summaryrefslogtreecommitdiff
path: root/commit.c
diff options
context:
space:
mode:
Diffstat (limited to 'commit.c')
-rw-r--r--commit.c704
1 files changed, 556 insertions, 148 deletions
diff --git a/commit.c b/commit.c
index 35af4988f0..a575564a15 100644
--- a/commit.c
+++ b/commit.c
@@ -7,10 +7,16 @@
#include "revision.h"
#include "notes.h"
#include "gpg-interface.h"
+#include "mergesort.h"
+#include "commit-slab.h"
+#include "prio-queue.h"
+
+static struct commit_extra_header *read_commit_extra_header_lines(const char *buf, size_t len, const char **);
int save_commit_buffer = 1;
const char *commit_type = "commit";
+static int commit_count;
static struct commit *check_commit(struct object *obj,
const unsigned char *sha1,
@@ -55,8 +61,11 @@ struct commit *lookup_commit_or_die(const unsigned char *sha1, const char *ref_n
struct commit *lookup_commit(const unsigned char *sha1)
{
struct object *obj = lookup_object(sha1);
- if (!obj)
- return create_object(sha1, OBJ_COMMIT, alloc_commit_node());
+ if (!obj) {
+ struct commit *c = alloc_commit_node();
+ c->index = commit_count++;
+ return create_object(sha1, OBJ_COMMIT, c);
+ }
if (!obj->type)
obj->type = OBJ_COMMIT;
return check_commit(obj, sha1, 0);
@@ -67,7 +76,7 @@ struct commit *lookup_commit_reference_by_name(const char *name)
unsigned char sha1[20];
struct commit *commit;
- if (get_sha1(name, sha1))
+ if (get_sha1_committish(name, sha1))
return NULL;
commit = lookup_commit_reference(sha1);
if (!commit || parse_commit(commit))
@@ -390,15 +399,31 @@ struct commit_list * commit_list_insert_by_date(struct commit *item, struct comm
return commit_list_insert(item, pp);
}
+static int commit_list_compare_by_date(const void *a, const void *b)
+{
+ unsigned long a_date = ((const struct commit_list *)a)->item->date;
+ unsigned long b_date = ((const struct commit_list *)b)->item->date;
+ if (a_date < b_date)
+ return 1;
+ if (a_date > b_date)
+ return -1;
+ return 0;
+}
+
+static void *commit_list_get_next(const void *a)
+{
+ return ((const struct commit_list *)a)->next;
+}
+
+static void commit_list_set_next(void *a, void *next)
+{
+ ((struct commit_list *)a)->next = next;
+}
void commit_list_sort_by_date(struct commit_list **list)
{
- struct commit_list *ret = NULL;
- while (*list) {
- commit_list_insert_by_date((*list)->item, &ret);
- *list = (*list)->next;
- }
- *list = ret;
+ *list = llist_mergesort(*list, commit_list_get_next, commit_list_set_next,
+ commit_list_compare_by_date);
}
struct commit *pop_most_recent_commit(struct commit_list **list,
@@ -422,7 +447,8 @@ struct commit *pop_most_recent_commit(struct commit_list **list,
return ret;
}
-void clear_commit_marks(struct commit *commit, unsigned int mark)
+static void clear_commit_marks_1(struct commit_list **plist,
+ struct commit *commit, unsigned int mark)
{
while (commit) {
struct commit_list *parents;
@@ -437,12 +463,29 @@ void clear_commit_marks(struct commit *commit, unsigned int mark)
return;
while ((parents = parents->next))
- clear_commit_marks(parents->item, mark);
+ commit_list_insert(parents->item, plist);
commit = commit->parents->item;
}
}
+void clear_commit_marks_many(int nr, struct commit **commit, unsigned int mark)
+{
+ struct commit_list *list = NULL;
+
+ while (nr--) {
+ commit_list_insert(*commit, &list);
+ commit++;
+ }
+ while (list)
+ clear_commit_marks_1(&list, pop_commit(&list), mark);
+}
+
+void clear_commit_marks(struct commit *commit, unsigned int mark)
+{
+ clear_commit_marks_many(1, &commit, mark);
+}
+
void clear_commit_marks_for_object_array(struct object_array *a, unsigned mark)
{
struct object *object;
@@ -470,32 +513,136 @@ struct commit *pop_commit(struct commit_list **stack)
}
/*
+ * Topological sort support
+ */
+
+/* count number of children that have not been emitted */
+define_commit_slab(indegree_slab, int);
+
+/* record author-date for each commit object */
+define_commit_slab(author_date_slab, unsigned long);
+
+static void record_author_date(struct author_date_slab *author_date,
+ struct commit *commit)
+{
+ const char *buf, *line_end;
+ char *buffer = NULL;
+ struct ident_split ident;
+ char *date_end;
+ unsigned long date;
+
+ if (!commit->buffer) {
+ unsigned long size;
+ enum object_type type;
+ buffer = read_sha1_file(commit->object.sha1, &type, &size);
+ if (!buffer)
+ return;
+ }
+
+ for (buf = commit->buffer ? commit->buffer : buffer;
+ buf;
+ buf = line_end + 1) {
+ line_end = strchrnul(buf, '\n');
+ if (prefixcmp(buf, "author ")) {
+ if (!line_end[0] || line_end[1] == '\n')
+ return; /* end of header */
+ continue;
+ }
+ if (split_ident_line(&ident,
+ buf + strlen("author "),
+ line_end - (buf + strlen("author "))) ||
+ !ident.date_begin || !ident.date_end)
+ goto fail_exit; /* malformed "author" line */
+ break;
+ }
+
+ date = strtoul(ident.date_begin, &date_end, 10);
+ if (date_end != ident.date_end)
+ goto fail_exit; /* malformed date */
+ *(author_date_slab_at(author_date, commit)) = date;
+
+fail_exit:
+ free(buffer);
+}
+
+static int compare_commits_by_author_date(const void *a_, const void *b_,
+ void *cb_data)
+{
+ const struct commit *a = a_, *b = b_;
+ struct author_date_slab *author_date = cb_data;
+ unsigned long a_date = *(author_date_slab_at(author_date, a));
+ unsigned long b_date = *(author_date_slab_at(author_date, b));
+
+ /* newer commits with larger date first */
+ if (a_date < b_date)
+ return 1;
+ else if (a_date > b_date)
+ return -1;
+ return 0;
+}
+
+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 */
+ if (a->date < b->date)
+ return 1;
+ else if (a->date > b->date)
+ return -1;
+ return 0;
+}
+
+/*
* Performs an in-place topological sort on the list supplied.
*/
-void sort_in_topological_order(struct commit_list ** list, int lifo)
+void sort_in_topological_order(struct commit_list **list, enum rev_sort_order sort_order)
{
struct commit_list *next, *orig = *list;
- struct commit_list *work, **insert;
struct commit_list **pptr;
+ struct indegree_slab indegree;
+ struct prio_queue queue;
+ struct commit *commit;
+ struct author_date_slab author_date;
if (!orig)
return;
*list = NULL;
+ init_indegree_slab(&indegree);
+ memset(&queue, '\0', sizeof(queue));
+
+ switch (sort_order) {
+ default: /* REV_SORT_IN_GRAPH_ORDER */
+ queue.compare = NULL;
+ break;
+ case REV_SORT_BY_COMMIT_DATE:
+ queue.compare = compare_commits_by_commit_date;
+ break;
+ case REV_SORT_BY_AUTHOR_DATE:
+ init_author_date_slab(&author_date);
+ queue.compare = compare_commits_by_author_date;
+ queue.cb_data = &author_date;
+ break;
+ }
+
/* Mark them and clear the indegree */
for (next = orig; next; next = next->next) {
struct commit *commit = next->item;
- commit->indegree = 1;
+ *(indegree_slab_at(&indegree, commit)) = 1;
+ /* also record the author dates, if needed */
+ if (sort_order == REV_SORT_BY_AUTHOR_DATE)
+ record_author_date(&author_date, commit);
}
/* update the indegree */
for (next = orig; next; next = next->next) {
- struct commit_list * parents = next->item->parents;
+ struct commit_list *parents = next->item->parents;
while (parents) {
struct commit *parent = parents->item;
+ int *pi = indegree_slab_at(&indegree, parent);
- if (parent->indegree)
- parent->indegree++;
+ if (*pi)
+ (*pi)++;
parents = parents->next;
}
}
@@ -507,34 +654,33 @@ void sort_in_topological_order(struct commit_list ** list, int lifo)
*
* the tips serve as a starting set for the work queue.
*/
- work = NULL;
- insert = &work;
for (next = orig; next; next = next->next) {
struct commit *commit = next->item;
- if (commit->indegree == 1)
- insert = &commit_list_insert(commit, insert)->next;
+ if (*(indegree_slab_at(&indegree, commit)) == 1)
+ prio_queue_put(&queue, commit);
}
- /* process the list in topological order */
- if (!lifo)
- commit_list_sort_by_date(&work);
+ /*
+ * This is unfortunate; the initial tips need to be shown
+ * in the order given from the revision traversal machinery.
+ */
+ if (sort_order == REV_SORT_IN_GRAPH_ORDER)
+ prio_queue_reverse(&queue);
+
+ /* We no longer need the commit list */
+ free_commit_list(orig);
pptr = list;
*list = NULL;
- while (work) {
- struct commit *commit;
- struct commit_list *parents, *work_item;
-
- work_item = work;
- work = work_item->next;
- work_item->next = NULL;
+ while ((commit = prio_queue_get(&queue)) != NULL) {
+ struct commit_list *parents;
- commit = work_item->item;
for (parents = commit->parents; parents ; parents = parents->next) {
struct commit *parent = parents->item;
+ int *pi = indegree_slab_at(&indegree, parent);
- if (!parent->indegree)
+ if (!*pi)
continue;
/*
@@ -542,21 +688,22 @@ void sort_in_topological_order(struct commit_list ** list, int lifo)
* when all their children have been emitted thereby
* guaranteeing topological order.
*/
- if (--parent->indegree == 1) {
- if (!lifo)
- commit_list_insert_by_date(parent, &work);
- else
- commit_list_insert(parent, &work);
- }
+ if (--(*pi) == 1)
+ prio_queue_put(&queue, parent);
}
/*
- * work_item is a commit all of whose children
- * have already been emitted. we can emit it now.
+ * all children of commit have already been
+ * emitted. we can emit it now.
*/
- commit->indegree = 0;
- *pptr = work_item;
- pptr = &work_item->next;
+ *(indegree_slab_at(&indegree, commit)) = 0;
+
+ pptr = &commit_list_insert(commit, pptr)->next;
}
+
+ clear_indegree_slab(&indegree);
+ clear_prio_queue(&queue);
+ if (sort_order == REV_SORT_BY_AUTHOR_DATE)
+ clear_author_date_slab(&author_date);
}
/* merge-base stuff */
@@ -581,30 +728,17 @@ static struct commit *interesting(struct commit_list *list)
return NULL;
}
-static struct commit_list *merge_bases_many(struct commit *one, int n, struct commit **twos)
+/* all input commits in one and twos[] must have been parsed! */
+static struct commit_list *paint_down_to_common(struct commit *one, int n, struct commit **twos)
{
struct commit_list *list = NULL;
struct commit_list *result = NULL;
int i;
- for (i = 0; i < n; i++) {
- if (one == twos[i])
- /*
- * We do not mark this even with RESULT so we do not
- * have to clean it up.
- */
- return commit_list_insert(one, &result);
- }
-
- if (parse_commit(one))
- return NULL;
- for (i = 0; i < n; i++) {
- if (parse_commit(twos[i]))
- return NULL;
- }
-
one->object.flags |= PARENT1;
commit_list_insert_by_date(one, &list);
+ if (!n)
+ return list;
for (i = 0; i < n; i++) {
twos[i]->object.flags |= PARENT2;
commit_list_insert_by_date(twos[i], &list);
@@ -643,9 +777,34 @@ static struct commit_list *merge_bases_many(struct commit *one, int n, struct co
}
}
- /* Clean up the result to remove stale ones */
free_commit_list(list);
- list = result; result = NULL;
+ return result;
+}
+
+static struct commit_list *merge_bases_many(struct commit *one, int n, struct commit **twos)
+{
+ struct commit_list *list = NULL;
+ struct commit_list *result = NULL;
+ int i;
+
+ for (i = 0; i < n; i++) {
+ if (one == twos[i])
+ /*
+ * We do not mark this even with RESULT so we do not
+ * have to clean it up.
+ */
+ return commit_list_insert(one, &result);
+ }
+
+ if (parse_commit(one))
+ return NULL;
+ for (i = 0; i < n; i++) {
+ if (parse_commit(twos[i]))
+ return NULL;
+ }
+
+ list = paint_down_to_common(one, n, twos);
+
while (list) {
struct commit_list *next = list->next;
if (!(list->item->object.flags & STALE))
@@ -683,6 +842,62 @@ struct commit_list *get_octopus_merge_bases(struct commit_list *in)
return ret;
}
+static int remove_redundant(struct commit **array, int cnt)
+{
+ /*
+ * Some commit in the array may be an ancestor of
+ * another commit. Move such commit to the end of
+ * the array, and return the number of commits that
+ * are independent from each other.
+ */
+ struct commit **work;
+ unsigned char *redundant;
+ int *filled_index;
+ int i, j, filled;
+
+ work = xcalloc(cnt, sizeof(*work));
+ redundant = xcalloc(cnt, 1);
+ filled_index = xmalloc(sizeof(*filled_index) * (cnt - 1));
+
+ for (i = 0; i < cnt; i++)
+ parse_commit(array[i]);
+ for (i = 0; i < cnt; i++) {
+ struct commit_list *common;
+
+ if (redundant[i])
+ continue;
+ for (j = filled = 0; j < cnt; j++) {
+ if (i == j || redundant[j])
+ continue;
+ filled_index[filled] = j;
+ work[filled++] = array[j];
+ }
+ common = paint_down_to_common(array[i], filled, work);
+ if (array[i]->object.flags & PARENT2)
+ redundant[i] = 1;
+ for (j = 0; j < filled; j++)
+ if (work[j]->object.flags & PARENT1)
+ redundant[filled_index[j]] = 1;
+ clear_commit_marks(array[i], all_flags);
+ for (j = 0; j < filled; j++)
+ clear_commit_marks(work[j], all_flags);
+ free_commit_list(common);
+ }
+
+ /* Now collect the result */
+ memcpy(work, array, sizeof(*array) * cnt);
+ for (i = filled = 0; i < cnt; i++)
+ if (!redundant[i])
+ array[filled++] = work[i];
+ for (j = filled, i = 0; i < cnt; i++)
+ if (redundant[i])
+ array[j++] = work[i];
+ free(work);
+ free(redundant);
+ free(filled_index);
+ return filled;
+}
+
struct commit_list *get_merge_bases_many(struct commit *one,
int n,
struct commit **twos,
@@ -691,7 +906,7 @@ struct commit_list *get_merge_bases_many(struct commit *one,
struct commit_list *list;
struct commit **rslt;
struct commit_list *result;
- int cnt, i, j;
+ int cnt, i;
result = merge_bases_many(one, n, twos);
for (i = 0; i < n; i++) {
@@ -701,8 +916,7 @@ struct commit_list *get_merge_bases_many(struct commit *one,
if (!result || !result->next) {
if (cleanup) {
clear_commit_marks(one, all_flags);
- for (i = 0; i < n; i++)
- clear_commit_marks(twos[i], all_flags);
+ clear_commit_marks_many(n, twos, all_flags);
}
return result;
}
@@ -720,30 +934,12 @@ struct commit_list *get_merge_bases_many(struct commit *one,
free_commit_list(result);
clear_commit_marks(one, all_flags);
- for (i = 0; i < n; i++)
- clear_commit_marks(twos[i], all_flags);
- for (i = 0; i < cnt - 1; i++) {
- for (j = i+1; j < cnt; j++) {
- if (!rslt[i] || !rslt[j])
- continue;
- result = merge_bases_many(rslt[i], 1, &rslt[j]);
- clear_commit_marks(rslt[i], all_flags);
- clear_commit_marks(rslt[j], all_flags);
- for (list = result; list; list = list->next) {
- if (rslt[i] == list->item)
- rslt[i] = NULL;
- if (rslt[j] == list->item)
- rslt[j] = NULL;
- }
- }
- }
+ clear_commit_marks_many(n, twos, all_flags);
- /* Surviving ones in rslt[] are the independent results */
+ cnt = remove_redundant(rslt, cnt);
result = NULL;
- for (i = 0; i < cnt; i++) {
- if (rslt[i])
- commit_list_insert_by_date(rslt[i], &result);
- }
+ for (i = 0; i < cnt; i++)
+ commit_list_insert_by_date(rslt[i], &result);
free(rslt);
return result;
}
@@ -754,6 +950,9 @@ struct commit_list *get_merge_bases(struct commit *one, struct commit *two,
return get_merge_bases_many(one, 1, &two, cleanup);
}
+/*
+ * Is "commit" a descendant of one of the elements on the "with_commit" list?
+ */
int is_descendant_of(struct commit *commit, struct commit_list *with_commit)
{
if (!with_commit)
@@ -763,81 +962,72 @@ int is_descendant_of(struct commit *commit, struct commit_list *with_commit)
other = with_commit->item;
with_commit = with_commit->next;
- if (in_merge_bases(other, &commit, 1))
+ if (in_merge_bases(other, commit))
return 1;
}
return 0;
}
-int in_merge_bases(struct commit *commit, struct commit **reference, int num)
+/*
+ * Is "commit" an ancestor of one of the "references"?
+ */
+int in_merge_bases_many(struct commit *commit, int nr_reference, struct commit **reference)
{
- struct commit_list *bases, *b;
- int ret = 0;
-
- if (num == 1)
- bases = get_merge_bases(commit, *reference, 1);
- else
- die("not yet");
- for (b = bases; b; b = b->next) {
- if (!hashcmp(commit->object.sha1, b->item->object.sha1)) {
- ret = 1;
- break;
- }
- }
-
+ struct commit_list *bases;
+ int ret = 0, i;
+
+ if (parse_commit(commit))
+ return ret;
+ for (i = 0; i < nr_reference; i++)
+ if (parse_commit(reference[i]))
+ return ret;
+
+ bases = paint_down_to_common(commit, nr_reference, reference);
+ if (commit->object.flags & PARENT2)
+ ret = 1;
+ clear_commit_marks(commit, all_flags);
+ clear_commit_marks_many(nr_reference, reference, all_flags);
free_commit_list(bases);
return ret;
}
+/*
+ * Is "commit" an ancestor of (i.e. reachable from) the "reference"?
+ */
+int in_merge_bases(struct commit *commit, struct commit *reference)
+{
+ return in_merge_bases_many(commit, 1, &reference);
+}
+
struct commit_list *reduce_heads(struct commit_list *heads)
{
struct commit_list *p;
struct commit_list *result = NULL, **tail = &result;
- struct commit **other;
- size_t num_head, num_other;
+ struct commit **array;
+ int num_head, i;
if (!heads)
return NULL;
- /* Avoid unnecessary reallocations */
- for (p = heads, num_head = 0; p; p = p->next)
- num_head++;
- other = xcalloc(sizeof(*other), num_head);
-
- /* For each commit, see if it can be reached by others */
- for (p = heads; p; p = p->next) {
- struct commit_list *q, *base;
-
- /* Do we already have this in the result? */
- for (q = result; q; q = q->next)
- if (p->item == q->item)
- break;
- if (q)
+ /* Uniquify */
+ for (p = heads; p; p = p->next)
+ p->item->object.flags &= ~STALE;
+ for (p = heads, num_head = 0; p; p = p->next) {
+ if (p->item->object.flags & STALE)
continue;
-
- num_other = 0;
- for (q = heads; q; q = q->next) {
- if (p->item == q->item)
- continue;
- other[num_other++] = q->item;
+ p->item->object.flags |= STALE;
+ num_head++;
+ }
+ array = xcalloc(sizeof(*array), num_head);
+ for (p = heads, i = 0; p; p = p->next) {
+ if (p->item->object.flags & STALE) {
+ array[i++] = p->item;
+ p->item->object.flags &= ~STALE;
}
- if (num_other)
- base = get_merge_bases_many(p->item, num_other, other, 1);
- else
- base = NULL;
- /*
- * If p->item does not have anything common with other
- * commits, there won't be any merge base. If it is
- * reachable from some of the others, p->item will be
- * the merge base. If its history is connected with
- * others, but p->item is not reachable by others, we
- * will get something other than p->item back.
- */
- if (!base || (base->item != p->item))
- tail = &(commit_list_insert(p->item, tail)->next);
- free_commit_list(base);
}
- free(other);
+ num_head = remove_redundant(array, num_head);
+ for (i = 0; i < num_head; i++)
+ tail = &commit_list_insert(array[i], tail)->next;
return result;
}
@@ -961,6 +1151,76 @@ free_return:
free(buf);
}
+static struct {
+ char result;
+ const char *check;
+} sigcheck_gpg_status[] = {
+ { 'G', "\n[GNUPG:] GOODSIG " },
+ { 'B', "\n[GNUPG:] BADSIG " },
+ { 'U', "\n[GNUPG:] TRUST_NEVER" },
+ { 'U', "\n[GNUPG:] TRUST_UNDEFINED" },
+};
+
+static void parse_gpg_output(struct signature_check *sigc)
+{
+ const char *buf = sigc->gpg_status;
+ int i;
+
+ /* Iterate over all search strings */
+ for (i = 0; i < ARRAY_SIZE(sigcheck_gpg_status); i++) {
+ const char *found, *next;
+
+ if (!prefixcmp(buf, sigcheck_gpg_status[i].check + 1)) {
+ /* At the very beginning of the buffer */
+ found = buf + strlen(sigcheck_gpg_status[i].check + 1);
+ } else {
+ found = strstr(buf, sigcheck_gpg_status[i].check);
+ if (!found)
+ continue;
+ found += strlen(sigcheck_gpg_status[i].check);
+ }
+ sigc->result = sigcheck_gpg_status[i].result;
+ /* The trust messages are not followed by key/signer information */
+ if (sigc->result != 'U') {
+ sigc->key = xmemdupz(found, 16);
+ found += 17;
+ next = strchrnul(found, '\n');
+ sigc->signer = xmemdupz(found, next - found);
+ }
+ }
+}
+
+void check_commit_signature(const struct commit* commit, struct signature_check *sigc)
+{
+ struct strbuf payload = STRBUF_INIT;
+ struct strbuf signature = STRBUF_INIT;
+ struct strbuf gpg_output = STRBUF_INIT;
+ struct strbuf gpg_status = STRBUF_INIT;
+ int status;
+
+ sigc->result = 'N';
+
+ if (parse_signed_commit(commit->object.sha1,
+ &payload, &signature) <= 0)
+ goto out;
+ status = verify_signed_buffer(payload.buf, payload.len,
+ signature.buf, signature.len,
+ &gpg_output, &gpg_status);
+ if (status && !gpg_output.len)
+ goto out;
+ sigc->gpg_output = strbuf_detach(&gpg_output, NULL);
+ sigc->gpg_status = strbuf_detach(&gpg_status, NULL);
+ parse_gpg_output(sigc);
+
+ out:
+ strbuf_release(&gpg_status);
+ strbuf_release(&gpg_output);
+ strbuf_release(&payload);
+ strbuf_release(&signature);
+}
+
+
+
void append_merge_tag_headers(struct commit_list *parents,
struct commit_extra_header ***tail)
{
@@ -1018,8 +1278,9 @@ static int excluded_header_field(const char *field, size_t len, const char **exc
return 0;
}
-struct commit_extra_header *read_commit_extra_header_lines(const char *buffer, size_t size,
- const char **exclude)
+static struct commit_extra_header *read_commit_extra_header_lines(
+ const char *buffer, size_t size,
+ const char **exclude)
{
struct commit_extra_header *extra = NULL, **tail = &extra, *it = NULL;
const char *line, *next, *eof, *eob;
@@ -1086,8 +1347,118 @@ int commit_tree(const struct strbuf *msg, unsigned char *tree,
return result;
}
+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++;
+
+ /* Simple US-ASCII? No worries. */
+ if (c < 0x80)
+ continue;
+
+ bad_offset = offset-1;
+
+ /*
+ * Count how many more high bits set: that's how
+ * many more bytes this sequence should have.
+ */
+ bytes = 0;
+ while (c & 0x40) {
+ c <<= 1;
+ bytes++;
+ }
+
+ /*
+ * 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);
+
+ /* 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;
+}
+
+/*
+ * This verifies that the buffer is in proper utf8 format.
+ *
+ * If it isn't, it assumes any non-utf8 characters are Latin1,
+ * and does the conversion.
+ */
+static int verify_utf8(struct strbuf *buf)
+{
+ int ok = 1;
+ long pos = 0;
+
+ for (;;) {
+ int bad;
+ unsigned char c;
+ unsigned char replace[2];
+
+ bad = find_invalid_utf8(buf->buf + pos, buf->len - pos);
+ if (bad < 0)
+ return ok;
+ pos += bad;
+ ok = 0;
+ c = buf->buf[pos];
+ strbuf_remove(buf, pos, 1);
+
+ /* We know 'c' must be in the range 128-255 */
+ replace[0] = 0xc0 + (c >> 6);
+ replace[1] = 0x80 + (c & 0x3f);
+ strbuf_insert(buf, pos, replace, 2);
+ pos += 2;
+ }
+}
+
static const char commit_utf8_warn[] =
-"Warning: commit message does not conform to UTF-8.\n"
+"Warning: commit message did not conform to UTF-8.\n"
"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";
@@ -1128,9 +1499,9 @@ int commit_tree_extended(const struct strbuf *msg, unsigned char *tree,
/* Person/date information */
if (!author)
- author = git_author_info(IDENT_ERROR_ON_NO_NAME);
+ author = git_author_info(IDENT_STRICT);
strbuf_addf(&buffer, "author %s\n", author);
- strbuf_addf(&buffer, "committer %s\n", git_committer_info(IDENT_ERROR_ON_NO_NAME));
+ strbuf_addf(&buffer, "committer %s\n", git_committer_info(IDENT_STRICT));
if (!encoding_is_utf8)
strbuf_addf(&buffer, "encoding %s\n", git_commit_encoding);
@@ -1144,7 +1515,7 @@ int commit_tree_extended(const struct strbuf *msg, unsigned char *tree,
strbuf_addbuf(&buffer, msg);
/* And check the encoding */
- if (encoding_is_utf8 && !is_utf8(buffer.buf))
+ if (encoding_is_utf8 && !verify_utf8(&buffer))
fprintf(stderr, commit_utf8_warn);
if (sign_commit && do_sign_commit(&buffer, sign_commit))
@@ -1173,3 +1544,40 @@ struct commit *get_merge_parent(const char *name)
}
return commit;
}
+
+/*
+ * Append a commit to the end of the commit_list.
+ *
+ * next starts by pointing to the variable that holds the head of an
+ * empty commit_list, and is updated to point to the "next" field of
+ * the last item on the list as new commits are appended.
+ *
+ * Usage example:
+ *
+ * struct commit_list *list;
+ * struct commit_list **next = &list;
+ *
+ * next = commit_list_append(c1, next);
+ * next = commit_list_append(c2, next);
+ * assert(commit_list_count(list) == 2);
+ * return list;
+ */
+struct commit_list **commit_list_append(struct commit *commit,
+ struct commit_list **next)
+{
+ struct commit_list *new = xmalloc(sizeof(struct commit_list));
+ new->item = commit;
+ *next = new;
+ new->next = NULL;
+ return &new->next;
+}
+
+void print_commit_list(struct commit_list *list,
+ const char *format_cur,
+ const char *format_last)
+{
+ for ( ; list; list = list->next) {
+ const char *format = list->next ? format_cur : format_last;
+ printf(format, sha1_to_hex(list->item->object.sha1));
+ }
+}