chrislit /
abydos
| Conditions | 79 |
| Total Lines | 297 |
| Code Lines | 211 |
| Lines | 0 |
| Ratio | 0 % |
| Tests | 135 |
| CRAP Score | 79 |
| 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() 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 -*- |
||
| 257 | 1 | def synoname( |
|
| 258 | src, |
||
| 259 | tar, |
||
| 260 | word_approx_min=0.3, |
||
| 261 | char_approx_min=0.73, |
||
| 262 | tests=2 ** 12 - 1, |
||
| 263 | ret_name=False, |
||
| 264 | ): |
||
| 265 | """Return the Synoname similarity type of two words. |
||
| 266 | |||
| 267 | Cf. :cite:`Getty:1991,Gross:1991` |
||
| 268 | |||
| 269 | :param str src: source string for comparison |
||
| 270 | :param str tar: target string for comparison |
||
| 271 | :param bool ret_name: return the name of the match type rather than the |
||
| 272 | int value |
||
| 273 | :param float word_approx_min: the minimum word approximation value to |
||
| 274 | signal a 'word_approx' match |
||
| 275 | :param float char_approx_min: the minimum character approximation value to |
||
| 276 | signal a 'char_approx' match |
||
| 277 | :param int or Iterable tests: either an integer indicating tests to |
||
| 278 | perform or a list of test names to perform (defaults to performing all |
||
| 279 | tests) |
||
| 280 | :param bool ret_name: if True, returns the match name rather than its |
||
| 281 | integer equivalent |
||
| 282 | :returns: Synoname value |
||
| 283 | :rtype: int (or str if ret_name is True) |
||
| 284 | |||
| 285 | >>> synoname(('Breghel', 'Pieter', ''), ('Brueghel', 'Pieter', '')) |
||
| 286 | 2 |
||
| 287 | >>> synoname(('Breghel', 'Pieter', ''), ('Brueghel', 'Pieter', ''), |
||
| 288 | ... ret_name=True) |
||
| 289 | 'omission' |
||
| 290 | >>> synoname(('Dore', 'Gustave', ''), |
||
| 291 | ... ('Dore', 'Paul Gustave Louis Christophe', ''), |
||
| 292 | ... ret_name=True) |
||
| 293 | 'inclusion' |
||
| 294 | >>> synoname(('Pereira', 'I. R.', ''), ('Pereira', 'I. Smith', ''), |
||
| 295 | ... ret_name=True) |
||
| 296 | 'word_approx' |
||
| 297 | """ |
||
| 298 | 1 | test_dict = { |
|
| 299 | val: 2 ** n |
||
| 300 | for n, val in enumerate( |
||
| 301 | [ |
||
| 302 | 'exact', |
||
| 303 | 'omission', |
||
| 304 | 'substitution', |
||
| 305 | 'transposition', |
||
| 306 | 'punctuation', |
||
| 307 | 'initials', |
||
| 308 | 'extension', |
||
| 309 | 'inclusion', |
||
| 310 | 'no_first', |
||
| 311 | 'word_approx', |
||
| 312 | 'confusions', |
||
| 313 | 'char_approx', |
||
| 314 | ] |
||
| 315 | ) |
||
| 316 | } |
||
| 317 | 1 | match_name = [ |
|
| 318 | '', |
||
| 319 | 'exact', |
||
| 320 | 'omission', |
||
| 321 | 'substitution', |
||
| 322 | 'transposition', |
||
| 323 | 'punctuation', |
||
| 324 | 'initials', |
||
| 325 | 'extension', |
||
| 326 | 'inclusion', |
||
| 327 | 'no_first', |
||
| 328 | 'word_approx', |
||
| 329 | 'confusions', |
||
| 330 | 'char_approx', |
||
| 331 | 'no_match', |
||
| 332 | ] |
||
| 333 | 1 | match_type_dict = {val: n for n, val in enumerate(match_name)} |
|
| 334 | |||
| 335 | 1 | if isinstance(tests, Iterable): |
|
| 336 | 1 | new_tests = 0 |
|
| 337 | 1 | for term in tests: |
|
| 338 | 1 | if term in test_dict: |
|
| 339 | 1 | new_tests += test_dict[term] |
|
| 340 | 1 | tests = new_tests |
|
| 341 | |||
| 342 | 1 | if isinstance(src, tuple): |
|
| 343 | 1 | src_ln, src_fn, src_qual = src |
|
| 344 | 1 | elif '#' in src: |
|
| 345 | 1 | src_ln, src_fn, src_qual = src.split('#')[-3:] |
|
| 346 | else: |
||
| 347 | 1 | src_ln, src_fn, src_qual = src, '', '' |
|
| 348 | |||
| 349 | 1 | if isinstance(tar, tuple): |
|
| 350 | 1 | tar_ln, tar_fn, tar_qual = tar |
|
| 351 | 1 | elif '#' in tar: |
|
| 352 | 1 | tar_ln, tar_fn, tar_qual = tar.split('#')[-3:] |
|
| 353 | else: |
||
| 354 | 1 | tar_ln, tar_fn, tar_qual = tar, '', '' |
|
| 355 | |||
| 356 | 1 | def _split_special(spec): |
|
| 357 | 1 | spec_list = [] |
|
| 358 | 1 | while spec: |
|
| 359 | 1 | spec_list.append((int(spec[:3]), spec[3:4])) |
|
| 360 | 1 | spec = spec[4:] |
|
| 361 | 1 | return spec_list |
|
| 362 | |||
| 363 | 1 | def _fmt_retval(val): |
|
| 364 | 1 | if ret_name: |
|
| 365 | 1 | return match_name[val] |
|
| 366 | 1 | return val |
|
| 367 | |||
| 368 | # 1. Preprocessing |
||
| 369 | |||
| 370 | # Lowercasing |
||
| 371 | 1 | src_fn = src_fn.strip().lower() |
|
| 372 | 1 | src_ln = src_ln.strip().lower() |
|
| 373 | 1 | src_qual = src_qual.strip().lower() |
|
| 374 | |||
| 375 | 1 | tar_fn = tar_fn.strip().lower() |
|
| 376 | 1 | tar_ln = tar_ln.strip().lower() |
|
| 377 | 1 | tar_qual = tar_qual.strip().lower() |
|
| 378 | |||
| 379 | # Create toolcodes |
||
| 380 | 1 | src_ln, src_fn, src_tc = synoname_toolcode(src_ln, src_fn, src_qual) |
|
| 381 | 1 | tar_ln, tar_fn, tar_tc = synoname_toolcode(tar_ln, tar_fn, tar_qual) |
|
| 382 | |||
| 383 | 1 | src_generation = int(src_tc[2]) |
|
| 384 | 1 | src_romancode = int(src_tc[3:6]) |
|
| 385 | 1 | src_len_fn = int(src_tc[6:8]) |
|
| 386 | 1 | src_tc = src_tc.split('$') |
|
| 387 | 1 | src_specials = _split_special(src_tc[1]) |
|
| 388 | |||
| 389 | 1 | tar_generation = int(tar_tc[2]) |
|
| 390 | 1 | tar_romancode = int(tar_tc[3:6]) |
|
| 391 | 1 | tar_len_fn = int(tar_tc[6:8]) |
|
| 392 | 1 | tar_tc = tar_tc.split('$') |
|
| 393 | 1 | tar_specials = _split_special(tar_tc[1]) |
|
| 394 | |||
| 395 | 1 | gen_conflict = (src_generation != tar_generation) and bool( |
|
| 396 | src_generation or tar_generation |
||
| 397 | ) |
||
| 398 | 1 | roman_conflict = (src_romancode != tar_romancode) and bool( |
|
| 399 | src_romancode or tar_romancode |
||
| 400 | ) |
||
| 401 | |||
| 402 | 1 | ln_equal = src_ln == tar_ln |
|
| 403 | 1 | fn_equal = src_fn == tar_fn |
|
| 404 | |||
| 405 | # approx_c |
||
| 406 | 1 | def _approx_c(): |
|
| 407 | 1 | if gen_conflict or roman_conflict: |
|
| 408 | 1 | return False, 0 |
|
| 409 | |||
| 410 | 1 | full_src = ' '.join((src_ln, src_fn)) |
|
| 411 | 1 | if full_src.startswith('master '): |
|
| 412 | 1 | full_src = full_src[len('master ') :] |
|
| 413 | 1 | for intro in [ |
|
| 414 | 'of the ', |
||
| 415 | 'of ', |
||
| 416 | 'known as the ', |
||
| 417 | 'with the ', |
||
| 418 | 'with ', |
||
| 419 | ]: |
||
| 420 | 1 | if full_src.startswith(intro): |
|
| 421 | 1 | full_src = full_src[len(intro) :] |
|
| 422 | |||
| 423 | 1 | full_tar = ' '.join((tar_ln, tar_fn)) |
|
| 424 | 1 | if full_tar.startswith('master '): |
|
| 425 | 1 | full_tar = full_tar[len('master ') :] |
|
| 426 | 1 | for intro in [ |
|
| 427 | 'of the ', |
||
| 428 | 'of ', |
||
| 429 | 'known as the ', |
||
| 430 | 'with the ', |
||
| 431 | 'with ', |
||
| 432 | ]: |
||
| 433 | 1 | if full_tar.startswith(intro): |
|
| 434 | 1 | full_tar = full_tar[len(intro) :] |
|
| 435 | |||
| 436 | 1 | loc_ratio = sim_ratcliff_obershelp(full_src, full_tar) |
|
| 437 | 1 | return loc_ratio >= char_approx_min, loc_ratio |
|
| 438 | |||
| 439 | 1 | approx_c_result, ca_ratio = _approx_c() |
|
| 440 | |||
| 441 | 1 | if tests & test_dict['exact'] and fn_equal and ln_equal: |
|
| 442 | 1 | return _fmt_retval(match_type_dict['exact']) |
|
| 443 | 1 | if tests & test_dict['omission']: |
|
| 444 | 1 | if fn_equal and levenshtein(src_ln, tar_ln, cost=(1, 1, 99, 99)) == 1: |
|
| 445 | 1 | if not roman_conflict: |
|
| 446 | 1 | return _fmt_retval(match_type_dict['omission']) |
|
| 447 | 1 | elif ( |
|
| 448 | ln_equal and levenshtein(src_fn, tar_fn, cost=(1, 1, 99, 99)) == 1 |
||
| 449 | ): |
||
| 450 | 1 | return _fmt_retval(match_type_dict['omission']) |
|
| 451 | 1 | if tests & test_dict['substitution']: |
|
| 452 | 1 | if fn_equal and levenshtein(src_ln, tar_ln, cost=(99, 99, 1, 99)) == 1: |
|
| 453 | 1 | return _fmt_retval(match_type_dict['substitution']) |
|
| 454 | 1 | elif ( |
|
| 455 | ln_equal and levenshtein(src_fn, tar_fn, cost=(99, 99, 1, 99)) == 1 |
||
| 456 | ): |
||
| 457 | 1 | return _fmt_retval(match_type_dict['substitution']) |
|
| 458 | 1 | if tests & test_dict['transposition']: |
|
| 459 | 1 | if fn_equal and ( |
|
| 460 | levenshtein(src_ln, tar_ln, mode='osa', cost=(99, 99, 99, 1)) == 1 |
||
| 461 | ): |
||
| 462 | 1 | return _fmt_retval(match_type_dict['transposition']) |
|
| 463 | 1 | elif ln_equal and ( |
|
| 464 | levenshtein(src_fn, tar_fn, mode='osa', cost=(99, 99, 99, 1)) == 1 |
||
| 465 | ): |
||
| 466 | 1 | return _fmt_retval(match_type_dict['transposition']) |
|
| 467 | 1 | if tests & test_dict['punctuation']: |
|
| 468 | 1 | np_src_fn = _synoname_strip_punct(src_fn) |
|
| 469 | 1 | np_tar_fn = _synoname_strip_punct(tar_fn) |
|
| 470 | 1 | np_src_ln = _synoname_strip_punct(src_ln) |
|
| 471 | 1 | np_tar_ln = _synoname_strip_punct(tar_ln) |
|
| 472 | |||
| 473 | 1 | if (np_src_fn == np_tar_fn) and (np_src_ln == np_tar_ln): |
|
| 474 | 1 | return _fmt_retval(match_type_dict['punctuation']) |
|
| 475 | |||
| 476 | 1 | np_src_fn = _synoname_strip_punct(src_fn.replace('-', ' ')) |
|
| 477 | 1 | np_tar_fn = _synoname_strip_punct(tar_fn.replace('-', ' ')) |
|
| 478 | 1 | np_src_ln = _synoname_strip_punct(src_ln.replace('-', ' ')) |
|
| 479 | 1 | np_tar_ln = _synoname_strip_punct(tar_ln.replace('-', ' ')) |
|
| 480 | |||
| 481 | 1 | if (np_src_fn == np_tar_fn) and (np_src_ln == np_tar_ln): |
|
| 482 | 1 | return _fmt_retval(match_type_dict['punctuation']) |
|
| 483 | |||
| 484 | 1 | if tests & test_dict['initials'] and ln_equal: |
|
| 485 | 1 | if src_fn and tar_fn: |
|
| 486 | 1 | src_initials = _synoname_strip_punct(src_fn).split() |
|
| 487 | 1 | tar_initials = _synoname_strip_punct(tar_fn).split() |
|
| 488 | 1 | initials = bool( |
|
| 489 | (len(src_initials) == len(''.join(src_initials))) |
||
| 490 | or (len(tar_initials) == len(''.join(tar_initials))) |
||
| 491 | ) |
||
| 492 | 1 | if initials: |
|
| 493 | 1 | src_initials = ''.join(_[0] for _ in src_initials) |
|
| 494 | 1 | tar_initials = ''.join(_[0] for _ in tar_initials) |
|
| 495 | 1 | if src_initials == tar_initials: |
|
| 496 | 1 | return _fmt_retval(match_type_dict['initials']) |
|
| 497 | 1 | initial_diff = abs(len(src_initials) - len(tar_initials)) |
|
| 498 | 1 | if initial_diff and ( |
|
| 499 | ( |
||
| 500 | initial_diff |
||
| 501 | == levenshtein( |
||
| 502 | src_initials, tar_initials, cost=(1, 99, 99, 99) |
||
| 503 | ) |
||
| 504 | ) |
||
| 505 | or ( |
||
| 506 | initial_diff |
||
| 507 | == levenshtein( |
||
| 508 | tar_initials, src_initials, cost=(1, 99, 99, 99) |
||
| 509 | ) |
||
| 510 | ) |
||
| 511 | ): |
||
| 512 | 1 | return _fmt_retval(match_type_dict['initials']) |
|
| 513 | 1 | if tests & test_dict['extension']: |
|
| 514 | 1 | if src_ln[1] == tar_ln[1] and ( |
|
| 515 | src_ln.startswith(tar_ln) or tar_ln.startswith(src_ln) |
||
| 516 | ): |
||
| 517 | 1 | if ( |
|
| 518 | (not src_len_fn and not tar_len_fn) |
||
| 519 | or (tar_fn and src_fn.startswith(tar_fn)) |
||
| 520 | or (src_fn and tar_fn.startswith(src_fn)) |
||
| 521 | ) and not roman_conflict: |
||
| 522 | 1 | return _fmt_retval(match_type_dict['extension']) |
|
| 523 | 1 | if tests & test_dict['inclusion'] and ln_equal: |
|
| 524 | 1 | if (src_fn and src_fn in tar_fn) or (tar_fn and tar_fn in src_ln): |
|
| 525 | 1 | return _fmt_retval(match_type_dict['inclusion']) |
|
| 526 | 1 | if tests & test_dict['no_first'] and ln_equal: |
|
| 527 | 1 | if src_fn == '' or tar_fn == '': |
|
| 528 | 1 | return _fmt_retval(match_type_dict['no_first']) |
|
| 529 | 1 | if tests & test_dict['word_approx']: |
|
| 530 | 1 | ratio = _synoname_word_approximation( |
|
| 531 | src_ln, |
||
| 532 | tar_ln, |
||
| 533 | src_fn, |
||
| 534 | tar_fn, |
||
| 535 | { |
||
| 536 | 'gen_conflict': gen_conflict, |
||
| 537 | 'roman_conflict': roman_conflict, |
||
| 538 | 'src_specials': src_specials, |
||
| 539 | 'tar_specials': tar_specials, |
||
| 540 | }, |
||
| 541 | ) |
||
| 542 | 1 | if ratio == 1 and tests & test_dict['confusions']: |
|
| 543 | 1 | if ( |
|
| 544 | ' '.join((src_fn, src_ln)).strip() |
||
| 545 | == ' '.join((tar_fn, tar_ln)).strip() |
||
| 546 | ): |
||
| 547 | 1 | return _fmt_retval(match_type_dict['confusions']) |
|
| 548 | 1 | if ratio >= word_approx_min: |
|
| 549 | 1 | return _fmt_retval(match_type_dict['word_approx']) |
|
| 550 | 1 | if tests & test_dict['char_approx']: |
|
| 551 | 1 | if ca_ratio >= char_approx_min: |
|
| 552 | 1 | return _fmt_retval(match_type_dict['char_approx']) |
|
| 553 | 1 | return _fmt_retval(match_type_dict['no_match']) |
|
| 554 | |||
| 560 |
Loading history...