From: "Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>
To: git@vger.kernel.org
Cc: "Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>
Subject: [PATCH 08/12] index-pack: parse v4 tree format
Date: Sat, 7 Sep 2013 17:43:15 +0700 [thread overview]
Message-ID: <1378550599-25365-9-git-send-email-pclouds@gmail.com> (raw)
In-Reply-To: <1378550599-25365-1-git-send-email-pclouds@gmail.com>
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
builtin/index-pack.c | 104 +++++++++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 100 insertions(+), 4 deletions(-)
diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index 210b78d..51ca64b 100644
--- a/builtin/index-pack.c
+++ b/builtin/index-pack.c
@@ -319,6 +319,21 @@ static const unsigned char *read_sha1ref(void)
return sha1_table + index * 20;
}
+static const unsigned char *read_sha1table_ref(void)
+{
+ const unsigned char *sha1 = read_sha1ref();
+ if (sha1 < sha1_table || sha1 >= sha1_table + nr_objects * 20) {
+ unsigned char *found;
+ found = bsearch(sha1, sha1_table, nr_objects, 20,
+ (int (*)(const void *, const void *))hashcmp);
+ if (!found)
+ bad_object(consumed_bytes,
+ _("SHA-1 %s not found in SHA-1 table"),
+ sha1_to_hex(sha1));
+ }
+ return sha1;
+}
+
static const unsigned char *read_dictref(struct packv4_dict *dict)
{
unsigned int index = read_varint();
@@ -561,17 +576,93 @@ static void *unpack_commit_v4(unsigned int offset,
return dst.buf;
}
-static void *unpack_entry_data(unsigned long offset, unsigned long size,
- enum object_type type, unsigned char *sha1)
+/*
+ * v4 trees are actually kind of deltas and we don't do delta in the
+ * first pass. This function only walks through a tree object to find
+ * the end offset, register object dependencies and performs limited
+ * validation.
+ */
+static void *unpack_tree_v4(struct object_entry *obj,
+ unsigned int offset, unsigned long size,
+ unsigned char *sha1)
+{
+ unsigned int nr = read_varint();
+ const unsigned char *last_base = NULL;
+ struct strbuf sb = STRBUF_INIT;
+ while (nr) {
+ unsigned int copy_start_or_path = read_varint();
+ if (copy_start_or_path & 1) { /* copy_start */
+ unsigned int copy_count = read_varint();
+ if (copy_count & 1) { /* first delta */
+ last_base = read_sha1table_ref();
+ } else if (!last_base)
+ bad_object(offset,
+ _("bad copy count index in unpack_tree_v4"));
+ copy_count >>= 1;
+ if (!copy_count)
+ bad_object(offset,
+ _("bad copy count index in unpack_tree_v4"));
+ nr -= copy_count;
+ } else { /* path */
+ unsigned int path_idx = copy_start_or_path >> 1;
+ const unsigned char *entry_sha1;
+
+ if (path_idx >= path_dict->nb_entries)
+ bad_object(offset,
+ _("bad path index in unpack_tree_v4"));
+ entry_sha1 = read_sha1ref();
+ nr--;
+
+ if (!last_base) {
+ const unsigned char *path;
+ unsigned mode;
+
+ path = path_dict->data + path_dict->offsets[path_idx];
+ mode = (path[0] << 8) | path[1];
+ strbuf_addf(&sb, "%o %s%c", mode, path+2, '\0');
+ strbuf_add(&sb, entry_sha1, 20);
+ if (sb.len > size)
+ bad_object(offset,
+ _("tree larger than expected"));
+ }
+ }
+ }
+
+ if (last_base) {
+ strbuf_release(&sb);
+ return NULL;
+ } else {
+ git_SHA_CTX ctx;
+ char hdr[32];
+ int hdrlen;
+
+ if (sb.len != size)
+ bad_object(offset, _("tree size mismatch"));
+
+ hdrlen = sprintf(hdr, "tree %lu", size) + 1;
+ git_SHA1_Init(&ctx);
+ git_SHA1_Update(&ctx, hdr, hdrlen);
+ git_SHA1_Update(&ctx, sb.buf, size);
+ git_SHA1_Final(sha1, &ctx);
+ return strbuf_detach(&sb, NULL);
+ }
+}
+
+static void *unpack_entry_data(struct object_entry *obj, unsigned char *sha1)
{
static char fixed_buf[8192];
void *buf;
git_SHA_CTX c;
char hdr[32];
int hdrlen;
+ unsigned long offset = obj->idx.offset;
+ unsigned long size = obj->size;
+ enum object_type type = obj->type;
if (type == OBJ_PV4_COMMIT)
return unpack_commit_v4(offset, size, sha1);
+ if (type == OBJ_PV4_TREE)
+ return unpack_tree_v4(obj, offset, size, sha1);
if (!is_delta_type(type)) {
hdrlen = sprintf(hdr, "%s %lu", typename(type), size) + 1;
@@ -640,16 +731,19 @@ static void *unpack_raw_entry(struct object_entry *obj,
case OBJ_BLOB:
case OBJ_TAG:
break;
-
case OBJ_PV4_COMMIT:
obj->real_type = OBJ_COMMIT;
break;
+ case OBJ_PV4_TREE:
+ obj->real_type = OBJ_TREE;
+ 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->type, sha1);
+ data = unpack_entry_data(obj, sha1);
obj->idx.crc32 = input_crc32;
return data;
}
@@ -1186,6 +1280,8 @@ static void parse_pack_objects(unsigned char *sha1)
nr_deltas++;
delta->obj_no = i;
delta++;
+ } else if (!data && obj->type == OBJ_PV4_TREE) {
+ /* delay sha1_object() until second pass */
} else if (!data) {
/* large blobs, check later */
obj->real_type = OBJ_BAD;
--
1.8.2.83.gc99314b
next prev parent reply other threads:[~2013-09-07 10:41 UTC|newest]
Thread overview: 124+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-09-05 6:19 [PATCH 00/38] pack version 4 basic functionalities Nicolas Pitre
2013-09-05 6:19 ` [PATCH 01/38] pack v4: initial pack dictionary structure and code Nicolas Pitre
2013-09-05 6:19 ` [PATCH 02/38] export packed_object_info() Nicolas Pitre
2013-09-05 6:19 ` [PATCH 03/38] pack v4: scan tree objects Nicolas Pitre
2013-09-05 6:19 ` [PATCH 04/38] pack v4: add tree entry mode support to dictionary entries Nicolas Pitre
2013-09-05 6:19 ` [PATCH 05/38] pack v4: add commit object parsing Nicolas Pitre
2013-09-05 10:30 ` SZEDER Gábor
2013-09-05 17:30 ` Nicolas Pitre
2013-09-05 6:19 ` [PATCH 06/38] pack v4: split the object list and dictionary creation Nicolas Pitre
2013-09-05 6:19 ` [PATCH 07/38] pack v4: move to struct pack_idx_entry and get rid of our own struct idx_entry Nicolas Pitre
2013-09-05 6:19 ` [PATCH 08/38] pack v4: basic SHA1 reference encoding Nicolas Pitre
2013-09-05 6:19 ` [PATCH 09/38] introduce get_sha1_lowhex() Nicolas Pitre
2013-09-05 6:19 ` [PATCH 10/38] pack v4: commit object encoding Nicolas Pitre
2013-09-06 6:57 ` Junio C Hamano
2013-09-06 21:28 ` Nicolas Pitre
2013-09-06 22:08 ` Junio C Hamano
2013-09-07 4:41 ` Nicolas Pitre
2013-09-05 6:19 ` [PATCH 11/38] pack v4: tree " Nicolas Pitre
2013-09-05 6:19 ` [PATCH 12/38] pack v4: dictionary table output Nicolas Pitre
2013-09-05 6:19 ` [PATCH 13/38] pack v4: creation code Nicolas Pitre
2013-09-05 6:19 ` [PATCH 14/38] pack v4: object headers Nicolas Pitre
2013-09-05 6:19 ` [PATCH 15/38] pack v4: object data copy Nicolas Pitre
2013-09-05 6:19 ` [PATCH 16/38] pack v4: object writing Nicolas Pitre
2013-09-05 6:19 ` [PATCH 17/38] pack v4: tree object delta encoding Nicolas Pitre
2013-09-05 6:19 ` [PATCH 18/38] pack v4: load delta candidate for encoding tree objects Nicolas Pitre
2013-09-05 6:19 ` [PATCH 19/38] packv4-create: optimize delta encoding Nicolas Pitre
2013-09-05 6:19 ` [PATCH 20/38] pack v4: honor pack.compression config option Nicolas Pitre
2013-09-05 6:19 ` [PATCH 21/38] pack v4: relax commit parsing a bit Nicolas Pitre
2013-09-05 6:19 ` [PATCH 22/38] pack index v3 Nicolas Pitre
2013-09-05 6:19 ` [PATCH 23/38] packv4-create: normalize pack name to properly generate the pack index file name Nicolas Pitre
2013-09-05 6:19 ` [PATCH 24/38] packv4-create: add progress display Nicolas Pitre
2013-09-05 6:19 ` [PATCH 25/38] pack v4: initial pack index v3 support on the read side Nicolas Pitre
2013-09-05 6:19 ` [PATCH 26/38] pack v4: object header decode Nicolas Pitre
2013-09-05 6:19 ` [PATCH 27/38] pack v4: code to obtain a SHA1 from a sha1ref Nicolas Pitre
2013-09-05 6:19 ` [PATCH 28/38] pack v4: code to load and prepare a pack dictionary table for use Nicolas Pitre
2013-09-05 6:19 ` [PATCH 29/38] pack v4: code to retrieve a name Nicolas Pitre
2013-09-05 6:19 ` [PATCH 30/38] pack v4: code to recreate a canonical commit object Nicolas Pitre
2013-09-05 6:19 ` [PATCH 31/38] sha1_file.c: make use of decode_varint() Nicolas Pitre
2013-09-05 7:35 ` SZEDER Gábor
2013-09-05 6:19 ` [PATCH 32/38] pack v4: parse delta base reference Nicolas Pitre
2013-09-05 6:19 ` [PATCH 33/38] pack v4: we can read commit objects now Nicolas Pitre
2013-09-05 6:19 ` [PATCH 34/38] pack v4: code to retrieve a path component Nicolas Pitre
2013-09-05 6:19 ` [PATCH 35/38] pack v4: decode tree objects Nicolas Pitre
2013-09-05 6:19 ` [PATCH 36/38] pack v4: get " Nicolas Pitre
2013-09-05 6:20 ` [PATCH 37/38] pack v4: introduce "escape hatches" in the name and path indexes Nicolas Pitre
2013-09-05 19:02 ` Nicolas Pitre
2013-09-05 21:48 ` Nicolas Pitre
2013-09-05 23:57 ` Duy Nguyen
2013-09-05 6:20 ` [PATCH 38/38] packv4-create: add a command line argument to limit tree copy sequences Nicolas Pitre
2013-09-07 10:43 ` [PATCH 00/12] pack v4 support in index-pack Nguyễn Thái Ngọc Duy
2013-09-07 10:43 ` [PATCH 01/12] pack v4: split pv4_create_dict() out of load_dict() Nguyễn Thái Ngọc Duy
2013-09-07 10:43 ` [PATCH 02/12] index-pack: split out varint decoding code Nguyễn Thái Ngọc Duy
2013-09-07 10:43 ` [PATCH 03/12] index-pack: do not allocate buffer for unpacking deltas in the first pass Nguyễn Thái Ngọc Duy
2013-09-07 10:43 ` [PATCH 04/12] index-pack: split inflate/digest code out of unpack_entry_data Nguyễn Thái Ngọc Duy
2013-09-07 10:43 ` [PATCH 05/12] index-pack: parse v4 header and dictionaries Nguyễn Thái Ngọc Duy
2013-09-08 2:14 ` Nicolas Pitre
2013-09-07 10:43 ` [PATCH 06/12] index-pack: make sure all objects are registered in v4's SHA-1 table Nguyễn Thái Ngọc Duy
2013-09-07 10:43 ` [PATCH 07/12] index-pack: parse v4 commit format Nguyễn Thái Ngọc Duy
2013-09-07 10:43 ` Nguyễn Thái Ngọc Duy [this message]
2013-09-08 2:52 ` [PATCH 08/12] index-pack: parse v4 tree format Nicolas Pitre
2013-09-07 10:43 ` [PATCH 09/12] index-pack: move delta base queuing code to unpack_raw_entry Nguyễn Thái Ngọc Duy
2013-09-07 10:43 ` [PATCH 10/12] index-pack: record all delta bases in v4 (tree and ref-delta) Nguyễn Thái Ngọc Duy
2013-09-07 10:43 ` [PATCH 11/12] index-pack: skip looking for ofs-deltas in v4 as they are not allowed Nguyễn Thái Ngọc Duy
2013-09-07 10:43 ` [PATCH 12/12] index-pack: resolve v4 one-base trees Nguyễn Thái Ngọc Duy
2013-09-08 3:28 ` Nicolas Pitre
2013-09-08 3:44 ` Duy Nguyen
2013-09-08 7:22 ` [PATCH v2 00/14] pack v4 support in index-pack Nguyễn Thái Ngọc Duy
2013-09-08 7:22 ` [PATCH v2 01/14] pack v4: split pv4_create_dict() out of load_dict() Nguyễn Thái Ngọc Duy
2013-09-08 7:22 ` [PATCH v2 02/14] pack v4: add pv4_free_dict() Nguyễn Thái Ngọc Duy
2013-09-08 7:22 ` [PATCH v2 03/14] index-pack: add more comments on some big functions Nguyễn Thái Ngọc Duy
2013-09-08 7:22 ` [PATCH v2 04/14] index-pack: split out varint decoding code Nguyễn Thái Ngọc Duy
2013-09-08 7:22 ` [PATCH v2 05/14] index-pack: do not allocate buffer for unpacking deltas in the first pass Nguyễn Thái Ngọc Duy
2013-09-08 7:22 ` [PATCH v2 06/14] index-pack: split inflate/digest code out of unpack_entry_data Nguyễn Thái Ngọc Duy
2013-09-08 7:22 ` [PATCH v2 07/14] index-pack: parse v4 header and dictionaries Nguyễn Thái Ngọc Duy
2013-09-08 7:22 ` [PATCH v2 08/14] index-pack: make sure all objects are registered in v4's SHA-1 table Nguyễn Thái Ngọc Duy
2013-09-08 7:22 ` [PATCH v2 09/14] index-pack: parse v4 commit format Nguyễn Thái Ngọc Duy
2013-09-08 7:22 ` [PATCH v2 10/14] index-pack: parse v4 tree format Nguyễn Thái Ngọc Duy
2013-09-08 7:22 ` [PATCH v2 11/14] index-pack: move delta base queuing code to unpack_raw_entry Nguyễn Thái Ngọc Duy
2013-09-08 7:22 ` [PATCH v2 12/14] index-pack: record all delta bases in v4 (tree and ref-delta) Nguyễn Thái Ngọc Duy
2013-09-08 7:22 ` [PATCH v2 13/14] index-pack: skip looking for ofs-deltas in v4 as they are not allowed Nguyễn Thái Ngọc Duy
2013-09-08 7:22 ` [PATCH v2 14/14] index-pack: resolve v4 one-base trees Nguyễn Thái Ngọc Duy
2013-09-08 15:04 ` [PATCH 00/11] pack v4 support in pack-objects Nguyễn Thái Ngọc Duy
2013-09-08 15:04 ` [PATCH 01/11] pack v4: allocate dicts from the beginning Nguyễn Thái Ngọc Duy
2013-09-08 15:04 ` [PATCH 02/11] pack v4: stop using static/global variables in packv4-create.c Nguyễn Thái Ngọc Duy
2013-09-08 15:04 ` [PATCH 03/11] pack v4: move packv4-create.c to libgit.a Nguyễn Thái Ngọc Duy
2013-09-08 20:56 ` Nicolas Pitre
2013-09-08 15:04 ` [PATCH 04/11] pack v4: add version argument to write_pack_header Nguyễn Thái Ngọc Duy
2013-09-08 15:04 ` [PATCH 05/11] pack-write.c: add pv4_encode_in_pack_object_header Nguyễn Thái Ngọc Duy
2013-09-08 20:51 ` Nicolas Pitre
2013-09-08 15:04 ` [PATCH 06/11] pack-objects: add --version to specify written pack version Nguyễn Thái Ngọc Duy
2013-09-08 15:04 ` [PATCH 07/11] list-objects.c: add show_tree_entry callback to traverse_commit_list Nguyễn Thái Ngọc Duy
2013-09-08 15:04 ` [PATCH 08/11] pack-objects: create pack v4 tables Nguyễn Thái Ngọc Duy
2013-09-09 10:40 ` Duy Nguyen
2013-09-09 13:07 ` Nicolas Pitre
2013-09-09 15:21 ` Junio C Hamano
2013-09-08 15:04 ` [PATCH 09/11] pack-objects: do not cache delta for v4 trees Nguyễn Thái Ngọc Duy
2013-09-08 15:04 ` [PATCH 10/11] pack-objects: exclude commits out of delta objects in v4 Nguyễn Thái Ngọc Duy
2013-09-08 15:04 ` [PATCH 11/11] pack-objects: support writing pack v4 Nguyễn Thái Ngọc Duy
2013-09-09 13:57 ` [PATCH v2 00/16] pack v4 support in pack-objects Nguyễn Thái Ngọc Duy
2013-09-09 13:57 ` [PATCH v2 01/16] pack v4: allocate dicts from the beginning Nguyễn Thái Ngọc Duy
2013-09-09 13:57 ` [PATCH v2 02/16] pack v4: stop using static/global variables in packv4-create.c Nguyễn Thái Ngọc Duy
2013-09-09 13:57 ` [PATCH v2 03/16] pack v4: move packv4-create.c to libgit.a Nguyễn Thái Ngọc Duy
2013-09-09 13:57 ` [PATCH v2 04/16] pack v4: add version argument to write_pack_header Nguyễn Thái Ngọc Duy
2013-09-09 13:57 ` [PATCH v2 05/16] pack_write: tighten valid object type check in encode_in_pack_object_header Nguyễn Thái Ngọc Duy
2013-09-09 13:57 ` [PATCH v2 06/16] pack-write.c: add pv4_encode_object_header Nguyễn Thái Ngọc Duy
2013-09-09 13:57 ` [PATCH v2 07/16] pack-objects: add --version to specify written pack version Nguyễn Thái Ngọc Duy
2013-09-09 13:57 ` [PATCH v2 08/16] list-objects.c: add show_tree_entry callback to traverse_commit_list Nguyễn Thái Ngọc Duy
2013-09-09 13:58 ` [PATCH v2 09/16] pack-objects: do not cache delta for v4 trees Nguyễn Thái Ngọc Duy
2013-09-09 13:58 ` [PATCH v2 10/16] pack-objects: exclude commits out of delta objects in v4 Nguyễn Thái Ngọc Duy
2013-09-09 13:58 ` [PATCH v2 11/16] pack-objects: create pack v4 tables Nguyễn Thái Ngọc Duy
2013-09-09 13:58 ` [PATCH v2 12/16] pack-objects: prepare SHA-1 table in v4 Nguyễn Thái Ngọc Duy
2013-09-09 13:58 ` [PATCH v2 13/16] pack-objects: support writing pack v4 Nguyễn Thái Ngọc Duy
2013-09-09 13:58 ` [PATCH v2 14/16] pack v4: support "end-of-pack" indicator in index-pack and pack-objects Nguyễn Thái Ngọc Duy
2013-09-09 13:58 ` [PATCH v2 15/16] index-pack: use nr_objects_final as sha1_table size Nguyễn Thái Ngọc Duy
2013-09-09 15:01 ` Nicolas Pitre
2013-09-09 18:34 ` Junio C Hamano
2013-09-09 18:46 ` Nicolas Pitre
2013-09-09 18:56 ` Junio C Hamano
2013-09-09 19:11 ` Nicolas Pitre
2013-09-09 19:30 ` Junio C Hamano
2013-09-09 19:56 ` Nicolas Pitre
2013-09-10 0:45 ` Duy Nguyen
2013-09-12 15:34 ` Nicolas Pitre
2013-09-09 13:58 ` [PATCH v2 16/16] index-pack: support completing thin packs v4 Nguyễn Thái Ngọc Duy
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: http://vger.kernel.org/majordomo-info.html
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1378550599-25365-9-git-send-email-pclouds@gmail.com \
--to=pclouds@gmail.com \
--cc=git@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this public inbox
https://80x24.org/mirrors/git.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).