Simplify commit and tag parsing

* Use skip_prefix to avoid magic numbers in the code.
* Use xcalloc() instead of xmalloc(), followed by manual initialization.
* Split out line splitting.

Signed-off-by: Lukas Fleischer <cgit@cryptocrack.de>
This commit is contained in:
Lukas Fleischer 2015-03-03 13:00:07 +01:00 committed by Jason A. Donenfeld
parent 911d574250
commit 936295c4e4

110
parsing.c
View File

@ -118,45 +118,50 @@ static const char *reencode(char **txt, const char *src_enc, const char *dst_enc
} }
#endif #endif
static const char *next_header_line(const char *p)
{
p = strchr(p, '\n');
if (!p)
return NULL;
return p + 1;
}
static int end_of_header(const char *p)
{
return !p || (*p == '\n');
}
struct commitinfo *cgit_parse_commit(struct commit *commit) struct commitinfo *cgit_parse_commit(struct commit *commit)
{ {
const int sha1hex_len = 40;
struct commitinfo *ret; struct commitinfo *ret;
const char *p = get_cached_commit_buffer(commit, NULL); const char *p = get_cached_commit_buffer(commit, NULL);
const char *t; const char *t;
ret = xmalloc(sizeof(*ret)); ret = xcalloc(1, sizeof(struct commitinfo));
ret->commit = commit; 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) if (!p)
return ret; return ret;
if (!starts_with(p, "tree ")) if (!skip_prefix(p, "tree ", &p))
die("Bad commit: %s", sha1_to_hex(commit->object.sha1)); die("Bad commit: %s", sha1_to_hex(commit->object.sha1));
else p += sha1hex_len + 1;
p += 46; // "tree " + hex[40] + "\n"
while (starts_with(p, "parent ")) while (skip_prefix(p, "parent ", &p))
p += 48; // "parent " + hex[40] + "\n" p += sha1hex_len + 1;
if (p && starts_with(p, "author ")) { if (p && skip_prefix(p, "author ", &p)) {
p = parse_user(p + 7, &ret->author, &ret->author_email, p = parse_user(p, &ret->author, &ret->author_email,
&ret->author_date); &ret->author_date);
} }
if (p && starts_with(p, "committer ")) { if (p && skip_prefix(p, "committer ", &p)) {
p = parse_user(p + 10, &ret->committer, &ret->committer_email, p = parse_user(p, &ret->committer, &ret->committer_email,
&ret->committer_date); &ret->committer_date);
} }
if (p && starts_with(p, "encoding ")) { if (p && skip_prefix(p, "encoding ", &p)) {
p += 9;
t = strchr(p, '\n'); t = strchr(p, '\n');
if (t) { if (t) {
ret->msg_encoding = substr(p, t + 1); ret->msg_encoding = substr(p, t + 1);
@ -164,38 +169,21 @@ struct commitinfo *cgit_parse_commit(struct commit *commit)
} }
} }
/* if no special encoding is found, assume UTF-8 */
if (!ret->msg_encoding) if (!ret->msg_encoding)
ret->msg_encoding = xstrdup("UTF-8"); ret->msg_encoding = xstrdup("UTF-8");
// skip unknown header fields while (!end_of_header(p))
while (p && *p && (*p != '\n')) { p = next_header_line(p);
p = strchr(p, '\n');
if (p)
p++;
}
// skip empty lines between headers and message
while (p && *p == '\n') while (p && *p == '\n')
p++; p++;
if (!p) if (!p)
return ret; return ret;
t = strchr(p, '\n'); t = strchrnul(p, '\n');
if (t) {
ret->subject = substr(p, t); ret->subject = substr(p, t);
p = t + 1; while (*t == '\n')
t++;
while (p && *p == '\n') { ret->msg = xstrdup(t);
p = strchr(p, '\n');
if (p)
p++;
}
if (p)
ret->msg = xstrdup(p);
} else
ret->subject = xstrdup(p);
reencode(&ret->author, ret->msg_encoding, PAGE_ENCODING); reencode(&ret->author, ret->msg_encoding, PAGE_ENCODING);
reencode(&ret->author_email, ret->msg_encoding, PAGE_ENCODING); reencode(&ret->author_email, ret->msg_encoding, PAGE_ENCODING);
@ -207,49 +195,31 @@ struct commitinfo *cgit_parse_commit(struct commit *commit)
return ret; return ret;
} }
struct taginfo *cgit_parse_tag(struct tag *tag) struct taginfo *cgit_parse_tag(struct tag *tag)
{ {
void *data; void *data;
enum object_type type; enum object_type type;
unsigned long size; unsigned long size;
const char *p; const char *p;
struct taginfo *ret; struct taginfo *ret = NULL;
data = read_sha1_file(tag->object.sha1, &type, &size); data = read_sha1_file(tag->object.sha1, &type, &size);
if (!data || type != OBJ_TAG) { if (!data || type != OBJ_TAG)
free(data); goto cleanup;
return 0;
}
ret = xmalloc(sizeof(*ret)); ret = xcalloc(1, sizeof(struct taginfo));
ret->tagger = NULL;
ret->tagger_email = NULL;
ret->tagger_date = 0;
ret->msg = NULL;
p = data; for (p = data; !end_of_header(p); p = next_header_line(p)) {
if (skip_prefix(p, "tagger ", &p)) {
while (p && *p) { p = parse_user(p, &ret->tagger, &ret->tagger_email,
if (*p == '\n')
break;
if (starts_with(p, "tagger ")) {
p = parse_user(p + 7, &ret->tagger, &ret->tagger_email,
&ret->tagger_date); &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) if (p && *p)
ret->msg = xstrdup(p); ret->msg = xstrdup(p);
cleanup:
free(data); free(data);
return ret; return ret;
} }