1 files changed, 240 insertions, 61 deletions

diff --git a/fast-import.c b/fast-import.c
index ff56ea2891..970d8470ed 100644
--- a/fast-import.c
+++ b/fast-import.c
@@ -132,14 +132,17 @@ 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 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;
+
   comment ::= '#' not_lf* lf;
   not_lf  ::= # Any byte that is not ASCII newline (LF);
 */
@@ -156,6 +159,7 @@ 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)
@@ -267,7 +271,7 @@ struct hash_list
 typedef enum {
 	WHENSPEC_RAW = 1,
 	WHENSPEC_RFC2822,
-	WHENSPEC_NOW,
+	WHENSPEC_NOW
 } whenspec_type;
 
 struct recent_command
@@ -361,7 +365,14 @@ static uintmax_t next_mark;
 static struct strbuf new_data = STRBUF_INIT;
 static int seen_data_command;
 
+/* 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 write_branch_report(FILE *rpt, struct branch *b)
 {
@@ -500,6 +511,32 @@ 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 +576,17 @@ 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;
 }
 
@@ -980,29 +1012,6 @@ static void cycle_packfile(void)
 	start_packfile();
 }
 
-static size_t encode_header(
-	enum object_type type,
-	uintmax_t size,
-	unsigned char *hdr)
-{
-	int n = 1;
-	unsigned char c;
-
-	if (type < OBJ_COMMIT || type > OBJ_REF_DELTA)
-		die("bad type %d", type);
-
-	c = (type << 4) | (size & 15);
-	size >>= 4;
-	while (size) {
-		*hdr++ = c | 0x80;
-		c = size & 0x7f;
-		size >>= 7;
-		n++;
-	}
-	*hdr = c;
-	return n;
-}
-
 static int store_object(
 	enum object_type type,
 	struct strbuf *dat,
@@ -1103,7 +1112,7 @@ static int store_object(
 		delta_count_by_type[type]++;
 		e->depth = last->depth + 1;
 
-		hdrlen = encode_header(OBJ_OFS_DELTA, deltalen, hdr);
+		hdrlen = encode_in_pack_object_header(OBJ_OFS_DELTA, deltalen, hdr);
 		sha1write(pack_file, hdr, hdrlen);
 		pack_size += hdrlen;
 
@@ -1114,7 +1123,7 @@ static int store_object(
 		pack_size += sizeof(hdr) - pos;
 	} else {
 		e->depth = 0;
-		hdrlen = encode_header(type, dat->len, hdr);
+		hdrlen = encode_in_pack_object_header(type, dat->len, hdr);
 		sha1write(pack_file, hdr, hdrlen);
 		pack_size += hdrlen;
 	}
@@ -1188,7 +1197,7 @@ static void stream_blob(uintmax_t len, unsigned char *sha1out, uintmax_t mark)
 	memset(&s, 0, sizeof(s));
 	deflateInit(&s, pack_compression_level);
 
-	hdrlen = encode_header(OBJ_BLOB, len, out_buf);
+	hdrlen = encode_in_pack_object_header(OBJ_BLOB, len, out_buf);
 	if (out_sz <= hdrlen)
 		die("impossibly large object header");
 
@@ -1460,6 +1469,20 @@ 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");
+	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,
@@ -1467,7 +1490,7 @@ 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;
@@ -1482,9 +1505,12 @@ 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
@@ -1537,7 +1563,7 @@ 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;
@@ -1548,9 +1574,20 @@ 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)
@@ -1587,7 +1624,7 @@ 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;
@@ -1598,9 +1635,12 @@ 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))
@@ -1689,7 +1729,7 @@ 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 {
@@ -1796,7 +1836,7 @@ static int read_next_command(void)
 		return EOF;
 	}
 
-	do {
+	for (;;) {
 		if (unread_command_buf) {
 			unread_command_buf = 0;
 		} else {
@@ -1829,9 +1869,14 @@ 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)
@@ -2154,6 +2199,7 @@ 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;
@@ -2185,6 +2231,12 @@ 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",
@@ -2199,25 +2251,34 @@ 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);
 }
 
@@ -2276,6 +2337,13 @@ 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,
@@ -2689,14 +2757,95 @@ 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);
+	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 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();
 }
 
@@ -2730,6 +2879,7 @@ 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;
 }
 
@@ -2745,21 +2895,39 @@ 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)
@@ -2815,6 +2983,8 @@ static int parse_one_feature(const char *feature, int from_stream)
 		option_import_marks(feature + 13, from_stream);
 	} else if (!prefixcmp(feature, "export-marks=")) {
 		option_export_marks(feature + 13);
+	} else if (!strcmp(feature, "cat-blob")) {
+		; /* Don't die - this feature is supported */
 	} else if (!prefixcmp(feature, "relative-marks")) {
 		relative_marks_paths = 1;
 	} else if (!prefixcmp(feature, "no-relative-marks")) {
@@ -2893,7 +3063,7 @@ static int git_pack_config(const char *k, const char *v, void *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)
 {
@@ -2911,6 +3081,11 @@ 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)
@@ -2953,6 +3128,7 @@ 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();
@@ -2974,6 +3150,9 @@ 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 */