Merge branch 'bw/pathspec-cleanup'

Code clean-up in the pathspec API.

* bw/pathspec-cleanup:
  pathspec: rename prefix_pathspec to init_pathspec_item
  pathspec: small readability changes
  pathspec: create strip submodule slash helpers
  pathspec: create parse_element_magic helper
  pathspec: create parse_long_magic function
  pathspec: create parse_short_magic function
  pathspec: factor global magic into its own function
  pathspec: simpler logic to prefix original pathspec elements
  pathspec: always show mnemonic and name in unsupported_magic
  pathspec: remove unused variable from unsupported_magic
  pathspec: copy and free owned memory
  pathspec: remove the deprecated get_pathspec function
  ls-tree: convert show_recursive to use the pathspec struct interface
  dir: convert fill_directory to use the pathspec struct interface
  dir: remove struct path_simplify
  mv: remove use of deprecated 'get_pathspec()'

7 files changed, 388 insertions, 357 deletions

diff --git a/Documentation/technical/api-setup.txt b/Documentation/technical/api-setup.txt
index 540e455689..eb1fa9853e 100644
--- a/Documentation/technical/api-setup.txt
+++ b/Documentation/technical/api-setup.txt
@@ -27,8 +27,6 @@ parse_pathspec(). This function takes several arguments:
 
 - prefix and args come from cmd_* functions
 
-get_pathspec() is obsolete and should never be used in new code.
-
 parse_pathspec() helps catch unsupported features and reject them
 politely. At a lower level, different pathspec-related functions may
 not support the same set of features. Such pathspec-sensitive
diff --git a/builtin/ls-tree.c b/builtin/ls-tree.c
index 0e30d86230..d7ebeb4ce6 100644
--- a/builtin/ls-tree.c
+++ b/builtin/ls-tree.c
@@ -31,21 +31,18 @@ static const  char * const ls_tree_usage[] = {
 
 static int show_recursive(const char *base, int baselen, const char *pathname)
 {
-	const char **s;
+	int i;
 
 	if (ls_options & LS_RECURSIVE)
 		return 1;
 
-	s = pathspec._raw;
-	if (!s)
+	if (!pathspec.nr)
 		return 0;
 
-	for (;;) {
-		const char *spec = *s++;
+	for (i = 0; i < pathspec.nr; i++) {
+		const char *spec = pathspec.items[i].match;
 		int len, speclen;
 
-		if (!spec)
-			return 0;
 		if (strncmp(base, spec, baselen))
 			continue;
 		len = strlen(pathname);
@@ -59,6 +56,7 @@ static int show_recursive(const char *base, int baselen, const char *pathname)
 			continue;
 		return 1;
 	}
+	return 0;
 }
 
 static int show_tree(const unsigned char *sha1, struct strbuf *base,
@@ -175,8 +173,8 @@ int cmd_ls_tree(int argc, const char **argv, const char *prefix)
 	 * cannot be lifted until it is converted to use
 	 * match_pathspec() or tree_entry_interesting()
 	 */
-	parse_pathspec(&pathspec, PATHSPEC_GLOB | PATHSPEC_ICASE |
-				  PATHSPEC_EXCLUDE,
+	parse_pathspec(&pathspec, PATHSPEC_ALL_MAGIC &
+				  ~(PATHSPEC_FROMTOP | PATHSPEC_LITERAL),
 		       PATHSPEC_PREFER_CWD,
 		       prefix, argv + 1);
 	for (i = 0; i < pathspec.nr; i++)
diff --git a/builtin/mv.c b/builtin/mv.c
index 43adf92ba6..61d20037ad 100644
--- a/builtin/mv.c
+++ b/builtin/mv.c
@@ -4,6 +4,7 @@
  * Copyright (C) 2006 Johannes Schindelin
  */
 #include "builtin.h"
+#include "pathspec.h"
 #include "lockfile.h"
 #include "dir.h"
 #include "cache-tree.h"
@@ -19,31 +20,42 @@ static const char * const builtin_mv_usage[] = {
 #define DUP_BASENAME 1
 #define KEEP_TRAILING_SLASH 2
 
-static const char **internal_copy_pathspec(const char *prefix,
-					   const char **pathspec,
-					   int count, unsigned flags)
+static const char **internal_prefix_pathspec(const char *prefix,
+					     const char **pathspec,
+					     int count, unsigned flags)
 {
 	int i;
 	const char **result;
+	int prefixlen = prefix ? strlen(prefix) : 0;
 	ALLOC_ARRAY(result, count + 1);
-	COPY_ARRAY(result, pathspec, count);
-	result[count] = NULL;
+
+	/* Create an intermediate copy of the pathspec based on the flags */
 	for (i = 0; i < count; i++) {
-		int length = strlen(result[i]);
+		int length = strlen(pathspec[i]);
 		int to_copy = length;
+		char *it;
 		while (!(flags & KEEP_TRAILING_SLASH) &&
-		       to_copy > 0 && is_dir_sep(result[i][to_copy - 1]))
+		       to_copy > 0 && is_dir_sep(pathspec[i][to_copy - 1]))
 			to_copy--;
-		if (to_copy != length || flags & DUP_BASENAME) {
-			char *it = xmemdupz(result[i], to_copy);
-			if (flags & DUP_BASENAME) {
-				result[i] = xstrdup(basename(it));
-				free(it);
-			} else
-				result[i] = it;
+
+		it = xmemdupz(pathspec[i], to_copy);
+		if (flags & DUP_BASENAME) {
+			result[i] = xstrdup(basename(it));
+			free(it);
+		} else {
+			result[i] = it;
 		}
 	}
-	return get_pathspec(prefix, result);
+	result[count] = NULL;
+
+	/* Prefix the pathspec and free the old intermediate strings */
+	for (i = 0; i < count; i++) {
+		const char *match = prefix_path(prefix, prefixlen, result[i]);
+		free((char *) result[i]);
+		result[i] = match;
+	}
+
+	return result;
 }
 
 static const char *add_slash(const char *path)
@@ -130,7 +142,7 @@ int cmd_mv(int argc, const char **argv, const char *prefix)
 	if (read_cache() < 0)
 		die(_("index file corrupt"));
 
-	source = internal_copy_pathspec(prefix, argv, argc, 0);
+	source = internal_prefix_pathspec(prefix, argv, argc, 0);
 	modes = xcalloc(argc, sizeof(enum update_mode));
 	/*
 	 * Keep trailing slash, needed to let
@@ -140,16 +152,16 @@ int cmd_mv(int argc, const char **argv, const char *prefix)
 	flags = KEEP_TRAILING_SLASH;
 	if (argc == 1 && is_directory(argv[0]) && !is_directory(argv[1]))
 		flags = 0;
-	dest_path = internal_copy_pathspec(prefix, argv + argc, 1, flags);
+	dest_path = internal_prefix_pathspec(prefix, argv + argc, 1, flags);
 	submodule_gitfile = xcalloc(argc, sizeof(char *));
 
 	if (dest_path[0][0] == '\0')
 		/* special case: "." was normalized to "" */
-		destination = internal_copy_pathspec(dest_path[0], argv, argc, DUP_BASENAME);
+		destination = internal_prefix_pathspec(dest_path[0], argv, argc, DUP_BASENAME);
 	else if (!lstat(dest_path[0], &st) &&
 			S_ISDIR(st.st_mode)) {
 		dest_path[0] = add_slash(dest_path[0]);
-		destination = internal_copy_pathspec(dest_path[0], argv, argc, DUP_BASENAME);
+		destination = internal_prefix_pathspec(dest_path[0], argv, argc, DUP_BASENAME);
 	} else {
 		if (argc != 1)
 			die(_("destination '%s' is not a directory"), dest_path[0]);
diff --git a/cache.h b/cache.h
index c74df70127..40f7ddd247 100644
--- a/cache.h
+++ b/cache.h
@@ -514,7 +514,6 @@ extern void set_git_work_tree(const char *tree);
 
 #define ALTERNATE_DB_ENVIRONMENT "GIT_ALTERNATE_OBJECT_DIRECTORIES"
 
-extern const char **get_pathspec(const char *prefix, const char **pathspec);
 extern void setup_work_tree(void);
 extern const char *setup_git_directory_gently(int *);
 extern const char *setup_git_directory(void);
diff --git a/dir.c b/dir.c
index d872cc1570..4ac63bc940 100644
--- a/dir.c
+++ b/dir.c
@@ -16,11 +16,6 @@
 #include "varint.h"
 #include "ewah/ewok.h"
 
-struct path_simplify {
-	int len;
-	const char *path;
-};
-
 /*
  * Tells read_directory_recursive how a file or directory should be treated.
  * Values are ordered by significance, e.g. if a directory contains both
@@ -50,7 +45,7 @@ struct cached_dir {
 
 static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 	const char *path, int len, struct untracked_cache_dir *untracked,
-	int check_only, const struct path_simplify *simplify);
+	int check_only, const struct pathspec *pathspec);
 static int get_dtype(struct dirent *de, const char *path, int len);
 
 int fspathcmp(const char *a, const char *b)
@@ -179,17 +174,21 @@ char *common_prefix(const struct pathspec *pathspec)
 
 int fill_directory(struct dir_struct *dir, const struct pathspec *pathspec)
 {
-	size_t len;
+	char *prefix;
+	size_t prefix_len;
 
 	/*
 	 * Calculate common prefix for the pathspec, and
 	 * use that to optimize the directory walk
 	 */
-	len = common_prefix_len(pathspec);
+	prefix = common_prefix(pathspec);
+	prefix_len = prefix ? strlen(prefix) : 0;
 
 	/* Read the directory and prune it */
-	read_directory(dir, pathspec->nr ? pathspec->_raw[0] : "", len, pathspec);
-	return len;
+	read_directory(dir, prefix, prefix_len, pathspec);
+
+	free(prefix);
+	return prefix_len;
 }
 
 int within_depth(const char *name, int namelen,
@@ -1312,7 +1311,7 @@ static enum exist_status directory_exists_in_index(const char *dirname, int len)
 static enum path_treatment treat_directory(struct dir_struct *dir,
 	struct untracked_cache_dir *untracked,
 	const char *dirname, int len, int baselen, int exclude,
-	const struct path_simplify *simplify)
+	const struct pathspec *pathspec)
 {
 	/* The "len-1" is to strip the final '/' */
 	switch (directory_exists_in_index(dirname, len-1)) {
@@ -1341,7 +1340,7 @@ static enum path_treatment treat_directory(struct dir_struct *dir,
 	untracked = lookup_untracked(dir->untracked, untracked,
 				     dirname + baselen, len - baselen);
 	return read_directory_recursive(dir, dirname, len,
-					untracked, 1, simplify);
+					untracked, 1, pathspec);
 }
 
 /*
@@ -1349,24 +1348,33 @@ static enum path_treatment treat_directory(struct dir_struct *dir,
  * reading - if the path cannot possibly be in the pathspec,
  * return true, and we'll skip it early.
  */
-static int simplify_away(const char *path, int pathlen, const struct path_simplify *simplify)
+static int simplify_away(const char *path, int pathlen,
+			 const struct pathspec *pathspec)
 {
-	if (simplify) {
-		for (;;) {
-			const char *match = simplify->path;
-			int len = simplify->len;
+	int i;
 
-			if (!match)
-				break;
-			if (len > pathlen)
-				len = pathlen;
-			if (!memcmp(path, match, len))
-				return 0;
-			simplify++;
-		}
-		return 1;
+	if (!pathspec || !pathspec->nr)
+		return 0;
+
+	GUARD_PATHSPEC(pathspec,
+		       PATHSPEC_FROMTOP |
+		       PATHSPEC_MAXDEPTH |
+		       PATHSPEC_LITERAL |
+		       PATHSPEC_GLOB |
+		       PATHSPEC_ICASE |
+		       PATHSPEC_EXCLUDE);
+
+	for (i = 0; i < pathspec->nr; i++) {
+		const struct pathspec_item *item = &pathspec->items[i];
+		int len = item->nowildcard_len;
+
+		if (len > pathlen)
+			len = pathlen;
+		if (!ps_strncmp(item, item->match, path, len))
+			return 0;
 	}
-	return 0;
+
+	return 1;
 }
 
 /*
@@ -1380,19 +1388,33 @@ static int simplify_away(const char *path, int pathlen, const struct path_simpli
  *   2. the path is a directory prefix of some element in the
  *      pathspec
  */
-static int exclude_matches_pathspec(const char *path, int len,
-		const struct path_simplify *simplify)
-{
-	if (simplify) {
-		for (; simplify->path; simplify++) {
-			if (len == simplify->len
-			    && !memcmp(path, simplify->path, len))
-				return 1;
-			if (len < simplify->len
-			    && simplify->path[len] == '/'
-			    && !memcmp(path, simplify->path, len))
-				return 1;
-		}
+static int exclude_matches_pathspec(const char *path, int pathlen,
+				    const struct pathspec *pathspec)
+{
+	int i;
+
+	if (!pathspec || !pathspec->nr)
+		return 0;
+
+	GUARD_PATHSPEC(pathspec,
+		       PATHSPEC_FROMTOP |
+		       PATHSPEC_MAXDEPTH |
+		       PATHSPEC_LITERAL |
+		       PATHSPEC_GLOB |
+		       PATHSPEC_ICASE |
+		       PATHSPEC_EXCLUDE);
+
+	for (i = 0; i < pathspec->nr; i++) {
+		const struct pathspec_item *item = &pathspec->items[i];
+		int len = item->nowildcard_len;
+
+		if (len == pathlen &&
+		    !ps_strncmp(item, item->match, path, pathlen))
+			return 1;
+		if (len > pathlen &&
+		    item->match[pathlen] == '/' &&
+		    !ps_strncmp(item, item->match, path, pathlen))
+			return 1;
 	}
 	return 0;
 }
@@ -1460,7 +1482,7 @@ static enum path_treatment treat_one_path(struct dir_struct *dir,
 					  struct untracked_cache_dir *untracked,
 					  struct strbuf *path,
 					  int baselen,
-					  const struct path_simplify *simplify,
+					  const struct pathspec *pathspec,
 					  int dtype, struct dirent *de)
 {
 	int exclude;
@@ -1512,7 +1534,7 @@ static enum path_treatment treat_one_path(struct dir_struct *dir,
 	case DT_DIR:
 		strbuf_addch(path, '/');
 		return treat_directory(dir, untracked, path->buf, path->len,
-				       baselen, exclude, simplify);
+				       baselen, exclude, pathspec);
 	case DT_REG:
 	case DT_LNK:
 		return exclude ? path_excluded : path_untracked;
@@ -1524,7 +1546,7 @@ static enum path_treatment treat_path_fast(struct dir_struct *dir,
 					   struct cached_dir *cdir,
 					   struct strbuf *path,
 					   int baselen,
-					   const struct path_simplify *simplify)
+					   const struct pathspec *pathspec)
 {
 	strbuf_setlen(path, baselen);
 	if (!cdir->ucd) {
@@ -1541,7 +1563,7 @@ static enum path_treatment treat_path_fast(struct dir_struct *dir,
 		 * with check_only set.
 		 */
 		return read_directory_recursive(dir, path->buf, path->len,
-						cdir->ucd, 1, simplify);
+						cdir->ucd, 1, pathspec);
 	/*
 	 * We get path_recurse in the first run when
 	 * directory_exists_in_index() returns index_nonexistent. We
@@ -1556,23 +1578,23 @@ static enum path_treatment treat_path(struct dir_struct *dir,
 				      struct cached_dir *cdir,
 				      struct strbuf *path,
 				      int baselen,
-				      const struct path_simplify *simplify)
+				      const struct pathspec *pathspec)
 {
 	int dtype;
 	struct dirent *de = cdir->de;
 
 	if (!de)
 		return treat_path_fast(dir, untracked, cdir, path,
-				       baselen, simplify);
+				       baselen, pathspec);
 	if (is_dot_or_dotdot(de->d_name) || !strcmp(de->d_name, ".git"))
 		return path_none;
 	strbuf_setlen(path, baselen);
 	strbuf_addstr(path, de->d_name);
-	if (simplify_away(path->buf, path->len, simplify))
+	if (simplify_away(path->buf, path->len, pathspec))
 		return path_none;
 
 	dtype = DTYPE(de);
-	return treat_one_path(dir, untracked, path, baselen, simplify, dtype, de);
+	return treat_one_path(dir, untracked, path, baselen, pathspec, dtype, de);
 }
 
 static void add_untracked(struct untracked_cache_dir *dir, const char *name)
@@ -1703,7 +1725,7 @@ static void close_cached_dir(struct cached_dir *cdir)
 static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 				    const char *base, int baselen,
 				    struct untracked_cache_dir *untracked, int check_only,
-				    const struct path_simplify *simplify)
+				    const struct pathspec *pathspec)
 {
 	struct cached_dir cdir;
 	enum path_treatment state, subdir_state, dir_state = path_none;
@@ -1719,7 +1741,8 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 
 	while (!read_cached_dir(&cdir)) {
 		/* check how the file or directory should be treated */
-		state = treat_path(dir, untracked, &cdir, &path, baselen, simplify);
+		state = treat_path(dir, untracked, &cdir, &path,
+				   baselen, pathspec);
 
 		if (state > dir_state)
 			dir_state = state;
@@ -1731,8 +1754,9 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 					      path.buf + baselen,
 					      path.len - baselen);
 			subdir_state =
-				read_directory_recursive(dir, path.buf, path.len,
-							 ud, check_only, simplify);
+				read_directory_recursive(dir, path.buf,
+							 path.len, ud,
+							 check_only, pathspec);
 			if (subdir_state > dir_state)
 				dir_state = subdir_state;
 		}
@@ -1756,7 +1780,7 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 			else if ((dir->flags & DIR_SHOW_IGNORED_TOO) ||
 				((dir->flags & DIR_COLLECT_IGNORED) &&
 				exclude_matches_pathspec(path.buf, path.len,
-					simplify)))
+							 pathspec)))
 				dir_add_ignored(dir, path.buf, path.len);
 			break;
 
@@ -1787,36 +1811,9 @@ static int cmp_name(const void *p1, const void *p2)
 	return name_compare(e1->name, e1->len, e2->name, e2->len);
 }
 
-static struct path_simplify *create_simplify(const char **pathspec)
-{
-	int nr, alloc = 0;
-	struct path_simplify *simplify = NULL;
-
-	if (!pathspec)
-		return NULL;
-
-	for (nr = 0 ; ; nr++) {
-		const char *match;
-		ALLOC_GROW(simplify, nr + 1, alloc);
-		match = *pathspec++;
-		if (!match)
-			break;
-		simplify[nr].path = match;
-		simplify[nr].len = simple_length(match);
-	}
-	simplify[nr].path = NULL;
-	simplify[nr].len = 0;
-	return simplify;
-}
-
-static void free_simplify(struct path_simplify *simplify)
-{
-	free(simplify);
-}
-
 static int treat_leading_path(struct dir_struct *dir,
 			      const char *path, int len,
-			      const struct path_simplify *simplify)
+			      const struct pathspec *pathspec)
 {
 	struct strbuf sb = STRBUF_INIT;
 	int baselen, rc = 0;
@@ -1840,9 +1837,9 @@ static int treat_leading_path(struct dir_struct *dir,
 		strbuf_add(&sb, path, baselen);
 		if (!is_directory(sb.buf))
 			break;
-		if (simplify_away(sb.buf, sb.len, simplify))
+		if (simplify_away(sb.buf, sb.len, pathspec))
 			break;
-		if (treat_one_path(dir, NULL, &sb, baselen, simplify,
+		if (treat_one_path(dir, NULL, &sb, baselen, pathspec,
 				   DT_DIR, NULL) == path_none)
 			break; /* do not recurse into it */
 		if (len <= baselen) {
@@ -2010,33 +2007,14 @@ static struct untracked_cache_dir *validate_untracked_cache(struct dir_struct *d
 	return root;
 }
 
-int read_directory(struct dir_struct *dir, const char *path, int len, const struct pathspec *pathspec)
+int read_directory(struct dir_struct *dir, const char *path,
+		   int len, const struct pathspec *pathspec)
 {
-	struct path_simplify *simplify;
 	struct untracked_cache_dir *untracked;
 
-	/*
-	 * Check out create_simplify()
-	 */
-	if (pathspec)
-		GUARD_PATHSPEC(pathspec,
-			       PATHSPEC_FROMTOP |
-			       PATHSPEC_MAXDEPTH |
-			       PATHSPEC_LITERAL |
-			       PATHSPEC_GLOB |
-			       PATHSPEC_ICASE |
-			       PATHSPEC_EXCLUDE);
-
 	if (has_symlink_leading_path(path, len))
 		return dir->nr;
 
-	/*
-	 * exclude patterns are treated like positive ones in
-	 * create_simplify. Usually exclude patterns should be a
-	 * subset of positive ones, which has no impacts on
-	 * create_simplify().
-	 */
-	simplify = create_simplify(pathspec ? pathspec->_raw : NULL);
 	untracked = validate_untracked_cache(dir, len, pathspec);
 	if (!untracked)
 		/*
@@ -2044,9 +2022,8 @@ int read_directory(struct dir_struct *dir, const char *path, int len, const stru
 		 * e.g. prep_exclude()
 		 */
 		dir->untracked = NULL;
-	if (!len || treat_leading_path(dir, path, len, simplify))
-		read_directory_recursive(dir, path, len, untracked, 0, simplify);
-	free_simplify(simplify);
+	if (!len || treat_leading_path(dir, path, len, pathspec))
+		read_directory_recursive(dir, path, len, untracked, 0, pathspec);
 	QSORT(dir->entries, dir->nr, cmp_name);
 	QSORT(dir->ignored, dir->ignored_nr, cmp_name);
 	if (dir->untracked) {
diff --git a/pathspec.c b/pathspec.c
index 22ca74a126..ff2509ddd1 100644
--- a/pathspec.c
+++ b/pathspec.c
@@ -67,20 +67,19 @@ static struct pathspec_magic {
 	char mnemonic; /* this cannot be ':'! */
 	const char *name;
 } pathspec_magic[] = {
-	{ PATHSPEC_FROMTOP, '/', "top" },
-	{ PATHSPEC_LITERAL,   0, "literal" },
-	{ PATHSPEC_GLOB,   '\0', "glob" },
-	{ PATHSPEC_ICASE,  '\0', "icase" },
-	{ PATHSPEC_EXCLUDE, '!', "exclude" },
+	{ PATHSPEC_FROMTOP,  '/', "top" },
+	{ PATHSPEC_LITERAL, '\0', "literal" },
+	{ PATHSPEC_GLOB,    '\0', "glob" },
+	{ PATHSPEC_ICASE,   '\0', "icase" },
+	{ PATHSPEC_EXCLUDE,  '!', "exclude" },
 };
 
-static void prefix_short_magic(struct strbuf *sb, int prefixlen,
-			       unsigned short_magic)
+static void prefix_magic(struct strbuf *sb, int prefixlen, unsigned magic)
 {
 	int i;
 	strbuf_addstr(sb, ":(");
 	for (i = 0; i < ARRAY_SIZE(pathspec_magic); i++)
-		if (short_magic & pathspec_magic[i].bit) {
+		if (magic & pathspec_magic[i].bit) {
 			if (sb->buf[sb->len - 1] != '(')
 				strbuf_addch(sb, ',');
 			strbuf_addstr(sb, pathspec_magic[i].name);
@@ -88,54 +87,61 @@ static void prefix_short_magic(struct strbuf *sb, int prefixlen,
 	strbuf_addf(sb, ",prefix:%d)", prefixlen);
 }
 
-/*
- * Take an element of a pathspec and check for magic signatures.
- * Append the result to the prefix. Return the magic bitmap.
- *
- * 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 unsigned prefix_pathspec(struct pathspec_item *item,
-				unsigned *p_short_magic,
-				const char **raw, unsigned flags,
-				const char *prefix, int prefixlen,
-				const char *elt)
+static inline int get_literal_global(void)
 {
-	static int literal_global = -1;
-	static int glob_global = -1;
-	static int noglob_global = -1;
-	static int icase_global = -1;
-	unsigned magic = 0, short_magic = 0, global_magic = 0;
-	const char *copyfrom = elt, *long_magic_end = NULL;
-	char *match;
-	int i, pathspec_prefix = -1;
+	static int literal = -1;
+
+	if (literal < 0)
+		literal = git_env_bool(GIT_LITERAL_PATHSPECS_ENVIRONMENT, 0);
+
+	return literal;
+}
+
+static inline int get_glob_global(void)
+{
+	static int glob = -1;
+
+	if (glob < 0)
+		glob = git_env_bool(GIT_GLOB_PATHSPECS_ENVIRONMENT, 0);
+
+	return glob;
+}
+
+static inline int get_noglob_global(void)
+{
+	static int noglob = -1;
+
+	if (noglob < 0)
+		noglob = git_env_bool(GIT_NOGLOB_PATHSPECS_ENVIRONMENT, 0);
+
+	return noglob;
+}
+
+static inline int get_icase_global(void)
+{
+	static int icase = -1;
 
-	if (literal_global < 0)
-		literal_global = git_env_bool(GIT_LITERAL_PATHSPECS_ENVIRONMENT, 0);
-	if (literal_global)
+	if (icase < 0)
+		icase = git_env_bool(GIT_ICASE_PATHSPECS_ENVIRONMENT, 0);
+
+	return icase;
+}
+
+static int get_global_magic(int element_magic)
+{
+	int global_magic = 0;
+
+	if (get_literal_global())
 		global_magic |= PATHSPEC_LITERAL;
 
-	if (glob_global < 0)
-		glob_global = git_env_bool(GIT_GLOB_PATHSPECS_ENVIRONMENT, 0);
-	if (glob_global)
+	/* --glob-pathspec is overridden by :(literal) */
+	if (get_glob_global() && !(element_magic & PATHSPEC_LITERAL))
 		global_magic |= PATHSPEC_GLOB;
 
-	if (noglob_global < 0)
-		noglob_global = git_env_bool(GIT_NOGLOB_PATHSPECS_ENVIRONMENT, 0);
-
-	if (glob_global && noglob_global)
+	if (get_glob_global() && get_noglob_global())
 		die(_("global 'glob' and 'noglob' pathspec settings are incompatible"));
 
-
-	if (icase_global < 0)
-		icase_global = git_env_bool(GIT_ICASE_PATHSPECS_ENVIRONMENT, 0);
-	if (icase_global)
+	if (get_icase_global())
 		global_magic |= PATHSPEC_ICASE;
 
 	if ((global_magic & PATHSPEC_LITERAL) &&
@@ -143,84 +149,177 @@ static unsigned prefix_pathspec(struct pathspec_item *item,
 		die(_("global 'literal' pathspec setting is incompatible "
 		      "with all other global pathspec settings"));
 
-	if (flags & PATHSPEC_LITERAL_PATH)
-		global_magic = 0;
+	/* --noglob-pathspec adds :(literal) _unless_ :(glob) is specified */
+	if (get_noglob_global() && !(element_magic & PATHSPEC_GLOB))
+		global_magic |= PATHSPEC_LITERAL;
+
+	return global_magic;
+}
 
-	if (elt[0] != ':' || literal_global ||
-	    (flags & PATHSPEC_LITERAL_PATH)) {
-		; /* 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 (starts_with(copyfrom, "prefix:")) {
-					char *endptr;
-					pathspec_prefix = strtol(copyfrom + 7,
-								 &endptr, 10);
-					if (endptr - copyfrom != len)
-						die(_("invalid parameter for pathspec magic 'prefix'"));
-					/* "i" would be wrong, but it does not matter */
-					break;
-				}
+/*
+ * Parse the pathspec element looking for long magic
+ *
+ * saves all magic in 'magic'
+ * if prefix magic is used, save the prefix length in 'prefix_len'
+ * returns the position in 'elem' after all magic has been parsed
+ */
+static const char *parse_long_magic(unsigned *magic, int *prefix_len,
+				    const char *elem)
+{
+	const char *pos;
+	const char *nextat;
+
+	for (pos = elem + 2; *pos && *pos != ')'; pos = nextat) {
+		size_t len = strcspn(pos, ",)");
+		int i;
+
+		if (pos[len] == ',')
+			nextat = pos + len + 1; /* handle ',' */
+		else
+			nextat = pos + len; /* handle ')' and '\0' */
+
+		if (!len)
+			continue;
+
+		if (starts_with(pos, "prefix:")) {
+			char *endptr;
+			*prefix_len = strtol(pos + 7, &endptr, 10);
+			if (endptr - pos != len)
+				die(_("invalid parameter for pathspec magic 'prefix'"));
+			continue;
+		}
+
+		for (i = 0; i < ARRAY_SIZE(pathspec_magic); i++) {
+			if (strlen(pathspec_magic[i].name) == len &&
+			    !strncmp(pathspec_magic[i].name, pos, 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);
-		long_magic_end = copyfrom;
-		copyfrom++;
-	} else {
-		/* shorthand */
-		for (copyfrom = elt + 1;
-		     *copyfrom && *copyfrom != ':';
-		     copyfrom++) {
-			char ch = *copyfrom;
 
-			if (!is_pathspec_magic(ch))
+		if (ARRAY_SIZE(pathspec_magic) <= i)
+			die(_("Invalid pathspec magic '%.*s' in '%s'"),
+			    (int) len, pos, elem);
+	}
+
+	if (*pos != ')')
+		die(_("Missing ')' at the end of pathspec magic in '%s'"),
+		    elem);
+	pos++;
+
+	return pos;
+}
+
+/*
+ * Parse the pathspec element looking for short magic
+ *
+ * saves all magic in 'magic'
+ * returns the position in 'elem' after all magic has been parsed
+ */
+static const char *parse_short_magic(unsigned *magic, const char *elem)
+{
+	const char *pos;
+
+	for (pos = elem + 1; *pos && *pos != ':'; pos++) {
+		char ch = *pos;
+		int i;
+
+		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;
-			for (i = 0; i < ARRAY_SIZE(pathspec_magic); i++)
-				if (pathspec_magic[i].mnemonic == ch) {
-					short_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 (ARRAY_SIZE(pathspec_magic) <= i)
+			die(_("Unimplemented pathspec magic '%c' in '%s'"),
+			    ch, elem);
 	}
 
-	magic |= short_magic;
-	*p_short_magic = short_magic;
+	if (*pos == ':')
+		pos++;
 
-	/* --noglob-pathspec adds :(literal) _unless_ :(glob) is specified */
-	if (noglob_global && !(magic & PATHSPEC_GLOB))
-		global_magic |= PATHSPEC_LITERAL;
+	return pos;
+}
 
-	/* --glob-pathspec is overridden by :(literal) */
-	if ((global_magic & PATHSPEC_GLOB) && (magic & PATHSPEC_LITERAL))
-		global_magic &= ~PATHSPEC_GLOB;
+static const char *parse_element_magic(unsigned *magic, int *prefix_len,
+				       const char *elem)
+{
+	if (elem[0] != ':' || get_literal_global())
+		return elem; /* nothing to do */
+	else if (elem[1] == '(')
+		/* longhand */
+		return parse_long_magic(magic, prefix_len, elem);
+	else
+		/* shorthand */
+		return parse_short_magic(magic, elem);
+}
+
+static void strip_submodule_slash_cheap(struct pathspec_item *item)
+{
+	if (item->len >= 1 && item->match[item->len - 1] == '/') {
+		int i = cache_name_pos(item->match, item->len - 1);
+
+		if (i >= 0 && S_ISGITLINK(active_cache[i]->ce_mode)) {
+			item->len--;
+			item->match[item->len] = '\0';
+		}
+	}
+}
+
+static void strip_submodule_slash_expensive(struct pathspec_item *item)
+{
+	int i;
+
+	for (i = 0; i < active_nr; i++) {
+		struct cache_entry *ce = active_cache[i];
+		int ce_len = ce_namelen(ce);
+
+		if (!S_ISGITLINK(ce->ce_mode))
+			continue;
+
+		if (item->len <= ce_len || item->match[ce_len] != '/' ||
+		    memcmp(ce->name, item->match, ce_len))
+			continue;
+
+		if (item->len == ce_len + 1) {
+			/* strip trailing slash */
+			item->len--;
+			item->match[item->len] = '\0';
+		} else {
+			die(_("Pathspec '%s' is in submodule '%.*s'"),
+			    item->original, ce_len, ce->name);
+		}
+	}
+}
 
-	magic |= global_magic;
+/*
+ * Perform the initialization of a pathspec_item based on a pathspec element.
+ */
+static void init_pathspec_item(struct pathspec_item *item, unsigned flags,
+			       const char *prefix, int prefixlen,
+			       const char *elt)
+{
+	unsigned magic = 0, element_magic = 0;
+	const char *copyfrom = elt;
+	char *match;
+	int pathspec_prefix = -1;
+
+	/* PATHSPEC_LITERAL_PATH ignores magic */
+	if (flags & PATHSPEC_LITERAL_PATH) {
+		magic = PATHSPEC_LITERAL;
+	} else {
+		copyfrom = parse_element_magic(&element_magic,
+					       &pathspec_prefix,
+					       elt);
+		magic |= element_magic;
+		magic |= get_global_magic(element_magic);
+	}
+
+	item->magic = magic;
 
 	if (pathspec_prefix >= 0 &&
 	    (prefixlen || (prefix && *prefix)))
@@ -229,6 +328,7 @@ static unsigned prefix_pathspec(struct pathspec_item *item,
 	if ((magic & PATHSPEC_LITERAL) && (magic & PATHSPEC_GLOB))
 		die(_("%s: 'literal' and 'glob' are incompatible"), elt);
 
+	/* Create match string which will be used for pathspec matching */
 	if (pathspec_prefix >= 0) {
 		match = xstrdup(copyfrom);
 		prefixlen = pathspec_prefix;
@@ -236,69 +336,47 @@ static unsigned prefix_pathspec(struct pathspec_item *item,
 		match = xstrdup(copyfrom);
 		prefixlen = 0;
 	} else {
-		match = prefix_path_gently(prefix, prefixlen, &prefixlen, copyfrom);
+		match = prefix_path_gently(prefix, prefixlen,
+					   &prefixlen, copyfrom);
 		if (!match)
 			die(_("%s: '%s' is outside repository"), elt, copyfrom);
 	}
-	*raw = item->match = match;
+
+	item->match = match;
+	item->len = strlen(item->match);
+	item->prefix = prefixlen;
+
 	/*
 	 * Prefix the pathspec (keep all magic) and assign to
 	 * original. Useful for passing to another command.
 	 */
-	if (flags & PATHSPEC_PREFIX_ORIGIN) {
+	if ((flags & PATHSPEC_PREFIX_ORIGIN) &&
+	    prefixlen && !get_literal_global()) {
 		struct strbuf sb = STRBUF_INIT;
-		if (prefixlen && !literal_global) {
-			/* Preserve the actual prefix length of each pattern */
-			if (short_magic)
-				prefix_short_magic(&sb, prefixlen, short_magic);
-			else if (long_magic_end) {
-				strbuf_add(&sb, elt, long_magic_end - elt);
-				strbuf_addf(&sb, ",prefix:%d)", prefixlen);
-			} else
-				strbuf_addf(&sb, ":(prefix:%d)", prefixlen);
-		}
+
+		/* Preserve the actual prefix length of each pattern */
+		prefix_magic(&sb, prefixlen, element_magic);
+
 		strbuf_addstr(&sb, match);
 		item->original = strbuf_detach(&sb, NULL);
-	} else
-		item->original = elt;
-	item->len = strlen(item->match);
-	item->prefix = prefixlen;
-
-	if ((flags & PATHSPEC_STRIP_SUBMODULE_SLASH_CHEAP) &&
-	    (item->len >= 1 && item->match[item->len - 1] == '/') &&
-	    (i = cache_name_pos(item->match, item->len - 1)) >= 0 &&
-	    S_ISGITLINK(active_cache[i]->ce_mode)) {
-		item->len--;
-		match[item->len] = '\0';
+	} else {
+		item->original = xstrdup(elt);
 	}
 
+	if (flags & PATHSPEC_STRIP_SUBMODULE_SLASH_CHEAP)
+		strip_submodule_slash_cheap(item);
+
 	if (flags & PATHSPEC_STRIP_SUBMODULE_SLASH_EXPENSIVE)
-		for (i = 0; i < active_nr; i++) {
-			struct cache_entry *ce = active_cache[i];
-			int ce_len = ce_namelen(ce);
-
-			if (!S_ISGITLINK(ce->ce_mode))
-				continue;
-
-			if (item->len <= ce_len || match[ce_len] != '/' ||
-			    memcmp(ce->name, match, ce_len))
-				continue;
-			if (item->len == ce_len + 1) {
-				/* strip trailing slash */
-				item->len--;
-				match[item->len] = '\0';
-			} else
-				die (_("Pathspec '%s' is in submodule '%.*s'"),
-				     elt, ce_len, ce->name);
-		}
+		strip_submodule_slash_expensive(item);
 
-	if (magic & PATHSPEC_LITERAL)
+	if (magic & PATHSPEC_LITERAL) {
 		item->nowildcard_len = item->len;
-	else {
+	} else {
 		item->nowildcard_len = simple_length(item->match);
 		if (item->nowildcard_len < prefixlen)
 			item->nowildcard_len = prefixlen;
 	}
+
 	item->flags = 0;
 	if (magic & PATHSPEC_GLOB) {
 		/*
@@ -315,7 +393,6 @@ static unsigned prefix_pathspec(struct pathspec_item *item,
 	/* sanity checks, pathspec matchers assume these are sane */
 	assert(item->nowildcard_len <= item->len &&
 	       item->prefix         <= item->len);
-	return magic;
 }
 
 static int pathspec_item_cmp(const void *a_, const void *b_)
@@ -328,22 +405,22 @@ static int pathspec_item_cmp(const void *a_, const void *b_)
 }
 
 static void NORETURN unsupported_magic(const char *pattern,
-				       unsigned magic,
-				       unsigned short_magic)
+				       unsigned magic)
 {
 	struct strbuf sb = STRBUF_INIT;
-	int i, n;
-	for (n = i = 0; i < ARRAY_SIZE(pathspec_magic); i++) {
+	int i;
+	for (i = 0; i < ARRAY_SIZE(pathspec_magic); i++) {
 		const struct pathspec_magic *m = pathspec_magic + i;
 		if (!(magic & m->bit))
 			continue;
 		if (sb.len)
-			strbuf_addch(&sb, ' ');
-		if (short_magic & m->bit)
-			strbuf_addf(&sb, "'%c'", m->mnemonic);
+			strbuf_addstr(&sb, ", ");
+
+		if (m->mnemonic)
+			strbuf_addf(&sb, _("'%s' (mnemonic: '%c')"),
+				    m->name, m->mnemonic);
 		else
 			strbuf_addf(&sb, "'%s'", m->name);
-		n++;
 	}
 	/*
 	 * We may want to substitute "this command" with a command
@@ -381,8 +458,6 @@ void parse_pathspec(struct pathspec *pathspec,
 
 	/* No arguments with prefix -> prefix pathspec */
 	if (!entry) {
-		static const char *raw[2];
-
 		if (flags & PATHSPEC_PREFER_FULL)
 			return;
 
@@ -390,14 +465,11 @@ void parse_pathspec(struct pathspec *pathspec,
 			die("BUG: PATHSPEC_PREFER_CWD requires arguments");
 
 		pathspec->items = item = xcalloc(1, sizeof(*item));
-		item->match = prefix;
-		item->original = prefix;
+		item->match = xstrdup(prefix);
+		item->original = xstrdup(prefix);
 		item->nowildcard_len = item->len = strlen(prefix);
 		item->prefix = item->len;
-		raw[0] = prefix;
-		raw[1] = NULL;
 		pathspec->nr = 1;
-		pathspec->_raw = raw;
 		return;
 	}
 
@@ -415,25 +487,17 @@ void parse_pathspec(struct pathspec *pathspec,
 	pathspec->nr = n;
 	ALLOC_ARRAY(pathspec->items, n);
 	item = pathspec->items;
-	pathspec->_raw = argv;
 	prefixlen = prefix ? strlen(prefix) : 0;
 
 	for (i = 0; i < n; i++) {
-		unsigned short_magic;
 		entry = argv[i];
 
-		item[i].magic = prefix_pathspec(item + i, &short_magic,
-						argv + i, flags,
-						prefix, prefixlen, entry);
-		if ((flags & PATHSPEC_LITERAL_PATH) &&
-		    !(magic_mask & PATHSPEC_LITERAL))
-			item[i].magic |= PATHSPEC_LITERAL;
+		init_pathspec_item(item + i, flags, prefix, prefixlen, entry);
+
 		if (item[i].magic & PATHSPEC_EXCLUDE)
 			nr_exclude++;
 		if (item[i].magic & magic_mask)
-			unsupported_magic(entry,
-					  item[i].magic & magic_mask,
-					  short_magic);
+			unsupported_magic(entry, item[i].magic & magic_mask);
 
 		if ((flags & PATHSPEC_SYMLINK_LEADING_PATH) &&
 		    has_symlink_leading_path(item[i].match, item[i].len)) {
@@ -457,45 +521,29 @@ void parse_pathspec(struct pathspec *pathspec,
 	}
 }
 
-/*
- * N.B. get_pathspec() is deprecated in favor of the "struct pathspec"
- * based interface - see pathspec.c:parse_pathspec().
- *
- * 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)
-{
-	struct pathspec ps;
-	parse_pathspec(&ps,
-		       PATHSPEC_ALL_MAGIC &
-		       ~(PATHSPEC_FROMTOP | PATHSPEC_LITERAL),
-		       PATHSPEC_PREFER_CWD,
-		       prefix, pathspec);
-	return ps._raw;
-}
-
 void copy_pathspec(struct pathspec *dst, const struct pathspec *src)
 {
+	int i;
+
 	*dst = *src;
 	ALLOC_ARRAY(dst->items, dst->nr);
 	COPY_ARRAY(dst->items, src->items, dst->nr);
+
+	for (i = 0; i < dst->nr; i++) {
+		dst->items[i].match = xstrdup(src->items[i].match);
+		dst->items[i].original = xstrdup(src->items[i].original);
+	}
 }
 
 void clear_pathspec(struct pathspec *pathspec)
 {
+	int i;
+
+	for (i = 0; i < pathspec->nr; i++) {
+		free(pathspec->items[i].match);
+		free(pathspec->items[i].original);
+	}
 	free(pathspec->items);
 	pathspec->items = NULL;
+	pathspec->nr = 0;
 }
diff --git a/pathspec.h b/pathspec.h
index 59809e4793..49fd823ddf 100644
--- a/pathspec.h
+++ b/pathspec.h
@@ -19,15 +19,14 @@
 #define PATHSPEC_ONESTAR 1	/* the pathspec pattern satisfies GFNM_ONESTAR */
 
 struct pathspec {
-	const char **_raw; /* get_pathspec() result, not freed by clear_pathspec() */
 	int nr;
 	unsigned int has_wildcard:1;
 	unsigned int recursive:1;
 	unsigned magic;
 	int max_depth;
 	struct pathspec_item {
-		const char *match;
-		const char *original;
+		char *match;
+		char *original;
 		unsigned magic;
 		int len, prefix;
 		int nowildcard_len;