本文整理汇总了Python中whoosh.analysis.unstopped函数的典型用法代码示例。如果您正苦于以下问题:Python unstopped函数的具体用法?Python unstopped怎么用?Python unstopped使用的例子?那么恭喜您, 这里精选的函数代码示例或许可以为您提供帮助。
在下文中一共展示了unstopped函数的7个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: word_datas
def word_datas(self, value, **kwargs):
seen = defaultdict(int)
if self.boost_as_freq:
for t in unstopped(self.analyzer(value, boosts=True)):
seen[t.text] += int(t.boost)
else:
for t in unstopped(self.analyzer(value)):
seen[t.text] += 1
return ((w, freq, freq) for w, freq in seen.iteritems())
示例2: word_values
def word_values(self, value, **kwargs):
seen = defaultdict(int)
if self.boost_as_freq:
for t in unstopped(self.analyzer(value, boosts=True, **kwargs)):
seen[t.text] += int(t.boost)
else:
for t in unstopped(self.analyzer(value, **kwargs)):
seen[t.text] += 1
encode = self.encode
return ((w, freq, float(freq), encode(freq))
for w, freq in seen.iteritems())
示例3: word_values
def word_values(self, value, doc_boost = 1.0, **kwargs):
seen = defaultdict(int)
for t in unstopped(self.analyzer(value, **kwargs)):
seen[t.text] += 1
encode = self.encode
return ((w, freq, encode((freq, doc_boost))) for w, freq in seen.iteritems())
示例4: word_datas
def word_datas(self, value, start_pos = 0, start_char = 0, **kwargs):
seen = defaultdict(list)
for t in unstopped(self.analyzer(value, positions = True, chars = True,
start_pos = start_pos, start_char = start_char)):
seen[t.text].append((t.pos, start_char + t.startchar, start_char + t.endchar))
return ((w, len(ls), ls) for w, ls in seen.iteritems())
示例5: word_values
def word_values(self, value, doc_boost=1.0, **kwargs):
freqs = defaultdict(int)
weights = defaultdict(float)
for t in unstopped(self.analyzer(value, boosts=True, **kwargs)):
weights[t.text] += t.boost
freqs[t.text] += 1
encode = self.encode
return ((w, freq, weights[w] * doc_boost, encode((freq, doc_boost)))
for w, freq in freqs.iteritems())
示例6: word_values
def word_values(self, value, **kwargs):
fb = self.field_boost
freqs = defaultdict(int)
weights = defaultdict(float)
for t in unstopped(self.analyzer(value, boosts=True, **kwargs)):
freqs[t.text] += 1
weights[t.text] += t.boost
encode = self.encode
return ((w, freq, weights[w] * fb, encode(freq))
for w, freq in freqs.iteritems())
示例7: tokens
def tokens(value, analyzer, kwargs):
if isinstance(value, (tuple, list)):
gen = entoken(value, **kwargs)
else:
gen = analyzer(value, **kwargs)
return unstopped(gen)