#include "cache.h"
-#include "commit.h"
-#include "tree.h"
+#include "object.h"
#include "blob.h"
-#include "tag.h"
-#include "refs.h"
-#include "pack.h"
-#include "cache-tree.h"
+#include "tree.h"
#include "tree-walk.h"
+#include "commit.h"
+#include "tag.h"
+#include "fsck.h"
-#define REACHABLE 0x0001
-#define SEEN 0x0002
-
-static int show_root;
-static int show_tags;
-static int show_unreachable;
-static int check_full;
-static int check_strict;
-static int keep_cache_objects;
-static unsigned char head_sha1[20];
-
-#ifdef NO_D_INO_IN_DIRENT
-#define SORT_DIRENT 0
-#define DIRENT_SORT_HINT(de) 0
-#else
-#define SORT_DIRENT 1
-#define DIRENT_SORT_HINT(de) ((de)->d_ino)
-#endif
-
-static void objreport(struct object *obj, const char *severity,
- const char *err, va_list params)
-{
- fprintf(stderr, "%s in %s %s: ",
- severity, typename(obj->type), sha1_to_hex(obj->sha1));
- vfprintf(stderr, err, params);
- fputs("\n", stderr);
-}
-
-static int objerror(struct object *obj, const char *err, ...)
-{
- va_list params;
- va_start(params, err);
- objreport(obj, "error", err, params);
- va_end(params);
- return -1;
-}
-
-static int objwarning(struct object *obj, const char *err, ...)
+static int fsck_walk_tree(struct tree *tree, fsck_walk_func walk, void *data)
{
- va_list params;
- va_start(params, err);
- objreport(obj, "warning", err, params);
- va_end(params);
- return -1;
-}
+ struct tree_desc desc;
+ struct name_entry entry;
+ int res = 0;
-/*
- * Check a single reachable object
- */
-static void check_reachable_object(struct object *obj)
-{
- const struct object_refs *refs;
+ if (parse_tree(tree))
+ return -1;
- /*
- * We obviously want the object to be parsed,
- * except if it was in a pack-file and we didn't
- * do a full fsck
- */
- if (!obj->parsed) {
- if (has_sha1_file(obj->sha1))
- return; /* it is in pack - forget about it */
- printf("missing %s %s\n", typename(obj->type), sha1_to_hex(obj->sha1));
- return;
- }
+ init_tree_desc(&desc, tree->buffer, tree->size);
+ while (tree_entry(&desc, &entry)) {
+ int result;
- /*
- * Check that everything that we try to reference is also good.
- */
- refs = lookup_object_refs(obj);
- if (refs) {
- unsigned j;
- for (j = 0; j < refs->count; j++) {
- struct object *ref = refs->ref[j];
- if (ref->parsed ||
- (has_sha1_file(ref->sha1)))
- continue;
- printf("broken link from %7s %s\n",
- typename(obj->type), sha1_to_hex(obj->sha1));
- printf(" to %7s %s\n",
- typename(ref->type), sha1_to_hex(ref->sha1));
+ if (S_ISGITLINK(entry.mode))
+ continue;
+ if (S_ISDIR(entry.mode))
+ result = walk(&lookup_tree(entry.sha1)->object, OBJ_TREE, data);
+ else if (S_ISREG(entry.mode) || S_ISLNK(entry.mode))
+ result = walk(&lookup_blob(entry.sha1)->object, OBJ_BLOB, data);
+ else {
+ result = error("in tree %s: entry %s has bad mode %.6o\n",
+ sha1_to_hex(tree->object.sha1), entry.path, entry.mode);
}
+ if (result < 0)
+ return result;
+ if (!res)
+ res = result;
}
+ return res;
}
-/*
- * Check a single unreachable object
- */
-static void check_unreachable_object(struct object *obj)
+static int fsck_walk_commit(struct commit *commit, fsck_walk_func walk, void *data)
{
- /*
- * Missing unreachable object? Ignore it. It's not like
- * we miss it (since it can't be reached), nor do we want
- * to complain about it being unreachable (since it does
- * not exist).
- */
- if (!obj->parsed)
- return;
-
- /*
- * Unreachable object that exists? Show it if asked to,
- * since this is something that is prunable.
- */
- if (show_unreachable) {
- printf("unreachable %s %s\n", typename(obj->type), sha1_to_hex(obj->sha1));
- return;
- }
-
- /*
- * "!used" means that nothing at all points to it, including
- * other unreacahble objects. In other words, it's the "tip"
- * of some set of unreachable objects, usually a commit that
- * got dropped.
- *
- * Such starting points are more interesting than some random
- * set of unreachable objects, so we show them even if the user
- * hasn't asked for _all_ unreachable objects. If you have
- * deleted a branch by mistake, this is a prime candidate to
- * start looking at, for example.
- */
- if (!obj->used) {
- printf("dangling %s %s\n", typename(obj->type),
- sha1_to_hex(obj->sha1));
- return;
+ struct commit_list *parents;
+ int res;
+ int result;
+
+ if (parse_commit(commit))
+ return -1;
+
+ result = walk((struct object *)commit->tree, OBJ_TREE, data);
+ if (result < 0)
+ return result;
+ res = result;
+
+ parents = commit->parents;
+ while (parents) {
+ result = walk((struct object *)parents->item, OBJ_COMMIT, data);
+ if (result < 0)
+ return result;
+ if (!res)
+ res = result;
+ parents = parents->next;
}
-
- /*
- * Otherwise? It's there, it's unreachable, and some other unreachable
- * object points to it. Ignore it - it's not interesting, and we showed
- * all the interesting cases above.
- */
+ return res;
}
-static void check_object(struct object *obj)
+static int fsck_walk_tag(struct tag *tag, fsck_walk_func walk, void *data)
{
- if (obj->flags & REACHABLE)
- check_reachable_object(obj);
- else
- check_unreachable_object(obj);
+ if (parse_tag(tag))
+ return -1;
+ return walk(tag->tagged, OBJ_ANY, data);
}
-static void check_connectivity(void)
+int fsck_walk(struct object *obj, fsck_walk_func walk, void *data)
{
- int i, max;
-
- /* Look up all the requirements, warn about missing objects.. */
- max = get_max_object_index();
- for (i = 0; i < max; i++) {
- struct object *obj = get_indexed_object(i);
-
- if (obj)
- check_object(obj);
+ if (!obj)
+ return -1;
+ switch (obj->type) {
+ case OBJ_BLOB:
+ return 0;
+ case OBJ_TREE:
+ return fsck_walk_tree((struct tree *)obj, walk, data);
+ case OBJ_COMMIT:
+ return fsck_walk_commit((struct commit *)obj, walk, data);
+ case OBJ_TAG:
+ return fsck_walk_tag((struct tag *)obj, walk, data);
+ default:
+ error("Unknown object type for %s", sha1_to_hex(obj->sha1));
+ return -1;
}
}
return c1 < c2 ? 0 : TREE_UNORDERED;
}
-static int fsck_tree(struct tree *item)
+static int fsck_tree(struct tree *item, int strict, fsck_error error_func)
{
int retval;
int has_full_path = 0;
+ int has_empty_name = 0;
int has_zero_pad = 0;
int has_bad_modes = 0;
int has_dup_entries = 0;
const char *o_name;
const unsigned char *o_sha1;
- desc.buf = item->buffer;
- desc.size = item->size;
+ init_tree_desc(&desc, item->buffer, item->size);
o_mode = 0;
o_name = NULL;
o_sha1 = NULL;
+
while (desc.size) {
unsigned mode;
const char *name;
if (strchr(name, '/'))
has_full_path = 1;
- has_zero_pad |= *(char *)desc.buf == '0';
+ if (!*name)
+ has_empty_name = 1;
+ has_zero_pad |= *(char *)desc.buffer == '0';
update_tree_entry(&desc);
switch (mode) {
case S_IFREG | 0644:
case S_IFLNK:
case S_IFDIR:
+ case S_IFGITLINK:
break;
/*
* This is nonstandard, but we had a few of these
* bits..
*/
case S_IFREG | 0664:
- if (!check_strict)
+ if (!strict)
break;
default:
has_bad_modes = 1;
o_name = name;
o_sha1 = sha1;
}
- free(item->buffer);
- item->buffer = NULL;
retval = 0;
- if (has_full_path) {
- objwarning(&item->object, "contains full pathnames");
- }
- if (has_zero_pad) {
- objwarning(&item->object, "contains zero-padded file modes");
- }
- if (has_bad_modes) {
- objwarning(&item->object, "contains bad file modes");
- }
- if (has_dup_entries) {
- retval = objerror(&item->object, "contains duplicate file entries");
- }
- if (not_properly_sorted) {
- retval = objerror(&item->object, "not properly sorted");
- }
+ if (has_full_path)
+ retval += error_func(&item->object, FSCK_WARN, "contains full pathnames");
+ if (has_empty_name)
+ retval += error_func(&item->object, FSCK_WARN, "contains empty pathname");
+ if (has_zero_pad)
+ retval += error_func(&item->object, FSCK_WARN, "contains zero-padded file modes");
+ if (has_bad_modes)
+ retval += error_func(&item->object, FSCK_WARN, "contains bad file modes");
+ if (has_dup_entries)
+ retval += error_func(&item->object, FSCK_ERROR, "contains duplicate file entries");
+ if (not_properly_sorted)
+ retval += error_func(&item->object, FSCK_ERROR, "not properly sorted");
return retval;
}
-static int fsck_commit(struct commit *commit)
+static int fsck_commit(struct commit *commit, fsck_error error_func)
{
char *buffer = commit->buffer;
unsigned char tree_sha1[20], sha1[20];
+ struct commit_graft *graft;
+ int parents = 0;
+
+ if (!commit->date)
+ return error_func(&commit->object, FSCK_ERROR, "invalid author/committer line");
if (memcmp(buffer, "tree ", 5))
- return objerror(&commit->object, "invalid format - expected 'tree' line");
+ return error_func(&commit->object, FSCK_ERROR, "invalid format - expected 'tree' line");
if (get_sha1_hex(buffer+5, tree_sha1) || buffer[45] != '\n')
- return objerror(&commit->object, "invalid 'tree' line format - bad sha1");
+ return error_func(&commit->object, FSCK_ERROR, "invalid 'tree' line format - bad sha1");
buffer += 46;
while (!memcmp(buffer, "parent ", 7)) {
if (get_sha1_hex(buffer+7, sha1) || buffer[47] != '\n')
- return objerror(&commit->object, "invalid 'parent' line format - bad sha1");
+ return error_func(&commit->object, FSCK_ERROR, "invalid 'parent' line format - bad sha1");
buffer += 48;
+ parents++;
+ }
+ graft = lookup_commit_graft(commit->object.sha1);
+ if (graft) {
+ struct commit_list *p = commit->parents;
+ parents = 0;
+ while (p) {
+ p = p->next;
+ parents++;
+ }
+ if (graft->nr_parent == -1 && !parents)
+ ; /* shallow commit */
+ else if (graft->nr_parent != parents)
+ return error_func(&commit->object, FSCK_ERROR, "graft objects missing");
+ } else {
+ struct commit_list *p = commit->parents;
+ while (p && parents) {
+ p = p->next;
+ parents--;
+ }
+ if (p || parents)
+ return error_func(&commit->object, FSCK_ERROR, "parent objects missing");
}
if (memcmp(buffer, "author ", 7))
- return objerror(&commit->object, "invalid format - expected 'author' line");
- free(commit->buffer);
- commit->buffer = NULL;
+ return error_func(&commit->object, FSCK_ERROR, "invalid format - expected 'author' line");
if (!commit->tree)
- return objerror(&commit->object, "could not load commit's tree %s", tree_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(commit->object.sha1));
+ return error_func(&commit->object, FSCK_ERROR, "could not load commit's tree %s", sha1_to_hex(tree_sha1));
+
return 0;
}
-static int fsck_tag(struct tag *tag)
+static int fsck_tag(struct tag *tag, fsck_error error_func)
{
struct object *tagged = tag->tagged;
- if (!tagged) {
- return objerror(&tag->object, "could not load tagged object");
- }
- if (!show_tags)
- return 0;
-
- printf("tagged %s %s", typename(tagged->type), sha1_to_hex(tagged->sha1));
- printf(" (%s) in %s\n", tag->tag, sha1_to_hex(tag->object.sha1));
+ if (!tagged)
+ return error_func(&tag->object, FSCK_ERROR, "could not load tagged object");
return 0;
}
-static int fsck_sha1(unsigned char *sha1)
+int fsck_object(struct object *obj, int strict, fsck_error error_func)
{
- struct object *obj = parse_object(sha1);
if (!obj)
- return error("%s: object corrupt or missing", sha1_to_hex(sha1));
- if (obj->flags & SEEN)
- return 0;
- obj->flags |= SEEN;
+ return error_func(obj, FSCK_ERROR, "no valid object to fsck");
+
if (obj->type == OBJ_BLOB)
return 0;
if (obj->type == OBJ_TREE)
- return fsck_tree((struct tree *) obj);
+ return fsck_tree((struct tree *) obj, strict, error_func);
if (obj->type == OBJ_COMMIT)
- return fsck_commit((struct commit *) obj);
+ return fsck_commit((struct commit *) obj, error_func);
if (obj->type == OBJ_TAG)
- return fsck_tag((struct tag *) obj);
- /* By now, parse_object() would've returned NULL instead. */
- return objerror(obj, "unknown type '%d' (internal fsck error)", obj->type);
-}
+ return fsck_tag((struct tag *) obj, error_func);
-/*
- * 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];
-};
-
-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;
-
- if (SORT_DIRENT)
- 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;
- fsck_sha1(sha1);
- free(entry);
- }
- sha1_list.nr = 0;
+ return error_func(obj, FSCK_ERROR, "unknown type '%d' (internal fsck error)",
+ obj->type);
}
-static void add_sha1_list(unsigned char *sha1, unsigned long ino)
+int fsck_error_function(struct object *obj, int type, const char *fmt, ...)
{
- struct sha1_entry *entry = xmalloc(sizeof(*entry));
- int nr;
-
- entry->ino = ino;
- hashcpy(entry->sha1, sha1);
- nr = sha1_list.nr;
- if (nr == MAX_SHA1_ENTRIES) {
- fsck_sha1_list();
- nr = 0;
+ va_list ap;
+ int len;
+ struct strbuf sb = STRBUF_INIT;
+
+ strbuf_addf(&sb, "object %s:", obj->sha1?sha1_to_hex(obj->sha1):"(null)");
+
+ va_start(ap, fmt);
+ len = vsnprintf(sb.buf + sb.len, strbuf_avail(&sb), fmt, ap);
+ va_end(ap);
+
+ if (len < 0)
+ len = 0;
+ if (len >= strbuf_avail(&sb)) {
+ strbuf_grow(&sb, len + 2);
+ va_start(ap, fmt);
+ len = vsnprintf(sb.buf + sb.len, strbuf_avail(&sb), fmt, ap);
+ va_end(ap);
+ if (len >= strbuf_avail(&sb))
+ die("this should not happen, your snprintf is broken");
}
- sha1_list.entry[nr] = entry;
- sha1_list.nr = ++nr;
-}
-
-static void fsck_dir(int i, char *path)
-{
- DIR *dir = opendir(path);
- struct dirent *de;
-
- if (!dir)
- return;
-
- while ((de = readdir(dir)) != NULL) {
- char name[100];
- unsigned char sha1[20];
- int len = strlen(de->d_name);
- switch (len) {
- case 2:
- if (de->d_name[1] != '.')
- break;
- case 1:
- if (de->d_name[0] != '.')
- break;
- continue;
- case 38:
- sprintf(name, "%02x", i);
- memcpy(name+2, de->d_name, len+1);
- if (get_sha1_hex(name, sha1) < 0)
- break;
- add_sha1_list(sha1, DIRENT_SORT_HINT(de));
- continue;
- }
- fprintf(stderr, "bad sha1 file: %s/%s\n", path, de->d_name);
- }
- closedir(dir);
-}
-
-static int default_refs;
-
-static int fsck_handle_reflog_ent(unsigned char *osha1, unsigned char *nsha1,
- const char *email, unsigned long timestamp, int tz,
- const char *message, void *cb_data)
-{
- struct object *obj;
-
- if (!is_null_sha1(osha1)) {
- obj = lookup_object(osha1);
- if (obj) {
- obj->used = 1;
- mark_reachable(obj, REACHABLE);
- }
- }
- obj = lookup_object(nsha1);
- if (obj) {
- obj->used = 1;
- mark_reachable(obj, REACHABLE);
- }
- return 0;
-}
-
-static int fsck_handle_ref(const char *refname, const unsigned char *sha1, int flag, void *cb_data)
-{
- struct object *obj;
-
- obj = lookup_object(sha1);
- if (!obj) {
- if (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);
-
- for_each_reflog_ent(refname, fsck_handle_reflog_ent, NULL);
-
- return 0;
-}
-
-static void get_default_heads(void)
-{
- for_each_ref(fsck_handle_ref, NULL);
-
- /*
- * Not having any default heads isn't really fatal, but
- * it does mean that "--unreachable" no longer makes any
- * sense (since in this case everything will obviously
- * be unreachable by definition.
- *
- * Showing dangling objects is valid, though (as those
- * dangling objects are likely lost heads).
- *
- * So we just print a warning about it, and clear the
- * "show_unreachable" flag.
- */
- if (!default_refs) {
- error("No default references");
- show_unreachable = 0;
- }
-}
-
-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)
-{
- unsigned char sha1[20];
- int flag;
- const char *head_points_at = resolve_ref("HEAD", sha1, 1, &flag);
-
- if (!head_points_at || !(flag & REF_ISSYMREF))
- return error("HEAD is not a symbolic ref");
- if (strncmp(head_points_at, "refs/heads/", 11))
- return error("HEAD points to something strange (%s)",
- head_points_at);
- if (is_null_sha1(sha1))
- return error("HEAD: not a valid git pointer");
- return 0;
-}
-
-static int fsck_cache_tree(struct cache_tree *it)
-{
- int i;
- int err = 0;
-
- if (0 <= it->entry_count) {
- struct object *obj = parse_object(it->sha1);
- if (!obj) {
- error("%s: invalid sha1 pointer in cache-tree",
- sha1_to_hex(it->sha1));
- return 1;
- }
- mark_reachable(obj, REACHABLE);
- obj->used = 1;
- if (obj->type != OBJ_TREE)
- err |= objerror(obj, "non-tree in cache-tree");
- }
- for (i = 0; i < it->subtree_nr; i++)
- err |= fsck_cache_tree(it->down[i]->cache_tree);
- return err;
-}
-
-int main(int argc, char **argv)
-{
- int i, heads;
-
- track_object_refs = 1;
- setup_git_directory();
-
- 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, "--full")) {
- check_full = 1;
- continue;
- }
- if (!strcmp(arg, "--strict")) {
- check_strict = 1;
- continue;
- }
- if (*arg == '-')
- usage("git-fsck [--tags] [--root] [[--unreachable] [--cache] [--full] [--strict] <head-sha1>*]");
- }
-
- 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);
- fsck_sha1(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("invalid parameter: 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);
- }
- if (active_cache_tree)
- fsck_cache_tree(active_cache_tree);
- }
-
- check_connectivity();
- return 0;
+ error(sb.buf);
+ strbuf_release(&sb);
+ return 1;
}