bytileAggregator.py 文件源码

def extract_keywords(sentence, keywords):
    # check if there are keywords for the sentence language
    language = sentence['Language']
    if language in keywords:
        languageKeywords = keywords[language]
        keywordMatches = []
        if languageKeywords != None:
            message = sentence['Sentence']
            # tokenize the sentence
            for keyword in sorted(languageKeywords):
                keywordRegex = languageKeywords[keyword]
                if keywordRegex.search(message):
                    # if match, add keyword canonical form to list
                    keywordMatches.append(keyword)
        sentence['Keywords'] = keywordMatches
    return sentence