Beispiel #1
0
def twoGramFingerprint(field):
    if len(field) > 1:
        return (u''.join(
            sorted(gram.strip()
                   for gram in set(ngrams(field.replace(' ', ''), 2)))), )
    else:
        return ()
Beispiel #2
0
def commonSixGram(field):
    """Split the field into overlapping windows of 6 characters (spaces removed).

    Examples:
    .. code:: python
        > print(commonFourGram('John Woodward'))
        > {'JohnWo', 'Woodwa', 'hnWood', 'nWoodw', 'odward', 'ohnWoo', 'oodwar'}
    """
    return set(ngrams(field.replace(' ', ''), 6))
Beispiel #3
0
def commonSixGram(field):
    """return 6-grams"""
    return ngrams(field, 6)
Beispiel #4
0
def commonFourGram(field):
    """return 4-grams"""
    return ngrams(field, 4)
Beispiel #5
0
def commonSixGram(field):
    """return 6-grams"""
    return set(ngrams(field.replace(' ', ''), 6))
Beispiel #6
0
def twoGramFingerprint(field):
    return (u''.join(sorted(gram.strip() for gram in ngrams(field, 2))), )
Beispiel #7
0
def commonFourGram(field):
    """return 4-grams"""
    return set(ngrams(field.replace(' ', ''), 4))
Beispiel #8
0
def oneGramFingerprint(field):
    return (u''.join(sorted(set(ngrams(field.replace(' ', ''), 1)))).strip(), )
Beispiel #9
0
def commonSixGram(field: str) -> Set[str]:
    """return 6-grams"""
    return set(ngrams(field.replace(' ', ''), 6))
Beispiel #10
0
 def preprocess(self, doc) :
     return tuple(ngrams(doc.replace(' ', ''), 2))
Beispiel #11
0
def commonSixGram(field):
    """return 6-grams"""
    return ngrams(field, 6)
Beispiel #12
0
def commonFourGram(field):
    """return 4-grams"""
    return ngrams(field, 4)
def twoGramFingerprint(field) :
    return (u''.join(sorted(gram.strip() for gram in ngrams(field, 2))),)
def oneGramFingerprint(field) :
    return (u''.join(sorted(ngrams(field, 1))).strip(),)
Beispiel #15
0
 def preprocess(self, doc):
     return tuple(sorted(ngrams(" ".join(strip_punc(doc).split()), 2)))
Beispiel #16
0
def commonFourGram(field: str) -> Set[str]:
    """return 4-grams"""
    return set(ngrams(field.replace(' ', ''), 4))
Beispiel #17
0
 def preprocess(self, doc):
     return tuple(sorted(ngrams(" ".join(strip_punc(doc).split()), 2)))
Beispiel #18
0
 def preprocess(self, doc):
     return tuple(ngrams(doc.replace(' ', ''), 2))
Beispiel #19
0
def oneGramFingerprint(field):
    return (u''.join(sorted(set(ngrams(field.replace(' ', ''), 1)))).strip(),)
Beispiel #20
0
def twoGramFingerprint(field):
    if len(field) > 1:
        return (u''.join(sorted(gram.strip() for gram
                                in set(ngrams(field.replace(' ', ''), 2)))),)
    else:
        return ()
Beispiel #21
0
def commonFourGram(field):
    """return 4-grams"""
    return set(ngrams(field.replace(' ', ''), 4))
Beispiel #22
0
def commonSixGram(field):
    """return 6-grams"""
    return set(ngrams(field.replace(' ', ''), 6))
Beispiel #23
0
def oneGramFingerprint(field):
    return (u''.join(sorted(ngrams(field, 1))).strip(), )