diff options
Diffstat (limited to 'arabluatex_fullvoc.lua')
-rw-r--r-- | arabluatex_fullvoc.lua | 119 |
1 files changed, 99 insertions, 20 deletions
diff --git a/arabluatex_fullvoc.lua b/arabluatex_fullvoc.lua index 6d63192..99efb75 100644 --- a/arabluatex_fullvoc.lua +++ b/arabluatex_fullvoc.lua | |||
@@ -354,12 +354,16 @@ trigraphsfv = { -- trigraphs or more | |||
354 | -- al- + lām | 354 | -- al- + lām |
355 | {a="^(a)l%-(l)", b="ا%1ل%2%2"}, | 355 | {a="^(a)l%-(l)", b="ا%1ل%2%2"}, |
356 | {a="([%(%[%|%<%s%-o])(a)l%-(l)", b="%1ا%2ل%3%3"}, --p | 356 | {a="([%(%[%|%<%s%-o])(a)l%-(l)", b="%1ا%2ل%3%3"}, --p |
357 | -- al- + solar consonant | 357 | -- al- + solar consonant ('c' and '^n' are additional characters) |
358 | {a="^(a)l%-([%_%^%.]?[tdrzsn])", b="ا%1ل%2%2"}, | 358 | {a="^(a)l%-(%^n)", b="ا%1ل%2"}, -- ^n is lunar |
359 | {a="([%(%[%|%<%s%-o])(a)l%-([%_%^%.]?[tdrzsn])", b="%1ا%2ل%3%3"}, --p | 359 | {a="([%(%[%|%<%s%-o])(a)l%-(%^n)", b="%1ا%2ل%3"}, -- ^n is lunar --p |
360 | -- assim. art. + solar consonant | 360 | {a="^(a)l%-([%_%^%.]?[tdrzsnc])", b="ا%1ل%2%2"}, |
361 | {a="^(a)([%_%^%.]?[tdrzsn])%-", b="ا%1ل%2"}, | 361 | {a="([%(%[%|%<%s%-o])(a)l%-([%_%^%.]?[tdrzsnc])", b="%1ا%2ل%3%3"}, --p |
362 | {a="([%(%[%|%<%s%-o])(a)([%_%^%.]?[tdrzsn])%-", b="%1ا%2ل%3"}, --p | 362 | -- assim. art. + solar consonant ('c' and '^n' are additional characters) |
363 | {a="^(a)(%^n)%-", b="ا%1ل"}, -- ^n is lunar | ||
364 | {a="([%(%[%|%<%s%-o])(a)(%^n)%-", b="%1ا%2ل"}, -- ^n is lunar --p | ||
365 | {a="^(a)([%_%^%.]?[tdrzsnc])%-", b="ا%1ل%2"}, | ||
366 | {a="([%(%[%|%<%s%-o])(a)([%_%^%.]?[tdrzsnc])%-", b="%1ا%2ل%3"}, --p | ||
363 | -- al- + initial unstable hamza | 367 | -- al- + initial unstable hamza |
364 | {a="^(a)l%-(\"?[uai])", b="ا%1ل%2ٱ"}, | 368 | {a="^(a)l%-(\"?[uai])", b="ا%1ل%2ٱ"}, |
365 | {a="([%(%[%|%<%s%-o])(a)l%-(\"?[uai])", b="%1ا%2ل%3ٱ"}, --p | 369 | {a="([%(%[%|%<%s%-o])(a)l%-(\"?[uai])", b="%1ا%2ل%3ٱ"}, --p |
@@ -378,15 +382,23 @@ trigraphsfv = { -- trigraphs or more | |||
378 | -- art. with waṣla + lām | 382 | -- art. with waṣla + lām |
379 | {a="'l%-(l)", b="ٱل%1%1"}, | 383 | {a="'l%-(l)", b="ٱل%1%1"}, |
380 | -- art. with waṣla + solar consonant | 384 | -- art. with waṣla + solar consonant |
381 | {a="'l%-([%_%^%.]?[tdrzsn])", b="ٱل%1%1"}, | 385 | -- ('c' and '^n' are additional characters) |
386 | {a="'l%-(%^n)", b="ٱل%1"}, -- ^n is lunar | ||
387 | {a="'l%-([%_%^%.]?[tdrzsnc])", b="ٱل%1%1"}, | ||
382 | -- li-/la- + art. + lām | 388 | -- li-/la- + art. + lām |
383 | {a="l([ai])%-l%-(l)", b="ل%1%2%2"}, | 389 | {a="l([ai])%-l%-(l)", b="ل%1%2%2"}, |
384 | -- assim. art. with waṣla + solar consonant | 390 | -- assim. art. with waṣla + solar consonant |
385 | {a="'([%_%^%.]?[tdrzsn])%-", b="ٱل%1"}, | 391 | -- ('c' and '^n' are additional characters) |
392 | {a="'(%^n)%-", b="ٱل"}, -- ^n is lunar | ||
393 | {a="'([%_%^%.]?[tdrzsnc])%-", b="ٱل%1"}, | ||
386 | -- li-/la- + art. + solar consonant is a special orthography | 394 | -- li-/la- + art. + solar consonant is a special orthography |
387 | {a="l([ai])%-l%-([%_%^%.]?[tdrzsn])", b="ل%1ل%2%2"}, | 395 | -- ('c' and '^n' are additional characters) |
396 | {a="l([ai])%-l%-(%^n)", b="ل%1ل%2"}, -- ^n is lunar | ||
397 | {a="l([ai])%-l%-([%_%^%.]?[tdrzsnc])", b="ل%1ل%2%2"}, | ||
388 | -- li-/la- + assim. art. + solar consonant is a special orthography | 398 | -- li-/la- + assim. art. + solar consonant is a special orthography |
389 | {a="l([ai])%-([%_%^%.]?[tdrzsn])%-([%_%^%.]?[tdrzsn])", b="ل%1ل%3%3"}, | 399 | -- ('c' and '^n' are additional characters) |
400 | {a="l([ai])%-(%^n)%-(%^n)", b="ل%1ل%3"}, -- ^n is lunar | ||
401 | {a="l([ai])%-([%_%^%.]?[tdrzsnc])%-([%_%^%.]?[tdrzsnc])", b="ل%1ل%3%3"}, | ||
390 | -- art. with waṣla + initial unstable hamza | 402 | -- art. with waṣla + initial unstable hamza |
391 | {a="'l%-(\"?[uai])", b="ٱل%1ٱ"}, | 403 | {a="'l%-(\"?[uai])", b="ٱل%1ٱ"}, |
392 | -- art. with waṣla + lunar consonant (i.e. what remains) | 404 | -- art. with waṣla + lunar consonant (i.e. what remains) |
@@ -423,12 +435,16 @@ trigraphsfveasy = { -- trigraphs or more (see 'easy' tag below for the diffs) | |||
423 | -- al- + lām | 435 | -- al- + lām |
424 | {a="^(a)l%-(l)", b="ا%1ل%2%2"}, | 436 | {a="^(a)l%-(l)", b="ا%1ل%2%2"}, |
425 | {a="([%(%[%|%<%s%-o])(a)l%-(l)", b="%1ا%2ل%3%3"}, --p | 437 | {a="([%(%[%|%<%s%-o])(a)l%-(l)", b="%1ا%2ل%3%3"}, --p |
426 | -- al- + solar consonant | 438 | -- al- + solar consonant ('c' and '^n' are additional characters) |
427 | {a="^(a)l%-([%_%^%.]?[tdrzsn])", b="ا%1ل%2%2"}, | 439 | {a="^(a)l%-(%^n)", b="ا%1ل%2"}, -- ^n is lunar |
428 | {a="([%(%[%|%<%s%-o])(a)l%-([%_%^%.]?[tdrzsn])", b="%1ا%2ل%3%3"}, --p | 440 | {a="([%(%[%|%<%s%-o])(a)l%-(%^n)", b="%1ا%2ل%3"}, -- ^n is lunar --p |
429 | -- assim. art. + solar consonant | 441 | {a="^(a)l%-([%_%^%.]?[tdrzsnc])", b="ا%1ل%2%2"}, |
430 | {a="^(a)([%_%^%.]?[tdrzsn])%-", b="ا%1ل%2"}, | 442 | {a="([%(%[%|%<%s%-o])(a)l%-([%_%^%.]?[tdrzsnc])", b="%1ا%2ل%3%3"}, --p |
431 | {a="([%(%[%|%<%s%-o])(a)([%_%^%.]?[tdrzsn])%-", b="%1ا%2ل%3"}, --p | 443 | -- assim. art. + solar consonant ('c' and '^n' are additional characters) |
444 | {a="^(a)(%^n)%-", b="ا%1ل"}, -- ^n is lunar | ||
445 | {a="([%(%[%|%<%s%-o])(a)(%^n)%-", b="%1ا%2ل"}, -- ^n is lunar --p | ||
446 | {a="^(a)([%_%^%.]?[tdrzsnc])%-", b="ا%1ل%2"}, | ||
447 | {a="([%(%[%|%<%s%-o])(a)([%_%^%.]?[tdrzsnc])%-", b="%1ا%2ل%3"}, --p | ||
432 | -- al- + initial unstable hamza | 448 | -- al- + initial unstable hamza |
433 | {a="^(a)l%-(\"?[uai])", b="ا%1ل%2ٱ"}, | 449 | {a="^(a)l%-(\"?[uai])", b="ا%1ل%2ٱ"}, |
434 | {a="([%(%[%|%<%s%-o])(a)l%-(\"?[uai])", b="%1ا%2ل%3ٱ"}, --p | 450 | {a="([%(%[%|%<%s%-o])(a)l%-(\"?[uai])", b="%1ا%2ل%3ٱ"}, --p |
@@ -447,15 +463,23 @@ trigraphsfveasy = { -- trigraphs or more (see 'easy' tag below for the diffs) | |||
447 | -- art. with waṣla + lām | 463 | -- art. with waṣla + lām |
448 | {a="'l%-(l)", b="ٱل%1%1"}, | 464 | {a="'l%-(l)", b="ٱل%1%1"}, |
449 | -- art. with waṣla + solar consonant | 465 | -- art. with waṣla + solar consonant |
450 | {a="'l%-([%_%^%.]?[tdrzsn])", b="ٱل%1%1"}, | 466 | -- ('c' and '^n' are additional characters) |
467 | {a="'l%-(%^n)", b="ٱل%1"}, -- ^n is lunar | ||
468 | {a="'l%-([%_%^%.]?[tdrzsnc])", b="ٱل%1%1"}, | ||
451 | -- li-/la- + art. + lām | 469 | -- li-/la- + art. + lām |
452 | {a="l([ai])%-l%-(l)", b="ل%1%2%2"}, | 470 | {a="l([ai])%-l%-(l)", b="ل%1%2%2"}, |
453 | -- assim. art. with waṣla + solar consonant | 471 | -- assim. art. with waṣla + solar consonant |
454 | {a="'([%_%^%.]?[tdrzsn])%-", b="ٱل%1"}, | 472 | -- ('c' and '^n' are is an additional characters) |
473 | {a="'(%^n)%-", b="ٱل"}, -- ^n is lunar | ||
474 | {a="'([%_%^%.]?[tdrzsnc])%-", b="ٱل%1"}, | ||
455 | -- li-/la- + art. + solar consonant is a special orthography | 475 | -- li-/la- + art. + solar consonant is a special orthography |
456 | {a="l([ai])%-l%-([%_%^%.]?[tdrzsn])", b="ل%1ل%2%2"}, | 476 | -- ('c' and '^n' are additional characters) |
477 | {a="l([ai])%-l%-(%^n)", b="ل%1ل%2"}, -- ^n is lunar | ||
478 | {a="l([ai])%-l%-([%_%^%.]?[tdrzsnc])", b="ل%1ل%2%2"}, | ||
457 | -- li-/la- + assim. art. + solar consonant is a special orthography | 479 | -- li-/la- + assim. art. + solar consonant is a special orthography |
458 | {a="l([ai])%-([%_%^%.]?[tdrzsn])%-([%_%^%.]?[tdrzsn])", b="ل%1ل%3%3"}, | 480 | -- ('c and '^n' are additional characters) |
481 | {a="l([ai])%-(%^n)%-(%^n)", b="ل%1ل%3"}, -- ^n is lunar | ||
482 | {a="l([ai])%-([%_%^%.]?[tdrzsnc])%-([%_%^%.]?[tdrzsnc])", b="ل%1ل%3%3"}, | ||
459 | -- art. with waṣla + initial unstable hamza | 483 | -- art. with waṣla + initial unstable hamza |
460 | {a="'l%-(\"?[uai])", b="ٱل%1ٱ"}, | 484 | {a="'l%-(\"?[uai])", b="ٱل%1ٱ"}, |
461 | -- art. with waṣla + lunar consonant (i.e. what remains) | 485 | -- art. with waṣla + lunar consonant (i.e. what remains) |
@@ -511,6 +535,8 @@ digraphsfvidgham = { | |||
511 | {a="bb", b="بّ"}, | 535 | {a="bb", b="بّ"}, |
512 | {a="BB", b="ـّ"}, | 536 | {a="BB", b="ـّ"}, |
513 | {a="([%_%^%.])([tghdsz])([tghdsz])", b="%1%2|%3"}, | 537 | {a="([%_%^%.])([tghdsz])([tghdsz])", b="%1%2|%3"}, |
538 | -- same as above for additional characters: | ||
539 | {a="([%_%^%.])([cn])([cn])", b="%1%2|%3"}, | ||
514 | {a="tt", b="تّ"}, | 540 | {a="tt", b="تّ"}, |
515 | {a="%_t%_t", b="ثّ"}, | 541 | {a="%_t%_t", b="ثّ"}, |
516 | {a="jj", b="جّ"}, | 542 | {a="jj", b="جّ"}, |
@@ -539,6 +565,14 @@ digraphsfvidgham = { | |||
539 | {a="hh", b="هّ"}, | 565 | {a="hh", b="هّ"}, |
540 | {a="ww", b="وّ"}, | 566 | {a="ww", b="وّ"}, |
541 | {a="yy", b="يّ"}, | 567 | {a="yy", b="يّ"}, |
568 | -- additional characters + šaddah (begin) | ||
569 | {a="pp", b="پّ"}, | ||
570 | {a="vv", b="ڤّ"}, | ||
571 | {a="gg", b="گّ"}, | ||
572 | {a="%^c%^c", b="چّ"}, | ||
573 | {a="%^z%^z", b="ژّ"}, | ||
574 | {a="%^n%^n", b="ڭّ"}, | ||
575 | -- additional characters + šaddah (end) | ||
542 | -- sukūn begin | 576 | -- sukūn begin |
543 | -- first, take out hyphen if any: | 577 | -- first, take out hyphen if any: |
544 | {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])%-([uaiUAI])", b="%1%2"}, | 578 | {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])%-([uaiUAI])", b="%1%2"}, |
@@ -565,6 +599,11 @@ digraphsfvidgham = { | |||
565 | {a="%.t", b="ط"}, | 599 | {a="%.t", b="ط"}, |
566 | {a="%.z", b="ظ"}, | 600 | {a="%.z", b="ظ"}, |
567 | {a="%.g", b="غ"}, | 601 | {a="%.g", b="غ"}, |
602 | -- additional characters (begin) | ||
603 | {a="%^c", b="چ"}, | ||
604 | {a="%^z", b="ژ"}, | ||
605 | {a="%^n", b="ڭ"}, | ||
606 | -- additional characters (end) | ||
568 | {a="(U)(A)", b="%1ا"}, | 607 | {a="(U)(A)", b="%1ا"}, |
569 | {a="WA", b="وْا"}, | 608 | {a="WA", b="وْا"}, |
570 | {a="(a)W\"", b="%1وا"}, | 609 | {a="(a)W\"", b="%1وا"}, |
@@ -619,6 +658,8 @@ digraphsfv = { | |||
619 | {a="bb", b="بّ"}, | 658 | {a="bb", b="بّ"}, |
620 | {a="BB", b="ـّ"}, | 659 | {a="BB", b="ـّ"}, |
621 | {a="([%_%^%.])([tghdsz])([tghdsz])", b="%1%2|%3"}, | 660 | {a="([%_%^%.])([tghdsz])([tghdsz])", b="%1%2|%3"}, |
661 | -- same as above for additional characters: | ||
662 | {a="([%_%^%.])([cn])([cn])", b="%1%2|%3"}, | ||
622 | {a="tt", b="تّ"}, | 663 | {a="tt", b="تّ"}, |
623 | {a="%_t%_t", b="ثّ"}, | 664 | {a="%_t%_t", b="ثّ"}, |
624 | {a="jj", b="جّ"}, | 665 | {a="jj", b="جّ"}, |
@@ -647,6 +688,14 @@ digraphsfv = { | |||
647 | {a="hh", b="هّ"}, | 688 | {a="hh", b="هّ"}, |
648 | {a="ww", b="وّ"}, | 689 | {a="ww", b="وّ"}, |
649 | {a="yy", b="يّ"}, | 690 | {a="yy", b="يّ"}, |
691 | -- additional characters + šaddah (begin) | ||
692 | {a="pp", b="پّ"}, | ||
693 | {a="vv", b="ڤّ"}, | ||
694 | {a="gg", b="گّ"}, | ||
695 | {a="%^c%^c", b="چّ"}, | ||
696 | {a="%^z%^z", b="ژّ"}, | ||
697 | {a="%^n%^n", b="ڭّ"}, | ||
698 | -- additional characters + šaddah (end) | ||
650 | -- sukūn begin | 699 | -- sukūn begin |
651 | -- first, take out hyphen if any: | 700 | -- first, take out hyphen if any: |
652 | {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])%-([uaiUAI])", b="%1%2"}, | 701 | {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])%-([uaiUAI])", b="%1%2"}, |
@@ -673,6 +722,11 @@ digraphsfv = { | |||
673 | {a="%.t", b="ط"}, | 722 | {a="%.t", b="ط"}, |
674 | {a="%.z", b="ظ"}, | 723 | {a="%.z", b="ظ"}, |
675 | {a="%.g", b="غ"}, | 724 | {a="%.g", b="غ"}, |
725 | -- additional characters (begin) | ||
726 | {a="%^c", b="چ"}, | ||
727 | {a="%^z", b="ژ"}, | ||
728 | {a="%^n", b="ڭ"}, | ||
729 | -- additional characters (end) | ||
676 | {a="(U)(A)", b="%1ا"}, | 730 | {a="(U)(A)", b="%1ا"}, |
677 | {a="WA", b="وْا"}, | 731 | {a="WA", b="وْا"}, |
678 | {a="(a)W\"", b="%1وا"}, | 732 | {a="(a)W\"", b="%1وا"}, |
@@ -727,6 +781,8 @@ digraphsfveasy = { -- see the differences under 'easy' marker below | |||
727 | {a="bb", b="بّ"}, | 781 | {a="bb", b="بّ"}, |
728 | {a="BB", b="ـّ"}, | 782 | {a="BB", b="ـّ"}, |
729 | {a="([%_%^%.])([tghdsz])([tghdsz])", b="%1%2|%3"}, | 783 | {a="([%_%^%.])([tghdsz])([tghdsz])", b="%1%2|%3"}, |
784 | -- same as above for additional characters: | ||
785 | {a="([%_%^%.])([cn])([cn])", b="%1%2|%3"}, | ||
730 | {a="tt", b="تّ"}, | 786 | {a="tt", b="تّ"}, |
731 | {a="%_t%_t", b="ثّ"}, | 787 | {a="%_t%_t", b="ثّ"}, |
732 | {a="jj", b="جّ"}, | 788 | {a="jj", b="جّ"}, |
@@ -755,6 +811,14 @@ digraphsfveasy = { -- see the differences under 'easy' marker below | |||
755 | {a="hh", b="هّ"}, | 811 | {a="hh", b="هّ"}, |
756 | {a="ww", b="وّ"}, | 812 | {a="ww", b="وّ"}, |
757 | {a="yy", b="يّ"}, | 813 | {a="yy", b="يّ"}, |
814 | -- additional characters + šaddah (begin) | ||
815 | {a="pp", b="پّ"}, | ||
816 | {a="vv", b="ڤّ"}, | ||
817 | {a="gg", b="گّ"}, | ||
818 | {a="%^c%^c", b="چّ"}, | ||
819 | {a="%^z%^z", b="ژّ"}, | ||
820 | {a="%^n%^n", b="ڭّ"}, | ||
821 | -- additional characters + šaddah (end) | ||
758 | -- sukūn begin ('easy' needs these rules to be taken out); but | 822 | -- sukūn begin ('easy' needs these rules to be taken out); but |
759 | -- first take out every previously generated sukūn by hamza rules, | 823 | -- first take out every previously generated sukūn by hamza rules, |
760 | -- so there be no need to edit them: | 824 | -- so there be no need to edit them: |
@@ -784,6 +848,11 @@ digraphsfveasy = { -- see the differences under 'easy' marker below | |||
784 | {a="%.t", b="ط"}, | 848 | {a="%.t", b="ط"}, |
785 | {a="%.z", b="ظ"}, | 849 | {a="%.z", b="ظ"}, |
786 | {a="%.g", b="غ"}, | 850 | {a="%.g", b="غ"}, |
851 | -- additional characters (begin) | ||
852 | {a="%^c", b="چ"}, | ||
853 | {a="%^z", b="ژ"}, | ||
854 | {a="%^n", b="ڭ"}, | ||
855 | -- additional characters (end) | ||
787 | {a="(U)(A)", b="%1ا"}, | 856 | {a="(U)(A)", b="%1ا"}, |
788 | {a="WA", b="وْا"}, | 857 | {a="WA", b="وْا"}, |
789 | {a="(a)W\"", b="%1وا"}, | 858 | {a="(a)W\"", b="%1وا"}, |
@@ -821,6 +890,11 @@ singlefv = { | |||
821 | {a="w", b="و"}, | 890 | {a="w", b="و"}, |
822 | {a="y", b="ي"}, | 891 | {a="y", b="ي"}, |
823 | {a="T", b="ة"}, | 892 | {a="T", b="ة"}, |
893 | -- additional characters (begin) | ||
894 | {a="p", b="پ"}, | ||
895 | {a="v", b="ڤ"}, | ||
896 | {a="g", b="گ"}, | ||
897 | -- additional characters (end) | ||
824 | {a="\"$", b=""}, | 898 | {a="\"$", b=""}, |
825 | {a="\"(%W)", b="%1"}, | 899 | {a="\"(%W)", b="%1"}, |
826 | {a="\"([^uaiUAI])", b="%1"}, | 900 | {a="\"([^uaiUAI])", b="%1"}, |
@@ -849,6 +923,11 @@ singlefveasy = { -- see the differences under 'easy' tag below | |||
849 | {a="w", b="و"}, | 923 | {a="w", b="و"}, |
850 | {a="y", b="ي"}, | 924 | {a="y", b="ي"}, |
851 | {a="T", b="ة"}, | 925 | {a="T", b="ة"}, |
926 | -- additional characters (begin) | ||
927 | {a="p", b="پ"}, | ||
928 | {a="v", b="ڤ"}, | ||
929 | {a="g", b="گ"}, | ||
930 | -- additional characters (end) | ||
852 | -- easy (begin): \" needs to put back the sukūn | 931 | -- easy (begin): \" needs to put back the sukūn |
853 | {a="\"$", b="ْ"}, | 932 | {a="\"$", b="ْ"}, |
854 | {a="\"(%W)", b="ْ%1"}, | 933 | {a="\"(%W)", b="ْ%1"}, |