mirror of
https://hub.njuu.cf/TheAlgorithms/Python.git
synced 2023-10-11 13:06:12 +08:00
Initial
This commit is contained in:
parent
ccf062a388
commit
052bcb1f52
45333
detect english/Dictionary.txt
Normal file
45333
detect english/Dictionary.txt
Normal file
File diff suppressed because it is too large
Load Diff
41
detect english/detecting_english_programmatically.py
Normal file
41
detect english/detecting_english_programmatically.py
Normal file
@ -0,0 +1,41 @@
|
||||
UPPERLETTERS = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
|
||||
LETTERS_AND_SPACE = UPPERLETTERS + UPPERLETTERS.lower() + ' \t\n'
|
||||
|
||||
def loadDictionary():
|
||||
dictionaryFile = open('Dictionary.txt')
|
||||
englishWords = {}
|
||||
for word in dictionaryFile.read().split('\n'):
|
||||
englishWords[word] = None
|
||||
dictionaryFile.close()
|
||||
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):
|
||||
wordsMatch = getEnglishCount(message) * 100 >= wordPercentage
|
||||
numLetters = len(removeNonLetters(message))
|
||||
messageLettersPercentage = (float(numLetters) / len(message)) * 100
|
||||
lettersMatch = messageLettersPercentage >= letterPercentage
|
||||
return wordsMatch and lettersMatch
|
Loading…
Reference in New Issue
Block a user