feat!: Docling v2 (#117)

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Maxim Lysak <mly@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
Co-authored-by: Maxim Lysak <mly@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
This commit is contained in:
Christoph Auer
2024-10-16 21:02:03 +02:00
committed by GitHub
parent d504432c1e
commit 7d3be0edeb
144 changed files with 15180 additions and 3828 deletions

View File

@@ -1,68 +1,63 @@
from abc import ABC, abstractmethod
from io import BytesIO
from pathlib import Path
from typing import TYPE_CHECKING, Any, Iterable, Optional, Union
from typing import TYPE_CHECKING, Set, Union
from PIL import Image
from docling_core.types.doc import DoclingDocument
if TYPE_CHECKING:
from docling.datamodel.base_models import BoundingBox, Cell, PageSize
from docling.datamodel.base_models import InputFormat
from docling.datamodel.document import InputDocument
class PdfPageBackend(ABC):
class AbstractDocumentBackend(ABC):
@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, float: int = 1) -> Iterable["BoundingBox"]:
pass
@abstractmethod
def get_page_image(
self, scale: float = 1, cropbox: Optional["BoundingBox"] = None
) -> Image.Image:
pass
@abstractmethod
def get_size(self) -> "PageSize":
pass
@abstractmethod
def is_valid(self) -> bool:
pass
@abstractmethod
def unload(self):
pass
class PdfDocumentBackend(ABC):
@abstractmethod
def __init__(self, path_or_stream: Union[BytesIO, Path], document_hash: str):
def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
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
self.document_hash = in_doc.document_hash
self.input_format = in_doc.format
@abstractmethod
def is_valid(self) -> bool:
pass
@classmethod
@abstractmethod
def supports_pagination(cls) -> bool:
pass
@abstractmethod
def unload(self):
if isinstance(self.path_or_stream, BytesIO):
self.path_or_stream.close()
self.path_or_stream = None
@classmethod
@abstractmethod
def supported_formats(cls) -> Set["InputFormat"]:
pass
class PaginatedDocumentBackend(AbstractDocumentBackend):
"""DeclarativeDocumentBackend.
A declarative document backend is a backend that can transform to DoclingDocument
straight without a recognition pipeline.
"""
@abstractmethod
def page_count(self) -> int:
pass
class DeclarativeDocumentBackend(AbstractDocumentBackend):
"""DeclarativeDocumentBackend.
A declarative document backend is a backend that can transform to DoclingDocument
straight without a recognition pipeline.
"""
@abstractmethod
def convert(self) -> DoclingDocument:
pass