strings/detecting_english_programmatically.py · python/Python

代码拉取完成,页面将自动刷新

richgiteeai

Watch

不关注关注所有动态仅关注版本发行动态关注但不提醒动态

1 Star 0 Fork 324

python/Python

forked from 编程语言算法集/Python

代码 Issues 0 Pull Requests 0 Wiki 统计流水线

服务

加入 Gitee

与超过 1400万开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)

免费加入

已有帐号? 立即登录

文件

master

分支 (54)

管理

master

mypy-reality-check

Python-3.10-beta-1

bubble_sort

Fix-validate_initial_digits-of-credit_card_validator.py

long-running-tests

fix-project-euler-problem-15

mypy-project-euler-092-sol-1

Add-tests-to-morse_code.py

from-__future__-import-annotations

flake8-bugbear

is_ip_v4_address_valid.py

cclauss-patch-4

cclauss-patch-3

mypy_--install-types_--non-interactive

Write-for-current-Python

harris_corner.py

dhruvmanila-patch-1

refactor/action

fix/action

克隆/下载

HTTPS SSH SVN SVN+SSH 下载ZIP

提示

下载代码请复制以下命令到终端执行

为确保你提交的代码身份被 Gitee 正确识别,请执行以下命令完成配置

git config --global user.name userName 
git config --global user.email userEmail

初次使用 SSH 协议进行代码克隆、推送等操作时,需按下述提示完成 SSH 配置

1 生成 RSA 密钥

2 获取 RSA 公钥内容,并配置到 SSH公钥中

在 Gitee 上使用 SVN,请访问使用指南

使用 HTTPS 协议时,命令行会出现如下账号密码验证步骤。基于安全考虑,Gitee 建议配置并使用私人令牌替代登录密码进行克隆、推送等操作

Username for 'https://gitee.com': userName

Password for 'https://userName@gitee.com': # 私人令牌

分支 54

标签 0

Python

strings

detecting_english_programmatically.py

detecting_english_programmatically.py 1.46 KB

import os

UPPERLETTERS = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
LETTERS_AND_SPACE = UPPERLETTERS + UPPERLETTERS.lower() + " \t\n"

def loadDictionary():
 path = os.path.split(os.path.realpath(__file__))
 englishWords = {}
 with open(path[0] + "/dictionary.txt") as dictionaryFile:
 for word in dictionaryFile.read().split("\n"):
 englishWords[word] = None
 return englishWords

ENGLISH_WORDS = loadDictionary()

def getEnglishCount(message):
 message = message.upper()
 message = removeNonLetters(message)
 possibleWords = message.split()

if possibleWords == []:
 return 0.0

matches = 0
 for word in possibleWords:
 if word in ENGLISH_WORDS:
 matches += 1

return float(matches) / len(possibleWords)

def removeNonLetters(message):
 lettersOnly = []
 for symbol in message:
 if symbol in LETTERS_AND_SPACE:
 lettersOnly.append(symbol)
 return "".join(lettersOnly)

def isEnglish(message, wordPercentage=20, letterPercentage=85):
 """
 >>> isEnglish('Hello World')
 True

>>> isEnglish('llold HorWd')
 False
 """
 wordsMatch = getEnglishCount(message) * 100 >= wordPercentage
 numLetters = len(removeNonLetters(message))
 messageLettersPercentage = (float(numLetters) / len(message)) * 100
 lettersMatch = messageLettersPercentage >= letterPercentage
 return wordsMatch and lettersMatch

if __name__ == "__main__":
 import doctest

doctest.testmod()

一键复制编辑原始数据按行查看历史

algobytewise 提交于 2021年03月21日 19:05 +08:00 . Move files to strings folder (#4283)

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61

import os

UPPERLETTERS = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
LETTERS_AND_SPACE = UPPERLETTERS + UPPERLETTERS.lower() + " \t\n"


def loadDictionary():
 path = os.path.split(os.path.realpath(__file__))
 englishWords = {}
 with open(path[0] + "/dictionary.txt") as dictionaryFile:
 for word in dictionaryFile.read().split("\n"):
 englishWords[word] = None
 return englishWords


ENGLISH_WORDS = loadDictionary()


def getEnglishCount(message):
 message = message.upper()
 message = removeNonLetters(message)
 possibleWords = message.split()

 if possibleWords == []:
 return 0.0

 matches = 0
 for word in possibleWords:
 if word in ENGLISH_WORDS:
 matches += 1

 return float(matches) / len(possibleWords)


def removeNonLetters(message):
 lettersOnly = []
 for symbol in message:
 if symbol in LETTERS_AND_SPACE:
 lettersOnly.append(symbol)
 return "".join(lettersOnly)


def isEnglish(message, wordPercentage=20, letterPercentage=85):
 """
 >>> isEnglish('Hello World')
 True

 >>> isEnglish('llold HorWd')
 False
 """
 wordsMatch = getEnglishCount(message) * 100 >= wordPercentage
 numLetters = len(removeNonLetters(message))
 messageLettersPercentage = (float(numLetters) / len(message)) * 100
 lettersMatch = messageLettersPercentage >= letterPercentage
 return wordsMatch and lettersMatch


if __name__ == "__main__":
 import doctest

 doctest.testmod()