From 02d2da6731292c2cb995fb3aa475404a6167c295 Mon Sep 17 00:00:00 2001 From: Trenton H <797416+stumpylog@users.noreply.github.com> Date: Mon, 16 Nov 2026 07:37:07 -0800 Subject: [PATCH] Chore: remove legacy DocumentParser base class Parsers are resolved through the parser registry and ParserProtocol now, and nothing referenced this class. Its now unused imports are removed too. --- src/documents/parsers.py | 82 ---------------------------------------- 1 file changed, 82 deletions(-) diff --git a/src/documents/parsers.py b/src/documents/parsers.py index d5aa48fca3..58ffd0c939 100644 --- a/src/documents/parsers.py +++ b/src/documents/parsers.py @@ -4,21 +4,13 @@ import logging import mimetypes import shutil import subprocess -import tempfile from pathlib import Path -from typing import TYPE_CHECKING from typing import Final -from django.conf import settings - -from documents.loggers import LoggingMixin from documents.utils import copy_file_with_basic_stats from documents.utils import run_subprocess from paperless.parsers.registry import get_parser_registry -if TYPE_CHECKING: - import datetime - logger = logging.getLogger("paperless.parsing") @@ -265,77 +257,3 @@ def make_thumbnail_from_pdf(in_path: Path, temp_dir: Path, logging_group=None) - class ParseError(Exception): pass - - -class DocumentParser(LoggingMixin): - """ - Subclass this to make your own parser. Have a look at - `paperless_tesseract.parsers` for inspiration. - """ - - logging_name = "paperless.parsing" - - def __init__(self, logging_group, progress_callback=None) -> None: - super().__init__() - self.renew_logging_group() - self.logging_group = logging_group - self.settings = self.get_settings() - settings.SCRATCH_DIR.mkdir(parents=True, exist_ok=True) - self.tempdir = Path( - tempfile.mkdtemp(prefix="paperless-", dir=settings.SCRATCH_DIR), - ) - - self.archive_path = None - self.text = None - self.date: datetime.datetime | None = None - self.progress_callback = progress_callback - - def progress(self, current_progress, max_progress) -> None: - if self.progress_callback: - self.progress_callback(current_progress, max_progress) - - def get_settings(self): # pragma: no cover - """ - A parser must implement this - """ - raise NotImplementedError - - def read_file_handle_unicode_errors(self, filepath: Path) -> str: - """ - Helper utility for reading from a file, and handling a problem with its - unicode, falling back to ignoring the error to remove the invalid bytes - """ - try: - text = filepath.read_text(encoding="utf-8") - except UnicodeDecodeError as e: - self.log.warning(f"Unicode error during text reading, continuing: {e}") - text = filepath.read_bytes().decode("utf-8", errors="replace") - return text - - def extract_metadata(self, document_path, mime_type): - return [] - - def get_page_count(self, document_path, mime_type) -> None: - return None - - def parse(self, document_path, mime_type, file_name=None): - raise NotImplementedError - - def get_archive_path(self): - return self.archive_path - - def get_thumbnail(self, document_path, mime_type, file_name=None): - """ - Returns the path to a file we can use as a thumbnail for this document. - """ - raise NotImplementedError - - def get_text(self): - return self.text - - def get_date(self) -> datetime.datetime | None: - return self.date - - def cleanup(self) -> None: - self.log.debug(f"Deleting directory {self.tempdir}") - shutil.rmtree(self.tempdir)