![[tokkee]](http://tokkee.org/images/avatar.png){kind=avatar}
| author | Junio C Hamano <gitster@pobox.com> | |
| Fri, 16 Mar 2012 15:19:18 +0000 (08:19 -0700) | ||
| committer | Junio C Hamano <gitster@pobox.com> | |
| Fri, 16 Mar 2012 15:19:18 +0000 (08:19 -0700) |
Andrew Sayers noticed that the svn-fe | git fast-import pipeline
mishandles a subversion history that copies the root directory to a
sub-directory (e.g. doing `svn cp . trunk` to standardise your
layout). As David Barr explained, the bug arises when the following
command is sent to git fast-import:
'ls' SP ':1' SP LF
Instead of reading back what is at the root of r1, it unconditionally
reports the path as missing.
After sleeping on it, here are two patches for 'maint'. One plugs a
memory leak. The other ensures that trying to pass an empty path to
the 'ls' command results in an error message that can help the
frontend author instead of the silently broken conversion Andrew
found.
Then we can carefully add 'ls ""' support in 1.7.11.
* commit 'refs/pull-request-tags/jn/maint-fast-import-empty-ls':
fast-import: don't allow 'ls' of path with empty components
fast-import: leakfix for 'ls' of dirty trees
mishandles a subversion history that copies the root directory to a
sub-directory (e.g. doing `svn cp . trunk` to standardise your
layout). As David Barr explained, the bug arises when the following
command is sent to git fast-import:
'ls' SP ':1' SP LF
Instead of reading back what is at the root of r1, it unconditionally
reports the path as missing.
After sleeping on it, here are two patches for 'maint'. One plugs a
memory leak. The other ensures that trying to pass an empty path to
the 'ls' command results in an error message that can help the
frontend author instead of the silently broken conversion Andrew
found.
Then we can carefully add 'ls ""' support in 1.7.11.
* commit 'refs/pull-request-tags/jn/maint-fast-import-empty-ls':
fast-import: don't allow 'ls' of path with empty components
fast-import: leakfix for 'ls' of dirty trees
| 1 | 2 | |||
|---|---|---|---|---|
| fast-import.c | patch | | diff1 | | diff2 | | blob | history |
| t/t9300-fast-import.sh | patch | | diff1 | | diff2 | | blob | history |
diff --combined fast-import.c
index c1486cabbaa5f736f92994587fafd1f3afdf43af,47f61f3cba7b7a4cde8ae116cbce38116562bda6..a85275dc682d2bb8068f003b8281c3933488f010
--- 1/fast-import.c
--- 2/fast-import.c
+++ b/fast-import.c
#define DEPTH_BITS 13
#define MAX_DEPTH ((1<<DEPTH_BITS)-1)
-struct object_entry
-{
+/*
+ * We abuse the setuid bit on directories to mean "do not delta".
+ */
+#define NO_DELTA S_ISUID
+
+struct object_entry {
struct pack_idx_entry idx;
struct object_entry *next;
uint32_t type : TYPE_BITS,
depth : DEPTH_BITS;
};
-struct object_entry_pool
-{
+struct object_entry_pool {
struct object_entry_pool *next_pool;
struct object_entry *next_free;
struct object_entry *end;
struct object_entry entries[FLEX_ARRAY]; /* more */
};
-struct mark_set
-{
+struct mark_set {
union {
struct object_entry *marked[1024];
struct mark_set *sets[1024];
unsigned int shift;
};
-struct last_object
-{
+struct last_object {
struct strbuf data;
off_t offset;
unsigned int depth;
unsigned no_swap : 1;
};
-struct mem_pool
-{
+struct mem_pool {
struct mem_pool *next_pool;
char *next_free;
char *end;
uintmax_t space[FLEX_ARRAY]; /* more */
};
-struct atom_str
-{
+struct atom_str {
struct atom_str *next_atom;
unsigned short str_len;
char str_dat[FLEX_ARRAY]; /* more */
};
struct tree_content;
-struct tree_entry
-{
+struct tree_entry {
struct tree_content *tree;
struct atom_str *name;
- struct tree_entry_ms
- {
+ struct tree_entry_ms {
uint16_t mode;
unsigned char sha1[20];
} versions[2];
};
-struct tree_content
-{
+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 */
};
-struct avail_tree_content
-{
+struct avail_tree_content {
unsigned int entry_capacity; /* must match tree_content */
struct avail_tree_content *next_avail;
};
-struct branch
-{
+struct branch {
struct branch *table_next_branch;
struct branch *active_next_branch;
const char *name;
unsigned char sha1[20];
};
-struct tag
-{
+struct tag {
struct tag *next_tag;
const char *name;
unsigned int pack_id;
unsigned char sha1[20];
};
-struct hash_list
-{
+struct hash_list {
struct hash_list *next;
unsigned char sha1[20];
};
WHENSPEC_NOW
} whenspec_type;
-struct recent_command
-{
+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;
-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;
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 uintmax_t delta_count_attempts_by_type[1 << TYPE_BITS];
static unsigned long object_count;
static unsigned long branch_count;
static unsigned long branch_load_count;
static struct atom_str **atom_table;
/* The .pack file being generated */
+static struct pack_idx_option pack_idx_opts;
static unsigned int pack_id;
static struct sha1file *pack_file;
static struct packed_git *pack_data;
static uintmax_t next_mark;
static struct strbuf new_data = STRBUF_INIT;
static int seen_data_command;
+static int require_explicit_termination;
/* Signal handling */
static volatile sig_atomic_t checkpoint_requested;
if (b)
die("Invalid attempt to create duplicate branch: %s", name);
- switch (check_ref_format(name)) {
- case 0: break; /* its valid */
- case CHECK_REF_FORMAT_ONELEVEL:
- break; /* valid, but too few '/', allow anyway */
- default:
+ if (check_refname_format(name, REFNAME_ALLOW_ONELEVEL))
die("Branch name doesn't conform to GIT standards: %s", name);
- }
b = pool_calloc(1, sizeof(struct branch));
b->name = pool_strdup(name);
static void start_packfile(void)
{
- static char tmpfile[PATH_MAX];
+ static char tmp_file[PATH_MAX];
struct packed_git *p;
struct pack_header hdr;
int pack_fd;
- pack_fd = odb_mkstemp(tmpfile, sizeof(tmpfile),
+ pack_fd = odb_mkstemp(tmp_file, sizeof(tmp_file),
"pack/tmp_pack_XXXXXX");
- p = xcalloc(1, sizeof(*p) + strlen(tmpfile) + 2);
- strcpy(p->pack_name, tmpfile);
+ p = xcalloc(1, sizeof(*p) + strlen(tmp_file) + 2);
+ strcpy(p->pack_name, tmp_file);
p->pack_fd = pack_fd;
+ p->do_not_close = 1;
pack_file = sha1fd(pack_fd, p->pack_name);
hdr.hdr_signature = htonl(PACK_SIGNATURE);
if (c != last)
die("internal consistency error creating the index");
- tmpfile = write_idx_file(NULL, idx, object_count, pack_data->sha1);
+ tmpfile = write_idx_file(NULL, idx, object_count, &pack_idx_opts, pack_data->sha1);
free(idx);
return tmpfile;
}
unsigned char sha1[20];
unsigned long hdrlen, deltalen;
git_SHA_CTX c;
- z_stream s;
+ git_zstream s;
hdrlen = sprintf((char *)hdr,"%s %lu", typename(type),
(unsigned long)dat->len) + 1;
}
if (last && last->data.buf && last->depth < max_depth && dat->len > 20) {
+ delta_count_attempts_by_type[type]++;
delta = diff_delta(last->data.buf, last->data.len,
dat->buf, dat->len,
&deltalen, dat->len - 20);
delta = NULL;
memset(&s, 0, sizeof(s));
- deflateInit(&s, pack_compression_level);
+ git_deflate_init(&s, pack_compression_level);
if (delta) {
s.next_in = delta;
s.avail_in = deltalen;
s.next_in = (void *)dat->buf;
s.avail_in = dat->len;
}
- s.avail_out = deflateBound(&s, s.avail_in);
+ s.avail_out = git_deflate_bound(&s, s.avail_in);
s.next_out = out = xmalloc(s.avail_out);
- while (deflate(&s, Z_FINISH) == Z_OK)
- /* nothing */;
- deflateEnd(&s);
+ while (git_deflate(&s, Z_FINISH) == Z_OK)
+ ; /* nothing */
+ git_deflate_end(&s);
/* Determine if we should auto-checkpoint. */
if ((max_packsize && (pack_size + 60 + s.total_out) > max_packsize)
delta = NULL;
memset(&s, 0, sizeof(s));
- deflateInit(&s, pack_compression_level);
+ git_deflate_init(&s, pack_compression_level);
s.next_in = (void *)dat->buf;
s.avail_in = dat->len;
- s.avail_out = deflateBound(&s, s.avail_in);
+ s.avail_out = git_deflate_bound(&s, s.avail_in);
s.next_out = out = xrealloc(out, s.avail_out);
- while (deflate(&s, Z_FINISH) == Z_OK)
- /* nothing */;
- deflateEnd(&s);
+ while (git_deflate(&s, Z_FINISH) == Z_OK)
+ ; /* nothing */
+ git_deflate_end(&s);
}
}
return 0;
}
-static void truncate_pack(off_t to, git_SHA_CTX *ctx)
+static void truncate_pack(struct sha1file_checkpoint *checkpoint)
{
- if (ftruncate(pack_data->pack_fd, to)
- || lseek(pack_data->pack_fd, to, SEEK_SET) != to)
+ if (sha1file_truncate(pack_file, checkpoint))
die_errno("cannot truncate pack to skip duplicate");
- pack_size = to;
-
- /* yes this is a layering violation */
- pack_file->total = to;
- pack_file->offset = 0;
- pack_file->ctx = *ctx;
+ pack_size = checkpoint->offset;
}
static void stream_blob(uintmax_t len, unsigned char *sha1out, uintmax_t mark)
unsigned long hdrlen;
off_t offset;
git_SHA_CTX c;
- git_SHA_CTX pack_file_ctx;
- z_stream s;
+ git_zstream s;
+ struct sha1file_checkpoint checkpoint;
int status = Z_OK;
/* Determine if we should auto-checkpoint. */
|| (pack_size + 60 + len) < pack_size)
cycle_packfile();
- offset = pack_size;
-
- /* preserve the pack_file SHA1 ctx in case we have to truncate later */
- sha1flush(pack_file);
- pack_file_ctx = pack_file->ctx;
+ sha1file_checkpoint(pack_file, &checkpoint);
+ offset = checkpoint.offset;
hdrlen = snprintf((char *)out_buf, out_sz, "blob %" PRIuMAX, len) + 1;
if (out_sz <= hdrlen)
crc32_begin(pack_file);
memset(&s, 0, sizeof(s));
- deflateInit(&s, pack_compression_level);
+ git_deflate_init(&s, pack_compression_level);
hdrlen = encode_in_pack_object_header(OBJ_BLOB, len, out_buf);
if (out_sz <= hdrlen)
len -= n;
}
- status = deflate(&s, len ? 0 : Z_FINISH);
+ status = git_deflate(&s, len ? 0 : Z_FINISH);
if (!s.avail_out || status == Z_STREAM_END) {
size_t n = s.next_out - out_buf;
die("unexpected deflate failure: %d", status);
}
}
- deflateEnd(&s);
+ git_deflate_end(&s);
git_SHA1_Final(sha1, &c);
if (sha1out)
if (e->idx.offset) {
duplicate_count_by_type[OBJ_BLOB]++;
- truncate_pack(offset, &pack_file_ctx);
+ truncate_pack(&checkpoint);
} else if (find_sha1_pack(sha1, packed_git)) {
e->type = OBJ_BLOB;
e->pack_id = MAX_PACK_ID;
e->idx.offset = 1; /* just not zero! */
duplicate_count_by_type[OBJ_BLOB]++;
- truncate_pack(offset, &pack_file_ctx);
+ truncate_pack(&checkpoint);
} else {
e->depth = 0;
struct tree_entry *e = t->entries[i];
if (!e->versions[v].mode)
continue;
- strbuf_addf(b, "%o %s%c", (unsigned int)e->versions[v].mode,
- e->name->str_dat, '\0');
+ strbuf_addf(b, "%o %s%c",
+ (unsigned int)(e->versions[v].mode & ~NO_DELTA),
+ e->name->str_dat, '\0');
strbuf_add(b, e->versions[v].sha1, 20);
}
}
struct tree_content *t = root->tree;
unsigned int i, j, del;
struct last_object lo = { STRBUF_INIT, 0, 0, /* no_swap */ 1 };
- struct object_entry *le;
+ struct object_entry *le = NULL;
if (!is_null_sha1(root->versions[1].sha1))
return;
store_tree(t->entries[i]);
}
- le = find_object(root->versions[0].sha1);
+ if (!(root->versions[0].mode & NO_DELTA))
+ le = find_object(root->versions[0].sha1);
if (S_ISDIR(root->versions[0].mode) && le && le->pack_id == pack_id) {
mktree(t, 0, &old_tree);
lo.data = old_tree;
{
if (!S_ISDIR(mode))
die("Root cannot be a non-directory");
+ hashclr(root->versions[0].sha1);
hashcpy(root->versions[1].sha1, sha1);
if (root->tree)
release_tree_content_recursive(root->tree);
if (e->tree)
release_tree_content_recursive(e->tree);
e->tree = subtree;
+
+ /*
+ * We need to leave e->versions[0].sha1 alone
+ * to avoid modifying the preimage tree used
+ * when writing out the parent directory.
+ * But after replacing the subdir with a
+ * completely different one, it's not a good
+ * delta base any more, and besides, we've
+ * thrown away the tree entries needed to
+ * make a delta against it.
+ *
+ * So let's just explicitly disable deltas
+ * for the subtree.
+ */
+ if (S_ISDIR(e->versions[0].mode))
+ e->versions[0].mode |= NO_DELTA;
+
hashclr(root->versions[1].sha1);
return 1;
}
n = slash1 - p;
else
n = strlen(p);
+ if (!n)
+ die("Empty path component found in input");
if (!root->tree)
load_tree(root);
static char *parse_ident(const char *buf)
{
- const char *gt;
+ const char *ltgt;
size_t name_len;
char *ident;
- gt = strrchr(buf, '>');
- if (!gt)
+ /* ensure there is a space delimiter even if there is no name */
+ if (*buf == '<')
+ --buf;
+
+ ltgt = buf + strcspn(buf, "<>");
+ if (*ltgt != '<')
+ die("Missing < in ident string: %s", buf);
+ if (ltgt != buf && ltgt[-1] != ' ')
+ die("Missing space before < in ident string: %s", buf);
+ ltgt = ltgt + 1 + strcspn(ltgt + 1, "<>");
+ if (*ltgt != '>')
die("Missing > in ident string: %s", buf);
- gt++;
- if (*gt != ' ')
+ ltgt++;
+ if (*ltgt != ' ')
die("Missing space after > in ident string: %s", buf);
- gt++;
- name_len = gt - buf;
+ ltgt++;
+ name_len = ltgt - buf;
ident = xmalloc(name_len + 24);
strncpy(ident, buf, name_len);
switch (whenspec) {
case WHENSPEC_RAW:
- if (validate_raw_date(gt, ident + name_len, 24) < 0)
- die("Invalid raw date \"%s\" in ident: %s", gt, buf);
+ if (validate_raw_date(ltgt, ident + name_len, 24) < 0)
+ die("Invalid raw date \"%s\" in ident: %s", ltgt, buf);
break;
case WHENSPEC_RFC2822:
- if (parse_date(gt, ident + name_len, 24) < 0)
- die("Invalid rfc2822 date \"%s\" in ident: %s", gt, buf);
+ if (parse_date(ltgt, ident + name_len, 24) < 0)
+ die("Invalid rfc2822 date \"%s\" in ident: %s", ltgt, buf);
break;
case WHENSPEC_NOW:
- if (strcmp("now", gt))
+ if (strcmp("now", ltgt))
die("Date in ident must be 'now': %s", buf);
datestamp(ident + name_len, 24);
break;
if (tmp_hex_sha1_len == 40 && !get_sha1_hex(hex_sha1, sha1)) {
/* This is a note entry */
+ if (fanout == 0xff) {
+ /* Counting mode, no rename */
+ num_notes++;
+ continue;
+ }
construct_path_with_fanout(hex_sha1, fanout, realpath);
if (!strcmp(fullpath, realpath)) {
/* Note entry is in correct location */
leaf.tree);
}
-static void note_change_n(struct branch *b, unsigned char old_fanout)
+static void note_change_n(struct branch *b, unsigned char *old_fanout)
{
const char *p = command_buf.buf + 2;
static struct strbuf uq = STRBUF_INIT;
uint16_t inline_data = 0;
unsigned char new_fanout;
+ /*
+ * When loading a branch, we don't traverse its tree to count the real
+ * number of notes (too expensive to do this for all non-note refs).
+ * This means that recently loaded notes refs might incorrectly have
+ * b->num_notes == 0, and consequently, old_fanout might be wrong.
+ *
+ * Fix this by traversing the tree and counting the number of notes
+ * when b->num_notes == 0. If the notes tree is truly empty, the
+ * calculation should not take long.
+ */
+ if (b->num_notes == 0 && *old_fanout == 0) {
+ /* Invoke change_note_fanout() in "counting mode". */
+ b->num_notes = change_note_fanout(&b->branch_tree, 0xff);
+ *old_fanout = convert_num_notes_to_fanout(b->num_notes);
+ }
+
+ /* Now parse the notemodify command. */
/* <dataref> or 'inline' */
if (*p == ':') {
char *x;
/* <committish> */
s = lookup_branch(p);
if (s) {
+ if (is_null_sha1(s->sha1))
+ die("Can't add a note on empty branch.");
hashcpy(commit_sha1, s->sha1);
} else if (*p == ':') {
uintmax_t commit_mark = strtoumax(p + 1, NULL, 10);
typename(type), command_buf.buf);
}
- construct_path_with_fanout(sha1_to_hex(commit_sha1), old_fanout, path);
+ construct_path_with_fanout(sha1_to_hex(commit_sha1), *old_fanout, path);
if (tree_content_remove(&b->branch_tree, path, NULL))
b->num_notes--;
else if (!prefixcmp(command_buf.buf, "C "))
file_change_cr(b, 0);
else if (!prefixcmp(command_buf.buf, "N "))
- note_change_n(b, prev_fanout);
+ note_change_n(b, &prev_fanout);
else if (!strcmp("deleteall", command_buf.buf))
file_change_deleteall(b);
else if (!prefixcmp(command_buf.buf, "ls "))
/* Obtain the new tag name from the rest of our command */
sp = strchr(command_buf.buf, ' ') + 1;
t = pool_alloc(sizeof(struct tag));
- t->next_tag = NULL;
+ memset(t, 0, sizeof(struct tag));
t->name = pool_strdup(sp);
if (last_tag)
last_tag->next_tag = t;
from = strchr(command_buf.buf, ' ') + 1;
s = lookup_branch(from);
if (s) {
+ if (is_null_sha1(s->sha1))
+ die("Can't tag an empty branch.");
hashcpy(sha1, s->sha1);
type = OBJ_COMMIT;
} else if (*from == ':') {
type = oe->type;
hashcpy(sha1, oe->idx.sha1);
} else if (!get_sha1(from, sha1)) {
- unsigned long size;
- char *buf;
-
- buf = read_sha1_file(sha1, &type, &size);
- if (!buf || size < 46)
- die("Not a valid commit: %s", from);
- free(buf);
+ struct object_entry *oe = find_object(sha1);
+ if (!oe) {
+ type = sha1_object_info(sha1, NULL);
+ if (type < 0)
+ die("Not a valid object: %s", from);
+ } else
+ type = oe->type;
} else
die("Invalid ref name or SHA1 expression: %s", from);
read_next_command();
strbuf_release(&line);
cat_blob_write(buf, size);
cat_blob_write("\n", 1);
- free(buf);
+ if (oe && oe->pack_id == pack_id) {
+ last_blob.offset = oe->idx.offset;
+ strbuf_attach(&last_blob.data, buf, size, size);
+ last_blob.depth = oe->depth;
+ } else
+ free(buf);
}
static void parse_cat_blob(void)
unsigned char sha1[20])
{
unsigned long size;
- void *buf = NULL;
+ char *buf = NULL;
if (!oe) {
enum object_type type = sha1_object_info(sha1, NULL);
if (type < 0)
/* mode SP type SP object_name TAB path LF */
strbuf_reset(&line);
strbuf_addf(&line, "%06o %s %s\t",
- mode, type, sha1_to_hex(sha1));
+ mode & ~NO_DELTA, type, sha1_to_hex(sha1));
quote_c_style(path, &line, NULL, 0);
strbuf_addch(&line, '\n');
}
{
const char *p;
struct tree_entry *root = NULL;
- struct tree_entry leaf = {0};
+ struct tree_entry leaf = {NULL};
/* ls SP (<treeish> SP)? <path> */
p = command_buf.buf + strlen("ls ");
store_tree(&leaf);
print_ls(leaf.versions[1].mode, leaf.versions[1].sha1, p);
+ if (leaf.tree)
+ release_tree_content_recursive(leaf.tree);
if (!b || root != &b->branch_tree)
release_tree_entry(root);
}
option_export_marks(feature + 13);
} else if (!strcmp(feature, "cat-blob")) {
; /* Don't die - this feature is supported */
- } else if (!prefixcmp(feature, "relative-marks")) {
+ } else if (!strcmp(feature, "relative-marks")) {
relative_marks_paths = 1;
- } else if (!prefixcmp(feature, "no-relative-marks")) {
+ } else if (!strcmp(feature, "no-relative-marks")) {
relative_marks_paths = 0;
- } else if (!prefixcmp(feature, "force")) {
+ } else if (!strcmp(feature, "done")) {
+ require_explicit_termination = 1;
+ } else if (!strcmp(feature, "force")) {
force_update = 1;
} else if (!strcmp(feature, "notes") || !strcmp(feature, "ls")) {
; /* do nothing; we have the feature */
return 0;
}
if (!strcmp(k, "pack.indexversion")) {
- pack_idx_default_version = git_config_int(k, v);
- if (pack_idx_default_version > 2)
+ pack_idx_opts.version = git_config_int(k, v);
+ if (pack_idx_opts.version > 2)
die("bad pack.indexversion=%"PRIu32,
- pack_idx_default_version);
+ pack_idx_opts.version);
return 0;
}
if (!strcmp(k, "pack.packsizelimit")) {
max_packsize = git_config_ulong(k, v);
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);
}
git_extract_argv0_path(argv[0]);
+ git_setup_gettext();
+
if (argc == 2 && !strcmp(argv[1], "-h"))
usage(fast_import_usage);
setup_git_directory();
+ reset_pack_idx_option(&pack_idx_opts);
git_config(git_pack_config, NULL);
if (!pack_compression_seen && core_compression_seen)
pack_compression_level = core_compression_level;
parse_reset_branch();
else if (!strcmp("checkpoint", command_buf.buf))
parse_checkpoint();
+ else if (!strcmp("done", command_buf.buf))
+ break;
else if (!prefixcmp(command_buf.buf, "progress "))
parse_progress();
else if (!prefixcmp(command_buf.buf, "feature "))
if (!seen_data_command)
parse_argv();
+ if (require_explicit_termination && feof(stdin))
+ die("stream ends early");
+
end_packfile();
dump_branches();
fprintf(stderr, "---------------------------------------------------------------------\n");
fprintf(stderr, "Alloc'd objects: %10" PRIuMAX "\n", alloc_count);
fprintf(stderr, "Total objects: %10" PRIuMAX " (%10" PRIuMAX " duplicates )\n", total_count, duplicate_count);
- fprintf(stderr, " blobs : %10" PRIuMAX " (%10" PRIuMAX " duplicates %10" PRIuMAX " deltas)\n", object_count_by_type[OBJ_BLOB], duplicate_count_by_type[OBJ_BLOB], delta_count_by_type[OBJ_BLOB]);
- fprintf(stderr, " trees : %10" PRIuMAX " (%10" PRIuMAX " duplicates %10" PRIuMAX " deltas)\n", object_count_by_type[OBJ_TREE], duplicate_count_by_type[OBJ_TREE], delta_count_by_type[OBJ_TREE]);
- fprintf(stderr, " commits: %10" PRIuMAX " (%10" PRIuMAX " duplicates %10" PRIuMAX " deltas)\n", object_count_by_type[OBJ_COMMIT], duplicate_count_by_type[OBJ_COMMIT], delta_count_by_type[OBJ_COMMIT]);
- fprintf(stderr, " tags : %10" PRIuMAX " (%10" PRIuMAX " duplicates %10" PRIuMAX " deltas)\n", object_count_by_type[OBJ_TAG], duplicate_count_by_type[OBJ_TAG], delta_count_by_type[OBJ_TAG]);
+ fprintf(stderr, " blobs : %10" PRIuMAX " (%10" PRIuMAX " duplicates %10" PRIuMAX " deltas of %10" PRIuMAX" attempts)\n", object_count_by_type[OBJ_BLOB], duplicate_count_by_type[OBJ_BLOB], delta_count_by_type[OBJ_BLOB], delta_count_attempts_by_type[OBJ_BLOB]);
+ fprintf(stderr, " trees : %10" PRIuMAX " (%10" PRIuMAX " duplicates %10" PRIuMAX " deltas of %10" PRIuMAX" attempts)\n", object_count_by_type[OBJ_TREE], duplicate_count_by_type[OBJ_TREE], delta_count_by_type[OBJ_TREE], delta_count_attempts_by_type[OBJ_TREE]);
+ fprintf(stderr, " commits: %10" PRIuMAX " (%10" PRIuMAX " duplicates %10" PRIuMAX " deltas of %10" PRIuMAX" attempts)\n", object_count_by_type[OBJ_COMMIT], duplicate_count_by_type[OBJ_COMMIT], delta_count_by_type[OBJ_COMMIT], delta_count_attempts_by_type[OBJ_COMMIT]);
+ fprintf(stderr, " tags : %10" PRIuMAX " (%10" PRIuMAX " duplicates %10" PRIuMAX " deltas of %10" PRIuMAX" attempts)\n", object_count_by_type[OBJ_TAG], duplicate_count_by_type[OBJ_TAG], delta_count_by_type[OBJ_TAG], delta_count_attempts_by_type[OBJ_TAG]);
fprintf(stderr, "Total branches: %10lu (%10lu loads )\n", branch_count, branch_load_count);
fprintf(stderr, " marks: %10" PRIuMAX " (%10" PRIuMAX " unique )\n", (((uintmax_t)1) << marks->shift) * 1024, marks_set_count);
fprintf(stderr, " atoms: %10u\n", atom_cnt);
diff --combined t/t9300-fast-import.sh
index 438aaf6b14b8ae0cb35739d6006eaf646876107c,2cd0f0614d2daa6622161cdc8afce34e22328a97..0f5b5e5964a60f31cdfd6bc456848c2f4b820d0a
+++ b/t/t9300-fast-import.sh
An annotated tag without a tagger
EOF
+tag series-A-blob
+from :3
+data <<EOF
+An annotated tag that annotates a blob.
+EOF
+
INPUT_END
test_expect_success \
'A: create pack from stdin' \
test_cmp expect actual
'
+cat >expect <<EOF
+object $(git rev-parse refs/heads/master:file3)
+type blob
+tag series-A-blob
+
+An annotated tag that annotates a blob.
+EOF
+test_expect_success 'A: verify tag/series-A-blob' '
+ git cat-file tag tags/series-A-blob >actual &&
+ test_cmp expect actual
+'
+
cat >expect <<EOF
:2 `git rev-parse --verify master:file2`
:3 `git rev-parse --verify master:file3`
</dev/null &&
test_cmp expect marks.new'
+test_tick
+new_blob=$(echo testing | git hash-object --stdin)
+cat >input <<INPUT_END
+tag series-A-blob-2
+from $(git rev-parse refs/heads/master:file3)
+data <<EOF
+Tag blob by sha1.
+EOF
+
+blob
+mark :6
+data <<EOF
+testing
+EOF
+
+commit refs/heads/new_blob
+committer <> 0 +0000
+data 0
+M 644 :6 new_blob
+#pretend we got sha1 from fast-import
+ls "new_blob"
+
+tag series-A-blob-3
+from $new_blob
+data <<EOF
+Tag new_blob.
+EOF
+INPUT_END
+
+cat >expect <<EOF
+object $(git rev-parse refs/heads/master:file3)
+type blob
+tag series-A-blob-2
+
+Tag blob by sha1.
+object $new_blob
+type blob
+tag series-A-blob-3
+
+Tag new_blob.
+EOF
+
+test_expect_success \
+ 'A: tag blob by sha1' \
+ 'git fast-import <input &&
+ git cat-file tag tags/series-A-blob-2 >actual &&
+ git cat-file tag tags/series-A-blob-3 >>actual &&
+ test_cmp expect actual'
+
test_tick
cat >input <<INPUT_END
commit refs/heads/verify--import-marks
test `git rev-parse master` = `git rev-parse TEMP_TAG^`'
rm -f .git/TEMP_TAG
+git gc 2>/dev/null >/dev/null
+git prune 2>/dev/null >/dev/null
+
+cat >input <<INPUT_END
+commit refs/heads/empty-committer-1
+committer <> $GIT_COMMITTER_DATE
+data <<COMMIT
+empty commit
+COMMIT
+INPUT_END
+test_expect_success 'B: accept empty committer' '
+ git fast-import <input &&
+ out=$(git fsck) &&
+ echo "$out" &&
+ test -z "$out"
+'
+git update-ref -d refs/heads/empty-committer-1 || true
+
+git gc 2>/dev/null >/dev/null
+git prune 2>/dev/null >/dev/null
+
+cat >input <<INPUT_END
+commit refs/heads/empty-committer-2
+committer <a@b.com> $GIT_COMMITTER_DATE
+data <<COMMIT
+empty commit
+COMMIT
+INPUT_END
+test_expect_success 'B: accept and fixup committer with no name' '
+ git fast-import <input &&
+ out=$(git fsck) &&
+ echo "$out" &&
+ test -z "$out"
+'
+git update-ref -d refs/heads/empty-committer-2 || true
+
+git gc 2>/dev/null >/dev/null
+git prune 2>/dev/null >/dev/null
+
+cat >input <<INPUT_END
+commit refs/heads/invalid-committer
+committer Name email> $GIT_COMMITTER_DATE
+data <<COMMIT
+empty commit
+COMMIT
+INPUT_END
+test_expect_success 'B: fail on invalid committer (1)' '
+ test_must_fail git fast-import <input
+'
+git update-ref -d refs/heads/invalid-committer || true
+
+cat >input <<INPUT_END
+commit refs/heads/invalid-committer
+committer Name <e<mail> $GIT_COMMITTER_DATE
+data <<COMMIT
+empty commit
+COMMIT
+INPUT_END
+test_expect_success 'B: fail on invalid committer (2)' '
+ test_must_fail git fast-import <input
+'
+git update-ref -d refs/heads/invalid-committer || true
+
+cat >input <<INPUT_END
+commit refs/heads/invalid-committer
+committer Name <email>> $GIT_COMMITTER_DATE
+data <<COMMIT
+empty commit
+COMMIT
+INPUT_END
+test_expect_success 'B: fail on invalid committer (3)' '
+ test_must_fail git fast-import <input
+'
+git update-ref -d refs/heads/invalid-committer || true
+
+cat >input <<INPUT_END
+commit refs/heads/invalid-committer
+committer Name <email $GIT_COMMITTER_DATE
+data <<COMMIT
+empty commit
+COMMIT
+INPUT_END
+test_expect_success 'B: fail on invalid committer (4)' '
+ test_must_fail git fast-import <input
+'
+git update-ref -d refs/heads/invalid-committer || true
+
+cat >input <<INPUT_END
+commit refs/heads/invalid-committer
+committer Name<email> $GIT_COMMITTER_DATE
+data <<COMMIT
+empty commit
+COMMIT
+INPUT_END
+test_expect_success 'B: fail on invalid committer (5)' '
+ test_must_fail git fast-import <input
+'
+git update-ref -d refs/heads/invalid-committer || true
+
###
### series C
###
'test 1 = `git rev-list J | wc -l` &&
test 0 = `git ls-tree J | wc -l`'
+cat >input <<INPUT_END
+reset refs/heads/J2
+
+tag wrong_tag
+from refs/heads/J2
+data <<EOF
+Tag branch that was reset.
+EOF
+INPUT_END
+test_expect_success \
+ 'J: tag must fail on empty branch' \
+ 'test_must_fail git fast-import <input'
###
### series K
###
git diff-tree --abbrev --raw L^ L >output &&
test_cmp expect output'
+cat >input <<INPUT_END
+blob
+mark :1
+data <<EOF
+the data
+EOF
+
+commit refs/heads/L2
+committer C O Mitter <committer@example.com> 1112912473 -0700
+data <<COMMIT
+init L2
+COMMIT
+M 644 :1 a/b/c
+M 644 :1 a/b/d
+M 644 :1 a/e/f
+
+commit refs/heads/L2
+committer C O Mitter <committer@example.com> 1112912473 -0700
+data <<COMMIT
+update L2
+COMMIT
+C a g
+C a/e g/b
+M 644 :1 g/b/h
+INPUT_END
+
+cat <<EOF >expect
+g/b/f
+g/b/h
+EOF
+
+test_expect_success \
+ 'L: nested tree copy does not corrupt deltas' \
+ 'git fast-import <input &&
+ git ls-tree L2 g/b/ >tmp &&
+ cat tmp | cut -f 2 >actual &&
+ test_cmp expect actual &&
+ git fsck `git rev-parse L2`'
+
+git update-ref -d refs/heads/L2
+
###
### series M
###
M 040000 $subdir file3/
INPUT_END'
+ test_expect_success \
+ 'N: reject foo/ syntax in copy source' \
+ 'test_must_fail git fast-import <<-INPUT_END
+ commit refs/heads/N5C
+ committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+ data <<COMMIT
+ copy with invalid syntax
+ COMMIT
+
+ from refs/heads/branch^0
+ C file2/ file3
+ INPUT_END'
+
+ test_expect_success \
+ 'N: reject foo/ syntax in rename source' \
+ 'test_must_fail git fast-import <<-INPUT_END
+ commit refs/heads/N5D
+ committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+ data <<COMMIT
+ rename with invalid syntax
+ COMMIT
+
+ from refs/heads/branch^0
+ R file2/ file3
+ INPUT_END'
+
+ test_expect_success \
+ 'N: reject foo/ syntax in ls argument' \
+ 'test_must_fail git fast-import <<-INPUT_END
+ commit refs/heads/N5E
+ committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+ data <<COMMIT
+ copy with invalid syntax
+ COMMIT
+
+ from refs/heads/branch^0
+ ls "file2/"
+ INPUT_END'
+
test_expect_success \
'N: copy to root by id and modify' \
'echo "hello, world" >expect.foo &&
'Q: verify second note for second commit' \
'git cat-file blob refs/notes/foobar:$commit2 >actual && test_cmp expect actual'
+cat >input <<EOF
+reset refs/heads/Q0
+
+commit refs/heads/note-Q0
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+data <<COMMIT
+Note for an empty branch.
+COMMIT
+
+N inline refs/heads/Q0
+data <<NOTE
+some note
+NOTE
+EOF
+test_expect_success \
+ 'Q: deny note on empty branch' \
+ 'test_must_fail git fast-import <input'
###
### series R (feature and option)
###
test_cmp expect io.marks
'
+test_expect_success 'R: feature import-marks-if-exists' '
+ rm -f io.marks &&
+ >expect &&
+
+ git fast-import --export-marks=io.marks <<-\EOF &&
+ feature import-marks-if-exists=not_io.marks
+ EOF
+ test_cmp expect io.marks &&
+
+ blob=$(echo hi | git hash-object --stdin) &&
+
+ echo ":1 $blob" >io.marks &&
+ echo ":1 $blob" >expect &&
+ echo ":2 $blob" >>expect &&
+
+ git fast-import --export-marks=io.marks <<-\EOF &&
+ feature import-marks-if-exists=io.marks
+ blob
+ mark :2
+ data 3
+ hi
+
+ EOF
+ test_cmp expect io.marks &&
+
+ echo ":3 $blob" >>expect &&
+
+ git fast-import --import-marks=io.marks \
+ --export-marks=io.marks <<-\EOF &&
+ feature import-marks-if-exists=not_io.marks
+ blob
+ mark :3
+ data 3
+ hi
+
+ EOF
+ test_cmp expect io.marks &&
+
+ >expect &&
+
+ git fast-import --import-marks-if-exists=not_io.marks \
+ --export-marks=io.marks <<-\EOF
+ feature import-marks-if-exists=io.marks
+ EOF
+ test_cmp expect io.marks
+'
+
cat >input << EOF
feature import-marks=marks.out
feature export-marks=marks.new
test_cmp marks.out marks.new'
cat >input <<EOF
-feature import-marks=nonexistant.marks
+feature import-marks=nonexistent.marks
feature export-marks=marks.new
EOF
cat >input <<EOF
-feature import-marks=nonexistant.marks
+feature import-marks=nonexistent.marks
feature export-marks=combined.marks
EOF
test_must_fail git fast-import --cat-blob-fd=-1 </dev/null
'
-test_expect_success 'R: print old blob' '
+test_expect_success NOT_MINGW 'R: print old blob' '
blob=$(echo "yes it can" | git hash-object -w --stdin) &&
cat >expect <<-EOF &&
${blob} blob 11
test_cmp expect actual
'
-test_expect_success 'R: in-stream cat-blob-fd not respected' '
+test_expect_success NOT_MINGW 'R: in-stream cat-blob-fd not respected' '
echo hello >greeting &&
blob=$(git hash-object -w greeting) &&
cat >expect <<-EOF &&
test_cmp expect actual.1
'
-test_expect_success 'R: print new blob' '
+test_expect_success NOT_MINGW 'R: print new blob' '
blob=$(echo "yep yep yep" | git hash-object --stdin) &&
cat >expect <<-EOF &&
${blob} blob 12
test_cmp expect actual
'
-test_expect_success 'R: print new blob by sha1' '
+test_expect_success NOT_MINGW 'R: print new blob by sha1' '
blob=$(echo "a new blob named by sha1" | git hash-object --stdin) &&
cat >expect <<-EOF &&
${blob} blob 25
test_cmp empty output
'
+test_expect_success 'R: feature done means terminating "done" is mandatory' '
+ echo feature done | test_must_fail git fast-import &&
+ test_must_fail git fast-import --done </dev/null
+'
+
+test_expect_success 'R: terminating "done" with trailing gibberish is ok' '
+ git fast-import <<-\EOF &&
+ feature done
+ done
+ trailing gibberish
+ EOF
+ git fast-import <<-\EOF
+ done
+ more trailing gibberish
+ EOF
+'
+
+test_expect_success 'R: terminating "done" within commit' '
+ cat >expect <<-\EOF &&
+ OBJID
+ :000000 100644 OBJID OBJID A hello.c
+ :000000 100644 OBJID OBJID A hello2.c
+ EOF
+ git fast-import <<-EOF &&
+ commit refs/heads/done-ends
+ committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
+ data <<EOT
+ Commit terminated by "done" command
+ EOT
+ M 100644 inline hello.c
+ data <<EOT
+ Hello, world.
+ EOT
+ C hello.c hello2.c
+ done
+ EOF
+ git rev-list done-ends |
+ git diff-tree -r --stdin --root --always |
+ sed -e "s/$_x40/OBJID/g" >actual &&
+ test_cmp expect actual
+'
+
cat >input <<EOF
option git non-existing-option
EOF