44 lines
1.3 KiB
Python
44 lines
1.3 KiB
Python
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
from typing import Iterable
|
|
|
|
|
|
def _is_relative_to(path: Path, other: Path) -> bool:
|
|
try:
|
|
path.relative_to(other)
|
|
return True
|
|
except ValueError:
|
|
return False
|
|
|
|
|
|
def list_supported_documents(root_dir: Path, supported_extensions: Iterable[str]) -> list[Path]:
|
|
"""List supported input documents while ignoring the GUI output subtree."""
|
|
normalized_exts = {ext.lower() for ext in supported_extensions}
|
|
output_dir = root_dir / "anonymise"
|
|
documents: list[Path] = []
|
|
|
|
for path in root_dir.rglob("*"):
|
|
if not path.is_file():
|
|
continue
|
|
if _is_relative_to(path, output_dir):
|
|
continue
|
|
if path.suffix.lower() not in normalized_exts:
|
|
continue
|
|
documents.append(path)
|
|
|
|
return sorted(documents)
|
|
|
|
|
|
def build_batch_output_dir(root_dir: Path, output_root: Path, source_path: Path) -> Path:
|
|
"""Preserve the source parent path under the batch output directory."""
|
|
relative_parent = source_path.relative_to(root_dir).parent
|
|
if relative_parent == Path("."):
|
|
return output_root
|
|
return output_root / relative_parent
|
|
|
|
|
|
def iter_pseudonymized_texts(output_dir: Path):
|
|
"""Yield anonymized text outputs recursively for post-run checks."""
|
|
return output_dir.rglob("*.pseudonymise.txt")
|