1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657
|
# -*- coding: utf-8 -*-
import io
import sys
import unittest
from contextlib import contextmanager
from slugify import PRE_TRANSLATIONS
from slugify import slugify
from slugify import smart_truncate
from slugify.__main__ import slugify_params, parse_args
class TestSlugify(unittest.TestCase):
def test_extraneous_seperators(self):
txt = "This is a test ---"
r = slugify(txt)
self.assertEqual(r, "this-is-a-test")
txt = "___This is a test ---"
r = slugify(txt)
self.assertEqual(r, "this-is-a-test")
txt = "___This is a test___"
r = slugify(txt)
self.assertEqual(r, "this-is-a-test")
def test_non_word_characters(self):
txt = "This -- is a ## test ---"
r = slugify(txt)
self.assertEqual(r, "this-is-a-test")
def test_phonetic_conversion_of_eastern_scripts(self):
txt = '影師嗎'
r = slugify(txt)
self.assertEqual(r, "ying-shi-ma")
def test_accented_text(self):
txt = '𝐚́́𝕒́àáâäãąā'
r = slugify(txt)
self.assertEqual(r, "aaaaaaaaa")
txt = 'C\'est déjà l\'été.'
r = slugify(txt)
self.assertEqual(r, "c-est-deja-l-ete")
txt = 'Nín hǎo. Wǒ shì zhōng guó rén'
r = slugify(txt)
self.assertEqual(r, "nin-hao-wo-shi-zhong-guo-ren")
def test_accented_text_with_non_word_characters(self):
txt = 'jaja---lol-méméméoo--a'
r = slugify(txt)
self.assertEqual(r, "jaja-lol-mememeoo-a")
def test_cyrillic_text(self):
txt = 'Компьютер'
r = slugify(txt)
self.assertEqual(r, "kompiuter")
def test_max_length(self):
txt = 'jaja---lol-méméméoo--a'
r = slugify(txt, max_length=9)
self.assertEqual(r, "jaja-lol")
txt = 'jaja---lol-méméméoo--a'
r = slugify(txt, max_length=15)
self.assertEqual(r, "jaja-lol-mememe")
def test_max_length_cutoff_not_required(self):
txt = 'jaja---lol-méméméoo--a'
r = slugify(txt, max_length=50)
self.assertEqual(r, "jaja-lol-mememeoo-a")
def test_word_boundary(self):
txt = 'jaja---lol-méméméoo--a'
r = slugify(txt, max_length=15, word_boundary=True)
self.assertEqual(r, "jaja-lol-a")
txt = 'jaja---lol-méméméoo--a'
r = slugify(txt, max_length=17, word_boundary=True)
self.assertEqual(r, "jaja-lol-mememeoo")
txt = 'jaja---lol-méméméoo--a'
r = slugify(txt, max_length=18, word_boundary=True)
self.assertEqual(r, "jaja-lol-mememeoo")
txt = 'jaja---lol-méméméoo--a'
r = slugify(txt, max_length=19, word_boundary=True)
self.assertEqual(r, "jaja-lol-mememeoo-a")
def test_custom_separator(self):
txt = 'jaja---lol-méméméoo--a'
r = slugify(txt, max_length=20, word_boundary=True, separator=".")
self.assertEqual(r, "jaja.lol.mememeoo.a")
def test_multi_character_separator(self):
txt = 'jaja---lol-méméméoo--a'
r = slugify(txt, max_length=20, word_boundary=True, separator="ZZZZZZ")
self.assertEqual(r, "jajaZZZZZZlolZZZZZZmememeooZZZZZZa")
def test_save_order(self):
txt = 'one two three four five'
r = slugify(txt, max_length=13, word_boundary=True, save_order=True)
self.assertEqual(r, "one-two-three")
txt = 'one two three four five'
r = slugify(txt, max_length=13, word_boundary=True, save_order=False)
self.assertEqual(r, "one-two-three")
txt = 'one two three four five'
r = slugify(txt, max_length=12, word_boundary=True, save_order=False)
self.assertEqual(r, "one-two-four")
txt = 'one two three four five'
r = slugify(txt, max_length=12, word_boundary=True, save_order=True)
self.assertEqual(r, "one-two")
def test_stopword_removal(self):
txt = 'this has a stopword'
r = slugify(txt, stopwords=['stopword'])
self.assertEqual(r, 'this-has-a')
def test_stopword_removal_casesensitive(self):
txt = 'thIs Has a stopword Stopword'
r = slugify(txt, stopwords=['Stopword'], lowercase=False)
self.assertEqual(r, 'thIs-Has-a-stopword')
def test_multiple_stopword_occurances(self):
txt = 'the quick brown fox jumps over the lazy dog'
r = slugify(txt, stopwords=['the'])
self.assertEqual(r, 'quick-brown-fox-jumps-over-lazy-dog')
def test_differently_cased_stopword_match(self):
txt = 'Foo A FOO B foo C'
r = slugify(txt, stopwords=['foo'])
self.assertEqual(r, 'a-b-c')
txt = 'Foo A FOO B foo C'
r = slugify(txt, stopwords=['FOO'])
self.assertEqual(r, 'a-b-c')
def test_multiple_stopwords(self):
txt = 'the quick brown fox jumps over the lazy dog in a hurry'
r = slugify(txt, stopwords=['the', 'in', 'a', 'hurry'])
self.assertEqual(r, 'quick-brown-fox-jumps-over-lazy-dog')
def test_stopwords_with_different_separator(self):
txt = 'the quick brown fox jumps over the lazy dog'
r = slugify(txt, stopwords=['the'], separator=' ')
self.assertEqual(r, 'quick brown fox jumps over lazy dog')
def test_html_entities_on(self):
txt = 'foo & bar'
r = slugify(txt)
self.assertEqual(r, 'foo-bar')
def test_html_entities_off(self):
txt = 'foo & bar'
r = slugify(txt, entities=False)
self.assertEqual(r, 'foo-amp-bar')
def test_html_decimal_on(self):
txt = 'Ž'
r = slugify(txt, decimal=True)
self.assertEqual(r, 'z')
def test_html_decimal_off(self):
txt = 'Ž'
r = slugify(txt, entities=False, decimal=False)
self.assertEqual(r, '381')
def test_html_hexadecimal_on(self):
txt = 'Ž'
r = slugify(txt, hexadecimal=True)
self.assertEqual(r, 'z')
def test_html_hexadecimal_off(self):
txt = 'Ž'
r = slugify(txt, hexadecimal=False)
self.assertEqual(r, 'x17d')
def test_starts_with_number(self):
txt = '10 amazing secrets'
r = slugify(txt)
self.assertEqual(r, '10-amazing-secrets')
def test_contains_numbers(self):
txt = 'buildings with 1000 windows'
r = slugify(txt)
self.assertEqual(r, 'buildings-with-1000-windows')
def test_ends_with_number(self):
txt = 'recipe number 3'
r = slugify(txt)
self.assertEqual(r, 'recipe-number-3')
def test_numbers_only(self):
txt = '404'
r = slugify(txt)
self.assertEqual(r, '404')
def test_numbers_and_symbols(self):
txt = '1,000 reasons you are #1'
r = slugify(txt)
self.assertEqual(r, '1000-reasons-you-are-1')
def test_regex_pattern_keep_underscore(self):
txt = "___This is a test___"
regex_pattern = r'[^-a-z0-9_]+'
r = slugify(txt, regex_pattern=regex_pattern)
self.assertEqual(r, "___this-is-a-test___")
def test_regex_pattern_keep_underscore_with_underscore_as_separator(self):
"""
The regex_pattern turns the power to the caller.
Hence the caller must ensure that a custom separator doesn't clash
with the regex_pattern.
"""
txt = "___This is a test___"
regex_pattern = r'[^-a-z0-9_]+'
r = slugify(txt, separator='_', regex_pattern=regex_pattern)
self.assertNotEqual(r, "_this_is_a_test_")
def test_replacements(self):
txt = '10 | 20 %'
r = slugify(txt, replacements=[['|', 'or'], ['%', 'percent']])
self.assertEqual(r, "10-or-20-percent")
txt = 'I ♥ 🦄'
r = slugify(txt, replacements=[['♥', 'amour'], ['🦄', 'licorne']])
self.assertEqual(r, "i-amour-licorne")
def test_replacements_german_umlaut_custom(self):
txt = 'ÜBER Über German Umlaut'
r = slugify(txt, replacements=[['Ü', 'UE'], ['ü', 'ue']])
self.assertEqual(r, "ueber-ueber-german-umlaut")
def test_pre_translation(self):
self.assertEqual(PRE_TRANSLATIONS, [('Ю', 'U'), ('Щ', 'Sch'), ('У', 'Y'), ('Х', 'H'), ('Я', 'Ya'), ('Ё', 'E'), ('ё', 'e'), ('я', 'ya'), ('х', 'h'), ('у', 'y'), ('щ', 'sch'), ('ю', 'u'), ('Ü', 'Ue'), ('Ö', 'Oe'), ('Ä', 'Ae'), ('ä', 'ae'), ('ö', 'oe'), ('ü', 'ue'), ('Ϋ́', 'Y'), ('Ϋ', 'Y'), ('Ύ', 'Y'), ('Υ', 'Y'), ('Χ', 'Ch'), ('χ', 'ch'), ('Ξ', 'X'), ('ϒ', 'Y'), ('υ', 'y'), ('ύ', 'y'), ('ϋ', 'y'), ('ΰ', 'y')])
class TestSlugifyUnicode(unittest.TestCase):
def test_extraneous_seperators(self):
txt = "This is a test ---"
r = slugify(txt, allow_unicode=True)
self.assertEqual(r, "this-is-a-test")
txt = "___This is a test ---"
r = slugify(txt, allow_unicode=True)
self.assertEqual(r, "this-is-a-test")
txt = "___This is a test___"
r = slugify(txt, allow_unicode=True)
self.assertEqual(r, "this-is-a-test")
def test_non_word_characters(self):
txt = "This -- is a ## test ---"
r = slugify(txt, allow_unicode=True)
self.assertEqual(r, "this-is-a-test")
def test_phonetic_conversion_of_eastern_scripts(self):
txt = '影師嗎'
r = slugify(txt, allow_unicode=True)
self.assertEqual(r, txt)
def test_accented_text(self):
txt = 'C\'est déjà l\'été.'
r = slugify(txt, allow_unicode=True)
self.assertEqual(r, "c-est-déjà-l-été")
txt = 'Nín hǎo. Wǒ shì zhōng guó rén'
r = slugify(txt, allow_unicode=True)
self.assertEqual(r, "nín-hǎo-wǒ-shì-zhōng-guó-rén")
def test_accented_text_with_non_word_characters(self):
txt = 'jaja---lol-méméméoo--a'
r = slugify(txt, allow_unicode=True)
self.assertEqual(r, "jaja-lol-méméméoo-a")
def test_cyrillic_text(self):
txt = 'Компьютер'
r = slugify(txt, allow_unicode=True)
self.assertEqual(r, "компьютер")
def test_max_length(self):
txt = 'jaja---lol-méméméoo--a'
r = slugify(txt, allow_unicode=True, max_length=9)
self.assertEqual(r, "jaja-lol")
txt = 'jaja---lol-méméméoo--a'
r = slugify(txt, allow_unicode=True, max_length=15)
self.assertEqual(r, "jaja-lol-mémémé")
def test_max_length_cutoff_not_required(self):
txt = 'jaja---lol-méméméoo--a'
r = slugify(txt, allow_unicode=True, max_length=50)
self.assertEqual(r, "jaja-lol-méméméoo-a")
def test_word_boundary(self):
txt = 'jaja---lol-méméméoo--a'
r = slugify(txt, allow_unicode=True, max_length=15, word_boundary=True)
self.assertEqual(r, "jaja-lol-a")
txt = 'jaja---lol-méméméoo--a'
r = slugify(txt, allow_unicode=True, max_length=17, word_boundary=True)
self.assertEqual(r, "jaja-lol-méméméoo")
txt = 'jaja---lol-méméméoo--a'
r = slugify(txt, allow_unicode=True, max_length=18, word_boundary=True)
self.assertEqual(r, "jaja-lol-méméméoo")
txt = 'jaja---lol-méméméoo--a'
r = slugify(txt, allow_unicode=True, max_length=19, word_boundary=True)
self.assertEqual(r, "jaja-lol-méméméoo-a")
def test_custom_separator(self):
txt = 'jaja---lol-méméméoo--a'
r = slugify(txt, allow_unicode=True, max_length=20, word_boundary=True, separator=".")
self.assertEqual(r, "jaja.lol.méméméoo.a")
def test_multi_character_separator(self):
txt = 'jaja---lol-méméméoo--a'
r = slugify(txt, allow_unicode=True, max_length=20, word_boundary=True, separator="ZZZZZZ")
self.assertEqual(r, "jajaZZZZZZlolZZZZZZméméméooZZZZZZa")
def test_save_order(self):
txt = 'one two three four five'
r = slugify(txt, allow_unicode=True, max_length=13, word_boundary=True, save_order=True)
self.assertEqual(r, "one-two-three")
txt = 'one two three four five'
r = slugify(txt, allow_unicode=True, max_length=13, word_boundary=True, save_order=False)
self.assertEqual(r, "one-two-three")
txt = 'one two three four five'
r = slugify(txt, allow_unicode=True, max_length=12, word_boundary=True, save_order=False)
self.assertEqual(r, "one-two-four")
txt = 'one two three four five'
r = slugify(txt, allow_unicode=True, max_length=12, word_boundary=True, save_order=True)
self.assertEqual(r, "one-two")
def test_save_order_rtl(self):
"""For right-to-left unicode languages"""
txt = 'دو سه چهار پنج'
r = slugify(txt, allow_unicode=True, max_length=10, word_boundary=True, save_order=True)
self.assertEqual(r, "دو-سه-چهار")
txt = 'دو سه چهار پنج'
r = slugify(txt, allow_unicode=True, max_length=10, word_boundary=True, save_order=False)
self.assertEqual(r, "دو-سه-چهار")
txt = 'دو سه چهار پنج'
r = slugify(txt, allow_unicode=True, max_length=9, word_boundary=True, save_order=False)
self.assertEqual(r, "دو-سه-پنج")
txt = 'دو سه چهار پنج'
r = slugify(txt, allow_unicode=True, max_length=9, word_boundary=True, save_order=True)
self.assertEqual(r, "دو-سه")
def test_stopword_removal(self):
txt = 'this has a stopword'
r = slugify(txt, allow_unicode=True, stopwords=['stopword'])
self.assertEqual(r, 'this-has-a')
txt = 'this has a Öländ'
r = slugify(txt, allow_unicode=True, stopwords=['Öländ'])
self.assertEqual(r, 'this-has-a')
def test_stopword_removal_casesensitive(self):
txt = 'thIs Has a stopword Stopword'
r = slugify(txt, allow_unicode=True, stopwords=['Stopword'], lowercase=False)
self.assertEqual(r, 'thIs-Has-a-stopword')
txt = 'thIs Has a öländ Öländ'
r = slugify(txt, allow_unicode=True, stopwords=['Öländ'], lowercase=False)
self.assertEqual(r, 'thIs-Has-a-öländ')
def test_multiple_stopword_occurances(self):
txt = 'the quick brown fox jumps over the lazy dog'
r = slugify(txt, allow_unicode=True, stopwords=['the'])
self.assertEqual(r, 'quick-brown-fox-jumps-over-lazy-dog')
def test_differently_cased_stopword_match(self):
txt = 'Foo A FOO B foo C'
r = slugify(txt, allow_unicode=True, stopwords=['foo'])
self.assertEqual(r, 'a-b-c')
txt = 'Foo A FOO B foo C'
r = slugify(txt, allow_unicode=True, stopwords=['FOO'])
self.assertEqual(r, 'a-b-c')
def test_multiple_stopwords(self):
txt = 'the quick brown fox jumps over the lazy dog in a hurry'
r = slugify(txt, allow_unicode=True, stopwords=['the', 'in', 'a', 'hurry'])
self.assertEqual(r, 'quick-brown-fox-jumps-over-lazy-dog')
def test_stopwords_with_different_separator(self):
txt = 'the quick brown fox jumps over the lazy dog'
r = slugify(txt, allow_unicode=True, stopwords=['the'], separator=' ')
self.assertEqual(r, 'quick brown fox jumps over lazy dog')
def test_html_entities_on(self):
txt = 'foo & bar'
r = slugify(txt, allow_unicode=True)
self.assertEqual(r, 'foo-bar')
def test_html_entities_off(self):
txt = 'foo & bår'
r = slugify(txt, allow_unicode=True, entities=False)
self.assertEqual(r, 'foo-amp-bår')
def test_html_decimal_on(self):
txt = 'Ž'
r = slugify(txt, allow_unicode=True, decimal=True)
self.assertEqual(r, 'ž')
def test_html_decimal_off(self):
txt = 'Ž'
r = slugify(txt, allow_unicode=True, entities=False, decimal=False)
self.assertEqual(r, '381')
def test_html_hexadecimal_on(self):
txt = 'Ž'
r = slugify(txt, allow_unicode=True, hexadecimal=True)
self.assertEqual(r, 'ž')
def test_html_hexadecimal_off(self):
txt = 'Ž'
r = slugify(txt, allow_unicode=True, hexadecimal=False)
self.assertEqual(r, 'x17d')
def test_starts_with_number(self):
txt = '10 amazing secrets'
r = slugify(txt, allow_unicode=True)
self.assertEqual(r, '10-amazing-secrets')
def test_contains_numbers(self):
txt = 'buildings with 1000 windows'
r = slugify(txt, allow_unicode=True)
self.assertEqual(r, 'buildings-with-1000-windows')
def test_ends_with_number(self):
txt = 'recipe number 3'
r = slugify(txt, allow_unicode=True)
self.assertEqual(r, 'recipe-number-3')
def test_numbers_only(self):
txt = '404'
r = slugify(txt, allow_unicode=True)
self.assertEqual(r, '404')
def test_numbers_and_symbols(self):
txt = '1,000 reasons you are #1'
r = slugify(txt, allow_unicode=True)
self.assertEqual(r, '1000-reasons-you-are-1')
txt = '۱,۰۰۰ reasons you are #۱'
r = slugify(txt, allow_unicode=True)
self.assertEqual(r, '۱۰۰۰-reasons-you-are-۱')
def test_regex_pattern_keep_underscore(self):
"""allowing unicode should not overrule the passed regex_pattern"""
txt = "___This is a test___"
regex_pattern = r'[^-a-z0-9_]+'
r = slugify(txt, allow_unicode=True, regex_pattern=regex_pattern)
self.assertEqual(r, "___this-is-a-test___")
def test_regex_pattern_keep_underscore_with_underscore_as_separator(self):
"""
The regex_pattern turns the power to the caller.
Hence, the caller must ensure that a custom separator doesn't clash
with the regex_pattern.
"""
txt = "___This is a test___"
regex_pattern = r'[^-a-z0-9_]+'
r = slugify(txt, allow_unicode=True, separator='_', regex_pattern=regex_pattern)
self.assertNotEqual(r, "_this_is_a_test_")
def test_replacements(self):
txt = '10 | 20 %'
r = slugify(txt, allow_unicode=True, replacements=[['|', 'or'], ['%', 'percent']])
self.assertEqual(r, "10-or-20-percent")
txt = 'I ♥ 🦄'
r = slugify(txt, allow_unicode=True, replacements=[['♥', 'amour'], ['🦄', 'licorne']])
self.assertEqual(r, "i-amour-licorne")
txt = 'I ♥ 🦄'
r = slugify(txt, allow_unicode=True, replacements=[['♥', 'სიყვარული'], ['🦄', 'licorne']])
self.assertEqual(r, "i-სიყვარული-licorne")
def test_replacements_german_umlaut_custom(self):
txt = 'ÜBER Über German Umlaut'
r = slugify(txt, allow_unicode=True, replacements=[['Ü', 'UE'], ['ü', 'ue']])
self.assertEqual(r, "ueber-ueber-german-umlaut")
def test_emojis(self):
"""
allowing unicode shouldn't allow emojis, even in replacements.
the only exception is when it is allowed by the regex_pattern. regex_pattern overrules all
"""
txt = 'i love 🦄'
r = slugify(txt, allow_unicode=True)
self.assertEqual(r, "i-love")
txt = 'i love 🦄'
r = slugify(txt, allow_unicode=True, decimal=True)
self.assertEqual(r, "i-love")
txt = 'i love 🦄'
r = slugify(txt, allow_unicode=True, hexadecimal=True)
self.assertEqual(r, "i-love")
txt = 'i love 🦄'
r = slugify(txt, allow_unicode=True, entities=True)
self.assertEqual(r, "i-love")
txt = 'i love you'
r = slugify(txt, allow_unicode=True, replacements=[['you', '🦄']])
self.assertEqual(r, "i-love")
txt = 'i love 🦄'
r = slugify(txt, allow_unicode=True, regex_pattern=r'[^🦄]+')
self.assertEqual(r, "🦄")
class TestUtils(unittest.TestCase):
def test_smart_truncate_no_max_length(self):
txt = '1,000 reasons you are #1'
r = smart_truncate(txt)
self.assertEqual(r, txt)
def test_smart_truncate_no_seperator(self):
txt = '1,000 reasons you are #1'
r = smart_truncate(txt, max_length=100, separator='_')
self.assertEqual(r, txt)
PY3 = sys.version_info.major == 3
@contextmanager
def captured_stderr():
backup = sys.stderr
sys.stderr = io.StringIO() if PY3 else io.BytesIO()
try:
yield sys.stderr
finally:
sys.stderr = backup
@contextmanager
def loaded_stdin(contents):
backup = sys.stdin
sys.stdin = io.StringIO(contents) if PY3 else io.BytesIO(contents)
try:
yield sys.stdin
finally:
sys.stdin = backup
class TestCommandParams(unittest.TestCase):
DEFAULTS = {
'entities': True,
'decimal': True,
'hexadecimal': True,
'max_length': 0,
'word_boundary': False,
'save_order': False,
'separator': '-',
'stopwords': None,
'lowercase': True,
'replacements': None
}
def get_params_from_cli(self, *argv):
args = parse_args([None] + list(argv))
return slugify_params(args)
def make_params(self, **values):
return dict(self.DEFAULTS, **values)
def assertParamsMatch(self, expected, checked):
reduced_checked = {}
for key in expected.keys():
reduced_checked[key] = checked[key]
self.assertEqual(expected, reduced_checked)
def test_defaults(self):
params = self.get_params_from_cli()
self.assertParamsMatch(self.DEFAULTS, params)
def test_negative_flags(self):
params = self.get_params_from_cli('--no-entities', '--no-decimal', '--no-hexadecimal', '--no-lowercase')
expected = self.make_params(entities=False, decimal=False, hexadecimal=False, lowercase=False)
self.assertFalse(expected['lowercase'])
self.assertFalse(expected['word_boundary'])
self.assertParamsMatch(expected, params)
def test_affirmative_flags(self):
params = self.get_params_from_cli('--word-boundary', '--save-order')
expected = self.make_params(word_boundary=True, save_order=True)
self.assertParamsMatch(expected, params)
def test_valued_arguments(self):
params = self.get_params_from_cli('--stopwords', 'abba', 'beatles', '--max-length', '98', '--separator', '+')
expected = self.make_params(stopwords=['abba', 'beatles'], max_length=98, separator='+')
self.assertParamsMatch(expected, params)
def test_replacements_right(self):
params = self.get_params_from_cli('--replacements', 'A->B', 'C->D')
expected = self.make_params(replacements=[['A', 'B'], ['C', 'D']])
self.assertParamsMatch(expected, params)
def test_replacements_wrong(self):
with self.assertRaises(SystemExit) as err, captured_stderr() as cse:
self.get_params_from_cli('--replacements', 'A--B')
self.assertEqual(err.exception.code, 2)
self.assertIn("Replacements must be of the form: ORIGINAL->REPLACED", cse.getvalue())
def test_text_in_cli(self):
params = self.get_params_from_cli('Cool Text')
expected = self.make_params(text='Cool Text')
self.assertParamsMatch(expected, params)
def test_text_in_cli_multi(self):
params = self.get_params_from_cli('Cool', 'Text')
expected = self.make_params(text='Cool Text')
self.assertParamsMatch(expected, params)
def test_text_in_stdin(self):
with loaded_stdin("Cool Stdin"):
params = self.get_params_from_cli('--stdin')
expected = self.make_params(text='Cool Stdin')
self.assertParamsMatch(expected, params)
def test_two_text_sources_fails(self):
with self.assertRaises(SystemExit) as err, captured_stderr() as cse:
self.get_params_from_cli('--stdin', 'Text')
self.assertEqual(err.exception.code, 2)
self.assertIn("Input strings and --stdin cannot work together", cse.getvalue())
def test_multivalued_options_with_text(self):
text = "the quick brown fox jumps over the lazy dog in a hurry"
cli_args = "--stopwords the in a hurry -- {}".format(text).split()
params = self.get_params_from_cli(*cli_args)
self.assertEqual(params['text'], text)
self.assertEqual(params['stopwords'], ['the', 'in', 'a', 'hurry'])
if __name__ == '__main__':
unittest.main()
|