path: root/builtin-fsck.c

#include "cache.h"
#include "commit.h"
#include "tree.h"
#include "blob.h"
#include "tag.h"
#include "refs.h"
#include "pack.h"
#include "cache-tree.h"
#include "tree-walk.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, ...)
{
	va_list params;
	va_start(params, err);
	objreport(obj, "warning", err, params);
	va_end(params);
	return -1;
}

/*
 * Check a single reachable object
 */
static void check_reachable_object(struct object *obj)
{
	const struct object_refs *refs;

	/*
	 * 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;
	}

	/*
	 * 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));
		}
	}
}

/*
 * Check a single unreachable object
 */
static void check_unreachable_object(struct object *obj)
{
	/*
	 * 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;
	}

	/*
	 * 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.
	 */
}

static void check_object(struct object *obj)
{
	if (obj->flags & REACHABLE)
		check_reachable_object(obj);
	else
		check_unreachable_object(obj);
}

static void check_connectivity(void)
{
	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);
	}
}

/*
 * 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(unsigned mode1, const char *name1, unsigned mode2, const char *name2)
{
	int len1 = strlen(name1);
	int len2 = strlen(name2);
	int len = len1 < len2 ? len1 : len2;
	unsigned char c1, c2;
	int cmp;

	cmp = memcmp(name1, name2, 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 = name1[len];
	c2 = name2[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 && S_ISDIR(mode1))
		c1 = '/';
	if (!c2 && S_ISDIR(mode2))
		c2 = '/';
	return c1 < c2 ? 0 : TREE_UNORDERED;
}

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_desc desc;
	unsigned o_mode;
	const char *o_name;
	const unsigned char *o_sha1;

	desc.buf = item->buffer;
	desc.size = item->size;

	o_mode = 0;
	o_name = NULL;
	o_sha1 = NULL;
	while (desc.size) {
		unsigned mode;
		const char *name;
		const unsigned char *sha1;

		sha1 = tree_entry_extract(&desc, &name, &mode);

		if (strchr(name, '/'))
			has_full_path = 1;
		has_zero_pad |= *(char *)desc.buf == '0';
		update_tree_entry(&desc);

		switch (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;
		}

		if (o_name) {
			switch (verify_ordered(o_mode, o_name, mode, name)) {
			case TREE_UNORDERED:
				not_properly_sorted = 1;
				break;
			case TREE_HAS_DUPS:
				has_dup_entries = 1;
				break;
			default:
				break;
			}
		}

		o_mode = mode;
		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");
	}
	return retval;
}

static int fsck_commit(