safety-screen/Nominatim
1
0
Fork 0
forked from hans/Nominatim
Code Pull Requests Activity

remove special casing for legacy tokenizer from BDD tests

Browse Source
This commit is contained in:
Sarah Hoffmann
2024-09-21 17:07:32 +02:00
parent 74c39267d9
commit d4f3eda314
13 changed files with 7 additions and 282 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
test/bdd/steps/steps_db_ops.py
View File

@@ -28,9 +28,8 @@ def check_database_integrity(context):
assert cur.fetchone()[0] == 0, "Duplicates found in place_addressline"
# word table must not have empty word_tokens
if context.nominatim.tokenizer != 'legacy':
cur.execute("SELECT count(*) FROM word WHERE word_token = ''")
assert cur.fetchone()[0] == 0, "Empty word tokens found in word table"
cur.execute("SELECT count(*) FROM word WHERE word_token = ''")
assert cur.fetchone()[0] == 0, "Empty word tokens found in word table"
@@ -324,13 +323,8 @@ def check_word_table_for_postcodes(context, exclude, postcodes):
plist.sort()
with context.db.cursor() as cur:
if nctx.tokenizer != 'legacy':
cur.execute("SELECT word FROM word WHERE type = 'P' and word = any(%s)",
(plist,))
else:
cur.execute("""SELECT word FROM word WHERE word = any(%s)
and class = 'place' and type = 'postcode'""",
(plist,))
cur.execute("SELECT word FROM word WHERE type = 'P' and word = any(%s)",
(plist,))
found = [row['word'] for row in cur]
assert len(found) == len(set(found)), f"Duplicate rows for postcodes: {found}"