rename use of category as POI search to near_item

[nominatim.git] / nominatim / api / search / icu_tokenizer.py

diff --git a/nominatim/api/search/icu_tokenizer.py b/nominatim/api/search/icu_tokenizer.py
index b68e8d10eef70816f6cb772da2d7036e8a31693d..fceec2df522feb5105936204b099e9a8a7a2ad96 100644 (file)
--- a/nominatim/api/search/icu_tokenizer.py
+++ b/nominatim/api/search/icu_tokenizer.py
@@ -101,10 +101,16 @@ class ICUToken(qmod.Token):
         penalty = 0.0
         if row.type == 'w':
             penalty = 0.3
         penalty = 0.0
         if row.type == 'w':
             penalty = 0.3

+        elif row.type == 'W':
+            if len(row.word_token) == 1 and row.word_token == row.word:
+                penalty = 0.2 if row.word.isdigit() else 0.3

         elif row.type == 'H':
             penalty = sum(0.1 for c in row.word_token if c != ' ' and not c.isdigit())
             if all(not c.isdigit() for c in row.word_token):
                 penalty += 0.2 * (len(row.word_token) - 1)
         elif row.type == 'H':
             penalty = sum(0.1 for c in row.word_token if c != ' ' and not c.isdigit())
             if all(not c.isdigit() for c in row.word_token):
                 penalty += 0.2 * (len(row.word_token) - 1)

+        elif row.type == 'C':
+            if len(row.word_token) == 1:
+                penalty = 0.3

 
         if row.info is None:
             lookup_word = row.word
 
         if row.info is None:
             lookup_word = row.word


@@ -178,13 +184,13 @@ class ICUQueryAnalyzer(AbstractQueryAnalyzer):
                 if row.type == 'S':
                     if row.info['op'] in ('in', 'near'):
                         if trange.start == 0:
                 if row.type == 'S':
                     if row.info['op'] in ('in', 'near'):
                         if trange.start == 0:

-                            query.add_token(trange, qmod.TokenType.CATEGORY, token)
+                            query.add_token(trange, qmod.TokenType.NEAR_ITEM, token)

                     else:
                         query.add_token(trange, qmod.TokenType.QUALIFIER, token)
                         if trange.start == 0 or trange.end == query.num_token_slots():
                             token = copy(token)
                             token.penalty += 0.1 * (query.num_token_slots())
                     else:
                         query.add_token(trange, qmod.TokenType.QUALIFIER, token)
                         if trange.start == 0 or trange.end == query.num_token_slots():
                             token = copy(token)
                             token.penalty += 0.1 * (query.num_token_slots())

-                            query.add_token(trange, qmod.TokenType.CATEGORY, token)
+                            query.add_token(trange, qmod.TokenType.NEAR_ITEM, token)

                 else:
                     query.add_token(trange, DB_TO_TOKEN_TYPE[row.type], token)
 
                 else:
                     query.add_token(trange, DB_TO_TOKEN_TYPE[row.type], token)