hans/Nominatim
1
0
Fork 1
mirror of https://github.com/osm-search/Nominatim.git synced 2026-03-11 21:34:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

adapt unit test for new word table

Browse Source 
Requires a second wrapper class for the word table with the new
layout. This class is interface-compatible, so that later when
the ICU tokenizer becomes the default, all tests that depend on
behaviour of the default tokenizer can be switched to the other
wrapper.
This commit is contained in:
Sarah Hoffmann
2021-07-22 17:24:43 +02:00
parent eb6814d74e
commit e42878eeda
7 changed files with 225 additions and 125 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
nominatim/tokenizer/legacy_icu_tokenizer.py
View File

@@ -236,17 +236,17 @@ class LegacyICUNameAnalyzer:
partial_tokens[word] = self.name_processor.get_search_normalized(word)
with self.conn.cursor() as cur:
cur.execute("""(SELECT word_token, word_id
FROM word WHERE word_token = ANY(%s) and type = 'W')
UNION
(SELECT word_token, word_id
FROM word WHERE word_token = ANY(%s) and type = 'w')""",
(list(full_tokens.values()),
list(partial_tokens.values())))
ids = {r[0]: r[1] for r in cur}
cur.execute("""SELECT word_token, word_id
FROM word WHERE word_token = ANY(%s) and type = 'W'
""", (list(full_tokens.values()),))
full_ids = {r[0]: r[1] for r in cur}
cur.execute("""SELECT word_token, word_id
FROM word WHERE word_token = ANY(%s) and type = 'w'""",
(list(partial_tokens.values()),))
part_ids = {r[0]: r[1] for r in cur}
return [(k, v, ids.get(v, None)) for k, v in full_tokens.items()] \
+ [(k, v, ids.get(v, None)) for k, v in partial_tokens.items()]
return [(k, v, full_ids.get(v, None)) for k, v in full_tokens.items()] \
+ [(k, v, part_ids.get(v, None)) for k, v in partial_tokens.items()]
@staticmethod
@@ -508,7 +508,7 @@ class LegacyICUNameAnalyzer:
FROM (VALUES (%s)) as v(pc)
WHERE NOT EXISTS
(SELECT * FROM word
WHERE type = 'P' and info->>postcode = pc))
WHERE type = 'P' and info->>'postcode' = pc))
""", (term, postcode))
self._cache.postcodes.add(postcode)