Showing 4,191 of 4,191 total issues
Similar lines in 2 files Open
# Copyright 2014-2020 by Christopher C. Little.
- Read upRead up
- Exclude checks
Indicates that a set of similar lines has been detected among multiple file. This usually means that the code should be refactored to avoid this duplication. ==abydos.tokenizer.cvcluster:133 ==abydos.tokenizer.vccluster:133 newtoken += char mode = 2 else: # This should cover combining marks, marks, etc. newtoken += char
self.orderedtokens.append(new_token)
self.orderedtokens = [ unicodedata.normalize('NFC', token) for token in self.orderedtokens ] self.scaleand_counterize() return self
if name == 'main': import doctest
doctest.testmod(optionflags=doctest.NORMALIZE_WHITESPACE)
Wrong hanging indentation before block (add 4 spaces). Open
scaler: Optional[Union[str, Callable[[float], float]]] = None,
- Read upRead up
- Exclude checks
TODO scaler: Optional[Union[str, Callable[[float], float]]] = None, ^ |
Similar lines in 2 files Open
# Copyright 2014-2020 by Christopher C. Little.
- Read upRead up
- Exclude checks
Indicates that a set of similar lines has been detected among multiple file. This usually means that the code should be refactored to avoid this duplication. ==abydos.tokenizer.corvcluster:137 ==abydos.tokenizer.cvcluster:134 mode = 2 else: # This should cover combining marks, marks, etc. new_token += char
self.orderedtokens.append(new_token)
self.orderedtokens = [ unicodedata.normalize('NFC', token) for token in self.orderedtokens ] self.scaleand_counterize() return self
if name == 'main': import doctest
doctest.testmod(optionflags=doctest.NORMALIZE_WHITESPACE)
Wrong hanging indentation before block (add 4 spaces). Open
feat2: int,
- Read upRead up
- Exclude checks
TODO feat2: int, ^ |
Similar lines in 2 files Open
# Copyright 2014-2020 by Christopher C. Little.
- Read upRead up
- Exclude checks
Indicates that a set of similar lines has been detected among multiple file. This usually means that the code should be refactored to avoid this duplication. ==abydos.distance.discountedlevenshtein:204 ==abydos.distance.levenshtein:165 ) dmat[i + 1, j + 1] = min(opts) if backtrace: trace_mat[i + 1, j + 1] = int(np.argmin(opts))
if self.mode == 'osa': if ( i + 1 > 1 and j + 1 > 1 and src[i] == tar[j - 1] and src[i - 1] == tar[j] ): # transposition dmat[i + 1, j + 1] = min(
String statement has no effect Open
"""
- Read upRead up
- Exclude checks
Used when a string is used as a statement (which of course has no effect). This is a particular case of W0104 with its own message so you can easily disable it if you're using those strings as documentation, instead of comments.
Variable name n
doesn't conform to snake_case naming style Open
n = tokens[tok] * count
- Read upRead up
- Exclude checks
Used when the name doesn't conform to naming rules associated to its type (constant, variable, class...).
Method could be a function Open
def decode(self, text: str) -> str:
- Read upRead up
- Exclude checks
Used when a method doesn't use its bound instance, and so could be written as a function.
Similar lines in 2 files Open
# Copyright 2014-2020 by Christopher C. Little.
- Read upRead up
- Exclude checks
Indicates that a set of similar lines has been detected among multiple file. This usually means that the code should be refactored to avoid this duplication. ==abydos.distance.prefix:32 ==abydos.distance.suffix:32 def sim(self, src: str, tar: str) -> float: ```Return the suffix similarity of two strings.
Suffix similarity is the ratio of the length of the shorter term that exactly matches the longer term to the length of the shorter term, beginning at the end of both terms.
Parameters
src : str Source string for comparison tar : str Target string for comparison
Returns
float Suffix similarity
Examples
cmp = Suffix() cmp.sim('cat', 'hat') 0.6666666666666666 cmp.sim('Niall', 'Neil') 0.25 cmp.sim('aluminum', 'Catalan') 0.0 cmp.sim('ATCG', 'TAGC') 0.0
.. versionadded:: 0.1.0 .. versionchanged:: 0.3.6 Encapsulated in class
if src == tar:
return 1.0
if not src or not tar:
return 0.0
min_word, max_word = (src, tar) if len(src) < len(tar) else (tar, src)
min_len = len(min_word)
for i in range(min_len, 0, -1):
Similar lines in 2 files Open
# Copyright 2014-2020 by Christopher C. Little.
- Read upRead up
- Exclude checks
Indicates that a set of similar lines has been detected among multiple file. This usually means that the code should be refactored to avoid this duplication. ==abydos.distance.euclidean:125 ==abydos.distance.minkowski:163 def dist(self, src: str, tar: str) -> float: ```Return the normalized Euclidean distance between two strings.
The normalized Euclidean distance is a distance
metric in :math:L^2
-space, normalized to [0, 1].
Parameters
src : str Source string (or QGrams/Counter objects) for comparison tar : str Target string (or QGrams/Counter objects) for comparison
Returns
float The normalized Euclidean distance
Examples
cmp = Euclidean() round(cmp.dist('cat', 'hat'), 12) 0.57735026919 round(cmp.dist('Niall', 'Neil'), 12) 0.683130051064 round(cmp.dist('Colin', 'Cuilen'), 12) 0.727606875109 cmp.dist('ATCG', 'TAGC') 1.0
.. versionadded:: 0.3.0 .. versionchanged:: 0.3.6 Encapsulated in class
return self.dist_abs(src, tar, normalized=True)
if __name__ == '__main__':
import doctest
doctest.testmod()
Similar lines in 2 files Open
# Copyright 2014-2020 by Christopher C. Little.
- Read upRead up
- Exclude checks
Indicates that a set of similar lines has been detected among multiple file. This usually means that the code should be refactored to avoid this duplication. ==abydos.tokenizer.corvcluster:110 ==abydos.tokenizer.cvcluster:111 self.string = string self.orderedtokens = [] tokenlist = self.regexp.findall(self.string) for token in tokenlist: if ( token[0] not in self.consonants and token[0] not in self.vowels ): self.orderedtokens.append(token) else: token = unicodedata.normalize('NFD', token) mode = 0 # 0 = starting mode, 1 = cons, 2 = vowels newtoken = '' # noqa: S105 for char in token: if char in self.consonants: if mode == 2: self.orderedtokens.append(newtoken) newtoken = char else: newtoken += char mode = 1 elif char in self._vowels:
Similar lines in 3 files Open
# Copyright 2014-2020 by Christopher C. Little.
- Read upRead up
- Exclude checks
Indicates that a set of similar lines has been detected among multiple file. This usually means that the code should be refactored to avoid this duplication. ==abydos.distance.azzoo:21 ==abydos.distance.minkowski:21 ==abydos.distance.mutualinformation:22 from typing import ( Any, Counter as TCounter, Optional, Sequence, Set, Union, cast, )
from .tokendistance import _TokenDistance from ..tokenizer import _Tokenizer
Wrong hanging indentation before block (add 4 spaces). Open
**kwargs: Any
- Read upRead up
- Exclude checks
TODO **kwargs: Any ^ |
Wrong hanging indentation before block (add 4 spaces). Open
self,
- Read upRead up
- Exclude checks
TODO self, ^ |
Wrong hanging indentation before block (add 4 spaces). Open
word_tokenizer: Optional[_Tokenizer] = None,
- Read upRead up
- Exclude checks
TODO wordtokenizer: Optional[Tokenizer] = None, ^ |
Wrong hanging indentation before block (add 4 spaces). Open
counts.items(), key=lambda x: (x[1], x[0]), reverse=True
- Read upRead up
- Exclude checks
TODO counts.items(), key=lambda x: (x[1], x[0]), reverse=True ^ |
Similar lines in 2 files Open
# Copyright 2014-2020 by Christopher C. Little.
- Read upRead up
- Exclude checks
Indicates that a set of similar lines has been detected among multiple file. This usually means that the code should be refactored to avoid this duplication. ==abydos.stemmer.snowballnorwegian:143 ==abydos.stemmer.snowballswedish:143 word = word[:-3] elif _r1[-2:] == 'ig': word = word[:-2]
return word
if name == 'main': import doctest
doctest.testmod()
Wrong hanging indentation before block (add 4 spaces). Open
self,
- Read upRead up
- Exclude checks
TODO self, ^ |
Wrong hanging indentation before block (add 4 spaces). Open
token[0] not in self._consonants
- Read upRead up
- Exclude checks
TODO token[0] not in self._consonants ^ |
Keyword argument before variable positional arguments list in the definition of __init__ function Open
def __init__(
- Read upRead up
- Exclude checks
When defining a keyword argument before variable positional arguments, one can end up in having multiple values passed for the aforementioned parameter in case the method is called with keyword arguments.