalyzerRule']):
+        # additional break signs are not relevant during name analysis
+        norm_rules += ";[[:Space:][-:]]+ > ' ';"
         self.normalizer = Transliterator.createFromRules("icu_normalization",
                                                          norm_rules)
         trans_rules += ";[:Space:]+ > ' '"