convert_tables.py
13.8 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
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
# -*- coding: utf-8 -*-
from django.core.management import BaseCommand
from common.util import GroupDict
from dictionary.models import Cell, NewTableTemplate, LexicalClass, \
PatternType, TableTemplate, NewTableCell, TableHeader, \
NewTableHeader, LexemeAttribute, NewExportCell, Variant, InflectionCharacteristic, LexemeAttributeValue
class Command(BaseCommand):
args = ''
help = ''
def handle(self, **options):
convert_tables()
nQ_ICS = ('dk', 'ndk', 'ndk/dk', 'dk/ndk', 'ndk/(dk)', 'dk/(ndk)')
Q_ICS = ('qndk', 'qdk', 'qndk/dk', 'qndk/(dk)')
ASPECT_POS = {
'fin', 'imps', 'impt', 'inf', 'praet', 'ger', 'pact', 'ppas',
'verb'
}
ASPECT_TAG = 'ASPEKT'
GENDER_POS = {'subst'}
GENDER_TAG = 'RODZAJ'
PERSON_POS = {'ppron12'}
PERSON_TAG = 'OSOBA'
CASE_POS = {'prep'}
CASE_TAG = 'PRZYPADEK'
TABLE_TEMPLATES = [
# formy bazowe
(u'rzeczowniki', '0', ('subst', 'osc', 'skrs'), ('f', 'm', 'n', '0'), ()),
(u'pron', '0', ('subst',), ('z0', "z0'", 'z1', 'z1p', 'z2'), ()), # rodzaj nieistotny
(u'my/wy', '0', ('ppron',), ('a',), ()),
(u'ja/ty/się', '0', ('ppron',), ('b', "b'"), ()),
(u'on', '0', ('ppron',), ('c',), ()),
(u'przymiotniki', '0', ('adj',), (), ((), (
u'forma złoż.', u'forma poprz.'
))),
(u'adjcom', '0', ('adjcom',), (), ()), # połączyć z adj
(u'czasowniki', '0', ('v',), ('', '67', 'b'), ((
(u'właściwy', ('', '(Q)'), nQ_ICS),
), ())),
(u'winien', '0', ('v',), ('p',), ((
(u'właściwy', ('', '(Q)'), nQ_ICS),
), ())),
(u'niewłaściwe', '0', ('v',), ('', '67'), ((
(u'właściwy', ('Q',), Q_ICS),
), ())),
(u'ger', '0', ('ger',), (), ()), # docelowo razem z subst
(u'imiesłowy', '0', ('pact', 'ppas', 'appas'), (), ()), # docelowo z adj
(u'num a', '0', ('num',), ('a', 'a1', "a'"), ()),
(u'num b', '0', ('num',), ('b',), ()),
(u'num cd', '0', ('num',), ('c', 'd', "d'", 'd"'), ()),
(u'nieodmienne', '0', (
'adv', 'advcom', 'advndm', 'burk', 'prep', 'comp', 'conj',
'interj', 'qub', 'pred'), (), ()),
(u'prefiksy', '0', ('pref',), (), ()),
# tabelki SGJP
(u'rzeczowniki', '1', ('subst', 'osc', 'skrs'), ('f', 'm', 'n', '0'), ()),
(u'pron', '1', ('subst',), ('z0', "z0'", 'z1', 'z1p', 'z2'), ()), # rodzaj nieistotny
(u'my/wy', '1', ('ppron',), ('a',), ()),
(u'ja/ty/się', '1', ('ppron',), ('b', "b'"), ()),
(u'on', '1', ('ppron',), ('c',), ()),
(u'przymiotniki', '1', ('adj',), (), ((), (
u'forma złoż.', u'forma poprz.'
))),
(u'adjcom', '1', ('adjcom',), (), ()), # połączyć z adj
(u'czasowniki', '1', ('v',), ('', '67', 'b'), ((
(u'właściwy', ('', '(Q)'), nQ_ICS),
), (
u'aspekt',
))),
(u'winien', '1', ('v',), ('p',), ((
(u'właściwy', ('', '(Q)'), nQ_ICS),
), ())),
(u'niewłaściwe', '1', ('v', 'pred'), ('', '67'), ((
(u'właściwy', ('Q',), Q_ICS),
), (
u'aspekt',
))),
(u'ger', '1', ('ger',), (), ()), # docelowo razem z subst
(u'imiesłowy', '1', ('pact', 'ppas', 'appas'), (), ()), # docelowo z adj
(u'num a', '1', ('num',), ('a', 'a1', "a'"), ()),
(u'num b', '1', ('num',), ('b',), ()),
(u'num c', '1', ('num',), ('c',), ()), # można próbować połączyć z d
(u'num d', '1', ('num',), ('d', "d'", 'd"'), ()),
(u'nieodmienne', '1', (
'adv', 'advcom', 'advndm', 'burk', 'prep', 'comp', 'conj',
'interj', 'qub'), (), ()),
(u'prefiksy', '1', ('pref',), (), ()),
# Morfeusz
(u'rzeczowniki', 'Morfeusz', ('subst', 'osc', 'skrs'), ('f', 'm', 'n', '0'), ()),
(u'pron', 'Morfeusz', ('subst',), ('z0', "z0'", 'z1', 'z1p', 'z2'), ()), # rodzaj istotny!
(u'my/wy', 'Morfeusz', ('ppron',), ('a',), ()),
(u'ja/ty/się', 'Morfeusz', ('ppron',), ('b', "b'"), ()),
(u'on', 'Morfeusz', ('ppron',), ('c',), ()),
(u'przymiotniki', 'Morfeusz', ('adj',), (), ((), (
u'forma złoż.', u'forma poprz.'
))),
(u'przymiotniki wyższe', 'Morfeusz', ('adjcom',), (), ()),
(u'czasowniki', 'Morfeusz', ('v',), ('', '67', 'b'), ((
(u'właściwy', ('', '(Q)'), nQ_ICS),
), (
u'aspekt',
))),
(u'winien', 'Morfeusz', ('v',), ('p',), ((
(u'właściwy', ('', '(Q)'), nQ_ICS),
), ())),
(u'niewłaściwe', 'Morfeusz', ('v', 'pred'), ('', '67'), ((
(u'właściwy', ('Q',), Q_ICS),
), (
u'aspekt',
))),
(u'gerundia', 'Morfeusz', ('ger',), (), ()),
(u'imiesłowy czynne', 'Morfeusz', ('pact',), (), ()),
(u'imiesłowy bierne', 'Morfeusz', ('ppas', 'appas'), (), ()),
(u'num a', 'Morfeusz', ('num',), ('a', 'a1', "a'"), ()),
(u'num b', 'Morfeusz', ('num',), ('b',), ()),
(u'num cd', 'Morfeusz', ('num',), ('c', 'd', "d'", 'd"'), ()),
(u'przysłówki', 'Morfeusz', ('adv',), (), ()),
(u'przysłówki wyższe', 'Morfeusz', ('advcom',), (), ()),
(u'przysłówki ndm', 'Morfeusz', ('advndm',), (), ()),
(u'burkinostki', 'Morfeusz', ('burk',), (), ()),
(u'przyimki', 'Morfeusz', ('prep',), (), ()),
(u'prefiksy', 'Morfeusz', ('pref',), (), ()),
(u'spójniki podrz.', 'Morfeusz', ('comp',), (), ()),
(u'spójniki współ.', 'Morfeusz', ('conj',), (), ()),
(u'wykrzykniki', 'Morfeusz', ('interj',), (), ()),
(u'kubliki', 'Morfeusz', ('qub',), (), ()),
# Morfologik
(u'rzeczowniki', 'Morfologik',
('subst', 'osc', 'skrs'),
('f', 'm', 'n', '0'), ()),
(u'pron', 'Morfologik', ('subst',), ('z0', "z0'", 'z1', 'z1p', 'z2'), ()), # jw.
(u'my/wy', 'Morfologik', ('ppron',), ('a',), ()),
(u'ja/ty/się', 'Morfologik', ('ppron',), ('b', "b'"), ()),
(u'on', 'Morfologik', ('ppron',), ('c',), ()),
(u'przymiotniki', 'Morfologik', ('adj',), (), ((), (
u'forma złoż.', u'forma poprz.'
))),
(u'przymiotniki wyższe', 'Morfologik', ('adjcom',), (), ()),
(u'czasowniki', 'Morfologik', ('v',), ('', '67', 'b'), ((
(u'właściwy', ('', '(Q)'), nQ_ICS),
), (
u'aspekt',
))),
(u'winien', 'Morfologik', ('v',), ('p',), ((
(u'właściwy', ('', '(Q)'), nQ_ICS),
), ())),
(u'niewłaściwe', 'Morfologik', ('v', 'pred'), ('', '67'), ((
(u'właściwy', ('Q',), Q_ICS),
), (
u'aspekt',
))),
(u'gerundia', 'Morfologik', ('ger',), (), ()),
(u'imiesłowy czynne', 'Morfologik', ('pact',), (), ()),
(u'imiesłowy bierne', 'Morfologik', ('ppas', 'appas'), (), ()),
(u'num a', 'Morfologik', ('num',), ('a', 'a1', "a'"), ()),
(u'num b', 'Morfologik', ('num',), ('b',), ()),
(u'num cd', 'Morfologik', ('num',), ('c', 'd', "d'", 'd"'), ()),
(u'przysłówki', 'Morfologik', ('adv',), (), ()),
(u'przysłówki wyższe', 'Morfologik', ('advcom',), (), ()),
(u'przysłówki ndm', 'Morfologik', ('advndm',), (), ()),
(u'burkinostki', 'Morfologik', ('burk',), (), ()),
(u'przyimki', 'Morfologik', ('prep',), (), ()),
(u'prefiksy', 'Morfologik', ('pref',), (), ()),
(u'spójniki podrz.', 'Morfologik', ('comp',), (), ()),
(u'spójniki współ.', 'Morfologik', ('conj',), (), ()),
(u'wykrzykniki', 'Morfologik', ('interj',), (), ()),
(u'kubliki', 'Morfologik', ('qub',), (), ()),
]
ADEF_ICS = set(InflectionCharacteristic.objects.filter(
symbol__in=('', '3+'), part_of_speech__symbol='adj'))
F_OSC = InflectionCharacteristic.objects.get(
symbol='f', part_of_speech__symbol='osc')
def rectangles(templates):
groups = {}
for template in templates:
if template.pattern_type not in groups:
groups[template.pattern_type] = set()
groups[template.pattern_type].add(
template.inflection_characteristic)
# QUICK & DIRTY
if template.pattern_type.symbol == 'adef':
groups[template.pattern_type] |= ADEF_ICS
if template.inflection_characteristic.symbol == 'f':
groups[template.pattern_type].add(F_OSC)
reverse_groups = GroupDict()
for pt, ic_set in groups.iteritems():
reverse_groups.add(tuple(sorted(ic_set, key=lambda ic: ic.id)), pt)
#print reverse_groups
return reverse_groups
def add_restrictions(x, pts, ics, attr_vals):
for pt_id in pts:
x.pattern_types.add(pt_id) #add
for ic_id in ics:
x.inflection_characteristics.add(ic_id) #add
ic_symbols = set(ic.symbol for ic in ics)
pos = ics[0].part_of_speech.symbol
for av in attr_vals:
if pos != 'v' or av.value in ic_symbols:
x.attribute_values.add(av) #add
def convert_table_cells(cell_group, new_cell, attr_vals):
table_groups = GroupDict()
for cell in cell_group:
tc = cell.tablecell
table_groups.add(
(tc.row, tc.col, tc.rowspan, tc.colspan, cell.index),
cell)
for table_key, table_group in table_groups.iteritems():
#print table_key
templates = TableTemplate.objects.filter(cell__in=table_group)
for ics, pts in rectangles(templates).iteritems():
new_table_cell = NewTableCell(
row=table_key[0], col=table_key[1],
rowspan=table_key[2], colspan=table_key[3],
index=table_key[4], **new_cell)
new_table_cell.save()
add_restrictions(new_table_cell, pts, ics, attr_vals)
def convert_export_cells(cell_group, new_cell, attr_vals):
export_groups = GroupDict()
for cell in cell_group:
key = cell.tag
ic = cell.table_template.inflection_characteristic
pos = key.split(':', 1)[0]
if pos in ASPECT_POS:
key = key.replace('imperf.perf', ASPECT_TAG)
key = key.replace('imperf', 'ASPEKT').replace('perf', ASPECT_TAG)
elif pos in GENDER_POS and key.split(':')[-1] == ic.symbol:
key = key[:key.rfind(':')] + ':' + GENDER_TAG
elif pos in PERSON_POS:
key = key.replace(ic.symbol, PERSON_TAG)
elif pos in CASE_POS and ic.symbol:
key = key.replace(ic.symbol, CASE_TAG)
export_groups.add(key, cell)
for tag_template, export_group in export_groups.iteritems():
templates = TableTemplate.objects.filter(cell__in=export_group)
for ics, pts in rectangles(templates).iteritems():
new_export_cell = NewExportCell(
tag_template=tag_template, **new_cell)
new_export_cell.save()
add_restrictions(new_export_cell, pts, ics, attr_vals)
def convert_cells(cells, new_template, variant, attr_vals):
cell_groups = GroupDict()
for cell in cells:
cell_groups.add(
(cell.prefix, cell.base_form_label, cell.suffix), cell)
for key, cell_group in cell_groups.iteritems():
#print key[1]
new_cell = {
'table_template': new_template,
'base_form_label': key[1],
'prefix': key[0],
'suffix': key[2]
}
if variant.type == 'table':
convert_table_cells(cell_group, new_cell, attr_vals)
else:
convert_export_cells(cell_group, new_cell, attr_vals)
def convert_headers(headers, new_template, attr_vals):
header_groups = GroupDict()
for h in headers:
header_groups.add(
(h.row, h.col, h.rowspan, h.colspan, h.label, h.css_class),
h)
for key, header_group in header_groups.iteritems():
templates = TableTemplate.objects.filter(tableheader__in=header_group)
for ics, pts in rectangles(templates).iteritems():
new_header = NewTableHeader(
table_template=new_template,
row=key[0], col=key[1], rowspan=key[2], colspan=key[3],
label=key[4], css_class=key[5])
new_header.save()
add_restrictions(new_header, pts, ics, attr_vals)
def convert_tables():
NewTableTemplate.objects.all().delete()
for name, variant_id, poses, p_types, attrs in TABLE_TEMPLATES:
variant = Variant.objects.get(id=variant_id)
new_template = NewTableTemplate(name=name, variant=variant)
new_template.save()
for pos in poses:
new_template.parts_of_speech.add(pos) #add
lexical_classes = LexicalClass.objects.filter(
partofspeech__symbol__in=poses)
pattern_types = PatternType.objects.filter(
lexical_class__in=lexical_classes)
if p_types:
pattern_types = pattern_types.filter(symbol__in=p_types)
for pt in pattern_types:
new_template.pattern_types.add(pt) #add
if attrs:
for name, values, ics in attrs[0]:
attr = LexemeAttribute.objects.get(name=name)
new_template.attributes.add(attr) #add
for v in attr.values.filter(value__in=values):
new_template.attribute_values.add(v)
cell_attrs = LexemeAttribute.objects.filter(name__in=attrs[1])
else:
cell_attrs = ()
attr_vals = LexemeAttributeValue.objects.filter(
attribute__in=cell_attrs)
for attr in cell_attrs:
new_template.cell_attributes.add(attr) #add
tts = TableTemplate.objects.filter(
inflection_characteristic__part_of_speech__symbol__in=poses,
variant=variant)
cells = Cell.objects.filter(table_template__in=tts)
headers = TableHeader.objects.filter(table_template__in=tts)
if p_types:
cells = cells.filter(
table_template__pattern_type__symbol__in=p_types)
headers = headers.filter(
table_template__pattern_type__symbol__in=p_types)
if attrs:
for name, values, ics in attrs[0]:
cells = cells.filter(
table_template__inflection_characteristic__symbol__in=ics)
headers = headers.filter(
table_template__inflection_characteristic__symbol__in=ics)
convert_cells(cells, new_template, variant, attr_vals)
if variant.type == 'table':
convert_headers(headers, new_template, attr_vals)