X-Git-Url: http://git.ipfire.org/?a=blobdiff_plain;f=fast-import.c;h=2c500d6be32e8b83e8c7bd0c3768f3b9e6a08907;hb=6f64f6d9d2b12cdae1648cbf536685c888f3b981;hp=309f4d353bb32e33f5e98980afcda48ebd6c41a1;hpb=35ef237cf630418c2e45752eb527268693a2895b;p=thirdparty%2Fgit.git diff --git a/fast-import.c b/fast-import.c index 309f4d353b..2c500d6be3 100644 --- a/fast-import.c +++ b/fast-import.c @@ -6,6 +6,7 @@ Format of STDIN stream: cmd ::= new_blob | new_commit | new_tag + | reset_branch ; new_blob ::= 'blob' lf @@ -19,6 +20,7 @@ Format of STDIN stream: '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; @@ -34,6 +36,13 @@ Format of STDIN stream: 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 @@ -63,6 +72,7 @@ Format of STDIN stream: path_str ::= path | '"' quoted(path) '"' ; 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; @@ -72,7 +82,7 @@ Format of STDIN stream: # 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"; @@ -104,8 +114,9 @@ Format of STDIN stream: 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]; }; @@ -119,19 +130,20 @@ struct object_entry_pool 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 int len; + unsigned long len; + unsigned long offset; unsigned int depth; - unsigned char sha1[20]; + unsigned no_free:1; }; struct mem_pool @@ -145,7 +157,7 @@ struct mem_pool struct atom_str { struct atom_str *next_atom; - int str_len; + unsigned int str_len; char str_dat[FLEX_ARRAY]; /* more */ }; @@ -154,14 +166,18 @@ struct tree_entry { 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 */ }; @@ -176,8 +192,9 @@ struct branch struct branch *table_next_branch; struct branch *active_next_branch; const char *name; - unsigned long last_commit; struct tree_entry branch_tree; + unsigned long last_commit; + unsigned int pack_id; unsigned char sha1[20]; }; @@ -185,21 +202,36 @@ struct tag { struct tag *next_tag; const char *name; + unsigned int pack_id; unsigned char sha1[20]; }; +struct dbuf +{ + void *buffer; + size_t capacity; +}; -/* Stats and misc. counters */ +struct hash_list +{ + struct hash_list *next; + unsigned char sha1[20]; +}; + +/* Configured limits on output */ static unsigned long max_depth = 10; -static unsigned long alloc_count; +static unsigned long max_packsize = (1LL << 32) - 1; +static uintmax_t max_objects = -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[9]; -static unsigned long duplicate_count_by_type[9]; /* Memory pools */ static size_t mem_pool_alloc = 2*1024*1024 - sizeof(struct mem_pool); @@ -212,14 +244,13 @@ static unsigned int atom_cnt; static struct atom_str **atom_table; /* The .pack file being generated */ -static int pack_fd; +static unsigned int pack_id; +static struct packed_git *pack_data; +static struct packed_git **all_packs; 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; @@ -233,6 +264,8 @@ static unsigned int tree_entry_alloc = 1000; 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; @@ -247,11 +280,12 @@ static struct tag *last_tag; /* 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; -static void alloc_objects(int cnt) +static void alloc_objects(unsigned int cnt) { struct object_entry_pool *b; @@ -272,7 +306,7 @@ static struct object_entry* new_object(unsigned char *sha1) alloc_objects(object_entry_alloc); e = blocks->next_free++; - memcpy(e->sha1, sha1, sizeof(e->sha1)); + hashcpy(e->sha1, sha1); return e; } @@ -281,7 +315,7 @@ static struct object_entry* find_object(unsigned char *sha1) 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; } @@ -293,7 +327,7 @@ static struct object_entry* insert_object(unsigned char *sha1) 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; @@ -362,7 +396,18 @@ static char* pool_strdup(const char *s) return r; } -static void insert_mark(unsigned long idnum, struct object_entry *oe) +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(uintmax_t idnum, struct object_entry *oe) { struct mark_set *s = marks; while ((idnum >> s->shift) >= 1024) { @@ -372,7 +417,7 @@ static void insert_mark(unsigned long idnum, struct object_entry *oe) 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)); @@ -385,14 +430,14 @@ static void insert_mark(unsigned long idnum, struct object_entry *oe) 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]; } @@ -400,7 +445,7 @@ static struct object_entry* find_mark(unsigned long idnum) oe = s->data.marked[idnum]; } if (!oe) - die("mark :%lu not declared", orig_idnum); + die("mark :%ju not declared", orig_idnum); return oe; } @@ -447,6 +492,8 @@ static struct branch* new_branch(const char *name) 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; @@ -481,6 +528,7 @@ static struct tree_content* new_tree_content(unsigned int cnt) t = (struct tree_content*)f; t->entry_count = 0; + t->delta_depth = 0; return t; } @@ -507,6 +555,7 @@ 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; @@ -540,30 +589,227 @@ static void release_tree_entry(struct tree_entry *e) avail_tree_entry = e; } -static void yread(int fd, void *buffer, size_t length) +static void start_packfile() +{ + 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() { - 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; + int pack_fd = pack_data->pack_fd; + 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); + if (read_in_full(pack_fd, hdr, 8) != 8) + die("Unable to reread header of %s", pack_data->pack_name); + 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_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 void ywrite(int fd, void *buffer, size_t length) +static char* create_index() { - 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; + static char tmpfile[PATH_MAX]; + SHA_CTX ctx; + struct sha1file *f; + struct object_entry **idx, **c, **last, *e; + struct object_entry_pool *o; + unsigned int 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++) { + unsigned int 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() +{ + 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() +{ + 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() +{ + end_packfile(); + start_packfile(); } static size_t encode_header( @@ -574,7 +820,7 @@ 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); @@ -595,7 +841,7 @@ static int store_object( size_t datlen, struct last_object *last, unsigned char *sha1out, - unsigned long mark) + uintmax_t mark) { void *out, *delta; struct object_entry *e; @@ -611,190 +857,124 @@ static int store_object( 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_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) { - 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); } 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); - 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); - ywrite(pack_fd, out, s.total_out); + /* Determine if we should auto-checkpoint. */ + if ((object_count + 1) > max_objects + || (object_count + 1) < object_count + || (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; + unsigned pos = sizeof(hdr) - 1; + + delta_count_by_type[type]++; + last->depth++; + + hdrlen = encode_header(OBJ_OFS_DELTA, deltalen, hdr); + 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_data->pack_fd, hdr + pos, sizeof(hdr) - pos); + pack_size += sizeof(hdr) - pos; + } else { + if (last) + last->depth = 0; + hdrlen = encode_header(type, datlen, hdr); + write_or_die(pack_data->pack_fd, hdr, hdrlen); + pack_size += hdrlen; + } + + write_or_die(pack_data->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) @@ -813,6 +993,7 @@ 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; @@ -820,19 +1001,20 @@ static void load_tree(struct tree_entry *root) 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; @@ -844,56 +1026,119 @@ static void load_tree(struct tree_entry *root) 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( @@ -917,25 +1162,26 @@ 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; @@ -946,17 +1192,19 @@ static int tree_content_set( 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; } @@ -976,15 +1224,18 @@ static int tree_content_remove(struct tree_entry *root, const char *p) 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; } @@ -992,106 +1243,14 @@ static int tree_content_remove(struct tree_entry *root, const char *p) 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() @@ -1103,7 +1262,7 @@ 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); } @@ -1119,17 +1278,17 @@ static void dump_tags() 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, + 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]) @@ -1139,7 +1298,7 @@ static void dump_marks_helper(FILE *f, } 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)); } } @@ -1163,7 +1322,7 @@ static void read_next_command() static void cmd_mark() { 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 @@ -1276,7 +1435,8 @@ static void file_change_m(struct branch *b) 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 (get_sha1_hex(p, sha1)) @@ -1353,27 +1513,32 @@ static void cmd_from(struct branch *b) 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); + 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); - memcpy(b->sha1, oe->sha1, 20); - buf = unpack_entry(oe->offset, &size); + die("Mark :%ju not a commit", idnum); + 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; @@ -1382,9 +1547,11 @@ static void cmd_from(struct branch *b) 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); @@ -1392,6 +1559,48 @@ static void cmd_from(struct branch *b) 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 == ':') { + uintmax_t idnum = strtoumax(from + 1, NULL, 10); + struct object_entry *oe = find_mark(idnum); + if (oe->type != OBJ_COMMIT) + 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); + + 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; @@ -1402,7 +1611,8 @@ static void cmd_new_commit() 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; @@ -1433,6 +1643,7 @@ static void cmd_new_commit() 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) { @@ -1455,14 +1666,24 @@ static void cmd_new_commit() /* 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 @@ -1475,9 +1696,11 @@ static void cmd_new_commit() 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]; + b->pack_id = pack_id; if (branch_log) { int need_dq = quote_c_style(b->name, NULL, NULL, 0); @@ -1488,7 +1711,7 @@ static void cmd_new_commit() 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)); } } @@ -1502,9 +1725,8 @@ static void cmd_new_tag() struct branch *s; void *msg; size_t msglen; - char *body; 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 */ @@ -1541,13 +1763,13 @@ static void cmd_new_tag() s = lookup_branch(from); if (s) { - memcpy(sha1, s->sha1, 20); + 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); - memcpy(sha1, oe->sha1, 20); + die("Mark :%ju not a commit", from_mark); + hashcpy(sha1, oe->sha1); } else if (!get_sha1(from, sha1)) { unsigned long size; char *buf; @@ -1574,8 +1796,8 @@ static void cmd_new_tag() 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); @@ -1585,8 +1807,9 @@ static void cmd_new_tag() 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); + t->pack_id = pack_id; if (branch_log) { int need_dq = quote_c_style(t->name, NULL, NULL, 0); @@ -1597,21 +1820,56 @@ static void cmd_new_tag() 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() +{ + 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) + 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 [--objects=n] [--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 = 1000; - char *pack_name; - char *idx_name; - struct stat sb; + uintmax_t est_obj_cnt = object_entry_alloc; + uintmax_t total_count, duplicate_count; setup_ident(); git_config(git_default_config); @@ -1622,7 +1880,11 @@ int main(int argc, const char **argv) if (*a != '-' || !strcmp(a, "--")) break; else if (!strncmp(a, "--objects=", 10)) - est_obj_cnt = strtoul(a + 10, NULL, 0); + est_obj_cnt = strtoumax(a + 10, NULL, 0); + else if (!strncmp(a, "--max-objects-per-pack=", 23)) + max_objects = strtoumax(a + 23, 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)) @@ -1637,20 +1899,9 @@ int main(int argc, const char **argv) 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)); - init_pack_header(); alloc_objects(est_obj_cnt); strbuf_init(&command_buf); @@ -1659,6 +1910,7 @@ int main(int argc, const char **argv) 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) @@ -1669,40 +1921,46 @@ int main(int argc, const char **argv) 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(); + unkeep_all_packs(); dump_marks(); - fclose(branch_log); + 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)\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, "---------------------------------------------------------------------\n"); + fprintf(stderr, "Alloc'd objects: %10ju (%10ju overflow )\n", alloc_count, alloc_count - est_obj_cnt); + 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); - 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, " objects: %10ju KiB\n", (alloc_count*sizeof(struct object_entry))/1024); + fprintf(stderr, "---------------------------------------------------------------------\n"); + pack_report(); + fprintf(stderr, "---------------------------------------------------------------------\n"); fprintf(stderr, "\n"); return 0;