Merge branch 'sb/pathspec-label' into sb/submodule-default-paths

* sb/pathspec-label:
  pathspec: disable preload-index when attribute pathspec magic is in use
  pathspec: allow escaped query values
  pathspec: allow querying for attributes
  pathspec: move prefix check out of the inner loop
  pathspec: move long magic parsing out of prefix_pathspec
  Documentation: fix a typo

7 files changed, 451 insertions, 39 deletions

diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt
index a18804c657..0705cf2e4e 100644
--- a/Documentation/gitattributes.txt
+++ b/Documentation/gitattributes.txt
@@ -88,7 +88,7 @@ is either not set or empty, $HOME/.config/git/attributes is used instead.
 Attributes for all users on a system should be placed in the
 `$(prefix)/etc/gitattributes` file.
 
-Sometimes you would need to override an setting of an attribute
+Sometimes you would need to override a setting of an attribute
 for a path to `Unspecified` state.  This can be done by listing
 the name of the attribute prefixed with an exclamation point `!`.
 
diff --git a/Documentation/glossary-content.txt b/Documentation/glossary-content.txt
index 8ad29e61a9..f90bd45395 100644
--- a/Documentation/glossary-content.txt
+++ b/Documentation/glossary-content.txt
@@ -384,6 +384,26 @@ full pathname may have special meaning:
 +
 Glob magic is incompatible with literal magic.
 
+attr;;
+After `attr:` comes a space separated list of "attribute
+requirements", all of which must be met in order for the
+path to be considered a match; this is in addition to the
+usual non-magic pathspec pattern matching.
++
+Each of the attribute requirements for the path takes one of
+these forms:
+
+- "`ATTR`" requires that the attribute `ATTR` must be set.
+
+- "`-ATTR`" requires that the attribute `ATTR` must be unset.
+
+- "`ATTR=VALUE`" requires that the attribute `ATTR` must be
+  set to the string `VALUE`.
+
+- "`!ATTR`" requires that the attribute `ATTR` must be
+  unspecified.
++
+
 exclude;;
 	After a path matches any non-exclude pathspec, it will be run
 	through all exclude pathspec (magic signature: `!`). If it
diff --git a/dir.c b/dir.c
index 6172b3438d..3fd1e9a197 100644
--- a/dir.c
+++ b/dir.c
@@ -9,6 +9,7 @@
  */
 #include "cache.h"
 #include "dir.h"
+#include "attr.h"
 #include "refs.h"
 #include "wildmatch.h"
 #include "pathspec.h"
@@ -207,6 +208,37 @@ int within_depth(const char *name, int namelen,
 	return 1;
 }
 
+static int match_attrs(const char *name, int namelen,
+		       const struct pathspec_item *item)
+{
+	int i;
+
+	git_check_attr_counted(name, namelen, item->attr_check);
+	for (i = 0; i < item->attr_match_nr; i++) {
+		const char *value;
+		int matched;
+		enum attr_match_mode match_mode;
+
+		value = item->attr_check->check[i].value;
+		match_mode = item->attr_match[i].match_mode;
+
+		if (ATTR_TRUE(value))
+			matched = (match_mode == MATCH_SET);
+		else if (ATTR_FALSE(value))
+			matched = (match_mode == MATCH_UNSET);
+		else if (ATTR_UNSET(value))
+			matched = (match_mode == MATCH_UNSPECIFIED);
+		else
+			matched = (match_mode == MATCH_VALUE &&
+				   !strcmp(item->attr_match[i].value, value));
+
+		if (!matched)
+			return 0;
+	}
+
+	return 1;
+}
+
 #define DO_MATCH_EXCLUDE   1
 #define DO_MATCH_DIRECTORY 2
 
@@ -262,6 +294,9 @@ static int match_pathspec_item(const struct pathspec_item *item, int prefix,
 	    strncmp(item->match, name - prefix, item->prefix))
 		return 0;
 
+	if (item->attr_match_nr && !match_attrs(name, namelen, item))
+		return 0;
+
 	/* If the match was just the prefix, we matched */
 	if (!*match)
 		return MATCHED_RECURSIVELY;
diff --git a/pathspec.c b/pathspec.c
index 24e0dd5232..c94327fb44 100644
--- a/pathspec.c
+++ b/pathspec.c
@@ -1,6 +1,7 @@
 #include "cache.h"
 #include "dir.h"
 #include "pathspec.h"
+#include "attr.h"
 
 /*
  * Finds which of the given pathspecs match items in the index.
@@ -88,6 +89,180 @@ static void prefix_short_magic(struct strbuf *sb, int prefixlen,
 	strbuf_addf(sb, ",prefix:%d)", prefixlen);
 }
 
+static size_t strcspn_escaped(const char *s, const char *stop)
+{
+	const char *i;
+
+	for (i = s; *i; i++) {
+		/* skip the escaped character */
+		if (i[0] == '\\' && i[1]) {
+			i++;
+			continue;
+		}
+
+		if (strchr(stop, *i))
+			break;
+	}
+	return i - s;
+}
+
+static inline int invalid_value_char(const char ch)
+{
+	if (isalnum(ch) || strchr(",-_", ch))
+		return 0;
+	return -1;
+}
+
+static char *attr_value_unescape(const char *value)
+{
+	const char *src;
+	char *dst, *ret;
+
+	ret = xmallocz(strlen(value));
+	for (src = value, dst = ret; *src; src++, dst++) {
+		if (*src == '\\') {
+			if (!src[1])
+				die(_("Escape character '\\' not allowed as "
+				      "last character in attr value"));
+			src++;
+		}
+		if (invalid_value_char(*src))
+			die("cannot use '%c' for value matching", *src);
+		*dst = *src;
+	}
+	*dst = '\0';
+	return ret;
+}
+
+static void parse_pathspec_attr_match(struct pathspec_item *item, const char *value)
+{
+	struct string_list_item *si;
+	struct string_list list = STRING_LIST_INIT_DUP;
+
+	if (!value || !strlen(value))
+		die(_("attr spec must not be empty"));
+
+	string_list_split(&list, value, ' ', -1);
+	string_list_remove_empty_items(&list, 0);
+
+	if (!item->attr_check)
+		item->attr_check = git_attr_check_alloc();
+	else
+		die(_("Only one 'attr:' specification is allowed."));
+
+	ALLOC_GROW(item->attr_match, item->attr_match_nr + list.nr, item->attr_match_alloc);
+
+	for_each_string_list_item(si, &list) {
+		size_t attr_len;
+
+		int j = item->attr_match_nr++;
+		const char *attr = si->string;
+		struct attr_match *am = &item->attr_match[j];
+
+		switch (*attr) {
+		case '!':
+			am->match_mode = MATCH_UNSPECIFIED;
+			attr++;
+			attr_len = strlen(attr);
+			break;
+		case '-':
+			am->match_mode = MATCH_UNSET;
+			attr++;
+			attr_len = strlen(attr);
+			break;
+		default:
+			attr_len = strcspn(attr, "=");
+			if (attr[attr_len] != '=')
+				am->match_mode = MATCH_SET;
+			else {
+				const char *v = &attr[attr_len + 1];
+				am->match_mode = MATCH_VALUE;
+				am->value = attr_value_unescape(v);
+			}
+			break;
+		}
+
+		am->attr = git_attr_counted(attr, attr_len);
+		if (!am->attr) {
+			struct strbuf sb = STRBUF_INIT;
+			am->match_mode = INVALID_ATTR;
+			invalid_attr_name_message(&sb, attr, attr_len);
+			die(_("invalid attribute in '%s': '%s'"), value, sb.buf);
+		}
+
+		git_attr_check_append(item->attr_check, am->attr);
+	}
+
+	string_list_clear(&list, 0);
+	return;
+}
+
+static void eat_long_magic(struct pathspec_item *item, const char *elt,
+		unsigned *magic, int *pathspec_prefix,
+		const char **copyfrom_, const char **long_magic_end)
+{
+	int i;
+	const char *copyfrom = *copyfrom_;
+	const char *body;
+	/* longhand */
+	const char *nextat;
+	for (copyfrom = elt + 2;
+	     *copyfrom && *copyfrom != ')';
+	     copyfrom = nextat) {
+		size_t len = strcspn_escaped(copyfrom, ",)");
+		if (copyfrom[len] == ',')
+			nextat = copyfrom + len + 1;
+		else
+			/* handle ')' and '\0' */
+			nextat = copyfrom + len;
+		if (!len)
+			continue;
+
+		if (skip_prefix(copyfrom, "prefix:", &body)) {
+			char *endptr;
+			*pathspec_prefix = strtol(body, &endptr, 10);
+			if (endptr - copyfrom != len)
+				die(_("invalid parameter for pathspec magic 'prefix'"));
+			continue;
+		}
+
+		if (skip_prefix(copyfrom, "attr:", &body)) {
+			char *attr_body = xmemdupz(body, len - strlen("attr:"));
+			parse_pathspec_attr_match(item, attr_body);
+			free(attr_body);
+			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 (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++;
+	*copyfrom_ = copyfrom;
+}
+
+int pathspec_is_non_threadable(const struct pathspec *pathspec)
+{
+	int i;
+
+	for (i = 0; i < pathspec->nr; i++) {
+		const struct pathspec_item *item = &pathspec->items[i];
+		if (item->attr_check)
+			return 1;
+	}
+	return 0;
+}
+
 /*
  * Take an element of a pathspec and check for magic signatures.
  * Append the result to the prefix. Return the magic bitmap.
@@ -150,43 +325,7 @@ static unsigned prefix_pathspec(struct pathspec_item *item,
 	    (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;
-				}
-			}
-			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++;
+		eat_long_magic(item, elt, &magic, &pathspec_prefix, &copyfrom, &long_magic_end);
 	} else {
 		/* shorthand */
 		for (copyfrom = elt + 1;
@@ -414,7 +553,10 @@ void parse_pathspec(struct pathspec *pathspec,
 	for (i = 0; i < n; i++) {
 		unsigned short_magic;
 		entry = argv[i];
-
+		item[i].attr_check = NULL;
+		item[i].attr_match = NULL;
+		item[i].attr_match_nr = 0;
+		item[i].attr_match_alloc = 0;
 		item[i].magic = prefix_pathspec(item + i, &short_magic,
 						argv + i, flags,
 						prefix, prefixlen, entry);
@@ -436,6 +578,13 @@ void parse_pathspec(struct pathspec *pathspec,
 		if (item[i].nowildcard_len < item[i].len)
 			pathspec->has_wildcard = 1;
 		pathspec->magic |= item[i].magic;
+
+		if (item[i].attr_match_nr) {
+			int j;
+			for (j = 0; j < item[i].attr_match_nr; j++)
+				if (item[i].attr_match[j].match_mode == INVALID_ATTR)
+					die(_("attribute spec in the wrong syntax are prohibited."));
+		}
 	}
 
 	if (nr_exclude == n)
@@ -491,6 +640,16 @@ void copy_pathspec(struct pathspec *dst, const struct pathspec *src)
 
 void clear_pathspec(struct pathspec *pathspec)
 {
+	int i, j;
+	for (i = 0; i < pathspec->nr; i++) {
+		if (!pathspec->items[i].attr_match_nr)
+			continue;
+		for (j = 0; j < pathspec->items[j].attr_match_nr; j++)
+			free(pathspec->items[i].attr_match[j].value);
+		free(pathspec->items[i].attr_match);
+		git_attr_check_free(pathspec->items[i].attr_check);
+	}
+
 	free(pathspec->items);
 	pathspec->items = NULL;
 }
diff --git a/pathspec.h b/pathspec.h
index 4a80f6fc96..b25181a0d0 100644
--- a/pathspec.h
+++ b/pathspec.h
@@ -32,6 +32,22 @@ struct pathspec {
 		int len, prefix;
 		int nowildcard_len;
 		int flags;
+		int attr_match_nr;
+		int attr_match_alloc;
+		struct attr_match {
+			struct git_attr *attr;
+			char *value;
+			enum attr_match_mode {
+				MATCH_SET,
+				MATCH_UNSET,
+				MATCH_VALUE,
+				MATCH_UNSPECIFIED,
+				MATCH_NOT_UNSPECIFIED,
+				MATCH_SET_OR_VALUE,
+				INVALID_ATTR
+			} match_mode;
+		} *attr_match;
+		struct git_attr_check *attr_check;
 	} *items;
 };
 
@@ -99,4 +115,6 @@ extern void add_pathspec_matches_against_index(const struct pathspec *pathspec,
 extern const char *check_path_for_gitlink(const char *path);
 extern void die_if_path_beyond_symlink(const char *path, const char *prefix);
 
+extern int pathspec_is_non_threadable(const struct pathspec *);
+
 #endif /* PATHSPEC_H */
diff --git a/preload-index.c b/preload-index.c
index c1fe3a3ef9..af468789f5 100644
--- a/preload-index.c
+++ b/preload-index.c
@@ -76,6 +76,10 @@ static void preload_index(struct index_state *index,
 	if (!core_preload_index)
 		return;
 
+	/* Do not preload when pathspec uses non-threadable subsystems */
+	if (pathspec && pathspec_is_non_threadable(pathspec))
+		return; /* for now ... */
+
 	threads = index->cache_nr / THREAD_COST;
 	if (threads < 2)
 		return;
diff --git a/t/t6134-pathspec-with-labels.sh b/t/t6134-pathspec-with-labels.sh
new file mode 100755
index 0000000000..f1e355f657
--- /dev/null
+++ b/t/t6134-pathspec-with-labels.sh
@@ -0,0 +1,176 @@
+#!/bin/sh
+
+test_description='test labels in pathspecs'
+. ./test-lib.sh
+
+test_expect_success 'setup a tree' '
+	cat <<-EOF >expect &&
+	fileA
+	fileAB
+	fileAC
+	fileB
+	fileBC
+	fileC
+	fileNoLabel
+	fileSetLabel
+	fileUnsetLabel
+	fileValue
+	fileWrongLabel
+	sub/fileA
+	sub/fileAB
+	sub/fileAC
+	sub/fileB
+	sub/fileBC
+	sub/fileC
+	sub/fileNoLabel
+	sub/fileSetLabel
+	sub/fileUnsetLabel
+	sub/fileValue
+	sub/fileWrongLabel
+	EOF
+	mkdir sub &&
+	while read path
+	do
+		: >$path &&
+		git add $path || return 1
+	done <expect &&
+	git commit -m "initial commit" &&
+	git ls-files >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'pathspec with no attr' '
+	test_must_fail git ls-files ":(attr:)"
+'
+
+test_expect_success 'pathspec with labels and non existent .gitattributes' '
+	git ls-files ":(attr:label)" >actual &&
+	test_must_be_empty actual
+'
+
+test_expect_success 'setup .gitattributes' '
+	cat <<-EOF >.gitattributes &&
+	fileA labelA
+	fileB labelB
+	fileC labelC
+	fileAB labelA labelB
+	fileAC labelA labelC
+	fileBC labelB labelC
+	fileUnsetLabel -label
+	fileSetLabel label
+	fileValue label=foo
+	fileWrongLabel label☺
+	EOF
+	git add .gitattributes &&
+	git commit -m "add attributes"
+'
+
+test_expect_success 'check specific set attr' '
+	cat <<-EOF >expect &&
+	fileSetLabel
+	sub/fileSetLabel
+	EOF
+	git ls-files ":(attr:label)" >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'check specific unset attr' '
+	cat <<-EOF >expect &&
+	fileUnsetLabel
+	sub/fileUnsetLabel
+	EOF
+	git ls-files ":(attr:-label)" >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'check specific value attr' '
+	cat <<-EOF >expect &&
+	fileValue
+	sub/fileValue
+	EOF
+	git ls-files ":(attr:label=foo)" >actual &&
+	test_cmp expect actual &&
+	git ls-files ":(attr:label=bar)" >actual &&
+	test_must_be_empty actual
+'
+
+test_expect_success 'check unspecified attr' '
+	cat <<-EOF >expect &&
+	.gitattributes
+	fileA
+	fileAB
+	fileAC
+	fileB
+	fileBC
+	fileC
+	fileNoLabel
+	fileWrongLabel
+	sub/fileA
+	sub/fileAB
+	sub/fileAC
+	sub/fileB
+	sub/fileBC
+	sub/fileC
+	sub/fileNoLabel
+	sub/fileWrongLabel
+	EOF
+	git ls-files ":(attr:!label)" >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'check multiple unspecified attr' '
+	cat <<-EOF >expect &&
+	.gitattributes
+	fileC
+	fileNoLabel
+	fileWrongLabel
+	sub/fileC
+	sub/fileNoLabel
+	sub/fileWrongLabel
+	EOF
+	git ls-files ":(attr:!labelB !labelA !label)" >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'check label with more labels but excluded path' '
+	cat <<-EOF >expect &&
+	fileAB
+	fileB
+	fileBC
+	EOF
+	git ls-files ":(attr:labelB)" ":(exclude)sub/" >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'check label excluding other labels' '
+	cat <<-EOF >expect &&
+	fileAB
+	fileB
+	fileBC
+	sub/fileAB
+	sub/fileB
+	EOF
+	git ls-files ":(attr:labelB)" ":(exclude,attr:labelC)sub/" >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'abort on giving invalid label on the command line' '
+	test_must_fail git ls-files . ":(attr:☺)"
+'
+
+test_expect_success 'abort on asking for wrong magic' '
+	test_must_fail git ls-files . ":(attr:-label=foo)" &&
+	test_must_fail git ls-files . ":(attr:!label=foo)"
+'
+
+test_expect_success 'check attribute list' '
+	cat <<-EOF >>.gitattributes &&
+	* whitespace=indent,trail,space
+	EOF
+	cat .gitattributes &&
+	git ls-files ":(attr:whitespace=indent\,trail\,space)" >actual &&
+	git ls-files >expect &&
+	test_cmp expect actual
+'
+
+test_done