python汉字转拼音

场景说明

把中文汉字、转成汉语拼音,包括:

  • 纯汉字转拼音
  • 汉字里面加有字母转拼音
  • 转加声调的拼音
  • 转用数字表示声调的拼音

install

$ pip install pinyin

《python汉字转拼音》 python.png

引用

GitHub-pinyin

代码

pinyinutil.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import pinyin


def to_pinyin(var_str):
    """
    汉字[钓鱼岛是中国的]=>拼音[diaoyudaoshizhongguode]\n
    汉字[我是shui]=>拼音[woshishui]\n
    汉字[AreYou好]=>拼音[AreYouhao]\n
    汉字[None]=>拼音[]\n
    汉字[]=>拼音[]\n
    :param var_str:  str 类型的字符串
    :return: 汉字转小写拼音
    """
    if isinstance(var_str, str):
        if var_str == 'None':
            return ""
        else:
            return pinyin.get(var_str, format='strip', delimiter="")
    else:
        return '类型不对'

测试代码:

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import unittest
from util.pinyinutil import *
from pinyin._compat import u

class TestPinYin(unittest.TestCase):
    def test_to_pinyin(self):
        list = ['钓鱼岛是中国的', '我是shui', 'AreYou好', None, '']
        for i in list:
            print('汉字[%s]=>拼音[%s]' % (i, to_pinyin(str(i))))

    def test_get(self):
        self.assertEqual(pinyin.get('你好'),
                         pinyin.get('你好', format="diacritical"))
        self.assertEqual(pinyin.get(u('你好'), format="strip"), u('nihao'))
        self.assertEqual(pinyin.get(u('你好'), format="numerical"), u('ni3hao3'))
        self.assertEqual(pinyin.get(u('你好'), format="diacritical"), u('nǐhǎo'))
        self.assertEqual(pinyin.get('你好吗?'), u('nǐhǎoma?'))
        self.assertEqual(pinyin.get('你好吗?'), u('nǐhǎoma?'))

        self.assertEqual(pinyin.get('你好'), u('nǐhǎo'))
        self.assertEqual(pinyin.get('叶'), u('yè'))
        self.assertEqual(pinyin.get('少女'), u('shǎonv̌'))

    def test_get_with_delimiter(self):
        self.assertEqual(pinyin.get('你好', " "), u('nǐ hǎo'))
        self.assertEqual(pinyin.get('你好吗?', " "), u('nǐ hǎo ma ?'))
        self.assertEqual(pinyin.get('你好吗?', " "), u('nǐ hǎo ma ?'))

    def test_get_initial_with_delimiter(self):
        self.assertEqual(pinyin.get_initial('你好', "-"), u('n-h'))
        self.assertEqual(pinyin.get_initial('你好吗?', "-"), u('n-h-m-?'))
        self.assertEqual(pinyin.get_initial('你好吗?', "-"), u('n-h-m-?'))

    def test_get_initial(self):
        self.assertEqual(pinyin.get_initial('你好'), u('n h'))
        self.assertEqual(pinyin.get_initial('你好吗?'), u('n h m ?'))
        self.assertEqual(pinyin.get_initial('你好吗?'), u('n h m ?'))

        self.assertEqual(pinyin.get_initial('你好'), 'n h')

    def test_mixed_chinese_english_input(self):
        self.assertEqual(pinyin.get('hi你好'), u('hinǐhǎo'))

    def test_correct_diacritical(self):
        self.assertEqual(pinyin.get("操"), u("cāo"))
        self.assertEqual(pinyin.get("小"), u("xiǎo"))
        self.assertEqual(pinyin.get("绝"), u("jué"))
        self.assertEqual(pinyin.get("被"), u("bèi"))
        self.assertEqual(pinyin.get("略"), u("lvè"))

    if __name__ == '__main__':
        unittest.main()
    原文作者:马拉松Mara
    原文地址: https://www.jianshu.com/p/5ec83ad2276b
    本文转自网络文章,转载此文章仅为分享知识,如有侵权,请联系博主进行删除。
点赞