├── README.md
└── cixing.py


/README.md:
--------------------------------------------------------------------------------
 1 | # ChineseCixing
 2 | ChineseCixing,针对中文词语的笔画拆解，偏旁查询，拼音转换接口．在当前的中文信息处理当中，语言外部形式上的特征在各个任务中扮演着越来越重要的角色，本项目目的是为提供这一接口
 3 | 
 4 | 
 5 | # 使用方式
 6 |     from cixing import *
 7 |     handler = ChineseCixing()
 8 |     strokes = handler.get_strokes(s)
 9 |     pinyins = handler.get_pinyin(s)
10 |     radicals = handler.get_radical(s)
11 | 
12 | # 测试样例
13 |     s = '自然语言处理是皇冠上的一颗明珠'
14 |     handler = ChineseCixing()
15 |     strokes = handler.get_strokes(s)
16 |     pinyins = handler.get_pinyin(s)
17 |     radicals = handler.get_radical(s)
18 | 
19 |     print('strokes', strokes)
20 |     print('pinyins', pinyins)
21 |     print('radicals', radicals)
22 | 
23 |     strokes: [
24 |           '㇓㇑㇕㇐㇐㇐',
25 |           '㇓㇇㇔㇔㇐㇓㇏㇔㇔㇔㇔㇔',
26 |           '㇔㇊㇐㇑㇕㇐㇑㇕㇐',
27 |           '㇔㇐㇐㇐㇑㇕㇐',
28 |           '㇓㇇㇏㇑㇔',
29 |           '㇐㇐㇑㇀㇑㇕㇐㇐㇑㇐㇐',
30 |           '㇑㇕㇐㇐㇐㇑㇐㇓㇏',
31 |           '㇓㇑㇕㇐㇐㇐㇐㇑㇐',
32 |           '㇔㇇㇐㇐㇓㇟㇐㇚㇔',
33 |           '㇑㇐㇐',
34 |           '㇓㇑㇕㇐㇐㇓㇆㇔',
35 |           '㇐',
36 |           '㇑㇕㇐㇐㇐㇑㇓㇔㇐㇓㇑㇕㇓㇔',
37 |           '㇑㇕㇐㇐㇓㇆㇐㇐',
38 |           '㇐㇐㇑㇀㇓㇐㇐㇑㇓㇏'
39 |           ]
40 | 
41 |     pinyins: ['zi', 'ran', 'yu', 'yan', 'chu', 'li', 'shi', 'huang',
42 |                 'guan', 'shang', 'de', 'yi', 'ke', 'ming', 'zhu']
43 |     radicals: ['自', '灬', '讠', '言', '夂', '王', '日', '白',
44 |                 '冖', '一', '白', '一', '页', '日', '王']
45 | 
46 | 
47 | 
48 | 


--------------------------------------------------------------------------------
/cixing.py:
--------------------------------------------------------------------------------
 1 | #!/usr/bin/env python3
 2 | # coding:utf-8
 3 | # File:cixing.py
 4 | # Author:lhy<lhy_in_blcu@126.com>
 5 | # Date:2018/6/9
 6 | from pypinyin import lazy_pinyin
 7 | import os
 8 | 
 9 | class ChineseCixing:
10 |     def __init__(self):
11 |         cur_dir = '/'.join(os.path.abspath(__file__).split('/')[:-1])
12 |         strokefile = os.path.join(cur_dir, 'strokes.txt')
13 |         radicalfile = os.path.join(cur_dir, 'radicals.txt')
14 |         self.char_dict = {
15 |             "点": "㇔",
16 |             "横": "㇐",
17 |             "横钩": "㇖",
18 |             "横撇": "㇇",
19 |             "横撇弯钩": "㇌",
20 |             "横斜钩": "⺄",
21 |             "横折": "㇕",
22 |             "横折竖钩": "㇆",
23 |             "横折提": "㇊",
24 |             "横折弯": "㇍",
25 |             "横折弯钩": "㇈",
26 |             "横折折": "㇅",
27 |             "横折折撇": "㇋",
28 |             "横折折折": "㇎",
29 |             "横折折折钩": "㇡",
30 |             "捺": "㇏",
31 |             "撇": "㇓",
32 |             "撇点": "㇛",
33 |             "撇折": "㇜",
34 |             "竖": "㇑",
35 |             "竖钩": "㇚",
36 |             "竖提": "㇙",
37 |             "竖弯": "㇄",
38 |             "竖弯横钩": "㇟",
39 |             "竖折": "㇗",
40 |             "竖折撇": "ㄣ",
41 |             "竖折折": "㇞",
42 |             "竖折折钩": "㇉",
43 |             "提": "㇀",
44 |             "弯钩": "㇁",
45 |             "卧钩": "㇃",
46 |             "斜钩": "㇂",
47 |             }
48 |         self.stroke_dict = {i.strip().split(':')[0]:[self.char_dict[j.split('/')[0]] for j in i.strip().split(':')[1].split(',')] for i in open(strokefile) if i.strip()}
49 |         self.radical_dict = {i.strip().split(':')[0]:i.strip().split(':')[1] for i in open(radicalfile) if i.strip()}
50 | 
51 |     '''获取汉字笔画'''
52 |     def get_strokes(self, word):
53 |         strokes = []
54 |         chars = [c for c in word]
55 |         for c in chars:
56 |             stroke = ''.join(self.stroke_dict.get(c, c))
57 |             strokes.append(stroke)
58 |         return strokes
59 | 
60 |     '''获取汉字汉语拼音'''
61 |     def get_pinyin(self, word):
62 |         pinyins = lazy_pinyin(word)
63 |         return pinyins
64 | 
65 |     '''获取汉字偏旁部首'''
66 |     def get_radical(self, word):
67 |         radicals = []
68 |         chars = [c for c in word]
69 |         for c in chars:
70 |             stroke = self.radical_dict.get(c, c)
71 |             radicals.append(stroke)
72 |         return radicals
73 | 
74 | 
75 | def demo():
76 |     word = '自然语言处理是皇冠上的一颗明珠'
77 |     handler = ChineseCixing()
78 |     strokes = handler.get_strokes(word)
79 |     pinyins = handler.get_pinyin(word)
80 |     radicals = handler.get_radical(word)
81 | 
82 |     print('strokes', strokes)
83 |     print('pinyins', pinyins)
84 |     print('radicals', radicals)
85 | 
86 | if __name__ == '__main__':
87 |     demo()
88 | 


--------------------------------------------------------------------------------