get_lexes_to_check.py
3.44 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
# -*- coding:utf-8 -*-
import codecs
import itertools
import os
from django.core.management.base import BaseCommand
from dictionary.models import Lemma
from settings import PROJECT_PATH
TO_CHECK_PATH = os.path.join(PROJECT_PATH, 'data', 'lemmas2check-20180907.csv')
class Command(BaseCommand):
def handle(self, **options):
write_schemata_to_check()
def write_schemata_to_check():
to_check_file = codecs.open(TO_CHECK_PATH, 'wt', 'utf-8')
lemmas = Lemma.objects.filter(old=False).order_by('entry_obj__name')
for lemma in lemmas:
print lemma
if lemma.frames.count() > 1:
combinations = itertools.combinations(lemma.frames.all(), 2)
for comb in combinations:
if only_lex_diff(comb[0], comb[1]):
to_check_file.write('%s (%s)\n' % (lemma.entry_obj.name, lemma.status.status))
break
to_check_file.close()
def only_lex_diff(schema1, schema2):
if (schema1.characteristics.get(type=u'ZWROTNOŚĆ') == schema2.characteristics.get(type=u'ZWROTNOŚĆ') and
schema1.characteristics.get(type=u'ASPEKT') == schema2.characteristics.get(type=u'ASPEKT') and
schema1.characteristics.get(type=u'NEGATYWNOŚĆ') == schema2.characteristics.get(type=u'NEGATYWNOŚĆ') and
schema1.characteristics.get(type=u'PREDYKATYWNOŚĆ') == schema2.characteristics.get(type=u'PREDYKATYWNOŚĆ') and
schema1.positions.count() == schema2.positions.count() and (schema1.phraseologic or schema2.phraseologic)):
pos_diff1 = schema1.positions.exclude(text_rep__in=[pos.text_rep for pos in schema2.positions.all()])
pos_diff2 = schema2.positions.exclude(text_rep__in=[pos.text_rep for pos in schema1.positions.all()])
for pos1 in pos_diff1:
match = False
for pos2 in pos_diff2:
if positions_lexically_match(pos1, pos2):
match = True
if not match:
return False
return True
return False
def positions_lexically_match(pos1, pos2):
if (pos1.categories.count() == pos2.categories.count() and
(pos1.categories.all() & pos2.categories.all()).count() == pos1.categories.count() and
phrase_types_match(pos1, pos2)):
return True
return False
def phrase_types_match(pos1, pos2):
if pos1.arguments.count() == pos2.arguments.count():
pt_diff1 = pos1.arguments.exclude(pk__in=pos2.arguments.all())
pt_diff2 = pos2.arguments.exclude(pk__in=pos1.arguments.all())
for pt1 in pt_diff1:
match = False
for pt2 in pt_diff2:
if lex_to_phrase_type_match(pt1, pt2) or lex_to_phrase_type_match(pt2, pt1):
match = True
break
if not match:
return False
return True
return False
def lex_to_phrase_type_match(pt1, pt2):
if pt1.type == 'lex' and pt2.type in ['adjp', 'prepadjp']:
lexicalized_pt = pt1.atributes.get(type='TYP FRAZY').values.all()[0].argument
if (pt2.type == 'adjp' and lexicalized_pt.type in ['adjp', 'ppasp', 'pactp'] and
pt2.text_rep.split('(')[1] == lexicalized_pt.text_rep.split('(')[1]):
return True
elif (pt2.type == 'prepadjp' and lexicalized_pt.type in ['prepadjp', 'prepppasp', 'preppactp'] and
pt2.text_rep.split('(')[1] == lexicalized_pt.text_rep.split('(')[1]):
return True
return False