Module: Unicode

Defined in:
ext/unicode/unicode.c

Constant Summary collapse

VERSION = 
rb_str_new2(UNICODE_VERSION)

Class Method Summary collapse

Class Method Details

.abbr_categories(str) ⇒ Object

wstr will be freed in get_text_elements_ensure()



1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
 
# File 'ext/unicode/unicode.c', line 1045

VALUE
unicode_get_abbr_categories(VALUE obj, VALUE str)
{
  WString wstr;
  get_categories_param param = { &wstr, str, catname_abbr };

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&wstr, RSTRING_PTR(str), RSTRING_LEN(str));

  return rb_ensure(get_categories_internal, (VALUE)&param,
                   get_categories_ensure, (VALUE)&wstr);
  /* wstr will be freed in get_text_elements_ensure() */
}

.capitalize(str) ⇒ Object 



964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
 
# File 'ext/unicode/unicode.c', line 964

static VALUE
unicode_capitalize(VALUE obj, VALUE str)
{
  WString ustr;
  WString result;
  UString ret;
  VALUE vret;

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&ustr, RSTRING_PTR(str), RSTRING_LEN(str));
  WStr_alloc(&result);
  capitalize_internal(&ustr, &result);
  //sort_canonical(&result);
  WStr_free(&ustr);
  UniStr_alloc(&ret);
  WStr_convertIntoUString(&result, &ret);
  WStr_free(&result);
  vret = TO_(str, ENC_(rb_str_new((char*)ret.str, ret.len)));
  UniStr_free(&ret);

  return vret;
}

.categories(str) ⇒ Object 



1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
 
# File 'ext/unicode/unicode.c', line 1027

VALUE
unicode_get_categories(VALUE obj, VALUE str)
{
  WString wstr;
  get_categories_param param = { &wstr, str, catname_long };

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&wstr, RSTRING_PTR(str), RSTRING_LEN(str));

  return rb_ensure(get_categories_internal, (VALUE)&param,
                   get_categories_ensure, (VALUE)&wstr);
  /* wstr will be freed in get_text_elements_ensure() */
}

.compose(str) ⇒ Object 



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
 
# File 'ext/unicode/unicode.c', line 791

static VALUE
unicode_compose(VALUE obj, VALUE str)
{
  WString ustr;
  WString result;
  UString ret;
  VALUE vret;

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&ustr, RSTRING_PTR(str), RSTRING_LEN(str));
  sort_canonical(&ustr);
  WStr_alloc(&result);
  compose_internal(&ustr, &result);
  WStr_free(&ustr);
  UniStr_alloc(&ret);
  WStr_convertIntoUString(&result, &ret);
  WStr_free(&result);
  vret = TO_(str, ENC_(rb_str_new((char*)ret.str, ret.len)));
  UniStr_free(&ret);

  return vret;
}

.decompose(str) ⇒ Object 



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
 
# File 'ext/unicode/unicode.c', line 713

static VALUE
unicode_decompose(VALUE obj, VALUE str)
{
  WString ustr;
  WString result;
  UString ret;
  VALUE vret;

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&ustr, RSTRING_PTR(str), RSTRING_LEN(str));
  WStr_alloc(&result);
  decompose_internal(&ustr, &result);
  WStr_free(&ustr);
  sort_canonical(&result);
  UniStr_alloc(&ret);
  WStr_convertIntoUString(&result, &ret);
  WStr_free(&result);
  vret = TO_(str, ENC_(rb_str_new((char*)ret.str, ret.len)));
  UniStr_free(&ret);

  return vret;
}

.decompose_compat(str) ⇒ Object 



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
 
# File 'ext/unicode/unicode.c', line 765

static VALUE
unicode_decompose_compat(VALUE obj, VALUE str)
{
  WString ustr;
  WString result;
  UString ret;
  VALUE vret;

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&ustr, RSTRING_PTR(str), RSTRING_LEN(str));
  WStr_alloc(&result);
  decompose_compat_internal(&ustr, &result);
  WStr_free(&ustr);
  sort_canonical(&result);
  UniStr_alloc(&ret);
  WStr_convertIntoUString(&result, &ret);
  WStr_free(&result);
  vret = TO_(str, ENC_(rb_str_new((char*)ret.str, ret.len)));
  UniStr_free(&ret);

  return vret;
}

.decompose_safe(str) ⇒ Object 



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
 
# File 'ext/unicode/unicode.c', line 739

static VALUE
unicode_decompose_safe(VALUE obj, VALUE str)
{
  WString ustr;
  WString result;
  UString ret;
  VALUE vret;

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&ustr, RSTRING_PTR(str), RSTRING_LEN(str));
  WStr_alloc(&result);
  decompose_safe_internal(&ustr, &result);
  WStr_free(&ustr);
  sort_canonical(&result);
  UniStr_alloc(&ret);
  WStr_convertIntoUString(&result, &ret);
  WStr_free(&result);
  vret = TO_(str, ENC_(rb_str_new((char*)ret.str, ret.len)));
  UniStr_free(&ret);

  return vret;
}

.downcase(str) ⇒ Object 



933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
 
# File 'ext/unicode/unicode.c', line 933

static VALUE
unicode_downcase(VALUE obj, VALUE str)
{
  WString ustr;
  WString result;
  UString ret;
  VALUE vret;

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&ustr, RSTRING_PTR(str), RSTRING_LEN(str));
  WStr_alloc(&result);
  downcase_internal(&ustr, &result);
  //sort_canonical(&result);
  WStr_free(&ustr);
  UniStr_alloc(&ret);
  WStr_convertIntoUString(&result, &ret);
  WStr_free(&result);
  vret = TO_(str, ENC_(rb_str_new((char*)ret.str, ret.len)));
  UniStr_free(&ret);

  return vret;
}

.nfc(str) ⇒ Object 



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
 
# File 'ext/unicode/unicode.c', line 817

static VALUE
unicode_normalize_C(VALUE obj, VALUE str)
{
  WString ustr1;
  WString ustr2;
  WString result;
  UString ret;
  VALUE vret;

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&ustr1, RSTRING_PTR(str), RSTRING_LEN(str));
  WStr_alloc(&ustr2);
  decompose_internal(&ustr1, &ustr2);
  WStr_free(&ustr1);
  sort_canonical(&ustr2);
  WStr_alloc(&result);
  compose_internal(&ustr2, &result);
  WStr_free(&ustr2);
  UniStr_alloc(&ret);
  WStr_convertIntoUString(&result, &ret);
  WStr_free(&result);
  vret = TO_(str, ENC_(rb_str_new((char*)ret.str, ret.len)));
  UniStr_free(&ret);

  return vret;
}

.nfc_safe(str) ⇒ Object 



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
 
# File 'ext/unicode/unicode.c', line 847

static VALUE
unicode_normalize_safe(VALUE obj, VALUE str)
{
  WString ustr1;
  WString ustr2;
  WString result;
  UString ret;
  VALUE vret;

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&ustr1, RSTRING_PTR(str), RSTRING_LEN(str));
  WStr_alloc(&ustr2);
  decompose_safe_internal(&ustr1, &ustr2);
  WStr_free(&ustr1);
  sort_canonical(&ustr2);
  WStr_alloc(&result);
  compose_internal(&ustr2, &result);
  WStr_free(&ustr2);
  UniStr_alloc(&ret);
  WStr_convertIntoUString(&result, &ret);
  WStr_free(&result);
  vret = TO_(str, ENC_(rb_str_new((char*)ret.str, ret.len)));
  UniStr_free(&ret);

  return vret;
}

.nfd(str) ⇒ Object

aliases



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
 
# File 'ext/unicode/unicode.c', line 713

static VALUE
unicode_decompose(VALUE obj, VALUE str)
{
  WString ustr;
  WString result;
  UString ret;
  VALUE vret;

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&ustr, RSTRING_PTR(str), RSTRING_LEN(str));
  WStr_alloc(&result);
  decompose_internal(&ustr, &result);
  WStr_free(&ustr);
  sort_canonical(&result);
  UniStr_alloc(&ret);
  WStr_convertIntoUString(&result, &ret);
  WStr_free(&result);
  vret = TO_(str, ENC_(rb_str_new((char*)ret.str, ret.len)));
  UniStr_free(&ret);

  return vret;
}

.nfd_safe(str) ⇒ Object 



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
 
# File 'ext/unicode/unicode.c', line 739

static VALUE
unicode_decompose_safe(VALUE obj, VALUE str)
{
  WString ustr;
  WString result;
  UString ret;
  VALUE vret;

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&ustr, RSTRING_PTR(str), RSTRING_LEN(str));
  WStr_alloc(&result);
  decompose_safe_internal(&ustr, &result);
  WStr_free(&ustr);
  sort_canonical(&result);
  UniStr_alloc(&ret);
  WStr_convertIntoUString(&result, &ret);
  WStr_free(&result);
  vret = TO_(str, ENC_(rb_str_new((char*)ret.str, ret.len)));
  UniStr_free(&ret);

  return vret;
}

.nfkc(str) ⇒ Object 



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
 
# File 'ext/unicode/unicode.c', line 877

static VALUE
unicode_normalize_KC(VALUE obj, VALUE str)
{
  WString ustr1;
  WString ustr2;
  WString result;
  UString ret;
  VALUE vret;

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&ustr1, RSTRING_PTR(str), RSTRING_LEN(str));
  WStr_alloc(&ustr2);
  decompose_compat_internal(&ustr1, &ustr2);
  WStr_free(&ustr1);
  sort_canonical(&ustr2);
  WStr_alloc(&result);
  compose_internal(&ustr2, &result);
  WStr_free(&ustr2);
  UniStr_alloc(&ret);
  WStr_convertIntoUString(&result, &ret);
  WStr_free(&result);
  vret = TO_(str, ENC_(rb_str_new((char*)ret.str, ret.len)));
  UniStr_free(&ret);

  return vret;
}

.nfkd(str) ⇒ Object 



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
 
# File 'ext/unicode/unicode.c', line 765

static VALUE
unicode_decompose_compat(VALUE obj, VALUE str)
{
  WString ustr;
  WString result;
  UString ret;
  VALUE vret;

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&ustr, RSTRING_PTR(str), RSTRING_LEN(str));
  WStr_alloc(&result);
  decompose_compat_internal(&ustr, &result);
  WStr_free(&ustr);
  sort_canonical(&result);
  UniStr_alloc(&ret);
  WStr_convertIntoUString(&result, &ret);
  WStr_free(&result);
  vret = TO_(str, ENC_(rb_str_new((char*)ret.str, ret.len)));
  UniStr_free(&ret);

  return vret;
}

.normalize_C(str) ⇒ Object 



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
 
# File 'ext/unicode/unicode.c', line 817

static VALUE
unicode_normalize_C(VALUE obj, VALUE str)
{
  WString ustr1;
  WString ustr2;
  WString result;
  UString ret;
  VALUE vret;

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&ustr1, RSTRING_PTR(str), RSTRING_LEN(str));
  WStr_alloc(&ustr2);
  decompose_internal(&ustr1, &ustr2);
  WStr_free(&ustr1);
  sort_canonical(&ustr2);
  WStr_alloc(&result);
  compose_internal(&ustr2, &result);
  WStr_free(&ustr2);
  UniStr_alloc(&ret);
  WStr_convertIntoUString(&result, &ret);
  WStr_free(&result);
  vret = TO_(str, ENC_(rb_str_new((char*)ret.str, ret.len)));
  UniStr_free(&ret);

  return vret;
}

.normalize_C_safe(str) ⇒ Object 



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
 
# File 'ext/unicode/unicode.c', line 847

static VALUE
unicode_normalize_safe(VALUE obj, VALUE str)
{
  WString ustr1;
  WString ustr2;
  WString result;
  UString ret;
  VALUE vret;

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&ustr1, RSTRING_PTR(str), RSTRING_LEN(str));
  WStr_alloc(&ustr2);
  decompose_safe_internal(&ustr1, &ustr2);
  WStr_free(&ustr1);
  sort_canonical(&ustr2);
  WStr_alloc(&result);
  compose_internal(&ustr2, &result);
  WStr_free(&ustr2);
  UniStr_alloc(&ret);
  WStr_convertIntoUString(&result, &ret);
  WStr_free(&result);
  vret = TO_(str, ENC_(rb_str_new((char*)ret.str, ret.len)));
  UniStr_free(&ret);

  return vret;
}

.normalize_D(str) ⇒ Object 



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
 
# File 'ext/unicode/unicode.c', line 713

static VALUE
unicode_decompose(VALUE obj, VALUE str)
{
  WString ustr;
  WString result;
  UString ret;
  VALUE vret;

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&ustr, RSTRING_PTR(str), RSTRING_LEN(str));
  WStr_alloc(&result);
  decompose_internal(&ustr, &result);
  WStr_free(&ustr);
  sort_canonical(&result);
  UniStr_alloc(&ret);
  WStr_convertIntoUString(&result, &ret);
  WStr_free(&result);
  vret = TO_(str, ENC_(rb_str_new((char*)ret.str, ret.len)));
  UniStr_free(&ret);

  return vret;
}

.normalize_D_safe(str) ⇒ Object 



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
 
# File 'ext/unicode/unicode.c', line 739

static VALUE
unicode_decompose_safe(VALUE obj, VALUE str)
{
  WString ustr;
  WString result;
  UString ret;
  VALUE vret;

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&ustr, RSTRING_PTR(str), RSTRING_LEN(str));
  WStr_alloc(&result);
  decompose_safe_internal(&ustr, &result);
  WStr_free(&ustr);
  sort_canonical(&result);
  UniStr_alloc(&ret);
  WStr_convertIntoUString(&result, &ret);
  WStr_free(&result);
  vret = TO_(str, ENC_(rb_str_new((char*)ret.str, ret.len)));
  UniStr_free(&ret);

  return vret;
}

.normalize_KC(str) ⇒ Object 



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
 
# File 'ext/unicode/unicode.c', line 877

static VALUE
unicode_normalize_KC(VALUE obj, VALUE str)
{
  WString ustr1;
  WString ustr2;
  WString result;
  UString ret;
  VALUE vret;

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&ustr1, RSTRING_PTR(str), RSTRING_LEN(str));
  WStr_alloc(&ustr2);
  decompose_compat_internal(&ustr1, &ustr2);
  WStr_free(&ustr1);
  sort_canonical(&ustr2);
  WStr_alloc(&result);
  compose_internal(&ustr2, &result);
  WStr_free(&ustr2);
  UniStr_alloc(&ret);
  WStr_convertIntoUString(&result, &ret);
  WStr_free(&result);
  vret = TO_(str, ENC_(rb_str_new((char*)ret.str, ret.len)));
  UniStr_free(&ret);

  return vret;
}

.normalize_KD(str) ⇒ Object 



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
 
# File 'ext/unicode/unicode.c', line 765

static VALUE
unicode_decompose_compat(VALUE obj, VALUE str)
{
  WString ustr;
  WString result;
  UString ret;
  VALUE vret;

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&ustr, RSTRING_PTR(str), RSTRING_LEN(str));
  WStr_alloc(&result);
  decompose_compat_internal(&ustr, &result);
  WStr_free(&ustr);
  sort_canonical(&result);
  UniStr_alloc(&ret);
  WStr_convertIntoUString(&result, &ret);
  WStr_free(&result);
  vret = TO_(str, ENC_(rb_str_new((char*)ret.str, ret.len)));
  UniStr_free(&ret);

  return vret;
}

.strcmp(str1, str2) ⇒ Object 



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
 
# File 'ext/unicode/unicode.c', line 629

static VALUE
unicode_strcmp(VALUE obj, VALUE str1, VALUE str2)
{
  WString wstr1;
  WString wstr2;
  WString result1;
  WString result2;
  UString ustr1;
  UString ustr2;
  int ret;

  Check_Type(str1, T_STRING);
  Check_Type(str2, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str1);
  CONVERT_TO_UTF8(str2);
#endif
  WStr_allocWithUTF8L(&wstr1, RSTRING_PTR(str1), RSTRING_LEN(str1));
  WStr_allocWithUTF8L(&wstr2, RSTRING_PTR(str2), RSTRING_LEN(str2));
  WStr_alloc(&result1);
  WStr_alloc(&result2);
  decompose_internal(&wstr1, &result1);
  decompose_internal(&wstr2, &result2);
  WStr_free(&wstr1);
  WStr_free(&wstr2);
  sort_canonical(&result1);
  sort_canonical(&result2);
  UniStr_alloc(&ustr1);
  UniStr_alloc(&ustr2);
  WStr_convertIntoUString(&result1, &ustr1);
  WStr_convertIntoUString(&result2, &ustr2);
  WStr_free(&result1);
  WStr_free(&result2);
  UniStr_addChar(&ustr1, '\0');
  UniStr_addChar(&ustr2, '\0');
  ret = strcmp((char*)ustr1.str, (char*)ustr2.str);
  UniStr_free(&ustr1);
  UniStr_free(&ustr2);

  return INT2FIX(ret);
}

.strcmp_compat(str1, str2) ⇒ Object 



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
 
# File 'ext/unicode/unicode.c', line 671

static VALUE
unicode_strcmp_compat(VALUE obj, VALUE str1, VALUE str2)
{
  WString wstr1;
  WString wstr2;
  WString result1;
  WString result2;
  UString ustr1;
  UString ustr2;
  int ret;

  Check_Type(str1, T_STRING);
  Check_Type(str2, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str1);
  CONVERT_TO_UTF8(str2);
#endif
  WStr_allocWithUTF8L(&wstr1, RSTRING_PTR(str1), RSTRING_LEN(str1));
  WStr_allocWithUTF8L(&wstr2, RSTRING_PTR(str2), RSTRING_LEN(str2));
  WStr_alloc(&result1);
  WStr_alloc(&result2);
  decompose_compat_internal(&wstr1, &result1);
  decompose_compat_internal(&wstr2, &result2);
  WStr_free(&wstr1);
  WStr_free(&wstr2);
  sort_canonical(&result1);
  sort_canonical(&result2);
  UniStr_alloc(&ustr1);
  UniStr_alloc(&ustr2);
  WStr_convertIntoUString(&result1, &ustr1);
  WStr_convertIntoUString(&result2, &ustr2);
  WStr_free(&result1);
  WStr_free(&result2);
  UniStr_addChar(&ustr1, '\0');
  UniStr_addChar(&ustr2, '\0');
  ret = strcmp((char*)ustr1.str, (char*)ustr2.str);
  UniStr_free(&ustr1);
  UniStr_free(&ustr2);

  return INT2FIX(ret);
}

.text_elements(str) ⇒ Object 



1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
 
# File 'ext/unicode/unicode.c', line 1215

VALUE
unicode_get_text_elements(VALUE obj, VALUE str)
{
  WString wstr;
  get_text_elements_param param = { &wstr, str };

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&wstr, RSTRING_PTR(str), RSTRING_LEN(str));

  return rb_ensure(get_text_elements_internal, (VALUE)&param,
                   get_text_elements_ensure, (VALUE)&wstr);
  /* wstr will be freed in get_text_elements_ensure() */
}

.upcase(str) ⇒ Object 



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
 
# File 'ext/unicode/unicode.c', line 907

static VALUE
unicode_upcase(VALUE obj, VALUE str)
{
  WString ustr;
  WString result;
  UString ret;
  VALUE vret;

  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&ustr, RSTRING_PTR(str), RSTRING_LEN(str));
  WStr_alloc(&result);
  upcase_internal(&ustr, &result);
  //sort_canonical(&result);
  WStr_free(&ustr);
  UniStr_alloc(&ret);
  WStr_convertIntoUString(&result, &ret);
  WStr_free(&result);
  vret = TO_(str, ENC_(rb_str_new((char*)ret.str, ret.len)));
  UniStr_free(&ret);

  return vret;
}

.width(*args) ⇒ Object

wstr will be freed in get_text_elements_ensure()



1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
 
# File 'ext/unicode/unicode.c', line 1062

VALUE
unicode_wcswidth(int argc, VALUE* argv, VALUE obj)
{
  WString wstr;
  int i, count;
  int width = 0;
  int cjk_p = 0;
  VALUE str;
  VALUE cjk;

  count = rb_scan_args(argc, argv, "11", &str, &cjk);
  if (count > 1)
    cjk_p = RTEST(cjk);
  Check_Type(str, T_STRING);
#ifdef HAVE_RUBY_ENCODING_H
  CONVERT_TO_UTF8(str);
#endif
  WStr_allocWithUTF8L(&wstr, RSTRING_PTR(str), RSTRING_LEN(str));
  for (i = 0; i <wstr.len; i++) {
    int c = wstr.str[i];
    int cat = get_gencat(c);
    int eaw = get_eawidth(c);
    if ((c > 0 && c < 32) || (c >= 0x7f && c < 0xa0)) {
      /* Control Characters */
      width = -1;
      break;
    }
    else if (c != 0x00ad && /* SOFT HYPHEN */
             (cat == c_Mn || cat == c_Me || /* Non-spacing Marks */
              cat == c_Cf || /* Format */
              c == 0 || /* NUL */
              (c >= 0x1160 && c <= 0x11ff))) /* HANGUL JUNGSEONG/JONGSEONG */
      /* zero width */ ;
    else if (eaw == w_F || eaw == w_W || /* Fullwidth or Wide */
             (c >= 0x4db6 && c <= 0x4dbf) || /* CJK Reserved */
             (c >= 0x9fcd && c <= 0x9fff) || /* CJK Reserved */
             (c >= 0xfa6e && c <= 0xfa6f) || /* CJK Reserved */
             (c >= 0xfada && c <= 0xfaff) || /* CJK Reserved */
             (c >= 0x2a6d7 && c <= 0x2a6ff) || /* CJK Reserved */
             (c >= 0x2b735 && c <= 0x2b73f) || /* CJK Reserved */
             (c >= 0x2b81e && c <= 0x2f7ff) || /* CJK Reserved */
             (c >= 0x2fa1e && c <= 0x2fffd) || /* CJK Reserved */
             (c >= 0x30000 && c <= 0x3fffd) || /* CJK Reserved */
             (cjk_p && eaw == w_A)) /* East Asian Ambiguous */
      width += 2;
    else
      width++; /* Halfwidth or Neutral */
  }
  WStr_free(&wstr);

  return INT2FIX(width);
}