python关键词匹配利器FlashText

关键词匹配利器FlashText

• 在实际开发工作中经常遇到，根据词表或映射表，查找或替换文本中内容，比较简单处理方法就是逐词匹配，这种处理方式不是高效的，而且代码写起来也会感觉很啰嗦，使用FlashText能够很好的帮助我们解决这个问题。

• 提取文本中字典涉及的关键词并将多个词归一化为某个关键词
  from flashtext import KeywordProcessor
  >>> keyword_processor = KeywordProcessor()
  >>> # keyword_processor.add_keyword(, )
  >>> keyword_processor.add_keyword(‘Big Apple’, ‘New York’)
  >>> keyword_processor.add_keyword(‘Bay Area’)
  >>> keywords_found = keyword_processor.extract_keywords(‘I love Big Apple and Bay Area.’)
  >>> keywords_found
  >>> # [‘New York’, ‘Bay Area’]

• 替换词组
  >>> keyword_processor.add_keyword(‘New Delhi’, ‘NCR region’)
  >>> new_sentence = keyword_processor.replace_keywords(‘I love Big Apple and new delhi.’)
  >>> new_sentence
  >>> # ‘I love New York and NCR region.’

• 大小写敏感，通过case_sensitive设置
  >>> from flashtext import KeywordProcessor
  >>> keyword_processor = KeywordProcessor(case_sensitive=True)
  >>> keyword_processor.add_keyword(‘Big Apple’, ‘New York’)
  >>> keyword_processor.add_keyword(‘Bay Area’)
  >>> keywords_found = keyword_processor.extract_keywords(‘I love big Apple and Bay Area.’)
  >>> keywords_found
  >>> # [‘Bay Area’]

• 获取匹配到字符起始位置，通过span_info设置
  >>> from flashtext import KeywordProcessor
  >>> keyword_processor = KeywordProcessor()
  >>> keyword_processor.add_keyword(‘Big Apple’, ‘New York’)
  >>> keyword_processor.add_keyword(‘Bay Area’)
  >>> keywords_found = keyword_processor.extract_keywords(‘I love big Apple and Bay Area.’, span_info=True)
  >>> keywords_found
  >>> # [(‘New York’, 7, 16), (‘Bay Area’, 21, 29)]

• 获取关键词提取时提取信息，包含匹配字符及归一化关键词
  >>> from flashtext import KeywordProcessor
  >>> kp = KeywordProcessor()
  >>> kp.add_keyword(‘Taj Mahal’, (‘Monument’, ‘Taj Mahal’))
  >>> kp.add_keyword(‘Delhi’, (‘Location’, ‘Delhi’))
  >>> kp.extract_keywords(‘Taj Mahal is in Delhi.’)
  >>> # [(‘Monument’, ‘Taj Mahal’), (‘Location’, ‘Delhi’)]
  >>> # NOTE: replace_keywords feature won’t work with this.

• 不包含多词归一化的关键词提取
  >>> from flashtext import KeywordProcessor
  >>> keyword_processor = KeywordProcessor()
  >>> keyword_processor.add_keyword(‘Big Apple’)
  >>> keyword_processor.add_keyword(‘Bay Area’)
  >>> keywords_found = keyword_processor.extract_keywords(‘I love big Apple and Bay Area.’)
  >>> keywords_found
  >>> # [‘Big Apple’, ‘Bay Area’]

• 增加多词词典
  >>> from flashtext import KeywordProcessor
  >>> keyword_processor = KeywordProcessor()
  >>> keyword_dict = {
  >>> “java”: [“java_2e”, “java programing”],
  >>> “product management”: [“PM”, “product manager”]
  >>> }
  >>> # {‘clean_name’: [‘list of unclean names’]}
  >>> keyword_processor.add_keywords_from_dict(keyword_dict)
  >>> # Or add keywords from a list:
  >>> keyword_processor.add_keywords_from_list([“java”, “python”])
  >>> keyword_processor.extract_keywords(‘I am a product manager for a java_2e platform’)
  >>> # output [‘product management’, ‘java’]

• 删除关键词
  >>> from flashtext import KeywordProcessor
  >>> keyword_processor = KeywordProcessor()
  >>> keyword_dict = {
  >>> “java”: [“java_2e”, “java programing”],
  >>> “product management”: [“PM”, “product manager”]
  >>> }
  >>> keyword_processor.add_keywords_from_dict(keyword_dict)
  >>> print(keyword_processor.extract_keywords(‘I am a product manager for a java_2e platform’))
  >>> # output [‘product management’, ‘java’]
  >>> keyword_processor.remove_keyword(‘java_2e’)
  >>> # you can also remove keywords from a list/ dictionary
  >>> keyword_processor.remove_keywords_from_dict({“product management”: [“PM”]})
  >>> keyword_processor.remove_keywords_from_list([“java programing”])
  >>> keyword_processor.extract_keywords(‘I am a product manager for a java_2e platform’)
  >>> # output [‘product management’]

• 查看关键词词条数
  >>> from flashtext import KeywordProcessor
  >>> keyword_processor = KeywordProcessor()
  >>> keyword_dict = {
  >>> “java”: [“java_2e”, “java programing”],
  >>> “product management”: [“PM”, “product manager”]
  >>> }
  >>> keyword_processor.add_keywords_from_dict(keyword_dict)
  >>> print(len(keyword_processor))
  >>> # output 4

• 查看词条是否在词典中
  >>> from flashtext import KeywordProcessor
  >>> keyword_processor = KeywordProcessor()
  >>> keyword_processor.add_keyword(‘j2ee’, ‘Java’)
  >>> ‘j2ee’ in keyword_processor
  >>> # output: True
  >>> keyword_processor.get_keyword(‘j2ee’)
  >>> # output: Java
  >>> keyword_processor[‘colour’] = ‘color’
  >>> keyword_processor[‘colour’]
  >>> # output: color

• 获取词典中所有关键词
  >>> from flashtext import KeywordProcessor
  >>> keyword_processor = KeywordProcessor()
  >>> keyword_processor.add_keyword(‘j2ee’, ‘Java’)
  >>> keyword_processor.add_keyword(‘colour’, ‘color’)
  >>> keyword_processor.get_all_keywords()
  >>> # output: {‘colour’: ‘color’, ‘j2ee’: ‘Java’}

• 设置或增加词分隔符，这个方法更适用于英文文本
  >>> from flashtext import KeywordProcessor
  >>> keyword_processor = KeywordProcessor()
  >>> keyword_processor.add_keyword(‘Big Apple’)
  >>> print(keyword_processor.extract_keywords(‘I love Big Apple/Bay Area.’))
  >>> # [‘Big Apple’]
  >>> keyword_processor.add_non_word_boundary(’/’)
  >>> print(keyword_processor.extract_keywords(‘I love Big Apple/Bay Area.’))
  >>> # [