diff options
Diffstat (limited to 'commit.c')
| -rw-r--r-- | commit.c | 1729 |
1 files changed, 1164 insertions, 565 deletions
@@ -1,56 +1,22 @@ #include "cache.h" #include "tag.h" #include "commit.h" +#include "pkt-line.h" +#include "utf8.h" +#include "diff.h" +#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; -struct sort_node -{ - /* - * the number of children of the associated commit - * that also occur in the list being sorted. - */ - unsigned int indegree; - - /* - * reference to original list item that we will re-use - * on output. - */ - struct commit_list * list_item; - -}; - const char *commit_type = "commit"; - -struct cmt_fmt_map { - const char *n; - size_t cmp_len; - enum cmit_fmt v; -} cmt_fmts[] = { - { "raw", 1, CMIT_FMT_RAW }, - { "medium", 1, CMIT_FMT_MEDIUM }, - { "short", 1, CMIT_FMT_SHORT }, - { "email", 1, CMIT_FMT_EMAIL }, - { "full", 5, CMIT_FMT_FULL }, - { "fuller", 5, CMIT_FMT_FULLER }, - { "oneline", 1, CMIT_FMT_ONELINE }, -}; - -enum cmit_fmt get_commit_format(const char *arg) -{ - int i; - - if (!arg || !*arg) - return CMIT_FMT_DEFAULT; - if (*arg == '=') - arg++; - for (i = 0; i < ARRAY_SIZE(cmt_fmts); i++) { - if (!strncmp(arg, cmt_fmts[i].n, cmt_fmts[i].cmp_len)) - return cmt_fmts[i].v; - } - - die("invalid --pretty format: %s", arg); -} +static int commit_count; static struct commit *check_commit(struct object *obj, const unsigned char *sha1, @@ -80,36 +46,69 @@ struct commit *lookup_commit_reference(const unsigned char *sha1) return lookup_commit_reference_gently(sha1, 0); } +struct commit *lookup_commit_or_die(const unsigned char *sha1, const char *ref_name) +{ + struct commit *c = lookup_commit_reference(sha1); + if (!c) + die(_("could not parse %s"), ref_name); + if (hashcmp(sha1, c->object.sha1)) { + warning(_("%s %s is not a commit!"), + ref_name, sha1_to_hex(sha1)); + } + return c; +} + struct commit *lookup_commit(const unsigned char *sha1) { struct object *obj = lookup_object(sha1); if (!obj) { - struct commit *ret = alloc_commit_node(); - created_object(sha1, &ret->object); - ret->object.type = OBJ_COMMIT; - return ret; + 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); } -static unsigned long parse_commit_date(const char *buf) +struct commit *lookup_commit_reference_by_name(const char *name) { - unsigned long date; + unsigned char sha1[20]; + struct commit *commit; + + if (get_sha1_committish(name, sha1)) + return NULL; + commit = lookup_commit_reference(sha1); + if (!commit || parse_commit(commit)) + return NULL; + return commit; +} + +static unsigned long parse_commit_date(const char *buf, const char *tail) +{ + const char *dateptr; + if (buf + 6 >= tail) + return 0; if (memcmp(buf, "author", 6)) return 0; - while (*buf++ != '\n') + while (buf < tail && *buf++ != '\n') /* nada */; + if (buf + 9 >= tail) + return 0; if (memcmp(buf, "committer", 9)) return 0; - while (*buf++ != '>') + while (buf < tail && *buf++ != '>') + /* nada */; + if (buf >= tail) + return 0; + dateptr = buf; + while (buf < tail && *buf++ != '\n') /* nada */; - date = strtoul(buf, NULL, 10); - if (date == ULONG_MAX) - date = 0; - return date; + if (buf >= tail) + return 0; + /* dateptr < buf && buf[-1] == '\n', so strtoul will stop at buf-1 */ + return strtoul(dateptr, NULL, 10); } static struct commit_graft **commit_graft; @@ -137,7 +136,7 @@ static int commit_graft_pos(const unsigned char *sha1) int register_commit_graft(struct commit_graft *graft, int ignore_dups) { int pos = commit_graft_pos(graft->sha1); - + if (0 <= pos) { if (ignore_dups) free(graft); @@ -169,16 +168,12 @@ struct commit_graft *read_graft_line(char *buf, int len) int i; struct commit_graft *graft = NULL; - if (buf[len-1] == '\n') - buf[--len] = 0; + while (len && isspace(buf[len-1])) + buf[--len] = '\0'; if (buf[0] == '#' || buf[0] == '\0') return NULL; - if ((len + 1) % 41) { - bad_graft_data: - error("bad graft data: %s", buf); - free(graft); - return NULL; - } + if ((len + 1) % 41) + goto bad_graft_data; i = (len + 1) / 41 - 1; graft = xmalloc(sizeof(*graft) + 20 * i); graft->nr_parent = i; @@ -191,9 +186,14 @@ struct commit_graft *read_graft_line(char *buf, int len) goto bad_graft_data; } return graft; + +bad_graft_data: + error("bad graft data: %s", buf); + free(graft); + return NULL; } -int read_graft_file(const char *graft_file) +static int read_graft_file(const char *graft_file) { FILE *fp = fopen(graft_file, "r"); char buf[1024]; @@ -221,10 +221,12 @@ static void prepare_commit_graft(void) return; graft_file = get_graft_file(); read_graft_file(graft_file); + /* make sure shallows are read */ + is_repository_shallow(); commit_graft_prepared = 1; } -static struct commit_graft *lookup_commit_graft(const unsigned char *sha1) +struct commit_graft *lookup_commit_graft(const unsigned char *sha1) { int pos; prepare_commit_graft(); @@ -234,27 +236,45 @@ static struct commit_graft *lookup_commit_graft(const unsigned char *sha1) return commit_graft[pos]; } -int parse_commit_buffer(struct commit *item, void *buffer, unsigned long size) +int for_each_commit_graft(each_commit_graft_fn fn, void *cb_data) +{ + int i, ret; + for (i = ret = 0; i < commit_graft_nr && !ret; i++) + ret = fn(commit_graft[i], cb_data); + return ret; +} + +int unregister_shallow(const unsigned char *sha1) { - char *tail = buffer; - char *bufptr = buffer; + int pos = commit_graft_pos(sha1); + if (pos < 0) + return -1; + if (pos + 1 < commit_graft_nr) + memmove(commit_graft + pos, commit_graft + pos + 1, + sizeof(struct commit_graft *) + * (commit_graft_nr - pos - 1)); + commit_graft_nr--; + return 0; +} + +int parse_commit_buffer(struct commit *item, const void *buffer, unsigned long size) +{ + const char *tail = buffer; + const char *bufptr = buffer; unsigned char parent[20]; struct commit_list **pptr; struct commit_graft *graft; - unsigned n_refs = 0; if (item->object.parsed) return 0; item->object.parsed = 1; tail += size; - if (tail <= bufptr + 5 || memcmp(bufptr, "tree ", 5)) + if (tail <= bufptr + 46 || memcmp(bufptr, "tree ", 5) || bufptr[45] != '\n') return error("bogus commit object %s", sha1_to_hex(item->object.sha1)); - if (tail <= bufptr + 45 || get_sha1_hex(bufptr + 5, parent) < 0) + if (get_sha1_hex(bufptr + 5, parent) < 0) return error("bad tree pointer in commit %s", sha1_to_hex(item->object.sha1)); item->tree = lookup_tree(parent); - if (item->tree) - n_refs++; bufptr += 46; /* "tree " + "hex sha1" + "\n" */ pptr = &item->parents; @@ -267,13 +287,15 @@ int parse_commit_buffer(struct commit *item, void *buffer, unsigned long size) bufptr[47] != '\n') return error("bad parents in commit %s", sha1_to_hex(item->object.sha1)); bufptr += 48; - if (graft) + /* + * The clone is shallow if nr_parent < 0, and we must + * not traverse its real parents even when we unhide them. + */ + if (graft && (graft->nr_parent < 0 || grafts_replace_parents)) continue; new_parent = lookup_commit(parent); - if (new_parent) { + if (new_parent) pptr = &commit_list_insert(new_parent, pptr)->next; - n_refs++; - } } if (graft) { int i; @@ -283,39 +305,29 @@ int parse_commit_buffer(struct commit *item, void *buffer, unsigned long size) if (!new_parent) continue; pptr = &commit_list_insert(new_parent, pptr)->next; - n_refs++; } } - item->date = parse_commit_date(bufptr); - - if (track_object_refs) { - unsigned i = 0; - struct commit_list *p; - struct object_refs *refs = alloc_object_refs(n_refs); - if (item->tree) - refs->ref[i++] = &item->tree->object; - for (p = item->parents; p; p = p->next) - refs->ref[i++] = &p->item->object; - set_object_refs(&item->object, refs); - } + item->date = parse_commit_date(bufptr, tail); return 0; } int parse_commit(struct commit *item) { - char type[20]; + enum object_type type; void *buffer; unsigned long size; int ret; + if (!item) + return -1; if (item->object.parsed) return 0; - buffer = read_sha1_file(item->object.sha1, type, &size); + buffer = read_sha1_file(item->object.sha1, &type, &size); if (!buffer) return error("Could not read %s", sha1_to_hex(item->object.sha1)); - if (strcmp(type, commit_type)) { + if (type != OBJ_COMMIT) { free(buffer); return error("Object %s not a commit", sha1_to_hex(item->object.sha1)); @@ -329,6 +341,25 @@ int parse_commit(struct commit *item) return ret; } +int find_commit_subject(const char *commit_buffer, const char **subject) +{ + const char *eol; + const char *p = commit_buffer; + + while (*p && (*p != '\n' || p[1] != '\n')) + p++; + if (*p) { + p += 2; + for (eol = p; *eol && *eol != '\n'; eol++) + ; /* do nothing */ + } else + eol = p; + + *subject = p; + + return eol - p; +} + struct commit_list *commit_list_insert(struct commit *item, struct commit_list **list_p) { struct commit_list *new_list = xmalloc(sizeof(struct commit_list)); @@ -338,6 +369,30 @@ struct commit_list *commit_list_insert(struct commit *item, struct commit_list * return new_list; } +unsigned commit_list_count(const struct commit_list *l) +{ + unsigned c = 0; + for (; l; l = l->next ) + c++; + 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) { @@ -347,7 +402,7 @@ void free_commit_list(struct commit_list *list) } } -struct commit_list * insert_by_date(struct commit *item, struct commit_list **list) +struct commit_list * commit_list_insert_by_date(struct commit *item, struct commit_list **list) { struct commit_list **pp = list; struct commit_list *p; @@ -360,15 +415,31 @@ struct commit_list * insert_by_date(struct commit *item, struct commit_list **li return commit_list_insert(item, pp); } - -void sort_by_date(struct commit_list **list) +static int commit_list_compare_by_date(const void *a, const void *b) { - struct commit_list *ret = NULL; - while (*list) { - insert_by_date((*list)->item, &ret); - *list = (*list)->next; - } - *list = ret; + 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) +{ + *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, @@ -383,485 +454,283 @@ struct commit *pop_most_recent_commit(struct commit_list **list, while (parents) { struct commit *commit = parents->item; - parse_commit(commit); - if (!(commit->object.flags & mark)) { + if (!parse_commit(commit) && !(commit->object.flags & mark)) { commit->object.flags |= mark; - insert_by_date(commit, list); + commit_list_insert_by_date(commit, list); } parents = parents->next; } 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) { - struct commit_list *parents; + while (commit) { + struct commit_list *parents; - commit->object.flags &= ~mark; - parents = commit->parents; - while (parents) { - struct commit *parent = parents->item; + if (!(mark & commit->object.flags)) + return; - /* Have we already cleared this? */ - if (mark & parent->object.flags) - clear_commit_marks(parent, mark); - parents = parents->next; + commit->object.flags &= ~mark; + + parents = commit->parents; + if (!parents) + return; + + while ((parents = parents->next)) + commit_list_insert(parents->item, plist); + + commit = commit->parents->item; } } -/* - * Generic support for pretty-printing the header - */ -static int get_one_line(const char *msg, unsigned long len) +void clear_commit_marks_many(int nr, struct commit **commit, unsigned int mark) { - int ret = 0; + struct commit_list *list = NULL; - while (len--) { - char c = *msg++; - if (!c) - break; - ret++; - if (c == '\n') - break; + while (nr--) { + commit_list_insert(*commit, &list); + commit++; } - return ret; + while (list) + clear_commit_marks_1(&list, pop_commit(&list), mark); } -static int is_rfc2047_special(char ch) +void clear_commit_marks(struct commit *commit, unsigned int mark) { - return ((ch & 0x80) || (ch == '=') || (ch == '?') || (ch == '_')); + clear_commit_marks_many(1, &commit, mark); } -static int add_rfc2047(char *buf, const char *line, int len) +void clear_commit_marks_for_object_array(struct object_array *a, unsigned mark) { - char *bp = buf; - int i, needquote; - static const char q_utf8[] = "=?utf-8?q?"; - - for (i = needquote = 0; !needquote && i < len; i++) { - unsigned ch = line[i]; - if (ch & 0x80) - needquote++; - if ((i + 1 < len) && - (ch == '=' && line[i+1] == '?')) - needquote++; + struct object *object; + struct commit *commit; + unsigned int i; + + for (i = 0; i < a->nr; i++) { + object = a->objects[i].item; + commit = lookup_commit_reference_gently(object->sha1, 1); + if (commit) + clear_commit_marks(commit, mark); } - if (!needquote) - return sprintf(buf, "%.*s", len, line); - - memcpy(bp, q_utf8, sizeof(q_utf8)-1); - bp += sizeof(q_utf8)-1; - for (i = 0; i < len; i++) { - unsigned ch = line[i] & 0xFF; - if (is_rfc2047_special(ch)) { - sprintf(bp, "=%02X", ch); - bp += 3; - } - else if (ch == ' ') - *bp++ = '_'; - else - *bp++ = ch; - } - memcpy(bp, "?=", 2); - bp += 2; - return bp - buf; } -static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf, const char *line) +struct commit *pop_commit(struct commit_list **stack) { - char *date; - int namelen; - unsigned long time; - int tz, ret; - const char *filler = " "; + struct commit_list *top = *stack; + struct commit *item = top ? top->item : NULL; - if (fmt == CMIT_FMT_ONELINE) - return 0; - date = strchr(line, '>'); - if (!date) - return 0; - namelen = ++date - line; - time = strtoul(date, &date, 10); - tz = strtol(date, NULL, 10); - - if (fmt == CMIT_FMT_EMAIL) { - char *name_tail = strchr(line, '<'); - int display_name_length; - if (!name_tail) - return 0; - while (line < name_tail && isspace(name_tail[-1])) - name_tail--; - display_name_length = name_tail - line; - filler = ""; - strcpy(buf, "From: "); - ret = strlen(buf); - ret += add_rfc2047(buf + ret, line, display_name_length); - memcpy(buf + ret, name_tail, namelen - display_name_length); - ret += namelen - display_name_length; - buf[ret++] = '\n'; - } - else { - ret = sprintf(buf, "%s: %.*s%.*s\n", what, - (fmt == CMIT_FMT_FULLER) ? 4 : 0, - filler, namelen, line); - } - switch (fmt) { - case CMIT_FMT_MEDIUM: - ret += sprintf(buf + ret, "Date: %s\n", show_date(time, tz)); - break; - case CMIT_FMT_EMAIL: - ret += sprintf(buf + ret, "Date: %s\n", - show_rfc2822_date(time, tz)); - break; - case CMIT_FMT_FULLER: - ret += sprintf(buf + ret, "%sDate: %s\n", what, show_date(time, tz)); - break; - default: - /* notin' */ - break; + if (top) { + *stack = top->next; + free(top); } - return ret; -} - -static int is_empty_line(const char *line, int *len_p) -{ - int len = *len_p; - while (len && isspace(line[len-1])) - len--; - *len_p = len; - return !len; + return item; } -static int add_merge_info(enum cmit_fmt fmt, char *buf, const struct commit *commit, int abbrev) -{ - struct commit_list *parent = commit->parents; - int offset; - - if ((fmt == CMIT_FMT_ONELINE) || (fmt == CMIT_FMT_EMAIL) || - !parent || !parent->next) - return 0; - - offset = sprintf(buf, "Merge:"); +/* + * Topological sort support + */ - while (parent) { - struct commit *p = parent->item; - const char *hex = abbrev - ? find_unique_abbrev(p->object.sha1, abbrev) - : sha1_to_hex(p->object.sha1); - const char *dots = (abbrev && strlen(hex) != 40) ? "..." : ""; - parent = parent->next; +/* count number of children that have not been emitted */ +define_commit_slab(indegree_slab, int); - offset += sprintf(buf + offset, " %s%s", hex, dots); - } - buf[offset++] = '\n'; - return offset; -} +/* record author-date for each commit object */ +define_commit_slab(author_date_slab, unsigned long); -unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit, unsigned long len, char *buf, unsigned long space, int abbrev, const char *subject, const char *after_subject) +static void record_author_date(struct author_date_slab *author_date, + struct commit *commit) { - int hdr = 1, body = 0; - unsigned long offset = 0; - int indent = 4; - int parents_shown = 0; - const char *msg = commit->buffer; - int plain_non_ascii = 0; - - if (fmt == CMIT_FMT_ONELINE || fmt == CMIT_FMT_EMAIL) - indent = 0; + const char *buf, *line_end; + char *buffer = NULL; + struct ident_split ident; + char *date_end; + unsigned long date; - /* After-subject is used to pass in Content-Type: multipart - * MIME header; in that case we do not have to do the - * plaintext content type even if the commit message has - * non 7-bit ASCII character. Otherwise, check if we need - * to say this is not a 7-bit ASCII. - */ - if (fmt == CMIT_FMT_EMAIL && !after_subject) { - int i, ch, in_body; - - for (in_body = i = 0; (ch = msg[i]) && i < len; i++) { - if (!in_body) { - /* author could be non 7-bit ASCII but - * the log may so; skip over the - * header part first. - */ - if (ch == '\n' && - i + 1 < len && msg[i+1] == '\n') - in_body = 1; - } - else if (ch & 0x80) { - plain_non_ascii = 1; - break; - } - } + if (!commit->buffer) { + unsigned long size; + enum object_type type; + buffer = read_sha1_file(commit->object.sha1, &type, &size); + if (!buffer) + return; } - for (;;) { - const char *line = msg; - int linelen = get_one_line(msg, len); - - if (!linelen) - break; - - /* - * We want some slop for indentation and a possible - * final "...". Thus the "+ 20". - */ - if (offset + linelen + 20 > space) { - memcpy(buf + offset, " ...\n", 8); - offset += 8; - break; - } - - msg += linelen; - len -= linelen; - if (hdr) { - if (linelen == 1) { - hdr = 0; - if ((fmt != CMIT_FMT_ONELINE) && !subject) - buf[offset++] = '\n'; - continue; - } - if (fmt == CMIT_FMT_RAW) { - memcpy(buf + offset, line, linelen); - offset += linelen; - continue; - } - if (!memcmp(line, "parent ", 7)) { - if (linelen != 48) - die("bad parent line in commit"); - continue; - } - - if (!parents_shown) { - offset += add_merge_info(fmt, buf + offset, - commit, abbrev); - parents_shown = 1; - continue; - } - /* - * MEDIUM == DEFAULT shows only author with dates. - * FULL shows both authors but not dates. - * FULLER shows both authors and dates. - */ - if (!memcmp(line, "author ", 7)) - offset += add_user_info("Author", fmt, - buf + offset, - line + 7); - if (!memcmp(line, "committer ", 10) && - (fmt == CMIT_FMT_FULL || fmt == CMIT_FMT_FULLER)) - offset += add_user_info("Commit", fmt, - buf + offset, - line + 10); + 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 (!subject) - body = 1; - - if (is_empty_line(line, &linelen)) { - if (!body) - continue; - if (subject) - continue; - if (fmt == CMIT_FMT_SHORT) - break; - } - - if (subject) { - int slen = strlen(subject); - memcpy(buf + offset, subject, slen); - offset += slen; - offset += add_rfc2047(buf + offset, line, linelen); - } - else { - memset(buf + offset, ' ', indent); - memcpy(buf + offset + indent, line, linelen); - offset += linelen + indent; - } - buf[offset++] = '\n'; - if (fmt == CMIT_FMT_ONELINE) - break; - if (subject && plain_non_ascii) { - static const char header[] = - "Content-Type: text/plain; charset=UTF-8\n" - "Content-Transfer-Encoding: 8bit\n"; - memcpy(buf + offset, header, sizeof(header)-1); - offset += sizeof(header)-1; - } - if (after_subject) { - int slen = strlen(after_subject); - if (slen > space - offset - 1) - slen = space - offset - 1; - memcpy(buf + offset, after_subject, slen); - offset += slen; - after_subject = NULL; - } - subject = NULL; + 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; } - while (offset && isspace(buf[offset-1])) - offset--; - /* Make sure there is an EOLN for the non-oneline case */ - if (fmt != CMIT_FMT_ONELINE) - buf[offset++] = '\n'; - /* - * make sure there is another EOLN to separate the headers from whatever - * body the caller appends if we haven't already written a body - */ - if (fmt == CMIT_FMT_EMAIL && !body) - buf[offset++] = '\n'; - buf[offset] = '\0'; - return offset; -} -struct commit *pop_commit(struct commit_list **stack) -{ - struct commit_list *top = *stack; - struct commit *item = top ? top->item : NULL; + 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; - if (top) { - *stack = top->next; - free(top); - } - return item; +fail_exit: + free(buffer); } -int count_parents(struct commit * commit) +static int compare_commits_by_author_date(const void *a_, const void *b_, + void *cb_data) { - int count; - struct commit_list * parents = commit->parents; - for (count = 0; parents; parents = parents->next,count++) - ; - return count; -} + 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)); -void topo_sort_default_setter(struct commit *c, void *data) -{ - c->util = data; + /* newer commits with larger date first */ + if (a_date < b_date) + return 1; + else if (a_date > b_date) + return -1; + return 0; } -void *topo_sort_default_getter(struct commit *c) +int compare_commits_by_commit_date(const void *a_, const void *b_, void *unused) { - return c->util; + 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) { - sort_in_topological_order_fn(list, lifo, topo_sort_default_setter, - topo_sort_default_getter); -} + struct commit_list *next, *orig = *list; + struct commit_list **pptr; + struct indegree_slab indegree; + struct prio_queue queue; + struct commit *commit; + struct author_date_slab author_date; -void sort_in_topological_order_fn(struct commit_list ** list, int lifo, - topo_sort_set_fn_t setter, - topo_sort_get_fn_t getter) -{ - struct commit_list * next = *list; - struct commit_list * work = NULL, **insert; - struct commit_list ** pptr = list; - struct sort_node * nodes; - struct sort_node * next_nodes; - int count = 0; + if (!orig) + return; + *list = NULL; + + init_indegree_slab(&indegree); + memset(&queue, '\0', sizeof(queue)); - /* determine the size of the list */ - while (next) { - next = next->next; - count++; + 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; } - - if (!count) - return; - /* allocate an array to help sort the list */ - nodes = xcalloc(count, sizeof(*nodes)); - /* link the list to the array */ - next_nodes = nodes; - next=*list; - while (next) { - next_nodes->list_item = next; - setter(next->item, next_nodes); - next_nodes++; - next = next->next; + + /* Mark them and clear the indegree */ + for (next = orig; next; next = next->next) { + struct commit *commit = next->item; + *(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 */ - next=*list; - while (next) { - struct commit_list * parents = next->item->parents; + for (next = orig; next; next = next->next) { + struct commit_list *parents = next->item->parents; while (parents) { - struct commit * parent=parents->item; - struct sort_node * pn = (struct sort_node *) getter(parent); + struct commit *parent = parents->item; + int *pi = indegree_slab_at(&indegree, parent); - if (pn) - pn->indegree++; - parents=parents->next; - } - next=next->next; - } - /* - * find the tips - * - * tips are nodes not reachable from any other node in the list - * - * the tips serve as a starting set for the work queue. - */ - next=*list; - insert = &work; - while (next) { - struct sort_node * node = (struct sort_node *) getter(next->item); - - if (node->indegree == 0) { - insert = &commit_list_insert(next->item, insert)->next; + if (*pi) + (*pi)++; + parents = parents->next; } - next=next->next; } - /* process the list in topological order */ - if (!lifo) - sort_by_date(&work); - while (work) { - struct commit * work_item = pop_commit(&work); - struct sort_node * work_node = (struct sort_node *) getter(work_item); - struct commit_list * parents = work_item->parents; + /* + * find the tips + * + * tips are nodes not reachable from any other node in the list + * + * the tips serve as a starting set for the work queue. + */ + for (next = orig; next; next = next->next) { + struct commit *commit = next->item; - while (parents) { - struct commit * parent=parents->item; - struct sort_node * pn = (struct sort_node *) getter(parent); - - if (pn) { - /* - * parents are only enqueued for emission - * when all their children have been emitted thereby - * guaranteeing topological order. - */ - pn->indegree--; - if (!pn->indegree) { - if (!lifo) - insert_by_date(parent, &work); - else - commit_list_insert(parent, &work); - } - } - parents=parents->next; + if (*(indegree_slab_at(&indegree, commit)) == 1) + prio_queue_put(&queue, commit); + } + + /* + * 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 ((commit = prio_queue_get(&queue)) != NULL) { + struct commit_list *parents; + + for (parents = commit->parents; parents ; parents = parents->next) { + struct commit *parent = parents->item; + int *pi = indegree_slab_at(&indegree, parent); + + if (!*pi) + continue; + + /* + * parents are only enqueued for emission + * when all their children have been emitted thereby + * guaranteeing topological order. + */ + 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. - */ - *pptr = work_node->list_item; - pptr = &(*pptr)->next; - *pptr = NULL; - setter(work_item, NULL); + * all children of commit have already been + * emitted. we can emit it now. + */ + *(indegree_slab_at(&indegree, commit)) = 0; + + pptr = &commit_list_insert(commit, pptr)->next; } - free(nodes); + + clear_indegree_slab(&indegree); + clear_prio_queue(&queue); + if (sort_order == REV_SORT_BY_AUTHOR_DATE) + clear_author_date_slab(&author_date); } -/* merge-rebase stuff */ +/* merge-base stuff */ + +/* bits #0..15 in revision.h */ +#define PARENT1 (1u<<16) +#define PARENT2 (1u<<17) +#define STALE (1u<<18) +#define RESULT (1u<<19) -/* bits #0..7 in revision.h */ -#define PARENT1 (1u<< 8) -#define PARENT2 (1u<< 9) -#define STALE (1u<<10) -#define RESULT (1u<<11) +static const unsigned all_flags = (PARENT1 | PARENT2 | STALE | RESULT); static struct commit *interesting(struct commit_list *list) { @@ -875,41 +744,38 @@ static struct commit *interesting(struct commit_list *list) return NULL; } -static struct commit_list *merge_bases(struct commit *one, struct commit *two) +/* 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; - - if (one == two) - /* We do not mark this even with RESULT so we do not - * have to clean it up. - */ - return commit_list_insert(one, &result); - - parse_commit(one); - parse_commit(two); + int i; one->object.flags |= PARENT1; - two->object.flags |= PARENT2; - insert_by_date(one, &list); - insert_by_date(two, &list); + 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); + } while (interesting(list)) { struct commit *commit; struct commit_list *parents; - struct commit_list *n; + struct commit_list *next; int flags; commit = list->item; - n = list->next; + next = list->next; free(list); - list = n; + list = next; flags = commit->object.flags & (PARENT1 | PARENT2 | STALE); if (flags == (PARENT1 | PARENT2)) { if (!(commit->object.flags & RESULT)) { commit->object.flags |= RESULT; - insert_by_date(commit, &result); + commit_list_insert_by_date(commit, &result); } /* Mark parents of a found merge stale */ flags |= STALE; @@ -920,41 +786,153 @@ static struct commit_list *merge_bases(struct commit *one, struct commit *two) parents = parents->next; if ((p->object.flags & flags) == flags) continue; - parse_commit(p); + if (parse_commit(p)) + return NULL; p->object.flags |= flags; - insert_by_date(p, &list); + commit_list_insert_by_date(p, &list); } } - /* Clean up the result to remove stale ones */ - list = result; result = NULL; + free_commit_list(list); + 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 *n = list->next; + struct commit_list *next = list->next; if (!(list->item->object.flags & STALE)) - insert_by_date(list->item, &result); + commit_list_insert_by_date(list->item, &result); free(list); - list = n; + list = next; } return result; } -struct commit_list *get_merge_bases(struct commit *one, - struct commit *two, - int cleanup) +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; + } + } + 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, + int cleanup) { - const unsigned all_flags = (PARENT1 | PARENT2 | STALE | RESULT); struct commit_list *list; struct commit **rslt; struct commit_list *result; - int cnt, i, j; + int cnt, i; - result = merge_bases(one, two); - if (one == two) - return result; + result = merge_bases_many(one, n, twos); + for (i = 0; i < n; i++) { + if (one == twos[i]) + return result; + } if (!result || !result->next) { if (cleanup) { clear_commit_marks(one, all_flags); - clear_commit_marks(two, all_flags); + clear_commit_marks_many(n, twos, all_flags); } return result; } @@ -972,29 +950,650 @@ struct commit_list *get_merge_bases(struct commit *one, free_commit_list(result); clear_commit_marks(one, all_flags); - clear_commit_marks(two, all_flags); - for (i = 0; i < cnt - 1; i++) { - for (j = i+1; j < cnt; j++) { - if (!rslt[i] || !rslt[j]) + clear_commit_marks_many(n, twos, all_flags); + + cnt = remove_redundant(rslt, cnt); + result = NULL; + 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) +{ + 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) + return 1; + while (with_commit) { + struct commit *other; + + other = with_commit->item; + with_commit = with_commit->next; + if (in_merge_bases(other, commit)) + return 1; + } + return 0; +} + +/* + * 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; + 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 **array; + int num_head, i; + + if (!heads) + return NULL; + + /* 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; + 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; + } + } + num_head = remove_redundant(array, num_head); + for (i = 0; i < num_head; i++) + tail = &commit_list_insert(array[i], tail)->next; + return result; +} + +static const char gpg_sig_header[] = "gpgsig"; +static const int gpg_sig_header_len = sizeof(gpg_sig_header) - 1; + +static int do_sign_commit(struct strbuf *buf, const char *keyid) +{ + struct strbuf sig = STRBUF_INIT; + int inspos, copypos; + + /* find the end of the header */ + inspos = strstr(buf->buf, "\n\n") - buf->buf + 1; + + if (!keyid || !*keyid) + keyid = get_signing_key(); + if (sign_buffer(buf, &sig, keyid)) { + strbuf_release(&sig); + return -1; + } + + for (copypos = 0; sig.buf[copypos]; ) { + const char *bol = sig.buf + copypos; + const char *eol = strchrnul(bol, '\n'); + int len = (eol - bol) + !!*eol; + + if (!copypos) { + strbuf_insert(buf, inspos, gpg_sig_header, gpg_sig_header_len); + inspos += gpg_sig_header_len; + } + strbuf_insert(buf, inspos++, " ", 1); + strbuf_insert(buf, inspos, bol, len); + inspos += len; + copypos += len; + } + strbuf_release(&sig); + return 0; +} + +int parse_signed_commit(const unsigned char *sha1, + struct strbuf *payload, struct strbuf *signature) +{ + unsigned long size; + enum object_type type; + char *buffer = read_sha1_file(sha1, &type, &size); + int in_signature, saw_signature = -1; + char *line, *tail; + + if (!buffer || type != OBJ_COMMIT) + goto cleanup; + + line = buffer; + tail = buffer + size; + in_signature = 0; + saw_signature = 0; + while (line < tail) { + const char *sig = NULL; + 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) && + line[gpg_sig_header_len] == ' ') + sig = line + gpg_sig_header_len + 1; + if (sig) { + strbuf_add(signature, sig, next - sig); + saw_signature = 1; + in_signature = 1; + } else { + if (*line == '\n') + /* dump the whole remainder of the buffer */ + next = tail; + strbuf_add(payload, line, next - line); + in_signature = 0; + } + line = next; + } + cleanup: + free(buffer); + return saw_signature; +} + +static void handle_signed_tag(struct commit *parent, struct commit_extra_header ***tail) +{ + struct merge_remote_desc *desc; + struct commit_extra_header *mergetag; + char *buf; + unsigned long size, len; + enum object_type type; + + desc = merge_remote_util(parent); + if (!desc || !desc->obj) + return; + buf = read_sha1_file(desc->obj->sha1, &type, &size); + if (!buf || type != OBJ_TAG) + goto free_return; + len = parse_signature(buf, size); + if (size == len) + goto free_return; + /* + * We could verify this signature and either omit the tag when + * it does not validate, but the integrator may not have the + * public key of the signer of the tag he is merging, while a + * later auditor may have it while auditing, so let's not run + * verify-signed-buffer here for now... + * + * if (verify_signed_buffer(buf, len, buf + len, size - len, ...)) + * warn("warning: signed tag unverified."); + */ + mergetag = xcalloc(1, sizeof(*mergetag)); + mergetag->key = xstrdup("mergetag"); + mergetag->value = buf; + mergetag->len = size; + + **tail = mergetag; + *tail = &mergetag->next; + return; + +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; - result = merge_bases(rslt[i], 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; - } + 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); } } +} - /* Surviving ones in rslt[] are the independent results */ - result = NULL; - for (i = 0; i < cnt; i++) { - if (rslt[i]) - insert_by_date(rslt[i], &result); +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) +{ + while (parents) { + struct commit *parent = parents->item; + handle_signed_tag(parent, tail); + parents = parents->next; } - free(rslt); +} + +static void add_extra_header(struct strbuf *buffer, + struct commit_extra_header *extra) +{ + strbuf_addstr(buffer, extra->key); + if (extra->len) + strbuf_add_lines(buffer, " ", extra->value, extra->len); + else + strbuf_addch(buffer, '\n'); +} + +struct commit_extra_header *read_commit_extra_headers(struct commit *commit, + const char **exclude) +{ + 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); + return extra; +} + +static inline int standard_header_field(const char *field, size_t len) +{ + return ((len == 4 && !memcmp(field, "tree ", 5)) || + (len == 6 && !memcmp(field, "parent ", 7)) || + (len == 6 && !memcmp(field, "author ", 7)) || + (len == 9 && !memcmp(field, "committer ", 10)) || + (len == 8 && !memcmp(field, "encoding ", 9))); +} + +static int excluded_header_field(const char *field, size_t len, const char **exclude) +{ + if (!exclude) + return 0; + + while (*exclude) { + size_t xlen = strlen(*exclude); + if (len == xlen && + !memcmp(field, *exclude, xlen) && field[xlen] == ' ') + return 1; + exclude++; + } + return 0; +} + +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; + struct strbuf buf = STRBUF_INIT; + + for (line = buffer, eob = line + size; + line < eob && *line != '\n'; + line = next) { + next = memchr(line, '\n', eob - line); + next = next ? next + 1 : eob; + if (*line == ' ') { + /* continuation */ + if (it) + strbuf_add(&buf, line + 1, next - (line + 1)); + continue; + } + if (it) + it->value = strbuf_detach(&buf, &it->len); + strbuf_reset(&buf); + it = NULL; + + eof = strchr(line, ' '); + if (next <= eof) + eof = next; + + if (standard_header_field(line, eof - line) || + excluded_header_field(line, eof - line, exclude)) + continue; + + it = xcalloc(1, sizeof(*it)); + it->key = xmemdupz(line, eof-line); + *tail = it; + tail = &it->next; + if (eof + 1 < next) + strbuf_add(&buf, eof + 1, next - (eof + 1)); + } + if (it) + it->value = strbuf_detach(&buf, &it->len); + return extra; +} + +void free_commit_extra_headers(struct commit_extra_header *extra) +{ + while (extra) { + struct commit_extra_header *next = extra->next; + free(extra->key); + free(extra->value); + free(extra); + extra = next; + } +} + +int commit_tree(const struct strbuf *msg, unsigned char *tree, + struct commit_list *parents, unsigned char *ret, + const char *author, const char *sign_commit) +{ + struct commit_extra_header *extra = NULL, **tail = &extra; + int result; + + append_merge_tag_headers(parents, &tail); + result = commit_tree_extended(msg, 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 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, + struct commit_list *parents, unsigned char *ret, + const char *author, const char *sign_commit, + struct commit_extra_header *extra) +{ + int result; + int encoding_is_utf8; + struct strbuf buffer; + + assert_sha1_type(tree, OBJ_TREE); + + if (memchr(msg->buf, '\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 */ + encoding_is_utf8 = is_encoding_utf8(git_commit_encoding); + + strbuf_init(&buffer, 8192); /* should avoid reallocs for the headers */ + strbuf_addf(&buffer, "tree %s\n", sha1_to_hex(tree)); + + /* + * NOTE! This ordering means that the same exact tree merged with a + * different order of parents will be a _different_ changeset even + * if everything else stays the same. + */ + while (parents) { + struct commit_list *next = parents->next; + struct commit *parent = parents->item; + + strbuf_addf(&buffer, "parent %s\n", + sha1_to_hex(parent->object.sha1)); + free(parents); + parents = next; + } + + /* Person/date information */ + if (!author) + author = git_author_info(IDENT_STRICT); + strbuf_addf(&buffer, "author %s\n", author); + strbuf_addf(&buffer, "committer %s\n", git_committer_info(IDENT_STRICT)); + if (!encoding_is_utf8) + strbuf_addf(&buffer, "encoding %s\n", git_commit_encoding); + + while (extra) { + add_extra_header(&buffer, extra); + extra = extra->next; + } + strbuf_addch(&buffer, '\n'); + + /* And add the comment */ + strbuf_addbuf(&buffer, msg); + + /* And check the encoding */ + if (encoding_is_utf8 && !verify_utf8(&buffer)) + fprintf(stderr, commit_utf8_warn); + + if (sign_commit && do_sign_commit(&buffer, sign_commit)) + return -1; + + result = write_sha1_file(buffer.buf, buffer.len, commit_type, ret); + strbuf_release(&buffer); return result; } + +struct commit *get_merge_parent(const char *name) +{ + struct object *obj; + struct commit *commit; + unsigned char sha1[20]; + if (get_sha1(name, sha1)) + return NULL; + obj = parse_object(sha1); + commit = (struct commit *)peel_to_type(name, 0, obj, OBJ_COMMIT); + if (commit && !commit->util) { + struct merge_remote_desc *desc; + desc = xmalloc(sizeof(*desc)); + desc->obj = obj; + desc->name = strdup(name); + commit->util = desc; + } + 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)); + } +} |