mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-27 04:24:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(ocr): avoid to swallow tesseract errors causing orientation detection failures

Browse Source 
Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>
This commit is contained in:
Clément Doumouro 2025-04-09 11:31:44 +02:00
parent c1ac22947f
commit 1181338737
1 changed files with 21 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
docling/models/tesseract_ocr_cli_model.py
View File

@ -2,6 +2,7 @@ import csv
import io import io
import logging import logging
import os import os
import subprocess
import tempfile import tempfile
from collections.abc import Iterable from collections.abc import Iterable
from pathlib import Path from pathlib import Path
@ -150,9 +151,8 @@ class TesseractOcrCliModel(BaseOcrModel):
cmd = [self.options.tesseract_cmd] cmd = [self.options.tesseract_cmd]
cmd.extend(["--psm", "0", "-l", "osd", ifilename, "stdout"]) cmd.extend(["--psm", "0", "-l", "osd", ifilename, "stdout"])
_log.info("command: {}".format(" ".join(cmd))) _log.info("command: {}".format(" ".join(cmd)))
proc = Popen(cmd, stdout=PIPE, stderr=DEVNULL) output = subprocess.run(cmd, capture_output=True, check=True)
output, _ = proc.communicate() decoded_data = output.stdout.decode("utf-8")
decoded_data = output.decode("utf-8")
df_detected = pd.read_csv( df_detected = pd.read_csv(
io.StringIO(decoded_data), sep=":", header=None, names=["key", "value"] io.StringIO(decoded_data), sep=":", header=None, names=["key", "value"]
) )
@ -231,14 +231,30 @@ class TesseractOcrCliModel(BaseOcrModel):
) as image_file: ) as image_file:
fname = image_file.name fname = image_file.name
high_res_image.save(image_file) high_res_image.save(image_file)
df_osd = self._perform_osd(fname) try:
df_osd = self._perform_osd(fname)
except subprocess.CalledProcessError as exc:
_log.error(
"OSD failed for: %s with error:\n %s",
image_file,
exc.stderr,
)
continue
doc_orientation = _parse_orientation(df_osd) doc_orientation = _parse_orientation(df_osd)
if doc_orientation != 0: if doc_orientation != 0:
high_res_image = high_res_image.rotate( high_res_image = high_res_image.rotate(
-doc_orientation, expand=True -doc_orientation, expand=True
) )
high_res_image.save(fname) high_res_image.save(fname)
df_result = self._run_tesseract(fname, df_osd) try:
df_result = self._run_tesseract(fname, df_osd)
except subprocess.CalledProcessError as exc:
_log.error(
"tesseract OCR failed for: %s with error:\n %s",
image_file,
exc.stderr,
)
continue
finally: finally:
if os.path.exists(fname): if os.path.exists(fname):
os.remove(fname) os.remove(fname)