public inbox for git@vger.kernel.org 
 help / color / mirror / Atom feed
From: Stefan Beller <sbeller@google•com>
To: gitster@pobox•com
Cc: git@vger•kernel.org, bmwill@google•com, pclouds@gmail•com,
	Stefan Beller <sbeller@google•com>
Subject: [PATCH 32/36] pathspec: allow querying for attributes
Date: Sat, 22 Oct 2016 16:32:21 -0700	[thread overview]
Message-ID: <20161022233225.8883-33-sbeller@google.com> (raw)
In-Reply-To: <20161022233225.8883-1-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>
Signed-off-by: Junio C Hamano <gitster@pobox•com>
---
 Documentation/glossary-content.txt |  20 +++++
 dir.c                              |  35 ++++++++
 pathspec.c                         | 103 +++++++++++++++++++++-
 pathspec.h                         |  16 ++++
 t/t6134-pathspec-with-labels.sh    | 170 +++++++++++++++++++++++++++++++++++++
 5 files changed, 340 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 8ad29e6..f90bd45 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 3bad1ad..3ec9117 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;
+	struct git_attr_result *res = git_attr_result_alloc(item->attr_check);
+
+	git_check_attr(name, item->attr_check, res);
+	for (i = 0; i < item->attr_match_nr; i++) {
+		const char *value;
+		int matched;
+		enum attr_match_mode match_mode;
+
+		value = res[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 d44f8e7..0eee177 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 +89,78 @@ 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)
+		git_attr_check_alloc(&item->attr_check);
+	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 {
+				am->match_mode = MATCH_VALUE;
+				am->value = xstrdup(&attr[attr_len + 1]);
+				if (strchr(am->value, '\\'))
+					die(_("attr spec values must not contain backslashes"));
+			}
+			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;
@@ -108,15 +175,21 @@ 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 +498,10 @@ 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 +523,13 @@ 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)
@@ -500,6 +583,18 @@ 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);
+		if (pathspec->items[i].attr_check)
+			git_attr_check_clear(pathspec->items[i].attr_check);
+		free(pathspec->items[i].attr_check);
+	}
+
 	free(pathspec->items);
 	pathspec->items = NULL;
 }
diff --git a/pathspec.h b/pathspec.h
index 59809e4..aebe6ea 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..1c9323c
--- /dev/null
+++ b/t/t6134-pathspec-with-labels.sh
@@ -0,0 +1,170 @@
+#!/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 'checking attributes in a multithreaded process' '
+	git status ":(attr:labelB)"
+'
+
+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_done
-- 
2.10.1.508.g6572022


  parent reply	other threads:[~2016-10-22 23:34 UTC|newest]

Thread overview: 81+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-10-22 23:31 [PATCHv2 00/36] Revamping the attr subsystem! Stefan Beller
2016-10-22 23:31 ` [PATCH 01/36] commit.c: use strchrnul() to scan for one line Stefan Beller
2016-10-22 23:31 ` [PATCH 02/36] attr.c: " Stefan Beller
2016-10-22 23:31 ` [PATCH 03/36] attr.c: update a stale comment on "struct match_attr" Stefan Beller
2016-10-22 23:31 ` [PATCH 04/36] attr.c: explain the lack of attr-name syntax check in parse_attr() Stefan Beller
2016-10-22 23:31 ` [PATCH 05/36] attr.c: complete a sentence in a comment Stefan Beller
2016-10-22 23:31 ` [PATCH 06/36] attr.c: mark where #if DEBUG ends more clearly Stefan Beller
2016-10-22 23:31 ` [PATCH 07/36] attr.c: simplify macroexpand_one() Stefan Beller
2016-10-22 23:31 ` [PATCH 08/36] attr.c: tighten constness around "git_attr" structure Stefan Beller
2016-10-22 23:31 ` [PATCH 09/36] attr.c: plug small leak in parse_attr_line() Stefan Beller
2016-10-22 23:31 ` [PATCH 10/36] attr: rename function and struct related to checking attributes Stefan Beller
2016-10-22 23:32 ` [PATCH 11/36] attr: (re)introduce git_check_attr() and struct git_attr_check Stefan Beller
2016-10-22 23:32 ` [PATCH 12/36] attr: convert git_all_attrs() to use "struct git_attr_check" Stefan Beller
2016-10-22 23:32 ` [PATCH 13/36] attr: convert git_check_attrs() callers to use the new API Stefan Beller
2016-10-22 23:32 ` [PATCH 14/36] attr: retire git_check_attrs() API Stefan Beller
2016-10-22 23:32 ` [PATCH 15/36] attr: add counted string version of git_check_attr() Stefan Beller
2016-10-22 23:32 ` [PATCH 16/36] attr: add counted string version of git_attr() Stefan Beller
2016-10-22 23:32 ` [PATCH 17/36] attr: expose validity check for attribute names Stefan Beller
2016-10-23 15:07   ` Ramsay Jones
2016-10-24 21:07     ` Stefan Beller
2016-10-27 20:57       ` Stefan Beller
2016-10-26 21:20     ` [PATCH] attr: expose error reporting function for invalid " Stefan Beller
2016-10-22 23:32 ` [PATCH 18/36] attr: support quoting pathname patterns in C style Stefan Beller
2016-10-22 23:32 ` [PATCH 19/36] attr.c: add push_stack() helper Stefan Beller
2016-10-22 23:32 ` [PATCH 20/36] attr.c: pass struct git_attr_check down the callchain Stefan Beller
2016-10-22 23:32 ` [PATCH 21/36] attr.c: rename a local variable check Stefan Beller
2016-10-22 23:32 ` [PATCH 22/36] attr.c: correct ugly hack for git_all_attrs() Stefan Beller
2016-10-22 23:32 ` [PATCH 23/36] attr.c: introduce empty_attr_check_elems() Stefan Beller
2016-10-22 23:32 ` [PATCH 24/36] attr.c: always pass check[] to collect_some_attrs() Stefan Beller
2016-10-22 23:32 ` [PATCH 25/36] attr.c: outline the future plans by heavily commenting Stefan Beller
2016-10-22 23:32 ` [PATCH 26/36] attr: make git_check_attr_counted static Stefan Beller
2016-10-22 23:32 ` [PATCH 27/36] attr: convert to new threadsafe API Stefan Beller
2016-10-24 18:55   ` Junio C Hamano
2016-10-24 19:18     ` Stefan Beller
2016-10-26 14:06       ` Duy Nguyen
2016-10-26  8:52   ` Johannes Schindelin
2016-10-26  9:35     ` Simon Ruderich
2016-10-26 12:15       ` Jeff King
2016-10-26 19:51         ` Stefan Beller
2016-10-26 20:20           ` Jeff King
2016-10-26 20:25           ` Johannes Sixt
2016-10-26 20:26             ` Jeff King
2016-10-26 20:40               ` Johannes Sixt
2016-10-26 20:46                 ` Stefan Beller
2016-10-26 22:41                   ` [PATCHv2 1/2] " Stefan Beller
2016-10-26 23:14                     ` Junio C Hamano
2016-10-27  0:08                       ` Stefan Beller
2016-10-27  0:16                         ` Junio C Hamano
2016-10-27  0:22                           ` Stefan Beller
2016-10-27  0:50                             ` Junio C Hamano
2016-10-27  0:49                     ` Junio C Hamano
2016-10-27  2:19                       ` Stefan Beller
2016-10-27  4:13                         ` Junio C Hamano
2016-10-27  5:44                           ` Junio C Hamano
2016-10-27 22:15                             ` [PATCH] " Stefan Beller
2016-10-28  8:55                               ` Johannes Schindelin
2016-10-28 17:20                               ` Junio C Hamano
2016-10-28 17:30                                 ` Junio C Hamano
2016-10-28 18:16                               ` Johannes Sixt
2016-10-26 20:43               ` [PATCH 27/36] " Stefan Beller
2016-10-26 13:52   ` Duy Nguyen
2016-10-22 23:32 ` [PATCH 28/36] attr: keep attr stack for each check Stefan Beller
2016-10-23 15:10   ` Ramsay Jones
2016-10-26 23:10     ` Stefan Beller
2016-10-24 19:07   ` Junio C Hamano
2016-10-24 19:32     ` Stefan Beller
2016-10-24 20:29       ` Junio C Hamano
2016-10-22 23:32 ` [PATCH 29/36] Documentation: fix a typo Stefan Beller
2016-10-22 23:32 ` [PATCH 30/36] pathspec: move long magic parsing out of prefix_pathspec Stefan Beller
2016-10-22 23:32 ` [PATCH 31/36] pathspec: move prefix check out of the inner loop Stefan Beller
2016-10-22 23:32 ` Stefan Beller [this message]
2016-10-26 13:33   ` [PATCH 32/36] pathspec: allow querying for attributes Duy Nguyen
2016-10-27 21:32     ` Stefan Beller
2016-10-27 18:29   ` Junio C Hamano
2016-11-09  9:45     ` Duy Nguyen
2016-11-09 18:08       ` Stefan Beller
2016-11-09 22:25         ` Junio C Hamano
2016-10-22 23:32 ` [PATCH 33/36] pathspec: allow escaped query values Stefan Beller
2016-10-22 23:32 ` [PATCH 34/36] submodule update: add `--init-default-path` switch Stefan Beller
2016-10-22 23:32 ` [PATCH 35/36] clone: add --init-submodule=<pathspec> switch Stefan Beller
2016-10-22 23:32 ` [PATCH 36/36] completion: clone can initialize specific submodules Stefan Beller

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20161022233225.8883-33-sbeller@google.com \
    --to=sbeller@google$(echo .)com \
    --cc=bmwill@google$(echo .)com \
    --cc=git@vger$(echo .)kernel.org \
    --cc=gitster@pobox$(echo .)com \
    --cc=pclouds@gmail$(echo .)com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox