chrislit /
abydos
| Conditions | 36 |
| Total Lines | 172 |
| Code Lines | 126 |
| Lines | 0 |
| Ratio | 0 % |
| Tests | 79 |
| CRAP Score | 36 |
| Changes | 0 | ||
Small methods make your code easier to understand, in particular if combined with a good name. Besides, if your method is small, finding a good name is usually much easier.
For example, if you find yourself adding comments to a method's body, this is usually a good sign to extract the commented part to a new method, and use the comment as a starting point when coming up with a good name for this new method.
Commonly applied refactorings include:
If many parameters/temporary variables are present:
Complex classes like abydos.phonetic._caverphone.caverphone() often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
| 1 | # -*- coding: utf-8 -*- |
||
| 29 | 1 | def caverphone(word, version=2): |
|
| 30 | """Return the Caverphone code for a word. |
||
| 31 | |||
| 32 | A description of version 1 of the algorithm can be found in |
||
| 33 | :cite:`Hood:2002`. |
||
| 34 | |||
| 35 | A description of version 2 of the algorithm can be found in |
||
| 36 | :cite:`Hood:2004`. |
||
| 37 | |||
| 38 | :param str word: the word to transform |
||
| 39 | :param int version: the version of Caverphone to employ for encoding |
||
| 40 | (defaults to 2) |
||
| 41 | :returns: the Caverphone value |
||
| 42 | :rtype: str |
||
| 43 | |||
| 44 | >>> caverphone('Christopher') |
||
| 45 | 'KRSTFA1111' |
||
| 46 | >>> caverphone('Niall') |
||
| 47 | 'NA11111111' |
||
| 48 | >>> caverphone('Smith') |
||
| 49 | 'SMT1111111' |
||
| 50 | >>> caverphone('Schmidt') |
||
| 51 | 'SKMT111111' |
||
| 52 | |||
| 53 | >>> caverphone('Christopher', 1) |
||
| 54 | 'KRSTF1' |
||
| 55 | >>> caverphone('Niall', 1) |
||
| 56 | 'N11111' |
||
| 57 | >>> caverphone('Smith', 1) |
||
| 58 | 'SMT111' |
||
| 59 | >>> caverphone('Schmidt', 1) |
||
| 60 | 'SKMT11' |
||
| 61 | """ |
||
| 62 | 1 | _vowels = {'a', 'e', 'i', 'o', 'u'} |
|
| 63 | |||
| 64 | 1 | word = word.lower() |
|
| 65 | 1 | word = ''.join( |
|
| 66 | c |
||
| 67 | for c in word |
||
| 68 | if c |
||
| 69 | in { |
||
| 70 | 'a', |
||
| 71 | 'b', |
||
| 72 | 'c', |
||
| 73 | 'd', |
||
| 74 | 'e', |
||
| 75 | 'f', |
||
| 76 | 'g', |
||
| 77 | 'h', |
||
| 78 | 'i', |
||
| 79 | 'j', |
||
| 80 | 'k', |
||
| 81 | 'l', |
||
| 82 | 'm', |
||
| 83 | 'n', |
||
| 84 | 'o', |
||
| 85 | 'p', |
||
| 86 | 'q', |
||
| 87 | 'r', |
||
| 88 | 's', |
||
| 89 | 't', |
||
| 90 | 'u', |
||
| 91 | 'v', |
||
| 92 | 'w', |
||
| 93 | 'x', |
||
| 94 | 'y', |
||
| 95 | 'z', |
||
| 96 | } |
||
| 97 | ) |
||
| 98 | |||
| 99 | 1 | def _squeeze_replace(word, char): |
|
| 100 | """Convert strings of char in word to one instance of new_char.""" |
||
| 101 | 1 | while char * 2 in word: |
|
| 102 | 1 | word = word.replace(char * 2, char) |
|
| 103 | 1 | return word.replace(char, char.upper()) |
|
| 104 | |||
| 105 | # the main replacement algorithm |
||
| 106 | 1 | if version != 1 and word[-1:] == 'e': |
|
| 107 | 1 | word = word[:-1] |
|
| 108 | 1 | if word: |
|
| 109 | 1 | if word[:5] == 'cough': |
|
| 110 | 1 | word = 'cou2f' + word[5:] |
|
| 111 | 1 | if word[:5] == 'rough': |
|
| 112 | 1 | word = 'rou2f' + word[5:] |
|
| 113 | 1 | if word[:5] == 'tough': |
|
| 114 | 1 | word = 'tou2f' + word[5:] |
|
| 115 | 1 | if word[:6] == 'enough': |
|
| 116 | 1 | word = 'enou2f' + word[6:] |
|
| 117 | 1 | if version != 1 and word[:6] == 'trough': |
|
| 118 | 1 | word = 'trou2f' + word[6:] |
|
| 119 | 1 | if word[:2] == 'gn': |
|
| 120 | 1 | word = '2n' + word[2:] |
|
| 121 | 1 | if word[-2:] == 'mb': |
|
| 122 | 1 | word = word[:-1] + '2' |
|
| 123 | 1 | for src, tar in ( |
|
| 124 | ('cq', '2q'), |
||
|
Coding Style
introduced
by
|
|||
| 125 | ('ci', 'si'), |
||
| 126 | ('ce', 'se'), |
||
| 127 | ('cy', 'sy'), |
||
| 128 | ('tch', '2ch'), |
||
| 129 | ('c', 'k'), |
||
| 130 | ('q', 'k'), |
||
| 131 | ('x', 'k'), |
||
| 132 | ('v', 'f'), |
||
| 133 | ('dg', '2g'), |
||
| 134 | ('tio', 'sio'), |
||
| 135 | ('tia', 'sia'), |
||
| 136 | ('d', 't'), |
||
| 137 | ('ph', 'fh'), |
||
| 138 | ('b', 'p'), |
||
| 139 | ('sh', 's2'), |
||
| 140 | ('z', 's'), |
||
| 141 | ): |
||
| 142 | 1 | word = word.replace(src, tar) |
|
| 143 | 1 | if word[0] in _vowels: |
|
| 144 | 1 | word = 'A' + word[1:] |
|
| 145 | 1 | for vowel in 'aeiou': |
|
| 146 | 1 | word = word.replace(vowel, '3') |
|
| 147 | 1 | if version != 1: |
|
| 148 | 1 | word = word.replace('j', 'y') |
|
| 149 | 1 | if word[:2] == 'y3': |
|
| 150 | 1 | word = 'Y3' + word[2:] |
|
| 151 | 1 | if word[:1] == 'y': |
|
| 152 | 1 | word = 'A' + word[1:] |
|
| 153 | 1 | word = word.replace('y', '3') |
|
| 154 | 1 | for src, tar in (('3gh3', '3kh3'), ('gh', '22'), ('g', 'k')): |
|
| 155 | 1 | word = word.replace(src, tar) |
|
| 156 | |||
| 157 | 1 | for char in 'stpkfmn': |
|
| 158 | 1 | word = _squeeze_replace(word, char) |
|
| 159 | |||
| 160 | 1 | word = word.replace('w3', 'W3') |
|
| 161 | 1 | if version == 1: |
|
| 162 | 1 | word = word.replace('wy', 'Wy') |
|
| 163 | 1 | word = word.replace('wh3', 'Wh3') |
|
| 164 | 1 | if version == 1: |
|
| 165 | 1 | word = word.replace('why', 'Why') |
|
| 166 | 1 | if version != 1 and word[-1:] == 'w': |
|
| 167 | 1 | word = word[:-1] + '3' |
|
| 168 | 1 | word = word.replace('w', '2') |
|
| 169 | 1 | if word[:1] == 'h': |
|
| 170 | 1 | word = 'A' + word[1:] |
|
| 171 | 1 | word = word.replace('h', '2') |
|
| 172 | 1 | word = word.replace('r3', 'R3') |
|
| 173 | 1 | if version == 1: |
|
| 174 | 1 | word = word.replace('ry', 'Ry') |
|
| 175 | 1 | if version != 1 and word[-1:] == 'r': |
|
| 176 | 1 | word = word[:-1] + '3' |
|
| 177 | 1 | word = word.replace('r', '2') |
|
| 178 | 1 | word = word.replace('l3', 'L3') |
|
| 179 | 1 | if version == 1: |
|
| 180 | 1 | word = word.replace('ly', 'Ly') |
|
| 181 | 1 | if version != 1 and word[-1:] == 'l': |
|
| 182 | 1 | word = word[:-1] + '3' |
|
| 183 | 1 | word = word.replace('l', '2') |
|
| 184 | 1 | if version == 1: |
|
| 185 | 1 | word = word.replace('j', 'y') |
|
| 186 | 1 | word = word.replace('y3', 'Y3') |
|
| 187 | 1 | word = word.replace('y', '2') |
|
| 188 | 1 | word = word.replace('2', '') |
|
| 189 | 1 | if version != 1 and word[-1:] == '3': |
|
| 190 | 1 | word = word[:-1] + 'A' |
|
| 191 | 1 | word = word.replace('3', '') |
|
| 192 | |||
| 193 | # pad with 1s, then extract the necessary length of code |
||
| 194 | 1 | word += '1' * 10 |
|
| 195 | 1 | if version != 1: |
|
| 196 | 1 | word = word[:10] |
|
| 197 | else: |
||
| 198 | 1 | word = word[:6] |
|
| 199 | |||
| 200 | 1 | return word |
|
| 201 | |||
| 207 |
Loading history...