urdu-text-utils 0.1.3 → 0.1.5
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +11 -0
- package/README.md +27 -5
- package/dist/index.cjs +519 -6
- package/dist/index.cjs.map +1 -1
- package/dist/index.d.cts +64 -4
- package/dist/index.d.ts +64 -4
- package/dist/index.js +516 -7
- package/dist/index.js.map +1 -1
- package/package.json +31 -6
package/dist/index.js
CHANGED
|
@@ -298,12 +298,51 @@ function splitWords(input) {
|
|
|
298
298
|
if (!input) return [];
|
|
299
299
|
return input.split(WORD_SPLIT_RE).map((w) => w.trim()).filter((w) => w.length > 0);
|
|
300
300
|
}
|
|
301
|
-
|
|
302
|
-
|
|
301
|
+
var ABBREVIATIONS = [
|
|
302
|
+
"\u0688\u0627\u06A9\u0679\u0631",
|
|
303
|
+
"\u067E\u0631\u0648\u0641\u06CC\u0633\u0631",
|
|
304
|
+
"\u0627\u0646\u062C\u06CC\u0646\u0626\u0631",
|
|
305
|
+
"\u0627\u06CC\u0688\u0648\u0648\u06A9\u06CC\u0679",
|
|
306
|
+
"\u062C\u0646\u0627\u0628",
|
|
307
|
+
"\u0635\u0627\u062D\u0628",
|
|
308
|
+
"\u0635\u0627\u062D\u0628\u06C1",
|
|
309
|
+
"\u0645\u062D\u062A\u0631\u0645",
|
|
310
|
+
"\u0645\u062D\u062A\u0631\u0645\u06C1",
|
|
311
|
+
"\u0645\u0648\u0644\u0627\u0646\u0627",
|
|
312
|
+
"\u0645\u0641\u062A\u06CC",
|
|
313
|
+
"\u0639\u0644\u0627\u0645\u06C1",
|
|
314
|
+
"\u0628\u06CC\u06AF\u0645",
|
|
315
|
+
"\u0648\u063A\u06CC\u0631\u06C1",
|
|
316
|
+
"\u0631\u062D\u0645\u062A\u06C1",
|
|
317
|
+
"\u0631\u0636\u06CC",
|
|
318
|
+
"\u062A\u0639\u0627\u0644\u06CC",
|
|
319
|
+
"\u062A\u0639\u0627\u0644\u06CC\u0670",
|
|
320
|
+
"\u0639\u0644\u06CC\u06C1",
|
|
321
|
+
"\u0627\u0644\u0633\u0644\u0627\u0645",
|
|
322
|
+
"\u0635\u0644\u06CC",
|
|
323
|
+
"\u0648\u0633\u0644\u0645"
|
|
324
|
+
];
|
|
325
|
+
var ABBREV_PATTERN = new RegExp(`(?:${ABBREVIATIONS.join("|")})[.\u06D4]`, "gu");
|
|
326
|
+
function countSentences(input, options) {
|
|
327
|
+
return splitSentences(input, options).length;
|
|
303
328
|
}
|
|
304
|
-
function splitSentences(input) {
|
|
329
|
+
function splitSentences(input, options = {}) {
|
|
305
330
|
if (!input) return [];
|
|
306
|
-
|
|
331
|
+
const { preserveTerminators = false } = options;
|
|
332
|
+
const PROTECTED_DOT = "\uE000";
|
|
333
|
+
const PROTECTED_URDU_FULL_STOP = "\uE001";
|
|
334
|
+
let sanitized = input.replace(/(\d)\.(\d)/gu, `$1${PROTECTED_DOT}$2`).replace(ABBREV_PATTERN, (match) => {
|
|
335
|
+
return match.replace(/\./g, PROTECTED_DOT).replace(/۔/g, PROTECTED_URDU_FULL_STOP);
|
|
336
|
+
});
|
|
337
|
+
if (preserveTerminators) {
|
|
338
|
+
const matches = sanitized.match(/[^۔؟?!.…]+[۔؟?!.…]+|[^۔؟?!.…]+$/gu) ?? [];
|
|
339
|
+
return matches.map(
|
|
340
|
+
(s) => s.replace(new RegExp(PROTECTED_DOT, "gu"), ".").replace(new RegExp(PROTECTED_URDU_FULL_STOP, "gu"), "\u06D4").trim()
|
|
341
|
+
).filter((s) => s.length > 0);
|
|
342
|
+
}
|
|
343
|
+
return sanitized.split(SENTENCE_SPLIT_RE).map(
|
|
344
|
+
(s) => s.replace(new RegExp(PROTECTED_DOT, "gu"), ".").replace(new RegExp(PROTECTED_URDU_FULL_STOP, "gu"), "\u06D4").trim()
|
|
345
|
+
).filter((s) => s.length > 0);
|
|
307
346
|
}
|
|
308
347
|
function analyzeUrdu(input) {
|
|
309
348
|
const text = input ?? "";
|
|
@@ -326,6 +365,264 @@ function analyzeUrdu(input) {
|
|
|
326
365
|
};
|
|
327
366
|
}
|
|
328
367
|
|
|
368
|
+
// src/stopwords.ts
|
|
369
|
+
var URDU_STOP_WORDS = /* @__PURE__ */ new Set([
|
|
370
|
+
// Tense auxiliaries & copulas
|
|
371
|
+
"\u06C1\u06D2",
|
|
372
|
+
"\u06C1\u06CC\u06BA",
|
|
373
|
+
"\u06C1\u0648\u06BA",
|
|
374
|
+
"\u06C1\u0648",
|
|
375
|
+
"\u062A\u06BE\u0627",
|
|
376
|
+
"\u062A\u06BE\u06CC",
|
|
377
|
+
"\u062A\u06BE\u06D2",
|
|
378
|
+
"\u062A\u06BE\u06CC\u06BA",
|
|
379
|
+
"\u06C1\u0648\u06AF\u0627",
|
|
380
|
+
"\u06C1\u0648\u06AF\u06CC",
|
|
381
|
+
"\u06C1\u0648\u0646\u06AF\u06D2",
|
|
382
|
+
"\u06C1\u0648\u06BA\u06AF\u06D2",
|
|
383
|
+
"\u06C1\u0648\u0646\u0627",
|
|
384
|
+
"\u06C1\u0648\u0646\u06D2",
|
|
385
|
+
"\u06C1\u0648\u0627",
|
|
386
|
+
"\u06C1\u0648\u0626\u06CC",
|
|
387
|
+
"\u06C1\u0648\u0626\u06D2",
|
|
388
|
+
// Postpositions, relations & prepositions
|
|
389
|
+
"\u06A9\u0627",
|
|
390
|
+
"\u06A9\u06CC",
|
|
391
|
+
"\u06A9\u06D2",
|
|
392
|
+
"\u06A9\u0648",
|
|
393
|
+
"\u0646\u06D2",
|
|
394
|
+
"\u0633\u06D2",
|
|
395
|
+
"\u067E\u0631",
|
|
396
|
+
"\u062A\u06A9",
|
|
397
|
+
"\u0645\u06CC\u06BA",
|
|
398
|
+
"\u0644\u06CC\u06D2",
|
|
399
|
+
"\u0633\u0627\u062A\u06BE",
|
|
400
|
+
"\u0628\u063A\u06CC\u0631",
|
|
401
|
+
"\u0637\u0631\u062D",
|
|
402
|
+
"\u0637\u0631\u0641",
|
|
403
|
+
"\u0628\u0627\u0631\u06D2",
|
|
404
|
+
"\u0628\u0639\u062F",
|
|
405
|
+
"\u067E\u06C1\u0644\u06D2",
|
|
406
|
+
"\u062F\u0648\u0631\u0627\u0646",
|
|
407
|
+
"\u062F\u0631\u0645\u06CC\u0627\u0646",
|
|
408
|
+
"\u0639\u0644\u0627\u0648\u06C1",
|
|
409
|
+
"\u0633\u0648\u0627\u0626\u06D2",
|
|
410
|
+
"\u0633\u0648\u0627",
|
|
411
|
+
"\u0645\u0637\u0627\u0628\u0642",
|
|
412
|
+
"\u0628\u0627\u0639\u062B",
|
|
413
|
+
"\u0630\u0631\u06CC\u0639\u06D2",
|
|
414
|
+
"\u062A\u062D\u062A",
|
|
415
|
+
"\u0627\u0648\u067E\u0631",
|
|
416
|
+
"\u0646\u06CC\u0686\u06D2",
|
|
417
|
+
"\u0622\u06AF\u06D2",
|
|
418
|
+
"\u067E\u06CC\u0686\u06BE\u06D2",
|
|
419
|
+
"\u0627\u0646\u062F\u0631",
|
|
420
|
+
"\u0628\u0627\u06C1\u0631",
|
|
421
|
+
"\u067E\u0627\u0633",
|
|
422
|
+
"\u0642\u0631\u06CC\u0628",
|
|
423
|
+
"\u0646\u0632\u062F\u06CC\u06A9",
|
|
424
|
+
// Conjunctions & discourse markers
|
|
425
|
+
"\u0627\u0648\u0631",
|
|
426
|
+
"\u06CC\u0627",
|
|
427
|
+
"\u0627\u06AF\u0631",
|
|
428
|
+
"\u0644\u06CC\u06A9\u0646",
|
|
429
|
+
"\u0645\u06AF\u0631",
|
|
430
|
+
"\u062A\u0648",
|
|
431
|
+
"\u0628\u06BE\u06CC",
|
|
432
|
+
"\u06C1\u06CC",
|
|
433
|
+
"\u0646\u06C1",
|
|
434
|
+
"\u0646\u06C1\u06CC\u06BA",
|
|
435
|
+
"\u0645\u062A",
|
|
436
|
+
"\u0646\u0627",
|
|
437
|
+
"\u0628\u0644\u06A9\u06C1",
|
|
438
|
+
"\u062D\u0627\u0644\u0627\u0646\u06A9\u06C1",
|
|
439
|
+
"\u0686\u0648\u0646\u06A9\u06C1",
|
|
440
|
+
"\u06A9\u06CC\u0648\u0646\u06A9\u06C1",
|
|
441
|
+
"\u062A\u0627\u06A9\u06C1",
|
|
442
|
+
"\u0648\u0631\u0646\u06C1",
|
|
443
|
+
"\u0627\u0644\u0628\u062A\u06C1",
|
|
444
|
+
"\u0645\u062B\u0644\u0627\u064B",
|
|
445
|
+
"\u06CC\u0639\u0646\u06CC",
|
|
446
|
+
"\u062E\u0635\u0648\u0635\u0627\u064B",
|
|
447
|
+
"\u0639\u0645\u0648\u0645\u0627\u064B",
|
|
448
|
+
"\u0686\u0646\u0627\u0646\u0686\u06C1",
|
|
449
|
+
"\u062E\u0648\u0627\u06C1",
|
|
450
|
+
"\u0686\u0627\u06C1\u06D2",
|
|
451
|
+
"\u06AF\u0648\u06CC\u0627",
|
|
452
|
+
"\u062A\u0627\u06C1\u0645",
|
|
453
|
+
"\u0646\u06CC\u0632",
|
|
454
|
+
"\u062D\u062A\u06CC",
|
|
455
|
+
"\u0648\u063A\u06CC\u0631\u06C1",
|
|
456
|
+
"\u0635\u0631\u0641",
|
|
457
|
+
"\u0645\u062D\u0636",
|
|
458
|
+
"\u0641\u0642\u0637",
|
|
459
|
+
// Pronouns, determiners & question words
|
|
460
|
+
"\u06C1\u0645",
|
|
461
|
+
"\u062A\u0645",
|
|
462
|
+
"\u0622\u067E",
|
|
463
|
+
"\u0648\u06C1",
|
|
464
|
+
"\u06CC\u06C1",
|
|
465
|
+
"\u0645\u06CC\u0631\u0627",
|
|
466
|
+
"\u0645\u06CC\u0631\u06CC",
|
|
467
|
+
"\u0645\u06CC\u0631\u06D2",
|
|
468
|
+
"\u06C1\u0645\u0627\u0631\u0627",
|
|
469
|
+
"\u06C1\u0645\u0627\u0631\u06CC",
|
|
470
|
+
"\u06C1\u0645\u0627\u0631\u06D2",
|
|
471
|
+
"\u062A\u0645\u06C1\u0627\u0631\u0627",
|
|
472
|
+
"\u062A\u0645\u06C1\u0627\u0631\u06CC",
|
|
473
|
+
"\u062A\u0645\u06C1\u0627\u0631\u06D2",
|
|
474
|
+
"\u0622\u067E\u06A9\u0627",
|
|
475
|
+
"\u0622\u067E\u06A9\u06CC",
|
|
476
|
+
"\u0622\u067E\u06A9\u06D2",
|
|
477
|
+
"\u0627\u0633",
|
|
478
|
+
"\u0627\u0633\u06A9\u0627",
|
|
479
|
+
"\u0627\u0633\u06A9\u06CC",
|
|
480
|
+
"\u0627\u0633\u06A9\u06D2",
|
|
481
|
+
"\u0627\u0633\u06D2",
|
|
482
|
+
"\u0627\u0646",
|
|
483
|
+
"\u0627\u0646\u06A9\u0627",
|
|
484
|
+
"\u0627\u0646\u06A9\u06CC",
|
|
485
|
+
"\u0627\u0646\u06A9\u06D2",
|
|
486
|
+
"\u0627\u0646\u06C1\u06CC\u06BA",
|
|
487
|
+
"\u0645\u062C\u06BE\u06D2",
|
|
488
|
+
"\u06C1\u0645\u06CC\u06BA",
|
|
489
|
+
"\u062A\u0645\u06C1\u06CC\u06BA",
|
|
490
|
+
"\u062C\u0633",
|
|
491
|
+
"\u062C\u0633\u06A9\u0627",
|
|
492
|
+
"\u062C\u0633\u06A9\u06CC",
|
|
493
|
+
"\u062C\u0633\u06A9\u06D2",
|
|
494
|
+
"\u062C\u0633\u06D2",
|
|
495
|
+
"\u062C\u0646",
|
|
496
|
+
"\u062C\u0646\u06A9\u0627",
|
|
497
|
+
"\u062C\u0646\u06A9\u06CC",
|
|
498
|
+
"\u062C\u0646\u06A9\u06D2",
|
|
499
|
+
"\u062C\u0646\u06C1\u0648\u06BA",
|
|
500
|
+
"\u0627\u0646\u06C1\u0648\u06BA",
|
|
501
|
+
"\u06A9\u0633",
|
|
502
|
+
"\u06A9\u0633\u06A9\u0627",
|
|
503
|
+
"\u06A9\u0633\u06A9\u06CC",
|
|
504
|
+
"\u06A9\u0633\u06A9\u06D2",
|
|
505
|
+
"\u06A9\u0633\u06D2",
|
|
506
|
+
"\u06A9\u0633\u06A9\u0648",
|
|
507
|
+
"\u06A9\u0648\u0646",
|
|
508
|
+
"\u06A9\u06CC\u0627",
|
|
509
|
+
"\u06A9\u06C1\u0627\u06BA",
|
|
510
|
+
"\u06A9\u062F\u06BE\u0631",
|
|
511
|
+
"\u0627\u062F\u06BE\u0631",
|
|
512
|
+
"\u062C\u062F\u06BE\u0631",
|
|
513
|
+
"\u06A9\u0628",
|
|
514
|
+
"\u06A9\u06CC\u0648\u06BA",
|
|
515
|
+
"\u06A9\u06CC\u0633\u06D2",
|
|
516
|
+
"\u06A9\u06CC\u0633\u0627",
|
|
517
|
+
"\u06A9\u06CC\u0633\u06CC",
|
|
518
|
+
"\u06A9\u062A\u0646\u0627",
|
|
519
|
+
"\u06A9\u062A\u0646\u06CC",
|
|
520
|
+
"\u06A9\u062A\u0646\u06D2",
|
|
521
|
+
"\u062C\u0648",
|
|
522
|
+
"\u0633\u0628",
|
|
523
|
+
"\u0633\u0628\u06BE\u06CC",
|
|
524
|
+
"\u06A9\u0648\u0626\u06CC",
|
|
525
|
+
"\u06A9\u0686\u06BE",
|
|
526
|
+
"\u06C1\u0631",
|
|
527
|
+
"\u0627\u06CC\u06A9",
|
|
528
|
+
"\u0627\u067E\u0646\u0627",
|
|
529
|
+
"\u0627\u067E\u0646\u06CC",
|
|
530
|
+
"\u0627\u067E\u0646\u06D2",
|
|
531
|
+
"\u062E\u0648\u062F",
|
|
532
|
+
// Common light/auxiliary verb forms
|
|
533
|
+
"\u06A9\u0631\u0646\u0627",
|
|
534
|
+
"\u06A9\u0631\u062A\u0627",
|
|
535
|
+
"\u06A9\u0631\u062A\u06CC",
|
|
536
|
+
"\u06A9\u0631\u062A\u06D2",
|
|
537
|
+
"\u06A9\u0631\u06CC\u06BA",
|
|
538
|
+
"\u06A9\u0631\u0648",
|
|
539
|
+
"\u06A9\u0631",
|
|
540
|
+
"\u06A9\u0631\u0646\u06D2",
|
|
541
|
+
"\u06A9\u06CC\u06D2",
|
|
542
|
+
"\u062C\u0627\u0646\u0627",
|
|
543
|
+
"\u062C\u0627\u062A\u0627",
|
|
544
|
+
"\u062C\u0627\u062A\u06CC",
|
|
545
|
+
"\u062C\u0627\u062A\u06D2",
|
|
546
|
+
"\u062C\u0627\u0626\u06D2",
|
|
547
|
+
"\u062C\u0627\u0626\u06CC\u06BA",
|
|
548
|
+
"\u062C\u0627\u0624",
|
|
549
|
+
"\u062C\u0627",
|
|
550
|
+
"\u062C\u0627\u0646\u06D2",
|
|
551
|
+
"\u06AF\u06CC\u0627",
|
|
552
|
+
"\u06AF\u0626\u06CC",
|
|
553
|
+
"\u06AF\u0626\u06D2",
|
|
554
|
+
"\u0622\u0646\u0627",
|
|
555
|
+
"\u0622\u062A\u0627",
|
|
556
|
+
"\u0622\u062A\u06CC",
|
|
557
|
+
"\u0622\u062A\u06D2",
|
|
558
|
+
"\u0622\u0626\u06D2",
|
|
559
|
+
"\u0622\u0626\u06CC\u06BA",
|
|
560
|
+
"\u0622\u06CC\u0627",
|
|
561
|
+
"\u0622\u0626\u06CC",
|
|
562
|
+
"\u0622\u0646\u06D2",
|
|
563
|
+
"\u0622\u0624",
|
|
564
|
+
"\u0622",
|
|
565
|
+
"\u062F\u06CC\u0646\u0627",
|
|
566
|
+
"\u062F\u06CC\u062A\u0627",
|
|
567
|
+
"\u062F\u06CC\u062A\u06CC",
|
|
568
|
+
"\u062F\u06CC\u062A\u06D2",
|
|
569
|
+
"\u062F\u06CC\u0627",
|
|
570
|
+
"\u062F\u06CC\u06D2",
|
|
571
|
+
"\u062F\u06D2",
|
|
572
|
+
"\u062F\u0648",
|
|
573
|
+
"\u062F\u06CC\u06BA",
|
|
574
|
+
"\u062F\u06CC\u0646\u06D2",
|
|
575
|
+
"\u0644\u06CC\u0646\u0627",
|
|
576
|
+
"\u0644\u06CC\u062A\u0627",
|
|
577
|
+
"\u0644\u06CC\u062A\u06CC",
|
|
578
|
+
"\u0644\u06CC\u062A\u06D2",
|
|
579
|
+
"\u0644\u06CC\u0627",
|
|
580
|
+
"\u0644\u06D2",
|
|
581
|
+
"\u0644\u0648",
|
|
582
|
+
"\u0644\u06CC\u06BA",
|
|
583
|
+
"\u0644\u06CC\u0646\u06D2",
|
|
584
|
+
"\u0631\u06C1\u0646\u0627",
|
|
585
|
+
"\u0631\u06C1\u0627",
|
|
586
|
+
"\u0631\u06C1\u06CC",
|
|
587
|
+
"\u0631\u06C1\u06D2",
|
|
588
|
+
"\u0631\u06C1\u062A\u0627",
|
|
589
|
+
"\u0631\u06C1\u062A\u06CC",
|
|
590
|
+
"\u0631\u06C1\u062A\u06D2",
|
|
591
|
+
"\u0631\u06C1\u0646\u06D2",
|
|
592
|
+
"\u0633\u06A9\u0646\u0627",
|
|
593
|
+
"\u0633\u06A9\u062A\u0627",
|
|
594
|
+
"\u0633\u06A9\u062A\u06CC",
|
|
595
|
+
"\u0633\u06A9\u062A\u06D2",
|
|
596
|
+
"\u0648\u0627\u0644\u0627",
|
|
597
|
+
"\u0648\u0627\u0644\u06CC",
|
|
598
|
+
"\u0648\u0627\u0644\u06D2"
|
|
599
|
+
]);
|
|
600
|
+
function toStopWordSet(custom) {
|
|
601
|
+
if (!custom) return URDU_STOP_WORDS;
|
|
602
|
+
if (custom instanceof Set) return custom;
|
|
603
|
+
return new Set(custom.map((w) => normalizeUrdu(w.trim())));
|
|
604
|
+
}
|
|
605
|
+
function isStopWord(word, customStopWords) {
|
|
606
|
+
if (!word) return false;
|
|
607
|
+
const normalized = normalizeUrdu(word.trim());
|
|
608
|
+
const stopSet = toStopWordSet(customStopWords);
|
|
609
|
+
return stopSet.has(normalized);
|
|
610
|
+
}
|
|
611
|
+
function filterStopWords(words, customStopWords) {
|
|
612
|
+
if (!words || words.length === 0) return [];
|
|
613
|
+
const stopSet = toStopWordSet(customStopWords);
|
|
614
|
+
return words.filter((w) => {
|
|
615
|
+
const normalized = normalizeUrdu(w.trim());
|
|
616
|
+
return normalized.length > 0 && !stopSet.has(normalized);
|
|
617
|
+
});
|
|
618
|
+
}
|
|
619
|
+
function removeStopWords(text, customStopWords) {
|
|
620
|
+
if (!text) return "";
|
|
621
|
+
const words = splitWords(text);
|
|
622
|
+
const filtered = filterStopWords(words, customStopWords);
|
|
623
|
+
return filtered.join(" ");
|
|
624
|
+
}
|
|
625
|
+
|
|
329
626
|
// src/collate.ts
|
|
330
627
|
var ALPHABET = [
|
|
331
628
|
"\u0627",
|
|
@@ -2586,7 +2883,191 @@ var WORD_DICTIONARY = {
|
|
|
2586
2883
|
"\u0641\u0631\u0632\u0627\u0646\u06C1": "farzana",
|
|
2587
2884
|
"\u0637\u0627\u06C1\u0631\u06C1": "tahira",
|
|
2588
2885
|
"\u0639\u0635\u0645\u062A": "ismat",
|
|
2589
|
-
"\u0646\u0635\u0631\u062A": "nusrat"
|
|
2886
|
+
"\u0646\u0635\u0631\u062A": "nusrat",
|
|
2887
|
+
// ---- classical, poetic and literary vocabulary ----
|
|
2888
|
+
"\u06AF\u0644\u0633\u062A\u0627\u06BA": "gulistan",
|
|
2889
|
+
"\u06AF\u0644\u0634\u0646": "gulshan",
|
|
2890
|
+
"\u0628\u06C1\u0627\u0631\u0627\u06BA": "baharan",
|
|
2891
|
+
"\u067E\u0631\u0648\u0627\u0646\u06C1": "parwana",
|
|
2892
|
+
"\u0634\u0645\u0639": "shama",
|
|
2893
|
+
"\u0633\u0627\u0642\u06CC": "saqi",
|
|
2894
|
+
"\u0645\u06CC\u062E\u0627\u0646\u06C1": "maikhana",
|
|
2895
|
+
"\u062C\u0627\u0645": "jaam",
|
|
2896
|
+
"\u0635\u0631\u0627\u062D\u06CC": "surahi",
|
|
2897
|
+
"\u0631\u0646\u062F": "rind",
|
|
2898
|
+
"\u0645\u062D\u062A\u0633\u0628": "muhtasib",
|
|
2899
|
+
"\u0642\u0627\u0635\u062F": "qasid",
|
|
2900
|
+
"\u067E\u06CC\u0627\u0645\u0628\u0631": "payambar",
|
|
2901
|
+
"\u0631\u0642\u06CC\u0628": "raqeeb",
|
|
2902
|
+
"\u062D\u0628\u06CC\u0628": "habeeb",
|
|
2903
|
+
"\u0645\u062D\u0628\u0648\u0628": "mahboob",
|
|
2904
|
+
"\u0645\u0639\u0634\u0648\u0642": "mashooq",
|
|
2905
|
+
"\u0635\u0646\u0645": "sanam",
|
|
2906
|
+
"\u0633\u0646\u06AF\u062F\u0644": "sangdil",
|
|
2907
|
+
"\u0628\u06CC\u062F\u0631\u062F": "bedard",
|
|
2908
|
+
"\u063A\u0645\u06AF\u0633\u0627\u0631": "ghamgusar",
|
|
2909
|
+
"\u0645\u0633\u06CC\u062D\u0627": "maseeha",
|
|
2910
|
+
"\u0646\u0627\u0635\u062D": "nasih",
|
|
2911
|
+
"\u0648\u0627\u0639\u0638": "waiz",
|
|
2912
|
+
"\u062A\u0634\u0646\u06C1": "tishna",
|
|
2913
|
+
"\u06AF\u06CC\u0633\u0648": "gesu",
|
|
2914
|
+
"\u0632\u0644\u0641": "zulf",
|
|
2915
|
+
"\u062F\u06CC\u062F\u0627\u0631": "deedar",
|
|
2916
|
+
"\u062C\u0644\u0648\u06C1": "jalwa",
|
|
2917
|
+
"\u062D\u062C\u0627\u0628": "hijab",
|
|
2918
|
+
"\u0646\u0642\u0627\u0628": "niqab",
|
|
2919
|
+
"\u0633\u0648\u0632": "soz",
|
|
2920
|
+
"\u0622\u06C1\u0646\u06AF": "aahang",
|
|
2921
|
+
"\u0646\u063A\u0645\u06C1": "naghma",
|
|
2922
|
+
"\u062A\u0631\u0627\u0646\u06C1": "tarana",
|
|
2923
|
+
"\u062F\u0627\u0633\u062A\u0627\u06BA": "dastan",
|
|
2924
|
+
"\u062D\u0648\u0631": "hoor",
|
|
2925
|
+
"\u067E\u0631\u06CC": "pari",
|
|
2926
|
+
"\u062F\u06CC\u0648": "deo",
|
|
2927
|
+
"\u062C\u0627\u062F\u0648": "jadoo",
|
|
2928
|
+
"\u0637\u0644\u0633\u0645": "tilism",
|
|
2929
|
+
"\u0627\u0641\u0633\u0648\u0646": "afsoon",
|
|
2930
|
+
"\u0633\u062D\u0631\u0627\u0646\u06AF\u06CC\u0632": "sehrangeez",
|
|
2931
|
+
"\u0641\u0633\u0648\u06BA": "fusoon",
|
|
2932
|
+
"\u062C\u0646\u0648\u06BA": "junoon",
|
|
2933
|
+
"\u0633\u0648\u062F\u0627": "sauda",
|
|
2934
|
+
"\u0648\u062D\u0634\u062A": "wahshat",
|
|
2935
|
+
"\u0627\u0631\u0645\u0627\u0646": "arman",
|
|
2936
|
+
"\u0630\u0648\u0642": "zauq",
|
|
2937
|
+
"\u0648\u062C\u062F": "wajd",
|
|
2938
|
+
"\u0645\u0633\u062A\u06CC": "masti",
|
|
2939
|
+
"\u06A9\u06CC\u0641": "kaif",
|
|
2940
|
+
"\u062E\u0645\u0627\u0631": "khumar",
|
|
2941
|
+
"\u0646\u0634\u06C1": "nasha",
|
|
2942
|
+
"\u0628\u06D2\u062E\u0648\u062F\u06CC": "bekhudi",
|
|
2943
|
+
// ---- commerce, finance and modern technology ----
|
|
2944
|
+
"\u062E\u0631\u06CC\u062F\u0627\u0631\u06CC": "khareedari",
|
|
2945
|
+
"\u0641\u0631\u0648\u062E\u062A": "farokht",
|
|
2946
|
+
"\u0633\u0631\u0645\u0627\u06CC\u06C1": "sarmaya",
|
|
2947
|
+
"\u0642\u0631\u0636\u06C1": "qarza",
|
|
2948
|
+
"\u0628\u06CC\u0646\u06A9\u0627\u0631\u06CC": "bainkari",
|
|
2949
|
+
"\u0642\u0633\u0637": "qist",
|
|
2950
|
+
"\u0627\u062F\u0627\u0626\u06CC\u06AF\u06CC": "adaigi",
|
|
2951
|
+
"\u0622\u0645\u062F\u0646\u06CC": "aamdani",
|
|
2952
|
+
"\u062E\u0631\u0686\u06C1": "kharcha",
|
|
2953
|
+
"\u0628\u0686\u062A": "bachat",
|
|
2954
|
+
"\u0645\u062D\u0635\u0648\u0644": "mahsool",
|
|
2955
|
+
"\u0645\u0627\u0644\u06CC\u062A": "maliyat",
|
|
2956
|
+
"\u06A9\u062A\u0627\u0628\u062A": "kitabat",
|
|
2957
|
+
"\u0645\u0646\u0688\u06CC": "mandi",
|
|
2958
|
+
"\u0646\u06CC\u0644\u0627\u0645\u06CC": "neelami",
|
|
2959
|
+
"\u0628\u0648\u0644\u06CC": "boli",
|
|
2960
|
+
"\u0634\u0631\u0627\u06A9\u062A": "sharakat",
|
|
2961
|
+
"\u062D\u0635\u0635": "hisas",
|
|
2962
|
+
"\u0627\u0633\u0679\u0627\u06A9": "stock",
|
|
2963
|
+
"\u062F\u0648\u0644\u062A": "daulat",
|
|
2964
|
+
"\u062B\u0631\u0648\u062A": "sarwat",
|
|
2965
|
+
"\u063A\u0631\u0628\u062A": "ghurbat",
|
|
2966
|
+
"\u0627\u0641\u0644\u0627\u0633": "iflas",
|
|
2967
|
+
"\u067E\u0631\u0648\u0641\u0627\u0626\u0644": "profile",
|
|
2968
|
+
"\u0633\u06CC\u0679\u0646\u06AF\u0632": "settings",
|
|
2969
|
+
"\u0646\u0648\u0679\u06CC\u0641\u06A9\u06CC\u0634\u0646": "notification",
|
|
2970
|
+
"\u0633\u0627\u0626\u0679": "site",
|
|
2971
|
+
"\u067E\u0648\u0631\u0679\u0644": "portal",
|
|
2972
|
+
// ---- administration, law, governance and politics ----
|
|
2973
|
+
"\u0639\u062F\u0644\u06CC\u06C1": "adliya",
|
|
2974
|
+
"\u0645\u0642\u0646\u0646\u06C1": "muqannana",
|
|
2975
|
+
"\u0627\u0646\u062A\u0638\u0627\u0645\u06CC\u06C1": "intizamia",
|
|
2976
|
+
"\u062D\u06A9\u0645\u0631\u0627\u0646\u06CC": "hukmrani",
|
|
2977
|
+
"\u062C\u0645\u06C1\u0648\u0631\u06CC\u06C1": "jamhooria",
|
|
2978
|
+
"\u0635\u062F\u0627\u0631\u062A": "sadarat",
|
|
2979
|
+
"\u0648\u0632\u0627\u0631\u062A": "wazarat",
|
|
2980
|
+
"\u0633\u0641\u0627\u0631\u062A": "safarat",
|
|
2981
|
+
"\u0642\u0648\u0646\u0635\u0644": "consul",
|
|
2982
|
+
"\u0633\u0641\u0627\u0631\u062A\u062E\u0627\u0646\u06C1": "safaratkhana",
|
|
2983
|
+
"\u0622\u0626\u06CC\u0646\u06CC": "aaeeni",
|
|
2984
|
+
"\u062F\u0633\u062A\u0648\u0631\u06CC": "dastoori",
|
|
2985
|
+
"\u0641\u0648\u062C\u062F\u0627\u0631\u06CC": "faujdari",
|
|
2986
|
+
"\u062F\u06CC\u0648\u0627\u0646\u06CC": "deewani",
|
|
2987
|
+
"\u0645\u0642\u062F\u0645\u06C1": "muqaddama",
|
|
2988
|
+
"\u0633\u0645\u0627\u0639\u062A": "samaat",
|
|
2989
|
+
"\u062F\u0631\u062E\u0648\u0627\u0633\u062A": "darkhwast",
|
|
2990
|
+
"\u0627\u067E\u06CC\u0644": "appeal",
|
|
2991
|
+
"\u0636\u0645\u0627\u0646\u062A": "zamanat",
|
|
2992
|
+
"\u0628\u0631\u06CC\u062A": "bariyat",
|
|
2993
|
+
"\u0639\u0645\u0631\u0642\u06CC\u062F": "umrqaid",
|
|
2994
|
+
"\u067E\u06BE\u0627\u0646\u0633\u06CC": "phansi",
|
|
2995
|
+
"\u0648\u06A9\u0627\u0644\u062A": "wukalat",
|
|
2996
|
+
"\u062D\u0642\u0648\u0642": "huqooq",
|
|
2997
|
+
"\u0641\u0631\u0627\u0626\u0636": "faraiz",
|
|
2998
|
+
"\u0634\u06C1\u0631\u06CC": "shahri",
|
|
2999
|
+
"\u0634\u06C1\u0631\u06CC\u062A": "shahriyat",
|
|
3000
|
+
"\u0634\u0646\u0627\u062E\u062A": "shanakht",
|
|
3001
|
+
"\u0646\u0627\u062F\u0631\u0627": "nadra",
|
|
3002
|
+
"\u0645\u062C\u0644\u0633": "majlis",
|
|
3003
|
+
"\u0634\u0648\u0631\u06CC": "shoora",
|
|
3004
|
+
"\u062D\u0644\u06CC\u0641": "haleef",
|
|
3005
|
+
"\u0645\u062E\u0627\u0644\u0641": "mukhalif",
|
|
3006
|
+
"\u0628\u063A\u0627\u0648\u062A": "baghawat",
|
|
3007
|
+
// ---- geography, nature and terrain ----
|
|
3008
|
+
"\u062E\u0637\u06C1": "khitta",
|
|
3009
|
+
"\u0635\u0648\u0628\u06C1": "sooba",
|
|
3010
|
+
"\u0636\u0644\u0639": "zila",
|
|
3011
|
+
"\u062A\u062D\u0635\u06CC\u0644": "tehsil",
|
|
3012
|
+
"\u06CC\u0648\u0646\u06CC\u0646": "union",
|
|
3013
|
+
"\u06A9\u0648\u0646\u0633\u0644": "council",
|
|
3014
|
+
"\u0642\u0631\u06CC\u06C1": "qarya",
|
|
3015
|
+
"\u0628\u0633\u062A\u06CC": "basti",
|
|
3016
|
+
"\u0634\u06C1\u0631\u0633\u062A\u0627\u0646": "shehristan",
|
|
3017
|
+
"\u0646\u062E\u0644\u0633\u062A\u0627\u0646": "nakhalistan",
|
|
3018
|
+
"\u06A9\u0648\u06C1\u0633\u0627\u0631": "kohsar",
|
|
3019
|
+
"\u06A9\u06C1\u0633\u0627\u0631": "kuhsar",
|
|
3020
|
+
"\u06AF\u06BE\u0627\u0679\u06CC": "ghati",
|
|
3021
|
+
"\u0648\u0627\u062F\u06CC\u0627\u06BA": "wadiyan",
|
|
3022
|
+
"\u06A9\u06BE\u0627\u0626\u06CC": "khaai",
|
|
3023
|
+
"\u062E\u0644\u06CC\u062C": "khaleej",
|
|
3024
|
+
"\u0631\u0627\u0633": "raas",
|
|
3025
|
+
// ---- verbs and verbal inflections ----
|
|
3026
|
+
"\u0645\u0627\u0646\u062A\u06D2": "mante",
|
|
3027
|
+
"\u0645\u0627\u0646\u062A\u06CC": "manti",
|
|
3028
|
+
"\u0645\u0627\u0646\u0648": "mano",
|
|
3029
|
+
"\u0679\u06BE\u06C1\u0631\u0646\u0627": "theharna",
|
|
3030
|
+
"\u0679\u06BE\u06C1\u0631\u0627": "thehra",
|
|
3031
|
+
"\u0679\u06BE\u06C1\u0631\u0648": "thehro",
|
|
3032
|
+
"\u0679\u06BE\u06C1\u0631\u062A\u06D2": "thehrte",
|
|
3033
|
+
"\u0633\u0645\u062C\u06BE\u0627\u0624": "samjhao",
|
|
3034
|
+
"\u067E\u06C1\u0646\u0686\u0627\u0624": "pohonchao",
|
|
3035
|
+
"\u0644\u0679\u0627\u0646\u0627": "lutana",
|
|
3036
|
+
"\u0644\u0679\u0627\u06CC\u0627": "lutaya",
|
|
3037
|
+
"\u0644\u0648\u0679\u0627": "loota",
|
|
3038
|
+
"\u067E\u06A9\u0627\u0631\u0627": "pukara",
|
|
3039
|
+
"\u067E\u06A9\u0627\u0631\u0648": "pukaro",
|
|
3040
|
+
"\u062C\u06BE\u06A9\u0646\u0627": "jhukna",
|
|
3041
|
+
"\u062C\u06BE\u06A9\u0627": "jhuka",
|
|
3042
|
+
"\u062C\u06BE\u06A9\u0627\u0624": "jhukao",
|
|
3043
|
+
"\u062C\u06BE\u06A9\u0627\u0646\u0627": "jhukana",
|
|
3044
|
+
"\u062A\u06BE\u0627\u0645\u0646\u0627": "thamna",
|
|
3045
|
+
"\u062A\u06BE\u0627\u0645\u0627": "thama",
|
|
3046
|
+
"\u062A\u06BE\u0627\u0645\u0648": "thamo",
|
|
3047
|
+
"\u0633\u0646\u0648\u0627\u0631\u0646\u0627": "sanwarna",
|
|
3048
|
+
"\u0633\u0646\u0648\u0627\u0631\u0627": "sanwara",
|
|
3049
|
+
"\u0646\u06A9\u06BE\u0627\u0631\u0646\u0627": "nikharna",
|
|
3050
|
+
"\u0646\u06A9\u06BE\u0627\u0631\u0627": "nikhara",
|
|
3051
|
+
"\u0633\u0646\u0628\u06BE\u0627\u0644\u0646\u0627": "sambhalna",
|
|
3052
|
+
"\u0633\u0646\u0628\u06BE\u0627\u0644\u0627": "sambhala",
|
|
3053
|
+
"\u0633\u0646\u0628\u06BE\u0627\u0644\u0648": "sambhalo",
|
|
3054
|
+
"\u067E\u0686\u06BE\u062A\u0627\u0646\u0627": "pachtana",
|
|
3055
|
+
"\u067E\u0686\u06BE\u062A\u0627\u06CC\u0627": "pachtaya",
|
|
3056
|
+
"\u06AF\u06BE\u0628\u0631\u0627\u0646\u0627": "ghabrana",
|
|
3057
|
+
"\u06AF\u06BE\u0628\u0631\u0627\u06CC\u0627": "ghabraya",
|
|
3058
|
+
"\u0645\u0633\u06A9\u0631\u0627\u0646\u0627": "muskurana",
|
|
3059
|
+
"\u0645\u0633\u06A9\u0631\u0627\u06CC\u0627": "muskuraya",
|
|
3060
|
+
"\u0645\u0633\u06A9\u0631\u0627\u06C1\u0679": "muskurahat",
|
|
3061
|
+
"\u062C\u06BE\u0646\u062C\u06BE\u0644\u0627\u0646\u0627": "jhanjhlana",
|
|
3062
|
+
"\u062A\u0644\u0645\u0644\u0627\u0646\u0627": "tilmilana",
|
|
3063
|
+
"\u0628\u0644\u0628\u0644\u0627\u0646\u0627": "bilbilana",
|
|
3064
|
+
"\u06A9\u06BE\u0644\u06A9\u06BE\u0644\u0627\u0646\u0627": "khilkhilana",
|
|
3065
|
+
"\u06A9\u06BE\u0679\u06A9\u06BE\u0679\u0627\u0646\u0627": "khatkhatana",
|
|
3066
|
+
"\u062C\u06BE\u0644\u0645\u0644\u0627\u0646\u0627": "jhilmilana",
|
|
3067
|
+
"\u0686\u0645\u0686\u0645\u0627\u062A\u0627": "chamchamata",
|
|
3068
|
+
"\u0644\u06C1\u0631\u0627\u0646\u0627": "lehrana",
|
|
3069
|
+
"\u0644\u06C1\u0631\u0627\u06CC\u0627": "lehraya",
|
|
3070
|
+
"\u0644\u06C1\u0631": "lehar"
|
|
2590
3071
|
};
|
|
2591
3072
|
var ROMAN_VARIANTS = {
|
|
2592
3073
|
hay: "\u06C1\u06D2",
|
|
@@ -2774,7 +3255,35 @@ var ROMAN_VARIANTS = {
|
|
|
2774
3255
|
daur: "\u062F\u0648\u0631",
|
|
2775
3256
|
kurta: "\u06A9\u0631\u062A\u0627",
|
|
2776
3257
|
haseen: "\u062D\u0633\u06CC\u0646",
|
|
2777
|
-
malik: "\u0645\u0644\u06A9"
|
|
3258
|
+
malik: "\u0645\u0644\u06A9",
|
|
3259
|
+
kidhr: "\u06A9\u062F\u06BE\u0631",
|
|
3260
|
+
idhr: "\u0627\u062F\u06BE\u0631",
|
|
3261
|
+
jdhr: "\u062C\u062F\u06BE\u0631",
|
|
3262
|
+
thek: "\u0679\u06BE\u06CC\u06A9",
|
|
3263
|
+
thk: "\u0679\u06BE\u06CC\u06A9",
|
|
3264
|
+
sahi: "\u0635\u062D\u06CC\u062D",
|
|
3265
|
+
galat: "\u063A\u0644\u0637",
|
|
3266
|
+
ghalat: "\u063A\u0644\u0637",
|
|
3267
|
+
sb: "\u0633\u0628",
|
|
3268
|
+
hmsha: "\u06C1\u0645\u06CC\u0634\u06C1",
|
|
3269
|
+
kbhi: "\u06A9\u0628\u06BE\u06CC",
|
|
3270
|
+
aksar: "\u0627\u06A9\u062B\u0631",
|
|
3271
|
+
behtareen: "\u0628\u06C1\u062A\u0631\u06CC\u0646",
|
|
3272
|
+
zabardast: "\u0632\u0628\u0631\u062F\u0633\u062A",
|
|
3273
|
+
shandar: "\u0634\u0627\u0646\u062F\u0627\u0631",
|
|
3274
|
+
khoob: "\u062E\u0648\u0628",
|
|
3275
|
+
khub: "\u062E\u0648\u0628",
|
|
3276
|
+
sharam: "\u0634\u0631\u0645",
|
|
3277
|
+
haya: "\u062D\u06CC\u0627",
|
|
3278
|
+
ghairat: "\u063A\u06CC\u0631\u062A",
|
|
3279
|
+
himmat: "\u06C1\u0645\u062A",
|
|
3280
|
+
hosla: "\u062D\u0648\u0635\u0644\u06C1",
|
|
3281
|
+
mashaallah: "\u0645\u0627\u0634\u0627\u0621\u0627\u0644\u0644\u06C1",
|
|
3282
|
+
inshaallah: "\u0627\u0646\u0634\u0627\u0621\u0627\u0644\u0644\u06C1",
|
|
3283
|
+
mashallah: "\u0645\u0627\u0634\u0627\u0621\u0627\u0644\u0644\u06C1",
|
|
3284
|
+
inshallah: "\u0627\u0646\u0634\u0627\u0621\u0627\u0644\u0644\u06C1",
|
|
3285
|
+
alhamdulillah: "\u0627\u0644\u062D\u0645\u062F\u0644\u0644\u06C1",
|
|
3286
|
+
jazakallah: "\u062C\u0632\u0627\u06A9\u200C\u0627\u0644\u0644\u06C1"
|
|
2778
3287
|
};
|
|
2779
3288
|
|
|
2780
3289
|
// src/transliterate.ts
|
|
@@ -2997,6 +3506,6 @@ function urduSlug(input, options = {}) {
|
|
|
2997
3506
|
return slug;
|
|
2998
3507
|
}
|
|
2999
3508
|
|
|
3000
|
-
export { analyzeUrdu, compareUrdu, convertNumbers, countSentences, countWords, editDistance, foldUrdu, hasUrduSpecificLetters, highlightUrdu, isUrdu, normalizeUrdu, numberToUrduWords, parseUrduNumber, removeDiacritics, romanToUrdu, romanize, searchUrdu, searchUrduRanked, sortUrdu, splitSentences, splitWords, toArabicIndicDigits, toEnglishDigits, toUrduDigits, urduRatio, urduSlug };
|
|
3509
|
+
export { URDU_STOP_WORDS, analyzeUrdu, compareUrdu, convertNumbers, countSentences, countWords, editDistance, filterStopWords, foldUrdu, hasUrduSpecificLetters, highlightUrdu, isStopWord, isUrdu, normalizeUrdu, numberToUrduWords, parseUrduNumber, removeDiacritics, removeStopWords, romanToUrdu, romanize, searchUrdu, searchUrduRanked, sortUrdu, splitSentences, splitWords, toArabicIndicDigits, toEnglishDigits, toUrduDigits, urduRatio, urduSlug };
|
|
3001
3510
|
//# sourceMappingURL=index.js.map
|
|
3002
3511
|
//# sourceMappingURL=index.js.map
|