mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-10-31 20:15:44 +00:00
Trenton H
6f99ad9469
* Chore: Import dateparser lazily so processes that never parse dates skip it * Chore: Import turbohtml lazily in the mail parser * Chore: Import lxml lazily in the SVG validator * Chore: Import paperless_ai.indexing lazily in document tasks * Chore: Import paperless_ai helpers lazily in views * Chore: Read the OCRmyPDF sRGB profile on first use instead of at import * Chore: Import pikepdf and img2pdf lazily so startup does not load them * Chore: Reuse the initialized Django ASGI application for HTTP routing
121 lines
3.3 KiB
Python
121 lines
3.3 KiB
Python
import datetime
|
|
import logging
|
|
from abc import ABC
|
|
from abc import abstractmethod
|
|
from collections.abc import Iterator
|
|
from dataclasses import dataclass
|
|
from types import TracebackType
|
|
from typing import Self
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
@dataclass(frozen=True, slots=True)
|
|
class DateParserConfig:
|
|
"""
|
|
Configuration for a DateParser instance.
|
|
|
|
This object is created by the factory and passed to the
|
|
parser's constructor, decoupling the parser from settings.
|
|
"""
|
|
|
|
languages: list[str]
|
|
timezone_str: str
|
|
ignore_dates: set[datetime.date]
|
|
|
|
# A "now" timestamp for filtering future dates.
|
|
# Passed in by the factory.
|
|
reference_time: datetime.datetime
|
|
|
|
# Settings for the default RegexDateParser
|
|
# Other plugins should use or consider these, but it is not required
|
|
filename_date_order: str | None
|
|
content_date_order: str
|
|
|
|
|
|
class DateParserPluginBase(ABC):
|
|
"""
|
|
Abstract base class for date parsing strategies.
|
|
|
|
Instances are configured via a DateParserConfig object.
|
|
"""
|
|
|
|
def __init__(self, config: DateParserConfig):
|
|
"""
|
|
Initializes the parser with its configuration.
|
|
"""
|
|
self.config = config
|
|
|
|
def __enter__(self) -> Self:
|
|
"""
|
|
Enter the runtime context related to this object.
|
|
|
|
Subclasses can override this to acquire resources (connections, handles).
|
|
"""
|
|
return self
|
|
|
|
def __exit__(
|
|
self,
|
|
exc_type: type[BaseException] | None,
|
|
exc_val: BaseException | None,
|
|
exc_tb: TracebackType | None,
|
|
) -> None:
|
|
"""
|
|
Exit the runtime context related to this object.
|
|
|
|
Subclasses can override this to release resources.
|
|
"""
|
|
# Default implementation does nothing.
|
|
# Returning None implies exceptions are propagated.
|
|
|
|
def _parse_string(
|
|
self,
|
|
date_string: str,
|
|
date_order: str,
|
|
) -> datetime.datetime | None:
|
|
"""
|
|
Helper method to parse a single date string using dateparser.
|
|
|
|
Uses configuration from `self.config`.
|
|
"""
|
|
import dateparser
|
|
|
|
try:
|
|
return dateparser.parse(
|
|
date_string,
|
|
settings={
|
|
"DATE_ORDER": date_order,
|
|
"PREFER_DAY_OF_MONTH": "first",
|
|
"RETURN_AS_TIMEZONE_AWARE": True,
|
|
"TIMEZONE": self.config.timezone_str,
|
|
},
|
|
locales=self.config.languages,
|
|
)
|
|
except Exception as e:
|
|
logger.exception(f"Error while parsing date string '{date_string}': {e}")
|
|
return None
|
|
|
|
def _filter_date(
|
|
self,
|
|
date: datetime.datetime | None,
|
|
) -> datetime.datetime | None:
|
|
"""
|
|
Helper method to validate a parsed datetime object.
|
|
|
|
Uses configuration from `self.config`.
|
|
"""
|
|
if (
|
|
date is not None
|
|
and date.year > 1900
|
|
and date <= self.config.reference_time
|
|
and date.date() not in self.config.ignore_dates
|
|
):
|
|
return date
|
|
return None
|
|
|
|
@abstractmethod
|
|
def parse(self, filename: str, content: str) -> Iterator[datetime.datetime]:
|
|
"""
|
|
Parses a document's filename and content, yielding valid datetime objects.
|
|
"""
|