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 +1,28 @@
|
|
1
|
+
#include <stdbool.h>
|
2
|
+
#include <stddef.h>
|
3
|
+
#include <stdint.h>
|
4
|
+
|
5
|
+
#include "u.h"
|
6
|
+
#include "private.h"
|
7
|
+
|
8
|
+
|
9
|
+
/* {{{1
|
10
|
+
* Determine whether ‘c’ is some form of whitespace, such as space, tab or a
|
11
|
+
* line separator (newline, carriage return, etc.).
|
12
|
+
*/
|
13
|
+
bool
|
14
|
+
u_char_isspace(uint32_t c)
|
15
|
+
{
|
16
|
+
switch (c) {
|
17
|
+
case '\t':
|
18
|
+
case '\n':
|
19
|
+
case '\r':
|
20
|
+
case '\f':
|
21
|
+
return true;
|
22
|
+
default:
|
23
|
+
return IS(u_char_general_category(c),
|
24
|
+
OR(U_GENERAL_CATEGORY_SEPARATOR_SPACE,
|
25
|
+
OR(U_GENERAL_CATEGORY_SEPARATOR_LINE,
|
26
|
+
OR(U_GENERAL_CATEGORY_SEPARATOR_PARAGRAPH, 0)))) ? true : false;
|
27
|
+
}
|
28
|
+
}
|
@@ -0,0 +1,16 @@
|
|
1
|
+
#include <stdbool.h>
|
2
|
+
#include <stddef.h>
|
3
|
+
#include <stdint.h>
|
4
|
+
|
5
|
+
#include "u.h"
|
6
|
+
#include "private.h"
|
7
|
+
|
8
|
+
|
9
|
+
/* {{{1
|
10
|
+
* Determine whether ‘c’ is an uppeercase letter, such as A, B, or C
|
11
|
+
*/
|
12
|
+
bool
|
13
|
+
u_char_isupper(uint32_t c)
|
14
|
+
{
|
15
|
+
return u_char_general_category(c) == U_GENERAL_CATEGORY_LETTER_UPPERCASE;
|
16
|
+
}
|
@@ -0,0 +1,18 @@
|
|
1
|
+
#include <stddef.h>
|
2
|
+
#include <stdint.h>
|
3
|
+
#include <stdbool.h>
|
4
|
+
|
5
|
+
#include "u.h"
|
6
|
+
|
7
|
+
|
8
|
+
/* {{{1
|
9
|
+
* Check whether ‘c’ is a valid Unicode character.
|
10
|
+
*/
|
11
|
+
bool
|
12
|
+
u_char_isvalid(uint32_t c)
|
13
|
+
{
|
14
|
+
return ((c) < 0x110000 &&
|
15
|
+
(((c) & 0xffffff800) != 0xd800) &&
|
16
|
+
((c) < 0xfdd0 || (c) > 0xfdef) &&
|
17
|
+
((c) & 0xfffe) != 0xfffe);
|
18
|
+
}
|
@@ -0,0 +1,18 @@
|
|
1
|
+
#include <stddef.h>
|
2
|
+
#include <stdint.h>
|
3
|
+
#include <stdbool.h>
|
4
|
+
#include <stdlib.h>
|
5
|
+
|
6
|
+
#include "u.h"
|
7
|
+
|
8
|
+
#include "private.h"
|
9
|
+
|
10
|
+
#include "data/wide.h"
|
11
|
+
|
12
|
+
/* Returns true if C is typically rendered a double-width cell on a terminal. */
|
13
|
+
bool
|
14
|
+
u_char_iswide(uint32_t c)
|
15
|
+
{
|
16
|
+
return bsearch(&c, wide, lengthof(wide), sizeof(wide[0]),
|
17
|
+
u_char_interval_compare) != NULL;
|
18
|
+
}
|
@@ -0,0 +1,22 @@
|
|
1
|
+
#include <stddef.h>
|
2
|
+
#include <stdint.h>
|
3
|
+
#include <stdbool.h>
|
4
|
+
#include <stdlib.h>
|
5
|
+
|
6
|
+
#include "u.h"
|
7
|
+
|
8
|
+
#include "private.h"
|
9
|
+
|
10
|
+
#include "data/wide-cjk.h"
|
11
|
+
|
12
|
+
/* Returns true if C is typically rendered a double-width cell on a terminal
|
13
|
+
* under legacy East Asian locales.
|
14
|
+
*
|
15
|
+
* See http://www.unicode.org/reports/tr11/ for more details. */
|
16
|
+
bool
|
17
|
+
u_char_iswide_cjk(uint32_t c)
|
18
|
+
{
|
19
|
+
return u_char_iswide(c) ||
|
20
|
+
bsearch(&c, wide, lengthof(wide), sizeof(wide[0]),
|
21
|
+
u_char_interval_compare) != NULL;
|
22
|
+
}
|
@@ -0,0 +1,27 @@
|
|
1
|
+
#include <stdbool.h>
|
2
|
+
#include <stddef.h>
|
3
|
+
#include <stdint.h>
|
4
|
+
|
5
|
+
#include "u.h"
|
6
|
+
#include "private.h"
|
7
|
+
|
8
|
+
|
9
|
+
#define FULLWIDTH_A ((uint32_t)0xff21)
|
10
|
+
#define FULLWIDTH_F ((uint32_t)0xff26)
|
11
|
+
#define FULLWIDTH_a ((uint32_t)0xff41)
|
12
|
+
#define FULLWIDTH_f ((uint32_t)0xff46)
|
13
|
+
|
14
|
+
|
15
|
+
/* {{{1
|
16
|
+
* Determine whether ‘c’ is a hexadecimal digit, such as 0, 1, ..., 9, a, b,
|
17
|
+
* ..., f, or A, B, ..., F.
|
18
|
+
*/
|
19
|
+
bool
|
20
|
+
u_char_isxdigit(uint32_t c)
|
21
|
+
{
|
22
|
+
return ((c >= 'a' && c <= 'f') ||
|
23
|
+
(c >= 'A' && c <= 'F') ||
|
24
|
+
(c >= FULLWIDTH_a && c <= FULLWIDTH_f) ||
|
25
|
+
(c >= FULLWIDTH_A && c <= FULLWIDTH_F) ||
|
26
|
+
(u_char_general_category(c) == U_GENERAL_CATEGORY_NUMBER_DECIMAL));
|
27
|
+
}
|
@@ -0,0 +1,29 @@
|
|
1
|
+
#include <stdbool.h>
|
2
|
+
#include <stddef.h>
|
3
|
+
#include <stdint.h>
|
4
|
+
|
5
|
+
#include "u.h"
|
6
|
+
#include "private.h"
|
7
|
+
|
8
|
+
|
9
|
+
#define SOFT_HYPHEN ((uint32_t)0x00ad)
|
10
|
+
#define ZERO_WIDTH_SPACE ((uint32_t)0x200b)
|
11
|
+
|
12
|
+
|
13
|
+
bool
|
14
|
+
u_char_iszerowidth(uint32_t c)
|
15
|
+
{
|
16
|
+
if (UNLIKELY(c == SOFT_HYPHEN))
|
17
|
+
return false;
|
18
|
+
|
19
|
+
if (UNLIKELY(IS(u_char_general_category(c),
|
20
|
+
OR(U_GENERAL_CATEGORY_MARK_NON_SPACING,
|
21
|
+
OR(U_GENERAL_CATEGORY_MARK_ENCLOSING,
|
22
|
+
OR(U_GENERAL_CATEGORY_OTHER_FORMAT, 0))))))
|
23
|
+
return true;
|
24
|
+
|
25
|
+
if (UNLIKELY((0x1160 <= c && c < 0x1200) || c == ZERO_WIDTH_SPACE))
|
26
|
+
return true;
|
27
|
+
|
28
|
+
return false;
|
29
|
+
}
|
@@ -0,0 +1,29 @@
|
|
1
|
+
#include <stdbool.h>
|
2
|
+
#include <stddef.h>
|
3
|
+
#include <stdint.h>
|
4
|
+
|
5
|
+
#include "u.h"
|
6
|
+
#include "data/constants.h"
|
7
|
+
#include "data/line-break.h"
|
8
|
+
#include "private.h"
|
9
|
+
|
10
|
+
/* Figure out what break type the Unicode character ‘c’ possesses, if any.
|
11
|
+
* This information is used for finding word and line boundaries, which is
|
12
|
+
* useful when displaying Unicode text on screen. */
|
13
|
+
enum u_line_break
|
14
|
+
u_char_line_break(uint32_t c)
|
15
|
+
{
|
16
|
+
int16_t index;
|
17
|
+
|
18
|
+
if (c <= UNICODE_LAST_CHAR_PART1)
|
19
|
+
index = line_break_property_table_part1[c >> 8];
|
20
|
+
else if (UNICODE_FIRST_CHAR_PART2 <= c && c <= UNICODE_LAST_CHAR)
|
21
|
+
index = line_break_property_table_part2[(c - UNICODE_FIRST_CHAR_PART2) >> 8];
|
22
|
+
else
|
23
|
+
return U_LINE_BREAK_UNKNOWN;
|
24
|
+
|
25
|
+
if (index >= UNICODE_MAX_TABLE_INDEX)
|
26
|
+
return index - UNICODE_MAX_TABLE_INDEX;
|
27
|
+
|
28
|
+
return line_break_property_data[index][c & 0xff];
|
29
|
+
}
|
@@ -0,0 +1,16 @@
|
|
1
|
+
#include <stdbool.h>
|
2
|
+
#include <stddef.h>
|
3
|
+
#include <stdint.h>
|
4
|
+
#include "u.h"
|
5
|
+
|
6
|
+
#include "data/bidi-mirroring.h"
|
7
|
+
#include "private.h"
|
8
|
+
|
9
|
+
uint32_t
|
10
|
+
u_char_mirror(uint32_t c)
|
11
|
+
{
|
12
|
+
size_t i;
|
13
|
+
return unicode_table_lookup(bidi_mirroring_table, c, &i) ?
|
14
|
+
bidi_mirroring_table[i].mirrored_ch :
|
15
|
+
c;
|
16
|
+
}
|
@@ -0,0 +1,23 @@
|
|
1
|
+
#include <stdbool.h>
|
2
|
+
#include <stddef.h>
|
3
|
+
#include <stdint.h>
|
4
|
+
#include "u.h"
|
5
|
+
|
6
|
+
#include "data/constants.h"
|
7
|
+
#include "data/normalization-quick-check.h"
|
8
|
+
|
9
|
+
enum u_normalized
|
10
|
+
u_char_normalized(uint32_t c, enum u_normalization_form form)
|
11
|
+
{
|
12
|
+
int16_t i;
|
13
|
+
if (c <= UNICODE_LAST_CHAR_PART1)
|
14
|
+
i = normalization_quick_check_table_part1[c >> 8];
|
15
|
+
else if (UNICODE_FIRST_CHAR_PART2 <= c && c <= UNICODE_LAST_CHAR)
|
16
|
+
i = normalization_quick_check_table_part2[(c - UNICODE_FIRST_CHAR_PART2) >> 8];
|
17
|
+
else
|
18
|
+
return U_NORMALIZED_YES;
|
19
|
+
|
20
|
+
return (i >= UNICODE_MAX_TABLE_INDEX ?
|
21
|
+
i - UNICODE_MAX_TABLE_INDEX :
|
22
|
+
normalization_quick_check_data[i][c & 0xff]) & (((1 << 2) - 1) << (2 * form));
|
23
|
+
}
|
@@ -0,0 +1,41 @@
|
|
1
|
+
#include <stdbool.h>
|
2
|
+
#include <stddef.h>
|
3
|
+
#include <stdint.h>
|
4
|
+
|
5
|
+
#include "u.h"
|
6
|
+
|
7
|
+
#include "private.h"
|
8
|
+
|
9
|
+
#include "data/script.h"
|
10
|
+
|
11
|
+
|
12
|
+
static inline enum u_script
|
13
|
+
u_char_script_bsearch(uint32_t c)
|
14
|
+
{
|
15
|
+
int begin = 0;
|
16
|
+
int end = lengthof(script_table) - 1;
|
17
|
+
static int cached_middle = lengthof(script_table) / 2;
|
18
|
+
int middle = cached_middle;
|
19
|
+
|
20
|
+
do {
|
21
|
+
uint32_t probe = script_table[middle].start;
|
22
|
+
if (c < probe)
|
23
|
+
end = middle - 1;
|
24
|
+
else if (c >= probe + script_table[middle].chars)
|
25
|
+
begin = middle + 1;
|
26
|
+
else
|
27
|
+
return script_table[cached_middle = middle].script;
|
28
|
+
|
29
|
+
middle = binary_search_middle_of(begin, end);
|
30
|
+
} while (begin <= end);
|
31
|
+
|
32
|
+
return U_SCRIPT_UNKNOWN;
|
33
|
+
}
|
34
|
+
|
35
|
+
enum u_script
|
36
|
+
u_char_script(uint32_t c)
|
37
|
+
{
|
38
|
+
return c < EASY_SCRIPTS_RANGE ?
|
39
|
+
script_easy_table[c] :
|
40
|
+
u_char_script_bsearch(c);
|
41
|
+
}
|
data/ext/u/u_char_to_u.c
ADDED
@@ -0,0 +1,48 @@
|
|
1
|
+
#include <stddef.h>
|
2
|
+
#include <stdint.h>
|
3
|
+
#include <stdbool.h>
|
4
|
+
|
5
|
+
#include "u.h"
|
6
|
+
|
7
|
+
|
8
|
+
/* {{{1
|
9
|
+
* Turn an Unicode character (UTF-32) into an UTF-8 character sequence and
|
10
|
+
* store it in ‘result’, returning the length of the stored sequence.
|
11
|
+
*/
|
12
|
+
int
|
13
|
+
u_char_to_u_n(uint32_t c, char *result, size_t n)
|
14
|
+
{
|
15
|
+
if (c < 0x80) {
|
16
|
+
if (n > 0)
|
17
|
+
result[0] = c;
|
18
|
+
return 1;
|
19
|
+
}
|
20
|
+
|
21
|
+
size_t m;
|
22
|
+
if (c < 0x800)
|
23
|
+
m = 2;
|
24
|
+
else if (c < 0x10000) {
|
25
|
+
if (0xd800 <= c && c < 0xe000)
|
26
|
+
return 0;
|
27
|
+
m = 3;
|
28
|
+
} else if (c < U_N_CODEPOINTS)
|
29
|
+
m = 4;
|
30
|
+
else
|
31
|
+
return 0;
|
32
|
+
|
33
|
+
if (result != NULL && n >= m) {
|
34
|
+
switch (m) {
|
35
|
+
case 4: result[3] = 0x80 | (c & 0x3f); c = c >> 6; c |= 0x10000;
|
36
|
+
case 3: result[2] = 0x80 | (c & 0x3f); c = c >> 6; c |= 0x800;
|
37
|
+
case 2: result[1] = 0x80 | (c & 0x3f); c = c >> 6; c |= 0xc0;
|
38
|
+
result[0] = c;
|
39
|
+
}
|
40
|
+
}
|
41
|
+
return (int)m;
|
42
|
+
}
|
43
|
+
|
44
|
+
int
|
45
|
+
u_char_to_u(uint32_t c, char *result)
|
46
|
+
{
|
47
|
+
return u_char_to_u_n(c, result, 4);
|
48
|
+
}
|
@@ -0,0 +1,24 @@
|
|
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 "attributes.h"
|
10
|
+
#include "titled.h"
|
11
|
+
|
12
|
+
|
13
|
+
uint32_t
|
14
|
+
u_char_upcase(uint32_t c)
|
15
|
+
{
|
16
|
+
switch (u_char_general_category(c)) {
|
17
|
+
case U_GENERAL_CATEGORY_LETTER_LOWERCASE:
|
18
|
+
return _u_special_case_table_lookup(c);
|
19
|
+
case U_GENERAL_CATEGORY_LETTER_TITLECASE:
|
20
|
+
return _u_titlecase_table_lookup(c, true);
|
21
|
+
default:
|
22
|
+
return c;
|
23
|
+
}
|
24
|
+
}
|
@@ -0,0 +1,28 @@
|
|
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/word-break.h"
|
10
|
+
|
11
|
+
|
12
|
+
enum u_word_break
|
13
|
+
u_char_word_break(uint32_t c)
|
14
|
+
{
|
15
|
+
int16_t index;
|
16
|
+
|
17
|
+
if (c <= UNICODE_LAST_CHAR_PART1)
|
18
|
+
index = word_break_property_table_part1[c >> 8];
|
19
|
+
else if (UNICODE_FIRST_CHAR_PART2 <= c && c <= UNICODE_LAST_CHAR)
|
20
|
+
index = word_break_property_table_part2[(c - UNICODE_FIRST_CHAR_PART2) >> 8];
|
21
|
+
else
|
22
|
+
return U_WORD_BREAK_OTHER;
|
23
|
+
|
24
|
+
if (index >= UNICODE_MAX_TABLE_INDEX)
|
25
|
+
return index - UNICODE_MAX_TABLE_INDEX;
|
26
|
+
|
27
|
+
return word_break_property_data[index][c & 0xff];
|
28
|
+
}
|
@@ -0,0 +1,31 @@
|
|
1
|
+
#include <stddef.h>
|
2
|
+
#include <stdint.h>
|
3
|
+
#include <stdbool.h>
|
4
|
+
|
5
|
+
#include "u.h"
|
6
|
+
#include "private.h"
|
7
|
+
|
8
|
+
|
9
|
+
#define FULLWIDTH_A ((uint32_t)0xff21)
|
10
|
+
#define FULLWIDTH_F ((uint32_t)0xff26)
|
11
|
+
#define FULLWIDTH_a ((uint32_t)0xff41)
|
12
|
+
#define FULLWIDTH_f ((uint32_t)0xff46)
|
13
|
+
|
14
|
+
|
15
|
+
/* {{{1
|
16
|
+
* Return the numeric value of ‘c’ if it's a hexadecimal digit, or -1 if not.
|
17
|
+
*/
|
18
|
+
int
|
19
|
+
u_char_xdigit_value(uint32_t c)
|
20
|
+
{
|
21
|
+
if (c >= 'a' && c <= 'f')
|
22
|
+
return c - 'a' + 10;
|
23
|
+
else if (c >= 'A' && c <= 'F')
|
24
|
+
return c - 'A' + 10;
|
25
|
+
else if (c >= FULLWIDTH_a && c <= FULLWIDTH_f)
|
26
|
+
return c - FULLWIDTH_a + 10;
|
27
|
+
else if (c >= FULLWIDTH_A && c <= FULLWIDTH_F)
|
28
|
+
return c - FULLWIDTH_A + 10;
|
29
|
+
else
|
30
|
+
return u_char_digit_value(c);
|
31
|
+
}
|
data/ext/u/u_collate.c
ADDED
@@ -0,0 +1,83 @@
|
|
1
|
+
#include "extconf.h"
|
2
|
+
#include <assert.h>
|
3
|
+
#include <errno.h>
|
4
|
+
#include <stdbool.h>
|
5
|
+
#include <stdint.h>
|
6
|
+
#include <stdlib.h>
|
7
|
+
#include <string.h>
|
8
|
+
|
9
|
+
#include "u.h"
|
10
|
+
#include "private.h"
|
11
|
+
|
12
|
+
static int
|
13
|
+
compare(const char *a, size_t a_n, const char *b, size_t b_n)
|
14
|
+
{
|
15
|
+
int r = memcmp(a, b, a_n < b_n ? a_n : b_n);
|
16
|
+
if (r == 0) {
|
17
|
+
if (a_n < b_n)
|
18
|
+
return -1;
|
19
|
+
else if (a_n > b_n)
|
20
|
+
return 1;
|
21
|
+
}
|
22
|
+
return r;
|
23
|
+
}
|
24
|
+
|
25
|
+
static size_t
|
26
|
+
ckey(char **result, char *buf, size_t m,
|
27
|
+
const char *string, size_t n,
|
28
|
+
const char *locale)
|
29
|
+
{
|
30
|
+
errno = 0;
|
31
|
+
size_t key_n = u_collation_key(buf, m, string, n, locale);
|
32
|
+
if (errno != 0)
|
33
|
+
return 0;
|
34
|
+
if (key_n < m) {
|
35
|
+
*result = buf;
|
36
|
+
return key_n;
|
37
|
+
}
|
38
|
+
char *key = malloc(key_n + 1);
|
39
|
+
if (key == NULL)
|
40
|
+
return 0;
|
41
|
+
key_n = u_collation_key(key, key_n + 1, string, n, locale);
|
42
|
+
if (errno != 0) {
|
43
|
+
free(key);
|
44
|
+
return 0;
|
45
|
+
}
|
46
|
+
*result = key;
|
47
|
+
return key_n;
|
48
|
+
}
|
49
|
+
|
50
|
+
int
|
51
|
+
u_collate(const char *a, size_t a_n, const char *b, size_t b_n,
|
52
|
+
const char *locale)
|
53
|
+
{
|
54
|
+
char a_buf[2048];
|
55
|
+
char *a_key = NULL;
|
56
|
+
size_t a_key_n = ckey(&a_key, a_buf, sizeof(a_buf), a, a_n, locale);
|
57
|
+
int a_errno = errno;
|
58
|
+
|
59
|
+
char b_buf[2048];
|
60
|
+
char *b_key = NULL;
|
61
|
+
size_t b_key_n = ckey(&b_key, b_buf, sizeof(b_buf), b, b_n, locale);
|
62
|
+
int b_errno = errno;
|
63
|
+
|
64
|
+
int r;
|
65
|
+
if (a_errno != 0) {
|
66
|
+
if (b_errno != 0)
|
67
|
+
r = compare(a, a_n, b, b_n);
|
68
|
+
else
|
69
|
+
r = 1;
|
70
|
+
errno = a_errno;
|
71
|
+
} else if (b_errno != 0) {
|
72
|
+
r = -1;
|
73
|
+
errno = b_errno;
|
74
|
+
} else
|
75
|
+
r = compare(a_key, a_key_n, b_key, b_key_n);
|
76
|
+
|
77
|
+
if (a_key != a_buf)
|
78
|
+
free(a_key);
|
79
|
+
if (b_key != b_buf)
|
80
|
+
free(b_key);
|
81
|
+
|
82
|
+
return r;
|
83
|
+
}
|