1 files changed, 206 insertions, 54 deletions

diff --git a/dir.c b/dir.c
index 1c55dc3e36..7c4b45e30e 100644
--- a/dir.c
+++ b/dir.c
@@ -18,6 +18,7 @@
 #include "utf8.h"
 #include "varint.h"
 #include "ewah/ewok.h"
+#include "fsmonitor.h"
 
 /*
  * Tells read_directory_recursive how a file or directory should be treated.
@@ -49,7 +50,7 @@ struct cached_dir {
 static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 	struct index_state *istate, const char *path, int len,
 	struct untracked_cache_dir *untracked,
-	int check_only, const struct pathspec *pathspec);
+	int check_only, int stop_at_first_file, const struct pathspec *pathspec);
 static int get_dtype(struct dirent *de, struct index_state *istate,
 		     const char *path, int len);
 
@@ -220,6 +221,57 @@ int within_depth(const char *name, int namelen,
 	return 1;
 }
 
+/*
+ * Read the contents of the blob with the given OID into a buffer.
+ * Append a trailing LF to the end if the last line doesn't have one.
+ *
+ * Returns:
+ *    -1 when the OID is invalid or unknown or does not refer to a blob.
+ *     0 when the blob is empty.
+ *     1 along with { data, size } of the (possibly augmented) buffer
+ *       when successful.
+ *
+ * Optionally updates the given sha1_stat with the given OID (when valid).
+ */
+static int do_read_blob(const struct object_id *oid,
+			struct sha1_stat *sha1_stat,
+			size_t *size_out,
+			char **data_out)
+{
+	enum object_type type;
+	unsigned long sz;
+	char *data;
+
+	*size_out = 0;
+	*data_out = NULL;
+
+	data = read_sha1_file(oid->hash, &type, &sz);
+	if (!data || type != OBJ_BLOB) {
+		free(data);
+		return -1;
+	}
+
+	if (sha1_stat) {
+		memset(&sha1_stat->stat, 0, sizeof(sha1_stat->stat));
+		hashcpy(sha1_stat->sha1, oid->hash);
+	}
+
+	if (sz == 0) {
+		free(data);
+		return 0;
+	}
+
+	if (data[sz - 1] != '\n') {
+		data = xrealloc(data, st_add(sz, 1));
+		data[sz++] = '\n';
+	}
+
+	*size_out = xsize_t(sz);
+	*data_out = data;
+
+	return 1;
+}
+
 #define DO_MATCH_EXCLUDE   (1<<0)
 #define DO_MATCH_DIRECTORY (1<<1)
 #define DO_MATCH_SUBMODULE (1<<2)
@@ -600,32 +652,22 @@ void add_exclude(const char *string, const char *base,
 	x->el = el;
 }
 
-static void *read_skip_worktree_file_from_index(const struct index_state *istate,
-						const char *path, size_t *size,
-						struct sha1_stat *sha1_stat)
+static int read_skip_worktree_file_from_index(const struct index_state *istate,
+					      const char *path,
+					      size_t *size_out,
+					      char **data_out,
+					      struct sha1_stat *sha1_stat)
 {
 	int pos, len;
-	unsigned long sz;
-	enum object_type type;
-	void *data;
 
 	len = strlen(path);
 	pos = index_name_pos(istate, path, len);
 	if (pos < 0)
-		return NULL;
+		return -1;
 	if (!ce_skip_worktree(istate->cache[pos]))
-		return NULL;
-	data = read_sha1_file(istate->cache[pos]->oid.hash, &type, &sz);
-	if (!data || type != OBJ_BLOB) {
-		free(data);
-		return NULL;
-	}
-	*size = xsize_t(sz);
-	if (sha1_stat) {
-		memset(&sha1_stat->stat, 0, sizeof(sha1_stat->stat));
-		hashcpy(sha1_stat->sha1, istate->cache[pos]->oid.hash);
-	}
-	return data;
+		return -1;
+
+	return do_read_blob(&istate->cache[pos]->oid, sha1_stat, size_out, data_out);
 }
 
 /*
@@ -739,6 +781,10 @@ static void invalidate_directory(struct untracked_cache *uc,
 		dir->dirs[i]->recurse = 0;
 }
 
+static int add_excludes_from_buffer(char *buf, size_t size,
+				    const char *base, int baselen,
+				    struct exclude_list *el);
+
 /*
  * Given a file with name "fname", read it (either from disk, or from
  * an index if 'istate' is non-null), parse it and store the
@@ -754,9 +800,10 @@ static int add_excludes(const char *fname, const char *base, int baselen,
 			struct sha1_stat *sha1_stat)
 {
 	struct stat st;
-	int fd, i, lineno = 1;
+	int r;
+	int fd;
 	size_t size = 0;
-	char *buf, *entry;
+	char *buf;
 
 	fd = open(fname, O_RDONLY);
 	if (fd < 0 || fstat(fd, &st) < 0) {
@@ -764,17 +811,13 @@ static int add_excludes(const char *fname, const char *base, int baselen,
 			warn_on_fopen_errors(fname);
 		else
 			close(fd);
-		if (!istate ||
-		    (buf = read_skip_worktree_file_from_index(istate, fname, &size, sha1_stat)) == NULL)
+		if (!istate)
 			return -1;
-		if (size == 0) {
-			free(buf);
-			return 0;
-		}
-		if (buf[size-1] != '\n') {
-			buf = xrealloc(buf, st_add(size, 1));
-			buf[size++] = '\n';
-		}
+		r = read_skip_worktree_file_from_index(istate, fname,
+						       &size, &buf,
+						       sha1_stat);
+		if (r != 1)
+			return r;
 	} else {
 		size = xsize_t(st.st_size);
 		if (size == 0) {
@@ -813,6 +856,17 @@ static int add_excludes(const char *fname, const char *base, int baselen,
 		}
 	}
 
+	add_excludes_from_buffer(buf, size, base, baselen, el);
+	return 0;
+}
+
+static int add_excludes_from_buffer(char *buf, size_t size,
+				    const char *base, int baselen,
+				    struct exclude_list *el)
+{
+	int i, lineno = 1;
+	char *entry;
+
 	el->filebuf = buf;
 
 	if (skip_utf8_bom(&buf, size))
@@ -841,6 +895,23 @@ int add_excludes_from_file_to_list(const char *fname, const char *base,
 	return add_excludes(fname, base, baselen, el, istate, NULL);
 }
 
+int add_excludes_from_blob_to_list(
+	struct object_id *oid,
+	const char *base, int baselen,
+	struct exclude_list *el)
+{
+	char *buf;
+	size_t size;
+	int r;
+
+	r = do_read_blob(oid, NULL, &size, &buf);
+	if (r != 1)
+		return r;
+
+	add_excludes_from_buffer(buf, size, base, baselen, el);
+	return 0;
+}
+
 struct exclude_list *add_exclude_list(struct dir_struct *dir,
 				      int group_type, const char *src)
 {
@@ -1389,10 +1460,34 @@ static enum path_treatment treat_directory(struct dir_struct *dir,
 	case index_nonexistent:
 		if (dir->flags & DIR_SHOW_OTHER_DIRECTORIES)
 			break;
+		if (exclude &&
+			(dir->flags & DIR_SHOW_IGNORED_TOO) &&
+			(dir->flags & DIR_SHOW_IGNORED_TOO_MODE_MATCHING)) {
+
+			/*
+			 * This is an excluded directory and we are
+			 * showing ignored paths that match an exclude
+			 * pattern.  (e.g. show directory as ignored
+			 * only if it matches an exclude pattern).
+			 * This path will either be 'path_excluded`
+			 * (if we are showing empty directories or if
+			 * the directory is not empty), or will be
+			 * 'path_none' (empty directory, and we are
+			 * not showing empty directories).
+			 */
+			if (!(dir->flags & DIR_HIDE_EMPTY_DIRECTORIES))
+				return path_excluded;
+
+			if (read_directory_recursive(dir, istate, dirname, len,
+						     untracked, 1, 1, pathspec) == path_excluded)
+				return path_excluded;
+
+			return path_none;
+		}
 		if (!(dir->flags & DIR_NO_GITLINKS)) {
-			unsigned char sha1[20];
-			if (resolve_gitlink_ref(dirname, "HEAD", sha1) == 0)
-				return path_untracked;
+			struct object_id oid;
+			if (resolve_gitlink_ref(dirname, "HEAD", &oid) == 0)
+				return exclude ? path_excluded : path_untracked;
 		}
 		return path_recurse;
 	}
@@ -1404,8 +1499,13 @@ static enum path_treatment treat_directory(struct dir_struct *dir,
 
 	untracked = lookup_untracked(dir->untracked, untracked,
 				     dirname + baselen, len - baselen);
+
+	/*
+	 * If this is an excluded directory, then we only need to check if
+	 * the directory contains any files.
+	 */
 	return read_directory_recursive(dir, istate, dirname, len,
-					untracked, 1, pathspec);
+					untracked, 1, exclude, pathspec);
 }
 
 /*
@@ -1556,6 +1656,7 @@ static enum path_treatment treat_one_path(struct dir_struct *dir,
 {
 	int exclude;
 	int has_path_in_index = !!index_file_exists(istate, path->buf, path->len, ignore_case);
+	enum path_treatment path_treatment;
 
 	if (dtype == DT_UNKNOWN)
 		dtype = get_dtype(de, istate, path->buf, path->len);
@@ -1602,8 +1703,23 @@ static enum path_treatment treat_one_path(struct dir_struct *dir,
 		return path_none;
 	case DT_DIR:
 		strbuf_addch(path, '/');
-		return treat_directory(dir, istate, untracked, path->buf, path->len,
-				       baselen, exclude, pathspec);
+		path_treatment = treat_directory(dir, istate, untracked,
+						 path->buf, path->len,
+						 baselen, exclude, pathspec);
+		/*
+		 * If 1) we only want to return directories that
+		 * match an exclude pattern and 2) this directory does
+		 * not match an exclude pattern but all of its
+		 * contents are excluded, then indicate that we should
+		 * recurse into this directory (instead of marking the
+		 * directory itself as an ignored path).
+		 */
+		if (!exclude &&
+		    path_treatment == path_excluded &&
+		    (dir->flags & DIR_SHOW_IGNORED_TOO) &&
+		    (dir->flags & DIR_SHOW_IGNORED_TOO_MODE_MATCHING))
+			return path_recurse;
+		return path_treatment;
 	case DT_REG:
 	case DT_LNK:
 		return exclude ? path_excluded : path_untracked;
@@ -1633,7 +1749,7 @@ static enum path_treatment treat_path_fast(struct dir_struct *dir,
 		 * with check_only set.
 		 */
 		return read_directory_recursive(dir, istate, path->buf, path->len,
-						cdir->ucd, 1, pathspec);
+						cdir->ucd, 1, 0, pathspec);
 	/*
 	 * We get path_recurse in the first run when
 	 * directory_exists_in_index() returns index_nonexistent. We
@@ -1688,17 +1804,23 @@ static int valid_cached_dir(struct dir_struct *dir,
 	if (!untracked)
 		return 0;
 
-	if (stat(path->len ? path->buf : ".", &st)) {
-		invalidate_directory(dir->untracked, untracked);
-		memset(&untracked->stat_data, 0, sizeof(untracked->stat_data));
-		return 0;
-	}
-	if (!untracked->valid ||
-	    match_stat_data_racy(istate, &untracked->stat_data, &st)) {
-		if (untracked->valid)
+	/*
+	 * With fsmonitor, we can trust the untracked cache's valid field.
+	 */
+	refresh_fsmonitor(istate);
+	if (!(dir->untracked->use_fsmonitor && untracked->valid)) {
+		if (stat(path->len ? path->buf : ".", &st)) {
 			invalidate_directory(dir->untracked, untracked);
-		fill_stat_data(&untracked->stat_data, &st);
-		return 0;
+			memset(&untracked->stat_data, 0, sizeof(untracked->stat_data));
+			return 0;
+		}
+		if (!untracked->valid ||
+			match_stat_data_racy(istate, &untracked->stat_data, &st)) {
+			if (untracked->valid)
+				invalidate_directory(dir->untracked, untracked);
+			fill_stat_data(&untracked->stat_data, &st);
+			return 0;
+		}
 	}
 
 	if (untracked->check_only != !!check_only) {
@@ -1793,12 +1915,20 @@ static void close_cached_dir(struct cached_dir *cdir)
  * Also, we ignore the name ".git" (even if it is not a directory).
  * That likely will not change.
  *
+ * If 'stop_at_first_file' is specified, 'path_excluded' is returned
+ * to signal that a file was found. This is the least significant value that
+ * indicates that a file was encountered that does not depend on the order of
+ * whether an untracked or exluded path was encountered first.
+ *
  * Returns the most significant path_treatment value encountered in the scan.
+ * If 'stop_at_first_file' is specified, `path_excluded` is the most
+ * significant path_treatment value that will be returned.
  */
+
 static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 	struct index_state *istate, const char *base, int baselen,
 	struct untracked_cache_dir *untracked, int check_only,
-	const struct pathspec *pathspec)
+	int stop_at_first_file, const struct pathspec *pathspec)
 {
 	struct cached_dir cdir;
 	enum path_treatment state, subdir_state, dir_state = path_none;
@@ -1832,12 +1962,34 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 			subdir_state =
 				read_directory_recursive(dir, istate, path.buf,
 							 path.len, ud,
-							 check_only, pathspec);
+							 check_only, stop_at_first_file, pathspec);
 			if (subdir_state > dir_state)
 				dir_state = subdir_state;
 		}
 
 		if (check_only) {
+			if (stop_at_first_file) {
+				/*
+				 * If stopping at first file, then
+				 * signal that a file was found by
+				 * returning `path_excluded`. This is
+				 * to return a consistent value
+				 * regardless of whether an ignored or
+				 * excluded file happened to be
+				 * encountered 1st.
+				 *
+				 * In current usage, the
+				 * `stop_at_first_file` is passed when
+				 * an ancestor directory has matched
+				 * an exclude pattern, so any found
+				 * files will be excluded.
+				 */
+				if (dir_state >= path_excluded) {
+					dir_state = path_excluded;
+					break;
+				}
+			}
+
 			/* abort early if maximum state has been reached */
 			if (dir_state == path_untracked) {
 				if (cdir.fdir)
@@ -2108,7 +2260,7 @@ int read_directory(struct dir_struct *dir, struct index_state *istate,
 		 */
 		dir->untracked = NULL;
 	if (!len || treat_leading_path(dir, istate, path, len, pathspec))
-		read_directory_recursive(dir, istate, path, len, untracked, 0, pathspec);
+		read_directory_recursive(dir, istate, path, len, untracked, 0, 0, pathspec);
 	QSORT(dir->entries, dir->nr, cmp_dir_entry);
 	QSORT(dir->ignored, dir->ignored_nr, cmp_dir_entry);
 
@@ -2244,10 +2396,10 @@ static int remove_dir_recurse(struct strbuf *path, int flag, int *kept_up)
 	int ret = 0, original_len = path->len, len, kept_down = 0;
 	int only_empty = (flag & REMOVE_DIR_EMPTY_ONLY);
 	int keep_toplevel = (flag & REMOVE_DIR_KEEP_TOPLEVEL);
-	unsigned char submodule_head[20];
+	struct object_id submodule_head;
 
 	if ((flag & REMOVE_DIR_KEEP_NESTED_GIT) &&
-	    !resolve_gitlink_ref(path->buf, "HEAD", submodule_head)) {
+	    !resolve_gitlink_ref(path->buf, "HEAD", &submodule_head)) {
 		/* Do not descend and nuke a nested git work tree. */
 		if (kept_up)
 			*kept_up = 1;