Merge branch 'ds/include-exclude'

The internal code originally invented for ".gitignore" processing
got reshuffled and renamed to make it less tied to "excluding" and
stress more that it is about "matching", as it has been reused for
things like sparse checkout specification that want to check if a
path is "included".

* ds/include-exclude:
  unpack-trees: rename 'is_excluded_from_list()'
  treewide: rename 'exclude' methods to 'pattern'
  treewide: rename 'EXCL_FLAG_' to 'PATTERN_FLAG_'
  treewide: rename 'struct exclude_list' to 'struct pattern_list'
  treewide: rename 'struct exclude' to 'struct path_pattern'

1 files changed, 148 insertions, 136 deletions

diff --git a/dir.c b/dir.c
index d021c908e5..cab9c2a458 100644
--- a/dir.c
+++ b/dir.c
@@ -561,7 +561,7 @@ int no_wildcard(const char *string)
 	return string[simple_length(string)] == '\0';
 }
 
-void parse_exclude_pattern(const char **pattern,
+void parse_path_pattern(const char **pattern,
 			   int *patternlen,
 			   unsigned *flags,
 			   int *nowildcardlen)
@@ -571,20 +571,20 @@ void parse_exclude_pattern(const char **pattern,
 
 	*flags = 0;
 	if (*p == '!') {
-		*flags |= EXC_FLAG_NEGATIVE;
+		*flags |= PATTERN_FLAG_NEGATIVE;
 		p++;
 	}
 	len = strlen(p);
 	if (len && p[len - 1] == '/') {
 		len--;
-		*flags |= EXC_FLAG_MUSTBEDIR;
+		*flags |= PATTERN_FLAG_MUSTBEDIR;
 	}
 	for (i = 0; i < len; i++) {
 		if (p[i] == '/')
 			break;
 	}
 	if (i == len)
-		*flags |= EXC_FLAG_NODIR;
+		*flags |= PATTERN_FLAG_NODIR;
 	*nowildcardlen = simple_length(p);
 	/*
 	 * we should have excluded the trailing slash from 'p' too,
@@ -594,35 +594,35 @@ void parse_exclude_pattern(const char **pattern,
 	if (*nowildcardlen > len)
 		*nowildcardlen = len;
 	if (*p == '*' && no_wildcard(p + 1))
-		*flags |= EXC_FLAG_ENDSWITH;
+		*flags |= PATTERN_FLAG_ENDSWITH;
 	*pattern = p;
 	*patternlen = len;
 }
 
-void add_exclude(const char *string, const char *base,
-		 int baselen, struct exclude_list *el, int srcpos)
+void add_pattern(const char *string, const char *base,
+		 int baselen, struct pattern_list *pl, int srcpos)
 {
-	struct exclude *x;
+	struct path_pattern *pattern;
 	int patternlen;
 	unsigned flags;
 	int nowildcardlen;
 
-	parse_exclude_pattern(&string, &patternlen, &flags, &nowildcardlen);
-	if (flags & EXC_FLAG_MUSTBEDIR) {
-		FLEXPTR_ALLOC_MEM(x, pattern, string, patternlen);
+	parse_path_pattern(&string, &patternlen, &flags, &nowildcardlen);
+	if (flags & PATTERN_FLAG_MUSTBEDIR) {
+		FLEXPTR_ALLOC_MEM(pattern, pattern, string, patternlen);
 	} else {
-		x = xmalloc(sizeof(*x));
-		x->pattern = string;
+		pattern = xmalloc(sizeof(*pattern));
+		pattern->pattern = string;
 	}
-	x->patternlen = patternlen;
-	x->nowildcardlen = nowildcardlen;
-	x->base = base;
-	x->baselen = baselen;
-	x->flags = flags;
-	x->srcpos = srcpos;
-	ALLOC_GROW(el->excludes, el->nr + 1, el->alloc);
-	el->excludes[el->nr++] = x;
-	x->el = el;
+	pattern->patternlen = patternlen;
+	pattern->nowildcardlen = nowildcardlen;
+	pattern->base = base;
+	pattern->baselen = baselen;
+	pattern->flags = flags;
+	pattern->srcpos = srcpos;
+	ALLOC_GROW(pl->patterns, pl->nr + 1, pl->alloc);
+	pl->patterns[pl->nr++] = pattern;
+	pattern->pl = pl;
 }
 
 static int read_skip_worktree_file_from_index(const struct index_state *istate,
@@ -643,19 +643,19 @@ static int read_skip_worktree_file_from_index(const struct index_state *istate,
 }
 
 /*
- * Frees memory within el which was allocated for exclude patterns and
- * the file buffer.  Does not free el itself.
+ * Frees memory within pl which was allocated for exclude patterns and
+ * the file buffer.  Does not free pl itself.
  */
-void clear_exclude_list(struct exclude_list *el)
+void clear_pattern_list(struct pattern_list *pl)
 {
 	int i;
 
-	for (i = 0; i < el->nr; i++)
-		free(el->excludes[i]);
-	free(el->excludes);
-	free(el->filebuf);
+	for (i = 0; i < pl->nr; i++)
+		free(pl->patterns[i]);
+	free(pl->patterns);
+	free(pl->filebuf);
 
-	memset(el, 0, sizeof(*el));
+	memset(pl, 0, sizeof(*pl));
 }
 
 static void trim_trailing_spaces(char *buf)
@@ -762,21 +762,21 @@ static void invalidate_directory(struct untracked_cache *uc,
 		dir->dirs[i]->recurse = 0;
 }
 
-static int add_excludes_from_buffer(char *buf, size_t size,
+static int add_patterns_from_buffer(char *buf, size_t size,
 				    const char *base, int baselen,
-				    struct exclude_list *el);
+				    struct pattern_list *pl);
 
 /*
  * 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
- * exclude rules in "el".
+ * exclude rules in "pl".
  *
  * If "ss" is not NULL, compute SHA-1 of the exclude file and fill
- * stat data from disk (only valid if add_excludes returns zero). If
+ * stat data from disk (only valid if add_patterns returns zero). If
  * ss_valid is non-zero, "ss" must contain good value as input.
  */
-static int add_excludes(const char *fname, const char *base, int baselen,
-			struct exclude_list *el, struct index_state *istate,
+static int add_patterns(const char *fname, const char *base, int baselen,
+			struct pattern_list *pl, struct index_state *istate,
 			struct oid_stat *oid_stat)
 {
 	struct stat st;
@@ -837,21 +837,21 @@ static int add_excludes(const char *fname, const char *base, int baselen,
 		}
 	}
 
-	add_excludes_from_buffer(buf, size, base, baselen, el);
+	add_patterns_from_buffer(buf, size, base, baselen, pl);
 	return 0;
 }
 
-static int add_excludes_from_buffer(char *buf, size_t size,
+static int add_patterns_from_buffer(char *buf, size_t size,
 				    const char *base, int baselen,
-				    struct exclude_list *el)
+				    struct pattern_list *pl)
 {
 	int i, lineno = 1;
 	char *entry;
 
-	el->filebuf = buf;
+	pl->filebuf = buf;
 
 	if (skip_utf8_bom(&buf, size))
-		size -= buf - el->filebuf;
+		size -= buf - pl->filebuf;
 
 	entry = buf;
 
@@ -860,7 +860,7 @@ static int add_excludes_from_buffer(char *buf, size_t size,
 			if (entry != buf + i && entry[0] != '#') {
 				buf[i - (i && buf[i-1] == '\r')] = 0;
 				trim_trailing_spaces(entry);
-				add_exclude(entry, base, baselen, el, lineno);
+				add_pattern(entry, base, baselen, pl, lineno);
 			}
 			lineno++;
 			entry = buf + i + 1;
@@ -869,17 +869,17 @@ static int add_excludes_from_buffer(char *buf, size_t size,
 	return 0;
 }
 
-int add_excludes_from_file_to_list(const char *fname, const char *base,
-				   int baselen, struct exclude_list *el,
+int add_patterns_from_file_to_list(const char *fname, const char *base,
+				   int baselen, struct pattern_list *pl,
 				   struct index_state *istate)
 {
-	return add_excludes(fname, base, baselen, el, istate, NULL);
+	return add_patterns(fname, base, baselen, pl, istate, NULL);
 }
 
-int add_excludes_from_blob_to_list(
+int add_patterns_from_blob_to_list(
 	struct object_id *oid,
 	const char *base, int baselen,
-	struct exclude_list *el)
+	struct pattern_list *pl)
 {
 	char *buf;
 	size_t size;
@@ -889,31 +889,31 @@ int add_excludes_from_blob_to_list(
 	if (r != 1)
 		return r;
 
-	add_excludes_from_buffer(buf, size, base, baselen, el);
+	add_patterns_from_buffer(buf, size, base, baselen, pl);
 	return 0;
 }
 
-struct exclude_list *add_exclude_list(struct dir_struct *dir,
+struct pattern_list *add_pattern_list(struct dir_struct *dir,
 				      int group_type, const char *src)
 {
-	struct exclude_list *el;
+	struct pattern_list *pl;
 	struct exclude_list_group *group;
 
 	group = &dir->exclude_list_group[group_type];
-	ALLOC_GROW(group->el, group->nr + 1, group->alloc);
-	el = &group->el[group->nr++];
-	memset(el, 0, sizeof(*el));
-	el->src = src;
-	return el;
+	ALLOC_GROW(group->pl, group->nr + 1, group->alloc);
+	pl = &group->pl[group->nr++];
+	memset(pl, 0, sizeof(*pl));
+	pl->src = src;
+	return pl;
 }
 
 /*
  * Used to set up core.excludesfile and .git/info/exclude lists.
  */
-static void add_excludes_from_file_1(struct dir_struct *dir, const char *fname,
+static void add_patterns_from_file_1(struct dir_struct *dir, const char *fname,
 				     struct oid_stat *oid_stat)
 {
-	struct exclude_list *el;
+	struct pattern_list *pl;
 	/*
 	 * catch setup_standard_excludes() that's called before
 	 * dir->untracked is assigned. That function behaves
@@ -921,15 +921,15 @@ static void add_excludes_from_file_1(struct dir_struct *dir, const char *fname,
 	 */
 	if (!dir->untracked)
 		dir->unmanaged_exclude_files++;
-	el = add_exclude_list(dir, EXC_FILE, fname);
-	if (add_excludes(fname, "", 0, el, NULL, oid_stat) < 0)
+	pl = add_pattern_list(dir, EXC_FILE, fname);
+	if (add_patterns(fname, "", 0, pl, NULL, oid_stat) < 0)
 		die(_("cannot use %s as an exclude file"), fname);
 }
 
-void add_excludes_from_file(struct dir_struct *dir, const char *fname)
+void add_patterns_from_file(struct dir_struct *dir, const char *fname)
 {
 	dir->unmanaged_exclude_files++; /* see validate_untracked_cache() */
-	add_excludes_from_file_1(dir, fname, NULL);
+	add_patterns_from_file_1(dir, fname, NULL);
 }
 
 int match_basename(const char *basename, int basenamelen,
@@ -940,7 +940,7 @@ int match_basename(const char *basename, int basenamelen,
 		if (patternlen == basenamelen &&
 		    !fspathncmp(pattern, basename, basenamelen))
 			return 1;
-	} else if (flags & EXC_FLAG_ENDSWITH) {
+	} else if (flags & PATTERN_FLAG_ENDSWITH) {
 		/* "*literal" matching against "fooliteral" */
 		if (patternlen - 1 <= basenamelen &&
 		    !fspathncmp(pattern + 1,
@@ -1021,85 +1021,97 @@ int match_pathname(const char *pathname, int pathlen,
  * any, determines the fate.  Returns the exclude_list element which
  * matched, or NULL for undecided.
  */
-static struct exclude *last_exclude_matching_from_list(const char *pathname,
+static struct path_pattern *last_matching_pattern_from_list(const char *pathname,
 						       int pathlen,
 						       const char *basename,
 						       int *dtype,
-						       struct exclude_list *el,
+						       struct pattern_list *pl,
 						       struct index_state *istate)
 {
-	struct exclude *exc = NULL; /* undecided */
+	struct path_pattern *res = NULL; /* undecided */
 	int i;
 
-	if (!el->nr)
+	if (!pl->nr)
 		return NULL;	/* undefined */
 
-	for (i = el->nr - 1; 0 <= i; i--) {
-		struct exclude *x = el->excludes[i];
-		const char *exclude = x->pattern;
-		int prefix = x->nowildcardlen;
+	for (i = pl->nr - 1; 0 <= i; i--) {
+		struct path_pattern *pattern = pl->patterns[i];
+		const char *exclude = pattern->pattern;
+		int prefix = pattern->nowildcardlen;
 
-		if (x->flags & EXC_FLAG_MUSTBEDIR) {
+		if (pattern->flags & PATTERN_FLAG_MUSTBEDIR) {
 			if (*dtype == DT_UNKNOWN)
 				*dtype = get_dtype(NULL, istate, pathname, pathlen);
 			if (*dtype != DT_DIR)
 				continue;
 		}
 
-		if (x->flags & EXC_FLAG_NODIR) {
+		if (pattern->flags & PATTERN_FLAG_NODIR) {
 			if (match_basename(basename,
 					   pathlen - (basename - pathname),
-					   exclude, prefix, x->patternlen,
-					   x->flags)) {
-				exc = x;
+					   exclude, prefix, pattern->patternlen,
+					   pattern->flags)) {
+				res = pattern;
 				break;
 			}
 			continue;
 		}
 
-		assert(x->baselen == 0 || x->base[x->baselen - 1] == '/');
+		assert(pattern->baselen == 0 ||
+		       pattern->base[pattern->baselen - 1] == '/');
 		if (match_pathname(pathname, pathlen,
-				   x->base, x->baselen ? x->baselen - 1 : 0,
-				   exclude, prefix, x->patternlen, x->flags)) {
-			exc = x;
+				   pattern->base,
+				   pattern->baselen ? pattern->baselen - 1 : 0,
+				   exclude, prefix, pattern->patternlen,
+				   pattern->flags)) {
+			res = pattern;
 			break;
 		}
 	}
-	return exc;
+	return res;
 }
 
 /*
- * Scan the list and let the last match determine the fate.
- * Return 1 for exclude, 0 for include and -1 for undecided.
+ * Scan the list of patterns to determine if the ordered list
+ * of patterns matches on 'pathname'.
+ *
+ * Return 1 for a match, 0 for not matched and -1 for undecided.
  */
-int is_excluded_from_list(const char *pathname,
-			  int pathlen, const char *basename, int *dtype,
-			  struct exclude_list *el, struct index_state *istate)
-{
-	struct exclude *exclude;
-	exclude = last_exclude_matching_from_list(pathname, pathlen, basename,
-						  dtype, el, istate);
-	if (exclude)
-		return exclude->flags & EXC_FLAG_NEGATIVE ? 0 : 1;
-	return -1; /* undecided */
+enum pattern_match_result path_matches_pattern_list(
+				const char *pathname, int pathlen,
+				const char *basename, int *dtype,
+				struct pattern_list *pl,
+				struct index_state *istate)
+{
+	struct path_pattern *pattern;
+	pattern = last_matching_pattern_from_list(pathname, pathlen, basename,
+						  dtype, pl, istate);
+	if (pattern) {
+		if (pattern->flags & PATTERN_FLAG_NEGATIVE)
+			return NOT_MATCHED;
+		else
+			return MATCHED;
+	}
+
+	return UNDECIDED;
 }
 
-static struct exclude *last_exclude_matching_from_lists(struct dir_struct *dir,
-							struct index_state *istate,
-		const char *pathname, int pathlen, const char *basename,
-		int *dtype_p)
+static struct path_pattern *last_matching_pattern_from_lists(
+		struct dir_struct *dir, struct index_state *istate,
+		const char *pathname, int pathlen,
+		const char *basename, int *dtype_p)
 {
 	int i, j;
 	struct exclude_list_group *group;
-	struct exclude *exclude;
+	struct path_pattern *pattern;
 	for (i = EXC_CMDL; i <= EXC_FILE; i++) {
 		group = &dir->exclude_list_group[i];
 		for (j = group->nr - 1; j >= 0; j--) {
-			exclude = last_exclude_matching_from_list(
+			pattern = last_matching_pattern_from_list(
 				pathname, pathlen, basename, dtype_p,
-				&group->el[j], istate);
-			if (exclude)
-				return exclude;
+				&group->pl[j], istate);
+			if (pattern)
+				return pattern;
 		}
 	}
 	return NULL;
@@ -1114,7 +1126,7 @@ static void prep_exclude(struct dir_struct *dir,
 			 const char *base, int baselen)
 {
 	struct exclude_list_group *group;
-	struct exclude_list *el;
+	struct pattern_list *pl;
 	struct exclude_stack *stk = NULL;
 	struct untracked_cache_dir *untracked;
 	int current;
@@ -1130,17 +1142,17 @@ static void prep_exclude(struct dir_struct *dir,
 		if (stk->baselen <= baselen &&
 		    !strncmp(dir->basebuf.buf, base, stk->baselen))
 			break;
-		el = &group->el[dir->exclude_stack->exclude_ix];
+		pl = &group->pl[dir->exclude_stack->exclude_ix];
 		dir->exclude_stack = stk->prev;
-		dir->exclude = NULL;
-		free((char *)el->src); /* see strbuf_detach() below */
-		clear_exclude_list(el);
+		dir->pattern = NULL;
+		free((char *)pl->src); /* see strbuf_detach() below */
+		clear_pattern_list(pl);
 		free(stk);
 		group->nr--;
 	}
 
 	/* Skip traversing into sub directories if the parent is excluded */
-	if (dir->exclude)
+	if (dir->pattern)
 		return;
 
 	/*
@@ -1181,7 +1193,7 @@ static void prep_exclude(struct dir_struct *dir,
 		stk->baselen = cp - base;
 		stk->exclude_ix = group->nr;
 		stk->ucd = untracked;
-		el = add_exclude_list(dir, EXC_DIRS, NULL);
+		pl = add_pattern_list(dir, EXC_DIRS, NULL);
 		strbuf_add(&dir->basebuf, base + current, stk->baselen - current);
 		assert(stk->baselen == dir->basebuf.len);
 
@@ -1189,15 +1201,15 @@ static void prep_exclude(struct dir_struct *dir,
 		if (stk->baselen) {
 			int dt = DT_DIR;
 			dir->basebuf.buf[stk->baselen - 1] = 0;
-			dir->exclude = last_exclude_matching_from_lists(dir,
+			dir->pattern = last_matching_pattern_from_lists(dir,
 									istate,
 				dir->basebuf.buf, stk->baselen - 1,
 				dir->basebuf.buf + current, &dt);
 			dir->basebuf.buf[stk->baselen - 1] = '/';
-			if (dir->exclude &&
-			    dir->exclude->flags & EXC_FLAG_NEGATIVE)
-				dir->exclude = NULL;
-			if (dir->exclude) {
+			if (dir->pattern &&
+			    dir->pattern->flags & PATTERN_FLAG_NEGATIVE)
+				dir->pattern = NULL;
+			if (dir->pattern) {
 				dir->exclude_stack = stk;
 				return;
 			}
@@ -1223,30 +1235,30 @@ static void prep_exclude(struct dir_struct *dir,
 			/*
 			 * dir->basebuf gets reused by the traversal, but we
 			 * need fname to remain unchanged to ensure the src
-			 * member of each struct exclude correctly
+			 * member of each struct path_pattern correctly
 			 * back-references its source file.  Other invocations
-			 * of add_exclude_list provide stable strings, so we
+			 * of add_pattern_list provide stable strings, so we
 			 * strbuf_detach() and free() here in the caller.
 			 */
 			struct strbuf sb = STRBUF_INIT;
 			strbuf_addbuf(&sb, &dir->basebuf);
 			strbuf_addstr(&sb, dir->exclude_per_dir);
-			el->src = strbuf_detach(&sb, NULL);
-			add_excludes(el->src, el->src, stk->baselen, el, istate,
+			pl->src = strbuf_detach(&sb, NULL);
+			add_patterns(pl->src, pl->src, stk->baselen, pl, istate,
 				     untracked ? &oid_stat : NULL);
 		}
 		/*
 		 * NEEDSWORK: when untracked cache is enabled, prep_exclude()
 		 * will first be called in valid_cached_dir() then maybe many
-		 * times more in last_exclude_matching(). When the cache is
-		 * used, last_exclude_matching() will not be called and
+		 * times more in last_matching_pattern(). When the cache is
+		 * used, last_matching_pattern() will not be called and
 		 * reading .gitignore content will be a waste.
 		 *
 		 * So when it's called by valid_cached_dir() and we can get
 		 * .gitignore SHA-1 from the index (i.e. .gitignore is not
 		 * modified on work tree), we could delay reading the
 		 * .gitignore content until we absolutely need it in
-		 * last_exclude_matching(). Be careful about ignore rule
+		 * last_matching_pattern(). Be careful about ignore rule
 		 * order, though, if you do that.
 		 */
 		if (untracked &&
@@ -1266,7 +1278,7 @@ static void prep_exclude(struct dir_struct *dir,
  * Returns the exclude_list element which matched, or NULL for
  * undecided.
  */
-struct exclude *last_exclude_matching(struct dir_struct *dir,
+struct path_pattern *last_matching_pattern(struct dir_struct *dir,
 				      struct index_state *istate,
 				      const char *pathname,
 				      int *dtype_p)
@@ -1277,10 +1289,10 @@ struct exclude *last_exclude_matching(struct dir_struct *dir,
 
 	prep_exclude(dir, istate, pathname, basename-pathname);
 
-	if (dir->exclude)
-		return dir->exclude;
+	if (dir->pattern)
+		return dir->pattern;
 
-	return last_exclude_matching_from_lists(dir, istate, pathname, pathlen,
+	return last_matching_pattern_from_lists(dir, istate, pathname, pathlen,
 			basename, dtype_p);
 }
 
@@ -1292,10 +1304,10 @@ struct exclude *last_exclude_matching(struct dir_struct *dir,
 int is_excluded(struct dir_struct *dir, struct index_state *istate,
 		const char *pathname, int *dtype_p)
 {
-	struct exclude *exclude =
-		last_exclude_matching(dir, istate, pathname, dtype_p);
-	if (exclude)
-		return exclude->flags & EXC_FLAG_NEGATIVE ? 0 : 1;
+	struct path_pattern *pattern =
+		last_matching_pattern(dir, istate, pathname, dtype_p);
+	if (pattern)
+		return pattern->flags & PATTERN_FLAG_NEGATIVE ? 0 : 1;
 	return 0;
 }
 
@@ -1808,7 +1820,7 @@ static int valid_cached_dir(struct dir_struct *dir,
 
 	/*
 	 * prep_exclude will be called eventually on this directory,
-	 * but it's called much later in last_exclude_matching(). We
+	 * but it's called much later in last_matching_pattern(). We
 	 * need it now to determine the validity of the cache for this
 	 * path. The next calls will be nearly no-op, the way
 	 * prep_exclude() is designed.
@@ -2488,14 +2500,14 @@ void setup_standard_excludes(struct dir_struct *dir)
 	if (!excludes_file)
 		excludes_file = xdg_config_home("ignore");
 	if (excludes_file && !access_or_warn(excludes_file, R_OK, 0))
-		add_excludes_from_file_1(dir, excludes_file,
+		add_patterns_from_file_1(dir, excludes_file,
 					 dir->untracked ? &dir->ss_excludes_file : NULL);
 
 	/* per repository user preference */
 	if (startup_info->have_repository) {
 		const char *path = git_path_info_exclude();
 		if (!access_or_warn(path, R_OK, 0))
-			add_excludes_from_file_1(dir, path,
+			add_patterns_from_file_1(dir, path,
 						 dir->untracked ? &dir->ss_info_exclude : NULL);
 	}
 }
@@ -2527,18 +2539,18 @@ void clear_directory(struct dir_struct *dir)
 {
 	int i, j;
 	struct exclude_list_group *group;
-	struct exclude_list *el;
+	struct pattern_list *pl;
 	struct exclude_stack *stk;
 
 	for (i = EXC_CMDL; i <= EXC_FILE; i++) {
 		group = &dir->exclude_list_group[i];
 		for (j = 0; j < group->nr; j++) {
-			el = &group->el[j];
+			pl = &group->pl[j];
 			if (i == EXC_DIRS)
-				free((char *)el->src);
-			clear_exclude_list(el);
+				free((char *)pl->src);
+			clear_pattern_list(pl);
 		}
-		free(group->el);
+		free(group->pl);
 	}
 
 	stk = dir->exclude_stack;