mirror of
https://github.com/TheAlgorithms/Python.git
synced 2024-11-28 07:21:07 +00:00
b7f13d991c
* Travis CI: Add type checking with mypy * Create requirements.txt * script: mypy --ignore-missing-stubs=cv2,numpy . * Delete requirements.txt * script: mypy --ignore-missing-imports . * Run doctests * Disable doctest -v other/detecting_english_programmatically.py * Pytest * No | * pytest || true * Run black doctest flake8 mypy pytest * after_success: Build Directory.md * Typo in filename: Dictionary.txt --> dictionary.txt' Discovered via doctest run in #964 * python -m doctest -v * pip install black flake8 mypy pytest * pytest --doctest-glob='*.py' * pytest --doctest-modules * pytest --doctest-modules ./sorts * pytest --doctest-modules ./ciphers ./other ./searches ./sorts ./strings || true * if __name__ == "__main__": * if __name__ == "__main__": * if __name__ == '__main__': * if __name__ == '__main__': * if __name__ == '__main__': * Create requirements.txt * Update requirements.txt * if __name__ == "__main__": * Lose the doctests * if __name__ == '__main__': * Remove print-a-tuple * doctest: Added missing spaces * Update tabu_search.py * The >>> are not doctests so change to >>) * Travis CI: Run black, doctest, flake8, mypy, and pytest * Link to the separate DIRECTORY.md file * Update README.md
55 lines
1.4 KiB
Python
55 lines
1.4 KiB
Python
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
|
|
|
|
|
|
import doctest
|
|
doctest.testmod()
|