-#include "cache.h"
-
#include <sys/types.h>
#include <dirent.h>
-struct needs {
- unsigned char parent[20];
- unsigned char needs[20];
- char tag[10];
-};
-
-struct seen {
- unsigned char sha1[20];
- char tag[10];
- unsigned needed;
-};
-
-static struct needs *needs;
-static struct seen *seen;
-
-static int nr_seen, alloc_seen, nr_needs, alloc_needs;
+#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 check_strict = 0;
+static int keep_cache_objects = 0;
+static unsigned char head_sha1[20];
-/*
- * These two functions build up a graph in memory about
- * what objects we've referenced, and found, and types..
- */
-static int compare_seen(const void *s1, const void *s2)
+static void check_connectivity(void)
{
- return memcmp(s1, s2, 20);
-}
+ int i;
-static int lookup_seen(unsigned char *sha1, char *tag)
-{
- int first = 0, last = nr_seen;
+ /* 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 (!standalone && has_sha1_file(obj->sha1))
+ ; /* it is in pack */
+ else
+ printf("missing %s %s\n",
+ obj->type, sha1_to_hex(obj->sha1));
+ continue;
+ }
- while (last > first) {
- int next = (last + first) / 2;
- struct seen *s = seen + next;
- int cmp = memcmp(sha1, s->sha1, 20);
+ 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 (cmp < 0) {
- last = next;
+ if (show_unreachable && !(obj->flags & REACHABLE)) {
+ printf("unreachable %s %s\n",
+ obj->type, sha1_to_hex(obj->sha1));
continue;
}
- if (cmp > 0) {
- first = next+1;
- continue;
+
+ if (!obj->used) {
+ printf("dangling %s %s\n", obj->type,
+ sha1_to_hex(obj->sha1));
}
- if (strcmp(tag, s->tag))
- break;
- s->needed++;
- return 1;
}
- return 0;
}
-static void check_connectivity(void)
+/*
+ * 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)
{
- int i;
+ 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;
+}
- /* Sort the "seen" tags for quicker lookup */
- qsort(seen, nr_seen, sizeof(struct seen), compare_seen);
+static int fsck_tree(struct tree *item)
+{
+ int retval;
+ int has_full_path = 0;
+ int has_zero_pad = 0;
+ int has_bad_modes = 0;
+ int has_dup_entries = 0;
+ int not_properly_sorted = 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;
+ has_zero_pad |= entry->zeropad;
+
+ 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:
+ if (!check_strict)
+ break;
+ default:
+ has_bad_modes = 1;
+ }
- /* Look up all the requirements, warn about missing objects.. */
- for (i = 0; i < nr_needs; i++) {
- struct needs *n = needs + i;
- char hex[60];
+ if (last) {
+ switch (verify_ordered(last, entry)) {
+ case TREE_UNORDERED:
+ not_properly_sorted = 1;
+ break;
+ case TREE_HAS_DUPS:
+ has_dup_entries = 1;
+ break;
+ default:
+ break;
+ }
+ }
- if (lookup_seen(n->needs, n->tag))
- continue;
- strcpy(hex, sha1_to_hex(n->parent));
+ last = entry;
}
- /* Tell the user about things not referenced.. */
- for (i = 0; i < nr_seen; i++) {
- struct seen *s = seen + i;
-
- if (s->needed)
- continue;
- printf("unreferenced %s: %s\n", s->tag, sha1_to_hex(s->sha1));
+ retval = 0;
+ if (has_full_path) {
+ fprintf(stderr, "warning: git-fsck-cache: tree %s "
+ "has full pathnames in it\n",
+ sha1_to_hex(item->object.sha1));
}
-}
-
-static void mark_needs_sha1(unsigned char *parent, const char * tag, unsigned char *child)
-{
- struct needs *n;
-
- if (nr_needs == alloc_needs) {
- alloc_needs = alloc_nr(alloc_needs);
- needs = realloc(needs, alloc_needs*sizeof(struct needs));
+ if (has_zero_pad) {
+ fprintf(stderr, "warning: git-fsck-cache: tree %s "
+ "has zero-padded file modes in it\n",
+ sha1_to_hex(item->object.sha1));
+ }
+ if (has_bad_modes) {
+ fprintf(stderr, "warning: git-fsck-cache: tree %s "
+ "has bad file modes in it\n",
+ sha1_to_hex(item->object.sha1));
+ }
+ if (has_dup_entries) {
+ fprintf(stderr, "error: git-fsck-cache: tree %s "
+ "has duplicate file entries\n",
+ sha1_to_hex(item->object.sha1));
+ retval = -1;
}
- n = needs + nr_needs;
- nr_needs++;
- memcpy(n->parent, parent, 20);
- memcpy(n->needs, child, 20);
- strncpy(n->tag, tag, sizeof(n->tag));
+ if (not_properly_sorted) {
+ fprintf(stderr, "error: git-fsck-cache: tree %s "
+ "is not properly sorted\n",
+ sha1_to_hex(item->object.sha1));
+ retval = -1;
+ }
+ return retval;
}
-static int mark_sha1_seen(unsigned char *sha1, char *tag)
+static int fsck_commit(struct commit *commit)
{
- struct seen *s;
-
- if (nr_seen == alloc_seen) {
- alloc_seen = alloc_nr(alloc_seen);
- seen = realloc(seen, alloc_seen*sizeof(struct seen));
- }
- s = seen + nr_seen;
- memset(s, 0, sizeof(s));
- nr_seen++;
- memcpy(s->sha1, sha1, 20);
- strncpy(s->tag, tag, sizeof(s->tag));
-
- return 0;
-}
+ char *buffer = commit->buffer;
+ unsigned char sha1[20];
-static int fsck_tree(unsigned char *sha1, void *data, unsigned long size)
-{
- 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)
+ if (memcmp(buffer, "tree ", 5))
+ return -1;
+ if (get_sha1_hex(buffer+5, sha1) || buffer[45] != '\n')
+ return -1;
+ buffer += 46;
+ while (!memcmp(buffer, "parent ", 7)) {
+ if (get_sha1_hex(buffer+7, sha1) || buffer[47] != '\n')
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);
+ buffer += 48;
}
+ if (memcmp(buffer, "author ", 7))
+ return -1;
+ 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);
+ 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)
struct dirent *de;
if (!dir) {
- fprintf(stderr, "missing sha1 directory '%s'", path);
- return -1;
+ return error("missing sha1 directory '%s'", path);
}
while ((de = readdir(dir)) != NULL) {
char name[100];
+ unsigned char sha1[20];
int len = strlen(de->d_name);
switch (len) {
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);
}
return 0;
}
-int main(int argc, char **argv)
+static int default_refs = 0;
+
+static int fsck_handle_ref(const char *refname, const unsigned char *sha1)
{
- int i;
- char *sha1_dir;
+ struct object *obj;
- if (argc != 1)
- usage("fsck-cache");
- sha1_dir = getenv(DB_ENVIRONMENT) ? : DEFAULT_DB_ENVIRONMENT;
+ 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", sha1_dir, i);
+ 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;
+
+ git_dir = gitenv(GIT_DIR_ENVIRONMENT);
+ if (!git_dir) git_dir = 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;
+
+ for (i = 1; i < argc; i++) {
+ const char *arg = argv[i];
+
+ if (!strcmp(arg, "--unreachable")) {
+ show_unreachable = 1;
+ continue;
+ }
+ if (!strcmp(arg, "--tags")) {
+ 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 (!strcmp(arg, "--strict")) {
+ check_strict = 1;
+ continue;
+ }
+ if (*arg == '-')
+ usage("git-fsck-cache [--tags] [--root] [[--unreachable] [--cache] [--standalone | --full] [--strict] <head-sha1>*]");
+ }
+
+ if (standalone && check_full)
+ die("Only one of --standalone or --full can be used.");
+ if (standalone)
+ putenv("GIT_ALTERNATE_OBJECT_DIRECTORIES=");
+
+ fsck_head_link();
+ fsck_object_dir(get_object_directory());
+ if (check_full) {
+ struct alternate_object_database *alt;
+ struct packed_git *p;
+ prepare_alt_odb();
+ for (alt = alt_odb_list; alt; alt = alt->next) {
+ char namebuf[PATH_MAX];
+ int namelen = alt->name - alt->base;
+ memcpy(namebuf, alt->base, namelen);
+ namebuf[namelen - 1] = 0;
+ fsck_object_dir(namebuf);
+ }
+ 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;
+ 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;
}