diff options
Diffstat (limited to 'commit.c')
| -rw-r--r-- | commit.c | 366 |
1 files changed, 284 insertions, 82 deletions
@@ -1,10 +1,13 @@ -#include "cache.h" +#include "git-compat-util.h" #include "tag.h" #include "commit.h" #include "commit-graph.h" +#include "environment.h" +#include "gettext.h" +#include "hex.h" #include "repository.h" -#include "object-store.h" -#include "pkt-line.h" +#include "object-name.h" +#include "object-store-ll.h" #include "utf8.h" #include "diff.h" #include "revision.h" @@ -19,9 +22,12 @@ #include "advice.h" #include "refs.h" #include "commit-reach.h" -#include "run-command.h" +#include "setup.h" #include "shallow.h" +#include "tree.h" #include "hook.h" +#include "parse.h" +#include "object-file-convert.h" static struct commit_extra_header *read_commit_extra_header_lines(const char *buf, size_t len, const char **); @@ -80,10 +86,10 @@ struct commit *lookup_commit_reference_by_name(const char *name) struct object_id oid; struct commit *commit; - if (get_oid_committish(name, &oid)) + if (repo_get_oid_committish(the_repository, name, &oid)) return NULL; commit = lookup_commit_reference(the_repository, &oid); - if (parse_commit(commit)) + if (repo_parse_commit(the_repository, commit)) return NULL; return commit; } @@ -91,6 +97,7 @@ struct commit *lookup_commit_reference_by_name(const char *name) static timestamp_t parse_commit_date(const char *buf, const char *tail) { const char *dateptr; + const char *eol; if (buf + 6 >= tail) return 0; @@ -102,16 +109,56 @@ static timestamp_t parse_commit_date(const char *buf, const char *tail) return 0; if (memcmp(buf, "committer", 9)) return 0; - while (buf < tail && *buf++ != '>') - /* nada */; - if (buf >= tail) + + /* + * Jump to end-of-line so that we can walk backwards to find the + * end-of-email ">". This is more forgiving of malformed cases + * because unexpected characters tend to be in the name and email + * fields. + */ + eol = memchr(buf, '\n', tail - buf); + if (!eol) return 0; - dateptr = buf; - while (buf < tail && *buf++ != '\n') - /* nada */; - if (buf >= tail) + dateptr = eol; + while (dateptr > buf && dateptr[-1] != '>') + dateptr--; + if (dateptr == buf) + return 0; + + /* + * Trim leading whitespace, but make sure we have at least one + * non-whitespace character, as parse_timestamp() will otherwise walk + * right past the newline we found in "eol" when skipping whitespace + * itself. + * + * In theory it would be sufficient to allow any character not matched + * by isspace(), but there's a catch: our isspace() does not + * necessarily match the behavior of parse_timestamp(), as the latter + * is implemented by system routines which match more exotic control + * codes, or even locale-dependent sequences. + * + * Since we expect the timestamp to be a number, we can check for that. + * Anything else (e.g., a non-numeric token like "foo") would just + * cause parse_timestamp() to return 0 anyway. + */ + while (dateptr < eol && isspace(*dateptr)) + dateptr++; + if (!isdigit(*dateptr) && *dateptr != '-') return 0; - /* dateptr < buf && buf[-1] == '\n', so parsing will stop at buf-1 */ + + /* + * We know there is at least one digit (or dash), so we'll begin + * parsing there and stop at worst case at eol. + * + * Note that we may feed parse_timestamp() extra characters here if the + * commit is malformed, and it will parse as far as it can. For + * example, "123foo456" would return "123". That might be questionable + * (versus returning "0"), but it would help in a hypothetical case + * like "123456+0100", where the whitespace from the timezone is + * missing. Since such syntactic errors may be baked into history and + * hard to correct now, let's err on trying to make our best guess + * here, rather than insist on perfect syntax. + */ return parse_timestamp(dateptr, NULL, 10); } @@ -382,7 +429,7 @@ struct tree *repo_get_commit_tree(struct repository *r, struct object_id *get_commit_tree_oid(const struct commit *commit) { - struct tree *tree = get_commit_tree(commit); + struct tree *tree = repo_get_commit_tree(the_repository, commit); return tree ? &tree->object.oid : NULL; } @@ -469,7 +516,7 @@ int parse_commit_buffer(struct repository *r, struct commit *item, const void *b * 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)) + if (graft && (graft->nr_parent < 0 || !grafts_keep_true_parents)) continue; new_parent = lookup_commit(r, &parent); if (!new_parent) @@ -525,8 +572,21 @@ int repo_parse_commit_internal(struct repository *r, return -1; if (item->object.parsed) return 0; - if (use_commit_graph && parse_commit_in_graph(r, item)) + if (use_commit_graph && parse_commit_in_graph(r, item)) { + static int commit_graph_paranoia = -1; + + if (commit_graph_paranoia == -1) + commit_graph_paranoia = git_env_bool(GIT_COMMIT_GRAPH_PARANOIA, 0); + + if (commit_graph_paranoia && !has_object(r, &item->object.oid, 0)) { + unparse_commit(r, &item->object.oid); + return quiet_on_missing ? -1 : + error(_("commit %s exists in commit-graph but not in the object database"), + oid_to_hex(&item->object.oid)); + } + return 0; + } if (oid_object_info_extended(r, &item->object.oid, &oi, flags) < 0) return quiet_on_missing ? -1 : @@ -555,7 +615,7 @@ int repo_parse_commit_gently(struct repository *r, void parse_commit_or_die(struct commit *item) { - if (parse_commit(item)) + if (repo_parse_commit(the_repository, item)) die("unable to parse commit %s", item ? oid_to_hex(&item->object.oid) : "(null)"); } @@ -688,7 +748,7 @@ struct commit *pop_most_recent_commit(struct commit_list **list, while (parents) { struct commit *commit = parents->item; - if (!parse_commit(commit) && !(commit->object.flags & mark)) { + if (!repo_parse_commit(the_repository, commit) && !(commit->object.flags & mark)) { commit->object.flags |= mark; commit_list_insert_by_date(commit, list); } @@ -762,7 +822,8 @@ define_commit_slab(author_date_slab, timestamp_t); void record_author_date(struct author_date_slab *author_date, struct commit *commit) { - const char *buffer = get_commit_buffer(commit, NULL); + const char *buffer = repo_get_commit_buffer(the_repository, commit, + NULL); struct ident_split ident; const char *ident_line; size_t ident_len; @@ -782,7 +843,7 @@ void record_author_date(struct author_date_slab *author_date, *(author_date_slab_at(author_date, commit)) = date; fail_exit: - unuse_commit_buffer(commit, buffer); + repo_unuse_commit_buffer(the_repository, commit, buffer); } int compare_commits_by_author_date(const void *a_, const void *b_, @@ -801,7 +862,8 @@ int compare_commits_by_author_date(const void *a_, const void *b_, return 0; } -int compare_commits_by_gen_then_commit_date(const void *a_, const void *b_, void *unused) +int compare_commits_by_gen_then_commit_date(const void *a_, const void *b_, + void *unused UNUSED) { const struct commit *a = a_, *b = b_; const timestamp_t generation_a = commit_graph_generation(a), @@ -821,7 +883,8 @@ int compare_commits_by_gen_then_commit_date(const void *a_, const void *b_, void return 0; } -int compare_commits_by_commit_date(const void *a_, const void *b_, void *unused) +int compare_commits_by_commit_date(const void *a_, const void *b_, + void *unused UNUSED) { const struct commit *a = a_, *b = b_; /* newer commits with larger date first */ @@ -963,7 +1026,7 @@ static void add_one_commit(struct object_id *oid, struct rev_collect *revs) commit = lookup_commit(the_repository, oid); if (!commit || (commit->object.flags & TMP_MARK) || - parse_commit(commit)) + repo_parse_commit(the_repository, commit)) return; ALLOC_GROW(revs->commit, revs->nr + 1, revs->alloc); @@ -990,12 +1053,13 @@ struct commit *get_fork_point(const char *refname, struct commit *commit) { struct object_id oid; struct rev_collect revs; - struct commit_list *bases; + struct commit_list *bases = NULL; int i; struct commit *ret = NULL; char *full_refname; - switch (dwim_ref(refname, strlen(refname), &oid, &full_refname, 0)) { + switch (repo_dwim_ref(the_repository, refname, strlen(refname), &oid, + &full_refname, 0)) { case 0: die("No such ref: '%s'", refname); case 1: @@ -1014,7 +1078,9 @@ struct commit *get_fork_point(const char *refname, struct commit *commit) for (i = 0; i < revs.nr; i++) revs.commit[i]->object.flags &= ~TMP_MARK; - bases = get_merge_bases_many(commit, revs.nr, revs.commit); + if (repo_get_merge_bases_many(the_repository, commit, revs.nr, + revs.commit, &bases) < 0) + exit(128); /* * There should be one and only one merge base, when we found @@ -1048,12 +1114,11 @@ static const char *gpg_sig_headers[] = { "gpgsig-sha256", }; -int sign_with_header(struct strbuf *buf, const char *keyid) +int add_header_signature(struct strbuf *buf, struct strbuf *sig, const struct git_hash_algo *algo) { - struct strbuf sig = STRBUF_INIT; int inspos, copypos; const char *eoh; - const char *gpg_sig_header = gpg_sig_headers[hash_algo_by_ptr(the_hash_algo)]; + const char *gpg_sig_header = gpg_sig_headers[hash_algo_by_ptr(algo)]; int gpg_sig_header_len = strlen(gpg_sig_header); /* find the end of the header */ @@ -1063,15 +1128,8 @@ int sign_with_header(struct strbuf *buf, const char *keyid) else inspos = eoh - 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; + for (copypos = 0; sig->buf[copypos]; ) { + const char *bol = sig->buf + copypos; const char *eol = strchrnul(bol, '\n'); int len = (eol - bol) + !!*eol; @@ -1084,21 +1142,28 @@ int sign_with_header(struct strbuf *buf, const char *keyid) inspos += len; copypos += len; } - strbuf_release(&sig); return 0; } - +static int sign_commit_to_strbuf(struct strbuf *sig, struct strbuf *buf, const char *keyid) +{ + if (!keyid || !*keyid) + keyid = get_signing_key(); + if (sign_buffer(buf, sig, keyid)) + return -1; + return 0; +} int parse_signed_commit(const struct commit *commit, struct strbuf *payload, struct strbuf *signature, const struct git_hash_algo *algop) { unsigned long size; - const char *buffer = get_commit_buffer(commit, &size); + const char *buffer = repo_get_commit_buffer(the_repository, commit, + &size); int ret = parse_buffer_signed_by_header(buffer, size, payload, signature, algop); - unuse_commit_buffer(commit, buffer); + repo_unuse_commit_buffer(the_repository, commit, buffer); return ret; } @@ -1209,7 +1274,8 @@ static void handle_signed_tag(struct commit *parent, struct commit_extra_header desc = merge_remote_util(parent); if (!desc || !desc->obj) return; - buf = read_object_file(&desc->obj->oid, &type, &size); + buf = repo_read_object_file(the_repository, &desc->obj->oid, &type, + &size); if (!buf || type != OBJ_TAG) goto free_return; if (!parse_signature(buf, size, &payload, &signature)) @@ -1271,7 +1337,8 @@ void verify_merge_signature(struct commit *commit, int verbosity, ret = check_commit_signature(commit, &signature_check); - find_unique_abbrev_r(hex, &commit->object.oid, DEFAULT_ABBREV); + repo_find_unique_abbrev_r(the_repository, hex, &commit->object.oid, + DEFAULT_ABBREV); switch (signature_check.result) { case 'G': if (ret || (check_trust && signature_check.trust_level < TRUST_MARGINAL)) @@ -1301,6 +1368,39 @@ void append_merge_tag_headers(struct commit_list *parents, } } +static int convert_commit_extra_headers(struct commit_extra_header *orig, + struct commit_extra_header **result) +{ + const struct git_hash_algo *compat = the_repository->compat_hash_algo; + const struct git_hash_algo *algo = the_repository->hash_algo; + struct commit_extra_header *extra = NULL, **tail = &extra; + struct strbuf out = STRBUF_INIT; + while (orig) { + struct commit_extra_header *new; + CALLOC_ARRAY(new, 1); + if (!strcmp(orig->key, "mergetag")) { + if (convert_object_file(&out, algo, compat, + orig->value, orig->len, + OBJ_TAG, 1)) { + free(new); + free_commit_extra_headers(extra); + return -1; + } + new->key = xstrdup("mergetag"); + new->value = strbuf_detach(&out, &new->len); + } else { + new->key = xstrdup(orig->key); + new->len = orig->len; + new->value = xmemdupz(orig->value, orig->len); + } + *tail = new; + tail = &new->next; + orig = orig->next; + } + *result = extra; + return 0; +} + static void add_extra_header(struct strbuf *buffer, struct commit_extra_header *extra) { @@ -1316,9 +1416,10 @@ struct commit_extra_header *read_commit_extra_headers(struct commit *commit, { struct commit_extra_header *extra = NULL; unsigned long size; - const char *buffer = get_commit_buffer(commit, &size); + const char *buffer = repo_get_commit_buffer(the_repository, commit, + &size); extra = read_commit_extra_header_lines(buffer, size, exclude); - unuse_commit_buffer(commit, buffer); + repo_unuse_commit_buffer(the_repository, commit, buffer); return extra; } @@ -1543,70 +1644,169 @@ 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 char *msg, size_t msg_len, - const struct object_id *tree, - struct commit_list *parents, struct object_id *ret, - const char *author, const char *committer, - const char *sign_commit, - struct commit_extra_header *extra) +static void write_commit_tree(struct strbuf *buffer, const char *msg, size_t msg_len, + const struct object_id *tree, + const struct object_id *parents, size_t parents_len, + const char *author, const char *committer, + struct commit_extra_header *extra) { - int result; int encoding_is_utf8; - struct strbuf buffer; - - assert_oid_type(tree, OBJ_TREE); - - if (memchr(msg, '\0', msg_len)) - return error("a NUL byte in commit log message not allowed."); + size_t i; /* 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", oid_to_hex(tree)); + strbuf_grow(buffer, 8192); /* should avoid reallocs for the headers */ + strbuf_addf(buffer, "tree %s\n", oid_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 *parent = pop_commit(&parents); - strbuf_addf(&buffer, "parent %s\n", - oid_to_hex(&parent->object.oid)); - } + for (i = 0; i < parents_len; i++) + strbuf_addf(buffer, "parent %s\n", oid_to_hex(&parents[i])); /* Person/date information */ if (!author) author = git_author_info(IDENT_STRICT); - strbuf_addf(&buffer, "author %s\n", author); + strbuf_addf(buffer, "author %s\n", author); if (!committer) committer = git_committer_info(IDENT_STRICT); - strbuf_addf(&buffer, "committer %s\n", committer); + strbuf_addf(buffer, "committer %s\n", committer); if (!encoding_is_utf8) - strbuf_addf(&buffer, "encoding %s\n", git_commit_encoding); + strbuf_addf(buffer, "encoding %s\n", git_commit_encoding); while (extra) { - add_extra_header(&buffer, extra); + add_extra_header(buffer, extra); extra = extra->next; } - strbuf_addch(&buffer, '\n'); + strbuf_addch(buffer, '\n'); /* And add the comment */ - strbuf_add(&buffer, msg, msg_len); + strbuf_add(buffer, msg, msg_len); +} - /* And check the encoding */ - if (encoding_is_utf8 && !verify_utf8(&buffer)) - fprintf(stderr, _(commit_utf8_warn)); +int commit_tree_extended(const char *msg, size_t msg_len, + const struct object_id *tree, + struct commit_list *parents, struct object_id *ret, + const char *author, const char *committer, + const char *sign_commit, + struct commit_extra_header *extra) +{ + struct repository *r = the_repository; + int result = 0; + int encoding_is_utf8; + struct strbuf buffer = STRBUF_INIT, compat_buffer = STRBUF_INIT; + struct strbuf sig = STRBUF_INIT, compat_sig = STRBUF_INIT; + struct object_id *parent_buf = NULL, *compat_oid = NULL; + struct object_id compat_oid_buf; + size_t i, nparents; + + /* Not having i18n.commitencoding is the same as having utf-8 */ + encoding_is_utf8 = is_encoding_utf8(git_commit_encoding); + + assert_oid_type(tree, OBJ_TREE); + + if (memchr(msg, '\0', msg_len)) + return error("a NUL byte in commit log message not allowed."); + + nparents = commit_list_count(parents); + CALLOC_ARRAY(parent_buf, nparents); + i = 0; + while (parents) { + struct commit *parent = pop_commit(&parents); + oidcpy(&parent_buf[i++], &parent->object.oid); + } - if (sign_commit && sign_with_header(&buffer, sign_commit)) { + write_commit_tree(&buffer, msg, msg_len, tree, parent_buf, nparents, author, committer, extra); + if (sign_commit && sign_commit_to_strbuf(&sig, &buffer, sign_commit)) { result = -1; goto out; } + if (r->compat_hash_algo) { + struct commit_extra_header *compat_extra = NULL; + struct object_id mapped_tree; + struct object_id *mapped_parents; + + CALLOC_ARRAY(mapped_parents, nparents); + + if (repo_oid_to_algop(r, tree, r->compat_hash_algo, &mapped_tree)) { + result = -1; + free(mapped_parents); + goto out; + } + for (i = 0; i < nparents; i++) + if (repo_oid_to_algop(r, &parent_buf[i], r->compat_hash_algo, &mapped_parents[i])) { + result = -1; + free(mapped_parents); + goto out; + } + if (convert_commit_extra_headers(extra, &compat_extra)) { + result = -1; + free(mapped_parents); + goto out; + } + write_commit_tree(&compat_buffer, msg, msg_len, &mapped_tree, + mapped_parents, nparents, author, committer, compat_extra); + free_commit_extra_headers(compat_extra); + free(mapped_parents); + + if (sign_commit && sign_commit_to_strbuf(&compat_sig, &compat_buffer, sign_commit)) { + result = -1; + goto out; + } + } + + if (sign_commit) { + struct sig_pairs { + struct strbuf *sig; + const struct git_hash_algo *algo; + } bufs [2] = { + { &compat_sig, r->compat_hash_algo }, + { &sig, r->hash_algo }, + }; + int i; + + /* + * We write algorithms in the order they were implemented in + * Git to produce a stable hash when multiple algorithms are + * used. + */ + if (r->compat_hash_algo && hash_algo_by_ptr(bufs[0].algo) > hash_algo_by_ptr(bufs[1].algo)) + SWAP(bufs[0], bufs[1]); + + /* + * We traverse each algorithm in order, and apply the signature + * to each buffer. + */ + for (i = 0; i < ARRAY_SIZE(bufs); i++) { + if (!bufs[i].algo) + continue; + add_header_signature(&buffer, bufs[i].sig, bufs[i].algo); + if (r->compat_hash_algo) + add_header_signature(&compat_buffer, bufs[i].sig, bufs[i].algo); + } + } + + /* And check the encoding. */ + if (encoding_is_utf8 && (!verify_utf8(&buffer) || !verify_utf8(&compat_buffer))) + fprintf(stderr, _(commit_utf8_warn)); + + if (r->compat_hash_algo) { + hash_object_file(r->compat_hash_algo, compat_buffer.buf, compat_buffer.len, + OBJ_COMMIT, &compat_oid_buf); + compat_oid = &compat_oid_buf; + } - result = write_object_file(buffer.buf, buffer.len, OBJ_COMMIT, ret); + result = write_object_file_flags(buffer.buf, buffer.len, OBJ_COMMIT, + ret, compat_oid, 0); out: + free(parent_buf); strbuf_release(&buffer); + strbuf_release(&compat_buffer); + strbuf_release(&sig); + strbuf_release(&compat_sig); return result; } @@ -1632,10 +1832,11 @@ struct commit *get_merge_parent(const char *name) struct object *obj; struct commit *commit; struct object_id oid; - if (get_oid(name, &oid)) + if (repo_get_oid(the_repository, name, &oid)) return NULL; obj = parse_object(the_repository, &oid); - commit = (struct commit *)peel_to_type(name, 0, obj, OBJ_COMMIT); + commit = (struct commit *)repo_peel_to_type(the_repository, name, 0, + obj, OBJ_COMMIT); if (commit && !merge_remote_util(commit)) set_merge_remote_desc(commit, name, obj); return commit; @@ -1712,7 +1913,7 @@ const char *find_commit_header(const char *msg, const char *key, size_t *out_len * Returns the number of bytes from the tail to ignore, to be fed as * the second parameter to append_signoff(). */ -size_t ignore_non_trailer(const char *buf, size_t len) +size_t ignored_log_message_bytes(const char *buf, size_t len) { size_t boc = 0; size_t bol = 0; @@ -1727,7 +1928,8 @@ size_t ignore_non_trailer(const char *buf, size_t len) else next_line++; - if (buf[bol] == comment_line_char || buf[bol] == '\n') { + if (starts_with_mem(buf + bol, cutoff - bol, comment_line_str) || + buf[bol] == '\n') { /* is this the first of the run of comments? */ if (!boc) boc = bol; |