chrislit /
abydos
| Conditions | 32 |
| Total Lines | 204 |
| Code Lines | 98 |
| Lines | 0 |
| Ratio | 0 % |
| Tests | 80 |
| CRAP Score | 32 |
| 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._sfinx_bis.SfinxBis.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 -*- |
||
| 154 | 1 | def encode(self, word, max_length=-1): |
|
| 155 | """Return the SfinxBis code for a word. |
||
| 156 | |||
| 157 | Parameters |
||
| 158 | ---------- |
||
| 159 | word : str |
||
| 160 | The word to transform |
||
| 161 | max_length : int |
||
| 162 | The length of the code returned (defaults to unlimited) |
||
| 163 | |||
| 164 | Returns |
||
| 165 | ------- |
||
| 166 | tuple |
||
| 167 | The SfinxBis value |
||
| 168 | |||
| 169 | Examples |
||
| 170 | -------- |
||
| 171 | >>> pe = SfinxBis() |
||
| 172 | >>> pe.encode('Christopher') |
||
| 173 | ('K68376',) |
||
| 174 | >>> pe.encode('Niall') |
||
| 175 | ('N4',) |
||
| 176 | >>> pe.encode('Smith') |
||
| 177 | ('S53',) |
||
| 178 | >>> pe.encode('Schmidt') |
||
| 179 | ('S53',) |
||
| 180 | |||
| 181 | >>> pe.encode('Johansson') |
||
| 182 | ('J585',) |
||
| 183 | >>> pe.encode('Sjöberg') |
||
| 184 | ('#162',) |
||
| 185 | |||
| 186 | """ |
||
| 187 | |||
| 188 | 1 | def _foersvensker(lokal_ordet): |
|
| 189 | """Return the Swedish-ized form of the word. |
||
| 190 | |||
| 191 | Parameters |
||
| 192 | ---------- |
||
| 193 | lokal_ordet : str |
||
| 194 | Word to transform |
||
| 195 | |||
| 196 | Returns |
||
| 197 | ------- |
||
| 198 | str |
||
| 199 | Transformed word |
||
| 200 | |||
| 201 | """ |
||
| 202 | 1 | lokal_ordet = lokal_ordet.replace('STIERN', 'STJÄRN') |
|
| 203 | 1 | lokal_ordet = lokal_ordet.replace('HIE', 'HJ') |
|
| 204 | 1 | lokal_ordet = lokal_ordet.replace('SIÖ', 'SJÖ') |
|
| 205 | 1 | lokal_ordet = lokal_ordet.replace('SCH', 'SH') |
|
| 206 | 1 | lokal_ordet = lokal_ordet.replace('QU', 'KV') |
|
| 207 | 1 | lokal_ordet = lokal_ordet.replace('IO', 'JO') |
|
| 208 | 1 | lokal_ordet = lokal_ordet.replace('PH', 'F') |
|
| 209 | |||
| 210 | 1 | for i in self._harde_vokaler: |
|
| 211 | 1 | lokal_ordet = lokal_ordet.replace(i + 'Ü', i + 'J') |
|
| 212 | 1 | lokal_ordet = lokal_ordet.replace(i + 'Y', i + 'J') |
|
| 213 | 1 | lokal_ordet = lokal_ordet.replace(i + 'I', i + 'J') |
|
| 214 | 1 | for i in self._mjuka_vokaler: |
|
| 215 | 1 | lokal_ordet = lokal_ordet.replace(i + 'Ü', i + 'J') |
|
| 216 | 1 | lokal_ordet = lokal_ordet.replace(i + 'Y', i + 'J') |
|
| 217 | 1 | lokal_ordet = lokal_ordet.replace(i + 'I', i + 'J') |
|
| 218 | |||
| 219 | 1 | if 'H' in lokal_ordet: |
|
| 220 | 1 | for i in self._uc_c_set: |
|
| 221 | 1 | lokal_ordet = lokal_ordet.replace('H' + i, i) |
|
| 222 | |||
| 223 | 1 | lokal_ordet = lokal_ordet.translate(self._substitutions) |
|
| 224 | |||
| 225 | 1 | lokal_ordet = lokal_ordet.replace('Ð', 'ETH') |
|
| 226 | 1 | lokal_ordet = lokal_ordet.replace('Þ', 'TH') |
|
| 227 | 1 | lokal_ordet = lokal_ordet.replace('ß', 'SS') |
|
| 228 | |||
| 229 | 1 | return lokal_ordet |
|
| 230 | |||
| 231 | 1 | def _koda_foersta_ljudet(lokal_ordet): |
|
| 232 | """Return the word with the first sound coded. |
||
| 233 | |||
| 234 | Parameters |
||
| 235 | ---------- |
||
| 236 | lokal_ordet : str |
||
| 237 | Word to transform |
||
| 238 | |||
| 239 | Returns |
||
| 240 | ------- |
||
| 241 | str |
||
| 242 | Transformed word |
||
| 243 | |||
| 244 | """ |
||
| 245 | 1 | if ( |
|
| 246 | lokal_ordet[0:1] in self._mjuka_vokaler |
||
| 247 | or lokal_ordet[0:1] in self._harde_vokaler |
||
| 248 | ): |
||
| 249 | 1 | lokal_ordet = '$' + lokal_ordet[1:] |
|
| 250 | 1 | elif lokal_ordet[0:2] in ('DJ', 'GJ', 'HJ', 'LJ'): |
|
| 251 | 1 | lokal_ordet = 'J' + lokal_ordet[2:] |
|
| 252 | 1 | elif ( |
|
| 253 | lokal_ordet[0:1] == 'G' |
||
| 254 | and lokal_ordet[1:2] in self._mjuka_vokaler |
||
| 255 | ): |
||
| 256 | 1 | lokal_ordet = 'J' + lokal_ordet[1:] |
|
| 257 | 1 | elif lokal_ordet[0:1] == 'Q': |
|
| 258 | 1 | lokal_ordet = 'K' + lokal_ordet[1:] |
|
| 259 | 1 | elif lokal_ordet[0:2] == 'CH' and lokal_ordet[2:3] in frozenset( |
|
| 260 | self._mjuka_vokaler | self._harde_vokaler |
||
| 261 | ): |
||
| 262 | 1 | lokal_ordet = '#' + lokal_ordet[2:] |
|
| 263 | 1 | elif ( |
|
| 264 | lokal_ordet[0:1] == 'C' |
||
| 265 | and lokal_ordet[1:2] in self._harde_vokaler |
||
| 266 | ): |
||
| 267 | 1 | lokal_ordet = 'K' + lokal_ordet[1:] |
|
| 268 | 1 | elif ( |
|
| 269 | lokal_ordet[0:1] == 'C' and lokal_ordet[1:2] in self._uc_c_set |
||
| 270 | ): |
||
| 271 | 1 | lokal_ordet = 'K' + lokal_ordet[1:] |
|
| 272 | 1 | elif lokal_ordet[0:1] == 'X': |
|
| 273 | 1 | lokal_ordet = 'S' + lokal_ordet[1:] |
|
| 274 | 1 | elif ( |
|
| 275 | lokal_ordet[0:1] == 'C' |
||
| 276 | and lokal_ordet[1:2] in self._mjuka_vokaler |
||
| 277 | ): |
||
| 278 | 1 | lokal_ordet = 'S' + lokal_ordet[1:] |
|
| 279 | 1 | elif lokal_ordet[0:3] in ('SKJ', 'STJ', 'SCH'): |
|
| 280 | 1 | lokal_ordet = '#' + lokal_ordet[3:] |
|
| 281 | 1 | elif lokal_ordet[0:2] in ('SH', 'KJ', 'TJ', 'SJ'): |
|
| 282 | 1 | lokal_ordet = '#' + lokal_ordet[2:] |
|
| 283 | 1 | elif ( |
|
| 284 | lokal_ordet[0:2] == 'SK' |
||
| 285 | and lokal_ordet[2:3] in self._mjuka_vokaler |
||
| 286 | ): |
||
| 287 | 1 | lokal_ordet = '#' + lokal_ordet[2:] |
|
| 288 | 1 | elif ( |
|
| 289 | lokal_ordet[0:1] == 'K' |
||
| 290 | and lokal_ordet[1:2] in self._mjuka_vokaler |
||
| 291 | ): |
||
| 292 | 1 | lokal_ordet = '#' + lokal_ordet[1:] |
|
| 293 | 1 | return lokal_ordet |
|
| 294 | |||
| 295 | # Steg 1, Versaler |
||
| 296 | 1 | word = unicode_normalize('NFC', text_type(word.upper())) |
|
| 297 | 1 | word = word.replace('ß', 'SS') |
|
| 298 | 1 | word = word.replace('-', ' ') |
|
| 299 | |||
| 300 | # Steg 2, Ta bort adelsprefix |
||
| 301 | 1 | for adelstitel in self._adelstitler: |
|
| 302 | 1 | while adelstitel in word: |
|
| 303 | 1 | word = word.replace(adelstitel, ' ') |
|
| 304 | 1 | if word.startswith(adelstitel[1:]): |
|
| 305 | 1 | word = word[len(adelstitel) - 1 :] |
|
| 306 | |||
| 307 | # Split word into tokens |
||
| 308 | 1 | ordlista = word.split() |
|
| 309 | |||
| 310 | # Steg 3, Ta bort dubbelteckning i början på namnet |
||
| 311 | 1 | ordlista = [ |
|
| 312 | self._delete_consecutive_repeats(ordet) for ordet in ordlista |
||
| 313 | ] |
||
| 314 | 1 | if not ordlista: |
|
| 315 | # noinspection PyRedundantParentheses |
||
| 316 | 1 | return ('',) |
|
| 317 | |||
| 318 | # Steg 4, Försvenskning |
||
| 319 | 1 | ordlista = [_foersvensker(ordet) for ordet in ordlista] |
|
| 320 | |||
| 321 | # Steg 5, Ta bort alla tecken som inte är A-Ö (65-90,196,197,214) |
||
| 322 | 1 | ordlista = [ |
|
| 323 | ''.join(c for c in ordet if c in self._uc_set) |
||
| 324 | for ordet in ordlista |
||
| 325 | ] |
||
| 326 | |||
| 327 | # Steg 6, Koda första ljudet |
||
| 328 | 1 | ordlista = [_koda_foersta_ljudet(ordet) for ordet in ordlista] |
|
| 329 | |||
| 330 | # Steg 7, Dela upp namnet i två delar |
||
| 331 | 1 | rest = [ordet[1:] for ordet in ordlista] |
|
| 332 | |||
| 333 | # Steg 8, Utför fonetisk transformation i resten |
||
| 334 | 1 | rest = [ordet.replace('DT', 'T') for ordet in rest] |
|
| 335 | 1 | rest = [ordet.replace('X', 'KS') for ordet in rest] |
|
| 336 | |||
| 337 | # Steg 9, Koda resten till en sifferkod |
||
| 338 | 1 | for vokal in self._mjuka_vokaler: |
|
| 339 | 1 | rest = [ordet.replace('C' + vokal, '8' + vokal) for ordet in rest] |
|
| 340 | 1 | rest = [ordet.translate(self._trans) for ordet in rest] |
|
| 341 | |||
| 342 | # Steg 10, Ta bort intilliggande dubbletter |
||
| 343 | 1 | rest = [self._delete_consecutive_repeats(ordet) for ordet in rest] |
|
| 344 | |||
| 345 | # Steg 11, Ta bort alla "9" |
||
| 346 | 1 | rest = [ordet.replace('9', '') for ordet in rest] |
|
| 347 | |||
| 348 | # Steg 12, Sätt ihop delarna igen |
||
| 349 | 1 | ordlista = [ |
|
| 350 | ''.join(ordet) for ordet in zip((_[0:1] for _ in ordlista), rest) |
||
| 351 | ] |
||
| 352 | |||
| 353 | # truncate, if max_length is set |
||
| 354 | 1 | if max_length > 0: |
|
| 355 | 1 | ordlista = [ordet[:max_length] for ordet in ordlista] |
|
| 356 | |||
| 357 | 1 | return tuple(ordlista) |
|
| 358 | |||
| 401 |
Loading history...