| Conditions | 80 |
| Total Lines | 200 |
| Code Lines | 128 |
| Lines | 0 |
| Ratio | 0 % |
| Tests | 99 |
| CRAP Score | 80 |
| 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._Metaphone.Metaphone.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=-1): |
|
| 51 | """Return the Metaphone code for a word. |
||
| 52 | |||
| 53 | Based on Lawrence Philips' Pick BASIC code from 1990 |
||
| 54 | :cite:`Philips:1990`, as described in :cite:`Philips:1990b`. |
||
| 55 | This incorporates some corrections to the above code, particularly |
||
| 56 | some of those suggested by Michael Kuhn in :cite:`Kuhn:1995`. |
||
| 57 | |||
| 58 | Args: |
||
| 59 | word (str): The word to transform |
||
| 60 | max_length (int): The maximum length of the returned Metaphone |
||
| 61 | code (defaults to 64, but in Philips' original implementation |
||
| 62 | this was 4) |
||
| 63 | |||
| 64 | Returns: |
||
| 65 | str: The Metaphone value |
||
| 66 | |||
| 67 | Examples: |
||
| 68 | >>> pe = Metaphone() |
||
| 69 | >>> pe.encode('Christopher') |
||
| 70 | 'KRSTFR' |
||
| 71 | >>> pe.encode('Niall') |
||
| 72 | 'NL' |
||
| 73 | >>> pe.encode('Smith') |
||
| 74 | 'SM0' |
||
| 75 | >>> pe.encode('Schmidt') |
||
| 76 | 'SKMTT' |
||
| 77 | |||
| 78 | """ |
||
| 79 | # Require a max_length of at least 4 |
||
| 80 | 1 | if max_length != -1: |
|
| 81 | 1 | max_length = max(4, max_length) |
|
| 82 | else: |
||
| 83 | 1 | max_length = 64 |
|
| 84 | |||
| 85 | # As in variable sound--those modified by adding an "h" |
||
| 86 | 1 | ename = ''.join(c for c in word.upper() if c.isalnum()) |
|
| 87 | 1 | ename = ename.replace('ß', 'SS') |
|
| 88 | |||
| 89 | # Delete non-alphanumeric characters and make all caps |
||
| 90 | 1 | if not ename: |
|
| 91 | 1 | return '' |
|
| 92 | 1 | if ename[0:2] in {'PN', 'AE', 'KN', 'GN', 'WR'}: |
|
| 93 | 1 | ename = ename[1:] |
|
| 94 | 1 | elif ename[0] == 'X': |
|
| 95 | 1 | ename = 'S' + ename[1:] |
|
| 96 | 1 | elif ename[0:2] == 'WH': |
|
| 97 | 1 | ename = 'W' + ename[2:] |
|
| 98 | |||
| 99 | # Convert to metaphone |
||
| 100 | 1 | elen = len(ename) - 1 |
|
| 101 | 1 | metaph = '' |
|
| 102 | 1 | for i in range(len(ename)): |
|
| 103 | 1 | if len(metaph) >= max_length: |
|
| 104 | 1 | break |
|
| 105 | 1 | if ( |
|
| 106 | ename[i] not in {'G', 'T'} |
||
| 107 | and i > 0 |
||
| 108 | and ename[i - 1] == ename[i] |
||
| 109 | ): |
||
| 110 | 1 | continue |
|
| 111 | |||
| 112 | 1 | if ename[i] in self._uc_v_set and i == 0: |
|
| 113 | 1 | metaph = ename[i] |
|
| 114 | |||
| 115 | 1 | elif ename[i] == 'B': |
|
| 116 | 1 | if i != elen or ename[i - 1] != 'M': |
|
| 117 | 1 | metaph += ename[i] |
|
| 118 | |||
| 119 | 1 | elif ename[i] == 'C': |
|
| 120 | 1 | if not ( |
|
| 121 | i > 0 |
||
| 122 | and ename[i - 1] == 'S' |
||
| 123 | and ename[i + 1 : i + 2] in self._frontv |
||
| 124 | ): |
||
| 125 | 1 | if ename[i + 1 : i + 3] == 'IA': |
|
| 126 | 1 | metaph += 'X' |
|
| 127 | 1 | elif ename[i + 1 : i + 2] in self._frontv: |
|
| 128 | 1 | metaph += 'S' |
|
| 129 | 1 | elif i > 0 and ename[i - 1 : i + 2] == 'SCH': |
|
| 130 | 1 | metaph += 'K' |
|
| 131 | 1 | elif ename[i + 1 : i + 2] == 'H': |
|
| 132 | 1 | if ( |
|
| 133 | i == 0 |
||
| 134 | and i + 1 < elen |
||
| 135 | and ename[i + 2 : i + 3] not in self._uc_v_set |
||
| 136 | ): |
||
| 137 | 1 | metaph += 'K' |
|
| 138 | else: |
||
| 139 | 1 | metaph += 'X' |
|
| 140 | else: |
||
| 141 | 1 | metaph += 'K' |
|
| 142 | |||
| 143 | 1 | elif ename[i] == 'D': |
|
| 144 | 1 | if ( |
|
| 145 | ename[i + 1 : i + 2] == 'G' |
||
| 146 | and ename[i + 2 : i + 3] in self._frontv |
||
| 147 | ): |
||
| 148 | 1 | metaph += 'J' |
|
| 149 | else: |
||
| 150 | 1 | metaph += 'T' |
|
| 151 | |||
| 152 | 1 | elif ename[i] == 'G': |
|
| 153 | 1 | if ename[i + 1 : i + 2] == 'H' and not ( |
|
| 154 | i + 1 == elen or ename[i + 2 : i + 3] not in self._uc_v_set |
||
| 155 | ): |
||
| 156 | 1 | continue |
|
| 157 | 1 | elif i > 0 and ( |
|
| 158 | (i + 1 == elen and ename[i + 1] == 'N') |
||
| 159 | or (i + 3 == elen and ename[i + 1 : i + 4] == 'NED') |
||
| 160 | ): |
||
| 161 | 1 | continue |
|
| 162 | 1 | elif ( |
|
| 163 | i - 1 > 0 |
||
| 164 | and i + 1 <= elen |
||
| 165 | and ename[i - 1] == 'D' |
||
| 166 | and ename[i + 1] in self._frontv |
||
| 167 | ): |
||
| 168 | 1 | continue |
|
| 169 | 1 | elif ename[i + 1 : i + 2] == 'G': |
|
| 170 | 1 | continue |
|
| 171 | 1 | elif ename[i + 1 : i + 2] in self._frontv: |
|
| 172 | 1 | if i == 0 or ename[i - 1] != 'G': |
|
| 173 | 1 | metaph += 'J' |
|
| 174 | else: |
||
| 175 | 1 | metaph += 'K' |
|
| 176 | else: |
||
| 177 | 1 | metaph += 'K' |
|
| 178 | |||
| 179 | 1 | elif ename[i] == 'H': |
|
| 180 | 1 | if ( |
|
| 181 | i > 0 |
||
| 182 | and ename[i - 1] in self._uc_v_set |
||
| 183 | and ename[i + 1 : i + 2] not in self._uc_v_set |
||
| 184 | ): |
||
| 185 | 1 | continue |
|
| 186 | 1 | elif i > 0 and ename[i - 1] in self._varson: |
|
| 187 | 1 | continue |
|
| 188 | else: |
||
| 189 | 1 | metaph += 'H' |
|
| 190 | |||
| 191 | 1 | elif ename[i] in {'F', 'J', 'L', 'M', 'N', 'R'}: |
|
| 192 | 1 | metaph += ename[i] |
|
| 193 | |||
| 194 | 1 | elif ename[i] == 'K': |
|
| 195 | 1 | if i > 0 and ename[i - 1] == 'C': |
|
| 196 | 1 | continue |
|
| 197 | else: |
||
| 198 | 1 | metaph += 'K' |
|
| 199 | |||
| 200 | 1 | elif ename[i] == 'P': |
|
| 201 | 1 | if ename[i + 1 : i + 2] == 'H': |
|
| 202 | 1 | metaph += 'F' |
|
| 203 | else: |
||
| 204 | 1 | metaph += 'P' |
|
| 205 | |||
| 206 | 1 | elif ename[i] == 'Q': |
|
| 207 | 1 | metaph += 'K' |
|
| 208 | |||
| 209 | 1 | elif ename[i] == 'S': |
|
| 210 | 1 | if ( |
|
| 211 | i > 0 |
||
| 212 | and i + 2 <= elen |
||
| 213 | and ename[i + 1] == 'I' |
||
| 214 | and ename[i + 2] in 'OA' |
||
| 215 | ): |
||
| 216 | 1 | metaph += 'X' |
|
| 217 | 1 | elif ename[i + 1 : i + 2] == 'H': |
|
| 218 | 1 | metaph += 'X' |
|
| 219 | else: |
||
| 220 | 1 | metaph += 'S' |
|
| 221 | |||
| 222 | 1 | elif ename[i] == 'T': |
|
| 223 | 1 | if ( |
|
| 224 | i > 0 |
||
| 225 | and i + 2 <= elen |
||
| 226 | and ename[i + 1] == 'I' |
||
| 227 | and ename[i + 2] in {'A', 'O'} |
||
| 228 | ): |
||
| 229 | 1 | metaph += 'X' |
|
| 230 | 1 | elif ename[i + 1 : i + 2] == 'H': |
|
| 231 | 1 | metaph += '0' |
|
| 232 | 1 | elif ename[i + 1 : i + 3] != 'CH': |
|
| 233 | 1 | if ename[i - 1 : i] != 'T': |
|
| 234 | 1 | metaph += 'T' |
|
| 235 | |||
| 236 | 1 | elif ename[i] == 'V': |
|
| 237 | 1 | metaph += 'F' |
|
| 238 | |||
| 239 | 1 | elif ename[i] in 'WY': |
|
| 240 | 1 | if ename[i + 1 : i + 2] in self._uc_v_set: |
|
| 241 | 1 | metaph += ename[i] |
|
| 242 | |||
| 243 | 1 | elif ename[i] == 'X': |
|
| 244 | 1 | metaph += 'KS' |
|
| 245 | |||
| 246 | 1 | elif ename[i] == 'Z': |
|
| 247 | 1 | metaph += 'S' |
|
| 248 | |||
| 249 | 1 | return metaph |
|
| 250 | |||
| 284 |
This check looks for invalid names for a range of different identifiers.
You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements.
If your project includes a Pylint configuration file, the settings contained in that file take precedence.
To find out more about Pylint, please refer to their site.