yujunjun/unstructured
1
0
Fork 0
mirror of https://github.com/Unstructured-IO/unstructured.git synced 2025-12-08 04:55:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix

Browse Source
This commit is contained in:
Marek Połom 2024-05-08 17:43:24 +02:00
parent de2b6ef718
commit d2f62abe56
2 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
unstructured/partition/pdf_image/pdfminer_processing.py
View File

@ -87,7 +87,7 @@ def process_data_with_pdfminer(
x2 * coef, x2 * coef,
y2 * coef, y2 * coef,
text=_text, text=_text,
source="pdftext", source=Source.PDFTEXT,
) )
if text_region.bbox is not None and text_region.bbox.area > 0: if text_region.bbox is not None and text_region.bbox.area > 0:
@ -104,7 +104,7 @@ def process_data_with_pdfminer(
x2 * coef, x2 * coef,
y2 * coef, y2 * coef,
text=None, text=None,
source="pdftext", source=Source.PDFTEXT,
) )
if image_region.bbox is not None and image_region.bbox.area > 0: if image_region.bbox is not None and image_region.bbox.area > 0:
layout.append(image_region) layout.append(image_region)

1
unstructured/partition/utils/constants.py
View File

@ -3,6 +3,7 @@ from enum import Enum
class Source(Enum): class Source(Enum):
PDFTEXT = "pdftext"
PDFMINER = "pdfminer" PDFMINER = "pdfminer"
OCR_TESSERACT = "ocr_tesseract" OCR_TESSERACT = "ocr_tesseract"
OCR_PADDLE = "ocr_paddle" OCR_PADDLE = "ocr_paddle"