chrislit/abydos

Used in order to highlight an unnecessary block of code following an if containing a raise statement. As such, it will warn when it encounters an else following a chain of ifs, all of them containing a raise statement.

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.phonetic.fuzzysoundex:62 ==abydos.phonetic.phonex:54 if maxlength != -1: self.maxlength = min(max(4, maxlength), 64) else: self.maxlength = 64 self.zeropad = zeropad

def encode_alpha(self, word: str) -> str: ```Return the alphabetic Fuzzy Soundex code for a word.

Parameters

word : str The word to transform

Returns

str The alphabetic Fuzzy Soundex value

Examples

pe = FuzzySoundex() pe.encodealpha('Christopher') 'KRSTP' pe.encodealpha('Niall') 'NL' pe.encodealpha('Smith') 'SNT' pe.encodealpha('Schmidt') 'SNT'

.. versionadded:: 0.4.0

code = self.encode(word).rstrip('0')
 return code[:1] + code[1:].translate(self._alphabetic)

 def encode(self, word: str) -> str:
 ```Return the Fuzzy Soundex code for a word.

 Parameters
 ----------
 word : str
 The word to transform

 Returns
 -------
 str
 The Fuzzy Soundex value

 Examples
 --------
 >>> pe = FuzzySoundex()
 >>> pe.encode('Christopher')
 'K6931'
 >>> pe.encode('Niall')
 'N4000'
 >>> pe.encode('Smith')
 'S5300'
 >>> pe.encode('Smith')
 'S5300'


 .. versionadded:: 0.1.0
 .. versionchanged:: 0.3.6
 Encapsulated in class

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.chebyshev:21 ==abydos.distance.unknown_f:22 from typing import ( Any, Counter as TCounter, NoReturn, Optional, Sequence, Set, Union, )

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:354 ==abydos.distance.phoneticedit_distance:309 )

return self.distabs(src, tar) / normalizeterm

if name == 'main': import doctest

doctest.testmod()

Used whenever we can detect that an overridden method is useless, relying on super() delegation to do the same thing as another method from the MRO.

Used when the name doesn't conform to naming rules associated to its type (constant, variable, class...).

TODO scaler: Optional[Union[str, Callable[[float], float]]] = None, ^ |

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.phonetic.fuzzysoundex:66 ==abydos.phonetic.lein:61 ==abydos.phonetic.phonex:58 ==abydos.phonetic.phonix:190 self.zeropad = zeropad

def encode_alpha(self, word: str) -> str: ```Return the alphabetic Phonex code for a word.

Parameters

word : str The word to transform

Returns

str The alphabetic Phonex value

Examples

pe = Phonex() pe.encodealpha('Christopher') 'CRST' pe.encodealpha('Niall') 'NL' pe.encodealpha('Smith') 'SNT' pe.encodealpha('Schmidt') 'SSNT'

.. versionadded:: 0.4.0

code = self.encode(word).rstrip('0')
 return code[:1] + code[1:].translate(self._alphabetic)

 def encode(self, word: str) -> str:
 ```Return the Phonex code for a word.

 Parameters
 ----------
 word : str
 The word to transform

 Returns
 -------
 str
 The Phonex value

 Examples
 --------
 >>> pe = Phonex()
 >>> pe.encode('Christopher')
 'C623'
 >>> pe.encode('Niall')
 'N400'
 >>> pe.encode('Schmidt')
 'S253'
 >>> pe.encode('Smith')
 'S530'


 .. versionadded:: 0.1.0
 .. versionchanged:: 0.3.6
 Encapsulated in class

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:283 ==abydos.distance._levenshtein:321 )

dmat = cast( np.ndarray, self.alignment_matrix(src, tar, backtrace=False) )

if int(dmat[srclen, tarlen]) == dmat[srclen, tarlen]: return int(dmat[srclen, tarlen]) else: return cast(float, dmat[srclen, tarlen])

def dist(self, src: str, tar: str) -> float: ```Return the normalized Levenshtein distance between two strings.

The Levenshtein distance is normalized by dividing the Levenshtein distance (calculated by any of the three supported methods) by the greater of the number of characters in src times the cost of a delete and the number of characters in tar times the cost of an insert. For the case in which all operations have :math:cost = 1, this is equivalent to the greater of the length of the two strings src & tar.

Parameters

src : str Source string for comparison tar : str Target string for comparison

Returns

float The normalized Levenshtein distance between src & tar

Examples

cmp = DiscountedLevenshtein() cmp.dist('cat', 'hat') 0.3513958291799864 cmp.dist('Niall', 'Neil') 0.5909885886270658 cmp.dist('aluminum', 'Catalan') 0.8348163322045603 cmp.dist('ATCG', 'TAGC') 0.7217609721523955

.. versionadded:: 0.4.1

TODO token[0] not in self._consonants ^ |

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:219 ==abydos.distance.phoneticeditdistance:197 ) if backtrace: tracemat[i + 1, j + 1] = 2 if backtrace: return dmat, tracemat return d_mat

def dist_abs(self, src: str, tar: str) -> float: ```Return the phonetic edit distance between two strings.

Parameters

src : str Source string for comparison tar : str Target string for comparison

Returns

int (may return a float if cost has float values) The phonetic edit distance between src & tar

Examples

cmp = PhoneticEditDistance() cmp.distabs('cat', 'hat') 0.17741935483870974 cmp.distabs('Niall', 'Neil') 1.161290322580645 cmp.distabs('aluminum', 'Catalan') 2.467741935483871 cmp.distabs('ATCG', 'TAGC') 1.193548387096774

cmp = PhoneticEditDistance(mode='osa') cmp.distabs('ATCG', 'TAGC') 0.46236225806451603 cmp.distabs('ACTG', 'TAGC') 1.2580645161290323

.. versionadded:: 0.4.1

Used when an if statement contains too many boolean expressions.

TODO stop_words: Optional[Union[List[str], Set[str], Tuple[str]]] = None, ^ |

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:38 ==abydos.distance.manhattan:38 def init( self, alphabet: Optional[ Union[TCounter[str], Sequence[str], Set[str], int] ] = 0, tokenizer: Optional[Tokenizer] = None, intersectiontype: str = 'crisp', **kwargs: Any ) -> None: ```Initialize Euclidean instance.

Parameters

alphabet : collection or int The values or size of the alphabet tokenizer : Tokenizer A tokenizer instance from the :py:mod:abydos.tokenizer package intersectiontype : str Specifies the intersection type, and set type as a result: See :ref:intersection_type <intersection_type> description in :py:class:_TokenDistance for details. **kwargs Arbitrary keyword arguments

Other Parameters

qval : int The length of each q-gram. Using this parameter and tokenizer=None will cause the instance to use the QGram tokenizer with this q value. metric : _Distance A string distance measure class for use in the soft and fuzzy variants. threshold : float A threshold value, similarities above which are counted as members of the intersection for the fuzzy variant.

.. versionadded:: 0.4.0

Used when a function or method takes too many arguments.

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 ==abydos.tokenizer.vccluster: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:

TODO ngram: Union[str, List[str]], ^ |

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.phonetic.lein:135 ==abydos.phonetic.rogerroot:241 if self.zeropad: code += '0' * self.max_length # Rule 4

return code[: self.maxlength]

if name == 'main': import doctest

doctest.testmod()

Used when a cyclic import between two or more modules is detected.

Used when a cyclic import between two or more modules is detected.