Python whoosh.analysis.Token() Examples

The following are 8 code examples of whoosh.analysis.Token(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module whoosh.analysis , or try the search function .
Example #1
Source File: analyzer.py    From jieba_fast with MIT License 5 votes vote down vote up 
def __call__(self, text, **kargs):
        words = jieba.tokenize(text, mode="search")
        token = Token()
        for (w, start_pos, stop_pos) in words:
            if not accepted_chars.match(w) and len(w) <= 1:
                continue
            token.original = token.text = w
            token.pos = start_pos
            token.startchar = start_pos
            token.endchar = stop_pos
            yield token
Example #2
Source File: analyzer.py    From jieba_fast with MIT License 5 votes vote down vote up 
def __call__(self, text, **kargs):
        words = jieba_fast.tokenize(text, mode="search")
        token = Token()
        for (w, start_pos, stop_pos) in words:
            if not accepted_chars.match(w) and len(w) <= 1:
                continue
            token.original = token.text = w
            token.pos = start_pos
            token.startchar = start_pos
            token.endchar = stop_pos
            yield token
Example #3
Source File: analyzer.py    From chinese-support-redux with GNU General Public License v3.0 5 votes vote down vote up 
def __call__(self, text, **kargs):
        words = jieba.tokenize(text, mode="search")
        token = Token()
        for (w, start_pos, stop_pos) in words:
            if not accepted_chars.match(w) and len(w) <= 1:
                continue
            token.original = token.text = w
            token.pos = start_pos
            token.startchar = start_pos
            token.endchar = stop_pos
            yield token
Example #4
Source File: analyzer.py    From Synonyms with MIT License 5 votes vote down vote up 
def __call__(self, text, **kargs):
        words = jieba.tokenize(text, mode="search")
        token = Token()
        for (w, start_pos, stop_pos) in words:
            if not accepted_chars.match(w) and len(w) <= 1:
                continue
            token.original = token.text = w
            token.pos = start_pos
            token.startchar = start_pos
            token.endchar = stop_pos
            yield token
Example #5
Source File: analyzer.py    From QAbot_by_base_KG with MIT License 5 votes vote down vote up 
def __call__(self, text, **kargs):
        words = jieba.tokenize(text, mode="search")
        token = Token()
        for (w, start_pos, stop_pos) in words:
            if not accepted_chars.match(w) and len(w) <= 1:
                continue
            token.original = token.text = w
            token.pos = start_pos
            token.startchar = start_pos
            token.endchar = stop_pos
            yield token
Example #6
Source File: analyzer.py    From python-girlfriend-mood with MIT License 5 votes vote down vote up 
def __call__(self, text, **kargs):
        words = jieba.tokenize(text, mode="search")
        token = Token()
        for (w, start_pos, stop_pos) in words:
            if not accepted_chars.match(w) and len(w) <= 1:
                continue
            token.original = token.text = w
            token.pos = start_pos
            token.startchar = start_pos
            token.endchar = stop_pos
            yield token
Example #7
Source File: analyzer.py    From annotated_jieba with MIT License 5 votes vote down vote up 
def __call__(self, text, **kargs):
        words = jieba.tokenize(text, mode="search")
        token = Token()
        for (w, start_pos, stop_pos) in words:
            if not accepted_chars.match(w) and len(w) <= 1:
                continue
            token.original = token.text = w
            token.pos = start_pos
            token.startchar = start_pos
            token.endchar = stop_pos
            yield token
Example #8
Source File: analyzer.py    From Malicious_Domain_Whois with GNU General Public License v3.0 5 votes vote down vote up 
def __call__(self, text, **kargs):
        words = jieba.tokenize(text, mode="search")
        token = Token()
        for (w, start_pos, stop_pos) in words:
            if not accepted_chars.match(w) and len(w) <= 1:
                continue
            token.original = token.text = w
            token.pos = start_pos
            token.startchar = start_pos
            token.endchar = stop_pos
            yield token