chrislit /
abydos
| Conditions | 29 |
| Total Lines | 172 |
| 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 | Args: |
||
| 54 | word (str): The word to transform |
||
| 55 | max_length (int): The length of the code returned (defaults to 6) |
||
| 56 | modified (bool): Set to True to use del Pilar Angeles & |
||
| 57 | Bailón-Miguel's modified version of the algorithm |
||
| 58 | |||
| 59 | Returns: |
||
| 60 | str: The Spanish Metaphone code |
||
| 61 | |||
| 62 | Examples: |
||
| 63 | >>> pe = SpanishMetaphone() |
||
| 64 | >>> pe.encode('Perez') |
||
| 65 | 'PRZ' |
||
| 66 | >>> pe.encode('Martinez') |
||
| 67 | 'MRTNZ' |
||
| 68 | >>> pe.encode('Gutierrez') |
||
| 69 | 'GTRRZ' |
||
| 70 | >>> pe.encode('Santiago') |
||
| 71 | 'SNTG' |
||
| 72 | >>> pe.encode('Nicolás') |
||
| 73 | 'NKLS' |
||
| 74 | |||
| 75 | """ |
||
| 76 | |||
| 77 | 1 | def _is_vowel(pos): |
|
| 78 | """Return True if the character at word[pos] is a vowel. |
||
| 79 | |||
| 80 | Args: |
||
| 81 | pos (int): Position to check for a vowel |
||
| 82 | |||
| 83 | Returns: |
||
| 84 | bool: True if word[pos] is a vowel |
||
| 85 | |||
| 86 | """ |
||
| 87 | 1 | return pos < len(word) and word[pos] in {'A', 'E', 'I', 'O', 'U'} |
|
| 88 | |||
| 89 | 1 | word = unicode_normalize('NFC', text_type(word.upper())) |
|
| 90 | |||
| 91 | 1 | meta_key = '' |
|
| 92 | 1 | pos = 0 |
|
| 93 | |||
| 94 | # do some replacements for the modified version |
||
| 95 | 1 | if modified: |
|
| 96 | 1 | word = word.replace('MB', 'NB') |
|
| 97 | 1 | word = word.replace('MP', 'NP') |
|
| 98 | 1 | word = word.replace('BS', 'S') |
|
| 99 | 1 | if word[:2] == 'PS': |
|
| 100 | 1 | word = word[1:] |
|
| 101 | |||
| 102 | # simple replacements |
||
| 103 | 1 | word = word.replace('Á', 'A') |
|
| 104 | 1 | word = word.replace('CH', 'X') |
|
| 105 | 1 | word = word.replace('Ç', 'S') |
|
| 106 | 1 | word = word.replace('É', 'E') |
|
| 107 | 1 | word = word.replace('Í', 'I') |
|
| 108 | 1 | word = word.replace('Ó', 'O') |
|
| 109 | 1 | word = word.replace('Ú', 'U') |
|
| 110 | 1 | word = word.replace('Ñ', 'NY') |
|
| 111 | 1 | word = word.replace('GÜ', 'W') |
|
| 112 | 1 | word = word.replace('Ü', 'U') |
|
| 113 | 1 | word = word.replace('B', 'V') |
|
| 114 | 1 | word = word.replace('LL', 'Y') |
|
| 115 | |||
| 116 | 1 | while len(meta_key) < max_length: |
|
| 117 | 1 | if pos >= len(word): |
|
| 118 | 1 | break |
|
| 119 | |||
| 120 | # get the next character |
||
| 121 | 1 | current_char = word[pos] |
|
| 122 | |||
| 123 | # if a vowel in pos 0, add to key |
||
| 124 | 1 | if _is_vowel(pos) and pos == 0: |
|
| 125 | 1 | meta_key += current_char |
|
| 126 | 1 | pos += 1 |
|
| 127 | # otherwise, do consonant rules |
||
| 128 | else: |
||
| 129 | # simple consonants (unmutated) |
||
| 130 | 1 | if current_char in { |
|
| 131 | 'D', |
||
| 132 | 'F', |
||
| 133 | 'J', |
||
| 134 | 'K', |
||
| 135 | 'M', |
||
| 136 | 'N', |
||
| 137 | 'P', |
||
| 138 | 'T', |
||
| 139 | 'V', |
||
| 140 | 'L', |
||
| 141 | 'Y', |
||
| 142 | }: |
||
| 143 | 1 | meta_key += current_char |
|
| 144 | # skip doubled consonants |
||
| 145 | 1 | if word[pos + 1 : pos + 2] == current_char: |
|
| 146 | 1 | pos += 2 |
|
| 147 | else: |
||
| 148 | 1 | pos += 1 |
|
| 149 | else: |
||
| 150 | 1 | if current_char == 'C': |
|
| 151 | # special case 'acción', 'reacción',etc. |
||
| 152 | 1 | if word[pos + 1 : pos + 2] == 'C': |
|
| 153 | 1 | meta_key += 'X' |
|
| 154 | 1 | pos += 2 |
|
| 155 | # special case 'cesar', 'cien', 'cid', 'conciencia' |
||
| 156 | 1 | elif word[pos + 1 : pos + 2] in {'E', 'I'}: |
|
| 157 | 1 | meta_key += 'Z' |
|
| 158 | 1 | pos += 2 |
|
| 159 | # base case |
||
| 160 | else: |
||
| 161 | 1 | meta_key += 'K' |
|
| 162 | 1 | pos += 1 |
|
| 163 | 1 | elif current_char == 'G': |
|
| 164 | # special case 'gente', 'ecologia',etc |
||
| 165 | 1 | if word[pos + 1 : pos + 2] in {'E', 'I'}: |
|
| 166 | 1 | meta_key += 'J' |
|
| 167 | 1 | pos += 2 |
|
| 168 | # base case |
||
| 169 | else: |
||
| 170 | 1 | meta_key += 'G' |
|
| 171 | 1 | pos += 1 |
|
| 172 | 1 | elif current_char == 'H': |
|
| 173 | # since the letter 'H' is silent in Spanish, |
||
| 174 | # set the meta key to the vowel after the letter 'H' |
||
| 175 | 1 | if _is_vowel(pos + 1): |
|
| 176 | 1 | meta_key += word[pos + 1] |
|
| 177 | 1 | pos += 2 |
|
| 178 | else: |
||
| 179 | 1 | meta_key += 'H' |
|
| 180 | 1 | pos += 1 |
|
| 181 | 1 | elif current_char == 'Q': |
|
| 182 | 1 | if word[pos + 1 : pos + 2] == 'U': |
|
| 183 | 1 | pos += 2 |
|
| 184 | else: |
||
| 185 | 1 | pos += 1 |
|
| 186 | 1 | meta_key += 'K' |
|
| 187 | 1 | elif current_char == 'W': |
|
| 188 | 1 | meta_key += 'U' |
|
| 189 | 1 | pos += 1 |
|
| 190 | 1 | elif current_char == 'R': |
|
| 191 | 1 | meta_key += 'R' |
|
| 192 | 1 | pos += 1 |
|
| 193 | 1 | elif current_char == 'S': |
|
| 194 | 1 | if not _is_vowel(pos + 1) and pos == 0: |
|
| 195 | 1 | meta_key += 'ES' |
|
| 196 | 1 | pos += 1 |
|
| 197 | else: |
||
| 198 | 1 | meta_key += 'S' |
|
| 199 | 1 | pos += 1 |
|
| 200 | 1 | elif current_char == 'Z': |
|
| 201 | 1 | meta_key += 'Z' |
|
| 202 | 1 | pos += 1 |
|
| 203 | 1 | elif current_char == 'X': |
|
| 204 | 1 | if ( |
|
| 205 | len(word) > 1 |
||
| 206 | and pos == 0 |
||
| 207 | and not _is_vowel(pos + 1) |
||
| 208 | ): |
||
| 209 | 1 | meta_key += 'EX' |
|
| 210 | 1 | pos += 1 |
|
| 211 | else: |
||
| 212 | 1 | meta_key += 'X' |
|
| 213 | 1 | pos += 1 |
|
| 214 | else: |
||
| 215 | 1 | pos += 1 |
|
| 216 | |||
| 217 | # Final change from S to Z in modified version |
||
| 218 | 1 | if modified: |
|
| 219 | 1 | meta_key = meta_key.replace('S', 'Z') |
|
| 220 | |||
| 221 | 1 | return meta_key |
|
| 222 | |||
| 258 |
Loading history...