[PATCH] fsck: print progress

["Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>]

fsck is usually a long process and it would be nice if it prints
progress from time to time.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 OK let's go with total object count for more accurate progress. One
 thing I did not realize that the title is not copied to struct
 progress and we can update title (e.g. current pack) while displaying
 progress.

 Updating once every 1024 objects may feel sluggish on large blobs,
 but we have more important things to worry about when it comes to
 large blobs than this progress bar.

 multithread fsck sounds interesting, I'll look into it.

 Documentation/git-fsck.txt |   12 +++++++++-
 builtin/fsck.c             |   49 ++++++++++++++++++++++++++++++++++++++++---
 pack-check.c               |   11 +++++++--
 pack.h                     |    4 ++-
 4 files changed, 67 insertions(+), 9 deletions(-)

diff --git a/Documentation/git-fsck.txt b/Documentation/git-fsck.txt
index a2a508d..5245101 100644
--- a/Documentation/git-fsck.txt
+++ b/Documentation/git-fsck.txt
@@ -10,7 +10,8 @@ SYNOPSIS
 --------
 [verse]
 'git fsck' [--tags] [--root] [--unreachable] [--cache] [--no-reflogs]
-	 [--[no-]full] [--strict] [--verbose] [--lost-found] [<object>*]
+	 [--[no-]full] [--strict] [--verbose] [--lost-found]
+	 [--[no-]progress] [<object>*]
 
 DESCRIPTION
 -----------
@@ -72,6 +73,15 @@ index file, all SHA1 references in .git/refs/*, and all reflogs (unless
 	a blob, the contents are written into the file, rather than
 	its object name.
 
+--progress::
+--no-progress::
+	When fsck is run in a terminal, it will show the progress.
+	These options can force progress to be shown or not
+	regardless terminal check.
++
+Progress is not shown when --verbose is used. --progress is ignored
+in this case.
+
 It tests SHA1 and general object sanity, and it does full tracking of
 the resulting reachability and everything else. It prints out any
 corruption it finds (missing or bad objects), and if you use the
diff --git a/builtin/fsck.c b/builtin/fsck.c
index df1a88b..e0cc4de 100644
--- a/builtin/fsck.c
+++ b/builtin/fsck.c
@@ -11,6 +11,7 @@
 #include "fsck.h"
 #include "parse-options.h"
 #include "dir.h"
+#include "progress.h"
 
 #define REACHABLE 0x0001
 #define SEEN      0x0002
@@ -27,6 +28,8 @@ static const char *head_points_at;
 static int errors_found;
 static int write_lost_and_found;
 static int verbose;
+static int show_progress = -1;
+
 #define ERROR_OBJECT 01
 #define ERROR_REACHABLE 02
 
@@ -512,15 +515,20 @@ static void get_default_heads(void)
 static void fsck_object_dir(const char *path)
 {
 	int i;
+	struct progress *progress = NULL;
 
 	if (verbose)
 		fprintf(stderr, "Checking object directory\n");
 
+	if (show_progress)
+		progress = start_progress("Checking object directories", 256);
 	for (i = 0; i < 256; i++) {
 		static char dir[4096];
 		sprintf(dir, "%s/%02x", path, i);
 		fsck_dir(i, dir);
+		display_progress(progress, i+1);
 	}
+	stop_progress(&progress);
 	fsck_sha1_list();
 }
 
@@ -591,6 +599,7 @@ static struct option fsck_opts[] = {
 	OPT_BOOLEAN(0, "strict", &check_strict, "enable more strict checking"),
 	OPT_BOOLEAN(0, "lost-found", &write_lost_and_found,
 				"write dangling objects in .git/lost-found"),
+	OPT_BOOL   (0, "progress", &show_progress, "show progress"),
 	OPT_END(),
 };
 
@@ -603,6 +612,12 @@ int cmd_fsck(int argc, const char **argv, const char *prefix)
 	read_replace_refs = 0;
 
 	argc = parse_options(argc, argv, prefix, fsck_opts, fsck_usage, 0);
+
+	if (show_progress == -1)
+		show_progress = isatty(2);
+	if (verbose)
+		show_progress = 0;
+
 	if (write_lost_and_found) {
 		check_full = 1;
 		include_reflogs = 0;
@@ -622,20 +637,46 @@ int cmd_fsck(int argc, const char **argv, const char *prefix)
 
 	if (check_full) {
 		struct packed_git *p;
+		int i, nr_objects = 0, object_count;
+		struct progress *progress = NULL;
 
 		prepare_packed_git();
-		for (p = packed_git; p; p = p->next)
+
+		if (show_progress) {
+			for (p = packed_git; p; p = p->next) {
+				if (open_pack_index(p))
+					continue;
+				nr_objects += p->num_objects;
+			}
+
+			object_count = 0;
+			progress = start_progress("Verifying packs", nr_objects);
+		}
+
+		for (i = 1, p = packed_git; p; p = p->next, i++) {
 			/* verify gives error messages itself */
-			verify_pack(p);
+			verify_pack(p, progress, object_count);
+			object_count += p->num_objects;
+		}
+		stop_progress(&progress);
 
-		for (p = packed_git; p; p = p->next) {
+		if (show_progress) {
+			object_count = 0;
+			progress = start_progress("Checking objects", nr_objects);
+		}
+
+		for (i = 1, p = packed_git; p; p = p->next, i++) {
 			uint32_t j, num;
 			if (open_pack_index(p))
 				continue;
 			num = p->num_objects;
-			for (j = 0; j < num; j++)
+			for (j = 0; j < num; j++) {
 				fsck_sha1(nth_packed_object_sha1(p, j));
+				display_progress(progress, object_count + j+1);
+			}
+			object_count += p->num_objects;
 		}
+		stop_progress(&progress);
 	}
 
 	heads = 0;
diff --git a/pack-check.c b/pack-check.c
index 0c19b6e..80de302 100644
--- a/pack-check.c
+++ b/pack-check.c
@@ -1,6 +1,7 @@
 #include "cache.h"
 #include "pack.h"
 #include "pack-revindex.h"
+#include "progress.h"
 
 struct idx_entry {
 	off_t                offset;
@@ -42,7 +43,8 @@ int check_pack_crc(struct packed_git *p, struct pack_window **w_curs,
 }
 
 static int verify_packfile(struct packed_git *p,
-		struct pack_window **w_curs)
+			   struct pack_window **w_curs,
+			   struct progress *progress, uint32_t base_count)
 {
 	off_t index_size = p->index_size;
 	const unsigned char *index_base = p->index_data;
@@ -126,7 +128,10 @@ static int verify_packfile(struct packed_git *p,
 			break;
 		}
 		free(data);
+		if (((base_count + i) & 1023) == 0)
+			display_progress(progress, base_count + i);
 	}
+	display_progress(progress, base_count + i);
 	free(entries);
 
 	return err;
@@ -155,7 +160,7 @@ int verify_pack_index(struct packed_git *p)
 	return err;
 }
 
-int verify_pack(struct packed_git *p)
+int verify_pack(struct packed_git *p, struct progress *progress, uint32_t base_count)
 {
 	int err = 0;
 	struct pack_window *w_curs = NULL;
@@ -164,7 +169,7 @@ int verify_pack(struct packed_git *p)
 	if (!p->index_data)
 		return -1;
 
-	err |= verify_packfile(p, &w_curs);
+	err |= verify_packfile(p, &w_curs, progress, base_count);
 	unuse_pack(&w_curs);
 
 	return err;
diff --git a/pack.h b/pack.h
index 722a54e..3a63bf6 100644
--- a/pack.h
+++ b/pack.h
@@ -70,10 +70,12 @@ struct pack_idx_entry {
 	off_t offset;
 };
 
+struct progress;
+
 extern const char *write_idx_file(const char *index_name, struct pack_idx_entry **objects, int nr_objects, const struct pack_idx_option *, unsigned char *sha1);
 extern int check_pack_crc(struct packed_git *p, struct pack_window **w_curs, off_t offset, off_t len, unsigned int nr);
 extern int verify_pack_index(struct packed_git *);
-extern int verify_pack(struct packed_git *);
+extern int verify_pack(struct packed_git *, struct progress *, uint32_t);
 extern void fixup_pack_header_footer(int, unsigned char *, const char *, uint32_t, unsigned char *, off_t);
 extern char *index_pack_lockfile(int fd);
 extern int encode_in_pack_object_header(enum object_type, uintmax_t, unsigned char *);
-- 
1.7.3.1.256.g2539c.dirty