git@vger.kernel.org mailing list mirror (one of many)
 help / color / mirror / code / Atom feed
From: "Derrick Stolee via GitGitGadget" <gitgitgadget@gmail.com>
To: git@vger.kernel.org
Cc: me@ttaylorr.com, peff@peff.net, newren@gmail.com,
	Derrick Stolee <dstolee@microsoft.com>,
	Derrick Stolee <dstolee@microsoft.com>
Subject: [PATCH 8/8] sparse-checkout: write escaped patterns in cone mode
Date: Tue, 14 Jan 2020 19:26:02 +0000	[thread overview]
Message-ID: <79b6e9a565fde766954d7cda84a835b9015af6cb.1579029963.git.gitgitgadget@gmail.com> (raw)
In-Reply-To: <pull.513.git.1579029962.gitgitgadget@gmail.com>

From: Derrick Stolee <dstolee@microsoft.com>

If a user somehow creates a directory with an asterisk (*) or backslash
(\), then the "git sparse-checkout set" command will struggle to provide
the correct pattern in the sparse-checkout file. When not in cone mode,
the provided pattern is written directly into the sparse-checkout file.
However, in cone mode we expect a list of paths to directories and then
we convert those into patterns.

Even more specifically, the goal is to always allow the following from
the root of a repo:

  git ls-tree --name-only -d HEAD | git sparse-checkout set --stdin

The ls-tree command provides directory names with an unescaped asterisk.
It also quotes the directories that contain an escaped backslash. We
must remove these quotes, then keep the escaped backslashes.

However, there is some care needed for the timing of these escapes. The
in-memory pattern list is used to update the working directory before
writing the patterns to disk. Thus, we need the command to have the
unescaped names in the hashsets for the cone comparisons, then escape
the patterns later.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 builtin/sparse-checkout.c          | 48 ++++++++++++++++++++++++++++--
 t/t1091-sparse-checkout-builtin.sh | 21 +++++++++++--
 2 files changed, 64 insertions(+), 5 deletions(-)

diff --git a/builtin/sparse-checkout.c b/builtin/sparse-checkout.c
index 3cee8ab46e..61d2c30036 100644
--- a/builtin/sparse-checkout.c
+++ b/builtin/sparse-checkout.c
@@ -140,6 +140,22 @@ static int update_working_directory(struct pattern_list *pl)
 	return result;
 }
 
+static char *escaped_pattern(char *pattern)
+{
+	char *p = pattern;
+	struct strbuf final = STRBUF_INIT;
+
+	while (*p) {
+		if (*p == '*' || *p == '\\')
+			strbuf_addch(&final, '\\');
+
+		strbuf_addch(&final, *p);
+		p++;
+	}
+
+	return strbuf_detach(&final, NULL);
+}
+
 static void write_cone_to_file(FILE *fp, struct pattern_list *pl)
 {
 	int i;
@@ -164,10 +180,11 @@ static void write_cone_to_file(FILE *fp, struct pattern_list *pl)
 	fprintf(fp, "/*\n!/*/\n");
 
 	for (i = 0; i < sl.nr; i++) {
-		char *pattern = sl.items[i].string;
+		char *pattern = escaped_pattern(sl.items[i].string);
 
 		if (strlen(pattern))
 			fprintf(fp, "%s/\n!%s/*/\n", pattern, pattern);
+		free(pattern);
 	}
 
 	string_list_clear(&sl, 0);
@@ -185,8 +202,9 @@ static void write_cone_to_file(FILE *fp, struct pattern_list *pl)
 	string_list_remove_duplicates(&sl, 0);
 
 	for (i = 0; i < sl.nr; i++) {
-		char *pattern = sl.items[i].string;
+		char *pattern = escaped_pattern(sl.items[i].string);
 		fprintf(fp, "%s/\n", pattern);
+		free(pattern);
 	}
 }
 
@@ -337,7 +355,9 @@ static void insert_recursive_pattern(struct pattern_list *pl, struct strbuf *pat
 {
 	struct pattern_entry *e = xmalloc(sizeof(*e));
 	e->patternlen = path->len;
-	e->pattern = strbuf_detach(path, NULL);
+	e->pattern = dup_and_filter_pattern(path->buf);
+	strbuf_release(path);
+
 	hashmap_entry_init(&e->ent,
 			   ignore_case ?
 			   strihash(e->pattern) :
@@ -369,6 +389,7 @@ static void insert_recursive_pattern(struct pattern_list *pl, struct strbuf *pat
 
 static void strbuf_to_cone_pattern(struct strbuf *line, struct pattern_list *pl)
 {
+	int i;
 	strbuf_trim(line);
 
 	strbuf_trim_trailing_dir_sep(line);
@@ -376,6 +397,27 @@ static void strbuf_to_cone_pattern(struct strbuf *line, struct pattern_list *pl)
 	if (!line->len)
 		return;
 
+	for (i = 0; i < line->len; i++) {
+		if (line->buf[i] == '*') {
+			strbuf_insert(line, i, "\\", 1);
+			i++;
+		}
+
+		if (line->buf[i] == '\\') {
+			if (i < line->len - 1 && line->buf[i + 1] == '\\')
+				i++;
+			else
+				strbuf_insert(line, i, "\\", 1);
+
+			i++;
+		}
+	}
+
+	if (line->buf[0] == '"' && line->buf[line->len - 1] == '"') {
+		strbuf_remove(line, 0, 1);
+		strbuf_remove(line, line->len - 1, 1);
+	}
+
 	if (line->buf[0] != '/')
 		strbuf_insert(line, 0, "/", 1);
 
diff --git a/t/t1091-sparse-checkout-builtin.sh b/t/t1091-sparse-checkout-builtin.sh
index 051c1f3bf2..3da7c10bd9 100755
--- a/t/t1091-sparse-checkout-builtin.sh
+++ b/t/t1091-sparse-checkout-builtin.sh
@@ -309,6 +309,9 @@ check_read_tree_errors () {
 	REPO=$1
 	FILES=$2
 	ERRORS=$3
+	git -C $REPO -c core.sparseCheckoutCone=false read-tree -mu HEAD 2>err &&
+	test_must_be_empty err &&
+	check_files $REPO "$FILES" &&
 	git -C $REPO read-tree -mu HEAD 2>err &&
 	if test -z "$ERRORS"
 	then
@@ -379,14 +382,28 @@ test_expect_success BSLASHPSPEC 'pattern-checks: escaped "*"' '
 	git -C escaped reset --hard $COMMIT &&
 	check_files escaped "a deep folder1 folder2 zbad\\dir zdoes*exist" &&
 	git -C escaped sparse-checkout init --cone &&
-	cat >escaped/.git/info/sparse-checkout <<-\EOF &&
+	git -C escaped sparse-checkout set zbad\\dir zdoes\*not\*exist zdoes\*exist &&
+	cat >expect <<-\EOF &&
 	/*
 	!/*/
 	/zbad\\dir/
+	/zdoes\*exist/
 	/zdoes\*not\*exist/
+	EOF
+	test_cmp expect escaped/.git/info/sparse-checkout &&
+	check_read_tree_errors escaped "a zbad\\dir zdoes*exist" &&
+	git -C escaped ls-tree -d --name-only HEAD | git -C escaped sparse-checkout set --stdin &&
+	cat >expect <<-\EOF &&
+	/*
+	!/*/
+	/deep/
+	/folder1/
+	/folder2/
+	/zbad\\dir/
 	/zdoes\*exist/
 	EOF
-	check_read_tree_errors escaped "a zbad\\dir zdoes*exist"
+	test_cmp expect escaped/.git/info/sparse-checkout &&
+	check_files escaped "a deep folder1 folder2 zbad\\dir zdoes*exist"
 '
 
 test_done
-- 
gitgitgadget

  parent reply	other threads:[~2020-01-14 19:26 UTC|newest]

Thread overview: 82+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-01-14 19:25 [PATCH 0/8] Harden the sparse-checkout builtin Derrick Stolee via GitGitGadget
2020-01-14 19:25 ` [PATCH 1/8] t1091: use check_files to reduce boilerplate Derrick Stolee via GitGitGadget
2020-01-16 21:40   ` Junio C Hamano
2020-01-14 19:25 ` [PATCH 2/8] sparse-checkout: create leading directories Derrick Stolee via GitGitGadget
2020-01-16 21:46   ` Junio C Hamano
2020-01-14 19:25 ` [PATCH 3/8] clone: fix --sparse option with URLs Derrick Stolee via GitGitGadget
2020-01-14 19:30   ` Taylor Blau
2020-01-14 19:25 ` [PATCH 4/8] sparse-checkout: cone mode does not recognize "**" Derrick Stolee via GitGitGadget
2020-01-14 21:16   ` Jeff King
2020-01-14 19:25 ` [PATCH 5/8] sparse-checkout: detect short patterns Derrick Stolee via GitGitGadget
2020-01-14 19:26 ` [PATCH 6/8] sparse-checkout: warn on incorrect '*' in patterns Derrick Stolee via GitGitGadget
2020-01-14 19:26 ` [PATCH 7/8] sparse-checkout: properly match escaped characters Derrick Stolee via GitGitGadget
2020-01-14 21:21   ` Jeff King
2020-01-14 22:08     ` Derrick Stolee
2020-01-14 19:26 ` Derrick Stolee via GitGitGadget [this message]
2020-01-14 21:25   ` [PATCH 8/8] sparse-checkout: write escaped patterns in cone mode Jeff King
2020-01-14 22:11     ` Derrick Stolee
2020-01-14 22:48       ` Jeff King
2020-01-24 21:10         ` Derrick Stolee
2020-01-24 21:42           ` Jeff King
2020-01-28 15:03             ` Derrick Stolee
2020-01-14 19:34 ` [PATCH 0/8] Harden the sparse-checkout builtin Taylor Blau
2020-01-14 19:44   ` Derrick Stolee
2020-01-14 21:31     ` Jeff King
2020-01-15 19:16 ` Junio C Hamano
2020-01-15 20:32   ` Derrick Stolee
2020-01-24 21:19 ` [PATCH v2 00/12] " Derrick Stolee via GitGitGadget
2020-01-24 21:19   ` [PATCH v2 01/12] t1091: use check_files to reduce boilerplate Derrick Stolee via GitGitGadget
2020-01-24 21:19   ` [PATCH v2 02/12] t1091: improve here-docs Derrick Stolee via GitGitGadget
2020-01-24 21:19   ` [PATCH v2 03/12] sparse-checkout: create leading directories Derrick Stolee via GitGitGadget
2020-01-24 21:19   ` [PATCH v2 04/12] clone: fix --sparse option with URLs Derrick Stolee via GitGitGadget
2020-01-24 21:19   ` [PATCH v2 05/12] sparse-checkout: fix documentation typo for core.sparseCheckoutCone Jeff King via GitGitGadget
2020-01-24 21:19   ` [PATCH v2 06/12] sparse-checkout: cone mode does not recognize "**" Derrick Stolee via GitGitGadget
2020-01-24 21:19   ` [PATCH v2 07/12] sparse-checkout: detect short patterns Derrick Stolee via GitGitGadget
2020-01-24 21:19   ` [PATCH v2 08/12] sparse-checkout: warn on incorrect '*' in patterns Derrick Stolee via GitGitGadget
2020-01-24 21:19   ` [PATCH v2 09/12] sparse-checkout: properly match escaped characters Derrick Stolee via GitGitGadget
2020-01-24 21:19   ` [PATCH v2 10/12] sparse-checkout: write escaped patterns in cone mode Derrick Stolee via GitGitGadget
2020-01-24 21:19   ` [PATCH v2 11/12] sparse-checkout: use C-style quotes in 'list' subcommand Derrick Stolee via GitGitGadget
2020-01-24 21:19   ` [PATCH v2 12/12] sparse-checkout: improve docs around 'set' in cone mode Derrick Stolee via GitGitGadget
2020-01-28 18:26   ` [PATCH v3 00/12] Harden the sparse-checkout builtin Derrick Stolee via GitGitGadget
2020-01-28 18:26     ` [PATCH v3 01/12] t1091: use check_files to reduce boilerplate Derrick Stolee via GitGitGadget
2020-01-28 18:26     ` [PATCH v3 02/12] t1091: improve here-docs Derrick Stolee via GitGitGadget
2020-01-28 18:26     ` [PATCH v3 03/12] sparse-checkout: create leading directories Derrick Stolee via GitGitGadget
2020-01-28 18:26     ` [PATCH v3 04/12] clone: fix --sparse option with URLs Derrick Stolee via GitGitGadget
2020-01-28 18:26     ` [PATCH v3 05/12] sparse-checkout: fix documentation typo for core.sparseCheckoutCone Jeff King via GitGitGadget
2020-01-28 18:26     ` [PATCH v3 06/12] sparse-checkout: cone mode does not recognize "**" Derrick Stolee via GitGitGadget
2020-01-28 18:26     ` [PATCH v3 07/12] sparse-checkout: detect short patterns Derrick Stolee via GitGitGadget
2020-01-28 18:26     ` [PATCH v3 08/12] sparse-checkout: warn on incorrect '*' in patterns Derrick Stolee via GitGitGadget
2020-01-28 18:26     ` [PATCH v3 09/12] sparse-checkout: properly match escaped characters Derrick Stolee via GitGitGadget
2020-01-29 10:03       ` Jeff King
2020-01-29 13:58         ` Derrick Stolee
2020-01-29 14:04           ` Derrick Stolee
2020-01-28 18:26     ` [PATCH v3 10/12] sparse-checkout: write escaped patterns in cone mode Derrick Stolee via GitGitGadget
2020-01-29 10:17       ` Jeff King
2020-01-29 10:33         ` Jeff King
2020-01-29 14:16           ` Derrick Stolee
2020-01-29 14:39             ` Derrick Stolee
2020-01-30  7:29             ` Jeff King
2020-01-30 15:01               ` Derrick Stolee
2020-01-28 18:26     ` [PATCH v3 11/12] sparse-checkout: use C-style quotes in 'list' subcommand Derrick Stolee via GitGitGadget
2020-01-29 10:23       ` Jeff King
2020-01-28 18:26     ` [PATCH v3 12/12] sparse-checkout: improve docs around 'set' in cone mode Derrick Stolee via GitGitGadget
2020-01-31 20:16     ` [PATCH v4 00/15] Harden the sparse-checkout builtin Derrick Stolee via GitGitGadget
2020-01-31 20:16       ` [PATCH v4 01/15] t1091: use check_files to reduce boilerplate Derrick Stolee via GitGitGadget
2020-01-31 20:16       ` [PATCH v4 02/15] t1091: improve here-docs Derrick Stolee via GitGitGadget
2020-01-31 20:16       ` [PATCH v4 03/15] sparse-checkout: create leading directories Derrick Stolee via GitGitGadget
2020-01-31 20:16       ` [PATCH v4 04/15] clone: fix --sparse option with URLs Derrick Stolee via GitGitGadget
2020-01-31 20:16       ` [PATCH v4 05/15] sparse-checkout: fix documentation typo for core.sparseCheckoutCone Jeff King via GitGitGadget
2020-01-31 20:16       ` [PATCH v4 06/15] sparse-checkout: cone mode does not recognize "**" Derrick Stolee via GitGitGadget
2020-01-31 20:16       ` [PATCH v4 07/15] sparse-checkout: detect short patterns Derrick Stolee via GitGitGadget
2020-01-31 20:16       ` [PATCH v4 08/15] sparse-checkout: warn on globs in cone patterns Derrick Stolee via GitGitGadget
2020-01-31 20:16       ` [PATCH v4 09/15] sparse-checkout: properly match escaped characters Derrick Stolee via GitGitGadget
2020-01-31 20:16       ` [PATCH v4 10/15] sparse-checkout: write escaped patterns in cone mode Derrick Stolee via GitGitGadget
2020-01-31 20:16       ` [PATCH v4 11/15] sparse-checkout: unquote C-style strings over --stdin Derrick Stolee via GitGitGadget
2020-01-31 20:16       ` [PATCH v4 12/15] sparse-checkout: use C-style quotes in 'list' subcommand Derrick Stolee via GitGitGadget
2020-01-31 20:16       ` [PATCH v4 13/15] sparse-checkout: escape all glob characters on write Derrick Stolee via GitGitGadget
2020-01-31 20:16       ` [PATCH v4 14/15] sparse-checkout: improve docs around 'set' in cone mode Derrick Stolee via GitGitGadget
2020-01-31 20:16       ` [PATCH v4 15/15] sparse-checkout: fix cone mode behavior mismatch Derrick Stolee via GitGitGadget
2020-01-31 20:36       ` [PATCH v4 00/15] Harden the sparse-checkout builtin Elijah Newren
2020-02-03 14:09         ` Derrick Stolee
2020-02-08 23:32           ` Taylor Blau
2020-02-09 17:27             ` Junio C Hamano

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

  List information: http://vger.kernel.org/majordomo-info.html

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

  git send-email \
    --in-reply-to=79b6e9a565fde766954d7cda84a835b9015af6cb.1579029963.git.gitgitgadget@gmail.com \
    --to=gitgitgadget@gmail.com \
    --cc=dstolee@microsoft.com \
    --cc=git@vger.kernel.org \
    --cc=me@ttaylorr.com \
    --cc=newren@gmail.com \
    --cc=peff@peff.net \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
Code repositories for project(s) associated with this public inbox

	https://80x24.org/mirrors/git.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).