fix(learn): decode directory names with spaces in Windows project paths (headroomlabs-ai#997) (headroomlabs-ai#1027)

RTCartist · web-flow · commit 2d3701b59e9f · 2026-06-15T23:29:53.000-05:00
## Description `headroom learn --apply` crashes with `FileNotFoundError` when the project lives in a Windows directory whose name contains spaces (e.g. `C:\Users\user\Desktop\Claude Code Projects`). Claude Code encodes that path as `-C-Users-user-Desktop-Claude-Code-Projects`, using `-` for both path separators *and* spaces. The greedy path decoder walks the real filesystem to reconstruct the original components, but `_component_tokenizations()` never tried splitting on spaces — so it couldn't match `Claude Code Projects` against tokens `["Claude", "Code", "Projects"]`. Closes headroomlabs-ai#997 ## Type of Change - [x] Bug fix (non-breaking change that fixes an issue) ## Changes Made - Added `" "` (space) to the explicit separator list in `_component_tokenizations()` - Updated the catch-all regex from `[-._]` to `[-.\s_]` so the combined split also covers whitespace - Same change in the hidden-component (dotfile) branch ## Testing - [x] Unit tests pass (`pytest`) - [x] Linting passes (`ruff check .`) - [x] New tests added for new functionality ### Test Output ```text tests/test_learn/test_scanner.py::TestGreedyPathDecode::test_single_space_in_dirname PASSED tests/test_learn/test_scanner.py::TestGreedyPathDecode::test_multiple_spaces_in_dirname PASSED tests/test_learn/test_scanner.py::TestGreedyPathDecode::test_space_nested_path PASSED tests/test_learn/test_scanner.py::TestDecodeProjectPath::test_windows_path_with_spaces_decoded_via_greedy PASSED 4 passed in 0.64s ``` ## Real Behavior Proof - Environment: Windows 11 Home 10.0.26200, Python 3.10.18 - Exact command / steps: Ran `python -m pytest tests/test_learn/test_scanner.py -v` on Windows after applying the fix. Also verified `_component_tokenizations("Claude Code Projects")` returns `[['Claude Code Projects'], ['Claude', 'Code', 'Projects']]`. The integration test creates a real temp directory with spaces and asserts `_decode_project_path()` resolves it correctly. - Observed result: All 4 new tests pass on Windows. All 34 scanner tests pass. Ruff check clean. - Not tested: No manual `headroom learn --apply` end-to-end run, but the integration test exercises the same `_decode_project_path` code path with a real temp directory on disk. ## Review Readiness - [x] I have performed a self-review - [x] This PR is ready for human review ## Checklist - [x] My code follows the project's style guidelines - [x] I have performed a self-review of my code - [x] My changes generate no new warnings - [x] I have added tests that prove my fix is effective or that my feature works - [x] New and existing unit tests pass locally with my changes ## Additional Notes The fix follows the exact same pattern used for underscores (issue headroomlabs-ai#159) and dots (issue headroomlabs-ai#47) — extending the separator list. Spaces are the last common character that Claude Code flattens to `-` but the decoder didn't know about.
diff --git a/headroom/learn/plugins/claude.py b/headroom/learn/plugins/claude.py
@@ -397,19 +397,19 @@ def add(tokens: list[str]) -> None:
 
     add([component])
 
-    for separator in ("-", ".", "_", None):
+    for separator in (" ", "-", ".", "_", None):
         if separator is None:
-            tokens = [token for token in re.split(r"[-._]", component) if token]
+            tokens = [token for token in re.split(r"[-.\s_]", component) if token]
         else:
             tokens = [token for token in component.split(separator) if token]
         add(tokens)
 
     if component.startswith(".") and len(component) > 1:
         hidden_component = component[1:]
         add(["", hidden_component])
-        for separator in ("-", ".", "_", None):
+        for separator in (" ", "-", ".", "_", None):
             if separator is None:
-                tokens = [token for token in re.split(r"[-._]", hidden_component) if token]
+                tokens = [token for token in re.split(r"[-.\s_]", hidden_component) if token]
             else:
                 tokens = [token for token in hidden_component.split(separator) if token]
             add(["", *tokens])
diff --git a/tests/test_learn/test_scanner.py b/tests/test_learn/test_scanner.py
@@ -104,6 +104,26 @@ def test_hybrid_hyphen_and_dot_flattening(self, tmp_path: Path) -> None:
         result = _greedy_path_decode(tmp_path, ["my", "cool", "project", "nosync", "headroom"])
         assert result == tmp_path / "my-cool-project.nosync" / "headroom"
 
+    # ---- Space tests (issue #997) ----
+
+    def test_single_space_in_dirname(self, tmp_path: Path) -> None:
+        """Directory name contains a space (e.g. 'Claude Projects')."""
+        _make_dirs(tmp_path, "Claude Projects")
+        result = _greedy_path_decode(tmp_path, ["Claude", "Projects"])
+        assert result == tmp_path / "Claude Projects"
+
+    def test_multiple_spaces_in_dirname(self, tmp_path: Path) -> None:
+        """Directory name contains multiple spaces (e.g. 'Claude Code Projects')."""
+        _make_dirs(tmp_path, "Claude Code Projects")
+        result = _greedy_path_decode(tmp_path, ["Claude", "Code", "Projects"])
+        assert result == tmp_path / "Claude Code Projects"
+
+    def test_space_nested_path(self, tmp_path: Path) -> None:
+        """Nested path like Desktop/'Claude Code Projects' should decode correctly."""
+        _make_dirs(tmp_path, "Desktop/Claude Code Projects")
+        result = _greedy_path_decode(tmp_path, ["Desktop", "Claude", "Code", "Projects"])
+        assert result == tmp_path / "Desktop" / "Claude Code Projects"
+
     # ---- Underscore tests (issue #159) ----
 
     def test_single_underscore_in_dirname(self, tmp_path: Path) -> None:
@@ -332,6 +352,32 @@ def test_windows_username_with_dot_stays_single_component(self) -> None:
         assert "john\\doe" not in rendered
         assert "john/doe" not in rendered
 
+    def test_windows_path_with_spaces_decoded_via_greedy(self) -> None:
+        """Spaces in Windows dir names must not split into separate components (#997).
+
+        Claude Code encodes 'C:\\Users\\user\\Desktop\\Claude Code Projects' as
+        '-C-Users-user-Desktop-Claude-Code-Projects'. The greedy decoder must
+        reconstruct 'Claude Code Projects' as a single directory.
+        """
+        import sys
+        import tempfile
+
+        if sys.platform != "win32":
+            pytest.skip("greedy Windows-path decode requires real Windows filesystem")
+
+        with tempfile.TemporaryDirectory() as td:
+            space_dir = Path(td) / "Claude Code Projects"
+            space_dir.mkdir()
+
+            drive = Path(td).drive[0]
+            rest = str(Path(td))[3:]  # strip 'C:\\'
+            rest_parts = rest.replace("\\", "-").replace(" ", "-")
+            encoded = f"-{drive}-{rest_parts}-Claude-Code-Projects"
+
+            result = _decode_project_path(encoded)
+            assert result is not None
+            assert result == space_dir
+
     def test_discover_windows_project_uses_leaf_name(self, tmp_path: Path) -> None:
         """A syntactic Windows path decoded on Unix should still display the project leaf."""
         claude_dir = tmp_path / ".claude"
