__all__ = ['get', 'get_pinyin', 'get_initial']
import os
# init pinyin dict
pinyin_dict = {}
dat = os.path.join(os.path.dirname(__file__), "Mandarin.dat")
with open(dat) as f:
for line in f:
k, v = line.strip().split('\t')
pinyin_dict[k] = v.lower().split(" ")[0][:-1]
from . import compat
def _pinyin_generator(chars):
"""Generate pinyin for chars, if char is not chinese character,
itself will be returned.
Chars must be unicode list.
"""
for char in chars:
key = "%X" % ord(char)
yield pinyin_dict.get(key, char)
def get(s, delimiter=''):
"""Return pinyin of string, the string must be unicode
"""
s = compat.u(s)
return delimiter.join(_pinyin_generator(s))
def get_pinyin(s):
"""This function is only for backward compatibility, use `get` instead.
"""
import warnings
warnings.warn('Deprecated, use `get` instead.')
return get(s)
def get_initial(s, delimiter=' '):
"""Return the 1st char of pinyin of string, the string must be unicode
"""
s = compat.u(s)
return delimiter.join([p[0] for p in _pinyin_generator(s)])
python 拼音模块
需积分: 50 45 浏览量
2015-12-02
13:03:33
上传
评论
收藏 123KB GZ 举报
tc936596778
- 粉丝: 0
- 资源: 1
最新资源
- Python大作业:音乐播放软件(爬虫+可视化+数据分析+数据库)
- 课程设计-python爬虫-爬取日报,爬取日报文章后存储到本地,附带源代码+课程设计报告
- 软件和信息技术服务行业投资与前景预测.pptx
- 课程设计-基于SpringBoot + Mybatis+python爬虫NBA球员数据爬取可视化+源代码+文档+sql+效果图
- 软件品质管理系列二项目策划规范.doc
- 基于TensorFlow+PyQt+GUI的酒店评论情感分析,支持分析本地数据文件和网络爬取数据分析+源代码+文档说明+安装教程
- 软件定义无线电中的模拟电路测试技术.pptx
- 软件开发协议(作为技术开发合同附件).doc
- 软件开发和咨询行业技术趋势分析.pptx
- 软件测试题详解及答案.doc
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈