Merge branch 'dt/cat-file-follow-symlinks'

"git cat-file --batch(-check)" learned the "--follow-symlinks"
option that follows an in-tree symbolic link when asked about an
object via extended SHA-1 syntax, e.g. HEAD:RelNotes that points at
Documentation/RelNotes/2.5.0.txt.  With the new option, the command
behaves as if HEAD:Documentation/RelNotes/2.5.0.txt was given as
input instead.

* dt/cat-file-follow-symlinks:
  cat-file: add --follow-symlinks to --batch
  sha1_name: get_sha1_with_context learns to follow symlinks
  tree-walk: learn get_tree_entry_follow_symlinks

Author: gitster

Documentation/git-cat-file.txt

@@ -10,7 +10,7 @@ SYNOPSIS
 --------
 [verse]
 'git cat-file' (-t [--allow-unknown-type]| -s [--allow-unknown-type]| -e | -p | <type> | --textconv ) <object>
-'git cat-file' (--batch | --batch-check) < <list-of-objects>
+'git cat-file' (--batch | --batch-check) [--follow-symlinks] < <list-of-objects>
 
 DESCRIPTION
 -----------
@@ -72,6 +72,62 @@ OPTIONS
 --allow-unknown-type::
 	Allow -s or -t to query broken/corrupt objects of unknown type.
 
+--follow-symlinks::
+	With --batch or --batch-check, follow symlinks inside the
+	repository when requesting objects with extended SHA-1
+	expressions of the form tree-ish:path-in-tree.  Instead of
+	providing output about the link itself, provide output about
+	the linked-to object.  If a symlink points outside the
+	tree-ish (e.g. a link to /foo or a root-level link to ../foo),
+	the portion of the link which is outside the tree will be
+	printed.
++
+This option does not (currently) work correctly when an object in the
+index is specified (e.g. `:link` instead of `HEAD:link`) rather than
+one in the tree.
++
+This option cannot (currently) be used unless `--batch` or
+`--batch-check` is used.
++
+For example, consider a git repository containing:
++
+--
+	f: a file containing "hello\n"
+	link: a symlink to f
+	dir/link: a symlink to ../f
+	plink: a symlink to ../f
+	alink: a symlink to /etc/passwd
+--
++
+For a regular file `f`, `echo HEAD:f | git cat-file --batch` would print
++
+--
+	ce013625030ba8dba906f756967f9e9ca394464a blob 6
+--
++
+And `echo HEAD:link | git cat-file --batch --follow-symlinks` would
+print the same thing, as would `HEAD:dir/link`, as they both point at
+`HEAD:f`.
++
+Without `--follow-symlinks`, these would print data about the symlink
+itself.  In the case of `HEAD:link`, you would see
++
+--
+	4d1ae35ba2c8ec712fa2a379db44ad639ca277bd blob 1
+--
++
+Both `plink` and `alink` point outside the tree, so they would
+respectively print:
++
+--
+	symlink 4
+	../f
+
+	symlink 11
+	/etc/passwd
+--
+
+
 OUTPUT
 ------
 If '-t' is specified, one of the <type>.
@@ -151,6 +207,47 @@ the repository, then `cat-file` will ignore any custom format and print:
 <object> SP missing LF
 ------------
 
+If --follow-symlinks is used, and a symlink in the repository points
+outside the repository, then `cat-file` will ignore any custom format
+and print:
+
+------------
+symlink SP <size> LF
+<symlink> LF
+------------
+
+The symlink will either be absolute (beginning with a /), or relative
+to the tree root.  For instance, if dir/link points to ../../foo, then
+<symlink> will be ../foo.  <size> is the size of the symlink in bytes.
+
+If --follow-symlinks is used, the following error messages will be
+displayed:
+
+------------
+<object> SP missing LF
+------------
+is printed when the initial symlink requested does not exist.
+
+------------
+dangling SP <size> LF
+<object> LF
+------------
+is printed when the initial symlink exists, but something that
+it (transitive-of) points to does not.
+
+------------
+loop SP <size> LF
+<object> LF
+------------
+is printed for symlink loops (or any symlinks that
+require more than 40 link resolutions to resolve).
+
+------------
+notdir SP <size> LF
+<object> LF
+------------
+is printed when, during symlink resolution, a file is used as a
+directory name.
 
 CAVEATS
 -------

builtin/cat-file.c

@@ -8,6 +8,7 @@
 #include "parse-options.h"
 #include "userdiff.h"
 #include "streaming.h"
+#include "tree-walk.h"
 
 static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
 			int unknown_type)
@@ -233,6 +234,7 @@ static void print_object_or_die(int fd, struct expand_data *data)
 
 struct batch_options {
 	int enabled;
+	int follow_symlinks;
 	int print_contents;
 	const char *format;
 };
@@ -241,12 +243,44 @@ static int batch_one_object(const char *obj_name, struct batch_options *opt,
 			    struct expand_data *data)
 {
 	struct strbuf buf = STRBUF_INIT;
+	struct object_context ctx;
+	int flags = opt->follow_symlinks ? GET_SHA1_FOLLOW_SYMLINKS : 0;
+	enum follow_symlinks_result result;
 
 	if (!obj_name)
 	   return 1;
 
-	if (get_sha1(obj_name, data->sha1)) {
-		printf("%s missing\n", obj_name);
+	result = get_sha1_with_context(obj_name, flags, data->sha1, &ctx);
+	if (result != FOUND) {
+		switch (result) {
+		case MISSING_OBJECT:
+			printf("%s missing\n", obj_name);
+			break;
+		case DANGLING_SYMLINK:
+			printf("dangling %"PRIuMAX"\n%s\n",
+			       (uintmax_t)strlen(obj_name), obj_name);
+			break;
+		case SYMLINK_LOOP:
+			printf("loop %"PRIuMAX"\n%s\n",
+			       (uintmax_t)strlen(obj_name), obj_name);
+			break;
+		case NOT_DIR:
+			printf("notdir %"PRIuMAX"\n%s\n",
+			       (uintmax_t)strlen(obj_name), obj_name);
+			break;
+		default:
+			die("BUG: unknown get_sha1_with_context result %d\n",
+			       result);
+			break;
+		}
+		fflush(stdout);
+		return 0;
+	}
+
+	if (ctx.mode == 0) {
+		printf("symlink %"PRIuMAX"\n%s\n",
+		       (uintmax_t)ctx.symlink_path.len,
+		       ctx.symlink_path.buf);
 		fflush(stdout);
 		return 0;
 	}
@@ -333,7 +367,7 @@ static int batch_objects(struct batch_options *opt)
 
 static const char * const cat_file_usage[] = {
 	N_("git cat-file (-t [--allow-unknown-type]|-s [--allow-unknown-type]|-e|-p|<type>|--textconv) <object>"),
-	N_("git cat-file (--batch | --batch-check) < <list-of-objects>"),
+	N_("git cat-file (--batch | --batch-check) [--follow-symlinks] < <list-of-objects>"),
 	NULL
 };
 
@@ -351,9 +385,8 @@ static int batch_option_callback(const struct option *opt,
 {
 	struct batch_options *bo = opt->value;
 
-	if (unset) {
-		memset(bo, 0, sizeof(*bo));
-		return 0;
+	if (bo->enabled) {
+		return 1;
 	}
 
 	bo->enabled = 1;
@@ -387,6 +420,8 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 		{ OPTION_CALLBACK, 0, "batch-check", &batch, "format",
 			N_("show info about objects fed from the standard input"),
 			PARSE_OPT_OPTARG, batch_option_callback },
+		OPT_BOOL(0, "follow-symlinks", &batch.follow_symlinks,
+			 N_("follow in-tree symlinks (used with --batch or --batch-check)")),
 		OPT_END()
 	};
 
@@ -411,6 +446,10 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 		usage_with_options(cat_file_usage, options);
 	}
 
+	if (batch.follow_symlinks && !batch.enabled) {
+		usage_with_options(cat_file_usage, options);
+	}
+
 	if (batch.enabled)
 		return batch_objects(&batch);
 

cache.h

@@ -971,15 +971,21 @@ struct object_context {
 	unsigned char tree[20];
 	char path[PATH_MAX];
 	unsigned mode;
+	/*
+	 * symlink_path is only used by get_tree_entry_follow_symlinks,
+	 * and only for symlinks that point outside the repository.
+	 */
+	struct strbuf symlink_path;
 };
 
-#define GET_SHA1_QUIETLY        01
-#define GET_SHA1_COMMIT         02
-#define GET_SHA1_COMMITTISH     04
-#define GET_SHA1_TREE          010
-#define GET_SHA1_TREEISH       020
-#define GET_SHA1_BLOB	       040
-#define GET_SHA1_ONLY_TO_DIE 04000
+#define GET_SHA1_QUIETLY           01
+#define GET_SHA1_COMMIT            02
+#define GET_SHA1_COMMITTISH        04
+#define GET_SHA1_TREE             010
+#define GET_SHA1_TREEISH          020
+#define GET_SHA1_BLOB             040
+#define GET_SHA1_FOLLOW_SYMLINKS 0100
+#define GET_SHA1_ONLY_TO_DIE    04000
 
 extern int get_sha1(const char *str, unsigned char *sha1);
 extern int get_sha1_commit(const char *str, unsigned char *sha1);

sha1_name.c

@@ -1433,11 +1433,19 @@ static int get_sha1_with_context_1(const char *name,
 			new_filename = resolve_relative_path(filename);
 			if (new_filename)
 				filename = new_filename;
-			ret = get_tree_entry(tree_sha1, filename, sha1, &oc->mode);
-			if (ret && only_to_die) {
-				diagnose_invalid_sha1_path(prefix, filename,
-							   tree_sha1,
-							   name, len);
+			if (flags & GET_SHA1_FOLLOW_SYMLINKS) {
+				ret = get_tree_entry_follow_symlinks(tree_sha1,
+					filename, sha1, &oc->symlink_path,
+					&oc->mode);
+			} else {
+				ret = get_tree_entry(tree_sha1, filename,
+						     sha1, &oc->mode);
+				if (ret && only_to_die) {
+					diagnose_invalid_sha1_path(prefix,
+								   filename,
+								   tree_sha1,
+								   name, len);
+				}
 			}
 			hashcpy(oc->tree, tree_sha1);
 			strlcpy(oc->path, filename, sizeof(oc->path));
@@ -1468,5 +1476,7 @@ void maybe_die_on_misspelt_object_name(const char *name, const char *prefix)
 
 int get_sha1_with_context(const char *str, unsigned flags, unsigned char *sha1, struct object_context *orc)
 {
+	if (flags & GET_SHA1_FOLLOW_SYMLINKS && flags & GET_SHA1_ONLY_TO_DIE)
+		die("BUG: incompatible flags for get_sha1_with_context");
 	return get_sha1_with_context_1(str, flags, NULL, sha1, orc);
 }