![[tokkee]](http://tokkee.org/images/avatar.png){kind=avatar}
diff --git a/fast-import.c b/fast-import.c
index a1cb13f09b1d661c6fff75d51378e3e63d211f20..9b71ccc479352c6a37b9b9652f1cb1793fdbb01b 100644 (file)
--- a/fast-import.c
+++ b/fast-import.c
| new_tag
| reset_branch
| checkpoint
+ | progress
;
new_blob ::= 'blob' lf
- mark?
+ mark?
file_content;
file_content ::= data;
('from' sp (ref_str | hexsha1 | sha1exp_str | idnum) lf)?
('merge' sp (ref_str | hexsha1 | sha1exp_str | idnum) lf)*
file_change*
- lf;
+ lf?;
commit_msg ::= data;
- file_change ::= file_clr | file_del | file_rnm | file_obm | file_inm;
+ file_change ::= file_clr
+ | file_del
+ | file_rnm
+ | file_cpy
+ | file_obm
+ | file_inm;
file_clr ::= 'deleteall' lf;
file_del ::= 'D' sp path_str lf;
file_rnm ::= 'R' sp path_str sp path_str lf;
+ file_cpy ::= 'C' sp path_str sp path_str lf;
file_obm ::= 'M' sp mode sp (hexsha1 | idnum) sp path_str lf;
file_inm ::= 'M' sp mode sp 'inline' sp path_str lf
data;
new_tag ::= 'tag' sp tag_str lf
'from' sp (ref_str | hexsha1 | sha1exp_str | idnum) lf
- 'tagger' sp name '<' email '>' when lf
+ 'tagger' sp name '<' email '>' when lf
tag_msg;
tag_msg ::= data;
reset_branch ::= 'reset' sp ref_str lf
('from' sp (ref_str | hexsha1 | sha1exp_str | idnum) lf)?
- 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.
# 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.
#
ref_str ::= ref;
sha1exp_str ::= sha1exp;
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";
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 the line (an lf have
+ # preceeded it).
+ #
+ comment ::= '#' not_lf* lf;
+ not_lf ::= # Any byte that is not ASCII newline (LF);
*/
#include "builtin.h"
#include "pack.h"
#include "refs.h"
#include "csum-file.h"
-#include "strbuf.h"
#include "quote.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];
};
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
struct mem_pool *next_pool;
char *next_free;
char *end;
- char space[FLEX_ARRAY]; /* more */
+ uintmax_t space[FLEX_ARRAY]; /* more */
};
struct atom_str
unsigned char sha1[20];
};
-struct dbuf
-{
- void *buffer;
- size_t capacity;
-};
-
struct hash_list
{
struct hash_list *next;
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 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;
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;
/* 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 write_crash_report(const char *err)
+{
+ char *loc = git_path("fast_import_crash_%d", 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: %d\n", getpid());
+ fprintf(rpt, " parent process : %d\n", 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);
+ }
+
+ fputc('\n', rpt);
+ fputs("-------------------\n", rpt);
+ fputs("END OF CRASH REPORT\n", rpt);
+ fclose(rpt);
+}
+
+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);
+ }
+ exit(128);
+}
static void alloc_objects(unsigned int cnt)
{
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));
+ /* round out to a 'uintmax_t' alignment */
+ if (len & (sizeof(uintmax_t) - 1))
+ len += sizeof(uintmax_t) - (len & (sizeof(uintmax_t) - 1));
p->next_free += len;
return r;
}
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;
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);
avail_tree_entry = e;
}
+static struct tree_content *dup_tree_content(struct tree_content *s)
+{
+ struct tree_content *d;
+ struct tree_entry *a, *b;
+ unsigned int i;
+
+ if (!s)
+ return NULL;
+ d = new_tree_content(s->entry_count);
+ for (i = 0; i < s->entry_count; i++) {
+ a = s->entries[i];
+ b = new_tree_entry();
+ memcpy(b, a, sizeof(*a));
+ if (a->tree && is_null_sha1(b->versions[1].sha1))
+ b->tree = dup_tree_content(a->tree);
+ else
+ b->tree = NULL;
+ d->entries[i] = b;
+ }
+ d->entry_count = s->entry_count;
+ d->delta_depth = s->delta_depth;
+
+ return d;
+}
+
static void start_packfile(void)
{
static char tmpfile[PATH_MAX];
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 = xmkstemp(tmpfile);
p = xcalloc(1, sizeof(*p) + strlen(tmpfile) + 2);
strcpy(p->pack_name, tmpfile);
p->pack_fd = pack_fd;
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 = xmkstemp(tmpfile);
f = sha1fd(idx_fd, tmpfile);
sha1write(f, array, 256 * sizeof(int));
SHA1_Init(&ctx);
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);
+ write_or_die(keep_fd, keep_msg, strlen(keep_msg));
+ if (close(keep_fd))
+ die("failed to write keep file");
snprintf(name, sizeof(name), "%s/pack/pack-%s.pack",
get_object_directory(), sha1_to_hex(pack_data->sha1));
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);
close(pack_data->pack_fd);
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);
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;
}
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)
z_stream s;
hdrlen = sprintf((char*)hdr,"%s %lu", typename(type),
- (unsigned long)datlen) + 1;
+ (unsigned long)dat->len) + 1;
SHA1_Init(&c);
SHA1_Update(&c, hdr, hdrlen);
- SHA1_Update(&c, dat, datlen);
+ SHA1_Update(&c, dat->buf, dat->len);
SHA1_Final(sha1, &c);
if (sha1out)
hashcpy(sha1out, sha1);
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;
}
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);
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)
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);
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;
}
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;
}
+/* 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);
}
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);
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);
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))
}
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++) {
return 1;
}
+static int tree_content_get(
+ struct tree_entry *root,
+ const char *p,
+ struct tree_entry *leaf)
+{
+ struct tree_content *t = root->tree;
+ const char *slash1;
+ unsigned int i, n;
+ struct tree_entry *e;
+
+ slash1 = strchr(p, '/');
+ if (slash1)
+ n = slash1 - p;
+ else
+ n = strlen(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) {
+ memcpy(leaf, e, sizeof(*leaf));
+ if (e->tree && is_null_sha1(e->versions[1].sha1))
+ leaf->tree = dup_tree_content(e->tree);
+ else
+ leaf->tree = NULL;
+ return 1;
+ }
+ if (!S_ISDIR(e->versions[1].mode))
+ return 0;
+ if (!e->tree)
+ load_tree(e);
+ return tree_content_get(e, slash1 + 1, leaf);
+ }
+ }
+ return 0;
+}
+
static int update_branch(struct branch *b)
{
static const char *msg = "fast-import";
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 int read_next_command(void)
+{
+ 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 read_next_command(void)
+static void skip_optional_lf(void)
{
- read_line(&command_buf, stdin, '\n');
+ int term_char = fgetc(stdin);
+ if (term_char != '\n' && term_char != EOF)
+ ungetc(term_char, stdin);
}
static void cmd_mark(void)
next_mark = 0;
}
-static void *cmd_data (size_t *size)
+static void cmd_data(struct strbuf *sb)
{
- 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;
+ size_t n = 0, length;
+
length = strtoul(command_buf.buf + 5, NULL, 10);
- buffer = xmalloc(length);
+
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));
}
}
- if (fgetc(stdin) != '\n')
- die("An lf did not trail the binary data as expected.");
-
- *size = length;
- return buffer;
+ skip_optional_lf();
}
static int validate_raw_date(const char *src, char *result, int maxlen)
static void cmd_new_blob(void)
{
- size_t l;
- void *d;
+ static struct strbuf buf = STRBUF_INIT;
read_next_command();
cmd_mark();
- d = cmd_data(&l);
-
- if (store_object(OBJ_BLOB, d, l, &last_blob, NULL, next_mark))
- free(d);
+ cmd_data(&buf);
+ store_object(OBJ_BLOB, &buf, &last_blob, NULL, next_mark);
}
static void unload_one_branch(void)
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];
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);
+ static struct strbuf buf = STRBUF_INIT;
+
+ 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);
+ cmd_data(&buf);
+ store_object(OBJ_BLOB, &buf, &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)
}
tree_content_set(&b->branch_tree, p, sha1, S_IFREG | mode, NULL);
- free(p_uq);
}
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_r(struct branch *b)
+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));
- tree_content_remove(&b->branch_tree, s, &leaf);
+ if (rename)
+ tree_content_remove(&b->branch_tree, s, &leaf);
+ else
+ tree_content_get(&b->branch_tree, s, &leaf);
if (!leaf.versions[1].mode)
die("Path %s not in branch", s);
tree_content_set(&b->branch_tree, d,
leaf.versions[1].sha1,
leaf.versions[1].mode,
leaf.tree);
-
- free(s_uq);
- free(d_uq);
}
static void file_change_deleteall(struct branch *b)
}
}
-static void cmd_from(struct branch *b)
+static int cmd_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);
die("Invalid ref name or SHA1 expression: %s", from);
read_next_command();
+ return 1;
}
static struct hash_list *cmd_merge(unsigned int *count)
static void cmd_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;
}
if (!committer)
die("Expected committer but didn't get one");
- msg = cmd_data(&msglen);
+ cmd_data(&msg);
read_next_command();
cmd_from(b);
merge_list = cmd_merge(&merge_count);
}
/* 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);
else if (!prefixcmp(command_buf.buf, "R "))
- file_change_r(b);
+ file_change_cr(b, 1);
+ else if (!prefixcmp(command_buf.buf, "C "))
+ file_change_cr(b, 0);
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 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];
/* tag payload/message */
read_next_command();
- msg = cmd_data(&msglen);
+ cmd_data(&msg);
/* 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"
+ "tagger %s\n"
+ "\n",
+ sha1_to_hex(sha1), commit_type, t->name, tagger);
+ 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;
else
b = new_branch(sp);
read_next_command();
- cmd_from(b);
+ if (!cmd_from(b) && command_buf.len > 0)
+ unread_command_buf = 1;
}
static void cmd_checkpoint(void)
dump_tags();
dump_marks();
}
- read_next_command();
+ skip_optional_lf();
+}
+
+static void cmd_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)
fclose(f);
}
+static int git_pack_config(const char *k, const char *v)
+{
+ 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;
+ }
+ return git_default_config(k, v);
+}
+
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]";
int main(int argc, const char **argv)
{
- int i, show_stats = 1;
+ unsigned int i, show_stats = 1;
+
+ git_config(git_pack_config);
+ 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*));
}
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, "--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="))
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))
+ set_die_routine(die_nicely);
+ while (read_next_command() != EOF) {
+ if (!strcmp("blob", command_buf.buf))
cmd_new_blob();
else if (!prefixcmp(command_buf.buf, "commit "))
cmd_new_commit();
cmd_reset_branch();
else if (!strcmp("checkpoint", command_buf.buf))
cmd_checkpoint();
+ else if (!prefixcmp(command_buf.buf, "progress "))
+ cmd_progress();
else
die("Unsupported command: %s", command_buf.buf);
}