fixing styling format

Signed-off-by: Swaymaw <swaymaw@gmail.com>

docling/cli/main.py

@@ -27,10 +27,10 @@ from docling.datamodel.pipeline_options import (
     OcrMacOptions,
     OcrOptions,
     PdfPipelineOptions,
+    RapidOcrOptions,
     TableFormerMode,
     TesseractCliOcrOptions,
     TesseractOcrOptions,
-    RapidOcrOptions
 )
 from docling.document_converter import DocumentConverter, FormatOption, PdfFormatOption
 

docling/datamodel/pipeline_options.py

@@ -28,19 +28,23 @@ class OcrOptions(BaseModel):
         0.05  # percentage of the area for a bitmap to processed with OCR
     )
 
+
 class RapidOcrOptions(OcrOptions):
     kind: Literal["rapidocr"] = "rapidocr"
 
-    # English and chinese are the most commly used models and have been tested with RapidOCR. 
-    lang: List[str] = ["english", "chinese"] # However, language as a parameter is not supported by rapidocr yet and hence changing this options doesn't affect anything. 
+    # English and chinese are the most commly used models and have been tested with RapidOCR.
+    lang: List[str] = [
+        "english",
+        "chinese",
+    ]  # However, language as a parameter is not supported by rapidocr yet and hence changing this options doesn't affect anything.
     # For more details on supported languages by RapidOCR visit https://rapidai.github.io/RapidOCRDocs/blog/2022/09/28/%E6%94%AF%E6%8C%81%E8%AF%86%E5%88%AB%E8%AF%AD%E8%A8%80/
 
     # For more details on the following options visit https://rapidai.github.io/RapidOCRDocs/install_usage/api/RapidOCR/
-    text_score: float = 0.5 # same default as rapidocr
+    text_score: float = 0.5  # same default as rapidocr
 
-    use_det: Optional[bool] = None # same default as rapidocr
-    use_cls: Optional[bool] = None # same default as rapidocr
-    use_rec: Optional[bool] = None # same default as rapidocr
+    use_det: Optional[bool] = None  # same default as rapidocr
+    use_cls: Optional[bool] = None  # same default as rapidocr
+    use_rec: Optional[bool] = None  # same default as rapidocr
 
     det_use_cuda: bool = False  # same default as rapidocr
     cls_use_cuda: bool = False  # same default as rapidocr
@@ -50,16 +54,17 @@ class RapidOcrOptions(OcrOptions):
     cls_use_dml: bool = False  # same default as rapidocr
     rec_use_dml: bool = False  # same default as rapidocr
 
-    print_verbose: bool = False # same default as rapidocr
-    
-    det_model_path: Optional[str] = None # same default as rapidocr
-    cls_model_path: Optional[str] = None # same default as rapidocr
-    rec_model_path: Optional[str] = None # same default as rapidocr
+    print_verbose: bool = False  # same default as rapidocr
+
+    det_model_path: Optional[str] = None  # same default as rapidocr
+    cls_model_path: Optional[str] = None  # same default as rapidocr
+    rec_model_path: Optional[str] = None  # same default as rapidocr
 
     model_config = ConfigDict(
         extra="forbid",
     )
 
+
 class EasyOcrOptions(OcrOptions):
     kind: Literal["easyocr"] = "easyocr"
     lang: List[str] = ["fr", "de", "es", "en"]

docling/models/rapid_ocr_model.py

@@ -23,7 +23,7 @@ class RapidOcrModel(BaseOcrModel):
 
         if self.enabled:
             try:
-                from rapidocr_onnxruntime import RapidOCR
+                from rapidocr_onnxruntime import RapidOCR  # type: ignore
             except ImportError:
                 raise ImportError(
                     "RapidOCR is not installed. Please install it via `pip install rapidocr_onnxruntime` to use this OCR engine. "
@@ -31,17 +31,17 @@ class RapidOcrModel(BaseOcrModel):
                 )
 
             self.reader = RapidOCR(
-                text_score = self.options.text_score,
-                cls_use_cuda = self.options.cls_use_cuda,
-                rec_use_cuda = self.options.rec_use_cuda,
-                det_use_cuda = self.options.det_use_cuda,
-                det_use_dml = self.options.det_use_dml,
-                cls_use_dml = self.options.cls_use_dml,
-                rec_use_dml = self.options.rec_use_dml,
-                print_verbose = self.options.print_verbose,
-                det_model_path = self.options.det_model_path,
-                cls_model_path = self.options.cls_model_path,
-                rec_model_path = self.options.rec_model_path,
+                text_score=self.options.text_score,
+                cls_use_cuda=self.options.cls_use_cuda,
+                rec_use_cuda=self.options.rec_use_cuda,
+                det_use_cuda=self.options.det_use_cuda,
+                det_use_dml=self.options.det_use_dml,
+                cls_use_dml=self.options.cls_use_dml,
+                rec_use_dml=self.options.rec_use_dml,
+                print_verbose=self.options.print_verbose,
+                det_model_path=self.options.det_model_path,
+                cls_model_path=self.options.cls_model_path,
+                rec_model_path=self.options.rec_model_path,
             )
 
     def __call__(
@@ -70,7 +70,12 @@ class RapidOcrModel(BaseOcrModel):
                             scale=self.scale, cropbox=ocr_rect
                         )
                         im = numpy.array(high_res_image)
-                        result, _ = self.reader(im, use_det=self.options.use_det, use_cls=self.options.use_cls, use_rec=self.options.use_rec)
+                        result, _ = self.reader(
+                            im,
+                            use_det=self.options.use_det,
+                            use_cls=self.options.use_cls,
+                            use_rec=self.options.use_rec,
+                        )
 
                         del high_res_image
                         del im
@@ -101,4 +106,4 @@ class RapidOcrModel(BaseOcrModel):
                 if settings.debug.visualize_ocr:
                     self.draw_ocr_rects_and_cells(conv_res, page, ocr_rects)
 
-                yield page
+                yield page

docling/pipeline/standard_pdf_pipeline.py

@@ -13,9 +13,9 @@ from docling.datamodel.pipeline_options import (
     EasyOcrOptions,
     OcrMacOptions,
     PdfPipelineOptions,
+    RapidOcrOptions,
     TesseractCliOcrOptions,
     TesseractOcrOptions,
-    RapidOcrOptions
 )
 from docling.models.base_ocr_model import BaseOcrModel
 from docling.models.ds_glm_model import GlmModel, GlmOptions
@@ -27,10 +27,10 @@ from docling.models.page_preprocessing_model import (
     PagePreprocessingModel,
     PagePreprocessingOptions,
 )
+from docling.models.rapid_ocr_model import RapidOcrModel
 from docling.models.table_structure_model import TableStructureModel
 from docling.models.tesseract_ocr_cli_model import TesseractOcrCliModel
 from docling.models.tesseract_ocr_model import TesseractOcrModel
-from docling.models.rapid_ocr_model import RapidOcrModel
 from docling.pipeline.base_pipeline import PaginatedPipeline
 from docling.utils.profiling import ProfilingScope, TimeRecorder
 

docs/examples/full_page_ocr.py

@@ -6,9 +6,9 @@ from docling.datamodel.pipeline_options import (
     EasyOcrOptions,
     OcrMacOptions,
     PdfPipelineOptions,
+    RapidOcrOptions,
     TesseractCliOcrOptions,
     TesseractOcrOptions,
-    RapidOcrOptions
 )
 from docling.document_converter import DocumentConverter, PdfFormatOption
 

tests/test_e2e_ocr_conversion.py

@@ -10,9 +10,9 @@ from docling.datamodel.pipeline_options import (
     OcrMacOptions,
     OcrOptions,
     PdfPipelineOptions,
+    RapidOcrOptions,
     TesseractCliOcrOptions,
     TesseractOcrOptions,
-    RapidOcrOptions
 )
 from docling.document_converter import DocumentConverter, PdfFormatOption
 
@@ -61,7 +61,7 @@ def test_e2e_conversions():
         EasyOcrOptions(force_full_page_ocr=True),
         TesseractOcrOptions(force_full_page_ocr=True),
         TesseractCliOcrOptions(force_full_page_ocr=True),
-        RapidOcrOptions(force_full_page_ocr=True)
+        RapidOcrOptions(force_full_page_ocr=True),
     ]
 
     # only works on mac