mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-27 12:34:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: PermissionError when using tesseract_ocr_cli_model (#496)

Browse Source 
Signed-off-by: Gaspard Petit <gaspardpetit@gmail.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Gaspard Petit 2024-12-03 04:22:03 -05:00 committed by GitHub
parent 6ca85993f4
commit 32e9b4a2cf
1 changed files with 10 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
docling/models/tesseract_ocr_cli_model.py
View File

@ -1,5 +1,6 @@
import io import io
import logging import logging
import os
import tempfile import tempfile
from subprocess import DEVNULL, PIPE, Popen from subprocess import DEVNULL, PIPE, Popen
from typing import Iterable, Optional, Tuple from typing import Iterable, Optional, Tuple
@ -130,14 +131,17 @@ class TesseractOcrCliModel(BaseOcrModel):
high_res_image = page._backend.get_page_image( high_res_image = page._backend.get_page_image(
scale=self.scale, cropbox=ocr_rect scale=self.scale, cropbox=ocr_rect
) )
try:
with tempfile.NamedTemporaryFile( with tempfile.NamedTemporaryFile(
suffix=".png", mode="w" suffix=".png", mode="w+b", delete=False
) as image_file: ) as image_file:
fname = image_file.name fname = image_file.name
high_res_image.save(fname) high_res_image.save(image_file)
df = self._run_tesseract(fname) df = self._run_tesseract(fname)
finally:
if os.path.exists(fname):
os.remove(fname)
# _log.info(df) # _log.info(df)