git-commit-vandalism/builtin/cat-file.c
Jeff King c334b87b30 cat-file: split --batch input lines on whitespace
If we get an input line to --batch or --batch-check that
looks like "HEAD foo bar", we will currently feed the whole
thing to get_sha1(). This means that to use --batch-check
with `rev-list --objects`, one must pre-process the input,
like:

  git rev-list --objects HEAD |
  cut -d' ' -f1 |
  git cat-file --batch-check

Besides being more typing and slightly less efficient to
invoke `cut`, the result loses information: we no longer
know which path each object was found at.

This patch teaches cat-file to split input lines at the
first whitespace. Everything to the left of the whitespace
is considered an object name, and everything to the right is
made available as the %(reset) atom. So you can now do:

  git rev-list --objects HEAD |
  git cat-file --batch-check='%(objectsize) %(rest)'

to collect object sizes at particular paths.

Even if %(rest) is not used, we always do the whitespace
split (which means you can simply eliminate the `cut`
command from the first example above).

This whitespace split is backwards compatible for any
reasonable input. Object names cannot contain spaces, so any
input with spaces would have resulted in a "missing" line.
The only input hurt is if somebody really expected input of
the form "HEAD is a fine-looking ref!" to fail; it will now
parse HEAD, and make "is a fine-looking ref!" available as
%(rest).

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-12 09:18:42 -07:00

377 lines
9.0 KiB
C

/*
* GIT - The information manager from hell
*
* Copyright (C) Linus Torvalds, 2005
*/
#include "cache.h"
#include "exec_cmd.h"
#include "tag.h"
#include "tree.h"
#include "builtin.h"
#include "parse-options.h"
#include "diff.h"
#include "userdiff.h"
#include "streaming.h"
static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
{
unsigned char sha1[20];
enum object_type type;
char *buf;
unsigned long size;
struct object_context obj_context;
if (get_sha1_with_context(obj_name, 0, sha1, &obj_context))
die("Not a valid object name %s", obj_name);
buf = NULL;
switch (opt) {
case 't':
type = sha1_object_info(sha1, NULL);
if (type > 0) {
printf("%s\n", typename(type));
return 0;
}
break;
case 's':
type = sha1_object_info(sha1, &size);
if (type > 0) {
printf("%lu\n", size);
return 0;
}
break;
case 'e':
return !has_sha1_file(sha1);
case 'p':
type = sha1_object_info(sha1, NULL);
if (type < 0)
die("Not a valid object name %s", obj_name);
/* custom pretty-print here */
if (type == OBJ_TREE) {
const char *ls_args[3] = { NULL };
ls_args[0] = "ls-tree";
ls_args[1] = obj_name;
return cmd_ls_tree(2, ls_args, NULL);
}
if (type == OBJ_BLOB)
return stream_blob_to_fd(1, sha1, NULL, 0);
buf = read_sha1_file(sha1, &type, &size);
if (!buf)
die("Cannot read object %s", obj_name);
/* otherwise just spit out the data */
break;
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))
die("git cat-file --textconv: unable to run textconv on %s",
obj_name);
break;
case 0:
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.
*/
}
buf = read_object_with_reference(sha1, exp_type, &size, NULL);
break;
default:
die("git cat-file: unknown option: %s", exp_type);
}
if (!buf)
die("git cat-file %s: bad file", obj_name);
write_or_die(1, buf, size);
return 0;
}
struct expand_data {
unsigned char sha1[20];
enum object_type type;
unsigned long size;
unsigned long disk_size;
const char *rest;
/*
* 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 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);
} else if (is_atom("rest", atom, len)) {
if (!data->mark_query && data->rest)
strbuf_addstr(sb, data->rest);
} 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)
{
if (type == OBJ_BLOB) {
if (stream_blob_to_fd(fd, sha1, NULL, 0) < 0)
die("unable to stream %s to stdout", sha1_to_hex(sha1));
}
else {
enum object_type rtype;
unsigned long rsize;
void *contents;
contents = read_sha1_file(sha1, &rtype, &rsize);
if (!contents)
die("object %s disappeared", sha1_to_hex(sha1));
if (rtype != type)
die("object %s changed type!?", sha1_to_hex(sha1));
if (rsize != size)
die("object %s change size!?", sha1_to_hex(sha1));
write_or_die(fd, contents, size);
free(contents);
}
}
struct batch_options {
int enabled;
int print_contents;
const char *format;
};
static int batch_one_object(const char *obj_name, struct batch_options *opt,
struct expand_data *data)
{
struct strbuf buf = STRBUF_INIT;
if (!obj_name)
return 1;
if (get_sha1(obj_name, data->sha1)) {
printf("%s missing\n", obj_name);
fflush(stdout);
return 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;
}
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, data->sha1, data->type, data->size);
write_or_die(1, "\n", 1);
}
return 0;
}
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) {
char *p;
int error;
/*
* Split at first whitespace, tying off the beginning of the
* string and saving the remainder (or NULL) in data.rest.
*/
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);
if (error)
return error;
}
return 0;
}
static const char * const cat_file_usage[] = {
N_("git cat-file (-t|-s|-e|-p|<type>|--textconv) <object>"),
N_("git cat-file (--batch|--batch-check) < <list_of_objects>"),
NULL
};
static int git_cat_file_config(const char *var, const char *value, void *cb)
{
if (userdiff_config(var, value) < 0)
return -1;
return git_default_config(var, value, cb);
}
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");
bo->format = arg;
return 0;
}
int cmd_cat_file(int argc, const char **argv, const char *prefix)
{
int opt = 0;
const char *exp_type = NULL, *obj_name = NULL;
struct batch_options batch = {0};
const struct option options[] = {
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'),
OPT_SET_INT('e', NULL, &opt,
N_("exit with zero when there's no error"), 'e'),
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, "format",
N_("show info and content of objects fed from the standard input"),
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_OPTARG, batch_option_callback },
OPT_END()
};
git_config(git_cat_file_config, NULL);
if (argc != 3 && argc != 2)
usage_with_options(cat_file_usage, options);
argc = parse_options(argc, argv, prefix, options, cat_file_usage, 0);
if (opt) {
if (argc == 1)
obj_name = argv[0];
else
usage_with_options(cat_file_usage, options);
}
if (!opt && !batch.enabled) {
if (argc == 2) {
exp_type = argv[0];
obj_name = argv[1];
} else
usage_with_options(cat_file_usage, options);
}
if (batch.enabled && (opt || argc)) {
usage_with_options(cat_file_usage, options);
}
if (batch.enabled)
return batch_objects(&batch);
return cat_one_file(opt, exp_type, obj_name);
}