[PATCHv8 5/5] pathspec: allow querying for attributes

[Stefan Beller <sbeller@google.com>]

The pathspec mechanism is extended via the new
":(attr:eol=input)pattern/to/match" syntax to filter paths so that it
requires paths to not just match the given pattern but also have the
specified attrs attached for them to be chosen.

Signed-off-by: Stefan Beller <sbeller@google.com>
---
 Documentation/glossary-content.txt |  17 ++++
 dir.c                              |  35 ++++++++
 pathspec.c                         |  97 +++++++++++++++++++++-
 pathspec.h                         |  16 ++++
 t/t6134-pathspec-with-labels.sh    | 166 +++++++++++++++++++++++++++++++++++++
 5 files changed, 327 insertions(+), 4 deletions(-)
 create mode 100755 t/t6134-pathspec-with-labels.sh

diff --git a/Documentation/glossary-content.txt b/Documentation/glossary-content.txt
index cafc284..aa9f220 100644
--- a/Documentation/glossary-content.txt
+++ b/Documentation/glossary-content.txt
@@ -384,6 +384,23 @@ full pathname may have special meaning:
 +
 Glob magic is incompatible with literal magic.
 
+attr;;
+	Additionally to matching the pathspec, the path must have the
+	attribute as specified. The syntax for specifying the required
+	attributes is "`attr: [mode] <attribute name> [=value]`"
++
+Attributes can have 4 states (Set, Unset, Set to a value, unspecified) and
+you can query each attribute for certain states. The "`[mode]`" is a special
+character to indicate which attribute states are looked for. The following
+modes are available:
+
+ - an empty "`[mode]`" matches if the attribute is set
+ - "`-`" the attribute must be unset
+ - "`!`" the attribute must be unspecified
+ - an empty "`[mode]`" combined with "`[=value]`" matches if the attribute has
+   the given value.
++
+
 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 996653b..f60a503 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"
@@ -215,6 +216,37 @@ 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
 
@@ -270,6 +302,9 @@ 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 4dff252..b795a9c 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.
@@ -88,12 +89,74 @@ static void prefix_short_magic(struct strbuf *sb, int prefixlen,
 	strbuf_addf(sb, ",prefix:%d)", prefixlen);
 }
 
+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];
+
+		if (attr[0] == '!')
+			am->match_mode = MATCH_UNSPECIFIED;
+		else if (attr[0] == '-')
+			am->match_mode = MATCH_UNSET;
+		else
+			am->match_mode = MATCH_SET;
+
+		if (am->match_mode != MATCH_SET)
+			/* skip first character */
+			attr++;
+
+		attr_len = strcspn(attr, "=");
+		if (attr[attr_len] == '=') {
+			am->match_mode = MATCH_VALUE;
+			am->value = xstrdup(&attr[attr_len + 1]);
+			if (strchr(am->value, '\\'))
+				die(_("attr spec values must not contain backslashes"));
+		} else
+			am->value = NULL;
+
+		if (!attr_name_valid(attr, attr_len)) {
+			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);
+		}
+
+		am->attr = git_attr_counted(attr, attr_len);
+		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;
@@ -108,15 +171,21 @@ static void eat_long_magic(struct pathspec_item *item, const char *elt,
 		if (!len)
 			continue;
 
-		if (starts_with(copyfrom, "prefix:")) {
+		if (skip_prefix(copyfrom, "prefix:", &body)) {
 			char *endptr;
-			*pathspec_prefix = strtol(copyfrom + 7,
-						  &endptr, 10);
+			*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)) {
@@ -425,7 +494,10 @@ 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);
@@ -447,6 +519,13 @@ 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)
@@ -502,6 +581,16 @@ void copy_pathspec(struct pathspec *dst, const struct pathspec *src)
 
 void free_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 0c11262..5308137 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;
 };
 
diff --git a/t/t6134-pathspec-with-labels.sh b/t/t6134-pathspec-with-labels.sh
new file mode 100755
index 0000000..c0d8cda
--- /dev/null
+++ b/t/t6134-pathspec-with-labels.sh
@@ -0,0 +1,166 @@
+#!/bin/sh
+
+test_description='test labels in pathspecs'
+. ./test-lib.sh
+
+test_expect_success 'setup a tree' '
+	mkdir sub &&
+	for p in fileA fileB fileC fileAB fileAC fileBC fileNoLabel fileUnsetLabel fileSetLabel fileValue fileWrongLabel; do
+		: >$p &&
+		git add $p &&
+		: >sub/$p
+		git add sub/$p
+	done &&
+	git commit -m $p &&
+	git ls-files >actual &&
+	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
+	test_cmp expect actual
+'
+
+test_expect_success 'pathspec with no attr' '
+	test_must_fail git ls-files ":(attr:)" 2>actual &&
+	test_i18ngrep fatal actual
+'
+
+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"
+'
+
+sq="'"
+
+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:☺)" 2>actual &&
+	test_i18ngrep "fatal" actual
+'
+
+test_done
-- 
2.8.2.123.g3bde101