mailinfo: assume input is latin-1 on the header as we do for the body
When the input mbox does not identify what encoding it is in, and already have RFC2047 stripped away, we cannot tell what encoding the header text is in. For body text, when the message does not say what charset it is in, we fall back to assume latin-1 input when converting to utf8. This should be done consistently to the header as well. Signed-off-by: Junio C Hamano <junkio@cox.net>
Junio C Hamano committed
Jul 5, 2006 at 14:17 UTC
b75bf2c3f08b70a3e4850867290a8c215d2c1abf
1 file changed
+24
-8
builtin-mailinfo.c
+24
-8
@@ -348,7 +348,7 @@ static void cleanup_space(char *buf)
348
}
349
}
350
351
-static void decode_header_bq(char *it);
351
+static void decode_header(char *it);
352
typedef int (*header_fn_t)(char *);
353
struct header_def {
354
const char *name;
@@ -371,7 +371,7 @@ static void check_header(char *line, struct header_def *header)
371
/* Unwrap inline B and Q encoding, and optionally
372
* normalize the meta information to utf8.
373
*/
374
- decode_header_bq(line + len + 2);
374
+ decode_header(line + len + 2);
375
header[i].func(line + len + 2);
376
break;
377
}
@@ -566,16 +566,19 @@ static void convert_to_utf8(char *line, char *charset)
566
#endif
567
}
568
569
-static void decode_header_bq(char *it)
569
+static int decode_header_bq(char *it)
570
{
571
char *in, *out, *ep, *cp, *sp;
572
char outbuf[1000];
573
+ int rfc2047 = 0;
574
575
in = it;
576
out = outbuf;
577
while ((ep = strstr(in, "=?")) != NULL) {
578
int sz, encoding;
579
char charset_q[256], piecebuf[256];
580
+ rfc2047 = 1;
581
+
582
if (in != ep) {
583
sz = ep - in;
584
memcpy(out, in, sz);
@@ -589,19 +592,19 @@ static void decode_header_bq(char *it)
592
ep += 2;
593
cp = strchr(ep, '?');
594
if (!cp)
592
- return; /* no munging */
595
+ return rfc2047; /* no munging */
596
for (sp = ep; sp < cp; sp++)
597
charset_q[sp - ep] = tolower(*sp);
598
charset_q[cp - ep] = 0;
599
encoding = cp[1];
600
if (!encoding || cp[2] != '?')
598
- return; /* no munging */
601
+ return rfc2047; /* no munging */
602
ep = strstr(cp + 3, "?=");
603
if (!ep)
601
- return; /* no munging */
604
+ return rfc2047; /* no munging */
605
switch (tolower(encoding)) {
606
default:
604
- return; /* no munging */
607
+ return rfc2047; /* no munging */
608
case 'b':
609
sz = decode_b_segment(cp + 3, piecebuf, ep);
610
break;
@@ -610,7 +613,7 @@ static void decode_header_bq(char *it)
613
break;
614
}
615
if (sz < 0)
613
- return;
616
+ return rfc2047;
617
if (metainfo_charset)
618
convert_to_utf8(piecebuf, charset_q);
619
strcpy(out, piecebuf);
@@ -619,6 +622,19 @@ static void decode_header_bq(char *it)
622
}
623
strcpy(out, in);
624
strcpy(it, outbuf);
625
+ return rfc2047;
626
+}
627
+
628
+static void decode_header(char *it)
629
+{
630
+
631
+ if (decode_header_bq(it))
632
+ return;
633
+ /* otherwise "it" is a straight copy of the input.
634
+ * This can be binary guck but there is no charset specified.
635
+ */
636
+ if (metainfo_charset)
637
+ convert_to_utf8(it, "");
638
}
639
640
static void decode_transfer_encoding(char *line)