attr.c: read attributes in a sparse directory

Before this patch, git check-attr was unable to read the attributes from
a .gitattributes file within a sparse directory. The original comment
was operating under the assumption that users are only interested in
files or directories inside the cones. Therefore, in the original code,
in the case of a cone-mode sparse-checkout, we didn't load the
.gitattributes file.

However, this behavior can lead to missing attributes for files inside
sparse directories, causing inconsistencies in file handling.

To resolve this, revise 'git check-attr' to allow attribute reading for
files in sparse directories from the corresponding .gitattributes files:

1.Utilize path_in_cone_mode_sparse_checkout() and index_name_pos_sparse
to check if a path falls within a sparse directory.

2.If path is inside a sparse directory, employ the value of
index_name_pos_sparse() to find the sparse directory containing path and
path relative to sparse directory. Proceed to read attributes from the
tree OID of the sparse directory using read_attr_from_blob().

3.If path is not inside a sparse directory，ensure that attributes are
fetched from the index blob with read_blob_data_from_index().

Change the test 'check-attr with pathspec outside sparse definition' to
'test_expect_success' to reflect that the attributes inside a sparse
directory can now be read. Ensure that the sparse index case works
correctly for git check-attr to illustrate the successful handling of
attributes within sparse directories.

Helped-by: Victoria Dye <vdye@github.com>
Signed-off-by: Shuqi Liang <cheskaqiqi@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/attr.c b/attr.c
index e5785c55dbcc9793d06725b23640c64659d33974..d85fd6d2edee4817acabaa1d71dd69563eb5e662 100644 (file)
--- a/attr.c
+++ b/attr.c
@@ -808,35 +808,56 @@ static struct attr_stack *read_attr_from_blob(struct index_state *istate,
 static struct attr_stack *read_attr_from_index(struct index_state *istate,
                                               const char *path, unsigned flags)
 {
+       struct attr_stack *stack = NULL;
        char *buf;
        unsigned long size;
+       int sparse_dir_pos = -1;
 
        if (!istate)
                return NULL;
 
        /*
-        * The .gitattributes file only applies to files within its
-        * parent directory. In the case of cone-mode sparse-checkout,
-        * the .gitattributes file is sparse if and only if all paths
-        * within that directory are also sparse. Thus, don't load the
-        * .gitattributes file since it will not matter.
-        *
-        * In the case of a sparse index, it is critical that we don't go
-        * looking for a .gitattributes file, as doing so would cause the
-        * index to expand.
+        * When handling sparse-checkouts, .gitattributes files
+        * may reside within a sparse directory. We distinguish
+        * whether a path exists directly in the index or not by
+        * evaluating if 'pos' is negative.
+        * If 'pos' is negative, the path is not directly present
+        * in the index and is likely within a sparse directory.
+        * For paths not in the index, The absolute value of 'pos'
+        * minus 1 gives us the position where the path would be
+        * inserted in lexicographic order within the index.
+        * We then subtract another 1 from this value
+        * (sparse_dir_pos = -pos - 2) to find the position of the
+        * last index entry which is lexicographically smaller than
+        * the path. This would be the sparse directory containing
+        * the path. By identifying the sparse directory containing
+        * the path, we can correctly read the attributes specified
+        * in the .gitattributes file from the tree object of the
+        * sparse directory.
         */
-       if (!path_in_cone_mode_sparse_checkout(path, istate))
-               return NULL;
+       if (!path_in_cone_mode_sparse_checkout(path, istate)) {
+               int pos = index_name_pos_sparse(istate, path, strlen(path));
 
-       buf = read_blob_data_from_index(istate, path, &size);
-       if (!buf)
-               return NULL;
-       if (size >= ATTR_MAX_FILE_SIZE) {
-               warning(_("ignoring overly large gitattributes blob '%s'"), path);
-               return NULL;
+               if (pos < 0)
+                       sparse_dir_pos = -pos - 2;
        }
 
-       return read_attr_from_buf(buf, path, flags);
+       if (sparse_dir_pos >= 0 &&
+           S_ISSPARSEDIR(istate->cache[sparse_dir_pos]->ce_mode) &&
+           !strncmp(istate->cache[sparse_dir_pos]->name, path, ce_namelen(istate->cache[sparse_dir_pos]))) {
+               const char *relative_path = path + ce_namelen(istate->cache[sparse_dir_pos]);
+               stack = read_attr_from_blob(istate, &istate->cache[sparse_dir_pos]->oid, relative_path, flags);
+       } else {
+               buf = read_blob_data_from_index(istate, path, &size);
+               if (!buf)
+                       return NULL;
+               if (size >= ATTR_MAX_FILE_SIZE) {
+                       warning(_("ignoring overly large gitattributes blob '%s'"), path);
+                       return NULL;
+               }
+               stack = read_attr_from_buf(buf, path, flags);
+       }
+       return stack;
 }
 
 static struct attr_stack *read_attr(struct index_state *istate,

diff --git a/t/t1092-sparse-checkout-compatibility.sh b/t/t1092-sparse-checkout-compatibility.sh
index 2d7fa65d8124882dce52e756f13d8fd17d5017f2..dc84b3e2e17fe289d029d26add6ece7f394274cf 100755 (executable)
--- a/t/t1092-sparse-checkout-compatibility.sh
+++ b/t/t1092-sparse-checkout-compatibility.sh
@@ -2271,7 +2271,7 @@ test_expect_success 'check-attr with pathspec inside sparse definition' '
        test_all_match git check-attr -a --cached -- deep/a
 '
 
-test_expect_failure 'check-attr with pathspec outside sparse definition' '
+test_expect_success 'check-attr with pathspec outside sparse definition' '
        init_repos &&
 
        echo "a -crlf myAttr" >>.gitattributes &&
@@ -2288,6 +2288,14 @@ test_expect_failure 'check-attr with pathspec outside sparse definition' '
        test_all_match git check-attr -a --cached -- folder1/a
 '
 
+# NEEDSWORK: The 'diff --check' test is left as 'test_expect_failure' due
+# to an underlying issue in oneway_diff() within diff-lib.c.
+# 'do_oneway_diff()' is not called as expected for paths that could match
+# inside of a sparse directory. Specifically, the 'ce_path_match()' function
+# fails to recognize files inside a sparse directory (e.g., when 'folder1/'
+# is a sparse directory, 'folder1/a' cannot be recognized). The goal is to
+# proceed with 'do_oneway_diff()' if the pathspec could match inside of a
+# sparse directory.
 test_expect_failure 'diff --check with pathspec outside sparse definition' '
        init_repos &&