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 +1,189 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
|
3
|
+
static void
|
4
|
+
rb_u_string_inspect_bad_input(const char *p, const char *q, VALUE result)
|
5
|
+
{
|
6
|
+
while (p < q) {
|
7
|
+
char hex[5];
|
8
|
+
snprintf(hex, lengthof(hex), "\\x%02X", *p & 0xff);
|
9
|
+
rb_str_buf_cat2(result, hex);
|
10
|
+
p++;
|
11
|
+
}
|
12
|
+
}
|
13
|
+
|
14
|
+
static void
|
15
|
+
rb_u_string_inspect_special_char(uint32_t c, VALUE result)
|
16
|
+
{
|
17
|
+
char str[U_CHAR_MAX_BYTE_LENGTH];
|
18
|
+
|
19
|
+
rb_str_buf_cat2(result, "\\");
|
20
|
+
rb_str_buf_cat(result, str, u_char_to_u(c, str));
|
21
|
+
}
|
22
|
+
|
23
|
+
static void
|
24
|
+
rb_u_string_inspect_escaped_char(uint32_t c, VALUE result)
|
25
|
+
{
|
26
|
+
char str[4 + 8 + 1];
|
27
|
+
|
28
|
+
if (c < 0x10000)
|
29
|
+
snprintf(str, lengthof(str), "\\u%04X", c);
|
30
|
+
else
|
31
|
+
snprintf(str, lengthof(str), "\\u{%X}", c & 0xffffffff);
|
32
|
+
|
33
|
+
rb_str_buf_cat2(result, str);
|
34
|
+
}
|
35
|
+
|
36
|
+
static void
|
37
|
+
rb_u_string_inspect_default(uint32_t c, VALUE result)
|
38
|
+
{
|
39
|
+
if (!u_char_isprint(c)) {
|
40
|
+
rb_u_string_inspect_escaped_char(c, result);
|
41
|
+
return;
|
42
|
+
}
|
43
|
+
|
44
|
+
char str[U_CHAR_MAX_BYTE_LENGTH];
|
45
|
+
rb_str_buf_cat(result, str, u_char_to_u(c, str));
|
46
|
+
}
|
47
|
+
|
48
|
+
#define REPLACEMENT_CHARACTER ((uint32_t)0xfffd)
|
49
|
+
|
50
|
+
static const char *
|
51
|
+
rb_u_string_inspect_hash_char(const char *q, const char *end,
|
52
|
+
VALUE result)
|
53
|
+
{
|
54
|
+
if (q == end) {
|
55
|
+
rb_str_buf_cat2(result, "#");
|
56
|
+
return q;
|
57
|
+
}
|
58
|
+
|
59
|
+
const char *p = q;
|
60
|
+
uint32_t c = u_decode(&q, p, end);
|
61
|
+
switch (c) {
|
62
|
+
case REPLACEMENT_CHARACTER:
|
63
|
+
rb_str_buf_cat2(result, "#");
|
64
|
+
if (!u_valid(p, q - p, NULL))
|
65
|
+
rb_u_string_inspect_bad_input(p, q, result);
|
66
|
+
else
|
67
|
+
rb_u_string_inspect_default(c, result);
|
68
|
+
return q;
|
69
|
+
case '$':
|
70
|
+
case '@':
|
71
|
+
case '{':
|
72
|
+
rb_str_buf_cat2(result, "\\#");
|
73
|
+
rb_u_string_inspect_default(c, result);
|
74
|
+
return q;
|
75
|
+
default:
|
76
|
+
rb_str_buf_cat2(result, "#");
|
77
|
+
return p;
|
78
|
+
}
|
79
|
+
}
|
80
|
+
|
81
|
+
/* Returns the receiver in a reader-friendly inspectable format, inheriting
|
82
|
+
* any taint and untrust, encoded using UTF-8.
|
83
|
+
*
|
84
|
+
* The reader-friendly inspectable format looks like “`"…".u`”. Inside the
|
85
|
+
* “…”, any {#print?} characters are output as-is, the following special
|
86
|
+
* characters are escaped according to the following table:
|
87
|
+
*
|
88
|
+
* <table>
|
89
|
+
* <thead><tr><th>Character</th><th>Dumped Sequence</th></tr></thead>
|
90
|
+
* <tbody>
|
91
|
+
* <tr><td>U+0022 QUOTATION MARK</td><td><code>\"</code></td></tr>
|
92
|
+
* <tr><td>U+005C REVERSE SOLIDUS</td><td><code>\\</code></td></tr>
|
93
|
+
* <tr><td>U+000A LINE FEED (LF)</td><td><code>\n</code></td></tr>
|
94
|
+
* <tr><td>U+000D CARRIAGE RETURN (CR)</td><td><code>\r</code></td></tr>
|
95
|
+
* <tr><td>U+0009 CHARACTER TABULATION</td><td><code>\t</code></td></tr>
|
96
|
+
* <tr><td>U+000C FORM FEED (FF)</td><td><code>\f</code></td></tr>
|
97
|
+
* <tr><td>U+000B LINE TABULATION</td><td><code>\v</code></td></tr>
|
98
|
+
* <tr><td>U+0008 BACKSPACE</td><td><code>\b</code></td></tr>
|
99
|
+
* <tr><td>U+0007 BELL</td><td><code>\a</code></td></tr>
|
100
|
+
* <tr><td>U+001B ESCAPE</td><td><code>\e</code></td></tr>
|
101
|
+
* </tbody>
|
102
|
+
* </table>
|
103
|
+
*
|
104
|
+
* the following special sequences are also escaped:
|
105
|
+
*
|
106
|
+
* <table>
|
107
|
+
* <thead><tr><th>Character</th><th>Dumped Sequence</th></tr></thead>
|
108
|
+
* <tbody>
|
109
|
+
* <tr><td><code>#$</code></td><td><code>\#$</code></td></tr>
|
110
|
+
* <tr><td><code>#@</code></td><td><code>\#@</code></td></tr>
|
111
|
+
* <tr><td><code>#{</code></td><td><code>\#{</code></td></tr>
|
112
|
+
* </tbody>
|
113
|
+
* </table>
|
114
|
+
*
|
115
|
+
* Valid UTF-8 byte sequences representing code points < 0x10000 are output as
|
116
|
+
* `\u`_n_, where _n_ is the four-digit uppercase hexadecimal representation
|
117
|
+
* of the code point.
|
118
|
+
*
|
119
|
+
* Valid UTF-8 byte sequences representing code points ≥ 0x10000 are output as
|
120
|
+
* `\u{`_n_`}`, where _n_ is the uppercase hexadecimal representation of the
|
121
|
+
* code point.
|
122
|
+
*
|
123
|
+
* Any other byte is output as `\x`_n_, where _n_ is the two-digit uppercase
|
124
|
+
* hexadecimal representation of the byte’s value.
|
125
|
+
*
|
126
|
+
* @return [String] */
|
127
|
+
VALUE
|
128
|
+
rb_u_string_inspect(VALUE self)
|
129
|
+
{
|
130
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
131
|
+
|
132
|
+
VALUE result = rb_u_str_buf_new(0);
|
133
|
+
rb_str_buf_cat2(result, "\"");
|
134
|
+
const char *p = USTRING_STR(string);
|
135
|
+
const char *end = USTRING_END(string);
|
136
|
+
while (p < end) {
|
137
|
+
const char *q;
|
138
|
+
uint32_t c = u_decode(&q, p, end);
|
139
|
+
switch (c) {
|
140
|
+
case '"':
|
141
|
+
case '\\':
|
142
|
+
rb_u_string_inspect_special_char(c, result);
|
143
|
+
break;
|
144
|
+
case '#':
|
145
|
+
p = rb_u_string_inspect_hash_char(q, end, result);
|
146
|
+
continue;
|
147
|
+
case '\n':
|
148
|
+
rb_str_buf_cat2(result, "\\n");
|
149
|
+
break;
|
150
|
+
case '\r':
|
151
|
+
rb_str_buf_cat2(result, "\\r");
|
152
|
+
break;
|
153
|
+
case '\t':
|
154
|
+
rb_str_buf_cat2(result, "\\t");
|
155
|
+
break;
|
156
|
+
case '\f':
|
157
|
+
rb_str_buf_cat2(result, "\\f");
|
158
|
+
break;
|
159
|
+
case '\013':
|
160
|
+
rb_str_buf_cat2(result, "\\v");
|
161
|
+
break;
|
162
|
+
case '\010':
|
163
|
+
rb_str_buf_cat2(result, "\\b");
|
164
|
+
break;
|
165
|
+
case '\007':
|
166
|
+
rb_str_buf_cat2(result, "\\a");
|
167
|
+
break;
|
168
|
+
case '\033':
|
169
|
+
rb_str_buf_cat2(result, "\\e");
|
170
|
+
break;
|
171
|
+
case REPLACEMENT_CHARACTER:
|
172
|
+
if (!u_valid(p, q - p, NULL)) {
|
173
|
+
rb_u_string_inspect_bad_input(p, q, result);
|
174
|
+
break;
|
175
|
+
}
|
176
|
+
/* fall through */
|
177
|
+
default:
|
178
|
+
rb_u_string_inspect_default(c, result);
|
179
|
+
break;
|
180
|
+
}
|
181
|
+
p = q;
|
182
|
+
}
|
183
|
+
|
184
|
+
rb_str_buf_cat2(result, "\".u");
|
185
|
+
|
186
|
+
OBJ_INFECT(result, self);
|
187
|
+
|
188
|
+
return result;
|
189
|
+
}
|
@@ -0,0 +1,148 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
#include "rb_u_string_internal_tr.h"
|
3
|
+
|
4
|
+
void
|
5
|
+
tr_init(struct tr *tr, const char *p, const char *end)
|
6
|
+
{
|
7
|
+
tr->p = p;
|
8
|
+
tr->end = end;
|
9
|
+
tr->inside_range = false;
|
10
|
+
}
|
11
|
+
|
12
|
+
bool
|
13
|
+
tr_should_exclude(struct tr *tr)
|
14
|
+
{
|
15
|
+
if (tr->p + 1 < tr->end && *tr->p == '^') {
|
16
|
+
tr->p++;
|
17
|
+
return true;
|
18
|
+
}
|
19
|
+
|
20
|
+
return false;
|
21
|
+
}
|
22
|
+
|
23
|
+
static enum tr_state
|
24
|
+
tr_next_char(struct tr *t)
|
25
|
+
{
|
26
|
+
if (t->p == t->end)
|
27
|
+
return TR_FINISHED;
|
28
|
+
|
29
|
+
t->now = u_decode(&t->p, t->p, t->end);
|
30
|
+
if (t->p == t->end)
|
31
|
+
return TR_FOUND;
|
32
|
+
if (t->now == '\\') {
|
33
|
+
t->now = u_decode(&t->p, t->p, t->end);
|
34
|
+
if (t->p == t->end)
|
35
|
+
return TR_FOUND;
|
36
|
+
}
|
37
|
+
|
38
|
+
const char *next;
|
39
|
+
if (u_decode(&next, t->p, t->end) == '-') {
|
40
|
+
/* TODO: Make this simpler. Perhaps we don’t need
|
41
|
+
* TR_READ_ANOTHER, as we advance it here ourselves. I got to
|
42
|
+
* check the offsets here. Perhaps TR_READ_ANOTHER should also
|
43
|
+
* have advanced t->p one more step. */
|
44
|
+
if (next < t->end) {
|
45
|
+
uint32_t max = u_decode(&t->p, next, t->end);
|
46
|
+
if (max < t->now) {
|
47
|
+
t->p = next;
|
48
|
+
return TR_READ_ANOTHER;
|
49
|
+
}
|
50
|
+
t->inside_range = true;
|
51
|
+
t->max = max;
|
52
|
+
}
|
53
|
+
}
|
54
|
+
|
55
|
+
return TR_FOUND;
|
56
|
+
}
|
57
|
+
|
58
|
+
enum tr_state
|
59
|
+
tr_next(struct tr *t)
|
60
|
+
{
|
61
|
+
while (true) {
|
62
|
+
if (!t->inside_range) {
|
63
|
+
enum tr_state state;
|
64
|
+
|
65
|
+
if ((state = tr_next_char(t)) == TR_READ_ANOTHER)
|
66
|
+
continue;
|
67
|
+
|
68
|
+
return state;
|
69
|
+
} else if (++t->now < t->max) {
|
70
|
+
return TR_FOUND;
|
71
|
+
} else {
|
72
|
+
t->inside_range = false;
|
73
|
+
return TR_FOUND;
|
74
|
+
}
|
75
|
+
}
|
76
|
+
}
|
77
|
+
|
78
|
+
static void
|
79
|
+
tr_table_set(struct tr_table *table, bool *buffer, uint32_t c, bool value)
|
80
|
+
{
|
81
|
+
if (c < lengthof(table->continuous)) {
|
82
|
+
buffer[c] = value;
|
83
|
+
return;
|
84
|
+
}
|
85
|
+
|
86
|
+
if (NIL_P(table->sparse))
|
87
|
+
table->sparse = rb_hash_new();
|
88
|
+
|
89
|
+
rb_hash_aset(table->sparse, UINT2NUM(c), value ? Qtrue : Qfalse);
|
90
|
+
}
|
91
|
+
|
92
|
+
static void
|
93
|
+
tr_table_add(struct tr_table *table, const struct rb_u_string *string)
|
94
|
+
{
|
95
|
+
struct tr tr;
|
96
|
+
tr_init(&tr, USTRING_STR(string), USTRING_END(string));
|
97
|
+
|
98
|
+
bool exclude = tr_should_exclude(&tr);
|
99
|
+
|
100
|
+
bool buffer[lengthof(table->continuous)];
|
101
|
+
|
102
|
+
for (size_t i = 0; i < lengthof(buffer); i++)
|
103
|
+
buffer[i] = exclude;
|
104
|
+
|
105
|
+
while (tr_next(&tr) != TR_FINISHED)
|
106
|
+
tr_table_set(table, buffer, tr.now, !exclude);
|
107
|
+
|
108
|
+
for (size_t i = 0; i < lengthof(table->continuous); i++)
|
109
|
+
table->continuous[i] = table->continuous[i] && buffer[i];
|
110
|
+
}
|
111
|
+
|
112
|
+
void
|
113
|
+
tr_table_initialize(struct tr_table *table, VALUE rbstring)
|
114
|
+
{
|
115
|
+
const struct rb_u_string *string = RVAL2USTRING_ANY(rbstring);
|
116
|
+
|
117
|
+
struct tr tr;
|
118
|
+
tr_init(&tr, USTRING_STR(string), USTRING_END(string));
|
119
|
+
|
120
|
+
table->exclude = tr_should_exclude(&tr);
|
121
|
+
|
122
|
+
for (size_t i = 0; i < lengthof(table->continuous); i++)
|
123
|
+
table->continuous[i] = true;
|
124
|
+
|
125
|
+
table->sparse = Qnil;
|
126
|
+
|
127
|
+
tr_table_add(table, string);
|
128
|
+
}
|
129
|
+
|
130
|
+
void
|
131
|
+
tr_table_initialize_from_strings(struct tr_table *table, int argc, VALUE *argv)
|
132
|
+
{
|
133
|
+
tr_table_initialize(table, argv[0]);
|
134
|
+
for (int i = 1; i < argc; i++)
|
135
|
+
tr_table_add(table, RVAL2USTRING_ANY(argv[i]));
|
136
|
+
}
|
137
|
+
|
138
|
+
bool
|
139
|
+
tr_table_lookup(struct tr_table *table, uint32_t c)
|
140
|
+
{
|
141
|
+
if (c < lengthof(table->continuous))
|
142
|
+
return table->continuous[c];
|
143
|
+
|
144
|
+
VALUE value = NIL_P(table->sparse) ?
|
145
|
+
Qnil : rb_hash_lookup(table->sparse, UINT2NUM(c));
|
146
|
+
|
147
|
+
return NIL_P(value) ? table->exclude : RTEST(value);
|
148
|
+
}
|
@@ -0,0 +1,29 @@
|
|
1
|
+
struct tr {
|
2
|
+
bool inside_range;
|
3
|
+
uint32_t now;
|
4
|
+
uint32_t max;
|
5
|
+
const char *p;
|
6
|
+
const char *end;
|
7
|
+
};
|
8
|
+
|
9
|
+
enum tr_state
|
10
|
+
{
|
11
|
+
TR_FOUND,
|
12
|
+
TR_READ_ANOTHER,
|
13
|
+
TR_FINISHED
|
14
|
+
};
|
15
|
+
|
16
|
+
struct tr_table {
|
17
|
+
bool exclude;
|
18
|
+
bool continuous[256];
|
19
|
+
VALUE sparse;
|
20
|
+
};
|
21
|
+
|
22
|
+
void tr_init(struct tr *tr, const char *p, const char *end);
|
23
|
+
bool tr_should_exclude(struct tr *tr);
|
24
|
+
enum tr_state tr_next(struct tr *t);
|
25
|
+
void tr_table_initialize(struct tr_table *table, VALUE rbstring);
|
26
|
+
void tr_table_initialize_from_strings(struct tr_table *table,
|
27
|
+
int argc,
|
28
|
+
VALUE *argv);
|
29
|
+
bool tr_table_lookup(struct tr_table *table, uint32_t c);
|
@@ -0,0 +1,169 @@
|
|
1
|
+
#include "rb_includes.h"
|
2
|
+
|
3
|
+
static char *
|
4
|
+
rb_u_string_justify_one_side(char *p, const struct rb_u_string *padding, long padding_width, long n)
|
5
|
+
{
|
6
|
+
const char *padding_str = USTRING_STR(padding);
|
7
|
+
long padding_size = USTRING_LENGTH(padding);
|
8
|
+
|
9
|
+
long i = 0;
|
10
|
+
|
11
|
+
for ( ; i + padding_width < n; i += padding_width, p += padding_size)
|
12
|
+
memcpy(p, padding_str, padding_size);
|
13
|
+
|
14
|
+
const char *q = padding_str;
|
15
|
+
const char *end = padding_str + padding_size;
|
16
|
+
while (i < n)
|
17
|
+
i += u_char_width(u_decode(&q, q, end));
|
18
|
+
memcpy(p, padding_str, q - padding_str);
|
19
|
+
p += q - padding_str;
|
20
|
+
|
21
|
+
return p;
|
22
|
+
}
|
23
|
+
|
24
|
+
static long
|
25
|
+
rounding_size(const struct rb_u_string *padding, long padding_width, long n)
|
26
|
+
{
|
27
|
+
const char *padding_str = USTRING_STR(padding);
|
28
|
+
const char *q = padding_str, *end = padding_str + USTRING_LENGTH(padding);
|
29
|
+
long r = n % padding_width;
|
30
|
+
long i = 0;
|
31
|
+
while (i < r && q < end)
|
32
|
+
i += u_char_width(u_decode(&q, q, end));
|
33
|
+
// NOTE I think i ≮ r is guaranteed, but I can’t seem to prove it, so
|
34
|
+
// leave this in for safety.
|
35
|
+
if (i < r)
|
36
|
+
rb_u_raise(rb_eArgError,
|
37
|
+
"padding isn’t wide enough to complete rounding (%ld < %ld)",
|
38
|
+
i, r);
|
39
|
+
if (i > r)
|
40
|
+
rb_u_raise(rb_eArgError,
|
41
|
+
"padding is too wide to complete rounding (%ld > %ld)",
|
42
|
+
i, r);
|
43
|
+
return q - padding_str;
|
44
|
+
}
|
45
|
+
|
46
|
+
static long
|
47
|
+
rb_u_string_justified_size(long string_size,
|
48
|
+
const struct rb_u_string *padding, long padding_width,
|
49
|
+
long left_n, long right_n)
|
50
|
+
{
|
51
|
+
long size;
|
52
|
+
|
53
|
+
long left_n_2 = rounding_size(padding, padding_width, left_n);
|
54
|
+
long right_n_2 = rounding_size(padding, padding_width, right_n);
|
55
|
+
if ((size = left_n / padding_width + right_n / padding_width) >= LONG_MAX / USTRING_LENGTH(padding) ||
|
56
|
+
(size *= USTRING_LENGTH(padding)) >= LONG_MAX - left_n_2 - right_n_2 ||
|
57
|
+
(size += left_n_2 + right_n_2) >= LONG_MAX - string_size)
|
58
|
+
rb_u_raise(rb_eArgError, "argument too big");
|
59
|
+
size += string_size;
|
60
|
+
|
61
|
+
return size;
|
62
|
+
}
|
63
|
+
|
64
|
+
static VALUE
|
65
|
+
rb_u_string_justify_impl(VALUE self,
|
66
|
+
const struct rb_u_string *string, long string_width,
|
67
|
+
const struct rb_u_string *padding, long padding_width,
|
68
|
+
long width, char jflag)
|
69
|
+
{
|
70
|
+
long n = width - string_width;
|
71
|
+
long left_n = (jflag == 'l') ? 0 : ((jflag == 'r') ? n : n / 2);
|
72
|
+
long right_n = n - left_n;
|
73
|
+
|
74
|
+
long string_size = USTRING_LENGTH(string);
|
75
|
+
long justified_size = rb_u_string_justified_size(string_size,
|
76
|
+
padding, padding_width,
|
77
|
+
left_n, right_n);
|
78
|
+
char *justified = ALLOC_N(char, justified_size + 1);
|
79
|
+
|
80
|
+
char *p = rb_u_string_justify_one_side(justified, padding, padding_width, left_n);
|
81
|
+
memcpy(p, USTRING_STR(string), string_size);
|
82
|
+
p += string_size;
|
83
|
+
p = rb_u_string_justify_one_side(p, padding, padding_width, right_n);
|
84
|
+
justified[justified_size] = '\0';
|
85
|
+
|
86
|
+
return rb_u_string_new_c_own(self, justified, justified_size);
|
87
|
+
}
|
88
|
+
|
89
|
+
static VALUE
|
90
|
+
rb_u_string_justify(int argc, VALUE *argv, VALUE self, char jflag)
|
91
|
+
{
|
92
|
+
const struct rb_u_string *string = RVAL2USTRING(self);
|
93
|
+
|
94
|
+
VALUE rbwidth, rbpadding;
|
95
|
+
const struct rb_u_string *padding = USTRING_LOCAL(Qnil, " ", 1);
|
96
|
+
long padding_width = 1;
|
97
|
+
if (rb_scan_args(argc, argv, "11", &rbwidth, &rbpadding) == 2) {
|
98
|
+
padding = RVAL2USTRING_ANY(rbpadding);
|
99
|
+
padding_width = u_width_n(USTRING_STR(padding), USTRING_LENGTH(padding));
|
100
|
+
if (padding_width == 0)
|
101
|
+
rb_u_raise(rb_eArgError, "zero-width padding");
|
102
|
+
}
|
103
|
+
|
104
|
+
long string_width = u_width_n(USTRING_STR(string), USTRING_LENGTH(string));
|
105
|
+
|
106
|
+
long width = NUM2LONG(rbwidth);
|
107
|
+
if (width < 0 || string_width >= width)
|
108
|
+
return self;
|
109
|
+
|
110
|
+
VALUE result = rb_u_string_justify_impl(self,
|
111
|
+
string, string_width,
|
112
|
+
padding, padding_width,
|
113
|
+
width, jflag);
|
114
|
+
if (!NIL_P(rbpadding))
|
115
|
+
OBJ_INFECT(result, rbpadding);
|
116
|
+
return result;
|
117
|
+
}
|
118
|
+
|
119
|
+
/* @overload center(width, padding = ' ')
|
120
|
+
* @param [#to_int] width
|
121
|
+
* @param [U::String, #to_str] padding
|
122
|
+
* @raise [ArgumentError] If PADDING{#width} = 0
|
123
|
+
* @raise [ArgumentError] If characters inside PADDING that should be used
|
124
|
+
* for round-off padding are too wide
|
125
|
+
* @return [U::String] The receiver padded as evenly as possible on both
|
126
|
+
* sides with PADDING to make it max({#length}, WIDTH) wide, inheriting any
|
127
|
+
* taint and untrust from the receiver and also from PADDING if PADDING is
|
128
|
+
* used
|
129
|
+
* @see #ljust
|
130
|
+
* @see #rjust */
|
131
|
+
VALUE
|
132
|
+
rb_u_string_center(int argc, VALUE *argv, VALUE self)
|
133
|
+
{
|
134
|
+
return rb_u_string_justify(argc, argv, self, 'c');
|
135
|
+
}
|
136
|
+
|
137
|
+
/* @overload ljust(width, padding = ' ')
|
138
|
+
* @param [#to_int] width
|
139
|
+
* @param [U::String, #to_str] padding
|
140
|
+
* @raise [ArgumentError] If PADDING{#width} = 0
|
141
|
+
* @raise [ArgumentError] If characters inside PADDING that should be used
|
142
|
+
* for round-off padding are too wide
|
143
|
+
* @return [U::String] The receiver padded on the right with PADDING to make
|
144
|
+
* it max({#length}, WIDTH) wide, inheriting any taint and untrust from
|
145
|
+
* the receiver and also from PADDING if PADDING is used
|
146
|
+
* @see #center
|
147
|
+
* @see #rjust */
|
148
|
+
VALUE
|
149
|
+
rb_u_string_ljust(int argc, VALUE *argv, VALUE self)
|
150
|
+
{
|
151
|
+
return rb_u_string_justify(argc, argv, self, 'l');
|
152
|
+
}
|
153
|
+
|
154
|
+
/* @overload rjust(width, padding = ' ')
|
155
|
+
* @param [#to_int] width
|
156
|
+
* @param [U::String, #to_str] padding
|
157
|
+
* @raise [ArgumentError] If PADDING{#width} = 0
|
158
|
+
* @raise [ArgumentError] If characters inside PADDING that should be used
|
159
|
+
* for round-off padding are too wide
|
160
|
+
* @return [U::String] The receiver padded on the left with PADDING to make
|
161
|
+
* it max({#length}, WIDTH) wide, inheriting any taint and untrust from the
|
162
|
+
* receiver and also from PADDING if PADDING is used
|
163
|
+
* @see #center
|
164
|
+
* @see #ljust */
|
165
|
+
VALUE
|
166
|
+
rb_u_string_rjust(int argc, VALUE *argv, VALUE self)
|
167
|
+
{
|
168
|
+
return rb_u_string_justify(argc, argv, self, 'r');
|
169
|
+
}
|