#include "exec_cmd.h"
static const char index_pack_usage[] =
-"git index-pack [-v] [-o <index-file>] [
--keep | --keep=<msg> ] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";
+"git index-pack [-v] [-o <index-file>] [
--keep | --keep=<msg>] [--verify] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";
struct object_entry
{
return data;
}
-static int find_delta(const union delta_base *base)
+static int compare_delta_bases(const union delta_base *base1,
+ const union delta_base *base2,
+ enum object_type type1,
+ enum object_type type2)
+{
+ int cmp = type1 - type2;
+ if (cmp)
+ return cmp;
+ return memcmp(base1, base2, UNION_BASE_SZ);
+}
+
+static int find_delta(const union delta_base *base, enum object_type type)
{
int first = 0, last = nr_deltas;
struct delta_entry *delta = &deltas[next];
int cmp;
- cmp = memcmp(base, &delta->base, UNION_BASE_SZ);
+ cmp = compare_delta_bases(base, &delta->base,
+ type, objects[delta->obj_no].type);
if (!cmp)
return next;
if (cmp < 0) {
}
static void find_delta_children(const union delta_base *base,
- int *first_index, int *last_index)
+ int *first_index, int *last_index,
+ enum object_type type)
{
- int first = find_delta(base);
+ int first = find_delta(base, type);
int last = first;
int end = nr_deltas - 1;
union delta_base base_spec;
hashcpy(base_spec.sha1, base->obj->idx.sha1);
- find_delta_children(&base_spec, &ref_first, &ref_last);
+ find_delta_children(&base_spec,
+ &ref_first, &ref_last, OBJ_REF_DELTA);
memset(&base_spec, 0, sizeof(base_spec));
base_spec.offset = base->obj->idx.offset;
- find_delta_children(&base_spec, &ofs_first, &ofs_last);
+ find_delta_children(&base_spec,
+ &ofs_first, &ofs_last, OBJ_OFS_DELTA);
}
if (ref_last == -1 && ofs_last == -1) {
for (i = ref_first; i <= ref_last; i++) {
struct object_entry *child = objects + deltas[i].obj_no;
- if (child->real_type == OBJ_REF_DELTA) {
- struct base_data result;
- resolve_delta(child, base, &result);
- if (i == ref_last && ofs_last == -1)
- free_base_data(base);
- find_unresolved_deltas(&result, base);
- }
+ struct base_data result;
+
+ assert(child->real_type == OBJ_REF_DELTA);
+ resolve_delta(child, base, &result);
+ if (i == ref_last && ofs_last == -1)
+ free_base_data(base);
+ find_unresolved_deltas(&result, base);
}
for (i = ofs_first; i <= ofs_last; i++) {
struct object_entry *child = objects + deltas[i].obj_no;
- if (child->real_type == OBJ_OFS_DELTA) {
- struct base_data result;
- resolve_delta(child, base, &result);
- if (i == ofs_last)
- free_base_data(base);
- find_unresolved_deltas(&result, base);
- }
+ struct base_data result;
+
+ assert(child->real_type == OBJ_OFS_DELTA);
+ resolve_delta(child, base, &result);
+ if (i == ofs_last)
+ free_base_data(base);
+ find_unresolved_deltas(&result, base);
}
unlink_base_data(base);
{
const struct delta_entry *delta_a = a;
const struct delta_entry *delta_b = b;
- return memcmp(&delta_a->base, &delta_b->base, UNION_BASE_SZ);
+
+ /* group by type (ref vs ofs) and then by value (sha-1 or offset) */
+ return compare_delta_bases(&delta_a->base, &delta_b->base,
+ objects[delta_a->obj_no].type,
+ objects[delta_b->obj_no].type);
}
/* Parse all objects and return the pack content SHA1 hash */
static int git_index_pack_config(const char *k, const char *v, void *cb)
{
+ struct pack_idx_option *opts = cb;
+
if (!strcmp(k, "pack.indexversion")) {
- pack_idx_default_version = git_config_int(k, v);
- if (pack_idx_default_version > 2)
- die("bad pack.indexversion=%"PRIu32,
- pack_idx_default_version);
+ opts->version = git_config_int(k, v);
+ if (opts->version > 2)
+ die("bad pack.indexversion=%"PRIu32, opts->version);
return 0;
}
return git_default_config(k, v, cb);
}
+static int cmp_uint32(const void *a_, const void *b_)
+{
+ uint32_t a = *((uint32_t *)a_);
+ uint32_t b = *((uint32_t *)b_);
+
+ return (a < b) ? -1 : (a != b);
+}
+
+static void read_v2_anomalous_offsets(struct packed_git *p,
+ struct pack_idx_option *opts)
+{
+ const uint32_t *idx1, *idx2;
+ uint32_t i;
+
+ /* The address of the 4-byte offset table */
+ idx1 = (((const uint32_t *)p->index_data)
+ + 2 /* 8-byte header */
+ + 256 /* fan out */
+ + 5 * p->num_objects /* 20-byte SHA-1 table */
+ + p->num_objects /* CRC32 table */
+ );
+
+ /* The address of the 8-byte offset table */
+ idx2 = idx1 + p->num_objects;
+
+ for (i = 0; i < p->num_objects; i++) {
+ uint32_t off = ntohl(idx1[i]);
+ if (!(off & 0x80000000))
+ continue;
+ off = off & 0x7fffffff;
+ if (idx2[off * 2])
+ continue;
+ /*
+ * The real offset is ntohl(idx2[off * 2]) in high 4
+ * octets, and ntohl(idx2[off * 2 + 1]) in low 4
+ * octets. But idx2[off * 2] is Zero!!!
+ */
+ ALLOC_GROW(opts->anomaly, opts->anomaly_nr + 1, opts->anomaly_alloc);
+ opts->anomaly[opts->anomaly_nr++] = ntohl(idx2[off * 2 + 1]);
+ }
+
+ if (1 < opts->anomaly_nr)
+ qsort(opts->anomaly, opts->anomaly_nr, sizeof(uint32_t), cmp_uint32);
+}
+
+static void read_idx_option(struct pack_idx_option *opts, const char *pack_name)
+{
+ struct packed_git *p = add_packed_git(pack_name, strlen(pack_name), 1);
+
+ if (!p)
+ die("Cannot open existing pack file '%s'", pack_name);
+ if (open_pack_index(p))
+ die("Cannot open existing pack idx file for '%s'", pack_name);
+
+ /* Read the attributes from the existing idx file */
+ opts->version = p->index_version;
+
+ if (opts->version == 2)
+ read_v2_anomalous_offsets(p, opts);
+
+ /*
+ * Get rid of the idx file as we do not need it anymore.
+ * NEEDSWORK: extract this bit from free_pack_by_name() in
+ * sha1_file.c, perhaps? It shouldn't matter very much as we
+ * know we haven't installed this pack (hence we never have
+ * read anything from it).
+ */
+ close_pack_index(p);
+ free(p);
+}
+
int cmd_index_pack(int argc, const char **argv, const char *prefix)
{
- int i, fix_thin_pack = 0;
+ int i, fix_thin_pack = 0, verify = 0;
const char *curr_pack, *curr_index;
const char *index_name = NULL, *pack_name = NULL;
const char *keep_name = NULL, *keep_msg = NULL;
char *index_name_buf = NULL, *keep_name_buf = NULL;
struct pack_idx_entry **idx_objects;
+ struct pack_idx_option opts;
unsigned char pack_sha1[20];
if (argc == 2 && !strcmp(argv[1], "-h"))
read_replace_refs = 0;
- git_config(git_index_pack_config, NULL);
+ reset_pack_idx_option(&opts);
+ git_config(git_index_pack_config, &opts);
if (prefix && chdir(prefix))
die("Cannot come back to cwd");
fix_thin_pack = 1;
} else if (!strcmp(arg, "--strict")) {
strict = 1;
+ } else if (!strcmp(arg, "--verify")) {
+ verify = 1;
} else if (!strcmp(arg, "--keep")) {
keep_msg = "";
} else if (!prefixcmp(arg, "--keep=")) {
index_name = argv[++i];
} else if (!prefixcmp(arg, "--index-version=")) {
char *c;
- pack_idx_default_version = strtoul(arg + 16, &c, 10);
- if (pack_idx_default_version > 2)
+ opts.version = strtoul(arg + 16, &c, 10);
+ if (opts.version > 2)
die("bad %s", arg);
if (*c == ',')
- pack_idx_off32_limit = strtoul(c+1, &c, 0);
- if (*c || pack_idx_off32_limit & 0x80000000)
+ opts.off32_limit = strtoul(c+1, &c, 0);
+ if (*c || opts.off32_limit & 0x80000000)
die("bad %s", arg);
} else
usage(index_pack_usage);
strcpy(keep_name_buf + len - 5, ".keep");
keep_name = keep_name_buf;
}
+ if (verify) {
+ if (!index_name)
+ die("--verify with no packfile name given");
+ read_idx_option(&opts, index_name);
+ opts.flags |= WRITE_IDX_VERIFY;
+ }
curr_pack = open_pack_file(pack_name);
parse_pack_header();
idx_objects = xmalloc((nr_objects) * sizeof(struct pack_idx_entry *));
for (i = 0; i < nr_objects; i++)
idx_objects[i] = &objects[i].idx;
- curr_index = write_idx_file(index_name, idx_objects, nr_objects, pack_sha1);
+ curr_index = write_idx_file(index_name, idx_objects, nr_objects, &opts, pack_sha1);
free(idx_objects);
- final(pack_name, curr_pack,
- index_name, curr_index,
- keep_name, keep_msg,
- pack_sha1);
+ if (!verify)
+ final(pack_name, curr_pack,
+ index_name, curr_index,
+ keep_name, keep_msg,
+ pack_sha1);
+ else
+ close(input_fd);
free(objects);
free(index_name_buf);
free(keep_name_buf);