mirrors/cgit
0
0
Fork 0
mirror of https://git.zx2c4.com/cgit synced 2024-11-26 02:18:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

parsing.c: be prepared for unexpected content in commit/tag objects

Browse Source 
When parsing commits and tags cgit made too many assumptions about the
formatting of said objects. This patch tries to make the code be more
prepared to handle 'malformed' objects.

Signed-off-by: Lars Hjemli <hjemli@gmail.com>
This commit is contained in:
Lars Hjemli 2008-09-14 09:45:37 +02:00
parent b28765135d
commit a8305a9543
2 changed files with 97 additions and 64 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
cgit.h
View File

@ -85,7 +85,7 @@ struct commitinfo {
struct taginfo { struct taginfo {
char *tagger; char *tagger;
char *tagger_email; char *tagger_email;
int tagger_date; unsigned long tagger_date;
char *msg; char *msg;
}; };

159
parsing.c
View File

@ -62,6 +62,55 @@ char *substr(const char *head, const char *tail)
return buf; 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;
}
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);
if (tmp) {
free(*txt);
*txt = tmp;
}
return *txt;
}
struct commitinfo *cgit_parse_commit(struct commit *commit) struct commitinfo *cgit_parse_commit(struct commit *commit)
{ {
struct commitinfo *ret; struct commitinfo *ret;
@ -88,70 +137,57 @@ struct commitinfo *cgit_parse_commit(struct commit *commit)
while (!strncmp(p, "parent ", 7)) while (!strncmp(p, "parent ", 7))
p += 48; // "parent " + hex[40] + "\n" p += 48; // "parent " + hex[40] + "\n"
if (!strncmp(p, "author ", 7)) { if (p && !strncmp(p, "author ", 7)) {
p += 7; p = parse_user(p + 7, &ret->author, &ret->author_email,
t = strchr(p, '<') - 1; &ret->author_date);
ret->author = substr(p, t);
p = t;
t = strchr(t, '>') + 1;
ret->author_email = substr(p, t);
ret->author_date = atol(t+1);
p = strchr(t, '\n') + 1;
} }
if (!strncmp(p, "committer ", 9)) { if (p && !strncmp(p, "committer ", 9)) {
p += 9; p = parse_user(p + 9, &ret->committer, &ret->committer_email,
t = strchr(p, '<') - 1; &ret->committer_date);
ret->committer = substr(p, t);
p = t;
t = strchr(t, '>') + 1;
ret->committer_email = substr(p, t);
ret->committer_date = atol(t+1);
p = strchr(t, '\n') + 1;
} }
if (!strncmp(p, "encoding ", 9)) { if (p && !strncmp(p, "encoding ", 9)) {
p += 9; p += 9;
t = strchr(p, '\n') + 1; t = strchr(p, '\n');
ret->msg_encoding = substr(p, t); if (t) {
p = t; ret->msg_encoding = substr(p, t + 1);
} else p = t + 1;
ret->msg_encoding = xstrdup(PAGE_ENCODING); }
}
while (*p && (*p != '\n')) // skip unknown header fields
p = strchr(p, '\n') + 1; // skip unknown header fields while (p && *p && (*p != '\n')) {
p = strchr(p, '\n');
if (p)
p++;
}
while (*p == '\n') // skip empty lines between headers and message
p = strchr(p, '\n') + 1; while (p && *p == '\n')
p++;
if (!p)
return ret;
t = strchr(p, '\n'); t = strchr(p, '\n');
if (t) { if (t) {
if (*t == '\0') ret->subject = substr(p, t);
ret->subject = "** empty **";
else
ret->subject = substr(p, t);
p = t + 1; p = t + 1;
while (*p == '\n') while (p && *p == '\n') {
p = strchr(p, '\n') + 1; p = strchr(p, '\n');
ret->msg = xstrdup(p); if (p)
p++;
}
if (p)
ret->msg = xstrdup(p);
} else } else
ret->subject = substr(p, p+strlen(p)); ret->subject = xstrdup(p);
if(strcmp(ret->msg_encoding, PAGE_ENCODING)) { if (ret->msg_encoding) {
t = reencode_string(ret->subject, PAGE_ENCODING, reencode(&ret->subject, PAGE_ENCODING, ret->msg_encoding);
ret->msg_encoding); reencode(&ret->msg, PAGE_ENCODING, ret->msg_encoding);
if(t) {
free(ret->subject);
ret->subject = t;
}
t = reencode_string(ret->msg, PAGE_ENCODING,
ret->msg_encoding);
if(t) {
free(ret->msg);
ret->msg = t;
}
} }
return ret; return ret;
@ -163,7 +199,7 @@ 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;
char *p, *t; char *p;
struct taginfo *ret; struct taginfo *ret;
data = read_sha1_file(tag->object.sha1, &type, &size); data = read_sha1_file(tag->object.sha1, &type, &size);
@ -185,22 +221,19 @@ struct taginfo *cgit_parse_tag(struct tag *tag)
break; break;
if (!strncmp(p, "tagger ", 7)) { if (!strncmp(p, "tagger ", 7)) {
p += 7; p = parse_user(p + 7, &ret->tagger, &ret->tagger_email,
t = strchr(p, '<') - 1; &ret->tagger_date);
ret->tagger = substr(p, t); } else {
p = t; p = strchr(p, '\n');
t = strchr(t, '>') + 1; if (p)
ret->tagger_email = substr(p, t); p++;
ret->tagger_date = atol(t+1);
} }
p = strchr(p, '\n') + 1;
} }
while (p && *p && (*p != '\n')) // skip empty lines between headers and message
p = strchr(p, '\n') + 1; // skip unknown tag fields while (p && *p == '\n')
p++;
while (p && (*p == '\n'))
p = strchr(p, '\n') + 1;
if (p && *p) if (p && *p)
ret->msg = xstrdup(p); ret->msg = xstrdup(p);
free(data); free(data);