| new_commit
| new_tag
| reset_branch
+ | checkpoint
;
new_blob ::= 'blob' lf
lf;
commit_msg ::= data;
- file_change ::= 'M' sp mode sp (hexsha1 | idnum) sp path_str lf
- | 'D' sp path_str lf
- ;
- mode ::= '644' | '755';
+ file_change ::= file_del | file_obm | file_inm;
+ file_del ::= 'D' sp path_str lf;
+ file_obm ::= 'M' sp mode sp (hexsha1 | idnum) sp path_str lf;
+ file_inm ::= 'M' sp mode sp 'inline' sp path_str lf
+ data;
new_tag ::= 'tag' sp tag_str lf
'from' sp (ref_str | hexsha1 | sha1exp_str | idnum) 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
# a new mark directive with the old idnum.
#
mark ::= 'mark' sp idnum lf;
+ data ::= (delimited_data | exact_data)
+ lf;
+
+ # note: delim may be any string but must not contain lf.
+ # data_line may contain any data but must not be exactly
+ # delim.
+ delimited_data ::= 'data' sp '<<' delim lf
+ (data_line lf)*
+ delim lf;
# note: declen indicates the length of binary_data in bytes.
- # declen does not include the lf preceeding or trailing the
- # binary data.
+ # declen does not include the lf preceeding the binary data.
#
- data ::= 'data' sp declen lf
- binary_data
- lf;
+ exact_data ::= 'data' sp declen lf
+ binary_data;
# note: quoted strings are C-style quoting supporting \c for
# common escapes of 'c' (e..g \n, \t, \\, \") or \nnn where nnn
sha1exp_str ::= sha1exp | '"' quoted(sha1exp) '"' ;
tag_str ::= tag | '"' quoted(tag) '"' ;
path_str ::= path | '"' quoted(path) '"' ;
+ mode ::= '100644' | '644'
+ | '100755' | '755'
+ | '140000'
+ ;
declen ::= # unsigned 32 bit value, ascii base10 notation;
+ bigint ::= # unsigned integer value, ascii base10 notation;
binary_data ::= # file content, not interpreted;
sp ::= # ASCII space character;
# an idnum. This is to distinguish it from a ref or tag name as
# GIT does not permit ':' in ref or tag strings.
#
- idnum ::= ':' declen;
+ idnum ::= ':' bigint;
path ::= # GIT style file path, e.g. "a/b/c";
ref ::= # GIT ref name, e.g. "refs/heads/MOZ_GECKO_EXPERIMENT";
tag ::= # GIT tag name, e.g. "FIREFOX_1_5";
#include "strbuf.h"
#include "quote.h"
+#define PACK_ID_BITS 16
+#define MAX_PACK_ID ((1<<PACK_ID_BITS)-1)
+
struct object_entry
{
struct object_entry *next;
- unsigned long offset;
+ uint32_t offset;
unsigned type : TYPE_BITS;
+ unsigned pack_id : PACK_ID_BITS;
unsigned char sha1[20];
};
struct mark_set
{
- int shift;
union {
struct object_entry *marked[1024];
struct mark_set *sets[1024];
} data;
+ unsigned int shift;
};
struct last_object
{
void *data;
unsigned long len;
- unsigned long offset;
+ uint32_t offset;
unsigned int depth;
unsigned no_free:1;
};
struct atom_str
{
struct atom_str *next_atom;
- int str_len;
+ unsigned short str_len;
char str_dat[FLEX_ARRAY]; /* more */
};
struct atom_str* name;
struct tree_entry_ms
{
- unsigned int mode;
+ uint16_t mode;
unsigned char sha1[20];
} versions[2];
};
struct branch *table_next_branch;
struct branch *active_next_branch;
const char *name;
- unsigned long last_commit;
struct tree_entry branch_tree;
+ uintmax_t last_commit;
+ unsigned int pack_id;
unsigned char sha1[20];
};
{
struct tag *next_tag;
const char *name;
+ unsigned int pack_id;
unsigned char sha1[20];
};
unsigned char sha1[20];
};
-/* Stats and misc. counters */
+/* Configured limits on output */
static unsigned long max_depth = 10;
-static unsigned long alloc_count;
+static unsigned long max_packsize = (1LL << 32) - 1;
+
+/* Stats and misc. counters */
+static uintmax_t alloc_count;
+static uintmax_t marks_set_count;
+static uintmax_t object_count_by_type[1 << TYPE_BITS];
+static uintmax_t duplicate_count_by_type[1 << TYPE_BITS];
+static uintmax_t delta_count_by_type[1 << TYPE_BITS];
+static unsigned long object_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[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 unsigned int pack_id;
static struct packed_git *pack_data;
-static int pack_fd;
+static struct packed_git **all_packs;
static unsigned long pack_size;
-static unsigned char pack_sha1[20];
/* Table of objects we've written. */
static unsigned int object_entry_alloc = 5000;
/* Input stream parsing */
static struct strbuf command_buf;
-static unsigned long next_mark;
+static uintmax_t next_mark;
static struct dbuf new_data;
static FILE* branch_log;
b->buffer = xmalloc(b->capacity);
}
-static void insert_mark(unsigned long idnum, struct object_entry *oe)
+static void insert_mark(uintmax_t idnum, struct object_entry *oe)
{
struct mark_set *s = marks;
while ((idnum >> s->shift) >= 1024) {
marks = s;
}
while (s->shift) {
- unsigned long i = idnum >> s->shift;
+ uintmax_t 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.marked[idnum] = oe;
}
-static struct object_entry* find_mark(unsigned long idnum)
+static struct object_entry* find_mark(uintmax_t idnum)
{
- unsigned long orig_idnum = idnum;
+ uintmax_t 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;
+ uintmax_t i = idnum >> s->shift;
idnum -= i << s->shift;
s = s->data.sets[i];
}
oe = s->data.marked[idnum];
}
if (!oe)
- die("mark :%lu not declared", orig_idnum);
+ die("mark :%ju not declared", orig_idnum);
return oe;
}
-static struct atom_str* to_atom(const char *s, size_t len)
+static struct atom_str* to_atom(const char *s, unsigned short len)
{
unsigned int hc = hc_str(s, len) % atom_table_sz;
struct atom_str *c;
b->table_next_branch = branch_table[hc];
b->branch_tree.versions[0].mode = S_IFDIR;
b->branch_tree.versions[1].mode = S_IFDIR;
+ b->pack_id = MAX_PACK_ID;
branch_table[hc] = b;
branch_count++;
return b;
return r;
}
-static struct tree_entry* new_tree_entry()
+static struct tree_entry* new_tree_entry(void)
{
struct tree_entry *e;
avail_tree_entry = e;
}
-static void yread(int fd, void *buffer, size_t length)
+static void start_packfile(void)
+{
+ static char tmpfile[PATH_MAX];
+ struct packed_git *p;
+ struct pack_header hdr;
+ int pack_fd;
+
+ snprintf(tmpfile, sizeof(tmpfile),
+ "%s/pack_XXXXXX", get_object_directory());
+ pack_fd = mkstemp(tmpfile);
+ if (pack_fd < 0)
+ die("Can't create %s: %s", tmpfile, strerror(errno));
+ p = xcalloc(1, sizeof(*p) + strlen(tmpfile) + 2);
+ strcpy(p->pack_name, tmpfile);
+ p->pack_fd = pack_fd;
+
+ hdr.hdr_signature = htonl(PACK_SIGNATURE);
+ hdr.hdr_version = htonl(2);
+ hdr.hdr_entries = 0;
+ write_or_die(p->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(void)
+{
+ static const int buf_sz = 128 * 1024;
+ int pack_fd = pack_data->pack_fd;
+ SHA_CTX c;
+ struct pack_header hdr;
+ char *buf;
+
+ if (lseek(pack_fd, 0, SEEK_SET) != 0)
+ die("Failed seeking to start: %s", strerror(errno));
+ if (read_in_full(pack_fd, &hdr, sizeof(hdr)) != sizeof(hdr))
+ die("Unable to reread header of %s", pack_data->pack_name);
+ if (lseek(pack_fd, 0, SEEK_SET) != 0)
+ die("Failed seeking to start: %s", strerror(errno));
+ hdr.hdr_entries = htonl(object_count);
+ write_or_die(pack_fd, &hdr, sizeof(hdr));
+
+ SHA1_Init(&c);
+ SHA1_Update(&c, &hdr, sizeof(hdr));
+
+ buf = xmalloc(buf_sz);
+ for (;;) {
+ size_t n = xread(pack_fd, buf, buf_sz);
+ if (!n)
+ break;
+ if (n < 0)
+ die("Failed to checksum %s", pack_data->pack_name);
+ SHA1_Update(&c, buf, n);
+ }
+ free(buf);
+
+ SHA1_Final(pack_data->sha1, &c);
+ write_or_die(pack_fd, pack_data->sha1, sizeof(pack_data->sha1));
+ close(pack_fd);
+}
+
+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 char* create_index(void)
+{
+ static char tmpfile[PATH_MAX];
+ SHA_CTX ctx;
+ struct sha1file *f;
+ struct object_entry **idx, **c, **last, *e;
+ struct object_entry_pool *o;
+ uint32_t array[256];
+ int i, idx_fd;
+
+ /* 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->next_free; e-- != o->entries;)
+ if (pack_id == e->pack_id)
+ *c++ = e;
+ last = idx + object_count;
+ if (c != last)
+ die("internal consistency error creating the index");
+ 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;
+ }
+
+ snprintf(tmpfile, sizeof(tmpfile),
+ "%s/index_XXXXXX", get_object_directory());
+ idx_fd = mkstemp(tmpfile);
+ if (idx_fd < 0)
+ die("Can't create %s: %s", tmpfile, strerror(errno));
+ f = sha1fd(idx_fd, tmpfile);
+ sha1write(f, array, 256 * sizeof(int));
+ SHA1_Init(&ctx);
+ for (c = idx; c != last; c++) {
+ uint32_t offset = htonl((*c)->offset);
+ sha1write(f, &offset, 4);
+ sha1write(f, (*c)->sha1, sizeof((*c)->sha1));
+ SHA1_Update(&ctx, (*c)->sha1, 20);
+ }
+ sha1write(f, pack_data->sha1, sizeof(pack_data->sha1));
+ sha1close(f, NULL, 1);
+ free(idx);
+ SHA1_Final(pack_data->sha1, &ctx);
+ return tmpfile;
+}
+
+static char* keep_pack(char *curr_index_name)
+{
+ static char name[PATH_MAX];
+ static char *keep_msg = "fast-import";
+ int keep_fd;
+
+ chmod(pack_data->pack_name, 0444);
+ chmod(curr_index_name, 0444);
+
+ snprintf(name, sizeof(name), "%s/pack/pack-%s.keep",
+ get_object_directory(), sha1_to_hex(pack_data->sha1));
+ keep_fd = open(name, O_RDWR|O_CREAT|O_EXCL, 0600);
+ if (keep_fd < 0)
+ die("cannot create keep file");
+ write(keep_fd, keep_msg, strlen(keep_msg));
+ close(keep_fd);
+
+ snprintf(name, sizeof(name), "%s/pack/pack-%s.pack",
+ get_object_directory(), sha1_to_hex(pack_data->sha1));
+ if (move_temp_to_file(pack_data->pack_name, name))
+ die("cannot store pack file");
+
+ snprintf(name, sizeof(name), "%s/pack/pack-%s.idx",
+ get_object_directory(), sha1_to_hex(pack_data->sha1));
+ if (move_temp_to_file(curr_index_name, name))
+ die("cannot store index file");
+ return name;
+}
+
+static void unkeep_all_packs(void)
{
- ssize_t ret = 0;
- while (ret < length) {
- ssize_t size = xread(fd, (char *) buffer + ret, length - ret);
- if (!size)
- die("Read from descriptor %i: end of stream", fd);
- if (size < 0)
- die("Read from descriptor %i: %s", fd, strerror(errno));
- ret += size;
+ static char name[PATH_MAX];
+ int k;
+
+ for (k = 0; k < pack_id; k++) {
+ struct packed_git *p = all_packs[k];
+ snprintf(name, sizeof(name), "%s/pack/pack-%s.keep",
+ get_object_directory(), sha1_to_hex(p->sha1));
+ unlink(name);
+ }
+}
+
+static void end_packfile(void)
+{
+ struct packed_git *old_p = pack_data, *new_p;
+
+ if (object_count) {
+ char *idx_name;
+ int i;
+ struct branch *b;
+ struct tag *t;
+
+ fixup_header_footer();
+ idx_name = keep_pack(create_index());
+
+ /* 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;
+ all_packs[pack_id] = new_p;
+ install_packed_git(new_p);
+
+ /* Print the boundary */
+ fprintf(stdout, "%s:", new_p->pack_name);
+ for (i = 0; i < branch_table_sz; i++) {
+ for (b = branch_table[i]; b; b = b->table_next_branch) {
+ if (b->pack_id == pack_id)
+ fprintf(stdout, " %s", sha1_to_hex(b->sha1));
+ }
+ }
+ for (t = first_tag; t; t = t->next_tag) {
+ if (t->pack_id == pack_id)
+ fprintf(stdout, " %s", sha1_to_hex(t->sha1));
+ }
+ fputc('\n', stdout);
+
+ pack_id++;
}
+ else
+ unlink(old_p->pack_name);
+ free(old_p);
+
+ /* 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 void checkpoint(void)
+{
+ end_packfile();
+ start_packfile();
}
static size_t encode_header(
size_t datlen,
struct last_object *last,
unsigned char *sha1out,
- unsigned long mark)
+ uintmax_t mark)
{
void *out, *delta;
struct object_entry *e;
if (mark)
insert_mark(mark, e);
if (e->offset) {
- duplicate_count++;
duplicate_count_by_type[type]++;
return 1;
}
- e->type = type;
- e->offset = pack_size;
- object_count++;
- object_count_by_type[type]++;
- if (last && last->data && last->depth < max_depth)
+ if (last && last->data && last->depth < max_depth) {
delta = diff_delta(last->data, last->len,
dat, datlen,
&deltalen, 0);
- else
- delta = 0;
+ if (delta && deltalen >= datlen) {
+ free(delta);
+ delta = NULL;
+ }
+ } else
+ delta = NULL;
memset(&s, 0, sizeof(s));
deflateInit(&s, zlib_compression_level);
+ if (delta) {
+ s.next_in = delta;
+ s.avail_in = deltalen;
+ } else {
+ s.next_in = dat;
+ s.avail_in = datlen;
+ }
+ s.avail_out = deflateBound(&s, s.avail_in);
+ s.next_out = out = xmalloc(s.avail_out);
+ while (deflate(&s, Z_FINISH) == Z_OK)
+ /* nothing */;
+ deflateEnd(&s);
+
+ /* Determine if we should auto-checkpoint. */
+ if ((pack_size + 60 + s.total_out) > max_packsize
+ || (pack_size + 60 + s.total_out) < pack_size) {
+
+ /* This new object needs to *not* have the current pack_id. */
+ e->pack_id = pack_id + 1;
+ checkpoint();
+
+ /* We cannot carry a delta into the new pack. */
+ if (delta) {
+ free(delta);
+ delta = NULL;
+
+ memset(&s, 0, sizeof(s));
+ deflateInit(&s, zlib_compression_level);
+ s.next_in = dat;
+ s.avail_in = datlen;
+ s.avail_out = deflateBound(&s, s.avail_in);
+ s.next_out = out = xrealloc(out, s.avail_out);
+ while (deflate(&s, Z_FINISH) == Z_OK)
+ /* nothing */;
+ deflateEnd(&s);
+ }
+ }
+
+ e->type = type;
+ e->pack_id = pack_id;
+ e->offset = pack_size;
+ object_count++;
+ object_count_by_type[type]++;
if (delta) {
unsigned long ofs = e->offset - last->offset;
delta_count_by_type[type]++;
last->depth++;
- s.next_in = delta;
- s.avail_in = deltalen;
hdrlen = encode_header(OBJ_OFS_DELTA, deltalen, hdr);
- write_or_die(pack_fd, hdr, hdrlen);
+ write_or_die(pack_data->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);
+ write_or_die(pack_data->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);
- write_or_die(pack_fd, hdr, hdrlen);
+ write_or_die(pack_data->pack_fd, hdr, hdrlen);
pack_size += hdrlen;
}
- s.avail_out = deflateBound(&s, s.avail_in);
- s.next_out = out = xmalloc(s.avail_out);
- while (deflate(&s, Z_FINISH) == Z_OK)
- /* nothing */;
- deflateEnd(&s);
-
- write_or_die(pack_fd, out, s.total_out);
+ write_or_die(pack_data->pack_fd, out, s.total_out);
pack_size += s.total_out;
free(out);
return 0;
}
-static void *gfi_unpack_entry(unsigned long ofs, unsigned long *sizep)
+static void *gfi_unpack_entry(
+ struct object_entry *oe,
+ unsigned long *sizep)
{
- char type[20];
- pack_data->pack_size = pack_size + 20;
- return unpack_entry(pack_data, ofs, type, sizep);
+ 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 const char *get_mode(const char *str, uint16_t *modep)
{
unsigned char c;
- unsigned int mode = 0;
+ uint16_t mode = 0;
while ((c = *str++) != ' ') {
if (c < '0' || c > '7')
if (myoe->type != OBJ_TREE)
die("Not a tree: %s", sha1_to_hex(sha1));
t->delta_depth = 0;
- buf = gfi_unpack_entry(myoe->offset, &size);
+ buf = gfi_unpack_entry(myoe, &size);
} else {
char type[20];
buf = read_sha1_file(sha1, type, &size);
if (!c)
die("Corrupt mode in %s", sha1_to_hex(sha1));
e->versions[0].mode = e->versions[1].mode;
- e->name = to_atom(c, strlen(c));
+ e->name = to_atom(c, (unsigned short)strlen(c));
c += e->name->str_len + 1;
hashcpy(e->versions[0].sha1, (unsigned char*)c);
hashcpy(e->versions[1].sha1, (unsigned char*)c);
struct tree_entry *e = t->entries[i];
if (!e->versions[v].mode)
continue;
- c += sprintf(c, "%o", e->versions[v].mode);
+ c += sprintf(c, "%o", (unsigned int)e->versions[v].mode);
*c++ = ' ';
strcpy(c, e->name->str_dat);
c += e->name->str_len + 1;
}
le = find_object(root->versions[0].sha1);
- if (!S_ISDIR(root->versions[0].mode) || !le) {
+ if (!S_ISDIR(root->versions[0].mode)
+ || !le
+ || le->pack_id != pack_id) {
lo.data = NULL;
lo.depth = 0;
} else {
struct tree_entry *root,
const char *p,
const unsigned char *sha1,
- const unsigned int mode)
+ const uint16_t mode)
{
struct tree_content *t = root->tree;
const char *slash1;
if (t->entry_count == t->entry_capacity)
root->tree = t = grow_tree_content(t, 8);
e = new_tree_entry();
- e->name = to_atom(p, n);
+ e->name = to_atom(p, (unsigned short)n);
e->versions[0].mode = 0;
hashclr(e->versions[0].sha1);
t->entries[t->entry_count++] = e;
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;
-
- write_or_die(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);
- write_or_die(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);
- 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;
- 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));
- }
- sha1write(f, pack_sha1, sizeof(pack_sha1));
- sha1close(f, NULL, 1);
- free(idx);
-}
-
-static void dump_branches()
+static void dump_branches(void)
{
static const char *msg = "fast-import";
unsigned int i;
}
}
-static void dump_tags()
+static void dump_tags(void)
{
static const char *msg = "fast-import";
struct tag *t;
}
static void dump_marks_helper(FILE *f,
- unsigned long base,
+ uintmax_t base,
struct mark_set *m)
{
- int k;
+ uintmax_t k;
if (m->shift) {
for (k = 0; k < 1024; k++) {
if (m->data.sets[k])
} else {
for (k = 0; k < 1024; k++) {
if (m->data.marked[k])
- fprintf(f, ":%lu %s\n", base + k,
+ fprintf(f, ":%ju %s\n", base + k,
sha1_to_hex(m->data.marked[k]->sha1));
}
}
}
-static void dump_marks()
+static void dump_marks(void)
{
if (mark_file)
{
}
}
-static void read_next_command()
+static void read_next_command(void)
{
read_line(&command_buf, stdin, '\n');
}
-static void cmd_mark()
+static void cmd_mark(void)
{
if (!strncmp("mark :", command_buf.buf, 6)) {
- next_mark = strtoul(command_buf.buf + 6, NULL, 10);
+ next_mark = strtoumax(command_buf.buf + 6, NULL, 10);
read_next_command();
}
else
static void* cmd_data (size_t *size)
{
- size_t n = 0;
- void *buffer;
size_t length;
+ char *buffer;
if (strncmp("data ", command_buf.buf, 5))
die("Expected 'data n' command, found: %s", command_buf.buf);
- length = strtoul(command_buf.buf + 5, NULL, 10);
- buffer = xmalloc(length);
-
- while (n < length) {
- size_t s = fread((char*)buffer + n, 1, length - n, stdin);
- if (!s && feof(stdin))
- die("EOF in data (%lu bytes remaining)", length - n);
- n += s;
+ if (!strncmp("<<", command_buf.buf + 5, 2)) {
+ char *term = xstrdup(command_buf.buf + 5 + 2);
+ size_t sz = 8192, term_len = command_buf.len - 5 - 2;
+ length = 0;
+ buffer = xmalloc(sz);
+ for (;;) {
+ read_next_command();
+ if (command_buf.eof)
+ die("EOF in data (terminator '%s' not found)", term);
+ if (term_len == command_buf.len
+ && !strcmp(term, command_buf.buf))
+ break;
+ if (sz < (length + command_buf.len)) {
+ sz = sz * 3 / 2 + 16;
+ if (sz < (length + command_buf.len))
+ sz = length + command_buf.len;
+ buffer = xrealloc(buffer, sz);
+ }
+ memcpy(buffer + length,
+ command_buf.buf,
+ command_buf.len - 1);
+ length += command_buf.len - 1;
+ buffer[length++] = '\n';
+ }
+ free(term);
+ }
+ else {
+ size_t n = 0;
+ length = strtoul(command_buf.buf + 5, NULL, 10);
+ buffer = xmalloc(length);
+ while (n < length) {
+ size_t s = fread(buffer + n, 1, length - n, stdin);
+ if (!s && feof(stdin))
+ die("EOF in data (%lu bytes remaining)", length - n);
+ n += s;
+ }
}
if (fgetc(stdin) != '\n')
return buffer;
}
-static void cmd_new_blob()
+static void cmd_new_blob(void)
{
size_t l;
void *d;
free(d);
}
-static void unload_one_branch()
+static void unload_one_branch(void)
{
while (cur_active_branches
&& cur_active_branches >= max_active_branches) {
const char *endp;
struct object_entry *oe;
unsigned char sha1[20];
- unsigned int mode;
+ uint16_t mode, inline_data = 0;
char type[20];
p = get_mode(p, &mode);
if (*p == ':') {
char *x;
- oe = find_mark(strtoul(p + 1, &x, 10));
+ oe = find_mark(strtoumax(p + 1, &x, 10));
hashcpy(sha1, oe->sha1);
p = x;
+ } else if (!strncmp("inline", p, 6)) {
+ inline_data = 1;
+ p += 6;
} else {
if (get_sha1_hex(p, sha1))
die("Invalid SHA1: %s", command_buf.buf);
p = p_uq;
}
- if (oe) {
+ if (inline_data) {
+ size_t l;
+ void *d;
+ if (!p_uq)
+ p = p_uq = xstrdup(p);
+ read_next_command();
+ d = cmd_data(&l);
+ if (store_object(OBJ_BLOB, d, l, &last_blob, sha1, 0))
+ free(d);
+ } else if (oe) {
if (oe->type != OBJ_BLOB)
die("Not a blob (actually a %s): %s",
command_buf.buf, type_names[oe->type]);
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);
+ uintmax_t idnum = strtoumax(from + 1, NULL, 10);
struct object_entry *oe = find_mark(idnum);
unsigned long size;
char *buf;
if (oe->type != OBJ_COMMIT)
- die("Mark :%lu not a commit", idnum);
+ die("Mark :%ju not a commit", idnum);
hashcpy(b->sha1, oe->sha1);
- buf = gfi_unpack_entry(oe->offset, &size);
+ buf = gfi_unpack_entry(oe, &size);
if (!buf || size < 46)
die("Not a valid commit: %s", from);
if (memcmp("tree ", buf, 5)
if (s)
hashcpy(n->sha1, s->sha1);
else if (*from == ':') {
- unsigned long idnum = strtoul(from + 1, NULL, 10);
+ uintmax_t idnum = strtoumax(from + 1, NULL, 10);
struct object_entry *oe = find_mark(idnum);
if (oe->type != OBJ_COMMIT)
- die("Mark :%lu not a commit", idnum);
+ die("Mark :%ju 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);
return list;
}
-static void cmd_new_commit()
+static void cmd_new_commit(void)
{
struct branch *b;
void *msg;
free(committer);
free(msg);
- store_object(OBJ_COMMIT,
+ if (!store_object(OBJ_COMMIT,
new_data.buffer, sp - (char*)new_data.buffer,
- NULL, b->sha1, next_mark);
+ NULL, b->sha1, next_mark))
+ b->pack_id = pack_id;
b->last_commit = object_count_by_type[OBJ_COMMIT];
if (branch_log) {
fputc('"', branch_log);
} else
fprintf(branch_log, "%s", b->name);
- fprintf(branch_log," :%lu %s\n",next_mark,sha1_to_hex(b->sha1));
+ fprintf(branch_log," :%ju %s\n",next_mark,sha1_to_hex(b->sha1));
}
}
-static void cmd_new_tag()
+static void cmd_new_tag(void)
{
char *str_uq;
const char *endp;
void *msg;
size_t msglen;
struct tag *t;
- unsigned long from_mark = 0;
+ uintmax_t from_mark = 0;
unsigned char sha1[20];
/* Obtain the new tag name from the rest of our command */
if (s) {
hashcpy(sha1, s->sha1);
} else if (*from == ':') {
- from_mark = strtoul(from + 1, NULL, 10);
+ from_mark = strtoumax(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);
+ die("Mark :%ju not a commit", from_mark);
hashcpy(sha1, oe->sha1);
} else if (!get_sha1(from, sha1)) {
unsigned long size;
free(tagger);
free(msg);
- store_object(OBJ_TAG, new_data.buffer, sp - (char*)new_data.buffer,
- NULL, t->sha1, 0);
+ if (store_object(OBJ_TAG, new_data.buffer,
+ sp - (char*)new_data.buffer,
+ NULL, t->sha1, 0))
+ t->pack_id = MAX_PACK_ID;
+ else
+ t->pack_id = pack_id;
if (branch_log) {
int need_dq = quote_c_style(t->name, NULL, NULL, 0);
fputc('"', branch_log);
} else
fprintf(branch_log, "%s", t->name);
- fprintf(branch_log," :%lu %s\n",from_mark,sha1_to_hex(t->sha1));
+ fprintf(branch_log," :%ju %s\n",from_mark,sha1_to_hex(t->sha1));
}
}
-static void cmd_reset_branch()
+static void cmd_reset_branch(void)
{
struct branch *b;
char *str_uq;
cmd_from(b);
}
+static void cmd_checkpoint(void)
+{
+ if (object_count)
+ checkpoint();
+ read_next_command();
+}
+
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";
+"git-fast-import [--depth=n] [--active-branches=n] [--export-marks=marks.file] [--branch-log=log]";
int main(int argc, const char **argv)
{
- const char *base_name;
int i;
- unsigned long est_obj_cnt = object_entry_alloc;
- char *pack_name;
- char *idx_name;
- struct stat sb;
+ uintmax_t total_count, duplicate_count;
- setup_ident();
git_config(git_default_config);
for (i = 1; i < argc; i++) {
if (*a != '-' || !strcmp(a, "--"))
break;
- else if (!strncmp(a, "--objects=", 10))
- est_obj_cnt = strtoul(a + 10, NULL, 0);
+ else if (!strncmp(a, "--max-pack-size=", 16))
+ max_packsize = strtoumax(a + 16, NULL, 0) * 1024 * 1024;
else if (!strncmp(a, "--depth=", 8))
max_depth = strtoul(a + 8, NULL, 0);
else if (!strncmp(a, "--active-branches=", 18))
else
die("unknown option %s", a);
}
- if ((i+1) != argc)
+ if (i != argc)
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));
-
- pack_data = xcalloc(1, sizeof(*pack_data) + strlen(pack_name) + 2);
- strcpy(pack_data->pack_name, pack_name);
- pack_data->pack_fd = pack_fd;
-
- init_pack_header();
- alloc_objects(est_obj_cnt);
+ alloc_objects(object_entry_alloc);
strbuf_init(&command_buf);
atom_table = xcalloc(atom_table_sz, sizeof(struct atom_str*));
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_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();
+ unkeep_all_packs();
dump_marks();
if (branch_log)
fclose(branch_log);
+ total_count = 0;
+ for (i = 0; i < ARRAY_SIZE(object_count_by_type); i++)
+ total_count += object_count_by_type[i];
+ duplicate_count = 0;
+ 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, "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 %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, "Alloc'd objects: %10ju\n", alloc_count);
+ fprintf(stderr, "Total objects: %10ju (%10ju duplicates )\n", total_count, duplicate_count);
+ fprintf(stderr, " blobs : %10ju (%10ju duplicates %10ju deltas)\n", object_count_by_type[OBJ_BLOB], duplicate_count_by_type[OBJ_BLOB], delta_count_by_type[OBJ_BLOB]);
+ fprintf(stderr, " trees : %10ju (%10ju duplicates %10ju deltas)\n", object_count_by_type[OBJ_TREE], duplicate_count_by_type[OBJ_TREE], delta_count_by_type[OBJ_TREE]);
+ fprintf(stderr, " commits: %10ju (%10ju duplicates %10ju deltas)\n", object_count_by_type[OBJ_COMMIT], duplicate_count_by_type[OBJ_COMMIT], delta_count_by_type[OBJ_COMMIT]);
+ fprintf(stderr, " tags : %10ju (%10ju duplicates %10ju 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, " marks: %10ju (%10ju unique )\n", (((uintmax_t)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, "Memory total: %10ju 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);
- 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, " objects: %10ju KiB\n", (alloc_count*sizeof(struct object_entry))/1024);
+ fprintf(stderr, "---------------------------------------------------------------------\n");
+ pack_report();
fprintf(stderr, "---------------------------------------------------------------------\n");
-
fprintf(stderr, "\n");
return 0;
projects / thirdparty / git.git / blobdiff