Mercurial > emacs
changeset 36647:0a75ccbe42b2
(detect_coding_sjis): Do more rigid check.
(detect_coding_big5): Likewise.
(decode_coding_sjis_big5): Likewise.
(Fdetect_coding_region): Call detect_coding_system with tailing
anchor byte `\0' for more rigid detection.
(Fdetect_coding_string): Likewise.
author | Kenichi Handa <handa@m17n.org> |
---|---|
date | Thu, 08 Mar 2001 02:01:00 +0000 |
parents | 5c9e147d55d8 |
children | b3dfa003ef9b |
files | src/coding.c |
diffstat | 1 files changed, 31 insertions(+), 21 deletions(-) [+] |
line wrap: on
line diff
--- a/src/coding.c Thu Mar 08 01:49:22 2001 +0000 +++ b/src/coding.c Thu Mar 08 02:01:00 2001 +0000 @@ -2653,7 +2653,7 @@ --- CODE RANGE of SJIS --- (character set) (range) ASCII 0x00 .. 0x7F - KATAKANA-JISX0201 0xA0 .. 0xDF + KATAKANA-JISX0201 0xA1 .. 0xDF JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF (2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC ------------------------------- @@ -2728,15 +2728,14 @@ while (1) { ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep); - if (c >= 0x81) + if (c < 0x80) + continue; + if (c == 0x80 || c == 0xA0 || c > 0xEF) + return 0; + if (c <= 0x9F || c >= 0xE0) { - if (c <= 0x9F || (c >= 0xE0 && c <= 0xEF)) - { - ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep); - if (c < 0x40 || c == 0x7F || c > 0xFC) - return 0; - } - else if (c > 0xDF) + ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep); + if (c < 0x40 || c == 0x7F || c > 0xFC) return 0; } } @@ -2761,12 +2760,13 @@ while (1) { ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep); - if (c >= 0xA1) - { - ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep); - if (c < 0x40 || (c >= 0x7F && c <= 0xA0)) - return 0; - } + if (c < 0x80) + continue; + if (c < 0xA1 || c > 0xFE) + return 0; + ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep); + if (c < 0x40 || (c > 0x7F && c < 0xA1) || c > 0xFE) + return 0; } label_end_of_loop: return CODING_CATEGORY_MASK_BIG5; @@ -2944,9 +2944,9 @@ { if (sjis_p) { - if (c1 >= 0xF0) + if (c1 == 0x80 || c1 == 0xA0 || c1 > 0xEF) goto label_invalid_code; - if (c1 < 0xA0 || c1 >= 0xE0) + if (c1 <= 0x9F || c1 >= 0xE0) { /* SJIS -> JISX0208 */ ONE_MORE_BYTE (c2); @@ -2962,7 +2962,7 @@ else { /* BIG5 -> Big5 */ - if (c1 < 0xA1 || c1 > 0xFE) + if (c1 < 0xA0 || c1 > 0xFE) goto label_invalid_code; ONE_MORE_BYTE (c2); if (c2 < 0x40 || (c2 > 0x7E && c2 < 0xA1) || c2 > 0xFE) @@ -6217,6 +6217,7 @@ { int from, to; int from_byte, to_byte; + int include_anchor_byte = 0; CHECK_NUMBER_COERCE_MARKER (start, 0); CHECK_NUMBER_COERCE_MARKER (end, 1); @@ -6228,9 +6229,14 @@ if (from < GPT && to >= GPT) move_gap_both (to, to_byte); - + if (to == Z || (to == GPT && GAP_SIZE > 0)) + include_anchor_byte = 1; return detect_coding_system (BYTE_POS_ADDR (from_byte), - to_byte - from_byte, + /* "+ include_anchor_byteq" is to + include the anchor byte `\0'. With + this, code detectors can check if + tailing bytes are valid. */ + to_byte - from_byte + include_anchor_byte, !NILP (highest), !NILP (current_buffer ->enable_multibyte_characters)); @@ -6253,7 +6259,11 @@ CHECK_STRING (string, 0); return detect_coding_system (XSTRING (string)->data, - STRING_BYTES (XSTRING (string)), + /* "+ 1" is to include the anchor byte + `\0'. With this, code detectors can + check if tailing bytes are + valid. */ + STRING_BYTES (XSTRING (string)) + 1, !NILP (highest), STRING_MULTIBYTE (string)); }