more unit tests for tokenizers

This commit is contained in:
Sarah Hoffmann
2021-12-02 15:46:36 +01:00
parent 7617a9316e
commit 14a78f55cd
5 changed files with 333 additions and 31 deletions

View File

@@ -20,6 +20,14 @@ class MockLegacyWordTable:
conn.commit()
def add_full_word(self, word_id, word, word_token=None):
with self.conn.cursor() as cur:
cur.execute("""INSERT INTO word (word_id, word_token, word)
VALUES (%s, %s, %s)
""", (word_id, ' ' + (word_token or word), word))
self.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)