cmd ::= new_blob
| new_commit
| new_tag
+ | reset_branch
;
new_blob ::= 'blob' lf
'committer' sp name '<' email '>' ts tz lf
commit_msg
('from' sp (ref_str | hexsha1 | sha1exp_str | idnum) lf)?
+ ('merge' sp (ref_str | hexsha1 | sha1exp_str | idnum) lf)*
file_change*
lf;
commit_msg ::= data;
tag_msg;
tag_msg ::= data;
+ reset_branch ::= 'reset' sp ref_str lf
+ ('from' sp (ref_str | hexsha1 | sha1exp_str | idnum) lf)?
+ lf;
+
+ checkpoint ::= 'checkpoint' lf
+ lf;
+
# note: the first idnum in a stream should be 1 and subsequent
# idnums should not have gaps between values as this will cause
# the stream parser to reserve space for the gapped values. An
struct object_entry
{
struct object_entry *next;
- enum object_type type;
unsigned long offset;
+ unsigned type : TYPE_BITS;
+ unsigned pack_id : 16;
unsigned char sha1[20];
};
struct last_object
{
void *data;
- unsigned int len;
+ unsigned long len;
+ unsigned long offset;
unsigned int depth;
- unsigned char sha1[20];
+ unsigned no_free:1;
};
struct mem_pool
{
struct tree_content *tree;
struct atom_str* name;
- unsigned int mode;
- unsigned char sha1[20];
+ struct tree_entry_ms
+ {
+ unsigned int mode;
+ unsigned char sha1[20];
+ } versions[2];
};
struct tree_content
{
unsigned int entry_capacity; /* must match avail_tree_content */
unsigned int entry_count;
+ unsigned int delta_depth;
struct tree_entry *entries[FLEX_ARRAY]; /* more */
};
unsigned char sha1[20];
};
+struct dbuf
+{
+ void *buffer;
+ size_t capacity;
+};
+
+struct hash_list
+{
+ struct hash_list *next;
+ unsigned char sha1[20];
+};
/* Stats and misc. counters */
static unsigned long max_depth = 10;
static unsigned long alloc_count;
static unsigned long branch_count;
static unsigned long branch_load_count;
-static unsigned long remap_count;
static unsigned long object_count;
-static unsigned long duplicate_count;
static unsigned long marks_set_count;
-static unsigned long object_count_by_type[9];
-static unsigned long duplicate_count_by_type[9];
+static unsigned long object_count_by_type[1 << TYPE_BITS];
+static unsigned long duplicate_count_by_type[1 << TYPE_BITS];
+static unsigned long delta_count_by_type[1 << TYPE_BITS];
/* Memory pools */
static size_t mem_pool_alloc = 2*1024*1024 - sizeof(struct mem_pool);
static struct atom_str **atom_table;
/* The .pack file being generated */
+static const char *base_name;
+static unsigned int pack_id;
+static char *idx_name;
+static struct packed_git *pack_data;
+static struct packed_git **all_packs;
static int pack_fd;
static unsigned long pack_size;
static unsigned char pack_sha1[20];
-static void* pack_base;
-static size_t pack_mlen;
/* Table of objects we've written. */
-static unsigned int object_entry_alloc = 1000;
+static unsigned int object_entry_alloc = 5000;
static struct object_entry_pool *blocks;
static struct object_entry *object_table[1 << 16];
static struct mark_set *marks;
+static const char* mark_file;
/* Our last blob */
static struct last_object last_blob;
static void *avail_tree_entry;
static unsigned int avail_tree_table_sz = 100;
static struct avail_tree_content **avail_tree_table;
+static struct dbuf old_tree;
+static struct dbuf new_tree;
/* Branch data */
static unsigned long max_active_branches = 5;
/* Input stream parsing */
static struct strbuf command_buf;
static unsigned long next_mark;
+static struct dbuf new_data;
+static FILE* branch_log;
-static void alloc_objects(int cnt)
+static void alloc_objects(unsigned int cnt)
{
struct object_entry_pool *b;
alloc_objects(object_entry_alloc);
e = blocks->next_free++;
- memcpy(e->sha1, sha1, sizeof(e->sha1));
+ e->pack_id = pack_id;
+ hashcpy(e->sha1, sha1);
return e;
}
unsigned int h = sha1[0] << 8 | sha1[1];
struct object_entry *e;
for (e = object_table[h]; e; e = e->next)
- if (!memcmp(sha1, e->sha1, sizeof(e->sha1)))
+ if (!hashcmp(sha1, e->sha1))
return e;
return NULL;
}
struct object_entry *p = NULL;
while (e) {
- if (!memcmp(sha1, e->sha1, sizeof(e->sha1)))
+ if (!hashcmp(sha1, e->sha1))
return e;
p = e;
e = e->next;
return r;
}
+static void size_dbuf(struct dbuf *b, size_t maxlen)
+{
+ if (b->buffer) {
+ if (b->capacity >= maxlen)
+ return;
+ free(b->buffer);
+ }
+ b->capacity = ((maxlen / 1024) + 1) * 1024;
+ b->buffer = xmalloc(b->capacity);
+}
+
static void insert_mark(unsigned long idnum, struct object_entry *oe)
{
struct mark_set *s = marks;
b = pool_calloc(1, sizeof(struct branch));
b->name = pool_strdup(name);
b->table_next_branch = branch_table[hc];
+ b->branch_tree.versions[0].mode = S_IFDIR;
+ b->branch_tree.versions[1].mode = S_IFDIR;
branch_table[hc] = b;
branch_count++;
return b;
t = (struct tree_content*)f;
t->entry_count = 0;
+ t->delta_depth = 0;
return t;
}
{
struct tree_content *r = new_tree_content(t->entry_count + amt);
r->entry_count = t->entry_count;
+ r->delta_depth = t->delta_depth;
memcpy(r->entries,t->entries,t->entry_count*sizeof(t->entries[0]));
release_tree_content(t);
return r;
if (!avail_tree_entry) {
unsigned int n = tree_entry_alloc;
+ total_allocd += n * sizeof(struct tree_entry);
avail_tree_entry = e = xmalloc(n * sizeof(struct tree_entry));
- while (n--) {
+ while (n-- > 1) {
*((void**)e) = e + 1;
e++;
}
+ *((void**)e) = NULL;
}
e = avail_tree_entry;
}
}
-static void ywrite(int fd, void *buffer, size_t length)
+static void start_packfile()
{
- ssize_t ret = 0;
- while (ret < length) {
- ssize_t size = xwrite(fd, (char *) buffer + ret, length - ret);
- if (!size)
- die("Write to descriptor %i: end of file", fd);
- if (size < 0)
- die("Write to descriptor %i: %s", fd, strerror(errno));
- ret += size;
+ struct packed_git *p;
+ struct pack_header hdr;
+
+ idx_name = xmalloc(strlen(base_name) + 11);
+ p = xcalloc(1, sizeof(*p) + strlen(base_name) + 13);
+ sprintf(p->pack_name, "%s%5.5i.pack", base_name, pack_id + 1);
+ sprintf(idx_name, "%s%5.5i.idx", base_name, pack_id + 1);
+
+ pack_fd = open(p->pack_name, O_RDWR|O_CREAT|O_EXCL, 0666);
+ if (pack_fd < 0)
+ die("Can't create %s: %s", p->pack_name, strerror(errno));
+ p->pack_fd = pack_fd;
+
+ hdr.hdr_signature = htonl(PACK_SIGNATURE);
+ hdr.hdr_version = htonl(2);
+ hdr.hdr_entries = 0;
+ write_or_die(pack_fd, &hdr, sizeof(hdr));
+
+ pack_data = p;
+ pack_size = sizeof(hdr);
+ object_count = 0;
+
+ all_packs = xrealloc(all_packs, sizeof(*all_packs) * (pack_id + 1));
+ all_packs[pack_id] = p;
+}
+
+static void fixup_header_footer()
+{
+ SHA_CTX c;
+ char hdr[8];
+ unsigned long cnt;
+ char *buf;
+
+ if (lseek(pack_fd, 0, SEEK_SET) != 0)
+ die("Failed seeking to start: %s", strerror(errno));
+
+ SHA1_Init(&c);
+ yread(pack_fd, hdr, 8);
+ SHA1_Update(&c, hdr, 8);
+
+ cnt = htonl(object_count);
+ SHA1_Update(&c, &cnt, 4);
+ write_or_die(pack_fd, &cnt, 4);
+
+ buf = xmalloc(128 * 1024);
+ for (;;) {
+ size_t n = xread(pack_fd, buf, 128 * 1024);
+ if (n <= 0)
+ break;
+ SHA1_Update(&c, buf, n);
}
+ free(buf);
+
+ SHA1_Final(pack_sha1, &c);
+ write_or_die(pack_fd, pack_sha1, sizeof(pack_sha1));
+}
+
+static int oecmp (const void *a_, const void *b_)
+{
+ struct object_entry *a = *((struct object_entry**)a_);
+ struct object_entry *b = *((struct object_entry**)b_);
+ return hashcmp(a->sha1, b->sha1);
+}
+
+static void write_index(const char *idx_name)
+{
+ struct sha1file *f;
+ struct object_entry **idx, **c, **last, *e;
+ struct object_entry_pool *o;
+ unsigned int array[256];
+ int i;
+
+ /* Build the sorted table of object IDs. */
+ idx = xmalloc(object_count * sizeof(struct object_entry*));
+ c = idx;
+ for (o = blocks; o; o = o->next_pool)
+ for (e = o->entries; e != o->next_free; e++)
+ if (pack_id == e->pack_id)
+ *c++ = e;
+ last = idx + object_count;
+ qsort(idx, object_count, sizeof(struct object_entry*), oecmp);
+
+ /* Generate the fan-out array. */
+ c = idx;
+ for (i = 0; i < 256; i++) {
+ struct object_entry **next = c;;
+ while (next < last) {
+ if ((*next)->sha1[0] != i)
+ break;
+ next++;
+ }
+ array[i] = htonl(next - idx);
+ c = next;
+ }
+
+ f = sha1create("%s", idx_name);
+ sha1write(f, array, 256 * sizeof(int));
+ for (c = idx; c != last; c++) {
+ unsigned int offset = htonl((*c)->offset);
+ sha1write(f, &offset, 4);
+ sha1write(f, (*c)->sha1, sizeof((*c)->sha1));
+ }
+ sha1write(f, pack_sha1, sizeof(pack_sha1));
+ sha1close(f, NULL, 1);
+ free(idx);
+}
+
+static void end_packfile()
+{
+ struct packed_git *old_p = pack_data, *new_p;
+
+ if (object_count) {
+ fixup_header_footer();
+ write_index(idx_name);
+
+ /* Register the packfile with core git's machinary. */
+ new_p = add_packed_git(idx_name, strlen(idx_name), 1);
+ if (!new_p)
+ die("core git rejected index %s", idx_name);
+ new_p->windows = old_p->windows;
+ new_p->pack_fd = old_p->pack_fd;
+ all_packs[pack_id++] = new_p;
+ install_packed_git(new_p);
+ }
+ else {
+ close(pack_fd);
+ unlink(old_p->pack_name);
+ }
+ free(old_p);
+ free(idx_name);
+
+ /* We can't carry a delta across packfiles. */
+ free(last_blob.data);
+ last_blob.data = NULL;
+ last_blob.len = 0;
+ last_blob.offset = 0;
+ last_blob.depth = 0;
}
static size_t encode_header(
int n = 1;
unsigned char c;
- if (type < OBJ_COMMIT || type > OBJ_DELTA)
+ if (type < OBJ_COMMIT || type > OBJ_REF_DELTA)
die("bad type %d", type);
c = (type << 4) | (size & 15);
SHA1_Update(&c, dat, datlen);
SHA1_Final(sha1, &c);
if (sha1out)
- memcpy(sha1out, sha1, sizeof(sha1));
+ hashcpy(sha1out, sha1);
e = insert_object(sha1);
if (mark)
insert_mark(mark, e);
if (e->offset) {
- duplicate_count++;
duplicate_count_by_type[type]++;
return 1;
}
deflateInit(&s, zlib_compression_level);
if (delta) {
+ unsigned long ofs = e->offset - last->offset;
+ unsigned pos = sizeof(hdr) - 1;
+
+ delta_count_by_type[type]++;
last->depth++;
s.next_in = delta;
s.avail_in = deltalen;
- hdrlen = encode_header(OBJ_DELTA, deltalen, hdr);
- ywrite(pack_fd, hdr, hdrlen);
- ywrite(pack_fd, last->sha1, sizeof(sha1));
- pack_size += hdrlen + sizeof(sha1);
+
+ hdrlen = encode_header(OBJ_OFS_DELTA, deltalen, hdr);
+ write_or_die(pack_fd, hdr, hdrlen);
+ pack_size += hdrlen;
+
+ hdr[pos] = ofs & 127;
+ while (ofs >>= 7)
+ hdr[--pos] = 128 | (--ofs & 127);
+ write_or_die(pack_fd, hdr + pos, sizeof(hdr) - pos);
+ pack_size += sizeof(hdr) - pos;
} else {
if (last)
last->depth = 0;
s.next_in = dat;
s.avail_in = datlen;
hdrlen = encode_header(type, datlen, hdr);
- ywrite(pack_fd, hdr, hdrlen);
+ write_or_die(pack_fd, hdr, hdrlen);
pack_size += hdrlen;
}
/* nothing */;
deflateEnd(&s);
- ywrite(pack_fd, out, s.total_out);
+ write_or_die(pack_fd, out, s.total_out);
pack_size += s.total_out;
free(out);
if (delta)
free(delta);
if (last) {
- if (last->data)
+ if (last->data && !last->no_free)
free(last->data);
last->data = dat;
+ last->offset = e->offset;
last->len = datlen;
- memcpy(last->sha1, sha1, sizeof(sha1));
}
return 0;
}
-static void* map_pack(unsigned long offset)
-{
- if (offset >= pack_size)
- die("object offset outside of pack file");
- if (offset >= pack_mlen) {
- if (pack_base)
- munmap(pack_base, pack_mlen);
- /* round out how much we map to 16 MB units */
- pack_mlen = pack_size;
- if (pack_mlen & ((1 << 24) - 1))
- pack_mlen = ((pack_mlen >> 24) + 1) << 24;
- pack_base = mmap(NULL,pack_mlen,PROT_READ,MAP_SHARED,pack_fd,0);
- if (pack_base == MAP_FAILED)
- die("Failed to map generated pack: %s", strerror(errno));
- remap_count++;
- }
- return (char*)pack_base + offset;
-}
-
-static unsigned long unpack_object_header(unsigned long offset,
- enum object_type *type,
- unsigned long *sizep)
-{
- unsigned shift;
- unsigned char c;
- unsigned long size;
-
- c = *(unsigned char*)map_pack(offset++);
- *type = (c >> 4) & 7;
- size = c & 15;
- shift = 4;
- while (c & 0x80) {
- c = *(unsigned char*)map_pack(offset++);
- size += (c & 0x7f) << shift;
- shift += 7;
- }
- *sizep = size;
- return offset;
-}
-
-static void *unpack_non_delta_entry(unsigned long o, unsigned long sz)
-{
- z_stream stream;
- unsigned char *result;
-
- result = xmalloc(sz + 1);
- result[sz] = 0;
-
- memset(&stream, 0, sizeof(stream));
- stream.next_in = map_pack(o);
- stream.avail_in = pack_mlen - o;
- stream.next_out = result;
- stream.avail_out = sz;
-
- inflateInit(&stream);
- for (;;) {
- int st = inflate(&stream, Z_FINISH);
- if (st == Z_STREAM_END)
- break;
- if (st == Z_OK) {
- o = stream.next_in - (unsigned char*)pack_base;
- stream.next_in = map_pack(o);
- stream.avail_in = pack_mlen - o;
- continue;
- }
- die("Error from zlib during inflate.");
- }
- inflateEnd(&stream);
- if (stream.total_out != sz)
- die("Error after inflate: sizes mismatch");
- return result;
-}
-
-static void *unpack_entry(unsigned long offset, unsigned long *sizep);
-
-static void *unpack_delta_entry(unsigned long offset,
- unsigned long delta_size,
+static void *gfi_unpack_entry(
+ struct object_entry *oe,
unsigned long *sizep)
{
- struct object_entry *base_oe;
- unsigned char *base_sha1;
- void *delta_data, *base, *result;
- unsigned long base_size, result_size;
-
- base_sha1 = (unsigned char*)map_pack(offset + 20) - 20;
- base_oe = find_object(base_sha1);
- if (!base_oe)
- die("I'm broken; I can't find a base I know must be here.");
- base = unpack_entry(base_oe->offset, &base_size);
- delta_data = unpack_non_delta_entry(offset + 20, delta_size);
- result = patch_delta(base, base_size,
- delta_data, delta_size,
- &result_size);
- if (!result)
- die("failed to apply delta");
- free(delta_data);
- free(base);
- *sizep = result_size;
- return result;
-}
-
-static void *unpack_entry(unsigned long offset, unsigned long *sizep)
-{
- unsigned long size;
- enum object_type kind;
-
- offset = unpack_object_header(offset, &kind, &size);
- switch (kind) {
- case OBJ_DELTA:
- return unpack_delta_entry(offset, size, sizep);
- case OBJ_COMMIT:
- case OBJ_TREE:
- case OBJ_BLOB:
- case OBJ_TAG:
- *sizep = size;
- return unpack_non_delta_entry(offset, size);
- default:
- die("I created an object I can't read!");
- }
+ static char type[20];
+ struct packed_git *p = all_packs[oe->pack_id];
+ if (p == pack_data)
+ p->pack_size = pack_size + 20;
+ return unpack_entry(p, oe->offset, type, sizep);
}
static const char *get_mode(const char *str, unsigned int *modep)
static void load_tree(struct tree_entry *root)
{
+ unsigned char* sha1 = root->versions[1].sha1;
struct object_entry *myoe;
struct tree_content *t;
unsigned long size;
const char *c;
root->tree = t = new_tree_content(8);
- if (!memcmp(root->sha1, null_sha1, 20))
+ if (is_null_sha1(sha1))
return;
- myoe = find_object(root->sha1);
+ myoe = find_object(sha1);
if (myoe) {
if (myoe->type != OBJ_TREE)
- die("Not a tree: %s", sha1_to_hex(root->sha1));
- buf = unpack_entry(myoe->offset, &size);
+ die("Not a tree: %s", sha1_to_hex(sha1));
+ t->delta_depth = 0;
+ buf = gfi_unpack_entry(myoe, &size);
} else {
char type[20];
- buf = read_sha1_file(root->sha1, type, &size);
+ buf = read_sha1_file(sha1, type, &size);
if (!buf || strcmp(type, tree_type))
- die("Can't load tree %s", sha1_to_hex(root->sha1));
+ die("Can't load tree %s", sha1_to_hex(sha1));
}
c = buf;
t->entries[t->entry_count++] = e;
e->tree = NULL;
- c = get_mode(c, &e->mode);
+ c = get_mode(c, &e->versions[1].mode);
if (!c)
- die("Corrupt mode in %s", sha1_to_hex(root->sha1));
+ die("Corrupt mode in %s", sha1_to_hex(sha1));
+ e->versions[0].mode = e->versions[1].mode;
e->name = to_atom(c, strlen(c));
c += e->name->str_len + 1;
- memcpy(e->sha1, c, sizeof(e->sha1));
+ hashcpy(e->versions[0].sha1, (unsigned char*)c);
+ hashcpy(e->versions[1].sha1, (unsigned char*)c);
c += 20;
}
free(buf);
}
-static int tecmp (const void *_a, const void *_b)
+static int tecmp0 (const void *_a, const void *_b)
{
struct tree_entry *a = *((struct tree_entry**)_a);
struct tree_entry *b = *((struct tree_entry**)_b);
return base_name_compare(
- a->name->str_dat, a->name->str_len, a->mode,
- b->name->str_dat, b->name->str_len, b->mode);
+ a->name->str_dat, a->name->str_len, a->versions[0].mode,
+ b->name->str_dat, b->name->str_len, b->versions[0].mode);
}
-static void store_tree(struct tree_entry *root)
+static int tecmp1 (const void *_a, const void *_b)
{
- struct tree_content *t = root->tree;
+ struct tree_entry *a = *((struct tree_entry**)_a);
+ struct tree_entry *b = *((struct tree_entry**)_b);
+ return base_name_compare(
+ a->name->str_dat, a->name->str_len, a->versions[1].mode,
+ b->name->str_dat, b->name->str_len, b->versions[1].mode);
+}
+
+static void mktree(struct tree_content *t,
+ int v,
+ unsigned long *szp,
+ struct dbuf *b)
+{
+ size_t maxlen = 0;
unsigned int i;
- size_t maxlen;
- char *buf, *c;
+ char *c;
- if (memcmp(root->sha1, null_sha1, 20))
- return;
+ if (!v)
+ qsort(t->entries,t->entry_count,sizeof(t->entries[0]),tecmp0);
+ else
+ qsort(t->entries,t->entry_count,sizeof(t->entries[0]),tecmp1);
- maxlen = 0;
for (i = 0; i < t->entry_count; i++) {
- maxlen += t->entries[i]->name->str_len + 34;
- if (t->entries[i]->tree)
- store_tree(t->entries[i]);
+ if (t->entries[i]->versions[v].mode)
+ maxlen += t->entries[i]->name->str_len + 34;
}
- qsort(t->entries, t->entry_count, sizeof(t->entries[0]), tecmp);
- buf = c = xmalloc(maxlen);
+ size_dbuf(b, maxlen);
+ c = b->buffer;
for (i = 0; i < t->entry_count; i++) {
struct tree_entry *e = t->entries[i];
- c += sprintf(c, "%o", e->mode);
+ if (!e->versions[v].mode)
+ continue;
+ c += sprintf(c, "%o", e->versions[v].mode);
*c++ = ' ';
strcpy(c, e->name->str_dat);
c += e->name->str_len + 1;
- memcpy(c, e->sha1, 20);
+ hashcpy((unsigned char*)c, e->versions[v].sha1);
c += 20;
}
- store_object(OBJ_TREE, buf, c - buf, NULL, root->sha1, 0);
- free(buf);
+ *szp = c - (char*)b->buffer;
+}
+
+static void store_tree(struct tree_entry *root)
+{
+ struct tree_content *t = root->tree;
+ unsigned int i, j, del;
+ unsigned long new_len;
+ struct last_object lo;
+ struct object_entry *le;
+
+ if (!is_null_sha1(root->versions[1].sha1))
+ return;
+
+ for (i = 0; i < t->entry_count; i++) {
+ if (t->entries[i]->tree)
+ store_tree(t->entries[i]);
+ }
+
+ le = find_object(root->versions[0].sha1);
+ if (!S_ISDIR(root->versions[0].mode)
+ || !le
+ || le->pack_id != pack_id) {
+ lo.data = NULL;
+ lo.depth = 0;
+ } else {
+ mktree(t, 0, &lo.len, &old_tree);
+ lo.data = old_tree.buffer;
+ lo.offset = le->offset;
+ lo.depth = t->delta_depth;
+ lo.no_free = 1;
+ }
+
+ mktree(t, 1, &new_len, &new_tree);
+ store_object(OBJ_TREE, new_tree.buffer, new_len,
+ &lo, root->versions[1].sha1, 0);
+
+ t->delta_depth = lo.depth;
+ for (i = 0, j = 0, del = 0; i < t->entry_count; i++) {
+ struct tree_entry *e = t->entries[i];
+ if (e->versions[1].mode) {
+ e->versions[0].mode = e->versions[1].mode;
+ hashcpy(e->versions[0].sha1, e->versions[1].sha1);
+ t->entries[j++] = e;
+ } else {
+ release_tree_entry(e);
+ del++;
+ }
+ }
+ t->entry_count -= del;
}
static int tree_content_set(
e = t->entries[i];
if (e->name->str_len == n && !strncmp(p, e->name->str_dat, n)) {
if (!slash1) {
- if (e->mode == mode && !memcmp(e->sha1, sha1, 20))
+ if (e->versions[1].mode == mode
+ && !hashcmp(e->versions[1].sha1, sha1))
return 0;
- e->mode = mode;
- memcpy(e->sha1, sha1, 20);
+ e->versions[1].mode = mode;
+ hashcpy(e->versions[1].sha1, sha1);
if (e->tree) {
release_tree_content_recursive(e->tree);
e->tree = NULL;
}
- memcpy(root->sha1, null_sha1, 20);
+ hashclr(root->versions[1].sha1);
return 1;
}
- if (!S_ISDIR(e->mode)) {
+ if (!S_ISDIR(e->versions[1].mode)) {
e->tree = new_tree_content(8);
- e->mode = S_IFDIR;
+ e->versions[1].mode = S_IFDIR;
}
if (!e->tree)
load_tree(e);
if (tree_content_set(e, slash1 + 1, sha1, mode)) {
- memcpy(root->sha1, null_sha1, 20);
+ hashclr(root->versions[1].sha1);
return 1;
}
return 0;
root->tree = t = grow_tree_content(t, 8);
e = new_tree_entry();
e->name = to_atom(p, n);
+ e->versions[0].mode = 0;
+ hashclr(e->versions[0].sha1);
t->entries[t->entry_count++] = e;
if (slash1) {
e->tree = new_tree_content(8);
- e->mode = S_IFDIR;
+ e->versions[1].mode = S_IFDIR;
tree_content_set(e, slash1 + 1, sha1, mode);
} else {
e->tree = NULL;
- e->mode = mode;
- memcpy(e->sha1, sha1, 20);
+ e->versions[1].mode = mode;
+ hashcpy(e->versions[1].sha1, sha1);
}
- memcpy(root->sha1, null_sha1, 20);
+ hashclr(root->versions[1].sha1);
return 1;
}
for (i = 0; i < t->entry_count; i++) {
e = t->entries[i];
if (e->name->str_len == n && !strncmp(p, e->name->str_dat, n)) {
- if (!slash1 || !S_ISDIR(e->mode))
+ if (!slash1 || !S_ISDIR(e->versions[1].mode))
goto del_entry;
if (!e->tree)
load_tree(e);
if (tree_content_remove(e, slash1 + 1)) {
- if (!e->tree->entry_count)
- goto del_entry;
- memcpy(root->sha1, null_sha1, 20);
- return 1;
+ for (n = 0; n < e->tree->entry_count; n++) {
+ if (e->tree->entries[n]->versions[1].mode) {
+ hashclr(root->versions[1].sha1);
+ return 1;
+ }
+ }
+ goto del_entry;
}
return 0;
}
return 0;
del_entry:
- for (i++; i < t->entry_count; i++)
- t->entries[i-1] = t->entries[i];
- t->entry_count--;
- release_tree_entry(e);
- memcpy(root->sha1, null_sha1, 20);
- return 1;
-}
-
-static void init_pack_header()
-{
- struct pack_header hdr;
-
- hdr.hdr_signature = htonl(PACK_SIGNATURE);
- hdr.hdr_version = htonl(2);
- hdr.hdr_entries = 0;
-
- ywrite(pack_fd, &hdr, sizeof(hdr));
- pack_size = sizeof(hdr);
-}
-
-static void fixup_header_footer()
-{
- SHA_CTX c;
- char hdr[8];
- unsigned long cnt;
- char *buf;
- size_t n;
-
- if (lseek(pack_fd, 0, SEEK_SET) != 0)
- die("Failed seeking to start: %s", strerror(errno));
-
- SHA1_Init(&c);
- yread(pack_fd, hdr, 8);
- SHA1_Update(&c, hdr, 8);
-
- cnt = htonl(object_count);
- SHA1_Update(&c, &cnt, 4);
- ywrite(pack_fd, &cnt, 4);
-
- buf = xmalloc(128 * 1024);
- for (;;) {
- n = xread(pack_fd, buf, 128 * 1024);
- if (n <= 0)
- break;
- SHA1_Update(&c, buf, n);
- }
- free(buf);
-
- SHA1_Final(pack_sha1, &c);
- ywrite(pack_fd, pack_sha1, sizeof(pack_sha1));
-}
-
-static int oecmp (const void *_a, const void *_b)
-{
- struct object_entry *a = *((struct object_entry**)_a);
- struct object_entry *b = *((struct object_entry**)_b);
- return memcmp(a->sha1, b->sha1, sizeof(a->sha1));
-}
-
-static void write_index(const char *idx_name)
-{
- struct sha1file *f;
- struct object_entry **idx, **c, **last;
- struct object_entry *e;
- struct object_entry_pool *o;
- unsigned int array[256];
- int i;
-
- /* Build the sorted table of object IDs. */
- idx = xmalloc(object_count * sizeof(struct object_entry*));
- c = idx;
- for (o = blocks; o; o = o->next_pool)
- for (e = o->entries; e != o->next_free; e++)
- *c++ = e;
- last = idx + object_count;
- qsort(idx, object_count, sizeof(struct object_entry*), oecmp);
-
- /* Generate the fan-out array. */
- c = idx;
- for (i = 0; i < 256; i++) {
- struct object_entry **next = c;;
- while (next < last) {
- if ((*next)->sha1[0] != i)
- break;
- next++;
- }
- array[i] = htonl(next - idx);
- c = next;
- }
-
- f = sha1create("%s", idx_name);
- sha1write(f, array, 256 * sizeof(int));
- for (c = idx; c != last; c++) {
- unsigned int offset = htonl((*c)->offset);
- sha1write(f, &offset, 4);
- sha1write(f, (*c)->sha1, sizeof((*c)->sha1));
+ if (e->tree) {
+ release_tree_content_recursive(e->tree);
+ e->tree = NULL;
}
- sha1write(f, pack_sha1, sizeof(pack_sha1));
- sha1close(f, NULL, 1);
- free(idx);
+ e->versions[1].mode = 0;
+ hashclr(e->versions[1].sha1);
+ hashclr(root->versions[1].sha1);
+ return 1;
}
static void dump_branches()
for (i = 0; i < branch_table_sz; i++) {
for (b = branch_table[i]; b; b = b->table_next_branch) {
- lock = lock_any_ref_for_update(b->name, NULL, 0);
+ lock = lock_any_ref_for_update(b->name, NULL);
if (!lock || write_ref_sha1(lock, b->sha1, msg) < 0)
die("Can't write %s", b->name);
}
for (t = first_tag; t; t = t->next_tag) {
sprintf(path, "refs/tags/%s", t->name);
- lock = lock_any_ref_for_update(path, NULL, 0);
+ lock = lock_any_ref_for_update(path, NULL);
if (!lock || write_ref_sha1(lock, t->sha1, msg) < 0)
die("Can't write %s", path);
}
}
+static void dump_marks_helper(FILE *f,
+ unsigned long base,
+ struct mark_set *m)
+{
+ int k;
+ if (m->shift) {
+ for (k = 0; k < 1024; k++) {
+ if (m->data.sets[k])
+ dump_marks_helper(f, (base + k) << m->shift,
+ m->data.sets[k]);
+ }
+ } else {
+ for (k = 0; k < 1024; k++) {
+ if (m->data.marked[k])
+ fprintf(f, ":%lu %s\n", base + k,
+ sha1_to_hex(m->data.marked[k]->sha1));
+ }
+ }
+}
+
+static void dump_marks()
+{
+ if (mark_file)
+ {
+ FILE *f = fopen(mark_file, "w");
+ dump_marks_helper(f, 0, marks);
+ fclose(f);
+ }
+}
+
static void read_next_command()
{
read_line(&command_buf, stdin, '\n');
if (*p == ':') {
char *x;
oe = find_mark(strtoul(p + 1, &x, 10));
+ hashcpy(sha1, oe->sha1);
p = x;
} else {
if (get_sha1_hex(p, sha1))
if (b == s)
die("Can't create a branch from itself: %s", b->name);
else if (s) {
- memcpy(b->sha1, s->sha1, 20);
- memcpy(b->branch_tree.sha1, s->branch_tree.sha1, 20);
+ unsigned char *t = s->branch_tree.versions[1].sha1;
+ hashcpy(b->sha1, s->sha1);
+ hashcpy(b->branch_tree.versions[0].sha1, t);
+ hashcpy(b->branch_tree.versions[1].sha1, t);
} else if (*from == ':') {
unsigned long idnum = strtoul(from + 1, NULL, 10);
struct object_entry *oe = find_mark(idnum);
char *buf;
if (oe->type != OBJ_COMMIT)
die("Mark :%lu not a commit", idnum);
- memcpy(b->sha1, oe->sha1, 20);
- buf = unpack_entry(oe->offset, &size);
+ hashcpy(b->sha1, oe->sha1);
+ buf = gfi_unpack_entry(oe, &size);
if (!buf || size < 46)
die("Not a valid commit: %s", from);
if (memcmp("tree ", buf, 5)
- || get_sha1_hex(buf + 5, b->branch_tree.sha1))
+ || get_sha1_hex(buf + 5, b->branch_tree.versions[1].sha1))
die("The commit %s is corrupt", sha1_to_hex(b->sha1));
free(buf);
+ hashcpy(b->branch_tree.versions[0].sha1,
+ b->branch_tree.versions[1].sha1);
} else if (!get_sha1(from, b->sha1)) {
- if (!memcmp(b->sha1, null_sha1, 20))
- memcpy(b->branch_tree.sha1, null_sha1, 20);
- else {
+ if (is_null_sha1(b->sha1)) {
+ hashclr(b->branch_tree.versions[0].sha1);
+ hashclr(b->branch_tree.versions[1].sha1);
+ } else {
unsigned long size;
char *buf;
if (!buf || size < 46)
die("Not a valid commit: %s", from);
if (memcmp("tree ", buf, 5)
- || get_sha1_hex(buf + 5, b->branch_tree.sha1))
+ || get_sha1_hex(buf + 5, b->branch_tree.versions[1].sha1))
die("The commit %s is corrupt", sha1_to_hex(b->sha1));
free(buf);
+ hashcpy(b->branch_tree.versions[0].sha1,
+ b->branch_tree.versions[1].sha1);
}
} else
die("Invalid ref name or SHA1 expression: %s", from);
read_next_command();
}
+static struct hash_list* cmd_merge(unsigned int *count)
+{
+ struct hash_list *list = NULL, *n, *e;
+ const char *from, *endp;
+ char *str_uq;
+ struct branch *s;
+
+ *count = 0;
+ while (!strncmp("merge ", command_buf.buf, 6)) {
+ from = strchr(command_buf.buf, ' ') + 1;
+ str_uq = unquote_c_style(from, &endp);
+ if (str_uq) {
+ if (*endp)
+ die("Garbage after string in: %s", command_buf.buf);
+ from = str_uq;
+ }
+
+ n = xmalloc(sizeof(*n));
+ s = lookup_branch(from);
+ if (s)
+ hashcpy(n->sha1, s->sha1);
+ else if (*from == ':') {
+ unsigned long idnum = strtoul(from + 1, NULL, 10);
+ struct object_entry *oe = find_mark(idnum);
+ if (oe->type != OBJ_COMMIT)
+ die("Mark :%lu not a commit", idnum);
+ hashcpy(n->sha1, oe->sha1);
+ } else if (get_sha1(from, n->sha1))
+ die("Invalid ref name or SHA1 expression: %s", from);
+
+ n->next = NULL;
+ if (list)
+ e->next = n;
+ else
+ list = n;
+ e = n;
+ *count++;
+ read_next_command();
+ }
+ return list;
+}
+
static void cmd_new_commit()
{
struct branch *b;
char *sp;
char *author = NULL;
char *committer = NULL;
- char *body;
+ struct hash_list *merge_list = NULL;
+ unsigned int merge_count;
/* Obtain the branch name from the rest of our command */
sp = strchr(command_buf.buf, ' ') + 1;
msg = cmd_data(&msglen);
read_next_command();
cmd_from(b);
+ merge_list = cmd_merge(&merge_count);
/* ensure the branch is active/loaded */
if (!b->branch_tree.tree || !max_active_branches) {
/* build the tree and the commit */
store_tree(&b->branch_tree);
- body = xmalloc(97 + msglen
+ hashcpy(b->branch_tree.versions[0].sha1,
+ b->branch_tree.versions[1].sha1);
+ size_dbuf(&new_data, 97 + msglen
+ + merge_count * 49
+ (author
? strlen(author) + strlen(committer)
: 2 * strlen(committer)));
- sp = body;
- sp += sprintf(sp, "tree %s\n", sha1_to_hex(b->branch_tree.sha1));
- if (memcmp(b->sha1, null_sha1, 20))
+ sp = new_data.buffer;
+ sp += sprintf(sp, "tree %s\n",
+ sha1_to_hex(b->branch_tree.versions[1].sha1));
+ if (!is_null_sha1(b->sha1))
sp += sprintf(sp, "parent %s\n", sha1_to_hex(b->sha1));
+ while (merge_list) {
+ struct hash_list *next = merge_list->next;
+ sp += sprintf(sp, "parent %s\n", sha1_to_hex(merge_list->sha1));
+ free(merge_list);
+ merge_list = next;
+ }
if (author)
sp += sprintf(sp, "%s\n", author);
else
free(committer);
free(msg);
- store_object(OBJ_COMMIT, body, sp - body, NULL, b->sha1, next_mark);
- free(body);
+ store_object(OBJ_COMMIT,
+ new_data.buffer, sp - (char*)new_data.buffer,
+ NULL, b->sha1, next_mark);
b->last_commit = object_count_by_type[OBJ_COMMIT];
+
+ if (branch_log) {
+ int need_dq = quote_c_style(b->name, NULL, NULL, 0);
+ fprintf(branch_log, "commit ");
+ if (need_dq) {
+ fputc('"', branch_log);
+ quote_c_style(b->name, NULL, branch_log, 0);
+ fputc('"', branch_log);
+ } else
+ fprintf(branch_log, "%s", b->name);
+ fprintf(branch_log," :%lu %s\n",next_mark,sha1_to_hex(b->sha1));
+ }
}
static void cmd_new_tag()
struct branch *s;
void *msg;
size_t msglen;
- char *body;
struct tag *t;
+ unsigned long from_mark = 0;
unsigned char sha1[20];
/* Obtain the new tag name from the rest of our command */
s = lookup_branch(from);
if (s) {
- memcpy(sha1, s->sha1, 20);
+ hashcpy(sha1, s->sha1);
} else if (*from == ':') {
- unsigned long idnum = strtoul(from + 1, NULL, 10);
- struct object_entry *oe = find_mark(idnum);
+ from_mark = strtoul(from + 1, NULL, 10);
+ struct object_entry *oe = find_mark(from_mark);
if (oe->type != OBJ_COMMIT)
- die("Mark :%lu not a commit", idnum);
- memcpy(sha1, oe->sha1, 20);
+ die("Mark :%lu not a commit", from_mark);
+ hashcpy(sha1, oe->sha1);
} else if (!get_sha1(from, sha1)) {
unsigned long size;
char *buf;
msg = cmd_data(&msglen);
/* build the tag object */
- body = xmalloc(67 + strlen(t->name) + strlen(tagger) + msglen);
- sp = body;
+ size_dbuf(&new_data, 67+strlen(t->name)+strlen(tagger)+msglen);
+ sp = new_data.buffer;
sp += sprintf(sp, "object %s\n", sha1_to_hex(sha1));
sp += sprintf(sp, "type %s\n", type_names[OBJ_COMMIT]);
sp += sprintf(sp, "tag %s\n", t->name);
free(tagger);
free(msg);
- store_object(OBJ_TAG, body, sp - body, NULL, t->sha1, 0);
- free(body);
+ store_object(OBJ_TAG, new_data.buffer, sp - (char*)new_data.buffer,
+ NULL, t->sha1, 0);
+
+ if (branch_log) {
+ int need_dq = quote_c_style(t->name, NULL, NULL, 0);
+ fprintf(branch_log, "tag ");
+ if (need_dq) {
+ fputc('"', branch_log);
+ quote_c_style(t->name, NULL, branch_log, 0);
+ fputc('"', branch_log);
+ } else
+ fprintf(branch_log, "%s", t->name);
+ fprintf(branch_log," :%lu %s\n",from_mark,sha1_to_hex(t->sha1));
+ }
+}
+
+static void cmd_reset_branch()
+{
+ struct branch *b;
+ char *str_uq;
+ const char *endp;
+ char *sp;
+
+ /* Obtain the branch name from the rest of our command */
+ sp = strchr(command_buf.buf, ' ') + 1;
+ str_uq = unquote_c_style(sp, &endp);
+ if (str_uq) {
+ if (*endp)
+ die("Garbage after ref in: %s", command_buf.buf);
+ sp = str_uq;
+ }
+ b = lookup_branch(sp);
+ if (b) {
+ b->last_commit = 0;
+ if (b->branch_tree.tree) {
+ release_tree_content_recursive(b->branch_tree.tree);
+ b->branch_tree.tree = NULL;
+ }
+ }
+ else
+ b = new_branch(sp);
+ if (str_uq)
+ free(str_uq);
+ read_next_command();
+ cmd_from(b);
+}
+
+static void cmd_checkpoint()
+{
+ if (object_count) {
+ end_packfile();
+ start_packfile();
+ }
+ read_next_command();
}
static const char fast_import_usage[] =
-"git-fast-import [--objects=n] [--depth=n] [--active-branches=n] temp.pack";
+"git-fast-import [--objects=n] [--depth=n] [--active-branches=n] [--export-marks=marks.file] [--branch-log=log] temp.pack";
int main(int argc, const char **argv)
{
- const char *base_name;
int i;
- unsigned long est_obj_cnt = 1000;
- char *pack_name;
- char *idx_name;
- struct stat sb;
+ unsigned long est_obj_cnt = object_entry_alloc;
+ unsigned long duplicate_count;
setup_ident();
git_config(git_default_config);
max_depth = strtoul(a + 8, NULL, 0);
else if (!strncmp(a, "--active-branches=", 18))
max_active_branches = strtoul(a + 18, NULL, 0);
+ else if (!strncmp(a, "--export-marks=", 15))
+ mark_file = a + 15;
+ else if (!strncmp(a, "--branch-log=", 13)) {
+ branch_log = fopen(a + 13, "w");
+ if (!branch_log)
+ die("Can't create %s: %s", a + 13, strerror(errno));
+ }
else
die("unknown option %s", a);
}
usage(fast_import_usage);
base_name = argv[i];
- pack_name = xmalloc(strlen(base_name) + 6);
- sprintf(pack_name, "%s.pack", base_name);
- idx_name = xmalloc(strlen(base_name) + 5);
- sprintf(idx_name, "%s.idx", base_name);
-
- pack_fd = open(pack_name, O_RDWR|O_CREAT|O_EXCL, 0666);
- if (pack_fd < 0)
- die("Can't create %s: %s", pack_name, strerror(errno));
-
- init_pack_header();
alloc_objects(est_obj_cnt);
strbuf_init(&command_buf);
avail_tree_table = xcalloc(avail_tree_table_sz, sizeof(struct avail_tree_content*));
marks = pool_calloc(1, sizeof(struct mark_set));
+ start_packfile();
for (;;) {
read_next_command();
if (command_buf.eof)
cmd_new_commit();
else if (!strncmp("tag ", command_buf.buf, 4))
cmd_new_tag();
+ else if (!strncmp("reset ", command_buf.buf, 6))
+ cmd_reset_branch();
+ else if (!strcmp("checkpoint", command_buf.buf))
+ cmd_checkpoint();
else
die("Unsupported command: %s", command_buf.buf);
}
+ end_packfile();
- fixup_header_footer();
- close(pack_fd);
- write_index(idx_name);
dump_branches();
dump_tags();
+ dump_marks();
+ if (branch_log)
+ fclose(branch_log);
+
+ for (i = 0; i < ARRAY_SIZE(duplicate_count_by_type); i++)
+ duplicate_count += duplicate_count_by_type[i];
fprintf(stderr, "%s statistics:\n", argv[0]);
- fprintf(stderr, "---------------------------------------------------\n");
+ fprintf(stderr, "---------------------------------------------------------------------\n");
fprintf(stderr, "Alloc'd objects: %10lu (%10lu overflow )\n", alloc_count, alloc_count - est_obj_cnt);
- fprintf(stderr, "Total objects: %10lu (%10lu duplicates)\n", object_count, duplicate_count);
- fprintf(stderr, " blobs : %10lu (%10lu duplicates)\n", object_count_by_type[OBJ_BLOB], duplicate_count_by_type[OBJ_BLOB]);
- fprintf(stderr, " trees : %10lu (%10lu duplicates)\n", object_count_by_type[OBJ_TREE], duplicate_count_by_type[OBJ_TREE]);
- fprintf(stderr, " commits: %10lu (%10lu duplicates)\n", object_count_by_type[OBJ_COMMIT], duplicate_count_by_type[OBJ_COMMIT]);
- fprintf(stderr, " tags : %10lu (%10lu duplicates)\n", object_count_by_type[OBJ_TAG], duplicate_count_by_type[OBJ_TAG]);
+ fprintf(stderr, "Total objects: %10lu (%10lu duplicates )\n", object_count, duplicate_count);
+ fprintf(stderr, " blobs : %10lu (%10lu duplicates %10lu deltas)\n", object_count_by_type[OBJ_BLOB], duplicate_count_by_type[OBJ_BLOB], delta_count_by_type[OBJ_BLOB]);
+ fprintf(stderr, " trees : %10lu (%10lu duplicates %10lu deltas)\n", object_count_by_type[OBJ_TREE], duplicate_count_by_type[OBJ_TREE], delta_count_by_type[OBJ_TREE]);
+ fprintf(stderr, " commits: %10lu (%10lu duplicates %10lu deltas)\n", object_count_by_type[OBJ_COMMIT], duplicate_count_by_type[OBJ_COMMIT], delta_count_by_type[OBJ_COMMIT]);
+ fprintf(stderr, " tags : %10lu (%10lu duplicates %10lu deltas)\n", object_count_by_type[OBJ_TAG], duplicate_count_by_type[OBJ_TAG], delta_count_by_type[OBJ_TAG]);
fprintf(stderr, "Total branches: %10lu (%10lu loads )\n", branch_count, branch_load_count);
fprintf(stderr, " marks: %10u (%10lu unique )\n", (1 << marks->shift) * 1024, marks_set_count);
fprintf(stderr, " atoms: %10u\n", atom_cnt);
fprintf(stderr, "Memory total: %10lu KiB\n", (total_allocd + alloc_count*sizeof(struct object_entry))/1024);
fprintf(stderr, " pools: %10lu KiB\n", total_allocd/1024);
fprintf(stderr, " objects: %10lu KiB\n", (alloc_count*sizeof(struct object_entry))/1024);
- fprintf(stderr, "Pack remaps: %10lu\n", remap_count);
- fprintf(stderr, "---------------------------------------------------\n");
-
- stat(pack_name, &sb);
- fprintf(stderr, "Pack size: %10lu KiB\n", (unsigned long)(sb.st_size/1024));
- stat(idx_name, &sb);
- fprintf(stderr, "Index size: %10lu KiB\n", (unsigned long)(sb.st_size/1024));
-
+ fprintf(stderr, "---------------------------------------------------------------------\n");
+ pack_report();
+ fprintf(stderr, "---------------------------------------------------------------------\n");
fprintf(stderr, "\n");
return 0;