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
@@ -1,319 +0,0 @@
|
|
1
|
-
/*
|
2
|
-
* contents: Unicode class.
|
3
|
-
*
|
4
|
-
* Copyright © 2005 Nikolai Weibull <work@rawuncut.elitemail.org>
|
5
|
-
*/
|
6
|
-
|
7
|
-
|
8
|
-
#include <ruby.h>
|
9
|
-
#include <re.h>
|
10
|
-
#include <stdbool.h>
|
11
|
-
#include <stddef.h>
|
12
|
-
#include <stdint.h>
|
13
|
-
#include <limits.h>
|
14
|
-
#include "unicode.h"
|
15
|
-
#include "private.h"
|
16
|
-
#include "rb_private.h"
|
17
|
-
#include "rb_methods.h"
|
18
|
-
|
19
|
-
static VALUE mUTF8Methods;
|
20
|
-
|
21
|
-
void
|
22
|
-
need_at_least_n_arguments(int argc, int n)
|
23
|
-
{
|
24
|
-
static const char *const words[] = {
|
25
|
-
NULL, NULL, "two", "three", "four",
|
26
|
-
"five", "six", "seven", "eight", "nine"
|
27
|
-
};
|
28
|
-
|
29
|
-
if (argc >= n)
|
30
|
-
return;
|
31
|
-
|
32
|
-
if (n == 1)
|
33
|
-
rb_raise(rb_eArgError, "need at least one argument");
|
34
|
-
else if (1 < n && n < 10)
|
35
|
-
rb_raise(rb_eArgError, "need at least %s arguments", words[n]);
|
36
|
-
else
|
37
|
-
rb_raise(rb_eArgError, "need at least %d arguments", n);
|
38
|
-
}
|
39
|
-
|
40
|
-
unichar
|
41
|
-
_utf_char_validated(char const *const str, char const *const str_end)
|
42
|
-
{
|
43
|
-
unichar c = utf_char_validated_n(str, str_end - str);
|
44
|
-
switch (c) {
|
45
|
-
case UTF_BAD_INPUT_UNICHAR:
|
46
|
-
rb_raise(rb_eArgError, "input isn’t valid UTF-8");
|
47
|
-
case UTF_INCOMPLETE_INPUT_UNICHAR:
|
48
|
-
rb_raise(rb_eArgError,
|
49
|
-
"input contains an incomplete UTF-8-encoded character");
|
50
|
-
default:
|
51
|
-
return c;
|
52
|
-
}
|
53
|
-
}
|
54
|
-
|
55
|
-
/* TODO: instead of ‘end’, perhaps use a len/max-type parameter? */
|
56
|
-
char *
|
57
|
-
_utf_offset_to_pointer_validated_impl(const char *str, long offset,
|
58
|
-
const char *limit, bool noisy)
|
59
|
-
{
|
60
|
-
const char *p = str;
|
61
|
-
long saved_offset = offset;
|
62
|
-
|
63
|
-
if (offset > 0) {
|
64
|
-
while (p < limit && offset-- > 0)
|
65
|
-
p = utf_next(p);
|
66
|
-
|
67
|
-
if (offset > 0) {
|
68
|
-
if (noisy)
|
69
|
-
rb_raise(rb_eIndexError,
|
70
|
-
"index %ld lays beyond end of string",
|
71
|
-
saved_offset);
|
72
|
-
else
|
73
|
-
return NULL;
|
74
|
-
}
|
75
|
-
} else {
|
76
|
-
while (offset != 0) {
|
77
|
-
const char *base = p;
|
78
|
-
p += offset;
|
79
|
-
while (p >= limit && (*p & 0xc0) == 0x80)
|
80
|
-
p--;
|
81
|
-
|
82
|
-
if (p < limit) {
|
83
|
-
if (noisy)
|
84
|
-
rb_raise(rb_eIndexError,
|
85
|
-
"index %ld lays before beginning of string",
|
86
|
-
saved_offset);
|
87
|
-
else
|
88
|
-
return NULL;
|
89
|
-
}
|
90
|
-
|
91
|
-
offset += utf_pointer_to_offset(p, base);
|
92
|
-
}
|
93
|
-
}
|
94
|
-
|
95
|
-
return (char *)p;
|
96
|
-
}
|
97
|
-
|
98
|
-
char *
|
99
|
-
_utf_offset_to_pointer_validated(const char *str, long offset, const char *end)
|
100
|
-
{
|
101
|
-
return _utf_offset_to_pointer_validated_impl(str, offset, end, true);
|
102
|
-
}
|
103
|
-
|
104
|
-
char *
|
105
|
-
_utf_offset_to_pointer_failable(const char *str, long offset, const char *end)
|
106
|
-
{
|
107
|
-
return _utf_offset_to_pointer_validated_impl(str, offset, end, false);
|
108
|
-
}
|
109
|
-
|
110
|
-
static char *
|
111
|
-
rb_utf_begin_setup(VALUE str, long offset, char **base_limit, char **limit)
|
112
|
-
{
|
113
|
-
char *base = RSTRING(str)->ptr;
|
114
|
-
|
115
|
-
*base_limit = RSTRING(str)->ptr + RSTRING(str)->len;
|
116
|
-
*limit = *base_limit;
|
117
|
-
|
118
|
-
if (offset < 0) {
|
119
|
-
char *tmp = base;
|
120
|
-
base = *base_limit;
|
121
|
-
*base_limit = tmp;
|
122
|
-
}
|
123
|
-
|
124
|
-
return base;
|
125
|
-
}
|
126
|
-
|
127
|
-
bool
|
128
|
-
rb_utf_begin_from_offset(VALUE str, long offset, char **begin, char **limit)
|
129
|
-
{
|
130
|
-
char *base_limit;
|
131
|
-
char *base = rb_utf_begin_setup(str, offset, &base_limit, limit);
|
132
|
-
|
133
|
-
*begin = _utf_offset_to_pointer_failable(base, offset, base_limit);
|
134
|
-
|
135
|
-
return (*begin != NULL);
|
136
|
-
}
|
137
|
-
|
138
|
-
void
|
139
|
-
rb_utf_begin_from_offset_validated(VALUE str, long offset, char **begin,
|
140
|
-
char **limit)
|
141
|
-
{
|
142
|
-
char *base_limit;
|
143
|
-
char *base = rb_utf_begin_setup(str, offset, &base_limit, limit);
|
144
|
-
|
145
|
-
*begin = _utf_offset_to_pointer_validated(base, offset, base_limit);
|
146
|
-
}
|
147
|
-
|
148
|
-
char *
|
149
|
-
rb_utf_prev_validated(const char *begin, const char *p)
|
150
|
-
{
|
151
|
-
char *prev = utf_find_prev(begin, p);
|
152
|
-
if (prev == NULL)
|
153
|
-
rb_raise(rb_eArgError, "input isn’t valid UTF-8");
|
154
|
-
return prev;
|
155
|
-
}
|
156
|
-
|
157
|
-
char *
|
158
|
-
rb_utf_next_validated(const char *p, const char *end)
|
159
|
-
{
|
160
|
-
char *next = (char *)utf_next(p);
|
161
|
-
if (next > end)
|
162
|
-
rb_raise(rb_eArgError, "input isn’t valid UTF-8");
|
163
|
-
return next;
|
164
|
-
}
|
165
|
-
|
166
|
-
VALUE
|
167
|
-
rb_utf_update(VALUE str, long offset, long len, VALUE replacement)
|
168
|
-
{
|
169
|
-
if (len < 0)
|
170
|
-
rb_raise(rb_eIndexError, "negative length %ld", len);
|
171
|
-
|
172
|
-
char *begin, *limit;
|
173
|
-
rb_utf_begin_from_offset_validated(str, offset, &begin, &limit);
|
174
|
-
char *end = _utf_offset_to_pointer_failable(begin, len, limit);
|
175
|
-
if (end == NULL)
|
176
|
-
end = limit;
|
177
|
-
|
178
|
-
rb_str_update(str, begin - RSTRING(str)->ptr, end - begin, replacement);
|
179
|
-
|
180
|
-
return replacement;
|
181
|
-
}
|
182
|
-
|
183
|
-
VALUE
|
184
|
-
rb_utf_new(const char *str, long len)
|
185
|
-
{
|
186
|
-
VALUE rbstr = rb_str_new(str, len);
|
187
|
-
rb_extend_object(rbstr, mUTF8Methods);
|
188
|
-
return rbstr;
|
189
|
-
}
|
190
|
-
|
191
|
-
VALUE
|
192
|
-
rb_utf_new2(const char *str)
|
193
|
-
{
|
194
|
-
VALUE rbstr = rb_str_new2(str);
|
195
|
-
rb_extend_object(rbstr, mUTF8Methods);
|
196
|
-
return rbstr;
|
197
|
-
}
|
198
|
-
|
199
|
-
VALUE
|
200
|
-
rb_utf_new5(VALUE obj, const char *str, long len)
|
201
|
-
{
|
202
|
-
VALUE rbstr = rb_str_new5(obj, str, len);
|
203
|
-
rb_extend_object(rbstr, mUTF8Methods);
|
204
|
-
return rbstr;
|
205
|
-
}
|
206
|
-
|
207
|
-
VALUE
|
208
|
-
rb_utf_alloc_using(char *str)
|
209
|
-
{
|
210
|
-
VALUE rbstr = rb_utf_new(NULL, 0);
|
211
|
-
long len = strlen(str);
|
212
|
-
|
213
|
-
RSTRING(rbstr)->ptr = str;
|
214
|
-
RSTRING(rbstr)->aux.capa = len;
|
215
|
-
RSTRING(rbstr)->len = len;
|
216
|
-
RSTRING(rbstr)->ptr[len] = '\0';
|
217
|
-
|
218
|
-
return rbstr;
|
219
|
-
}
|
220
|
-
|
221
|
-
VALUE
|
222
|
-
rb_utf_dup(VALUE str)
|
223
|
-
{
|
224
|
-
str = rb_str_dup(str);
|
225
|
-
rb_extend_object(str, mUTF8Methods);
|
226
|
-
return str;
|
227
|
-
}
|
228
|
-
|
229
|
-
/* TODO: rewrite this using the new offset-calculating functions. */
|
230
|
-
long
|
231
|
-
rb_utf_index(VALUE str, VALUE sub, long offset)
|
232
|
-
{
|
233
|
-
long n_chars = utf_length_n(RSTRING(str)->ptr, RSTRING(str)->len);
|
234
|
-
|
235
|
-
if (offset < 0) {
|
236
|
-
offset += n_chars;
|
237
|
-
|
238
|
-
if (offset < 0)
|
239
|
-
return -1;
|
240
|
-
}
|
241
|
-
|
242
|
-
if (n_chars - offset < utf_length(RSTRING(sub)->ptr))
|
243
|
-
return -1;
|
244
|
-
|
245
|
-
if (RSTRING(sub)->len == 0)
|
246
|
-
return offset;
|
247
|
-
|
248
|
-
char *begin = utf_offset_to_pointer(RSTRING(str)->ptr, offset);
|
249
|
-
long pos = rb_memsearch(RSTRING(sub)->ptr, RSTRING(sub)->len,
|
250
|
-
begin, RSTRING(str)->len - (begin - RSTRING(str)->ptr));
|
251
|
-
|
252
|
-
if (pos < 0)
|
253
|
-
return -1;
|
254
|
-
|
255
|
-
return offset + utf_pointer_to_offset(begin, begin + pos);
|
256
|
-
}
|
257
|
-
|
258
|
-
long
|
259
|
-
rb_utf_index_regexp(VALUE str, const char *s, const char *end, VALUE sub,
|
260
|
-
long offset, bool reverse)
|
261
|
-
{
|
262
|
-
long byte_offset = _utf_offset_to_pointer_validated(s, offset, end) - s;
|
263
|
-
long byte_startpos = rb_reg_adjust_startpos(sub, str, byte_offset, reverse);
|
264
|
-
long byte_index = rb_reg_search(sub, str, byte_startpos, reverse);
|
265
|
-
if (byte_index == -1)
|
266
|
-
return -1;
|
267
|
-
return utf_pointer_to_offset(s, s + byte_index);
|
268
|
-
}
|
269
|
-
|
270
|
-
void Init_utf8(void);
|
271
|
-
void
|
272
|
-
Init_utf8(void)
|
273
|
-
{
|
274
|
-
VALUE mEncoding = rb_define_module("Encoding");
|
275
|
-
VALUE mCharacter = rb_define_module_under(mEncoding, "Character");
|
276
|
-
VALUE mUTF8 = rb_define_module_under(mCharacter, "UTF8");
|
277
|
-
|
278
|
-
mUTF8Methods = rb_define_module_under(mUTF8, "Methods");
|
279
|
-
|
280
|
-
rb_define_module_function(mUTF8, "collate", rb_utf_collate, 2);
|
281
|
-
rb_define_module_function(mUTF8, "aref", rb_utf_aref_m, -1);
|
282
|
-
rb_define_module_function(mUTF8, "aset", rb_utf_aset_m, -1);
|
283
|
-
rb_define_module_function(mUTF8, "casecmp", rb_utf_casecmp, 2);
|
284
|
-
rb_define_module_function(mUTF8, "center", rb_utf_center, -1);
|
285
|
-
rb_define_module_function(mUTF8, "chomp", rb_utf_chomp, -1);
|
286
|
-
rb_define_module_function(mUTF8, "chomp!", rb_utf_chomp_bang, -1);
|
287
|
-
rb_define_module_function(mUTF8, "chop", rb_utf_chop, 1);
|
288
|
-
rb_define_module_function(mUTF8, "chop!", rb_utf_chop_bang, 1);
|
289
|
-
rb_define_module_function(mUTF8, "count", rb_utf_count, -1);
|
290
|
-
rb_define_module_function(mUTF8, "delete", rb_utf_delete, -1);
|
291
|
-
rb_define_module_function(mUTF8, "delete!", rb_utf_delete_bang, -1);
|
292
|
-
rb_define_module_function(mUTF8, "each_char", rb_utf_each_char, 1);
|
293
|
-
rb_define_module_function(mUTF8, "index", rb_utf_index_m, -1);
|
294
|
-
rb_define_module_function(mUTF8, "insert", rb_utf_insert, 3);
|
295
|
-
rb_define_module_function(mUTF8, "lstrip", rb_utf_lstrip, 1);
|
296
|
-
rb_define_module_function(mUTF8, "lstrip!", rb_utf_lstrip_bang, 1);
|
297
|
-
rb_define_module_function(mUTF8, "rindex", rb_utf_rindex_m, -1);
|
298
|
-
rb_define_module_function(mUTF8, "rstrip", rb_utf_rstrip, 1);
|
299
|
-
rb_define_module_function(mUTF8, "rstrip!", rb_utf_rstrip_bang, 1);
|
300
|
-
rb_define_module_function(mUTF8, "squeeze", rb_utf_squeeze, -1);
|
301
|
-
rb_define_module_function(mUTF8, "squeeze!", rb_utf_squeeze_bang, -1);
|
302
|
-
rb_define_module_function(mUTF8, "strip", rb_utf_strip, 1);
|
303
|
-
rb_define_module_function(mUTF8, "strip!", rb_utf_strip_bang, 1);
|
304
|
-
rb_define_module_function(mUTF8, "to_i", rb_utf_to_i, -1);
|
305
|
-
rb_define_module_function(mUTF8, "hex", rb_utf_hex, 1);
|
306
|
-
rb_define_module_function(mUTF8, "oct", rb_utf_oct, 1);
|
307
|
-
rb_define_module_function(mUTF8, "tr", rb_utf_tr, 3);
|
308
|
-
rb_define_module_function(mUTF8, "tr_s", rb_utf_tr_s, 3);
|
309
|
-
|
310
|
-
rb_define_module_function(mUTF8, "downcase", rb_utf_downcase, 1);
|
311
|
-
rb_define_module_function(mUTF8, "ljust", rb_utf_ljust, -1);
|
312
|
-
rb_define_module_function(mUTF8, "length", rb_utf_length, 1);
|
313
|
-
rb_define_module_function(mUTF8, "reverse", rb_utf_reverse, 1);
|
314
|
-
rb_define_module_function(mUTF8, "rjust", rb_utf_rjust, -1);
|
315
|
-
rb_define_module_function(mUTF8, "upcase", rb_utf_upcase, 1);
|
316
|
-
|
317
|
-
rb_define_module_function(mUTF8, "foldcase", rb_utf_foldcase, 1);
|
318
|
-
rb_define_module_function(mUTF8, "normalize", rb_utf_normalize, -1);
|
319
|
-
}
|
@@ -1,216 +0,0 @@
|
|
1
|
-
/*
|
2
|
-
* contents: Unicode handling.
|
3
|
-
*
|
4
|
-
* Copyright (C) 2004 Nikolai Weibull <source@pcppopper.org>
|
5
|
-
*/
|
6
|
-
|
7
|
-
|
8
|
-
#ifndef UNICODE_H
|
9
|
-
#define UNICODE_H
|
10
|
-
|
11
|
-
#if __GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ > 4)
|
12
|
-
#define CONST_FUNC \
|
13
|
-
__attribute__((__const__))
|
14
|
-
#else
|
15
|
-
#define CONST_FUNC
|
16
|
-
#endif
|
17
|
-
|
18
|
-
typedef uint32_t unichar;
|
19
|
-
|
20
|
-
#define MAXUNICHAR UINT32_MAX
|
21
|
-
|
22
|
-
#define MAX_UNICHAR_BYTE_LENGTH 6
|
23
|
-
|
24
|
-
#define UNICODE_N_CODEPOINTS (0x10ffff + 1)
|
25
|
-
|
26
|
-
/* unichar return used for representing bad input to a function. */
|
27
|
-
#define UTF_BAD_INPUT_UNICHAR ((unichar)-1)
|
28
|
-
|
29
|
-
|
30
|
-
/* unichar return used for representing an incomplete input to a function. */
|
31
|
-
#define UTF_INCOMPLETE_INPUT_UNICHAR ((unichar)-2)
|
32
|
-
|
33
|
-
|
34
|
-
typedef enum {
|
35
|
-
UNICODE_CONTROL,
|
36
|
-
UNICODE_FORMAT,
|
37
|
-
UNICODE_UNASSIGNED,
|
38
|
-
UNICODE_PRIVATE_USE,
|
39
|
-
UNICODE_SURROGATE,
|
40
|
-
UNICODE_LOWERCASE_LETTER,
|
41
|
-
UNICODE_MODIFIER_LETTER,
|
42
|
-
UNICODE_OTHER_LETTER,
|
43
|
-
UNICODE_TITLECASE_LETTER,
|
44
|
-
UNICODE_UPPERCASE_LETTER,
|
45
|
-
UNICODE_COMBINING_MARK,
|
46
|
-
UNICODE_ENCLOSING_MARK,
|
47
|
-
UNICODE_NON_SPACING_MARK,
|
48
|
-
UNICODE_DECIMAL_NUMBER,
|
49
|
-
UNICODE_LETTER_NUMBER,
|
50
|
-
UNICODE_OTHER_NUMBER,
|
51
|
-
UNICODE_CONNECT_PUNCTUATION,
|
52
|
-
UNICODE_DASH_PUNCTUATION,
|
53
|
-
UNICODE_CLOSE_PUNCTUATION,
|
54
|
-
UNICODE_FINAL_PUNCTUATION,
|
55
|
-
UNICODE_INITIAL_PUNCTUATION,
|
56
|
-
UNICODE_OTHER_PUNCTUATION,
|
57
|
-
UNICODE_OPEN_PUNCTUATION,
|
58
|
-
UNICODE_CURRENCY_SYMBOL,
|
59
|
-
UNICODE_MODIFIER_SYMBOL,
|
60
|
-
UNICODE_MATH_SYMBOL,
|
61
|
-
UNICODE_OTHER_SYMBOL,
|
62
|
-
UNICODE_LINE_SEPARATOR,
|
63
|
-
UNICODE_PARAGRAPH_SEPARATOR,
|
64
|
-
UNICODE_SPACE_SEPARATOR
|
65
|
-
} UnicodeType;
|
66
|
-
|
67
|
-
bool unichar_isalnum(unichar c);
|
68
|
-
bool unichar_isalpha(unichar c);
|
69
|
-
bool unichar_iscntrl(unichar c);
|
70
|
-
bool unichar_isdigit(unichar c);
|
71
|
-
bool unichar_isgraph(unichar c);
|
72
|
-
bool unichar_islower(unichar c);
|
73
|
-
bool unichar_isprint(unichar c);
|
74
|
-
bool unichar_ispunct(unichar c);
|
75
|
-
bool unichar_isspace(unichar c);
|
76
|
-
bool unichar_isupper(unichar c);
|
77
|
-
bool unichar_istitle(unichar c);
|
78
|
-
bool unichar_isnewline(unichar c);
|
79
|
-
bool unichar_isxdigit(unichar c);
|
80
|
-
bool unichar_isassigned(unichar c);
|
81
|
-
bool unichar_iswide(unichar c);
|
82
|
-
bool unichar_isvalid(unichar c);
|
83
|
-
|
84
|
-
unichar unichar_toupper(unichar c);
|
85
|
-
unichar unichar_tolower(unichar c);
|
86
|
-
unichar unichar_totitle(unichar c);
|
87
|
-
|
88
|
-
int unichar_digit_value(unichar c);
|
89
|
-
int unichar_xdigit_value(unichar c);
|
90
|
-
|
91
|
-
UnicodeType unichar_type(unichar c);
|
92
|
-
|
93
|
-
int unichar_combining_class(unichar c) CONST_FUNC;
|
94
|
-
|
95
|
-
bool unichar_mirror(unichar c, unichar *mirrored);
|
96
|
-
|
97
|
-
|
98
|
-
typedef enum {
|
99
|
-
UNICODE_BREAK_MANDATORY,
|
100
|
-
UNICODE_BREAK_CARRIAGE_RETURN,
|
101
|
-
UNICODE_BREAK_LINE_FEED,
|
102
|
-
UNICODE_BREAK_COMBINING_MARK,
|
103
|
-
UNICODE_BREAK_SURROGATE,
|
104
|
-
UNICODE_BREAK_ZERO_WIDTH_SPACE,
|
105
|
-
UNICODE_BREAK_INSEPARABLE,
|
106
|
-
UNICODE_BREAK_NON_BREAKING_GLUE,
|
107
|
-
UNICODE_BREAK_CONTINGENT,
|
108
|
-
UNICODE_BREAK_SPACE,
|
109
|
-
UNICODE_BREAK_AFTER,
|
110
|
-
UNICODE_BREAK_BEFORE,
|
111
|
-
UNICODE_BREAK_BEFORE_AND_AFTER,
|
112
|
-
UNICODE_BREAK_HYPHEN,
|
113
|
-
UNICODE_BREAK_NON_STARTER,
|
114
|
-
UNICODE_BREAK_OPEN_PUNCTUATION,
|
115
|
-
UNICODE_BREAK_CLOSE_PUNCTUATION,
|
116
|
-
UNICODE_BREAK_QUOTATION,
|
117
|
-
UNICODE_BREAK_EXCLAMATION,
|
118
|
-
UNICODE_BREAK_IDEOGRAPHIC,
|
119
|
-
UNICODE_BREAK_NUMERIC,
|
120
|
-
UNICODE_BREAK_INFIX_SEPARATOR,
|
121
|
-
UNICODE_BREAK_SYMBOL,
|
122
|
-
UNICODE_BREAK_ALPHABETIC,
|
123
|
-
UNICODE_BREAK_PREFIX,
|
124
|
-
UNICODE_BREAK_POSTFIX,
|
125
|
-
UNICODE_BREAK_COMPLEX_CONTEXT,
|
126
|
-
UNICODE_BREAK_AMBIGUOUS,
|
127
|
-
UNICODE_BREAK_UNKNOWN,
|
128
|
-
UNICODE_BREAK_NEXT_LINE,
|
129
|
-
UNICODE_BREAK_WORD_JOINER,
|
130
|
-
UNICODE_BREAK_HANGUL_L_JAMO,
|
131
|
-
UNICODE_BREAK_HANGUL_V_JAMO,
|
132
|
-
UNICODE_BREAK_HANGUL_T_JAMO,
|
133
|
-
UNICODE_BREAK_HANGUL_LV_SYLLABLE,
|
134
|
-
UNICODE_BREAK_HANGUL_LVT_SYLLABLE
|
135
|
-
} UnicodeBreakType;
|
136
|
-
|
137
|
-
UnicodeBreakType unichar_break_type(unichar c);
|
138
|
-
|
139
|
-
|
140
|
-
typedef enum {
|
141
|
-
NORMALIZE_DEFAULT,
|
142
|
-
NORMALIZE_NFD = NORMALIZE_DEFAULT,
|
143
|
-
NORMALIZE_DEFAULT_COMPOSE,
|
144
|
-
NORMALIZE_NFC = NORMALIZE_DEFAULT_COMPOSE,
|
145
|
-
NORMALIZE_ALL,
|
146
|
-
NORMALIZE_NFKD = NORMALIZE_ALL,
|
147
|
-
NORMALIZE_ALL_COMPOSE,
|
148
|
-
NORMALIZE_NFKC = NORMALIZE_ALL_COMPOSE
|
149
|
-
} NormalizeMode;
|
150
|
-
|
151
|
-
void unicode_canonical_ordering(unichar *str, size_t len);
|
152
|
-
unichar *unicode_canonical_decomposition(unichar c, size_t *result_len);
|
153
|
-
|
154
|
-
char *utf_normalize(const char *str, NormalizeMode mode);
|
155
|
-
char *utf_normalize_n(const char *str, NormalizeMode mode, size_t len);
|
156
|
-
|
157
|
-
|
158
|
-
|
159
|
-
|
160
|
-
char *utf_upcase(const char *str);
|
161
|
-
char *utf_upcase_n(const char *str, size_t len);
|
162
|
-
char *utf_downcase(const char *str);
|
163
|
-
char *utf_downcase_n(const char *str, size_t len);
|
164
|
-
char *utf_foldcase(const char *str);
|
165
|
-
char *utf_foldcase_n(const char *str, size_t len);
|
166
|
-
|
167
|
-
unichar utf_char(const char *str);
|
168
|
-
unichar utf_char_n(const char *str, size_t max);
|
169
|
-
unichar utf_char_validated(const char *str);
|
170
|
-
unichar utf_char_validated_n(const char *str, size_t max);
|
171
|
-
|
172
|
-
extern const char * const s_utf_skip_lengths;
|
173
|
-
#define utf_next(str) ((str) + s_utf_skip_lengths[*(const unsigned char *)(str)])
|
174
|
-
char *utf_find_next(const char *p, const char *end);
|
175
|
-
char *utf_prev(const char *p);
|
176
|
-
char *utf_find_prev(const char *begin, const char *p);
|
177
|
-
char *utf_offset_to_pointer(const char *str, long offset);
|
178
|
-
long utf_pointer_to_offset(const char *str, const char *pos);
|
179
|
-
|
180
|
-
void utf_copy(char *dest, const char *src);
|
181
|
-
void utf_copy_n(char *dest, const char *src, size_t n);
|
182
|
-
void utf_append(char *dest, const char *src);
|
183
|
-
void utf_append_n(char *dest, const char *src, size_t n);
|
184
|
-
int utf_collate(const char *a, const char *b);
|
185
|
-
char *utf_collate_key(const char *str);
|
186
|
-
char *utf_collate_key_n(const char *str, size_t len);
|
187
|
-
int utf_char_index(const char *str, unichar c);
|
188
|
-
int utf_char_index_n(const char *str, unichar c, size_t len);
|
189
|
-
int utf_char_rindex(const char *str, unichar c);
|
190
|
-
int utf_char_rindex_n(const char *str, unichar c, size_t len);
|
191
|
-
int utf_index(const char *haystack, const char *needle);
|
192
|
-
int utf_index_n(const char *haystack, const char *needle, size_t len);
|
193
|
-
int utf_rindex(const char *haystack, const char *needle);
|
194
|
-
int utf_rindex_n(const char *haystack, const char *needle, size_t len);
|
195
|
-
bool utf_has_prefix(const char *str, const char *prefix);
|
196
|
-
long utf_length(const char *str);
|
197
|
-
long utf_length_n(const char *str, long len);
|
198
|
-
size_t utf_width(const char *str);
|
199
|
-
size_t utf_width_n(const char *str, size_t len);
|
200
|
-
size_t utf_byte_length(const char *str);
|
201
|
-
char *utf_reverse(const char *str);
|
202
|
-
char *utf_reverse_n(const char *str, size_t len);
|
203
|
-
|
204
|
-
bool utf_isvalid(const char *str);
|
205
|
-
bool utf_isvalid_n(const char *str, size_t max, const char **end);
|
206
|
-
|
207
|
-
/* XXX: should probably name stuff utf32 instead of ucs4 */
|
208
|
-
int unichar_to_utf(unichar c, char *result);
|
209
|
-
char *ucs4_to_utf8(unichar *str, size_t *items_read, size_t *items_written);
|
210
|
-
char *ucs4_to_utf8_n(unichar *str, size_t len, size_t *items_read, size_t *items_written);
|
211
|
-
unichar *utf8_to_ucs4_fast(const char *str, size_t *items_written);
|
212
|
-
unichar *utf8_to_ucs4_fast_n(const char *str, size_t len, size_t *items_written);
|
213
|
-
unichar *utf8_to_ucs4(const char *str, size_t *items_read, size_t *items_written);
|
214
|
-
unichar *utf8_to_ucs4_n(const char *str, int len, size_t *items_read, size_t *items_written);
|
215
|
-
|
216
|
-
#endif /* UNICODE_H */
|