2005-04-08 00:16:10 +02:00
|
|
|
/*
|
|
|
|
* GIT - The information manager from hell
|
|
|
|
*
|
|
|
|
* Copyright (C) Linus Torvalds, 2005
|
|
|
|
*/
|
2005-04-08 00:13:13 +02:00
|
|
|
#include "cache.h"
|
2006-03-02 01:43:19 +01:00
|
|
|
#include "exec_cmd.h"
|
2006-04-02 14:44:09 +02:00
|
|
|
#include "tag.h"
|
|
|
|
#include "tree.h"
|
2006-05-24 13:08:46 +02:00
|
|
|
#include "builtin.h"
|
2008-05-23 16:19:42 +02:00
|
|
|
#include "parse-options.h"
|
2010-06-15 17:50:28 +02:00
|
|
|
#include "diff.h"
|
|
|
|
#include "userdiff.h"
|
2012-03-07 11:54:17 +01:00
|
|
|
#include "streaming.h"
|
2008-05-23 16:19:42 +02:00
|
|
|
|
2008-04-23 21:17:44 +02:00
|
|
|
static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
|
2005-04-08 00:13:13 +02:00
|
|
|
{
|
|
|
|
unsigned char sha1[20];
|
2007-02-26 20:55:59 +01:00
|
|
|
enum object_type type;
|
2010-06-15 17:50:28 +02:00
|
|
|
char *buf;
|
2005-04-08 00:13:13 +02:00
|
|
|
unsigned long size;
|
2010-06-15 17:50:28 +02:00
|
|
|
struct object_context obj_context;
|
2007-04-22 03:14:39 +02:00
|
|
|
|
2012-07-02 19:32:11 +02:00
|
|
|
if (get_sha1_with_context(obj_name, 0, sha1, &obj_context))
|
2007-04-22 03:14:39 +02:00
|
|
|
die("Not a valid object name %s", obj_name);
|
2005-12-04 02:57:48 +01:00
|
|
|
|
|
|
|
buf = NULL;
|
|
|
|
switch (opt) {
|
|
|
|
case 't':
|
2007-02-26 20:55:59 +01:00
|
|
|
type = sha1_object_info(sha1, NULL);
|
|
|
|
if (type > 0) {
|
|
|
|
printf("%s\n", typename(type));
|
2005-06-28 08:58:45 +02:00
|
|
|
return 0;
|
2005-05-02 04:28:18 +02:00
|
|
|
}
|
2005-12-04 02:57:48 +01:00
|
|
|
break;
|
|
|
|
|
|
|
|
case 's':
|
2007-02-26 20:55:59 +01:00
|
|
|
type = sha1_object_info(sha1, &size);
|
|
|
|
if (type > 0) {
|
2005-12-04 02:57:48 +01:00
|
|
|
printf("%lu\n", size);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
|
|
|
|
case 'e':
|
|
|
|
return !has_sha1_file(sha1);
|
|
|
|
|
2013-05-10 17:10:13 +02:00
|
|
|
case 'c':
|
|
|
|
if (!obj_context.path[0])
|
|
|
|
die("git cat-file --textconv %s: <object> must be <sha1:path>",
|
|
|
|
obj_name);
|
|
|
|
|
|
|
|
if (textconv_object(obj_context.path, obj_context.mode, sha1, 1, &buf, &size))
|
|
|
|
break;
|
|
|
|
|
2006-03-02 01:43:19 +01:00
|
|
|
case 'p':
|
2007-02-26 20:55:59 +01:00
|
|
|
type = sha1_object_info(sha1, NULL);
|
|
|
|
if (type < 0)
|
2007-04-22 03:14:39 +02:00
|
|
|
die("Not a valid object name %s", obj_name);
|
2006-03-02 01:43:19 +01:00
|
|
|
|
|
|
|
/* custom pretty-print here */
|
2007-04-22 03:14:39 +02:00
|
|
|
if (type == OBJ_TREE) {
|
2010-05-14 11:31:33 +02:00
|
|
|
const char *ls_args[3] = { NULL };
|
|
|
|
ls_args[0] = "ls-tree";
|
|
|
|
ls_args[1] = obj_name;
|
2007-04-22 03:14:39 +02:00
|
|
|
return cmd_ls_tree(2, ls_args, NULL);
|
|
|
|
}
|
2006-03-02 01:43:19 +01:00
|
|
|
|
2012-03-07 11:54:17 +01:00
|
|
|
if (type == OBJ_BLOB)
|
|
|
|
return stream_blob_to_fd(1, sha1, NULL, 0);
|
2007-02-26 20:55:59 +01:00
|
|
|
buf = read_sha1_file(sha1, &type, &size);
|
2006-03-02 01:43:19 +01:00
|
|
|
if (!buf)
|
2007-04-22 03:14:39 +02:00
|
|
|
die("Cannot read object %s", obj_name);
|
2006-03-02 01:43:19 +01:00
|
|
|
|
|
|
|
/* otherwise just spit out the data */
|
|
|
|
break;
|
2010-06-15 17:50:28 +02:00
|
|
|
|
2005-12-04 02:57:48 +01:00
|
|
|
case 0:
|
2012-03-07 11:54:17 +01:00
|
|
|
if (type_from_string(exp_type) == OBJ_BLOB) {
|
|
|
|
unsigned char blob_sha1[20];
|
|
|
|
if (sha1_object_info(sha1, NULL) == OBJ_TAG) {
|
|
|
|
enum object_type type;
|
|
|
|
unsigned long size;
|
|
|
|
char *buffer = read_sha1_file(sha1, &type, &size);
|
|
|
|
if (memcmp(buffer, "object ", 7) ||
|
|
|
|
get_sha1_hex(buffer + 7, blob_sha1))
|
|
|
|
die("%s not a valid tag", sha1_to_hex(sha1));
|
|
|
|
free(buffer);
|
|
|
|
} else
|
|
|
|
hashcpy(blob_sha1, sha1);
|
|
|
|
|
|
|
|
if (sha1_object_info(blob_sha1, NULL) == OBJ_BLOB)
|
|
|
|
return stream_blob_to_fd(1, blob_sha1, NULL, 0);
|
|
|
|
/*
|
|
|
|
* we attempted to dereference a tag to a blob
|
|
|
|
* and failed; there may be new dereference
|
|
|
|
* mechanisms this code is not aware of.
|
|
|
|
* fall-back to the usual case.
|
|
|
|
*/
|
|
|
|
}
|
2007-04-22 03:14:39 +02:00
|
|
|
buf = read_object_with_reference(sha1, exp_type, &size, NULL);
|
2005-12-04 02:57:48 +01:00
|
|
|
break;
|
|
|
|
|
|
|
|
default:
|
2009-01-04 19:38:41 +01:00
|
|
|
die("git cat-file: unknown option: %s", exp_type);
|
2005-04-08 18:16:38 +02:00
|
|
|
}
|
|
|
|
|
2005-05-02 04:28:18 +02:00
|
|
|
if (!buf)
|
2008-08-30 13:12:53 +02:00
|
|
|
die("git cat-file %s: bad file", obj_name);
|
2005-05-02 04:28:18 +02:00
|
|
|
|
2006-08-21 20:43:43 +02:00
|
|
|
write_or_die(1, buf, size);
|
2005-04-08 18:16:38 +02:00
|
|
|
return 0;
|
2005-04-08 00:13:13 +02:00
|
|
|
}
|
2008-04-23 21:17:44 +02:00
|
|
|
|
2013-07-10 13:45:47 +02:00
|
|
|
struct expand_data {
|
|
|
|
unsigned char sha1[20];
|
|
|
|
enum object_type type;
|
|
|
|
unsigned long size;
|
2013-07-10 13:46:25 +02:00
|
|
|
unsigned long disk_size;
|
cat-file: only split on whitespace when %(rest) is used
Commit c334b87b (cat-file: split --batch input lines on whitespace,
2013-07-11) taught `cat-file --batch-check` to split input lines on
the first whitespace, and stash everything after the first token
into the %(rest) output format element. It claimed:
Object names cannot contain spaces, so any input with
spaces would have resulted in a "missing" line.
But that is not correct. Refs, object sha1s, and various peeling
suffixes cannot contain spaces, but some object names can. In
particular:
1. Tree paths like "[<tree>]:path with whitespace"
2. Reflog specifications like "@{2 days ago}"
3. Commit searches like "rev^{/grep me}" or ":/grep me"
To remain backwards compatible, we cannot split on whitespace by
default, hence we will ship 1.8.4 with the commit reverted.
Resurrect its attempt but in a weaker form; only do the splitting
when "%(rest)" is used in the output format. Since that element did
not exist at all before c334b87, old scripts cannot be affected.
The existence of object names with spaces does mean that you
cannot reliably do:
echo ":path with space and other data" |
git cat-file --batch-check="%(objectname) %(rest)"
as it would split the path and feed only ":path" to get_sha1. But
that command is nonsensical. If you wanted to see "and other data"
in "%(rest)", git cannot possibly know where the filename ends and
the "rest" begins.
It might be more robust to have something like "-z" to separate the
input elements. But this patch is still a reasonable step before
having that. It makes the easy cases easy; people who do not care
about %(rest) do not have to consider it, and the %(rest) code
handles the spaces and newlines of "rev-list --objects" correctly.
Hard cases remain hard but possible (if you might get whitespace in
your input, you do not get to use %(rest) and must split and join
the output yourself using more flexible tools). And most
importantly, it does not preclude us from having different splitting
rules later if a "-z" (or similar) option is added. So we can make
the hard cases easier later, if we choose to.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-08-02 13:59:07 +02:00
|
|
|
const char *rest;
|
2013-12-21 15:25:22 +01:00
|
|
|
unsigned char delta_base_sha1[20];
|
2013-07-10 13:45:47 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* If mark_query is true, we do not expand anything, but rather
|
|
|
|
* just mark the object_info with items we wish to query.
|
|
|
|
*/
|
|
|
|
int mark_query;
|
|
|
|
|
cat-file: only split on whitespace when %(rest) is used
Commit c334b87b (cat-file: split --batch input lines on whitespace,
2013-07-11) taught `cat-file --batch-check` to split input lines on
the first whitespace, and stash everything after the first token
into the %(rest) output format element. It claimed:
Object names cannot contain spaces, so any input with
spaces would have resulted in a "missing" line.
But that is not correct. Refs, object sha1s, and various peeling
suffixes cannot contain spaces, but some object names can. In
particular:
1. Tree paths like "[<tree>]:path with whitespace"
2. Reflog specifications like "@{2 days ago}"
3. Commit searches like "rev^{/grep me}" or ":/grep me"
To remain backwards compatible, we cannot split on whitespace by
default, hence we will ship 1.8.4 with the commit reverted.
Resurrect its attempt but in a weaker form; only do the splitting
when "%(rest)" is used in the output format. Since that element did
not exist at all before c334b87, old scripts cannot be affected.
The existence of object names with spaces does mean that you
cannot reliably do:
echo ":path with space and other data" |
git cat-file --batch-check="%(objectname) %(rest)"
as it would split the path and feed only ":path" to get_sha1. But
that command is nonsensical. If you wanted to see "and other data"
in "%(rest)", git cannot possibly know where the filename ends and
the "rest" begins.
It might be more robust to have something like "-z" to separate the
input elements. But this patch is still a reasonable step before
having that. It makes the easy cases easy; people who do not care
about %(rest) do not have to consider it, and the %(rest) code
handles the spaces and newlines of "rev-list --objects" correctly.
Hard cases remain hard but possible (if you might get whitespace in
your input, you do not get to use %(rest) and must split and join
the output yourself using more flexible tools). And most
importantly, it does not preclude us from having different splitting
rules later if a "-z" (or similar) option is added. So we can make
the hard cases easier later, if we choose to.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-08-02 13:59:07 +02:00
|
|
|
/*
|
|
|
|
* Whether to split the input on whitespace before feeding it to
|
|
|
|
* get_sha1; this is decided during the mark_query phase based on
|
|
|
|
* whether we have a %(rest) token in our format.
|
|
|
|
*/
|
|
|
|
int split_on_whitespace;
|
|
|
|
|
2013-07-10 13:45:47 +02:00
|
|
|
/*
|
|
|
|
* After a mark_query run, this object_info is set up to be
|
|
|
|
* passed to sha1_object_info_extended. It will point to the data
|
|
|
|
* elements above, so you can retrieve the response from there.
|
|
|
|
*/
|
|
|
|
struct object_info info;
|
|
|
|
};
|
|
|
|
|
|
|
|
static int is_atom(const char *atom, const char *s, int slen)
|
|
|
|
{
|
|
|
|
int alen = strlen(atom);
|
|
|
|
return alen == slen && !memcmp(atom, s, alen);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void expand_atom(struct strbuf *sb, const char *atom, int len,
|
|
|
|
void *vdata)
|
|
|
|
{
|
|
|
|
struct expand_data *data = vdata;
|
|
|
|
|
|
|
|
if (is_atom("objectname", atom, len)) {
|
|
|
|
if (!data->mark_query)
|
|
|
|
strbuf_addstr(sb, sha1_to_hex(data->sha1));
|
|
|
|
} else if (is_atom("objecttype", atom, len)) {
|
2013-07-12 08:34:57 +02:00
|
|
|
if (data->mark_query)
|
|
|
|
data->info.typep = &data->type;
|
|
|
|
else
|
2013-07-10 13:45:47 +02:00
|
|
|
strbuf_addstr(sb, typename(data->type));
|
|
|
|
} else if (is_atom("objectsize", atom, len)) {
|
|
|
|
if (data->mark_query)
|
|
|
|
data->info.sizep = &data->size;
|
|
|
|
else
|
|
|
|
strbuf_addf(sb, "%lu", data->size);
|
2013-07-10 13:46:25 +02:00
|
|
|
} else if (is_atom("objectsize:disk", atom, len)) {
|
|
|
|
if (data->mark_query)
|
|
|
|
data->info.disk_sizep = &data->disk_size;
|
|
|
|
else
|
|
|
|
strbuf_addf(sb, "%lu", data->disk_size);
|
cat-file: only split on whitespace when %(rest) is used
Commit c334b87b (cat-file: split --batch input lines on whitespace,
2013-07-11) taught `cat-file --batch-check` to split input lines on
the first whitespace, and stash everything after the first token
into the %(rest) output format element. It claimed:
Object names cannot contain spaces, so any input with
spaces would have resulted in a "missing" line.
But that is not correct. Refs, object sha1s, and various peeling
suffixes cannot contain spaces, but some object names can. In
particular:
1. Tree paths like "[<tree>]:path with whitespace"
2. Reflog specifications like "@{2 days ago}"
3. Commit searches like "rev^{/grep me}" or ":/grep me"
To remain backwards compatible, we cannot split on whitespace by
default, hence we will ship 1.8.4 with the commit reverted.
Resurrect its attempt but in a weaker form; only do the splitting
when "%(rest)" is used in the output format. Since that element did
not exist at all before c334b87, old scripts cannot be affected.
The existence of object names with spaces does mean that you
cannot reliably do:
echo ":path with space and other data" |
git cat-file --batch-check="%(objectname) %(rest)"
as it would split the path and feed only ":path" to get_sha1. But
that command is nonsensical. If you wanted to see "and other data"
in "%(rest)", git cannot possibly know where the filename ends and
the "rest" begins.
It might be more robust to have something like "-z" to separate the
input elements. But this patch is still a reasonable step before
having that. It makes the easy cases easy; people who do not care
about %(rest) do not have to consider it, and the %(rest) code
handles the spaces and newlines of "rev-list --objects" correctly.
Hard cases remain hard but possible (if you might get whitespace in
your input, you do not get to use %(rest) and must split and join
the output yourself using more flexible tools). And most
importantly, it does not preclude us from having different splitting
rules later if a "-z" (or similar) option is added. So we can make
the hard cases easier later, if we choose to.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-08-02 13:59:07 +02:00
|
|
|
} else if (is_atom("rest", atom, len)) {
|
|
|
|
if (data->mark_query)
|
|
|
|
data->split_on_whitespace = 1;
|
|
|
|
else if (data->rest)
|
|
|
|
strbuf_addstr(sb, data->rest);
|
2013-12-21 15:25:22 +01:00
|
|
|
} else if (is_atom("deltabase", atom, len)) {
|
|
|
|
if (data->mark_query)
|
|
|
|
data->info.delta_base_sha1 = data->delta_base_sha1;
|
|
|
|
else
|
|
|
|
strbuf_addstr(sb, sha1_to_hex(data->delta_base_sha1));
|
2013-07-10 13:45:47 +02:00
|
|
|
} else
|
|
|
|
die("unknown format element: %.*s", len, atom);
|
|
|
|
}
|
|
|
|
|
|
|
|
static size_t expand_format(struct strbuf *sb, const char *start, void *data)
|
|
|
|
{
|
|
|
|
const char *end;
|
|
|
|
|
|
|
|
if (*start != '(')
|
|
|
|
return 0;
|
|
|
|
end = strchr(start + 1, ')');
|
|
|
|
if (!end)
|
|
|
|
die("format element '%s' does not end in ')'", start);
|
|
|
|
|
|
|
|
expand_atom(sb, start + 1, end - start - 1, data);
|
|
|
|
|
|
|
|
return end - start + 1;
|
|
|
|
}
|
|
|
|
|
2013-12-12 00:01:42 +01:00
|
|
|
static void print_object_or_die(int fd, struct expand_data *data)
|
2013-07-10 13:38:24 +02:00
|
|
|
{
|
2013-12-12 00:01:42 +01:00
|
|
|
const unsigned char *sha1 = data->sha1;
|
|
|
|
|
cat-file: handle --batch format with missing type/size
Commit 98e2092 taught cat-file to stream blobs with --batch,
which requires that we look up the object type before
loading it into memory. As a result, we now print the
object header from information in sha1_object_info, and the
actual contents from the read_sha1_file. We double-check
that the information we printed in the header matches the
content we are about to show.
Later, commit 93d2a60 allowed custom header lines for
--batch, and commit 5b08640 made type lookups optional. As a
result, specifying a header line without the type or size
means that we will not look up those items at all.
This causes our double-checking to erroneously die with an
error; we think the type or size has changed, when in fact
it was simply left at "0".
For the size, we can fix this by only doing the consistency
double-check when we have retrieved the size via
sha1_object_info. In the case that we have not retrieved the
value, that means we also did not print it, so there is
nothing for us to check that we are consistent with.
We could do the same for the type. However, besides our
consistency check, we also care about the type in deciding
whether to stream or not. So instead of handling the case
where we do not know the type, this patch instead makes sure
that we always trigger a type lookup when we are printing,
so that even a format without the type will stream as we
would in the normal case.
Reviewed-by: Jonathan Nieder <jrnieder@gmail.com>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-12 00:15:50 +01:00
|
|
|
assert(data->info.typep);
|
|
|
|
|
2013-12-12 00:01:42 +01:00
|
|
|
if (data->type == OBJ_BLOB) {
|
2013-07-10 13:38:24 +02:00
|
|
|
if (stream_blob_to_fd(fd, sha1, NULL, 0) < 0)
|
|
|
|
die("unable to stream %s to stdout", sha1_to_hex(sha1));
|
|
|
|
}
|
|
|
|
else {
|
2013-12-12 00:01:42 +01:00
|
|
|
enum object_type type;
|
|
|
|
unsigned long size;
|
2013-07-10 13:38:24 +02:00
|
|
|
void *contents;
|
|
|
|
|
2013-12-12 00:01:42 +01:00
|
|
|
contents = read_sha1_file(sha1, &type, &size);
|
2013-07-10 13:38:24 +02:00
|
|
|
if (!contents)
|
|
|
|
die("object %s disappeared", sha1_to_hex(sha1));
|
2013-12-12 00:01:42 +01:00
|
|
|
if (type != data->type)
|
2013-07-10 13:38:24 +02:00
|
|
|
die("object %s changed type!?", sha1_to_hex(sha1));
|
cat-file: handle --batch format with missing type/size
Commit 98e2092 taught cat-file to stream blobs with --batch,
which requires that we look up the object type before
loading it into memory. As a result, we now print the
object header from information in sha1_object_info, and the
actual contents from the read_sha1_file. We double-check
that the information we printed in the header matches the
content we are about to show.
Later, commit 93d2a60 allowed custom header lines for
--batch, and commit 5b08640 made type lookups optional. As a
result, specifying a header line without the type or size
means that we will not look up those items at all.
This causes our double-checking to erroneously die with an
error; we think the type or size has changed, when in fact
it was simply left at "0".
For the size, we can fix this by only doing the consistency
double-check when we have retrieved the size via
sha1_object_info. In the case that we have not retrieved the
value, that means we also did not print it, so there is
nothing for us to check that we are consistent with.
We could do the same for the type. However, besides our
consistency check, we also care about the type in deciding
whether to stream or not. So instead of handling the case
where we do not know the type, this patch instead makes sure
that we always trigger a type lookup when we are printing,
so that even a format without the type will stream as we
would in the normal case.
Reviewed-by: Jonathan Nieder <jrnieder@gmail.com>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-12 00:15:50 +01:00
|
|
|
if (data->info.sizep && size != data->size)
|
2013-12-12 00:01:42 +01:00
|
|
|
die("object %s changed size!?", sha1_to_hex(sha1));
|
2013-07-10 13:38:24 +02:00
|
|
|
|
|
|
|
write_or_die(fd, contents, size);
|
|
|
|
free(contents);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2013-07-10 13:38:58 +02:00
|
|
|
struct batch_options {
|
|
|
|
int enabled;
|
|
|
|
int print_contents;
|
2013-07-10 13:45:47 +02:00
|
|
|
const char *format;
|
2013-07-10 13:38:58 +02:00
|
|
|
};
|
|
|
|
|
2013-07-10 13:45:47 +02:00
|
|
|
static int batch_one_object(const char *obj_name, struct batch_options *opt,
|
|
|
|
struct expand_data *data)
|
2008-04-23 21:17:46 +02:00
|
|
|
{
|
2013-07-10 13:45:47 +02:00
|
|
|
struct strbuf buf = STRBUF_INIT;
|
2008-04-23 21:17:46 +02:00
|
|
|
|
|
|
|
if (!obj_name)
|
|
|
|
return 1;
|
|
|
|
|
2013-07-10 13:45:47 +02:00
|
|
|
if (get_sha1(obj_name, data->sha1)) {
|
2008-04-23 21:17:46 +02:00
|
|
|
printf("%s missing\n", obj_name);
|
2008-06-03 20:34:17 +02:00
|
|
|
fflush(stdout);
|
2008-04-23 21:17:46 +02:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2013-12-11 08:46:07 +01:00
|
|
|
if (sha1_object_info_extended(data->sha1, &data->info, LOOKUP_REPLACE_OBJECT) < 0) {
|
2008-06-09 02:02:21 +02:00
|
|
|
printf("%s missing\n", obj_name);
|
|
|
|
fflush(stdout);
|
|
|
|
return 0;
|
|
|
|
}
|
2008-04-23 21:17:46 +02:00
|
|
|
|
2013-07-10 13:45:47 +02:00
|
|
|
strbuf_expand(&buf, opt->format, expand_format, data);
|
|
|
|
strbuf_addch(&buf, '\n');
|
|
|
|
write_or_die(1, buf.buf, buf.len);
|
|
|
|
strbuf_release(&buf);
|
2008-04-23 21:17:47 +02:00
|
|
|
|
2013-07-10 13:38:58 +02:00
|
|
|
if (opt->print_contents) {
|
2013-12-12 00:01:42 +01:00
|
|
|
print_object_or_die(1, data);
|
2013-07-10 13:38:24 +02:00
|
|
|
write_or_die(1, "\n", 1);
|
2008-04-23 21:17:47 +02:00
|
|
|
}
|
2008-04-23 21:17:46 +02:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2013-07-10 13:38:58 +02:00
|
|
|
static int batch_objects(struct batch_options *opt)
|
2008-04-23 21:17:46 +02:00
|
|
|
{
|
2008-10-09 21:12:12 +02:00
|
|
|
struct strbuf buf = STRBUF_INIT;
|
2013-07-10 13:45:47 +02:00
|
|
|
struct expand_data data;
|
|
|
|
|
|
|
|
if (!opt->format)
|
|
|
|
opt->format = "%(objectname) %(objecttype) %(objectsize)";
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Expand once with our special mark_query flag, which will prime the
|
|
|
|
* object_info to be handed to sha1_object_info_extended for each
|
|
|
|
* object.
|
|
|
|
*/
|
|
|
|
memset(&data, 0, sizeof(data));
|
|
|
|
data.mark_query = 1;
|
|
|
|
strbuf_expand(&buf, opt->format, expand_format, &data);
|
|
|
|
data.mark_query = 0;
|
2008-04-23 21:17:46 +02:00
|
|
|
|
cat-file: handle --batch format with missing type/size
Commit 98e2092 taught cat-file to stream blobs with --batch,
which requires that we look up the object type before
loading it into memory. As a result, we now print the
object header from information in sha1_object_info, and the
actual contents from the read_sha1_file. We double-check
that the information we printed in the header matches the
content we are about to show.
Later, commit 93d2a60 allowed custom header lines for
--batch, and commit 5b08640 made type lookups optional. As a
result, specifying a header line without the type or size
means that we will not look up those items at all.
This causes our double-checking to erroneously die with an
error; we think the type or size has changed, when in fact
it was simply left at "0".
For the size, we can fix this by only doing the consistency
double-check when we have retrieved the size via
sha1_object_info. In the case that we have not retrieved the
value, that means we also did not print it, so there is
nothing for us to check that we are consistent with.
We could do the same for the type. However, besides our
consistency check, we also care about the type in deciding
whether to stream or not. So instead of handling the case
where we do not know the type, this patch instead makes sure
that we always trigger a type lookup when we are printing,
so that even a format without the type will stream as we
would in the normal case.
Reviewed-by: Jonathan Nieder <jrnieder@gmail.com>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-12 00:15:50 +01:00
|
|
|
/*
|
|
|
|
* If we are printing out the object, then always fill in the type,
|
|
|
|
* since we will want to decide whether or not to stream.
|
|
|
|
*/
|
|
|
|
if (opt->print_contents)
|
|
|
|
data.info.typep = &data.type;
|
|
|
|
|
cat-file: disable object/refname ambiguity check for batch mode
A common use of "cat-file --batch-check" is to feed a list
of objects from "rev-list --objects" or a similar command.
In this instance, all of our input objects are 40-byte sha1
ids. However, cat-file has always allowed arbitrary revision
specifiers, and feeds the result to get_sha1().
Fortunately, get_sha1() recognizes a 40-byte sha1 before
doing any hard work trying to look up refs, meaning this
scenario should end up spending very little time converting
the input into an object sha1. However, since 798c35f
(get_sha1: warn about full or short object names that look
like refs, 2013-05-29), when we encounter this case, we
spend the extra effort to do a refname lookup anyway, just
to print a warning. This is further exacerbated by ca91993
(get_packed_ref_cache: reload packed-refs file when it
changes, 2013-06-20), which makes individual ref lookup more
expensive by requiring a stat() of the packed-refs file for
each missing ref.
With no patches, this is the time it takes to run:
$ git rev-list --objects --all >objects
$ time git cat-file --batch-check='%(objectname)' <objects
on the linux.git repository:
real 1m13.494s
user 0m25.924s
sys 0m47.532s
If we revert ca91993, the packed-refs up-to-date check, it
gets a little better:
real 0m54.697s
user 0m21.692s
sys 0m32.916s
but we are still spending quite a bit of time on ref lookup
(and we would not want to revert that patch, anyway, which
has correctness issues). If we revert 798c35f, disabling
the warning entirely, we get a much more reasonable time:
real 0m7.452s
user 0m6.836s
sys 0m0.608s
This patch does the moral equivalent of this final case (and
gets similar speedups). We introduce a global flag that
callers of get_sha1() can use to avoid paying the price for
the warning.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-12 08:20:05 +02:00
|
|
|
/*
|
|
|
|
* We are going to call get_sha1 on a potentially very large number of
|
|
|
|
* objects. In most large cases, these will be actual object sha1s. The
|
|
|
|
* cost to double-check that each one is not also a ref (just so we can
|
|
|
|
* warn) ends up dwarfing the actual cost of the object lookups
|
|
|
|
* themselves. We can work around it by just turning off the warning.
|
|
|
|
*/
|
|
|
|
warn_on_object_refname_ambiguity = 0;
|
|
|
|
|
2008-04-23 21:17:46 +02:00
|
|
|
while (strbuf_getline(&buf, stdin, '\n') != EOF) {
|
cat-file: only split on whitespace when %(rest) is used
Commit c334b87b (cat-file: split --batch input lines on whitespace,
2013-07-11) taught `cat-file --batch-check` to split input lines on
the first whitespace, and stash everything after the first token
into the %(rest) output format element. It claimed:
Object names cannot contain spaces, so any input with
spaces would have resulted in a "missing" line.
But that is not correct. Refs, object sha1s, and various peeling
suffixes cannot contain spaces, but some object names can. In
particular:
1. Tree paths like "[<tree>]:path with whitespace"
2. Reflog specifications like "@{2 days ago}"
3. Commit searches like "rev^{/grep me}" or ":/grep me"
To remain backwards compatible, we cannot split on whitespace by
default, hence we will ship 1.8.4 with the commit reverted.
Resurrect its attempt but in a weaker form; only do the splitting
when "%(rest)" is used in the output format. Since that element did
not exist at all before c334b87, old scripts cannot be affected.
The existence of object names with spaces does mean that you
cannot reliably do:
echo ":path with space and other data" |
git cat-file --batch-check="%(objectname) %(rest)"
as it would split the path and feed only ":path" to get_sha1. But
that command is nonsensical. If you wanted to see "and other data"
in "%(rest)", git cannot possibly know where the filename ends and
the "rest" begins.
It might be more robust to have something like "-z" to separate the
input elements. But this patch is still a reasonable step before
having that. It makes the easy cases easy; people who do not care
about %(rest) do not have to consider it, and the %(rest) code
handles the spaces and newlines of "rev-list --objects" correctly.
Hard cases remain hard but possible (if you might get whitespace in
your input, you do not get to use %(rest) and must split and join
the output yourself using more flexible tools). And most
importantly, it does not preclude us from having different splitting
rules later if a "-z" (or similar) option is added. So we can make
the hard cases easier later, if we choose to.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-08-02 13:59:07 +02:00
|
|
|
int error;
|
|
|
|
|
|
|
|
if (data.split_on_whitespace) {
|
|
|
|
/*
|
|
|
|
* Split at first whitespace, tying off the beginning
|
|
|
|
* of the string and saving the remainder (or NULL) in
|
|
|
|
* data.rest.
|
|
|
|
*/
|
|
|
|
char *p = strpbrk(buf.buf, " \t");
|
|
|
|
if (p) {
|
|
|
|
while (*p && strchr(" \t", *p))
|
|
|
|
*p++ = '\0';
|
|
|
|
}
|
|
|
|
data.rest = p;
|
|
|
|
}
|
|
|
|
|
|
|
|
error = batch_one_object(buf.buf, opt, &data);
|
2008-04-23 21:17:46 +02:00
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2008-05-23 16:19:42 +02:00
|
|
|
static const char * const cat_file_usage[] = {
|
2012-08-20 14:31:56 +02:00
|
|
|
N_("git cat-file (-t|-s|-e|-p|<type>|--textconv) <object>"),
|
|
|
|
N_("git cat-file (--batch|--batch-check) < <list_of_objects>"),
|
2008-05-23 16:19:42 +02:00
|
|
|
NULL
|
|
|
|
};
|
2008-04-23 21:17:45 +02:00
|
|
|
|
2010-06-15 17:50:28 +02:00
|
|
|
static int git_cat_file_config(const char *var, const char *value, void *cb)
|
|
|
|
{
|
drop odd return value semantics from userdiff_config
When the userdiff_config function was introduced in be58e70
(diff: unify external diff and funcname parsing code,
2008-10-05), it used a return value convention unlike any
other config callback. Like other callbacks, it used "-1" to
signal error. But it returned "1" to indicate that it found
something, and "0" otherwise; other callbacks simply
returned "0" to indicate that no error occurred.
This distinction was necessary at the time, because the
userdiff namespace overlapped slightly with the color
configuration namespace. So "diff.color.foo" could mean "the
'foo' slot of diff coloring" or "the 'foo' component of the
"color" userdiff driver". Because the color-parsing code
would die on an unknown color slot, we needed the userdiff
code to indicate that it had matched the variable, letting
us bypass the color-parsing code entirely.
Later, in 8b8e862 (ignore unknown color configuration,
2009-12-12), the color-parsing code learned to silently
ignore unknown slots. This means we no longer need to
protect userdiff-matched variables from reaching the
color-parsing code.
We can therefore change the userdiff_config calling
convention to a more normal one. This drops some code from
each caller, which is nice. But more importantly, it reduces
the cognitive load for readers who may wonder why
userdiff_config is unlike every other config callback.
There's no need to add a new test confirming that this
works; t4020 already contains a test that sets
diff.color.external.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-07 19:23:02 +01:00
|
|
|
if (userdiff_config(var, value) < 0)
|
2010-06-15 17:50:28 +02:00
|
|
|
return -1;
|
|
|
|
|
|
|
|
return git_default_config(var, value, cb);
|
|
|
|
}
|
|
|
|
|
2013-07-10 13:38:58 +02:00
|
|
|
static int batch_option_callback(const struct option *opt,
|
|
|
|
const char *arg,
|
|
|
|
int unset)
|
|
|
|
{
|
|
|
|
struct batch_options *bo = opt->value;
|
|
|
|
|
|
|
|
if (unset) {
|
|
|
|
memset(bo, 0, sizeof(*bo));
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
bo->enabled = 1;
|
|
|
|
bo->print_contents = !strcmp(opt->long_name, "batch");
|
2013-07-10 13:45:47 +02:00
|
|
|
bo->format = arg;
|
2013-07-10 13:38:58 +02:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2008-04-23 21:17:44 +02:00
|
|
|
int cmd_cat_file(int argc, const char **argv, const char *prefix)
|
|
|
|
{
|
2013-07-10 13:38:58 +02:00
|
|
|
int opt = 0;
|
2008-04-23 21:17:45 +02:00
|
|
|
const char *exp_type = NULL, *obj_name = NULL;
|
2013-07-10 13:38:58 +02:00
|
|
|
struct batch_options batch = {0};
|
2008-04-23 21:17:44 +02:00
|
|
|
|
2008-05-23 16:19:42 +02:00
|
|
|
const struct option options[] = {
|
2012-08-20 14:31:56 +02:00
|
|
|
OPT_GROUP(N_("<type> can be one of: blob, tree, commit, tag")),
|
|
|
|
OPT_SET_INT('t', NULL, &opt, N_("show object type"), 't'),
|
|
|
|
OPT_SET_INT('s', NULL, &opt, N_("show object size"), 's'),
|
2008-05-23 16:19:42 +02:00
|
|
|
OPT_SET_INT('e', NULL, &opt,
|
2012-08-20 14:31:56 +02:00
|
|
|
N_("exit with zero when there's no error"), 'e'),
|
|
|
|
OPT_SET_INT('p', NULL, &opt, N_("pretty-print object's content"), 'p'),
|
2010-06-15 17:50:28 +02:00
|
|
|
OPT_SET_INT(0, "textconv", &opt,
|
2012-08-20 14:31:56 +02:00
|
|
|
N_("for blob objects, run textconv on object's content"), 'c'),
|
2013-07-10 13:45:47 +02:00
|
|
|
{ OPTION_CALLBACK, 0, "batch", &batch, "format",
|
2013-07-10 13:38:58 +02:00
|
|
|
N_("show info and content of objects fed from the standard input"),
|
2013-07-10 13:45:47 +02:00
|
|
|
PARSE_OPT_OPTARG, batch_option_callback },
|
|
|
|
{ OPTION_CALLBACK, 0, "batch-check", &batch, "format",
|
2013-07-10 13:38:58 +02:00
|
|
|
N_("show info about objects fed from the standard input"),
|
2013-07-10 13:45:47 +02:00
|
|
|
PARSE_OPT_OPTARG, batch_option_callback },
|
2008-05-23 16:19:42 +02:00
|
|
|
OPT_END()
|
|
|
|
};
|
2008-04-23 21:17:47 +02:00
|
|
|
|
2010-06-15 17:50:28 +02:00
|
|
|
git_config(git_cat_file_config, NULL);
|
2008-04-23 21:17:45 +02:00
|
|
|
|
2008-05-23 16:19:42 +02:00
|
|
|
if (argc != 3 && argc != 2)
|
|
|
|
usage_with_options(cat_file_usage, options);
|
2008-04-23 21:17:45 +02:00
|
|
|
|
2009-05-23 20:53:12 +02:00
|
|
|
argc = parse_options(argc, argv, prefix, options, cat_file_usage, 0);
|
2008-04-23 21:17:46 +02:00
|
|
|
|
2008-05-23 16:19:42 +02:00
|
|
|
if (opt) {
|
|
|
|
if (argc == 1)
|
|
|
|
obj_name = argv[0];
|
|
|
|
else
|
|
|
|
usage_with_options(cat_file_usage, options);
|
|
|
|
}
|
2013-07-10 13:38:58 +02:00
|
|
|
if (!opt && !batch.enabled) {
|
2008-05-23 16:19:42 +02:00
|
|
|
if (argc == 2) {
|
|
|
|
exp_type = argv[0];
|
|
|
|
obj_name = argv[1];
|
|
|
|
} else
|
|
|
|
usage_with_options(cat_file_usage, options);
|
|
|
|
}
|
2013-07-10 13:38:58 +02:00
|
|
|
if (batch.enabled && (opt || argc)) {
|
2008-05-23 16:19:42 +02:00
|
|
|
usage_with_options(cat_file_usage, options);
|
2008-04-23 21:17:44 +02:00
|
|
|
}
|
|
|
|
|
2013-07-10 13:38:58 +02:00
|
|
|
if (batch.enabled)
|
|
|
|
return batch_objects(&batch);
|
2008-04-23 21:17:46 +02:00
|
|
|
|
2008-04-23 21:17:44 +02:00
|
|
|
return cat_one_file(opt, exp_type, obj_name);
|
|
|
|
}
|