fix pathlib exception handling with symlinks (#4161)

Fixes #4077

Author: dankrzeminski32

CHANGES.md

@@ -29,6 +29,8 @@
 
 <!-- Changes to how Black can be configured -->
 
+- Fix symlink handling, properly catch and ignore symlinks that point outside of root
+  (#4161)
 - Fix cache mtime logic that resulted in false positive cache hits (#4128)
 
 ### Packaging

src/black/__init__.py

@@ -49,6 +49,7 @@
     find_user_pyproject_toml,
     gen_python_files,
     get_gitignore,
+    get_root_relative_path,
     normalize_path_maybe_ignore,
     parse_pyproject_toml,
     path_is_excluded,
@@ -700,7 +701,10 @@ def get_sources(
 
         # Compare the logic here to the logic in `gen_python_files`.
         if is_stdin or path.is_file():
-            root_relative_path = path.absolute().relative_to(root).as_posix()
+            root_relative_path = get_root_relative_path(path, root, report)
+
+            if root_relative_path is None:
+                continue
 
             root_relative_path = "/" + root_relative_path
 

src/black/files.py

@@ -259,14 +259,7 @@ def normalize_path_maybe_ignore(
     try:
         abspath = path if path.is_absolute() else Path.cwd() / path
         normalized_path = abspath.resolve()
-        try:
-            root_relative_path = normalized_path.relative_to(root).as_posix()
-        except ValueError:
-            if report:
-                report.path_ignored(
-                    path, f"is a symbolic link that points outside {root}"
-                )
-            return None
+        root_relative_path = get_root_relative_path(normalized_path, root, report)
 
     except OSError as e:
         if report:
@@ -276,6 +269,21 @@ def normalize_path_maybe_ignore(
     return root_relative_path
 
 
+def get_root_relative_path(
+    path: Path,
+    root: Path,
+    report: Optional[Report] = None,
+) -> Optional[str]:
+    """Returns the file path relative to the 'root' directory"""
+    try:
+        root_relative_path = path.absolute().relative_to(root).as_posix()
+    except ValueError:
+        if report:
+            report.path_ignored(path, f"is a symbolic link that points outside {root}")
+        return None
+    return root_relative_path
+
+
 def _path_is_ignored(
     root_relative_path: str,
     root: Path,

tests/test_black.py

@@ -2592,6 +2592,20 @@ def test_symlinks(self) -> None:
         outside_root_symlink.resolve.assert_called_once()
         ignored_symlink.resolve.assert_not_called()
 
+    def test_get_sources_with_stdin_symlink_outside_root(
+        self,
+    ) -> None:
+        path = THIS_DIR / "data" / "include_exclude_tests"
+        stdin_filename = str(path / "b/exclude/a.py")
+        outside_root_symlink = Path("/target_directory/a.py")
+        with patch("pathlib.Path.resolve", return_value=outside_root_symlink):
+            assert_collected_sources(
+                root=Path("target_directory/"),
+                src=["-"],
+                expected=[],
+                stdin_filename=stdin_filename,
+            )
+
     @patch("black.find_project_root", lambda *args: (THIS_DIR.resolve(), None))
     def test_get_sources_with_stdin(self) -> None:
         src = ["-"]