def find_match_word(hash_content, wordlist):
split_words = []
while len(hash_content) !=0:
#return the index of the matched word
word, index = check_match(hash_content,wordlist)
split_words.append(word)
#remove the matched words from the original tokens
hash_content = hash_content[len(hash_content)*(-1):index]
return split_words
#use WordNetLemmatizer to lemmatize the word
评论列表
文章目录