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 v3 09/12] sparse-checkout: properly match escaped characters
Date: Tue, 28 Jan 2020 18:26:40 +0000	[thread overview]
Message-ID: <9ea69e90694e53842acd68d3ac85c9a00c4bd343.1580236003.git.gitgitgadget@gmail.com> (raw)
In-Reply-To: <pull.513.v3.git.1580236003.gitgitgadget@gmail.com>

From: Derrick Stolee <dstolee@microsoft.com>

In cone mode, the sparse-checkout feature uses hashset containment
queries to match paths. Make this algorithm respect escaped asterisk
(*) and backslash (\) characters.

Create dup_and_filter_pattern() method to convert a pattern by
removing escape characters and dropping an optional "/*" at the end.
This method is available in dir.h as we will use it in
builtin/sparse-checkout.c in a later change.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 dir.c                              | 31 +++++++++++++++++++++++++++---
 t/t1091-sparse-checkout-builtin.sh | 22 +++++++++++++++++----
 2 files changed, 46 insertions(+), 7 deletions(-)

diff --git a/dir.c b/dir.c
index 7cb78c8b87..579f274d13 100644
--- a/dir.c
+++ b/dir.c
@@ -630,6 +630,32 @@ int pl_hashmap_cmp(const void *unused_cmp_data,
 	return strncmp(ee1->pattern, ee2->pattern, min_len);
 }
 
+static char *dup_and_filter_pattern(const char *pattern)
+{
+	char *set, *read;
+	char *result = xstrdup(pattern);
+
+	set = result;
+	read = result;
+
+	while (*read) {
+		/* skip escape characters (once) */
+		if (*read == '\\')
+			read++;
+
+		*set = *read;
+
+		set++;
+		read++;
+	}
+	*set = 0;
+
+	if (*(read - 2) == '/' && *(read - 1) == '*')
+		*(read - 2) = 0;
+
+	return result;
+}
+
 static void add_pattern_to_hashsets(struct pattern_list *pl, struct path_pattern *given)
 {
 	struct pattern_entry *translated;
@@ -695,8 +721,7 @@ static void add_pattern_to_hashsets(struct pattern_list *pl, struct path_pattern
 			goto clear_hashmaps;
 		}
 
-		truncated = xstrdup(given->pattern);
-		truncated[given->patternlen - 2] = 0;
+		truncated = dup_and_filter_pattern(given->pattern);
 
 		translated = xmalloc(sizeof(struct pattern_entry));
 		translated->pattern = truncated;
@@ -730,7 +755,7 @@ static void add_pattern_to_hashsets(struct pattern_list *pl, struct path_pattern
 
 	translated = xmalloc(sizeof(struct pattern_entry));
 
-	translated->pattern = xstrdup(given->pattern);
+	translated->pattern = dup_and_filter_pattern(given->pattern);
 	translated->patternlen = given->patternlen;
 	hashmap_entry_init(&translated->ent,
 			   ignore_case ?
diff --git a/t/t1091-sparse-checkout-builtin.sh b/t/t1091-sparse-checkout-builtin.sh
index 470900f6f4..0a21a5e15d 100755
--- a/t/t1091-sparse-checkout-builtin.sh
+++ b/t/t1091-sparse-checkout-builtin.sh
@@ -366,13 +366,27 @@ test_expect_success 'pattern-checks: starting "*"' '
 	check_read_tree_errors repo "a deep" "disabling cone pattern matching"
 '
 
-test_expect_success 'pattern-checks: escaped "*"' '
-	cat >repo/.git/info/sparse-checkout <<-\EOF &&
+test_expect_success BSLASHPSPEC 'pattern-checks: escaped "*"' '
+	git clone repo escaped &&
+	TREEOID=$(git -C escaped rev-parse HEAD:folder1) &&
+	NEWTREE=$(git -C escaped mktree <<-EOF
+	$(git -C escaped ls-tree HEAD)
+	040000 tree $TREEOID	zbad\\dir
+	040000 tree $TREEOID	zdoes*exist
+	EOF
+	) &&
+	COMMIT=$(git -C escaped commit-tree $NEWTREE -p HEAD) &&
+	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 &&
 	/*
 	!/*/
-	/does\*not\*exist/
+	/zbad\\dir/
+	/zdoes\*not\*exist/
+	/zdoes\*exist/
 	EOF
-	check_read_tree_errors repo "a" ""
+	check_read_tree_errors escaped "a zbad\\dir zdoes*exist"
 '
 
 test_done
-- 
gitgitgadget


  parent reply	other threads:[~2020-01-28 18:27 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 ` [PATCH 8/8] sparse-checkout: write escaped patterns in cone mode Derrick Stolee via GitGitGadget
2020-01-14 21:25   ` 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     ` Derrick Stolee via GitGitGadget [this message]
2020-01-29 10:03       ` [PATCH v3 09/12] sparse-checkout: properly match escaped characters 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=9ea69e90694e53842acd68d3ac85c9a00c4bd343.1580236003.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).