mirror of
https://github.com/ruby/ruby.git
synced 2022-11-09 12:17:21 -05:00
6270ad5b7f
from rb_econv_stateless_encoding to apply stateless ASCII incompatible encodings such as UTF-16BE. * io.c (make_writeconv): use rb_econv_asciicompat_encoding. * transcode_data.h (rb_transcoder_asciicompat_type_t): renamed from rb_transcoder_stateful_type_t. (rb_transcoder): use rb_transcoder_asciicompat_type_t. * transcode.c: follow the type change. (asciicompat_encoding_i): renamed from stateless_encoding_i. (rb_econv_asciicompat_encoding): renamed from rb_econv_stateless_encoding. (econv_s_asciicompat_encoding): method renamed. * tool/transcode-tblgen.rb: follow the type change. * enc/trans/utf_16_32.trans: follow the type change. rb_from_UTF_16BE to UTF-8 is asciicompat_decoder. rb_from_UTF_16LE to UTF-8 is asciicompat_decoder. rb_from_UTF_32BE to UTF-8 is asciicompat_decoder. rb_from_UTF_32LE to UTF-8 is asciicompat_decoder. UTF-8 to rb_to_UTF_16BE is asciicompat_encoder. UTF-8 to rb_to_UTF_16LE is asciicompat_encoder. UTF-8 to rb_to_UTF_32BE is asciicompat_encoder. UTF-8 to rb_to_UTF_32LE is asciicompat_encoder. * enc/trans/newline.trans: follow the type change. universal newline decoder is asciicompat_converter. * enc/trans/escape.trans: follow the type change. * enc/trans/iso2022.trans: ditto. * enc/trans/japanese.trans: ditto. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@19249 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
98 lines
2.2 KiB
Text
98 lines
2.2 KiB
Text
#include "transcode_data.h"
|
|
|
|
<%
|
|
map = {}
|
|
map["{00-7f}"] = :nomap
|
|
map["{a1-fe}{a1-fe}"] = :func_so
|
|
map["8e{a1-df}"] = :func_so
|
|
map["8e{e0-fe}"] = :undef
|
|
map["8f{a1-fe}{a1-fe}"] = :undef
|
|
transcode_generate_node(ActionMap.parse(map), "eucjp2sjis")
|
|
|
|
map = {}
|
|
map["{00-7f}"] = :nomap
|
|
map["{81-9f,e0-ef}{40-7e,80-fc}"] = :func_so
|
|
map["{f0-fc}{40-7e,80-fc}"] = :undef
|
|
map["{a1-df}"] = :func_so
|
|
transcode_generate_node(ActionMap.parse(map), "sjis2eucjp")
|
|
%>
|
|
|
|
<%= transcode_generated_code %>
|
|
|
|
static int
|
|
fun_so_eucjp2sjis(void *statep, const unsigned char *s, size_t l, unsigned char *o)
|
|
{
|
|
if (s[0] == 0x8e) {
|
|
o[0] = s[1];
|
|
return 1;
|
|
}
|
|
else {
|
|
int h, m, l;
|
|
m = s[0] & 1;
|
|
h = (s[0]+m) >> 1;
|
|
h += s[0] < 0xdf ? 0x30 : 0x70;
|
|
l = s[1] - m * 94 - 3;
|
|
if (0x7f <= l)
|
|
l++;
|
|
o[0] = h;
|
|
o[1] = l;
|
|
return 2;
|
|
}
|
|
}
|
|
|
|
static int
|
|
fun_so_sjis2eucjp(void *statep, const unsigned char *s, size_t l, unsigned char *o)
|
|
{
|
|
if (l == 1) {
|
|
o[0] = '\x8e';
|
|
o[1] = s[0];
|
|
return 2;
|
|
}
|
|
else {
|
|
int h, l;
|
|
h = s[0];
|
|
l = s[1];
|
|
if (0xe0 <= h)
|
|
h -= 64;
|
|
l += l < 0x80 ? 0x61 : 0x60;
|
|
h = h * 2 - 0x61;
|
|
if (0xfe < l) {
|
|
l -= 94;
|
|
h += 1;
|
|
}
|
|
o[0] = h;
|
|
o[1] = l;
|
|
return 2;
|
|
}
|
|
}
|
|
|
|
static const rb_transcoder
|
|
rb_eucjp2sjis = {
|
|
"EUC-JP", "Shift_JIS", eucjp2sjis,
|
|
TRANSCODE_TABLE_INFO,
|
|
1, /* input_unit_length */
|
|
3, /* max_input */
|
|
2, /* max_output */
|
|
asciicompat_converter, /* asciicompat_type */
|
|
0, NULL, NULL, /* state_size, state_init, state_fini */
|
|
NULL, NULL, NULL, fun_so_eucjp2sjis
|
|
};
|
|
|
|
static const rb_transcoder
|
|
rb_sjis2eucjp = {
|
|
"Shift_JIS", "EUC-JP", sjis2eucjp,
|
|
TRANSCODE_TABLE_INFO,
|
|
1, /* input_unit_length */
|
|
2, /* max_input */
|
|
2, /* max_output */
|
|
asciicompat_converter, /* asciicompat_type */
|
|
0, NULL, NULL, /* state_size, state_init, state_fini */
|
|
NULL, NULL, NULL, fun_so_sjis2eucjp
|
|
};
|
|
|
|
void
|
|
Init_japanese(void)
|
|
{
|
|
rb_register_transcoder(&rb_eucjp2sjis);
|
|
rb_register_transcoder(&rb_sjis2eucjp);
|
|
}
|