hans/Nominatim
1
0
Fork 1
mirror of https://github.com/osm-search/Nominatim.git synced 2026-02-14 10:27:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

do not count words when in reverse-only mode

Browse Source
This commit is contained in:
Sarah Hoffmann
2021-10-26 11:42:42 +02:00
parent 2c4b798f9b
commit 53dbe58ada
2 changed files with 26 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
nominatim/tokenizer/icu_tokenizer.py
View File

@@ -99,18 +99,19 @@ class LegacyICUTokenizer(AbstractTokenizer):
""" Recompute frequencies for all name words.
"""
with connect(self.dsn) as conn:
with conn.cursor() as cur:
cur.drop_table("word_frequencies")
LOG.info("Computing word frequencies")
cur.execute("""CREATE TEMP TABLE word_frequencies AS
SELECT unnest(name_vector) as id, count(*)
FROM search_name GROUP BY id""")
cur.execute("CREATE INDEX ON word_frequencies(id)")
LOG.info("Update word table with recomputed frequencies")
cur.execute("""UPDATE word
SET info = info || jsonb_build_object('count', count)
FROM word_frequencies WHERE word_id = id""")
cur.drop_table("word_frequencies")
if conn.table_exists('search_name'):
with conn.cursor() as cur:
cur.drop_table("word_frequencies")
LOG.info("Computing word frequencies")
cur.execute("""CREATE TEMP TABLE word_frequencies AS
SELECT unnest(name_vector) as id, count(*)
FROM search_name GROUP BY id""")
cur.execute("CREATE INDEX ON word_frequencies(id)")
LOG.info("Update word table with recomputed frequencies")
cur.execute("""UPDATE word
SET info = info || jsonb_build_object('count', count)
FROM word_frequencies WHERE word_id = id""")
cur.drop_table("word_frequencies")
conn.commit()

25
nominatim/tokenizer/legacy_tokenizer.py
View File

@@ -190,18 +190,19 @@ class LegacyTokenizer(AbstractTokenizer):
""" Recompute the frequency of full words.
"""
with connect(self.dsn) as conn:
with conn.cursor() as cur:
cur.drop_table("word_frequencies")
LOG.info("Computing word frequencies")
cur.execute("""CREATE TEMP TABLE word_frequencies AS
SELECT unnest(name_vector) as id, count(*)
FROM search_name GROUP BY id""")
cur.execute("CREATE INDEX ON word_frequencies(id)")
LOG.info("Update word table with recomputed frequencies")
cur.execute("""UPDATE word SET search_name_count = count
FROM word_frequencies
WHERE word_token like ' %' and word_id = id""")
cur.drop_table("word_frequencies")
if conn.table_exists('search_name'):
with conn.cursor() as cur:
cur.drop_table("word_frequencies")
LOG.info("Computing word frequencies")
cur.execute("""CREATE TEMP TABLE word_frequencies AS
SELECT unnest(name_vector) as id, count(*)
FROM search_name GROUP BY id""")
cur.execute("CREATE INDEX ON word_frequencies(id)")
LOG.info("Update word table with recomputed frequencies")
cur.execute("""UPDATE word SET search_name_count = count
FROM word_frequencies
WHERE word_token like ' %' and word_id = id""")
cur.drop_table("word_frequencies")
conn.commit()
def name_analyzer(self):