diff options
Diffstat (limited to '')
| -rw-r--r-- | third_party/git/builtin/fast-import.c (renamed from third_party/git/fast-import.c) | 499 |
1 files changed, 364 insertions, 135 deletions
diff --git a/third_party/git/fast-import.c b/third_party/git/builtin/fast-import.c index b44d6a467ef1..1bf50a73dc35 100644 --- a/third_party/git/fast-import.c +++ b/third_party/git/builtin/fast-import.c @@ -18,6 +18,7 @@ #include "object-store.h" #include "mem-pool.h" #include "commit-reach.h" +#include "khash.h" #define PACK_ID_BITS 16 #define MAX_PACK_ID ((1<<PACK_ID_BITS)-1) @@ -38,12 +39,28 @@ struct object_entry { struct pack_idx_entry idx; - struct object_entry *next; + struct hashmap_entry ent; uint32_t type : TYPE_BITS, pack_id : PACK_ID_BITS, depth : DEPTH_BITS; }; +static int object_entry_hashcmp(const void *map_data, + const struct hashmap_entry *eptr, + const struct hashmap_entry *entry_or_key, + const void *keydata) +{ + const struct object_id *oid = keydata; + const struct object_entry *e1, *e2; + + e1 = container_of(eptr, const struct object_entry, ent); + if (oid) + return oidcmp(&e1->idx.oid, oid); + + e2 = container_of(entry_or_key, const struct object_entry, ent); + return oidcmp(&e1->idx.oid, &e2->idx.oid); +} + struct object_entry_pool { struct object_entry_pool *next_pool; struct object_entry *next_free; @@ -53,6 +70,7 @@ struct object_entry_pool { struct mark_set { union { + struct object_id *oids[1024]; struct object_entry *marked[1024]; struct mark_set *sets[1024]; } data; @@ -121,6 +139,7 @@ struct hash_list { typedef enum { WHENSPEC_RAW = 1, + WHENSPEC_RAW_PERMISSIVE, WHENSPEC_RFC2822, WHENSPEC_NOW } whenspec_type; @@ -131,6 +150,9 @@ struct recent_command { char *buf; }; +typedef void (*mark_set_inserter_t)(struct mark_set *s, struct object_id *oid, uintmax_t mark); +typedef void (*each_mark_fn_t)(uintmax_t mark, void *obj, void *cbp); + /* Configured limits on output */ static unsigned long max_depth = 50; static off_t max_packsize; @@ -173,7 +195,7 @@ static off_t pack_size; /* Table of objects we've written. */ static unsigned int object_entry_alloc = 5000; static struct object_entry_pool *blocks; -static struct object_entry *object_table[1 << 16]; +static struct hashmap object_table; static struct mark_set *marks; static const char *export_marks_file; static const char *import_marks_file; @@ -217,10 +239,16 @@ static uintmax_t next_mark; static struct strbuf new_data = STRBUF_INIT; static int seen_data_command; static int require_explicit_termination; +static int allow_unsafe_features; /* Signal handling */ static volatile sig_atomic_t checkpoint_requested; +/* Submodule marks */ +static struct string_list sub_marks_from = STRING_LIST_INIT_DUP; +static struct string_list sub_marks_to = STRING_LIST_INIT_DUP; +static kh_oid_map_t *sub_oid_map; + /* Where to write output of cat-blob commands */ static int cat_blob_fd = STDOUT_FILENO; @@ -229,6 +257,29 @@ static void parse_get_mark(const char *p); static void parse_cat_blob(const char *p); static void parse_ls(const char *p, struct branch *b); +static void for_each_mark(struct mark_set *m, uintmax_t base, each_mark_fn_t callback, void *p) +{ + uintmax_t k; + if (m->shift) { + for (k = 0; k < 1024; k++) { + if (m->data.sets[k]) + for_each_mark(m->data.sets[k], base + (k << m->shift), callback, p); + } + } else { + for (k = 0; k < 1024; k++) { + if (m->data.marked[k]) + callback(base + k, m->data.marked[k], p); + } + } +} + +static void dump_marks_fn(uintmax_t mark, void *object, void *cbp) { + struct object_entry *e = object; + FILE *f = cbp; + + fprintf(f, ":%" PRIuMAX " %s\n", mark, oid_to_hex(&e->idx.oid)); +} + static void write_branch_report(FILE *rpt, struct branch *b) { fprintf(rpt, "%s:\n", b->name); @@ -257,8 +308,6 @@ static void write_branch_report(FILE *rpt, struct branch *b) fputc('\n', rpt); } -static void dump_marks_helper(FILE *, uintmax_t, struct mark_set *); - static void write_crash_report(const char *err) { char *loc = git_pathdup("fast_import_crash_%"PRIuMAX, (uintmax_t) getpid()); @@ -337,7 +386,7 @@ static void write_crash_report(const char *err) if (export_marks_file) fprintf(rpt, " exported to %s\n", export_marks_file); else - dump_marks_helper(rpt, 0, marks); + for_each_mark(marks, 0, dump_marks_fn, rpt); fputc('\n', rpt); fputs("-------------------\n", rpt); @@ -423,44 +472,37 @@ static struct object_entry *new_object(struct object_id *oid) static struct object_entry *find_object(struct object_id *oid) { - unsigned int h = oid->hash[0] << 8 | oid->hash[1]; - struct object_entry *e; - for (e = object_table[h]; e; e = e->next) - if (oideq(oid, &e->idx.oid)) - return e; - return NULL; + return hashmap_get_entry_from_hash(&object_table, oidhash(oid), oid, + struct object_entry, ent); } static struct object_entry *insert_object(struct object_id *oid) { - unsigned int h = oid->hash[0] << 8 | oid->hash[1]; - struct object_entry *e = object_table[h]; + struct object_entry *e; + unsigned int hash = oidhash(oid); - while (e) { - if (oideq(oid, &e->idx.oid)) - return e; - e = e->next; + e = hashmap_get_entry_from_hash(&object_table, hash, oid, + struct object_entry, ent); + if (!e) { + e = new_object(oid); + e->idx.offset = 0; + hashmap_entry_init(&e->ent, hash); + hashmap_add(&object_table, &e->ent); } - e = new_object(oid); - e->next = object_table[h]; - e->idx.offset = 0; - object_table[h] = e; return e; } static void invalidate_pack_id(unsigned int id) { - unsigned int h; unsigned long lu; struct tag *t; + struct hashmap_iter iter; + struct object_entry *e; - for (h = 0; h < ARRAY_SIZE(object_table); h++) { - struct object_entry *e; - - for (e = object_table[h]; e; e = e->next) - if (e->pack_id == id) - e->pack_id = MAX_PACK_ID; + hashmap_for_each_entry(&object_table, &iter, e, ent) { + if (e->pack_id == id) + e->pack_id = MAX_PACK_ID; } for (lu = 0; lu < branch_table_sz; lu++) { @@ -484,17 +526,8 @@ static unsigned int hc_str(const char *s, size_t len) return r; } -static char *pool_strdup(const char *s) -{ - size_t len = strlen(s) + 1; - char *r = mem_pool_alloc(&fi_mem_pool, len); - memcpy(r, s, len); - return r; -} - -static void insert_mark(uintmax_t idnum, struct object_entry *oe) +static void insert_mark(struct mark_set *s, uintmax_t idnum, struct object_entry *oe) { - struct mark_set *s = marks; while ((idnum >> s->shift) >= 1024) { s = mem_pool_calloc(&fi_mem_pool, 1, sizeof(struct mark_set)); s->shift = marks->shift + 10; @@ -515,10 +548,9 @@ static void insert_mark(uintmax_t idnum, struct object_entry *oe) s->data.marked[idnum] = oe; } -static struct object_entry *find_mark(uintmax_t idnum) +static void *find_mark(struct mark_set *s, uintmax_t idnum) { uintmax_t orig_idnum = idnum; - struct mark_set *s = marks; struct object_entry *oe = NULL; if ((idnum >> s->shift) < 1024) { while (s && s->shift) { @@ -575,7 +607,7 @@ static struct branch *new_branch(const char *name) die("Branch name doesn't conform to GIT standards: %s", name); b = mem_pool_calloc(&fi_mem_pool, 1, sizeof(struct branch)); - b->name = pool_strdup(name); + b->name = mem_pool_strdup(&fi_mem_pool, name); b->table_next_branch = branch_table[hc]; b->branch_tree.versions[0].mode = S_IFDIR; b->branch_tree.versions[1].mode = S_IFDIR; @@ -707,7 +739,6 @@ static void start_packfile(void) { struct strbuf tmp_file = STRBUF_INIT; struct packed_git *p; - struct pack_header hdr; int pack_fd; pack_fd = odb_mkstemp(&tmp_file, "pack/tmp_pack_XXXXXX"); @@ -718,13 +749,8 @@ static void start_packfile(void) p->do_not_close = 1; pack_file = hashfd(pack_fd, p->pack_name); - hdr.hdr_signature = htonl(PACK_SIGNATURE); - hdr.hdr_version = htonl(2); - hdr.hdr_entries = 0; - hashwrite(pack_file, &hdr, sizeof(hdr)); - pack_data = p; - pack_size = sizeof(hdr); + pack_size = write_pack_header(pack_file, 0); object_count = 0; REALLOC_ARRAY(all_packs, pack_id + 1); @@ -803,9 +829,9 @@ static int loosen_small_pack(const struct packed_git *p) unpack.in = p->pack_fd; unpack.git_cmd = 1; unpack.stdout_to_stderr = 1; - argv_array_push(&unpack.args, "unpack-objects"); + strvec_push(&unpack.args, "unpack-objects"); if (!show_stats) - argv_array_push(&unpack.args, "-q"); + strvec_push(&unpack.args, "-q"); return run_command(&unpack); } @@ -918,7 +944,7 @@ static int store_object( e = insert_object(&oid); if (mark) - insert_mark(mark, e); + insert_mark(marks, mark, e); if (e->idx.offset) { duplicate_count_by_type[type]++; return 1; @@ -1116,7 +1142,7 @@ static void stream_blob(uintmax_t len, struct object_id *oidout, uintmax_t mark) e = insert_object(&oid); if (mark) - insert_mark(mark, e); + insert_mark(marks, mark, e); if (e->idx.offset) { duplicate_count_by_type[OBJ_BLOB]++; @@ -1654,26 +1680,6 @@ static void dump_tags(void) strbuf_release(&err); } -static void dump_marks_helper(FILE *f, - uintmax_t base, - struct mark_set *m) -{ - uintmax_t k; - if (m->shift) { - for (k = 0; k < 1024; k++) { - if (m->data.sets[k]) - dump_marks_helper(f, base + (k << m->shift), - m->data.sets[k]); - } - } else { - for (k = 0; k < 1024; k++) { - if (m->data.marked[k]) - fprintf(f, ":%" PRIuMAX " %s\n", base + k, - oid_to_hex(&m->data.marked[k]->idx.oid)); - } - } -} - static void dump_marks(void) { struct lock_file mark_lock = LOCK_INIT; @@ -1682,6 +1688,12 @@ static void dump_marks(void) if (!export_marks_file || (import_marks_file && !import_marks_file_done)) return; + if (safe_create_leading_directories_const(export_marks_file)) { + failure |= error_errno("unable to create leading directories of %s", + export_marks_file); + return; + } + if (hold_lock_file_for_update(&mark_lock, export_marks_file, 0) < 0) { failure |= error_errno("Unable to write marks file %s", export_marks_file); @@ -1697,7 +1709,7 @@ static void dump_marks(void) return; } - dump_marks_helper(f, 0, marks); + for_each_mark(marks, 0, dump_marks_fn, f); if (commit_lock_file(&mark_lock)) { failure |= error_errno("Unable to write file %s", export_marks_file); @@ -1705,21 +1717,38 @@ static void dump_marks(void) } } -static void read_marks(void) +static void insert_object_entry(struct mark_set *s, struct object_id *oid, uintmax_t mark) +{ + struct object_entry *e; + e = find_object(oid); + if (!e) { + enum object_type type = oid_object_info(the_repository, + oid, NULL); + if (type < 0) + die("object not found: %s", oid_to_hex(oid)); + e = insert_object(oid); + e->type = type; + e->pack_id = MAX_PACK_ID; + e->idx.offset = 1; /* just not zero! */ + } + insert_mark(s, mark, e); +} + +static void insert_oid_entry(struct mark_set *s, struct object_id *oid, uintmax_t mark) +{ + insert_mark(s, mark, xmemdupz(oid, sizeof(*oid))); +} + +static void read_mark_file(struct mark_set *s, FILE *f, mark_set_inserter_t inserter) { char line[512]; - FILE *f = fopen(import_marks_file, "r"); - if (f) - ; - else if (import_marks_file_ignore_missing && errno == ENOENT) - goto done; /* Marks file does not exist */ - else - die_errno("cannot read '%s'", import_marks_file); while (fgets(line, sizeof(line), f)) { uintmax_t mark; char *end; struct object_id oid; - struct object_entry *e; + + /* Ensure SHA-1 objects are padded with zeros. */ + memset(oid.hash, 0, sizeof(oid.hash)); end = strchr(line, '\n'); if (line[0] != ':' || !end) @@ -1727,21 +1756,23 @@ static void read_marks(void) *end = 0; mark = strtoumax(line + 1, &end, 10); if (!mark || end == line + 1 - || *end != ' ' || get_oid_hex(end + 1, &oid)) + || *end != ' ' + || get_oid_hex_any(end + 1, &oid) == GIT_HASH_UNKNOWN) die("corrupt mark line: %s", line); - e = find_object(&oid); - if (!e) { - enum object_type type = oid_object_info(the_repository, - &oid, NULL); - if (type < 0) - die("object not found: %s", oid_to_hex(&oid)); - e = insert_object(&oid); - e->type = type; - e->pack_id = MAX_PACK_ID; - e->idx.offset = 1; /* just not zero! */ - } - insert_mark(mark, e); + inserter(s, &oid, mark); } +} + +static void read_marks(void) +{ + FILE *f = fopen(import_marks_file, "r"); + if (f) + ; + else if (import_marks_file_ignore_missing && errno == ENOENT) + goto done; /* Marks file does not exist */ + else + die_errno("cannot read '%s'", import_marks_file); + read_mark_file(marks, f, insert_object_entry); fclose(f); done: import_marks_file_done = 1; @@ -1763,7 +1794,6 @@ static int read_next_command(void) } else { struct recent_command *rc; - strbuf_detach(&command_buf, NULL); stdin_eof = strbuf_getline_lf(&command_buf, stdin); if (stdin_eof) return EOF; @@ -1784,7 +1814,7 @@ static int read_next_command(void) free(rc->buf); } - rc->buf = command_buf.buf; + rc->buf = xstrdup(command_buf.buf); rc->prev = cmd_tail; rc->next = cmd_hist.prev; rc->prev->next = rc; @@ -1833,7 +1863,6 @@ static int parse_data(struct strbuf *sb, uintmax_t limit, uintmax_t *len_res) char *term = xstrdup(data); size_t term_len = command_buf.len - (data - command_buf.buf); - strbuf_detach(&command_buf, NULL); for (;;) { if (strbuf_getline_lf(&command_buf, stdin) == EOF) die("EOF in data (terminator '%s' not found)", term); @@ -1869,7 +1898,7 @@ static int parse_data(struct strbuf *sb, uintmax_t limit, uintmax_t *len_res) return 1; } -static int validate_raw_date(const char *src, struct strbuf *result) +static int validate_raw_date(const char *src, struct strbuf *result, int strict) { const char *orig_src = src; char *endp; @@ -1878,7 +1907,11 @@ static int validate_raw_date(const char *src, struct strbuf *result) errno = 0; num = strtoul(src, &endp, 10); - /* NEEDSWORK: perhaps check for reasonable values? */ + /* + * NEEDSWORK: perhaps check for reasonable values? For example, we + * could error on values representing times more than a + * day in the future. + */ if (errno || endp == src || *endp != ' ') return -1; @@ -1887,7 +1920,13 @@ static int validate_raw_date(const char *src, struct strbuf *result) return -1; num = strtoul(src + 1, &endp, 10); - if (errno || endp == src + 1 || *endp || 1400 < num) + /* + * NEEDSWORK: check for brokenness other than num > 1400, such as + * (num % 100) >= 60, or ((num % 100) % 15) != 0 ? + */ + if (errno || endp == src + 1 || *endp || /* did not parse */ + (strict && (1400 < num)) /* parsed a broken timezone */ + ) return -1; strbuf_addstr(result, orig_src); @@ -1921,7 +1960,11 @@ static char *parse_ident(const char *buf) switch (whenspec) { case WHENSPEC_RAW: - if (validate_raw_date(ltgt, &ident) < 0) + if (validate_raw_date(ltgt, &ident, 1) < 0) + die("Invalid raw date \"%s\" in ident: %s", ltgt, buf); + break; + case WHENSPEC_RAW_PERMISSIVE: + if (validate_raw_date(ltgt, &ident, 0) < 0) die("Invalid raw date \"%s\" in ident: %s", ltgt, buf); break; case WHENSPEC_RFC2822: @@ -2129,6 +2172,30 @@ static uintmax_t change_note_fanout(struct tree_entry *root, return do_change_note_fanout(root, root, hex_oid, 0, path, 0, fanout); } +static int parse_mapped_oid_hex(const char *hex, struct object_id *oid, const char **end) +{ + int algo; + khiter_t it; + + /* Make SHA-1 object IDs have all-zero padding. */ + memset(oid->hash, 0, sizeof(oid->hash)); + + algo = parse_oid_hex_any(hex, oid, end); + if (algo == GIT_HASH_UNKNOWN) + return -1; + + it = kh_get_oid_map(sub_oid_map, *oid); + /* No such object? */ + if (it == kh_end(sub_oid_map)) { + /* If we're using the same algorithm, pass it through. */ + if (hash_algos[algo].format_id == the_hash_algo->format_id) + return 0; + return -1; + } + oidcpy(oid, kh_value(sub_oid_map, it)); + return 0; +} + /* * Given a pointer into a string, parse a mark reference: * @@ -2209,13 +2276,13 @@ static void file_change_m(const char *p, struct branch *b) } if (*p == ':') { - oe = find_mark(parse_mark_ref_space(&p)); + oe = find_mark(marks, parse_mark_ref_space(&p)); oidcpy(&oid, &oe->idx.oid); } else if (skip_prefix(p, "inline ", &p)) { inline_data = 1; oe = NULL; /* not used with inline_data, but makes gcc happy */ } else { - if (parse_oid_hex(p, &oid, &p)) + if (parse_mapped_oid_hex(p, &oid, &p)) die("Invalid dataref: %s", command_buf.buf); oe = find_object(&oid); if (*p++ != ' ') @@ -2383,13 +2450,13 @@ static void note_change_n(const char *p, struct branch *b, unsigned char *old_fa /* Now parse the notemodify command. */ /* <dataref> or 'inline' */ if (*p == ':') { - oe = find_mark(parse_mark_ref_space(&p)); + oe = find_mark(marks, parse_mark_ref_space(&p)); oidcpy(&oid, &oe->idx.oid); } else if (skip_prefix(p, "inline ", &p)) { inline_data = 1; oe = NULL; /* not used with inline_data, but makes gcc happy */ } else { - if (parse_oid_hex(p, &oid, &p)) + if (parse_mapped_oid_hex(p, &oid, &p)) die("Invalid dataref: %s", command_buf.buf); oe = find_object(&oid); if (*p++ != ' ') @@ -2404,7 +2471,7 @@ static void note_change_n(const char *p, struct branch *b, unsigned char *old_fa oidcpy(&commit_oid, &s->oid); } else if (*p == ':') { uintmax_t commit_mark = parse_mark_ref_eol(p); - struct object_entry *commit_oe = find_mark(commit_mark); + struct object_entry *commit_oe = find_mark(marks, commit_mark); if (commit_oe->type != OBJ_COMMIT) die("Mark :%" PRIuMAX " not a commit", commit_mark); oidcpy(&commit_oid, &commit_oe->idx.oid); @@ -2491,18 +2558,14 @@ static void parse_from_existing(struct branch *b) } } -static int parse_from(struct branch *b) +static int parse_objectish(struct branch *b, const char *objectish) { - const char *from; struct branch *s; struct object_id oid; - if (!skip_prefix(command_buf.buf, "from ", &from)) - return 0; - oidcpy(&oid, &b->branch_tree.versions[1].oid); - s = lookup_branch(from); + s = lookup_branch(objectish); if (b == s) die("Can't create a branch from itself: %s", b->name); else if (s) { @@ -2510,9 +2573,9 @@ static int parse_from(struct branch *b) oidcpy(&b->oid, &s->oid); oidcpy(&b->branch_tree.versions[0].oid, t); oidcpy(&b->branch_tree.versions[1].oid, t); - } else if (*from == ':') { - uintmax_t idnum = parse_mark_ref_eol(from); - struct object_entry *oe = find_mark(idnum); + } else if (*objectish == ':') { + uintmax_t idnum = parse_mark_ref_eol(objectish); + struct object_entry *oe = find_mark(marks, idnum); if (oe->type != OBJ_COMMIT) die("Mark :%" PRIuMAX " not a commit", idnum); if (!oideq(&b->oid, &oe->idx.oid)) { @@ -2525,13 +2588,13 @@ static int parse_from(struct branch *b) } else parse_from_existing(b); } - } else if (!get_oid(from, &b->oid)) { + } else if (!get_oid(objectish, &b->oid)) { parse_from_existing(b); if (is_null_oid(&b->oid)) b->delete = 1; } else - die("Invalid ref name or SHA1 expression: %s", from); + die("Invalid ref name or SHA1 expression: %s", objectish); if (b->branch_tree.tree && !oideq(&oid, &b->branch_tree.versions[1].oid)) { release_tree_content_recursive(b->branch_tree.tree); @@ -2542,6 +2605,26 @@ static int parse_from(struct branch *b) return 1; } +static int parse_from(struct branch *b) +{ + const char *from; + + if (!skip_prefix(command_buf.buf, "from ", &from)) + return 0; + + return parse_objectish(b, from); +} + +static int parse_objectish_with_prefix(struct branch *b, const char *prefix) +{ + const char *base; + + if (!skip_prefix(command_buf.buf, prefix, &base)) + return 0; + + return parse_objectish(b, base); +} + static struct hash_list *parse_merge(unsigned int *count) { struct hash_list *list = NULL, **tail = &list, *n; @@ -2556,7 +2639,7 @@ static struct hash_list *parse_merge(unsigned int *count) oidcpy(&n->oid, &s->oid); else if (*from == ':') { uintmax_t idnum = parse_mark_ref_eol(from); - struct object_entry *oe = find_mark(idnum); + struct object_entry *oe = find_mark(marks, idnum); if (oe->type != OBJ_COMMIT) die("Mark :%" PRIuMAX " not a commit", idnum); oidcpy(&n->oid, &oe->idx.oid); @@ -2588,7 +2671,7 @@ static void parse_new_commit(const char *arg) struct branch *b; char *author = NULL; char *committer = NULL; - const char *encoding = NULL; + char *encoding = NULL; struct hash_list *merge_list = NULL; unsigned int merge_count; unsigned char prev_fanout, new_fanout; @@ -2611,8 +2694,10 @@ static void parse_new_commit(const char *arg) } if (!committer) die("Expected committer but didn't get one"); - if (skip_prefix(command_buf.buf, "encoding ", &encoding)) + if (skip_prefix(command_buf.buf, "encoding ", &v)) { + encoding = xstrdup(v); read_next_command(); + } parse_data(&msg, 0, NULL); read_next_command(); parse_from(b); @@ -2686,6 +2771,7 @@ static void parse_new_commit(const char *arg) strbuf_addbuf(&new_data, &msg); free(author); free(committer); + free(encoding); if (!store_object(OBJ_COMMIT, &new_data, NULL, &b->oid, next_mark)) b->pack_id = pack_id; @@ -2706,13 +2792,14 @@ static void parse_new_tag(const char *arg) t = mem_pool_alloc(&fi_mem_pool, sizeof(struct tag)); memset(t, 0, sizeof(struct tag)); - t->name = pool_strdup(arg); + t->name = mem_pool_strdup(&fi_mem_pool, arg); if (last_tag) last_tag->next_tag = t; else first_tag = t; last_tag = t; read_next_command(); + parse_mark(); /* from ... */ if (!skip_prefix(command_buf.buf, "from ", &from)) @@ -2726,7 +2813,7 @@ static void parse_new_tag(const char *arg) } else if (*from == ':') { struct object_entry *oe; from_mark = parse_mark_ref_eol(from); - oe = find_mark(from_mark); + oe = find_mark(marks, from_mark); type = oe->type; oidcpy(&oid, &oe->idx.oid); } else if (!get_oid(from, &oid)) { @@ -2769,7 +2856,7 @@ static void parse_new_tag(const char *arg) strbuf_addbuf(&new_data, &msg); free(tagger); - if (store_object(OBJ_TAG, &new_data, NULL, &t->oid, 0)) + if (store_object(OBJ_TAG, &new_data, NULL, &t->oid, next_mark)) t->pack_id = MAX_PACK_ID; else t->pack_id = pack_id; @@ -2778,6 +2865,7 @@ static void parse_new_tag(const char *arg) static void parse_reset_branch(const char *arg) { struct branch *b; + const char *tag_name; b = lookup_branch(arg); if (b) { @@ -2793,6 +2881,32 @@ static void parse_reset_branch(const char *arg) b = new_branch(arg); read_next_command(); parse_from(b); + if (b->delete && skip_prefix(b->name, "refs/tags/", &tag_name)) { + /* + * Elsewhere, we call dump_branches() before dump_tags(), + * and dump_branches() will handle ref deletions first, so + * in order to make sure the deletion actually takes effect, + * we need to remove the tag from our list of tags to update. + * + * NEEDSWORK: replace list of tags with hashmap for faster + * deletion? + */ + struct tag *t, *prev = NULL; + for (t = first_tag; t; t = t->next_tag) { + if (!strcmp(t->name, tag_name)) + break; + prev = t; + } + if (t) { + if (prev) + prev->next_tag = t->next_tag; + else + first_tag = t->next_tag; + if (!t->next_tag) + last_tag = prev; + /* There is no mem_pool_free(t) function to call. */ + } + } if (command_buf.len > 0) unread_command_buf = 1; } @@ -2857,7 +2971,7 @@ static void parse_get_mark(const char *p) if (*p != ':') die("Not a mark: %s", p); - oe = find_mark(parse_mark_ref_eol(p)); + oe = find_mark(marks, parse_mark_ref_eol(p)); if (!oe) die("Unknown mark: %s", command_buf.buf); @@ -2872,12 +2986,12 @@ static void parse_cat_blob(const char *p) /* cat-blob SP <object> LF */ if (*p == ':') { - oe = find_mark(parse_mark_ref_eol(p)); + oe = find_mark(marks, parse_mark_ref_eol(p)); if (!oe) die("Unknown mark: %s", command_buf.buf); oidcpy(&oid, &oe->idx.oid); } else { - if (parse_oid_hex(p, &oid, &p)) + if (parse_mapped_oid_hex(p, &oid, &p)) die("Invalid dataref: %s", command_buf.buf); if (*p) die("Garbage after SHA1: %s", command_buf.buf); @@ -2941,18 +3055,54 @@ static struct object_entry *dereference(struct object_entry *oe, return find_object(oid); } +static void insert_mapped_mark(uintmax_t mark, void *object, void *cbp) +{ + struct object_id *fromoid = object; + struct object_id *tooid = find_mark(cbp, mark); + int ret; + khiter_t it; + + it = kh_put_oid_map(sub_oid_map, *fromoid, &ret); + /* We've already seen this object. */ + if (ret == 0) + return; + kh_value(sub_oid_map, it) = tooid; +} + +static void build_mark_map_one(struct mark_set *from, struct mark_set *to) +{ + for_each_mark(from, 0, insert_mapped_mark, to); +} + +static void build_mark_map(struct string_list *from, struct string_list *to) +{ + struct string_list_item *fromp, *top; + + sub_oid_map = kh_init_oid_map(); + + for_each_string_list_item(fromp, from) { + top = string_list_lookup(to, fromp->string); + if (!fromp->util) { + die(_("Missing from marks for submodule '%s'"), fromp->string); + } else if (!top || !top->util) { + die(_("Missing to marks for submodule '%s'"), fromp->string); + } + build_mark_map_one(fromp->util, top->util); + } +} + static struct object_entry *parse_treeish_dataref(const char **p) { struct object_id oid; struct object_entry *e; if (**p == ':') { /* <mark> */ - e = find_mark(parse_mark_ref_space(p)); + e = find_mark(marks, parse_mark_ref_space(p)); if (!e) die("Unknown mark: %s", command_buf.buf); oidcpy(&oid, &e->idx.oid); } else { /* <sha1> */ - if (parse_oid_hex(*p, &oid, p)) + if (parse_mapped_oid_hex(*p, &oid, p)) die("Invalid dataref: %s", command_buf.buf); e = find_object(&oid); if (*(*p)++ != ' ') @@ -3059,6 +3209,28 @@ static void parse_progress(void) skip_optional_lf(); } +static void parse_alias(void) +{ + struct object_entry *e; + struct branch b; + + skip_optional_lf(); + read_next_command(); + + /* mark ... */ + parse_mark(); + if (!next_mark) + die(_("Expected 'mark' command, got %s"), command_buf.buf); + + /* to ... */ + memset(&b, 0, sizeof(b)); + if (!parse_objectish_with_prefix(&b, "to ")) + die(_("Expected 'to' command, got %s"), command_buf.buf); + e = find_object(&b.oid); + assert(e); + insert_mark(marks, next_mark, e); +} + static char* make_fast_import_path(const char *path) { if (!relative_marks_paths || is_absolute_path(path)) @@ -3079,7 +3251,6 @@ static void option_import_marks(const char *marks, } import_marks_file = make_fast_import_path(marks); - safe_create_leading_directories_const(import_marks_file); import_marks_file_from_stream = from_stream; import_marks_file_ignore_missing = ignore_missing; } @@ -3088,6 +3259,8 @@ static void option_date_format(const char *fmt) { if (!strcmp(fmt, "raw")) whenspec = WHENSPEC_RAW; + else if (!strcmp(fmt, "raw-permissive")) + whenspec = WHENSPEC_RAW_PERMISSIVE; else if (!strcmp(fmt, "rfc2822")) whenspec = WHENSPEC_RFC2822; else if (!strcmp(fmt, "now")) @@ -3120,7 +3293,6 @@ static void option_active_branches(const char *branches) static void option_export_marks(const char *marks) { export_marks_file = make_fast_import_path(marks); - safe_create_leading_directories_const(export_marks_file); } static void option_cat_blob_fd(const char *fd) @@ -3138,6 +3310,26 @@ static void option_export_pack_edges(const char *edges) pack_edges = xfopen(edges, "a"); } +static void option_rewrite_submodules(const char *arg, struct string_list *list) +{ + struct mark_set *ms; + FILE *fp; + char *s = xstrdup(arg); + char *f = strchr(s, ':'); + if (!f) + die(_("Expected format name:filename for submodule rewrite option")); + *f = '\0'; + f++; + ms = xcalloc(1, sizeof(*ms)); + string_list_insert(list, s)->util = ms; + + fp = fopen(f, "r"); + if (!fp) + die_errno("cannot read '%s'", f); + read_mark_file(ms, fp, insert_oid_entry); + fclose(fp); +} + static int parse_one_option(const char *option) { if (skip_prefix(option, "max-pack-size=", &option)) { @@ -3163,10 +3355,12 @@ static int parse_one_option(const char *option) option_active_branches(option); } else if (skip_prefix(option, "export-pack-edges=", &option)) { option_export_pack_edges(option); - } else if (starts_with(option, "quiet")) { + } else if (!strcmp(option, "quiet")) { show_stats = 0; - } else if (starts_with(option, "stats")) { + } else if (!strcmp(option, "stats")) { show_stats = 1; + } else if (!strcmp(option, "allow-unsafe-features")) { + ; /* already handled during early option parsing */ } else { return 0; } @@ -3174,6 +3368,13 @@ static int parse_one_option(const char *option) return 1; } +static void check_unsafe_feature(const char *feature, int from_stream) +{ + if (from_stream && !allow_unsafe_features) + die(_("feature '%s' forbidden in input without --allow-unsafe-features"), + feature); +} + static int parse_one_feature(const char *feature, int from_stream) { const char *arg; @@ -3181,11 +3382,21 @@ static int parse_one_feature(const char *feature, int from_stream) if (skip_prefix(feature, "date-format=", &arg)) { option_date_format(arg); } else if (skip_prefix(feature, "import-marks=", &arg)) { + check_unsafe_feature("import-marks", from_stream); option_import_marks(arg, from_stream, 0); } else if (skip_prefix(feature, "import-marks-if-exists=", &arg)) { + check_unsafe_feature("import-marks-if-exists", from_stream); option_import_marks(arg, from_stream, 1); } else if (skip_prefix(feature, "export-marks=", &arg)) { + check_unsafe_feature(feature, from_stream); option_export_marks(arg); + } else if (!strcmp(feature, "alias")) { + ; /* Don't die - this feature is supported */ + } else if (skip_prefix(feature, "rewrite-submodules-to=", &arg)) { + option_rewrite_submodules(arg, &sub_marks_to); + } else if (skip_prefix(feature, "rewrite-submodules-from=", &arg)) { + option_rewrite_submodules(arg, &sub_marks_from); + } else if (skip_prefix(feature, "rewrite-submodules-from=", &arg)) { } else if (!strcmp(feature, "get-mark")) { ; /* Don't die - this feature is supported */ } else if (!strcmp(feature, "cat-blob")) { @@ -3291,16 +3502,16 @@ static void parse_argv(void) seen_data_command = 1; if (import_marks_file) read_marks(); + build_mark_map(&sub_marks_from, &sub_marks_to); } -int cmd_main(int argc, const char **argv) +int cmd_fast_import(int argc, const char **argv, const char *prefix) { unsigned int i; if (argc == 2 && !strcmp(argv[1], "-h")) usage(fast_import_usage); - setup_git_directory(); reset_pack_idx_option(&pack_idx_opts); git_pack_config(); @@ -3311,6 +3522,22 @@ int cmd_main(int argc, const char **argv) avail_tree_table = xcalloc(avail_tree_table_sz, sizeof(struct avail_tree_content*)); marks = mem_pool_calloc(&fi_mem_pool, 1, sizeof(struct mark_set)); + hashmap_init(&object_table, object_entry_hashcmp, NULL, 0); + + /* + * We don't parse most options until after we've seen the set of + * "feature" lines at the start of the stream (which allows the command + * line to override stream data). But we must do an early parse of any + * command-line options that impact how we interpret the feature lines. + */ + for (i = 1; i < argc; i++) { + const char *arg = argv[i]; + if (*arg != '-' || !strcmp(arg, "--")) + break; + if (!strcmp(arg, "--allow-unsafe-features")) + allow_unsafe_features = 1; + } + global_argc = argc; global_argv = argv; @@ -3342,6 +3569,8 @@ int cmd_main(int argc, const char **argv) parse_checkpoint(); else if (!strcmp("done", command_buf.buf)) break; + else if (!strcmp("alias", command_buf.buf)) + parse_alias(); else if (starts_with(command_buf.buf, "progress ")) parse_progress(); else if (skip_prefix(command_buf.buf, "feature ", &v)) |