1 files changed, 121 insertions, 40 deletions

diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index 049a95f1f1..560f6c2cc7 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -9,6 +9,16 @@
 #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;
+	const char *format;
+};
 
 static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
 			int unknown_type)
@@ -121,7 +131,7 @@ struct expand_data {
 	unsigned char sha1[20];
 	enum object_type type;
 	unsigned long size;
-	unsigned long disk_size;
+	off_t disk_size;
 	const char *rest;
 	unsigned char delta_base_sha1[20];
 
@@ -144,6 +154,13 @@ struct expand_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)
@@ -174,7 +191,7 @@ static void expand_atom(struct strbuf *sb, const char *atom, int len,
 		if (data->mark_query)
 			data->info.disk_sizep = &data->disk_size;
 		else
-			strbuf_addf(sb, "%lu", data->disk_size);
+			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;
@@ -204,14 +221,25 @@ static size_t expand_format(struct strbuf *sb, const char *start, void *data)
 	return end - start + 1;
 }
 
-static void print_object_or_die(int fd, struct expand_data *data)
+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 unsigned char *sha1 = data->sha1;
 
 	assert(data->info.typep);
 
 	if (data->type == OBJ_BLOB) {
-		if (stream_blob_to_fd(fd, sha1, NULL, 0) < 0)
+		if (opt->buffer_output)
+			fflush(stdout);
+		if (stream_blob_to_fd(1, sha1, NULL, 0) < 0)
 			die("unable to stream %s to stdout", sha1_to_hex(sha1));
 	}
 	else {
@@ -227,29 +255,41 @@ static void print_object_or_die(int fd, struct expand_data *data)
 		if (data->info.sizep && size != data->size)
 			die("object %s changed size!?", sha1_to_hex(sha1));
 
-		write_or_die(fd, contents, size);
+		batch_write(opt, contents, size);
 		free(contents);
 	}
 }
 
-struct batch_options {
-	int enabled;
-	int follow_symlinks;
-	int print_contents;
-	const char *format;
-};
-
-static int batch_one_object(const char *obj_name, struct batch_options *opt,
-			    struct expand_data *data)
+static void batch_object_write(const char *obj_name, struct batch_options *opt,
+			       struct expand_data *data)
 {
 	struct strbuf buf = STRBUF_INIT;
+
+	if (!data->skip_object_info &&
+	    sha1_object_info_extended(data->sha1, &data->info, LOOKUP_REPLACE_OBJECT) < 0) {
+		printf("%s missing\n", obj_name ? obj_name : sha1_to_hex(data->sha1));
+		fflush(stdout);
+		return;
+	}
+
+	strbuf_expand(&buf, opt->format, expand_format, data);
+	strbuf_addch(&buf, '\n');
+	batch_write(opt, buf.buf, buf.len);
+	strbuf_release(&buf);
+
+	if (opt->print_contents) {
+		print_object_or_die(opt, data);
+		batch_write(opt, "\n", 1);
+	}
+}
+
+static void batch_one_object(const char *obj_name, struct batch_options *opt,
+			     struct expand_data *data)
+{
 	struct object_context ctx;
 	int flags = opt->follow_symlinks ? GET_SHA1_FOLLOW_SYMLINKS : 0;
 	enum follow_symlinks_result result;
 
-	if (!obj_name)
-	   return 1;
-
 	result = get_sha1_with_context(obj_name, flags, data->sha1, &ctx);
 	if (result != FOUND) {
 		switch (result) {
@@ -274,7 +314,7 @@ static int batch_one_object(const char *obj_name, struct batch_options *opt,
 			break;
 		}
 		fflush(stdout);
-		return 0;
+		return;
 	}
 
 	if (ctx.mode == 0) {
@@ -282,24 +322,38 @@ static int batch_one_object(const char *obj_name, struct batch_options *opt,
 		       (uintmax_t)ctx.symlink_path.len,
 		       ctx.symlink_path.buf);
 		fflush(stdout);
-		return 0;
+		return;
 	}
 
-	if (sha1_object_info_extended(data->sha1, &data->info, LOOKUP_REPLACE_OBJECT) < 0) {
-		printf("%s missing\n", obj_name);
-		fflush(stdout);
-		return 0;
-	}
+	batch_object_write(obj_name, opt, data);
+}
 
-	strbuf_expand(&buf, opt->format, expand_format, data);
-	strbuf_addch(&buf, '\n');
-	write_or_die(1, buf.buf, buf.len);
-	strbuf_release(&buf);
+struct object_cb_data {
+	struct batch_options *opt;
+	struct expand_data *expand;
+};
 
-	if (opt->print_contents) {
-		print_object_or_die(1, data);
-		write_or_die(1, "\n", 1);
-	}
+static void batch_object_cb(const unsigned char sha1[20], void *vdata)
+{
+	struct object_cb_data *data = vdata;
+	hashcpy(data->expand->sha1, sha1);
+	batch_object_write(NULL, data->opt, data->expand);
+}
+
+static int batch_loose_object(const unsigned char *sha1,
+			      const char *path,
+			      void *data)
+{
+	sha1_array_append(data, sha1);
+	return 0;
+}
+
+static int batch_packed_object(const unsigned char *sha1,
+			       struct packed_git *pack,
+			       uint32_t pos,
+			       void *data)
+{
+	sha1_array_append(data, sha1);
 	return 0;
 }
 
@@ -323,6 +377,13 @@ static int batch_objects(struct batch_options *opt)
 	strbuf_expand(&buf, opt->format, expand_format, &data);
 	data.mark_query = 0;
 
+	if (opt->all_objects) {
+		struct object_info empty;
+		memset(&empty, 0, sizeof(empty));
+		if (!memcmp(&data.info, &empty, sizeof(empty)))
+			data.skip_object_info = 1;
+	}
+
 	/*
 	 * If we are printing out the object, then always fill in the type,
 	 * since we will want to decide whether or not to stream.
@@ -330,6 +391,21 @@ static int batch_objects(struct batch_options *opt)
 	if (opt->print_contents)
 		data.info.typep = &data.type;
 
+	if (opt->all_objects) {
+		struct sha1_array sa = SHA1_ARRAY_INIT;
+		struct object_cb_data cb;
+
+		for_each_loose_object(batch_loose_object, &sa, 0);
+		for_each_packed_object(batch_packed_object, &sa, 0);
+
+		cb.opt = opt;
+		cb.expand = &data;
+		sha1_array_for_each_unique(&sa, batch_object_cb, &cb);
+
+		sha1_array_clear(&sa);
+		return 0;
+	}
+
 	/*
 	 * 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
@@ -340,7 +416,7 @@ static int batch_objects(struct batch_options *opt)
 	save_warning = warn_on_object_refname_ambiguity;
 	warn_on_object_refname_ambiguity = 0;
 
-	while (strbuf_getline(&buf, stdin, '\n') != EOF) {
+	while (strbuf_getline(&buf, stdin) != EOF) {
 		if (data.split_on_whitespace) {
 			/*
 			 * Split at first whitespace, tying off the beginning
@@ -355,9 +431,7 @@ static int batch_objects(struct batch_options *opt)
 			data.rest = p;
 		}
 
-		retval = batch_one_object(buf.buf, opt, &data);
-		if (retval)
-			break;
+		batch_one_object(buf.buf, opt, &data);
 	}
 
 	strbuf_release(&buf);
@@ -366,8 +440,8 @@ static int batch_objects(struct batch_options *opt)
 }
 
 static const char * const cat_file_usage[] = {
-	N_("git cat-file (-t [--allow-unknown-type]|-s [--allow-unknown-type]|-e|-p|<type>|--textconv) <object>"),
-	N_("git cat-file (--batch | --batch-check) [--follow-symlinks] < <list-of-objects>"),
+	N_("git cat-file (-t [--allow-unknown-type] | -s [--allow-unknown-type] | -e | -p | <type> | --textconv) <object>"),
+	N_("git cat-file (--batch | --batch-check) [--follow-symlinks]"),
 	NULL
 };
 
@@ -412,8 +486,9 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 		OPT_CMDMODE('p', NULL, &opt, N_("pretty-print object's content"), 'p'),
 		OPT_CMDMODE(0, "textconv", &opt,
 			    N_("for blob objects, run textconv on object's content"), 'c'),
-		OPT_BOOL( 0, "allow-unknown-type", &unknown_type,
+		OPT_BOOL(0, "allow-unknown-type", &unknown_type,
 			  N_("allow -s and -t to work with broken/corrupt objects")),
+		OPT_BOOL(0, "buffer", &batch.buffer_output, N_("buffer --batch output")),
 		{ OPTION_CALLBACK, 0, "batch", &batch, "format",
 			N_("show info and content of objects fed from the standard input"),
 			PARSE_OPT_OPTARG, batch_option_callback },
@@ -422,11 +497,14 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 			PARSE_OPT_OPTARG, batch_option_callback },
 		OPT_BOOL(0, "follow-symlinks", &batch.follow_symlinks,
 			 N_("follow in-tree symlinks (used with --batch or --batch-check)")),
+		OPT_BOOL(0, "batch-all-objects", &batch.all_objects,
+			 N_("show all objects with --batch or --batch-check")),
 		OPT_END()
 	};
 
 	git_config(git_cat_file_config, NULL);
 
+	batch.buffer_output = -1;
 	argc = parse_options(argc, argv, prefix, options, cat_file_usage, 0);
 
 	if (opt) {
@@ -446,10 +524,13 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 		usage_with_options(cat_file_usage, options);
 	}
 
-	if (batch.follow_symlinks && !batch.enabled) {
+	if ((batch.follow_symlinks || batch.all_objects) && !batch.enabled) {
 		usage_with_options(cat_file_usage, options);
 	}
 
+	if (batch.buffer_output < 0)
+		batch.buffer_output = batch.all_objects;
+
 	if (batch.enabled)
 		return batch_objects(&batch);