1 files changed, 277 insertions, 47 deletions

diff --git a/dir.c b/dir.c
index 7b25634832..552af23704 100644
--- a/dir.c
+++ b/dir.c
@@ -53,6 +53,8 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 	int check_only, const struct path_simplify *simplify);
 static int get_dtype(struct dirent *de, const char *path, int len);
 
+static struct trace_key trace_exclude = TRACE_KEY_INIT(EXCLUDE);
+
 /* helper string functions with support for the ignore_case flag */
 int strcmp_icase(const char *a, const char *b)
 {
@@ -519,6 +521,7 @@ void add_exclude(const char *string, const char *base,
 	x->baselen = baselen;
 	x->flags = flags;
 	x->srcpos = srcpos;
+	string_list_init(&x->sticky_paths, 1);
 	ALLOC_GROW(el->excludes, el->nr + 1, el->alloc);
 	el->excludes[el->nr++] = x;
 	x->el = el;
@@ -559,14 +562,14 @@ void clear_exclude_list(struct exclude_list *el)
 {
 	int i;
 
-	for (i = 0; i < el->nr; i++)
+	for (i = 0; i < el->nr; i++) {
+		string_list_clear(&el->excludes[i]->sticky_paths, 0);
 		free(el->excludes[i]);
+	}
 	free(el->excludes);
 	free(el->filebuf);
 
-	el->nr = 0;
-	el->excludes = NULL;
-	el->filebuf = NULL;
+	memset(el, 0, sizeof(*el));
 }
 
 static void trim_trailing_spaces(char *buf)
@@ -880,7 +883,7 @@ int match_pathname(const char *pathname, int pathlen,
 		 * then our prefix match is all we need; we
 		 * do not need to call fnmatch at all.
 		 */
-		if (!patternlen && !namelen)
+		if (!patternlen && (!namelen || *name == '/'))
 			return 1;
 	}
 
@@ -889,6 +892,113 @@ int match_pathname(const char *pathname, int pathlen,
 				 WM_PATHNAME) == 0;
 }
 
+static void add_sticky(struct exclude *exc, const char *pathname, int pathlen)
+{
+	struct strbuf sb = STRBUF_INIT;
+	int i;
+
+	for (i = exc->sticky_paths.nr - 1; i >= 0; i--) {
+		const char *sticky = exc->sticky_paths.items[i].string;
+		int len = strlen(sticky);
+
+		if (pathlen < len && sticky[pathlen] == '/' &&
+		    !strncmp(pathname, sticky, pathlen))
+			return;
+	}
+
+	strbuf_add(&sb, pathname, pathlen);
+	string_list_append_nodup(&exc->sticky_paths, strbuf_detach(&sb, NULL));
+}
+
+static int match_sticky(struct exclude *exc, const char *pathname, int pathlen, int dtype)
+{
+	int i;
+
+	for (i = exc->sticky_paths.nr - 1; i >= 0; i--) {
+		const char *sticky = exc->sticky_paths.items[i].string;
+		int len = strlen(sticky);
+
+		if (pathlen == len && dtype == DT_DIR &&
+		    !strncmp(pathname, sticky, len))
+			return 1;
+
+		if (pathlen > len && pathname[len] == '/' &&
+		    !strncmp(pathname, sticky, len))
+			return 1;
+	}
+
+	return 0;
+}
+
+static inline int different_decisions(const struct exclude *a,
+				      const struct exclude *b)
+{
+	return (a->flags & EXC_FLAG_NEGATIVE) != (b->flags & EXC_FLAG_NEGATIVE);
+}
+
+/*
+ * Return non-zero if pathname is a directory and an ancestor of the
+ * literal path in a pattern.
+ */
+static int match_directory_part(const char *pathname, int pathlen,
+				int *dtype, struct exclude *x)
+{
+	const char	*base	    = x->base;
+	int		 baselen    = x->baselen ? x->baselen - 1 : 0;
+	const char	*pattern    = x->pattern;
+	int		 prefix	    = x->nowildcardlen;
+	int		 patternlen = x->patternlen;
+
+	if (*dtype == DT_UNKNOWN)
+		*dtype = get_dtype(NULL, pathname, pathlen);
+	if (*dtype != DT_DIR)
+		return 0;
+
+	if (*pattern == '/') {
+		pattern++;
+		patternlen--;
+		prefix--;
+	}
+
+	if (baselen) {
+		if (((pathlen < baselen && base[pathlen] == '/') ||
+		     pathlen == baselen) &&
+		    !strncmp_icase(pathname, base, pathlen))
+			return 1;
+		pathname += baselen + 1;
+		pathlen  -= baselen + 1;
+	}
+
+
+	if (prefix &&
+	    (((pathlen < prefix && pattern[pathlen] == '/') ||
+	      pathlen == prefix) &&
+	     !strncmp_icase(pathname, pattern, pathlen)))
+		return 1;
+
+	return 0;
+}
+
+static struct exclude *should_descend(const char *pathname, int pathlen,
+				      int *dtype, struct exclude_list *el,
+				      struct exclude *exc)
+{
+	int i;
+
+	for (i = el->nr - 1; 0 <= i; i--) {
+		struct exclude *x = el->excludes[i];
+
+		if (x == exc)
+			break;
+
+		if (!(x->flags & EXC_FLAG_NODIR) &&
+		    different_decisions(x, exc) &&
+		    match_directory_part(pathname, pathlen, dtype, x))
+			return x;
+	}
+	return NULL;
+}
+
 /*
  * Scan the given exclude list in reverse to see whether pathname
  * should be ignored.  The first match (i.e. the last on the list), if
@@ -901,16 +1011,33 @@ static struct exclude *last_exclude_matching_from_list(const char *pathname,
 						       int *dtype,
 						       struct exclude_list *el)
 {
-	int i;
+	struct exclude *exc = NULL; /* undecided */
+	int i, maybe_descend = 0;
 
 	if (!el->nr)
 		return NULL;	/* undefined */
 
+	trace_printf_key(&trace_exclude, "exclude: from %s\n", el->src);
+
 	for (i = el->nr - 1; 0 <= i; i--) {
 		struct exclude *x = el->excludes[i];
 		const char *exclude = x->pattern;
 		int prefix = x->nowildcardlen;
 
+		if (!maybe_descend && i < el->nr - 1 &&
+		    different_decisions(x, el->excludes[i+1]))
+			maybe_descend = 1;
+
+		if (x->sticky_paths.nr) {
+			if (*dtype == DT_UNKNOWN)
+				*dtype = get_dtype(NULL, pathname, pathlen);
+			if (match_sticky(x, pathname, pathlen, *dtype)) {
+				exc = x;
+				break;
+			}
+			continue;
+		}
+
 		if (x->flags & EXC_FLAG_MUSTBEDIR) {
 			if (*dtype == DT_UNKNOWN)
 				*dtype = get_dtype(NULL, pathname, pathlen);
@@ -922,18 +1049,61 @@ static struct exclude *last_exclude_matching_from_list(const char *pathname,
 			if (match_basename(basename,
 					   pathlen - (basename - pathname),
 					   exclude, prefix, x->patternlen,
-					   x->flags))
-				return x;
+					   x->flags)) {
+				exc = x;
+				break;
+			}
 			continue;
 		}
 
 		assert(x->baselen == 0 || x->base[x->baselen - 1] == '/');
 		if (match_pathname(pathname, pathlen,
 				   x->base, x->baselen ? x->baselen - 1 : 0,
-				   exclude, prefix, x->patternlen, x->flags))
-			return x;
+				   exclude, prefix, x->patternlen, x->flags)) {
+			exc = x;
+			break;
+		}
+	}
+
+	if (!exc) {
+		trace_printf_key(&trace_exclude, "exclude: %.*s => n/a\n",
+				 pathlen, pathname);
+		return NULL;
+	}
+
+	/*
+	 * We have found a matching pattern "exc" that may exclude whole
+	 * directory. We also found that there may be a pattern that matches
+	 * something inside the directory and reincludes stuff.
+	 *
+	 * Go through the patterns again, find that pattern and double check.
+	 * If it's true, return "undecided" and keep descending in. "exc" is
+	 * marked sticky so that it continues to match inside the directory.
+	 */
+	if (!(exc->flags & EXC_FLAG_NEGATIVE) && maybe_descend) {
+		struct exclude *x;
+
+		if (*dtype == DT_UNKNOWN)
+			*dtype = get_dtype(NULL, pathname, pathlen);
+
+		if (*dtype == DT_DIR &&
+		    (x = should_descend(pathname, pathlen, dtype, el, exc))) {
+			add_sticky(exc, pathname, pathlen);
+			trace_printf_key(&trace_exclude,
+					 "exclude: %.*s vs %s at line %d => %s,"
+					 " forced open by %s at line %d => n/a\n",
+					 pathlen, pathname, exc->pattern, exc->srcpos,
+					 exc->flags & EXC_FLAG_NEGATIVE ? "no" : "yes",
+					 x->pattern, x->srcpos);
+			return NULL;
+		}
 	}
-	return NULL; /* undecided */
+
+	trace_printf_key(&trace_exclude, "exclude: %.*s vs %s at line %d => %s%s\n",
+			 pathlen, pathname, exc->pattern, exc->srcpos,
+			 exc->flags & EXC_FLAG_NEGATIVE ? "no" : "yes",
+			 exc->sticky_paths.nr ? " (stuck)" : "");
+	return exc;
 }
 
 /*
@@ -1202,29 +1372,15 @@ enum exist_status {
  */
 static enum exist_status directory_exists_in_index_icase(const char *dirname, int len)
 {
-	const struct cache_entry *ce = cache_dir_exists(dirname, len);
-	unsigned char endchar;
-
-	if (!ce)
-		return index_nonexistent;
-	endchar = ce->name[len];
+	struct cache_entry *ce;
 
-	/*
-	 * The cache_entry structure returned will contain this dirname
-	 * and possibly additional path components.
-	 */
-	if (endchar == '/')
+	if (cache_dir_exists(dirname, len))
 		return index_directory;
 
-	/*
-	 * If there are no additional path components, then this cache_entry
-	 * represents a submodule.  Submodules, despite being directories,
-	 * are stored in the cache without a closing slash.
-	 */
-	if (!endchar && S_ISGITLINK(ce->ce_mode))
+	ce = cache_file_exists(dirname, len, ignore_case);
+	if (ce && S_ISGITLINK(ce->ce_mode))
 		return index_gitdir;
 
-	/* This should never be hit, but it exists just in case. */
 	return index_nonexistent;
 }
 
@@ -1519,8 +1675,7 @@ static enum path_treatment treat_path_fast(struct dir_struct *dir,
 	}
 	strbuf_addstr(path, cdir->ucd->name);
 	/* treat_one_path() does this before it calls treat_directory() */
-	if (path->buf[path->len - 1] != '/')
-		strbuf_addch(path, '/');
+	strbuf_complete(path, '/');
 	if (cdir->ucd->check_only)
 		/*
 		 * check_only is set as a result of treat_directory() getting
@@ -1695,9 +1850,13 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 	struct cached_dir cdir;
 	enum path_treatment state, subdir_state, dir_state = path_none;
 	struct strbuf path = STRBUF_INIT;
+	static int level = 0;
 
 	strbuf_add(&path, base, baselen);
 
+	trace_printf_key(&trace_exclude, "exclude: [%d] enter '%.*s'\n",
+			 level++, baselen, base);
+
 	if (open_cached_dir(&cdir, dir, untracked, &path, check_only))
 		goto out;
 
@@ -1761,6 +1920,8 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 	}
 	close_cached_dir(&cdir);
  out:
+	trace_printf_key(&trace_exclude, "exclude: [%d] leave '%.*s'\n",
+			 --level, baselen, base);
 	strbuf_release(&path);
 
 	return dir_state;
@@ -1851,31 +2012,67 @@ static const char *get_ident_string(void)
 		return sb.buf;
 	if (uname(&uts) < 0)
 		die_errno(_("failed to get kernel name and information"));
-	strbuf_addf(&sb, "Location %s, system %s %s %s", get_git_work_tree(),
-		    uts.sysname, uts.release, uts.version);
+	strbuf_addf(&sb, "Location %s, system %s", get_git_work_tree(),
+		    uts.sysname);
 	return sb.buf;
 }
 
 static int ident_in_untracked(const struct untracked_cache *uc)
 {
-	const char *end = uc->ident.buf + uc->ident.len;
-	const char *p   = uc->ident.buf;
+	/*
+	 * Previous git versions may have saved many NUL separated
+	 * strings in the "ident" field, but it is insane to manage
+	 * many locations, so just take care of the first one.
+	 */
 
-	for (p = uc->ident.buf; p < end; p += strlen(p) + 1)
-		if (!strcmp(p, get_ident_string()))
-			return 1;
-	return 0;
+	return !strcmp(uc->ident.buf, get_ident_string());
 }
 
-void add_untracked_ident(struct untracked_cache *uc)
+static void set_untracked_ident(struct untracked_cache *uc)
 {
-	if (ident_in_untracked(uc))
-		return;
+	strbuf_reset(&uc->ident);
 	strbuf_addstr(&uc->ident, get_ident_string());
-	/* this strbuf contains a list of strings, save NUL too */
+
+	/*
+	 * This strbuf used to contain a list of NUL separated
+	 * strings, so save NUL too for backward compatibility.
+	 */
 	strbuf_addch(&uc->ident, 0);
 }
 
+static void new_untracked_cache(struct index_state *istate)
+{
+	struct untracked_cache *uc = xcalloc(1, sizeof(*uc));
+	strbuf_init(&uc->ident, 100);
+	uc->exclude_per_dir = ".gitignore";
+	/* should be the same flags used by git-status */
+	uc->dir_flags = DIR_SHOW_OTHER_DIRECTORIES | DIR_HIDE_EMPTY_DIRECTORIES;
+	set_untracked_ident(uc);
+	istate->untracked = uc;
+	istate->cache_changed |= UNTRACKED_CHANGED;
+}
+
+void add_untracked_cache(struct index_state *istate)
+{
+	if (!istate->untracked) {
+		new_untracked_cache(istate);
+	} else {
+		if (!ident_in_untracked(istate->untracked)) {
+			free_untracked_cache(istate->untracked);
+			new_untracked_cache(istate);
+		}
+	}
+}
+
+void remove_untracked_cache(struct index_state *istate)
+{
+	if (istate->untracked) {
+		free_untracked_cache(istate->untracked);
+		istate->untracked = NULL;
+		istate->cache_changed |= UNTRACKED_CHANGED;
+	}
+}
+
 static struct untracked_cache_dir *validate_untracked_cache(struct dir_struct *dir,
 						      int base_len,
 						      const struct pathspec *pathspec)
@@ -1933,7 +2130,7 @@ static struct untracked_cache_dir *validate_untracked_cache(struct dir_struct *d
 		return NULL;
 
 	if (!ident_in_untracked(dir->untracked)) {
-		warning(_("Untracked cache is disabled on this system."));
+		warning(_("Untracked cache is disabled on this system or location."));
 		return NULL;
 	}
 
@@ -1961,6 +2158,25 @@ static struct untracked_cache_dir *validate_untracked_cache(struct dir_struct *d
 	return root;
 }
 
+static void clear_sticky(struct dir_struct *dir)
+{
+	struct exclude_list_group *g;
+	struct exclude_list *el;
+	struct exclude *x;
+	int i, j, k;
+
+	for (i = EXC_CMDL; i <= EXC_FILE; i++) {
+		g = &dir->exclude_list_group[i];
+		for (j = g->nr - 1; j >= 0; j--) {
+			el = &g->el[j];
+			for (k = el->nr - 1; 0 <= k; k--) {
+				x = el->excludes[k];
+				string_list_clear(&x->sticky_paths, 0);
+			}
+		}
+	}
+}
+
 int read_directory(struct dir_struct *dir, const char *path, int len, const struct pathspec *pathspec)
 {
 	struct path_simplify *simplify;
@@ -1982,6 +2198,12 @@ int read_directory(struct dir_struct *dir, const char *path, int len, const stru
 		return dir->nr;
 
 	/*
+	 * Stay on the safe side. if read_directory() has run once on
+	 * "dir", some sticky flag may have been left. Clear them all.
+	 */
+	clear_sticky(dir);
+
+	/*
 	 * 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
@@ -2030,6 +2252,15 @@ int file_exists(const char *f)
 	return lstat(f, &sb) == 0;
 }
 
+static int cmp_icase(char a, char b)
+{
+	if (a == b)
+		return 0;
+	if (ignore_case)
+		return toupper(a) - toupper(b);
+	return a - b;
+}
+
 /*
  * Given two normalized paths (a trailing slash is ok), if subdir is
  * outside dir, return -1.  Otherwise return the offset in subdir that
@@ -2041,7 +2272,7 @@ int dir_inside_of(const char *subdir, const char *dir)
 
 	assert(dir && subdir && *dir && *subdir);
 
-	while (*dir && *subdir && *dir == *subdir) {
+	while (*dir && *subdir && !cmp_icase(*dir, *subdir)) {
 		dir++;
 		subdir++;
 		offset++;
@@ -2126,8 +2357,7 @@ static int remove_dir_recurse(struct strbuf *path, int flag, int *kept_up)
 		else
 			return -1;
 	}
-	if (path->buf[original_len - 1] != '/')
-		strbuf_addch(path, '/');
+	strbuf_complete(path, '/');
 
 	len = path->len;
 	while ((e = readdir(dir)) != NULL) {