NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat!: Docling v2 (#117)

Browse Source 
---------

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
Download Patch File Download Diff File Expand all files Collapse all files

28
docling/backend/docling_parse_backend.py
View File

@@ -5,12 +5,14 @@ from pathlib import Path
from typing import Iterable, List, Optional, Union
import pypdfium2 as pdfium
from docling_core.types.doc import BoundingBox, CoordOrigin, Size
from docling_parse.docling_parse import pdf_parser
from PIL import Image, ImageDraw
from pypdfium2 import PdfPage
from docling.backend.abstract_backend import PdfDocumentBackend, PdfPageBackend
from docling.datamodel.base_models import BoundingBox, Cell, CoordOrigin, PageSize
from docling.backend.pdf_backend import PdfDocumentBackend, PdfPageBackend
from docling.datamodel.base_models import Cell
from docling.datamodel.document import InputDocument
_log = logging.getLogger(__name__)
@@ -177,8 +179,8 @@ class DoclingParsePageBackend(PdfPageBackend):
return image
def get_size(self) -> PageSize:
return PageSize(width=self._ppage.get_width(), height=self._ppage.get_height())
def get_size(self) -> Size:
return Size(width=self._ppage.get_width(), height=self._ppage.get_height())
def unload(self):
self._ppage = None
@@ -186,23 +188,25 @@ class DoclingParsePageBackend(PdfPageBackend):
class DoclingParseDocumentBackend(PdfDocumentBackend):
def __init__(self, path_or_stream: Union[BytesIO, Path], document_hash: str):
super().__init__(path_or_stream, document_hash)
def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
super().__init__(in_doc, path_or_stream)
self._pdoc = pdfium.PdfDocument(path_or_stream)
self._pdoc = pdfium.PdfDocument(self.path_or_stream)
self.parser = pdf_parser()
success = False
if isinstance(path_or_stream, BytesIO):
if isinstance(self.path_or_stream, BytesIO):
success = self.parser.load_document_from_bytesio(
document_hash, path_or_stream
self.document_hash, self.path_or_stream
)
elif isinstance(self.path_or_stream, Path):
success = self.parser.load_document(
self.document_hash, str(self.path_or_stream)
)
elif isinstance(path_or_stream, Path):
success = self.parser.load_document(document_hash, str(path_or_stream))
if not success:
raise RuntimeError(
f"docling-parse could not load document {document_hash}."
f"docling-parse could not load document with hash {self.document_hash}."
)
def page_count(self) -> int: