cat-file: add --batch-check=<format>

The `cat-file --batch-check` command can be used to quickly
get information about a large number of objects. However, it
provides a fixed set of information.

This patch adds an optional <format> option to --batch-check
to allow a caller to specify which items they are interested
in, and in which order to output them. This is not very
exciting for now, since we provide the same limited set that
you could already get. However, it opens the door to adding
new format items in the future without breaking backwards
compatibility (or forcing callers to pay the cost to
calculate uninteresting items).

Since the --batch option shares code with --batch-check, it
receives the same feature, though it is less likely to be of
interest there.

The format atom names are chosen to match their counterparts
in for-each-ref. Though we do not (yet) share any code with
for-each-ref's formatter, this keeps the interface as
consistent as possible, and may help later on if the
implementations are unified.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
This commit is contained in:
Jeff King 2013-07-10 07:45:47 -04:00 коммит произвёл Junio C Hamano
Родитель b71bd48017
Коммит 93d2a607ba
3 изменённых файлов: 142 добавлений и 26 удалений

Просмотреть файл

@ -58,12 +58,16 @@ OPTIONS
to apply the filter to the content recorded in the index at <path>.
--batch::
Print the SHA-1, type, size, and contents of each object provided on
stdin. May not be combined with any other options or arguments.
--batch=<format>::
Print object information and contents for each object provided
on stdin. May not be combined with any other options or arguments.
See the section `BATCH OUTPUT` below for details.
--batch-check::
Print the SHA-1, type, and size of each object provided on stdin. May not
be combined with any other options or arguments.
--batch-check=<format>::
Print object information for each object provided on stdin. May
not be combined with any other options or arguments. See the
section `BATCH OUTPUT` below for details.
OUTPUT
------
@ -78,23 +82,52 @@ If '-p' is specified, the contents of <object> are pretty-printed.
If <type> is specified, the raw (though uncompressed) contents of the <object>
will be returned.
If '--batch' is specified, output of the following form is printed for each
object specified on stdin:
BATCH OUTPUT
------------
If `--batch` or `--batch-check` is given, `cat-file` will read objects
from stdin, one per line, and print information about them.
Each line is considered as a whole object name, and is parsed as if
given to linkgit:git-rev-parse[1].
You can specify the information shown for each object by using a custom
`<format>`. The `<format>` is copied literally to stdout for each
object, with placeholders of the form `%(atom)` expanded, followed by a
newline. The available atoms are:
`objectname`::
The 40-hex object name of the object.
`objecttype`::
The type of of the object (the same as `cat-file -t` reports).
`objectsize`::
The size, in bytes, of the object (the same as `cat-file -s`
reports).
If no format is specified, the default format is `%(objectname)
%(objecttype) %(objectsize)`.
If `--batch` is specified, the object information is followed by the
object contents (consisting of `%(objectsize)` bytes), followed by a
newline.
For example, `--batch` without a custom format would produce:
------------
<sha1> SP <type> SP <size> LF
<contents> LF
------------
If '--batch-check' is specified, output of the following form is printed for
each object specified on stdin:
Whereas `--batch-check='%(objectname) %(objecttype)'` would produce:
------------
<sha1> SP <type> SP <size> LF
<sha1> SP <type> LF
------------
For both '--batch' and '--batch-check', output of the following form is printed
for each object specified on stdin that does not exist in the repository:
If a name is specified on stdin that cannot be resolved to an object in
the repository, then `cat-file` will ignore any custom format and print:
------------
<object> SP missing LF

Просмотреть файл

@ -114,6 +114,66 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
return 0;
}
struct expand_data {
unsigned char sha1[20];
enum object_type type;
unsigned long size;
/*
* 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;
/*
* 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)) {
if (!data->mark_query)
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);
} 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;
}
static void print_object_or_die(int fd, const unsigned char *sha1,
enum object_type type, unsigned long size)
{
@ -142,35 +202,37 @@ static void print_object_or_die(int fd, const unsigned char *sha1,
struct batch_options {
int enabled;
int print_contents;
const char *format;
};
static int batch_one_object(const char *obj_name, struct batch_options *opt)
static int batch_one_object(const char *obj_name, struct batch_options *opt,
struct expand_data *data)
{
unsigned char sha1[20];
enum object_type type = 0;
unsigned long size;
struct strbuf buf = STRBUF_INIT;
if (!obj_name)
return 1;
if (get_sha1(obj_name, sha1)) {
if (get_sha1(obj_name, data->sha1)) {
printf("%s missing\n", obj_name);
fflush(stdout);
return 0;
}
type = sha1_object_info(sha1, &size);
if (type <= 0) {
data->type = sha1_object_info_extended(data->sha1, &data->info);
if (data->type <= 0) {
printf("%s missing\n", obj_name);
fflush(stdout);
return 0;
}
printf("%s %s %lu\n", sha1_to_hex(sha1), typename(type), size);
fflush(stdout);
strbuf_expand(&buf, opt->format, expand_format, data);
strbuf_addch(&buf, '\n');
write_or_die(1, buf.buf, buf.len);
strbuf_release(&buf);
if (opt->print_contents) {
print_object_or_die(1, sha1, type, size);
print_object_or_die(1, data->sha1, data->type, data->size);
write_or_die(1, "\n", 1);
}
return 0;
@ -179,9 +241,23 @@ static int batch_one_object(const char *obj_name, struct batch_options *opt)
static int batch_objects(struct batch_options *opt)
{
struct strbuf buf = STRBUF_INIT;
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;
while (strbuf_getline(&buf, stdin, '\n') != EOF) {
int error = batch_one_object(buf.buf, opt);
int error = batch_one_object(buf.buf, opt, &data);
if (error)
return error;
}
@ -216,6 +292,7 @@ static int batch_option_callback(const struct option *opt,
bo->enabled = 1;
bo->print_contents = !strcmp(opt->long_name, "batch");
bo->format = arg;
return 0;
}
@ -235,12 +312,12 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
OPT_SET_INT('p', NULL, &opt, N_("pretty-print object's content"), 'p'),
OPT_SET_INT(0, "textconv", &opt,
N_("for blob objects, run textconv on object's content"), 'c'),
{ OPTION_CALLBACK, 0, "batch", &batch, NULL,
{ OPTION_CALLBACK, 0, "batch", &batch, "format",
N_("show info and content of objects fed from the standard input"),
PARSE_OPT_NOARG, batch_option_callback },
{ OPTION_CALLBACK, 0, "batch-check", &batch, NULL,
PARSE_OPT_OPTARG, batch_option_callback },
{ OPTION_CALLBACK, 0, "batch-check", &batch, "format",
N_("show info about objects fed from the standard input"),
PARSE_OPT_NOARG, batch_option_callback },
PARSE_OPT_OPTARG, batch_option_callback },
OPT_END()
};

Просмотреть файл

@ -72,6 +72,12 @@ $content"
echo_without_newline $sha1 | git cat-file --batch-check >actual &&
test_cmp expect actual
'
test_expect_success "custom --batch-check format" '
echo "$type $sha1" >expect &&
echo $sha1 | git cat-file --batch-check="%(objecttype) %(objectname)" >actual &&
test_cmp expect actual
'
}
hello_content="Hello World"