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()'

1 files changed, 84 insertions, 107 deletions

diff --git a/dir.c b/dir.c
index d872cc157..4ac63bc94 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) {