diff options
Diffstat (limited to 'commit.c')
| -rw-r--r-- | commit.c | 1047 |
1 files changed, 782 insertions, 265 deletions
@@ -7,24 +7,17 @@ #include "revision.h" #include "notes.h" #include "gpg-interface.h" +#include "mergesort.h" +#include "commit-slab.h" +#include "prio-queue.h" +#include "sha1-lookup.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 struct commit *check_commit(struct object *obj, - const unsigned char *sha1, - int quiet) -{ - if (obj->type != OBJ_COMMIT) { - if (!quiet) - error("Object %s is a %s, not a commit", - sha1_to_hex(sha1), typename(obj->type)); - return NULL; - } - return (struct commit *) obj; -} - struct commit *lookup_commit_reference_gently(const unsigned char *sha1, int quiet) { @@ -32,7 +25,7 @@ struct commit *lookup_commit_reference_gently(const unsigned char *sha1, if (!obj) return NULL; - return check_commit(obj, sha1, quiet); + return object_as_type(obj, OBJ_COMMIT, quiet); } struct commit *lookup_commit_reference(const unsigned char *sha1) @@ -56,10 +49,8 @@ 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->type) - obj->type = OBJ_COMMIT; - return check_commit(obj, sha1, 0); + return create_object(sha1, alloc_commit_node()); + return object_as_type(obj, OBJ_COMMIT, 0); } struct commit *lookup_commit_reference_by_name(const char *name) @@ -67,10 +58,10 @@ 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)) + if (parse_commit(commit)) return NULL; return commit; } @@ -105,23 +96,16 @@ static unsigned long parse_commit_date(const char *buf, const char *tail) static struct commit_graft **commit_graft; static int commit_graft_alloc, commit_graft_nr; +static const unsigned char *commit_graft_sha1_access(size_t index, void *table) +{ + struct commit_graft **commit_graft_table = table; + return commit_graft_table[index]->sha1; +} + static int commit_graft_pos(const unsigned char *sha1) { - int lo, hi; - lo = 0; - hi = commit_graft_nr; - while (lo < hi) { - int mi = (lo + hi) / 2; - struct commit_graft *graft = commit_graft[mi]; - int cmp = hashcmp(sha1, graft->sha1); - if (!cmp) - return mi; - if (cmp < 0) - hi = mi; - else - lo = mi + 1; - } - return -lo - 1; + return sha1_pos(sha1, commit_graft, commit_graft_nr, + commit_graft_sha1_access); } int register_commit_graft(struct commit_graft *graft, int ignore_dups) @@ -138,12 +122,8 @@ int register_commit_graft(struct commit_graft *graft, int ignore_dups) return 1; } pos = -pos - 1; - if (commit_graft_alloc <= ++commit_graft_nr) { - commit_graft_alloc = alloc_nr(commit_graft_alloc); - commit_graft = xrealloc(commit_graft, - sizeof(*commit_graft) * - commit_graft_alloc); - } + ALLOC_GROW(commit_graft, commit_graft_nr + 1, commit_graft_alloc); + commit_graft_nr++; if (pos < commit_graft_nr) memmove(commit_graft + pos + 1, commit_graft + pos, @@ -187,19 +167,19 @@ bad_graft_data: 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; } @@ -248,6 +228,76 @@ int unregister_shallow(const unsigned char *sha1) return 0; } +struct commit_buffer { + void *buffer; + unsigned long size; +}; +define_commit_slab(buffer_slab, struct commit_buffer); +static struct buffer_slab buffer_slab = COMMIT_SLAB_INIT(1, buffer_slab); + +void set_commit_buffer(struct commit *commit, void *buffer, unsigned long size) +{ + struct commit_buffer *v = buffer_slab_at(&buffer_slab, commit); + v->buffer = buffer; + v->size = size; +} + +const void *get_cached_commit_buffer(const struct commit *commit, unsigned long *sizep) +{ + struct commit_buffer *v = buffer_slab_at(&buffer_slab, commit); + if (sizep) + *sizep = v->size; + return v->buffer; +} + +const void *get_commit_buffer(const struct commit *commit, unsigned long *sizep) +{ + const void *ret = get_cached_commit_buffer(commit, sizep); + if (!ret) { + enum object_type type; + unsigned long size; + ret = read_sha1_file(commit->object.sha1, &type, &size); + if (!ret) + die("cannot read commit object %s", + sha1_to_hex(commit->object.sha1)); + if (type != OBJ_COMMIT) + die("expected commit for %s, got %s", + sha1_to_hex(commit->object.sha1), typename(type)); + if (sizep) + *sizep = size; + } + return ret; +} + +void unuse_commit_buffer(const struct commit *commit, const void *buffer) +{ + struct commit_buffer *v = buffer_slab_at(&buffer_slab, commit); + if (v->buffer != buffer) + free((void *)buffer); +} + +void free_commit_buffer(struct commit *commit) +{ + struct commit_buffer *v = buffer_slab_at(&buffer_slab, commit); + free(v->buffer); + v->buffer = NULL; + v->size = 0; +} + +const void *detach_commit_buffer(struct commit *commit, unsigned long *sizep) +{ + struct commit_buffer *v = buffer_slab_at(&buffer_slab, commit); + void *ret; + + ret = v->buffer; + if (sizep) + *sizep = v->size; + + v->buffer = NULL; + v->size = 0; + return ret; +} + int parse_commit_buffer(struct commit *item, const void *buffer, unsigned long size) { const char *tail = buffer; @@ -325,13 +375,20 @@ int parse_commit(struct commit *item) } ret = parse_commit_buffer(item, buffer, size); if (save_commit_buffer && !ret) { - item->buffer = buffer; + set_commit_buffer(item, buffer, size); return 0; } free(buffer); 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; @@ -368,6 +425,17 @@ unsigned commit_list_count(const struct commit_list *l) return c; } +struct commit_list *copy_commit_list(struct commit_list *list) +{ + struct commit_list *head = NULL; + struct commit_list **pp = &head; + while (list) { + pp = commit_list_append(list->item, pp); + list = list->next; + } + return head; +} + void free_commit_list(struct commit_list *list) { while (list) { @@ -390,15 +458,31 @@ 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, @@ -444,14 +528,23 @@ static void clear_commit_marks_1(struct commit_list **plist, } } -void clear_commit_marks(struct commit *commit, unsigned int mark) +void clear_commit_marks_many(int nr, struct commit **commit, unsigned int mark) { struct commit_list *list = NULL; - commit_list_insert(commit, &list); + + 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; @@ -479,32 +572,119 @@ 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 *buffer = get_commit_buffer(commit, NULL); + struct ident_split ident; + const char *ident_line; + size_t ident_len; + char *date_end; + unsigned long date; + + ident_line = find_commit_header(buffer, "author", &ident_len); + if (!ident_line) + goto fail_exit; /* no author line */ + if (split_ident_line(&ident, ident_line, ident_len) || + !ident.date_begin || !ident.date_end) + goto fail_exit; /* malformed "author" line */ + + 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: + unuse_commit_buffer(commit, 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; } } @@ -516,34 +696,33 @@ 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; /* @@ -551,26 +730,27 @@ 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 */ -/* bits #0..15 in revision.h */ +/* Remember to update object flag allocation in object.h */ #define PARENT1 (1u<<16) #define PARENT2 (1u<<17) #define STALE (1u<<18) @@ -578,58 +758,41 @@ void sort_in_topological_order(struct commit_list ** list, int lifo) static const unsigned all_flags = (PARENT1 | PARENT2 | STALE | RESULT); -static struct commit *interesting(struct commit_list *list) +static int queue_has_nonstale(struct prio_queue *queue) { - while (list) { - struct commit *commit = list->item; - list = list->next; - if (commit->object.flags & STALE) - continue; - return commit; + int i; + for (i = 0; i < queue->nr; i++) { + struct commit *commit = queue->array[i].data; + if (!(commit->object.flags & STALE)) + return 1; } - return NULL; + return 0; } -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 prio_queue queue = { compare_commits_by_commit_date }; 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); + one->object.flags |= PARENT1; + if (!n) { + commit_list_append(one, &result); + return result; } + prio_queue_put(&queue, one); - 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); for (i = 0; i < n; i++) { twos[i]->object.flags |= PARENT2; - commit_list_insert_by_date(twos[i], &list); + prio_queue_put(&queue, twos[i]); } - while (interesting(list)) { - struct commit *commit; + while (queue_has_nonstale(&queue)) { + struct commit *commit = prio_queue_get(&queue); struct commit_list *parents; - struct commit_list *next; int flags; - commit = list->item; - next = list->next; - free(list); - list = next; - flags = commit->object.flags & (PARENT1 | PARENT2 | STALE); if (flags == (PARENT1 | PARENT2)) { if (!(commit->object.flags & RESULT)) { @@ -648,13 +811,38 @@ static struct commit_list *merge_bases_many(struct commit *one, int n, struct co if (parse_commit(p)) return NULL; p->object.flags |= flags; - commit_list_insert_by_date(p, &list); + prio_queue_put(&queue, p); } } - /* Clean up the result to remove stale ones */ - free_commit_list(list); - list = result; result = NULL; + clear_prio_queue(&queue); + 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)) @@ -668,39 +856,95 @@ static struct commit_list *merge_bases_many(struct commit *one, int n, struct co 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); + if (!new) + new = bases; + else + end->next = bases; + for (k = bases; k; k = k->next) + end = k; } + ret = new; } return ret; } -struct commit_list *get_merge_bases_many(struct commit *one, - int n, - struct commit **twos, - int cleanup) +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; +} + +static struct commit_list *get_merge_bases_many_0(struct commit *one, + int n, + struct commit **twos, + int cleanup) { 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++) { @@ -710,59 +954,51 @@ 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; } /* There are more than one */ - cnt = 0; - list = result; - while (list) { - list = list->next; - cnt++; - } + cnt = commit_list_count(result); rslt = xcalloc(cnt, sizeof(*rslt)); for (list = result, i = 0; list; list = list->next) rslt[i++] = list->item; 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; } -struct commit_list *get_merge_bases(struct commit *one, struct commit *two, - int cleanup) +struct commit_list *get_merge_bases_many(struct commit *one, + int n, + struct commit **twos) { - return get_merge_bases_many(one, 1, &two, cleanup); + return get_merge_bases_many_0(one, n, twos, 1); } +struct commit_list *get_merge_bases_many_dirty(struct commit *one, + int n, + struct commit **twos) +{ + return get_merge_bases_many_0(one, n, twos, 0); +} + +struct commit_list *get_merge_bases(struct commit *one, struct commit *two) +{ + return get_merge_bases_many_0(one, 1, &two, 1); +} + +/* + * 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) @@ -772,81 +1008,72 @@ 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(num_head, sizeof(*array)); + 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; } @@ -886,17 +1113,14 @@ static int do_sign_commit(struct strbuf *buf, const char *keyid) return 0; } -int parse_signed_commit(const unsigned char *sha1, +int parse_signed_commit(const struct commit *commit, struct strbuf *payload, struct strbuf *signature) { + unsigned long size; - enum object_type type; - char *buffer = read_sha1_file(sha1, &type, &size); + const char *buffer = get_commit_buffer(commit, &size); int in_signature, saw_signature = -1; - char *line, *tail; - - if (!buffer || type != OBJ_COMMIT) - goto cleanup; + const char *line, *tail; line = buffer; tail = buffer + size; @@ -904,12 +1128,12 @@ int parse_signed_commit(const unsigned char *sha1, saw_signature = 0; while (line < tail) { const char *sig = NULL; - char *next = memchr(line, '\n', tail - line); + const char *next = memchr(line, '\n', tail - line); 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) { @@ -925,11 +1149,44 @@ int parse_signed_commit(const unsigned char *sha1, } line = next; } - cleanup: - free(buffer); + unuse_commit_buffer(commit, buffer); return saw_signature; } +int remove_signature(struct strbuf *buf) +{ + const char *line = buf->buf; + const char *tail = buf->buf + buf->len; + int in_signature = 0; + const char *sig_start = NULL; + const char *sig_end = NULL; + + while (line < tail) { + const char *next = memchr(line, '\n', tail - line); + next = next ? next + 1 : tail; + + if (in_signature && line[0] == ' ') + sig_end = next; + else if (starts_with(line, gpg_sig_header) && + line[gpg_sig_header_len] == ' ') { + sig_start = line; + sig_end = next; + in_signature = 1; + } else { + if (*line == '\n') + /* dump the whole remainder of the buffer */ + next = tail; + in_signature = 0; + } + line = next; + } + + if (sig_start) + strbuf_remove(buf, sig_start - buf->buf, sig_end - sig_start); + + return sig_start != NULL; +} + static void handle_signed_tag(struct commit *parent, struct commit_extra_header ***tail) { struct merge_remote_desc *desc; @@ -970,6 +1227,37 @@ free_return: free(buf); } +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, &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->payload = strbuf_detach(&payload, NULL); + 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) { @@ -995,14 +1283,25 @@ struct commit_extra_header *read_commit_extra_headers(struct commit *commit, { struct commit_extra_header *extra = NULL; unsigned long size; - enum object_type type; - char *buffer = read_sha1_file(commit->object.sha1, &type, &size); - if (buffer && type == OBJ_COMMIT) - extra = read_commit_extra_header_lines(buffer, size, exclude); - free(buffer); + const char *buffer = get_commit_buffer(commit, &size); + extra = read_commit_extra_header_lines(buffer, size, exclude); + unuse_commit_buffer(commit, buffer); return extra; } +void for_each_mergetag(each_mergetag_fn fn, struct commit *commit, void *data) +{ + struct commit_extra_header *extra, *to_free; + + to_free = read_commit_extra_headers(commit, NULL); + for (extra = to_free; extra; extra = extra->next) { + if (strcmp(extra->key, "mergetag")) + continue; /* not a merge tag */ + fn(commit, extra, data); + } + free_commit_extra_headers(to_free); +} + static inline int standard_header_field(const char *field, size_t len) { return ((len == 4 && !memcmp(field, "tree ", 5)) || @@ -1027,8 +1326,9 @@ 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; @@ -1081,7 +1381,8 @@ void free_commit_extra_headers(struct commit_extra_header *extra) } } -int commit_tree(const struct strbuf *msg, unsigned char *tree, +int commit_tree(const char *msg, size_t msg_len, + const unsigned char *tree, struct commit_list *parents, unsigned char *ret, const char *author, const char *sign_commit) { @@ -1089,18 +1390,129 @@ int commit_tree(const struct strbuf *msg, unsigned char *tree, int result; append_merge_tag_headers(parents, &tail); - result = commit_tree_extended(msg, tree, parents, ret, + result = commit_tree_extended(msg, msg_len, tree, parents, ret, author, sign_commit, extra); free_commit_extra_headers(extra); 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"; -int commit_tree_extended(const struct strbuf *msg, unsigned char *tree, +int commit_tree_extended(const char *msg, size_t msg_len, + const unsigned char *tree, struct commit_list *parents, unsigned char *ret, const char *author, const char *sign_commit, struct commit_extra_header *extra) @@ -1111,7 +1523,7 @@ int commit_tree_extended(const struct strbuf *msg, unsigned char *tree, assert_sha1_type(tree, OBJ_TREE); - if (memchr(msg->buf, '\0', msg->len)) + if (memchr(msg, '\0', msg_len)) return error("a NUL byte in commit log message not allowed."); /* Not having i18n.commitencoding is the same as having utf-8 */ @@ -1137,9 +1549,9 @@ 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); @@ -1150,10 +1562,10 @@ int commit_tree_extended(const struct strbuf *msg, unsigned char *tree, strbuf_addch(&buffer, '\n'); /* And add the comment */ - strbuf_addbuf(&buffer, msg); + strbuf_add(&buffer, msg, msg_len); /* 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)) @@ -1182,3 +1594,108 @@ 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)); + } +} + +const char *find_commit_header(const char *msg, const char *key, size_t *out_len) +{ + int key_len = strlen(key); + const char *line = msg; + + while (line) { + const char *eol = strchrnul(line, '\n'); + + if (line == eol) + return NULL; + + if (eol - line > key_len && + !strncmp(line, key, key_len) && + line[key_len] == ' ') { + *out_len = eol - line - key_len - 1; + return line + key_len + 1; + } + line = *eol ? eol + 1 : NULL; + } + return NULL; +} + +/* + * Inspect sb and determine the true "end" of the log message, in + * order to find where to put a new Signed-off-by: line. Ignored are + * trailing comment lines and blank lines, and also the traditional + * "Conflicts:" block that is not commented out, so that we can use + * "git commit -s --amend" on an existing commit that forgot to remove + * it. + * + * Returns the number of bytes from the tail to ignore, to be fed as + * the second parameter to append_signoff(). + */ +int ignore_non_trailer(struct strbuf *sb) +{ + int boc = 0; + int bol = 0; + int in_old_conflicts_block = 0; + + while (bol < sb->len) { + char *next_line; + + if (!(next_line = memchr(sb->buf + bol, '\n', sb->len - bol))) + next_line = sb->buf + sb->len; + else + next_line++; + + if (sb->buf[bol] == comment_line_char || sb->buf[bol] == '\n') { + /* is this the first of the run of comments? */ + if (!boc) + boc = bol; + /* otherwise, it is just continuing */ + } else if (starts_with(sb->buf + bol, "Conflicts:\n")) { + in_old_conflicts_block = 1; + if (!boc) + boc = bol; + } else if (in_old_conflicts_block && sb->buf[bol] == '\t') { + ; /* a pathname in the conflicts block */ + } else if (boc) { + /* the previous was not trailing comment */ + boc = 0; + in_old_conflicts_block = 0; + } + bol = next_line - sb->buf; + } + return boc ? sb->len - boc : 0; +} |