mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-30 14:04:27 +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):

12
docling/backend/docling_parse_v2_backend.py
View File

@ -26,7 +26,7 @@ class DoclingParseV2PageBackend(PdfPageBackend):
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)
self.valid = "pages" in parsed_page and len(parsed_page["pages"])==1 self.valid = "pages" in parsed_page and len(parsed_page["pages"]) == 1
if self.valid: if self.valid:
self._dpage = parsed_page["pages"][0] self._dpage = parsed_page["pages"][0]
else: else:
@ -223,16 +223,16 @@ class DoclingParseV2DocumentBackend(PdfDocumentBackend):
) )
def page_count(self) -> int: def page_count(self) -> int:
#return len(self._pdoc) # To be replaced with docling-parse API # return len(self._pdoc) # To be replaced with docling-parse API
len_1 = len(self._pdoc) len_1 = len(self._pdoc)
len_2 = self.parser.number_of_pages(self.document_hash) len_2 = self.parser.number_of_pages(self.document_hash)
if len_1!=len_2: if len_1 != len_2:
_log.error(f"Inconsistent number of pages: {len_1}!={len_2}") _log.error(f"Inconsistent number of pages: {len_1}!={len_2}")
return len_2 return len_2
def load_page(self, page_no: int) -> DoclingParseV2PageBackend: def load_page(self, page_no: int) -> DoclingParseV2PageBackend:
return DoclingParseV2PageBackend( return DoclingParseV2PageBackend(
self.parser, self.document_hash, page_no, self._pdoc[page_no] self.parser, self.document_hash, page_no, self._pdoc[page_no]