Walenty / Slowal

Commit 83ceb233ca020e4f70a9c4290901714efdf63d28

Authored by Bartłomiej Nitoń
1 parent 40f59aee
master ... desimilators dev grouping morfeusz rm tomek

Added possibility for selecting vocabularies while creating Walenty exports by scripts.

Inline Side-by-side
Showing 4 changed files with 79 additions and 37 deletions
dictionary/ajax_vocabulary_management.py
  View file @83ceb23
... ... @@ -80,6 +80,8 @@ def create_text_walenty(file_name, lemmas, vocabularies, frame_opinions,
80 80 lemma_statuses_pks=lemma_statuses,
81 81 poss_pks=poss,
82 82 add_frame_opinions=add_frame_opinions))
  83 + if vocabularies.exists():
  84 + lemmas = lemmas.filter(vocabulary__in=vocabularies)
83 85 for lemma in lemmas:
84 86 founded_frame_opinions = lemma.frame_opinions.filter(value__in=frame_opinions)
85 87 #frame_chars_dict = sorted_frame_char_values_dict()
... ...
dictionary/management/commands/create_TEI_walenty.py
  View file @83ceb23
... ... @@ -12,17 +12,29 @@ from dictionary.teixml import createteixml, write_phrase_types_expansions_in_TEI
12 12 from settings import WALENTY_PATH
13 13  
14 14 class Command(BaseCommand):
15   - args = 'none'
  15 + args = '<dict dict ...>'
  16 + help = 'Get Walenty in TEI format.'
16 17  
17 18 def handle(self, *args, **options):
18 19 try:
19 20 now = datetime.datetime.now().strftime('%Y%m%d')
20   - filename_base = '%s_%s' % ('walenty', now)
  21 +
  22 + vocab_names = list(args)
  23 + vocab_names.sort()
  24 + if vocab_names:
  25 + filename_base = '%s_%s_%s' % ('walenty', '+'.join(vocab_names), now)
  26 + else:
  27 + filename_base = '%s_%s' % ('walenty', now)
  28 +
21 29 base_path = os.path.join(WALENTY_PATH, filename_base)
22 30 outpath = base_path + '.xml'
23 31 ready_statuses = get_ready_statuses()
24   - lemmas = Lemma.objects.filter(old=False).order_by('entry_obj__name')
25   - ready_lemmas = lemmas.filter(status__in=ready_statuses)
  32 +
  33 + lemmas = Lemma.objects.filter(old=False)
  34 + if vocab_names:
  35 + lemmas = lemmas.filter(vocabulary__name__in=vocab_names)
  36 + ready_lemmas = lemmas.filter(status__in=ready_statuses).order_by('entry_obj__name')
  37 +
26 38 frame_opinion_values = Frame_Opinion_Value.objects.all()
27 39 createteixml(outpath, ready_lemmas, frame_opinion_values)
28 40 archive = tarfile.open(base_path + '-TEI.tar.gz', 'w:gz')
... ...
dictionary/management/commands/create_tex_walenty.py
  View file @83ceb23
... ... @@ -14,17 +14,28 @@ from dictionary.models import Lemma, WalentyStat, get_ready_statuses
14 14 from settings import WALENTY_PATH
15 15  
16 16 class Command(BaseCommand):
17   - args = 'none'
18   - help = 'Script for creating Walenty vocabulary in tex format.'
  17 + args = '<dict dict ...>'
  18 + help = 'Get Walenty in TeX format.'
19 19  
20 20 def handle(self, *args, **options):
21 21 try:
22 22 now = datetime.datetime.now().strftime('%Y%m%d')
23   - filename_base = '%s_%s' % ('walenty', now)
  23 +
  24 + vocab_names = list(args)
  25 + vocab_names.sort()
  26 + if vocab_names:
  27 + filename_base = '%s_%s_%s' % ('walenty', '+'.join(vocab_names), now)
  28 + else:
  29 + filename_base = '%s_%s' % ('walenty', now)
  30 +
24 31 base_path = os.path.join(WALENTY_PATH, filename_base)
25 32 outpath = base_path + '.tex'
26 33 ready_statuses = get_ready_statuses()
27 34 lemmas = Lemma.objects.filter(old=False)
  35 +
  36 + if vocab_names:
  37 + lemmas = lemmas.filter(vocabulary__name__in=vocab_names)
  38 +
28 39 ready_lemmas = lemmas.filter(status__in=ready_statuses).order_by('entry_obj__name')
29 40 write_tex_walenty(outpath, ready_lemmas)
30 41 archive = tarfile.open(base_path + '-tex.tar.gz', 'w:gz')
... ...
dictionary/management/commands/create_text_walenty.py
  View file @83ceb23
... ... @@ -17,17 +17,30 @@ from dictionary.models import Frame_Opinion, Lemma, Vocabulary, POS, \
17 17 from settings import WALENTY_PATH
18 18  
19 19 class Command(BaseCommand):
20   - args = 'none'
  20 + args = '<dict dict ...>'
  21 + help = 'Get Walenty in text format.'
21 22  
22 23 def handle(self, *args, **options):
23 24 now = datetime.datetime.now().strftime('%Y%m%d')
24   - filename_base = '%s_%s' % ('walenty', now)
  25 +
  26 + vocab_names = list(args)
  27 + vocab_names.sort()
  28 + if vocab_names:
  29 + filename_base = '%s_%s_%s' % ('walenty', '+'.join(vocab_names), now)
  30 + else:
  31 + filename_base = '%s_%s' % ('walenty', now)
  32 +
25 33 realizations_path = os.path.join(WALENTY_PATH,
26 34 '%s_%s.txt' % ('phrase_types_expand', now))
27 35 checked_stats_path = os.path.join(WALENTY_PATH, u'%s_%s.txt' % (filename_base.replace('walenty', 'stats'),
28 36 'verified'))
29 37 ready_stats_path = os.path.join(WALENTY_PATH, u'%s_%s.txt' % (filename_base.replace('walenty', 'stats'),
30 38 'all'))
  39 +
  40 + vocabularies = Vocabulary.objects.none()
  41 + if vocab_names:
  42 + vocabularies = Vocabulary.objects.filter(name__in=vocab_names)
  43 +
31 44 try:
32 45 all_stats = Counter({})
33 46 verified_stats = Counter({})
... ... @@ -35,24 +48,26 @@ class Command(BaseCommand):
35 48 archive = tarfile.open(base_path + '-text.tar.gz', 'w:gz')
36 49 os.chdir(WALENTY_PATH)
37 50 for pos in POS.objects.exclude(tag=u'unk').order_by('priority'):
38   - pos_stats = create_pos_archive_and_get_stats(archive, pos, filename_base)
  51 + pos_stats = create_pos_archive_and_get_stats(archive, pos, vocabularies, filename_base)
39 52 all_stats = all_stats + Counter(pos_stats['all'])
40 53 verified_stats = verified_stats + Counter(pos_stats['verified'])
41 54  
42 55 create_realizations_file(realizations_path)
43 56 archive.add(os.path.basename(realizations_path))
44   - write_stats(checked_stats_path, verified_stats)
45   - archive.add(os.path.basename(checked_stats_path))
46   - write_stats(ready_stats_path, all_stats)
47   - archive.add(os.path.basename(ready_stats_path))
48   - update_walenty_stats(all_stats)
  57 + if not vocab_names:
  58 + write_stats(checked_stats_path, verified_stats)
  59 + archive.add(os.path.basename(checked_stats_path))
  60 + write_stats(ready_stats_path, all_stats)
  61 + archive.add(os.path.basename(ready_stats_path))
  62 + update_walenty_stats(all_stats)
49 63 finally:
50 64 archive.close()
51 65 os.remove(realizations_path)
52   - os.remove(checked_stats_path)
53   - os.remove(ready_stats_path)
  66 + if not vocab_names:
  67 + os.remove(checked_stats_path)
  68 + os.remove(ready_stats_path)
54 69  
55   -def create_pos_archive_and_get_stats(archive, pos, filename_base):
  70 +def create_pos_archive_and_get_stats(archive, pos, vocabularies, filename_base):
56 71 all_stats = {}
57 72 checked_stats = {}
58 73 try:
... ... @@ -65,7 +80,7 @@ def create_pos_archive_and_get_stats(archive, pos, filename_base):
65 80 all_path = os.path.join(WALENTY_PATH, u'%s_%ss_%s' % (filename_base, pos.tag, 'all'))
66 81 walenty_path_ready = create_text_walenty(file_name=all_path,
67 82 lemmas=ready_lemmas,
68   - vocabularies=Vocabulary.objects.none(),
  83 + vocabularies=vocabularies,
69 84 frame_opinions=Frame_Opinion.objects.none(),
70 85 lemma_statuses=ready_statuses,
71 86 owners=User.objects.none(),
... ... @@ -76,8 +91,8 @@ def create_pos_archive_and_get_stats(archive, pos, filename_base):
76 91  
77 92 checked_path = os.path.join(WALENTY_PATH, u'%s_%ss_%s' % (filename_base, pos.tag, 'verified'))
78 93 walenty_path_checked = create_text_walenty(file_name=checked_path,
79   - lemmas=checked_lemmas,
80   - vocabularies=Vocabulary.objects.none(),
  94 + lemmas=checked_lemmas,
  95 + vocabularies=vocabularies,
81 96 frame_opinions=Frame_Opinion.objects.none(),
82 97 lemma_statuses=checked_statuses,
83 98 owners=User.objects.none(),
... ... @@ -85,25 +100,27 @@ def create_pos_archive_and_get_stats(archive, pos, filename_base):
85 100 add_frame_opinions=True)
86 101 checked_filename = os.path.basename(walenty_path_checked)
87 102 archive.add(name=checked_filename, arcname=os.path.join(u'%ss' % pos.tag, checked_filename))
88   -
89   - all_stats = get_stats(ready_statuses, pos.tag)
90   - all_stats_path = os.path.join(WALENTY_PATH, u'%s_%ss_%s.txt' % (filename_base.replace('walenty', 'stats'),
91   - pos.tag, 'all'))
92   - write_stats(all_stats_path, all_stats)
93   - all_stats_filename = os.path.basename(all_stats_path)
94   - archive.add(name=all_stats_filename, arcname=os.path.join(u'%ss' % pos.tag, all_stats_filename))
95   -
96   - checked_stats = get_stats(checked_statuses, pos.tag)
97   - checked_stats_path = os.path.join(WALENTY_PATH, u'%s_%ss_%s.txt' % (filename_base.replace('walenty', 'stats'),
98   - pos.tag, 'verified'))
99   - write_stats(checked_stats_path, checked_stats)
100   - checked_stats_filename = os.path.basename(checked_stats_path)
101   - archive.add(name=checked_stats_filename, arcname=os.path.join(u'%ss' % pos.tag, checked_stats_filename))
  103 +
  104 + if not vocabularies.exists():
  105 + all_stats = get_stats(ready_statuses, pos.tag)
  106 + all_stats_path = os.path.join(WALENTY_PATH, u'%s_%ss_%s.txt' % (filename_base.replace('walenty', 'stats'),
  107 + pos.tag, 'all'))
  108 + write_stats(all_stats_path, all_stats)
  109 + all_stats_filename = os.path.basename(all_stats_path)
  110 + archive.add(name=all_stats_filename, arcname=os.path.join(u'%ss' % pos.tag, all_stats_filename))
  111 +
  112 + checked_stats = get_stats(checked_statuses, pos.tag)
  113 + checked_stats_path = os.path.join(WALENTY_PATH, u'%s_%ss_%s.txt' % (filename_base.replace('walenty', 'stats'),
  114 + pos.tag, 'verified'))
  115 + write_stats(checked_stats_path, checked_stats)
  116 + checked_stats_filename = os.path.basename(checked_stats_path)
  117 + archive.add(name=checked_stats_filename, arcname=os.path.join(u'%ss' % pos.tag, checked_stats_filename))
102 118 finally:
103 119 os.remove(walenty_path_ready)
104 120 os.remove(walenty_path_checked)
105   - os.remove(all_stats_path)
106   - os.remove(checked_stats_path)
  121 + if not vocabularies.exists():
  122 + os.remove(all_stats_path)
  123 + os.remove(checked_stats_path)
107 124 return {'all': all_stats,
108 125 'verified': checked_stats}
109 126  
110 127 \ No newline at end of file
... ...