[PATCH v4 14/17] sparse-checkout: sanitize for nested folders

[Derrick Stolee via GitGitGadget]

From: Derrick Stolee <dsto...@microsoft.com>

If a user provides folders A/ and A/B/ for inclusion in a cone-mode
sparse-checkout file, the parsing logic will notice that A/ appears
both as a "parent" type pattern and as a "recursive" type pattern.
This is unexpected and hence will complain via a warning and revert
to the old logic for checking sparse-checkout patterns.

Prevent this from happening accidentally by sanitizing the folders
for this type of inclusion in the 'git sparse-checkout' builtin.
This happens in two ways:

1. Do not include any parent patterns that also appear as recursive
   patterns.

2. Do not include any recursive patterns deeper than other recursive
   patterns.

In order to minimize duplicate code for scanning parents, create
hashmap_contains_parent() method. It takes a strbuf buffer to
avoid reallocating a buffer when calling in a tight loop.

Helped-by: Eric Wong <e...@80x24.org>
Helped-by: Johannes Schindelin <johannes.schinde...@gmx.de>
Signed-off-by: Derrick Stolee <dsto...@microsoft.com>
---
 builtin/sparse-checkout.c          | 22 ++++++++++++++++++----
 t/t1091-sparse-checkout-builtin.sh | 11 +++++++++++
 2 files changed, 29 insertions(+), 4 deletions(-)

diff --git a/builtin/sparse-checkout.c b/builtin/sparse-checkout.c
index 95d9a90b84..40b6c599dc 100644
--- a/builtin/sparse-checkout.c
+++ b/builtin/sparse-checkout.c
@@ -212,9 +212,17 @@ static void write_cone_to_file(FILE *fp, struct 
pattern_list *pl)
        struct pattern_entry *pe;
        struct hashmap_iter iter;
        struct string_list sl = STRING_LIST_INIT_DUP;
+       struct strbuf parent_pattern = STRBUF_INIT;
 
-       hashmap_for_each_entry(&pl->parent_hashmap, &iter, pe, ent)
-               string_list_insert(&sl, pe->pattern);
+       hashmap_for_each_entry(&pl->parent_hashmap, &iter, pe, ent) {
+               if (hashmap_get_entry(&pl->recursive_hashmap, pe, ent, NULL))
+                       continue;
+
+               if (!hashmap_contains_parent(&pl->recursive_hashmap,
+                                            pe->pattern,
+                                            &parent_pattern))
+                       string_list_insert(&sl, pe->pattern);
+       }
 
        string_list_sort(&sl);
        string_list_remove_duplicates(&sl, 0);
@@ -230,8 +238,14 @@ static void write_cone_to_file(FILE *fp, struct 
pattern_list *pl)
 
        string_list_clear(&sl, 0);
 
-       hashmap_for_each_entry(&pl->recursive_hashmap, &iter, pe, ent)
-               string_list_insert(&sl, pe->pattern);
+       hashmap_for_each_entry(&pl->recursive_hashmap, &iter, pe, ent) {
+               if (!hashmap_contains_parent(&pl->recursive_hashmap,
+                                            pe->pattern,
+                                            &parent_pattern))
+                       string_list_insert(&sl, pe->pattern);
+       }
+
+       strbuf_release(&parent_pattern);
 
        string_list_sort(&sl);
        string_list_remove_duplicates(&sl, 0);
diff --git a/t/t1091-sparse-checkout-builtin.sh 
b/t/t1091-sparse-checkout-builtin.sh
index 3a4c0e6f5d..e752f3ba0f 100755
--- a/t/t1091-sparse-checkout-builtin.sh
+++ b/t/t1091-sparse-checkout-builtin.sh
@@ -236,4 +236,15 @@ test_expect_success 'cone mode: init and set' '
        test_cmp expect dir
 '
 
+test_expect_success 'cone mode: set with nested folders' '
+       git -C repo sparse-checkout set deep deep/deeper1/deepest 2>err &&
+       test_line_count = 0 err &&
+       cat >expect <<-EOF &&
+               /*
+               !/*/
+               /deep/
+       EOF
+       test_cmp repo/.git/info/sparse-checkout expect
+'
+
 test_done
-- 
gitgitgadget