path: root/builtin/cat-file.c

/*
 * GIT - The information manager from hell
 *
 * Copyright (C) Linus Torvalds, 2005
 */
#include "cache.h"
#include "config.h"
#include "builtin.h"
#include "diff.h"
#include "parse-options.h"
#include "userdiff.h"
#include "streaming.h"
#include "tree-walk.h"
#include "sha1-array.h"

struct batch_options {
	int enabled;
	int follow_symlinks;
	int print_contents;
	int buffer_output;
	int all_objects;
	int cmdmode; /* may be 'w' or 'c' for --filters or --textconv */
	const char *format;
};

static const char *force_path;

static int filter_object(const char *path, unsigned mode,
			 const struct object_id *oid,
			 char **buf, unsigned long *size)
{
	enum object_type type;

	*buf = read_sha1_file(oid->hash, &type, size);
	if (!*buf)
		return error(_("cannot read object %s '%s'"),
			     oid_to_hex(oid), path);
	if ((type == OBJ_BLOB) && S_ISREG(mode)) {
		struct strbuf strbuf = STRBUF_INIT;
		if (convert_to_working_tree(path, *buf, *size, &strbuf)) {
			free(*buf);
			*size = strbuf.len;
			*buf = strbuf_detach(&strbuf, NULL);
		}
	}

	return 0;
}

static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
			int unknown_type)
{
	struct object_id oid;
	enum object_type type;
	char *buf;
	unsigned long size;
	struct object_context obj_context;
	struct object_info oi = OBJECT_INFO_INIT;
	struct strbuf sb = STRBUF_INIT;
	unsigned flags = OBJECT_INFO_LOOKUP_REPLACE;
	const char *path = force_path;

	if (unknown_type)
		flags |= OBJECT_INFO_ALLOW_UNKNOWN_TYPE;

	if (get_sha1_with_context(obj_name, GET_SHA1_RECORD_PATH,
				  oid.hash, &obj_context))
		die("Not a valid object name %s", obj_name);

	if (!path)
		path = obj_context.path;
	if (obj_context.mode == S_IFINVALID)
		obj_context.mode = 0100644;

	buf = NULL;
	switch (opt) {
	case 't':
		oi.typename = &sb;
		if (sha1_object_info_extended(oid.hash, &oi, flags) < 0)
			die("git cat-file: could not get object info");
		if (sb.len) {
			printf("%s\n", sb.buf);
			strbuf_release(&sb);
			return 0;
		}
		break;

	case 's':
		oi.sizep = &size;
		if (sha1_object_info_extended(oid.hash, &oi, flags) < 0)
			die("git cat-file: could not get object info");
		printf("%lu\n", size);
		return 0;

	case 'e':
		return !has_object_file(&oid);

	case 'w':
		if (!path[0])
			die("git cat-file --filters %s: <object> must be "
			    "<sha1:path>", obj_name);

		if (filter_object(path, obj_context.mode,
				  &oid, &buf, &size))
			return -1;
		break;

	case 'c':
		if (!path[0])
			die("git cat-file --textconv %s: <object> must be <sha1:path>",
			    obj_name);

		if (textconv_object(path, obj_context.mode, &oid, 1, &buf, &size))
			break;

	case 'p':
		type = sha1_object_info(oid.hash, 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, &oid, NULL, 0);
		buf = read_sha1_file(oid.hash, &type, &size);
		if (!buf)
			die("Cannot read object %s", obj_name);

		/* otherwise just spit out the data */
		break;

	case 0:
		if (type_from_string(exp_type) == OBJ_BLOB) {
			struct object_id blob_oid;
			if (sha1_object_info(oid.hash, NULL) == OBJ_TAG) {
				char *buffer = read_sha1_file(oid.hash, &type, &size);
				const char *target;
				if (!skip_prefix(buffer, "object ", &target) ||
				    get_oid_hex(target, &blob_oid))
					die("%s not a valid tag", oid_to_hex(&oid));
				free(buffer);
			} else
				oidcpy(&blob_oid, &oid);

			if (sha1_object_info(blob_oid.hash, NULL) == OBJ_BLOB)
				return stream_blob_to_fd(1, &blob_oid, 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(oid.hash, 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);
	free(buf);
	free(obj_context.path);
	return 0;
}

struct expand_data {
	struct object_id oid;
	enum object_type type;
	unsigned long size;
	off_t disk_size;
	const char *rest;
	struct object_id delta_base_oid;

	/*
	 * 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;

	/*
	 * 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;

	/*
	 * 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;

	/*
	 * This flag will be true if the requested batch format and options
	 * don't require us to call sha1_object_info, which can then be
	 * optimized out.
	 */
	unsigned skip_object_info : 1;
};

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, oid_to_hex(&data->oid));
	} else if (is_atom("objecttype", atom, len)) {
		if (data->mark_query)
			data->info.typep = &data->type;
		else
			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, "%"PRIuMAX, (uintmax_t)data->disk_size);
	} 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);
	} else if (is_atom("deltabase", atom, len)) {
		if (data->mark_query)
			data->info.delta_base_sha1 = data->delta_base_oid.hash;
		else
			strbuf_addstr(sb,
				      oid_to_hex(&data->delta_base_oid));
	} 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 batch_write(struct batch_options *opt, const void *data, int len)
{
	if (opt->buffer_output) {
		if (fwrite(data, 1, len, stdout) != len)
			die_errno("unable to write to stdout");
	} else
		write_or_die(1, data, len);
}

static void print_object_or_die(struct batch_options *opt, struct expand_data *data)
{
	const struct object_id *oid = &data->oid;

	assert(data->info.typep);

	if (data->type == OBJ_BLOB) {
		if (opt->buffer_output)
			fflu