1 file changed, 43 insertions, 33 deletions
diff --git a/source/parsing.c b/source/parsing.c
index 71ecdb7..f684241 100644
--- a/source/parsing.c
+++ b/source/parsing.c
@@ -4,7 +4,8 @@
  * the request path settles which repository and which page the request works
  * on. Commit and tag objects arrive as header lines, a blank line, and then
  * the message, so the readers here walk the headers, copy out the fields the
- * pages need, and re-encode the message into the page encoding.
+ * pages need, and re-encode the message into the page encoding. The records
+ * they return are freed here too.
  */
 
 #define USE_THE_REPOSITORY_VARIABLE
@@ -15,22 +16,6 @@
 
 #include <mailmap.h>
 
-static char *substr(const char *start, const char *end)
-{
-	size_t len;
-	char *buf;
-
-	if (end < start)
-		return xstrdup("");
-	// start points into the object buffer, so strlcpy would measure the
-	// whole rest of the object to copy a name off the front of it.
-	len = end - start;
-	buf = xmalloc(len + 1);
-	memcpy(buf, start, len);
-	buf[len] = '\0';
-	return buf;
-}
-
 // The repository's mailmap, read once per request and applied to every ident a
 // page shows. Only the blob at HEAD is read, the way git reads a bare
 // repository, so a repository cannot point the reader at a file on the server.
@@ -112,22 +97,21 @@ static int end_of_header(const char *p)
  * not UTF-8 has its stray bytes replaced, and a page declared UTF-8 never
  * carries any.
  */
-static const char *reencode(char **text, const char *from, const char *to)
+static void reencode(char **text, const char *encoding)
 {
 	char *converted;
 
-	if (!*text || !from || !to)
-		return *text;
+	if (!*text)
+		return;
 
-	if (strcasecmp(from, to)) {
-		converted = reencode_string(*text, to, from);
+	if (strcasecmp(encoding, PAGE_ENCODING)) {
+		converted = reencode_string(*text, PAGE_ENCODING, encoding);
 		if (converted) {
 			free(*text);
 			*text = converted;
 		}
 	}
 	cgit_utf8_sanitize(*text);
-	return *text;
 }
 
 /*
@@ -182,6 +166,7 @@ struct commitinfo *cgit_parse_commit(struct commit *commit)
 	struct commitinfo *info;
 	const char *p = repo_get_commit_buffer(the_repository, commit, NULL);
 	const char *eol;
+	char *encoding = NULL;
 
 	info = xcalloc(1, sizeof(struct commitinfo));
 	info->commit = commit;
@@ -210,15 +195,15 @@ struct commitinfo *cgit_parse_commit(struct commit *commit)
 	if (p && skip_prefix(p, "encoding ", &p)) {
 		eol = strchr(p, '\n');
 		if (eol) {
-			info->msg_encoding = substr(p, eol);
+			encoding = xmemdupz(p, eol - p);
 			p = eol + 1;
 		}
 	}
 
 	// Git only writes the header when the message is in something other
 	// than UTF-8, so its absence means UTF-8.
-	if (!info->msg_encoding)
-		info->msg_encoding = xstrdup("UTF-8");
+	if (!encoding)
+		encoding = xstrdup("UTF-8");
 
 	while (!end_of_header(p))
 		p = next_header_line(p);
@@ -227,7 +212,7 @@ struct commitinfo *cgit_parse_commit(struct commit *commit)
 
 	if (p) {
 		eol = strchrnul(p, '\n');
-		info->subject = substr(p, eol);
+		info->subject = xmemdupz(p, eol - p);
 		while (*eol == '\n')
 			eol++;
 		info->msg = xstrdup(eol);
@@ -238,16 +223,28 @@ struct commitinfo *cgit_parse_commit(struct commit *commit)
 		info->msg = xstrdup("");
 	}
 
-	reencode(&info->author, info->msg_encoding, PAGE_ENCODING);
-	reencode(&info->author_email, info->msg_encoding, PAGE_ENCODING);
-	reencode(&info->committer, info->msg_encoding, PAGE_ENCODING);
-	reencode(&info->committer_email, info->msg_encoding, PAGE_ENCODING);
-	reencode(&info->subject, info->msg_encoding, PAGE_ENCODING);
-	reencode(&info->msg, info->msg_encoding, PAGE_ENCODING);
+	reencode(&info->author, encoding);
+	reencode(&info->author_email, encoding);
+	reencode(&info->committer, encoding);
+	reencode(&info->committer_email, encoding);
+	reencode(&info->subject, encoding);
+	reencode(&info->msg, encoding);
+	free(encoding);
 
 	return info;
 }
 
+void cgit_free_commitinfo(struct commitinfo *info)
+{
+	free(info->author);
+	free(info->author_email);
+	free(info->committer);
+	free(info->committer_email);
+	free(info->subject);
+	free(info->msg);
+	free(info);
+}
+
 struct taginfo *cgit_parse_tag(struct tag *tag)
 {
 	void *data;
@@ -283,3 +280,16 @@ cleanup:
 	free(data);
 	return info;
 }
+
+void cgit_free_taginfo(struct taginfo *info)
+{
+	// NULL is accepted because cgit_parse_tag returns it for a tag object
+	// that cannot be read, and a ref left holding that still gets freed
+	// along with the rest of its list.
+	if (!info)
+		return;
+	free(info->tagger);
+	free(info->tagger_email);
+	free(info->msg);
+	free(info);
+}