chrislit /
abydos
| Conditions | 29 |
| Total Lines | 183 |
| Code Lines | 101 |
| Lines | 0 |
| Ratio | 0 % |
| Tests | 87 |
| CRAP Score | 29 |
| 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._spanish_metaphone.SpanishMetaphone.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 -*- |
||
| 50 | 1 | def encode(self, word, max_length=6, modified=False): |
|
| 51 | """Return the Spanish Metaphone of a word. |
||
| 52 | |||
| 53 | Parameters |
||
| 54 | ---------- |
||
| 55 | word : str |
||
| 56 | The word to transform |
||
| 57 | max_length : int |
||
| 58 | The length of the code returned (defaults to 6) |
||
| 59 | modified : bool |
||
| 60 | Set to True to use del Pilar Angeles & Bailón-Miguel's modified |
||
| 61 | version of the algorithm |
||
| 62 | |||
| 63 | Returns |
||
| 64 | ------- |
||
| 65 | str |
||
| 66 | The Spanish Metaphone code |
||
| 67 | |||
| 68 | Examples |
||
| 69 | -------- |
||
| 70 | >>> pe = SpanishMetaphone() |
||
| 71 | >>> pe.encode('Perez') |
||
| 72 | 'PRZ' |
||
| 73 | >>> pe.encode('Martinez') |
||
| 74 | 'MRTNZ' |
||
| 75 | >>> pe.encode('Gutierrez') |
||
| 76 | 'GTRRZ' |
||
| 77 | >>> pe.encode('Santiago') |
||
| 78 | 'SNTG' |
||
| 79 | >>> pe.encode('Nicolás') |
||
| 80 | 'NKLS' |
||
| 81 | |||
| 82 | """ |
||
| 83 | |||
| 84 | 1 | def _is_vowel(pos): |
|
| 85 | """Return True if the character at word[pos] is a vowel. |
||
| 86 | |||
| 87 | Parameters |
||
| 88 | ---------- |
||
| 89 | pos : int |
||
| 90 | Position to check for a vowel |
||
| 91 | |||
| 92 | Returns |
||
| 93 | ------- |
||
| 94 | bool |
||
| 95 | True if word[pos] is a vowel |
||
| 96 | |||
| 97 | """ |
||
| 98 | 1 | return pos < len(word) and word[pos] in {'A', 'E', 'I', 'O', 'U'} |
|
| 99 | |||
| 100 | 1 | word = unicode_normalize('NFC', text_type(word.upper())) |
|
| 101 | |||
| 102 | 1 | meta_key = '' |
|
| 103 | 1 | pos = 0 |
|
| 104 | |||
| 105 | # do some replacements for the modified version |
||
| 106 | 1 | if modified: |
|
| 107 | 1 | word = word.replace('MB', 'NB') |
|
| 108 | 1 | word = word.replace('MP', 'NP') |
|
| 109 | 1 | word = word.replace('BS', 'S') |
|
| 110 | 1 | if word[:2] == 'PS': |
|
| 111 | 1 | word = word[1:] |
|
| 112 | |||
| 113 | # simple replacements |
||
| 114 | 1 | word = word.replace('Á', 'A') |
|
| 115 | 1 | word = word.replace('CH', 'X') |
|
| 116 | 1 | word = word.replace('Ç', 'S') |
|
| 117 | 1 | word = word.replace('É', 'E') |
|
| 118 | 1 | word = word.replace('Í', 'I') |
|
| 119 | 1 | word = word.replace('Ó', 'O') |
|
| 120 | 1 | word = word.replace('Ú', 'U') |
|
| 121 | 1 | word = word.replace('Ñ', 'NY') |
|
| 122 | 1 | word = word.replace('GÜ', 'W') |
|
| 123 | 1 | word = word.replace('Ü', 'U') |
|
| 124 | 1 | word = word.replace('B', 'V') |
|
| 125 | 1 | word = word.replace('LL', 'Y') |
|
| 126 | |||
| 127 | 1 | while len(meta_key) < max_length: |
|
| 128 | 1 | if pos >= len(word): |
|
| 129 | 1 | break |
|
| 130 | |||
| 131 | # get the next character |
||
| 132 | 1 | current_char = word[pos] |
|
| 133 | |||
| 134 | # if a vowel in pos 0, add to key |
||
| 135 | 1 | if _is_vowel(pos) and pos == 0: |
|
| 136 | 1 | meta_key += current_char |
|
| 137 | 1 | pos += 1 |
|
| 138 | # otherwise, do consonant rules |
||
| 139 | else: |
||
| 140 | # simple consonants (unmutated) |
||
| 141 | 1 | if current_char in { |
|
| 142 | 'D', |
||
| 143 | 'F', |
||
| 144 | 'J', |
||
| 145 | 'K', |
||
| 146 | 'M', |
||
| 147 | 'N', |
||
| 148 | 'P', |
||
| 149 | 'T', |
||
| 150 | 'V', |
||
| 151 | 'L', |
||
| 152 | 'Y', |
||
| 153 | }: |
||
| 154 | 1 | meta_key += current_char |
|
| 155 | # skip doubled consonants |
||
| 156 | 1 | if word[pos + 1 : pos + 2] == current_char: |
|
| 157 | 1 | pos += 2 |
|
| 158 | else: |
||
| 159 | 1 | pos += 1 |
|
| 160 | else: |
||
| 161 | 1 | if current_char == 'C': |
|
| 162 | # special case 'acción', 'reacción',etc. |
||
| 163 | 1 | if word[pos + 1 : pos + 2] == 'C': |
|
| 164 | 1 | meta_key += 'X' |
|
| 165 | 1 | pos += 2 |
|
| 166 | # special case 'cesar', 'cien', 'cid', 'conciencia' |
||
| 167 | 1 | elif word[pos + 1 : pos + 2] in {'E', 'I'}: |
|
| 168 | 1 | meta_key += 'Z' |
|
| 169 | 1 | pos += 2 |
|
| 170 | # base case |
||
| 171 | else: |
||
| 172 | 1 | meta_key += 'K' |
|
| 173 | 1 | pos += 1 |
|
| 174 | 1 | elif current_char == 'G': |
|
| 175 | # special case 'gente', 'ecologia',etc |
||
| 176 | 1 | if word[pos + 1 : pos + 2] in {'E', 'I'}: |
|
| 177 | 1 | meta_key += 'J' |
|
| 178 | 1 | pos += 2 |
|
| 179 | # base case |
||
| 180 | else: |
||
| 181 | 1 | meta_key += 'G' |
|
| 182 | 1 | pos += 1 |
|
| 183 | 1 | elif current_char == 'H': |
|
| 184 | # since the letter 'H' is silent in Spanish, |
||
| 185 | # set the meta key to the vowel after the letter 'H' |
||
| 186 | 1 | if _is_vowel(pos + 1): |
|
| 187 | 1 | meta_key += word[pos + 1] |
|
| 188 | 1 | pos += 2 |
|
| 189 | else: |
||
| 190 | 1 | meta_key += 'H' |
|
| 191 | 1 | pos += 1 |
|
| 192 | 1 | elif current_char == 'Q': |
|
| 193 | 1 | if word[pos + 1 : pos + 2] == 'U': |
|
| 194 | 1 | pos += 2 |
|
| 195 | else: |
||
| 196 | 1 | pos += 1 |
|
| 197 | 1 | meta_key += 'K' |
|
| 198 | 1 | elif current_char == 'W': |
|
| 199 | 1 | meta_key += 'U' |
|
| 200 | 1 | pos += 1 |
|
| 201 | 1 | elif current_char == 'R': |
|
| 202 | 1 | meta_key += 'R' |
|
| 203 | 1 | pos += 1 |
|
| 204 | 1 | elif current_char == 'S': |
|
| 205 | 1 | if not _is_vowel(pos + 1) and pos == 0: |
|
| 206 | 1 | meta_key += 'ES' |
|
| 207 | 1 | pos += 1 |
|
| 208 | else: |
||
| 209 | 1 | meta_key += 'S' |
|
| 210 | 1 | pos += 1 |
|
| 211 | 1 | elif current_char == 'Z': |
|
| 212 | 1 | meta_key += 'Z' |
|
| 213 | 1 | pos += 1 |
|
| 214 | 1 | elif current_char == 'X': |
|
| 215 | 1 | if ( |
|
| 216 | len(word) > 1 |
||
| 217 | and pos == 0 |
||
| 218 | and not _is_vowel(pos + 1) |
||
| 219 | ): |
||
| 220 | 1 | meta_key += 'EX' |
|
| 221 | 1 | pos += 1 |
|
| 222 | else: |
||
| 223 | 1 | meta_key += 'X' |
|
| 224 | 1 | pos += 1 |
|
| 225 | else: |
||
| 226 | 1 | pos += 1 |
|
| 227 | |||
| 228 | # Final change from S to Z in modified version |
||
| 229 | 1 | if modified: |
|
| 230 | 1 | meta_key = meta_key.replace('S', 'Z') |
|
| 231 | |||
| 232 | 1 | return meta_key |
|
| 233 | |||
| 276 |
Loading history...