Class: CharacterSet

Inherits:
Object
  • Object
show all
Extended by:
PredefinedSets
Includes:
SetMethodAdapters, SharedMethods, Enumerable
Defined in:
lib/character_set/pure.rb,
lib/character_set.rb,
lib/character_set/parser.rb,
lib/character_set/writer.rb,
lib/character_set/version.rb,
lib/character_set/character.rb,
lib/character_set/ruby_fallback.rb,
lib/character_set/shared_methods.rb,
lib/character_set/predefined_sets.rb,
lib/character_set/core_ext/regexp_ext.rb,
lib/character_set/core_ext/string_ext.rb,
lib/character_set/set_method_adapters.rb,
lib/character_set/expression_converter.rb,
lib/character_set/ruby_fallback/set_methods.rb,
lib/character_set/ruby_fallback/character_set_methods.rb,
ext/character_set/character_set.c

Overview

Various methods shared by the pure-Ruby and the extended implementation.

Many of these methods are hotspots, so they are defined directly on the including classes for better performance.

Defined Under Namespace

Modules: CoreExt, ExpressionConverter, Parser, PredefinedSets, RubyFallback, SetMethodAdapters, SharedMethods, Writer Classes: Character, Pure

Constant Summary collapse

VERSION =
'1.4.0'

Class Method Summary collapse

Instance Method Summary collapse

Methods included from PredefinedSets

build_from_cps_file

Methods included from SharedMethods

included

Class Method Details

.from_ranges(ranges) ⇒ Object

******************************



679
680
681
682
683
684
685
686
687
688
689
690
# File 'ext/character_set/character_set.c', line 679

static VALUE
cs_class_method_from_ranges(VALUE self, VALUE ranges)
{
  VALUE new_cs, range_count, i;
  new_cs = rb_class_new_instance(0, 0, self);
  range_count = RARRAY_LEN(ranges);
  for (i = 0; i < range_count; i++)
  {
    cs_merge_rb_range(new_cs, RARRAY_AREF(ranges, i));
  }
  return new_cs;
}

.of(str) ⇒ Object



1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
# File 'ext/character_set/character_set.c', line 1047

static VALUE
cs_class_method_of(VALUE self, VALUE str)
{
  VALUE new_cs;
  struct cs_data *new_data;
  new_cs = cs_alloc(self, &new_data);
  raise_arg_err_unless_string(str);
  each_cp(str, add_str_cp_to_arr, 0, 0, new_data, 0);
  return new_cs;
}

Instance Method Details

#&(other) ⇒ Object



330
331
332
333
334
# File 'ext/character_set/character_set.c', line 330

static VALUE
cs_method_intersection(VALUE self, VALUE other)
{
  RETURN_COMBINED_CS(self, other, &&);
}

#+(other) ⇒ Object



342
343
344
345
346
# File 'ext/character_set/character_set.c', line 342

static VALUE
cs_method_union(VALUE self, VALUE other)
{
  RETURN_COMBINED_CS(self, other, ||);
}

#-(other) ⇒ Object



348
349
350
351
352
# File 'ext/character_set/character_set.c', line 348

static VALUE
cs_method_difference(VALUE self, VALUE other)
{
  RETURN_COMBINED_CS(self, other, >);
}

#<(other) ⇒ Object



653
654
655
656
657
658
659
# File 'ext/character_set/character_set.c', line 653

static VALUE
cs_method_proper_subset_p(VALUE self, VALUE other)
{
  int is_subset, is_proper;
  is_subset = cs_a_subset_of_b(self, other, &is_proper);
  return (is_subset && is_proper) ? Qtrue : Qfalse;
}

#<<(cp_num) ⇒ Object



392
393
394
395
396
# File 'ext/character_set/character_set.c', line 392

static VALUE
cs_method_add(VALUE self, VALUE cp_num)
{
  return cs_toggle_codepoint(self, cp_num, 1, 0);
}

#<=(other) ⇒ Object



647
648
649
650
651
# File 'ext/character_set/character_set.c', line 647

static VALUE
cs_method_subset_p(VALUE self, VALUE other)
{
  return cs_a_subset_of_b(self, other, NULL) ? Qtrue : Qfalse;
}

#==(other) ⇒ Object



462
463
464
465
466
467
468
469
470
471
472
473
474
# File 'ext/character_set/character_set.c', line 462

static VALUE
cs_method_eql_p(VALUE self, VALUE other)
{
  if (!cs_check_type(other))
  {
    return Qfalse;
  }
  if (self == other) // same object_id
  {
    return Qtrue;
  }
  return cs_cps_eql(self, other);
}

#===(num) ⇒ Object



354
355
356
357
358
359
360
361
# File 'ext/character_set/character_set.c', line 354

static VALUE
cs_method_include_p(VALUE self, VALUE num)
{
  cs_ar *cps;
  cs_cp len;
  cps = cs_fetch_cps(self, &len);
  return (tst_cp(cps, len, FIX2ULONG(num)) ? Qtrue : Qfalse);
}

#>(other) ⇒ Object



667
668
669
670
671
672
673
# File 'ext/character_set/character_set.c', line 667

static VALUE
cs_method_proper_superset_p(VALUE self, VALUE other)
{
  int is_superset, is_proper;
  is_superset = cs_a_subset_of_b(other, self, &is_proper);
  return (is_superset && is_proper) ? Qtrue : Qfalse;
}

#>=(other) ⇒ Object



661
662
663
664
665
# File 'ext/character_set/character_set.c', line 661

static VALUE
cs_method_superset_p(VALUE self, VALUE other)
{
  return cs_a_subset_of_b(other, self, NULL) ? Qtrue : Qfalse;
}

#^(other) ⇒ Object



336
337
338
339
340
# File 'ext/character_set/character_set.c', line 336

static VALUE
cs_method_exclusion(VALUE self, VALUE other)
{
  RETURN_COMBINED_CS(self, other, ^);
}

#add(cp_num) ⇒ Object



392
393
394
395
396
# File 'ext/character_set/character_set.c', line 392

static VALUE
cs_method_add(VALUE self, VALUE cp_num)
{
  return cs_toggle_codepoint(self, cp_num, 1, 0);
}

#add?(cp_num) ⇒ Boolean

Returns:

  • (Boolean)


398
399
400
401
402
# File 'ext/character_set/character_set.c', line 398

static VALUE
cs_method_add_p(VALUE self, VALUE cp_num)
{
  return cs_toggle_codepoint(self, cp_num, 1, 1);
}

#allocated_lengthObject



1276
1277
1278
1279
1280
# File 'ext/character_set/character_set.c', line 1276

static VALUE
cs_method_allocated_length(VALUE self)
{
  return LONG2FIX(cs_fetch_data(self)->len);
}

#case_insensitiveObject



924
925
926
927
928
929
930
931
932
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
958
959
960
961
962
# File 'ext/character_set/character_set.c', line 924

static VALUE
cs_method_case_insensitive(VALUE self)
{
  cs_cp i, len;
  cs_ar *cps;
  VALUE new_cs;
  struct cs_data *new_data;

  cps = cs_fetch_cps(self, &len);
  new_cs = cs_alloc(RBASIC(self)->klass, &new_data);
  cs_merge_cs(new_cs, self);

  for (i = 0; i < CASEFOLD_COUNT; i++)
  {
    casefold_mapping m = unicode_casefold_table[i];

    if (tst_cp(cps, len, m.from))
    {
      set_cp(new_data, m.to);
    }
    else if (tst_cp(cps, len, m.to))
    {
      set_cp(new_data, m.from);
    }
  }

  return new_cs;

  // OnigCaseFoldType flags;
  // rb_encoding *enc;
  //
  // enc = rb_utf8_encoding();
  //
  // ONIGENC_CASE_UPCASE | ONIGENC_CASE_DOWNCASE (not public on ruby < 2.4)
  // flags = (1<<13) | (1<<14);
  //
  // // case_map args: flags, pp, end, to, to_end, enc
  // enc->case_map(flags, (const OnigUChar**)&cp, ?, ?, ?, enc);
}

#clearObject



266
267
268
269
270
271
272
273
274
# File 'ext/character_set/character_set.c', line 266

static VALUE
cs_method_clear(VALUE self)
{
  struct cs_data *data;
  rb_check_frozen(self);
  data = cs_fetch_data(self);
  memset(data->cps, 0, CS_MSIZE(data->len));
  return self;
}

#count_in(str) ⇒ Object



1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
# File 'ext/character_set/character_set.c', line 1068

static VALUE
cs_method_count_in(VALUE self, VALUE str)
{
  VALUE count;
  struct cs_data *data;
  raise_arg_err_unless_string(str);
  data = cs_fetch_data(self);
  count = 0;
  each_cp(str, count_str_cp, data->cps, data->len, data, &count);
  return INT2NUM(count);
}

#cover?(str) ⇒ Boolean

Returns:

  • (Boolean)


1086
1087
1088
1089
1090
1091
1092
1093
# File 'ext/character_set/character_set.c', line 1086

static VALUE
cs_method_cover_p(VALUE self, VALUE str)
{
  struct cs_data *data;
  raise_arg_err_unless_string(str);
  data = cs_fetch_data(self);
  return each_cp(str, str_cp_in_arr, data->cps, data->len, data, 0);
}

#delete(cp_num) ⇒ Object



404
405
406
407
408
# File 'ext/character_set/character_set.c', line 404

static VALUE
cs_method_delete(VALUE self, VALUE cp_num)
{
  return cs_toggle_codepoint(self, cp_num, 0, 0);
}

#delete?(cp_num) ⇒ Boolean

Returns:

  • (Boolean)


410
411
412
413
414
# File 'ext/character_set/character_set.c', line 410

static VALUE
cs_method_delete_p(VALUE self, VALUE cp_num)
{
  return cs_toggle_codepoint(self, cp_num, 0, 1);
}

#delete_ifObject



252
253
254
255
256
257
# File 'ext/character_set/character_set.c', line 252

static VALUE
cs_method_delete_if(VALUE self)
{
  RETURN_SIZED_ENUMERATOR(self, 0, 0, cs_enumerator_length);
  return cs_delete_if_block_result(self, 1);
}

#delete_in(str) ⇒ Object



1252
1253
1254
1255
1256
# File 'ext/character_set/character_set.c', line 1252

static VALUE
cs_method_delete_in(VALUE self, VALUE str)
{
  return cs_apply_to_str(self, str, 1, 0);
}

#delete_in!(str) ⇒ Object



1258
1259
1260
1261
1262
# File 'ext/character_set/character_set.c', line 1258

static VALUE
cs_method_delete_in_bang(VALUE self, VALUE str)
{
  return cs_apply_to_str(self, str, 1, 1);
}

#difference(other) ⇒ Object



348
349
350
351
352
# File 'ext/character_set/character_set.c', line 348

static VALUE
cs_method_difference(VALUE self, VALUE other)
{
  RETURN_COMBINED_CS(self, other, >);
}

#disjoint?(other) ⇒ Boolean

Returns:

  • (Boolean)


433
434
435
436
437
# File 'ext/character_set/character_set.c', line 433

static VALUE
cs_method_disjoint_p(VALUE self, VALUE other)
{
  return cs_method_intersect_p(self, other) ? Qfalse : Qtrue;
}

#eachObject

Set compatibility methods



175
176
177
178
179
180
181
# File 'ext/character_set/character_set.c', line 175

static VALUE
cs_method_each(VALUE self)
{
  RETURN_SIZED_ENUMERATOR(self, 0, 0, cs_enumerator_length);
  FOR_EACH_ACTIVE_CODEPOINT(rb_yield(LONG2FIX(cp)));
  return self;
}

#empty?Boolean

Returns:

  • (Boolean)


206
207
208
209
210
211
# File 'ext/character_set/character_set.c', line 206

static VALUE
cs_method_empty_p(VALUE self)
{
  FOR_EACH_ACTIVE_CODEPOINT(return Qfalse);
  return Qtrue;
}

#eql?(other) ⇒ Boolean

Returns:

  • (Boolean)


462
463
464
465
466
467
468
469
470
471
472
473
474
# File 'ext/character_set/character_set.c', line 462

static VALUE
cs_method_eql_p(VALUE self, VALUE other)
{
  if (!cs_check_type(other))
  {
    return Qfalse;
  }
  if (self == other) // same object_id
  {
    return Qtrue;
  }
  return cs_cps_eql(self, other);
}

#ext_count_in_section(from, upto) ⇒ Object



773
774
775
776
777
778
779
# File 'ext/character_set/character_set.c', line 773

static VALUE
cs_method_ext_count_in_section(VALUE self, VALUE from, VALUE upto)
{
  cs_cp count;
  count = cs_active_cp_count_in_section(self, FIX2ULONG(from), FIX2ULONG(upto));
  return LONG2FIX(count);
}

#ext_inversion(*args) ⇒ Object



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
# File 'ext/character_set/character_set.c', line 888

static VALUE
cs_method_ext_inversion(int argc, VALUE *argv, VALUE self)
{
  int inc_surr;
  cs_cp upto, cp, len;
  cs_ar *cps;
  VALUE new_cs;
  struct cs_data *new_data;

  rb_check_arity(argc, 0, 2);

  cps = cs_fetch_cps(self, &len);
  inc_surr = argc && argv[0] == Qtrue;
  new_cs = cs_alloc(RBASIC(self)->klass, &new_data);
  upto = argc > 1 && FIXNUM_P(argv[1]) ? FIX2ULONG(argv[1]) : UNICODE_CP_COUNT;

  for (cp = 0; cp < UNICODE_CP_COUNT; cp++)
  {
    if (cp <= upto && !tst_cp(cps, len, cp) && (inc_surr || NON_SURROGATE(cp)))
    {
      set_cp(new_data, cp);
    }
  }

  return new_cs;
}

#ext_section(from, upto) ⇒ Object



751
752
753
754
755
# File 'ext/character_set/character_set.c', line 751

static VALUE
cs_method_ext_section(VALUE self, VALUE from, VALUE upto)
{
  return cs_from_section(self, FIX2ULONG(from), FIX2ULONG(upto));
}

#ext_section?(from, upto) ⇒ Boolean

Returns:

  • (Boolean)


795
796
797
798
799
800
801
802
# File 'ext/character_set/character_set.c', line 795

static VALUE
cs_method_ext_section_p(VALUE self, VALUE from, VALUE upto)
{
  cs_ar *cps;
  cs_cp len;
  cps = cs_fetch_cps(self, &len);
  return cs_has_cp_in_section(cps, len, FIX2ULONG(from), FIX2ULONG(upto));
}

#ext_section_ratio(from, upto) ⇒ Object



813
814
815
816
817
# File 'ext/character_set/character_set.c', line 813

static VALUE
cs_method_ext_section_ratio(VALUE self, VALUE from, VALUE upto)
{
  return cs_ratio_of_section(self, FIX2ULONG(from), FIX2ULONG(upto));
}

#hashObject



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
# File 'ext/character_set/character_set.c', line 213

static VALUE
cs_method_hash(VALUE self)
{
  cs_cp cp, len, hash, four_byte_value;
  cs_ar *cps;
  cps = cs_fetch_cps(self, &len);

  hash = 17;
  for (cp = 0; cp < len; cp++)
  {
    if (cp % 32 == 0)
    {
      if (cp != 0)
      {
        hash = hash * 23 + four_byte_value;
      }
      four_byte_value = 0;
    }
    if (tst_cp(cps, len, cp))
    {
      four_byte_value++;
    }
  }

  return LONG2FIX(hash);
}

#include?(num) ⇒ Boolean

Returns:

  • (Boolean)


354
355
356
357
358
359
360
361
# File 'ext/character_set/character_set.c', line 354

static VALUE
cs_method_include_p(VALUE self, VALUE num)
{
  cs_ar *cps;
  cs_cp len;
  cps = cs_fetch_cps(self, &len);
  return (tst_cp(cps, len, FIX2ULONG(num)) ? Qtrue : Qfalse);
}

#initialize_clone(orig) ⇒ Object



580
581
582
583
584
585
# File 'ext/character_set/character_set.c', line 580

static VALUE
cs_method_initialize_copy(VALUE self, VALUE orig)
{
  cs_merge_cs(self, orig);
  return self;
}

#initialize_dup(orig) ⇒ Object



580
581
582
583
584
585
# File 'ext/character_set/character_set.c', line 580

static VALUE
cs_method_initialize_copy(VALUE self, VALUE orig)
{
  cs_merge_cs(self, orig);
  return self;
}

#intersect?(other) ⇒ Boolean

Returns:

  • (Boolean)


416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
# File 'ext/character_set/character_set.c', line 416

static VALUE
cs_method_intersect_p(VALUE self, VALUE other)
{
  cs_cp cp, alen, blen;
  cs_ar *acps, *bcps;
  acps = cs_fetch_cps(self, &alen);
  bcps = cs_fetch_cps(other, &blen);
  for (cp = 0; cp < UNICODE_CP_COUNT; cp++)
  {
    if (tst_cp(acps, alen, cp) && tst_cp(bcps, blen, cp))
    {
      return Qtrue;
    }
  }
  return Qfalse;
}

#intersection(other) ⇒ Object



330
331
332
333
334
# File 'ext/character_set/character_set.c', line 330

static VALUE
cs_method_intersection(VALUE self, VALUE other)
{
  RETURN_COMBINED_CS(self, other, &&);
}

#keep_ifObject



259
260
261
262
263
264
# File 'ext/character_set/character_set.c', line 259

static VALUE
cs_method_keep_if(VALUE self)
{
  RETURN_SIZED_ENUMERATOR(self, 0, 0, cs_enumerator_length);
  return cs_delete_if_block_result(self, 0);
}

#keep_in(str) ⇒ Object



1264
1265
1266
1267
1268
# File 'ext/character_set/character_set.c', line 1264

static VALUE
cs_method_keep_in(VALUE self, VALUE str)
{
  return cs_apply_to_str(self, str, 0, 0);
}

#keep_in!(str) ⇒ Object



1270
1271
1272
1273
1274
# File 'ext/character_set/character_set.c', line 1270

static VALUE
cs_method_keep_in_bang(VALUE self, VALUE str)
{
  return cs_apply_to_str(self, str, 0, 1);
}

#lengthObject



163
164
165
166
167
# File 'ext/character_set/character_set.c', line 163

static VALUE
cs_method_length(VALUE self)
{
  return LONG2FIX(cs_active_cp_count(self));
}

#maxObject



283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
# File 'ext/character_set/character_set.c', line 283

static VALUE
cs_method_max(VALUE self)
{
  cs_cp len;
  long reverse_idx;
  cs_ar *cps;
  cps = cs_fetch_cps(self, &len);
  for (reverse_idx = len; reverse_idx >= 0; reverse_idx--)
  {
    if (tst_cp(cps, len, reverse_idx))
    {
      return LONG2FIX(reverse_idx);
    }
  }
  return Qnil;
}

#member?(num) ⇒ Boolean

Returns:

  • (Boolean)


354
355
356
357
358
359
360
361
# File 'ext/character_set/character_set.c', line 354

static VALUE
cs_method_include_p(VALUE self, VALUE num)
{
  cs_ar *cps;
  cs_cp len;
  cps = cs_fetch_cps(self, &len);
  return (tst_cp(cps, len, FIX2ULONG(num)) ? Qtrue : Qfalse);
}

#member_in_plane?(plane_num) ⇒ Boolean

Returns:

  • (Boolean)


875
876
877
878
879
880
881
882
883
884
# File 'ext/character_set/character_set.c', line 875

static VALUE
cs_method_member_in_plane_p(VALUE self, VALUE plane_num)
{
  cs_ar *cps;
  cs_cp len;
  unsigned int plane;
  plane = cs_valid_plane_num(plane_num);
  cps = cs_fetch_cps(self, &len);
  return cs_has_cp_in_plane(cps, len, plane);
}

#merge(other) ⇒ Object



565
566
567
568
569
570
571
572
573
574
575
576
577
578
# File 'ext/character_set/character_set.c', line 565

static VALUE
cs_method_merge(VALUE self, VALUE other)
{
  rb_check_frozen(self);
  if (cs_check_type(other))
  {
    return cs_merge_cs(self, other);
  }
  else if (TYPE(other) == T_ARRAY)
  {
    return cs_merge_rb_array(self, other);
  }
  return cs_merge_rb_range(self, other);
}

#minObject



276
277
278
279
280
281
# File 'ext/character_set/character_set.c', line 276

static VALUE
cs_method_min(VALUE self)
{
  FOR_EACH_ACTIVE_CODEPOINT(return LONG2FIX(cp));
  return Qnil;
}

#minmaxObject



300
301
302
303
304
305
306
307
308
# File 'ext/character_set/character_set.c', line 300

static VALUE
cs_method_minmax(VALUE self)
{
  VALUE arr;
  arr = rb_ary_new2(2);
  rb_ary_push(arr, cs_method_min(self));
  rb_ary_push(arr, cs_method_max(self));
  return arr;
}

#plane(plane_num) ⇒ Object



865
866
867
868
869
870
871
872
873
# File 'ext/character_set/character_set.c', line 865

static VALUE
cs_method_plane(VALUE self, VALUE plane_num)
{
  cs_cp plane, plane_beg, plane_end;
  plane = cs_valid_plane_num(plane_num);
  plane_beg = plane * UNICODE_PLANE_SIZE;
  plane_end = (plane + 1) * MAX_BMP_CP;
  return cs_from_section(self, plane_beg, plane_end);
}

#planesObject



833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
# File 'ext/character_set/character_set.c', line 833

static VALUE
cs_method_planes(VALUE self)
{
  cs_ar *cps;
  cs_cp len;
  unsigned int i;
  VALUE planes;
  cps = cs_fetch_cps(self, &len);
  planes = rb_ary_new();
  for (i = 0; i < UNICODE_PLANE_COUNT; i++)
  {
    if (cs_has_cp_in_plane(cps, len, i))
    {
      rb_ary_push(planes, INT2FIX(i));
    }
  }
  return planes;
}

#proper_subset?(other) ⇒ Boolean

Returns:

  • (Boolean)


653
654
655
656
657
658
659
# File 'ext/character_set/character_set.c', line 653

static VALUE
cs_method_proper_subset_p(VALUE self, VALUE other)
{
  int is_subset, is_proper;
  is_subset = cs_a_subset_of_b(self, other, &is_proper);
  return (is_subset && is_proper) ? Qtrue : Qfalse;
}

#proper_superset?(other) ⇒ Boolean

Returns:

  • (Boolean)


667
668
669
670
671
672
673
# File 'ext/character_set/character_set.c', line 667

static VALUE
cs_method_proper_superset_p(VALUE self, VALUE other)
{
  int is_superset, is_proper;
  is_superset = cs_a_subset_of_b(other, self, &is_proper);
  return (is_superset && is_proper) ? Qtrue : Qfalse;
}

#rangesObject



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
# File 'ext/character_set/character_set.c', line 692

static VALUE
cs_method_ranges(VALUE self)
{
  VALUE ranges, cp_num, previous_cp_num, current_start, current_end;

  ranges = rb_ary_new();
  previous_cp_num = 0;
  current_start = 0;
  current_end = 0;

  FOR_EACH_ACTIVE_CODEPOINT(
      cp_num = LONG2FIX(cp);

      if (!previous_cp_num) {
        current_start = cp_num;
      } else if (previous_cp_num + 2 != cp_num) {
        // gap found, finalize previous range
        rb_ary_push(ranges, rb_range_new(current_start, current_end, 0));
        current_start = cp_num;
      } current_end = cp_num;
      previous_cp_num = cp_num;);

  // add final range
  if (current_start)
  {
    rb_ary_push(ranges, rb_range_new(current_start, current_end, 0));
  }

  return ranges;
}

#sample(*args) ⇒ Object



723
724
725
726
727
728
729
730
# File 'ext/character_set/character_set.c', line 723

static VALUE
cs_method_sample(int argc, VALUE *argv, VALUE self)
{
  VALUE array, to_a_args[1] = {Qtrue};
  rb_check_arity(argc, 0, 1);
  array = cs_method_to_a(1, to_a_args, self);
  return rb_funcall(array, rb_intern("sample"), argc, argc ? argv[0] : 0);
}

#scan(str) ⇒ Object



1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
# File 'ext/character_set/character_set.c', line 1105

static VALUE
cs_method_scan(VALUE self, VALUE str)
{
  VALUE memo[2];
  struct cs_data *data;
  raise_arg_err_unless_string(str);
  data = cs_fetch_data(self);
  memo[0] = rb_ary_new();
  memo[1] = (VALUE)rb_enc_get(str);
  each_cp(str, add_str_cp_to_str_arr, data->cps, data->len, data, memo);
  return memo[0];
}

#sizeObject



163
164
165
166
167
# File 'ext/character_set/character_set.c', line 163

static VALUE
cs_method_length(VALUE self)
{
  return LONG2FIX(cs_active_cp_count(self));
}

#subset?(other) ⇒ Boolean

Returns:

  • (Boolean)


647
648
649
650
651
# File 'ext/character_set/character_set.c', line 647

static VALUE
cs_method_subset_p(VALUE self, VALUE other)
{
  return cs_a_subset_of_b(self, other, NULL) ? Qtrue : Qfalse;
}

#subtract(other) ⇒ Object



587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
# File 'ext/character_set/character_set.c', line 587

static VALUE
cs_method_subtract(VALUE self, VALUE other)
{
  cs_cp cp, len, other_len;
  cs_ar *cps, *other_cps;
  rb_check_frozen(self);
  cps = cs_fetch_cps(self, &len);
  other_cps = cs_fetch_cps(other, &other_len);
  for (cp = 0; cp < UNICODE_CP_COUNT; cp++)
  {
    if (tst_cp(other_cps, other_len, cp))
    {
      clr_cp(cps, len, cp);
    }
  }
  return self;
}

#superset?(other) ⇒ Boolean

Returns:

  • (Boolean)


661
662
663
664
665
# File 'ext/character_set/character_set.c', line 661

static VALUE
cs_method_superset_p(VALUE self, VALUE other)
{
  return cs_a_subset_of_b(other, self, NULL) ? Qtrue : Qfalse;
}

#to_a(*args) ⇒ Object

returns an Array of Strings of length 1 if passed true.



185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
# File 'ext/character_set/character_set.c', line 185

static VALUE
cs_method_to_a(int argc, VALUE *argv, VALUE self)
{
  VALUE arr;
  rb_encoding *enc;
  rb_check_arity(argc, 0, 1);

  arr = rb_ary_new();
  if (!argc || NIL_P(argv[0]) || argv[0] == Qfalse)
  {
    FOR_EACH_ACTIVE_CODEPOINT(rb_ary_push(arr, LONG2FIX(cp)));
  }
  else
  {
    enc = rb_utf8_encoding();
    FOR_EACH_ACTIVE_CODEPOINT(rb_ary_push(arr, rb_enc_uint_chr((int)cp, enc)));
  }

  return arr;
}

#union(other) ⇒ Object



342
343
344
345
346
# File 'ext/character_set/character_set.c', line 342

static VALUE
cs_method_union(VALUE self, VALUE other)
{
  RETURN_COMBINED_CS(self, other, ||);
}

#used_by?(str) ⇒ Boolean

Returns:

  • (Boolean)


1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
# File 'ext/character_set/character_set.c', line 1124

static VALUE
cs_method_used_by_p(VALUE self, VALUE str)
{
  VALUE only_uses_other_cps;
  struct cs_data *data;
  raise_arg_err_unless_string(str);
  data = cs_fetch_data(self);
  only_uses_other_cps = each_cp(str, str_cp_not_in_arr, data->cps, data->len, data, 0);
  return only_uses_other_cps == Qfalse ? Qtrue : Qfalse;
}

#|(other) ⇒ Object



342
343
344
345
346
# File 'ext/character_set/character_set.c', line 342

static VALUE
cs_method_union(VALUE self, VALUE other)
{
  RETURN_COMBINED_CS(self, other, ||);
}