lf;
commit_msg ::= data;
- file_change ::= file_clr | file_del | file_obm | file_inm;
+ file_change ::= file_clr | file_del | file_rnm | file_obm | file_inm;
file_clr ::= 'deleteall' lf;
file_del ::= 'D' sp path_str lf;
+ file_rnm ::= 'R' sp path_str sp path_str lf;
file_obm ::= 'M' sp mode sp (hexsha1 | idnum) sp path_str lf;
file_inm ::= 'M' sp mode sp 'inline' sp path_str lf
data;
#define PACK_ID_BITS 16
#define MAX_PACK_ID ((1<<PACK_ID_BITS)-1)
-#ifndef PRIuMAX
-#define PRIuMAX "llu"
-#endif
-
struct object_entry
{
struct object_entry *next;
const char *name;
struct tree_entry branch_tree;
uintmax_t last_commit;
- unsigned int pack_id;
+ unsigned active : 1;
+ unsigned pack_id : PACK_ID_BITS;
unsigned char sha1[20];
};
/* Configured limits on output */
static unsigned long max_depth = 10;
-static unsigned long max_packsize = (1LL << 32) - 1;
+static off_t max_packsize = (1LL << 32) - 1;
static int force_update;
/* Stats and misc. counters */
b->table_next_branch = branch_table[hc];
b->branch_tree.versions[0].mode = S_IFDIR;
b->branch_tree.versions[1].mode = S_IFDIR;
+ b->active = 0;
b->pack_id = MAX_PACK_ID;
branch_table[hc] = b;
branch_count++;
int pack_fd;
snprintf(tmpfile, sizeof(tmpfile),
- "%s/pack_XXXXXX", get_object_directory());
+ "%s/tmp_pack_XXXXXX", get_object_directory());
pack_fd = mkstemp(tmpfile);
if (pack_fd < 0)
die("Can't create %s: %s", tmpfile, strerror(errno));
all_packs[pack_id] = p;
}
-static void fixup_header_footer(void)
-{
- static const int buf_sz = 128 * 1024;
- int pack_fd = pack_data->pack_fd;
- SHA_CTX c;
- struct pack_header hdr;
- char *buf;
-
- if (lseek(pack_fd, 0, SEEK_SET) != 0)
- die("Failed seeking to start: %s", strerror(errno));
- if (read_in_full(pack_fd, &hdr, sizeof(hdr)) != sizeof(hdr))
- die("Unable to reread header of %s", pack_data->pack_name);
- if (lseek(pack_fd, 0, SEEK_SET) != 0)
- die("Failed seeking to start: %s", strerror(errno));
- hdr.hdr_entries = htonl(object_count);
- write_or_die(pack_fd, &hdr, sizeof(hdr));
-
- SHA1_Init(&c);
- SHA1_Update(&c, &hdr, sizeof(hdr));
-
- buf = xmalloc(buf_sz);
- for (;;) {
- size_t n = xread(pack_fd, buf, buf_sz);
- if (!n)
- break;
- if (n < 0)
- die("Failed to checksum %s", pack_data->pack_name);
- SHA1_Update(&c, buf, n);
- }
- free(buf);
-
- SHA1_Final(pack_data->sha1, &c);
- write_or_die(pack_fd, pack_data->sha1, sizeof(pack_data->sha1));
- close(pack_fd);
-}
-
static int oecmp (const void *a_, const void *b_)
{
struct object_entry *a = *((struct object_entry**)a_);
}
snprintf(tmpfile, sizeof(tmpfile),
- "%s/index_XXXXXX", get_object_directory());
+ "%s/tmp_idx_XXXXXX", get_object_directory());
idx_fd = mkstemp(tmpfile);
if (idx_fd < 0)
die("Can't create %s: %s", tmpfile, strerror(errno));
static char *keep_pack(char *curr_index_name)
{
static char name[PATH_MAX];
- static char *keep_msg = "fast-import";
+ static const char *keep_msg = "fast-import";
int keep_fd;
chmod(pack_data->pack_name, 0444);
struct branch *b;
struct tag *t;
- fixup_header_footer();
+ fixup_pack_header_footer(pack_data->pack_fd, pack_data->sha1,
+ pack_data->pack_name, object_count);
+ close(pack_data->pack_fd);
idx_name = keep_pack(create_index());
/* Register the packfile with core git's machinary. */
SHA_CTX c;
z_stream s;
- hdrlen = sprintf((char*)hdr,"%s %lu", type_names[type],
+ hdrlen = sprintf((char*)hdr,"%s %lu", typename(type),
(unsigned long)datlen) + 1;
SHA1_Init(&c);
SHA1_Update(&c, hdr, hdrlen);
if (e->offset) {
duplicate_count_by_type[type]++;
return 1;
+ } else if (find_sha1_pack(sha1, packed_git)) {
+ e->type = type;
+ e->pack_id = MAX_PACK_ID;
+ e->offset = 1; /* just not zero! */
+ duplicate_count_by_type[type]++;
+ return 1;
}
if (last && last->data && last->depth < max_depth) {
struct object_entry *oe,
unsigned long *sizep)
{
- static char type[20];
+ enum object_type type;
struct packed_git *p = all_packs[oe->pack_id];
if (p == pack_data)
p->pack_size = pack_size + 20;
- return unpack_entry(p, oe->offset, type, sizep);
+ return unpack_entry(p, oe->offset, &type, sizep);
}
static const char *get_mode(const char *str, uint16_t *modep)
return;
myoe = find_object(sha1);
- if (myoe) {
+ if (myoe && myoe->pack_id != MAX_PACK_ID) {
if (myoe->type != OBJ_TREE)
die("Not a tree: %s", sha1_to_hex(sha1));
t->delta_depth = 0;
buf = gfi_unpack_entry(myoe, &size);
} else {
- char type[20];
- buf = read_sha1_file(sha1, type, &size);
- if (!buf || strcmp(type, tree_type))
+ enum object_type type;
+ buf = read_sha1_file(sha1, &type, &size);
+ if (!buf || type != OBJ_TREE)
die("Can't load tree %s", sha1_to_hex(sha1));
}
struct tree_entry *e = new_tree_entry();
if (t->entry_count == t->entry_capacity)
- root->tree = t = grow_tree_content(t, 8);
+ root->tree = t = grow_tree_content(t, t->entry_count);
t->entries[t->entry_count++] = e;
e->tree = NULL;
if (!c)
die("Corrupt mode in %s", sha1_to_hex(sha1));
e->versions[0].mode = e->versions[1].mode;
- e->name = to_atom(c, (unsigned short)strlen(c));
+ e->name = to_atom(c, strlen(c));
c += e->name->str_len + 1;
hashcpy(e->versions[0].sha1, (unsigned char*)c);
hashcpy(e->versions[1].sha1, (unsigned char*)c);
|| le->pack_id != pack_id) {
lo.data = NULL;
lo.depth = 0;
+ lo.no_free = 0;
} else {
mktree(t, 0, &lo.len, &old_tree);
lo.data = old_tree.buffer;
struct tree_entry *root,
const char *p,
const unsigned char *sha1,
- const uint16_t mode)
+ const uint16_t mode,
+ struct tree_content *subtree)
{
struct tree_content *t = root->tree;
const char *slash1;
n = slash1 - p;
else
n = strlen(p);
+ if (!n)
+ die("Empty path component found in input");
+ if (!slash1 && !S_ISDIR(mode) && subtree)
+ die("Non-directories cannot have subtrees");
for (i = 0; i < t->entry_count; i++) {
e = t->entries[i];
if (e->name->str_len == n && !strncmp(p, e->name->str_dat, n)) {
if (!slash1) {
- if (e->versions[1].mode == mode
+ if (!S_ISDIR(mode)
+ && e->versions[1].mode == mode
&& !hashcmp(e->versions[1].sha1, sha1))
return 0;
e->versions[1].mode = mode;
hashcpy(e->versions[1].sha1, sha1);
- if (e->tree) {
+ if (e->tree)
release_tree_content_recursive(e->tree);
- e->tree = NULL;
- }
+ e->tree = subtree;
hashclr(root->versions[1].sha1);
return 1;
}
}
if (!e->tree)
load_tree(e);
- if (tree_content_set(e, slash1 + 1, sha1, mode)) {
+ if (tree_content_set(e, slash1 + 1, sha1, mode, subtree)) {
hashclr(root->versions[1].sha1);
return 1;
}
}
if (t->entry_count == t->entry_capacity)
- root->tree = t = grow_tree_content(t, 8);
+ root->tree = t = grow_tree_content(t, t->entry_count);
e = new_tree_entry();
- e->name = to_atom(p, (unsigned short)n);
+ e->name = to_atom(p, n);
e->versions[0].mode = 0;
hashclr(e->versions[0].sha1);
t->entries[t->entry_count++] = e;
if (slash1) {
e->tree = new_tree_content(8);
e->versions[1].mode = S_IFDIR;
- tree_content_set(e, slash1 + 1, sha1, mode);
+ tree_content_set(e, slash1 + 1, sha1, mode, subtree);
} else {
- e->tree = NULL;
+ e->tree = subtree;
e->versions[1].mode = mode;
hashcpy(e->versions[1].sha1, sha1);
}
return 1;
}
-static int tree_content_remove(struct tree_entry *root, const char *p)
+static int tree_content_remove(
+ struct tree_entry *root,
+ const char *p,
+ struct tree_entry *backup_leaf)
{
struct tree_content *t = root->tree;
const char *slash1;
goto del_entry;
if (!e->tree)
load_tree(e);
- if (tree_content_remove(e, slash1 + 1)) {
+ if (tree_content_remove(e, slash1 + 1, backup_leaf)) {
for (n = 0; n < e->tree->entry_count; n++) {
if (e->tree->entries[n]->versions[1].mode) {
hashclr(root->versions[1].sha1);
return 1;
}
}
+ backup_leaf = NULL;
goto del_entry;
}
return 0;
return 0;
del_entry:
- if (e->tree) {
+ if (backup_leaf)
+ memcpy(backup_leaf, e, sizeof(*backup_leaf));
+ else if (e->tree)
release_tree_content_recursive(e->tree);
- e->tree = NULL;
- }
+ e->tree = NULL;
e->versions[1].mode = 0;
hashclr(e->versions[1].sha1);
hashclr(root->versions[1].sha1);
if (read_ref(b->name, old_sha1))
hashclr(old_sha1);
- lock = lock_any_ref_for_update(b->name, old_sha1);
+ lock = lock_any_ref_for_update(b->name, old_sha1, 0);
if (!lock)
return error("Unable to lock %s", b->name);
if (!force_update && !is_null_sha1(old_sha1)) {
if (!in_merge_bases(old_cmit, &new_cmit, 1)) {
unlock_ref(lock);
- warn("Not updating %s"
+ warning("Not updating %s"
" (new tip %s does not contain %s)",
b->name, sha1_to_hex(b->sha1), sha1_to_hex(old_sha1));
return -1;
static void dump_marks(void)
{
- if (mark_file)
- {
- FILE *f = fopen(mark_file, "w");
- if (f) {
- dump_marks_helper(f, 0, marks);
- fclose(f);
- } else
- failure |= error("Unable to write marks file %s: %s",
- mark_file, strerror(errno));
+ static struct lock_file mark_lock;
+ int mark_fd;
+ FILE *f;
+
+ if (!mark_file)
+ return;
+
+ mark_fd = hold_lock_file_for_update(&mark_lock, mark_file, 0);
+ if (mark_fd < 0) {
+ failure |= error("Unable to write marks file %s: %s",
+ mark_file, strerror(errno));
+ return;
}
+
+ f = fdopen(mark_fd, "w");
+ if (!f) {
+ rollback_lock_file(&mark_lock);
+ failure |= error("Unable to write marks file %s: %s",
+ mark_file, strerror(errno));
+ return;
+ }
+
+ dump_marks_helper(f, 0, marks);
+ fclose(f);
+ if (commit_lock_file(&mark_lock))
+ failure |= error("Unable to write marks file %s: %s",
+ mark_file, strerror(errno));
}
static void read_next_command(void)
{
while (cur_active_branches
&& cur_active_branches >= max_active_branches) {
- unsigned long min_commit = ULONG_MAX;
+ uintmax_t min_commit = ULONG_MAX;
struct branch *e, *l = NULL, *p = NULL;
for (e = active_branches; e; e = e->active_next_branch) {
e = active_branches;
active_branches = e->active_next_branch;
}
+ e->active = 0;
e->active_next_branch = NULL;
if (e->branch_tree.tree) {
release_tree_content_recursive(e->branch_tree.tree);
static void load_branch(struct branch *b)
{
load_tree(&b->branch_tree);
- b->active_next_branch = active_branches;
- active_branches = b;
- cur_active_branches++;
- branch_load_count++;
+ if (!b->active) {
+ b->active = 1;
+ b->active_next_branch = active_branches;
+ active_branches = b;
+ cur_active_branches++;
+ branch_load_count++;
+ }
}
static void file_change_m(struct branch *b)
struct object_entry *oe = oe;
unsigned char sha1[20];
uint16_t mode, inline_data = 0;
- char type[20];
p = get_mode(p, &mode);
if (!p)
} else if (oe) {
if (oe->type != OBJ_BLOB)
die("Not a blob (actually a %s): %s",
- command_buf.buf, type_names[oe->type]);
+ command_buf.buf, typename(oe->type));
} else {
- if (sha1_object_info(sha1, type, NULL))
+ enum object_type type = sha1_object_info(sha1, NULL);
+ if (type < 0)
die("Blob not found: %s", command_buf.buf);
- if (strcmp(blob_type, type))
+ if (type != OBJ_BLOB)
die("Not a blob (actually a %s): %s",
- command_buf.buf, type);
+ typename(type), command_buf.buf);
}
- tree_content_set(&b->branch_tree, p, sha1, S_IFREG | mode);
+ tree_content_set(&b->branch_tree, p, sha1, S_IFREG | mode, NULL);
free(p_uq);
}
die("Garbage after path in: %s", command_buf.buf);
p = p_uq;
}
- tree_content_remove(&b->branch_tree, p);
+ tree_content_remove(&b->branch_tree, p, NULL);
free(p_uq);
}
+static void file_change_r(struct branch *b)
+{
+ const char *s, *d;
+ char *s_uq, *d_uq;
+ const char *endp;
+ struct tree_entry leaf;
+
+ s = command_buf.buf + 2;
+ s_uq = unquote_c_style(s, &endp);
+ if (s_uq) {
+ if (*endp != ' ')
+ die("Missing space after source: %s", command_buf.buf);
+ }
+ else {
+ endp = strchr(s, ' ');
+ if (!endp)
+ die("Missing space after source: %s", command_buf.buf);
+ s_uq = xmalloc(endp - s + 1);
+ memcpy(s_uq, s, endp - s);
+ s_uq[endp - s] = 0;
+ }
+ s = s_uq;
+
+ endp++;
+ if (!*endp)
+ die("Missing dest: %s", command_buf.buf);
+
+ d = endp;
+ d_uq = unquote_c_style(d, &endp);
+ if (d_uq) {
+ if (*endp)
+ die("Garbage after dest in: %s", command_buf.buf);
+ d = d_uq;
+ }
+
+ memset(&leaf, 0, sizeof(leaf));
+ tree_content_remove(&b->branch_tree, s, &leaf);
+ if (!leaf.versions[1].mode)
+ die("Path %s not in branch", s);
+ tree_content_set(&b->branch_tree, d,
+ leaf.versions[1].sha1,
+ leaf.versions[1].mode,
+ leaf.tree);
+
+ free(s_uq);
+ free(d_uq);
+}
+
static void file_change_deleteall(struct branch *b)
{
release_tree_content_recursive(b->branch_tree.tree);
load_tree(&b->branch_tree);
}
+static void cmd_from_commit(struct branch *b, char *buf, unsigned long size)
+{
+ if (!buf || size < 46)
+ die("Not a valid commit: %s", sha1_to_hex(b->sha1));
+ if (memcmp("tree ", buf, 5)
+ || get_sha1_hex(buf + 5, b->branch_tree.versions[1].sha1))
+ die("The commit %s is corrupt", sha1_to_hex(b->sha1));
+ hashcpy(b->branch_tree.versions[0].sha1,
+ b->branch_tree.versions[1].sha1);
+}
+
+static void cmd_from_existing(struct branch *b)
+{
+ if (is_null_sha1(b->sha1)) {
+ hashclr(b->branch_tree.versions[0].sha1);
+ hashclr(b->branch_tree.versions[1].sha1);
+ } else {
+ unsigned long size;
+ char *buf;
+
+ buf = read_object_with_reference(b->sha1,
+ commit_type, &size, b->sha1);
+ cmd_from_commit(b, buf, size);
+ free(buf);
+ }
+}
+
static void cmd_from(struct branch *b)
{
const char *from;
} else if (*from == ':') {
uintmax_t idnum = strtoumax(from + 1, NULL, 10);
struct object_entry *oe = find_mark(idnum);
- unsigned long size;
- char *buf;
if (oe->type != OBJ_COMMIT)
die("Mark :%" PRIuMAX " not a commit", idnum);
hashcpy(b->sha1, oe->sha1);
- buf = gfi_unpack_entry(oe, &size);
- if (!buf || size < 46)
- die("Not a valid commit: %s", from);
- if (memcmp("tree ", buf, 5)
- || get_sha1_hex(buf + 5, b->branch_tree.versions[1].sha1))
- die("The commit %s is corrupt", sha1_to_hex(b->sha1));
- free(buf);
- hashcpy(b->branch_tree.versions[0].sha1,
- b->branch_tree.versions[1].sha1);
- } else if (!get_sha1(from, b->sha1)) {
- if (is_null_sha1(b->sha1)) {
- hashclr(b->branch_tree.versions[0].sha1);
- hashclr(b->branch_tree.versions[1].sha1);
- } else {
+ if (oe->pack_id != MAX_PACK_ID) {
unsigned long size;
- char *buf;
-
- buf = read_object_with_reference(b->sha1,
- type_names[OBJ_COMMIT], &size, b->sha1);
- if (!buf || size < 46)
- die("Not a valid commit: %s", from);
- if (memcmp("tree ", buf, 5)
- || get_sha1_hex(buf + 5, b->branch_tree.versions[1].sha1))
- die("The commit %s is corrupt", sha1_to_hex(b->sha1));
+ char *buf = gfi_unpack_entry(oe, &size);
+ cmd_from_commit(b, buf, size);
free(buf);
- hashcpy(b->branch_tree.versions[0].sha1,
- b->branch_tree.versions[1].sha1);
- }
- } else
+ } else
+ cmd_from_existing(b);
+ } else if (!get_sha1(from, b->sha1))
+ cmd_from_existing(b);
+ else
die("Invalid ref name or SHA1 expression: %s", from);
read_next_command();
if (oe->type != OBJ_COMMIT)
die("Mark :%" PRIuMAX " not a commit", idnum);
hashcpy(n->sha1, oe->sha1);
- } else if (get_sha1(from, n->sha1))
+ } else if (!get_sha1(from, n->sha1)) {
+ unsigned long size;
+ char *buf = read_object_with_reference(n->sha1,
+ commit_type, &size, n->sha1);
+ if (!buf || size < 46)
+ die("Not a valid commit: %s", from);
+ free(buf);
+ } else
die("Invalid ref name or SHA1 expression: %s", from);
n->next = NULL;
file_change_m(b);
else if (!prefixcmp(command_buf.buf, "D "))
file_change_d(b);
+ else if (!prefixcmp(command_buf.buf, "R "))
+ file_change_r(b);
else if (!strcmp("deleteall", command_buf.buf))
file_change_deleteall(b);
else
char *buf;
buf = read_object_with_reference(sha1,
- type_names[OBJ_COMMIT], &size, sha1);
+ commit_type, &size, sha1);
if (!buf || size < 46)
die("Not a valid commit: %s", from);
free(buf);
size_dbuf(&new_data, 67+strlen(t->name)+strlen(tagger)+msglen);
sp = new_data.buffer;
sp += sprintf(sp, "object %s\n", sha1_to_hex(sha1));
- sp += sprintf(sp, "type %s\n", type_names[OBJ_COMMIT]);
+ sp += sprintf(sp, "type %s\n", commit_type);
sp += sprintf(sp, "tag %s\n", t->name);
sp += sprintf(sp, "tagger %s\n", tagger);
*sp++ = '\n';
read_next_command();
}
+static void import_marks(const char *input_file)
+{
+ char line[512];
+ FILE *f = fopen(input_file, "r");
+ if (!f)
+ die("cannot read %s: %s", input_file, strerror(errno));
+ while (fgets(line, sizeof(line), f)) {
+ uintmax_t mark;
+ char *end;
+ unsigned char sha1[20];
+ struct object_entry *e;
+
+ end = strchr(line, '\n');
+ if (line[0] != ':' || !end)
+ die("corrupt mark line: %s", line);
+ *end = 0;
+ mark = strtoumax(line + 1, &end, 10);
+ if (!mark || end == line + 1
+ || *end != ' ' || get_sha1(end + 1, sha1))
+ die("corrupt mark line: %s", line);
+ e = find_object(sha1);
+ if (!e) {
+ enum object_type type = sha1_object_info(sha1, NULL);
+ if (type < 0)
+ die("object not found: %s", sha1_to_hex(sha1));
+ e = insert_object(sha1);
+ e->type = type;
+ e->pack_id = MAX_PACK_ID;
+ e->offset = 1; /* just not zero! */
+ }
+ insert_mark(mark, e);
+ }
+ fclose(f);
+}
+
static const char fast_import_usage[] =
"git-fast-import [--date-format=f] [--max-pack-size=n] [--depth=n] [--active-branches=n] [--export-marks=marks.file]";
int i, show_stats = 1;
git_config(git_default_config);
+ alloc_objects(object_entry_alloc);
+ strbuf_init(&command_buf);
+ atom_table = xcalloc(atom_table_sz, sizeof(struct atom_str*));
+ branch_table = xcalloc(branch_table_sz, sizeof(struct branch*));
+ avail_tree_table = xcalloc(avail_tree_table_sz, sizeof(struct avail_tree_content*));
+ marks = pool_calloc(1, sizeof(struct mark_set));
for (i = 1; i < argc; i++) {
const char *a = argv[i];
max_depth = strtoul(a + 8, NULL, 0);
else if (!prefixcmp(a, "--active-branches="))
max_active_branches = strtoul(a + 18, NULL, 0);
+ else if (!prefixcmp(a, "--import-marks="))
+ import_marks(a + 15);
else if (!prefixcmp(a, "--export-marks="))
mark_file = a + 15;
else if (!prefixcmp(a, "--export-pack-edges=")) {
if (i != argc)
usage(fast_import_usage);
- alloc_objects(object_entry_alloc);
- strbuf_init(&command_buf);
-
- atom_table = xcalloc(atom_table_sz, sizeof(struct atom_str*));
- branch_table = xcalloc(branch_table_sz, sizeof(struct branch*));
- avail_tree_table = xcalloc(avail_tree_table_sz, sizeof(struct avail_tree_content*));
- marks = pool_calloc(1, sizeof(struct mark_set));
-
+ prepare_packed_git();
start_packfile();
for (;;) {
read_next_command();