mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-31 14:34:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update imports for docling_parse.pdf_parser_v1

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer 2024-10-23 14:28:15 +02:00
parent b8796e6705
commit 9204d5e79f
2 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
docling/backend/docling_parse_backend.py
View File

@ -6,7 +6,7 @@ from typing import Iterable, List, Optional, Union
import pypdfium2 as pdfium import pypdfium2 as pdfium
from docling_core.types.doc import BoundingBox, CoordOrigin, Size from docling_core.types.doc import BoundingBox, CoordOrigin, Size
from docling_parse.docling_parse import pdf_parser from docling_parse.docling_parse import pdf_parser_v1
from PIL import Image, ImageDraw from PIL import Image, ImageDraw
from pypdfium2 import PdfPage from pypdfium2 import PdfPage
@ -19,7 +19,7 @@ _log = logging.getLogger(__name__)
class DoclingParsePageBackend(PdfPageBackend): class DoclingParsePageBackend(PdfPageBackend):
def __init__( def __init__(
self, parser: pdf_parser, document_hash: str, page_no: int, page_obj: PdfPage self, parser: pdf_parser_v1, document_hash: str, page_no: int, page_obj: PdfPage
): ):
self._ppage = page_obj self._ppage = page_obj
parsed_page = parser.parse_pdf_from_key_on_page(document_hash, page_no) parsed_page = parser.parse_pdf_from_key_on_page(document_hash, page_no)
@ -192,7 +192,7 @@ class DoclingParseDocumentBackend(PdfDocumentBackend):
super().__init__(in_doc, path_or_stream) super().__init__(in_doc, path_or_stream)
self._pdoc = pdfium.PdfDocument(self.path_or_stream) self._pdoc = pdfium.PdfDocument(self.path_or_stream)
self.parser = pdf_parser() self.parser = pdf_parser_v1()
success = False success = False
if isinstance(self.path_or_stream, BytesIO): if isinstance(self.path_or_stream, BytesIO):