Tera TermRevision: 10764
https://osdn.net/projects/ttssh2/scm/svn/commits/10764
Author: zmatsuo
Date: 2023-06-15 00:31:33 +0900 (Thu, 15 Jun 2023)
Log Message:
-----------
受信文字コードがUTF-8の時の不正な文字チェックを修正
- r10763のチェックが十分ではなかった
Modified Paths:
--------------
trunk/teraterm/teraterm/charset.c
-------------- next part --------------
Modified: trunk/teraterm/teraterm/charset.c
===================================================================
--- trunk/teraterm/teraterm/charset.c 2023-06-14 14:24:25 UTC (rev 10763)
+++ trunk/teraterm/teraterm/charset.c 2023-06-14 15:31:33 UTC (rev 10764)
@@ -536,19 +536,26 @@
}
}
-static void PutReplacementChr(VttermKanjiWork *w, const BYTE *ptr, size_t len)
+static void PutReplacementChr(VttermKanjiWork *w, const BYTE *ptr, size_t len, BOOL fallback)
{
const char32_t replacement_char = w->replacement_char;
int i;
for (i = 0; i < len; i++) {
BYTE c = *ptr++;
- if (c < 0x80) {
- // \x95s\x90\xB3\x82\xC8UTF-8\x95\xB6\x8E\x9A\x97\xF1\x82̂Ȃ\xA9\x82\xC90x80\x96\xA2\x96\x9E\x82\xAA\x82\xA0\x82\xEA\x82A
- // 1\x95\xB6\x8E\x9A\x82\xCCUTF-8\x95\xB6\x8E\x9A\x82Ƃ\xB5\x82Ă\xBB\x82̂܂ܕ\\x8E\xA6\x82\xB7\x82\xE9
- ParseASCII(c);
+ if (fallback) {
+ // fallback ISO8859-1
+ PutU32(c);
}
else {
- PutU32(replacement_char);
+ // fallback\x82\xB5\x82Ȃ\xA2
+ if (c < 0x80) {
+ // \x95s\x90\xB3\x82\xC8UTF-8\x95\xB6\x8E\x9A\x97\xF1\x82̂Ȃ\xA9\x82\xC90x80\x96\xA2\x96\x9E\x82\xAA\x82\xA0\x82\xEA\x82A
+ // 1\x95\xB6\x8E\x9A\x82\xCCUTF-8\x95\xB6\x8E\x9A\x82Ƃ\xB5\x82Ă\xBB\x82̂܂ܕ\\x8E\xA6\x82\xB7\x82\xE9
+ ParseASCII(c);
+ }
+ else {
+ PutU32(replacement_char);
+ }
}
}
}
@@ -572,7 +579,7 @@
}
if (b < 0x20) {
- PutReplacementChr(w, buf, count);
+ PutReplacementChr(w, buf, count, ts.FallbackToCP932);
count = 0;
ParseASCII(b);
return TRUE;
@@ -601,7 +608,7 @@
ParseASCII(b);
return TRUE;
}
- if ((b & 0x40) == 0x00 || b >= 0xf6 ) {
+ if ((b & 0x40) == 0x00 || b >= 0xf6) {
// UTF-8\x82\xC51byte\x82ɏo\x8C\xBB\x82\xB5\x82Ȃ\xA2\x83R\x81[\x83h\x82̂Ƃ\xAB
// 0x40 = 0b1011_1111, 0b10xx_xxxx\x82Ƃ\xA2\x82\xA4bit\x83p\x83^\x81[\x83\x93\x82ɂ͂Ȃ\xE7\x82Ȃ\xA2
// 0xf6 \x88ȏ\xE3\x82̂Ƃ\xAB U+10FFFF\x82\xE6\x82\xE8\x91傫\x82\xAD\x82Ȃ\xE9
@@ -623,7 +630,7 @@
else {
// fallback\x82\xB5\x82Ȃ\xA2, \x95s\x90\xB3\x82ȕ\xB6\x8E\x9A\x93\xFC\x97\xCD
buf[0] = b;
- PutReplacementChr(w, buf, 1);
+ PutReplacementChr(w, buf, 1, FALSE);
}
return TRUE;
}
@@ -644,14 +651,7 @@
}
}
if (code == 0){
- if (ts.FallbackToCP932) {
- // fallback ISO8859-1
- PutU32(buf[0]);
- }
- else {
- buf[1] = b;
- PutReplacementChr(w, buf, 1);
- }
+ PutReplacementChr(w, buf, 1, ts.FallbackToCP932);
count = 0;
goto recheck;
}
@@ -662,6 +662,13 @@
}
}
+ // 2byte\x88ȍ~\x90\xB3\x8F\xED?
+ if ((b & 0xc0) != 0x80) { // \x8F\xE3\x88\xCA2bit\x82\xAA 10 \x82\xA9?
+ PutReplacementChr(w, buf, count, ts.FallbackToCP932);
+ count = 0;
+ goto recheck;
+ }
+
// 2byte\x96ڈȍ~\x95ۑ\xB6
buf[count++] = b;
@@ -682,14 +689,7 @@
}
}
if (code == 0) {
- if (ts.FallbackToCP932) {
- // fallback ISO8859-1
- PutU32(buf[0]);
- PutU32(buf[1]);
- }
- else {
- PutReplacementChr(w, buf, 2);
- }
+ PutReplacementChr(w, buf, count - 1, ts.FallbackToCP932);
count = 0;
goto recheck;
} else {
@@ -717,15 +717,7 @@
}
}
if (code == 0) {
- if (ts.FallbackToCP932) {
- // fallback ISO8859-1
- PutU32(buf[0]);
- PutU32(buf[1]);
- PutU32(buf[2]);
- }
- else {
- PutReplacementChr(w, buf, 3);
- }
+ PutReplacementChr(w, buf, count - 1, ts.FallbackToCP932);
count = 0;
goto recheck;
} else {