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

7
docling/utils/export.py
View File

@@ -1,9 +1,10 @@
import logging
from typing import Any, Dict, Iterable, List, Tuple, Union
from docling_core.types.doc.base import BaseCell, BaseText, Ref, Table, TableCell
from docling_core.types.doc import BoundingBox, CoordOrigin
from docling_core.types.legacy_doc.base import BaseCell, BaseText, Ref, Table
from docling.datamodel.base_models import BoundingBox, CoordOrigin, OcrCell
from docling.datamodel.base_models import OcrCell
from docling.datamodel.document import ConversionResult, Page
_log = logging.getLogger(__name__)
@@ -40,7 +41,7 @@ def generate_multimodal_pages(
end_ix = 0
doc_items: List[Tuple[int, Union[BaseCell, BaseText]]] = []
doc = doc_result.output
doc = doc_result.legacy_document
def _process_page_segments(doc_items: list[Tuple[int, BaseCell]], page: Page):
segments = []