summaryrefslogtreecommitdiff
path: root/transcode_data_japanese.c
diff options
context:
space:
mode:
Diffstat (limited to 'transcode_data_japanese.c')
-rw-r--r--transcode_data_japanese.c207
1 files changed, 206 insertions, 1 deletions
diff --git a/transcode_data_japanese.c b/transcode_data_japanese.c
index fc7243186d9..223d1586e34 100644
--- a/transcode_data_japanese.c
+++ b/transcode_data_japanese.c
@@ -23618,4 +23618,209 @@ rb_to_EUC_JP = {
to_EUC_JP_infos
};
-/* Footprint (bytes): gross: 212680, saved: 50764, net: 161916 */
+#define ISO_2022_ENCODING(escseq, byte) ((escseq<<8)|byte)
+enum ISO_2022_ESCSEQ {
+ ISO_2022_CZD = '!',
+ ISO_2022_C1D = '"',
+ ISO_2022_GZD4 = '(',
+ ISO_2022_G1D4 = ')',
+ ISO_2022_G2D4 = '*',
+ ISO_2022_G3D4 = '+',
+ ISO_2022_G1D6 = '-',
+ ISO_2022_G2D6 = '.',
+ ISO_2022_G3D6 = '/',
+ ISO_2022_GZDM4 = ISO_2022_ENCODING('$','('),
+ ISO_2022_G1DM4 = ISO_2022_ENCODING('$',')'),
+ ISO_2022_G2DM4 = ISO_2022_ENCODING('$','*'),
+ ISO_2022_G3DM4 = ISO_2022_ENCODING('$','+'),
+ ISO_2022_G1DM6 = ISO_2022_ENCODING('$','-'),
+ ISO_2022_G2DM6 = ISO_2022_ENCODING('$','.'),
+ ISO_2022_G3DM6 = ISO_2022_ENCODING('$','/'),
+ ISO_2022_DOCS = ISO_2022_ENCODING('%','I'),
+ ISO_2022_IRR = '&'
+};
+
+
+#define ISO_2022_GZ_ASCII ISO_2022_ENCODING(ISO_2022_GZD4, 'B')
+#define ISO_2022_GZ_JIS_X_0201_Katakana ISO_2022_ENCODING(ISO_2022_GZD4, 'I')
+#define ISO_2022_GZ_JIS_X_0201_Roman ISO_2022_ENCODING(ISO_2022_GZD4, 'J')
+#define ISO_2022_GZ_JIS_C_6226_1978 ISO_2022_ENCODING(ISO_2022_GZDM4,'@')
+#define ISO_2022_GZ_JIS_X_0208_1983 ISO_2022_ENCODING(ISO_2022_GZDM4,'B')
+#define ISO_2022_GZ_JIS_X_0212_1990 ISO_2022_ENCODING(ISO_2022_GZDM4,'D')
+#define ISO_2022_GZ_JIS_X_0213_2000_1 ISO_2022_ENCODING(ISO_2022_GZDM4,'O')
+#define ISO_2022_GZ_JIS_X_0213_2000_2 ISO_2022_ENCODING(ISO_2022_GZDM4,'P')
+#define ISO_2022_GZ_JIS_X_0213_2004_1 ISO_2022_ENCODING(ISO_2022_GZDM4,'Q')
+
+static int
+get_iso_2022_mode(char **in_pos)
+{
+ int new_mode;
+ char *in_p = *in_pos;
+ switch (*in_p++)
+ {
+ case '(':
+ switch (*in_p++)
+ {
+ case 'B': case 'I': case 'J':
+ new_mode = ISO_2022_ENCODING(ISO_2022_GZD4, *(in_p-1));
+ break;
+ default:
+ rb_raise(rb_eRuntimeError /*change exception*/, "this mode is not supported (ESC ( %c)", *(in_p-1));
+ break;
+ }
+ break;
+ case '$':
+ switch (*in_p++)
+ {
+ case '@': case 'A': case 'B':
+ new_mode = ISO_2022_ENCODING(ISO_2022_GZDM4, *(in_p-1));
+ break;
+ case '(':
+ switch (*in_p++)
+ {
+ case 'D': case 'O': case 'P': case 'Q':
+ new_mode = ISO_2022_ENCODING(ISO_2022_GZDM4, *(in_p-1));
+ break;
+ default:
+ rb_raise(rb_eRuntimeError /*change exception*/, "this mode is not supported (ESC $ ( %c)", *(in_p-1));
+ break;
+ }
+ break;
+ default:
+ rb_raise(rb_eRuntimeError /*change exception*/, "this mode is not supported (ESC $ %c)", *(in_p-1));
+ break;
+ }
+ break;
+ default:
+ rb_raise(rb_eRuntimeError /*change exception*/, "this mode is not supported (ESC %c)", *(in_p-1));
+ break;
+ }
+ *in_pos = in_p;
+ return new_mode;
+}
+
+void
+from_iso_2022_jp_transcoder_preprocessor(char **in_pos, char **out_pos,
+ char *in_stop, char *out_stop,
+ transcoder *my_transcoder,
+ transcoding *my_transcoding)
+{
+ char *in_p = *in_pos, *out_p = *out_pos;
+ int cur_mode = ISO_2022_GZ_ASCII;
+ unsigned char c1;
+ char *out_s = out_stop - my_transcoder->max_output + 1;
+ while (in_p < in_stop) {
+ if (out_p >= out_s) {
+ int len = (out_p - *out_pos);
+ int new_len = (len + my_transcoder->max_output) * 2;
+ *out_pos = (*my_transcoding->flush_func)(my_transcoding, len, new_len);
+ out_p = *out_pos + len;
+ out_s = *out_pos + new_len - my_transcoder->max_output;
+ }
+ c1 = *in_p++;
+ if (c1 == 0x1B) {
+ cur_mode = get_iso_2022_mode(&in_p);
+ } else if (c1 == 0x1E || c1 == 0x1F) {
+ /* SHIFT */
+ rb_raise(rb_eRuntimeError /*change exception*/, "shift is not supported");
+ } else if (c1 >= 0x80) {
+ rb_raise(rb_eRuntimeError /*change exception*/, "illegal byte sequence");
+ } else {
+ switch (cur_mode) {
+ case ISO_2022_GZ_ASCII:
+ case ISO_2022_GZ_JIS_X_0201_Roman:
+ *out_p++ = c1;
+ break;
+ case ISO_2022_GZ_JIS_X_0201_Katakana:
+ *out_p++ = 0x8E;
+ *out_p++ = c1 | 0x80;
+ break;
+ case ISO_2022_GZ_JIS_X_0212_1990:
+ *out_p++ = 0x8F;
+ case ISO_2022_GZ_JIS_C_6226_1978:
+ case ISO_2022_GZ_JIS_X_0208_1983:
+ *out_p++ = c1 | 0x80;
+ *out_p++ = *in_p++ | 0x80;
+ break;
+ }
+ }
+ }
+ /* cleanup */
+ *in_pos = in_p;
+ *out_pos = out_p;
+}
+
+static int
+select_iso_2022_mode(char **out_pos, int new_mode)
+{
+ char *out_p = *out_pos;
+ *out_p++ = '\e';
+ switch (new_mode>>8)
+ {
+ case ISO_2022_GZD4:
+ *out_p++ = new_mode >> 8;
+ *out_p++ = new_mode & 0x7F;
+ break;
+ case ISO_2022_GZDM4:
+ *out_p++ = new_mode >> 16;
+ if ((new_mode & 0x7F) != '@' &&
+ (new_mode & 0x7F) != 'A' &&
+ (new_mode & 0x7F) != 'B')
+ {
+ *out_p++ = (new_mode>>8) & 0x7F;
+ }
+ *out_p++ = new_mode & 0x7F;
+ break;
+ default:
+ rb_raise(rb_eRuntimeError /*change exception*/, "this mode is not supported.");
+ break;
+ }
+ *out_pos = out_p;
+ return new_mode;
+}
+
+void
+to_iso_2022_jp_transcoder_postprocessor(char **in_pos, char **out_pos,
+ char *in_stop, char *out_stop,
+ transcoder *my_transcoder,
+ transcoding *my_transcoding)
+{
+ char *in_p = *in_pos, *out_p = *out_pos;
+ int cur_mode = ISO_2022_GZ_ASCII, new_mode = 0;
+ unsigned char next_byte;
+ char *out_s = out_stop - my_transcoder->max_output + 1;
+ while (in_p < in_stop) {
+ if (out_p >= out_s) {
+ int len = (out_p - *out_pos);
+ int new_len = (len + my_transcoder->max_output) * 2;
+ *out_pos = (*my_transcoding->flush_func)(my_transcoding, len, new_len);
+ out_p = *out_pos + len;
+ out_s = *out_pos + new_len - my_transcoder->max_output;
+ }
+ next_byte = *in_p++;
+ if (next_byte < 0x80) {
+ new_mode = ISO_2022_GZ_ASCII;
+ } else if (next_byte == 0x8E) {
+ new_mode = ISO_2022_GZ_JIS_X_0201_Katakana;
+ next_byte = *in_p++;
+ } else if (next_byte == 0x8F) {
+ new_mode = ISO_2022_GZ_JIS_X_0212_1990;
+ next_byte = *in_p++;
+ } else {
+ new_mode = ISO_2022_GZ_JIS_X_0208_1983;
+ }
+ if (cur_mode != new_mode)
+ cur_mode = select_iso_2022_mode(&out_p, new_mode);
+ if (cur_mode < 0xFFFF) {
+ *out_p++ = next_byte & 0x7F;
+ } else {
+ *out_p++ = next_byte & 0x7F;
+ *out_p++ = *in_p++ & 0x7F;
+ }
+ }
+ if (cur_mode != ISO_2022_GZ_ASCII)
+ cur_mode = select_iso_2022_mode(&out_p, ISO_2022_GZ_ASCII);
+ /* cleanup */
+ *in_pos = in_p;
+ *out_pos = out_p;
+}