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 +1,13 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
|
3
|
+
/* @overload soft_dotted?
|
4
|
+
* @return [Boolean] True if this {U::String} only contains soft-dotted
|
5
|
+
* characters
|
6
|
+
* @note Soft-dotted characters have the soft-dotted property and thus lose
|
7
|
+
* their dot if an accent is applied to them, for example, ‘i’ and ‘j’.
|
8
|
+
* @see http://unicode.org/review/pr-11.html Unicode Public Review Issue #11 */
|
9
|
+
VALUE
|
10
|
+
rb_u_string_soft_dotted(VALUE self)
|
11
|
+
{
|
12
|
+
return _rb_u_character_test(self, u_char_issoftdotted);
|
13
|
+
}
|
@@ -0,0 +1,24 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
|
3
|
+
/* @overload space?
|
4
|
+
*
|
5
|
+
* Returns true if the receiver contains only “space” characters. Space
|
6
|
+
* characters are those in the general category Separator:
|
7
|
+
*
|
8
|
+
* * Separator, space (Zs)
|
9
|
+
* * Separator, line (Zl)
|
10
|
+
* * Separator, paragraph (Zp)
|
11
|
+
*
|
12
|
+
* such as ‘ ’, or a control character acting as such, namely
|
13
|
+
*
|
14
|
+
* * U+0009 CHARACTER TABULATION (HT)
|
15
|
+
* * U+000A LINE FEED (LF)
|
16
|
+
* * U+000C FORM FEED (FF)
|
17
|
+
* * U+000D CARRIAGE RETURN (CR)
|
18
|
+
*
|
19
|
+
* @return [Boolean] */
|
20
|
+
VALUE
|
21
|
+
rb_u_string_space(VALUE self)
|
22
|
+
{
|
23
|
+
return _rb_u_character_test(self, u_char_isspace);
|
24
|
+
}
|
@@ -0,0 +1,245 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
#include "rb_u_re.h"
|
3
|
+
|
4
|
+
static VALUE
|
5
|
+
rb_u_string_split_trim(VALUE result, bool limit_given, int limit)
|
6
|
+
{
|
7
|
+
if (limit_given || limit != 0)
|
8
|
+
return result;
|
9
|
+
|
10
|
+
long length;
|
11
|
+
while ((length = RARRAY_LEN(result)) > 0 &&
|
12
|
+
USTRING_LENGTH(RVAL2USTRING(RARRAY_PTR(result)[length - 1])) == 0)
|
13
|
+
rb_ary_pop(result);
|
14
|
+
|
15
|
+
return result;
|
16
|
+
}
|
17
|
+
|
18
|
+
static VALUE
|
19
|
+
rb_u_string_split_rest(VALUE self, long offset, bool limit_given, int limit, VALUE result)
|
20
|
+
{
|
21
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
22
|
+
long length = USTRING_LENGTH(string);
|
23
|
+
|
24
|
+
if (length > 0 && (limit_given || length > offset || limit < 0))
|
25
|
+
rb_ary_push(result,
|
26
|
+
length == offset ?
|
27
|
+
rb_u_string_new_empty(self) :
|
28
|
+
rb_u_string_new_subsequence(self,
|
29
|
+
offset,
|
30
|
+
length - offset));
|
31
|
+
|
32
|
+
return rb_u_string_split_trim(result, limit_given, limit);
|
33
|
+
}
|
34
|
+
|
35
|
+
static VALUE
|
36
|
+
rb_u_string_split_awk(VALUE self, bool limit_given, int limit)
|
37
|
+
{
|
38
|
+
VALUE result = rb_ary_new();
|
39
|
+
|
40
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
41
|
+
const char *begin = USTRING_STR(string);
|
42
|
+
const char *p = begin;
|
43
|
+
const char *end = USTRING_END(string);
|
44
|
+
int i = 1;
|
45
|
+
while (p < end) {
|
46
|
+
const char *q;
|
47
|
+
while (p < end && u_char_isspace(u_decode(&q, p, end)))
|
48
|
+
p = q;
|
49
|
+
|
50
|
+
if (p == end || (limit_given && i >= limit))
|
51
|
+
break;
|
52
|
+
i++;
|
53
|
+
|
54
|
+
q = p;
|
55
|
+
const char *r;
|
56
|
+
while (q < end && !u_char_isspace(u_decode(&r, q, end)))
|
57
|
+
q = r;
|
58
|
+
|
59
|
+
rb_ary_push(result,
|
60
|
+
rb_u_string_new_subsequence(self,
|
61
|
+
p - begin,
|
62
|
+
q - p));
|
63
|
+
p = q;
|
64
|
+
}
|
65
|
+
|
66
|
+
return rb_u_string_split_rest(self, p - begin, limit_given, limit, result);
|
67
|
+
}
|
68
|
+
|
69
|
+
static VALUE
|
70
|
+
rb_u_string_split_string(VALUE self, VALUE rbseparator, bool limit_given, int limit)
|
71
|
+
{
|
72
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
73
|
+
const struct rb_u_string *separator = RVAL2USTRING_ANY(rbseparator);
|
74
|
+
|
75
|
+
const char *begin = USTRING_STR(string);
|
76
|
+
const char *p = begin;
|
77
|
+
const char *end = USTRING_END(string);
|
78
|
+
|
79
|
+
const char *s_p = USTRING_STR(separator);
|
80
|
+
long s_len = USTRING_LENGTH(separator);
|
81
|
+
|
82
|
+
rb_u_validate(p, USTRING_LENGTH(string));
|
83
|
+
rb_u_validate(s_p, s_len);
|
84
|
+
|
85
|
+
VALUE result = rb_ary_new();
|
86
|
+
|
87
|
+
/* TODO: Better variable name. */
|
88
|
+
long offset;
|
89
|
+
for (int i = 1; (!limit_given || i < limit) && p < end; i++) {
|
90
|
+
if ((offset = rb_u_memsearch(s_p, s_len, p, end - p)) < 0)
|
91
|
+
break;
|
92
|
+
rb_ary_push(result, rb_u_string_new_subsequence(self, p - begin, offset));
|
93
|
+
p += offset + s_len;
|
94
|
+
}
|
95
|
+
|
96
|
+
return rb_u_string_split_rest(self, p - begin, limit_given, limit, result);
|
97
|
+
}
|
98
|
+
|
99
|
+
static void
|
100
|
+
rb_u_string_split_pattern_push_registers(VALUE self,
|
101
|
+
struct re_registers *registers,
|
102
|
+
VALUE result)
|
103
|
+
{
|
104
|
+
for (int i = 1; i < registers->num_regs; i++) {
|
105
|
+
if (registers->beg[i] == -1)
|
106
|
+
continue;
|
107
|
+
rb_ary_push(result,
|
108
|
+
registers->beg[i] == registers->end[i] ?
|
109
|
+
rb_u_string_new_empty(self) :
|
110
|
+
rb_u_string_new_subsequence(self,
|
111
|
+
registers->beg[i],
|
112
|
+
registers->end[i] - registers->beg[i]));
|
113
|
+
}
|
114
|
+
}
|
115
|
+
|
116
|
+
static VALUE
|
117
|
+
rb_u_string_split_pattern(VALUE self, VALUE pattern, bool limit_given, int limit)
|
118
|
+
{
|
119
|
+
VALUE str = rb_str_to_str(self);
|
120
|
+
|
121
|
+
const char *begin = RSTRING_PTR(str);
|
122
|
+
const char *p = begin;
|
123
|
+
const char *end = RSTRING_END(str);
|
124
|
+
|
125
|
+
VALUE result = rb_ary_new();
|
126
|
+
|
127
|
+
bool last_was_empty = false;
|
128
|
+
|
129
|
+
long start = 0;
|
130
|
+
/* TODO: Better variable name. */
|
131
|
+
long offset;
|
132
|
+
int i = 1;
|
133
|
+
while ((offset = rb_reg_search(pattern, str, start, 0)) >= 0) {
|
134
|
+
struct re_registers *registers = RMATCH_REGS(rb_backref_get());
|
135
|
+
if (start == offset && registers->beg[0] == registers->end[0]) {
|
136
|
+
if (begin == NULL) {
|
137
|
+
rb_ary_push(result, rb_u_string_new_empty(self));
|
138
|
+
break;
|
139
|
+
} else if (last_was_empty) {
|
140
|
+
const char *q;
|
141
|
+
u_decode(&q, p, end);
|
142
|
+
rb_ary_push(result,
|
143
|
+
rb_u_string_new_subsequence(self,
|
144
|
+
p - begin,
|
145
|
+
q - p));
|
146
|
+
} else {
|
147
|
+
if (begin + start == end)
|
148
|
+
start++;
|
149
|
+
else {
|
150
|
+
const char *q;
|
151
|
+
u_decode(&q, p, end);
|
152
|
+
start += q - p;
|
153
|
+
}
|
154
|
+
last_was_empty = true;
|
155
|
+
continue;
|
156
|
+
}
|
157
|
+
} else {
|
158
|
+
rb_ary_push(result,
|
159
|
+
rb_u_string_new_subsequence(self,
|
160
|
+
p - begin,
|
161
|
+
offset - (p - begin)));
|
162
|
+
start = registers->end[0];
|
163
|
+
}
|
164
|
+
last_was_empty = false;
|
165
|
+
p = begin + start;
|
166
|
+
|
167
|
+
rb_u_string_split_pattern_push_registers(self, registers, result);
|
168
|
+
|
169
|
+
i++;
|
170
|
+
if (limit_given && i == limit)
|
171
|
+
break;
|
172
|
+
}
|
173
|
+
|
174
|
+
return rb_u_string_split_rest(self, p - begin, limit_given, limit, result);
|
175
|
+
}
|
176
|
+
|
177
|
+
/* @overload split(pattern = $;, limit = 0)
|
178
|
+
*
|
179
|
+
* Returns the receiver split into LIMIT substrings separated by PATTERN,
|
180
|
+
* each inheriting any taint and untrust.
|
181
|
+
*
|
182
|
+
* If PATTERN = `$;` = nil or PATTERN = `' '`, splits according to AWK rules,
|
183
|
+
* that is, any {#space?} prefix is skipped, then substrings are separated by
|
184
|
+
* non-empty {#space?} substrings.
|
185
|
+
*
|
186
|
+
* If LIMIT < 0, then no limit is imposed and trailing {#empty?} substrings
|
187
|
+
* aren’t removed.
|
188
|
+
*
|
189
|
+
* If LIMIT = 0, then no limit is imposed and trailing {#empty?} substrings
|
190
|
+
* are removed.
|
191
|
+
*
|
192
|
+
* If LIMIT = 1, then, if {#length} = 0, the result will be empty, otherwise
|
193
|
+
* it will consist of the receiver only.
|
194
|
+
*
|
195
|
+
* If LIMIT > 1, then the receiver is split into at most LIMIT substrings.
|
196
|
+
*
|
197
|
+
* @param [Regexp, #to_str] pattern
|
198
|
+
* @param [#to_int] limit
|
199
|
+
* @return [Array<U::String>] */
|
200
|
+
VALUE
|
201
|
+
rb_u_string_split_m(int argc, VALUE *argv, VALUE self)
|
202
|
+
{
|
203
|
+
VALUE rbpattern, rblimit;
|
204
|
+
int limit = 0;
|
205
|
+
bool limit_given;
|
206
|
+
|
207
|
+
if (rb_scan_args(argc, argv, "02", &rbpattern, &rblimit) == 2)
|
208
|
+
limit = NUM2INT(rblimit);
|
209
|
+
|
210
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
211
|
+
|
212
|
+
if (limit == 1) {
|
213
|
+
if (USTRING_LENGTH(string) == 0)
|
214
|
+
return rb_ary_new2(0);
|
215
|
+
|
216
|
+
return rb_ary_new3(1, self);
|
217
|
+
}
|
218
|
+
|
219
|
+
limit_given = !NIL_P(rblimit) && limit >= 0;
|
220
|
+
|
221
|
+
if (NIL_P(rbpattern) && NIL_P(rb_fs))
|
222
|
+
return rb_u_string_split_awk(self, limit_given, limit);
|
223
|
+
else if (NIL_P(rbpattern))
|
224
|
+
rbpattern = rb_fs;
|
225
|
+
|
226
|
+
if (TYPE(rbpattern) != T_STRING && !RTEST(rb_obj_is_kind_of(rbpattern, rb_cUString)))
|
227
|
+
return rb_u_string_split_pattern(self,
|
228
|
+
rb_u_pattern_argument(rbpattern, true),
|
229
|
+
limit_given,
|
230
|
+
limit);
|
231
|
+
|
232
|
+
const struct rb_u_string *pattern = RVAL2USTRING_ANY(rbpattern);
|
233
|
+
const char *p = USTRING_STR(pattern);
|
234
|
+
long length = USTRING_LENGTH(pattern);
|
235
|
+
|
236
|
+
if (length == 0)
|
237
|
+
return rb_u_string_split_pattern(self,
|
238
|
+
rb_reg_regcomp(rb_str_to_str(rbpattern)),
|
239
|
+
limit_given,
|
240
|
+
limit);
|
241
|
+
else if (length == 1 && *p == ' ')
|
242
|
+
return rb_u_string_split_awk(self, limit_given, limit);
|
243
|
+
else
|
244
|
+
return rb_u_string_split_string(self, rbpattern, limit_given, limit);
|
245
|
+
}
|
@@ -0,0 +1,75 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
#include "rb_u_string_internal_tr.h"
|
3
|
+
|
4
|
+
static long
|
5
|
+
rb_u_string_squeeze_loop(const struct rb_u_string *string, struct tr_table *table,
|
6
|
+
char *result)
|
7
|
+
{
|
8
|
+
long count = 0;
|
9
|
+
|
10
|
+
const char *p = USTRING_STR(string);
|
11
|
+
const char *end = USTRING_END(string);
|
12
|
+
|
13
|
+
uint32_t previous = U_N_CODEPOINTS;
|
14
|
+
char *base = result;
|
15
|
+
while (p < end) {
|
16
|
+
const char *q;
|
17
|
+
uint32_t c = u_decode(&q, p, end);
|
18
|
+
if (c != previous ||
|
19
|
+
(table != NULL && !tr_table_lookup(table, c))) {
|
20
|
+
long run = q - p;
|
21
|
+
if (base != NULL) {
|
22
|
+
memcpy(base, p, run);
|
23
|
+
base += run;
|
24
|
+
}
|
25
|
+
count += run;
|
26
|
+
previous = c;
|
27
|
+
}
|
28
|
+
p = q;
|
29
|
+
}
|
30
|
+
|
31
|
+
return count;
|
32
|
+
}
|
33
|
+
|
34
|
+
/* @overload squeeze(*sets)
|
35
|
+
*
|
36
|
+
* Returns the receiver, replacing any substrings of {#length} > 1 consisting
|
37
|
+
* of the same character _c_ with _c_, where _c_ is a member of the
|
38
|
+
* intersection of the character sets in SETS, inheriting any taint and
|
39
|
+
* untrust.
|
40
|
+
*
|
41
|
+
* If SETS is empty, then the set of all Unicode characters is used.
|
42
|
+
*
|
43
|
+
* The complement of all Unicode characters and a given set of characters may
|
44
|
+
* be specified by prefixing a non-empty set with ‘`^`’ (U+005E CIRCUMFLEX
|
45
|
+
* ACCENT).
|
46
|
+
*
|
47
|
+
* Any sequence of characters _a_-_b_ inside a set will expand to also
|
48
|
+
* include all characters whose code points lay between those of _a_ and _b_.
|
49
|
+
*
|
50
|
+
* @param [Array<U::String, #to_str>] sets
|
51
|
+
* @return [U::String] */
|
52
|
+
VALUE
|
53
|
+
rb_u_string_squeeze(int argc, VALUE *argv, VALUE self)
|
54
|
+
{
|
55
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
56
|
+
|
57
|
+
if (USTRING_LENGTH(string) == 0)
|
58
|
+
return Qnil;
|
59
|
+
|
60
|
+
struct tr_table table;
|
61
|
+
if (argc > 0)
|
62
|
+
tr_table_initialize_from_strings(&table, argc, argv);
|
63
|
+
|
64
|
+
struct tr_table *table_pointer = (argc > 0) ? &table : NULL;
|
65
|
+
|
66
|
+
long count = rb_u_string_squeeze_loop(string, table_pointer, NULL);
|
67
|
+
if (count == 0)
|
68
|
+
return self;
|
69
|
+
|
70
|
+
char *remaining = ALLOC_N(char, count + 1);
|
71
|
+
rb_u_string_squeeze_loop(string, table_pointer, remaining);
|
72
|
+
remaining[count] = '\0';
|
73
|
+
|
74
|
+
return rb_u_string_new_c_own(self, remaining, count);
|
75
|
+
}
|
@@ -0,0 +1,31 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
|
3
|
+
/* @overload start_with?(*prefixes)
|
4
|
+
* @param [Array] prefixes
|
5
|
+
* @return [Boolean] True if any element of PREFIXES that responds to #to_str
|
6
|
+
* is a byte-level prefix of the receiver */
|
7
|
+
VALUE
|
8
|
+
rb_u_string_start_with(int argc, VALUE *argv, VALUE self)
|
9
|
+
{
|
10
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
11
|
+
const char *p = USTRING_STR(string);
|
12
|
+
long p_length = USTRING_LENGTH(string);
|
13
|
+
|
14
|
+
for (int i = 0; i < argc; i++) {
|
15
|
+
VALUE tmp = rb_u_string_check_type(argv[i]);
|
16
|
+
if (NIL_P(tmp))
|
17
|
+
continue;
|
18
|
+
|
19
|
+
const struct rb_u_string *other = RVAL2USTRING_ANY(tmp);
|
20
|
+
const char *q = USTRING_STR(other);
|
21
|
+
long q_length = USTRING_LENGTH(other);
|
22
|
+
|
23
|
+
if (p_length < q_length)
|
24
|
+
continue;
|
25
|
+
|
26
|
+
if (memcmp(p, q, q_length) == 0)
|
27
|
+
return Qtrue;
|
28
|
+
}
|
29
|
+
|
30
|
+
return Qfalse;
|
31
|
+
}
|
@@ -0,0 +1,36 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
|
3
|
+
/* @return [U::String] The receiver with its maximum {#space?} prefix and
|
4
|
+
* suffix removed, inheriting any taint and untrust
|
5
|
+
* @see #lstrip
|
6
|
+
* @see #rstrip */
|
7
|
+
VALUE
|
8
|
+
rb_u_string_strip(VALUE self)
|
9
|
+
{
|
10
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
11
|
+
|
12
|
+
const char *begin = USTRING_STR(string);
|
13
|
+
if (begin == NULL)
|
14
|
+
return self;
|
15
|
+
|
16
|
+
const char *end = USTRING_END(string);
|
17
|
+
const char *s = begin;
|
18
|
+
uint32_t c;
|
19
|
+
const char *t;
|
20
|
+
while (s < end && u_char_isspace(u_decode(&t, s, end)))
|
21
|
+
s = t;
|
22
|
+
|
23
|
+
t = end;
|
24
|
+
while (begin < t) {
|
25
|
+
const char *p;
|
26
|
+
c = u_decode_r(&p, begin, t);
|
27
|
+
if (c != '\0' && !u_char_isspace(c))
|
28
|
+
break;
|
29
|
+
t = p;
|
30
|
+
}
|
31
|
+
|
32
|
+
if (s == begin && t == end)
|
33
|
+
return self;
|
34
|
+
|
35
|
+
return rb_u_string_new_c(self, s, t - s);
|
36
|
+
}
|
@@ -0,0 +1,147 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
#include "rb_u_re.h"
|
3
|
+
|
4
|
+
/* @overload sub(pattern, replacement)
|
5
|
+
*
|
6
|
+
* Returns the receiver with the first match of PATTERN replaced by
|
7
|
+
* REPLACEMENT, inheriting any taint and untrust from the receiver and from
|
8
|
+
* REPLACEMENT, or nil if there’s no match.
|
9
|
+
*
|
10
|
+
* The REPLACEMENT is used as a specification for what to replace matches
|
11
|
+
* with:
|
12
|
+
*
|
13
|
+
* <table>
|
14
|
+
* <thead>
|
15
|
+
* <tr><th>Specification</th><th>Replacement</th></tr>
|
16
|
+
* </thead>
|
17
|
+
* <tbody>
|
18
|
+
* <tr>
|
19
|
+
* <td><code>\1</code>, <code>\2</code>, …, <code>\</code><em>n</em></td>
|
20
|
+
* <td>Numbered sub-match <em>n</em></td>
|
21
|
+
* </tr>
|
22
|
+
* <tr>
|
23
|
+
* <td><code>\k<</code><em>name</em><code>></code></td>
|
24
|
+
* <td>Named sub-match <em>name</em></td>
|
25
|
+
* </tr>
|
26
|
+
* </tbody>
|
27
|
+
* </table>
|
28
|
+
*
|
29
|
+
* The Regexp special variables `$&`, `$'`, <code>$\`</code>, `$1`, `$2`, …,
|
30
|
+
* `$`_n_ are updated accordingly.
|
31
|
+
*
|
32
|
+
* @param [Regexp, #to_str] pattern
|
33
|
+
* @param [#to_str] replacement
|
34
|
+
* @return [U::String, nil]
|
35
|
+
*
|
36
|
+
* @overload sub(pattern, replacements)
|
37
|
+
*
|
38
|
+
* Returns the receiver with the first match of PATTERN replaced by
|
39
|
+
* REPLACEMENTS#[_match_], where _match_ is the matched substring, inheriting
|
40
|
+
* any taint and untrust from the receiver, REPLACEMENTS, and
|
41
|
+
* REPLACEMENTS#[_match_], or nil if there’s no match.
|
42
|
+
*
|
43
|
+
* The Regexp special variables `$&`, `$'`, <code>$\`</code>, `$1`, `$2`, …,
|
44
|
+
* `$`_n_ are updated accordingly.
|
45
|
+
*
|
46
|
+
* @param [Regexp, #to_str] pattern
|
47
|
+
* @param [#to_hash] replacements
|
48
|
+
* @raise [Exception] Any error raised by REPLACEMENTS#default, if it gets
|
49
|
+
* called
|
50
|
+
* @return [U::String, nil]
|
51
|
+
*
|
52
|
+
* @overload sub(pattern){ |match| … }
|
53
|
+
*
|
54
|
+
* Returns the receiver with all instances of PATTERN replaced by the results
|
55
|
+
* of the given block, inheriting any taint and untrust from the receiver and
|
56
|
+
* from the results of the given block, or nil if there’s no match.
|
57
|
+
*
|
58
|
+
* The Regexp special variables `$&`, `$'`, <code>$\`</code>, `$1`, `$2`, …,
|
59
|
+
* `$`_n_ are updated accordingly.
|
60
|
+
*
|
61
|
+
* @param [Regexp, #to_str] pattern
|
62
|
+
* @yieldparam [U::String] match
|
63
|
+
* @yieldreturn [#to_str]
|
64
|
+
* @return [U::String, nil] */
|
65
|
+
VALUE
|
66
|
+
rb_u_string_sub(int argc, VALUE *argv, VALUE self)
|
67
|
+
{
|
68
|
+
VALUE pattern, replacement;
|
69
|
+
VALUE replacements = Qnil;
|
70
|
+
bool use_block = false;
|
71
|
+
bool tainted = false;
|
72
|
+
bool untrusted = false;
|
73
|
+
|
74
|
+
if (argc == 1)
|
75
|
+
use_block = true;
|
76
|
+
|
77
|
+
if (rb_scan_args(argc, argv, "11", &pattern, &replacement) == 2) {
|
78
|
+
replacements = rb_check_convert_type(replacement, T_HASH,
|
79
|
+
"Hash", "to_hash");
|
80
|
+
if (NIL_P(replacements))
|
81
|
+
StringValue(replacement);
|
82
|
+
if (OBJ_TAINTED(replacement))
|
83
|
+
tainted = true;
|
84
|
+
if (OBJ_UNTRUSTED(replacement))
|
85
|
+
untrusted = true;
|
86
|
+
}
|
87
|
+
|
88
|
+
pattern = rb_u_pattern_argument(pattern, true);
|
89
|
+
|
90
|
+
VALUE str = rb_str_to_str(self);
|
91
|
+
long begin = rb_reg_search(pattern, str, 0, 0);
|
92
|
+
if (begin < 0)
|
93
|
+
return Qnil;
|
94
|
+
|
95
|
+
VALUE match = rb_backref_get();
|
96
|
+
struct re_registers *registers = RMATCH_REGS(match);
|
97
|
+
VALUE result;
|
98
|
+
if (use_block || !NIL_P(replacements)) {
|
99
|
+
if (use_block) {
|
100
|
+
VALUE ustr = rb_u_string_new_rb(rb_reg_nth_match(0, match));
|
101
|
+
result = rb_u_string_object_as_string(rb_yield(ustr));
|
102
|
+
} else {
|
103
|
+
VALUE ustr = rb_u_string_new_c(self,
|
104
|
+
RSTRING_PTR(str) + registers->beg[0],
|
105
|
+
registers->end[0] - registers->beg[0]);
|
106
|
+
result = rb_u_string_object_as_string(rb_hash_aref(replacements, ustr));
|
107
|
+
}
|
108
|
+
} else
|
109
|
+
result =
|
110
|
+
#ifdef HAVE_RB_REG_REGSUB4
|
111
|
+
rb_reg_regsub(replacement, str, registers, pattern);
|
112
|
+
#else
|
113
|
+
rb_reg_regsub(replacement, str, registers);
|
114
|
+
#endif
|
115
|
+
|
116
|
+
if (OBJ_TAINTED(result))
|
117
|
+
tainted = true;
|
118
|
+
if (OBJ_UNTRUSTED(result))
|
119
|
+
untrusted = true;
|
120
|
+
|
121
|
+
const struct rb_u_string *value = RVAL2USTRING_ANY(result);
|
122
|
+
|
123
|
+
size_t length = registers->beg[0] +
|
124
|
+
USTRING_LENGTH(value) +
|
125
|
+
(RSTRING_LEN(str) - registers->end[0]);
|
126
|
+
char *base = ALLOC_N(char, length + 1);
|
127
|
+
MEMCPY(base,
|
128
|
+
RSTRING_PTR(str),
|
129
|
+
char,
|
130
|
+
registers->beg[0]);
|
131
|
+
MEMCPY(base + registers->beg[0],
|
132
|
+
USTRING_STR(value),
|
133
|
+
char,
|
134
|
+
USTRING_LENGTH(value));
|
135
|
+
MEMCPY(base + registers->beg[0] + USTRING_LENGTH(value),
|
136
|
+
RSTRING_PTR(str) + registers->end[0],
|
137
|
+
char,
|
138
|
+
RSTRING_LEN(str) - registers->end[0]);
|
139
|
+
base[length] = '\0';
|
140
|
+
|
141
|
+
VALUE substituted = rb_u_string_new_c_own(self, base, length);
|
142
|
+
if (tainted)
|
143
|
+
OBJ_TAINT(substituted);
|
144
|
+
if (untrusted)
|
145
|
+
OBJ_UNTRUST(substituted);
|
146
|
+
return substituted;
|
147
|
+
}
|