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 +1,22 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
|
3
|
+
/* @overload xdigit?
|
4
|
+
*
|
5
|
+
* Returns true if the receiver contains only characters in the general
|
6
|
+
* category Number, decimal digit (Nd) or is a lower- or uppercase letter
|
7
|
+
* between ‘a’ and ‘f’. Specifically, any character that
|
8
|
+
*
|
9
|
+
* * Belongs to the general category Number, decimal digit (Nd)
|
10
|
+
* * Falls in the range U+0041 (LATIN CAPITAL LETTER A) through U+0046 (LATIN CAPITAL LETTER F)
|
11
|
+
* * Falls in the range U+0061 (LATIN SMALL LETTER A) through U+0066 (LATIN SMALL LETTER F)
|
12
|
+
* * Falls in the range U+FF21 (FULLWIDTH LATIN CAPITAL LETTER A) through U+FF26 (FULLWIDTH LATIN CAPITAL LETTER F)
|
13
|
+
* * Falls in the range U+FF41 (FULLWIDTH LATIN SMALL LETTER A) through U+FF46 (FULLWIDTH LATIN SMALL LETTER F)
|
14
|
+
*
|
15
|
+
* will do.
|
16
|
+
*
|
17
|
+
* @return [Boolean] */
|
18
|
+
VALUE
|
19
|
+
rb_u_string_xdigit(VALUE self)
|
20
|
+
{
|
21
|
+
return _rb_u_character_test(self, u_char_isxdigit);
|
22
|
+
}
|
@@ -0,0 +1,16 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
|
3
|
+
/* @overload zero_width?
|
4
|
+
*
|
5
|
+
* Returns true if the receiver contains only “zero-width” characters. A
|
6
|
+
* zero-width character is defined as a character in the general categories
|
7
|
+
* Mark, nonspacing (Mn), Mark, enclosing (Me) or Other, format (Of),
|
8
|
+
* excluding the character U+00AD (SOFT HYPHEN), or is a Hangul character
|
9
|
+
* between U+1160 and U+1200 or U+200B (ZERO WIDTH SPACE).
|
10
|
+
*
|
11
|
+
* @return [Boolean] */
|
12
|
+
VALUE
|
13
|
+
rb_u_string_zero_width(VALUE self)
|
14
|
+
{
|
15
|
+
return _rb_u_character_test(self, u_char_iszerowidth);
|
16
|
+
}
|
data/ext/u/titled.c
ADDED
@@ -0,0 +1,55 @@
|
|
1
|
+
#include <stdbool.h>
|
2
|
+
#include <stddef.h>
|
3
|
+
#include <stdint.h>
|
4
|
+
|
5
|
+
#include "u.h"
|
6
|
+
#include "private.h"
|
7
|
+
|
8
|
+
#include "data/constants.h"
|
9
|
+
#include "data/title-table.h"
|
10
|
+
|
11
|
+
#include "titled.h"
|
12
|
+
|
13
|
+
/* {{{1
|
14
|
+
* Determine whether ‘c’ is a titlecase letter, such as the slavic digraph DZ,
|
15
|
+
* which at the beginning of a word is written as Dz, where only the initial D
|
16
|
+
* is capitalized. (Complicated huh?)
|
17
|
+
*/
|
18
|
+
bool
|
19
|
+
u_char_istitle(uint32_t c)
|
20
|
+
{
|
21
|
+
size_t index;
|
22
|
+
|
23
|
+
return unicode_table_lookup(title_table, c, &index);
|
24
|
+
}
|
25
|
+
|
26
|
+
|
27
|
+
/* {{{1
|
28
|
+
* Convert ‘c’ to its titlecase representation (if any).
|
29
|
+
*/
|
30
|
+
uint32_t
|
31
|
+
u_char_titlecase(uint32_t c)
|
32
|
+
{
|
33
|
+
for (size_t i = 0; i < lengthof(title_table); i++)
|
34
|
+
if (title_table[i].ch == c ||
|
35
|
+
title_table[i].upper == c ||
|
36
|
+
title_table[i].lower == c)
|
37
|
+
return title_table[i].ch;
|
38
|
+
|
39
|
+
if (u_char_general_category(c) == U_GENERAL_CATEGORY_LETTER_LOWERCASE)
|
40
|
+
return u_char_upcase(c);
|
41
|
+
|
42
|
+
return c;
|
43
|
+
}
|
44
|
+
|
45
|
+
|
46
|
+
uint32_t
|
47
|
+
_u_titlecase_table_lookup(uint32_t c, bool want_upper)
|
48
|
+
{
|
49
|
+
size_t index;
|
50
|
+
|
51
|
+
if (!unicode_table_lookup(title_table, c, &index))
|
52
|
+
return c;
|
53
|
+
|
54
|
+
return want_upper ? title_table[index].upper : title_table[index].lower;
|
55
|
+
}
|
data/ext/u/titled.h
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
U_CONST uint32_t _u_titlecase_table_lookup(uint32_t c, bool want_upper);
|
data/ext/u/u.c
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
#include <stddef.h>
|
2
|
+
#include <stdint.h>
|
3
|
+
#include <stdbool.h>
|
4
|
+
|
5
|
+
#include "u.h"
|
6
|
+
|
7
|
+
/* {{{1
|
8
|
+
* s_utf_skip_lengths: This table is used for keeping track of how long a given
|
9
|
+
* UTF-8 character sequence is from the contents of the first byte.
|
10
|
+
*/
|
11
|
+
static const uint8_t s_u_skip_length_data[256] = {
|
12
|
+
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
13
|
+
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
14
|
+
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
15
|
+
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
16
|
+
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
17
|
+
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
18
|
+
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
19
|
+
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 6, 6, 1, 1
|
20
|
+
};
|
21
|
+
|
22
|
+
|
23
|
+
const char * const u_skip_lengths = (const char *)s_u_skip_length_data;
|
data/ext/u/u.h
ADDED
@@ -0,0 +1,458 @@
|
|
1
|
+
#if __GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ > 4)
|
2
|
+
# define U_CONST __attribute__((__const__))
|
3
|
+
#else
|
4
|
+
# define U_CONST
|
5
|
+
#endif
|
6
|
+
|
7
|
+
#if __GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ > 96)
|
8
|
+
# define U_PURE __attribute__((__pure__))
|
9
|
+
#else
|
10
|
+
# define U_PURE
|
11
|
+
#endif
|
12
|
+
|
13
|
+
#if __GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ > 2)
|
14
|
+
# define U_NON_NULL(parameters) __attribute__((__nonnull__ parameters))
|
15
|
+
#else
|
16
|
+
# define U_NON_NULL(parameters)
|
17
|
+
#endif
|
18
|
+
|
19
|
+
#define U_CHAR_MAX_BYTE_LENGTH 4
|
20
|
+
|
21
|
+
#define U_N_CODEPOINTS (0x10ffff + 1)
|
22
|
+
|
23
|
+
enum u_general_category {
|
24
|
+
U_GENERAL_CATEGORY_OTHER_CONTROL,
|
25
|
+
U_GENERAL_CATEGORY_OTHER_FORMAT,
|
26
|
+
U_GENERAL_CATEGORY_OTHER_NOT_ASSIGNED,
|
27
|
+
U_GENERAL_CATEGORY_OTHER_PRIVATE_USE,
|
28
|
+
U_GENERAL_CATEGORY_OTHER_SURROGATE,
|
29
|
+
U_GENERAL_CATEGORY_LETTER_LOWERCASE,
|
30
|
+
U_GENERAL_CATEGORY_LETTER_MODIFIER,
|
31
|
+
U_GENERAL_CATEGORY_LETTER_OTHER,
|
32
|
+
U_GENERAL_CATEGORY_LETTER_TITLECASE,
|
33
|
+
U_GENERAL_CATEGORY_LETTER_UPPERCASE,
|
34
|
+
U_GENERAL_CATEGORY_MARK_SPACING_COMBINING,
|
35
|
+
U_GENERAL_CATEGORY_MARK_ENCLOSING,
|
36
|
+
U_GENERAL_CATEGORY_MARK_NON_SPACING,
|
37
|
+
U_GENERAL_CATEGORY_NUMBER_DECIMAL,
|
38
|
+
U_GENERAL_CATEGORY_NUMBER_LETTER,
|
39
|
+
U_GENERAL_CATEGORY_NUMBER_OTHER,
|
40
|
+
U_GENERAL_CATEGORY_PUNCTUATION_CONNECTOR,
|
41
|
+
U_GENERAL_CATEGORY_PUNCTUATION_DASH,
|
42
|
+
U_GENERAL_CATEGORY_PUNCTUATION_CLOSE,
|
43
|
+
U_GENERAL_CATEGORY_PUNCTUATION_FINAL_QUOTE,
|
44
|
+
U_GENERAL_CATEGORY_PUNCTUATION_INITIAL_QUOTE,
|
45
|
+
U_GENERAL_CATEGORY_PUNCTUATION_OTHER,
|
46
|
+
U_GENERAL_CATEGORY_PUNCTUATION_OPEN,
|
47
|
+
U_GENERAL_CATEGORY_SYMBOL_CURRENCY,
|
48
|
+
U_GENERAL_CATEGORY_SYMBOL_MODIFIER,
|
49
|
+
U_GENERAL_CATEGORY_SYMBOL_MATH,
|
50
|
+
U_GENERAL_CATEGORY_SYMBOL_OTHER,
|
51
|
+
U_GENERAL_CATEGORY_SEPARATOR_LINE,
|
52
|
+
U_GENERAL_CATEGORY_SEPARATOR_PARAGRAPH,
|
53
|
+
U_GENERAL_CATEGORY_SEPARATOR_SPACE,
|
54
|
+
};
|
55
|
+
|
56
|
+
U_CONST bool u_char_isalnum(uint32_t c);
|
57
|
+
U_CONST bool u_char_isalpha(uint32_t c);
|
58
|
+
U_CONST bool u_char_isassigned(uint32_t c);
|
59
|
+
U_CONST bool u_char_iscased(uint32_t c);
|
60
|
+
U_CONST bool u_char_iscaseignorable(uint32_t c);
|
61
|
+
U_CONST bool u_char_iscntrl(uint32_t c);
|
62
|
+
U_CONST bool u_char_isdefined(uint32_t c);
|
63
|
+
U_CONST bool u_char_isdigit(uint32_t c);
|
64
|
+
U_CONST bool u_char_isgraph(uint32_t c);
|
65
|
+
U_CONST bool u_char_islower(uint32_t c);
|
66
|
+
U_CONST bool u_char_isnewline(uint32_t c);
|
67
|
+
U_CONST bool u_char_isprint(uint32_t c);
|
68
|
+
U_CONST bool u_char_ispunct(uint32_t c);
|
69
|
+
U_CONST bool u_char_issoftdotted(uint32_t c);
|
70
|
+
U_CONST bool u_char_isspace(uint32_t c);
|
71
|
+
U_CONST bool u_char_istitle(uint32_t c);
|
72
|
+
U_CONST bool u_char_isupper(uint32_t c);
|
73
|
+
U_CONST bool u_char_isvalid(uint32_t c);
|
74
|
+
U_CONST bool u_char_iswide(uint32_t c);
|
75
|
+
U_CONST bool u_char_iswide_cjk(uint32_t c);
|
76
|
+
U_CONST bool u_char_isxdigit(uint32_t c);
|
77
|
+
U_CONST bool u_char_iszerowidth(uint32_t c);
|
78
|
+
|
79
|
+
U_CONST uint32_t u_char_downcase(uint32_t c);
|
80
|
+
U_CONST uint32_t u_char_titlecase(uint32_t c);
|
81
|
+
U_CONST uint32_t u_char_upcase(uint32_t c);
|
82
|
+
|
83
|
+
U_CONST size_t u_char_width(uint32_t c);
|
84
|
+
|
85
|
+
U_CONST int u_char_digit_value(uint32_t c);
|
86
|
+
U_CONST int u_char_xdigit_value(uint32_t c);
|
87
|
+
|
88
|
+
U_CONST enum u_general_category u_char_general_category(uint32_t c);
|
89
|
+
|
90
|
+
enum u_canonical_combining_class {
|
91
|
+
U_CANONICAL_COMBINING_CLASS_NOT_REORDERED = 0,
|
92
|
+
U_CANONICAL_COMBINING_CLASS_OVERLAY = 1,
|
93
|
+
U_CANONICAL_COMBINING_CLASS_NUKTA = 7,
|
94
|
+
U_CANONICAL_COMBINING_CLASS_KANA_VOICING = 8,
|
95
|
+
U_CANONICAL_COMBINING_CLASS_VIRAMA = 9,
|
96
|
+
U_CANONICAL_COMBINING_CLASS_CCC10 = 10,
|
97
|
+
U_CANONICAL_COMBINING_CLASS_CCC11 = 11,
|
98
|
+
U_CANONICAL_COMBINING_CLASS_CCC12 = 12,
|
99
|
+
U_CANONICAL_COMBINING_CLASS_CCC13 = 13,
|
100
|
+
U_CANONICAL_COMBINING_CLASS_CCC14 = 14,
|
101
|
+
U_CANONICAL_COMBINING_CLASS_CCC15 = 15,
|
102
|
+
U_CANONICAL_COMBINING_CLASS_CCC16 = 16,
|
103
|
+
U_CANONICAL_COMBINING_CLASS_CCC17 = 17,
|
104
|
+
U_CANONICAL_COMBINING_CLASS_CCC18 = 18,
|
105
|
+
U_CANONICAL_COMBINING_CLASS_CCC19 = 19,
|
106
|
+
U_CANONICAL_COMBINING_CLASS_CCC20 = 20,
|
107
|
+
U_CANONICAL_COMBINING_CLASS_CCC21 = 21,
|
108
|
+
U_CANONICAL_COMBINING_CLASS_CCC22 = 22,
|
109
|
+
U_CANONICAL_COMBINING_CLASS_CCC23 = 23,
|
110
|
+
U_CANONICAL_COMBINING_CLASS_CCC24 = 24,
|
111
|
+
U_CANONICAL_COMBINING_CLASS_CCC25 = 25,
|
112
|
+
U_CANONICAL_COMBINING_CLASS_CCC26 = 26,
|
113
|
+
U_CANONICAL_COMBINING_CLASS_CCC27 = 27,
|
114
|
+
U_CANONICAL_COMBINING_CLASS_CCC28 = 28,
|
115
|
+
U_CANONICAL_COMBINING_CLASS_CCC29 = 29,
|
116
|
+
U_CANONICAL_COMBINING_CLASS_CCC30 = 30,
|
117
|
+
U_CANONICAL_COMBINING_CLASS_CCC31 = 31,
|
118
|
+
U_CANONICAL_COMBINING_CLASS_CCC32 = 32,
|
119
|
+
U_CANONICAL_COMBINING_CLASS_CCC33 = 33,
|
120
|
+
U_CANONICAL_COMBINING_CLASS_CCC34 = 34,
|
121
|
+
U_CANONICAL_COMBINING_CLASS_CCC35 = 35,
|
122
|
+
U_CANONICAL_COMBINING_CLASS_CCC36 = 36,
|
123
|
+
U_CANONICAL_COMBINING_CLASS_CCC84 = 84,
|
124
|
+
U_CANONICAL_COMBINING_CLASS_CCC91 = 91,
|
125
|
+
U_CANONICAL_COMBINING_CLASS_CCC103 = 103,
|
126
|
+
U_CANONICAL_COMBINING_CLASS_CCC107 = 107,
|
127
|
+
U_CANONICAL_COMBINING_CLASS_CCC118 = 118,
|
128
|
+
U_CANONICAL_COMBINING_CLASS_CCC122 = 122,
|
129
|
+
U_CANONICAL_COMBINING_CLASS_CCC129 = 129,
|
130
|
+
U_CANONICAL_COMBINING_CLASS_CCC130 = 130,
|
131
|
+
U_CANONICAL_COMBINING_CLASS_CCC132 = 132,
|
132
|
+
U_CANONICAL_COMBINING_CLASS_ATTACHED_BELOW_LEFT = 200,
|
133
|
+
U_CANONICAL_COMBINING_CLASS_ATTACHED_BELOW = 202,
|
134
|
+
U_CANONICAL_COMBINING_CLASS_ATTACHED_ABOVE = 214,
|
135
|
+
U_CANONICAL_COMBINING_CLASS_ATTACHED_ABOVE_RIGHT = 216,
|
136
|
+
U_CANONICAL_COMBINING_CLASS_BELOW_LEFT = 218,
|
137
|
+
U_CANONICAL_COMBINING_CLASS_BELOW = 220,
|
138
|
+
U_CANONICAL_COMBINING_CLASS_BELOW_RIGHT = 222,
|
139
|
+
U_CANONICAL_COMBINING_CLASS_LEFT = 224,
|
140
|
+
U_CANONICAL_COMBINING_CLASS_RIGHT = 226,
|
141
|
+
U_CANONICAL_COMBINING_CLASS_ABOVE_LEFT = 228,
|
142
|
+
U_CANONICAL_COMBINING_CLASS_ABOVE = 230,
|
143
|
+
U_CANONICAL_COMBINING_CLASS_ABOVE_RIGHT = 232,
|
144
|
+
U_CANONICAL_COMBINING_CLASS_DOUBLE_BELOW = 233,
|
145
|
+
U_CANONICAL_COMBINING_CLASS_DOUBLE_ABOVE = 234,
|
146
|
+
U_CANONICAL_COMBINING_CLASS_IOTA_SUBSCRIPT = 240,
|
147
|
+
};
|
148
|
+
|
149
|
+
U_CONST enum u_canonical_combining_class
|
150
|
+
u_char_canonical_combining_class(uint32_t c);
|
151
|
+
|
152
|
+
uint32_t u_char_mirror(uint32_t c);
|
153
|
+
|
154
|
+
enum u_line_break {
|
155
|
+
U_LINE_BREAK_MANDATORY,
|
156
|
+
U_LINE_BREAK_CARRIAGE_RETURN,
|
157
|
+
U_LINE_BREAK_LINE_FEED,
|
158
|
+
U_LINE_BREAK_COMBINING_MARK,
|
159
|
+
U_LINE_BREAK_NEXT_LINE,
|
160
|
+
U_LINE_BREAK_SURROGATE,
|
161
|
+
U_LINE_BREAK_WORD_JOINER,
|
162
|
+
U_LINE_BREAK_ZERO_WIDTH_SPACE,
|
163
|
+
U_LINE_BREAK_NON_BREAKING_GLUE,
|
164
|
+
U_LINE_BREAK_SPACE,
|
165
|
+
U_LINE_BREAK_BREAK_OPPORTUNITY_BEFORE_AND_AFTER,
|
166
|
+
U_LINE_BREAK_BREAK_AFTER,
|
167
|
+
U_LINE_BREAK_BREAK_BEFORE,
|
168
|
+
U_LINE_BREAK_HYPHEN,
|
169
|
+
U_LINE_BREAK_CONTINGENT_BREAK_OPPORTUNITY,
|
170
|
+
U_LINE_BREAK_CLOSE_PUNCTUATION,
|
171
|
+
U_LINE_BREAK_CLOSE_PARENTHESIS,
|
172
|
+
U_LINE_BREAK_EXCLAMATION_INTERROGATION,
|
173
|
+
U_LINE_BREAK_INSEPARABLE,
|
174
|
+
U_LINE_BREAK_NONSTARTER,
|
175
|
+
U_LINE_BREAK_OPEN_PUNCTUATION,
|
176
|
+
U_LINE_BREAK_QUOTATION,
|
177
|
+
U_LINE_BREAK_INFIX_NUMERIC_SEPARATOR,
|
178
|
+
U_LINE_BREAK_NUMERIC,
|
179
|
+
U_LINE_BREAK_POSTFIX_NUMERIC,
|
180
|
+
U_LINE_BREAK_PREFIX_NUMERIC,
|
181
|
+
U_LINE_BREAK_SYMBOLS_ALLOWING_BREAK_AFTER,
|
182
|
+
U_LINE_BREAK_AMBIGUOUS,
|
183
|
+
U_LINE_BREAK_ALPHABETIC,
|
184
|
+
U_LINE_BREAK_CONDITIONAL_JAPANESE_STARTER,
|
185
|
+
U_LINE_BREAK_HANGUL_LV_SYLLABLE,
|
186
|
+
U_LINE_BREAK_HANGUL_LVT_SYLLABLE,
|
187
|
+
U_LINE_BREAK_HEBREW_LETTER,
|
188
|
+
U_LINE_BREAK_IDEOGRAPHIC,
|
189
|
+
U_LINE_BREAK_HANGUL_L_JAMO,
|
190
|
+
U_LINE_BREAK_HANGUL_V_JAMO,
|
191
|
+
U_LINE_BREAK_HANGUL_T_JAMO,
|
192
|
+
U_LINE_BREAK_REGIONAL_INDICATOR,
|
193
|
+
U_LINE_BREAK_COMPLEX_CONTEXT_DEPENDENT,
|
194
|
+
U_LINE_BREAK_UNKNOWN,
|
195
|
+
};
|
196
|
+
|
197
|
+
U_CONST enum u_line_break u_char_line_break(uint32_t c);
|
198
|
+
|
199
|
+
enum u_grapheme_break {
|
200
|
+
U_GRAPHEME_BREAK_CONTROL,
|
201
|
+
U_GRAPHEME_BREAK_CR,
|
202
|
+
U_GRAPHEME_BREAK_EXTEND,
|
203
|
+
U_GRAPHEME_BREAK_L,
|
204
|
+
U_GRAPHEME_BREAK_LF,
|
205
|
+
U_GRAPHEME_BREAK_LV,
|
206
|
+
U_GRAPHEME_BREAK_LVT,
|
207
|
+
U_GRAPHEME_BREAK_OTHER,
|
208
|
+
U_GRAPHEME_BREAK_PREPEND,
|
209
|
+
U_GRAPHEME_BREAK_REGIONAL_INDICATOR,
|
210
|
+
U_GRAPHEME_BREAK_SPACINGMARK,
|
211
|
+
U_GRAPHEME_BREAK_T,
|
212
|
+
U_GRAPHEME_BREAK_V,
|
213
|
+
};
|
214
|
+
|
215
|
+
U_CONST enum u_grapheme_break u_char_grapheme_break(uint32_t c);
|
216
|
+
|
217
|
+
enum u_word_break {
|
218
|
+
U_WORD_BREAK_ALETTER,
|
219
|
+
U_WORD_BREAK_CR,
|
220
|
+
U_WORD_BREAK_EXTEND,
|
221
|
+
U_WORD_BREAK_EXTENDNUMLET,
|
222
|
+
U_WORD_BREAK_FORMAT,
|
223
|
+
U_WORD_BREAK_KATAKANA,
|
224
|
+
U_WORD_BREAK_LF,
|
225
|
+
U_WORD_BREAK_MIDLETTER,
|
226
|
+
U_WORD_BREAK_MIDNUM,
|
227
|
+
U_WORD_BREAK_MIDNUMLET,
|
228
|
+
U_WORD_BREAK_NEWLINE,
|
229
|
+
U_WORD_BREAK_NUMERIC,
|
230
|
+
U_WORD_BREAK_OTHER,
|
231
|
+
U_WORD_BREAK_REGIONAL_INDICATOR,
|
232
|
+
};
|
233
|
+
|
234
|
+
U_CONST enum u_word_break u_char_word_break(uint32_t c);
|
235
|
+
|
236
|
+
|
237
|
+
enum u_script {
|
238
|
+
U_SCRIPT_COMMON,
|
239
|
+
U_SCRIPT_INHERITED,
|
240
|
+
U_SCRIPT_ARABIC,
|
241
|
+
U_SCRIPT_ARMENIAN,
|
242
|
+
U_SCRIPT_BENGALI,
|
243
|
+
U_SCRIPT_BOPOMOFO,
|
244
|
+
U_SCRIPT_CHEROKEE,
|
245
|
+
U_SCRIPT_COPTIC,
|
246
|
+
U_SCRIPT_CYRILLIC,
|
247
|
+
U_SCRIPT_DESERET,
|
248
|
+
U_SCRIPT_DEVANAGARI,
|
249
|
+
U_SCRIPT_ETHIOPIC,
|
250
|
+
U_SCRIPT_GEORGIAN,
|
251
|
+
U_SCRIPT_GOTHIC,
|
252
|
+
U_SCRIPT_GREEK,
|
253
|
+
U_SCRIPT_GUJARATI,
|
254
|
+
U_SCRIPT_GURMUKHI,
|
255
|
+
U_SCRIPT_HAN,
|
256
|
+
U_SCRIPT_HANGUL,
|
257
|
+
U_SCRIPT_HEBREW,
|
258
|
+
U_SCRIPT_HIRAGANA,
|
259
|
+
U_SCRIPT_KANNADA,
|
260
|
+
U_SCRIPT_KATAKANA,
|
261
|
+
U_SCRIPT_KHMER,
|
262
|
+
U_SCRIPT_LAO,
|
263
|
+
U_SCRIPT_LATIN,
|
264
|
+
U_SCRIPT_MALAYALAM,
|
265
|
+
U_SCRIPT_MONGOLIAN,
|
266
|
+
U_SCRIPT_MYANMAR,
|
267
|
+
U_SCRIPT_OGHAM,
|
268
|
+
U_SCRIPT_OLD_ITALIC,
|
269
|
+
U_SCRIPT_ORIYA,
|
270
|
+
U_SCRIPT_RUNIC,
|
271
|
+
U_SCRIPT_SINHALA,
|
272
|
+
U_SCRIPT_SYRIAC,
|
273
|
+
U_SCRIPT_TAMIL,
|
274
|
+
U_SCRIPT_TELUGU,
|
275
|
+
U_SCRIPT_THAANA,
|
276
|
+
U_SCRIPT_THAI,
|
277
|
+
U_SCRIPT_TIBETAN,
|
278
|
+
U_SCRIPT_CANADIAN_ABORIGINAL,
|
279
|
+
U_SCRIPT_YI,
|
280
|
+
U_SCRIPT_TAGALOG,
|
281
|
+
U_SCRIPT_HANUNOO,
|
282
|
+
U_SCRIPT_BUHID,
|
283
|
+
U_SCRIPT_TAGBANWA,
|
284
|
+
U_SCRIPT_BRAILLE,
|
285
|
+
U_SCRIPT_CYPRIOT,
|
286
|
+
U_SCRIPT_LIMBU,
|
287
|
+
U_SCRIPT_OSMANYA,
|
288
|
+
U_SCRIPT_SHAVIAN,
|
289
|
+
U_SCRIPT_LINEAR_B,
|
290
|
+
U_SCRIPT_TAI_LE,
|
291
|
+
U_SCRIPT_UGARITIC,
|
292
|
+
U_SCRIPT_NEW_TAI_LUE,
|
293
|
+
U_SCRIPT_BUGINESE,
|
294
|
+
U_SCRIPT_GLAGOLITIC,
|
295
|
+
U_SCRIPT_TIFINAGH,
|
296
|
+
U_SCRIPT_SYLOTI_NAGRI,
|
297
|
+
U_SCRIPT_OLD_PERSIAN,
|
298
|
+
U_SCRIPT_KHAROSHTHI,
|
299
|
+
U_SCRIPT_UNKNOWN,
|
300
|
+
U_SCRIPT_BALINESE,
|
301
|
+
U_SCRIPT_CUNEIFORM,
|
302
|
+
U_SCRIPT_PHOENICIAN,
|
303
|
+
U_SCRIPT_PHAGS_PA,
|
304
|
+
U_SCRIPT_NKO,
|
305
|
+
U_SCRIPT_KAYAH_LI,
|
306
|
+
U_SCRIPT_LEPCHA,
|
307
|
+
U_SCRIPT_REJANG,
|
308
|
+
U_SCRIPT_SUNDANESE,
|
309
|
+
U_SCRIPT_SAURASHTRA,
|
310
|
+
U_SCRIPT_CHAM,
|
311
|
+
U_SCRIPT_OL_CHIKI,
|
312
|
+
U_SCRIPT_VAI,
|
313
|
+
U_SCRIPT_CARIAN,
|
314
|
+
U_SCRIPT_LYCIAN,
|
315
|
+
U_SCRIPT_LYDIAN,
|
316
|
+
U_SCRIPT_AVESTAN,
|
317
|
+
U_SCRIPT_BAMUM,
|
318
|
+
U_SCRIPT_EGYPTIAN_HIEROGLYPHS,
|
319
|
+
U_SCRIPT_IMPERIAL_ARAMAIC,
|
320
|
+
U_SCRIPT_INSCRIPTIONAL_PAHLAVI,
|
321
|
+
U_SCRIPT_INSCRIPTIONAL_PARTHIAN,
|
322
|
+
U_SCRIPT_JAVANESE,
|
323
|
+
U_SCRIPT_KAITHI,
|
324
|
+
U_SCRIPT_LISU,
|
325
|
+
U_SCRIPT_MEETEI_MAYEK,
|
326
|
+
U_SCRIPT_OLD_SOUTH_ARABIAN,
|
327
|
+
U_SCRIPT_OLD_TURKIC,
|
328
|
+
U_SCRIPT_SAMARITAN,
|
329
|
+
U_SCRIPT_TAI_THAM,
|
330
|
+
U_SCRIPT_TAI_VIET,
|
331
|
+
U_SCRIPT_BATAK,
|
332
|
+
U_SCRIPT_BRAHMI,
|
333
|
+
U_SCRIPT_MANDAIC,
|
334
|
+
U_SCRIPT_MEROITIC_HIEROGLYPHS,
|
335
|
+
U_SCRIPT_MEROITIC_CURSIVE,
|
336
|
+
U_SCRIPT_SORA_SOMPENG,
|
337
|
+
U_SCRIPT_CHAKMA,
|
338
|
+
U_SCRIPT_SHARADA,
|
339
|
+
U_SCRIPT_TAKRI,
|
340
|
+
U_SCRIPT_MIAO,
|
341
|
+
};
|
342
|
+
|
343
|
+
U_CONST enum u_script u_char_script(uint32_t c);
|
344
|
+
|
345
|
+
enum u_normalization_form {
|
346
|
+
U_NORMALIZATION_FORM_D,
|
347
|
+
U_NORMALIZATION_FORM_C,
|
348
|
+
U_NORMALIZATION_FORM_KD,
|
349
|
+
U_NORMALIZATION_FORM_KC,
|
350
|
+
};
|
351
|
+
|
352
|
+
size_t u_normalize(char *restrict result, size_t m,
|
353
|
+
const char *restrict u, size_t n,
|
354
|
+
enum u_normalization_form form) U_NON_NULL((3));
|
355
|
+
|
356
|
+
enum u_normalized {
|
357
|
+
U_NORMALIZED_YES,
|
358
|
+
U_NORMALIZED_NO,
|
359
|
+
U_NORMALIZED_MAYBE,
|
360
|
+
};
|
361
|
+
|
362
|
+
enum u_normalized u_char_normalized(uint32_t c, enum u_normalization_form form);
|
363
|
+
enum u_normalized u_normalized(const char *u, size_t n,
|
364
|
+
enum u_normalization_form form) U_NON_NULL((1));
|
365
|
+
|
366
|
+
size_t u_downcase(char *restrict result, size_t m,
|
367
|
+
const char *restrict u, size_t n,
|
368
|
+
const char *restrict locale) U_NON_NULL((3));
|
369
|
+
|
370
|
+
size_t u_foldcase(char *restrict result, size_t m,
|
371
|
+
const char *restrict string, size_t n,
|
372
|
+
const char *restrict locale) U_NON_NULL((3));
|
373
|
+
|
374
|
+
size_t u_titlecase(char *restrict result, size_t m,
|
375
|
+
const char *restrict string, size_t n,
|
376
|
+
const char *restrict locale) U_NON_NULL((3));
|
377
|
+
|
378
|
+
size_t u_upcase(char *restrict result, size_t m,
|
379
|
+
const char *restrict string, size_t n,
|
380
|
+
const char *restrict locale) U_NON_NULL((3));
|
381
|
+
|
382
|
+
size_t u_mirror(char *restrict result, size_t m,
|
383
|
+
const char *restrict u, size_t n) U_NON_NULL((3));
|
384
|
+
|
385
|
+
size_t u_recode(char *restrict result, size_t m,
|
386
|
+
const char *restrict string, size_t n,
|
387
|
+
const char *restrict codeset) U_NON_NULL((3, 5));
|
388
|
+
|
389
|
+
extern const char * const u_skip_lengths;
|
390
|
+
|
391
|
+
#define u_next(str) ((str) + u_skip_lengths[*(const unsigned char *)(str)])
|
392
|
+
|
393
|
+
uint32_t u_decode(const char **q, const char *u, const char *end)
|
394
|
+
U_NON_NULL((1, 2, 3));
|
395
|
+
int u_decode_n(uint32_t *result, const char *u, size_t n)
|
396
|
+
U_NON_NULL((1, 2));
|
397
|
+
uint32_t u_decode_r(const char **p, const char *begin, const char *u);
|
398
|
+
|
399
|
+
U_PURE char *u_offset_to_pointer(const char *str, long offset) U_NON_NULL((1));
|
400
|
+
U_PURE char *u_offset_to_pointer_n(const char *str, long offset, size_t n)
|
401
|
+
U_NON_NULL((1));
|
402
|
+
|
403
|
+
U_PURE long u_pointer_to_offset(const char *str, const char *pos)
|
404
|
+
U_NON_NULL((1, 2));
|
405
|
+
|
406
|
+
U_PURE int u_collate(const char *a, size_t a_n, const char *b, size_t b_n,
|
407
|
+
const char *locale) U_NON_NULL((1, 3));
|
408
|
+
size_t u_collation_key(char *restrict result, size_t m,
|
409
|
+
const char *restrict string, size_t n,
|
410
|
+
const char *restrict locale) U_NON_NULL((3));
|
411
|
+
size_t u_normalized_collation_key(char *restrict result, size_t m,
|
412
|
+
const char *restrict string, size_t n,
|
413
|
+
const char *restrict locale) U_NON_NULL((3));
|
414
|
+
|
415
|
+
U_PURE size_t u_char_index(const char *str, uint32_t c) U_NON_NULL((1));
|
416
|
+
U_PURE size_t u_char_index_n(const char *str, uint32_t c, size_t n)
|
417
|
+
U_NON_NULL((1));
|
418
|
+
U_PURE size_t u_index(const char *haystack, const char *needle)
|
419
|
+
U_NON_NULL((1, 2));
|
420
|
+
U_PURE size_t u_index_n(const char *haystack, const char *needle, size_t n)
|
421
|
+
U_NON_NULL((1, 2));
|
422
|
+
|
423
|
+
U_PURE size_t u_char_rindex(const char *str, uint32_t c) U_NON_NULL((1));
|
424
|
+
U_PURE size_t u_char_rindex_n(const char *str, uint32_t c, size_t n)
|
425
|
+
U_NON_NULL((1));
|
426
|
+
U_PURE size_t u_rindex(const char *haystack, const char *needle)
|
427
|
+
U_NON_NULL((1, 2));
|
428
|
+
U_PURE size_t u_rindex_n(const char *haystack, const char *needle, size_t n)
|
429
|
+
U_NON_NULL((1, 2));
|
430
|
+
|
431
|
+
U_PURE bool u_has_prefix(const char *str, const char *prefix)
|
432
|
+
U_NON_NULL((1, 2));
|
433
|
+
|
434
|
+
bool u_valid(const char *restrict u, size_t n, const char **restrict end)
|
435
|
+
U_NON_NULL((1));
|
436
|
+
|
437
|
+
U_PURE bool u_is_ascii_only(const char *string) U_NON_NULL((1));
|
438
|
+
U_PURE bool u_is_ascii_only_n(const char *string, size_t n) U_NON_NULL((1));
|
439
|
+
|
440
|
+
U_PURE size_t u_n_chars(const char *str) U_NON_NULL((1));
|
441
|
+
U_PURE size_t u_n_chars_n(const char *str, size_t n) U_NON_NULL((1));
|
442
|
+
|
443
|
+
U_PURE size_t u_width(const char *string) U_NON_NULL((1));
|
444
|
+
U_PURE size_t u_width_n(const char *string, size_t n) U_NON_NULL((1));
|
445
|
+
|
446
|
+
U_PURE size_t u_n_bytes(const char *str) U_NON_NULL((1));
|
447
|
+
|
448
|
+
size_t u_reverse(char *restrict result, size_t m,
|
449
|
+
const char *restrict string, size_t n) U_NON_NULL((3));
|
450
|
+
|
451
|
+
typedef void (*u_substring_fn)(const char *, size_t, void *);
|
452
|
+
void u_words(const char *string, size_t n, u_substring_fn fn, void *closure)
|
453
|
+
U_NON_NULL((1));
|
454
|
+
void u_grapheme_clusters(const char *string, size_t n, u_substring_fn fn,
|
455
|
+
void *closure) U_NON_NULL((1));
|
456
|
+
|
457
|
+
int u_char_to_u_n(uint32_t c, char *result, size_t n);
|
458
|
+
int u_char_to_u(uint32_t c, char *result);
|