fixed conflicts

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

docling/datamodel/pipeline_options.py

@@ -30,7 +30,7 @@ class EasyOcrOptions(OcrOptions):
 
 class TesseractOcrOptions(OcrOptions):
     kind: Literal["tesseract"] = "tesseract"
-
+    lang: List[str] = ["fr", "de", "es", "en"]
 
 class TesserOcrOptions(OcrOptions):
     kind: Literal["tesseract"] = "tesserocr"

docling/models/tesseract_model.py

@@ -10,7 +10,6 @@ from docling.models.base_ocr_model import BaseOcrModel
 
 _log = logging.getLogger(__name__)
 
-
 class TesseractOcrModel(BaseOcrModel):
 
     def __init__(self, enabled: bool, options: TesseractOcrOptions):

docling/pipeline/standard_model_pipeline.py

@@ -8,6 +8,7 @@ from docling.datamodel.pipeline_options import (
 )
 from docling.models.base_ocr_model import BaseOcrModel
 from docling.models.easyocr_model import EasyOcrModel
+from docling.models.tesseract_model import TesseractOCRModel
 from docling.models.layout_model import LayoutModel
 from docling.models.table_structure_model import TableStructureModel
 from docling.models.tesseract_model import TesseractOcrModel

tests/test_e2e_ocr_conversion.py

@@ -47,7 +47,28 @@ def get_pdf_paths():
     return pdf_files
 
 
-def get_converter():
+def get_easyocr_converter():
+
+    ocr_options = EasyOcrOptions(
+        
+    )
+    
+    pipeline_options = PipelineOptions()
+    # Debug
+    pipeline_options.do_ocr = True
+    pipeline_options.do_table_structure = True
+    pipeline_options.table_structure_options.do_cell_matching = True
+
+    
+    
+    converter = DocumentConverter(
+        pipeline_options=pipeline_options,
+        pdf_backend=DoclingParseDocumentBackend,
+    )
+
+    return converter
+
+def get_tesseract_converter():
 
     pipeline_options = PipelineOptions()
     # Debug
@@ -63,6 +84,7 @@ def get_converter():
     return converter
 
 
+
 def test_e2e_conversions():
 
     pdf_paths = get_pdf_paths()