From b75bf2c3f08b70a3e4850867290a8c215d2c1abf Mon Sep 17 00:00:00 2001
From: Junio C Hamano <junkio@cox.net>
Date: Wed, 5 Jul 2006 14:17:49 -0700
Subject: [PATCH] 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>
---
 builtin-mailinfo.c | 32 ++++++++++++++++++++++++--------
 1 file changed, 24 insertions(+), 8 deletions(-)

diff --git a/builtin-mailinfo.c b/builtin-mailinfo.c
index 3e40747cf..ac53f76f6 100644
--- a/builtin-mailinfo.c
+++ b/builtin-mailinfo.c
@@ -348,7 +348,7 @@ static void cleanup_space(char *buf)
 	}
 }
 
-static void decode_header_bq(char *it);
+static void decode_header(char *it);
 typedef int (*header_fn_t)(char *);
 struct header_def {
 	const char *name;
@@ -371,7 +371,7 @@ static void check_header(char *line, struct header_def *header)
 			/* Unwrap inline B and Q encoding, and optionally
 			 * normalize the meta information to utf8.
 			 */
-			decode_header_bq(line + len + 2);
+			decode_header(line + len + 2);
 			header[i].func(line + len + 2);
 			break;
 		}
@@ -566,16 +566,19 @@ static void convert_to_utf8(char *line, char *charset)
 #endif
 }
 
-static void decode_header_bq(char *it)
+static int decode_header_bq(char *it)
 {
 	char *in, *out, *ep, *cp, *sp;
 	char outbuf[1000];
+	int rfc2047 = 0;
 
 	in = it;
 	out = outbuf;
 	while ((ep = strstr(in, "=?")) != NULL) {
 		int sz, encoding;
 		char charset_q[256], piecebuf[256];
+		rfc2047 = 1;
+
 		if (in != ep) {
 			sz = ep - in;
 			memcpy(out, in, sz);
@@ -589,19 +592,19 @@ static void decode_header_bq(char *it)
 		ep += 2;
 		cp = strchr(ep, '?');
 		if (!cp)
-			return; /* no munging */
+			return rfc2047; /* no munging */
 		for (sp = ep; sp < cp; sp++)
 			charset_q[sp - ep] = tolower(*sp);
 		charset_q[cp - ep] = 0;
 		encoding = cp[1];
 		if (!encoding || cp[2] != '?')
-			return; /* no munging */
+			return rfc2047; /* no munging */
 		ep = strstr(cp + 3, "?=");
 		if (!ep)
-			return; /* no munging */
+			return rfc2047; /* no munging */
 		switch (tolower(encoding)) {
 		default:
-			return; /* no munging */
+			return rfc2047; /* no munging */
 		case 'b':
 			sz = decode_b_segment(cp + 3, piecebuf, ep);
 			break;
@@ -610,7 +613,7 @@ static void decode_header_bq(char *it)
 			break;
 		}
 		if (sz < 0)
-			return;
+			return rfc2047;
 		if (metainfo_charset)
 			convert_to_utf8(piecebuf, charset_q);
 		strcpy(out, piecebuf);
@@ -619,6 +622,19 @@ static void decode_header_bq(char *it)
 	}
 	strcpy(out, in);
 	strcpy(it, outbuf);
+	return rfc2047;
+}
+
+static void decode_header(char *it)
+{
+
+	if (decode_header_bq(it))
+		return;
+	/* otherwise "it" is a straight copy of the input.
+	 * This can be binary guck but there is no charset specified.
+	 */
+	if (metainfo_charset)
+		convert_to_utf8(it, "");
 }
 
 static void decode_transfer_encoding(char *line)
-- 
2.26.2