Merge branch 'dp/hash-literally'

* dp/hash-literally:
  add --no-filters option to git hash-object
  add --path option to git hash-object
  use parse_options() in git hash-object
  correct usage help string for git-hash-object
  correct argument checking test for git hash-object
  teach index_fd to work with pipes

5 files changed, 178 insertions, 122 deletions

diff --git a/Documentation/git-hash-object.txt b/Documentation/git-hash-object.txt
index ac928e198e..0af40cfb85 100644
--- a/Documentation/git-hash-object.txt
+++ b/Documentation/git-hash-object.txt
@@ -8,7 +8,9 @@ git-hash-object - Compute object ID and optionally creates a blob from a file
 
 SYNOPSIS
 --------
-'git hash-object' [-t <type>] [-w] [--stdin | --stdin-paths] [--] <file>...
+[verse]
+'git hash-object' [-t <type>] [-w] [--path=<file>|--no-filters] [--stdin] [--] <file>...
+'git hash-object' [-t <type>] [-w] --stdin-paths < <list-of-paths>
 
 DESCRIPTION
 -----------
@@ -35,6 +37,22 @@ OPTIONS
 --stdin-paths::
 	Read file names from stdin instead of from the command-line.
 
+--path::
+	Hash object as it were located at the given path. The location of
+	file does not directly influence on the hash value, but path is
+	used to determine what git filters should be applied to the object
+	before it can be placed to the object database, and, as result of
+	applying filters, the actual blob put into the object database may
+	differ from the given file. This option is mainly useful for hashing
+	temporary files located outside of the working directory or files
+	read from stdin.
+
+--no-filters::
+	Hash the contents as is, ignoring any input filter that would
+	have been chosen by the attributes mechanism, including crlf
+	conversion. If the file is read from standard input then this
+	is always implied, unless the --path option is given.
+
 Author
 ------
 Written by Junio C Hamano <gitster@pobox.com>
diff --git a/cache.h b/cache.h
index 2475de9fa8..68ce6e686f 100644
--- a/cache.h
+++ b/cache.h
@@ -391,7 +391,6 @@ extern int ie_modified(const struct index_state *, struct cache_entry *, struct
 
 extern int ce_path_match(const struct cache_entry *ce, const char **pathspec);
 extern int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, enum object_type type, const char *path);
-extern int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object);
 extern int index_path(unsigned char *sha1, const char *path, struct stat *st, int write_object);
 extern void fill_stat_cache_info(struct cache_entry *ce, struct stat *st);
 
diff --git a/hash-object.c b/hash-object.c
index 46c06a9552..a4d127cf78 100644
--- a/hash-object.c
+++ b/hash-object.c
@@ -7,16 +7,14 @@
 #include "cache.h"
 #include "blob.h"
 #include "quote.h"
+#include "parse-options.h"
 
-static void hash_object(const char *path, enum object_type type, int write_object)
+static void hash_fd(int fd, const char *type, int write_object, const char *path)
 {
-	int fd;
 	struct stat st;
 	unsigned char sha1[20];
-	fd = open(path, O_RDONLY);
-	if (fd < 0 ||
-	    fstat(fd, &st) < 0 ||
-	    index_fd(sha1, fd, &st, write_object, type, path))
+	if (fstat(fd, &st) < 0 ||
+	    index_fd(sha1, fd, &st, write_object, type_from_string(type), path))
 		die(write_object
 		    ? "Unable to add %s to database"
 		    : "Unable to hash %s", path);
@@ -24,12 +22,14 @@ static void hash_object(const char *path, enum object_type type, int write_objec
 	maybe_flush_or_die(stdout, "hash to stdout");
 }
 
-static void hash_stdin(const char *type, int write_object)
+static void hash_object(const char *path, const char *type, int write_object,
+			const char *vpath)
 {
-	unsigned char sha1[20];
-	if (index_pipe(sha1, 0, type, write_object))
-		die("Unable to add stdin to database");
-	printf("%s\n", sha1_to_hex(sha1));
+	int fd;
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		die("Cannot open %s", path);
+	hash_fd(fd, type, write_object, vpath);
 }
 
 static void hash_stdin_paths(const char *type, int write_objects)
@@ -45,92 +45,91 @@ static void hash_stdin_paths(const char *type, int write_objects)
 				die("line is badly quoted");
 			strbuf_swap(&buf, &nbuf);
 		}
-		hash_object(buf.buf, type_from_string(type), write_objects);
+		hash_object(buf.buf, type, write_objects, buf.buf);
 	}
 	strbuf_release(&buf);
 	strbuf_release(&nbuf);
 }
 
-static const char hash_object_usage[] =
-"git hash-object [ [-t <type>] [-w] [--stdin] <file>... | --stdin-paths < <list-of-paths> ]";
+static const char * const hash_object_usage[] = {
+	"git hash-object [-t <type>] [-w] [--path=<file>|--no-filters] [--stdin] [--] <file>...",
+	"git hash-object  --stdin-paths < <list-of-paths>",
+	NULL
+};
 
-int main(int argc, char **argv)
+static const char *type;
+static int write_object;
+static int hashstdin;
+static int stdin_paths;
+static int no_filters;
+static const char *vpath;
+
+static const struct option hash_object_options[] = {
+	OPT_STRING('t', NULL, &type, "type", "object type"),
+	OPT_BOOLEAN('w', NULL, &write_object, "write the object into the object database"),
+	OPT_BOOLEAN( 0 , "stdin", &hashstdin, "read the object from stdin"),
+	OPT_BOOLEAN( 0 , "stdin-paths", &stdin_paths, "read file names from stdin"),
+	OPT_BOOLEAN( 0 , "no-filters", &no_filters, "store file as is without filters"),
+	OPT_STRING( 0 , "path", &vpath, "file", "process file as it were from this path"),
+	OPT_END()
+};
+
+int main(int argc, const char **argv)
 {
 	int i;
-	const char *type = blob_type;
-	int write_object = 0;
 	const char *prefix = NULL;
 	int prefix_length = -1;
-	int no_more_flags = 0;
-	int hashstdin = 0;
-	int stdin_paths = 0;
+	const char *errstr = NULL;
+
+	type = blob_type;
 
 	git_config(git_default_config, NULL);
 
-	for (i = 1 ; i < argc; i++) {
-		if (!no_more_flags && argv[i][0] == '-') {
-			if (!strcmp(argv[i], "-t")) {
-				if (argc <= ++i)
-					usage(hash_object_usage);
-				type = argv[i];
-			}
-			else if (!strcmp(argv[i], "-w")) {
-				if (prefix_length < 0) {
-					prefix = setup_git_directory();
-					prefix_length =
-						prefix ? strlen(prefix) : 0;
-				}
-				write_object = 1;
-			}
-			else if (!strcmp(argv[i], "--")) {
-				no_more_flags = 1;
-			}
-			else if (!strcmp(argv[i], "--help"))
-				usage(hash_object_usage);
-			else if (!strcmp(argv[i], "--stdin-paths")) {
-				if (hashstdin) {
-					error("Can't use --stdin-paths with --stdin");
-					usage(hash_object_usage);
-				}
-				stdin_paths = 1;
-
-			}
-			else if (!strcmp(argv[i], "--stdin")) {
-				if (stdin_paths) {
-					error("Can't use %s with --stdin-paths", argv[i]);
-					usage(hash_object_usage);
-				}
-				if (hashstdin)
-					die("Multiple --stdin arguments are not supported");
-				hashstdin = 1;
-			}
-			else
-				usage(hash_object_usage);
-		}
-		else {
-			const char *arg = argv[i];
-
-			if (stdin_paths) {
-				error("Can't specify files (such as \"%s\") with --stdin-paths", arg);
-				usage(hash_object_usage);
-			}
-
-			if (hashstdin) {
-				hash_stdin(type, write_object);
-				hashstdin = 0;
-			}
-			if (0 <= prefix_length)
-				arg = prefix_filename(prefix, prefix_length,
-						      arg);
-			hash_object(arg, type_from_string(type), write_object);
-			no_more_flags = 1;
-		}
+	argc = parse_options(argc, argv, hash_object_options, hash_object_usage, 0);
+
+	if (write_object) {
+		prefix = setup_git_directory();
+		prefix_length = prefix ? strlen(prefix) : 0;
+		if (vpath && prefix)
+			vpath = prefix_filename(prefix, prefix_length, vpath);
+	}
+
+	if (stdin_paths) {
+		if (hashstdin)
+			errstr = "Can't use --stdin-paths with --stdin";
+		else if (argc)
+			errstr = "Can't specify files with --stdin-paths";
+		else if (vpath)
+			errstr = "Can't use --stdin-paths with --path";
+		else if (no_filters)
+			errstr = "Can't use --stdin-paths with --no-filters";
+	}
+	else {
+		if (hashstdin > 1)
+			errstr = "Multiple --stdin arguments are not supported";
+		if (vpath && no_filters)
+			errstr = "Can't use --path with --no-filters";
+	}
+
+	if (errstr) {
+		error (errstr);
+		usage_with_options(hash_object_usage, hash_object_options);
+	}
+
+	if (hashstdin)
+		hash_fd(0, type, write_object, vpath);
+
+	for (i = 0 ; i < argc; i++) {
+		const char *arg = argv[i];
+
+		if (0 <= prefix_length)
+			arg = prefix_filename(prefix, prefix_length, arg);
+		hash_object(arg, type, write_object,
+			    no_filters ? NULL : vpath ? vpath : arg);
 	}
 
 	if (stdin_paths)
 		hash_stdin_paths(type, write_object);
 
-	if (hashstdin)
-		hash_stdin(type, write_object);
 	return 0;
 }
diff --git a/sha1_file.c b/sha1_file.c
index 32e4664b1b..2aff59b90f 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -2360,51 +2360,22 @@ int has_sha1_file(const unsigned char *sha1)
 	return has_loose_object(sha1);
 }
 
-int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object)
+static int index_mem(unsigned char *sha1, void *buf, size_t size,
+		     int write_object, enum object_type type, const char *path)
 {
-	struct strbuf buf;
-	int ret;
-
-	strbuf_init(&buf, 0);
-	if (strbuf_read(&buf, fd, 4096) < 0) {
-		strbuf_release(&buf);
-		return -1;
-	}
-
-	if (!type)
-		type = blob_type;
-	if (write_object)
-		ret = write_sha1_file(buf.buf, buf.len, type, sha1);
-	else
-		ret = hash_sha1_file(buf.buf, buf.len, type, sha1);
-	strbuf_release(&buf);
-
-	return ret;
-}
-
-int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object,
-	     enum object_type type, const char *path)
-{
-	size_t size = xsize_t(st->st_size);
-	void *buf = NULL;
 	int ret, re_allocated = 0;
 
-	if (size)
-		buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
-	close(fd);
-
 	if (!type)
 		type = OBJ_BLOB;
 
 	/*
 	 * Convert blobs to git internal format
 	 */
-	if ((type == OBJ_BLOB) && S_ISREG(st->st_mode)) {
+	if ((type == OBJ_BLOB) && path) {
 		struct strbuf nbuf;
 		strbuf_init(&nbuf, 0);
 		if (convert_to_git(path, buf, size, &nbuf,
 		                   write_object ? safe_crlf : 0)) {
-			munmap(buf, size);
 			buf = strbuf_detach(&nbuf, &size);
 			re_allocated = 1;
 		}
@@ -2414,12 +2385,33 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object,
 		ret = write_sha1_file(buf, size, typename(type), sha1);
 	else
 		ret = hash_sha1_file(buf, size, typename(type), sha1);
-	if (re_allocated) {
+	if (re_allocated)
 		free(buf);
-		return ret;
-	}
-	if (size)
+	return ret;
+}
+
+int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object,
+	     enum object_type type, const char *path)
+{
+	int ret;
+	size_t size = xsize_t(st->st_size);
+
+	if (!S_ISREG(st->st_mode)) {
+		struct strbuf sbuf;
+		strbuf_init(&sbuf, 0);
+		if (strbuf_read(&sbuf, fd, 4096) >= 0)
+			ret = index_mem(sha1, sbuf.buf, sbuf.len, write_object,
+					type, path);
+		else
+			ret = -1;
+		strbuf_release(&sbuf);
+	} else if (size) {
+		void *buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
+		ret = index_mem(sha1, buf, size, write_object, type, path);
 		munmap(buf, size);
+	} else
+		ret = index_mem(sha1, NULL, size, write_object, type, path);
+	close(fd);
 	return ret;
 }
 
diff --git a/t/t1007-hash-object.sh b/t/t1007-hash-object.sh
index 1ec0535138..fcdd15a358 100755
--- a/t/t1007-hash-object.sh
+++ b/t/t1007-hash-object.sh
@@ -49,16 +49,28 @@ setup_repo
 # Argument checking
 
 test_expect_success "multiple '--stdin's are rejected" '
-	test_must_fail git hash-object --stdin --stdin < example
+	echo example | test_must_fail git hash-object --stdin --stdin
 '
 
 test_expect_success "Can't use --stdin and --stdin-paths together" '
-	test_must_fail git hash-object --stdin --stdin-paths &&
-	test_must_fail git hash-object --stdin-paths --stdin
+	echo example | test_must_fail git hash-object --stdin --stdin-paths &&
+	echo example | test_must_fail git hash-object --stdin-paths --stdin
 '
 
 test_expect_success "Can't pass filenames as arguments with --stdin-paths" '
-	test_must_fail git hash-object --stdin-paths hello < example
+	echo example | test_must_fail git hash-object --stdin-paths hello
+'
+
+test_expect_success "Can't use --path with --stdin-paths" '
+	echo example | test_must_fail git hash-object --stdin-paths --path=foo
+'
+
+test_expect_success "Can't use --stdin-paths with --no-filters" '
+	echo example | test_must_fail git hash-object --stdin-paths --no-filters
+'
+
+test_expect_success "Can't use --path with --no-filters" '
+	test_must_fail git hash-object --no-filters --path=foo
 '
 
 # Behavior
@@ -93,6 +105,42 @@ test_expect_success 'git hash-object --stdin file1 <file0 first operates on file
 	test "$obname1" = "$obname1new"
 '
 
+test_expect_success 'check that appropriate filter is invoke when --path is used' '
+	echo fooQ | tr Q "\\015" >file0 &&
+	cp file0 file1 &&
+	echo "file0 -crlf" >.gitattributes &&
+	echo "file1 crlf" >>.gitattributes &&
+	git config core.autocrlf true &&
+	file0_sha=$(git hash-object file0) &&
+	file1_sha=$(git hash-object file1) &&
+	test "$file0_sha" != "$file1_sha" &&
+	path1_sha=$(git hash-object --path=file1 file0) &&
+	path0_sha=$(git hash-object --path=file0 file1) &&
+	test "$file0_sha" = "$path0_sha" &&
+	test "$file1_sha" = "$path1_sha" &&
+	path1_sha=$(cat file0 | git hash-object --path=file1 --stdin) &&
+	path0_sha=$(cat file1 | git hash-object --path=file0 --stdin) &&
+	test "$file0_sha" = "$path0_sha" &&
+	test "$file1_sha" = "$path1_sha" &&
+	git config --unset core.autocrlf
+'
+
+test_expect_success 'check that --no-filters option works' '
+	echo fooQ | tr Q "\\015" >file0 &&
+	cp file0 file1 &&
+	echo "file0 -crlf" >.gitattributes &&
+	echo "file1 crlf" >>.gitattributes &&
+	git config core.autocrlf true &&
+	file0_sha=$(git hash-object file0) &&
+	file1_sha=$(git hash-object file1) &&
+	test "$file0_sha" != "$file1_sha" &&
+	nofilters_file1=$(git hash-object --no-filters file1) &&
+	test "$file0_sha" = "$nofilters_file1" &&
+	nofilters_file1=$(cat file1 | git hash-object --stdin) &&
+	test "$file0_sha" = "$nofilters_file1" &&
+	git config --unset core.autocrlf
+'
+
 pop_repo
 
 for args in "-w --stdin" "--stdin -w"; do