X-Git-Url: https://git.tokkee.org/?a=blobdiff_plain;f=fsck-cache.c;h=48be6553a3b1d9b7e4b9a3382646bf753e15a4f3;hb=454fbbcde3beb5eb36a4554e5b7074f8d501a6f1;hp=a83266ce2f3bd5b3ed8dae1e720825b9d9a4aadb;hpb=889262eacf43a7a8810c288c00732b9134d79630;p=git.git

diff --git a/fsck-cache.c b/fsck-cache.c
index a83266ce2..48be6553a 100644
--- a/fsck-cache.c
+++ b/fsck-cache.c
@@ -1,16 +1,22 @@
-#include "cache.h"
-
 #include <sys/types.h>
 #include <dirent.h>
 
+#include "cache.h"
 #include "commit.h"
 #include "tree.h"
 #include "blob.h"
+#include "tag.h"
+#include "refs.h"
+#include "pack.h"
 
 #define REACHABLE 0x0001
 
+static int show_root = 0;
 static int show_tags = 0;
 static int show_unreachable = 0;
+static int standalone = 0;
+static int check_full = 0;
+static int keep_cache_objects = 0; 
 static unsigned char head_sha1[20];
 
 static void check_connectivity(void)
@@ -20,16 +26,33 @@ static void check_connectivity(void)
 	/* 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 (show_unreachable && !(obj->flags & REACHABLE)) {
-			printf("unreachable %s %s\n", obj->type, sha1_to_hex(obj->sha1));
+		if (!obj->parsed) {
+			if (!standalone && has_sha1_file(obj->sha1))
+				; /* it is in pack */
+			else
+				printf("missing %s %s\n",
+				       obj->type, sha1_to_hex(obj->sha1));
 			continue;
 		}
 
-		if (!obj->parsed) {
-			printf("missing %s %s\n", obj->type, 
-			       sha1_to_hex(obj->sha1));
+		for (refs = obj->refs; refs; refs = refs->next) {
+			if (refs->item->parsed ||
+			    (!standalone && has_sha1_file(refs->item->sha1)))
+				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));
 		}
+
+		if (show_unreachable && !(obj->flags & REACHABLE)) {
+			printf("unreachable %s %s\n",
+			       obj->type, sha1_to_hex(obj->sha1));
+			continue;
+		}
+
 		if (!obj->used) {
 			printf("dangling %s %s\n", obj->type, 
 			       sha1_to_hex(obj->sha1));
@@ -37,121 +60,212 @@ static void check_connectivity(void)
 	}
 }
 
-static int fsck_tree(unsigned char *sha1, void *data, unsigned long size)
+/*
+ * 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 tree *item = lookup_tree(sha1);
-	if (parse_tree(item))
-		return -1;
-	if (item->has_full_path) {
-		fprintf(stderr, "warning: fsck-cache: tree %s "
-			"has full pathnames in it\n", sha1_to_hex(sha1));
+	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 int fsck_tree(struct tree *item)
+{
+	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;
+		/*
+		 * 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);
+		}
+
+		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;
+			}
+		}
+
+		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));
+	}
+
 	return 0;
 }
 
-static int fsck_commit(unsigned char *sha1, void *data, unsigned long size)
+static int fsck_commit(struct commit *commit)
 {
-	struct commit *commit = lookup_commit(sha1);
-	if (parse_commit(commit))
-		return -1;
+	free(commit->buffer);
+	commit->buffer = NULL;
 	if (!commit->tree)
 		return -1;
-	if (!commit->parents)
-		printf("root %s\n", sha1_to_hex(sha1));
+	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(sha1));
+		printf("bad commit date in %s\n", 
+		       sha1_to_hex(commit->object.sha1));
 	return 0;
 }
 
-static int fsck_blob(unsigned char *sha1, void *data, unsigned long size)
+static int fsck_tag(struct tag *tag)
 {
-	struct blob *blob = lookup_blob(sha1);
-	blob->object.parsed = 1;
-	return 0;
-}
+	struct object *tagged = tag->tagged;
 
-static int fsck_tag(unsigned char *sha1, void *data, unsigned long size)
-{
-	int typelen, taglen;
-	unsigned char object[20];
-	char object_hex[60];
-	const char *type_line, *tag_line, *sig_line;
-
-	if (size < 64)
-		return -1;
-	if (memcmp("object ", data, 7) || get_sha1_hex(data + 7, object))
+	if (!tagged) {
+		printf("bad object in tag %s\n", sha1_to_hex(tag->object.sha1));
 		return -1;
+	}
+	if (!show_tags)
+		return 0;
 
-	type_line = data + 48;
-	if (memcmp("\ntype ", type_line-1, 6))
-		return -1;
+	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;
+}
 
-	tag_line = strchr(type_line, '\n');
-	if (!tag_line || memcmp("tag ", ++tag_line, 4))
+static int fsck_sha1(unsigned char *sha1)
+{
+	struct object *obj = parse_object(sha1);
+	if (!obj)
 		return -1;
+	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);
+	return -1;
+}
 
-	sig_line = strchr(tag_line, '\n');
-	if (!sig_line)
-		return -1;
-	sig_line++;
+/*
+ * This is the sorting chunk size: make it reasonably
+ * big so that we can sort well..
+ */
+#define MAX_SHA1_ENTRIES (1024)
 
-	typelen = tag_line - type_line - strlen("type \n");
-	if (typelen >= 20)
-		return -1;
-	taglen = sig_line - tag_line - strlen("tag \n");
+struct sha1_entry {
+	unsigned long ino;
+	unsigned char sha1[20];
+};
 
-	if (!show_tags)
-		return 0;
+static struct {
+	unsigned long nr;
+	struct sha1_entry *entry[MAX_SHA1_ENTRIES];
+} sha1_list;
 
-	strcpy(object_hex, sha1_to_hex(object));
-	printf("tagged %.*s %s (%.*s) in %s\n",
-		typelen, type_line + 5,
-		object_hex,
-		taglen, tag_line + 4,
-		sha1_to_hex(sha1));
-	return 0;
+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 int fsck_entry(unsigned char *sha1, char *tag, void *data, 
-		      unsigned long size)
+static void fsck_sha1_list(void)
 {
-	if (!strcmp(tag, "blob")) {
-		if (fsck_blob(sha1, data, size) < 0)
-			return -1;
-	} 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 if (!strcmp(tag, "tag")) {
-		if (fsck_tag(sha1, data, size) < 0)
-			return -1;
-	} else
-		return -1;
-	return 0;
+	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);
+	}
+	sha1_list.nr = 0;
 }
 
-static int fsck_name(char *hex)
+static void add_sha1_list(unsigned char *sha1, 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 = unpack_sha1_file(map, mapsize, type, &size);
-			if (!buffer)
-				return -1;
-			if (check_sha1_signature(sha1, buffer, size, type) < 0)
-				printf("sha1 mismatch %s\n", sha1_to_hex(sha1));
-			munmap(map, mapsize);
-			if (!fsck_entry(sha1, type, buffer, size))
-				return 0;
-		}
+	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;
 	}
-	return -1;
+	sha1_list.entry[nr] = entry;
+	sha1_list.nr = ++nr;
 }
 
 static int fsck_dir(int i, char *path)
@@ -165,6 +279,7 @@ 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) {
@@ -178,8 +293,10 @@ 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);
 	}
@@ -187,10 +304,74 @@ static int fsck_dir(int i, char *path)
 	return 0;
 }
 
+static int default_refs = 0;
+
+static int fsck_handle_ref(const char *refname, const unsigned char *sha1)
+{
+	struct object *obj;
+
+	obj = lookup_object(sha1);
+	if (!obj) {
+		if (!standalone && has_sha1_file(sha1)) {
+			default_refs++;
+			return 0; /* it is in a pack */
+		}
+		error("%s: invalid sha1 pointer %s", refname, sha1_to_hex(sha1));
+		/* We'll continue with the rest despite the error.. */
+		return 0;
+	}
+	default_refs++;
+	obj->used = 1;
+	mark_reachable(obj, REACHABLE);
+	return 0;
+}
+
+static void get_default_heads(void)
+{
+	for_each_ref(fsck_handle_ref);
+	if (!default_refs)
+		die("No default references");
+}
+
+static void fsck_object_dir(const char *path)
+{
+	int i;
+	for (i = 0; i < 256; i++) {
+		static char dir[4096];
+		sprintf(dir, "%s/%02x", path, i);
+		fsck_dir(i, dir);
+	}
+	fsck_sha1_list();
+}
+
+static int fsck_head_link(void)
+{
+	int fd, count;
+	char hex[40];
+	unsigned char sha1[20];
+	static char path[PATH_MAX], link[PATH_MAX];
+	const char *git_dir = gitenv(GIT_DIR_ENVIRONMENT) ? : DEFAULT_GIT_DIR_ENVIRONMENT;
+
+	snprintf(path, sizeof(path), "%s/HEAD", git_dir);
+	if (readlink(path, link, sizeof(link)) < 0)
+		return error("HEAD is not a symlink");
+	if (strncmp("refs/heads/", link, 11))
+		return error("HEAD points to something strange (%s)", link);
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return error("HEAD: %s", strerror(errno));
+	count = read(fd, hex, sizeof(hex));
+	close(fd);
+	if (count < 0)
+		return error("HEAD: %s", strerror(errno));
+	if (count < 40 || get_sha1_hex(hex, sha1))
+		return error("HEAD: not a valid git pointer");
+	return 0;
+}
+
 int main(int argc, char **argv)
 {
 	int i, heads;
-	char *sha1_dir;
 
 	for (i = 1; i < argc; i++) {
 		const char *arg = argv[i];
@@ -203,15 +384,57 @@ int main(int argc, char **argv)
 			show_tags = 1;
 			continue;
 		}
+		if (!strcmp(arg, "--root")) {
+			show_root = 1;
+			continue;
+		}
+		if (!strcmp(arg, "--cache")) {
+			keep_cache_objects = 1;
+			continue;
+		}
+		if (!strcmp(arg, "--standalone")) {
+			standalone = 1;
+			continue;
+		}
+		if (!strcmp(arg, "--full")) {
+			check_full = 1;
+			continue;
+		}
 		if (*arg == '-')
-			usage("fsck-cache [--tags] [[--unreachable] <head-sha1>*]");
+			usage("git-fsck-cache [--tags] [[--unreachable] [--cache] [--standalone | --full] <head-sha1>*]");
 	}
 
-	sha1_dir = getenv(DB_ENVIRONMENT) ? : DEFAULT_DB_ENVIRONMENT;
-	for (i = 0; i < 256; i++) {
-		static char dir[4096];
-		sprintf(dir, "%s/%02x", sha1_dir, i);
-		fsck_dir(i, dir);
+	if (standalone && check_full)
+		die("Only one of --standalone or --full can be used.");
+	if (standalone)
+		unsetenv("GIT_ALTERNATE_OBJECT_DIRECTORIES");
+
+	fsck_head_link();
+	fsck_object_dir(get_object_directory());
+	if (check_full) {
+		int j;
+		struct packed_git *p;
+		prepare_alt_odb();
+		for (j = 0; alt_odb[j].base; j++) {
+			alt_odb[j].name[-1] = 0; /* was slash */
+			fsck_object_dir(alt_odb[j].base);
+			alt_odb[j].name[-1] = '/';
+		}
+		prepare_packed_git();
+		for (p = packed_git; p; p = p->next)
+			/* verify gives error messages itself */
+			verify_pack(p, 0);
+
+		for (p = packed_git; p; p = p->next) {
+			int num = num_packed_objects(p);
+			for (i = 0; i < num; i++) {
+				unsigned char sha1[20];
+				nth_packed_object_sha1(p, i, sha1);
+				if (fsck_sha1(sha1) < 0)
+					fprintf(stderr, "bad sha1 entry '%s'\n", sha1_to_hex(sha1));
+
+			}
+		}
 	}
 
 	heads = 0;
@@ -221,8 +444,13 @@ int main(int argc, char **argv)
 		if (*arg == '-')
 			continue;
 
-		if (!get_sha1_hex(arg, head_sha1)) {
-			struct object *obj = &lookup_commit(head_sha1)->object;
+		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++;
@@ -231,12 +459,28 @@ int main(int argc, char **argv)
 		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) {
-		if (show_unreachable) {
-			fprintf(stderr, "unable to do reachability without a head\n");
-			show_unreachable = 0; 
+		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);
 		}
-		fprintf(stderr, "expect dangling commits - potential heads - due to lack of head information\n");
 	}
 
 	check_connectivity();