Merge branch 'nd/stream-more'

Use API to read blob data in smaller chunks in more places to reduce the
memory footprint.

By Nguyễn Thái Ngọc Duy (6) and Junio C Hamano (1)
* nd/stream-more:
  update-server-info: respect core.bigfilethreshold
  fsck: use streaming API for writing lost-found blobs
  show: use streaming API for showing blobs
  parse_object: avoid putting whole blob in core
  cat-file: use streaming API to print blobs
  Add more large blob test cases
  streaming: make streaming-write-entry to be more reusable

4 files changed, 48 insertions, 20 deletions

diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index 8ed501f22..36a910443 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -11,6 +11,7 @@
 #include "parse-options.h"
 #include "diff.h"
 #include "userdiff.h"
+#include "streaming.h"
 
 #define BATCH 1
 #define BATCH_CHECK 2
@@ -127,6 +128,8 @@ static int cat_one_file(int opt, const char *exp_type, const char *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);
@@ -149,6 +152,28 @@ static int cat_one_file(int opt, const char *exp_type, const char *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;
 
diff --git a/builtin/fsck.c b/builtin/fsck.c
index 67eb553c7..a710227a6 100644
--- a/builtin/fsck.c
+++ b/builtin/fsck.c
@@ -12,6 +12,7 @@
 #include "parse-options.h"
 #include "dir.h"
 #include "progress.h"
+#include "streaming.h"
 
 #define REACHABLE 0x0001
 #define SEEN      0x0002
@@ -238,13 +239,8 @@ static void check_unreachable_object(struct object *obj)
 			if (!(f = fopen(filename, "w")))
 				die_errno("Could not open '%s'", filename);
 			if (obj->type == OBJ_BLOB) {
-				enum object_type type;
-				unsigned long size;
-				char *buf = read_sha1_file(obj->sha1,
-						&type, &size);
-				if (buf && fwrite(buf, 1, size, f) != size)
+				if (stream_blob_to_fd(fileno(f), obj->sha1, NULL, 1))
 					die_errno("Could not write '%s'", filename);
-				free(buf);
 			} else
 				fprintf(f, "%s\n", sha1_to_hex(obj->sha1));
 			if (fclose(f))
diff --git a/builtin/log.c b/builtin/log.c
index 8a47012b0..690caa783 100644
--- a/builtin/log.c
+++ b/builtin/log.c
@@ -20,6 +20,7 @@
 #include "string-list.h"
 #include "parse-options.h"
 #include "branch.h"
+#include "streaming.h"
 
 /* Set a default date-time format for git log ("log.date" config variable) */
 static const char *default_date_mode = NULL;
@@ -383,8 +384,13 @@ static void show_tagger(char *buf, int len, struct rev_info *rev)
 	strbuf_release(&out);
 }
 
-static int show_object(const unsigned char *sha1, int show_tag_object,
-	struct rev_info *rev)
+static int show_blob_object(const unsigned char *sha1, struct rev_info *rev)
+{
+	fflush(stdout);
+	return stream_blob_to_fd(1, sha1, NULL, 0);
+}
+
+static int show_tag_object(const unsigned char *sha1, struct rev_info *rev)
 {
 	unsigned long size;
 	enum object_type type;
@@ -394,16 +400,16 @@ static int show_object(const unsigned char *sha1, int show_tag_object,
 	if (!buf)
 		return error(_("Could not read object %s"), sha1_to_hex(sha1));
 
-	if (show_tag_object)
-		while (offset < size && buf[offset] != '\n') {
-			int new_offset = offset + 1;
-			while (new_offset < size && buf[new_offset++] != '\n')
-				; /* do nothing */
-			if (!prefixcmp(buf + offset, "tagger "))
-				show_tagger(buf + offset + 7,
-					    new_offset - offset - 7, rev);
-			offset = new_offset;
-		}
+	assert(type == OBJ_TAG);
+	while (offset < size && buf[offset] != '\n') {
+		int new_offset = offset + 1;
+		while (new_offset < size && buf[new_offset++] != '\n')
+			; /* do nothing */
+		if (!prefixcmp(buf + offset, "tagger "))
+			show_tagger(buf + offset + 7,
+				    new_offset - offset - 7, rev);
+		offset = new_offset;
+	}
 
 	if (offset < size)
 		fwrite(buf + offset, size - offset, 1, stdout);
@@ -463,7 +469,7 @@ int cmd_show(int argc, const char **argv, const char *prefix)
 		const char *name = objects[i].name;
 		switch (o->type) {
 		case OBJ_BLOB:
-			ret = show_object(o->sha1, 0, NULL);
+			ret = show_blob_object(o->sha1, NULL);
 			break;
 		case OBJ_TAG: {
 			struct tag *t = (struct tag *)o;
@@ -474,7 +480,7 @@ int cmd_show(int argc, const char **argv, const char *prefix)
 					diff_get_color_opt(&rev.diffopt, DIFF_COMMIT),
 					t->tag,
 					diff_get_color_opt(&rev.diffopt, DIFF_RESET));
-			ret = show_object(o->sha1, 1, &rev);
+			ret = show_tag_object(o->sha1, &rev);
 			rev.shown_one = 1;
 			if (ret)
 				break;
diff --git a/builtin/update-server-info.c b/builtin/update-server-info.c
index b90dce635..0d63c4498 100644
--- a/builtin/update-server-info.c
+++ b/builtin/update-server-info.c
@@ -15,6 +15,7 @@ int cmd_update_server_info(int argc, const char **argv, const char *prefix)
 		OPT_END()
 	};
 
+	git_config(git_default_config, NULL);
 	argc = parse_options(argc, argv, prefix, options,
 			     update_server_info_usage, 0);
 	if (argc > 0)