--(no-)-relative-marks= with the --(import|export)-marks=
options.
+--cat-blob-fd=<fd>::
+ Specify the file descriptor that will be written to
+ when the `cat-blob` command is encountered in the stream.
+ The default behaviour is to write to `stdout`.
+
--export-pack-edges=<file>::
After creating a packfile, print a line of data to
<file> listing the filename of the packfile and the last
standard output. This command is optional and is not needed
to perform an import.
+`cat-blob`::
+ Causes fast-import to print a blob in 'cat-file --batch'
+ format to the file descriptor set with `--cat-blob-fd` or
+ `stdout` if unspecified.
+
`feature`::
Require that fast-import supports the specified feature, or
abort if it does not.
* A complete 40 byte or abbreviated commit SHA-1 in hex.
* Any valid Git SHA-1 expression that resolves to a commit. See
- ``SPECIFYING REVISIONS'' in linkgit:git-rev-parse[1] for details.
+ ``SPECIFYING REVISIONS'' in linkgit:gitrevisions[7] for details.
The special case of restarting an incremental import from the
current branch value should be written as:
'M' SP <mode> SP <dataref> SP <path> LF
....
+
-Here `<dataref>` can be either a mark reference (`:<idnum>`)
+Here usually `<dataref>` must be either a mark reference (`:<idnum>`)
set by a prior `blob` command, or a full 40-byte SHA-1 of an
-existing Git blob object.
+existing Git blob object. If `<mode>` is `040000`` then
+`<dataref>` must be the full 40-byte SHA-1 of an existing
+Git tree object or a mark reference set with `--import-marks`.
Inline data format::
The data content for the file has not been supplied yet.
* `160000`: A gitlink, SHA-1 of the object refers to a commit in
another repository. Git links can only be specified by SHA or through
a commit mark. They are used to implement submodules.
+* `040000`: A subdirectory. Subdirectories can only be specified by
+ SHA or through a tree mark set with `--import-marks`.
In both formats `<path>` is the complete path of the file to be added
(if not already existing) or modified (if already existing).
* contain the special component `.` or `..` (e.g. `foo/./bar` and
`foo/../bar` are invalid).
+The root of the tree can be represented by an empty string as `<path>`.
+
It is recommended that `<path>` always be encoded using UTF-8.
`filedelete`
inform the reader when the `checkpoint` has been completed and it
can safely access the refs that fast-import updated.
+`cat-blob`
+~~~~~~~~~~
+Causes fast-import to print a blob to a file descriptor previously
+arranged with the `--cat-blob-fd` argument. The command otherwise
+has no impact on the current import; its main purpose is to
+retrieve blobs that may be in fast-import's memory but not
+accessible from the target repository.
+
+....
+ 'cat-blob' SP <dataref> LF
+....
+
+The `<dataref>` can be either a mark reference (`:<idnum>`)
+set previously or a full 40-byte SHA-1 of a Git blob, preexisting or
+ready to be written.
+
+Output uses the same format as `git cat-file --batch`:
+
+====
+ <sha1> SP 'blob' SP <size> LF
+ <contents> LF
+====
+
+This command can be used anywhere in the stream that comments are
+accepted. In particular, the `cat-blob` command can be used in the
+middle of a commit but not in the middle of a `data` command.
+
`feature`
~~~~~~~~~
Require that fast-import supports the specified feature, or abort if
second, an --import-marks= command-line option overrides
any "feature import-marks" command in the stream.
+cat-blob::
+ Ignored. Versions of fast-import not supporting the
+ "cat-blob" command will exit with a message indicating so.
+ This lets the import error out early with a clear message,
+ rather than wasting time on the early part of an import
+ before the unsupported command is detected.
+
+ notes::
+ Require that the backend support the 'notemodify' (N)
+ subcommand to the 'commit' command.
+ Versions of fast-import not supporting notes will exit
+ with a message indicating so.
+
++
`option`
~~~~~~~~
Processes the specified option so that git fast-import behaves in a
* date-format
* import-marks
* export-marks
+* cat-blob-fd
* force
Crash Reports
projects with 2,000+ branches and 45,114+ files in a very limited
memory footprint (less than 2.7 MiB per active branch).
+Signals
+-------
+Sending *SIGUSR1* to the 'git fast-import' process ends the current
+packfile early, simulating a `checkpoint` command. The impatient
+operator can use this facility to peek at the objects and refs from an
+import in progress, at the cost of some added running time and worse
+compression.
Author
------
ts ::= # time since the epoch in seconds, ascii base10 notation;
tz ::= # GIT style timezone;
- # note: comments may appear anywhere in the input, except
- # within a data command. Any form of the data command
- # always escapes the related input from comment processing.
+ # note: comments and cat requests may appear anywhere
+ # in the input, except within a data command. Any form
+ # of the data command always escapes the related input
+ # from comment processing.
#
# In case it is not clear, the '#' that starts the comment
# must be the first character on that line (an lf
# preceded it).
#
+ cat_blob ::= 'cat-blob' sp (hexsha1 | idnum) lf;
+
comment ::= '#' not_lf* lf;
not_lf ::= # Any byte that is not ASCII newline (LF);
*/
#include "csum-file.h"
#include "quote.h"
#include "exec_cmd.h"
+#include "dir.h"
#define PACK_ID_BITS 16
#define MAX_PACK_ID ((1<<PACK_ID_BITS)-1)
typedef enum {
WHENSPEC_RAW = 1,
WHENSPEC_RFC2822,
- WHENSPEC_NOW,
+ WHENSPEC_NOW
} whenspec_type;
struct recent_command
static struct strbuf new_data = STRBUF_INIT;
static int seen_data_command;
+/* Signal handling */
+static volatile sig_atomic_t checkpoint_requested;
+
+/* Where to write output of cat-blob commands */
+static int cat_blob_fd = STDOUT_FILENO;
+
static void parse_argv(void);
+static void parse_cat_blob(void);
static void write_branch_report(FILE *rpt, struct branch *b)
{
exit(128);
}
+#ifndef SIGUSR1 /* Windows, for example */
+
+static void set_checkpoint_signal(void)
+{
+}
+
+#else
+
+static void checkpoint_signal(int signo)
+{
+ checkpoint_requested = 1;
+}
+
+static void set_checkpoint_signal(void)
+{
+ struct sigaction sa;
+
+ memset(&sa, 0, sizeof(sa));
+ sa.sa_handler = checkpoint_signal;
+ sigemptyset(&sa.sa_mask);
+ sa.sa_flags = SA_RESTART;
+ sigaction(SIGUSR1, &sa, NULL);
+}
+
+#endif
+
static void alloc_objects(unsigned int cnt)
{
struct object_entry_pool *b;
{
unsigned int h = sha1[0] << 8 | sha1[1];
struct object_entry *e = object_table[h];
- struct object_entry *p = NULL;
while (e) {
if (!hashcmp(sha1, e->idx.sha1))
return e;
- p = e;
e = e->next;
}
e = new_object(sha1);
- e->next = NULL;
+ e->next = object_table[h];
e->idx.offset = 0;
- if (p)
- p->next = e;
- else
- object_table[h] = e;
+ object_table[h] = e;
return e;
}
start_packfile();
}
-static size_t encode_header(
- enum object_type type,
- uintmax_t size,
- unsigned char *hdr)
-{
- int n = 1;
- unsigned char c;
-
- if (type < OBJ_COMMIT || type > OBJ_REF_DELTA)
- die("bad type %d", type);
-
- c = (type << 4) | (size & 15);
- size >>= 4;
- while (size) {
- *hdr++ = c | 0x80;
- c = size & 0x7f;
- size >>= 7;
- n++;
- }
- *hdr = c;
- return n;
-}
-
static int store_object(
enum object_type type,
struct strbuf *dat,
delta_count_by_type[type]++;
e->depth = last->depth + 1;
- hdrlen = encode_header(OBJ_OFS_DELTA, deltalen, hdr);
+ hdrlen = encode_in_pack_object_header(OBJ_OFS_DELTA, deltalen, hdr);
sha1write(pack_file, hdr, hdrlen);
pack_size += hdrlen;
pack_size += sizeof(hdr) - pos;
} else {
e->depth = 0;
- hdrlen = encode_header(type, dat->len, hdr);
+ hdrlen = encode_in_pack_object_header(type, dat->len, hdr);
sha1write(pack_file, hdr, hdrlen);
pack_size += hdrlen;
}
memset(&s, 0, sizeof(s));
deflateInit(&s, pack_compression_level);
- hdrlen = encode_header(OBJ_BLOB, len, out_buf);
+ hdrlen = encode_in_pack_object_header(OBJ_BLOB, len, out_buf);
if (out_sz <= hdrlen)
die("impossibly large object header");
t->entry_count -= del;
}
+static void tree_content_replace(
+ struct tree_entry *root,
+ const unsigned char *sha1,
+ const uint16_t mode,
+ struct tree_content *newtree)
+{
+ if (!S_ISDIR(mode))
+ die("Root cannot be a non-directory");
+ hashcpy(root->versions[1].sha1, sha1);
+ if (root->tree)
+ release_tree_content_recursive(root->tree);
+ root->tree = newtree;
+}
+
static int tree_content_set(
struct tree_entry *root,
const char *p,
const uint16_t mode,
struct tree_content *subtree)
{
- struct tree_content *t = root->tree;
+ struct tree_content *t;
const char *slash1;
unsigned int i, n;
struct tree_entry *e;
if (!slash1 && !S_ISDIR(mode) && subtree)
die("Non-directories cannot have subtrees");
+ if (!root->tree)
+ load_tree(root);
+ t = root->tree;
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 (e->name->str_len == n && !strncmp_icase(p, e->name->str_dat, n)) {
if (!slash1) {
if (!S_ISDIR(mode)
&& e->versions[1].mode == mode
const char *p,
struct tree_entry *backup_leaf)
{
- struct tree_content *t = root->tree;
+ struct tree_content *t;
const char *slash1;
unsigned int i, n;
struct tree_entry *e;
else
n = strlen(p);
+ if (!root->tree)
+ load_tree(root);
+ t = root->tree;
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 (e->name->str_len == n && !strncmp_icase(p, e->name->str_dat, n)) {
+ if (slash1 && !S_ISDIR(e->versions[1].mode))
+ /*
+ * If p names a file in some subdirectory, and a
+ * file or symlink matching the name of the
+ * parent directory of p exists, then p cannot
+ * exist and need not be deleted.
+ */
+ return 1;
if (!slash1 || !S_ISDIR(e->versions[1].mode))
goto del_entry;
if (!e->tree)
const char *p,
struct tree_entry *leaf)
{
- struct tree_content *t = root->tree;
+ struct tree_content *t;
const char *slash1;
unsigned int i, n;
struct tree_entry *e;
else
n = strlen(p);
+ if (!root->tree)
+ load_tree(root);
+ t = root->tree;
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 (e->name->str_len == n && !strncmp_icase(p, e->name->str_dat, n)) {
if (!slash1) {
memcpy(leaf, e, sizeof(*leaf));
if (e->tree && is_null_sha1(e->versions[1].sha1))
if (m->shift) {
for (k = 0; k < 1024; k++) {
if (m->data.sets[k])
- dump_marks_helper(f, (base + k) << m->shift,
+ dump_marks_helper(f, base + (k << m->shift),
m->data.sets[k]);
}
} else {
return EOF;
}
- do {
+ for (;;) {
if (unread_command_buf) {
unread_command_buf = 0;
} else {
rc->prev->next = rc;
cmd_tail = rc;
}
- } while (command_buf.buf[0] == '#');
-
- return 0;
+ if (!prefixcmp(command_buf.buf, "cat-blob ")) {
+ parse_cat_blob();
+ continue;
+ }
+ if (command_buf.buf[0] == '#')
+ continue;
+ return 0;
+ }
}
static void skip_optional_lf(void)
case S_IFREG | 0644:
case S_IFREG | 0755:
case S_IFLNK:
+ case S_IFDIR:
case S_IFGITLINK:
/* ok */
break;
p = uq.buf;
}
+ /* Git does not track empty, non-toplevel directories. */
+ if (S_ISDIR(mode) && !memcmp(sha1, EMPTY_TREE_SHA1_BIN, 20) && *p) {
+ tree_content_remove(&b->branch_tree, p, NULL);
+ return;
+ }
+
if (S_ISGITLINK(mode)) {
if (inline_data)
die("Git links cannot be specified 'inline': %s",
* another repository.
*/
} else if (inline_data) {
+ if (S_ISDIR(mode))
+ die("Directories cannot be specified 'inline': %s",
+ command_buf.buf);
if (p != uq.buf) {
strbuf_addstr(&uq, p);
p = uq.buf;
}
read_next_command();
parse_and_store_blob(&last_blob, sha1, 0);
- } else if (oe) {
- if (oe->type != OBJ_BLOB)
- die("Not a blob (actually a %s): %s",
- typename(oe->type), command_buf.buf);
} else {
- enum object_type type = sha1_object_info(sha1, NULL);
+ enum object_type expected = S_ISDIR(mode) ?
+ OBJ_TREE: OBJ_BLOB;
+ enum object_type type = oe ? oe->type :
+ sha1_object_info(sha1, NULL);
if (type < 0)
- die("Blob not found: %s", command_buf.buf);
- if (type != OBJ_BLOB)
- die("Not a blob (actually a %s): %s",
- typename(type), command_buf.buf);
+ die("%s not found: %s",
+ S_ISDIR(mode) ? "Tree" : "Blob",
+ command_buf.buf);
+ if (type != expected)
+ die("Not a %s (actually a %s): %s",
+ typename(expected), typename(type),
+ command_buf.buf);
}
+ if (!*p) {
+ tree_content_replace(&b->branch_tree, sha1, mode, NULL);
+ return;
+ }
tree_content_set(&b->branch_tree, p, sha1, mode, NULL);
}
tree_content_get(&b->branch_tree, s, &leaf);
if (!leaf.versions[1].mode)
die("Path %s not in branch", s);
+ if (!*d) { /* C "path/to/subdir" "" */
+ tree_content_replace(&b->branch_tree,
+ leaf.versions[1].sha1,
+ leaf.versions[1].mode,
+ leaf.tree);
+ return;
+ }
tree_content_set(&b->branch_tree, d,
leaf.versions[1].sha1,
leaf.versions[1].mode,
unread_command_buf = 1;
}
-static void parse_checkpoint(void)
+static void cat_blob_write(const char *buf, unsigned long size)
{
+ if (write_in_full(cat_blob_fd, buf, size) != size)
+ die_errno("Write to frontend failed");
+}
+
+static void cat_blob(struct object_entry *oe, unsigned char sha1[20])
+{
+ struct strbuf line = STRBUF_INIT;
+ unsigned long size;
+ enum object_type type = 0;
+ char *buf;
+
+ if (!oe || oe->pack_id == MAX_PACK_ID) {
+ buf = read_sha1_file(sha1, &type, &size);
+ } else {
+ type = oe->type;
+ buf = gfi_unpack_entry(oe, &size);
+ }
+
+ /*
+ * Output based on batch_one_object() from cat-file.c.
+ */
+ if (type <= 0) {
+ strbuf_reset(&line);
+ strbuf_addf(&line, "%s missing\n", sha1_to_hex(sha1));
+ cat_blob_write(line.buf, line.len);
+ strbuf_release(&line);
+ free(buf);
+ return;
+ }
+ if (!buf)
+ die("Can't read object %s", sha1_to_hex(sha1));
+ if (type != OBJ_BLOB)
+ die("Object %s is a %s but a blob was expected.",
+ sha1_to_hex(sha1), typename(type));
+ strbuf_reset(&line);
+ strbuf_addf(&line, "%s %s %lu\n", sha1_to_hex(sha1),
+ typename(type), size);
+ cat_blob_write(line.buf, line.len);
+ strbuf_release(&line);
+ cat_blob_write(buf, size);
+ cat_blob_write("\n", 1);
+ free(buf);
+}
+
+static void parse_cat_blob(void)
+{
+ const char *p;
+ struct object_entry *oe = oe;
+ unsigned char sha1[20];
+
+ /* cat-blob SP <object> LF */
+ p = command_buf.buf + strlen("cat-blob ");
+ if (*p == ':') {
+ char *x;
+ oe = find_mark(strtoumax(p + 1, &x, 10));
+ if (x == p + 1)
+ die("Invalid mark: %s", command_buf.buf);
+ if (!oe)
+ die("Unknown mark: %s", command_buf.buf);
+ if (*x)
+ die("Garbage after mark: %s", command_buf.buf);
+ hashcpy(sha1, oe->idx.sha1);
+ } else {
+ if (get_sha1_hex(p, sha1))
+ die("Invalid SHA1: %s", command_buf.buf);
+ if (p[40])
+ die("Garbage after SHA1: %s", command_buf.buf);
+ oe = find_object(sha1);
+ }
+
+ cat_blob(oe, sha1);
+}
+
+static void checkpoint(void)
+{
+ checkpoint_requested = 0;
if (object_count) {
cycle_packfile();
dump_branches();
dump_tags();
dump_marks();
}
+}
+
+static void parse_checkpoint(void)
+{
+ checkpoint_requested = 1;
skip_optional_lf();
}
}
import_marks_file = make_fast_import_path(marks);
+ safe_create_leading_directories_const(import_marks_file);
import_marks_file_from_stream = from_stream;
}
die("unknown --date-format argument %s", fmt);
}
+static unsigned long ulong_arg(const char *option, const char *arg)
+{
+ char *endptr;
+ unsigned long rv = strtoul(arg, &endptr, 0);
+ if (strchr(arg, '-') || endptr == arg || *endptr)
+ die("%s: argument must be a non-negative integer", option);
+ return rv;
+}
+
static void option_depth(const char *depth)
{
- max_depth = strtoul(depth, NULL, 0);
+ max_depth = ulong_arg("--depth", depth);
if (max_depth > MAX_DEPTH)
die("--depth cannot exceed %u", MAX_DEPTH);
}
static void option_active_branches(const char *branches)
{
- max_active_branches = strtoul(branches, NULL, 0);
+ max_active_branches = ulong_arg("--active-branches", 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)
+{
+ unsigned long n = ulong_arg("--cat-blob-fd", fd);
+ if (n > (unsigned long) INT_MAX)
+ die("--cat-blob-fd cannot exceed %d", INT_MAX);
+ cat_blob_fd = (int) n;
}
static void option_export_pack_edges(const char *edges)
option_import_marks(feature + 13, from_stream);
} else if (!prefixcmp(feature, "export-marks=")) {
option_export_marks(feature + 13);
+ } else if (!strcmp(feature, "cat-blob")) {
+ ; /* Don't die - this feature is supported */
} else if (!prefixcmp(feature, "relative-marks")) {
relative_marks_paths = 1;
} else if (!prefixcmp(feature, "no-relative-marks")) {
relative_marks_paths = 0;
} else if (!prefixcmp(feature, "force")) {
force_update = 1;
+ } else if (!strcmp(feature, "notes")) {
+ ; /* do nothing; we have the feature */
} else {
return 0;
}
}
static const char fast_import_usage[] =
-"git fast-import [--date-format=f] [--max-pack-size=n] [--big-file-threshold=n] [--depth=n] [--active-branches=n] [--export-marks=marks.file]";
+"git fast-import [--date-format=<f>] [--max-pack-size=<n>] [--big-file-threshold=<n>] [--depth=<n>] [--active-branches=<n>] [--export-marks=<marks.file>]";
static void parse_argv(void)
{
if (parse_one_feature(a + 2, 0))
continue;
+ if (!prefixcmp(a + 2, "cat-blob-fd=")) {
+ option_cat_blob_fd(a + 2 + strlen("cat-blob-fd="));
+ continue;
+ }
+
die("unknown option %s", a);
}
if (i != global_argc)
prepare_packed_git();
start_packfile();
set_die_routine(die_nicely);
+ set_checkpoint_signal();
while (read_next_command() != EOF) {
if (!strcmp("blob", command_buf.buf))
parse_new_blob();
/* ignore non-git options*/;
else
die("Unsupported command: %s", command_buf.buf);
+
+ if (checkpoint_requested)
+ checkpoint();
}
/* argv hasn't been parsed yet, do so */