fix: respect ignored files during source discovery

insight/utils.py

@@ -10,6 +10,8 @@
     ".ipynb"
 )
 
+SUPPORTED_FILENAMES = {"dockerfile", "makefile", "containerfile", "jenkinsfile"}
+
 # Default directories to ignore
 DEFAULT_IGNORED_DIRS = {"venv", "node_modules", "__pycache__", ".git", "dist", "build"}
 
@@ -37,16 +39,22 @@ def list_source_files(path):
     # Determine the base path to look for the ignore file
     base_path = path if os.path.isdir(path) else os.path.dirname(path)
     IGNORED_DIRS = get_ignored_dirs(base_path)
-
+
+    if os.path.basename(os.path.normpath(path)) in IGNORED_DIRS:
+        return
+
     if os.path.isfile(path):
-        yield path
+        if os.path.basename(path) not in IGNORED_DIRS:
+            yield path
         return
 
     for root, dirs, files in os.walk(path):
         # This line is key: it modifies the list of directories `os.walk` will visit
         dirs[:] = [d for d in dirs if d not in IGNORED_DIRS]
 
         for file in files:
+            if file in IGNORED_DIRS:
+                continue
             # Check for both extension and exact filename match (for Dockerfile, etc.)
-            if file.lower().endswith(SUPPORTED_EXTS) or file in IGNORED_DIRS:
-                 yield os.path.join(root, file)
+            if file.lower().endswith(SUPPORTED_EXTS) or file.lower() in SUPPORTED_FILENAMES:
+                yield os.path.join(root, file)

tests/test_utils.py

@@ -0,0 +1,45 @@
+from pathlib import Path
+
+from insight.utils import list_source_files
+
+
+def _relative_sources(root: Path) -> set[str]:
+    return {
+        Path(path).relative_to(root).as_posix() for path in list_source_files(str(root))
+    }
+
+
+def test_list_source_files_respects_ignored_files_and_supports_extensionless_names(
+    tmp_path: Path,
+) -> None:
+    (tmp_path / ".insightignore").write_text(".env\nignored.log\n", encoding="utf-8")
+    (tmp_path / ".env").write_text("API_SECRET=do-not-send\n", encoding="utf-8")
+    (tmp_path / "ignored.log").write_text("not source\n", encoding="utf-8")
+    (tmp_path / "main.py").write_text("print('safe')\n", encoding="utf-8")
+    for filename in ("Dockerfile", "Makefile", "Containerfile", "Jenkinsfile"):
+        (tmp_path / filename).write_text("source\n", encoding="utf-8")
+
+    ignored_directory = tmp_path / "venv"
+    ignored_directory.mkdir()
+    (ignored_directory / "secret.py").write_text("secret = True\n", encoding="utf-8")
+
+    sources = _relative_sources(tmp_path)
+
+    assert ".env" not in sources
+    assert "ignored.log" not in sources
+    assert "venv/secret.py" not in sources
+    assert {
+        "main.py",
+        "Dockerfile",
+        "Makefile",
+        "Containerfile",
+        "Jenkinsfile",
+    } <= sources
+
+
+def test_explicitly_ignored_file_is_not_returned(tmp_path: Path) -> None:
+    (tmp_path / ".insightignore").write_text(".env\n", encoding="utf-8")
+    ignored_file = tmp_path / ".env"
+    ignored_file.write_text("API_SECRET=do-not-send\n", encoding="utf-8")
+
+    assert list(list_source_files(str(ignored_file))) == []