stream ::= cmd*;
cmd ::= new_blob
- | new_branch
| new_commit
| new_tag
+ | reset_branch
;
new_blob ::= 'blob' lf
file_content;
file_content ::= data;
- new_branch ::= 'branch' sp ref_str lf
- ('from' sp (ref_str | hexsha1 | sha1exp_str | idnum) lf)?
- lf;
-
new_commit ::= 'commit' sp ref_str lf
- mark?
- ('author' sp name '<' email '>' ts tz lf)?
- 'committer' sp name '<' email '>' ts tz lf
- commit_msg
+ mark?
+ ('author' sp name '<' email '>' ts tz lf)?
+ 'committer' sp name '<' email '>' ts tz lf
+ commit_msg
+ ('from' 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;
+
# 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 entries[FLEX_ARRAY]; /* more */
};
+struct mark_set
+{
+ int shift;
+ union {
+ struct object_entry *marked[1024];
+ struct mark_set *sets[1024];
+ } data;
+};
+
struct last_object
{
void *data;
- unsigned int len;
+ unsigned long len;
unsigned int depth;
unsigned char sha1[20];
};
{
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 tag
+{
+ struct tag *next_tag;
+ const char *name;
+ unsigned char sha1[20];
+};
+
/* Stats and misc. counters */
-static int max_depth = 10;
+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 delta_count_by_type[9];
/* Memory pools */
static size_t mem_pool_alloc = 2*1024*1024 - sizeof(struct mem_pool);
/* The .pack file being generated */
static int pack_fd;
-static unsigned long pack_offset;
+static unsigned long pack_size;
static unsigned char pack_sha1[20];
+static unsigned char* pack_base;
+static unsigned long pack_moff;
+static unsigned long pack_mlen = 128*1024*1024;
+static unsigned long page_size;
/* 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 struct avail_tree_content **avail_tree_table;
/* Branch data */
-static unsigned int max_active_branches = 5;
-static unsigned int cur_active_branches;
-static unsigned int branch_table_sz = 1039;
+static unsigned long max_active_branches = 5;
+static unsigned long cur_active_branches;
+static unsigned long branch_table_sz = 1039;
static struct branch **branch_table;
static struct branch *active_branches;
+/* Tag data */
+static struct tag *first_tag;
+static struct tag *last_tag;
+
/* Input stream parsing */
static struct strbuf command_buf;
-static unsigned long command_mark;
+static unsigned long next_mark;
+static FILE* branch_log;
static void alloc_objects(int cnt)
alloc_objects(object_entry_alloc);
e = blocks->next_free++;
- memcpy(e->sha1, sha1, sizeof(e->sha1));
+ 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;
}
r = p->next_free;
+ /* round out to a pointer alignment */
+ if (len & (sizeof(void*) - 1))
+ len += sizeof(void*) - (len & (sizeof(void*) - 1));
p->next_free += len;
return r;
}
return r;
}
+static void insert_mark(unsigned long idnum, struct object_entry *oe)
+{
+ struct mark_set *s = marks;
+ while ((idnum >> s->shift) >= 1024) {
+ s = pool_calloc(1, sizeof(struct mark_set));
+ s->shift = marks->shift + 10;
+ s->data.sets[0] = marks;
+ marks = s;
+ }
+ while (s->shift) {
+ unsigned long i = idnum >> s->shift;
+ idnum -= i << s->shift;
+ if (!s->data.sets[i]) {
+ s->data.sets[i] = pool_calloc(1, sizeof(struct mark_set));
+ s->data.sets[i]->shift = s->shift - 10;
+ }
+ s = s->data.sets[i];
+ }
+ if (!s->data.marked[idnum])
+ marks_set_count++;
+ s->data.marked[idnum] = oe;
+}
+
+static struct object_entry* find_mark(unsigned long idnum)
+{
+ unsigned long orig_idnum = idnum;
+ struct mark_set *s = marks;
+ struct object_entry *oe = NULL;
+ if ((idnum >> s->shift) < 1024) {
+ while (s && s->shift) {
+ unsigned long i = idnum >> s->shift;
+ idnum -= i << s->shift;
+ s = s->data.sets[i];
+ }
+ if (s)
+ oe = s->data.marked[idnum];
+ }
+ if (!oe)
+ die("mark :%lu not declared", orig_idnum);
+ return oe;
+}
+
static struct atom_str* to_atom(const char *s, size_t len)
{
unsigned int hc = hc_str(s, len) % atom_table_sz;
t = (struct tree_content*)f;
t->entry_count = 0;
+ t->delta_depth = 0;
return t;
}
{
struct avail_tree_content *f = (struct avail_tree_content*)t;
unsigned int hc = hc_entries(f->entry_capacity);
+ f->next_avail = avail_tree_table[hc];
+ avail_tree_table[hc] = f;
+}
+
+static void release_tree_content_recursive(struct tree_content *t)
+{
unsigned int i;
for (i = 0; i < t->entry_count; i++)
release_tree_entry(t->entries[i]);
- f->next_avail = avail_tree_table[hc];
- avail_tree_table[hc] = f;
+ release_tree_content(t);
}
static struct tree_content* grow_tree_content(
{
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 release_tree_entry(struct tree_entry *e)
{
if (e->tree)
- release_tree_content(e->tree);
+ release_tree_content_recursive(e->tree);
*((void**)e) = avail_tree_entry;
avail_tree_entry = e;
}
void *dat,
size_t datlen,
struct last_object *last,
- unsigned char *sha1out)
+ unsigned char *sha1out,
+ unsigned long mark)
{
void *out, *delta;
struct object_entry *e;
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;
}
e->type = type;
- e->offset = pack_offset;
+ e->offset = pack_size;
object_count++;
object_count_by_type[type]++;
deflateInit(&s, zlib_compression_level);
if (delta) {
+ 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_offset += hdrlen + sizeof(sha1);
+ pack_size += hdrlen + sizeof(sha1);
} else {
if (last)
last->depth = 0;
s.avail_in = datlen;
hdrlen = encode_header(type, datlen, hdr);
ywrite(pack_fd, hdr, hdrlen);
- pack_offset += hdrlen;
+ pack_size += hdrlen;
}
s.avail_out = deflateBound(&s, s.avail_in);
deflateEnd(&s);
ywrite(pack_fd, out, s.total_out);
- pack_offset += s.total_out;
+ pack_size += s.total_out;
free(out);
if (delta)
free(last->data);
last->data = dat;
last->len = datlen;
- memcpy(last->sha1, sha1, sizeof(sha1));
+ hashcpy(last->sha1, sha1);
}
return 0;
}
+static unsigned char* map_pack(unsigned long offset, unsigned int *left)
+{
+ if (offset >= pack_size)
+ die("object offset outside of pack file");
+ if (!pack_base
+ || offset < pack_moff
+ || (offset + 20) >= (pack_moff + pack_mlen)) {
+ if (pack_base)
+ munmap(pack_base, pack_mlen);
+ pack_moff = (offset / page_size) * page_size;
+ pack_base = mmap(NULL,pack_mlen,PROT_READ,MAP_SHARED,
+ pack_fd,pack_moff);
+ if (pack_base == MAP_FAILED)
+ die("Failed to map generated pack: %s", strerror(errno));
+ remap_count++;
+ }
+ offset -= pack_moff;
+ if (left)
+ *left = pack_mlen - offset;
+ return 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 = *map_pack(offset++, NULL);
+ *type = (c >> 4) & 7;
+ size = c & 15;
+ shift = 4;
+ while (c & 0x80) {
+ c = *map_pack(offset++, NULL);
+ 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);
+ 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 || st == Z_BUF_ERROR) {
+ o = stream.next_in - pack_base + pack_moff;
+ stream.next_in = map_pack(o, &stream.avail_in);
+ continue;
+ }
+ die("Error %i from zlib during inflate.", st);
+ }
+ 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,
+ unsigned int *delta_depth);
+
+static void *unpack_delta_entry(unsigned long offset,
+ unsigned long delta_size,
+ unsigned long *sizep,
+ unsigned int *delta_depth)
+{
+ struct object_entry *base_oe;
+ unsigned char *base_sha1;
+ void *delta_data, *base, *result;
+ unsigned long base_size, result_size;
+
+ base_sha1 = map_pack(offset, NULL);
+ 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_depth);
+ 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;
+ (*delta_depth)++;
+ return result;
+}
+
+static void *unpack_entry(unsigned long offset,
+ unsigned long *sizep,
+ unsigned int *delta_depth)
+{
+ 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, delta_depth);
+ case OBJ_COMMIT:
+ case OBJ_TREE:
+ case OBJ_BLOB:
+ case OBJ_TAG:
+ *sizep = size;
+ *delta_depth = 0;
+ return unpack_non_delta_entry(offset, size);
+ default:
+ die("I created an object I can't read!");
+ }
+}
+
static const char *get_mode(const char *str, unsigned int *modep)
{
unsigned char c;
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;
char *buf;
const char *c;
- char type[20];
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) {
- die("FIXME");
+ if (myoe->type != OBJ_TREE)
+ die("Not a tree: %s", sha1_to_hex(sha1));
+ buf = unpack_entry(myoe->offset, &size, &t->delta_depth);
} else {
- buf = read_sha1_file(root->sha1, type, &size);
+ char type[20];
+ buf = read_sha1_file(sha1, type, &size);
if (!buf || strcmp(type, tree_type))
- die("Can't load existing 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)
+{
+ size_t maxlen = 0;
unsigned int i;
- size_t maxlen;
char *buf, *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);
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);
- free(buf);
+
+ *szp = c - buf;
+ return buf;
+}
+
+static void store_tree(struct tree_entry *root)
+{
+ struct tree_content *t = root->tree;
+ unsigned int i, j, del;
+ unsigned long vers1len;
+ void **vers1dat;
+ struct last_object lo;
+
+ 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]);
+ }
+
+ if (is_null_sha1(root->versions[0].sha1)
+ || !find_object(root->versions[0].sha1)) {
+ lo.data = NULL;
+ lo.depth = 0;
+ } else {
+ lo.data = mktree(t, 0, &lo.len);
+ lo.depth = t->delta_depth;
+ hashcpy(lo.sha1, root->versions[0].sha1);
+ }
+ vers1dat = mktree(t, 1, &vers1len);
+
+ store_object(OBJ_TREE, vers1dat, vers1len,
+ &lo, root->versions[1].sha1, 0);
+ /* note: lo.dat (if created) was freed by store_object */
+ free(vers1dat);
+
+ t->delta_depth = lo.depth;
+ hashcpy(root->versions[0].sha1, root->versions[1].sha1);
+ 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(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);
+ hashclr(root->versions[1].sha1);
return 1;
}
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);
+ if (e->tree) {
+ release_tree_content_recursive(e->tree);
+ e->tree = NULL;
+ }
+ e->versions[1].mode = 0;
+ hashclr(e->versions[1].sha1);
+ hashclr(root->versions[1].sha1);
return 1;
}
static void init_pack_header()
{
- const char* magic = "PACK";
- unsigned long version = 3;
- unsigned long zero = 0;
+ struct pack_header hdr;
- version = htonl(version);
- ywrite(pack_fd, (char*)magic, 4);
- ywrite(pack_fd, &version, 4);
- ywrite(pack_fd, &zero, 4);
- pack_offset = 4 * 3;
+ 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()
{
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));
+ return hashcmp(a->sha1, b->sha1);
}
static void write_index(const char *idx_name)
}
}
+static void dump_tags()
+{
+ static const char *msg = "fast-import";
+ struct tag *t;
+ struct ref_lock *lock;
+ char path[PATH_MAX];
+
+ 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);
+ 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');
static void cmd_mark()
{
if (!strncmp("mark :", command_buf.buf, 6)) {
- command_mark = strtoul(command_buf.buf + 6, NULL, 10);
+ next_mark = strtoul(command_buf.buf + 6, NULL, 10);
read_next_command();
}
else
- command_mark = 0;
+ next_mark = 0;
}
static void* cmd_data (size_t *size)
static void cmd_new_blob()
{
- size_t datlen;
- void *dat;
- unsigned char sha1[20];
+ size_t l;
+ void *d;
read_next_command();
cmd_mark();
- dat = cmd_data(&datlen);
+ d = cmd_data(&l);
- if (store_object(OBJ_BLOB, dat, datlen, &last_blob, sha1))
- free(dat);
+ if (store_object(OBJ_BLOB, d, l, &last_blob, NULL, next_mark))
+ free(d);
}
static void unload_one_branch()
{
- while (cur_active_branches >= max_active_branches) {
+ while (cur_active_branches
+ && cur_active_branches >= max_active_branches) {
unsigned long min_commit = ULONG_MAX;
struct branch *e, *l = NULL, *p = NULL;
}
e->active_next_branch = NULL;
if (e->branch_tree.tree) {
- release_tree_content(e->branch_tree.tree);
+ release_tree_content_recursive(e->branch_tree.tree);
e->branch_tree.tree = NULL;
}
cur_active_branches--;
b->active_next_branch = active_branches;
active_branches = b;
cur_active_branches++;
+ branch_load_count++;
}
static void file_change_m(struct branch *b)
switch (mode) {
case S_IFREG | 0644:
case S_IFREG | 0755:
+ case S_IFLNK:
case 0644:
case 0755:
/* ok */
die("Corrupt mode: %s", command_buf.buf);
}
- if (get_sha1_hex(p, sha1))
- die("Invalid SHA1: %s", command_buf.buf);
- p += 40;
+ if (*p == ':') {
+ char *x;
+ oe = find_mark(strtoul(p + 1, &x, 10));
+ p = x;
+ } else {
+ if (get_sha1_hex(p, sha1))
+ die("Invalid SHA1: %s", command_buf.buf);
+ oe = find_object(sha1);
+ p += 40;
+ }
if (*p++ != ' ')
die("Missing space after SHA1: %s", command_buf.buf);
p = p_uq;
}
- oe = find_object(sha1);
if (oe) {
if (oe->type != OBJ_BLOB)
die("Not a blob (actually a %s): %s",
free(p_uq);
}
+static void cmd_from(struct branch *b)
+{
+ const char *from, *endp;
+ char *str_uq;
+ struct branch *s;
+
+ if (strncmp("from ", command_buf.buf, 5))
+ return;
+
+ if (b->last_commit)
+ die("Can't reinitailize branch %s", b->name);
+
+ 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;
+ }
+
+ s = lookup_branch(from);
+ if (b == s)
+ die("Can't create a branch from itself: %s", b->name);
+ else if (s) {
+ 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);
+ unsigned long size;
+ unsigned int depth;
+ char *buf;
+ if (oe->type != OBJ_COMMIT)
+ die("Mark :%lu not a commit", idnum);
+ hashcpy(b->sha1, oe->sha1);
+ buf = unpack_entry(oe->offset, &size, &depth);
+ if (!buf || size < 46)
+ die("Not a valid commit: %s", from);
+ if (memcmp("tree ", buf, 5)
+ || 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 (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;
+
+ buf = read_object_with_reference(b->sha1,
+ type_names[OBJ_COMMIT], &size, b->sha1);
+ if (!buf || size < 46)
+ die("Not a valid commit: %s", from);
+ if (memcmp("tree ", buf, 5)
+ || 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 void cmd_new_commit()
{
struct branch *b;
}
b = lookup_branch(sp);
if (!b)
- die("Branch not declared: %s", sp);
+ b = new_branch(sp);
if (str_uq)
free(str_uq);
if (!committer)
die("Expected committer but didn't get one");
msg = cmd_data(&msglen);
+ read_next_command();
+ cmd_from(b);
/* ensure the branch is active/loaded */
- if (!b->branch_tree.tree) {
+ if (!b->branch_tree.tree || !max_active_branches) {
unload_one_branch();
load_branch(b);
}
/* file_change* */
for (;;) {
- read_next_command();
if (1 == command_buf.len)
break;
else if (!strncmp("M ", command_buf.buf, 2))
file_change_d(b);
else
die("Unsupported file_change: %s", command_buf.buf);
+ read_next_command();
}
/* build the tree and the commit */
? 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 += 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));
if (author)
sp += sprintf(sp, "%s\n", author);
free(committer);
free(msg);
- store_object(OBJ_COMMIT, body, sp - body, NULL, b->sha1);
+ store_object(OBJ_COMMIT, body, sp - body, NULL, b->sha1, next_mark);
free(body);
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_branch()
+static void cmd_new_tag()
{
- struct branch *b;
char *str_uq;
const char *endp;
char *sp;
+ const char *from;
+ char *tagger;
+ 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 branch name from the rest of our command */
+ /* Obtain the new tag 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);
+ die("Garbage after tag name in: %s", command_buf.buf);
sp = str_uq;
}
- b = new_branch(sp);
+ t = pool_alloc(sizeof(struct tag));
+ t->next_tag = NULL;
+ t->name = pool_strdup(sp);
+ if (last_tag)
+ last_tag->next_tag = t;
+ else
+ first_tag = t;
+ last_tag = t;
if (str_uq)
free(str_uq);
read_next_command();
/* from ... */
- if (!strncmp("from ", command_buf.buf, 5)) {
- const char *from;
- struct branch *s;
-
- 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;
- }
+ if (strncmp("from ", command_buf.buf, 5))
+ die("Expected from command, got %s", command_buf.buf);
- s = lookup_branch(from);
- 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);
- } else if (!get_sha1(from, b->sha1)) {
- if (!memcmp(b->sha1, null_sha1, 20))
- memcpy(b->branch_tree.sha1, null_sha1, 20);
- else {
- unsigned long size;
- char *buf;
-
- buf = read_object_with_reference(b->sha1,
- type_names[OBJ_COMMIT], &size, b->sha1);
- 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))
- die("The commit %s is corrupt", sha1_to_hex(b->sha1));
- free(buf);
- }
- } else
- die("Invalid ref name or SHA1 expression: %s", from);
+ 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;
+ }
- if (str_uq)
- free(str_uq);
- read_next_command();
- } else {
- memcpy(b->sha1, null_sha1, 20);
- memcpy(b->branch_tree.sha1, null_sha1, 20);
+ s = lookup_branch(from);
+ if (s) {
+ hashcpy(sha1, s->sha1);
+ } else if (*from == ':') {
+ 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", from_mark);
+ hashcpy(sha1, oe->sha1);
+ } else if (!get_sha1(from, sha1)) {
+ unsigned long size;
+ char *buf;
+
+ buf = read_object_with_reference(sha1,
+ type_names[OBJ_COMMIT], &size, sha1);
+ if (!buf || size < 46)
+ die("Not a valid commit: %s", from);
+ free(buf);
+ } else
+ die("Invalid ref name or SHA1 expression: %s", from);
+
+ if (str_uq)
+ free(str_uq);
+ read_next_command();
+
+ /* tagger ... */
+ if (strncmp("tagger ", command_buf.buf, 7))
+ die("Expected tagger command, got %s", command_buf.buf);
+ tagger = strdup(command_buf.buf);
+
+ /* tag payload/message */
+ read_next_command();
+ msg = cmd_data(&msglen);
+
+ /* build the tag object */
+ body = xmalloc(67 + strlen(t->name) + strlen(tagger) + msglen);
+ sp = body;
+ 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);
+ sp += sprintf(sp, "%s\n\n", tagger);
+ memcpy(sp, msg, msglen);
+ sp += msglen;
+ free(tagger);
+ free(msg);
+
+ store_object(OBJ_TAG, body, sp - body, NULL, t->sha1, 0);
+ free(body);
+
+ 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;
- if (command_buf.eof || command_buf.len > 1)
- die("An lf did not terminate the branch command as expected.");
+ /* 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;
+ }
+ }
+ if (str_uq)
+ free(str_uq);
}
+static const char fast_import_usage[] =
+"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 = argv[1];
- int est_obj_cnt = atoi(argv[2]);
+ const char *base_name;
+ int i;
+ unsigned long est_obj_cnt = 1000;
char *pack_name;
char *idx_name;
struct stat sb;
setup_ident();
git_config(git_default_config);
+ page_size = getpagesize();
+
+ for (i = 1; i < argc; i++) {
+ const char *a = argv[i];
+
+ if (*a != '-' || !strcmp(a, "--"))
+ break;
+ else if (!strncmp(a, "--objects=", 10))
+ est_obj_cnt = strtoul(a + 10, NULL, 0);
+ else if (!strncmp(a, "--depth=", 8))
+ 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);
+ }
+ if ((i+1) != argc)
+ usage(fast_import_usage);
+ base_name = argv[i];
pack_name = xmalloc(strlen(base_name) + 6);
sprintf(pack_name, "%s.pack", base_name);
atom_table = xcalloc(atom_table_sz, sizeof(struct atom_str*));
branch_table = xcalloc(branch_table_sz, sizeof(struct branch*));
avail_tree_table = xcalloc(avail_tree_table_sz, sizeof(struct avail_tree_content*));
+ marks = pool_calloc(1, sizeof(struct mark_set));
for (;;) {
read_next_command();
break;
else if (!strcmp("blob", command_buf.buf))
cmd_new_blob();
- else if (!strncmp("branch ", command_buf.buf, 7))
- cmd_new_branch();
else if (!strncmp("commit ", command_buf.buf, 7))
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
die("Unsupported command: %s", command_buf.buf);
}
close(pack_fd);
write_index(idx_name);
dump_branches();
+ dump_tags();
+ dump_marks();
+ if (branch_log)
+ fclose(branch_log);
fprintf(stderr, "%s statistics:\n", argv[0]);
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 branches: %10lu\n", branch_count);
- fprintf(stderr, "Total atoms: %10u\n", atom_cnt);
+ 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);