NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: Ensure that TesseractOcrModel does not crash in case OSD is not installed (#1866)

Browse Source 
fix: Ensure that TesseractOcrModel does not crash if tesseract OSD is not installed

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
This commit is contained in:
Nikos Livathinos 2025-06-30 10:55:56 +02:00 committed by GitHub
parent bb99be6c24
commit ae39a9411a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 10 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
docling/models/tesseract_ocr_model.py
View File

@ -144,7 +144,10 @@ class TesseractOcrModel(BaseOcrModel):
local_reader = self.reader local_reader = self.reader
self.osd_reader.SetImage(high_res_image) self.osd_reader.SetImage(high_res_image)
doc_orientation = 0
osd = self.osd_reader.DetectOrientationScript() osd = self.osd_reader.DetectOrientationScript()
# No text, or Orientation and Script detection failure # No text, or Orientation and Script detection failure
if osd is None: if osd is None:
_log.error( _log.error(
@ -158,11 +161,14 @@ class TesseractOcrModel(BaseOcrModel):
# to OCR in the hope OCR will succeed while OSD failed # to OCR in the hope OCR will succeed while OSD failed
if self._is_auto: if self._is_auto:
continue continue
doc_orientation = parse_tesseract_orientation(osd["orient_deg"]) else:
if doc_orientation != 0: doc_orientation = parse_tesseract_orientation(
high_res_image = high_res_image.rotate( osd["orient_deg"]
-doc_orientation, expand=True
) )
if doc_orientation != 0:
high_res_image = high_res_image.rotate(
-doc_orientation, expand=True
)
if self._is_auto: if self._is_auto:
script = osd["script_name"] script = osd["script_name"]
script = map_tesseract_script(script) script = map_tesseract_script(script)