[PATCH v3 10/12] sparse-checkout: write escaped patterns in cone mode

["Derrick Stolee via GitGitGadget" <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.

Use unquote_c_style() when parsing lines from stdin. Command-line
arguments will be parsed as-is, assuming the user can do the correct
level of escaping from their environment to match the exact directory
names.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 builtin/sparse-checkout.c          | 38 +++++++++++++++++++++++++++---
 t/t1091-sparse-checkout-builtin.sh | 21 +++++++++++++++--
 2 files changed, 54 insertions(+), 5 deletions(-)

diff --git a/builtin/sparse-checkout.c b/builtin/sparse-checkout.c
index 3cee8ab46e..61414fef18 100644
--- a/builtin/sparse-checkout.c
+++ b/builtin/sparse-checkout.c
@@ -13,6 +13,7 @@
 #include "resolve-undo.h"
 #include "unpack-trees.h"
 #include "wt-status.h"
+#include "quote.h"
 
 static const char *empty_base = "";
 
@@ -140,6 +141,22 @@ 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 +181,11 @@ 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 +203,9 @@ 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);
 	}
 }
 
@@ -423,8 +442,21 @@ static int sparse_checkout_set(int argc, const char **argv, const char *prefix)
 		pl.use_cone_patterns = 1;
 
 		if (set_opts.use_stdin) {
-			while (!strbuf_getline(&line, stdin))
+			struct strbuf unquoted = STRBUF_INIT;
+			while (!strbuf_getline(&line, stdin)) {
+				if (line.buf[0] == '"') {
+					strbuf_setlen(&unquoted, 0);
+					if (unquote_c_style(&unquoted, line.buf, NULL))
+						die(_("unable to unquote C-style string '%s'"),
+						line.buf);
+
+					strbuf_swap(&unquoted, &line);
+				}
+
 				strbuf_to_cone_pattern(&line, &pl);
+			}
+
+			strbuf_release(&unquoted);
 		} else {
 			for (i = 0; i < argc; i++) {
 				strbuf_setlen(&line, 0);
diff --git a/t/t1091-sparse-checkout-builtin.sh b/t/t1091-sparse-checkout-builtin.sh
index 0a21a5e15d..459715d541 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