1 files changed, 529 insertions, 127 deletions

diff --git a/fast-import.c b/fast-import.c
index 309f2c58a2..8d8ea3c45c 100644
--- a/fast-import.c
+++ b/fast-import.c
@@ -24,10 +24,12 @@ Format of STDIN stream:
     commit_msg
     ('from' sp committish lf)?
     ('merge' sp committish lf)*
-    file_change*
+    (file_change | ls)*
     lf?;
   commit_msg ::= data;
 
+  ls ::= 'ls' sp '"' quoted(path) '"' lf;
+
   file_change ::= file_clr
     | file_del
     | file_rnm
@@ -132,14 +134,19 @@ Format of STDIN stream:
   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.
+     # note: comments, ls and cat requests 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).
      #
+
+  cat_blob ::= 'cat-blob' sp (hexsha1 | idnum) lf;
+  ls_tree  ::= 'ls' sp (hexsha1 | idnum) sp path_str lf;
+
   comment ::= '#' not_lf* lf;
   not_lf  ::= # Any byte that is not ASCII newline (LF);
 */
@@ -156,14 +163,19 @@ Format of STDIN stream:
 #include "csum-file.h"
 #include "quote.h"
 #include "exec_cmd.h"
+#include "dir.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
-{
+/*
+ * 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,
@@ -171,16 +183,14 @@ struct object_entry
 		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];
@@ -188,57 +198,49 @@ struct mark_set
 	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;
@@ -250,16 +252,14 @@ struct branch
 	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];
 };
@@ -267,11 +267,10 @@ struct hash_list
 typedef enum {
 	WHENSPEC_RAW = 1,
 	WHENSPEC_RFC2822,
-	WHENSPEC_NOW,
+	WHENSPEC_NOW
 } whenspec_type;
 
-struct recent_command
-{
+struct recent_command {
 	struct recent_command *prev;
 	struct recent_command *next;
 	char *buf;
@@ -280,7 +279,6 @@ struct recent_command
 /* 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;
@@ -291,6 +289,7 @@ static uintmax_t marks_set_count;
 static uintmax_t object_count_by_type[1 << TYPE_BITS];
 static uintmax_t duplicate_count_by_type[1 << TYPE_BITS];
 static uintmax_t delta_count_by_type[1 << TYPE_BITS];
+static 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;
@@ -311,6 +310,7 @@ static unsigned int atom_cnt;
 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;
@@ -325,6 +325,7 @@ static struct mark_set *marks;
 static const char *export_marks_file;
 static const char *import_marks_file;
 static int import_marks_file_from_stream;
+static int import_marks_file_ignore_missing;
 static int relative_marks_paths;
 
 /* Our last blob */
@@ -360,8 +361,17 @@ static unsigned int cmd_save = 100;
 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;
+
+/* Where to write output of cat-blob commands */
+static int cat_blob_fd = STDOUT_FILENO;
 
 static void parse_argv(void);
+static void parse_cat_blob(void);
+static void parse_ls(struct branch *b);
 
 static void write_branch_report(FILE *rpt, struct branch *b)
 {
@@ -500,6 +510,32 @@ static NORETURN void die_nicely(const char *err, va_list params)
 	exit(128);
 }
 
+#ifndef SIGUSR1	/* Windows, for example */
+
+static void set_checkpoint_signal(void)
+{
+}
+
+#else
+
+static void checkpoint_signal(int signo)
+{
+	checkpoint_requested = 1;
+}
+
+static void set_checkpoint_signal(void)
+{
+	struct sigaction sa;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_handler = checkpoint_signal;
+	sigemptyset(&sa.sa_mask);
+	sa.sa_flags = SA_RESTART;
+	sigaction(SIGUSR1, &sa, NULL);
+}
+
+#endif
+
 static void alloc_objects(unsigned int cnt)
 {
 	struct object_entry_pool *b;
@@ -539,22 +575,17 @@ static struct object_entry *insert_object(unsigned char *sha1)
 {
 	unsigned int h = sha1[0] << 8 | sha1[1];
 	struct object_entry *e = object_table[h];
-	struct object_entry *p = NULL;
 
 	while (e) {
 		if (!hashcmp(sha1, e->idx.sha1))
 			return e;
-		p = e;
 		e = e->next;
 	}
 
 	e = new_object(sha1);
-	e->next = NULL;
+	e->next = object_table[h];
 	e->idx.offset = 0;
-	if (p)
-		p->next = e;
-	else
-		object_table[h] = e;
+	object_table[h] = e;
 	return e;
 }
 
@@ -691,13 +722,8 @@ static struct branch *new_branch(const char *name)
 
 	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);
@@ -839,6 +865,7 @@ static void start_packfile(void)
 	p = xcalloc(1, sizeof(*p) + strlen(tmpfile) + 2);
 	strcpy(p->pack_name, tmpfile);
 	p->pack_fd = pack_fd;
+	p->do_not_close = 1;
 	pack_file = sha1fd(pack_fd, p->pack_name);
 
 	hdr.hdr_signature = htonl(PACK_SIGNATURE);
@@ -872,7 +899,7 @@ static const char *create_index(void)
 	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;
 }
@@ -993,7 +1020,7 @@ static int store_object(
 	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;
@@ -1019,6 +1046,7 @@ static int store_object(
 	}
 
 	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);
@@ -1026,7 +1054,7 @@ static int store_object(
 		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;
@@ -1034,11 +1062,11 @@ static int store_object(
 		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)
@@ -1054,14 +1082,14 @@ static int store_object(
 			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);
 		}
 	}
 
@@ -1139,7 +1167,7 @@ static void stream_blob(uintmax_t len, unsigned char *sha1out, uintmax_t mark)
 	off_t offset;
 	git_SHA_CTX c;
 	git_SHA_CTX pack_file_ctx;
-	z_stream s;
+	git_zstream s;
 	int status = Z_OK;
 
 	/* Determine if we should auto-checkpoint. */
@@ -1163,7 +1191,7 @@ static void stream_blob(uintmax_t len, unsigned char *sha1out, uintmax_t mark)
 	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)
@@ -1185,7 +1213,7 @@ static void stream_blob(uintmax_t len, unsigned char *sha1out, uintmax_t mark)
 			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;
@@ -1204,7 +1232,7 @@ static void stream_blob(uintmax_t len, unsigned char *sha1out, uintmax_t mark)
 			die("unexpected deflate failure: %d", status);
 		}
 	}
-	deflateEnd(&s);
+	git_deflate_end(&s);
 	git_SHA1_Final(sha1, &c);
 
 	if (sha1out)
@@ -1390,8 +1418,9 @@ static void mktree(struct tree_content *t, int v, struct strbuf *b)
 		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);
 	}
 }
@@ -1401,7 +1430,7 @@ static void store_tree(struct tree_entry *root)
 	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;
@@ -1411,7 +1440,8 @@ static void store_tree(struct tree_entry *root)
 			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;
@@ -1437,6 +1467,21 @@ static void store_tree(struct tree_entry *root)
 	t->entry_count -= del;
 }
 
+static void tree_content_replace(
+	struct tree_entry *root,
+	const unsigned char *sha1,
+	const uint16_t mode,
+	struct tree_content *newtree)
+{
+	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);
+	root->tree = newtree;
+}
+
 static int tree_content_set(
 	struct tree_entry *root,
 	const char *p,
@@ -1444,7 +1489,7 @@ static int tree_content_set(
 	const uint16_t mode,
 	struct tree_content *subtree)
 {
-	struct tree_content *t = root->tree;
+	struct tree_content *t;
 	const char *slash1;
 	unsigned int i, n;
 	struct tree_entry *e;
@@ -1459,9 +1504,12 @@ static int tree_content_set(
 	if (!slash1 && !S_ISDIR(mode) && subtree)
 		die("Non-directories cannot have subtrees");
 
+	if (!root->tree)
+		load_tree(root);
+	t = root->tree;
 	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 (e->name->str_len == n && !strncmp_icase(p, e->name->str_dat, n)) {
 			if (!slash1) {
 				if (!S_ISDIR(mode)
 						&& e->versions[1].mode == mode
@@ -1472,6 +1520,23 @@ static int tree_content_set(
 				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;
 			}
@@ -1514,7 +1579,7 @@ static int tree_content_remove(
 	const char *p,
 	struct tree_entry *backup_leaf)
 {
-	struct tree_content *t = root->tree;
+	struct tree_content *t;
 	const char *slash1;
 	unsigned int i, n;
 	struct tree_entry *e;
@@ -1525,9 +1590,20 @@ static int tree_content_remove(
 	else
 		n = strlen(p);
 
+	if (!root->tree)
+		load_tree(root);
+	t = root->tree;
 	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 (e->name->str_len == n && !strncmp_icase(p, e->name->str_dat, n)) {
+			if (slash1 && !S_ISDIR(e->versions[1].mode))
+				/*
+				 * If p names a file in some subdirectory, and a
+				 * file or symlink matching the name of the
+				 * parent directory of p exists, then p cannot
+				 * exist and need not be deleted.
+				 */
+				return 1;
 			if (!slash1 || !S_ISDIR(e->versions[1].mode))
 				goto del_entry;
 			if (!e->tree)
@@ -1564,7 +1640,7 @@ static int tree_content_get(
 	const char *p,
 	struct tree_entry *leaf)
 {
-	struct tree_content *t = root->tree;
+	struct tree_content *t;
 	const char *slash1;
 	unsigned int i, n;
 	struct tree_entry *e;
@@ -1575,9 +1651,12 @@ static int tree_content_get(
 	else
 		n = strlen(p);
 
+	if (!root->tree)
+		load_tree(root);
+	t = root->tree;
 	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 (e->name->str_len == n && !strncmp_icase(p, e->name->str_dat, n)) {
 			if (!slash1) {
 				memcpy(leaf, e, sizeof(*leaf));
 				if (e->tree && is_null_sha1(e->versions[1].sha1))
@@ -1666,7 +1745,7 @@ static void dump_marks_helper(FILE *f,
 	if (m->shift) {
 		for (k = 0; k < 1024; k++) {
 			if (m->data.sets[k])
-				dump_marks_helper(f, (base + k) << m->shift,
+				dump_marks_helper(f, base + (k << m->shift),
 					m->data.sets[k]);
 		}
 	} else {
@@ -1732,7 +1811,11 @@ static void read_marks(void)
 {
 	char line[512];
 	FILE *f = fopen(import_marks_file, "r");
-	if (!f)
+	if (f)
+		;
+	else if (import_marks_file_ignore_missing && errno == ENOENT)
+		return; /* Marks file does not exist */
+	else
 		die_errno("cannot read '%s'", import_marks_file);
 	while (fgets(line, sizeof(line), f)) {
 		uintmax_t mark;
@@ -1773,7 +1856,7 @@ static int read_next_command(void)
 		return EOF;
 	}
 
-	do {
+	for (;;) {
 		if (unread_command_buf) {
 			unread_command_buf = 0;
 		} else {
@@ -1806,9 +1889,14 @@ static int read_next_command(void)
 			rc->prev->next = rc;
 			cmd_tail = rc;
 		}
-	} while (command_buf.buf[0] == '#');
-
-	return 0;
+		if (!prefixcmp(command_buf.buf, "cat-blob ")) {
+			parse_cat_blob();
+			continue;
+		}
+		if (command_buf.buf[0] == '#')
+			continue;
+		return 0;
+	}
 }
 
 static void skip_optional_lf(void)
@@ -1903,32 +1991,41 @@ static int validate_raw_date(const char *src, char *result, int maxlen)
 
 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;
@@ -2131,6 +2228,7 @@ static void file_change_m(struct branch *b)
 	case S_IFREG | 0644:
 	case S_IFREG | 0755:
 	case S_IFLNK:
+	case S_IFDIR:
 	case S_IFGITLINK:
 		/* ok */
 		break;
@@ -2162,6 +2260,12 @@ static void file_change_m(struct branch *b)
 		p = uq.buf;
 	}
 
+	/* Git does not track empty, non-toplevel directories. */
+	if (S_ISDIR(mode) && !memcmp(sha1, EMPTY_TREE_SHA1_BIN, 20) && *p) {
+		tree_content_remove(&b->branch_tree, p, NULL);
+		return;
+	}
+
 	if (S_ISGITLINK(mode)) {
 		if (inline_data)
 			die("Git links cannot be specified 'inline': %s",
@@ -2176,25 +2280,34 @@ static void file_change_m(struct branch *b)
 		 * another repository.
 		 */
 	} else if (inline_data) {
+		if (S_ISDIR(mode))
+			die("Directories cannot be specified 'inline': %s",
+				command_buf.buf);
 		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);
+		enum object_type expected = S_ISDIR(mode) ?
+						OBJ_TREE: OBJ_BLOB;
+		enum object_type type = oe ? oe->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);
+			die("%s not found: %s",
+					S_ISDIR(mode) ?  "Tree" : "Blob",
+					command_buf.buf);
+		if (type != expected)
+			die("Not a %s (actually a %s): %s",
+				typename(expected), typename(type),
+				command_buf.buf);
 	}
 
+	if (!*p) {
+		tree_content_replace(&b->branch_tree, sha1, mode, NULL);
+		return;
+	}
 	tree_content_set(&b->branch_tree, p, sha1, mode, NULL);
 }
 
@@ -2253,6 +2366,13 @@ static void file_change_cr(struct branch *b, int rename)
 		tree_content_get(&b->branch_tree, s, &leaf);
 	if (!leaf.versions[1].mode)
 		die("Path %s not in branch", s);
+	if (!*d) {	/* C "path/to/subdir" "" */
+		tree_content_replace(&b->branch_tree,
+			leaf.versions[1].sha1,
+			leaf.versions[1].mode,
+			leaf.tree);
+		return;
+	}
 	tree_content_set(&b->branch_tree, d,
 		leaf.versions[1].sha1,
 		leaf.versions[1].mode,
@@ -2291,6 +2411,8 @@ static void note_change_n(struct branch *b, unsigned char old_fanout)
 	/* <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);
@@ -2518,6 +2640,8 @@ static void parse_new_commit(void)
 			note_change_n(b, prev_fanout);
 		else if (!strcmp("deleteall", command_buf.buf))
 			file_change_deleteall(b);
+		else if (!prefixcmp(command_buf.buf, "ls "))
+			parse_ls(b);
 		else {
 			unread_command_buf = 1;
 			break;
@@ -2590,6 +2714,8 @@ static void parse_new_tag(void)
 	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 == ':') {
@@ -2599,13 +2725,13 @@ static void parse_new_tag(void)
 		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();
@@ -2666,14 +2792,247 @@ static void parse_reset_branch(void)
 		unread_command_buf = 1;
 }
 
-static void parse_checkpoint(void)
+static void cat_blob_write(const char *buf, unsigned long size)
+{
+	if (write_in_full(cat_blob_fd, buf, size) != size)
+		die_errno("Write to frontend failed");
+}
+
+static void cat_blob(struct object_entry *oe, unsigned char sha1[20])
+{
+	struct strbuf line = STRBUF_INIT;
+	unsigned long size;
+	enum object_type type = 0;
+	char *buf;
+
+	if (!oe || oe->pack_id == MAX_PACK_ID) {
+		buf = read_sha1_file(sha1, &type, &size);
+	} else {
+		type = oe->type;
+		buf = gfi_unpack_entry(oe, &size);
+	}
+
+	/*
+	 * Output based on batch_one_object() from cat-file.c.
+	 */
+	if (type <= 0) {
+		strbuf_reset(&line);
+		strbuf_addf(&line, "%s missing\n", sha1_to_hex(sha1));
+		cat_blob_write(line.buf, line.len);
+		strbuf_release(&line);
+		free(buf);
+		return;
+	}
+	if (!buf)
+		die("Can't read object %s", sha1_to_hex(sha1));
+	if (type != OBJ_BLOB)
+		die("Object %s is a %s but a blob was expected.",
+		    sha1_to_hex(sha1), typename(type));
+	strbuf_reset(&line);
+	strbuf_addf(&line, "%s %s %lu\n", sha1_to_hex(sha1),
+						typename(type), size);
+	cat_blob_write(line.buf, line.len);
+	strbuf_release(&line);
+	cat_blob_write(buf, size);
+	cat_blob_write("\n", 1);
+	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)
 {
+	const char *p;
+	struct object_entry *oe = oe;
+	unsigned char sha1[20];
+
+	/* cat-blob SP <object> LF */
+	p = command_buf.buf + strlen("cat-blob ");
+	if (*p == ':') {
+		char *x;
+		oe = find_mark(strtoumax(p + 1, &x, 10));
+		if (x == p + 1)
+			die("Invalid mark: %s", command_buf.buf);
+		if (!oe)
+			die("Unknown mark: %s", command_buf.buf);
+		if (*x)
+			die("Garbage after mark: %s", command_buf.buf);
+		hashcpy(sha1, oe->idx.sha1);
+	} else {
+		if (get_sha1_hex(p, sha1))
+			die("Invalid SHA1: %s", command_buf.buf);
+		if (p[40])
+			die("Garbage after SHA1: %s", command_buf.buf);
+		oe = find_object(sha1);
+	}
+
+	cat_blob(oe, sha1);
+}
+
+static struct object_entry *dereference(struct object_entry *oe,
+					unsigned char sha1[20])
+{
+	unsigned long size;
+	char *buf = NULL;
+	if (!oe) {
+		enum object_type type = sha1_object_info(sha1, NULL);
+		if (type < 0)
+			die("object not found: %s", sha1_to_hex(sha1));
+		/* cache it! */
+		oe = insert_object(sha1);
+		oe->type = type;
+		oe->pack_id = MAX_PACK_ID;
+		oe->idx.offset = 1;
+	}
+	switch (oe->type) {
+	case OBJ_TREE:	/* easy case. */
+		return oe;
+	case OBJ_COMMIT:
+	case OBJ_TAG:
+		break;
+	default:
+		die("Not a treeish: %s", command_buf.buf);
+	}
+
+	if (oe->pack_id != MAX_PACK_ID) {	/* in a pack being written */
+		buf = gfi_unpack_entry(oe, &size);
+	} else {
+		enum object_type unused;
+		buf = read_sha1_file(sha1, &unused, &size);
+	}
+	if (!buf)
+		die("Can't load object %s", sha1_to_hex(sha1));
+
+	/* Peel one layer. */
+	switch (oe->type) {
+	case OBJ_TAG:
+		if (size < 40 + strlen("object ") ||
+		    get_sha1_hex(buf + strlen("object "), sha1))
+			die("Invalid SHA1 in tag: %s", command_buf.buf);
+		break;
+	case OBJ_COMMIT:
+		if (size < 40 + strlen("tree ") ||
+		    get_sha1_hex(buf + strlen("tree "), sha1))
+			die("Invalid SHA1 in commit: %s", command_buf.buf);
+	}
+
+	free(buf);
+	return find_object(sha1);
+}
+
+static struct object_entry *parse_treeish_dataref(const char **p)
+{
+	unsigned char sha1[20];
+	struct object_entry *e;
+
+	if (**p == ':') {	/* <mark> */
+		char *endptr;
+		e = find_mark(strtoumax(*p + 1, &endptr, 10));
+		if (endptr == *p + 1)
+			die("Invalid mark: %s", command_buf.buf);
+		if (!e)
+			die("Unknown mark: %s", command_buf.buf);
+		*p = endptr;
+		hashcpy(sha1, e->idx.sha1);
+	} else {	/* <sha1> */
+		if (get_sha1_hex(*p, sha1))
+			die("Invalid SHA1: %s", command_buf.buf);
+		e = find_object(sha1);
+		*p += 40;
+	}
+
+	while (!e || e->type != OBJ_TREE)
+		e = dereference(e, sha1);
+	return e;
+}
+
+static void print_ls(int mode, const unsigned char *sha1, const char *path)
+{
+	static struct strbuf line = STRBUF_INIT;
+
+	/* See show_tree(). */
+	const char *type =
+		S_ISGITLINK(mode) ? commit_type :
+		S_ISDIR(mode) ? tree_type :
+		blob_type;
+
+	if (!mode) {
+		/* missing SP path LF */
+		strbuf_reset(&line);
+		strbuf_addstr(&line, "missing ");
+		quote_c_style(path, &line, NULL, 0);
+		strbuf_addch(&line, '\n');
+	} else {
+		/* mode SP type SP object_name TAB path LF */
+		strbuf_reset(&line);
+		strbuf_addf(&line, "%06o %s %s\t",
+				mode & ~NO_DELTA, type, sha1_to_hex(sha1));
+		quote_c_style(path, &line, NULL, 0);
+		strbuf_addch(&line, '\n');
+	}
+	cat_blob_write(line.buf, line.len);
+}
+
+static void parse_ls(struct branch *b)
+{
+	const char *p;
+	struct tree_entry *root = NULL;
+	struct tree_entry leaf = {NULL};
+
+	/* ls SP (<treeish> SP)? <path> */
+	p = command_buf.buf + strlen("ls ");
+	if (*p == '"') {
+		if (!b)
+			die("Not in a commit: %s", command_buf.buf);
+		root = &b->branch_tree;
+	} else {
+		struct object_entry *e = parse_treeish_dataref(&p);
+		root = new_tree_entry();
+		hashcpy(root->versions[1].sha1, e->idx.sha1);
+		load_tree(root);
+		if (*p++ != ' ')
+			die("Missing space after tree-ish: %s", command_buf.buf);
+	}
+	if (*p == '"') {
+		static struct strbuf uq = STRBUF_INIT;
+		const char *endp;
+		strbuf_reset(&uq);
+		if (unquote_c_style(&uq, p, &endp))
+			die("Invalid path: %s", command_buf.buf);
+		if (*endp)
+			die("Garbage after path in: %s", command_buf.buf);
+		p = uq.buf;
+	}
+	tree_content_get(root, p, &leaf);
+	/*
+	 * A directory in preparation would have a sha1 of zero
+	 * until it is saved.  Save, for simplicity.
+	 */
+	if (S_ISDIR(leaf.versions[1].mode))
+		store_tree(&leaf);
+
+	print_ls(leaf.versions[1].mode, leaf.versions[1].sha1, p);
+	if (!b || root != &b->branch_tree)
+		release_tree_entry(root);
+}
+
+static void checkpoint(void)
+{
+	checkpoint_requested = 0;
 	if (object_count) {
 		cycle_packfile();
 		dump_branches();
 		dump_tags();
 		dump_marks();
 	}
+}
+
+static void parse_checkpoint(void)
+{
+	checkpoint_requested = 1;
 	skip_optional_lf();
 }
 
@@ -2695,7 +3054,8 @@ static char* make_fast_import_path(const char *path)
 	return strbuf_detach(&abs_path, NULL);
 }
 
-static void option_import_marks(const char *marks, int from_stream)
+static void option_import_marks(const char *marks,
+					int from_stream, int ignore_missing)
 {
 	if (import_marks_file) {
 		if (from_stream)
@@ -2707,7 +3067,9 @@ static void option_import_marks(const char *marks, int from_stream)
 	}
 
 	import_marks_file = make_fast_import_path(marks);
+	safe_create_leading_directories_const(import_marks_file);
 	import_marks_file_from_stream = from_stream;
+	import_marks_file_ignore_missing = ignore_missing;
 }
 
 static void option_date_format(const char *fmt)
@@ -2722,21 +3084,39 @@ static void option_date_format(const char *fmt)
 		die("unknown --date-format argument %s", fmt);
 }
 
+static unsigned long ulong_arg(const char *option, const char *arg)
+{
+	char *endptr;
+	unsigned long rv = strtoul(arg, &endptr, 0);
+	if (strchr(arg, '-') || endptr == arg || *endptr)
+		die("%s: argument must be a non-negative integer", option);
+	return rv;
+}
+
 static void option_depth(const char *depth)
 {
-	max_depth = strtoul(depth, NULL, 0);
+	max_depth = ulong_arg("--depth", depth);
 	if (max_depth > MAX_DEPTH)
 		die("--depth cannot exceed %u", MAX_DEPTH);
 }
 
 static void option_active_branches(const char *branches)
 {
-	max_active_branches = strtoul(branches, NULL, 0);
+	max_active_branches = ulong_arg("--active-branches", branches);
 }
 
 static void option_export_marks(const char *marks)
 {
 	export_marks_file = make_fast_import_path(marks);
+	safe_create_leading_directories_const(export_marks_file);
+}
+
+static void option_cat_blob_fd(const char *fd)
+{
+	unsigned long n = ulong_arg("--cat-blob-fd", fd);
+	if (n > (unsigned long) INT_MAX)
+		die("--cat-blob-fd cannot exceed %d", INT_MAX);
+	cat_blob_fd = (int) n;
 }
 
 static void option_export_pack_edges(const char *edges)
@@ -2789,15 +3169,24 @@ static int parse_one_feature(const char *feature, int from_stream)
 	if (!prefixcmp(feature, "date-format=")) {
 		option_date_format(feature + 12);
 	} else if (!prefixcmp(feature, "import-marks=")) {
-		option_import_marks(feature + 13, from_stream);
+		option_import_marks(feature + 13, from_stream, 0);
+	} else if (!prefixcmp(feature, "import-marks-if-exists=")) {
+		option_import_marks(feature + strlen("import-marks-if-exists="),
+					from_stream, 1);
 	} else if (!prefixcmp(feature, "export-marks=")) {
 		option_export_marks(feature + 13);
-	} else if (!prefixcmp(feature, "relative-marks")) {
+	} else if (!strcmp(feature, "cat-blob")) {
+		; /* Don't die - this feature is supported */
+	} 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 */
 	} else {
 		return 0;
 	}
@@ -2850,25 +3239,21 @@ static int git_pack_config(const char *k, const char *v, void *cb)
 		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);
 }
 
 static const char fast_import_usage[] =
-"git fast-import [--date-format=f] [--max-pack-size=n] [--big-file-threshold=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>]";
 
 static void parse_argv(void)
 {
@@ -2886,6 +3271,11 @@ static void parse_argv(void)
 		if (parse_one_feature(a + 2, 0))
 			continue;
 
+		if (!prefixcmp(a + 2, "cat-blob-fd=")) {
+			option_cat_blob_fd(a + 2 + strlen("cat-blob-fd="));
+			continue;
+		}
+
 		die("unknown option %s", a);
 	}
 	if (i != global_argc)
@@ -2906,6 +3296,7 @@ int main(int argc, const char **argv)
 		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;
@@ -2928,9 +3319,12 @@ int main(int argc, const char **argv)
 	prepare_packed_git();
 	start_packfile();
 	set_die_routine(die_nicely);
+	set_checkpoint_signal();
 	while (read_next_command() != EOF) {
 		if (!strcmp("blob", command_buf.buf))
 			parse_new_blob();
+		else if (!prefixcmp(command_buf.buf, "ls "))
+			parse_ls(NULL);
 		else if (!prefixcmp(command_buf.buf, "commit "))
 			parse_new_commit();
 		else if (!prefixcmp(command_buf.buf, "tag "))
@@ -2939,6 +3333,8 @@ int main(int argc, const char **argv)
 			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 "))
@@ -2949,12 +3345,18 @@ int main(int argc, const char **argv)
 			/* ignore non-git options*/;
 		else
 			die("Unsupported command: %s", command_buf.buf);
+
+		if (checkpoint_requested)
+			checkpoint();
 	}
 
 	/* argv hasn't been parsed yet, do so */
 	if (!seen_data_command)
 		parse_argv();
 
+	if (require_explicit_termination && feof(stdin))
+		die("stream ends early");
+
 	end_packfile();
 
 	dump_branches();
@@ -2976,10 +3378,10 @@ int main(int argc, const char **argv)
 		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);