mirror of
https://github.com/osm-search/Nominatim.git
synced 2026-02-15 19:07:58 +00:00
e42878eeda
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.
87 lines
3.2 KiB
Python
87 lines
3.2 KiB
Python
"""
|
|
Legacy word table for testing with functions to prefil and test contents
|
|
of the table.
|
|
"""
|
|
|
|
class MockLegacyWordTable:
|
|
""" A word table for testing using legacy word table structure.
|
|
"""
|
|
def __init__(self, conn):
|
|
self.conn = conn
|
|
with conn.cursor() as cur:
|
|
cur.execute("""CREATE TABLE word (word_id INTEGER,
|
|
word_token text,
|
|
word text,
|
|
class text,
|
|
type text,
|
|
country_code varchar(2),
|
|
search_name_count INTEGER,
|
|
operator TEXT)""")
|
|
|
|
conn.commit()
|
|
|
|
def add_special(self, word_token, word, cls, typ, oper):
|
|
with self.conn.cursor() as cur:
|
|
cur.execute("""INSERT INTO word (word_token, word, class, type, operator)
|
|
VALUES (%s, %s, %s, %s, %s)
|
|
""", (word_token, word, cls, typ, oper))
|
|
self.conn.commit()
|
|
|
|
|
|
def add_country(self, country_code, word_token):
|
|
with self.conn.cursor() as cur:
|
|
cur.execute("INSERT INTO word (word_token, country_code) VALUES(%s, %s)",
|
|
(word_token, country_code))
|
|
self.conn.commit()
|
|
|
|
|
|
def add_postcode(self, word_token, postcode):
|
|
with self.conn.cursor() as cur:
|
|
cur.execute("""INSERT INTO word (word_token, word, class, type)
|
|
VALUES (%s, %s, 'place', 'postcode')
|
|
""", (word_token, postcode))
|
|
self.conn.commit()
|
|
|
|
|
|
def count(self):
|
|
with self.conn.cursor() as cur:
|
|
return cur.scalar("SELECT count(*) FROM word")
|
|
|
|
|
|
def count_special(self):
|
|
with self.conn.cursor() as cur:
|
|
return cur.scalar("SELECT count(*) FROM word WHERE class != 'place'")
|
|
|
|
|
|
def get_special(self):
|
|
with self.conn.cursor() as cur:
|
|
cur.execute("""SELECT word_token, word, class, type, operator
|
|
FROM word WHERE class != 'place'""")
|
|
result = set((tuple(row) for row in cur))
|
|
assert len(result) == cur.rowcount, "Word table has duplicates."
|
|
return result
|
|
|
|
|
|
def get_country(self):
|
|
with self.conn.cursor() as cur:
|
|
cur.execute("""SELECT country_code, word_token
|
|
FROM word WHERE country_code is not null""")
|
|
result = set((tuple(row) for row in cur))
|
|
assert len(result) == cur.rowcount, "Word table has duplicates."
|
|
return result
|
|
|
|
|
|
def get_postcodes(self):
|
|
with self.conn.cursor() as cur:
|
|
cur.execute("""SELECT word FROM word
|
|
WHERE class = 'place' and type = 'postcode'""")
|
|
return set((row[0] for row in cur))
|
|
|
|
def get_partial_words(self):
|
|
with self.conn.cursor() as cur:
|
|
cur.execute("""SELECT word_token, search_name_count FROM word
|
|
WHERE class is null and country_code is null
|
|
and not word_token like ' %'""")
|
|
return set((tuple(row) for row in cur))
|
|
|