1 files changed, 218 insertions, 118 deletions

diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index 40f87b4649..d5a93e0e91 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -13,76 +13,6 @@
 #include "userdiff.h"
 #include "streaming.h"
 
-#define BATCH 1
-#define BATCH_CHECK 2
-
-static void pprint_tag(const unsigned char *sha1, const char *buf, unsigned long size)
-{
-	/* the parser in tag.c is useless here. */
-	const char *endp = buf + size;
-	const char *cp = buf;
-
-	while (cp < endp) {
-		char c = *cp++;
-		if (c != '\n')
-			continue;
-		if (7 <= endp - cp && !memcmp("tagger ", cp, 7)) {
-			const char *tagger = cp;
-
-			/* Found the tagger line.  Copy out the contents
-			 * of the buffer so far.
-			 */
-			write_or_die(1, buf, cp - buf);
-
-			/*
-			 * Do something intelligent, like pretty-printing
-			 * the date.
-			 */
-			while (cp < endp) {
-				if (*cp++ == '\n') {
-					/* tagger to cp is a line
-					 * that has ident and time.
-					 */
-					const char *sp = tagger;
-					char *ep;
-					unsigned long date;
-					long tz;
-					while (sp < cp && *sp != '>')
-						sp++;
-					if (sp == cp) {
-						/* give up */
-						write_or_die(1, tagger,
-							     cp - tagger);
-						break;
-					}
-					while (sp < cp &&
-					       !('0' <= *sp && *sp <= '9'))
-						sp++;
-					write_or_die(1, tagger, sp - tagger);
-					date = strtoul(sp, &ep, 10);
-					tz = strtol(ep, NULL, 10);
-					sp = show_date(date, tz, 0);
-					write_or_die(1, sp, strlen(sp));
-					xwrite(1, "\n", 1);
-					break;
-				}
-			}
-			break;
-		}
-		if (cp < endp && *cp == '\n')
-			/* end of header */
-			break;
-	}
-	/* At this point, we have copied out the header up to the end of
-	 * the tagger line and cp points at one past \n.  It could be the
-	 * next header line after the tagger line, or it could be another
-	 * \n that marks the end of the headers.  We need to copy out the
-	 * remainder as is.
-	 */
-	if (cp < endp)
-		write_or_die(1, cp, endp - cp);
-}
-
 static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
 {
 	unsigned char sha1[20];
@@ -115,6 +45,14 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
 	case 'e':
 		return !has_sha1_file(sha1);
 
+	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;
+
 	case 'p':
 		type = sha1_object_info(sha1, NULL);
 		if (type < 0)
@@ -133,24 +71,10 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
 		buf = read_sha1_file(sha1, &type, &size);
 		if (!buf)
 			die("Cannot read object %s", obj_name);
-		if (type == OBJ_TAG) {
-			pprint_tag(sha1, buf, size);
-			return 0;
-		}
 
 		/* 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];
@@ -188,54 +112,211 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
 	return 0;
 }
 
-static int batch_one_object(const char *obj_name, int print_contents)
-{
+struct expand_data {
 	unsigned char sha1[20];
-	enum object_type type = 0;
+	enum object_type type;
 	unsigned long size;
-	void *contents = NULL;
+	unsigned long disk_size;
+	const char *rest;
+	unsigned char delta_base_sha1[20];
+
+	/*
+	 * 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;
+};
+
+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)
+			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, "%lu", 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_sha1;
+		else
+			strbuf_addstr(sb, sha1_to_hex(data->delta_base_sha1));
+	} 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, struct expand_data *data)
+{
+	const unsigned char *sha1 = data->sha1;
+
+	assert(data->info.typep);
+
+	if (data->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 type;
+		unsigned long size;
+		void *contents;
+
+		contents = read_sha1_file(sha1, &type, &size);
+		if (!contents)
+			die("object %s disappeared", sha1_to_hex(sha1));
+		if (type != data->type)
+			die("object %s changed type!?", sha1_to_hex(sha1));
+		if (data->info.sizep && size != data->size)
+			die("object %s changed 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, sha1)) {
+	if (get_sha1(obj_name, data->sha1)) {
 		printf("%s missing\n", obj_name);
 		fflush(stdout);
 		return 0;
 	}
 
-	if (print_contents == BATCH)
-		contents = read_sha1_file(sha1, &type, &size);
-	else
-		type = sha1_object_info(sha1, &size);
-
-	if (type <= 0) {
+	if (sha1_object_info_extended(data->sha1, &data->info, LOOKUP_REPLACE_OBJECT) < 0) {
 		printf("%s missing\n", obj_name);
 		fflush(stdout);
-		if (print_contents == BATCH)
-			free(contents);
 		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 (print_contents == BATCH) {
-		write_or_die(1, contents, size);
-		printf("\n");
-		fflush(stdout);
-		free(contents);
+	if (opt->print_contents) {
+		print_object_or_die(1, data);
+		write_or_die(1, "\n", 1);
 	}
-
 	return 0;
 }
 
-static int batch_objects(int print_contents)
+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;
+
+	/*
+	 * 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;
+
+	/*
+	 * 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;
 
 	while (strbuf_getline(&buf, stdin, '\n') != EOF) {
-		int error = batch_one_object(buf.buf, print_contents);
+		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);
 		if (error)
 			return error;
 	}
@@ -257,10 +338,29 @@ static int git_cat_file_config(const char *var, const char *value, void *cb)
 	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, batch = 0;
+	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")),
@@ -271,12 +371,12 @@ 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'),
-		OPT_SET_INT(0, "batch", &batch,
-			    N_("show info and content of objects fed from the standard input"),
-			    BATCH),
-		OPT_SET_INT(0, "batch-check", &batch,
-			    N_("show info about objects fed from the standard input"),
-			    BATCH_CHECK),
+		{ 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()
 	};
 
@@ -293,19 +393,19 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 		else
 			usage_with_options(cat_file_usage, options);
 	}
-	if (!opt && !batch) {
+	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 && (opt || argc)) {
+	if (batch.enabled && (opt || argc)) {
 		usage_with_options(cat_file_usage, options);
 	}
 
-	if (batch)
-		return batch_objects(batch);
+	if (batch.enabled)
+		return batch_objects(&batch);
 
 	return cat_one_file(opt, exp_type, obj_name);
 }