You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
48 lines
1.6 KiB
48 lines
1.6 KiB
from luscenje_struktur.word import Word
|
|
|
|
class StructureMatch:
|
|
def __init__(self, match_id, structure):
|
|
self.match_id = str(match_id)
|
|
self.structure = structure
|
|
|
|
self.matches = []
|
|
self.representations = {}
|
|
|
|
@staticmethod
|
|
def from_db(db, colocation_id, structure):
|
|
result = StructureMatch(colocation_id, structure)
|
|
prev_match_id = None
|
|
|
|
stmt = """SELECT match_id, component_id, word_lemma, word_text, word_msd, word_id
|
|
FROM ColocationMatches
|
|
JOIN Matches ON Matches.match_id=ColocationMatches.mid_match_id
|
|
WHERE mid_colocation_id=?
|
|
ORDER BY match_id"""
|
|
|
|
for row in db.execute(stmt, (colocation_id,)):
|
|
match_id, component_id, word_lemma, word_text, word_msd, word_id = row
|
|
|
|
if match_id != prev_match_id:
|
|
result.matches.append({})
|
|
prev_match_id = match_id
|
|
|
|
result.matches[-1][str(component_id)] = Word(word_lemma, word_msd, word_id, word_text, False)
|
|
|
|
for component_id, text, msd in db.execute("SELECT component_id, text, msd FROM Representations WHERE colocation_id=?", (colocation_id,)):
|
|
result.representations[str(component_id)] = (text, msd)
|
|
|
|
return result
|
|
|
|
def distinct_forms(self):
|
|
dm = set()
|
|
keys = list(self.matches[0].keys())
|
|
for words in self.matches:
|
|
dm.add(" ".join(words[k].text for k in keys))
|
|
return len(dm)
|
|
|
|
def append(self, match):
|
|
self.matches.append(match)
|
|
|
|
def __len__(self):
|
|
return len(self.matches)
|