fix two encoding bugs

reencode() takes three arguments in the order (txt, from, to), opposed to
reencode_string, which will, like iconv, handle the arguments with from
and to swapped. Fix that (this makes reencode more intuitive).
If src and dst encoding are equivalent, don't do any encoding.

If no special encoding parameter is found within the commit, assume
UTF-8 and explicitly convert to PAGE_ENCODING. The change to reencode()
mentioned above avoids re-encoding a UTF-8 string to UTF-8, for example.

Signed-off-by: Julius Plenz <plenz@cis.fu-berlin.de>
Signed-off-by: Lars Hjemli <hjemli@gmail.com>

1 files changed, 15 insertions, 9 deletions

diff --git a/parsing.c b/parsing.c
index f37c49d..c9e4350 100644
--- a/parsing.c
+++ b/parsing.c
@@ -61,187 +61,193 @@ char *substr(const char *head, const char *tail)
 	buf[tail - head] = '\0';
 	return buf;
 }
 
 char *parse_user(char *t, char **name, char **email, unsigned long *date)
 {
 	char *p = t;
 	int mode = 1;
 
 	while (p && *p) {
 		if (mode == 1 && *p == '<') {
 			*name = substr(t, p - 1);
 			t = p;
 			mode++;
 		} else if (mode == 1 && *p == '\n') {
 			*name = substr(t, p);
 			p++;
 			break;
 		} else if (mode == 2 && *p == '>') {
 			*email = substr(t, p + 1);
 			t = p;
 			mode++;
 		} else if (mode == 2 && *p == '\n') {
 			*email = substr(t, p);
 			p++;
 			break;
 		} else if (mode == 3 && isdigit(*p)) {
 			*date = atol(p);
 			mode++;
 		} else if (*p == '\n') {
 			p++;
 			break;
 		}
 		p++;
 	}
 	return p;
 }
 
 #ifdef NO_ICONV
 #define reencode(a, b, c)
 #else
 const char *reencode(char **txt, const char *src_enc, const char *dst_enc)
 {
 	char *tmp;
 
 	if (!txt || !*txt || !src_enc || !dst_enc)
 		return *txt;
 
-	tmp = reencode_string(*txt, src_enc, dst_enc);
+	/* no encoding needed if src_enc equals dst_enc */
+	if(!strcasecmp(src_enc, dst_enc))
+		return *txt;
+
+	tmp = reencode_string(*txt, dst_enc, src_enc);
 	if (tmp) {
 		free(*txt);
 		*txt = tmp;
 	}
 	return *txt;
 }
 #endif
 
 struct commitinfo *cgit_parse_commit(struct commit *commit)
 {
 	struct commitinfo *ret;
 	char *p = commit->buffer, *t = commit->buffer;
 
 	ret = xmalloc(sizeof(*ret));
 	ret->commit = commit;
 	ret->author = NULL;
 	ret->author_email = NULL;
 	ret->committer = NULL;
 	ret->committer_email = NULL;
 	ret->subject = NULL;
 	ret->msg = NULL;
 	ret->msg_encoding = NULL;
 
 	if (p == NULL)
 		return ret;
 
 	if (strncmp(p, "tree ", 5))
 		die("Bad commit: %s", sha1_to_hex(commit->object.sha1));
 	else
 		p += 46; // "tree " + hex[40] + "\n"
 
 	while (!strncmp(p, "parent ", 7))
 		p += 48; // "parent " + hex[40] + "\n"
 
 	if (p && !strncmp(p, "author ", 7)) {
 		p = parse_user(p + 7, &ret->author, &ret->author_email,
 			&ret->author_date);
 	}
 
 	if (p && !strncmp(p, "committer ", 9)) {
 		p = parse_user(p + 9, &ret->committer, &ret->committer_email,
 			&ret->committer_date);
 	}
 
 	if (p && !strncmp(p, "encoding ", 9)) {
 		p += 9;
 		t = strchr(p, '\n');
 		if (t) {
 			ret->msg_encoding = substr(p, t + 1);
 			p = t + 1;
 		}
 	}
 
+	/* if no special encoding is found, assume UTF-8 */
+	if(!ret->msg_encoding)
+		ret->msg_encoding = xstrdup("UTF-8");
+
 	// skip unknown header fields
 	while (p && *p && (*p != '\n')) {
 		p = strchr(p, '\n');
 		if (p)
 			p++;
 	}
 
 	// skip empty lines between headers and message
 	while (p && *p == '\n')
 		p++;
 
 	if (!p)
 		return ret;
 
 	t = strchr(p, '\n');
 	if (t) {
 		ret->subject = substr(p, t);
 		p = t + 1;
 
 		while (p && *p == '\n') {
 			p = strchr(p, '\n');
 			if (p)
 				p++;
 		}
 		if (p)
 			ret->msg = xstrdup(p);
 	} else
 		ret->subject = xstrdup(p);
 
-	if (ret->msg_encoding) {
-		reencode(&ret->author, PAGE_ENCODING, ret->msg_encoding);
-		reencode(&ret->author_email, PAGE_ENCODING, ret->msg_encoding);
-		reencode(&ret->committer, PAGE_ENCODING, ret->msg_encoding);
-		reencode(&ret->committer_email, PAGE_ENCODING, ret->msg_encoding);
-		reencode(&ret->subject, PAGE_ENCODING, ret->msg_encoding);
-		reencode(&ret->msg, PAGE_ENCODING, ret->msg_encoding);
-	}
+	reencode(&ret->author, ret->msg_encoding, PAGE_ENCODING);
+	reencode(&ret->author_email, ret->msg_encoding, PAGE_ENCODING);
+	reencode(&ret->committer, ret->msg_encoding, PAGE_ENCODING);
+	reencode(&ret->committer_email, ret->msg_encoding, PAGE_ENCODING);
+	reencode(&ret->subject, ret->msg_encoding, PAGE_ENCODING);
+	reencode(&ret->msg, ret->msg_encoding, PAGE_ENCODING);
 
 	return ret;
 }
 
 
 struct taginfo *cgit_parse_tag(struct tag *tag)
 {
 	void *data;
 	enum object_type type;
 	unsigned long size;
 	char *p;
 	struct taginfo *ret;
 
 	data = read_sha1_file(tag->object.sha1, &type, &size);
 	if (!data || type != OBJ_TAG) {
 		free(data);
 		return 0;
 	}
 
 	ret = xmalloc(sizeof(*ret));
 	ret->tagger = NULL;
 	ret->tagger_email = NULL;
 	ret->tagger_date = 0;
 	ret->msg = NULL;
 
 	p = data;
 
 	while (p && *p) {
 		if (*p == '\n')
 			break;
 
 		if (!strncmp(p, "tagger ", 7)) {
 			p = parse_user(p + 7, &ret->tagger, &ret->tagger_email,
 				&ret->tagger_date);
 		} else {
 			p = strchr(p, '\n');
 			if (p)
 				p++;
 		}
 	}
 
 	// skip empty lines between headers and message
 	while (p && *p == '\n')
 		p++;
 
 	if (p && *p)
 		ret->msg = xstrdup(p);
 	free(data);