nokolexbor 0.3.4 → 0.3.5
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/ext/nokolexbor/nl_attribute.c +46 -0
- data/ext/nokolexbor/nl_cdata.c +8 -0
- data/ext/nokolexbor/nl_comment.c +6 -0
- data/ext/nokolexbor/nl_document.c +53 -7
- data/ext/nokolexbor/nl_document_fragment.c +9 -0
- data/ext/nokolexbor/nl_error.c +21 -19
- data/ext/nokolexbor/nl_node.c +255 -49
- data/ext/nokolexbor/nl_node_set.c +56 -1
- data/ext/nokolexbor/nl_processing_instruction.c +6 -0
- data/ext/nokolexbor/nl_text.c +6 -0
- data/ext/nokolexbor/nokolexbor.h +1 -0
- data/lib/nokolexbor/document.rb +52 -5
- data/lib/nokolexbor/document_fragment.rb +11 -0
- data/lib/nokolexbor/node.rb +367 -18
- data/lib/nokolexbor/node_set.rb +56 -0
- data/lib/nokolexbor/version.rb +1 -1
- metadata +2 -24
- data/vendor/lexbor/source/lexbor/encoding/base.h +0 -218
- data/vendor/lexbor/source/lexbor/encoding/big5.c +0 -42839
- data/vendor/lexbor/source/lexbor/encoding/config.cmake +0 -12
- data/vendor/lexbor/source/lexbor/encoding/const.h +0 -65
- data/vendor/lexbor/source/lexbor/encoding/decode.c +0 -3193
- data/vendor/lexbor/source/lexbor/encoding/decode.h +0 -370
- data/vendor/lexbor/source/lexbor/encoding/encode.c +0 -1931
- data/vendor/lexbor/source/lexbor/encoding/encode.h +0 -377
- data/vendor/lexbor/source/lexbor/encoding/encoding.c +0 -252
- data/vendor/lexbor/source/lexbor/encoding/encoding.h +0 -475
- data/vendor/lexbor/source/lexbor/encoding/euc_kr.c +0 -53883
- data/vendor/lexbor/source/lexbor/encoding/gb18030.c +0 -47905
- data/vendor/lexbor/source/lexbor/encoding/iso_2022_jp_katakana.c +0 -159
- data/vendor/lexbor/source/lexbor/encoding/jis0208.c +0 -22477
- data/vendor/lexbor/source/lexbor/encoding/jis0212.c +0 -15787
- data/vendor/lexbor/source/lexbor/encoding/multi.h +0 -53
- data/vendor/lexbor/source/lexbor/encoding/range.c +0 -71
- data/vendor/lexbor/source/lexbor/encoding/range.h +0 -34
- data/vendor/lexbor/source/lexbor/encoding/res.c +0 -222
- data/vendor/lexbor/source/lexbor/encoding/res.h +0 -34
- data/vendor/lexbor/source/lexbor/encoding/single.c +0 -13748
- data/vendor/lexbor/source/lexbor/encoding/single.h +0 -116
@@ -1,159 +0,0 @@
|
|
1
|
-
/*
|
2
|
-
* Copyright (C) 2019 Alexander Borisov
|
3
|
-
*
|
4
|
-
* Author: Alexander Borisov <borisov@lexbor.com>
|
5
|
-
*/
|
6
|
-
|
7
|
-
/*
|
8
|
-
* Caution!
|
9
|
-
* This file generated by the script "utils/lexbor/encoding/multi-byte.py"!
|
10
|
-
* Do not change this file!
|
11
|
-
*/
|
12
|
-
|
13
|
-
#include "lexbor/encoding/base.h"
|
14
|
-
|
15
|
-
#include "lexbor/core/shs.h"
|
16
|
-
|
17
|
-
|
18
|
-
LXB_API const lxb_encoding_multi_index_t lxb_encoding_multi_index_iso_2022_jp_katakana[63] =
|
19
|
-
{
|
20
|
-
{(lxb_char_t *) "\xe3\x80\x82", 3, 0x3002}, /* (IDEOGRAPHIC FULL STOP) */
|
21
|
-
{(lxb_char_t *) "\xe3\x80\x8c", 3, 0x300C}, /* (LEFT CORNER BRACKET) */
|
22
|
-
{(lxb_char_t *) "\xe3\x80\x8d", 3, 0x300D}, /* (RIGHT CORNER BRACKET) */
|
23
|
-
{(lxb_char_t *) "\xe3\x80\x81", 3, 0x3001}, /* (IDEOGRAPHIC COMMA) */
|
24
|
-
{(lxb_char_t *) "\xe3\x83\xbb", 3, 0x30FB}, /* (KATAKANA MIDDLE DOT) */
|
25
|
-
{(lxb_char_t *) "\xe3\x83\xb2", 3, 0x30F2}, /* (KATAKANA LETTER WO) */
|
26
|
-
{(lxb_char_t *) "\xe3\x82\xa1", 3, 0x30A1}, /* (KATAKANA LETTER SMALL A) */
|
27
|
-
{(lxb_char_t *) "\xe3\x82\xa3", 3, 0x30A3}, /* (KATAKANA LETTER SMALL I) */
|
28
|
-
{(lxb_char_t *) "\xe3\x82\xa5", 3, 0x30A5}, /* (KATAKANA LETTER SMALL U) */
|
29
|
-
{(lxb_char_t *) "\xe3\x82\xa7", 3, 0x30A7}, /* (KATAKANA LETTER SMALL E) */
|
30
|
-
{(lxb_char_t *) "\xe3\x82\xa9", 3, 0x30A9}, /* (KATAKANA LETTER SMALL O) */
|
31
|
-
{(lxb_char_t *) "\xe3\x83\xa3", 3, 0x30E3}, /* (KATAKANA LETTER SMALL YA) */
|
32
|
-
{(lxb_char_t *) "\xe3\x83\xa5", 3, 0x30E5}, /* (KATAKANA LETTER SMALL YU) */
|
33
|
-
{(lxb_char_t *) "\xe3\x83\xa7", 3, 0x30E7}, /* (KATAKANA LETTER SMALL YO) */
|
34
|
-
{(lxb_char_t *) "\xe3\x83\x83", 3, 0x30C3}, /* (KATAKANA LETTER SMALL TU) */
|
35
|
-
{(lxb_char_t *) "\xe3\x83\xbc", 3, 0x30FC}, /* (KATAKANA-HIRAGANA PROLONGED SOUND MARK) */
|
36
|
-
{(lxb_char_t *) "\xe3\x82\xa2", 3, 0x30A2}, /* (KATAKANA LETTER A) */
|
37
|
-
{(lxb_char_t *) "\xe3\x82\xa4", 3, 0x30A4}, /* (KATAKANA LETTER I) */
|
38
|
-
{(lxb_char_t *) "\xe3\x82\xa6", 3, 0x30A6}, /* (KATAKANA LETTER U) */
|
39
|
-
{(lxb_char_t *) "\xe3\x82\xa8", 3, 0x30A8}, /* (KATAKANA LETTER E) */
|
40
|
-
{(lxb_char_t *) "\xe3\x82\xaa", 3, 0x30AA}, /* (KATAKANA LETTER O) */
|
41
|
-
{(lxb_char_t *) "\xe3\x82\xab", 3, 0x30AB}, /* (KATAKANA LETTER KA) */
|
42
|
-
{(lxb_char_t *) "\xe3\x82\xad", 3, 0x30AD}, /* (KATAKANA LETTER KI) */
|
43
|
-
{(lxb_char_t *) "\xe3\x82\xaf", 3, 0x30AF}, /* (KATAKANA LETTER KU) */
|
44
|
-
{(lxb_char_t *) "\xe3\x82\xb1", 3, 0x30B1}, /* (KATAKANA LETTER KE) */
|
45
|
-
{(lxb_char_t *) "\xe3\x82\xb3", 3, 0x30B3}, /* (KATAKANA LETTER KO) */
|
46
|
-
{(lxb_char_t *) "\xe3\x82\xb5", 3, 0x30B5}, /* (KATAKANA LETTER SA) */
|
47
|
-
{(lxb_char_t *) "\xe3\x82\xb7", 3, 0x30B7}, /* (KATAKANA LETTER SI) */
|
48
|
-
{(lxb_char_t *) "\xe3\x82\xb9", 3, 0x30B9}, /* (KATAKANA LETTER SU) */
|
49
|
-
{(lxb_char_t *) "\xe3\x82\xbb", 3, 0x30BB}, /* (KATAKANA LETTER SE) */
|
50
|
-
{(lxb_char_t *) "\xe3\x82\xbd", 3, 0x30BD}, /* (KATAKANA LETTER SO) */
|
51
|
-
{(lxb_char_t *) "\xe3\x82\xbf", 3, 0x30BF}, /* (KATAKANA LETTER TA) */
|
52
|
-
{(lxb_char_t *) "\xe3\x83\x81", 3, 0x30C1}, /* (KATAKANA LETTER TI) */
|
53
|
-
{(lxb_char_t *) "\xe3\x83\x84", 3, 0x30C4}, /* (KATAKANA LETTER TU) */
|
54
|
-
{(lxb_char_t *) "\xe3\x83\x86", 3, 0x30C6}, /* (KATAKANA LETTER TE) */
|
55
|
-
{(lxb_char_t *) "\xe3\x83\x88", 3, 0x30C8}, /* (KATAKANA LETTER TO) */
|
56
|
-
{(lxb_char_t *) "\xe3\x83\x8a", 3, 0x30CA}, /* (KATAKANA LETTER NA) */
|
57
|
-
{(lxb_char_t *) "\xe3\x83\x8b", 3, 0x30CB}, /* (KATAKANA LETTER NI) */
|
58
|
-
{(lxb_char_t *) "\xe3\x83\x8c", 3, 0x30CC}, /* (KATAKANA LETTER NU) */
|
59
|
-
{(lxb_char_t *) "\xe3\x83\x8d", 3, 0x30CD}, /* (KATAKANA LETTER NE) */
|
60
|
-
{(lxb_char_t *) "\xe3\x83\x8e", 3, 0x30CE}, /* (KATAKANA LETTER NO) */
|
61
|
-
{(lxb_char_t *) "\xe3\x83\x8f", 3, 0x30CF}, /* (KATAKANA LETTER HA) */
|
62
|
-
{(lxb_char_t *) "\xe3\x83\x92", 3, 0x30D2}, /* (KATAKANA LETTER HI) */
|
63
|
-
{(lxb_char_t *) "\xe3\x83\x95", 3, 0x30D5}, /* (KATAKANA LETTER HU) */
|
64
|
-
{(lxb_char_t *) "\xe3\x83\x98", 3, 0x30D8}, /* (KATAKANA LETTER HE) */
|
65
|
-
{(lxb_char_t *) "\xe3\x83\x9b", 3, 0x30DB}, /* (KATAKANA LETTER HO) */
|
66
|
-
{(lxb_char_t *) "\xe3\x83\x9e", 3, 0x30DE}, /* (KATAKANA LETTER MA) */
|
67
|
-
{(lxb_char_t *) "\xe3\x83\x9f", 3, 0x30DF}, /* (KATAKANA LETTER MI) */
|
68
|
-
{(lxb_char_t *) "\xe3\x83\xa0", 3, 0x30E0}, /* (KATAKANA LETTER MU) */
|
69
|
-
{(lxb_char_t *) "\xe3\x83\xa1", 3, 0x30E1}, /* (KATAKANA LETTER ME) */
|
70
|
-
{(lxb_char_t *) "\xe3\x83\xa2", 3, 0x30E2}, /* (KATAKANA LETTER MO) */
|
71
|
-
{(lxb_char_t *) "\xe3\x83\xa4", 3, 0x30E4}, /* (KATAKANA LETTER YA) */
|
72
|
-
{(lxb_char_t *) "\xe3\x83\xa6", 3, 0x30E6}, /* (KATAKANA LETTER YU) */
|
73
|
-
{(lxb_char_t *) "\xe3\x83\xa8", 3, 0x30E8}, /* (KATAKANA LETTER YO) */
|
74
|
-
{(lxb_char_t *) "\xe3\x83\xa9", 3, 0x30E9}, /* (KATAKANA LETTER RA) */
|
75
|
-
{(lxb_char_t *) "\xe3\x83\xaa", 3, 0x30EA}, /* (KATAKANA LETTER RI) */
|
76
|
-
{(lxb_char_t *) "\xe3\x83\xab", 3, 0x30EB}, /* (KATAKANA LETTER RU) */
|
77
|
-
{(lxb_char_t *) "\xe3\x83\xac", 3, 0x30EC}, /* (KATAKANA LETTER RE) */
|
78
|
-
{(lxb_char_t *) "\xe3\x83\xad", 3, 0x30ED}, /* (KATAKANA LETTER RO) */
|
79
|
-
{(lxb_char_t *) "\xe3\x83\xaf", 3, 0x30EF}, /* (KATAKANA LETTER WA) */
|
80
|
-
{(lxb_char_t *) "\xe3\x83\xb3", 3, 0x30F3}, /* (KATAKANA LETTER N) */
|
81
|
-
{(lxb_char_t *) "\xe3\x82\x9b", 3, 0x309B}, /* (KATAKANA-HIRAGANA VOICED SOUND MARK) */
|
82
|
-
{(lxb_char_t *) "\xe3\x82\x9c", 3, 0x309C}, /* (KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK) */
|
83
|
-
};
|
84
|
-
|
85
|
-
/* Table size: 52; Max deep: 2 */
|
86
|
-
LXB_API const lexbor_shs_hash_t lxb_encoding_multi_hash_iso_2022_jp_katakana[72] =
|
87
|
-
{
|
88
|
-
{0, NULL, 0},{0, NULL, 0},
|
89
|
-
{12481, (void *) 32, 0},
|
90
|
-
{0, NULL, 0},
|
91
|
-
{12483, (void *) 14, 0},
|
92
|
-
{12484, (void *) 33, 0},
|
93
|
-
{0, NULL, 0},
|
94
|
-
{12486, (void *) 34, 0},
|
95
|
-
{12539, (void *) 4, 0},
|
96
|
-
{12540, (void *) 15, 58},
|
97
|
-
{0, NULL, 0},
|
98
|
-
{12490, (void *) 36, 0},
|
99
|
-
{12491, (void *) 37, 0},
|
100
|
-
{12492, (void *) 38, 0},
|
101
|
-
{12493, (void *) 39, 0},
|
102
|
-
{12494, (void *) 40, 0},
|
103
|
-
{12495, (void *) 41, 71},
|
104
|
-
{12444, (void *) 62, 0},
|
105
|
-
{12289, (void *) 3, 0},
|
106
|
-
{12290, (void *) 0, 59},
|
107
|
-
{0, NULL, 0},
|
108
|
-
{0, NULL, 0},
|
109
|
-
{12449, (void *) 6, 60},
|
110
|
-
{12450, (void *) 16, 0},
|
111
|
-
{12451, (void *) 7, 0},
|
112
|
-
{12452, (void *) 17, 61},
|
113
|
-
{12453, (void *) 8, 0},
|
114
|
-
{12454, (void *) 18, 0},
|
115
|
-
{12455, (void *) 9, 62},
|
116
|
-
{12300, (void *) 1, 54},
|
117
|
-
{12301, (void *) 2, 53},
|
118
|
-
{12458, (void *) 20, 63},
|
119
|
-
{12459, (void *) 21, 64},
|
120
|
-
{12512, (void *) 48, 0},
|
121
|
-
{12461, (void *) 22, 65},
|
122
|
-
{12514, (void *) 50, 0},
|
123
|
-
{12515, (void *) 11, 55},
|
124
|
-
{12516, (void *) 51, 0},
|
125
|
-
{12517, (void *) 12, 56},
|
126
|
-
{12518, (void *) 52, 0},
|
127
|
-
{12519, (void *) 13, 57},
|
128
|
-
{12520, (void *) 53, 0},
|
129
|
-
{12469, (void *) 26, 66},
|
130
|
-
{12522, (void *) 55, 0},
|
131
|
-
{12471, (void *) 27, 67},
|
132
|
-
{12524, (void *) 57, 0},
|
133
|
-
{12473, (void *) 28, 68},
|
134
|
-
{0, NULL, 0},
|
135
|
-
{12475, (void *) 29, 69},
|
136
|
-
{0, NULL, 0},
|
137
|
-
{12477, (void *) 30, 0},
|
138
|
-
{12530, (void *) 5, 0},
|
139
|
-
{12479, (void *) 31, 70},
|
140
|
-
{12457, (void *) 10, 0},
|
141
|
-
{12456, (void *) 19, 0},
|
142
|
-
{12463, (void *) 23, 0},
|
143
|
-
{12465, (void *) 24, 0},
|
144
|
-
{12467, (void *) 25, 0},
|
145
|
-
{12488, (void *) 35, 0},
|
146
|
-
{12498, (void *) 42, 0},
|
147
|
-
{12501, (void *) 43, 0},
|
148
|
-
{12504, (void *) 44, 0},
|
149
|
-
{12507, (void *) 45, 0},
|
150
|
-
{12510, (void *) 46, 0},
|
151
|
-
{12511, (void *) 47, 0},
|
152
|
-
{12513, (void *) 49, 0},
|
153
|
-
{12521, (void *) 54, 0},
|
154
|
-
{12523, (void *) 56, 0},
|
155
|
-
{12525, (void *) 58, 0},
|
156
|
-
{12527, (void *) 59, 0},
|
157
|
-
{12531, (void *) 60, 0},
|
158
|
-
{12443, (void *) 61, 0}
|
159
|
-
};
|