Module: Onigmo

Defined in:
lib/onigmo.rb,
lib/onigmo/node.rb,
lib/onigmo/visitor.rb,
lib/onigmo/json_visitor.rb,
lib/onigmo/deconstruct_visitor.rb,
lib/onigmo/pretty_print_visitor.rb,
ext/onigmo/onigmo.c

Defined Under Namespace

Classes: AlternationNode, AnchorBufferBeginNode, AnchorBufferEndNode, AnchorKeepNode, AnchorLineBeginNode, AnchorLineEndNode, AnchorPositionBeginNode, AnchorSemiEndNode, AnchorWordBoundaryInvertNode, AnchorWordBoundaryNode, AnyNode, BackrefNode, CClassInvertNode, CClassNode, CallNode, DeconstructVisitor, EncloseAbsentNode, EncloseConditionNode, EncloseMemoryNode, EncloseOptionsNode, EncloseStopBacktrackNode, JSONVisitor, ListNode, LookAheadInvertNode, LookAheadNode, LookBehindInvertNode, LookBehindNode, Node, PrettyPrintVisitor, QuantifierNode, StringNode, Visitor, WordInvertNode, WordNode

Class Method Summary collapse

Class Method Details

.compile(string) ⇒ Object



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
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
# File 'ext/onigmo/onigmo.c', line 399

static VALUE
compile(VALUE self, VALUE string) {
    const OnigUChar *pattern = (const OnigUChar *) StringValueCStr(string);

    regex_t *regex;
    OnigErrorInfo einfo;

    OnigEncoding encoding = rb_enc_get(string);
    int result = onig_new(&regex, pattern, pattern + strlen((const char *) pattern), ONIG_OPTION_DEFAULT, encoding, ONIG_SYNTAX_DEFAULT, &einfo);

    if (result != ONIG_NORMAL) {
        fail(result, regex, &einfo);
        return Qnil;
    }

    VALUE insns = rb_ary_new();
    const unsigned char *cursor = regex->p;
    const unsigned char *end = cursor + regex->used;
    LengthType length;

    while (cursor < end) {
        VALUE insn = rb_ary_new();

        switch (*cursor++) {
            case OP_FINISH: {
                rb_ary_push(insn, ID2SYM(rb_intern("finish")));
                break;
            }
            case OP_END: {
                rb_ary_push(insn, ID2SYM(rb_intern("end")));
                break;
            }
            case OP_EXACT1: {
                rb_ary_push(insn, ID2SYM(rb_intern("exact1")));
                rb_ary_push(insn, read_exact(&cursor, 1, encoding));
                break;
            }
            case OP_EXACT2: {
                rb_ary_push(insn, ID2SYM(rb_intern("exact2")));
                rb_ary_push(insn, read_exact(&cursor, 2, encoding));
                break;
            }
            case OP_EXACT3: {
                rb_ary_push(insn, ID2SYM(rb_intern("exact3")));
                rb_ary_push(insn, read_exact(&cursor, 3, encoding));
                break;
            }
            case OP_EXACT4: {
                rb_ary_push(insn, ID2SYM(rb_intern("exact4")));
                rb_ary_push(insn, read_exact(&cursor, 4, encoding));
                break;
            }
            case OP_EXACT5: {
                rb_ary_push(insn, ID2SYM(rb_intern("exact5")));
                rb_ary_push(insn, read_exact(&cursor, 5, encoding));
                break;
            }
            case OP_EXACTN: {
                rb_ary_push(insn, ID2SYM(rb_intern("exactn")));
                rb_ary_push(insn, read_length(&cursor));
                break;
            }
            case OP_EXACTMB2N1: {
                rb_ary_push(insn, ID2SYM(rb_intern("exactmb2n1")));
                rb_ary_push(insn, read_exact(&cursor, 2, encoding));
                break;
            }
            case OP_EXACTMB2N2: {
                rb_ary_push(insn, ID2SYM(rb_intern("exactmb2n2")));
                rb_ary_push(insn, read_exact(&cursor, 4, encoding));
                break;
            }
            case OP_EXACTMB2N3: {
                rb_ary_push(insn, ID2SYM(rb_intern("exactmb2n3")));
                rb_ary_push(insn, read_exact(&cursor, 6, encoding));
                break;
            }
            case OP_EXACTMB2N: {
                rb_ary_push(insn, ID2SYM(rb_intern("exactmb2n")));

                VALUE length = read_length(&cursor);
                rb_ary_push(insn, length);

                rb_ary_push(insn, read_exact(&cursor, NUM2INT(length) * 2, encoding));
                break;
            }
            case OP_EXACTMB3N: {
                rb_ary_push(insn, ID2SYM(rb_intern("exactmb3n")));

                VALUE length = read_length(&cursor);
                rb_ary_push(insn, length);

                rb_ary_push(insn, read_exact(&cursor, NUM2INT(length) * 3, encoding));
                break;
            }
            case OP_EXACTMBN: {
                rb_ary_push(insn, ID2SYM(rb_intern("exactmbn")));

                VALUE length = read_length(&cursor);
                rb_ary_push(insn, length);

                rb_ary_push(insn, read_exact(&cursor, NUM2INT(length) * 2, encoding));
                break;
            }
            case OP_EXACT1_IC: {
                rb_ary_push(insn, ID2SYM(rb_intern("exact1_ic")));
                length = enclen(encoding, cursor, end);
                rb_ary_push(insn, read_exact(&cursor, length, encoding));
                break;
            }
            case OP_EXACTN_IC: {
                rb_ary_push(insn, ID2SYM(rb_intern("exactn_ic")));
                length = enclen(encoding, cursor, end);
                rb_ary_push(insn, read_exact(&cursor, length, encoding));
                break;
            }
            case OP_CCLASS: {
                rb_ary_push(insn, ID2SYM(rb_intern("cclass")));
                rb_ary_push(insn, read_bitset(&cursor, encoding));
                break;
            }
            case OP_CCLASS_MB: {
                rb_ary_push(insn, ID2SYM(rb_intern("cclass_mb")));

                VALUE length = read_length(&cursor);
                rb_ary_push(insn, length);
                rb_ary_push(insn, read_codepoint(&cursor, NUM2INT(length)));

                break;
            }
            case OP_CCLASS_MB_NOT: {
                rb_ary_push(insn, ID2SYM(rb_intern("cclass_mb_not")));

                VALUE length = read_length(&cursor);
                rb_ary_push(insn, length);
                rb_ary_push(insn, read_codepoint(&cursor, NUM2INT(length)));

                break;
            }
            case OP_CCLASS_NOT: {
                rb_ary_push(insn, ID2SYM(rb_intern("cclass_not")));
                rb_ary_push(insn, read_bitset(&cursor, encoding));
                break;
            }
            case OP_CCLASS_MIX: {
                rb_ary_push(insn, ID2SYM(rb_intern("cclass_mix")));
                rb_ary_push(insn, read_bitset(&cursor, encoding));

                VALUE length = read_length(&cursor);
                rb_ary_push(insn, length);
                rb_ary_push(insn, read_codepoint(&cursor, NUM2INT(length)));

                break;
            }
            case OP_CCLASS_MIX_NOT: {
                rb_ary_push(insn, ID2SYM(rb_intern("cclass_mix_not")));
                rb_ary_push(insn, read_bitset(&cursor, encoding));

                VALUE length = read_length(&cursor);
                rb_ary_push(insn, length);
                rb_ary_push(insn, read_codepoint(&cursor, NUM2INT(length)));

                break;
            }
            case OP_ANYCHAR: {
                rb_ary_push(insn, ID2SYM(rb_intern("anychar")));
                break;
            }
            case OP_ANYCHAR_ML: {
                rb_ary_push(insn, ID2SYM(rb_intern("anychar_ml")));
                break;
            }
            case OP_ANYCHAR_STAR: {
                rb_ary_push(insn, ID2SYM(rb_intern("anychar_star")));
                break;
            }
            case OP_ANYCHAR_ML_STAR: {
                rb_ary_push(insn, ID2SYM(rb_intern("anychar_ml_star")));
                break;
            }
            case OP_ANYCHAR_STAR_PEEK_NEXT: {
                rb_ary_push(insn, ID2SYM(rb_intern("anychar_star_peek_next")));
                rb_ary_push(insn, read_exact(&cursor, 1, encoding));
                break;
            }
            case OP_ANYCHAR_ML_STAR_PEEK_NEXT: {
                rb_ary_push(insn, ID2SYM(rb_intern("anychar_ml_star_peek_next")));
                rb_ary_push(insn, read_exact(&cursor, 1, encoding));
                break;
            }
            case OP_WORD: {
                rb_ary_push(insn, ID2SYM(rb_intern("word")));
                break;
            }
            case OP_NOT_WORD: {
                rb_ary_push(insn, ID2SYM(rb_intern("not_word")));
                break;
            }
            case OP_WORD_BOUND: {
                rb_ary_push(insn, ID2SYM(rb_intern("word_bound")));
                break;
            }
            case OP_NOT_WORD_BOUND: {
                rb_ary_push(insn, ID2SYM(rb_intern("not_word_bound")));
                break;
            }
            case OP_WORD_BEGIN: {
                rb_ary_push(insn, ID2SYM(rb_intern("word_begin")));
                break;
            }
            case OP_WORD_END: {
                rb_ary_push(insn, ID2SYM(rb_intern("word_end")));
                break;
            }
            case OP_ASCII_WORD: {
                rb_ary_push(insn, ID2SYM(rb_intern("ascii_word")));
                break;
            }
            case OP_NOT_ASCII_WORD: {
                rb_ary_push(insn, ID2SYM(rb_intern("not_ascii_word")));
                break;
            }
            case OP_ASCII_WORD_BOUND: {
                rb_ary_push(insn, ID2SYM(rb_intern("ascii_word_bound")));
                break;
            }
            case OP_NOT_ASCII_WORD_BOUND: {
                rb_ary_push(insn, ID2SYM(rb_intern("not_ascii_word_bound")));
                break;
            }
            case OP_ASCII_WORD_BEGIN: {
                rb_ary_push(insn, ID2SYM(rb_intern("ascii_word_begin")));
                break;
            }
            case OP_ASCII_WORD_END: {
                rb_ary_push(insn, ID2SYM(rb_intern("ascii_word_end")));
                break;
            }
            case OP_BEGIN_BUF: {
                rb_ary_push(insn, ID2SYM(rb_intern("begin_buf")));
                break;
            }
            case OP_END_BUF: {
                rb_ary_push(insn, ID2SYM(rb_intern("end_buf")));
                break;
            }
            case OP_BEGIN_LINE: {
                rb_ary_push(insn, ID2SYM(rb_intern("begin_line")));
                break;
            }
            case OP_END_LINE: {
                rb_ary_push(insn, ID2SYM(rb_intern("end_line")));
                break;
            }
            case OP_SEMI_END_BUF: {
                rb_ary_push(insn, ID2SYM(rb_intern("semi_end_buf")));
                break;
            }
            case OP_BEGIN_POSITION: {
                rb_ary_push(insn, ID2SYM(rb_intern("begin_position")));
                break;
            }
            case OP_BACKREF1: {
                rb_ary_push(insn, ID2SYM(rb_intern("backref1")));
                break;
            }
            case OP_BACKREF2: {
                rb_ary_push(insn, ID2SYM(rb_intern("backref2")));
                break;
            }
            case OP_BACKREFN: {
                rb_ary_push(insn, ID2SYM(rb_intern("backrefn")));
                rb_ary_push(insn, read_memnum(&cursor));
                break;
            }
            case OP_BACKREFN_IC: {
                rb_ary_push(insn, ID2SYM(rb_intern("backrefn_ic")));
                rb_ary_push(insn, read_memnum(&cursor));
                break;
            }
            case OP_BACKREF_MULTI: {
                rb_ary_push(insn, ID2SYM(rb_intern("backref_multi")));

                VALUE length = read_length(&cursor);
                rb_ary_push(insn, length);

                for (int i = 0; i < NUM2INT(length); i++) {
                    rb_ary_push(insn, read_memnum(&cursor));
                }

                break;
            }
            case OP_BACKREF_MULTI_IC: {
                rb_ary_push(insn, ID2SYM(rb_intern("backref_multi_ic")));

                VALUE length = read_length(&cursor);
                rb_ary_push(insn, length);

                for (int i = 0; i < NUM2INT(length); i++) {
                    rb_ary_push(insn, read_memnum(&cursor));
                }

                break;
            }
            case OP_BACKREF_WITH_LEVEL: {
                rb_ary_push(insn, ID2SYM(rb_intern("backref_with_level")));

                rb_ary_push(insn, read_option(&cursor));
                rb_ary_push(insn, read_length(&cursor));

                VALUE length = read_length(&cursor);
                rb_ary_push(insn, length);

                for (int i = 0; i < NUM2INT(length); i++) {
                    rb_ary_push(insn, read_memnum(&cursor));
                }

                break;
            }
            case OP_MEMORY_START:
                rb_ary_push(insn, ID2SYM(rb_intern("memory_start")));
                rb_ary_push(insn, read_memnum(&cursor));
                break;

            case OP_MEMORY_START_PUSH:
                rb_ary_push(insn, ID2SYM(rb_intern("memory_start_push")));
                rb_ary_push(insn, read_memnum(&cursor));
                break;

            case OP_MEMORY_END_PUSH:
                rb_ary_push(insn, ID2SYM(rb_intern("memory_end_push")));
                rb_ary_push(insn, read_memnum(&cursor));
                break;

            case OP_MEMORY_END_PUSH_REC:
                rb_ary_push(insn, ID2SYM(rb_intern("memory_end_push_rec")));
                rb_ary_push(insn, read_memnum(&cursor));
                break;

            case OP_MEMORY_END:
                rb_ary_push(insn, ID2SYM(rb_intern("memory_end")));
                rb_ary_push(insn, read_memnum(&cursor));
                break;

            case OP_MEMORY_END_REC:
                rb_ary_push(insn, ID2SYM(rb_intern("memory_end_rec")));
                rb_ary_push(insn, read_memnum(&cursor));
                break;

            case OP_KEEP: {
                rb_ary_push(insn, ID2SYM(rb_intern("keep")));
                break;
            }
            case OP_FAIL: {
                rb_ary_push(insn, ID2SYM(rb_intern("fail")));
                break;
            }
            case OP_JUMP: {
                rb_ary_push(insn, ID2SYM(rb_intern("jump")));
                rb_ary_push(insn, read_reladdr(&cursor));
                break;
            }
            case OP_PUSH: {
                rb_ary_push(insn, ID2SYM(rb_intern("push")));
                rb_ary_push(insn, read_reladdr(&cursor));
                break;
            }
            case OP_POP: {
                rb_ary_push(insn, ID2SYM(rb_intern("pop")));
                break;
            }
            case OP_PUSH_OR_JUMP_EXACT1: {
                rb_ary_push(insn, ID2SYM(rb_intern("push_or_jump_exact1")));
                rb_ary_push(insn, read_reladdr(&cursor));
                rb_ary_push(insn, read_exact(&cursor, 1, encoding));
                break;
            }
            case OP_PUSH_IF_PEEK_NEXT: {
                rb_ary_push(insn, ID2SYM(rb_intern("push_if_peek_next")));
                rb_ary_push(insn, read_reladdr(&cursor));
                rb_ary_push(insn, read_exact(&cursor, 1, encoding));
                break;
            }
            case OP_REPEAT: {
                rb_ary_push(insn, ID2SYM(rb_intern("repeat")));
                rb_ary_push(insn, read_memnum(&cursor));
                rb_ary_push(insn, read_reladdr(&cursor));
                break;
            }
            case OP_REPEAT_NG: {
                rb_ary_push(insn, ID2SYM(rb_intern("repeat_ng")));
                rb_ary_push(insn, read_memnum(&cursor));
                rb_ary_push(insn, read_reladdr(&cursor));
                break;
            }
            case OP_REPEAT_INC: {
                rb_ary_push(insn, ID2SYM(rb_intern("repeat_inc")));
                rb_ary_push(insn, read_memnum(&cursor));
                break;
            }
            case OP_REPEAT_INC_NG: {
                rb_ary_push(insn, ID2SYM(rb_intern("repeat_inc_ng")));
                rb_ary_push(insn, read_memnum(&cursor));
                break;
            }
            case OP_REPEAT_INC_SG: {
                rb_ary_push(insn, ID2SYM(rb_intern("repeat_inc_sg")));
                rb_ary_push(insn, read_memnum(&cursor));
                break;
            }
            case OP_REPEAT_INC_NG_SG: {
                rb_ary_push(insn, ID2SYM(rb_intern("repeat_inc_ng_sg")));
                rb_ary_push(insn, read_memnum(&cursor));
                break;
            }
            case OP_NULL_CHECK_START: {
                rb_ary_push(insn, ID2SYM(rb_intern("null_check_start")));
                rb_ary_push(insn, read_memnum(&cursor));
                break;
            }
            case OP_NULL_CHECK_END: {
                rb_ary_push(insn, ID2SYM(rb_intern("null_check_end")));
                rb_ary_push(insn, read_memnum(&cursor));
                break;
            }
            case OP_NULL_CHECK_END_MEMST: {
                rb_ary_push(insn, ID2SYM(rb_intern("null_check_end_memst")));
                rb_ary_push(insn, read_memnum(&cursor));
                break;
            }
            case OP_NULL_CHECK_END_MEMST_PUSH: {
                rb_ary_push(insn, ID2SYM(rb_intern("null_check_end_memst_push")));
                rb_ary_push(insn, read_memnum(&cursor));
                break;
            }
            case OP_PUSH_POS: {
                rb_ary_push(insn, ID2SYM(rb_intern("push_pos")));
                break;
            }
            case OP_POP_POS: {
                rb_ary_push(insn, ID2SYM(rb_intern("pop_pos")));
                break;
            }
            case OP_PUSH_POS_NOT: {
                rb_ary_push(insn, ID2SYM(rb_intern("push_pos_not")));
                rb_ary_push(insn, read_reladdr(&cursor));
                break;
            }
            case OP_FAIL_POS: {
                rb_ary_push(insn, ID2SYM(rb_intern("fail_pos")));
                break;
            }
            case OP_PUSH_STOP_BT: {
                rb_ary_push(insn, ID2SYM(rb_intern("push_stop_bt")));
                break;
            }
            case OP_POP_STOP_BT: {
                rb_ary_push(insn, ID2SYM(rb_intern("pop_stop_bt")));
                break;
            }
            case OP_LOOK_BEHIND: {
                rb_ary_push(insn, ID2SYM(rb_intern("look_behind")));
                rb_ary_push(insn, read_length(&cursor));
                break;
            }
            case OP_PUSH_LOOK_BEHIND_NOT: {
                rb_ary_push(insn, ID2SYM(rb_intern("push_look_behind_not")));
                rb_ary_push(insn, read_reladdr(&cursor));
                rb_ary_push(insn, read_length(&cursor));
                break;
            }
            case OP_FAIL_LOOK_BEHIND_NOT: {
                rb_ary_push(insn, ID2SYM(rb_intern("fail_look_behind_not")));
                break;
            }
            case OP_PUSH_ABSENT_POS: {
                rb_ary_push(insn, ID2SYM(rb_intern("push_absent_pos")));
                break;
            }
            case OP_ABSENT: {
                rb_ary_push(insn, ID2SYM(rb_intern("absent")));
                rb_ary_push(insn, read_reladdr(&cursor));
                break;
            }
            case OP_ABSENT_END: {
                rb_ary_push(insn, ID2SYM(rb_intern("absent_end")));
                break;
            }
            case OP_CALL: {
                rb_ary_push(insn, ID2SYM(rb_intern("call")));
                rb_ary_push(insn, read_absaddr(&cursor));
                break;
            }
            case OP_RETURN: {
                rb_ary_push(insn, ID2SYM(rb_intern("return")));
                break;
            }
            case OP_CONDITION: {
                rb_ary_push(insn, ID2SYM(rb_intern("condition")));
                rb_ary_push(insn, read_memnum(&cursor));
                rb_ary_push(insn, read_reladdr(&cursor));
                break;
            }
            case OP_STATE_CHECK_PUSH: {
                rb_ary_push(insn, ID2SYM(rb_intern("state_check_push")));
                rb_ary_push(insn, read_state_check(&cursor));
                rb_ary_push(insn, read_reladdr(&cursor));
                break;
            }
            case OP_STATE_CHECK_PUSH_OR_JUMP: {
                rb_ary_push(insn, ID2SYM(rb_intern("state_check_push_or_jump")));
                rb_ary_push(insn, read_state_check(&cursor));
                rb_ary_push(insn, read_reladdr(&cursor));
                break;
            }
            case OP_STATE_CHECK: {
                rb_ary_push(insn, ID2SYM(rb_intern("state_check")));
                rb_ary_push(insn, read_state_check(&cursor));
                break;
            }
            case OP_STATE_CHECK_ANYCHAR_STAR: {
                rb_ary_push(insn, ID2SYM(rb_intern("state_check_anychar_star")));
                rb_ary_push(insn, read_state_check(&cursor));
                break;
            }
            case OP_STATE_CHECK_ANYCHAR_ML_STAR: {
                rb_ary_push(insn, ID2SYM(rb_intern("state_check_anychar_ml_star")));
                rb_ary_push(insn, read_state_check(&cursor));
                break;
            }
            case OP_SET_OPTION_PUSH: {
                rb_ary_push(insn, ID2SYM(rb_intern("set_option_push")));
                rb_ary_push(insn, read_option(&cursor));
                break;
            }
            case OP_SET_OPTION: {
                rb_ary_push(insn, ID2SYM(rb_intern("set_option")));
                rb_ary_push(insn, read_option(&cursor));
                break;
            }
        }

        rb_ary_push(insns, insn);
    }

    onig_free(regex);
    onig_end();
    return insns;
}

.parse(string) ⇒ Object



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
# File 'ext/onigmo/onigmo.c', line 284

static VALUE
parse(VALUE self, VALUE string) {
    const OnigUChar *pattern = (const OnigUChar *) StringValueCStr(string); 
    const OnigUChar *pattern_end = pattern + strlen((const char *) pattern);

    regex_t *regex = calloc(1, sizeof(regex_t));
    if (regex == NULL) {
        rb_raise(rb_eNoMemError, "failed to allocate memory");
        return Qnil;
    }

    int result;
    OnigEncoding encoding = rb_enc_get(string);

    if ((result = onig_reg_init(regex, ONIG_OPTION_DEFAULT, ONIGENC_CASE_FOLD_DEFAULT, encoding, ONIG_SYNTAX_DEFAULT)) != ONIG_NORMAL) {
        fail(result, regex, NULL);
        return Qnil;
    }

    OnigDistance init_size = (pattern_end - pattern) * 2;
    result = BBUF_INIT(regex, init_size);

    if (result != ONIG_NORMAL) {
        fail(result, regex, NULL);
        return Qnil;
    }

    Node *root;
    ScanEnv scan_env = { 0 };

    result = onig_parse_make_tree(&root, pattern, pattern_end, regex, &scan_env);
    if (result != ONIG_NORMAL) {
        fail(result, regex, NULL);
        return Qnil;
    }

    VALUE node = build_node(root, encoding);

    onig_node_free(root);
    onig_free(regex);
    onig_end();

    return node;
}