| Conditions | 73 |
| Total Lines | 310 |
| Code Lines | 204 |
| Lines | 0 |
| Ratio | 0 % |
| Tests | 103 |
| CRAP Score | 73.0047 |
| 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.distance._synoname.Synoname._synoname_word_approximation() 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 -*- |
||
| 114 | 1 | def _synoname_word_approximation( |
|
| 115 | self, src_ln, tar_ln, src_fn='', tar_fn='', features=None |
||
| 116 | ): |
||
| 117 | """Return the Synoname word approximation score for two names. |
||
| 118 | |||
| 119 | Parameters |
||
| 120 | ---------- |
||
| 121 | src_ln : str |
||
| 122 | Last name of the source |
||
| 123 | tar_ln : str |
||
| 124 | Last name of the target |
||
| 125 | src_fn : str |
||
| 126 | First name of the source (optional) |
||
| 127 | tar_fn : str |
||
| 128 | First name of the target (optional) |
||
| 129 | features : dict |
||
| 130 | A dict containing special features calculated using |
||
| 131 | :py:class:`fingerprint.SynonameToolcode` (optional) |
||
| 132 | |||
| 133 | Returns |
||
| 134 | ------- |
||
| 135 | float |
||
| 136 | The word approximation score |
||
| 137 | |||
| 138 | Examples |
||
| 139 | -------- |
||
| 140 | >>> pe = Synoname() |
||
| 141 | >>> pe._synoname_word_approximation('Smith Waterman', 'Waterman', |
||
| 142 | ... 'Tom Joe Bob', 'Tom Joe') |
||
| 143 | 0.6 |
||
| 144 | |||
| 145 | """ |
||
| 146 | 1 | if features is None: |
|
| 147 | 1 | features = {} |
|
| 148 | 1 | if 'src_specials' not in features: |
|
| 149 | 1 | features['src_specials'] = [] |
|
| 150 | 1 | if 'tar_specials' not in features: |
|
| 151 | 1 | features['tar_specials'] = [] |
|
| 152 | |||
| 153 | 1 | src_len_specials = len(features['src_specials']) |
|
| 154 | 1 | tar_len_specials = len(features['tar_specials']) |
|
| 155 | |||
| 156 | # 1 |
||
| 157 | 1 | if ('gen_conflict' in features and features['gen_conflict']) or ( |
|
| 158 | 'roman_conflict' in features and features['roman_conflict'] |
||
| 159 | ): |
||
| 160 | 1 | return 0 |
|
| 161 | |||
| 162 | # 3 & 7 |
||
| 163 | 1 | full_tar1 = ' '.join((tar_ln, tar_fn)).replace('-', ' ').strip() |
|
| 164 | 1 | for s_pos, s_type in features['tar_specials']: |
|
| 165 | 1 | if s_type == 'a': |
|
| 166 | 1 | full_tar1 = full_tar1[ |
|
| 167 | : -( |
||
| 168 | 1 |
||
| 169 | + len( |
||
| 170 | self._stc._synoname_special_table[ # noqa: SF01 |
||
| 171 | s_pos |
||
| 172 | ][1] |
||
| 173 | ) |
||
| 174 | ) |
||
| 175 | ] |
||
| 176 | 1 | elif s_type == 'b': |
|
| 177 | 1 | loc = ( |
|
| 178 | full_tar1.find( |
||
| 179 | ' ' |
||
| 180 | + self._stc._synoname_special_table[ # noqa: SF01 |
||
| 181 | s_pos |
||
| 182 | ][1] |
||
| 183 | + ' ' |
||
| 184 | ) |
||
| 185 | + 1 |
||
| 186 | ) |
||
| 187 | 1 | full_tar1 = ( |
|
| 188 | full_tar1[:loc] |
||
| 189 | + full_tar1[ |
||
| 190 | loc |
||
| 191 | + len( |
||
| 192 | self._stc._synoname_special_table[ # noqa: SF01 |
||
| 193 | s_pos |
||
| 194 | ][1] |
||
| 195 | ) : |
||
| 196 | ] |
||
| 197 | ) |
||
| 198 | 1 | elif s_type == 'c': |
|
| 199 | 1 | full_tar1 = full_tar1[ |
|
| 200 | 1 |
||
| 201 | + len( |
||
| 202 | self._stc._synoname_special_table[s_pos][ # noqa: SF01 |
||
| 203 | 1 |
||
| 204 | ] |
||
| 205 | ) : |
||
| 206 | ] |
||
| 207 | |||
| 208 | 1 | full_src1 = ' '.join((src_ln, src_fn)).replace('-', ' ').strip() |
|
| 209 | 1 | for s_pos, s_type in features['src_specials']: |
|
| 210 | 1 | if s_type == 'a': |
|
| 211 | 1 | full_src1 = full_src1[ |
|
| 212 | : -( |
||
| 213 | 1 |
||
| 214 | + len( |
||
| 215 | self._stc._synoname_special_table[ # noqa: SF01 |
||
| 216 | s_pos |
||
| 217 | ][1] |
||
| 218 | ) |
||
| 219 | ) |
||
| 220 | ] |
||
| 221 | 1 | elif s_type == 'b': |
|
| 222 | 1 | loc = ( |
|
| 223 | full_src1.find( |
||
| 224 | ' ' |
||
| 225 | + self._stc._synoname_special_table[ # noqa: SF01 |
||
| 226 | s_pos |
||
| 227 | ][1] |
||
| 228 | + ' ' |
||
| 229 | ) |
||
| 230 | + 1 |
||
| 231 | ) |
||
| 232 | 1 | full_src1 = ( |
|
| 233 | full_src1[:loc] |
||
| 234 | + full_src1[ |
||
| 235 | loc |
||
| 236 | + len( |
||
| 237 | self._stc._synoname_special_table[ # noqa: SF01 |
||
| 238 | s_pos |
||
| 239 | ][1] |
||
| 240 | ) : |
||
| 241 | ] |
||
| 242 | ) |
||
| 243 | 1 | elif s_type == 'c': |
|
| 244 | 1 | full_src1 = full_src1[ |
|
| 245 | 1 |
||
| 246 | + len( |
||
| 247 | self._stc._synoname_special_table[s_pos][ # noqa: SF01 |
||
| 248 | 1 |
||
| 249 | ] |
||
| 250 | ) : |
||
| 251 | ] |
||
| 252 | |||
| 253 | 1 | full_tar2 = full_tar1 |
|
| 254 | 1 | for s_pos, s_type in features['tar_specials']: |
|
| 255 | 1 | if s_type == 'd': |
|
| 256 | 1 | full_tar2 = full_tar2[ |
|
| 257 | len( |
||
| 258 | self._stc._synoname_special_table[s_pos][ # noqa: SF01 |
||
| 259 | 1 |
||
| 260 | ] |
||
| 261 | ) : |
||
| 262 | ] |
||
| 263 | 1 | elif ( |
|
| 264 | s_type == 'X' |
||
| 265 | and self._stc._synoname_special_table[s_pos][1] # noqa: SF01 |
||
| 266 | in full_tar2 |
||
| 267 | ): |
||
| 268 | 1 | loc = full_tar2.find( |
|
| 269 | ' ' |
||
| 270 | + self._stc._synoname_special_table[s_pos][1] # noqa: SF01 |
||
| 271 | ) |
||
| 272 | 1 | full_tar2 = ( |
|
| 273 | full_tar2[:loc] |
||
| 274 | + full_tar2[ |
||
| 275 | loc |
||
| 276 | + len( |
||
| 277 | self._stc._synoname_special_table[ # noqa: SF01 |
||
| 278 | s_pos |
||
| 279 | ][1] |
||
| 280 | ) : |
||
| 281 | ] |
||
| 282 | ) |
||
| 283 | |||
| 284 | 1 | full_src2 = full_src1 |
|
| 285 | 1 | for s_pos, s_type in features['src_specials']: |
|
| 286 | 1 | if s_type == 'd': |
|
| 287 | 1 | full_src2 = full_src2[ |
|
| 288 | len( |
||
| 289 | self._stc._synoname_special_table[s_pos][ # noqa: SF01 |
||
| 290 | 1 |
||
| 291 | ] |
||
| 292 | ) : |
||
| 293 | ] |
||
| 294 | 1 | elif ( |
|
| 295 | s_type == 'X' |
||
| 296 | and self._stc._synoname_special_table[s_pos][1] # noqa: SF01 |
||
| 297 | in full_src2 |
||
| 298 | ): |
||
| 299 | 1 | loc = full_src2.find( |
|
| 300 | ' ' |
||
| 301 | + self._stc._synoname_special_table[s_pos][1] # noqa: SF01 |
||
| 302 | ) |
||
| 303 | 1 | full_src2 = ( |
|
| 304 | full_src2[:loc] |
||
| 305 | + full_src2[ |
||
| 306 | loc |
||
| 307 | + len( |
||
| 308 | self._stc._synoname_special_table[ # noqa: SF01 |
||
| 309 | s_pos |
||
| 310 | ][1] |
||
| 311 | ) : |
||
| 312 | ] |
||
| 313 | ) |
||
| 314 | |||
| 315 | 1 | full_tar1 = self._synoname_strip_punct(full_tar1) |
|
| 316 | 1 | tar1_words = full_tar1.split() |
|
| 317 | 1 | tar1_num_words = len(tar1_words) |
|
| 318 | |||
| 319 | 1 | full_src1 = self._synoname_strip_punct(full_src1) |
|
| 320 | 1 | src1_words = full_src1.split() |
|
| 321 | 1 | src1_num_words = len(src1_words) |
|
| 322 | |||
| 323 | 1 | full_tar2 = self._synoname_strip_punct(full_tar2) |
|
| 324 | 1 | tar2_words = full_tar2.split() |
|
| 325 | 1 | tar2_num_words = len(tar2_words) |
|
| 326 | |||
| 327 | 1 | full_src2 = self._synoname_strip_punct(full_src2) |
|
| 328 | 1 | src2_words = full_src2.split() |
|
| 329 | 1 | src2_num_words = len(src2_words) |
|
| 330 | |||
| 331 | # 2 |
||
| 332 | 1 | if ( |
|
| 333 | src1_num_words < 2 |
||
| 334 | and src_len_specials == 0 |
||
| 335 | and src2_num_words < 2 |
||
| 336 | and tar_len_specials == 0 |
||
| 337 | ): |
||
| 338 | 1 | return 0 |
|
| 339 | |||
| 340 | # 4 |
||
| 341 | 1 | if ( |
|
| 342 | tar1_num_words == 1 |
||
| 343 | and src1_num_words == 1 |
||
| 344 | and tar1_words[0] == src1_words[0] |
||
| 345 | ): |
||
| 346 | 1 | return 1 |
|
| 347 | 1 | if tar1_num_words < 2 and tar_len_specials == 0: |
|
| 348 | 1 | return 0 |
|
| 349 | |||
| 350 | # 5 |
||
| 351 | 1 | last_found = False |
|
| 352 | 1 | for word in tar1_words: |
|
| 353 | 1 | if src_ln.endswith(word) or word + ' ' in src_ln: |
|
| 354 | 1 | last_found = True |
|
| 355 | |||
| 356 | 1 | if not last_found: |
|
| 357 | 1 | for word in src1_words: |
|
| 358 | 1 | if tar_ln.endswith(word) or word + ' ' in tar_ln: |
|
| 359 | 1 | last_found = True |
|
| 360 | |||
| 361 | # 6 |
||
| 362 | 1 | matches = 0 |
|
| 363 | 1 | if last_found: |
|
| 364 | 1 | for i, s_word in enumerate(src1_words): |
|
| 365 | 1 | for j, t_word in enumerate(tar1_words): |
|
| 366 | 1 | if s_word == t_word: |
|
| 367 | 1 | src1_words[i] = '@' |
|
| 368 | 1 | tar1_words[j] = '@' |
|
| 369 | 1 | matches += 1 |
|
| 370 | 1 | w_ratio = matches / max(tar1_num_words, src1_num_words) |
|
| 371 | 1 | if matches > 1 or ( |
|
| 372 | matches == 1 |
||
| 373 | and src1_num_words == 1 |
||
| 374 | and tar1_num_words == 1 |
||
| 375 | and (tar_len_specials > 0 or src_len_specials > 0) |
||
| 376 | ): |
||
| 377 | 1 | return w_ratio |
|
| 378 | |||
| 379 | # 8 |
||
| 380 | 1 | if ( |
|
| 381 | tar2_num_words == 1 |
||
| 382 | and src2_num_words == 1 |
||
| 383 | and tar2_words[0] == src2_words[0] |
||
| 384 | ): |
||
| 385 | 1 | return 1 |
|
| 386 | # I see no way that the following can be True if the equivalent in |
||
| 387 | # #4 was False. |
||
| 388 | if tar2_num_words < 2 and tar_len_specials == 0: # pragma: no cover |
||
| 389 | return 0 |
||
| 390 | |||
| 391 | # 9 |
||
| 392 | 1 | last_found = False |
|
| 393 | 1 | for word in tar2_words: |
|
| 394 | 1 | if src_ln.endswith(word) or word + ' ' in src_ln: |
|
| 395 | 1 | last_found = True |
|
| 396 | |||
| 397 | 1 | if not last_found: |
|
| 398 | 1 | for word in src2_words: |
|
| 399 | 1 | if tar_ln.endswith(word) or word + ' ' in tar_ln: |
|
| 400 | 1 | last_found = True |
|
| 401 | |||
| 402 | 1 | if not last_found: |
|
| 403 | 1 | return 0 |
|
| 404 | |||
| 405 | # 10 |
||
| 406 | 1 | matches = 0 |
|
| 407 | 1 | if last_found: |
|
| 408 | 1 | for i, s_word in enumerate(src2_words): |
|
| 409 | 1 | for j, t_word in enumerate(tar2_words): |
|
| 410 | 1 | if s_word == t_word: |
|
| 411 | 1 | src2_words[i] = '@' |
|
| 412 | 1 | tar2_words[j] = '@' |
|
| 413 | 1 | matches += 1 |
|
| 414 | 1 | w_ratio = matches / max(tar2_num_words, src2_num_words) |
|
| 415 | 1 | if matches > 1 or ( |
|
| 416 | matches == 1 |
||
| 417 | and src2_num_words == 1 |
||
| 418 | and tar2_num_words == 1 |
||
| 419 | and (tar_len_specials > 0 or src_len_specials > 0) |
||
| 420 | ): |
||
| 421 | return w_ratio |
||
| 422 | |||
| 423 | 1 | return 0 |
|
| 424 | |||
| 809 |