![[tokkee]](http://tokkee.org/images/avatar.png){kind=avatar}
summary | shortlog | log | commit | commitdiff | tree
raw | patch | inline | side by side (parent: 377d027)
raw | patch | inline | side by side (parent: 377d027)
| author | Linus Torvalds <torvalds@linux-foundation.org> | |
| Fri, 22 Jan 2010 15:55:19 +0000 (07:55 -0800) | ||
| committer | Junio C Hamano <gitster@pobox.com> | |
| Fri, 22 Jan 2010 18:10:27 +0000 (10:10 -0800) |
This required some fairly trivial packfile function 'const' cleanup,
since the builtin commands get a const char *argv[] array.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
since the builtin commands get a const char *argv[] array.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
| Makefile | patch | blob | history | |
| builtin-index-pack.c | [new file with mode: 0644] | patch | blob |
| builtin-pack-objects.c | patch | blob | history | |
| builtin.h | patch | blob | history | |
| git.c | patch | blob | history | |
| index-pack.c | [deleted file] | patch | blob | history |
| pack-write.c | patch | blob | history | |
| pack.h | patch | blob | history |
diff --git a/Makefile b/Makefile
index 33f987088645f974e6ac50fa48fe4cc5b7b26514..c0dbee2ae40823b4e8433891a704f94eaaf6d525 100644 (file)
--- a/Makefile
+++ b/Makefile
PROGRAMS += $(EXTRA_PROGRAMS)
PROGRAMS += git-fast-import$X
PROGRAMS += git-imap-send$X
-PROGRAMS += git-index-pack$X
PROGRAMS += git-shell$X
PROGRAMS += git-show-index$X
PROGRAMS += git-upload-pack$X
BUILTIN_OBJS += builtin-grep.o
BUILTIN_OBJS += builtin-hash-object.o
BUILTIN_OBJS += builtin-help.o
+BUILTIN_OBJS += builtin-index-pack.o
BUILTIN_OBJS += builtin-init-db.o
BUILTIN_OBJS += builtin-log.o
BUILTIN_OBJS += builtin-ls-files.o
diff --git a/builtin-index-pack.c b/builtin-index-pack.c
--- /dev/null
+++ b/builtin-index-pack.c
@@ -0,0 +1,1045 @@
+#include "cache.h"
+#include "delta.h"
+#include "pack.h"
+#include "csum-file.h"
+#include "blob.h"
+#include "commit.h"
+#include "tag.h"
+#include "tree.h"
+#include "progress.h"
+#include "fsck.h"
+#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>] }";
+
+struct object_entry
+{
+ struct pack_idx_entry idx;
+ unsigned long size;
+ unsigned int hdr_size;
+ enum object_type type;
+ enum object_type real_type;
+};
+
+union delta_base {
+ unsigned char sha1[20];
+ off_t offset;
+};
+
+struct base_data {
+ struct base_data *base;
+ struct base_data *child;
+ struct object_entry *obj;
+ void *data;
+ unsigned long size;
+};
+
+/*
+ * Even if sizeof(union delta_base) == 24 on 64-bit archs, we really want
+ * to memcmp() only the first 20 bytes.
+ */
+#define UNION_BASE_SZ 20
+
+#define FLAG_LINK (1u<<20)
+#define FLAG_CHECKED (1u<<21)
+
+struct delta_entry
+{
+ union delta_base base;
+ int obj_no;
+};
+
+static struct object_entry *objects;
+static struct delta_entry *deltas;
+static struct base_data *base_cache;
+static size_t base_cache_used;
+static int nr_objects;
+static int nr_deltas;
+static int nr_resolved_deltas;
+
+static int from_stdin;
+static int strict;
+static int verbose;
+
+static struct progress *progress;
+
+/* We always read in 4kB chunks. */
+static unsigned char input_buffer[4096];
+static unsigned int input_offset, input_len;
+static off_t consumed_bytes;
+static git_SHA_CTX input_ctx;
+static uint32_t input_crc32;
+static int input_fd, output_fd, pack_fd;
+
+static int mark_link(struct object *obj, int type, void *data)
+{
+ if (!obj)
+ return -1;
+
+ if (type != OBJ_ANY && obj->type != type)
+ die("object type mismatch at %s", sha1_to_hex(obj->sha1));
+
+ obj->flags |= FLAG_LINK;
+ return 0;
+}
+
+/* The content of each linked object must have been checked
+ or it must be already present in the object database */
+static void check_object(struct object *obj)
+{
+ if (!obj)
+ return;
+
+ if (!(obj->flags & FLAG_LINK))
+ return;
+
+ if (!(obj->flags & FLAG_CHECKED)) {
+ unsigned long size;
+ int type = sha1_object_info(obj->sha1, &size);
+ if (type != obj->type || type <= 0)
+ die("object of unexpected type");
+ obj->flags |= FLAG_CHECKED;
+ return;
+ }
+}
+
+static void check_objects(void)
+{
+ unsigned i, max;
+
+ max = get_max_object_index();
+ for (i = 0; i < max; i++)
+ check_object(get_indexed_object(i));
+}
+
+
+/* Discard current buffer used content. */
+static void flush(void)
+{
+ if (input_offset) {
+ if (output_fd >= 0)
+ write_or_die(output_fd, input_buffer, input_offset);
+ git_SHA1_Update(&input_ctx, input_buffer, input_offset);
+ memmove(input_buffer, input_buffer + input_offset, input_len);
+ input_offset = 0;
+ }
+}
+
+/*
+ * Make sure at least "min" bytes are available in the buffer, and
+ * return the pointer to the buffer.
+ */
+static void *fill(int min)
+{
+ if (min <= input_len)
+ return input_buffer + input_offset;
+ if (min > sizeof(input_buffer))
+ die("cannot fill %d bytes", min);
+ flush();
+ do {
+ ssize_t ret = xread(input_fd, input_buffer + input_len,
+ sizeof(input_buffer) - input_len);
+ if (ret <= 0) {
+ if (!ret)
+ die("early EOF");
+ die_errno("read error on input");
+ }
+ input_len += ret;
+ if (from_stdin)
+ display_throughput(progress, consumed_bytes + input_len);
+ } while (input_len < min);
+ return input_buffer;
+}
+
+static void use(int bytes)
+{
+ if (bytes > input_len)
+ die("used more bytes than were available");
+ input_crc32 = crc32(input_crc32, input_buffer + input_offset, bytes);
+ input_len -= bytes;
+ input_offset += bytes;
+
+ /* make sure off_t is sufficiently large not to wrap */
+ if (consumed_bytes > consumed_bytes + bytes)
+ die("pack too large for current definition of off_t");
+ consumed_bytes += bytes;
+}
+
+static const char *open_pack_file(const char *pack_name)
+{
+ if (from_stdin) {
+ input_fd = 0;
+ if (!pack_name) {
+ static char tmpfile[PATH_MAX];
+ output_fd = odb_mkstemp(tmpfile, sizeof(tmpfile),
+ "pack/tmp_pack_XXXXXX");
+ pack_name = xstrdup(tmpfile);
+ } else
+ output_fd = open(pack_name, O_CREAT|O_EXCL|O_RDWR, 0600);
+ if (output_fd < 0)
+ die_errno("unable to create '%s'", pack_name);
+ pack_fd = output_fd;
+ } else {
+ input_fd = open(pack_name, O_RDONLY);
+ if (input_fd < 0)
+ die_errno("cannot open packfile '%s'", pack_name);
+ output_fd = -1;
+ pack_fd = input_fd;
+ }
+ git_SHA1_Init(&input_ctx);
+ return pack_name;
+}
+
+static void parse_pack_header(void)
+{
+ struct pack_header *hdr = fill(sizeof(struct pack_header));
+
+ /* Header consistency check */
+ if (hdr->hdr_signature != htonl(PACK_SIGNATURE))
+ die("pack signature mismatch");
+ if (!pack_version_ok(hdr->hdr_version))
+ die("pack version %"PRIu32" unsupported",
+ ntohl(hdr->hdr_version));
+
+ nr_objects = ntohl(hdr->hdr_entries);
+ use(sizeof(struct pack_header));
+}
+
+static NORETURN void bad_object(unsigned long offset, const char *format,
+ ...) __attribute__((format (printf, 2, 3)));
+
+static void bad_object(unsigned long offset, const char *format, ...)
+{
+ va_list params;
+ char buf[1024];
+
+ va_start(params, format);
+ vsnprintf(buf, sizeof(buf), format, params);
+ va_end(params);
+ die("pack has bad object at offset %lu: %s", offset, buf);
+}
+
+static void free_base_data(struct base_data *c)
+{
+ if (c->data) {
+ free(c->data);
+ c->data = NULL;
+ base_cache_used -= c->size;
+ }
+}
+
+static void prune_base_data(struct base_data *retain)
+{
+ struct base_data *b;
+ for (b = base_cache;
+ base_cache_used > delta_base_cache_limit && b;
+ b = b->child) {
+ if (b->data && b != retain)
+ free_base_data(b);
+ }
+}
+
+static void link_base_data(struct base_data *base, struct base_data *c)
+{
+ if (base)
+ base->child = c;
+ else
+ base_cache = c;
+
+ c->base = base;
+ c->child = NULL;
+ if (c->data)
+ base_cache_used += c->size;
+ prune_base_data(c);
+}
+
+static void unlink_base_data(struct base_data *c)
+{
+ struct base_data *base = c->base;
+ if (base)
+ base->child = NULL;
+ else
+ base_cache = NULL;
+ free_base_data(c);
+}
+
+static void *unpack_entry_data(unsigned long offset, unsigned long size)
+{
+ z_stream stream;
+ void *buf = xmalloc(size);
+
+ memset(&stream, 0, sizeof(stream));
+ stream.next_out = buf;
+ stream.avail_out = size;
+ stream.next_in = fill(1);
+ stream.avail_in = input_len;
+ git_inflate_init(&stream);
+
+ for (;;) {
+ int ret = git_inflate(&stream, 0);
+ use(input_len - stream.avail_in);
+ if (stream.total_out == size && ret == Z_STREAM_END)
+ break;
+ if (ret != Z_OK)
+ bad_object(offset, "inflate returned %d", ret);
+ stream.next_in = fill(1);
+ stream.avail_in = input_len;
+ }
+ git_inflate_end(&stream);
+ return buf;
+}
+
+static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_base)
+{
+ unsigned char *p;
+ unsigned long size, c;
+ off_t base_offset;
+ unsigned shift;
+ void *data;
+
+ obj->idx.offset = consumed_bytes;
+ input_crc32 = crc32(0, Z_NULL, 0);
+
+ p = fill(1);
+ c = *p;
+ use(1);
+ obj->type = (c >> 4) & 7;
+ size = (c & 15);
+ shift = 4;
+ while (c & 0x80) {
+ p = fill(1);
+ c = *p;
+ use(1);
+ size += (c & 0x7f) << shift;
+ shift += 7;
+ }
+ obj->size = size;
+
+ switch (obj->type) {
+ case OBJ_REF_DELTA:
+ hashcpy(delta_base->sha1, fill(20));
+ use(20);
+ break;
+ case OBJ_OFS_DELTA:
+ memset(delta_base, 0, sizeof(*delta_base));
+ p = fill(1);
+ c = *p;
+ use(1);
+ base_offset = c & 127;
+ while (c & 128) {
+ base_offset += 1;
+ if (!base_offset || MSB(base_offset, 7))
+ bad_object(obj->idx.offset, "offset value overflow for delta base object");
+ p = fill(1);
+ c = *p;
+ use(1);
+ base_offset = (base_offset << 7) + (c & 127);
+ }
+ delta_base->offset = obj->idx.offset - base_offset;
+ if (delta_base->offset <= 0 || delta_base->offset >= obj->idx.offset)
+ bad_object(obj->idx.offset, "delta base offset is out of bound");
+ break;
+ case OBJ_COMMIT:
+ case OBJ_TREE:
+ case OBJ_BLOB:
+ case OBJ_TAG:
+ break;
+ default:
+ bad_object(obj->idx.offset, "unknown object type %d", obj->type);
+ }
+ obj->hdr_size = consumed_bytes - obj->idx.offset;
+
+ data = unpack_entry_data(obj->idx.offset, obj->size);
+ obj->idx.crc32 = input_crc32;
+ return data;
+}
+
+static void *get_data_from_pack(struct object_entry *obj)
+{
+ off_t from = obj[0].idx.offset + obj[0].hdr_size;
+ unsigned long len = obj[1].idx.offset - from;
+ unsigned long rdy = 0;
+ unsigned char *src, *data;
+ z_stream stream;
+ int st;
+
+ src = xmalloc(len);
+ data = src;
+ do {
+ ssize_t n = pread(pack_fd, data + rdy, len - rdy, from + rdy);
+ if (n < 0)
+ die_errno("cannot pread pack file");
+ if (!n)
+ die("premature end of pack file, %lu bytes missing",
+ len - rdy);
+ rdy += n;
+ } while (rdy < len);
+ data = xmalloc(obj->size);
+ memset(&stream, 0, sizeof(stream));
+ stream.next_out = data;
+ stream.avail_out = obj->size;
+ stream.next_in = src;
+ stream.avail_in = len;
+ git_inflate_init(&stream);
+ while ((st = git_inflate(&stream, Z_FINISH)) == Z_OK);
+ git_inflate_end(&stream);
+ if (st != Z_STREAM_END || stream.total_out != obj->size)
+ die("serious inflate inconsistency");
+ free(src);
+ return data;
+}
+
+static int find_delta(const union delta_base *base)
+{
+ int first = 0, last = nr_deltas;
+
+ while (first < last) {
+ int next = (first + last) / 2;
+ struct delta_entry *delta = &deltas[next];
+ int cmp;
+
+ cmp = memcmp(base, &delta->base, UNION_BASE_SZ);
+ if (!cmp)
+ return next;
+ if (cmp < 0) {
+ last = next;
+ continue;
+ }
+ first = next+1;
+ }
+ return -first-1;
+}
+
+static void find_delta_children(const union delta_base *base,
+ int *first_index, int *last_index)
+{
+ int first = find_delta(base);
+ int last = first;
+ int end = nr_deltas - 1;
+
+ if (first < 0) {
+ *first_index = 0;
+ *last_index = -1;
+ return;
+ }
+ while (first > 0 && !memcmp(&deltas[first - 1].base, base, UNION_BASE_SZ))
+ --first;
+ while (last < end && !memcmp(&deltas[last + 1].base, base, UNION_BASE_SZ))
+ ++last;
+ *first_index = first;
+ *last_index = last;
+}
+
+static void sha1_object(const void *data, unsigned long size,
+ enum object_type type, unsigned char *sha1)
+{
+ hash_sha1_file(data, size, typename(type), sha1);
+ if (has_sha1_file(sha1)) {
+ void *has_data;
+ enum object_type has_type;
+ unsigned long has_size;
+ has_data = read_sha1_file(sha1, &has_type, &has_size);
+ if (!has_data)
+ die("cannot read existing object %s", sha1_to_hex(sha1));
+ if (size != has_size || type != has_type ||
+ memcmp(data, has_data, size) != 0)
+ die("SHA1 COLLISION FOUND WITH %s !", sha1_to_hex(sha1));
+ free(has_data);
+ }
+ if (strict) {
+ if (type == OBJ_BLOB) {
+ struct blob *blob = lookup_blob(sha1);
+ if (blob)
+ blob->object.flags |= FLAG_CHECKED;
+ else
+ die("invalid blob object %s", sha1_to_hex(sha1));
+ } else {
+ struct object *obj;
+ int eaten;
+ void *buf = (void *) data;
+
+ /*
+ * we do not need to free the memory here, as the
+ * buf is deleted by the caller.
+ */
+ obj = parse_object_buffer(sha1, type, size, buf, &eaten);
+ if (!obj)
+ die("invalid %s", typename(type));
+ if (fsck_object(obj, 1, fsck_error_function))
+ die("Error in object");
+ if (fsck_walk(obj, mark_link, NULL))
+ die("Not all child objects of %s are reachable", sha1_to_hex(obj->sha1));
+
+ if (obj->type == OBJ_TREE) {
+ struct tree *item = (struct tree *) obj;
+ item->buffer = NULL;
+ }
+ if (obj->type == OBJ_COMMIT) {
+ struct commit *commit = (struct commit *) obj;
+ commit->buffer = NULL;
+ }
+ obj->flags |= FLAG_CHECKED;
+ }
+ }
+}
+
+static void *get_base_data(struct base_data *c)
+{
+ if (!c->data) {
+ struct object_entry *obj = c->obj;
+
+ if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA) {
+ void *base = get_base_data(c->base);
+ void *raw = get_data_from_pack(obj);
+ c->data = patch_delta(
+ base, c->base->size,
+ raw, obj->size,
+ &c->size);
+ free(raw);
+ if (!c->data)
+ bad_object(obj->idx.offset, "failed to apply delta");
+ } else {
+ c->data = get_data_from_pack(obj);
+ c->size = obj->size;
+ }
+
+ base_cache_used += c->size;
+ prune_base_data(c);
+ }
+ return c->data;
+}
+
+static void resolve_delta(struct object_entry *delta_obj,
+ struct base_data *base, struct base_data *result)
+{
+ void *base_data, *delta_data;
+
+ delta_obj->real_type = base->obj->real_type;
+ delta_data = get_data_from_pack(delta_obj);
+ base_data = get_base_data(base);
+ result->obj = delta_obj;
+ result->data = patch_delta(base_data, base->size,
+ delta_data, delta_obj->size, &result->size);
+ free(delta_data);
+ if (!result->data)
+ bad_object(delta_obj->idx.offset, "failed to apply delta");
+ sha1_object(result->data, result->size, delta_obj->real_type,
+ delta_obj->idx.sha1);
+ nr_resolved_deltas++;
+}
+
+static void find_unresolved_deltas(struct base_data *base,
+ struct base_data *prev_base)
+{
+ int i, ref_first, ref_last, ofs_first, ofs_last;
+
+ /*
+ * This is a recursive function. Those brackets should help reducing
+ * stack usage by limiting the scope of the delta_base union.
+ */
+ {
+ union delta_base base_spec;
+
+ hashcpy(base_spec.sha1, base->obj->idx.sha1);
+ find_delta_children(&base_spec, &ref_first, &ref_last);
+
+ memset(&base_spec, 0, sizeof(base_spec));
+ base_spec.offset = base->obj->idx.offset;
+ find_delta_children(&base_spec, &ofs_first, &ofs_last);
+ }
+
+ if (ref_last == -1 && ofs_last == -1) {
+ free(base->data);
+ return;
+ }
+
+ link_base_data(prev_base, base);
+
+ 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);
+ }
+ }
+
+ 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);
+ }
+ }
+
+ unlink_base_data(base);
+}
+
+static int compare_delta_entry(const void *a, const void *b)
+{
+ 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);
+}
+
+/* Parse all objects and return the pack content SHA1 hash */
+static void parse_pack_objects(unsigned char *sha1)
+{
+ int i;
+ struct delta_entry *delta = deltas;
+ struct stat st;
+
+ /*
+ * First pass:
+ * - find locations of all objects;
+ * - calculate SHA1 of all non-delta objects;
+ * - remember base (SHA1 or offset) for all deltas.
+ */
+ if (verbose)
+ progress = start_progress(
+ from_stdin ? "Receiving objects" : "Indexing objects",
+ nr_objects);
+ for (i = 0; i < nr_objects; i++) {
+ struct object_entry *obj = &objects[i];
+ void *data = unpack_raw_entry(obj, &delta->base);
+ obj->real_type = obj->type;
+ if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA) {
+ nr_deltas++;
+ delta->obj_no = i;
+ delta++;
+ } else
+ sha1_object(data, obj->size, obj->type, obj->idx.sha1);
+ free(data);
+ display_progress(progress, i+1);
+ }
+ objects[i].idx.offset = consumed_bytes;
+ stop_progress(&progress);
+
+ /* Check pack integrity */
+ flush();
+ git_SHA1_Final(sha1, &input_ctx);
+ if (hashcmp(fill(20), sha1))
+ die("pack is corrupted (SHA1 mismatch)");
+ use(20);
+
+ /* If input_fd is a file, we should have reached its end now. */
+ if (fstat(input_fd, &st))
+ die_errno("cannot fstat packfile");
+ if (S_ISREG(st.st_mode) &&
+ lseek(input_fd, 0, SEEK_CUR) - input_len != st.st_size)
+ die("pack has junk at the end");
+
+ if (!nr_deltas)
+ return;
+
+ /* Sort deltas by base SHA1/offset for fast searching */
+ qsort(deltas, nr_deltas, sizeof(struct delta_entry),
+ compare_delta_entry);
+
+ /*
+ * Second pass:
+ * - for all non-delta objects, look if it is used as a base for
+ * deltas;
+ * - if used as a base, uncompress the object and apply all deltas,
+ * recursively checking if the resulting object is used as a base
+ * for some more deltas.
+ */
+ if (verbose)
+ progress = start_progress("Resolving deltas", nr_deltas);
+ for (i = 0; i < nr_objects; i++) {
+ struct object_entry *obj = &objects[i];
+ struct base_data base_obj;
+
+ if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA)
+ continue;
+ base_obj.obj = obj;
+ base_obj.data = NULL;
+ find_unresolved_deltas(&base_obj, NULL);
+ display_progress(progress, nr_resolved_deltas);
+ }
+}
+
+static int write_compressed(struct sha1file *f, void *in, unsigned int size)
+{
+ z_stream stream;
+ unsigned long maxsize;
+ void *out;
+
+ memset(&stream, 0, sizeof(stream));
+ deflateInit(&stream, zlib_compression_level);
+ maxsize = deflateBound(&stream, size);
+ out = xmalloc(maxsize);
+
+ /* Compress it */
+ stream.next_in = in;
+ stream.avail_in = size;
+ stream.next_out = out;
+ stream.avail_out = maxsize;
+ while (deflate(&stream, Z_FINISH) == Z_OK);
+ deflateEnd(&stream);
+
+ size = stream.total_out;
+ sha1write(f, out, size);
+ free(out);
+ return size;
+}
+
+static struct object_entry *append_obj_to_pack(struct sha1file *f,
+ const unsigned char *sha1, void *buf,
+ unsigned long size, enum object_type type)
+{
+ struct object_entry *obj = &objects[nr_objects++];
+ unsigned char header[10];
+ unsigned long s = size;
+ int n = 0;
+ unsigned char c = (type << 4) | (s & 15);
+ s >>= 4;
+ while (s) {
+ header[n++] = c | 0x80;
+ c = s & 0x7f;
+ s >>= 7;
+ }
+ header[n++] = c;
+ crc32_begin(f);
+ sha1write(f, header, n);
+ obj[0].size = size;
+ obj[0].hdr_size = n;
+ obj[0].type = type;
+ obj[0].real_type = type;
+ obj[1].idx.offset = obj[0].idx.offset + n;
+ obj[1].idx.offset += write_compressed(f, buf, size);
+ obj[0].idx.crc32 = crc32_end(f);
+ sha1flush(f);
+ hashcpy(obj->idx.sha1, sha1);
+ return obj;
+}
+
+static int delta_pos_compare(const void *_a, const void *_b)
+{
+ struct delta_entry *a = *(struct delta_entry **)_a;
+ struct delta_entry *b = *(struct delta_entry **)_b;
+ return a->obj_no - b->obj_no;
+}
+
+static void fix_unresolved_deltas(struct sha1file *f, int nr_unresolved)
+{
+ struct delta_entry **sorted_by_pos;
+ int i, n = 0;
+
+ /*
+ * Since many unresolved deltas may well be themselves base objects
+ * for more unresolved deltas, we really want to include the
+ * smallest number of base objects that would cover as much delta
+ * as possible by picking the
+ * trunc deltas first, allowing for other deltas to resolve without
+ * additional base objects. Since most base objects are to be found
+ * before deltas depending on them, a good heuristic is to start
+ * resolving deltas in the same order as their position in the pack.
+ */
+ sorted_by_pos = xmalloc(nr_unresolved * sizeof(*sorted_by_pos));
+ for (i = 0; i < nr_deltas; i++) {
+ if (objects[deltas[i].obj_no].real_type != OBJ_REF_DELTA)
+ continue;
+ sorted_by_pos[n++] = &deltas[i];
+ }
+ qsort(sorted_by_pos, n, sizeof(*sorted_by_pos), delta_pos_compare);
+
+ for (i = 0; i < n; i++) {
+ struct delta_entry *d = sorted_by_pos[i];
+ enum object_type type;
+ struct base_data base_obj;
+
+ if (objects[d->obj_no].real_type != OBJ_REF_DELTA)
+ continue;
+ base_obj.data = read_sha1_file(d->base.sha1, &type, &base_obj.size);
+ if (!base_obj.data)
+ continue;
+
+ if (check_sha1_signature(d->base.sha1, base_obj.data,
+ base_obj.size, typename(type)))
+ die("local object %s is corrupt", sha1_to_hex(d->base.sha1));
+ base_obj.obj = append_obj_to_pack(f, d->base.sha1,
+ base_obj.data, base_obj.size, type);
+ find_unresolved_deltas(&base_obj, NULL);
+ display_progress(progress, nr_resolved_deltas);
+ }
+ free(sorted_by_pos);
+}
+
+static void final(const char *final_pack_name, const char *curr_pack_name,
+ const char *final_index_name, const char *curr_index_name,
+ const char *keep_name, const char *keep_msg,
+ unsigned char *sha1)
+{
+ const char *report = "pack";
+ char name[PATH_MAX];
+ int err;
+
+ if (!from_stdin) {
+ close(input_fd);
+ } else {
+ fsync_or_die(output_fd, curr_pack_name);
+ err = close(output_fd);
+ if (err)
+ die_errno("error while closing pack file");
+ }
+
+ if (keep_msg) {
+ int keep_fd, keep_msg_len = strlen(keep_msg);
+
+ if (!keep_name)
+ keep_fd = odb_pack_keep(name, sizeof(name), sha1);
+ else
+ keep_fd = open(keep_name, O_RDWR|O_CREAT|O_EXCL, 0600);
+
+ if (keep_fd < 0) {
+ if (errno != EEXIST)
+ die_errno("cannot write keep file '%s'",
+ keep_name);
+ } else {
+ if (keep_msg_len > 0) {
+ write_or_die(keep_fd, keep_msg, keep_msg_len);
+ write_or_die(keep_fd, "\n", 1);
+ }
+ if (close(keep_fd) != 0)
+ die_errno("cannot close written keep file '%s'",
+ keep_name);
+ report = "keep";
+ }
+ }
+
+ if (final_pack_name != curr_pack_name) {
+ if (!final_pack_name) {
+ snprintf(name, sizeof(name), "%s/pack/pack-%s.pack",
+ get_object_directory(), sha1_to_hex(sha1));
+ final_pack_name = name;
+ }
+ if (move_temp_to_file(curr_pack_name, final_pack_name))
+ die("cannot store pack file");
+ } else if (from_stdin)
+ chmod(final_pack_name, 0444);
+
+ if (final_index_name != curr_index_name) {
+ if (!final_index_name) {
+ snprintf(name, sizeof(name), "%s/pack/pack-%s.idx",
+ get_object_directory(), sha1_to_hex(sha1));
+ final_index_name = name;
+ }
+ if (move_temp_to_file(curr_index_name, final_index_name))
+ die("cannot store index file");
+ } else
+ chmod(final_index_name, 0444);
+
+ if (!from_stdin) {
+ printf("%s\n", sha1_to_hex(sha1));
+ } else {
+ char buf[48];
+ int len = snprintf(buf, sizeof(buf), "%s\t%s\n",
+ report, sha1_to_hex(sha1));
+ write_or_die(1, buf, len);
+
+ /*
+ * Let's just mimic git-unpack-objects here and write
+ * the last part of the input buffer to stdout.
+ */
+ while (input_len) {
+ err = xwrite(1, input_buffer + input_offset, input_len);
+ if (err <= 0)
+ break;
+ input_len -= err;
+ input_offset += err;
+ }
+ }
+}
+
+static int git_index_pack_config(const char *k, const char *v, void *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);
+ return 0;
+ }
+ return git_default_config(k, v, cb);
+}
+
+int cmd_index_pack(int argc, const char **argv, const char *prefix)
+{
+ int i, fix_thin_pack = 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;
+ unsigned char pack_sha1[20];
+
+ if (argc == 2 && !strcmp(argv[1], "-h"))
+ usage(index_pack_usage);
+
+ /*
+ * We wish to read the repository's config file if any, and
+ * for that it is necessary to call setup_git_directory_gently().
+ * However if the cwd was inside .git/objects/pack/ then we need
+ * to go back there or all the pack name arguments will be wrong.
+ * And in that case we cannot rely on any prefix returned by
+ * setup_git_directory_gently() either.
+ */
+ {
+ char cwd[PATH_MAX+1];
+ int nongit;
+
+ if (!getcwd(cwd, sizeof(cwd)-1))
+ die("Unable to get current working directory");
+ setup_git_directory_gently(&nongit);
+ git_config(git_index_pack_config, NULL);
+ if (chdir(cwd))
+ die("Cannot come back to cwd");
+ }
+
+ for (i = 1; i < argc; i++) {
+ const char *arg = argv[i];
+
+ if (*arg == '-') {
+ if (!strcmp(arg, "--stdin")) {
+ from_stdin = 1;
+ } else if (!strcmp(arg, "--fix-thin")) {
+ fix_thin_pack = 1;
+ } else if (!strcmp(arg, "--strict")) {
+ strict = 1;
+ } else if (!strcmp(arg, "--keep")) {
+ keep_msg = "";
+ } else if (!prefixcmp(arg, "--keep=")) {
+ keep_msg = arg + 7;
+ } else if (!prefixcmp(arg, "--pack_header=")) {
+ struct pack_header *hdr;
+ char *c;
+
+ hdr = (struct pack_header *)input_buffer;
+ hdr->hdr_signature = htonl(PACK_SIGNATURE);
+ hdr->hdr_version = htonl(strtoul(arg + 14, &c, 10));
+ if (*c != ',')
+ die("bad %s", arg);
+ hdr->hdr_entries = htonl(strtoul(c + 1, &c, 10));
+ if (*c)
+ die("bad %s", arg);
+ input_len = sizeof(*hdr);
+ } else if (!strcmp(arg, "-v")) {
+ verbose = 1;
+ } else if (!strcmp(arg, "-o")) {
+ if (index_name || (i+1) >= argc)
+ usage(index_pack_usage);
+ 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)
+ die("bad %s", arg);
+ if (*c == ',')
+ pack_idx_off32_limit = strtoul(c+1, &c, 0);
+ if (*c || pack_idx_off32_limit & 0x80000000)
+ die("bad %s", arg);
+ } else
+ usage(index_pack_usage);
+ continue;
+ }
+
+ if (pack_name)
+ usage(index_pack_usage);
+ pack_name = arg;
+ }
+
+ if (!pack_name && !from_stdin)
+ usage(index_pack_usage);
+ if (fix_thin_pack && !from_stdin)
+ die("--fix-thin cannot be used without --stdin");
+ if (!index_name && pack_name) {
+ int len = strlen(pack_name);
+ if (!has_extension(pack_name, ".pack"))
+ die("packfile name '%s' does not end with '.pack'",
+ pack_name);
+ index_name_buf = xmalloc(len);
+ memcpy(index_name_buf, pack_name, len - 5);
+ strcpy(index_name_buf + len - 5, ".idx");
+ index_name = index_name_buf;
+ }
+ if (keep_msg && !keep_name && pack_name) {
+ int len = strlen(pack_name);
+ if (!has_extension(pack_name, ".pack"))
+ die("packfile name '%s' does not end with '.pack'",
+ pack_name);
+ keep_name_buf = xmalloc(len);
+ memcpy(keep_name_buf, pack_name, len - 5);
+ strcpy(keep_name_buf + len - 5, ".keep");
+ keep_name = keep_name_buf;
+ }
+
+ curr_pack = open_pack_file(pack_name);
+ parse_pack_header();
+ objects = xmalloc((nr_objects + 1) * sizeof(struct object_entry));
+ deltas = xmalloc(nr_objects * sizeof(struct delta_entry));
+ parse_pack_objects(pack_sha1);
+ if (nr_deltas == nr_resolved_deltas) {
+ stop_progress(&progress);
+ /* Flush remaining pack final 20-byte SHA1. */
+ flush();
+ } else {
+ if (fix_thin_pack) {
+ struct sha1file *f;
+ unsigned char read_sha1[20], tail_sha1[20];
+ char msg[48];
+ int nr_unresolved = nr_deltas - nr_resolved_deltas;
+ int nr_objects_initial = nr_objects;
+ if (nr_unresolved <= 0)
+ die("confusion beyond insanity");
+ objects = xrealloc(objects,
+ (nr_objects + nr_unresolved + 1)
+ * sizeof(*objects));
+ f = sha1fd(output_fd, curr_pack);
+ fix_unresolved_deltas(f, nr_unresolved);
+ sprintf(msg, "completed with %d local objects",
+ nr_objects - nr_objects_initial);
+ stop_progress_msg(&progress, msg);
+ sha1close(f, tail_sha1, 0);
+ hashcpy(read_sha1, pack_sha1);
+ fixup_pack_header_footer(output_fd, pack_sha1,
+ curr_pack, nr_objects,
+ read_sha1, consumed_bytes-20);
+ if (hashcmp(read_sha1, tail_sha1) != 0)
+ die("Unexpected tail checksum for %s "
+ "(disk corruption?)", curr_pack);
+ }
+ if (nr_deltas != nr_resolved_deltas)
+ die("pack has %d unresolved deltas",
+ nr_deltas - nr_resolved_deltas);
+ }
+ free(deltas);
+ if (strict)
+ check_objects();
+
+ 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);
+ free(idx_objects);
+
+ final(pack_name, curr_pack,
+ index_name, curr_index,
+ keep_name, keep_msg,
+ pack_sha1);
+ free(objects);
+ free(index_name_buf);
+ free(keep_name_buf);
+ if (pack_name == NULL)
+ free((void *) curr_pack);
+ if (index_name == NULL)
+ free((void *) curr_index);
+
+ return 0;
+}
diff --git a/builtin-pack-objects.c b/builtin-pack-objects.c
index 59b07fe491f37fbe47e04fe834138720336e3627..b0887d759dc02e1b57fbbfa9e8e3d16c9ac00d8b 100644 (file)
--- a/builtin-pack-objects.c
+++ b/builtin-pack-objects.c
if (!pack_to_stdout) {
mode_t mode = umask(0);
struct stat st;
- char *idx_tmp_name, tmpname[PATH_MAX];
+ const char *idx_tmp_name;
+ char tmpname[PATH_MAX];
umask(mode);
mode = 0444 & ~mode;
if (rename(idx_tmp_name, tmpname))
die_errno("unable to rename temporary index file");
- free(idx_tmp_name);
+ free((void *) idx_tmp_name);
free(pack_tmp_name);
puts(sha1_to_hex(sha1));
}
diff --git a/builtin.h b/builtin.h
index bd7f737485d24fe0203b9d39291426847efc1bf7..e8202f3f5e57a302634be9268866edaba0fd6eb0 100644 (file)
--- a/builtin.h
+++ b/builtin.h
extern int cmd_hash_object(int argc, const char **argv, const char *prefix);
extern int cmd_help(int argc, const char **argv, const char *prefix);
extern int cmd_http_fetch(int argc, const char **argv, const char *prefix);
+extern int cmd_index_pack(int argc, const char **argv, const char *prefix);
extern int cmd_init_db(int argc, const char **argv, const char *prefix);
extern int cmd_log(int argc, const char **argv, const char *prefix);
extern int cmd_log_reflog(int argc, const char **argv, const char *prefix);
index 6cc1eba29e71fb4bbb26789ff71b21041442720b..b3e23f10441924de45ab768e086ead90b214d4c7 100644 (file)
--- a/git.c
+++ b/git.c
{ "grep", cmd_grep, USE_PAGER },
{ "hash-object", cmd_hash_object },
{ "help", cmd_help },
+ { "index-pack", cmd_index_pack },
{ "init", cmd_init_db },
{ "init-db", cmd_init_db },
{ "log", cmd_log, RUN_SETUP | USE_PAGER },
diff --git a/index-pack.c b/index-pack.c
--- a/index-pack.c
+++ /dev/null
@@ -1,1047 +0,0 @@
-#include "cache.h"
-#include "delta.h"
-#include "pack.h"
-#include "csum-file.h"
-#include "blob.h"
-#include "commit.h"
-#include "tag.h"
-#include "tree.h"
-#include "progress.h"
-#include "fsck.h"
-#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>] }";
-
-struct object_entry
-{
- struct pack_idx_entry idx;
- unsigned long size;
- unsigned int hdr_size;
- enum object_type type;
- enum object_type real_type;
-};
-
-union delta_base {
- unsigned char sha1[20];
- off_t offset;
-};
-
-struct base_data {
- struct base_data *base;
- struct base_data *child;
- struct object_entry *obj;
- void *data;
- unsigned long size;
-};
-
-/*
- * Even if sizeof(union delta_base) == 24 on 64-bit archs, we really want
- * to memcmp() only the first 20 bytes.
- */
-#define UNION_BASE_SZ 20
-
-#define FLAG_LINK (1u<<20)
-#define FLAG_CHECKED (1u<<21)
-
-struct delta_entry
-{
- union delta_base base;
- int obj_no;
-};
-
-static struct object_entry *objects;
-static struct delta_entry *deltas;
-static struct base_data *base_cache;
-static size_t base_cache_used;
-static int nr_objects;
-static int nr_deltas;
-static int nr_resolved_deltas;
-
-static int from_stdin;
-static int strict;
-static int verbose;
-
-static struct progress *progress;
-
-/* We always read in 4kB chunks. */
-static unsigned char input_buffer[4096];
-static unsigned int input_offset, input_len;
-static off_t consumed_bytes;
-static git_SHA_CTX input_ctx;
-static uint32_t input_crc32;
-static int input_fd, output_fd, pack_fd;
-
-static int mark_link(struct object *obj, int type, void *data)
-{
- if (!obj)
- return -1;
-
- if (type != OBJ_ANY && obj->type != type)
- die("object type mismatch at %s", sha1_to_hex(obj->sha1));
-
- obj->flags |= FLAG_LINK;
- return 0;
-}
-
-/* The content of each linked object must have been checked
- or it must be already present in the object database */
-static void check_object(struct object *obj)
-{
- if (!obj)
- return;
-
- if (!(obj->flags & FLAG_LINK))
- return;
-
- if (!(obj->flags & FLAG_CHECKED)) {
- unsigned long size;
- int type = sha1_object_info(obj->sha1, &size);
- if (type != obj->type || type <= 0)
- die("object of unexpected type");
- obj->flags |= FLAG_CHECKED;
- return;
- }
-}
-
-static void check_objects(void)
-{
- unsigned i, max;
-
- max = get_max_object_index();
- for (i = 0; i < max; i++)
- check_object(get_indexed_object(i));
-}
-
-
-/* Discard current buffer used content. */
-static void flush(void)
-{
- if (input_offset) {
- if (output_fd >= 0)
- write_or_die(output_fd, input_buffer, input_offset);
- git_SHA1_Update(&input_ctx, input_buffer, input_offset);
- memmove(input_buffer, input_buffer + input_offset, input_len);
- input_offset = 0;
- }
-}
-
-/*
- * Make sure at least "min" bytes are available in the buffer, and
- * return the pointer to the buffer.
- */
-static void *fill(int min)
-{
- if (min <= input_len)
- return input_buffer + input_offset;
- if (min > sizeof(input_buffer))
- die("cannot fill %d bytes", min);
- flush();
- do {
- ssize_t ret = xread(input_fd, input_buffer + input_len,
- sizeof(input_buffer) - input_len);
- if (ret <= 0) {
- if (!ret)
- die("early EOF");
- die_errno("read error on input");
- }
- input_len += ret;
- if (from_stdin)
- display_throughput(progress, consumed_bytes + input_len);
- } while (input_len < min);
- return input_buffer;
-}
-
-static void use(int bytes)
-{
- if (bytes > input_len)
- die("used more bytes than were available");
- input_crc32 = crc32(input_crc32, input_buffer + input_offset, bytes);
- input_len -= bytes;
- input_offset += bytes;
-
- /* make sure off_t is sufficiently large not to wrap */
- if (consumed_bytes > consumed_bytes + bytes)
- die("pack too large for current definition of off_t");
- consumed_bytes += bytes;
-}
-
-static char *open_pack_file(char *pack_name)
-{
- if (from_stdin) {
- input_fd = 0;
- if (!pack_name) {
- static char tmpfile[PATH_MAX];
- output_fd = odb_mkstemp(tmpfile, sizeof(tmpfile),
- "pack/tmp_pack_XXXXXX");
- pack_name = xstrdup(tmpfile);
- } else
- output_fd = open(pack_name, O_CREAT|O_EXCL|O_RDWR, 0600);
- if (output_fd < 0)
- die_errno("unable to create '%s'", pack_name);
- pack_fd = output_fd;
- } else {
- input_fd = open(pack_name, O_RDONLY);
- if (input_fd < 0)
- die_errno("cannot open packfile '%s'", pack_name);
- output_fd = -1;
- pack_fd = input_fd;
- }
- git_SHA1_Init(&input_ctx);
- return pack_name;
-}
-
-static void parse_pack_header(void)
-{
- struct pack_header *hdr = fill(sizeof(struct pack_header));
-
- /* Header consistency check */
- if (hdr->hdr_signature != htonl(PACK_SIGNATURE))
- die("pack signature mismatch");
- if (!pack_version_ok(hdr->hdr_version))
- die("pack version %"PRIu32" unsupported",
- ntohl(hdr->hdr_version));
-
- nr_objects = ntohl(hdr->hdr_entries);
- use(sizeof(struct pack_header));
-}
-
-static NORETURN void bad_object(unsigned long offset, const char *format,
- ...) __attribute__((format (printf, 2, 3)));
-
-static void bad_object(unsigned long offset, const char *format, ...)
-{
- va_list params;
- char buf[1024];
-
- va_start(params, format);
- vsnprintf(buf, sizeof(buf), format, params);
- va_end(params);
- die("pack has bad object at offset %lu: %s", offset, buf);
-}
-
-static void free_base_data(struct base_data *c)
-{
- if (c->data) {
- free(c->data);
- c->data = NULL;
- base_cache_used -= c->size;
- }
-}
-
-static void prune_base_data(struct base_data *retain)
-{
- struct base_data *b;
- for (b = base_cache;
- base_cache_used > delta_base_cache_limit && b;
- b = b->child) {
- if (b->data && b != retain)
- free_base_data(b);
- }
-}
-
-static void link_base_data(struct base_data *base, struct base_data *c)
-{
- if (base)
- base->child = c;
- else
- base_cache = c;
-
- c->base = base;
- c->child = NULL;
- if (c->data)
- base_cache_used += c->size;
- prune_base_data(c);
-}
-
-static void unlink_base_data(struct base_data *c)
-{
- struct base_data *base = c->base;
- if (base)
- base->child = NULL;
- else
- base_cache = NULL;
- free_base_data(c);
-}
-
-static void *unpack_entry_data(unsigned long offset, unsigned long size)
-{
- z_stream stream;
- void *buf = xmalloc(size);
-
- memset(&stream, 0, sizeof(stream));
- stream.next_out = buf;
- stream.avail_out = size;
- stream.next_in = fill(1);
- stream.avail_in = input_len;
- git_inflate_init(&stream);
-
- for (;;) {
- int ret = git_inflate(&stream, 0);
- use(input_len - stream.avail_in);
- if (stream.total_out == size && ret == Z_STREAM_END)
- break;
- if (ret != Z_OK)
- bad_object(offset, "inflate returned %d", ret);
- stream.next_in = fill(1);
- stream.avail_in = input_len;
- }
- git_inflate_end(&stream);
- return buf;
-}
-
-static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_base)
-{
- unsigned char *p;
- unsigned long size, c;
- off_t base_offset;
- unsigned shift;
- void *data;
-
- obj->idx.offset = consumed_bytes;
- input_crc32 = crc32(0, Z_NULL, 0);
-
- p = fill(1);
- c = *p;
- use(1);
- obj->type = (c >> 4) & 7;
- size = (c & 15);
- shift = 4;
- while (c & 0x80) {
- p = fill(1);
- c = *p;
- use(1);
- size += (c & 0x7f) << shift;
- shift += 7;
- }
- obj->size = size;
-
- switch (obj->type) {
- case OBJ_REF_DELTA:
- hashcpy(delta_base->sha1, fill(20));
- use(20);
- break;
- case OBJ_OFS_DELTA:
- memset(delta_base, 0, sizeof(*delta_base));
- p = fill(1);
- c = *p;
- use(1);
- base_offset = c & 127;
- while (c & 128) {
- base_offset += 1;
- if (!base_offset || MSB(base_offset, 7))
- bad_object(obj->idx.offset, "offset value overflow for delta base object");
- p = fill(1);
- c = *p;
- use(1);
- base_offset = (base_offset << 7) + (c & 127);
- }
- delta_base->offset = obj->idx.offset - base_offset;
- if (delta_base->offset <= 0 || delta_base->offset >= obj->idx.offset)
- bad_object(obj->idx.offset, "delta base offset is out of bound");
- break;
- case OBJ_COMMIT:
- case OBJ_TREE:
- case OBJ_BLOB:
- case OBJ_TAG:
- break;
- default:
- bad_object(obj->idx.offset, "unknown object type %d", obj->type);
- }
- obj->hdr_size = consumed_bytes - obj->idx.offset;
-
- data = unpack_entry_data(obj->idx.offset, obj->size);
- obj->idx.crc32 = input_crc32;
- return data;
-}
-
-static void *get_data_from_pack(struct object_entry *obj)
-{
- off_t from = obj[0].idx.offset + obj[0].hdr_size;
- unsigned long len = obj[1].idx.offset - from;
- unsigned long rdy = 0;
- unsigned char *src, *data;
- z_stream stream;
- int st;
-
- src = xmalloc(len);
- data = src;
- do {
- ssize_t n = pread(pack_fd, data + rdy, len - rdy, from + rdy);
- if (n < 0)
- die_errno("cannot pread pack file");
- if (!n)
- die("premature end of pack file, %lu bytes missing",
- len - rdy);
- rdy += n;
- } while (rdy < len);
- data = xmalloc(obj->size);
- memset(&stream, 0, sizeof(stream));
- stream.next_out = data;
- stream.avail_out = obj->size;
- stream.next_in = src;
- stream.avail_in = len;
- git_inflate_init(&stream);
- while ((st = git_inflate(&stream, Z_FINISH)) == Z_OK);
- git_inflate_end(&stream);
- if (st != Z_STREAM_END || stream.total_out != obj->size)
- die("serious inflate inconsistency");
- free(src);
- return data;
-}
-
-static int find_delta(const union delta_base *base)
-{
- int first = 0, last = nr_deltas;
-
- while (first < last) {
- int next = (first + last) / 2;
- struct delta_entry *delta = &deltas[next];
- int cmp;
-
- cmp = memcmp(base, &delta->base, UNION_BASE_SZ);
- if (!cmp)
- return next;
- if (cmp < 0) {
- last = next;
- continue;
- }
- first = next+1;
- }
- return -first-1;
-}
-
-static void find_delta_children(const union delta_base *base,
- int *first_index, int *last_index)
-{
- int first = find_delta(base);
- int last = first;
- int end = nr_deltas - 1;
-
- if (first < 0) {
- *first_index = 0;
- *last_index = -1;
- return;
- }
- while (first > 0 && !memcmp(&deltas[first - 1].base, base, UNION_BASE_SZ))
- --first;
- while (last < end && !memcmp(&deltas[last + 1].base, base, UNION_BASE_SZ))
- ++last;
- *first_index = first;
- *last_index = last;
-}
-
-static void sha1_object(const void *data, unsigned long size,
- enum object_type type, unsigned char *sha1)
-{
- hash_sha1_file(data, size, typename(type), sha1);
- if (has_sha1_file(sha1)) {
- void *has_data;
- enum object_type has_type;
- unsigned long has_size;
- has_data = read_sha1_file(sha1, &has_type, &has_size);
- if (!has_data)
- die("cannot read existing object %s", sha1_to_hex(sha1));
- if (size != has_size || type != has_type ||
- memcmp(data, has_data, size) != 0)
- die("SHA1 COLLISION FOUND WITH %s !", sha1_to_hex(sha1));
- free(has_data);
- }
- if (strict) {
- if (type == OBJ_BLOB) {
- struct blob *blob = lookup_blob(sha1);
- if (blob)
- blob->object.flags |= FLAG_CHECKED;
- else
- die("invalid blob object %s", sha1_to_hex(sha1));
- } else {
- struct object *obj;
- int eaten;
- void *buf = (void *) data;
-
- /*
- * we do not need to free the memory here, as the
- * buf is deleted by the caller.
- */
- obj = parse_object_buffer(sha1, type, size, buf, &eaten);
- if (!obj)
- die("invalid %s", typename(type));
- if (fsck_object(obj, 1, fsck_error_function))
- die("Error in object");
- if (fsck_walk(obj, mark_link, NULL))
- die("Not all child objects of %s are reachable", sha1_to_hex(obj->sha1));
-
- if (obj->type == OBJ_TREE) {
- struct tree *item = (struct tree *) obj;
- item->buffer = NULL;
- }
- if (obj->type == OBJ_COMMIT) {
- struct commit *commit = (struct commit *) obj;
- commit->buffer = NULL;
- }
- obj->flags |= FLAG_CHECKED;
- }
- }
-}
-
-static void *get_base_data(struct base_data *c)
-{
- if (!c->data) {
- struct object_entry *obj = c->obj;
-
- if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA) {
- void *base = get_base_data(c->base);
- void *raw = get_data_from_pack(obj);
- c->data = patch_delta(
- base, c->base->size,
- raw, obj->size,
- &c->size);
- free(raw);
- if (!c->data)
- bad_object(obj->idx.offset, "failed to apply delta");
- } else {
- c->data = get_data_from_pack(obj);
- c->size = obj->size;
- }
-
- base_cache_used += c->size;
- prune_base_data(c);
- }
- return c->data;
-}
-
-static void resolve_delta(struct object_entry *delta_obj,
- struct base_data *base, struct base_data *result)
-{
- void *base_data, *delta_data;
-
- delta_obj->real_type = base->obj->real_type;
- delta_data = get_data_from_pack(delta_obj);
- base_data = get_base_data(base);
- result->obj = delta_obj;
- result->data = patch_delta(base_data, base->size,
- delta_data, delta_obj->size, &result->size);
- free(delta_data);
- if (!result->data)
- bad_object(delta_obj->idx.offset, "failed to apply delta");
- sha1_object(result->data, result->size, delta_obj->real_type,
- delta_obj->idx.sha1);
- nr_resolved_deltas++;
-}
-
-static void find_unresolved_deltas(struct base_data *base,
- struct base_data *prev_base)
-{
- int i, ref_first, ref_last, ofs_first, ofs_last;
-
- /*
- * This is a recursive function. Those brackets should help reducing
- * stack usage by limiting the scope of the delta_base union.
- */
- {
- union delta_base base_spec;
-
- hashcpy(base_spec.sha1, base->obj->idx.sha1);
- find_delta_children(&base_spec, &ref_first, &ref_last);
-
- memset(&base_spec, 0, sizeof(base_spec));
- base_spec.offset = base->obj->idx.offset;
- find_delta_children(&base_spec, &ofs_first, &ofs_last);
- }
-
- if (ref_last == -1 && ofs_last == -1) {
- free(base->data);
- return;
- }
-
- link_base_data(prev_base, base);
-
- 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);
- }
- }
-
- 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);
- }
- }
-
- unlink_base_data(base);
-}
-
-static int compare_delta_entry(const void *a, const void *b)
-{
- 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);
-}
-
-/* Parse all objects and return the pack content SHA1 hash */
-static void parse_pack_objects(unsigned char *sha1)
-{
- int i;
- struct delta_entry *delta = deltas;
- struct stat st;
-
- /*
- * First pass:
- * - find locations of all objects;
- * - calculate SHA1 of all non-delta objects;
- * - remember base (SHA1 or offset) for all deltas.
- */
- if (verbose)
- progress = start_progress(
- from_stdin ? "Receiving objects" : "Indexing objects",
- nr_objects);
- for (i = 0; i < nr_objects; i++) {
- struct object_entry *obj = &objects[i];
- void *data = unpack_raw_entry(obj, &delta->base);
- obj->real_type = obj->type;
- if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA) {
- nr_deltas++;
- delta->obj_no = i;
- delta++;
- } else
- sha1_object(data, obj->size, obj->type, obj->idx.sha1);
- free(data);
- display_progress(progress, i+1);
- }
- objects[i].idx.offset = consumed_bytes;
- stop_progress(&progress);
-
- /* Check pack integrity */
- flush();
- git_SHA1_Final(sha1, &input_ctx);
- if (hashcmp(fill(20), sha1))
- die("pack is corrupted (SHA1 mismatch)");
- use(20);
-
- /* If input_fd is a file, we should have reached its end now. */
- if (fstat(input_fd, &st))
- die_errno("cannot fstat packfile");
- if (S_ISREG(st.st_mode) &&
- lseek(input_fd, 0, SEEK_CUR) - input_len != st.st_size)
- die("pack has junk at the end");
-
- if (!nr_deltas)
- return;
-
- /* Sort deltas by base SHA1/offset for fast searching */
- qsort(deltas, nr_deltas, sizeof(struct delta_entry),
- compare_delta_entry);
-
- /*
- * Second pass:
- * - for all non-delta objects, look if it is used as a base for
- * deltas;
- * - if used as a base, uncompress the object and apply all deltas,
- * recursively checking if the resulting object is used as a base
- * for some more deltas.
- */
- if (verbose)
- progress = start_progress("Resolving deltas", nr_deltas);
- for (i = 0; i < nr_objects; i++) {
- struct object_entry *obj = &objects[i];
- struct base_data base_obj;
-
- if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA)
- continue;
- base_obj.obj = obj;
- base_obj.data = NULL;
- find_unresolved_deltas(&base_obj, NULL);
- display_progress(progress, nr_resolved_deltas);
- }
-}
-
-static int write_compressed(struct sha1file *f, void *in, unsigned int size)
-{
- z_stream stream;
- unsigned long maxsize;
- void *out;
-
- memset(&stream, 0, sizeof(stream));
- deflateInit(&stream, zlib_compression_level);
- maxsize = deflateBound(&stream, size);
- out = xmalloc(maxsize);
-
- /* Compress it */
- stream.next_in = in;
- stream.avail_in = size;
- stream.next_out = out;
- stream.avail_out = maxsize;
- while (deflate(&stream, Z_FINISH) == Z_OK);
- deflateEnd(&stream);
-
- size = stream.total_out;
- sha1write(f, out, size);
- free(out);
- return size;
-}
-
-static struct object_entry *append_obj_to_pack(struct sha1file *f,
- const unsigned char *sha1, void *buf,
- unsigned long size, enum object_type type)
-{
- struct object_entry *obj = &objects[nr_objects++];
- unsigned char header[10];
- unsigned long s = size;
- int n = 0;
- unsigned char c = (type << 4) | (s & 15);
- s >>= 4;
- while (s) {
- header[n++] = c | 0x80;
- c = s & 0x7f;
- s >>= 7;
- }
- header[n++] = c;
- crc32_begin(f);
- sha1write(f, header, n);
- obj[0].size = size;
- obj[0].hdr_size = n;
- obj[0].type = type;
- obj[0].real_type = type;
- obj[1].idx.offset = obj[0].idx.offset + n;
- obj[1].idx.offset += write_compressed(f, buf, size);
- obj[0].idx.crc32 = crc32_end(f);
- sha1flush(f);
- hashcpy(obj->idx.sha1, sha1);
- return obj;
-}
-
-static int delta_pos_compare(const void *_a, const void *_b)
-{
- struct delta_entry *a = *(struct delta_entry **)_a;
- struct delta_entry *b = *(struct delta_entry **)_b;
- return a->obj_no - b->obj_no;
-}
-
-static void fix_unresolved_deltas(struct sha1file *f, int nr_unresolved)
-{
- struct delta_entry **sorted_by_pos;
- int i, n = 0;
-
- /*
- * Since many unresolved deltas may well be themselves base objects
- * for more unresolved deltas, we really want to include the
- * smallest number of base objects that would cover as much delta
- * as possible by picking the
- * trunc deltas first, allowing for other deltas to resolve without
- * additional base objects. Since most base objects are to be found
- * before deltas depending on them, a good heuristic is to start
- * resolving deltas in the same order as their position in the pack.
- */
- sorted_by_pos = xmalloc(nr_unresolved * sizeof(*sorted_by_pos));
- for (i = 0; i < nr_deltas; i++) {
- if (objects[deltas[i].obj_no].real_type != OBJ_REF_DELTA)
- continue;
- sorted_by_pos[n++] = &deltas[i];
- }
- qsort(sorted_by_pos, n, sizeof(*sorted_by_pos), delta_pos_compare);
-
- for (i = 0; i < n; i++) {
- struct delta_entry *d = sorted_by_pos[i];
- enum object_type type;
- struct base_data base_obj;
-
- if (objects[d->obj_no].real_type != OBJ_REF_DELTA)
- continue;
- base_obj.data = read_sha1_file(d->base.sha1, &type, &base_obj.size);
- if (!base_obj.data)
- continue;
-
- if (check_sha1_signature(d->base.sha1, base_obj.data,
- base_obj.size, typename(type)))
- die("local object %s is corrupt", sha1_to_hex(d->base.sha1));
- base_obj.obj = append_obj_to_pack(f, d->base.sha1,
- base_obj.data, base_obj.size, type);
- find_unresolved_deltas(&base_obj, NULL);
- display_progress(progress, nr_resolved_deltas);
- }
- free(sorted_by_pos);
-}
-
-static void final(const char *final_pack_name, const char *curr_pack_name,
- const char *final_index_name, const char *curr_index_name,
- const char *keep_name, const char *keep_msg,
- unsigned char *sha1)
-{
- const char *report = "pack";
- char name[PATH_MAX];
- int err;
-
- if (!from_stdin) {
- close(input_fd);
- } else {
- fsync_or_die(output_fd, curr_pack_name);
- err = close(output_fd);
- if (err)
- die_errno("error while closing pack file");
- }
-
- if (keep_msg) {
- int keep_fd, keep_msg_len = strlen(keep_msg);
-
- if (!keep_name)
- keep_fd = odb_pack_keep(name, sizeof(name), sha1);
- else
- keep_fd = open(keep_name, O_RDWR|O_CREAT|O_EXCL, 0600);
-
- if (keep_fd < 0) {
- if (errno != EEXIST)
- die_errno("cannot write keep file '%s'",
- keep_name);
- } else {
- if (keep_msg_len > 0) {
- write_or_die(keep_fd, keep_msg, keep_msg_len);
- write_or_die(keep_fd, "\n", 1);
- }
- if (close(keep_fd) != 0)
- die_errno("cannot close written keep file '%s'",
- keep_name);
- report = "keep";
- }
- }
-
- if (final_pack_name != curr_pack_name) {
- if (!final_pack_name) {
- snprintf(name, sizeof(name), "%s/pack/pack-%s.pack",
- get_object_directory(), sha1_to_hex(sha1));
- final_pack_name = name;
- }
- if (move_temp_to_file(curr_pack_name, final_pack_name))
- die("cannot store pack file");
- } else if (from_stdin)
- chmod(final_pack_name, 0444);
-
- if (final_index_name != curr_index_name) {
- if (!final_index_name) {
- snprintf(name, sizeof(name), "%s/pack/pack-%s.idx",
- get_object_directory(), sha1_to_hex(sha1));
- final_index_name = name;
- }
- if (move_temp_to_file(curr_index_name, final_index_name))
- die("cannot store index file");
- } else
- chmod(final_index_name, 0444);
-
- if (!from_stdin) {
- printf("%s\n", sha1_to_hex(sha1));
- } else {
- char buf[48];
- int len = snprintf(buf, sizeof(buf), "%s\t%s\n",
- report, sha1_to_hex(sha1));
- write_or_die(1, buf, len);
-
- /*
- * Let's just mimic git-unpack-objects here and write
- * the last part of the input buffer to stdout.
- */
- while (input_len) {
- err = xwrite(1, input_buffer + input_offset, input_len);
- if (err <= 0)
- break;
- input_len -= err;
- input_offset += err;
- }
- }
-}
-
-static int git_index_pack_config(const char *k, const char *v, void *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);
- return 0;
- }
- return git_default_config(k, v, cb);
-}
-
-int main(int argc, char **argv)
-{
- int i, fix_thin_pack = 0;
- char *curr_pack, *pack_name = NULL;
- char *curr_index, *index_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;
- unsigned char pack_sha1[20];
-
- git_extract_argv0_path(argv[0]);
-
- if (argc == 2 && !strcmp(argv[1], "-h"))
- usage(index_pack_usage);
-
- /*
- * We wish to read the repository's config file if any, and
- * for that it is necessary to call setup_git_directory_gently().
- * However if the cwd was inside .git/objects/pack/ then we need
- * to go back there or all the pack name arguments will be wrong.
- * And in that case we cannot rely on any prefix returned by
- * setup_git_directory_gently() either.
- */
- {
- char cwd[PATH_MAX+1];
- int nongit;
-
- if (!getcwd(cwd, sizeof(cwd)-1))
- die("Unable to get current working directory");
- setup_git_directory_gently(&nongit);
- git_config(git_index_pack_config, NULL);
- if (chdir(cwd))
- die("Cannot come back to cwd");
- }
-
- for (i = 1; i < argc; i++) {
- char *arg = argv[i];
-
- if (*arg == '-') {
- if (!strcmp(arg, "--stdin")) {
- from_stdin = 1;
- } else if (!strcmp(arg, "--fix-thin")) {
- fix_thin_pack = 1;
- } else if (!strcmp(arg, "--strict")) {
- strict = 1;
- } else if (!strcmp(arg, "--keep")) {
- keep_msg = "";
- } else if (!prefixcmp(arg, "--keep=")) {
- keep_msg = arg + 7;
- } else if (!prefixcmp(arg, "--pack_header=")) {
- struct pack_header *hdr;
- char *c;
-
- hdr = (struct pack_header *)input_buffer;
- hdr->hdr_signature = htonl(PACK_SIGNATURE);
- hdr->hdr_version = htonl(strtoul(arg + 14, &c, 10));
- if (*c != ',')
- die("bad %s", arg);
- hdr->hdr_entries = htonl(strtoul(c + 1, &c, 10));
- if (*c)
- die("bad %s", arg);
- input_len = sizeof(*hdr);
- } else if (!strcmp(arg, "-v")) {
- verbose = 1;
- } else if (!strcmp(arg, "-o")) {
- if (index_name || (i+1) >= argc)
- usage(index_pack_usage);
- 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)
- die("bad %s", arg);
- if (*c == ',')
- pack_idx_off32_limit = strtoul(c+1, &c, 0);
- if (*c || pack_idx_off32_limit & 0x80000000)
- die("bad %s", arg);
- } else
- usage(index_pack_usage);
- continue;
- }
-
- if (pack_name)
- usage(index_pack_usage);
- pack_name = arg;
- }
-
- if (!pack_name && !from_stdin)
- usage(index_pack_usage);
- if (fix_thin_pack && !from_stdin)
- die("--fix-thin cannot be used without --stdin");
- if (!index_name && pack_name) {
- int len = strlen(pack_name);
- if (!has_extension(pack_name, ".pack"))
- die("packfile name '%s' does not end with '.pack'",
- pack_name);
- index_name_buf = xmalloc(len);
- memcpy(index_name_buf, pack_name, len - 5);
- strcpy(index_name_buf + len - 5, ".idx");
- index_name = index_name_buf;
- }
- if (keep_msg && !keep_name && pack_name) {
- int len = strlen(pack_name);
- if (!has_extension(pack_name, ".pack"))
- die("packfile name '%s' does not end with '.pack'",
- pack_name);
- keep_name_buf = xmalloc(len);
- memcpy(keep_name_buf, pack_name, len - 5);
- strcpy(keep_name_buf + len - 5, ".keep");
- keep_name = keep_name_buf;
- }
-
- curr_pack = open_pack_file(pack_name);
- parse_pack_header();
- objects = xmalloc((nr_objects + 1) * sizeof(struct object_entry));
- deltas = xmalloc(nr_objects * sizeof(struct delta_entry));
- parse_pack_objects(pack_sha1);
- if (nr_deltas == nr_resolved_deltas) {
- stop_progress(&progress);
- /* Flush remaining pack final 20-byte SHA1. */
- flush();
- } else {
- if (fix_thin_pack) {
- struct sha1file *f;
- unsigned char read_sha1[20], tail_sha1[20];
- char msg[48];
- int nr_unresolved = nr_deltas - nr_resolved_deltas;
- int nr_objects_initial = nr_objects;
- if (nr_unresolved <= 0)
- die("confusion beyond insanity");
- objects = xrealloc(objects,
- (nr_objects + nr_unresolved + 1)
- * sizeof(*objects));
- f = sha1fd(output_fd, curr_pack);
- fix_unresolved_deltas(f, nr_unresolved);
- sprintf(msg, "completed with %d local objects",
- nr_objects - nr_objects_initial);
- stop_progress_msg(&progress, msg);
- sha1close(f, tail_sha1, 0);
- hashcpy(read_sha1, pack_sha1);
- fixup_pack_header_footer(output_fd, pack_sha1,
- curr_pack, nr_objects,
- read_sha1, consumed_bytes-20);
- if (hashcmp(read_sha1, tail_sha1) != 0)
- die("Unexpected tail checksum for %s "
- "(disk corruption?)", curr_pack);
- }
- if (nr_deltas != nr_resolved_deltas)
- die("pack has %d unresolved deltas",
- nr_deltas - nr_resolved_deltas);
- }
- free(deltas);
- if (strict)
- check_objects();
-
- 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);
- free(idx_objects);
-
- final(pack_name, curr_pack,
- index_name, curr_index,
- keep_name, keep_msg,
- pack_sha1);
- free(objects);
- free(index_name_buf);
- free(keep_name_buf);
- if (pack_name == NULL)
- free(curr_pack);
- if (index_name == NULL)
- free(curr_index);
-
- return 0;
-}
diff --git a/pack-write.c b/pack-write.c
index 741efcd93bd2a2c105bfe2d771d32857ce2ae816..9f47cf9961212242bc01082944e83fb54da2a515 100644 (file)
--- a/pack-write.c
+++ b/pack-write.c
* the SHA1 hash of sorted object names. The objects array passed in
* will be sorted by SHA1 on exit.
*/
-char *write_idx_file(char *index_name, struct pack_idx_entry **objects,
- int nr_objects, unsigned char *sha1)
+const char *write_idx_file(const char *index_name, struct pack_idx_entry **objects,
+ int nr_objects, unsigned char *sha1)
{
struct sha1file *f;
struct pack_idx_entry **sorted_by_sha, **list, **last;
index a883334b269c76d8de1395adf2b8f3d0d7e8564f..b759a23d4d022c4acef893ec35a5dd4e2324715c 100644 (file)
--- a/pack.h
+++ b/pack.h
off_t offset;
};
-extern char *write_idx_file(char *index_name, struct pack_idx_entry **objects, int nr_objects, unsigned char *sha1);
+extern const char *write_idx_file(const char *index_name, struct pack_idx_entry **objects, int nr_objects, unsigned char *sha1);
extern int check_pack_crc(struct packed_git *p, struct pack_window **w_curs, off_t offset, off_t len, unsigned int nr);
extern int verify_pack(struct packed_git *);
extern void fixup_pack_header_footer(int, unsigned char *, const char *, uint32_t, unsigned char *, off_t);