Merge branch 'jc/mktree'

* jc/mktree:
  mktree: validate entry type in input
  mktree --batch: build more than one tree object
  mktree --missing: updated usage message and man page
  mktree --missing: allow missing objects
  t1010: add mktree test
  mktree: do not barf on a submodule commit
  builtin-mktree.c: use a helper function to handle one line of input
  mktree: use parse-options
  build-in git-mktree

Documentation/git-mktree.txt

@@ -8,12 +8,13 @@ git-mktree - Build a tree-object from ls-tree formatted text
 
 SYNOPSIS
 --------
-'git mktree' [-z]
+'git mktree' [-z] [--missing] [--batch]
 
 DESCRIPTION
 -----------
-Reads standard input in non-recursive `ls-tree` output format,
-and creates a tree object.  The object name of the tree object
+Reads standard input in non-recursive `ls-tree` output format, and creates
+a tree object.  The order of the tree entries is normalised by mktree so
+pre-sorting the input is not required.  The object name of the tree object
 built is written to the standard output.
 
 OPTIONS
@@ -21,6 +22,18 @@ OPTIONS
 -z::
 	Read the NUL-terminated `ls-tree -z` output instead.
 
+--missing::
+	Allow missing objects.  The default behaviour (without this option)
+	is to verify that each tree entry's sha1 identifies an existing
+	object.  This option has no effect on the treatment of gitlink entries
+	(aka "submodules") which are always allowed to be missing.
+
+--batch::
+	Allow building of more than one tree object before exiting.  Each
+	tree is separated by as single blank line. The final new-line is
+	optional.  Note - if the '-z' option is used, lines are terminated
+	with NUL.
+
 Author
 ------
 Written by Junio C Hamano <gitster@pobox.com>

Makefile

@@ -336,7 +336,6 @@ PROGRAMS += git-index-pack$X
 PROGRAMS += git-merge-index$X
 PROGRAMS += git-merge-tree$X
 PROGRAMS += git-mktag$X
-PROGRAMS += git-mktree$X
 PROGRAMS += git-pack-redundant$X
 PROGRAMS += git-patch-id$X
 PROGRAMS += git-shell$X
@@ -590,6 +589,7 @@ BUILTIN_OBJS += builtin-merge-base.o
 BUILTIN_OBJS += builtin-merge-file.o
 BUILTIN_OBJS += builtin-merge-ours.o
 BUILTIN_OBJS += builtin-merge-recursive.o
+BUILTIN_OBJS += builtin-mktree.o
 BUILTIN_OBJS += builtin-mv.o
 BUILTIN_OBJS += builtin-name-rev.o
 BUILTIN_OBJS += builtin-pack-objects.o

builtin-mktree.c

@@ -0,0 +1,190 @@
+/*
+ * GIT - the stupid content tracker
+ *
+ * Copyright (c) Junio C Hamano, 2006, 2009
+ */
+#include "builtin.h"
+#include "quote.h"
+#include "tree.h"
+#include "parse-options.h"
+
+static struct treeent {
+	unsigned mode;
+	unsigned char sha1[20];
+	int len;
+	char name[FLEX_ARRAY];
+} **entries;
+static int alloc, used;
+
+static void append_to_tree(unsigned mode, unsigned char *sha1, char *path)
+{
+	struct treeent *ent;
+	int len = strlen(path);
+	if (strchr(path, '/'))
+		die("path %s contains slash", path);
+
+	if (alloc <= used) {
+		alloc = alloc_nr(used);
+		entries = xrealloc(entries, sizeof(*entries) * alloc);
+	}
+	ent = entries[used++] = xmalloc(sizeof(**entries) + len + 1);
+	ent->mode = mode;
+	ent->len = len;
+	hashcpy(ent->sha1, sha1);
+	memcpy(ent->name, path, len+1);
+}
+
+static int ent_compare(const void *a_, const void *b_)
+{
+	struct treeent *a = *(struct treeent **)a_;
+	struct treeent *b = *(struct treeent **)b_;
+	return base_name_compare(a->name, a->len, a->mode,
+				 b->name, b->len, b->mode);
+}
+
+static void write_tree(unsigned char *sha1)
+{
+	struct strbuf buf;
+	size_t size;
+	int i;
+
+	qsort(entries, used, sizeof(*entries), ent_compare);
+	for (size = i = 0; i < used; i++)
+		size += 32 + entries[i]->len;
+
+	strbuf_init(&buf, size);
+	for (i = 0; i < used; i++) {
+		struct treeent *ent = entries[i];
+		strbuf_addf(&buf, "%o %s%c", ent->mode, ent->name, '\0');
+		strbuf_add(&buf, ent->sha1, 20);
+	}
+
+	write_sha1_file(buf.buf, buf.len, tree_type, sha1);
+}
+
+static const char *mktree_usage[] = {
+	"git mktree [-z] [--missing] [--batch]",
+	NULL
+};
+
+static void mktree_line(char *buf, size_t len, int line_termination, int allow_missing)
+{
+	char *ptr, *ntr;
+	unsigned mode;
+	enum object_type mode_type; /* object type derived from mode */
+	enum object_type obj_type; /* object type derived from sha */
+	char *path;
+	unsigned char sha1[20];
+
+	ptr = buf;
+	/*
+	 * Read non-recursive ls-tree output format:
+	 *     mode SP type SP sha1 TAB name
+	 */
+	mode = strtoul(ptr, &ntr, 8);
+	if (ptr == ntr || !ntr || *ntr != ' ')
+		die("input format error: %s", buf);
+	ptr = ntr + 1; /* type */
+	ntr = strchr(ptr, ' ');
+	if (!ntr || buf + len <= ntr + 40 ||
+	    ntr[41] != '\t' ||
+	    get_sha1_hex(ntr + 1, sha1))
+		die("input format error: %s", buf);
+
+	/* It is perfectly normal if we do not have a commit from a submodule */
+	if (S_ISGITLINK(mode))
+		allow_missing = 1;
+
+
+	*ntr++ = 0; /* now at the beginning of SHA1 */
+
+	path = ntr + 41;  /* at the beginning of name */
+	if (line_termination && path[0] == '"') {
+		struct strbuf p_uq = STRBUF_INIT;
+		if (unquote_c_style(&p_uq, path, NULL))
+			die("invalid quoting");
+		path = strbuf_detach(&p_uq, NULL);
+	}
+
+	/*
+	 * Object type is redundantly derivable three ways.
+	 * These should all agree.
+	 */
+	mode_type = object_type(mode);
+	if (mode_type != type_from_string(ptr)) {
+		die("entry '%s' object type (%s) doesn't match mode type (%s)",
+			path, ptr, typename(mode_type));
+	}
+
+	/* Check the type of object identified by sha1 */
+	obj_type = sha1_object_info(sha1, NULL);
+	if (obj_type < 0) {
+		if (allow_missing) {
+			; /* no problem - missing objects are presumed to be of the right type */
+		} else {
+			die("entry '%s' object %s is unavailable", path, sha1_to_hex(sha1));
+		}
+	} else {
+		if (obj_type != mode_type) {
+			/*
+			 * The object exists but is of the wrong type.
+			 * This is a problem regardless of allow_missing
+			 * because the new tree entry will never be correct.
+			 */
+			die("entry '%s' object %s is a %s but specified type was (%s)",
+				path, sha1_to_hex(sha1), typename(obj_type), typename(mode_type));
+		}
+	}
+
+	append_to_tree(mode, sha1, path);
+}
+
+int cmd_mktree(int ac, const char **av, const char *prefix)
+{
+	struct strbuf sb = STRBUF_INIT;
+	unsigned char sha1[20];
+	int line_termination = '\n';
+	int allow_missing = 0;
+	int is_batch_mode = 0;
+	int got_eof = 0;
+
+	const struct option option[] = {
+		OPT_SET_INT('z', NULL, &line_termination, "input is NUL terminated", '\0'),
+		OPT_SET_INT( 0 , "missing", &allow_missing, "allow missing objects", 1),
+		OPT_SET_INT( 0 , "batch", &is_batch_mode, "allow creation of more than one tree", 1),
+		OPT_END()
+	};
+
+	ac = parse_options(ac, av, option, mktree_usage, 0);
+
+	while (!got_eof) {
+		while (1) {
+			if (strbuf_getline(&sb, stdin, line_termination) == EOF) {
+				got_eof = 1;
+				break;
+			}
+			if (sb.buf[0] == '\0') {
+				/* empty lines denote tree boundaries in batch mode */
+				if (is_batch_mode)
+					break;
+				die("input format error: (blank line only valid in batch mode)");
+			}
+			mktree_line(sb.buf, sb.len, line_termination, allow_missing);
+		}
+		if (is_batch_mode && got_eof && used < 1) {
+			/*
+			 * Execution gets here if the last tree entry is terminated with a
+			 * new-line.  The final new-line has been made optional to be
+			 * consistent with the original non-batch behaviour of mktree.
+			 */
+			; /* skip creating an empty tree */
+		} else {
+			write_tree(sha1);
+			puts(sha1_to_hex(sha1));
+			fflush(stdout);
+		}
+		used=0; /* reset tree entry buffer for re-use in batch mode */
+	}
+	strbuf_release(&sb);
+	exit(0);
+}

builtin.h

@@ -72,6 +72,7 @@ extern int cmd_merge_base(int argc, const char **argv, const char *prefix);
 extern int cmd_merge_ours(int argc, const char **argv, const char *prefix);
 extern int cmd_merge_file(int argc, const char **argv, const char *prefix);
 extern int cmd_merge_recursive(int argc, const char **argv, const char *prefix);
+extern int cmd_mktree(int argc, const char **argv, const char *prefix);
 extern int cmd_mv(int argc, const char **argv, const char *prefix);
 extern int cmd_name_rev(int argc, const char **argv, const char *prefix);
 extern int cmd_pack_objects(int argc, const char **argv, const char *prefix);

git.c

@@ -327,6 +327,7 @@ static void handle_internal_command(int argc, const char **argv)
 		{ "merge-ours", cmd_merge_ours, RUN_SETUP },
 		{ "merge-recursive", cmd_merge_recursive, RUN_SETUP | NEED_WORK_TREE },
 		{ "merge-subtree", cmd_merge_recursive, RUN_SETUP | NEED_WORK_TREE },
+		{ "mktree", cmd_mktree, RUN_SETUP },
 		{ "mv", cmd_mv, RUN_SETUP | NEED_WORK_TREE },
 		{ "name-rev", cmd_name_rev, RUN_SETUP },
 		{ "pack-objects", cmd_pack_objects, RUN_SETUP },

mktree.c

@@ -1,131 +0,0 @@
-/*
- * GIT - the stupid content tracker
- *
- * Copyright (c) Junio C Hamano, 2006
- */
-#include "cache.h"
-#include "quote.h"
-#include "tree.h"
-#include "exec_cmd.h"
-
-static struct treeent {
-	unsigned mode;
-	unsigned char sha1[20];
-	int len;
-	char name[FLEX_ARRAY];
-} **entries;
-static int alloc, used;
-
-static void append_to_tree(unsigned mode, unsigned char *sha1, char *path)
-{
-	struct treeent *ent;
-	int len = strlen(path);
-	if (strchr(path, '/'))
-		die("path %s contains slash", path);
-
-	if (alloc <= used) {
-		alloc = alloc_nr(used);
-		entries = xrealloc(entries, sizeof(*entries) * alloc);
-	}
-	ent = entries[used++] = xmalloc(sizeof(**entries) + len + 1);
-	ent->mode = mode;
-	ent->len = len;
-	hashcpy(ent->sha1, sha1);
-	memcpy(ent->name, path, len+1);
-}
-
-static int ent_compare(const void *a_, const void *b_)
-{
-	struct treeent *a = *(struct treeent **)a_;
-	struct treeent *b = *(struct treeent **)b_;
-	return base_name_compare(a->name, a->len, a->mode,
-				 b->name, b->len, b->mode);
-}
-
-static void write_tree(unsigned char *sha1)
-{
-	struct strbuf buf;
-	size_t size;
-	int i;
-
-	qsort(entries, used, sizeof(*entries), ent_compare);
-	for (size = i = 0; i < used; i++)
-		size += 32 + entries[i]->len;
-
-	strbuf_init(&buf, size);
-	for (i = 0; i < used; i++) {
-		struct treeent *ent = entries[i];
-		strbuf_addf(&buf, "%o %s%c", ent->mode, ent->name, '\0');
-		strbuf_add(&buf, ent->sha1, 20);
-	}
-
-	write_sha1_file(buf.buf, buf.len, tree_type, sha1);
-}
-
-static const char mktree_usage[] = "git mktree [-z]";
-
-int main(int ac, char **av)
-{
-	struct strbuf sb = STRBUF_INIT;
-	struct strbuf p_uq = STRBUF_INIT;
-	unsigned char sha1[20];
-	int line_termination = '\n';
-
-	git_extract_argv0_path(av[0]);
-
-	setup_git_directory();
-
-	while ((1 < ac) && av[1][0] == '-') {
-		char *arg = av[1];
-		if (!strcmp("-z", arg))
-			line_termination = 0;
-		else
-			usage(mktree_usage);
-		ac--;
-		av++;
-	}
-
-	while (strbuf_getline(&sb, stdin, line_termination) != EOF) {
-		char *ptr, *ntr;
-		unsigned mode;
-		enum object_type type;
-		char *path;
-
-		ptr = sb.buf;
-		/* Input is non-recursive ls-tree output format
-		 * mode SP type SP sha1 TAB name
-		 */
-		mode = strtoul(ptr, &ntr, 8);
-		if (ptr == ntr || !ntr || *ntr != ' ')
-			die("input format error: %s", sb.buf);
-		ptr = ntr + 1; /* type */
-		ntr = strchr(ptr, ' ');
-		if (!ntr || sb.buf + sb.len <= ntr + 40 ||
-		    ntr[41] != '\t' ||
-		    get_sha1_hex(ntr + 1, sha1))
-			die("input format error: %s", sb.buf);
-		type = sha1_object_info(sha1, NULL);
-		if (type < 0)
-			die("object %s unavailable", sha1_to_hex(sha1));
-		*ntr++ = 0; /* now at the beginning of SHA1 */
-		if (type != type_from_string(ptr))
-			die("object type %s mismatch (%s)", ptr, typename(type));
-
-		path = ntr + 41;  /* at the beginning of name */
-		if (line_termination && path[0] == '"') {
-			strbuf_reset(&p_uq);
-			if (unquote_c_style(&p_uq, path, NULL)) {
-				die("invalid quoting");
-			}
-			path = p_uq.buf;
-		}
-
-		append_to_tree(mode, sha1, path);
-	}
-	strbuf_release(&p_uq);
-	strbuf_release(&sb);
-
-	write_tree(sha1);
-	puts(sha1_to_hex(sha1));
-	exit(0);
-}

t/t1010-mktree.sh

@@ -0,0 +1,71 @@
+#!/bin/sh
+
+test_description='git mktree'
+
+. ./test-lib.sh
+
+test_expect_success setup '
+	for d in a a. a0
+	do
+		mkdir "$d" && echo "$d/one" >"$d/one" &&
+		git add "$d"
+	done &&
+	echo zero >one &&
+	git update-index --add --info-only one &&
+	git write-tree --missing-ok >tree.missing &&
+	git ls-tree $(cat tree.missing) >top.missing &&
+	git ls-tree -r $(cat tree.missing) >all.missing &&
+	echo one >one &&
+	git add one &&
+	git write-tree >tree &&
+	git ls-tree $(cat tree) >top &&
+	git ls-tree -r $(cat tree) >all &&
+	test_tick &&
+	git commit -q -m one &&
+	H=$(git rev-parse HEAD) &&
+	git update-index --add --cacheinfo 160000 $H sub &&
+	test_tick &&
+	git commit -q -m two &&
+	git rev-parse HEAD^{tree} >tree.withsub &&
+	git ls-tree HEAD >top.withsub &&
+	git ls-tree -r HEAD >all.withsub
+'
+
+test_expect_success 'ls-tree piped to mktree (1)' '
+	git mktree <top >actual &&
+	test_cmp tree actual
+'
+
+test_expect_success 'ls-tree piped to mktree (2)' '
+	git mktree <top.withsub >actual &&
+	test_cmp tree.withsub actual
+'
+
+test_expect_success 'ls-tree output in wrong order given to mktree (1)' '
+	perl -e "print reverse <>" <top |
+	git mktree >actual &&
+	test_cmp tree actual
+'
+
+test_expect_success 'ls-tree output in wrong order given to mktree (2)' '
+	perl -e "print reverse <>" <top.withsub |
+	git mktree >actual &&
+	test_cmp tree.withsub actual
+'
+
+test_expect_success 'allow missing object with --missing' '
+	git mktree --missing <top.missing >actual &&
+	test_cmp tree.missing actual
+'
+
+test_expect_failure 'mktree reads ls-tree -r output (1)' '
+	git mktree <all >actual &&
+	test_cmp tree actual
+'
+
+test_expect_failure 'mktree reads ls-tree -r output (2)' '
+	git mktree <all.withsub >actual &&
+	test_cmp tree.withsub actual
+'
+
+test_done