1 files changed, 266 insertions, 54 deletions

diff --git a/setup.c b/setup.c
index b6e6b5ae27..94c1e61bda 100644
--- a/setup.c
+++ b/setup.c
@@ -1,10 +1,11 @@
 #include "cache.h"
 #include "dir.h"
+#include "string-list.h"
 
 static int inside_git_dir = -1;
 static int inside_work_tree = -1;
 
-char *prefix_path(const char *prefix, int len, const char *path)
+static char *prefix_path_gently(const char *prefix, int len, const char *path)
 {
 	const char *orig = path;
 	char *sanitized;
@@ -31,7 +32,8 @@ char *prefix_path(const char *prefix, int len, const char *path)
 		if (strncmp(sanitized, work_tree, len) ||
 		    (len > root_len && sanitized[len] != '\0' && sanitized[len] != '/')) {
 		error_out:
-			die("'%s' is outside repository", orig);
+			free(sanitized);
+			return NULL;
 		}
 		if (sanitized[len] == '/')
 			len++;
@@ -40,32 +42,23 @@ char *prefix_path(const char *prefix, int len, const char *path)
 	return sanitized;
 }
 
-/*
- * Unlike prefix_path, this should be used if the named file does
- * not have to interact with index entry; i.e. name of a random file
- * on the filesystem.
- */
-const char *prefix_filename(const char *pfx, int pfx_len, const char *arg)
+char *prefix_path(const char *prefix, int len, const char *path)
 {
-	static char path[PATH_MAX];
-#ifndef WIN32
-	if (!pfx_len || is_absolute_path(arg))
-		return arg;
-	memcpy(path, pfx, pfx_len);
-	strcpy(path + pfx_len, arg);
-#else
-	char *p;
-	/* don't add prefix to absolute paths, but still replace '\' by '/' */
-	if (is_absolute_path(arg))
-		pfx_len = 0;
-	else if (pfx_len)
-		memcpy(path, pfx, pfx_len);
-	strcpy(path + pfx_len, arg);
-	for (p = path + pfx_len; *p; p++)
-		if (*p == '\\')
-			*p = '/';
-#endif
-	return path;
+	char *r = prefix_path_gently(prefix, len, path);
+	if (!r)
+		die("'%s' is outside repository", path);
+	return r;
+}
+
+int path_inside_repo(const char *prefix, const char *path)
+{
+	int len = prefix ? strlen(prefix) : 0;
+	char *r = prefix_path_gently(prefix, len, path);
+	if (r) {
+		free(r);
+		return 1;
+	}
+	return 0;
 }
 
 int check_filename(const char *prefix, const char *arg)
@@ -73,7 +66,14 @@ int check_filename(const char *prefix, const char *arg)
 	const char *name;
 	struct stat st;
 
-	name = prefix ? prefix_filename(prefix, strlen(prefix), arg) : arg;
+	if (!prefixcmp(arg, ":/")) {
+		if (arg[2] == '\0') /* ":/" is root dir, always exists */
+			return 1;
+		name = arg + 2;
+	} else if (prefix)
+		name = prefix_filename(prefix, strlen(prefix), arg);
+	else
+		name = arg;
 	if (!lstat(name, &st))
 		return 1; /* file exists */
 	if (errno == ENOENT || errno == ENOTDIR)
@@ -81,15 +81,27 @@ int check_filename(const char *prefix, const char *arg)
 	die_errno("failed to stat '%s'", arg);
 }
 
-static void NORETURN die_verify_filename(const char *prefix, const char *arg)
+static void NORETURN die_verify_filename(const char *prefix,
+					 const char *arg,
+					 int diagnose_misspelt_rev)
 {
-	unsigned char sha1[20];
-	unsigned mode;
-	/* try a detailed diagnostic ... */
-	get_sha1_with_mode_1(arg, sha1, &mode, 0, prefix);
+	if (!diagnose_misspelt_rev)
+		die("%s: no such path in the working tree.\n"
+		    "Use 'git <command> -- <path>...' to specify paths that do not exist locally.",
+		    arg);
+	/*
+	 * Saying "'(icase)foo' does not exist in the index" when the
+	 * user gave us ":(icase)foo" is just stupid.  A magic pathspec
+	 * begins with a colon and is followed by a non-alnum; do not
+	 * let maybe_die_on_misspelt_object_name() even trigger.
+	 */
+	if (!(arg[0] == ':' && !isalnum(arg[1])))
+		maybe_die_on_misspelt_object_name(arg, prefix);
+
 	/* ... or fall back the most general message. */
 	die("ambiguous argument '%s': unknown revision or path not in the working tree.\n"
-	    "Use '--' to separate paths from revisions", arg);
+	    "Use '--' to separate paths from revisions, like this:\n"
+	    "'git <command> [<revision>...] -- [<file>...]'", arg);
 
 }
 
@@ -99,14 +111,29 @@ static void NORETURN die_verify_filename(const char *prefix, const char *arg)
  * as true, because even if such a filename were to exist, we want
  * it to be preceded by the "--" marker (or we want the user to
  * use a format like "./-filename")
+ *
+ * The "diagnose_misspelt_rev" is used to provide a user-friendly
+ * diagnosis when dying upon finding that "name" is not a pathname.
+ * If set to 1, the diagnosis will try to diagnose "name" as an
+ * invalid object name (e.g. HEAD:foo). If set to 0, the diagnosis
+ * will only complain about an inexisting file.
+ *
+ * This function is typically called to check that a "file or rev"
+ * argument is unambiguous. In this case, the caller will want
+ * diagnose_misspelt_rev == 1 when verifying the first non-rev
+ * argument (which could have been a revision), and
+ * diagnose_misspelt_rev == 0 for the next ones (because we already
+ * saw a filename, there's not ambiguity anymore).
  */
-void verify_filename(const char *prefix, const char *arg)
+void verify_filename(const char *prefix,
+		     const char *arg,
+		     int diagnose_misspelt_rev)
 {
 	if (*arg == '-')
 		die("bad flag '%s' used after filename", arg);
 	if (check_filename(prefix, arg))
 		return;
-	die_verify_filename(prefix, arg);
+	die_verify_filename(prefix, arg, diagnose_misspelt_rev);
 }
 
 /*
@@ -123,9 +150,130 @@ void verify_non_filename(const char *prefix, const char *arg)
 	if (!check_filename(prefix, arg))
 		return;
 	die("ambiguous argument '%s': both revision and filename\n"
-	    "Use '--' to separate filenames from revisions", arg);
+	    "Use '--' to separate paths from revisions, like this:\n"
+	    "'git <command> [<revision>...] -- [<file>...]'", arg);
 }
 
+/*
+ * Magic pathspec
+ *
+ * NEEDSWORK: These need to be moved to dir.h or even to a new
+ * pathspec.h when we restructure get_pathspec() users to use the
+ * "struct pathspec" interface.
+ *
+ * Possible future magic semantics include stuff like:
+ *
+ *	{ PATHSPEC_NOGLOB, '!', "noglob" },
+ *	{ PATHSPEC_ICASE, '\0', "icase" },
+ *	{ PATHSPEC_RECURSIVE, '*', "recursive" },
+ *	{ PATHSPEC_REGEXP, '\0', "regexp" },
+ *
+ */
+#define PATHSPEC_FROMTOP    (1<<0)
+
+static struct pathspec_magic {
+	unsigned bit;
+	char mnemonic; /* this cannot be ':'! */
+	const char *name;
+} pathspec_magic[] = {
+	{ PATHSPEC_FROMTOP, '/', "top" },
+};
+
+/*
+ * Take an element of a pathspec and check for magic signatures.
+ * Append the result to the prefix.
+ *
+ * For now, we only parse the syntax and throw out anything other than
+ * "top" magic.
+ *
+ * NEEDSWORK: This needs to be rewritten when we start migrating
+ * get_pathspec() users to use the "struct pathspec" interface.  For
+ * example, a pathspec element may be marked as case-insensitive, but
+ * the prefix part must always match literally, and a single stupid
+ * string cannot express such a case.
+ */
+static const char *prefix_pathspec(const char *prefix, int prefixlen, const char *elt)
+{
+	unsigned magic = 0;
+	const char *copyfrom = elt;
+	int i;
+
+	if (elt[0] != ':') {
+		; /* nothing to do */
+	} else if (elt[1] == '(') {
+		/* longhand */
+		const char *nextat;
+		for (copyfrom = elt + 2;
+		     *copyfrom && *copyfrom != ')';
+		     copyfrom = nextat) {
+			size_t len = strcspn(copyfrom, ",)");
+			if (copyfrom[len] == ',')
+				nextat = copyfrom + len + 1;
+			else
+				/* handle ')' and '\0' */
+				nextat = copyfrom + len;
+			if (!len)
+				continue;
+			for (i = 0; i < ARRAY_SIZE(pathspec_magic); i++)
+				if (strlen(pathspec_magic[i].name) == len &&
+				    !strncmp(pathspec_magic[i].name, copyfrom, len)) {
+					magic |= pathspec_magic[i].bit;
+					break;
+				}
+			if (ARRAY_SIZE(pathspec_magic) <= i)
+				die("Invalid pathspec magic '%.*s' in '%s'",
+				    (int) len, copyfrom, elt);
+		}
+		if (*copyfrom != ')')
+			die("Missing ')' at the end of pathspec magic in '%s'", elt);
+		copyfrom++;
+	} else {
+		/* shorthand */
+		for (copyfrom = elt + 1;
+		     *copyfrom && *copyfrom != ':';
+		     copyfrom++) {
+			char ch = *copyfrom;
+
+			if (!is_pathspec_magic(ch))
+				break;
+			for (i = 0; i < ARRAY_SIZE(pathspec_magic); i++)
+				if (pathspec_magic[i].mnemonic == ch) {
+					magic |= pathspec_magic[i].bit;
+					break;
+				}
+			if (ARRAY_SIZE(pathspec_magic) <= i)
+				die("Unimplemented pathspec magic '%c' in '%s'",
+				    ch, elt);
+		}
+		if (*copyfrom == ':')
+			copyfrom++;
+	}
+
+	if (magic & PATHSPEC_FROMTOP)
+		return xstrdup(copyfrom);
+	else
+		return prefix_path(prefix, prefixlen, copyfrom);
+}
+
+/*
+ * N.B. get_pathspec() is deprecated in favor of the "struct pathspec"
+ * based interface - see pathspec_magic above.
+ *
+ * Arguments:
+ *  - prefix - a path relative to the root of the working tree
+ *  - pathspec - a list of paths underneath the prefix path
+ *
+ * Iterates over pathspec, prepending each path with prefix,
+ * and return the resulting list.
+ *
+ * If pathspec is empty, return a singleton list containing prefix.
+ *
+ * If pathspec and prefix are both empty, return an empty list.
+ *
+ * This is typically used by built-in commands such as add.c, in order
+ * to normalize argv arguments provided to the built-in into a list of
+ * paths to process, all relative to the root of the working tree.
+ */
 const char **get_pathspec(const char *prefix, const char **pathspec)
 {
 	const char *entry = *pathspec;
@@ -147,8 +295,7 @@ const char **get_pathspec(const char *prefix, const char **pathspec)
 	dst = pathspec;
 	prefixlen = prefix ? strlen(prefix) : 0;
 	while (*src) {
-		const char *p = prefix_path(prefix, prefixlen, *src);
-		*(dst++) = p;
+		*(dst++) = prefix_pathspec(prefix, prefixlen, *src);
 		src++;
 	}
 	*dst = NULL;
@@ -168,7 +315,7 @@ const char **get_pathspec(const char *prefix, const char **pathspec)
  *    a proper "ref:", or a regular file HEAD that has a properly
  *    formatted sha1 object name.
  */
-static int is_git_directory(const char *suspect)
+int is_git_directory(const char *suspect)
 {
 	char path[PATH_MAX];
 	size_t len = strlen(suspect);
@@ -268,14 +415,14 @@ static int check_repository_format_gently(const char *gitdir, int *nongit_ok)
  * Try to read the location of the git directory from the .git file,
  * return path to git directory if found.
  */
-const char *read_gitfile_gently(const char *path)
+const char *read_gitfile(const char *path)
 {
 	char *buf;
 	char *dir;
 	const char *slash;
 	struct stat st;
 	int fd;
-	size_t len;
+	ssize_t len;
 
 	if (stat(path, &st))
 		return NULL;
@@ -330,7 +477,7 @@ static const char *setup_explicit_git_dir(const char *gitdirenv,
 	if (PATH_MAX - 40 < strlen(gitdirenv))
 		die("'$%s' too big", GIT_DIR_ENVIRONMENT);
 
-	gitfile = (char*)read_gitfile_gently(gitdirenv);
+	gitfile = (char*)read_gitfile(gitdirenv);
 	if (gitfile) {
 		gitfile = xstrdup(gitfile);
 		gitdirenv = gitfile;
@@ -378,6 +525,12 @@ static const char *setup_explicit_git_dir(const char *gitdirenv,
 			set_git_work_tree(core_worktree);
 		}
 	}
+	else if (!git_env_bool(GIT_IMPLICIT_WORK_TREE_ENVIRONMENT, 1)) {
+		/* #16d */
+		set_git_dir(gitdirenv);
+		free(gitfile);
+		return NULL;
+	}
 	else /* #2, #10 */
 		set_git_work_tree(".");
 
@@ -456,6 +609,8 @@ static const char *setup_bare_git_dir(char *cwd, int offset, int len, int *nongi
 	if (check_repository_format_gently(".", nongit_ok))
 		return NULL;
 
+	setenv(GIT_IMPLICIT_WORK_TREE_ENVIRONMENT, "0", 1);
+
 	/* --work-tree is set without --git-dir; use discovered one */
 	if (getenv(GIT_WORK_TREE_ENVIRONMENT) || git_work_tree_cfg) {
 		const char *gitdir;
@@ -490,27 +645,61 @@ static const char *setup_nongit(const char *cwd, int *nongit_ok)
 	return NULL;
 }
 
-static dev_t get_device_or_die(const char *path, const char *prefix)
+static dev_t get_device_or_die(const char *path, const char *prefix, int prefix_len)
 {
 	struct stat buf;
-	if (stat(path, &buf))
-		die_errno("failed to stat '%s%s%s'",
+	if (stat(path, &buf)) {
+		die_errno("failed to stat '%*s%s%s'",
+				prefix_len,
 				prefix ? prefix : "",
 				prefix ? "/" : "", path);
+	}
 	return buf.st_dev;
 }
 
 /*
+ * A "string_list_each_func_t" function that canonicalizes an entry
+ * from GIT_CEILING_DIRECTORIES using real_path_if_valid(), or
+ * discards it if unusable.  The presence of an empty entry in
+ * GIT_CEILING_DIRECTORIES turns off canonicalization for all
+ * subsequent entries.
+ */
+static int canonicalize_ceiling_entry(struct string_list_item *item,
+				      void *cb_data)
+{
+	int *empty_entry_found = cb_data;
+	char *ceil = item->string;
+
+	if (!*ceil) {
+		*empty_entry_found = 1;
+		return 0;
+	} else if (!is_absolute_path(ceil)) {
+		return 0;
+	} else if (*empty_entry_found) {
+		/* Keep entry but do not canonicalize it */
+		return 1;
+	} else {
+		const char *real_path = real_path_if_valid(ceil);
+		if (!real_path)
+			return 0;
+		free(item->string);
+		item->string = xstrdup(real_path);
+		return 1;
+	}
+}
+
+/*
  * We cannot decide in this function whether we are in the work tree or
  * not, since the config can only be read _after_ this function was called.
  */
 static const char *setup_git_directory_gently_1(int *nongit_ok)
 {
 	const char *env_ceiling_dirs = getenv(CEILING_DIRECTORIES_ENVIRONMENT);
+	struct string_list ceiling_dirs = STRING_LIST_INIT_DUP;
 	static char cwd[PATH_MAX+1];
 	const char *gitdirenv, *ret;
 	char *gitfile;
-	int len, offset, ceil_offset;
+	int len, offset, offset_parent, ceil_offset = -1;
 	dev_t current_device = 0;
 	int one_filesystem = 1;
 
@@ -535,7 +724,16 @@ static const char *setup_git_directory_gently_1(int *nongit_ok)
 	if (gitdirenv)
 		return setup_explicit_git_dir(gitdirenv, cwd, len, nongit_ok);
 
-	ceil_offset = longest_ancestor_length(cwd, env_ceiling_dirs);
+	if (env_ceiling_dirs) {
+		int empty_entry_found = 0;
+
+		string_list_split(&ceiling_dirs, env_ceiling_dirs, PATH_SEP, -1);
+		filter_string_list(&ceiling_dirs, 0,
+				   canonicalize_ceiling_entry, &empty_entry_found);
+		ceil_offset = longest_ancestor_length(cwd, &ceiling_dirs);
+		string_list_clear(&ceiling_dirs, 0);
+	}
+
 	if (ceil_offset < 0 && has_dos_drive_prefix(cwd))
 		ceil_offset = 1;
 
@@ -552,9 +750,9 @@ static const char *setup_git_directory_gently_1(int *nongit_ok)
 	 */
 	one_filesystem = !git_env_bool("GIT_DISCOVERY_ACROSS_FILESYSTEM", 0);
 	if (one_filesystem)
-		current_device = get_device_or_die(".", NULL);
+		current_device = get_device_or_die(".", NULL, 0);
 	for (;;) {
-		gitfile = (char*)read_gitfile_gently(DEFAULT_GIT_DIR_ENVIRONMENT);
+		gitfile = (char*)read_gitfile(DEFAULT_GIT_DIR_ENVIRONMENT);
 		if (gitfile)
 			gitdirenv = gitfile = xstrdup(gitfile);
 		else {
@@ -574,11 +772,12 @@ static const char *setup_git_directory_gently_1(int *nongit_ok)
 		if (is_git_directory("."))
 			return setup_bare_git_dir(cwd, offset, len, nongit_ok);
 
-		while (--offset > ceil_offset && cwd[offset] != '/');
-		if (offset <= ceil_offset)
+		offset_parent = offset;
+		while (--offset_parent > ceil_offset && cwd[offset_parent] != '/');
+		if (offset_parent <= ceil_offset)
 			return setup_nongit(cwd, nongit_ok);
 		if (one_filesystem) {
-			dev_t parent_device = get_device_or_die("..", cwd);
+			dev_t parent_device = get_device_or_die("..", cwd, offset);
 			if (parent_device != current_device) {
 				if (nongit_ok) {
 					if (chdir(cwd))
@@ -587,7 +786,7 @@ static const char *setup_git_directory_gently_1(int *nongit_ok)
 					return NULL;
 				}
 				cwd[offset] = '\0';
-				die("Not a git repository (or any parent up to mount parent %s)\n"
+				die("Not a git repository (or any parent up to mount point %s)\n"
 				"Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).", cwd);
 			}
 		}
@@ -595,6 +794,7 @@ static const char *setup_git_directory_gently_1(int *nongit_ok)
 			cwd[offset] = '\0';
 			die_errno("Cannot change to '%s/..'", cwd);
 		}
+		offset = offset_parent;
 	}
 }
 
@@ -603,6 +803,11 @@ const char *setup_git_directory_gently(int *nongit_ok)
 	const char *prefix;
 
 	prefix = setup_git_directory_gently_1(nongit_ok);
+	if (prefix)
+		setenv(GIT_PREFIX_ENVIRONMENT, prefix, 1);
+	else
+		setenv(GIT_PREFIX_ENVIRONMENT, "", 1);
+
 	if (startup_info) {
 		startup_info->have_repository = !nongit_ok || !*nongit_ok;
 		startup_info->prefix = prefix;
@@ -696,3 +901,10 @@ const char *setup_git_directory(void)
 {
 	return setup_git_directory_gently(NULL);
 }
+
+const char *resolve_gitdir(const char *suspect)
+{
+	if (is_git_directory(suspect))
+		return suspect;
+	return read_gitfile(suspect);
+}