![[tokkee]](http://tokkee.org/images/avatar.png){kind=avatar}
diff --git a/fast-import.c b/fast-import.c
index 25c3588385af63fdb9782ece39a1a4533b805260..b477dc6a8f8104cecf21b68375b7c5cf7ab8842c 100644 (file)
--- a/fast-import.c
+++ b/fast-import.c
const char *name;
struct tree_entry branch_tree;
uintmax_t last_commit;
+ uintmax_t num_notes;
unsigned active : 1;
unsigned pack_id : PACK_ID_BITS;
unsigned char sha1[20];
/* Configured limits on output */
static unsigned long max_depth = 10;
static off_t max_packsize = (1LL << 32) - 1;
+static uintmax_t big_file_threshold = 512 * 1024 * 1024;
static int force_update;
static int pack_compression_level = Z_DEFAULT_COMPRESSION;
static int pack_compression_seen;
b->table_next_branch = branch_table[hc];
b->branch_tree.versions[0].mode = S_IFDIR;
b->branch_tree.versions[1].mode = S_IFDIR;
+ b->num_notes = 0;
b->active = 0;
b->pack_id = MAX_PACK_ID;
branch_table[hc] = b;
static size_t encode_header(
enum object_type type,
- size_t size,
+ uintmax_t size,
unsigned char *hdr)
{
int n = 1;
return 0;
}
+static void truncate_pack(off_t to)
+{
+ if (ftruncate(pack_data->pack_fd, to)
+ || lseek(pack_data->pack_fd, to, SEEK_SET) != to)
+ die_errno("cannot truncate pack to skip duplicate");
+ pack_size = to;
+}
+
+static void stream_blob(uintmax_t len, unsigned char *sha1out, uintmax_t mark)
+{
+ size_t in_sz = 64 * 1024, out_sz = 64 * 1024;
+ unsigned char *in_buf = xmalloc(in_sz);
+ unsigned char *out_buf = xmalloc(out_sz);
+ struct object_entry *e;
+ unsigned char sha1[20];
+ unsigned long hdrlen;
+ off_t offset;
+ git_SHA_CTX c;
+ z_stream s;
+ int status = Z_OK;
+
+ /* Determine if we should auto-checkpoint. */
+ if ((pack_size + 60 + len) > max_packsize
+ || (pack_size + 60 + len) < pack_size)
+ cycle_packfile();
+
+ offset = pack_size;
+
+ hdrlen = snprintf((char *)out_buf, out_sz, "blob %" PRIuMAX, len) + 1;
+ if (out_sz <= hdrlen)
+ die("impossibly large object header");
+
+ git_SHA1_Init(&c);
+ git_SHA1_Update(&c, out_buf, hdrlen);
+
+ memset(&s, 0, sizeof(s));
+ deflateInit(&s, pack_compression_level);
+
+ hdrlen = encode_header(OBJ_BLOB, len, out_buf);
+ if (out_sz <= hdrlen)
+ die("impossibly large object header");
+
+ s.next_out = out_buf + hdrlen;
+ s.avail_out = out_sz - hdrlen;
+
+ while (status != Z_STREAM_END) {
+ if (0 < len && !s.avail_in) {
+ size_t cnt = in_sz < len ? in_sz : (size_t)len;
+ size_t n = fread(in_buf, 1, cnt, stdin);
+ if (!n && feof(stdin))
+ die("EOF in data (%" PRIuMAX " bytes remaining)", len);
+
+ git_SHA1_Update(&c, in_buf, n);
+ s.next_in = in_buf;
+ s.avail_in = n;
+ len -= n;
+ }
+
+ status = deflate(&s, len ? 0 : Z_FINISH);
+
+ if (!s.avail_out || status == Z_STREAM_END) {
+ size_t n = s.next_out - out_buf;
+ write_or_die(pack_data->pack_fd, out_buf, n);
+ pack_size += n;
+ s.next_out = out_buf;
+ s.avail_out = out_sz;
+ }
+
+ switch (status) {
+ case Z_OK:
+ case Z_BUF_ERROR:
+ case Z_STREAM_END:
+ continue;
+ default:
+ die("unexpected deflate failure: %d", status);
+ }
+ }
+ deflateEnd(&s);
+ git_SHA1_Final(sha1, &c);
+
+ if (sha1out)
+ hashcpy(sha1out, sha1);
+
+ e = insert_object(sha1);
+
+ if (mark)
+ insert_mark(mark, e);
+
+ if (e->offset) {
+ duplicate_count_by_type[OBJ_BLOB]++;
+ truncate_pack(offset);
+
+ } else if (find_sha1_pack(sha1, packed_git)) {
+ e->type = OBJ_BLOB;
+ e->pack_id = MAX_PACK_ID;
+ e->offset = 1; /* just not zero! */
+ duplicate_count_by_type[OBJ_BLOB]++;
+ truncate_pack(offset);
+
+ } else {
+ e->depth = 0;
+ e->type = OBJ_BLOB;
+ e->pack_id = pack_id;
+ e->offset = offset;
+ object_count++;
+ object_count_by_type[OBJ_BLOB]++;
+ }
+
+ free(in_buf);
+ free(out_buf);
+}
+
/* All calls must be guarded by find_object() or find_mark() to
* ensure the 'struct object_entry' passed was written by this
* process instance. We unpack the entry by the offset, avoiding
next_mark = 0;
}
-static void parse_data(struct strbuf *sb)
+static int parse_data(struct strbuf *sb, uintmax_t limit, uintmax_t *len_res)
{
strbuf_reset(sb);
free(term);
}
else {
- size_t n = 0, length;
+ uintmax_t len = strtoumax(command_buf.buf + 5, NULL, 10);
+ size_t n = 0, length = (size_t)len;
- length = strtoul(command_buf.buf + 5, NULL, 10);
+ if (limit && limit < len) {
+ *len_res = len;
+ return 0;
+ }
+ if (length < len)
+ die("data is too large to use in this context");
while (n < length) {
size_t s = strbuf_fread(sb, length - n, stdin);
}
skip_optional_lf();
+ return 1;
}
static int validate_raw_date(const char *src, char *result, int maxlen)
return ident;
}
-static void parse_new_blob(void)
+static void parse_and_store_blob(
+ struct last_object *last,
+ unsigned char *sha1out,
+ uintmax_t mark)
{
static struct strbuf buf = STRBUF_INIT;
+ uintmax_t len;
+
+ if (parse_data(&buf, big_file_threshold, &len))
+ store_object(OBJ_BLOB, &buf, last, sha1out, mark);
+ else {
+ if (last) {
+ strbuf_release(&last->data);
+ last->offset = 0;
+ last->depth = 0;
+ }
+ stream_blob(len, sha1out, mark);
+ skip_optional_lf();
+ }
+}
+static void parse_new_blob(void)
+{
read_next_command();
parse_mark();
- parse_data(&buf);
- store_object(OBJ_BLOB, &buf, &last_blob, NULL, next_mark);
+ parse_and_store_blob(&last_blob, NULL, next_mark);
}
static void unload_one_branch(void)
}
}
+static unsigned char convert_num_notes_to_fanout(uintmax_t num_notes)
+{
+ unsigned char fanout = 0;
+ while ((num_notes >>= 8))
+ fanout++;
+ return fanout;
+}
+
+static void construct_path_with_fanout(const char *hex_sha1,
+ unsigned char fanout, char *path)
+{
+ unsigned int i = 0, j = 0;
+ if (fanout >= 20)
+ die("Too large fanout (%u)", fanout);
+ while (fanout) {
+ path[i++] = hex_sha1[j++];
+ path[i++] = hex_sha1[j++];
+ path[i++] = '/';
+ fanout--;
+ }
+ memcpy(path + i, hex_sha1 + j, 40 - j);
+ path[i + 40 - j] = '\0';
+}
+
+static uintmax_t do_change_note_fanout(
+ struct tree_entry *orig_root, struct tree_entry *root,
+ char *hex_sha1, unsigned int hex_sha1_len,
+ char *fullpath, unsigned int fullpath_len,
+ unsigned char fanout)
+{
+ struct tree_content *t = root->tree;
+ struct tree_entry *e, leaf;
+ unsigned int i, tmp_hex_sha1_len, tmp_fullpath_len;
+ uintmax_t num_notes = 0;
+ unsigned char sha1[20];
+ char realpath[60];
+
+ for (i = 0; t && i < t->entry_count; i++) {
+ e = t->entries[i];
+ tmp_hex_sha1_len = hex_sha1_len + e->name->str_len;
+ tmp_fullpath_len = fullpath_len;
+
+ /*
+ * We're interested in EITHER existing note entries (entries
+ * with exactly 40 hex chars in path, not including directory
+ * separators), OR directory entries that may contain note
+ * entries (with < 40 hex chars in path).
+ * Also, each path component in a note entry must be a multiple
+ * of 2 chars.
+ */
+ if (!e->versions[1].mode ||
+ tmp_hex_sha1_len > 40 ||
+ e->name->str_len % 2)
+ continue;
+
+ /* This _may_ be a note entry, or a subdir containing notes */
+ memcpy(hex_sha1 + hex_sha1_len, e->name->str_dat,
+ e->name->str_len);
+ if (tmp_fullpath_len)
+ fullpath[tmp_fullpath_len++] = '/';
+ memcpy(fullpath + tmp_fullpath_len, e->name->str_dat,
+ e->name->str_len);
+ tmp_fullpath_len += e->name->str_len;
+ fullpath[tmp_fullpath_len] = '\0';
+
+ if (tmp_hex_sha1_len == 40 && !get_sha1_hex(hex_sha1, sha1)) {
+ /* This is a note entry */
+ construct_path_with_fanout(hex_sha1, fanout, realpath);
+ if (!strcmp(fullpath, realpath)) {
+ /* Note entry is in correct location */
+ num_notes++;
+ continue;
+ }
+
+ /* Rename fullpath to realpath */
+ if (!tree_content_remove(orig_root, fullpath, &leaf))
+ die("Failed to remove path %s", fullpath);
+ tree_content_set(orig_root, realpath,
+ leaf.versions[1].sha1,
+ leaf.versions[1].mode,
+ leaf.tree);
+ } else if (S_ISDIR(e->versions[1].mode)) {
+ /* This is a subdir that may contain note entries */
+ if (!e->tree)
+ load_tree(e);
+ num_notes += do_change_note_fanout(orig_root, e,
+ hex_sha1, tmp_hex_sha1_len,
+ fullpath, tmp_fullpath_len, fanout);
+ }
+
+ /* The above may have reallocated the current tree_content */
+ t = root->tree;
+ }
+ return num_notes;
+}
+
+static uintmax_t change_note_fanout(struct tree_entry *root,
+ unsigned char fanout)
+{
+ char hex_sha1[40], path[60];
+ return do_change_note_fanout(root, root, hex_sha1, 0, path, 0, fanout);
+}
+
static void file_change_m(struct branch *b)
{
const char *p = command_buf.buf + 2;
* another repository.
*/
} else if (inline_data) {
- static struct strbuf buf = STRBUF_INIT;
-
if (p != uq.buf) {
strbuf_addstr(&uq, p);
p = uq.buf;
}
read_next_command();
- parse_data(&buf);
- store_object(OBJ_BLOB, &buf, &last_blob, sha1, 0);
+ parse_and_store_blob(&last_blob, sha1, 0);
} else if (oe) {
if (oe->type != OBJ_BLOB)
die("Not a blob (actually a %s): %s",
leaf.tree);
}
-static void note_change_n(struct branch *b)
+static void note_change_n(struct branch *b, unsigned char old_fanout)
{
const char *p = command_buf.buf + 2;
static struct strbuf uq = STRBUF_INIT;
struct object_entry *oe = oe;
struct branch *s;
unsigned char sha1[20], commit_sha1[20];
+ char path[60];
uint16_t inline_data = 0;
+ unsigned char new_fanout;
/* <dataref> or 'inline' */
if (*p == ':') {
die("Invalid ref name or SHA1 expression: %s", p);
if (inline_data) {
- static struct strbuf buf = STRBUF_INIT;
-
if (p != uq.buf) {
strbuf_addstr(&uq, p);
p = uq.buf;
}
read_next_command();
- parse_data(&buf);
- store_object(OBJ_BLOB, &buf, &last_blob, sha1, 0);
+ parse_and_store_blob(&last_blob, sha1, 0);
} else if (oe) {
if (oe->type != OBJ_BLOB)
die("Not a blob (actually a %s): %s",
typename(oe->type), command_buf.buf);
- } else {
+ } else if (!is_null_sha1(sha1)) {
enum object_type type = sha1_object_info(sha1, NULL);
if (type < 0)
die("Blob not found: %s", command_buf.buf);
typename(type), command_buf.buf);
}
- tree_content_set(&b->branch_tree, sha1_to_hex(commit_sha1), sha1,
- S_IFREG | 0644, NULL);
+ construct_path_with_fanout(sha1_to_hex(commit_sha1), old_fanout, path);
+ if (tree_content_remove(&b->branch_tree, path, NULL))
+ b->num_notes--;
+
+ if (is_null_sha1(sha1))
+ return; /* nothing to insert */
+
+ b->num_notes++;
+ new_fanout = convert_num_notes_to_fanout(b->num_notes);
+ construct_path_with_fanout(sha1_to_hex(commit_sha1), new_fanout, path);
+ tree_content_set(&b->branch_tree, path, sha1, S_IFREG | 0644, NULL);
}
static void file_change_deleteall(struct branch *b)
hashclr(b->branch_tree.versions[0].sha1);
hashclr(b->branch_tree.versions[1].sha1);
load_tree(&b->branch_tree);
+ b->num_notes = 0;
}
static void parse_from_commit(struct branch *b, char *buf, unsigned long size)
char *committer = NULL;
struct hash_list *merge_list = NULL;
unsigned int merge_count;
+ unsigned char prev_fanout, new_fanout;
/* Obtain the branch name from the rest of our command */
sp = strchr(command_buf.buf, ' ') + 1;
}
if (!committer)
die("Expected committer but didn't get one");
- parse_data(&msg);
+ parse_data(&msg, 0, NULL);
read_next_command();
parse_from(b);
merge_list = parse_merge(&merge_count);
load_branch(b);
}
+ prev_fanout = convert_num_notes_to_fanout(b->num_notes);
+
/* file_change* */
while (command_buf.len > 0) {
if (!prefixcmp(command_buf.buf, "M "))
else if (!prefixcmp(command_buf.buf, "C "))
file_change_cr(b, 0);
else if (!prefixcmp(command_buf.buf, "N "))
- note_change_n(b);
+ note_change_n(b, prev_fanout);
else if (!strcmp("deleteall", command_buf.buf))
file_change_deleteall(b);
else {
break;
}
+ new_fanout = convert_num_notes_to_fanout(b->num_notes);
+ if (new_fanout != prev_fanout)
+ b->num_notes = change_note_fanout(&b->branch_tree, new_fanout);
+
/* build the tree and the commit */
store_tree(&b->branch_tree);
hashcpy(b->branch_tree.versions[0].sha1,
tagger = NULL;
/* tag payload/message */
- parse_data(&msg);
+ parse_data(&msg, 0, NULL);
/* build the tag object */
strbuf_reset(&new_data);
die("unknown --date-format argument %s", fmt);
}
-static void option_max_pack_size(const char *packsize)
-{
- max_packsize = strtoumax(packsize, NULL, 0) * 1024 * 1024;
-}
-
static void option_depth(const char *depth)
{
max_depth = strtoul(depth, NULL, 0);
static int parse_one_option(const char *option)
{
if (!prefixcmp(option, "max-pack-size=")) {
- option_max_pack_size(option + 14);
+ unsigned long v;
+ if (!git_parse_ulong(option + 14, &v))
+ return 0;
+ if (v < 8192) {
+ warning("max-pack-size is now in bytes, assuming --max-pack-size=%lum", v);
+ v *= 1024 * 1024;
+ } else if (v < 1024 * 1024) {
+ warning("minimum max-pack-size is 1 MiB");
+ v = 1024 * 1024;
+ }
+ max_packsize = v;
+ } else if (!prefixcmp(option, "big-file-threshold=")) {
+ unsigned long v;
+ if (!git_parse_ulong(option + 19, &v))
+ return 0;
+ big_file_threshold = v;
} else if (!prefixcmp(option, "depth=")) {
option_depth(option + 6);
} else if (!prefixcmp(option, "active-branches=")) {
pack_compression_seen = 1;
return 0;
}
+ if (!strcmp(k, "core.bigfilethreshold")) {
+ long n = git_config_int(k, v);
+ big_file_threshold = 0 < n ? n : 0;
+ }
return git_default_config(k, v, cb);
}
static const char fast_import_usage[] =
-"git fast-import [--date-format=f] [--max-pack-size=n] [--depth=n] [--active-branches=n] [--export-marks=marks.file]";
+"git fast-import [--date-format=f] [--max-pack-size=n] [--big-file-threshold=n] [--depth=n] [--active-branches=n] [--export-marks=marks.file]";
static void parse_argv(void)
{