Fix case-sensitive file suffix filtering silently skipping capitalized/mixed-case extensions (#1671)

graphify/extract.py

@@ -15844,7 +15844,7 @@ def _is_cpp_header(path: Path) -> bool:
 
 def _get_extractor(path: Path) -> Any | None:
     """Return the correct extractor function for a file, or None if unsupported."""
-    if path.name.endswith(".blade.php"):
+    if path.name.lower().endswith(".blade.php"):
         return extract_blade
     # MCP config files (.mcp.json, claude_desktop_config.json, ...) are routed
     # by filename before generic .json dispatch so they get MCP-aware nodes
@@ -15860,14 +15860,17 @@ def _get_extractor(path: Path) -> Any | None:
     # (the suffix map sends `.h` to extract_c, which can't read @interface etc.).
     # ObjC sniffing has priority over the C++ sniff: an Objective-C++ header can
     # contain both `@interface` and inline C++ (`::`), and it must parse as ObjC.
-    if path.suffix == ".h":
+    suffix = path.suffix
+    if suffix not in _DISPATCH and suffix.lower() in _DISPATCH:
+        suffix = suffix.lower()
+    if suffix == ".h":
         if _is_objc_header(path):
             return extract_objc
         # A C++ class header routed to extract_c loses the class entirely (the C
         # grammar has no class_specifier). Reroute to extract_cpp (#1547).
         if _is_cpp_header(path):
             return extract_cpp
-    return _DISPATCH.get(path.suffix)
+    return _DISPATCH.get(suffix)
 
 
 def _safe_extract_with_xaml_root(extractor, path: Path, root: Path) -> dict:
@@ -16646,7 +16649,8 @@ def collect_files(target: Path, *, follow_symlinks: bool = False, root: Path | N
             ]
             for fname in filenames:
                 p = dp / fname
-                if p.suffix in _EXTENSIONS and not _ignored(p) and _resolves_under_root(p, containment_root):
+                suffix = p.suffix
+                if (suffix in _EXTENSIONS or suffix.lower() in _EXTENSIONS) and not _ignored(p) and _resolves_under_root(p, containment_root):
                     results.append(p)
         return sorted(results)
     # Walk with symlink following + cycle detection
@@ -16666,7 +16670,8 @@ def collect_files(target: Path, *, follow_symlinks: bool = False, root: Path | N
         ]
         for fname in filenames:
             p = dp / fname
-            if p.suffix in _EXTENSIONS and not _ignored(p) and _resolves_under_root(p, containment_root):
+            suffix = p.suffix
+            if (suffix in _EXTENSIONS or suffix.lower() in _EXTENSIONS) and not _ignored(p) and _resolves_under_root(p, containment_root):
                 results.append(p)
     return sorted(results)
 

tests/test_extract.py

@@ -408,7 +408,8 @@ def _legacy_collect_files(target, *, root=None):
     for ext in sorted(extensions):
         results.extend(
             p for p in target.rglob(f"*{ext}")
-            if not any(_is_noise_dir(part) for part in p.parts)
+            if p.suffix == ext
+            and not any(_is_noise_dir(part) for part in p.parts)
             and not (patterns and _is_ignored(p, ignore_root, patterns))
         )
     return sorted(results)
@@ -1693,3 +1694,28 @@ def test_non_colliding_path_id_is_not_salted(tmp_path):
     result = extract([p], cache_root=tmp_path)
     file_id = next(n["id"] for n in result["nodes"] if n.get("source_location") == "L1")
     assert file_id == make_id(_file_stem(Path("src/auth/session.py"))) == "src_auth_session"
+
+
+def test_case_insensitive_suffix_filtering(tmp_path):
+    py_file = tmp_path / "app.PY"
+    js_file = tmp_path / "script.JS"
+    ts_file = tmp_path / "lib.Ts"
+    
+    py_file.write_text("class MyPythonClass:\n    pass\n")
+    js_file.write_text("function myJSFunction() {}\n")
+    ts_file.write_text("export class MyTSClass {}\n")
+    
+    collected = collect_files(tmp_path)
+    collected_names = {f.name for f in collected}
+    assert "app.PY" in collected_names
+    assert "script.JS" in collected_names
+    assert "lib.Ts" in collected_names
+
+    result = extract(collected, cache_root=tmp_path)
+    nodes = result["nodes"]
+    labels = {n.get("label") for n in nodes if "label" in n}
+    
+    assert "MyPythonClass" in labels
+    assert "myJSFunction()" in labels
+    assert "MyTSClass" in labels
+