Skip to content

[pull] master from zer4tul:master #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[pull] master from zer4tul:master #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 11 additions & 3 deletions tools/IME/Baidu.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,6 +61,7 @@ def _get_word(self, data, length = 0, pure_english = False):
else:
word.pinyin = ' '.join(pinyin)
hanzi = byte2str(data[pos:pos+ length*2])
hanzi = hanzi.strip('\x00')
pos = pos+ length*2
word.value = hanzi.encode('utf-8')
return word
Expand Down Expand Up @@ -101,9 +102,16 @@ def read(self, data):
pos = pos + length * 4
if word.value:
if self.dictionary.has_key(word.pinyin):
self.dictionary[word.pinyin].append(word)
# 校验拼音和词汇的长度是否相等，如不相等则丢弃
if len(word.value.decode('utf-8')) == len(word.pinyin.split(' ')):
self.dictionary[word.pinyin].append(word)
# print(word.value.decode('utf-8'), len(word.value.decode('utf-8')), word.pinyin,len(word.pinyin.split(' ')))
#if word.value.decocde('utf-8') == u'\u7fbd\u5b50':
# print(word.dump())
else:
self.dictionary[word.pinyin] = []
self.dictionary[word.pinyin].append(word)
if len(word.value.decode('utf-8')) == len(word.pinyin.split(' ')):
self.dictionary[word.pinyin] = []
self.dictionary[word.pinyin].append(word)
# print(word.dump())

return self.dictionary
24 changes: 23 additions & 1 deletion tools/IME/tools.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,6 +88,13 @@ def __init__(self, value='', encoding='utf-8', count=0):
self.encoding = encoding
def __repr__(self):
return self.value
def dump(self):
return {'value' : self.value,
'count' : self.count,
'pinyin' : self.pinyin,
'encoding' : self.encoding
}


class WordDict(dict):
def _opencc(self, string):
Expand Down Expand Up @@ -116,8 +123,23 @@ def zhs_to_zht(self):
for line in tmp_string.split('\n'):
key, words = line.split(':', 1)
words = words.split('\t')

for i in xrange(len(self[key])):
self[key][i].value = words[i]
self[key][i].value = words[i]
# print(self[key], len(self[key]), words)
# for i in xrange(len(self[key])):
# if len(self[key][i].value.decode('utf-8')) == len(words[i].decode('utf-8')):
# self[key][i].value = words[i]
# else:
# for j in xrange(len(words)):
# #print(self[key][i].value.decode('utf-8'), words[j].decode('utf-8'))
# print(self[key][i].value)
# print(words[j])
# #if self[key][i].value.decode('utf-8') == words[j].decode('utf-8'):
# if len(self[key][i].value) == len(words[j].decode('utf-8')):
# print(self[key])
# self[key][i].value = words[j]

# self[key] = map(self._opencc, self[key])
# for i in xrange(len(self[key])):
# self[key][i].value = self._opencc(self[key][i].value)
Expand Down