def load(source_slug, name_slug, chunk_len=200, debug=False):
print source_slug
print name_slug
i = 0
bulk = Bulk(source_slug, name_slug, chunk_len)
slug = "%s_%s" % (source_slug, name_slug)
parts = get_parts(slug, '\n\n')
for part in parts:
# print part
# print
if not part:
continue
try:
num, word, desc = part.split('\n', 2)
except ValueError:
num, word = part.split('\n', 1)
desc = ''
if num[:3] != 'id=':
print '### WRONG_NUM ###', num, part
num = num[3:]
# if num[-2:] == '.d':
# num = num[:-2]
# # todo: write bool, downloaded or not
word = word.decode('utf8').strip()
desc = desc.decode('utf8').strip()
if (source_slug, name_slug) == ('academic', 'efremova'):
# print word
word, desc = desc.split('\n', 1)
# print word
word = word.replace(u'́', '')
# print word
if (source_slug, name_slug) == ('academic', 'kuznetsov'):
if desc.find(u'[с прописной буквы]') != -1:
# todo: бывает и с большой буквы, и с маленькой "Галактика"
print word
word = word.capitalize()
print word
# word = prettify(word, encoding=False).decode('utf8')
# desc = prettify(desc, encoding=False).decode('utf8')
word = remove_end(word, ['1', '2', ' .', ';']).strip()
if not check_word(word, debug): # "-" and " "
continue
bulk.add(word, desc, num)
# todo: also save num to db
# print num
# print desc
# print
i += 1
# if i > 10:
# break
if not i % 10000:
print i
def load(chunk_len=200, debug=False):
print source_slug
print name_slug
bulk = Bulk(source_slug, name_slug, chunk_len)
lines = get_lines(slug)
for line in lines:
word, desc = line.split('#')
word = prettify(word)
desc = prettify(desc)
if not check_word(word, debug): # "-", "." and " "
continue
bulk.add(word, desc)
bulk.process()
def load(chunk_len=200, debug=False):
for source_slug, name_slug in slugs:
print source_slug
print name_slug
bulk = Bulk(source_slug, name_slug, chunk_len)
slug = "%s_%s" % (source_slug, name_slug)
lines = get_lines(slug)
for value in lines:
value = prettify(value, remove_dot=False)
if not check_word(value, debug): # "-" and "."
continue
bulk.add(value)
bulk.process()
def load(chunk_len=200, debug=False):
print source_slug
print name_slug
bulk = Bulk(source_slug, name_slug, chunk_len)
parts = get_parts(slug, '\n\n')
for desc in parts:
desc = prettify(join_lines(desc))
first_words = re.findall(u'^([-А-ЯЁ\d][-А-ЯЁ\d]*\.?\.?\.?)', desc,
re.UNICODE)
if len(first_words) != 1:
print u'Ошибка в первом слове:'
print '#', desc
word = first_words[0]
words = [word]
cutted = desc[len(word):]
other_words = re.findall(u'\W([А-ЯЁ][-А-ЯЁ\d]+\.?\.?\.?)\W', cutted,
re.UNICODE)
# todo: слова с пробелами: "ВСЕ Ж ТАКИ" (2 случая)
for word in other_words:
length = cutted.index(word) + len(word)
wrong_words = [
u'США', u'США.', u'СССР', u'ССР', u'СЯ', u'СЯ1', u'ЧК', u'СЯ2',
u'ТЕ', u'СЯ1-2', u'ЭВМ', u'ВЛКСМ', u'Т-34']
# 70 получено опытным путем и годится только для этого файла
if length <= 70 and word not in wrong_words:
words.append(word)
for i in range(len(words)):
word = remove_last_dot(words[i])
if re.search('\d-\d-\d$', word):
word = word[:-5]
elif re.search('\d-\d$', word):
word = word[:-3]
elif re.search('\d$', word):
word = word[:-1]
elif re.search('\d-\d\.\.\.$', word):
word = word[:-6] + word[-3:]
elif re.search('\d\.\.\.$', word):
word = word[:-4] + word[-3:]
elif re.search('\d', word):
print u'Ошибка! Цифра в слове: ', word
words[i] = word
words = set(words) # remove duplicates
for word in words:
if not check_word(word, debug): # "-" and "..."
continue
bulk.add(word, desc)
bulk.process()
def load(chunk_len=200, debug=False):
print source_slug
print name_slug
bulk = Bulk(source_slug, name_slug, chunk_len)
lines = get_parts(slug, '\n ')
for desc in lines:#[:1000]:
desc = prettify(join_lines(desc))
words = re.findall(u'^([-А-ЯЁ\d][-А-ЯЁ\d\s?]*)\W', desc, re.UNICODE)
if not words:
bulk.append_desc(desc)
continue
word = prettify(words[0], encoding=False)
if not check_word(word, debug):
continue
bulk.add(word, desc)
bulk.process()
def load(chunk_len=200, debug=False):
print source_slug
print name_slug
bulk = Bulk(source_slug, name_slug, chunk_len)
lines = get_lines(slug)
for line in lines:
word, desc = line.split('#', 1)
# todo: не покрывает два случая:
# - Господин# (ж. р. госпожа)#, владелец, ...
# - Приходить# (прийти# ), прибыть, ...
# todo: c запятыми можно отдельно повозиться:
# - аутентичный (автентичный, отентичный)
# - барон, баронет
# - бросать деньги (за окно, на ветер)
word = prettify(word).upper()
desc = prettify(remove_begin(desc, [',', '||']).strip())
if not check_word(word, debug): # "-", "," and " "
continue
bulk.add(word, desc)
bulk.process()