feat: fix file filters in folder hashing

Author: matiasdaloia

src/scanoss/file_filters.py

@@ -525,39 +525,3 @@ def _should_skip_file(self, file_rel_path: str) -> bool:  # noqa: PLR0911
             self.print_debug(f'Skipping file: {file_rel_path} (matches custom pattern)')
             return True
         return False
-
-    def _should_skip_file_for_hfh(self, file_path: Path) -> bool:
-        """
-        Check if a file should be skipped during folder hashing scan.
-
-        Args:
-            file_path (Path): The path to the file to check.
-
-        Returns:
-            bool: True if the file should be skipped, False otherwise.
-        """
-        try:
-            if (
-                any(part.startswith('.') for part in file_path.parts)  # Hidden files/folders
-                or file_path.is_symlink()  # Symlinks
-                or file_path.stat().st_size == 0  # Empty files
-            ):
-                self.print_debug(f'Skipping file: {file_path} (hidden/symlink/empty)')
-                return True
-
-            # Files ending with null
-            if file_path.suffix.lower() == '.txt':
-                try:
-                    with open(file_path, 'rb') as f:
-                        if f.read().endswith(b'\x00'):
-                            self.print_debug(f'Skipping file: {file_path} (text file ending with null)')
-                            return True
-                except (OSError, IOError):
-                    self.print_debug(f'Skipping file: {file_path} (cannot read file content)')
-                    return True
-
-            return False
-
-        except Exception as e:
-            self.print_debug(f'Error checking file {file_path}: {str(e)}')
-            return True

src/scanoss/scanners/folder_hasher.py

@@ -138,18 +138,19 @@ def _build_root_node(self, path: str) -> DirectoryNode:
         root = Path(path).resolve()
         root_node = DirectoryNode(str(root))
 
-        all_files = [
-            f for f in root.rglob('*') if f.is_file() and len(f.name.encode('utf-8')) < MINIMUM_FILE_NAME_LENGTH
+        filtered_files = [
+            f
+            for f in self.file_filters.get_filtered_files_from_folder(str(root))
+            if len(f.encode('utf-8')) < MINIMUM_FILE_NAME_LENGTH
         ]
-        filtered_files = self.file_filters.get_filtered_files_from_files(all_files, str(root))
 
         # Sort the files by name to ensure the hash is the same for the same folder
         filtered_files.sort()
 
         bar = Bar('Hashing files...', max=len(filtered_files))
         for file_path in filtered_files:
             try:
-                file_path_obj = Path(file_path) if isinstance(file_path, str) else file_path
+                file_path_obj = Path(file_path)
                 full_file_path = file_path_obj if file_path_obj.is_absolute() else root / file_path_obj
 
                 self.base.print_debug(f'\nHashing file {str(full_file_path)}')