X-Git-Url: https://git.octo.it/?a=blobdiff_plain;f=fsck-cache.c;h=d69c426b360db21820a4e180202ae4d71e0ba965;hb=001d4a27dbfaaa59c25dc35dafc69bd9b9bc21d3;hp=34c80811c94f64f0f6bf0201c9b5c6d39d014877;hpb=2845dbe4a451b20f963f872c3914b9184142ff3f;p=git.git

diff --git a/fsck-cache.c b/fsck-cache.c
index 34c80811..d69c426b 100644
--- a/fsck-cache.c
+++ b/fsck-cache.c
@@ -1,250 +1,308 @@
-#include "cache.h"
-
 #include <sys/types.h>
 #include <dirent.h>
 
-/*
- * The low 16 bits of the "flags" field shows whether
- * a commit is part of the path to the root for that
- * parent.
- *
- * Bit 16 is an internal flag that we've seen the
- * definition for this rev, and not just seen it as
- * a parent target.
- */
-#define MAX_COMMITS (16)
-#define marked(rev)	((rev)->flags & 0xffff)
-#define SEEN 0x10000
-#define USED 0x20000
-#define REACHABLE 0x40000
+#include "cache.h"
+#include "commit.h"
+#include "tree.h"
+#include "blob.h"
+#include "tag.h"
+#include "delta.h"
+
+#define REACHABLE 0x0001
 
+static int show_root = 0;
+static int show_tags = 0;
 static int show_unreachable = 0;
-static int head_supplied = 0;
+static int show_max_delta_depth = 0;
+static int keep_cache_objects = 0; 
 static unsigned char head_sha1[20];
 
-struct parent {
-	struct revision *parent;
-	struct parent *next;
-};
-
-struct revision {
-	unsigned int flags;
-	unsigned char sha1[20];
-	unsigned long date;
-	struct parent *parent;
-};
-
-static struct revision **revs;
-static int nr_revs, rev_allocs;
-
-static int find_rev(unsigned char *sha1)
+static void expand_deltas(void)
 {
-	int first = 0, last = nr_revs;
-
-	while (first < last) {
-		int next = (first + last) / 2;
-		struct revision *rev = revs[next];
-		int cmp;
-
-		cmp = memcmp(sha1, rev->sha1, 20);
-		if (!cmp)
-			return next;
-		if (cmp < 0) {
-			last = next;
-			continue;
+	int i, max_depth = 0;
+
+	/*
+	 * To be as efficient as possible we look for delta heads and
+	 * recursively process them going backward, and parsing
+	 * resulting objects along the way.  This allows for processing
+	 * each delta objects only once regardless of the delta depth.
+	 */
+	for (i = 0; i < nr_objs; i++) {
+		struct object *obj = objs[i];
+		if (obj->parsed && !obj->delta && obj->attached_deltas) {
+			int depth = 0;
+			char type[10];
+			unsigned long size;
+			void *buf = read_sha1_file(obj->sha1, type, &size);
+			if (!buf)
+				continue;
+			depth = process_deltas(buf, size, obj->type,
+					       obj->attached_deltas);
+			if (max_depth < depth)
+				max_depth = depth;
 		}
-		first = next+1;
 	}
-	return -first-1;
+	if (show_max_delta_depth)
+		printf("maximum delta depth = %d\n", max_depth);
 }
-
-static struct revision *lookup_rev(unsigned char *sha1)
+															
+static void check_connectivity(void)
 {
-	int pos = find_rev(sha1);
-	struct revision *n;
-
-	if (pos >= 0)
-		return revs[pos];
-	
-	pos = -pos-1;
-
-	if (rev_allocs == nr_revs) {
-		rev_allocs = alloc_nr(rev_allocs);
-		revs = realloc(revs, rev_allocs * sizeof(struct revision *));
-	}
-	n = malloc(sizeof(struct revision));
+	int i;
 
-	n->flags = 0;
-	memcpy(n->sha1, sha1, 20);
-	n->parent = NULL;
+	/* Look up all the requirements, warn about missing objects.. */
+	for (i = 0; i < nr_objs; i++) {
+		struct object *obj = objs[i];
+		struct object_list *refs;
+
+		if (!obj->parsed) {
+			if (obj->delta)
+				printf("unresolved delta %s\n",
+				       sha1_to_hex(obj->sha1));
+			else
+				printf("missing %s %s\n",
+				       obj->type, sha1_to_hex(obj->sha1));
+			continue;
+		}
 
-	/* Insert it into the right place */
-	memmove(revs + pos + 1, revs + pos, (nr_revs - pos) * sizeof(struct revision *));
-	revs[pos] = n;
-	nr_revs++;
+		for (refs = obj->refs; refs; refs = refs->next) {
+			if (refs->item->parsed)
+				continue;
+			printf("broken link from %7s %s\n",
+			       obj->type, sha1_to_hex(obj->sha1));
+			printf("              to %7s %s\n",
+			       refs->item->type, sha1_to_hex(refs->item->sha1));
+		}
 
-	return n;
-}
+		/* Don't bother with tag reachability. */
+		if (obj->type == tag_type)
+			continue;
 
-static struct revision *add_relationship(struct revision *rev, unsigned char *needs)
-{
-	struct revision *parent_rev = lookup_rev(needs);
-	struct parent **pp = &rev->parent, *p;
+		if (show_unreachable && !(obj->flags & REACHABLE)) {
+			if (obj->attached_deltas)
+				printf("foreign delta reference %s\n", 
+				       sha1_to_hex(obj->sha1));
+			else
+				printf("unreachable %s %s\n",
+				       obj->type, sha1_to_hex(obj->sha1));
+			continue;
+		}
 
-	while ((p = *pp) != NULL) {
-		if (p->parent == parent_rev)
-			return parent_rev;
-		pp = &p->next;
+		if (!obj->used) {
+			printf("dangling %s %s\n", obj->type, 
+			       sha1_to_hex(obj->sha1));
+		}
 	}
-
-	p = malloc(sizeof(*p));
-	p->parent = parent_rev;
-	p->next = NULL;
-	*pp = p;
-	return parent_rev;
 }
 
-static void mark_reachable(struct revision *rev)
+/*
+ * The entries in a tree are ordered in the _path_ order,
+ * which means that a directory entry is ordered by adding
+ * a slash to the end of it.
+ *
+ * So a directory called "a" is ordered _after_ a file
+ * called "a.c", because "a/" sorts after "a.c".
+ */
+#define TREE_UNORDERED (-1)
+#define TREE_HAS_DUPS  (-2)
+
+static int verify_ordered(struct tree_entry_list *a, struct tree_entry_list *b)
 {
-	struct parent *p = rev->parent;
-
-	/* If we've been here already, don't bother */
-	if (rev->flags & REACHABLE)
-		return;
-	rev->flags |= REACHABLE | USED;
-	while (p) {
-		mark_reachable(p->parent);
-		p = p->next;
-	}
+	int len1 = strlen(a->name);
+	int len2 = strlen(b->name);
+	int len = len1 < len2 ? len1 : len2;
+	unsigned char c1, c2;
+	int cmp;
+
+	cmp = memcmp(a->name, b->name, len);
+	if (cmp < 0)
+		return 0;
+	if (cmp > 0)
+		return TREE_UNORDERED;
+
+	/*
+	 * Ok, the first <len> characters are the same.
+	 * Now we need to order the next one, but turn
+	 * a '\0' into a '/' for a directory entry.
+	 */
+	c1 = a->name[len];
+	c2 = b->name[len];
+	if (!c1 && !c2)
+		/*
+		 * git-write-tree used to write out a nonsense tree that has
+		 * entries with the same name, one blob and one tree.  Make
+		 * sure we do not have duplicate entries.
+		 */
+		return TREE_HAS_DUPS;
+	if (!c1 && a->directory)
+		c1 = '/';
+	if (!c2 && b->directory)
+		c2 = '/';
+	return c1 < c2 ? 0 : TREE_UNORDERED;
 }
 
-static void check_connectivity(void)
+static int fsck_tree(struct tree *item)
 {
-	int i;
-
-	if (head_supplied)
-		mark_reachable(lookup_rev(head_sha1));
-
-	/* Look up all the requirements, warn about missing objects.. */
-	for (i = 0; i < nr_revs; i++) {
-		struct revision *rev = revs[i];
-
-		if (show_unreachable && !(rev->flags & REACHABLE)) {
-			printf("unreachable %s\n", sha1_to_hex(rev->sha1));
-			continue;
-		}
-
-		switch (rev->flags & (SEEN | USED)) {
-		case 0:
-			printf("bad %s\n", sha1_to_hex(rev->sha1));
+	int has_full_path = 0;
+	struct tree_entry_list *entry, *last;
+
+	last = NULL;
+	for (entry = item->entries; entry; entry = entry->next) {
+		if (strchr(entry->name, '/'))
+			has_full_path = 1;
+
+		switch (entry->mode) {
+		/*
+		 * Standard modes.. 
+		 */
+		case S_IFREG | 0755:
+		case S_IFREG | 0644:
+		case S_IFLNK:
+		case S_IFDIR:
 			break;
-		case USED:
-			printf("missing %s\n", sha1_to_hex(rev->sha1));
-			break;
-		case SEEN:
-			printf("dangling %s\n", sha1_to_hex(rev->sha1));
+		/*
+		 * This is nonstandard, but we had a few of these
+		 * early on when we honored the full set of mode
+		 * bits..
+		 */
+		case S_IFREG | 0664:
 			break;
+		default:
+			printf("tree %s has entry %o %s\n",
+				sha1_to_hex(item->object.sha1),
+				entry->mode, entry->name);
 		}
-	}
-}
 
-static void mark_needs_sha1(unsigned char *parent, const char * tag, unsigned char *child)
-{
-	struct revision * child_rev = add_relationship(lookup_rev(parent), child);
-	child_rev->flags |= USED;
-}
+		if (last) {
+			switch (verify_ordered(last, entry)) {
+			case TREE_UNORDERED:
+				fprintf(stderr, "tree %s not ordered\n",
+					sha1_to_hex(item->object.sha1));
+				return -1;
+			case TREE_HAS_DUPS:
+				fprintf(stderr, "tree %s has duplicate entries for '%s'\n",
+					sha1_to_hex(item->object.sha1),
+					entry->name);
+				return -1;
+			default:
+				break;
+			}
+		}
 
-static int mark_sha1_seen(unsigned char *sha1, char *tag)
-{
-	struct revision *rev = lookup_rev(sha1);
+		last = entry;
+	}
+
+	if (has_full_path) {
+		fprintf(stderr, "warning: git-fsck-cache: tree %s "
+			"has full pathnames in it\n", 
+			sha1_to_hex(item->object.sha1));
+	}
 
-	rev->flags |= SEEN;
 	return 0;
 }
 
-static int fsck_tree(unsigned char *sha1, void *data, unsigned long size)
+static int fsck_commit(struct commit *commit)
 {
-	int warn_old_tree = 1;
-
-	while (size) {
-		int len = 1+strlen(data);
-		unsigned char *file_sha1 = data + len;
-		char *path = strchr(data, ' ');
-		unsigned int mode;
-		if (size < len + 20 || !path || sscanf(data, "%o", &mode) != 1)
-			return -1;
-
-		/* Warn about trees that don't do the recursive thing.. */
-		if (warn_old_tree && strchr(path, '/')) {
-			fprintf(stderr, "warning: fsck-cache: tree %s has full pathnames in it\n", sha1_to_hex(sha1));
-			warn_old_tree = 0;
-		}
-
-		data += len + 20;
-		size -= len + 20;
-		mark_needs_sha1(sha1, S_ISDIR(mode) ? "tree" : "blob", file_sha1);
-	}
+	free(commit->buffer);
+	commit->buffer = NULL;
+	if (!commit->tree)
+		return -1;
+	if (!commit->parents && show_root)
+		printf("root %s\n", sha1_to_hex(commit->object.sha1));
+	if (!commit->date)
+		printf("bad commit date in %s\n", 
+		       sha1_to_hex(commit->object.sha1));
 	return 0;
 }
 
-static int fsck_commit(unsigned char *sha1, void *data, unsigned long size)
+static int fsck_tag(struct tag *tag)
 {
-	int parents;
-	unsigned char tree_sha1[20];
-	unsigned char parent_sha1[20];
+	struct object *tagged = tag->tagged;
 
-	if (memcmp(data, "tree ", 5))
+	if (!tagged) {
+		printf("bad object in tag %s\n", sha1_to_hex(tag->object.sha1));
 		return -1;
-	if (get_sha1_hex(data + 5, tree_sha1) < 0)
-		return -1;
-	mark_needs_sha1(sha1, "tree", tree_sha1);
-	data += 5 + 40 + 1;	/* "tree " + <hex sha1> + '\n' */
-	parents = 0;
-	while (!memcmp(data, "parent ", 7)) {
-		if (get_sha1_hex(data + 7, parent_sha1) < 0)
-			return -1;
-		mark_needs_sha1(sha1, "commit", parent_sha1);
-		data += 7 + 40 + 1; 	/* "parent " + <hex sha1> + '\n' */
-		parents++;
 	}
-	if (!parents)
-		printf("root %s\n", sha1_to_hex(sha1));
+	if (!show_tags)
+		return 0;
+
+	printf("tagged %s %s", tagged->type, sha1_to_hex(tagged->sha1));
+	printf(" (%s) in %s\n", tag->tag, sha1_to_hex(tag->object.sha1));
 	return 0;
 }
 
-static int fsck_entry(unsigned char *sha1, char *tag, void *data, unsigned long size)
+static int fsck_sha1(unsigned char *sha1)
 {
-	if (!strcmp(tag, "blob")) {
-		/* Nothing to check */;
-	} else if (!strcmp(tag, "tree")) {
-		if (fsck_tree(sha1, data, size) < 0)
-			return -1;
-	} else if (!strcmp(tag, "commit")) {
-		if (fsck_commit(sha1, data, size) < 0)
-			return -1;
-	} else
+	struct object *obj = parse_object(sha1);
+	if (!obj)
 		return -1;
-	return mark_sha1_seen(sha1, tag);
+	if (obj->type == blob_type)
+		return 0;
+	if (obj->type == tree_type)
+		return fsck_tree((struct tree *) obj);
+	if (obj->type == commit_type)
+		return fsck_commit((struct commit *) obj);
+	if (obj->type == tag_type)
+		return fsck_tag((struct tag *) obj);
+	if (!obj->type && obj->delta)
+		return 0;
+	return -1;
 }
 
-static int fsck_name(char *hex)
-{
+/*
+ * This is the sorting chunk size: make it reasonably
+ * big so that we can sort well..
+ */
+#define MAX_SHA1_ENTRIES (1024)
+
+struct sha1_entry {
+	unsigned long ino;
 	unsigned char sha1[20];
-	if (!get_sha1_hex(hex, sha1)) {
-		unsigned long mapsize;
-		void *map = map_sha1_file(sha1, &mapsize);
-		if (map) {
-			char type[100];
-			unsigned long size;
-			void *buffer = NULL;
-			if (!check_sha1_signature(sha1, map, mapsize))
-				buffer = unpack_sha1_file(map, mapsize, type, &size);
-			munmap(map, mapsize);
-			if (buffer && !fsck_entry(sha1, type, buffer, size))
-				return 0;
-		}
+};
+
+static struct {
+	unsigned long nr;
+	struct sha1_entry *entry[MAX_SHA1_ENTRIES];
+} sha1_list;
+
+static int ino_compare(const void *_a, const void *_b)
+{
+	const struct sha1_entry *a = _a, *b = _b;
+	unsigned long ino1 = a->ino, ino2 = b->ino;
+	return ino1 < ino2 ? -1 : ino1 > ino2 ? 1 : 0;
+}
+
+static void fsck_sha1_list(void)
+{
+	int i, nr = sha1_list.nr;
+
+	qsort(sha1_list.entry, nr, sizeof(struct sha1_entry *), ino_compare);
+	for (i = 0; i < nr; i++) {
+		struct sha1_entry *entry = sha1_list.entry[i];
+		unsigned char *sha1 = entry->sha1;
+
+		sha1_list.entry[i] = NULL;
+		if (fsck_sha1(sha1) < 0)
+			fprintf(stderr, "bad sha1 entry '%s'\n", sha1_to_hex(sha1));
+		free(entry);
 	}
-	return -1;
+	sha1_list.nr = 0;
+}
+
+static void add_sha1_list(unsigned char *sha1, unsigned long ino)
+{
+	struct sha1_entry *entry = xmalloc(sizeof(*entry));
+	int nr;
+
+	entry->ino = ino;
+	memcpy(entry->sha1, sha1, 20);
+	nr = sha1_list.nr;
+	if (nr == MAX_SHA1_ENTRIES) {
+		fsck_sha1_list();
+		nr = 0;
+	}
+	sha1_list.entry[nr] = entry;
+	sha1_list.nr = ++nr;
 }
 
 static int fsck_dir(int i, char *path)
@@ -258,6 +316,7 @@ static int fsck_dir(int i, char *path)
 
 	while ((de = readdir(dir)) != NULL) {
 		char name[100];
+		unsigned char sha1[20];
 		int len = strlen(de->d_name);
 
 		switch (len) {
@@ -271,8 +330,10 @@ static int fsck_dir(int i, char *path)
 		case 38:
 			sprintf(name, "%02x", i);
 			memcpy(name+2, de->d_name, len+1);
-			if (!fsck_name(name))
-				continue;
+			if (get_sha1_hex(name, sha1) < 0)
+				break;
+			add_sha1_list(sha1, de->d_ino);
+			continue;
 		}
 		fprintf(stderr, "bad sha1 file: %s/%s\n", path, de->d_name);
 	}
@@ -280,31 +341,164 @@ static int fsck_dir(int i, char *path)
 	return 0;
 }
 
+static int read_sha1_reference(const char *path)
+{
+	char hexname[60];
+	unsigned char sha1[20];
+	int fd = open(path, O_RDONLY), len;
+	struct object *obj;
+
+	if (fd < 0)
+		return -1;
+
+	len = read(fd, hexname, sizeof(hexname));
+	close(fd);
+	if (len < 40)
+		return -1;
+
+	if (get_sha1_hex(hexname, sha1) < 0)
+		return -1;
+
+	obj = lookup_object(sha1);
+	if (!obj)
+		return error("%s: invalid sha1 pointer %.40s", path, hexname);
+
+	obj->used = 1;
+	mark_reachable(obj, REACHABLE);
+	return 0;
+}
+
+static int find_file_objects(const char *base, const char *name)
+{
+	int baselen = strlen(base);
+	int namelen = strlen(name);
+	char *path = xmalloc(baselen + namelen + 2);
+	struct stat st;
+
+	memcpy(path, base, baselen);
+	path[baselen] = '/';
+	memcpy(path + baselen + 1, name, namelen+1);
+	if (stat(path, &st) < 0)
+		return 0;
+
+	/*
+	 * Recurse into directories
+	 */
+	if (S_ISDIR(st.st_mode)) {
+		int count = 0;
+		DIR *dir = opendir(path);
+		if (dir) {
+			struct dirent *de;
+			while ((de = readdir(dir)) != NULL) {
+				if (de->d_name[0] == '.')
+					continue;
+				count += find_file_objects(path, de->d_name);
+			}
+			closedir(dir);
+		}
+		return count;
+	}
+	if (S_ISREG(st.st_mode))
+		return read_sha1_reference(path) == 0;
+	return 0;
+}
+
+static void get_default_heads(void)
+{
+	char *git_dir = gitenv(GIT_DIR_ENVIRONMENT) ? : DEFAULT_GIT_DIR_ENVIRONMENT;
+	int count = find_file_objects(git_dir, "refs");
+	if (!count)
+		die("No default references");
+}
+
 int main(int argc, char **argv)
 {
-	int i;
+	int i, heads;
 	char *sha1_dir;
 
 	for (i = 1; i < argc; i++) {
-		if (!strcmp(argv[i], "--unreachable")) {
+		const char *arg = argv[i];
+
+		if (!strcmp(arg, "--unreachable")) {
 			show_unreachable = 1;
 			continue;
 		}
-		if (!get_sha1_hex(argv[i], head_sha1)) {
-			head_supplied = 1;
+		if (!strcmp(arg, "--tags")) {
+			show_tags = 1;
 			continue;
 		}
-		usage("fsck-cache [[--unreachable] <head-sha1>]");
+		if (!strcmp(arg, "--root")) {
+			show_root = 1;
+			continue;
+		}
+		if (!strcmp(arg, "--delta-depth")) {
+			show_max_delta_depth = 1;
+			continue;
+		}
+		if (!strcmp(arg, "--cache")) {
+			keep_cache_objects = 1;
+			continue;
+		}
+		if (*arg == '-')
+			usage("git-fsck-cache [--tags] [[--unreachable] [--cache] <head-sha1>*]");
 	}
-	if (show_unreachable && !head_supplied)
-		usage("unable to do reachability checks without a head");
 
-	sha1_dir = getenv(DB_ENVIRONMENT) ? : DEFAULT_DB_ENVIRONMENT;
+	sha1_dir = get_object_directory();
 	for (i = 0; i < 256; i++) {
 		static char dir[4096];
 		sprintf(dir, "%s/%02x", sha1_dir, i);
 		fsck_dir(i, dir);
 	}
+	fsck_sha1_list();
+
+	expand_deltas();
+
+	heads = 0;
+	for (i = 1; i < argc; i++) {
+		const char *arg = argv[i]; 
+
+		if (*arg == '-')
+			continue;
+
+		if (!get_sha1(arg, head_sha1)) {
+			struct object *obj = lookup_object(head_sha1);
+
+			/* Error is printed by lookup_object(). */
+			if (!obj)
+				continue;
+
+			obj->used = 1;
+			mark_reachable(obj, REACHABLE);
+			heads++;
+			continue;
+		}
+		error("expected sha1, got %s", arg);
+	}
+
+	/*
+	 * If we've not been given any explicit head information, do the
+	 * default ones from .git/refs. We also consider the index file
+	 * in this case (ie this implies --cache).
+	 */
+	if (!heads) {
+		get_default_heads();
+		keep_cache_objects = 1;
+	}
+
+	if (keep_cache_objects) {
+		int i;
+		read_cache();
+		for (i = 0; i < active_nr; i++) {
+			struct blob *blob = lookup_blob(active_cache[i]->sha1);
+			struct object *obj;
+			if (!blob)
+				continue;
+			obj = &blob->object;
+			obj->used = 1;
+			mark_reachable(obj, REACHABLE);
+		}
+	}
+
 	check_connectivity();
 	return 0;
 }