Merge pull request #503 from madmaze/fix_default_hocr_config

Fix default hocr config
madmaze · Aug 25, 2023 · e0b8104 · e0b8104
2 parents 1fd3e60 + b560563
commit e0b8104
Showing 1 changed file with 4 additions and 0 deletions.
diff --git a/pytesseract/pytesseract.py b/pytesseract/pytesseract.py
@@ -445,6 +445,10 @@ def image_to_pdf_or_hocr(
 
     if extension not in {'pdf', 'hocr'}:
         raise ValueError(f'Unsupported extension: {extension}')
+
+    if extension == 'hocr':
+        config = f'-c tessedit_create_hocr=1 {config.strip()}'
+
     args = [image, extension, lang, config, nice, timeout, True]
 
     return run_and_get_output(*args)