Merge branch 'jn/fast-import-blob-access'

* jn/fast-import-blob-access:
  t9300: avoid short reads from dd
  t9300: remove unnecessary use of /dev/stdin
  fast-import: Allow cat-blob requests at arbitrary points in stream
  fast-import: let importers retrieve blobs
  fast-import: clarify documentation of "feature" command
  fast-import: stricter parsing of integer options

Conflicts:
	fast-import.c
This commit is contained in:
Junio C Hamano 2010-12-16 12:58:38 -08:00
commit 914584266c
3 changed files with 444 additions and 28 deletions

View file

@ -92,6 +92,11 @@ OPTIONS
--(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
@ -320,6 +325,11 @@ and control the current import process. More detailed discussion
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.
@ -879,34 +889,65 @@ Placing a `progress` command immediately after a `checkpoint` will
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
it does not.
....
'feature' SP <feature> LF
'feature' SP <feature> ('=' <argument>)? LF
....
The <feature> part of the command may be any string matching
^[a-zA-Z][a-zA-Z-]*$ and should be understood by fast-import.
The <feature> part of the command may be any one of the following:
Feature work identical as their option counterparts with the
exception of the import-marks feature, see below.
date-format::
export-marks::
relative-marks::
no-relative-marks::
force::
Act as though the corresponding command-line option with
a leading '--' was passed on the command line
(see OPTIONS, above).
The following features are currently supported:
import-marks::
Like --import-marks except in two respects: first, only one
"feature import-marks" command is allowed per stream;
second, an --import-marks= command-line option overrides
any "feature import-marks" command in the stream.
* date-format
* import-marks
* export-marks
* relative-marks
* no-relative-marks
* force
The import-marks behaves differently from when it is specified as
commandline option in that only one "feature import-marks" is allowed
per stream. Also, any --import-marks= specified on the commandline
will override those from the stream (if any).
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.
`option`
~~~~~~~~
@ -933,6 +974,7 @@ not be passed as option:
* date-format
* import-marks
* export-marks
* cat-blob-fd
* force
Crash Reports

View file

@ -132,14 +132,17 @@ Format of STDIN stream:
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);
*/
@ -365,7 +368,11 @@ 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)
{
@ -1829,7 +1836,7 @@ static int read_next_command(void)
return EOF;
}
do {
for (;;) {
if (unread_command_buf) {
unread_command_buf = 0;
} else {
@ -1862,9 +1869,14 @@ static int read_next_command(void)
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)
@ -2739,6 +2751,81 @@ static void parse_reset_branch(void)
unread_command_buf = 1;
}
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;
@ -2802,16 +2889,25 @@ static void option_date_format(const char *fmt)
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)
@ -2820,6 +2916,14 @@ static void option_export_marks(const char *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)
{
if (pack_edges)
@ -2873,6 +2977,8 @@ static int parse_one_feature(const char *feature, int from_stream)
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")) {
@ -2967,6 +3073,11 @@ 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)

View file

@ -23,11 +23,18 @@ file5_data='an inline file.
file6_data='#!/bin/sh
echo "$@"'
>empty
###
### series A
###
test_tick
test_expect_success 'empty stream succeeds' '
git fast-import </dev/null
'
cat >input <<INPUT_END
blob
mark :2
@ -1740,6 +1747,256 @@ test_expect_success 'R: feature no-relative-marks should be honoured' '
test_cmp marks.new non-relative.out
'
test_expect_success 'R: feature cat-blob supported' '
echo "feature cat-blob" |
git fast-import
'
test_expect_success 'R: cat-blob-fd must be a nonnegative integer' '
test_must_fail git fast-import --cat-blob-fd=-1 </dev/null
'
test_expect_success 'R: print old blob' '
blob=$(echo "yes it can" | git hash-object -w --stdin) &&
cat >expect <<-EOF &&
${blob} blob 11
yes it can
EOF
echo "cat-blob $blob" |
git fast-import --cat-blob-fd=6 6>actual &&
test_cmp expect actual
'
test_expect_success 'R: in-stream cat-blob-fd not respected' '
echo hello >greeting &&
blob=$(git hash-object -w greeting) &&
cat >expect <<-EOF &&
${blob} blob 6
hello
EOF
git fast-import --cat-blob-fd=3 3>actual.3 >actual.1 <<-EOF &&
cat-blob $blob
EOF
test_cmp expect actual.3 &&
test_cmp empty actual.1 &&
git fast-import 3>actual.3 >actual.1 <<-EOF &&
option cat-blob-fd=3
cat-blob $blob
EOF
test_cmp empty actual.3 &&
test_cmp expect actual.1
'
test_expect_success 'R: print new blob' '
blob=$(echo "yep yep yep" | git hash-object --stdin) &&
cat >expect <<-EOF &&
${blob} blob 12
yep yep yep
EOF
git fast-import --cat-blob-fd=6 6>actual <<-\EOF &&
blob
mark :1
data <<BLOB_END
yep yep yep
BLOB_END
cat-blob :1
EOF
test_cmp expect actual
'
test_expect_success 'R: print new blob by sha1' '
blob=$(echo "a new blob named by sha1" | git hash-object --stdin) &&
cat >expect <<-EOF &&
${blob} blob 25
a new blob named by sha1
EOF
git fast-import --cat-blob-fd=6 6>actual <<-EOF &&
blob
data <<BLOB_END
a new blob named by sha1
BLOB_END
cat-blob $blob
EOF
test_cmp expect actual
'
test_expect_success 'setup: big file' '
(
echo "the quick brown fox jumps over the lazy dog" >big &&
for i in 1 2 3
do
cat big big big big >bigger &&
cat bigger bigger bigger bigger >big ||
exit
done
)
'
test_expect_success 'R: print two blobs to stdout' '
blob1=$(git hash-object big) &&
blob1_len=$(wc -c <big) &&
blob2=$(echo hello | git hash-object --stdin) &&
{
echo ${blob1} blob $blob1_len &&
cat big &&
cat <<-EOF
${blob2} blob 6
hello
EOF
} >expect &&
{
cat <<-\END_PART1 &&
blob
mark :1
data <<data_end
END_PART1
cat big &&
cat <<-\EOF
data_end
blob
mark :2
data <<data_end
hello
data_end
cat-blob :1
cat-blob :2
EOF
} |
git fast-import >actual &&
test_cmp expect actual
'
test_expect_success 'setup: have pipes?' '
rm -f frob &&
if mkfifo frob
then
test_set_prereq PIPE
fi
'
test_expect_success PIPE 'R: copy using cat-file' '
expect_id=$(git hash-object big) &&
expect_len=$(wc -c <big) &&
echo $expect_id blob $expect_len >expect.response &&
rm -f blobs &&
cat >frontend <<-\FRONTEND_END &&
#!/bin/sh
cat <<EOF &&
feature cat-blob
blob
mark :1
data <<BLOB
EOF
cat big
cat <<EOF
BLOB
cat-blob :1
EOF
read blob_id type size <&3 &&
echo "$blob_id $type $size" >response &&
dd of=blob bs=1 count=$size <&3 &&
read newline <&3 &&
cat <<EOF &&
commit refs/heads/copied
committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
data <<COMMIT
copy big file as file3
COMMIT
M 644 inline file3
data <<BLOB
EOF
cat blob &&
cat <<EOF
BLOB
EOF
FRONTEND_END
mkfifo blobs &&
(
export GIT_COMMITTER_NAME GIT_COMMITTER_EMAIL GIT_COMMITTER_DATE &&
sh frontend 3<blobs |
git fast-import --cat-blob-fd=3 3>blobs
) &&
git show copied:file3 >actual &&
test_cmp expect.response response &&
test_cmp big actual
'
test_expect_success PIPE 'R: print blob mid-commit' '
rm -f blobs &&
echo "A blob from _before_ the commit." >expect &&
mkfifo blobs &&
(
exec 3<blobs &&
cat <<-EOF &&
feature cat-blob
blob
mark :1
data <<BLOB
A blob from _before_ the commit.
BLOB
commit refs/heads/temporary
committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
data <<COMMIT
Empty commit
COMMIT
cat-blob :1
EOF
read blob_id type size <&3 &&
dd of=actual bs=1 count=$size <&3 &&
read newline <&3 &&
echo
) |
git fast-import --cat-blob-fd=3 3>blobs &&
test_cmp expect actual
'
test_expect_success PIPE 'R: print staged blob within commit' '
rm -f blobs &&
echo "A blob from _within_ the commit." >expect &&
mkfifo blobs &&
(
exec 3<blobs &&
cat <<-EOF &&
feature cat-blob
commit refs/heads/within
committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
data <<COMMIT
Empty commit
COMMIT
M 644 inline within
data <<BLOB
A blob from _within_ the commit.
BLOB
EOF
to_get=$(
echo "A blob from _within_ the commit." |
git hash-object --stdin
) &&
echo "cat-blob $to_get" &&
read blob_id type size <&3 &&
dd of=actual bs=1 count=$size <&3 &&
read newline <&3 &&
echo deleteall
) |
git fast-import --cat-blob-fd=3 3>blobs &&
test_cmp expect actual
'
cat >input << EOF
option git quiet
blob
@ -1748,8 +2005,6 @@ hi
EOF
touch empty
test_expect_success 'R: quiet option results in no stats being output' '
cat input | git fast-import 2> output &&
test_cmp empty output
@ -1767,6 +2022,14 @@ test_expect_success 'R: unknown commandline options are rejected' '\
test_must_fail git fast-import --non-existing-option < /dev/null
'
test_expect_success 'R: die on invalid option argument' '
echo "option git active-branches=-5" |
test_must_fail git fast-import &&
echo "option git depth=" |
test_must_fail git fast-import &&
test_must_fail git fast-import --depth="5 elephants" </dev/null
'
cat >input <<EOF
option non-existing-vcs non-existing-option
EOF