python 汉字转拼音,五笔

拼音方法一(较全)

下载库:Mandarin.dat

Python
01
#coding:utf-8
02
class pinyin():
03
    def __init__(self, data_path='./Mandarin.dat'):
04
        self.dict = {}
05
        for line in open(data_path):
06
            k, v = line.split('\t')
07
            self.dict[k] = v
08
        self.splitter = ''
09
    def pinyin(self, chars):
10
        result = []
11
        for char in chars:
12
            key = "%X" % ord(char)
13
            try:
14
                result.append(self.dict[key].split(" ")[0].strip()[:-1].lower())
15
            except:
16
                result.append(char)
17
        return self.splitter.join(result)
18
if __name__ == "__main__":
19
    p = pinyin()
20
    print p.pinyin(u"中国人的一天")

五笔与拼音

下载库:ChineseCode.dat

Python
01
#coding:utf-8
02
class pinyin():
03
    def __init__(self, data_path='./ChineseCode.dat'):
04
        self.dict = {}
05
        for line in open(data_path):
06
            v = line.split('\t')
07
            self.dict[v[0]] = v[6]
08
        self.splitter = ''
09
    def wb(self, chars):
10
        result = []
11
        for char in chars:
12
            key = "%X" % ord(char)
13
            try:
14
                result.append(self.dict[key]+'\n')
15
            except:
16
                result.append(char)
17
        return self.splitter.join(result)
18
    def pinyin(self, chars):
19
        result = []
20
        for char in chars:
21
            key = "%X" % ord(char)
22
            try:
23
                result.append(self.dict[key].split(",")[0].strip()[:-1].lower())
24
            except:
25
                result.append(char)
26
        return self.splitter.join(result)
27
if __name__ == "__main__":
28
    p = pinyin()
29
    print p.get_wb(u"小强")

合并两者

Python
01
#coding:utf-8
02
import cPickle
03
dict = {}
04
i=0;
05
for line in open('./Mandarin.dat'):
06
    k, v = line.split('\t')
07
    dict[k] = v.rstrip().lower()
08
    i += 1
09
    #if i > 1000: break
10
i=0;
11
for line in open('./ChineseCode.dat'):
12
    items = line.split('\t')
13
    #if dict.get(items[0]) <> None:
14
        #print dict.get(items[0]), items[6]
15
    key = items[0]
16
    if  key in dict:
17
        dict[key] = dict[key] + '\t' + items[6] + '\t' + items[2]
18
        if i % 100 ==0:
19
            print i
20
    i += 1
21
f = file('ChineseCode2.dat', 'w')
22
cPickle.dump(dict, f)
23
f.close()
24
 
25
#print dict

较完整的拼音与五笔

Python
01
#coding:utf-8
02
import cPickle
03
class CnCode():
04
    def __init__(self):
05
        f = file('./ChineseCode2.dat')
06
        self.dict = cPickle.load(f)
07
        f.close()
08
 
09
    def pinyin(self, chars,splitter=' '):
10
        result = []
11
        for char in chars:
12
            key = "%X" % ord(char)
13
            try:
14
                result.append(self.dict[key].split("\t")[0].split(" ")[0].strip()[:-1])
15
            except:
16
                result.append(char)
17
        return splitter.join(result)
18
 
19
    def wb(self, char,splitter=','):
20
        key = "%X" % ord(char)
21
        try:
22
            result = self.dict[key].split("\t")[1].strip()
23
            result = splitter.join(result.split(" "))
24
        except:
25
            result = char
26
        return result
27
if __name__ == "__main__":
28
    p = CnCode()
29
    print p.pinyin(u"中国人的一天")
30
    print p.wb(u"国")

为拼音加上声调

ChineseCode2.dat下载

Python
view plain
print?
01
#coding:utf-8
02
import cPickle
03
import re
04
class CnCode():
05
    '''汉字拼音与五笔及声调对照类
06
 
07
    @author HzqGhost admin@ QQ:313143468'''
08
    def __init__(self):
09
        f = file('./ChineseCode2.dat')
10
        self.dict = cPickle.load(f)
11
        f.close()
12
        self.yunmu = ( 'ang','eng','ing','ong','an','en','in','un','ai','ei','ui','ao','ou','iu','ie','ue','er','en','a','o','e','i','u')
13
        self.sheng = {'a':'ā á ǎ à','o':'ō ó ǒ ò','e':'ē é ě è','i':'ī í ǐ ì','u':'ū ú ǔ ù'}
14
 
15
    def pinyin(self, chars, splitter=' ', issheng=False, isFirstUpper=True):
16
        '''汉字转拼音 powered by blog. (hzqghost)
17
 
18
        --chars [ustring] 查找对象
19
        --splitter [string] 连接字符串
20
        --issheng [bool] 是否返回带有声调的拼音
21
        --isFirstUpper [bool] 是否首字母大写'''
22
        result = []
23
        for char in chars:
24
            key = "%X" % ord(char)
25
            py = ''
26
            try:
27
                if self.dict.has_key(key):
28
                    py = self.dict[key].split("\t")[0].split(" ")[0].strip()
29
                    if issheng:
30
                        for ym in self.yunmu:
31
                            if re.search(ym, py):
32
                                t = py[-1:].encode('ascii','ignore')
33
                                t2 = "%d" % ord(t)
34
                                t3 = (int(t2) - 48)%4 -1
35
                                py2 = py[:-len(ym)-1]
36
                                letter = self.sheng[ym[0]].split(' ')[t3]
37
                                ym = letter + ym[1:]
38
                                py = py2 + ym
39
                                break
40
                    else:
41
                        py = py[:-1]
42
                    if isFirstUpper:
43
                        py = py[0:1].upper()+py[1:]
44
                    result.append(py)
45
            except:
46
                pass
47
        return splitter.join(result)
48
 
49
    def wb(self, char,splitter=','):
50
        key = "%X" % ord(char)
51
        try:
52
            result = self.dict[key].split("\t")[1].strip()
53
            result = splitter.join(result.split(" "))
54
        except:
55
            result = char
56
        return result
57
 
58
if __name__ == "__main__":
59
    p = CnCode()
60
    print p.pinyin(u"中国人的一天我看", ' ',True)
61
    print p.wb(u"国")