chrislit /
abydos
| Conditions | 66 |
| Total Lines | 172 |
| Code Lines | 114 |
| Lines | 0 |
| Ratio | 0 % |
| Tests | 109 |
| CRAP Score | 66 |
| 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._nysiis.NYSIIS.encode() 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 -*- |
||
| 49 | 1 | def encode(self, word, max_length=6, modified=False): |
|
| 50 | """Return the NYSIIS code for a word. |
||
| 51 | |||
| 52 | Parameters |
||
| 53 | ---------- |
||
| 54 | word : str |
||
| 55 | The word to transform |
||
| 56 | max_length : int |
||
| 57 | The maximum length (default 6) of the code to return |
||
| 58 | modified : bool |
||
| 59 | Indicates whether to use USDA modified NYSIIS |
||
| 60 | |||
| 61 | Returns |
||
| 62 | ------- |
||
| 63 | str |
||
| 64 | The NYSIIS value |
||
| 65 | |||
| 66 | Examples |
||
| 67 | -------- |
||
| 68 | >>> pe = NYSIIS() |
||
| 69 | >>> pe.encode('Christopher') |
||
| 70 | 'CRASTA' |
||
| 71 | >>> pe.encode('Niall') |
||
| 72 | 'NAL' |
||
| 73 | >>> pe.encode('Smith') |
||
| 74 | 'SNAT' |
||
| 75 | >>> pe.encode('Schmidt') |
||
| 76 | 'SNAD' |
||
| 77 | |||
| 78 | >>> pe.encode('Christopher', max_length=-1) |
||
| 79 | 'CRASTAFAR' |
||
| 80 | |||
| 81 | >>> pe.encode('Christopher', max_length=8, modified=True) |
||
| 82 | 'CRASTAFA' |
||
| 83 | >>> pe.encode('Niall', max_length=8, modified=True) |
||
| 84 | 'NAL' |
||
| 85 | >>> pe.encode('Smith', max_length=8, modified=True) |
||
| 86 | 'SNAT' |
||
| 87 | >>> pe.encode('Schmidt', max_length=8, modified=True) |
||
| 88 | 'SNAD' |
||
| 89 | |||
| 90 | """ |
||
| 91 | # Require a max_length of at least 6 |
||
| 92 | 1 | if max_length > -1: |
|
| 93 | 1 | max_length = max(6, max_length) |
|
| 94 | |||
| 95 | 1 | word = ''.join(c for c in word.upper() if c.isalpha()) |
|
| 96 | 1 | word = word.replace('ß', 'SS') |
|
| 97 | |||
| 98 | # exit early if there are no alphas |
||
| 99 | 1 | if not word: |
|
| 100 | 1 | return '' |
|
| 101 | |||
| 102 | 1 | original_first_char = word[0] |
|
| 103 | |||
| 104 | 1 | if word[:3] == 'MAC': |
|
| 105 | 1 | word = 'MCC' + word[3:] |
|
| 106 | 1 | elif word[:2] == 'KN': |
|
| 107 | 1 | word = 'NN' + word[2:] |
|
| 108 | 1 | elif word[:1] == 'K': |
|
| 109 | 1 | word = 'C' + word[1:] |
|
| 110 | 1 | elif word[:2] in {'PH', 'PF'}: |
|
| 111 | 1 | word = 'FF' + word[2:] |
|
| 112 | 1 | elif word[:3] == 'SCH': |
|
| 113 | 1 | word = 'SSS' + word[3:] |
|
| 114 | 1 | elif modified: |
|
| 115 | 1 | if word[:2] == 'WR': |
|
| 116 | 1 | word = 'RR' + word[2:] |
|
| 117 | 1 | elif word[:2] == 'RH': |
|
| 118 | 1 | word = 'RR' + word[2:] |
|
| 119 | 1 | elif word[:2] == 'DG': |
|
| 120 | 1 | word = 'GG' + word[2:] |
|
| 121 | 1 | elif word[:1] in self._uc_v_set: |
|
| 122 | 1 | word = 'A' + word[1:] |
|
| 123 | |||
| 124 | 1 | if modified and word[-1:] in {'S', 'Z'}: |
|
| 125 | 1 | word = word[:-1] |
|
| 126 | |||
| 127 | 1 | if ( |
|
| 128 | word[-2:] == 'EE' |
||
| 129 | or word[-2:] == 'IE' |
||
| 130 | or (modified and word[-2:] == 'YE') |
||
| 131 | ): |
||
| 132 | 1 | word = word[:-2] + 'Y' |
|
| 133 | 1 | elif word[-2:] in {'DT', 'RT', 'RD'}: |
|
| 134 | 1 | word = word[:-2] + 'D' |
|
| 135 | 1 | elif word[-2:] in {'NT', 'ND'}: |
|
| 136 | 1 | word = word[:-2] + ('N' if modified else 'D') |
|
| 137 | 1 | elif modified: |
|
| 138 | 1 | if word[-2:] == 'IX': |
|
| 139 | 1 | word = word[:-2] + 'ICK' |
|
| 140 | 1 | elif word[-2:] == 'EX': |
|
| 141 | 1 | word = word[:-2] + 'ECK' |
|
| 142 | 1 | elif word[-2:] in {'JR', 'SR'}: |
|
| 143 | 1 | return 'ERROR' |
|
| 144 | |||
| 145 | 1 | key = word[:1] |
|
| 146 | |||
| 147 | 1 | skip = 0 |
|
| 148 | 1 | for i in range(1, len(word)): |
|
| 149 | 1 | if i >= len(word): |
|
| 150 | 1 | continue |
|
| 151 | 1 | elif skip: |
|
| 152 | 1 | skip -= 1 |
|
| 153 | 1 | continue |
|
| 154 | 1 | elif word[i : i + 2] == 'EV': |
|
| 155 | 1 | word = word[:i] + 'AF' + word[i + 2 :] |
|
| 156 | 1 | skip = 1 |
|
| 157 | 1 | elif word[i] in self._uc_v_set: |
|
| 158 | 1 | word = word[:i] + 'A' + word[i + 1 :] |
|
| 159 | 1 | elif modified and i != len(word) - 1 and word[i] == 'Y': |
|
| 160 | 1 | word = word[:i] + 'A' + word[i + 1 :] |
|
| 161 | 1 | elif word[i] == 'Q': |
|
| 162 | 1 | word = word[:i] + 'G' + word[i + 1 :] |
|
| 163 | 1 | elif word[i] == 'Z': |
|
| 164 | 1 | word = word[:i] + 'S' + word[i + 1 :] |
|
| 165 | 1 | elif word[i] == 'M': |
|
| 166 | 1 | word = word[:i] + 'N' + word[i + 1 :] |
|
| 167 | 1 | elif word[i : i + 2] == 'KN': |
|
| 168 | 1 | word = word[:i] + 'N' + word[i + 2 :] |
|
| 169 | 1 | elif word[i] == 'K': |
|
| 170 | 1 | word = word[:i] + 'C' + word[i + 1 :] |
|
| 171 | 1 | elif modified and i == len(word) - 3 and word[i : i + 3] == 'SCH': |
|
| 172 | 1 | word = word[:i] + 'SSA' |
|
| 173 | 1 | skip = 2 |
|
| 174 | 1 | elif word[i : i + 3] == 'SCH': |
|
| 175 | 1 | word = word[:i] + 'SSS' + word[i + 3 :] |
|
| 176 | 1 | skip = 2 |
|
| 177 | 1 | elif modified and i == len(word) - 2 and word[i : i + 2] == 'SH': |
|
| 178 | 1 | word = word[:i] + 'SA' |
|
| 179 | 1 | skip = 1 |
|
| 180 | 1 | elif word[i : i + 2] == 'SH': |
|
| 181 | 1 | word = word[:i] + 'SS' + word[i + 2 :] |
|
| 182 | 1 | skip = 1 |
|
| 183 | 1 | elif word[i : i + 2] == 'PH': |
|
| 184 | 1 | word = word[:i] + 'FF' + word[i + 2 :] |
|
| 185 | 1 | skip = 1 |
|
| 186 | 1 | elif modified and word[i : i + 3] == 'GHT': |
|
| 187 | 1 | word = word[:i] + 'TTT' + word[i + 3 :] |
|
| 188 | 1 | skip = 2 |
|
| 189 | 1 | elif modified and word[i : i + 2] == 'DG': |
|
| 190 | 1 | word = word[:i] + 'GG' + word[i + 2 :] |
|
| 191 | 1 | skip = 1 |
|
| 192 | 1 | elif modified and word[i : i + 2] == 'WR': |
|
| 193 | 1 | word = word[:i] + 'RR' + word[i + 2 :] |
|
| 194 | 1 | skip = 1 |
|
| 195 | 1 | elif word[i] == 'H' and ( |
|
| 196 | word[i - 1] not in self._uc_v_set |
||
| 197 | or word[i + 1 : i + 2] not in self._uc_v_set |
||
| 198 | ): |
||
| 199 | 1 | word = word[:i] + word[i - 1] + word[i + 1 :] |
|
| 200 | 1 | elif word[i] == 'W' and word[i - 1] in self._uc_v_set: |
|
| 201 | 1 | word = word[:i] + word[i - 1] + word[i + 1 :] |
|
| 202 | |||
| 203 | 1 | if word[i : i + skip + 1] != key[-1:]: |
|
| 204 | 1 | key += word[i : i + skip + 1] |
|
| 205 | |||
| 206 | 1 | key = self._delete_consecutive_repeats(key) |
|
| 207 | |||
| 208 | 1 | if key[-1:] == 'S': |
|
| 209 | 1 | key = key[:-1] |
|
| 210 | 1 | if key[-2:] == 'AY': |
|
| 211 | 1 | key = key[:-2] + 'Y' |
|
| 212 | 1 | if key[-1:] == 'A': |
|
| 213 | 1 | key = key[:-1] |
|
| 214 | 1 | if modified and key[:1] == 'A': |
|
| 215 | 1 | key = original_first_char + key[1:] |
|
| 216 | |||
| 217 | 1 | if max_length > 0: |
|
| 218 | 1 | key = key[:max_length] |
|
| 219 | |||
| 220 | 1 | return key |
|
| 221 | |||
| 273 |
Loading history...