diff options
Diffstat (limited to 'fast-import.c')
| -rw-r--r-- | fast-import.c | 1147 |
1 files changed, 820 insertions, 327 deletions
diff --git a/fast-import.c b/fast-import.c index 99a19d89e8..2105310c54 100644 --- a/fast-import.c +++ b/fast-import.c @@ -1,4 +1,5 @@ /* +(See Documentation/git-fast-import.txt for maintained documentation.) Format of STDIN stream: stream ::= cmd*; @@ -8,22 +9,23 @@ Format of STDIN stream: | new_tag | reset_branch | checkpoint + | progress ; new_blob ::= 'blob' lf - mark? + mark? file_content; file_content ::= data; new_commit ::= 'commit' sp ref_str lf mark? - ('author' sp name '<' email '>' when lf)? - 'committer' sp name '<' email '>' when lf + ('author' (sp name)? sp '<' email '>' sp when lf)? + 'committer' (sp name)? sp '<' email '>' sp when lf commit_msg - ('from' sp (ref_str | hexsha1 | sha1exp_str | idnum) lf)? - ('merge' sp (ref_str | hexsha1 | sha1exp_str | idnum) lf)* + ('from' sp committish lf)? + ('merge' sp committish lf)* file_change* - lf; + lf?; commit_msg ::= data; file_change ::= file_clr @@ -39,50 +41,57 @@ Format of STDIN stream: file_obm ::= 'M' sp mode sp (hexsha1 | idnum) sp path_str lf; file_inm ::= 'M' sp mode sp 'inline' sp path_str lf data; + note_obm ::= 'N' sp (hexsha1 | idnum) sp committish lf; + note_inm ::= 'N' sp 'inline' sp committish lf + data; new_tag ::= 'tag' sp tag_str lf - 'from' sp (ref_str | hexsha1 | sha1exp_str | idnum) lf - 'tagger' sp name '<' email '>' when lf + 'from' sp committish lf + ('tagger' (sp name)? sp '<' email '>' sp when lf)? tag_msg; tag_msg ::= data; reset_branch ::= 'reset' sp ref_str lf - ('from' sp (ref_str | hexsha1 | sha1exp_str | idnum) lf)? - lf; + ('from' sp committish lf)? + lf?; checkpoint ::= 'checkpoint' lf - lf; + lf?; + + progress ::= 'progress' sp not_lf* 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 - # idnum can be updated in the future to a new object by issuing + # idnum can be updated in the future to a new object by issuing # a new mark directive with the old idnum. - # + # mark ::= 'mark' sp idnum lf; data ::= (delimited_data | exact_data) - lf; + 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; + delim lf; # note: declen indicates the length of binary_data in bytes. - # declen does not include the lf preceeding the binary data. + # declen does not include the lf preceding the binary data. # 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 - # is the signed byte value in octal. Note that the only + # is the signed byte value in octal. Note that the only # characters which must actually be escaped to protect the # stream formatting is: \, " and LF. Otherwise these values - # are UTF8. + # are UTF8. # + committish ::= (ref_str | hexsha1 | sha1exp_str | idnum); ref_str ::= ref; sha1exp_str ::= sha1exp; tag_str ::= tag; @@ -104,9 +113,9 @@ Format of STDIN stream: lf ::= # ASCII newline (LF) character; # note: a colon (':') must precede the numerical value assigned to - # an idnum. This is to distinguish it from a ref or tag name as + # an idnum. This is to distinguish it from a ref or tag name as # GIT does not permit ':' in ref or tag strings. - # + # idnum ::= ':' bigint; path ::= # GIT style file path, e.g. "a/b/c"; ref ::= # GIT ref name, e.g. "refs/heads/MOZ_GECKO_EXPERIMENT"; @@ -115,13 +124,24 @@ Format of STDIN stream: hexsha1 ::= # SHA1 in hexadecimal format; # note: name and email are UTF8 strings, however name must not - # contain '<' or lf and email must not contain any of the + # contain '<' or lf and email must not contain any of the # following: '<', '>', lf. - # + # name ::= # valid GIT author/committer name; email ::= # valid GIT author/committer email; ts ::= # time since the epoch in seconds, ascii base10 notation; tz ::= # GIT style timezone; + + # note: comments may appear anywhere in the input, except + # within a data command. Any form of the data command + # always escapes the related input from comment processing. + # + # In case it is not clear, the '#' that starts the comment + # must be the first character on that line (an lf + # preceded it). + # + comment ::= '#' not_lf* lf; + not_lf ::= # Any byte that is not ASCII newline (LF); */ #include "builtin.h" @@ -134,18 +154,21 @@ Format of STDIN stream: #include "pack.h" #include "refs.h" #include "csum-file.h" -#include "strbuf.h" #include "quote.h" +#include "exec_cmd.h" #define PACK_ID_BITS 16 #define MAX_PACK_ID ((1<<PACK_ID_BITS)-1) +#define DEPTH_BITS 13 +#define MAX_DEPTH ((1<<DEPTH_BITS)-1) struct object_entry { struct object_entry *next; uint32_t offset; - unsigned type : TYPE_BITS; - unsigned pack_id : PACK_ID_BITS; + uint32_t type : TYPE_BITS, + pack_id : PACK_ID_BITS, + depth : DEPTH_BITS; unsigned char sha1[20]; }; @@ -168,11 +191,10 @@ struct mark_set struct last_object { - void *data; - unsigned long len; + struct strbuf data; uint32_t offset; unsigned int depth; - unsigned no_free:1; + unsigned no_swap : 1; }; struct mem_pool @@ -180,7 +202,7 @@ struct mem_pool struct mem_pool *next_pool; char *next_free; char *end; - char space[FLEX_ARRAY]; /* more */ + uintmax_t space[FLEX_ARRAY]; /* more */ }; struct atom_str @@ -194,7 +216,7 @@ struct tree_content; struct tree_entry { struct tree_content *tree; - struct atom_str* name; + struct atom_str *name; struct tree_entry_ms { uint16_t mode; @@ -236,12 +258,6 @@ struct tag unsigned char sha1[20]; }; -struct dbuf -{ - void *buffer; - size_t capacity; -}; - struct hash_list { struct hash_list *next; @@ -254,10 +270,20 @@ typedef enum { WHENSPEC_NOW, } whenspec_type; +struct recent_command +{ + struct recent_command *prev; + struct recent_command *next; + char *buf; +}; + /* Configured limits on output */ static unsigned long max_depth = 10; static off_t max_packsize = (1LL << 32) - 1; +static uintmax_t big_file_threshold = 512 * 1024 * 1024; static int force_update; +static int pack_compression_level = Z_DEFAULT_COMPRESSION; +static int pack_compression_seen; /* Stats and misc. counters */ static uintmax_t alloc_count; @@ -292,18 +318,18 @@ 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; +static const char *mark_file; /* Our last blob */ -static struct last_object last_blob; +static struct last_object last_blob = { STRBUF_INIT, 0, 0, 0 }; /* Tree management */ 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; +static struct strbuf old_tree = STRBUF_INIT; +static struct strbuf new_tree = STRBUF_INIT; /* Branch data */ static unsigned long max_active_branches = 5; @@ -318,10 +344,151 @@ static struct tag *last_tag; /* Input stream parsing */ static whenspec_type whenspec = WHENSPEC_RAW; -static struct strbuf command_buf; +static struct strbuf command_buf = STRBUF_INIT; +static int unread_command_buf; +static struct recent_command cmd_hist = {&cmd_hist, &cmd_hist, NULL}; +static struct recent_command *cmd_tail = &cmd_hist; +static struct recent_command *rc_free; +static unsigned int cmd_save = 100; static uintmax_t next_mark; -static struct dbuf new_data; +static struct strbuf new_data = STRBUF_INIT; + +static void write_branch_report(FILE *rpt, struct branch *b) +{ + fprintf(rpt, "%s:\n", b->name); + + fprintf(rpt, " status :"); + if (b->active) + fputs(" active", rpt); + if (b->branch_tree.tree) + fputs(" loaded", rpt); + if (is_null_sha1(b->branch_tree.versions[1].sha1)) + fputs(" dirty", rpt); + fputc('\n', rpt); + + fprintf(rpt, " tip commit : %s\n", sha1_to_hex(b->sha1)); + fprintf(rpt, " old tree : %s\n", sha1_to_hex(b->branch_tree.versions[0].sha1)); + fprintf(rpt, " cur tree : %s\n", sha1_to_hex(b->branch_tree.versions[1].sha1)); + fprintf(rpt, " commit clock: %" PRIuMAX "\n", b->last_commit); + + fputs(" last pack : ", rpt); + if (b->pack_id < MAX_PACK_ID) + fprintf(rpt, "%u", b->pack_id); + fputc('\n', rpt); + + fputc('\n', rpt); +} + +static void dump_marks_helper(FILE *, uintmax_t, struct mark_set *); + +static void write_crash_report(const char *err) +{ + char *loc = git_path("fast_import_crash_%"PRIuMAX, (uintmax_t) getpid()); + FILE *rpt = fopen(loc, "w"); + struct branch *b; + unsigned long lu; + struct recent_command *rc; + + if (!rpt) { + error("can't write crash report %s: %s", loc, strerror(errno)); + return; + } + + fprintf(stderr, "fast-import: dumping crash report to %s\n", loc); + + fprintf(rpt, "fast-import crash report:\n"); + fprintf(rpt, " fast-import process: %"PRIuMAX"\n", (uintmax_t) getpid()); + fprintf(rpt, " parent process : %"PRIuMAX"\n", (uintmax_t) getppid()); + fprintf(rpt, " at %s\n", show_date(time(NULL), 0, DATE_LOCAL)); + fputc('\n', rpt); + + fputs("fatal: ", rpt); + fputs(err, rpt); + fputc('\n', rpt); + + fputc('\n', rpt); + fputs("Most Recent Commands Before Crash\n", rpt); + fputs("---------------------------------\n", rpt); + for (rc = cmd_hist.next; rc != &cmd_hist; rc = rc->next) { + if (rc->next == &cmd_hist) + fputs("* ", rpt); + else + fputs(" ", rpt); + fputs(rc->buf, rpt); + fputc('\n', rpt); + } + + fputc('\n', rpt); + fputs("Active Branch LRU\n", rpt); + fputs("-----------------\n", rpt); + fprintf(rpt, " active_branches = %lu cur, %lu max\n", + cur_active_branches, + max_active_branches); + fputc('\n', rpt); + fputs(" pos clock name\n", rpt); + fputs(" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n", rpt); + for (b = active_branches, lu = 0; b; b = b->active_next_branch) + fprintf(rpt, " %2lu) %6" PRIuMAX" %s\n", + ++lu, b->last_commit, b->name); + + fputc('\n', rpt); + fputs("Inactive Branches\n", rpt); + fputs("-----------------\n", rpt); + for (lu = 0; lu < branch_table_sz; lu++) { + for (b = branch_table[lu]; b; b = b->table_next_branch) + write_branch_report(rpt, b); + } + + if (first_tag) { + struct tag *tg; + fputc('\n', rpt); + fputs("Annotated Tags\n", rpt); + fputs("--------------\n", rpt); + for (tg = first_tag; tg; tg = tg->next_tag) { + fputs(sha1_to_hex(tg->sha1), rpt); + fputc(' ', rpt); + fputs(tg->name, rpt); + fputc('\n', rpt); + } + } + + fputc('\n', rpt); + fputs("Marks\n", rpt); + fputs("-----\n", rpt); + if (mark_file) + fprintf(rpt, " exported to %s\n", mark_file); + else + dump_marks_helper(rpt, 0, marks); + + fputc('\n', rpt); + fputs("-------------------\n", rpt); + fputs("END OF CRASH REPORT\n", rpt); + fclose(rpt); +} + +static void end_packfile(void); +static void unkeep_all_packs(void); +static void dump_marks(void); + +static NORETURN void die_nicely(const char *err, va_list params) +{ + static int zombie; + char message[2 * PATH_MAX]; + vsnprintf(message, sizeof(message), err, params); + fputs("fatal: ", stderr); + fputs(message, stderr); + fputc('\n', stderr); + + if (!zombie) { + zombie = 1; + write_crash_report(message); + end_packfile(); + unkeep_all_packs(); + dump_marks(); + } + exit(128); +} static void alloc_objects(unsigned int cnt) { @@ -394,6 +561,10 @@ static void *pool_alloc(size_t len) struct mem_pool *p; void *r; + /* round up to a 'uintmax_t' alignment */ + if (len & (sizeof(uintmax_t) - 1)) + len += sizeof(uintmax_t) - (len & (sizeof(uintmax_t) - 1)); + for (p = mem_pool; p; p = p->next_pool) if ((p->end - p->next_free >= len)) break; @@ -406,15 +577,12 @@ static void *pool_alloc(size_t len) total_allocd += sizeof(struct mem_pool) + mem_pool_alloc; p = xmalloc(sizeof(struct mem_pool) + mem_pool_alloc); p->next_pool = mem_pool; - p->next_free = p->space; + p->next_free = (char *) p->space; p->end = p->next_free + mem_pool_alloc; mem_pool = p; } 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; } @@ -434,17 +602,6 @@ static char *pool_strdup(const char *s) return r; } -static void size_dbuf(struct dbuf *b, size_t maxlen) -{ - if (b->buffer) { - if (b->capacity >= maxlen) - return; - free(b->buffer); - } - b->capacity = ((maxlen / 1024) + 1) * 1024; - b->buffer = xmalloc(b->capacity); -} - static void insert_mark(uintmax_t idnum, struct object_entry *oe) { struct mark_set *s = marks; @@ -520,12 +677,17 @@ static struct branch *lookup_branch(const char *name) static struct branch *new_branch(const char *name) { unsigned int hc = hc_str(name, strlen(name)) % branch_table_sz; - struct branch* b = lookup_branch(name); + struct branch *b = lookup_branch(name); if (b) die("Invalid attempt to create duplicate branch: %s", name); - if (check_ref_format(name)) + switch (check_ref_format(name)) { + case 0: break; /* its valid */ + case CHECK_REF_FORMAT_ONELEVEL: + break; /* valid, but too few '/', allow anyway */ + default: die("Branch name doesn't conform to GIT standards: %s", name); + } b = pool_calloc(1, sizeof(struct branch)); b->name = pool_strdup(name); @@ -661,11 +823,8 @@ static void start_packfile(void) struct pack_header hdr; int pack_fd; - snprintf(tmpfile, sizeof(tmpfile), - "%s/tmp_pack_XXXXXX", get_object_directory()); - pack_fd = mkstemp(tmpfile); - if (pack_fd < 0) - die("Can't create %s: %s", tmpfile, strerror(errno)); + pack_fd = odb_mkstemp(tmpfile, sizeof(tmpfile), + "pack/tmp_pack_XXXXXX"); p = xcalloc(1, sizeof(*p) + strlen(tmpfile) + 2); strcpy(p->pack_name, tmpfile); p->pack_fd = pack_fd; @@ -693,7 +852,7 @@ static int oecmp (const void *a_, const void *b_) static char *create_index(void) { static char tmpfile[PATH_MAX]; - SHA_CTX ctx; + git_SHA_CTX ctx; struct sha1file *f; struct object_entry **idx, **c, **last, *e; struct object_entry_pool *o; @@ -715,7 +874,7 @@ static char *create_index(void) /* Generate the fan-out array. */ c = idx; for (i = 0; i < 256; i++) { - struct object_entry **next = c;; + struct object_entry **next = c; while (next < last) { if ((*next)->sha1[0] != i) break; @@ -725,24 +884,21 @@ static char *create_index(void) c = next; } - snprintf(tmpfile, sizeof(tmpfile), - "%s/tmp_idx_XXXXXX", get_object_directory()); - idx_fd = mkstemp(tmpfile); - if (idx_fd < 0) - die("Can't create %s: %s", tmpfile, strerror(errno)); + idx_fd = odb_mkstemp(tmpfile, sizeof(tmpfile), + "pack/tmp_idx_XXXXXX"); f = sha1fd(idx_fd, tmpfile); sha1write(f, array, 256 * sizeof(int)); - SHA1_Init(&ctx); + git_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); + git_SHA1_Update(&ctx, (*c)->sha1, 20); } sha1write(f, pack_data->sha1, sizeof(pack_data->sha1)); - sha1close(f, NULL, 1); + sha1close(f, NULL, CSUM_FSYNC); free(idx); - SHA1_Final(pack_data->sha1, &ctx); + git_SHA1_Final(pack_data->sha1, &ctx); return tmpfile; } @@ -752,16 +908,12 @@ static char *keep_pack(char *curr_index_name) static const 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); + keep_fd = odb_pack_keep(name, sizeof(name), pack_data->sha1); if (keep_fd < 0) - die("cannot create keep file"); - write(keep_fd, keep_msg, strlen(keep_msg)); - close(keep_fd); + die_errno("cannot create keep file"); + write_or_die(keep_fd, keep_msg, strlen(keep_msg)); + if (close(keep_fd)) + die_errno("failed to write keep file"); snprintf(name, sizeof(name), "%s/pack/pack-%s.pack", get_object_directory(), sha1_to_hex(pack_data->sha1)); @@ -784,7 +936,7 @@ static void unkeep_all_packs(void) 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); + unlink_or_warn(name); } } @@ -792,22 +944,24 @@ static void end_packfile(void) { struct packed_git *old_p = pack_data, *new_p; + clear_delta_base_cache(); if (object_count) { char *idx_name; int i; struct branch *b; struct tag *t; + close_pack_windows(pack_data); fixup_pack_header_footer(pack_data->pack_fd, pack_data->sha1, - pack_data->pack_name, object_count); + pack_data->pack_name, object_count, + NULL, 0); close(pack_data->pack_fd); idx_name = keep_pack(create_index()); - /* Register the packfile with core git's machinary. */ + /* Register the packfile with core git's machinery. */ 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); @@ -830,14 +984,14 @@ static void end_packfile(void) pack_id++; } - else - unlink(old_p->pack_name); + else { + close(old_p->pack_fd); + unlink_or_warn(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; + strbuf_release(&last_blob.data); last_blob.offset = 0; last_blob.depth = 0; } @@ -850,7 +1004,7 @@ static void cycle_packfile(void) static size_t encode_header( enum object_type type, - size_t size, + uintmax_t size, unsigned char *hdr) { int n = 1; @@ -873,8 +1027,7 @@ static size_t encode_header( static int store_object( enum object_type type, - void *dat, - size_t datlen, + struct strbuf *dat, struct last_object *last, unsigned char *sha1out, uintmax_t mark) @@ -884,15 +1037,15 @@ static int store_object( unsigned char hdr[96]; unsigned char sha1[20]; unsigned long hdrlen, deltalen; - SHA_CTX c; + git_SHA_CTX c; z_stream s; - hdrlen = sprintf((char*)hdr,"%s %lu", typename(type), - (unsigned long)datlen) + 1; - SHA1_Init(&c); - SHA1_Update(&c, hdr, hdrlen); - SHA1_Update(&c, dat, datlen); - SHA1_Final(sha1, &c); + hdrlen = sprintf((char *)hdr,"%s %lu", typename(type), + (unsigned long)dat->len) + 1; + git_SHA1_Init(&c); + git_SHA1_Update(&c, hdr, hdrlen); + git_SHA1_Update(&c, dat->buf, dat->len); + git_SHA1_Final(sha1, &c); if (sha1out) hashcpy(sha1out, sha1); @@ -910,11 +1063,11 @@ static int store_object( return 1; } - if (last && last->data && last->depth < max_depth) { - delta = diff_delta(last->data, last->len, - dat, datlen, + if (last && last->data.buf && last->depth < max_depth) { + delta = diff_delta(last->data.buf, last->data.len, + dat->buf, dat->len, &deltalen, 0); - if (delta && deltalen >= datlen) { + if (delta && deltalen >= dat->len) { free(delta); delta = NULL; } @@ -922,13 +1075,13 @@ static int store_object( delta = NULL; memset(&s, 0, sizeof(s)); - deflateInit(&s, zlib_compression_level); + deflateInit(&s, pack_compression_level); if (delta) { s.next_in = delta; s.avail_in = deltalen; } else { - s.next_in = dat; - s.avail_in = datlen; + s.next_in = (void *)dat->buf; + s.avail_in = dat->len; } s.avail_out = deflateBound(&s, s.avail_in); s.next_out = out = xmalloc(s.avail_out); @@ -950,9 +1103,9 @@ static int store_object( delta = NULL; memset(&s, 0, sizeof(s)); - deflateInit(&s, zlib_compression_level); - s.next_in = dat; - s.avail_in = datlen; + deflateInit(&s, pack_compression_level); + s.next_in = (void *)dat->buf; + s.avail_in = dat->len; s.avail_out = deflateBound(&s, s.avail_in); s.next_out = out = xrealloc(out, s.avail_out); while (deflate(&s, Z_FINISH) == Z_OK) @@ -972,7 +1125,7 @@ static int store_object( unsigned pos = sizeof(hdr) - 1; delta_count_by_type[type]++; - last->depth++; + e->depth = last->depth + 1; hdrlen = encode_header(OBJ_OFS_DELTA, deltalen, hdr); write_or_die(pack_data->pack_fd, hdr, hdrlen); @@ -984,9 +1137,8 @@ static int store_object( 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); + e->depth = 0; + hdrlen = encode_header(type, dat->len, hdr); write_or_die(pack_data->pack_fd, hdr, hdrlen); pack_size += hdrlen; } @@ -997,23 +1149,172 @@ static int store_object( free(out); free(delta); if (last) { - if (!last->no_free) - free(last->data); - last->data = dat; + if (last->no_swap) { + last->data = *dat; + } else { + strbuf_swap(&last->data, dat); + } last->offset = e->offset; - last->len = datlen; + last->depth = e->depth; } return 0; } +static void truncate_pack(off_t to) +{ + if (ftruncate(pack_data->pack_fd, to) + || lseek(pack_data->pack_fd, to, SEEK_SET) != to) + die_errno("cannot truncate pack to skip duplicate"); + pack_size = to; +} + +static void stream_blob(uintmax_t len, unsigned char *sha1out, uintmax_t mark) +{ + size_t in_sz = 64 * 1024, out_sz = 64 * 1024; + unsigned char *in_buf = xmalloc(in_sz); + unsigned char *out_buf = xmalloc(out_sz); + struct object_entry *e; + unsigned char sha1[20]; + unsigned long hdrlen; + off_t offset; + git_SHA_CTX c; + z_stream s; + int status = Z_OK; + + /* Determine if we should auto-checkpoint. */ + if ((pack_size + 60 + len) > max_packsize + || (pack_size + 60 + len) < pack_size) + cycle_packfile(); + + offset = pack_size; + + hdrlen = snprintf((char *)out_buf, out_sz, "blob %" PRIuMAX, len) + 1; + if (out_sz <= hdrlen) + die("impossibly large object header"); + + git_SHA1_Init(&c); + git_SHA1_Update(&c, out_buf, hdrlen); + + memset(&s, 0, sizeof(s)); + deflateInit(&s, pack_compression_level); + + hdrlen = encode_header(OBJ_BLOB, len, out_buf); + if (out_sz <= hdrlen) + die("impossibly large object header"); + + s.next_out = out_buf + hdrlen; + s.avail_out = out_sz - hdrlen; + + while (status != Z_STREAM_END) { + if (0 < len && !s.avail_in) { + size_t cnt = in_sz < len ? in_sz : (size_t)len; + size_t n = fread(in_buf, 1, cnt, stdin); + if (!n && feof(stdin)) + die("EOF in data (%" PRIuMAX " bytes remaining)", len); + + git_SHA1_Update(&c, in_buf, n); + s.next_in = in_buf; + s.avail_in = n; + len -= n; + } + + status = deflate(&s, len ? 0 : Z_FINISH); + + if (!s.avail_out || status == Z_STREAM_END) { + size_t n = s.next_out - out_buf; + write_or_die(pack_data->pack_fd, out_buf, n); + pack_size += n; + s.next_out = out_buf; + s.avail_out = out_sz; + } + + switch (status) { + case Z_OK: + case Z_BUF_ERROR: + case Z_STREAM_END: + continue; + default: + die("unexpected deflate failure: %d", status); + } + } + deflateEnd(&s); + git_SHA1_Final(sha1, &c); + + if (sha1out) + hashcpy(sha1out, sha1); + + e = insert_object(sha1); + + if (mark) + insert_mark(mark, e); + + if (e->offset) { + duplicate_count_by_type[OBJ_BLOB]++; + truncate_pack(offset); + + } else if (find_sha1_pack(sha1, packed_git)) { + e->type = OBJ_BLOB; + e->pack_id = MAX_PACK_ID; + e->offset = 1; /* just not zero! */ + duplicate_count_by_type[OBJ_BLOB]++; + truncate_pack(offset); + + } else { + e->depth = 0; + e->type = OBJ_BLOB; + e->pack_id = pack_id; + e->offset = offset; + object_count++; + object_count_by_type[OBJ_BLOB]++; + } + + free(in_buf); + free(out_buf); +} + +/* All calls must be guarded by find_object() or find_mark() to + * ensure the 'struct object_entry' passed was written by this + * process instance. We unpack the entry by the offset, avoiding + * the need for the corresponding .idx file. This unpacking rule + * works because we only use OBJ_REF_DELTA within the packfiles + * created by fast-import. + * + * oe must not be NULL. Such an oe usually comes from giving + * an unknown SHA-1 to find_object() or an undefined mark to + * find_mark(). Callers must test for this condition and use + * the standard read_sha1_file() when it happens. + * + * oe->pack_id must not be MAX_PACK_ID. Such an oe is usually from + * find_mark(), where the mark was reloaded from an existing marks + * file and is referencing an object that this fast-import process + * instance did not write out to a packfile. Callers must test for + * this condition and use read_sha1_file() instead. + */ static void *gfi_unpack_entry( struct object_entry *oe, unsigned long *sizep) { enum object_type type; struct packed_git *p = all_packs[oe->pack_id]; - if (p == pack_data) + if (p == pack_data && p->pack_size < (pack_size + 20)) { + /* The object is stored in the packfile we are writing to + * and we have modified it since the last time we scanned + * back to read a previously written object. If an old + * window covered [p->pack_size, p->pack_size + 20) its + * data is stale and is not valid. Closing all windows + * and updating the packfile length ensures we can read + * the newly written data. + */ + close_pack_windows(p); + + /* We have to offer 20 bytes additional on the end of + * the packfile as the core unpacker code assumes the + * footer is present at the file end and must promise + * at least 20 bytes within any window it maps. But + * we don't actually create the footer here. + */ p->pack_size = pack_size + 20; + } return unpack_entry(p, oe->offset, &type, sizep); } @@ -1033,7 +1334,7 @@ static const char *get_mode(const char *str, uint16_t *modep) static void load_tree(struct tree_entry *root) { - unsigned char* sha1 = root->versions[1].sha1; + unsigned char *sha1 = root->versions[1].sha1; struct object_entry *myoe; struct tree_content *t; unsigned long size; @@ -1048,8 +1349,10 @@ static void load_tree(struct tree_entry *root) if (myoe && myoe->pack_id != MAX_PACK_ID) { if (myoe->type != OBJ_TREE) die("Not a tree: %s", sha1_to_hex(sha1)); - t->delta_depth = 0; + t->delta_depth = myoe->depth; buf = gfi_unpack_entry(myoe, &size); + if (!buf) + die("Can't load tree %s", sha1_to_hex(sha1)); } else { enum object_type type; buf = read_sha1_file(sha1, &type, &size); @@ -1072,8 +1375,8 @@ static void load_tree(struct tree_entry *root) e->versions[0].mode = e->versions[1].mode; e->name = to_atom(c, strlen(c)); c += e->name->str_len + 1; - hashcpy(e->versions[0].sha1, (unsigned char*)c); - hashcpy(e->versions[1].sha1, (unsigned char*)c); + hashcpy(e->versions[0].sha1, (unsigned char *)c); + hashcpy(e->versions[1].sha1, (unsigned char *)c); c += 20; } free(buf); @@ -1097,14 +1400,10 @@ static int tecmp1 (const void *_a, const void *_b) 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) +static void mktree(struct tree_content *t, int v, struct strbuf *b) { size_t maxlen = 0; unsigned int i; - char *c; if (!v) qsort(t->entries,t->entry_count,sizeof(t->entries[0]),tecmp0); @@ -1116,28 +1415,23 @@ static void mktree(struct tree_content *t, maxlen += t->entries[i]->name->str_len + 34; } - size_dbuf(b, maxlen); - c = b->buffer; + strbuf_reset(b); + strbuf_grow(b, maxlen); for (i = 0; i < t->entry_count; i++) { struct tree_entry *e = t->entries[i]; if (!e->versions[v].mode) continue; - c += sprintf(c, "%o", (unsigned int)e->versions[v].mode); - *c++ = ' '; - strcpy(c, e->name->str_dat); - c += e->name->str_len + 1; - hashcpy((unsigned char*)c, e->versions[v].sha1); - c += 20; + strbuf_addf(b, "%o %s%c", (unsigned int)e->versions[v].mode, + e->name->str_dat, '\0'); + strbuf_add(b, e->versions[v].sha1, 20); } - *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 last_object lo = { STRBUF_INIT, 0, 0, /* no_swap */ 1 }; struct object_entry *le; if (!is_null_sha1(root->versions[1].sha1)) @@ -1149,23 +1443,15 @@ static void store_tree(struct tree_entry *root) } 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; - lo.no_free = 0; - } else { - mktree(t, 0, &lo.len, &old_tree); - lo.data = old_tree.buffer; + if (S_ISDIR(root->versions[0].mode) && le && le->pack_id == pack_id) { + mktree(t, 0, &old_tree); + lo.data = old_tree; 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); + mktree(t, 1, &new_tree); + store_object(OBJ_TREE, &new_tree, &lo, root->versions[1].sha1, 0); t->delta_depth = lo.depth; for (i = 0, j = 0, del = 0; i < t->entry_count; i++) { @@ -1347,6 +1633,8 @@ static int update_branch(struct branch *b) struct ref_lock *lock; unsigned char old_sha1[20]; + if (is_null_sha1(b->sha1)) + return 0; if (read_ref(b->name, old_sha1)) hashclr(old_sha1); lock = lock_any_ref_for_update(b->name, old_sha1, 0); @@ -1439,25 +1727,87 @@ static void dump_marks(void) f = fdopen(mark_fd, "w"); if (!f) { + int saved_errno = errno; rollback_lock_file(&mark_lock); failure |= error("Unable to write marks file %s: %s", - mark_file, strerror(errno)); + mark_file, strerror(saved_errno)); return; } + /* + * Since the lock file was fdopen()'ed, it should not be close()'ed. + * Assign -1 to the lock file descriptor so that commit_lock_file() + * won't try to close() it. + */ + mark_lock.fd = -1; + dump_marks_helper(f, 0, marks); - fclose(f); - if (commit_lock_file(&mark_lock)) + if (ferror(f) || fclose(f)) { + int saved_errno = errno; + rollback_lock_file(&mark_lock); failure |= error("Unable to write marks file %s: %s", - mark_file, strerror(errno)); + mark_file, strerror(saved_errno)); + return; + } + + if (commit_lock_file(&mark_lock)) { + int saved_errno = errno; + rollback_lock_file(&mark_lock); + failure |= error("Unable to commit marks file %s: %s", + mark_file, strerror(saved_errno)); + return; + } } -static void read_next_command(void) +static int read_next_command(void) { - read_line(&command_buf, stdin, '\n'); + static int stdin_eof = 0; + + if (stdin_eof) { + unread_command_buf = 0; + return EOF; + } + + do { + if (unread_command_buf) { + unread_command_buf = 0; + } else { + struct recent_command *rc; + + strbuf_detach(&command_buf, NULL); + stdin_eof = strbuf_getline(&command_buf, stdin, '\n'); + if (stdin_eof) + return EOF; + + rc = rc_free; + if (rc) + rc_free = rc->next; + else { + rc = cmd_hist.next; + cmd_hist.next = rc->next; + cmd_hist.next->prev = &cmd_hist; + free(rc->buf); + } + + rc->buf = command_buf.buf; + rc->prev = cmd_tail; + rc->next = cmd_hist.prev; + rc->prev->next = rc; + cmd_tail = rc; + } + } while (command_buf.buf[0] == '#'); + + return 0; +} + +static void skip_optional_lf(void) +{ + int term_char = fgetc(stdin); + if (term_char != '\n' && term_char != EOF) + ungetc(term_char, stdin); } -static void cmd_mark(void) +static void parse_mark(void) { if (!prefixcmp(command_buf.buf, "mark :")) { next_mark = strtoumax(command_buf.buf + 6, NULL, 10); @@ -1467,46 +1817,42 @@ static void cmd_mark(void) next_mark = 0; } -static void *cmd_data (size_t *size) +static int parse_data(struct strbuf *sb, uintmax_t limit, uintmax_t *len_res) { - size_t length; - char *buffer; + strbuf_reset(sb); if (prefixcmp(command_buf.buf, "data ")) die("Expected 'data n' command, found: %s", command_buf.buf); if (!prefixcmp(command_buf.buf + 5, "<<")) { char *term = xstrdup(command_buf.buf + 5 + 2); - size_t sz = 8192, term_len = command_buf.len - 5 - 2; - length = 0; - buffer = xmalloc(sz); + size_t term_len = command_buf.len - 5 - 2; + + strbuf_detach(&command_buf, NULL); for (;;) { - read_next_command(); - if (command_buf.eof) + if (strbuf_getline(&command_buf, stdin, '\n') == 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'; + strbuf_addbuf(sb, &command_buf); + strbuf_addch(sb, '\n'); } free(term); } else { - size_t n = 0; - length = strtoul(command_buf.buf + 5, NULL, 10); - buffer = xmalloc(length); + uintmax_t len = strtoumax(command_buf.buf + 5, NULL, 10); + size_t n = 0, length = (size_t)len; + + if (limit && limit < len) { + *len_res = len; + return 0; + } + if (length < len) + die("data is too large to use in this context"); + while (n < length) { - size_t s = fread(buffer + n, 1, length - n, stdin); + size_t s = strbuf_fread(sb, length - n, stdin); if (!s && feof(stdin)) die("EOF in data (%lu bytes remaining)", (unsigned long)(length - n)); @@ -1514,29 +1860,30 @@ static void *cmd_data (size_t *size) } } - if (fgetc(stdin) != '\n') - die("An lf did not trail the binary data as expected."); - - *size = length; - return buffer; + skip_optional_lf(); + return 1; } static int validate_raw_date(const char *src, char *result, int maxlen) { const char *orig_src = src; - char *endp, sign; + char *endp; + unsigned long num; + + errno = 0; - strtoul(src, &endp, 10); - if (endp == src || *endp != ' ') + num = strtoul(src, &endp, 10); + /* NEEDSWORK: perhaps check for reasonable values? */ + if (errno || endp == src || *endp != ' ') return -1; src = endp + 1; if (*src != '-' && *src != '+') return -1; - sign = *src; - strtoul(src + 1, &endp, 10); - if (endp == src || *endp || (endp - orig_src) >= maxlen) + num = strtoul(src + 1, &endp, 10); + if (errno || endp == src + 1 || *endp || (endp - orig_src) >= maxlen || + 1400 < num) return -1; strcpy(result, orig_src); @@ -1579,17 +1926,32 @@ static char *parse_ident(const char *buf) return ident; } -static void cmd_new_blob(void) +static void parse_and_store_blob( + struct last_object *last, + unsigned char *sha1out, + uintmax_t mark) { - size_t l; - void *d; + static struct strbuf buf = STRBUF_INIT; + uintmax_t len; - read_next_command(); - cmd_mark(); - d = cmd_data(&l); + if (parse_data(&buf, big_file_threshold, &len)) + store_object(OBJ_BLOB, &buf, last, sha1out, mark); + else { + if (last) { + strbuf_release(&last->data); + last->offset = 0; + last->depth = 0; + } + stream_blob(len, sha1out, mark); + skip_optional_lf(); + } +} - if (store_object(OBJ_BLOB, d, l, &last_blob, NULL, next_mark)) - free(d); +static void parse_new_blob(void) +{ + read_next_command(); + parse_mark(); + parse_and_store_blob(&last_blob, NULL, next_mark); } static void unload_one_branch(void) @@ -1639,7 +2001,7 @@ static void load_branch(struct branch *b) static void file_change_m(struct branch *b) { const char *p = command_buf.buf + 2; - char *p_uq; + static struct strbuf uq = STRBUF_INIT; const char *endp; struct object_entry *oe = oe; unsigned char sha1[20]; @@ -1649,11 +2011,13 @@ static void file_change_m(struct branch *b) if (!p) die("Corrupt mode: %s", command_buf.buf); switch (mode) { + case 0644: + case 0755: + mode |= S_IFREG; case S_IFREG | 0644: case S_IFREG | 0755: case S_IFLNK: - case 0644: - case 0755: + case S_IFGITLINK: /* ok */ break; default: @@ -1677,26 +2041,37 @@ static void file_change_m(struct branch *b) if (*p++ != ' ') die("Missing space after SHA1: %s", command_buf.buf); - p_uq = unquote_c_style(p, &endp); - if (p_uq) { + strbuf_reset(&uq); + if (!unquote_c_style(&uq, p, &endp)) { if (*endp) die("Garbage after path in: %s", command_buf.buf); - p = p_uq; + p = uq.buf; } - if (inline_data) { - size_t l; - void *d; - if (!p_uq) - p = p_uq = xstrdup(p); + if (S_ISGITLINK(mode)) { + if (inline_data) + die("Git links cannot be specified 'inline': %s", + command_buf.buf); + else if (oe) { + if (oe->type != OBJ_COMMIT) + die("Not a commit (actually a %s): %s", + typename(oe->type), command_buf.buf); + } + /* + * Accept the sha1 without checking; it expected to be in + * another repository. + */ + } else if (inline_data) { + if (p != uq.buf) { + strbuf_addstr(&uq, p); + p = uq.buf; + } read_next_command(); - d = cmd_data(&l); - if (store_object(OBJ_BLOB, d, l, &last_blob, sha1, 0)) - free(d); + parse_and_store_blob(&last_blob, sha1, 0); } else if (oe) { if (oe->type != OBJ_BLOB) die("Not a blob (actually a %s): %s", - command_buf.buf, typename(oe->type)); + typename(oe->type), command_buf.buf); } else { enum object_type type = sha1_object_info(sha1, NULL); if (type < 0) @@ -1706,59 +2081,55 @@ static void file_change_m(struct branch *b) typename(type), command_buf.buf); } - tree_content_set(&b->branch_tree, p, sha1, S_IFREG | mode, NULL); - free(p_uq); + tree_content_set(&b->branch_tree, p, sha1, mode, NULL); } static void file_change_d(struct branch *b) { const char *p = command_buf.buf + 2; - char *p_uq; + static struct strbuf uq = STRBUF_INIT; const char *endp; - p_uq = unquote_c_style(p, &endp); - if (p_uq) { + strbuf_reset(&uq); + if (!unquote_c_style(&uq, p, &endp)) { if (*endp) die("Garbage after path in: %s", command_buf.buf); - p = p_uq; + p = uq.buf; } tree_content_remove(&b->branch_tree, p, NULL); - free(p_uq); } static void file_change_cr(struct branch *b, int rename) { const char *s, *d; - char *s_uq, *d_uq; + static struct strbuf s_uq = STRBUF_INIT; + static struct strbuf d_uq = STRBUF_INIT; const char *endp; struct tree_entry leaf; s = command_buf.buf + 2; - s_uq = unquote_c_style(s, &endp); - if (s_uq) { + strbuf_reset(&s_uq); + if (!unquote_c_style(&s_uq, s, &endp)) { if (*endp != ' ') die("Missing space after source: %s", command_buf.buf); - } - else { + } else { endp = strchr(s, ' '); if (!endp) die("Missing space after source: %s", command_buf.buf); - s_uq = xmalloc(endp - s + 1); - memcpy(s_uq, s, endp - s); - s_uq[endp - s] = 0; + strbuf_add(&s_uq, s, endp - s); } - s = s_uq; + s = s_uq.buf; endp++; if (!*endp) die("Missing dest: %s", command_buf.buf); d = endp; - d_uq = unquote_c_style(d, &endp); - if (d_uq) { + strbuf_reset(&d_uq); + if (!unquote_c_style(&d_uq, d, &endp)) { if (*endp) die("Garbage after dest in: %s", command_buf.buf); - d = d_uq; + d = d_uq.buf; } memset(&leaf, 0, sizeof(leaf)); @@ -1772,9 +2143,77 @@ static void file_change_cr(struct branch *b, int rename) leaf.versions[1].sha1, leaf.versions[1].mode, leaf.tree); +} + +static void note_change_n(struct branch *b) +{ + const char *p = command_buf.buf + 2; + static struct strbuf uq = STRBUF_INIT; + struct object_entry *oe = oe; + struct branch *s; + unsigned char sha1[20], commit_sha1[20]; + uint16_t inline_data = 0; + + /* <dataref> or 'inline' */ + if (*p == ':') { + char *x; + oe = find_mark(strtoumax(p + 1, &x, 10)); + hashcpy(sha1, oe->sha1); + p = x; + } else if (!prefixcmp(p, "inline")) { + inline_data = 1; + p += 6; + } 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); + + /* <committish> */ + s = lookup_branch(p); + if (s) { + hashcpy(commit_sha1, s->sha1); + } else if (*p == ':') { + uintmax_t commit_mark = strtoumax(p + 1, NULL, 10); + struct object_entry *commit_oe = find_mark(commit_mark); + if (commit_oe->type != OBJ_COMMIT) + die("Mark :%" PRIuMAX " not a commit", commit_mark); + hashcpy(commit_sha1, commit_oe->sha1); + } else if (!get_sha1(p, commit_sha1)) { + unsigned long size; + char *buf = read_object_with_reference(commit_sha1, + commit_type, &size, commit_sha1); + if (!buf || size < 46) + die("Not a valid commit: %s", p); + free(buf); + } else + die("Invalid ref name or SHA1 expression: %s", p); + + if (inline_data) { + if (p != uq.buf) { + strbuf_addstr(&uq, p); + p = uq.buf; + } + read_next_command(); + parse_and_store_blob(&last_blob, sha1, 0); + } else if (oe) { + if (oe->type != OBJ_BLOB) + die("Not a blob (actually a %s): %s", + typename(oe->type), command_buf.buf); + } else { + enum object_type type = sha1_object_info(sha1, NULL); + if (type < 0) + die("Blob not found: %s", command_buf.buf); + if (type != OBJ_BLOB) + die("Not a blob (actually a %s): %s", + typename(type), command_buf.buf); + } - free(s_uq); - free(d_uq); + tree_content_set(&b->branch_tree, sha1_to_hex(commit_sha1), sha1, + S_IFREG | 0644, NULL); } static void file_change_deleteall(struct branch *b) @@ -1785,7 +2224,7 @@ static void file_change_deleteall(struct branch *b) load_tree(&b->branch_tree); } -static void cmd_from_commit(struct branch *b, char *buf, unsigned long size) +static void parse_from_commit(struct branch *b, char *buf, unsigned long size) { if (!buf || size < 46) die("Not a valid commit: %s", sha1_to_hex(b->sha1)); @@ -1796,7 +2235,7 @@ static void cmd_from_commit(struct branch *b, char *buf, unsigned long size) b->branch_tree.versions[1].sha1); } -static void cmd_from_existing(struct branch *b) +static void parse_from_existing(struct branch *b) { if (is_null_sha1(b->sha1)) { hashclr(b->branch_tree.versions[0].sha1); @@ -1807,18 +2246,18 @@ static void cmd_from_existing(struct branch *b) buf = read_object_with_reference(b->sha1, commit_type, &size, b->sha1); - cmd_from_commit(b, buf, size); + parse_from_commit(b, buf, size); free(buf); } } -static void cmd_from(struct branch *b) +static int parse_from(struct branch *b) { const char *from; struct branch *s; if (prefixcmp(command_buf.buf, "from ")) - return; + return 0; if (b->branch_tree.tree) { release_tree_content_recursive(b->branch_tree.tree); @@ -1843,19 +2282,20 @@ static void cmd_from(struct branch *b) if (oe->pack_id != MAX_PACK_ID) { unsigned long size; char *buf = gfi_unpack_entry(oe, &size); - cmd_from_commit(b, buf, size); + parse_from_commit(b, buf, size); free(buf); } else - cmd_from_existing(b); + parse_from_existing(b); } else if (!get_sha1(from, b->sha1)) - cmd_from_existing(b); + parse_from_existing(b); else die("Invalid ref name or SHA1 expression: %s", from); read_next_command(); + return 1; } -static struct hash_list *cmd_merge(unsigned int *count) +static struct hash_list *parse_merge(unsigned int *count) { struct hash_list *list = NULL, *n, *e = e; const char *from; @@ -1896,11 +2336,10 @@ static struct hash_list *cmd_merge(unsigned int *count) return list; } -static void cmd_new_commit(void) +static void parse_new_commit(void) { + static struct strbuf msg = STRBUF_INIT; struct branch *b; - void *msg; - size_t msglen; char *sp; char *author = NULL; char *committer = NULL; @@ -1914,7 +2353,7 @@ static void cmd_new_commit(void) b = new_branch(sp); read_next_command(); - cmd_mark(); + parse_mark(); if (!prefixcmp(command_buf.buf, "author ")) { author = parse_ident(command_buf.buf + 7); read_next_command(); @@ -1925,10 +2364,10 @@ static void cmd_new_commit(void) } if (!committer) die("Expected committer but didn't get one"); - msg = cmd_data(&msglen); + parse_data(&msg, 0, NULL); read_next_command(); - cmd_from(b); - merge_list = cmd_merge(&merge_count); + parse_from(b); + merge_list = parse_merge(&merge_count); /* ensure the branch is active/loaded */ if (!b->branch_tree.tree || !max_active_branches) { @@ -1937,10 +2376,8 @@ static void cmd_new_commit(void) } /* file_change* */ - for (;;) { - if (1 == command_buf.len) - break; - else if (!prefixcmp(command_buf.buf, "M ")) + while (command_buf.len > 0) { + if (!prefixcmp(command_buf.buf, "M ")) file_change_m(b); else if (!prefixcmp(command_buf.buf, "D ")) file_change_d(b); @@ -1948,60 +2385,59 @@ static void cmd_new_commit(void) file_change_cr(b, 1); else if (!prefixcmp(command_buf.buf, "C ")) file_change_cr(b, 0); + else if (!prefixcmp(command_buf.buf, "N ")) + note_change_n(b); else if (!strcmp("deleteall", command_buf.buf)) file_change_deleteall(b); - else - die("Unsupported file_change: %s", command_buf.buf); - read_next_command(); + else { + unread_command_buf = 1; + break; + } + if (read_next_command() == EOF) + break; } /* build the tree and the commit */ store_tree(&b->branch_tree); hashcpy(b->branch_tree.versions[0].sha1, b->branch_tree.versions[1].sha1); - size_dbuf(&new_data, 114 + msglen - + merge_count * 49 - + (author - ? strlen(author) + strlen(committer) - : 2 * strlen(committer))); - sp = new_data.buffer; - sp += sprintf(sp, "tree %s\n", + + strbuf_reset(&new_data); + strbuf_addf(&new_data, "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)); + strbuf_addf(&new_data, "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)); + strbuf_addf(&new_data, "parent %s\n", sha1_to_hex(merge_list->sha1)); free(merge_list); merge_list = next; } - sp += sprintf(sp, "author %s\n", author ? author : committer); - sp += sprintf(sp, "committer %s\n", committer); - *sp++ = '\n'; - memcpy(sp, msg, msglen); - sp += msglen; + strbuf_addf(&new_data, + "author %s\n" + "committer %s\n" + "\n", + author ? author : committer, committer); + strbuf_addbuf(&new_data, &msg); free(author); free(committer); - free(msg); - if (!store_object(OBJ_COMMIT, - new_data.buffer, sp - (char*)new_data.buffer, - NULL, b->sha1, next_mark)) + if (!store_object(OBJ_COMMIT, &new_data, NULL, b->sha1, next_mark)) b->pack_id = pack_id; b->last_commit = object_count_by_type[OBJ_COMMIT]; } -static void cmd_new_tag(void) +static void parse_new_tag(void) { + static struct strbuf msg = STRBUF_INIT; char *sp; const char *from; char *tagger; struct branch *s; - void *msg; - size_t msglen; struct tag *t; uintmax_t from_mark = 0; unsigned char sha1[20]; + enum object_type type; /* Obtain the new tag name from the rest of our command */ sp = strchr(command_buf.buf, ' ') + 1; @@ -2022,19 +2458,18 @@ static void cmd_new_tag(void) s = lookup_branch(from); if (s) { hashcpy(sha1, s->sha1); + type = OBJ_COMMIT; } else if (*from == ':') { struct object_entry *oe; from_mark = strtoumax(from + 1, NULL, 10); oe = find_mark(from_mark); - if (oe->type != OBJ_COMMIT) - die("Mark :%" PRIuMAX " not a commit", from_mark); + type = oe->type; hashcpy(sha1, oe->sha1); } else if (!get_sha1(from, sha1)) { unsigned long size; char *buf; - buf = read_object_with_reference(sha1, - commit_type, &size, sha1); + buf = read_sha1_file(sha1, &type, &size); if (!buf || size < 46) die("Not a valid commit: %s", from); free(buf); @@ -2043,36 +2478,37 @@ static void cmd_new_tag(void) read_next_command(); /* tagger ... */ - if (prefixcmp(command_buf.buf, "tagger ")) - die("Expected tagger command, got %s", command_buf.buf); - tagger = parse_ident(command_buf.buf + 7); + if (!prefixcmp(command_buf.buf, "tagger ")) { + tagger = parse_ident(command_buf.buf + 7); + read_next_command(); + } else + tagger = NULL; /* tag payload/message */ - read_next_command(); - msg = cmd_data(&msglen); + parse_data(&msg, 0, NULL); /* build the tag object */ - 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", commit_type); - sp += sprintf(sp, "tag %s\n", t->name); - sp += sprintf(sp, "tagger %s\n", tagger); - *sp++ = '\n'; - memcpy(sp, msg, msglen); - sp += msglen; + strbuf_reset(&new_data); + + strbuf_addf(&new_data, + "object %s\n" + "type %s\n" + "tag %s\n", + sha1_to_hex(sha1), typename(type), t->name); + if (tagger) + strbuf_addf(&new_data, + "tagger %s\n", tagger); + strbuf_addch(&new_data, '\n'); + strbuf_addbuf(&new_data, &msg); free(tagger); - free(msg); - if (store_object(OBJ_TAG, new_data.buffer, - sp - (char*)new_data.buffer, - NULL, t->sha1, 0)) + if (store_object(OBJ_TAG, &new_data, NULL, t->sha1, 0)) t->pack_id = MAX_PACK_ID; else t->pack_id = pack_id; } -static void cmd_reset_branch(void) +static void parse_reset_branch(void) { struct branch *b; char *sp; @@ -2092,10 +2528,12 @@ static void cmd_reset_branch(void) else b = new_branch(sp); read_next_command(); - cmd_from(b); + parse_from(b); + if (command_buf.len > 0) + unread_command_buf = 1; } -static void cmd_checkpoint(void) +static void parse_checkpoint(void) { if (object_count) { cycle_packfile(); @@ -2103,7 +2541,15 @@ static void cmd_checkpoint(void) dump_tags(); dump_marks(); } - read_next_command(); + skip_optional_lf(); +} + +static void parse_progress(void) +{ + fwrite(command_buf.buf, 1, command_buf.len, stdout); + fputc('\n', stdout); + fflush(stdout); + skip_optional_lf(); } static void import_marks(const char *input_file) @@ -2111,7 +2557,7 @@ static void import_marks(const char *input_file) char line[512]; FILE *f = fopen(input_file, "r"); if (!f) - die("cannot read %s: %s", input_file, strerror(errno)); + die_errno("cannot read '%s'", input_file); while (fgets(line, sizeof(line), f)) { uintmax_t mark; char *end; @@ -2141,16 +2587,50 @@ static void import_marks(const char *input_file) fclose(f); } +static int git_pack_config(const char *k, const char *v, void *cb) +{ + if (!strcmp(k, "pack.depth")) { + max_depth = git_config_int(k, v); + if (max_depth > MAX_DEPTH) + max_depth = MAX_DEPTH; + return 0; + } + if (!strcmp(k, "pack.compression")) { + int level = git_config_int(k, v); + if (level == -1) + level = Z_DEFAULT_COMPRESSION; + else if (level < 0 || level > Z_BEST_COMPRESSION) + die("bad pack compression level %d", level); + pack_compression_level = level; + pack_compression_seen = 1; + return 0; + } + if (!strcmp(k, "core.bigfilethreshold")) { + long n = git_config_int(k, v); + big_file_threshold = 0 < n ? n : 0; + } + return git_default_config(k, v, cb); +} + static const char fast_import_usage[] = -"git-fast-import [--date-format=f] [--max-pack-size=n] [--depth=n] [--active-branches=n] [--export-marks=marks.file]"; +"git fast-import [--date-format=f] [--max-pack-size=n] [--big-file-threshold=n] [--depth=n] [--active-branches=n] [--export-marks=marks.file]"; int main(int argc, const char **argv) { - int i, show_stats = 1; + unsigned int i, show_stats = 1; + + git_extract_argv0_path(argv[0]); + + if (argc == 2 && !strcmp(argv[1], "-h")) + usage(fast_import_usage); + + setup_git_directory(); + git_config(git_pack_config, NULL); + if (!pack_compression_seen && core_compression_seen) + pack_compression_level = core_compression_level; - git_config(git_default_config); alloc_objects(object_entry_alloc); - strbuf_init(&command_buf); + strbuf_init(&command_buf, 0); 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*)); @@ -2174,8 +2654,16 @@ int main(int argc, const char **argv) } else if (!prefixcmp(a, "--max-pack-size=")) max_packsize = strtoumax(a + 16, NULL, 0) * 1024 * 1024; - else if (!prefixcmp(a, "--depth=")) + else if (!prefixcmp(a, "--big-file-threshold=")) { + unsigned long v; + if (!git_parse_ulong(a + 21, &v)) + usage(fast_import_usage); + big_file_threshold = v; + } else if (!prefixcmp(a, "--depth=")) { max_depth = strtoul(a + 8, NULL, 0); + if (max_depth > MAX_DEPTH) + die("--depth cannot exceed %u", MAX_DEPTH); + } else if (!prefixcmp(a, "--active-branches=")) max_active_branches = strtoul(a + 18, NULL, 0); else if (!prefixcmp(a, "--import-marks=")) @@ -2187,7 +2675,7 @@ int main(int argc, const char **argv) fclose(pack_edges); pack_edges = fopen(a + 20, "a"); if (!pack_edges) - die("Cannot open %s: %s", a + 20, strerror(errno)); + die_errno("Cannot open '%s'", a + 20); } else if (!strcmp(a, "--force")) force_update = 1; else if (!strcmp(a, "--quiet")) @@ -2200,22 +2688,27 @@ int main(int argc, const char **argv) if (i != argc) usage(fast_import_usage); + rc_free = pool_alloc(cmd_save * sizeof(*rc_free)); + for (i = 0; i < (cmd_save - 1); i++) + rc_free[i].next = &rc_free[i + 1]; + rc_free[cmd_save - 1].next = NULL; + prepare_packed_git(); start_packfile(); - for (;;) { - read_next_command(); - if (command_buf.eof) - break; - else if (!strcmp("blob", command_buf.buf)) - cmd_new_blob(); + set_die_routine(die_nicely); + while (read_next_command() != EOF) { + if (!strcmp("blob", command_buf.buf)) + parse_new_blob(); else if (!prefixcmp(command_buf.buf, "commit ")) - cmd_new_commit(); + parse_new_commit(); else if (!prefixcmp(command_buf.buf, "tag ")) - cmd_new_tag(); + parse_new_tag(); else if (!prefixcmp(command_buf.buf, "reset ")) - cmd_reset_branch(); + parse_reset_branch(); else if (!strcmp("checkpoint", command_buf.buf)) - cmd_checkpoint(); + parse_checkpoint(); + else if (!prefixcmp(command_buf.buf, "progress ")) + parse_progress(); else die("Unsupported command: %s", command_buf.buf); } |