Skip to content

add index in search #7

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

add index in search #7

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
21 changes: 17 additions & 4 deletions pinyin.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,9 @@
__all__ = ["PinYin"]

import os.path
import re

INDEX =[0,0,0,0,2239,5543,9510,13471,17413,21406,25333]

class PinYin(object):
def __init__(self, dict_file='word.data'):
Expand All @@ -25,8 +27,11 @@ def load_word(self):
with file(self.dict_file) as f_obj:
for f_line in f_obj.readlines():
try:
line = f_line.split(' ')
self.word_dict[line[0]] = line[1]
match = re.compile('\s+')
line = match.split(f_line)
self.word_dict.setdefault(line[0],[])
for value in line[1:]:
self.word_dict[line[0]].append(value)
except:
line = f_line.split(' ')
self.word_dict[line[0]] = line[1]
Expand All @@ -39,8 +44,16 @@ def hanzi2pinyin(self, string=""):

for char in string:
key = '%X' % ord(char)
result.append(self.word_dict.get(key, char).split()[0][:-1].lower())

if len(key)==4:
index = INDEX[(int)(key[0])]
else:
index = INDEX[10]

for ks in sorted(self.word_dict)[index:]:
if key == ks:
result.append(self.word_dict[key][0][:-1].lower())
break

return result


Expand Down