u 0.5.0 → 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/build/ext/u/data/attributes.rb +39 -0
- data/build/ext/u/data/bidi-mirroring.rb +27 -0
- data/build/ext/u/data/canonical-combining-class.rb +15 -0
- data/build/ext/u/data/case-folding.rb +39 -0
- data/build/ext/u/data/cased.rb +19 -0
- data/build/ext/u/data/compose.rb +304 -0
- data/build/ext/u/data/constants.rb +31 -0
- data/build/ext/u/data/decompose.rb +85 -0
- data/build/ext/u/data/general-category.rb +61 -0
- data/build/ext/u/data/grapheme-word-break.rb +15 -0
- data/build/ext/u/data/marshalled.rb +5 -0
- data/build/ext/u/data/script.rb +91 -0
- data/build/ext/u/data/soft-dotted.rb +17 -0
- data/build/ext/u/data/title-table.rb +30 -0
- data/build/ext/u/data/wide.rb +17 -0
- data/build/lib/u/build.rb +8 -0
- data/build/lib/u/build/data.rb +16 -0
- data/build/lib/u/build/data/bidimirroring.rb +26 -0
- data/build/lib/u/build/data/break.rb +14 -0
- data/build/lib/u/build/data/casefolding.rb +77 -0
- data/build/lib/u/build/data/compositionexclusions.rb +14 -0
- data/build/lib/u/build/data/derivedeastasianwidth.rb +15 -0
- data/build/lib/u/build/data/file.rb +88 -0
- data/build/lib/u/build/data/linebreak.rb +14 -0
- data/build/lib/u/build/data/proplist.rb +18 -0
- data/build/lib/u/build/data/scripts.rb +22 -0
- data/build/lib/u/build/data/specialcasing.rb +106 -0
- data/build/lib/u/build/data/unicode.rb +41 -0
- data/build/lib/u/build/data/unicode/entry.rb +27 -0
- data/build/lib/u/build/data/unicode/entry/decomposition.rb +29 -0
- data/build/lib/u/build/data/unicode/points.rb +32 -0
- data/build/lib/u/build/header.rb +11 -0
- data/build/lib/u/build/header/table.rb +19 -0
- data/build/lib/u/build/header/table/row.rb +64 -0
- data/build/lib/u/build/header/tables.rb +6 -0
- data/build/lib/u/build/header/tables/intervals.rb +50 -0
- data/build/lib/u/build/header/tables/split.rb +20 -0
- data/build/lib/u/build/header/tables/split/data.rb +29 -0
- data/build/lib/u/build/header/tables/split/part1.rb +28 -0
- data/build/lib/u/build/header/tables/split/part2.rb +13 -0
- data/build/lib/u/build/header/tables/split/row.rb +34 -0
- data/build/lib/u/build/header/tables/split/rows.rb +22 -0
- data/build/test/unit/break.rb +45 -0
- data/build/test/unit/case.rb +178 -0
- data/build/test/unit/foldcase.rb +44 -0
- data/build/test/unit/normalize.rb +81 -0
- data/ext/u/attributes.c +62 -0
- data/ext/u/attributes.h +5 -0
- data/ext/u/case.h +41 -0
- data/ext/u/data/attributes.h +3070 -0
- data/ext/u/data/bidi-mirroring.h +373 -0
- data/ext/u/data/canonical-combining-class.h +2157 -0
- data/ext/u/data/case-folding.h +171 -0
- data/ext/u/data/cased.h +42 -0
- data/ext/u/data/compose.h +1714 -0
- data/ext/u/data/constants.h +17 -0
- data/ext/u/data/decompose.h +9356 -0
- data/ext/u/data/general-category.h +28959 -0
- data/ext/u/data/grapheme-break.h +13201 -0
- data/ext/u/data/line-break.h +26501 -0
- data/ext/u/data/normalization-quick-check.h +3002 -0
- data/ext/u/data/script.h +2928 -0
- data/ext/u/data/soft-dotted.h +55 -0
- data/ext/u/data/title-table.h +41 -0
- data/ext/u/data/types.h +11117 -0
- data/ext/u/data/wide-cjk.h +197 -0
- data/ext/u/data/wide.h +59 -0
- data/ext/u/data/word-break.h +10001 -0
- data/ext/u/depend +281 -0
- data/ext/u/extconf.rb +158 -0
- data/ext/u/output.h +51 -0
- data/ext/{encoding/character/utf-8 → u}/private.c +11 -15
- data/ext/u/private.h +58 -0
- data/ext/u/rb_includes.h +10 -0
- data/ext/u/rb_private.c +98 -0
- data/ext/u/rb_private.h +67 -0
- data/ext/u/rb_u.c +251 -0
- data/ext/u/rb_u_buffer.c +443 -0
- data/ext/u/rb_u_buffer.h +24 -0
- data/ext/u/rb_u_re.c +43 -0
- data/ext/u/rb_u_re.h +15 -0
- data/ext/u/rb_u_string.c +478 -0
- data/ext/u/rb_u_string.h +173 -0
- data/ext/u/rb_u_string_alnum.c +10 -0
- data/ext/u/rb_u_string_alpha.c +10 -0
- data/ext/u/rb_u_string_aref.c +142 -0
- data/ext/u/rb_u_string_ascii_only.c +13 -0
- data/ext/u/rb_u_string_assigned.c +10 -0
- data/ext/u/rb_u_string_b.c +18 -0
- data/ext/u/rb_u_string_bytesize.c +10 -0
- data/ext/u/rb_u_string_byteslice.c +103 -0
- data/ext/u/rb_u_string_canonical_combining_class.c +33 -0
- data/ext/u/rb_u_string_case_ignorable.c +25 -0
- data/ext/u/rb_u_string_casecmp.c +61 -0
- data/ext/u/rb_u_string_cased.c +17 -0
- data/ext/u/rb_u_string_chomp.c +107 -0
- data/ext/u/rb_u_string_chop.c +33 -0
- data/ext/u/rb_u_string_chr.c +9 -0
- data/ext/u/rb_u_string_cntrl.c +10 -0
- data/ext/u/rb_u_string_collate.c +46 -0
- data/ext/u/rb_u_string_collation_key.c +18 -0
- data/ext/u/rb_u_string_count.c +38 -0
- data/ext/u/rb_u_string_defined.c +10 -0
- data/ext/u/rb_u_string_delete.c +62 -0
- data/ext/u/rb_u_string_digit.c +10 -0
- data/ext/u/rb_u_string_downcase.c +13 -0
- data/ext/u/rb_u_string_dump.c +153 -0
- data/ext/u/rb_u_string_each_byte.c +46 -0
- data/ext/u/rb_u_string_each_char.c +49 -0
- data/ext/u/rb_u_string_each_codepoint.c +45 -0
- data/ext/u/rb_u_string_each_grapheme_cluster.c +36 -0
- data/ext/u/rb_u_string_each_line.c +142 -0
- data/ext/u/rb_u_string_each_word.c +34 -0
- data/ext/u/rb_u_string_empty.c +11 -0
- data/ext/u/rb_u_string_end_with.c +31 -0
- data/ext/u/rb_u_string_eql.c +30 -0
- data/ext/u/rb_u_string_equal.c +33 -0
- data/ext/u/rb_u_string_foldcase.c +12 -0
- data/ext/u/rb_u_string_folded.c +13 -0
- data/ext/u/rb_u_string_format.c +1745 -0
- data/ext/u/rb_u_string_general_category.c +109 -0
- data/ext/u/rb_u_string_getbyte.c +21 -0
- data/ext/u/rb_u_string_graph.c +21 -0
- data/ext/u/rb_u_string_grapheme_break.c +61 -0
- data/ext/u/rb_u_string_gsub.c +164 -0
- data/ext/u/rb_u_string_hash.c +10 -0
- data/ext/u/rb_u_string_hex.c +9 -0
- data/ext/u/rb_u_string_include.c +10 -0
- data/ext/u/rb_u_string_index.c +110 -0
- data/ext/u/rb_u_string_inspect.c +189 -0
- data/ext/u/rb_u_string_internal_tr.c +148 -0
- data/ext/u/rb_u_string_internal_tr.h +29 -0
- data/ext/u/rb_u_string_justify.c +169 -0
- data/ext/u/rb_u_string_length.c +10 -0
- data/ext/u/rb_u_string_line_break.c +115 -0
- data/ext/u/rb_u_string_lower.c +13 -0
- data/ext/u/rb_u_string_lstrip.c +24 -0
- data/ext/u/rb_u_string_match.c +65 -0
- data/ext/u/rb_u_string_mirror.c +16 -0
- data/ext/u/rb_u_string_newline.c +21 -0
- data/ext/u/rb_u_string_normalize.c +70 -0
- data/ext/u/rb_u_string_normalized.c +28 -0
- data/ext/u/rb_u_string_oct.c +11 -0
- data/ext/u/rb_u_string_ord.c +14 -0
- data/ext/u/rb_u_string_partition.c +80 -0
- data/ext/u/rb_u_string_plus.c +33 -0
- data/ext/u/rb_u_string_print.c +10 -0
- data/ext/u/rb_u_string_punct.c +10 -0
- data/ext/u/rb_u_string_reverse.c +13 -0
- data/ext/u/rb_u_string_rindex.c +104 -0
- data/ext/u/rb_u_string_rpartition.c +81 -0
- data/ext/u/rb_u_string_rstrip.c +29 -0
- data/ext/u/rb_u_string_scan.c +109 -0
- data/ext/u/rb_u_string_script.c +253 -0
- data/ext/u/rb_u_string_soft_dotted.c +13 -0
- data/ext/u/rb_u_string_space.c +24 -0
- data/ext/u/rb_u_string_split.c +245 -0
- data/ext/u/rb_u_string_squeeze.c +75 -0
- data/ext/u/rb_u_string_start_with.c +31 -0
- data/ext/u/rb_u_string_strip.c +36 -0
- data/ext/u/rb_u_string_sub.c +147 -0
- data/ext/u/rb_u_string_times.c +35 -0
- data/ext/u/rb_u_string_title.c +10 -0
- data/ext/u/rb_u_string_titlecase.c +13 -0
- data/ext/u/rb_u_string_to_i.c +45 -0
- data/ext/u/rb_u_string_to_inum.c +364 -0
- data/ext/u/rb_u_string_to_inum.h +1 -0
- data/ext/u/rb_u_string_to_str.c +17 -0
- data/ext/u/rb_u_string_to_sym.c +12 -0
- data/ext/u/rb_u_string_tr.c +290 -0
- data/ext/u/rb_u_string_upcase.c +12 -0
- data/ext/u/rb_u_string_upper.c +13 -0
- data/ext/u/rb_u_string_valid.c +10 -0
- data/ext/u/rb_u_string_valid_encoding.c +12 -0
- data/ext/u/rb_u_string_wide.c +21 -0
- data/ext/u/rb_u_string_wide_cjk.c +21 -0
- data/ext/u/rb_u_string_width.c +19 -0
- data/ext/u/rb_u_string_word_break.c +63 -0
- data/ext/u/rb_u_string_xdigit.c +22 -0
- data/ext/u/rb_u_string_zero_width.c +16 -0
- data/ext/u/titled.c +55 -0
- data/ext/u/titled.h +1 -0
- data/ext/u/u.c +23 -0
- data/ext/u/u.h +458 -0
- data/ext/u/u_char_canonical_combining_class.c +31 -0
- data/ext/u/u_char_digit_value.c +21 -0
- data/ext/u/u_char_downcase.c +27 -0
- data/ext/u/u_char_general_category.c +31 -0
- data/ext/u/u_char_grapheme_break.c +28 -0
- data/ext/u/u_char_isalnum.c +24 -0
- data/ext/u/u_char_isalpha.c +21 -0
- data/ext/u/u_char_isassigned.c +16 -0
- data/ext/u/u_char_iscased.c +22 -0
- data/ext/u/u_char_iscaseignorable.c +29 -0
- data/ext/u/u_char_iscntrl.c +17 -0
- data/ext/u/u_char_isdefined.c +15 -0
- data/ext/u/u_char_isdigit.c +16 -0
- data/ext/u/u_char_isgraph.c +22 -0
- data/ext/u/u_char_islower.c +16 -0
- data/ext/u/u_char_isnewline.c +24 -0
- data/ext/u/u_char_isprint.c +21 -0
- data/ext/u/u_char_ispunct.c +27 -0
- data/ext/u/u_char_issoftdotted.c +18 -0
- data/ext/u/u_char_isspace.c +28 -0
- data/ext/u/u_char_isupper.c +16 -0
- data/ext/u/u_char_isvalid.c +18 -0
- data/ext/u/u_char_iswide.c +18 -0
- data/ext/u/u_char_iswide_cjk.c +22 -0
- data/ext/u/u_char_isxdigit.c +27 -0
- data/ext/u/u_char_iszerowidth.c +29 -0
- data/ext/u/u_char_line_break.c +29 -0
- data/ext/u/u_char_mirror.c +16 -0
- data/ext/u/u_char_normalized.c +23 -0
- data/ext/u/u_char_script.c +41 -0
- data/ext/u/u_char_to_u.c +48 -0
- data/ext/u/u_char_upcase.c +24 -0
- data/ext/u/u_char_width.c +12 -0
- data/ext/u/u_char_word_break.c +28 -0
- data/ext/u/u_char_xdigit_value.c +31 -0
- data/ext/u/u_collate.c +83 -0
- data/ext/u/u_collation_key.c +132 -0
- data/ext/u/u_decode.c +156 -0
- data/ext/u/u_downcase.c +201 -0
- data/ext/u/u_foldcase.c +68 -0
- data/ext/u/u_grapheme_clusters.c +57 -0
- data/ext/u/u_has_prefix.c +27 -0
- data/ext/u/u_index.c +93 -0
- data/ext/u/u_is_ascii_only.c +33 -0
- data/ext/u/u_locale.c +40 -0
- data/ext/u/u_locale.h +14 -0
- data/ext/u/u_mirror.c +20 -0
- data/ext/u/u_n_bytes.c +16 -0
- data/ext/u/u_n_chars.c +43 -0
- data/ext/u/u_normalize.c +232 -0
- data/ext/u/u_normalized.c +28 -0
- data/ext/u/u_offset_to_pointer.c +62 -0
- data/ext/u/u_pointer_to_offset.c +23 -0
- data/ext/u/u_recode.c +73 -0
- data/ext/u/u_reverse.c +21 -0
- data/ext/u/u_rindex.c +132 -0
- data/ext/u/u_titlecase.c +68 -0
- data/ext/u/u_upcase.c +89 -0
- data/ext/u/u_width.c +35 -0
- data/ext/u/u_words.c +82 -0
- data/ext/u/yield.h +27 -0
- data/lib/u-1.0.rb +20 -0
- data/lib/u-1.0/buffer.rb +10 -0
- data/lib/u-1.0/string.rb +9 -0
- data/lib/u-1.0/version.rb +287 -0
- data/test/unit/case.rb +2080 -0
- data/test/unit/foldcase.rb +1136 -0
- data/test/unit/graphemebreak.rb +407 -0
- data/test/unit/normalize.rb +367545 -0
- data/test/unit/u-1.0.rb +10 -0
- data/test/unit/u-1.0/buffer.rb +52 -0
- data/test/unit/u-1.0/string.rb +1439 -0
- data/test/unit/{u.rb → u-1.0/version.rb} +0 -1
- data/test/unit/wordbreak.rb +1083 -0
- metadata +603 -148
- data/README +0 -38
- data/Rakefile +0 -64
- data/ext/encoding/character/utf-8/break.c +0 -25
- data/ext/encoding/character/utf-8/data/break.h +0 -22931
- data/ext/encoding/character/utf-8/data/character-tables.h +0 -14358
- data/ext/encoding/character/utf-8/data/compose.h +0 -1607
- data/ext/encoding/character/utf-8/data/decompose.h +0 -10926
- data/ext/encoding/character/utf-8/data/generate-unicode-data.rb +0 -1070
- data/ext/encoding/character/utf-8/decompose.c +0 -444
- data/ext/encoding/character/utf-8/depend +0 -65
- data/ext/encoding/character/utf-8/extconf.rb +0 -67
- data/ext/encoding/character/utf-8/private.h +0 -51
- data/ext/encoding/character/utf-8/properties.c +0 -1056
- data/ext/encoding/character/utf-8/rb_includes.h +0 -19
- data/ext/encoding/character/utf-8/rb_methods.h +0 -49
- data/ext/encoding/character/utf-8/rb_private.h +0 -52
- data/ext/encoding/character/utf-8/rb_utf_aref.c +0 -111
- data/ext/encoding/character/utf-8/rb_utf_aset.c +0 -105
- data/ext/encoding/character/utf-8/rb_utf_casecmp.c +0 -24
- data/ext/encoding/character/utf-8/rb_utf_chomp.c +0 -114
- data/ext/encoding/character/utf-8/rb_utf_chop.c +0 -44
- data/ext/encoding/character/utf-8/rb_utf_collate.c +0 -13
- data/ext/encoding/character/utf-8/rb_utf_count.c +0 -30
- data/ext/encoding/character/utf-8/rb_utf_delete.c +0 -60
- data/ext/encoding/character/utf-8/rb_utf_downcase.c +0 -13
- data/ext/encoding/character/utf-8/rb_utf_each_char.c +0 -27
- data/ext/encoding/character/utf-8/rb_utf_foldcase.c +0 -13
- data/ext/encoding/character/utf-8/rb_utf_hex.c +0 -14
- data/ext/encoding/character/utf-8/rb_utf_index.c +0 -50
- data/ext/encoding/character/utf-8/rb_utf_insert.c +0 -48
- data/ext/encoding/character/utf-8/rb_utf_internal_bignum.c +0 -332
- data/ext/encoding/character/utf-8/rb_utf_internal_bignum.h +0 -12
- data/ext/encoding/character/utf-8/rb_utf_internal_tr.c +0 -142
- data/ext/encoding/character/utf-8/rb_utf_internal_tr.h +0 -41
- data/ext/encoding/character/utf-8/rb_utf_justify.c +0 -96
- data/ext/encoding/character/utf-8/rb_utf_length.c +0 -14
- data/ext/encoding/character/utf-8/rb_utf_lstrip.c +0 -41
- data/ext/encoding/character/utf-8/rb_utf_normalize.c +0 -51
- data/ext/encoding/character/utf-8/rb_utf_oct.c +0 -14
- data/ext/encoding/character/utf-8/rb_utf_reverse.c +0 -13
- data/ext/encoding/character/utf-8/rb_utf_rindex.c +0 -88
- data/ext/encoding/character/utf-8/rb_utf_rstrip.c +0 -51
- data/ext/encoding/character/utf-8/rb_utf_squeeze.c +0 -70
- data/ext/encoding/character/utf-8/rb_utf_strip.c +0 -27
- data/ext/encoding/character/utf-8/rb_utf_to_i.c +0 -25
- data/ext/encoding/character/utf-8/rb_utf_tr.c +0 -250
- data/ext/encoding/character/utf-8/rb_utf_upcase.c +0 -13
- data/ext/encoding/character/utf-8/tables.h +0 -38
- data/ext/encoding/character/utf-8/unicode.c +0 -319
- data/ext/encoding/character/utf-8/unicode.h +0 -216
- data/ext/encoding/character/utf-8/utf.c +0 -1334
- data/lib/encoding/character/utf-8.rb +0 -201
- data/lib/u.rb +0 -16
- data/lib/u/string.rb +0 -185
- data/lib/u/version.rb +0 -5
- data/test/unit/u/string.rb +0 -91
@@ -0,0 +1,109 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
|
3
|
+
#define CATEGORY2ID(type, symbol) \
|
4
|
+
case U_GENERAL_CATEGORY_##type: { \
|
5
|
+
static ID id_##symbol; \
|
6
|
+
if (id_##symbol == 0) \
|
7
|
+
id_##symbol = rb_intern(#symbol); \
|
8
|
+
return ID2SYM(id_##symbol); \
|
9
|
+
}
|
10
|
+
|
11
|
+
static VALUE
|
12
|
+
category_to_symbol(enum u_general_category category)
|
13
|
+
{
|
14
|
+
switch (category) {
|
15
|
+
CATEGORY2ID(OTHER_CONTROL, other_control)
|
16
|
+
CATEGORY2ID(OTHER_FORMAT, other_format)
|
17
|
+
CATEGORY2ID(OTHER_NOT_ASSIGNED, other_not_assigned)
|
18
|
+
CATEGORY2ID(OTHER_PRIVATE_USE, other_private_use)
|
19
|
+
CATEGORY2ID(OTHER_SURROGATE, other_surrogate)
|
20
|
+
CATEGORY2ID(LETTER_LOWERCASE, letter_lowercase)
|
21
|
+
CATEGORY2ID(LETTER_MODIFIER, letter_modifier)
|
22
|
+
CATEGORY2ID(LETTER_OTHER, letter_other)
|
23
|
+
CATEGORY2ID(LETTER_TITLECASE, letter_titlecase)
|
24
|
+
CATEGORY2ID(LETTER_UPPERCASE, letter_uppercase)
|
25
|
+
CATEGORY2ID(MARK_SPACING_COMBINING, mark_spacing_combining)
|
26
|
+
CATEGORY2ID(MARK_ENCLOSING, mark_enclosing)
|
27
|
+
CATEGORY2ID(MARK_NON_SPACING, mark_non_spacing)
|
28
|
+
CATEGORY2ID(NUMBER_DECIMAL, number_decimal)
|
29
|
+
CATEGORY2ID(NUMBER_LETTER, number_letter)
|
30
|
+
CATEGORY2ID(NUMBER_OTHER, number_other)
|
31
|
+
CATEGORY2ID(PUNCTUATION_CONNECTOR, punctuation_connector)
|
32
|
+
CATEGORY2ID(PUNCTUATION_DASH, punctuation_dash)
|
33
|
+
CATEGORY2ID(PUNCTUATION_CLOSE, punctuation_close)
|
34
|
+
CATEGORY2ID(PUNCTUATION_FINAL_QUOTE, punctuation_final_quote)
|
35
|
+
CATEGORY2ID(PUNCTUATION_INITIAL_QUOTE, punctuation_initial_quote)
|
36
|
+
CATEGORY2ID(PUNCTUATION_OTHER, punctuation_other)
|
37
|
+
CATEGORY2ID(PUNCTUATION_OPEN, punctuation_open)
|
38
|
+
CATEGORY2ID(SYMBOL_CURRENCY, symbol_currency)
|
39
|
+
CATEGORY2ID(SYMBOL_MODIFIER, symbol_modifier)
|
40
|
+
CATEGORY2ID(SYMBOL_MATH, symbol_math)
|
41
|
+
CATEGORY2ID(SYMBOL_OTHER, symbol_other)
|
42
|
+
CATEGORY2ID(SEPARATOR_LINE, separator_line)
|
43
|
+
CATEGORY2ID(SEPARATOR_PARAGRAPH, separator_paragraph)
|
44
|
+
CATEGORY2ID(SEPARATOR_SPACE, separator_space)
|
45
|
+
default:
|
46
|
+
rb_u_raise(rb_eNotImpError, "unknown general category: %d", category);
|
47
|
+
}
|
48
|
+
}
|
49
|
+
|
50
|
+
/* Returns the general category of the characters of the receiver.
|
51
|
+
*
|
52
|
+
* The general category identifies what kind of symbol the character is.
|
53
|
+
*
|
54
|
+
* <table>
|
55
|
+
* <thead>
|
56
|
+
* <tr>
|
57
|
+
* <th>Category Major, minor</th>
|
58
|
+
* <th>Unicode Value</th>
|
59
|
+
* <th>Ruby Value</th>
|
60
|
+
* </tr>
|
61
|
+
* </thead>
|
62
|
+
* <tbody>
|
63
|
+
* <tr><td>Other, control</td><td>Cc</td><td>:other_control</td></tr>
|
64
|
+
* <tr><td>Other, format</td><td>Cf</td><td>:other_format</td></tr>
|
65
|
+
* <tr><td>Other, not assigned</td><td>Cn</td><td>:other_not_assigned</td></tr>
|
66
|
+
* <tr><td>Other, private use</td><td>Co</td><td>:other_private_use</td></tr>
|
67
|
+
* <tr><td>Other, surrogate</td><td>Cs</td><td>:other_surrogate</td></tr>
|
68
|
+
* <tr><td>Letter, lowercase</td><td>Ll</td><td>:letter_lowercase</td></tr>
|
69
|
+
* <tr><td>Letter, modifier</td><td>Lm</td><td>:letter_modifier</td></tr>
|
70
|
+
* <tr><td>Letter, other</td><td>Lo</td><td>:letter_other</td></tr>
|
71
|
+
* <tr><td>Letter, titlecase</td><td>Lt</td><td>:letter_titlecase</td></tr>
|
72
|
+
* <tr><td>Letter, uppercase</td><td>Lu</td><td>:letter_uppercase</td></tr>
|
73
|
+
* <tr><td>Mark, spacing combining</td><td>Mc</td><td>:mark_spacing_combining</td></tr>
|
74
|
+
* <tr><td>Mark, enclosing</td><td>Me</td><td>:mark_enclosing</td></tr>
|
75
|
+
* <tr><td>Mark, nonspacing</td><td>Mn</td><td>:mark_non_spacing</td></tr>
|
76
|
+
* <tr><td>Number, decimal digit</td><td>Nd</td><td>:number_decimal</td></tr>
|
77
|
+
* <tr><td>Number, letter</td><td>Nl</td><td>:number_letter</td></tr>
|
78
|
+
* <tr><td>Number, other</td><td>No</td><td>:number_other</td></tr>
|
79
|
+
* <tr><td>Punctuation, connector</td><td>Pc</td><td>:punctuation_connector</td></tr>
|
80
|
+
* <tr><td>Punctuation, dash</td><td>Pd</td><td>:punctuation_dash</td></tr>
|
81
|
+
* <tr><td>Punctuation, close</td><td>Pe</td><td>:punctuation_close</td></tr>
|
82
|
+
* <tr><td>Punctuation, final quote</td><td>Pf</td><td>:punctuation_final_quote</td></tr>
|
83
|
+
* <tr><td>Punctuation, initial quote</td><td>Pi</td><td>:punctuation_initial_quote</td></tr>
|
84
|
+
* <tr><td>Punctuation, other</td><td>Po</td><td>:punctuation_other</td></tr>
|
85
|
+
* <tr><td>Punctuation, open</td><td>Ps</td><td>:punctuation_open</td></tr>
|
86
|
+
* <tr><td>Symbol, currency</td><td>Sc</td><td>:symbol_currency</td></tr>
|
87
|
+
* <tr><td>Symbol, modifier</td><td>Sk</td><td>:symbol_modifier</td></tr>
|
88
|
+
* <tr><td>Symbol, math</td><td>Sm</td><td>:symbol_math</td></tr>
|
89
|
+
* <tr><td>Symbol, other</td><td>So</td><td>:symbol_other</td></tr>
|
90
|
+
* <tr><td>Separator, line</td><td>Zl</td><td>:separator_line</td></tr>
|
91
|
+
* <tr><td>Separator, paragraph</td><td>Zp</td><td>:separator_paragraph</td></tr>
|
92
|
+
* <tr><td>Separator, space</td><td>Zs</td><td>:separator_space</td></tr>
|
93
|
+
* </tbody>
|
94
|
+
* </table>
|
95
|
+
*
|
96
|
+
* @raise [ArgumentError] If the receiver contains two characters belonging to
|
97
|
+
* different general categories
|
98
|
+
* @raise [ArgumentError] If the receiver contains an incomplete UTF-8 sequence
|
99
|
+
* @raise [ArgumentError] If the receiver contains an invalid UTF-8 sequence
|
100
|
+
* @return [Symbol]
|
101
|
+
* @see http://www.unicode.org/notes/tn36/
|
102
|
+
* Unicode Technical Note #36: A Categorization of Unicode Characters */
|
103
|
+
VALUE
|
104
|
+
rb_u_string_general_category(VALUE self)
|
105
|
+
{
|
106
|
+
return _rb_u_string_property(self, "general category", U_GENERAL_CATEGORY_OTHER_NOT_ASSIGNED,
|
107
|
+
(int (*)(uint32_t))u_char_general_category,
|
108
|
+
(VALUE (*)(int))category_to_symbol);
|
109
|
+
}
|
@@ -0,0 +1,21 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
|
3
|
+
/* @overload getbyte(index)
|
4
|
+
* @param [#to_int] index
|
5
|
+
* @return [Fixnum, nil] The byte at byte-index _i_, where _i_ = INDEX if
|
6
|
+
* INDEX ≥ 0, _i_ = {#bytesize} - abs(INDEX) otherwise, or nil if _i_ lays
|
7
|
+
* outside of [0, {#bytesize}] */
|
8
|
+
VALUE
|
9
|
+
rb_u_string_getbyte(VALUE self, VALUE rbindex)
|
10
|
+
{
|
11
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
12
|
+
long index = NUM2LONG(rbindex);
|
13
|
+
|
14
|
+
if (index < 0)
|
15
|
+
index += USTRING_LENGTH(string);
|
16
|
+
|
17
|
+
if (index < 0 || USTRING_LENGTH(string) <= index)
|
18
|
+
return Qnil;
|
19
|
+
|
20
|
+
return INT2FIX((unsigned char)USTRING_STR(string)[index]);
|
21
|
+
}
|
@@ -0,0 +1,21 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
|
3
|
+
/* @overload graph?
|
4
|
+
*
|
5
|
+
* Returns true if the receiver contains only non-space “printable” characters.
|
6
|
+
*
|
7
|
+
* Non-space “printable” character are those not in the general categories
|
8
|
+
* Other or Space, separator (Zs):
|
9
|
+
*
|
10
|
+
* * Other, control (Cc)
|
11
|
+
* * Other, format (Cf)
|
12
|
+
* * Other, not assigned (Cn)
|
13
|
+
* * Other, surrogate (Cs)
|
14
|
+
* * Space, separator (Zs)
|
15
|
+
*
|
16
|
+
* @return [Boolean] */
|
17
|
+
VALUE
|
18
|
+
rb_u_string_graph(VALUE self)
|
19
|
+
{
|
20
|
+
return _rb_u_character_test(self, u_char_isgraph);
|
21
|
+
}
|
@@ -0,0 +1,61 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
|
3
|
+
#define BREAK2ID(value, symbol) \
|
4
|
+
case U_GRAPHEME_BREAK_##value: { \
|
5
|
+
static ID id_##symbol; \
|
6
|
+
if (id_##symbol == 0) \
|
7
|
+
id_##symbol = rb_intern(#symbol); \
|
8
|
+
return ID2SYM(id_##symbol); \
|
9
|
+
}
|
10
|
+
|
11
|
+
static VALUE
|
12
|
+
break_to_symbol(enum u_grapheme_break value)
|
13
|
+
{
|
14
|
+
switch (value) {
|
15
|
+
BREAK2ID(CONTROL, control)
|
16
|
+
BREAK2ID(CR, cr)
|
17
|
+
BREAK2ID(EXTEND, extend)
|
18
|
+
BREAK2ID(L, l)
|
19
|
+
BREAK2ID(LF, lf)
|
20
|
+
BREAK2ID(LV, lv)
|
21
|
+
BREAK2ID(LVT, lvt)
|
22
|
+
BREAK2ID(OTHER, other)
|
23
|
+
BREAK2ID(PREPEND, prepend)
|
24
|
+
BREAK2ID(REGIONAL_INDICATOR, regional_indicator)
|
25
|
+
BREAK2ID(SPACINGMARK, spacingmark)
|
26
|
+
BREAK2ID(T, t)
|
27
|
+
BREAK2ID(V, v)
|
28
|
+
default:
|
29
|
+
rb_u_raise(rb_eNotImpError, "unknown grapheme break: %d", value);
|
30
|
+
}
|
31
|
+
}
|
32
|
+
|
33
|
+
/* Returns the grapheme break property value of the characters of the receiver.
|
34
|
+
*
|
35
|
+
* The possible break values are
|
36
|
+
*
|
37
|
+
* * :control
|
38
|
+
* * :cr
|
39
|
+
* * :extend
|
40
|
+
* * :l
|
41
|
+
* * :lf
|
42
|
+
* * :lv
|
43
|
+
* * :lvt
|
44
|
+
* * :other
|
45
|
+
* * :prepend
|
46
|
+
* * :regional_indicator
|
47
|
+
* * :spacingmark
|
48
|
+
* * :t
|
49
|
+
* * :v
|
50
|
+
*
|
51
|
+
* @raise [ArgumentError] If the string consists of more than one break type
|
52
|
+
* @return [Symbol]
|
53
|
+
* @see http://www.unicode.org/reports/tr29/
|
54
|
+
* Unicode Standard Annex #29: Unicode Text Segmentation */
|
55
|
+
VALUE
|
56
|
+
rb_u_string_grapheme_break(VALUE self)
|
57
|
+
{
|
58
|
+
return _rb_u_string_property(self, "grapheme break", U_GRAPHEME_BREAK_OTHER,
|
59
|
+
(int (*)(uint32_t))u_char_grapheme_break,
|
60
|
+
(VALUE (*)(int))break_to_symbol);
|
61
|
+
}
|
@@ -0,0 +1,164 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
#include "rb_u_re.h"
|
3
|
+
|
4
|
+
/* @overload gsub(pattern, replacement)
|
5
|
+
*
|
6
|
+
* Returns the receiver with all matches of PATTERN replaced by REPLACEMENT,
|
7
|
+
* inheriting any taint and untrust from the receiver and from REPLACEMENT.
|
8
|
+
*
|
9
|
+
* The REPLACEMENT is used as a specification for what to replace matches
|
10
|
+
* with:
|
11
|
+
*
|
12
|
+
* <table>
|
13
|
+
* <thead>
|
14
|
+
* <tr><th>Specification</th><th>Replacement</th></tr>
|
15
|
+
* </thead>
|
16
|
+
* <tbody>
|
17
|
+
* <tr>
|
18
|
+
* <td><code>\1</code>, <code>\2</code>, …, <code>\</code><em>n</em></td>
|
19
|
+
* <td>Numbered sub-match <em>n</em></td>
|
20
|
+
* </tr>
|
21
|
+
* <tr>
|
22
|
+
* <td><code>\k<</code><em>name</em><code>></code></td>
|
23
|
+
* <td>Named sub-match <em>name</em></td>
|
24
|
+
* </tr>
|
25
|
+
* </tbody>
|
26
|
+
* </table>
|
27
|
+
*
|
28
|
+
* The Regexp special variables `$&`, `$'`, <code>$\`</code>, `$1`, `$2`, …,
|
29
|
+
* `$`_n_ are updated accordingly.
|
30
|
+
*
|
31
|
+
* @param [Regexp, #to_str] pattern
|
32
|
+
* @param [#to_str] replacement
|
33
|
+
* @return [U::String]
|
34
|
+
*
|
35
|
+
* @overload gsub(pattern, replacements)
|
36
|
+
*
|
37
|
+
* Returns the receiver with all matches of PATTERN replaced by
|
38
|
+
* REPLACEMENTS#[_match_], where _match_ is the matched substring, inheriting
|
39
|
+
* any taint and untrust from the receiver and from the
|
40
|
+
* REPLACEMENTS#[_match_]es, as well as any taint on REPLACEMENTS.
|
41
|
+
*
|
42
|
+
* The Regexp special variables `$&`, `$'`, <code>$\`</code>, `$1`, `$2`, …,
|
43
|
+
* `$`_n_ are updated accordingly.
|
44
|
+
*
|
45
|
+
* @param [Regexp, #to_str] pattern
|
46
|
+
* @param [#to_hash] replacements
|
47
|
+
* @raise [RuntimeError] If any replacement is the result being constructed
|
48
|
+
* @raise [Exception] Any error raised by REPLACEMENTS#default, if it gets
|
49
|
+
* called
|
50
|
+
* @return [U::String]
|
51
|
+
*
|
52
|
+
* @overload gsub(pattern){ |match| … }
|
53
|
+
*
|
54
|
+
* Returns the receiver with all matches of PATTERN replaced by the results
|
55
|
+
* of the given block, inheriting any taint and untrust from the receiver and
|
56
|
+
* from the results of the given block.
|
57
|
+
*
|
58
|
+
* The Regexp special variables `$&`, `$'`, <code>$\`</code>, `$1`, `$2`, …,
|
59
|
+
* `$`_n_ are updated accordingly.
|
60
|
+
*
|
61
|
+
* @param [Regexp, #to_str] pattern
|
62
|
+
* @yieldparam [U::String] match
|
63
|
+
* @yieldreturn [#to_str]
|
64
|
+
* @return [U::String]
|
65
|
+
*
|
66
|
+
* @overload gsub(pattern)
|
67
|
+
*
|
68
|
+
* Returns an Enumerator over the matches of PATTERN in the receiver.
|
69
|
+
*
|
70
|
+
* The Regexp special variables `$&`, `$'`, <code>$\`</code>, `$1`, `$2`, …,
|
71
|
+
* `$`_n_ will be updated accordingly.
|
72
|
+
*
|
73
|
+
* @param [Regexp, #to_str] pattern
|
74
|
+
* @return [Enumerator] */
|
75
|
+
VALUE
|
76
|
+
rb_u_string_gsub(int argc, VALUE *argv, VALUE self)
|
77
|
+
{
|
78
|
+
VALUE pattern, replacement;
|
79
|
+
VALUE replacements = Qnil;
|
80
|
+
bool use_block = false;
|
81
|
+
bool tainted = false;
|
82
|
+
|
83
|
+
if (argc == 1) {
|
84
|
+
RETURN_ENUMERATOR(self, argc, argv);
|
85
|
+
use_block = true;
|
86
|
+
}
|
87
|
+
|
88
|
+
if (rb_scan_args(argc, argv, "11", &pattern, &replacement) == 2) {
|
89
|
+
replacements = rb_check_convert_type(replacement, T_HASH,
|
90
|
+
"Hash", "to_hash");
|
91
|
+
if (NIL_P(replacements))
|
92
|
+
StringValue(replacement);
|
93
|
+
if (OBJ_TAINTED(replacement))
|
94
|
+
tainted = true;
|
95
|
+
}
|
96
|
+
|
97
|
+
pattern = rb_u_pattern_argument(pattern, true);
|
98
|
+
|
99
|
+
VALUE str = rb_str_to_str(self);
|
100
|
+
long begin = rb_reg_search(pattern, str, 0, 0);
|
101
|
+
if (begin < 0)
|
102
|
+
return self;
|
103
|
+
|
104
|
+
const char *base = RSTRING_PTR(str);
|
105
|
+
const char *p = base;
|
106
|
+
const char *end = RSTRING_END(str);
|
107
|
+
VALUE substituted = rb_u_str_buf_new(RSTRING_LEN(str) + 30);
|
108
|
+
do {
|
109
|
+
VALUE match = rb_backref_get();
|
110
|
+
struct re_registers *registers = RMATCH_REGS(match);
|
111
|
+
VALUE result;
|
112
|
+
|
113
|
+
if (use_block || !NIL_P(replacements)) {
|
114
|
+
if (use_block) {
|
115
|
+
VALUE ustr = rb_u_string_new_rb(rb_reg_nth_match(0, match));
|
116
|
+
result = rb_u_string_object_as_string(rb_yield(ustr));
|
117
|
+
} else {
|
118
|
+
VALUE ustr = rb_u_string_new_c(self,
|
119
|
+
base + registers->beg[0],
|
120
|
+
registers->end[0] - registers->beg[0]);
|
121
|
+
result = rb_u_string_object_as_string(rb_hash_aref(replacements, ustr));
|
122
|
+
}
|
123
|
+
|
124
|
+
if (result == substituted)
|
125
|
+
rb_u_raise(rb_eRuntimeError,
|
126
|
+
"result of block is string being built; please try not to cheat");
|
127
|
+
} else
|
128
|
+
result =
|
129
|
+
#ifdef HAVE_RB_REG_REGSUB4
|
130
|
+
rb_reg_regsub(replacement, str, registers, pattern);
|
131
|
+
#else
|
132
|
+
rb_reg_regsub(replacement, str, registers);
|
133
|
+
#endif
|
134
|
+
|
135
|
+
if (OBJ_TAINTED(result))
|
136
|
+
tainted = true;
|
137
|
+
|
138
|
+
const struct rb_u_string *value = RVAL2USTRING_ANY(result);
|
139
|
+
|
140
|
+
rb_str_buf_cat(substituted, p, registers->beg[0] - (p - base));
|
141
|
+
rb_str_buf_cat(substituted, USTRING_STR(value), USTRING_LENGTH(value));
|
142
|
+
OBJ_INFECT(substituted, result);
|
143
|
+
|
144
|
+
p = base + registers->end[0];
|
145
|
+
if (registers->beg[0] == registers->end[0])
|
146
|
+
p = u_next(p);
|
147
|
+
if (p >= end)
|
148
|
+
break;
|
149
|
+
|
150
|
+
begin = rb_reg_search(pattern, str, registers->end[0], 0);
|
151
|
+
} while (begin >= 0);
|
152
|
+
|
153
|
+
if (p < end)
|
154
|
+
rb_str_buf_cat(substituted, p, end - p);
|
155
|
+
|
156
|
+
rb_reg_search(pattern, str, end - p, 0);
|
157
|
+
|
158
|
+
RBASIC(substituted)->klass = rb_obj_class(str);
|
159
|
+
OBJ_INFECT(substituted, str);
|
160
|
+
if (tainted)
|
161
|
+
OBJ_TAINT(substituted);
|
162
|
+
|
163
|
+
return rb_u_string_new_rb(substituted);
|
164
|
+
}
|
@@ -0,0 +1,10 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
|
3
|
+
/* @return [Fixnum] The hash value of the receiver’s content */
|
4
|
+
VALUE
|
5
|
+
rb_u_string_hash(VALUE self)
|
6
|
+
{
|
7
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
8
|
+
|
9
|
+
return INT2FIX(rb_memhash(USTRING_STR(string), USTRING_LENGTH(string)));
|
10
|
+
}
|
@@ -0,0 +1,10 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
|
3
|
+
/* @overload include?(substring)
|
4
|
+
* @param [#to_str] substring
|
5
|
+
* @return [Boolean] True if {#index}(SUBSTRING) ≠ nil */
|
6
|
+
VALUE
|
7
|
+
rb_u_string_include(VALUE self, VALUE substring)
|
8
|
+
{
|
9
|
+
return rb_u_string_index(self, substring, 0) != -1 ? Qtrue : Qfalse;
|
10
|
+
}
|
@@ -0,0 +1,110 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
#include "rb_u_re.h"
|
3
|
+
|
4
|
+
/* TODO: Return VALUE. */
|
5
|
+
long
|
6
|
+
rb_u_string_index_regexp(VALUE self, const char *begin, VALUE regex, bool reverse)
|
7
|
+
{
|
8
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
9
|
+
VALUE rbstring = rb_str_to_str(self);
|
10
|
+
|
11
|
+
const char *base = USTRING_STR(string);
|
12
|
+
|
13
|
+
long index = rb_reg_search(regex, rbstring,
|
14
|
+
rb_reg_adjust_startpos(regex, rbstring,
|
15
|
+
begin - base,
|
16
|
+
reverse),
|
17
|
+
reverse);
|
18
|
+
if (index == -1)
|
19
|
+
return -1;
|
20
|
+
|
21
|
+
return u_pointer_to_offset(base, base + index);
|
22
|
+
}
|
23
|
+
|
24
|
+
/* TODO: Return VALUE. */
|
25
|
+
long
|
26
|
+
rb_u_string_index(VALUE self, VALUE rbsubstring, long offset)
|
27
|
+
{
|
28
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
29
|
+
const struct rb_u_string *substring = RVAL2USTRING_ANY(rbsubstring);
|
30
|
+
|
31
|
+
const char *begin = rb_u_string_begin_from_offset(string, offset);
|
32
|
+
if (begin == NULL)
|
33
|
+
return -1;
|
34
|
+
|
35
|
+
const char *end = USTRING_END(string);
|
36
|
+
|
37
|
+
long substring_length = USTRING_LENGTH(substring);
|
38
|
+
if (end - begin < substring_length)
|
39
|
+
return -1;
|
40
|
+
if (substring_length == 0)
|
41
|
+
return offset;
|
42
|
+
|
43
|
+
/* TODO: Should we really be using rb_memsearch? Why not something
|
44
|
+
* more Unicodey? */
|
45
|
+
long index = rb_u_memsearch(USTRING_STR(substring), substring_length,
|
46
|
+
begin,
|
47
|
+
end - begin);
|
48
|
+
if (index < 0)
|
49
|
+
return -1;
|
50
|
+
|
51
|
+
return offset + u_pointer_to_offset(begin, begin + index);
|
52
|
+
}
|
53
|
+
|
54
|
+
/* @overload index(pattern, offset = 0)
|
55
|
+
*
|
56
|
+
* Returns the minimal index of the receiver where PATTERN matches, equal to or
|
57
|
+
* greater than _i_, where _i_ = OFFSET if OFFSET ≥ 0, _i_ = {#length} -
|
58
|
+
* abs(OFFSET) otherwise, or nil if there is no match.
|
59
|
+
*
|
60
|
+
* If PATTERN is a Regexp, the Regexp special variables `$&`, `$'`,
|
61
|
+
* <code>$\`</code>, `$1`, `$2`, …, `$`_n_ are updated accordingly.
|
62
|
+
*
|
63
|
+
* If PATTERN responds to #to_str, the matching is performed by byte
|
64
|
+
* comparison.
|
65
|
+
*
|
66
|
+
* @param [Regexp, #to_str] pattern
|
67
|
+
* @param [#to_int] offset
|
68
|
+
* @return [Integer, nil]
|
69
|
+
* @see #rindex */
|
70
|
+
VALUE
|
71
|
+
rb_u_string_index_m(int argc, VALUE *argv, VALUE self)
|
72
|
+
{
|
73
|
+
VALUE sub, rboffset;
|
74
|
+
long offset = 0;
|
75
|
+
if (rb_scan_args(argc, argv, "11", &sub, &rboffset) == 2)
|
76
|
+
offset = NUM2LONG(rboffset);
|
77
|
+
|
78
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
79
|
+
|
80
|
+
const char *begin = rb_u_string_begin_from_offset(string, offset);
|
81
|
+
if (begin == NULL) {
|
82
|
+
if (TYPE(sub) == T_REGEXP)
|
83
|
+
rb_backref_set(Qnil);
|
84
|
+
|
85
|
+
return Qnil;
|
86
|
+
}
|
87
|
+
|
88
|
+
switch (TYPE(sub)) {
|
89
|
+
case T_REGEXP:
|
90
|
+
offset = rb_u_string_index_regexp(self, begin, sub, false);
|
91
|
+
break;
|
92
|
+
default: {
|
93
|
+
VALUE tmp = rb_check_string_type(sub);
|
94
|
+
if (NIL_P(tmp))
|
95
|
+
rb_u_raise(rb_eTypeError, "type mismatch: %s given",
|
96
|
+
rb_obj_classname(sub));
|
97
|
+
|
98
|
+
sub = tmp;
|
99
|
+
}
|
100
|
+
/* fall through */
|
101
|
+
case T_STRING:
|
102
|
+
offset = rb_u_string_index(self, sub, offset);
|
103
|
+
break;
|
104
|
+
}
|
105
|
+
|
106
|
+
if (offset < 0)
|
107
|
+
return Qnil;
|
108
|
+
|
109
|
+
return LONG2NUM(offset);
|
110
|
+
}
|