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
data/ext/u/rb_u_string.h
ADDED
@@ -0,0 +1,173 @@
|
|
1
|
+
/* TODO: Move this to rb_u_string.c and turn USTRING_STR() into
|
2
|
+
* rb_u_string_c_str() and USTRING_LENGTH() into rb_u_string_c_length() */
|
3
|
+
struct rb_u_string {
|
4
|
+
VALUE rb;
|
5
|
+
const char *c;
|
6
|
+
long length;
|
7
|
+
};
|
8
|
+
|
9
|
+
|
10
|
+
#define RVAL2USTRING(object) \
|
11
|
+
(Check_Type(object, T_DATA), (struct rb_u_string *)DATA_PTR(object))
|
12
|
+
|
13
|
+
#define RVAL2USTRING_ANY(value) \
|
14
|
+
(rb_obj_is_kind_of((value), rb_cUString) ? \
|
15
|
+
RVAL2USTRING(value) : \
|
16
|
+
USTRING_LOCAL(StringValue(value), NULL, 0))
|
17
|
+
|
18
|
+
#define USTRING2RVAL(string) \
|
19
|
+
Data_Wrap_Struct(rb_cUString, rb_u_string_mark, rb_u_string_free, string)
|
20
|
+
|
21
|
+
#define USTRING_LOCAL(arb, ac, alength) \
|
22
|
+
(&(struct rb_u_string){ .rb = (arb), .c = (ac), .length = (alength) })
|
23
|
+
|
24
|
+
/* TODO: Call this USTRING_BEGIN() instead */
|
25
|
+
#define USTRING_STR(string) \
|
26
|
+
(NIL_P((string)->rb) ? (string)->c : RSTRING_PTR(string->rb))
|
27
|
+
|
28
|
+
#define USTRING_LENGTH(string) \
|
29
|
+
(NIL_P((string)->rb) ? (string)->length : RSTRING_LEN(string->rb))
|
30
|
+
|
31
|
+
#define USTRING_END(string) \
|
32
|
+
(NIL_P((string)->rb) ? (string)->c + (string)->length : RSTRING_END(string->rb))
|
33
|
+
|
34
|
+
static inline const char *
|
35
|
+
rb_u_string_begin_from_offset(const struct rb_u_string *string, long offset)
|
36
|
+
{
|
37
|
+
return u_offset_to_pointer_n(offset >= 0 ?
|
38
|
+
USTRING_STR(string) :
|
39
|
+
USTRING_END(string),
|
40
|
+
offset,
|
41
|
+
USTRING_LENGTH(string));
|
42
|
+
}
|
43
|
+
|
44
|
+
|
45
|
+
extern VALUE rb_cUString;
|
46
|
+
|
47
|
+
|
48
|
+
VALUE rb_u_string_new_uninfected(const char *str, long length);
|
49
|
+
VALUE rb_u_string_new_uninfected_own(const char *str, long length);
|
50
|
+
VALUE rb_u_string_new_c(VALUE self, const char *str, long length);
|
51
|
+
VALUE rb_u_string_new_c_own(VALUE self, const char *str, long length);
|
52
|
+
VALUE rb_u_string_new_rb(VALUE str);
|
53
|
+
VALUE rb_u_string_new_subsequence(VALUE self, long begin, long length);
|
54
|
+
VALUE rb_u_string_new_empty(VALUE self);
|
55
|
+
|
56
|
+
VALUE rb_u_string_check_type(VALUE str);
|
57
|
+
VALUE rb_u_string_validate_type(VALUE str);
|
58
|
+
VALUE rb_u_string_object_as_string(VALUE object);
|
59
|
+
|
60
|
+
const char *rb_u_string_begin_from_offset(const struct rb_u_string *string, long offset);
|
61
|
+
|
62
|
+
/* TODO: Move to rb_private.h. */
|
63
|
+
long rb_u_string_index(VALUE self, VALUE sub, long offset);
|
64
|
+
long rb_u_string_rindex(VALUE self, VALUE rbsubstring, long offset);
|
65
|
+
|
66
|
+
VALUE rb_u_string_alnum(VALUE self);
|
67
|
+
VALUE rb_u_string_alpha(VALUE self);
|
68
|
+
VALUE rb_u_string_assigned(VALUE self);
|
69
|
+
VALUE rb_u_string_aref_m(int argc, VALUE *argv, VALUE self);
|
70
|
+
VALUE rb_u_string_ascii_only(VALUE self);
|
71
|
+
VALUE rb_u_string_b(VALUE self);
|
72
|
+
VALUE rb_u_string_bytes(VALUE self);
|
73
|
+
VALUE rb_u_string_bytesize(VALUE self);
|
74
|
+
VALUE rb_u_string_byteslice_m(int argc, VALUE *argv, VALUE self);
|
75
|
+
VALUE rb_u_string_center(int argc, VALUE *argv, VALUE self);
|
76
|
+
VALUE rb_u_string_casecmp(int argc, VALUE *argv, VALUE self);
|
77
|
+
VALUE rb_u_string_cased(VALUE self);
|
78
|
+
VALUE rb_u_string_case_ignorable(VALUE self);
|
79
|
+
VALUE rb_u_string_chars(VALUE self);
|
80
|
+
VALUE rb_u_string_chomp(int argc, VALUE *argv, VALUE self);
|
81
|
+
VALUE rb_u_string_chop(VALUE self);
|
82
|
+
VALUE rb_u_string_chr(VALUE self);
|
83
|
+
VALUE rb_u_string_cntrl(VALUE self);
|
84
|
+
VALUE rb_u_string_codepoints(VALUE self);
|
85
|
+
VALUE rb_u_string_collate(int argc, VALUE *argv, VALUE self);
|
86
|
+
VALUE rb_u_string_collation_key(int argc, VALUE *argv, VALUE self);
|
87
|
+
VALUE rb_u_string_canonical_combining_class(VALUE self);
|
88
|
+
VALUE rb_u_string_count(int argc, VALUE *argv, VALUE self);
|
89
|
+
VALUE rb_u_string_defined(VALUE self);
|
90
|
+
VALUE rb_u_string_delete(int argc, VALUE *argv, VALUE self);
|
91
|
+
VALUE rb_u_string_digit(VALUE self);
|
92
|
+
VALUE rb_u_string_downcase(int argc, VALUE *argv, VALUE self);
|
93
|
+
VALUE rb_u_string_dump(VALUE self);
|
94
|
+
VALUE rb_u_string_dup(VALUE self);
|
95
|
+
VALUE rb_u_string_each_byte(VALUE self);
|
96
|
+
VALUE rb_u_string_each_char(VALUE self);
|
97
|
+
VALUE rb_u_string_each_codepoint(VALUE self);
|
98
|
+
VALUE rb_u_string_each_grapheme_cluster(VALUE self);
|
99
|
+
VALUE rb_u_string_each_line(int argc, VALUE *argv, VALUE self);
|
100
|
+
VALUE rb_u_string_each_word(VALUE self);
|
101
|
+
VALUE rb_u_string_empty(VALUE self);
|
102
|
+
VALUE rb_u_string_end_with(int argc, VALUE *argv, VALUE self);
|
103
|
+
VALUE rb_u_string_equal(VALUE self, VALUE other);
|
104
|
+
VALUE rb_u_string_eql(VALUE self, VALUE other);
|
105
|
+
VALUE rb_u_string_foldcase(int argc, VALUE *argv, VALUE self);
|
106
|
+
VALUE rb_u_string_folded(int argc, VALUE *argv, VALUE self);
|
107
|
+
VALUE rb_u_string_format(int argc, const VALUE *argv, VALUE self);
|
108
|
+
VALUE rb_u_string_format_m(VALUE self, VALUE argument);
|
109
|
+
VALUE rb_u_string_general_category(VALUE self);
|
110
|
+
VALUE rb_u_string_getbyte(VALUE self, VALUE rbindex);
|
111
|
+
VALUE rb_u_string_graph(VALUE self);
|
112
|
+
VALUE rb_u_string_grapheme_break(VALUE self);
|
113
|
+
VALUE rb_u_string_gsub(int argc, VALUE *argv, VALUE self);
|
114
|
+
VALUE rb_u_string_hash(VALUE self);
|
115
|
+
VALUE rb_u_string_hex(VALUE self);
|
116
|
+
VALUE rb_u_string_index_m(int argc, VALUE *argv, VALUE self);
|
117
|
+
VALUE rb_u_string_include(VALUE self, VALUE other);
|
118
|
+
VALUE rb_u_string_inspect(VALUE self);
|
119
|
+
VALUE rb_u_string_length(VALUE self);
|
120
|
+
VALUE rb_u_string_line_break(VALUE self);
|
121
|
+
VALUE rb_u_string_lines(int argc, VALUE *argv, VALUE self);
|
122
|
+
VALUE rb_u_string_ljust(int argc, VALUE *argv, VALUE self);
|
123
|
+
VALUE rb_u_string_lower(int argc, VALUE *argv, VALUE self);
|
124
|
+
VALUE rb_u_string_lstrip(VALUE self);
|
125
|
+
VALUE rb_u_string_match(VALUE self, VALUE other);
|
126
|
+
VALUE rb_u_string_match_m(int argc, VALUE *argv, VALUE self);
|
127
|
+
VALUE rb_u_string_mirror(VALUE self);
|
128
|
+
VALUE rb_u_string_normalize(int argc, VALUE *argv, VALUE self);
|
129
|
+
VALUE rb_u_string_normalized(int argc, VALUE *argv, VALUE self);
|
130
|
+
VALUE rb_u_string_newline(VALUE self);
|
131
|
+
VALUE rb_u_string_oct(VALUE self);
|
132
|
+
VALUE rb_u_string_ord(VALUE self);
|
133
|
+
VALUE rb_u_string_partition(VALUE self, VALUE separator);
|
134
|
+
VALUE rb_u_string_plus(VALUE self, VALUE rbother);
|
135
|
+
VALUE rb_u_string_print(VALUE self);
|
136
|
+
VALUE rb_u_string_punct(VALUE self);
|
137
|
+
VALUE rb_u_string_reverse(VALUE self);
|
138
|
+
VALUE rb_u_string_rindex_m(int argc, VALUE *argv, VALUE self);
|
139
|
+
VALUE rb_u_string_rjust(int argc, VALUE *argv, VALUE self);
|
140
|
+
VALUE rb_u_string_rpartition(VALUE self, VALUE separator);
|
141
|
+
VALUE rb_u_string_rstrip(VALUE self);
|
142
|
+
VALUE rb_u_string_scan(VALUE self, VALUE pattern);
|
143
|
+
VALUE rb_u_string_script(VALUE self);
|
144
|
+
VALUE rb_u_string_soft_dotted(VALUE self);
|
145
|
+
VALUE rb_u_string_space(VALUE self);
|
146
|
+
VALUE rb_u_string_split(VALUE self, const char *separator, long length);
|
147
|
+
VALUE rb_u_string_split_m(int argc, VALUE *argv, VALUE self);
|
148
|
+
VALUE rb_u_string_squeeze(int argc, VALUE *argv, VALUE self);
|
149
|
+
VALUE rb_u_string_start_with(int argc, VALUE *argv, VALUE self);
|
150
|
+
VALUE rb_u_string_strip(VALUE self);
|
151
|
+
VALUE rb_u_string_sub(int argc, VALUE *argv, VALUE self);
|
152
|
+
VALUE rb_u_string_substr(VALUE self, long offset, long len);
|
153
|
+
VALUE rb_u_string_times(VALUE self, VALUE rbtimes);
|
154
|
+
VALUE rb_u_string_title(VALUE self);
|
155
|
+
VALUE rb_u_string_titlecase(int argc, VALUE *argv, VALUE self);
|
156
|
+
VALUE rb_u_string_to_i(int argc, VALUE *argv, VALUE self);
|
157
|
+
VALUE rb_u_string_to_str(VALUE self);
|
158
|
+
VALUE rb_u_string_to_sym(VALUE self);
|
159
|
+
VALUE rb_u_string_tr(VALUE self, VALUE from, VALUE to);
|
160
|
+
VALUE rb_u_string_tr_s(VALUE self, VALUE from, VALUE to);
|
161
|
+
VALUE rb_u_string_upcase(int argc, VALUE *argv, VALUE self);
|
162
|
+
VALUE rb_u_string_upper(int argc, VALUE *argv, VALUE self);
|
163
|
+
VALUE rb_u_string_valid(VALUE self);
|
164
|
+
VALUE rb_u_string_valid_encoding(VALUE self);
|
165
|
+
VALUE rb_u_string_wide(VALUE self);
|
166
|
+
VALUE rb_u_string_wide_cjk(VALUE self);
|
167
|
+
VALUE rb_u_string_width(VALUE self);
|
168
|
+
VALUE rb_u_string_word_break(VALUE self);
|
169
|
+
VALUE rb_u_string_xdigit(VALUE self);
|
170
|
+
VALUE rb_u_string_zero_width(VALUE self);
|
171
|
+
|
172
|
+
|
173
|
+
void Init_u_string(VALUE mU);
|
@@ -0,0 +1,10 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
|
3
|
+
/* @overload alnum?
|
4
|
+
* @return [Boolean] True if the receiver contains only characters in the
|
5
|
+
* general categories Letter and Number */
|
6
|
+
VALUE
|
7
|
+
rb_u_string_alnum(VALUE self)
|
8
|
+
{
|
9
|
+
return _rb_u_character_test(self, u_char_isalnum);
|
10
|
+
}
|
@@ -0,0 +1,142 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
#include "rb_u_re.h"
|
3
|
+
|
4
|
+
static VALUE
|
5
|
+
rb_u_string_substr_impl(VALUE self, long offset, long len, bool nil_on_empty)
|
6
|
+
{
|
7
|
+
if (len < 0)
|
8
|
+
return Qnil;
|
9
|
+
|
10
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
11
|
+
|
12
|
+
const char *begin = rb_u_string_begin_from_offset(string, offset);
|
13
|
+
if (begin == NULL)
|
14
|
+
return Qnil;
|
15
|
+
|
16
|
+
const char *end = u_offset_to_pointer_n(begin, len, USTRING_END(string) - begin);
|
17
|
+
if (end == NULL)
|
18
|
+
end = USTRING_END(string);
|
19
|
+
|
20
|
+
if (nil_on_empty && begin == end)
|
21
|
+
return Qnil;
|
22
|
+
|
23
|
+
if (begin == USTRING_STR(string) && end == USTRING_END(string))
|
24
|
+
return self;
|
25
|
+
|
26
|
+
return rb_u_string_new_c(self, begin, end - begin);
|
27
|
+
}
|
28
|
+
|
29
|
+
VALUE
|
30
|
+
rb_u_string_substr(VALUE self, long offset, long len)
|
31
|
+
{
|
32
|
+
return rb_u_string_substr_impl(self, offset, len, false);
|
33
|
+
}
|
34
|
+
|
35
|
+
static VALUE
|
36
|
+
rb_u_string_subpat(VALUE self, VALUE re, VALUE reference)
|
37
|
+
{
|
38
|
+
if (rb_reg_search(re, StringValue(self), 0, 0) < 0)
|
39
|
+
return Qnil;
|
40
|
+
|
41
|
+
volatile VALUE match = rb_u_pattern_match_reference(reference);
|
42
|
+
|
43
|
+
return NIL_P(match) ? Qnil : rb_u_string_new_rb(match);
|
44
|
+
}
|
45
|
+
|
46
|
+
static VALUE
|
47
|
+
rb_u_string_aref_num(VALUE self, long offset)
|
48
|
+
{
|
49
|
+
return rb_u_string_substr_impl(self, offset, 1, true);
|
50
|
+
}
|
51
|
+
|
52
|
+
static VALUE
|
53
|
+
rb_u_string_aref_default(VALUE self, VALUE index)
|
54
|
+
{
|
55
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
56
|
+
long n_chars = u_n_chars_n(USTRING_STR(string), USTRING_LENGTH(string));
|
57
|
+
|
58
|
+
long begin, length;
|
59
|
+
switch (rb_range_beg_len(index, &begin, &length, n_chars, 0)) {
|
60
|
+
case Qfalse:
|
61
|
+
return rb_u_string_aref_num(self, NUM2LONG(index));
|
62
|
+
case Qnil:
|
63
|
+
return Qnil;
|
64
|
+
default:
|
65
|
+
return rb_u_string_substr(self, begin, length);
|
66
|
+
}
|
67
|
+
}
|
68
|
+
|
69
|
+
static VALUE
|
70
|
+
rb_u_string_aref(VALUE self, VALUE index)
|
71
|
+
{
|
72
|
+
if (TYPE(index) == T_STRING || RTEST(rb_obj_is_kind_of(index, rb_cUString))) {
|
73
|
+
if (rb_u_string_index(self, index, 0) == -1)
|
74
|
+
return Qnil;
|
75
|
+
|
76
|
+
return TYPE(index) == T_STRING ?
|
77
|
+
rb_u_string_new_c(index, RSTRING_PTR(index), RSTRING_LEN(index)) :
|
78
|
+
index;
|
79
|
+
}
|
80
|
+
|
81
|
+
switch (TYPE(index)) {
|
82
|
+
case T_FIXNUM:
|
83
|
+
return rb_u_string_aref_num(self, FIX2LONG(index));
|
84
|
+
case T_REGEXP:
|
85
|
+
return rb_u_string_subpat(self, index, INT2FIX(0));
|
86
|
+
default:
|
87
|
+
return rb_u_string_aref_default(self, index);
|
88
|
+
}
|
89
|
+
}
|
90
|
+
|
91
|
+
/* @overload [](index)
|
92
|
+
* @param [#to_int] index
|
93
|
+
* @return [U::String, nil] The substring [max(_i_, 0), min({#length}, _i_ +
|
94
|
+
* 1)], where _i_ = INDEX if INDEX ≥ 0, _i_ = {#length} - abs(INDEX)
|
95
|
+
* otherwise, inheriting any taint and untrust, or nil if this substring is
|
96
|
+
* empty
|
97
|
+
*
|
98
|
+
* @overload [](index, length)
|
99
|
+
* @param [#to_int] index
|
100
|
+
* @param [#to_int] length
|
101
|
+
* @return [U::String, nil] The substring [max(_i_, 0), min({#length}, _i_ +
|
102
|
+
* LENGTH)], where _i_ = INDEX if INDEX ≥ 0, _i_ = {#length} - abs(INDEX)
|
103
|
+
* otherwise, inheriting any taint or untrust, or nil if LENGTH < 0
|
104
|
+
*
|
105
|
+
* @overload [](range)
|
106
|
+
* @param [Range] range
|
107
|
+
* @return [U::String, nil] The result of `#[i, j - k]`, where _i_ =
|
108
|
+
* RANGE#begin if RANGE#begin ≥ 0, _i_ = {#length} - abs(RANGE#begin)
|
109
|
+
* otherwise, _j_ = RANGE#end if RANGE#end ≥ 0, _j_ = {#length} -
|
110
|
+
* abs(RANGE#end) otherwise, and _k_ = 1 if RANGE#exclude_end?, _k_ = 0
|
111
|
+
* otherwise, or nil if _j_ - _k_ < 0
|
112
|
+
*
|
113
|
+
* @overload [](regexp, reference = 0)
|
114
|
+
* @param [Regexp] regexp
|
115
|
+
* @param [#to_int, #to_str, Symbol] reference
|
116
|
+
* @raise [IndexError] If REFERENCE doesn’t refer to a submatch
|
117
|
+
* @return [U::String, nil] The submatch REFERENCE from the first match of
|
118
|
+
* REGEXP in the receiver, inheriting any taint and untrust from both
|
119
|
+
* the receiver and from REGEXP, or nil if there is no match or if the
|
120
|
+
* submatch isn’t part of the overall match
|
121
|
+
*
|
122
|
+
* @overload [](string)
|
123
|
+
* @param [U::String, ::String] string
|
124
|
+
* @return [U::String, nil] The substring STRING, inheriting any taint and
|
125
|
+
* untrust from STRING, if STRING is a substring of the receiver
|
126
|
+
*
|
127
|
+
* @overload [](object)
|
128
|
+
* @param [Object] object
|
129
|
+
* @return [nil] Nil for any object that doesn’t satisfy the other cases */
|
130
|
+
VALUE
|
131
|
+
rb_u_string_aref_m(int argc, VALUE *argv, VALUE self)
|
132
|
+
{
|
133
|
+
need_m_to_n_arguments(argc, 1, 2);
|
134
|
+
|
135
|
+
if (argc == 1)
|
136
|
+
return rb_u_string_aref(self, argv[0]);
|
137
|
+
|
138
|
+
if (TYPE(argv[0]) == T_REGEXP)
|
139
|
+
return rb_u_string_subpat(self, argv[0], argv[1]);
|
140
|
+
|
141
|
+
return rb_u_string_substr(self, NUM2LONG(argv[0]), NUM2LONG(argv[1]));
|
142
|
+
}
|
@@ -0,0 +1,13 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
|
3
|
+
/* @overload ascii_only?
|
4
|
+
* @return [Boolean] True if the receiver contains only characters in the ASCII region, that
|
5
|
+
* is, U+0000 through U+007F */
|
6
|
+
VALUE
|
7
|
+
rb_u_string_ascii_only(VALUE self)
|
8
|
+
{
|
9
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
10
|
+
|
11
|
+
return u_is_ascii_only_n(USTRING_STR(string), USTRING_LENGTH(string)) ?
|
12
|
+
Qtrue : Qfalse;
|
13
|
+
}
|
@@ -0,0 +1,10 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
|
3
|
+
/* @overload assigned?
|
4
|
+
* @return [Boolean] True if the receiver contains only code points that have
|
5
|
+
* been assigned a code value */
|
6
|
+
VALUE
|
7
|
+
rb_u_string_assigned(VALUE self)
|
8
|
+
{
|
9
|
+
return _rb_u_character_test(self, u_char_isassigned);
|
10
|
+
}
|
@@ -0,0 +1,18 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
#ifdef HAVE_RUBY_ENCODING_H
|
3
|
+
# include <ruby/encoding.h>
|
4
|
+
#endif
|
5
|
+
|
6
|
+
/* @return [String] The String representation of the receiver, inheriting any
|
7
|
+
* taint and untrust, encoded as ASCII-8BIT. */
|
8
|
+
VALUE
|
9
|
+
rb_u_string_b(VALUE self)
|
10
|
+
{
|
11
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
12
|
+
VALUE result = rb_str_new(USTRING_STR(string), USTRING_LENGTH(string));
|
13
|
+
#ifdef HAVE_RUBY_ENCODING_H
|
14
|
+
rb_enc_associate(result, rb_ascii8bit_encoding());
|
15
|
+
#endif
|
16
|
+
OBJ_INFECT(result, self);
|
17
|
+
return result;
|
18
|
+
}
|
@@ -0,0 +1,10 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
|
3
|
+
/* @return [Integer] The number of bytes required to represent the receiver */
|
4
|
+
VALUE
|
5
|
+
rb_u_string_bytesize(VALUE self)
|
6
|
+
{
|
7
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
8
|
+
|
9
|
+
return LONG2NUM(USTRING_LENGTH(string));
|
10
|
+
}
|
@@ -0,0 +1,103 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
|
3
|
+
static VALUE
|
4
|
+
rb_u_string_byte_substr(VALUE self, long offset, long length)
|
5
|
+
{
|
6
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
7
|
+
long n = USTRING_LENGTH(string);
|
8
|
+
|
9
|
+
if (offset > n || length < 0)
|
10
|
+
return Qnil;
|
11
|
+
|
12
|
+
if (offset < 0) {
|
13
|
+
offset += n;
|
14
|
+
if (offset < 0)
|
15
|
+
return Qnil;
|
16
|
+
}
|
17
|
+
|
18
|
+
if (offset + length > n)
|
19
|
+
length = n - offset;
|
20
|
+
|
21
|
+
if (length <= 0)
|
22
|
+
return rb_u_string_new_empty(self);
|
23
|
+
|
24
|
+
return rb_u_string_new_subsequence(self, offset, length);
|
25
|
+
}
|
26
|
+
|
27
|
+
static VALUE
|
28
|
+
rb_u_string_byteslice_num(VALUE self, long offset)
|
29
|
+
{
|
30
|
+
VALUE result = rb_u_string_byte_substr(self, offset, 1);
|
31
|
+
|
32
|
+
if (NIL_P(result) || USTRING_LENGTH(RVAL2USTRING(result)) == 0)
|
33
|
+
return Qnil;
|
34
|
+
|
35
|
+
return result;
|
36
|
+
}
|
37
|
+
|
38
|
+
static VALUE
|
39
|
+
rb_u_string_byteslice_default(VALUE self, VALUE index)
|
40
|
+
{
|
41
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
42
|
+
long n_bytes = USTRING_LENGTH(string);
|
43
|
+
|
44
|
+
long begin, length;
|
45
|
+
switch (rb_range_beg_len(index, &begin, &length, n_bytes, 0)) {
|
46
|
+
case Qfalse:
|
47
|
+
return rb_u_string_byteslice_num(self, NUM2LONG(index));
|
48
|
+
case Qnil:
|
49
|
+
return Qnil;
|
50
|
+
default:
|
51
|
+
return rb_u_string_byte_substr(self, begin, length);
|
52
|
+
}
|
53
|
+
}
|
54
|
+
|
55
|
+
static VALUE
|
56
|
+
rb_u_string_byteslice(VALUE self, VALUE index)
|
57
|
+
{
|
58
|
+
switch (TYPE(index)) {
|
59
|
+
case T_FIXNUM:
|
60
|
+
return rb_u_string_byteslice_num(self, FIX2LONG(index));
|
61
|
+
default:
|
62
|
+
return rb_u_string_byteslice_default(self, index);
|
63
|
+
}
|
64
|
+
}
|
65
|
+
|
66
|
+
/* @overload byteslice(index)
|
67
|
+
* @param [#to_int] index
|
68
|
+
* @return [U::String, nil] The byte-index-based substring [max(_i_, 0),
|
69
|
+
* min({#bytesize}, _i_ + 1)], where _i_ = INDEX if INDEX ≥ 0, _i_ =
|
70
|
+
* {#bytesize} - abs(INDEX) otherwise, inheriting any taint and untrust, or
|
71
|
+
* nil if this substring is empty
|
72
|
+
*
|
73
|
+
* @overload byteslice(index, length)
|
74
|
+
* @param [#to_int] index
|
75
|
+
* @param [#to_int] length
|
76
|
+
* @return [U::String, nil] The byte-index-based substring [max(_i_, 0),
|
77
|
+
* min({#bytesize}, _i_ + LENGTH)], where _i_ = INDEX if INDEX ≥ 0, _i_ =
|
78
|
+
* {#bytesize} - abs(INDEX) otherwise, inheriting any taint and untrust, or
|
79
|
+
* nil if LENGTH < 0
|
80
|
+
*
|
81
|
+
* @overload byteslice(range)
|
82
|
+
* @param [Range] range
|
83
|
+
* @return [U::String, nil] The result of `#[i, j - k]`, where _i_ =
|
84
|
+
* RANGE#begin if RANGE#begin ≥ 0, _i_ = {#bytesize} - abs(RANGE#begin)
|
85
|
+
* otherwise, _j_ = RANGE#end if RANGE#end ≥ 0, _j_ = {#bytesize} -
|
86
|
+
* abs(RANGE#end) otherwise, and _k_ = 1 if RANGE#exclude_end?, _k_ = 0
|
87
|
+
* otherwise, or nil if _j_ - _k_ < 0
|
88
|
+
*
|
89
|
+
* @overload byteslice(object)
|
90
|
+
* @param [Object] object
|
91
|
+
* @return [nil] Nil for any object that doesn’t satisfy the other cases */
|
92
|
+
VALUE
|
93
|
+
rb_u_string_byteslice_m(int argc, VALUE *argv, VALUE self)
|
94
|
+
{
|
95
|
+
need_m_to_n_arguments(argc, 1, 2);
|
96
|
+
|
97
|
+
if (argc == 1)
|
98
|
+
return rb_u_string_byteslice(self, argv[0]);
|
99
|
+
|
100
|
+
return rb_u_string_byte_substr(self,
|
101
|
+
NUM2LONG(argv[0]),
|
102
|
+
NUM2LONG(argv[1]));
|
103
|
+
}
|