feat: add options for choosing OCR engines (#118)

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
Co-authored-by: Nikos Livathinos <nli@zurich.ibm.com>
Co-authored-by: Peter Staar <taa@zurich.ibm.com>

docling/datamodel/base_models.py

@@ -110,7 +110,10 @@ class BoundingBox(BaseModel):
             return BoundingBox(l=l, t=t, r=r, b=b, coord_origin=origin)
 
     def area(self) -> float:
-        return (self.r - self.l) * (self.b - self.t)
+        area = (self.r - self.l) * (self.b - self.t)
+        if self.coord_origin == CoordOrigin.BOTTOMLEFT:
+            area = -area
+        return area
 
     def intersection_area_with(self, other: "BoundingBox") -> float:
         # Calculate intersection coordinates

docling/datamodel/pipeline_options.py

@@ -1,6 +1,7 @@
 from enum import Enum, auto
+from typing import List, Literal, Optional, Union
 
-from pydantic import BaseModel
+from pydantic import BaseModel, ConfigDict, Field
 
 
 class TableFormerMode(str, Enum):
@@ -18,8 +19,49 @@ class TableStructureOptions(BaseModel):
     mode: TableFormerMode = TableFormerMode.FAST
 
 
+class OcrOptions(BaseModel):
+    kind: str
+
+
+class EasyOcrOptions(OcrOptions):
+    kind: Literal["easyocr"] = "easyocr"
+    lang: List[str] = ["fr", "de", "es", "en"]
+    use_gpu: bool = True  # same default as easyocr.Reader
+    model_storage_directory: Optional[str] = None
+    download_enabled: bool = True  # same default as easyocr.Reader
+
+    model_config = ConfigDict(
+        extra="forbid",
+        protected_namespaces=(),
+    )
+
+
+class TesseractCliOcrOptions(OcrOptions):
+    kind: Literal["tesseract"] = "tesseract"
+    lang: List[str] = ["fra", "deu", "spa", "eng"]
+    tesseract_cmd: str = "tesseract"
+    path: Optional[str] = None
+
+    model_config = ConfigDict(
+        extra="forbid",
+    )
+
+
+class TesseractOcrOptions(OcrOptions):
+    kind: Literal["tesserocr"] = "tesserocr"
+    lang: List[str] = ["fra", "deu", "spa", "eng"]
+    path: Optional[str] = None
+
+    model_config = ConfigDict(
+        extra="forbid",
+    )
+
+
 class PipelineOptions(BaseModel):
     do_table_structure: bool = True  # True: perform table structure extraction
     do_ocr: bool = True  # True: perform OCR, replace programmatic PDF text
 
     table_structure_options: TableStructureOptions = TableStructureOptions()
+    ocr_options: Union[EasyOcrOptions, TesseractCliOcrOptions, TesseractOcrOptions] = (
+        Field(EasyOcrOptions(), discriminator="kind")
+    )