if (get_sha1_committish(name, sha1))
return NULL;
commit = lookup_commit_reference(sha1);
- if (!commit || parse_commit(commit))
+ if (parse_commit(commit))
return NULL;
return commit;
}
static int read_graft_file(const char *graft_file)
{
FILE *fp = fopen(graft_file, "r");
- char buf[1024];
+ struct strbuf buf = STRBUF_INIT;
if (!fp)
return -1;
- while (fgets(buf, sizeof(buf), fp)) {
+ while (!strbuf_getwholeline(&buf, fp, '\n')) {
/* The format is just "Commit Parent1 Parent2 ...\n" */
- int len = strlen(buf);
- struct commit_graft *graft = read_graft_line(buf, len);
+ struct commit_graft *graft = read_graft_line(buf.buf, buf.len);
if (!graft)
continue;
if (register_commit_graft(graft, 1))
- error("duplicate graft data: %s", buf);
+ error("duplicate graft data: %s", buf.buf);
}
fclose(fp);
+ strbuf_release(&buf);
return 0;
}
return ret;
}
+void parse_commit_or_die(struct commit *item)
+{
+ if (parse_commit(item))
+ die("unable to parse commit %s",
+ item ? sha1_to_hex(item->object.sha1) : "(null)");
+}
+
int find_commit_subject(const char *commit_buffer, const char **subject)
{
const char *eol;
return c;
}
+struct commit_list *copy_commit_list(struct commit_list *list)
+{
+ struct commit_list *head = NULL;
+ struct commit_list **pp = &head;
+ while (list) {
+ struct commit_list *new;
+ new = xmalloc(sizeof(struct commit_list));
+ new->item = list->item;
+ new->next = NULL;
+ *pp = new;
+ pp = &new->next;
+ list = list->next;
+ }
+ return head;
+}
+
void free_commit_list(struct commit_list *list)
{
while (list) {
buf;
buf = line_end + 1) {
line_end = strchrnul(buf, '\n');
- if (prefixcmp(buf, "author ")) {
+ if (!starts_with(buf, "author ")) {
if (!line_end[0] || line_end[1] == '\n')
return; /* end of header */
continue;
return 0;
}
-static int compare_commits_by_commit_date(const void *a_, const void *b_, void *unused)
+int compare_commits_by_commit_date(const void *a_, const void *b_, void *unused)
{
const struct commit *a = a_, *b = b_;
/* newer commits with larger date first */
struct commit_list *get_octopus_merge_bases(struct commit_list *in)
{
struct commit_list *i, *j, *k, *ret = NULL;
- struct commit_list **pptr = &ret;
- for (i = in; i; i = i->next) {
- if (!ret)
- pptr = &commit_list_insert(i->item, pptr)->next;
- else {
- struct commit_list *new = NULL, *end = NULL;
-
- for (j = ret; j; j = j->next) {
- struct commit_list *bases;
- bases = get_merge_bases(i->item, j->item, 1);
- if (!new)
- new = bases;
- else
- end->next = bases;
- for (k = bases; k; k = k->next)
- end = k;
- }
- ret = new;
+ if (!in)
+ return ret;
+
+ commit_list_insert(in->item, &ret);
+
+ for (i = in->next; i; i = i->next) {
+ struct commit_list *new = NULL, *end = NULL;
+
+ for (j = ret; j; j = j->next) {
+ struct commit_list *bases;
+ bases = get_merge_bases(i->item, j->item, 1);
+ if (!new)
+ new = bases;
+ else
+ end->next = bases;
+ for (k = bases; k; k = k->next)
+ end = k;
}
+ ret = new;
}
return ret;
}
next = next ? next + 1 : tail;
if (in_signature && line[0] == ' ')
sig = line + 1;
- else if (!prefixcmp(line, gpg_sig_header) &&
+ else if (starts_with(line, gpg_sig_header) &&
line[gpg_sig_header_len] == ' ')
sig = line + gpg_sig_header_len + 1;
if (sig) {
for (i = 0; i < ARRAY_SIZE(sigcheck_gpg_status); i++) {
const char *found, *next;
- if (!prefixcmp(buf, sigcheck_gpg_status[i].check + 1)) {
+ if (starts_with(buf, sigcheck_gpg_status[i].check + 1)) {
/* At the very beginning of the buffer */
found = buf + strlen(sigcheck_gpg_status[i].check + 1);
} else {
}
}
-int commit_tree(const struct strbuf *msg, unsigned char *tree,
+int commit_tree(const struct strbuf *msg, const unsigned char *tree,
struct commit_list *parents, unsigned char *ret,
const char *author, const char *sign_commit)
{
static int find_invalid_utf8(const char *buf, int len)
{
int offset = 0;
+ static const unsigned int max_codepoint[] = {
+ 0x7f, 0x7ff, 0xffff, 0x10ffff
+ };
while (len) {
unsigned char c = *buf++;
int bytes, bad_offset;
+ unsigned int codepoint;
+ unsigned int min_val, max_val;
len--;
offset++;
bytes++;
}
- /* Must be between 1 and 5 more bytes */
- if (bytes < 1 || bytes > 5)
+ /*
+ * Must be between 1 and 3 more bytes. Longer sequences result in
+ * codepoints beyond U+10FFFF, which are guaranteed never to exist.
+ */
+ if (bytes < 1 || 3 < bytes)
return bad_offset;
/* Do we *have* that many bytes? */
if (len < bytes)
return bad_offset;
+ /*
+ * Place the encoded bits at the bottom of the value and compute the
+ * valid range.
+ */
+ codepoint = (c & 0x7f) >> bytes;
+ min_val = max_codepoint[bytes-1] + 1;
+ max_val = max_codepoint[bytes];
+
offset += bytes;
len -= bytes;
/* And verify that they are good continuation bytes */
do {
+ codepoint <<= 6;
+ codepoint |= *buf & 0x3f;
if ((*buf++ & 0xc0) != 0x80)
return bad_offset;
} while (--bytes);
- /* We could/should check the value and length here too */
+ /* Reject codepoints that are out of range for the sequence length. */
+ if (codepoint < min_val || codepoint > max_val)
+ return bad_offset;
+ /* Surrogates are only for UTF-16 and cannot be encoded in UTF-8. */
+ if ((codepoint & 0x1ff800) == 0xd800)
+ return bad_offset;
+ /* U+xxFFFE and U+xxFFFF are guaranteed non-characters. */
+ if ((codepoint & 0xfffe) == 0xfffe)
+ return bad_offset;
+ /* So are anything in the range U+FDD0..U+FDEF. */
+ if (codepoint >= 0xfdd0 && codepoint <= 0xfdef)
+ return bad_offset;
}
return -1;
}
*
* If it isn't, it assumes any non-utf8 characters are Latin1,
* and does the conversion.
- *
- * Fixme: we should probably also disallow overlong forms and
- * invalid characters. But we don't do that currently.
*/
static int verify_utf8(struct strbuf *buf)
{
"You may want to amend it after fixing the message, or set the config\n"
"variable i18n.commitencoding to the encoding your project uses.\n";
-int commit_tree_extended(const struct strbuf *msg, unsigned char *tree,
+int commit_tree_extended(const struct strbuf *msg, const unsigned char *tree,
struct commit_list *parents, unsigned char *ret,
const char *author, const char *sign_commit,
struct commit_extra_header *extra)