osm-search/Nominatim
1
1
Fork 0
mirror of https://github.com/osm-search/Nominatim.git synced 2024-11-23 05:35:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

increase penalty for one-letter words

Browse Source
This commit is contained in:
Sarah Hoffmann 2023-11-23 10:51:58 +01:00
parent 195c13ee8a
commit 4e4d29f653
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
nominatim/api/search/icu_tokenizer.py
View File

@ -101,10 +101,16 @@ class ICUToken(qmod.Token):
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 == 'C':
if len(row.word_token) == 1:
penalty = 0.3
if row.info is None:
lookup_word = row.word