create_TEI_walenty.py
6.19 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
#-*- coding:utf-8 -*-
import datetime
import os
import tarfile
from django.core.management.base import BaseCommand
from optparse import make_option
from dictionary.models import Lemma, Frame_Opinion_Value, POS, \
get_statuses
from dictionary.teixml import createteixml, write_phrase_types_expansions_in_TEI
from settings import WALENTY_PATH
class Command(BaseCommand):
args = '<dict dict ...>'
help = 'Get Walenty in TEI format.'
option_list = BaseCommand.option_list + (
make_option('--min_status',
action='store',
type='string',
dest='min_status_type',
default='ready',
help='Minimum lemma status.'),
make_option('--pos',
action='store',
type='string',
dest='pos',
default='all',
help='Part of speech tag.'),
make_option('--start_date',
action='store',
type='string',
dest='start_date',
default='all',
help='Status change start date (format: YYYY-MM-DD).'),
)
def handle(self, *args, **options):
try:
now = datetime.datetime.now().strftime('%Y%m%d')
vocab_names = list(args)
vocab_names.sort()
filename_base = self.create_filename_base(vocab_names, options, now)
base_path = os.path.join(WALENTY_PATH, filename_base)
outpath = base_path + '.xml'
statuses = get_statuses(options['min_status_type'])
lemmas = Lemma.objects.filter(old=False)
if vocab_names:
lemmas = lemmas.filter(vocabulary__name__in=vocab_names)
lemmas = lemmas.filter(status__in=statuses)
if options['start_date'] != 'all':
lemmas = self.filter_lemmas_by_status_change(lemmas, statuses, options['start_date'])
if options['pos'] != 'all':
lemmas = lemmas.filter(entry_obj__pos__tag=options['pos'])
lemmas = self.add_related_lemmas(lemmas)
lemmas = lemmas.order_by('entry_obj__name')
self.print_statistics(lemmas)
frame_opinion_values = Frame_Opinion_Value.objects.all()
createteixml(outpath, lemmas, frame_opinion_values)
phrase_types_expand_path = os.path.join(WALENTY_PATH,
'%s_%s.xml' % ('phrase_types_expand', now))
write_phrase_types_expansions_in_TEI(phrase_types_expand_path)
archive = tarfile.open(base_path + '-TEI.tar.gz', 'w:gz')
os.chdir(WALENTY_PATH)
archive.add(os.path.basename(outpath))
archive.add(os.path.basename(phrase_types_expand_path))
finally:
archive.close()
os.remove(outpath)
os.remove(phrase_types_expand_path)
def create_filename_base(self, vocab_names, options, now):
start_date = ''
if options['start_date'] != 'all':
start_date = '-' + options['start_date'].replace('-', '')
vocab_names_str = ''
if vocab_names:
vocab_names_str = '-' + '+'.join(vocab_names)
min_status = ''
if options['min_status_type'] != 'ready':
min_status = '-' + options['min_status_type']
filename_base = 'walenty%s%s%s_%s' % (min_status, vocab_names_str,
start_date, now)
return filename_base
def filter_lemmas_by_status_change(self, lemmas, statuses, start_date_str):
start_date = self.parse_date(start_date_str)
filtered_lemmas_pks = []
for lemma in lemmas:
if lemma.status_history.filter(status=statuses[0], date__gte=start_date).exists():
filtered_lemmas_pks.append(lemma.pk)
return lemmas.filter(pk__in=filtered_lemmas_pks)
def parse_date(self, date_str):
date_parts = date_str.split('-')
year = int(date_parts[0])
month = int(date_parts[1].lstrip('0'))
day = int(date_parts[2].lstrip('0'))
date = datetime.datetime(year, month, day, 00, 00)
return date
def add_related_lemmas(self, lemmas):
all_lemmas_pks = []
for lemma in lemmas:
all_lemmas_pks.append(lemma.pk)
if lemma.semantics_ready():
entry = lemma.entry_obj
visible_frames = entry.visible_frames()
for frame in visible_frames:
if frame.entry != entry and not lemmas.filter(entry_obj=frame.entry).exists():
all_lemmas_pks.append(frame.entry.actual_lemma().pk)
return Lemma.objects.filter(pk__in=all_lemmas_pks)
def print_statistics(self, lemmas):
self.print_total_statistics(lemmas)
self.print_statistics_by_pos(lemmas)
def print_total_statistics(self, lemmas):
count = {'frames': 0,
'arguments': 0}
for lemma in lemmas:
frames = lemma.entry_obj.actual_frames()
count['frames'] += frames.count()
for frame in frames.all():
count['arguments'] += frame.complements.count()
print (u'Total:')
print (u'-- Lemmas:\t%d' % lemmas.count())
print (u'-- Frames:\t%d' % count['frames'])
print (u'-- Arguments:\t%d' % count['arguments'])
def print_statistics_by_pos(self, lemmas):
for pos in POS.objects.all():
pos_lemmas = lemmas.filter(entry_obj__pos=pos)
if pos_lemmas.exists():
count = {'frames': 0,
'arguments': 0}
for lemma in pos_lemmas:
frames = lemma.entry_obj.visible_frames()
count['frames'] += frames.count()
for frame in frames.all():
count['arguments'] += frame.complements.count()
print (u'%s (%s):' % (pos.name, pos.tag))
print (u'-- Lemmas:\t%d' % pos_lemmas.count())
print (u'-- Frames:\t%d' % count['frames'])
print (u'-- Arguments:\t%d' % count['arguments'])