Docling/docling/backend/abstract_backend.py
Christoph Auer a8c6b29a67
feat: Upgrade docling-parse PDF backend and interface to use page-by-page parsing (#44)
* Use docling-parse page-by-page

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Propagate document_hash to PDF backends, use docling-parse 1.0.0

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Upgrade lockfile

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* repin after more packages on pypi

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
2024-08-22 13:49:37 +02:00

64 lines
1.4 KiB
Python

from abc import ABC, abstractmethod
from io import BytesIO
from pathlib import Path
from typing import Any, Iterable, Optional, Union
from PIL import Image
class PdfPageBackend(ABC):
def __init__(self, page_obj: Any) -> object:
pass
@abstractmethod
def get_text_in_rect(self, bbox: "BoundingBox") -> str:
pass
@abstractmethod
def get_text_cells(self) -> Iterable["Cell"]:
pass
@abstractmethod
def get_bitmap_rects(self, scale: int = 1) -> Iterable["BoundingBox"]:
pass
@abstractmethod
def get_page_image(
self, scale: int = 1, cropbox: Optional["BoundingBox"] = None
) -> Image.Image:
pass
@abstractmethod
def get_size(self) -> "PageSize":
pass
@abstractmethod
def unload(self):
pass
class PdfDocumentBackend(ABC):
@abstractmethod
def __init__(self, path_or_stream: Union[BytesIO, Path], document_hash: str):
self.path_or_stream = path_or_stream
self.document_hash = document_hash
@abstractmethod
def load_page(self, page_no: int) -> PdfPageBackend:
pass
@abstractmethod
def page_count(self) -> int:
pass
@abstractmethod
def is_valid(self) -> bool:
pass
@abstractmethod
def unload(self):
if isinstance(self.path_or_stream, BytesIO):
self.path_or_stream.close()
self.path_or_stream = None