fix: Rename the tesseract OCR related classes and filenames

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>

docling/cli/main.py

@@ -17,8 +17,8 @@ from docling.datamodel.document import ConversionResult, DocumentConversionInput
 from docling.datamodel.pipeline_options import (
     EasyOcrOptions,
     PipelineOptions,
-    TesseractCLIOptions,
+    TesseractCliOcrOptions,
-    TesseractOptions,
+    TesseractOcrOptions,
 )
 from docling.document_converter import DocumentConverter
 
@@ -210,9 +210,9 @@ def convert(
         case OcrEngine.EASYOCR:
             ocr_options = EasyOcrOptions()
         case OcrEngine.TESSERACT_CLI:
-            ocr_options = TesseractCLIOptions()
+            ocr_options = TesseractCliOcrOptions()
         case OcrEngine.TESSERACT:
-            ocr_options = TesseractOptions()
+            ocr_options = TesseractOcrOptions()
         case _:
             raise RuntimeError(f"Unexpected backend type {backend}")
 

docling/datamodel/pipeline_options.py

@@ -36,7 +36,7 @@ class EasyOcrOptions(OcrOptions):
     )
 
 
-class TesseractCLIOptions(OcrOptions):
+class TesseractCliOcrOptions(OcrOptions):
     kind: Literal["tesseract"] = "tesseract"
     lang: List[str] = ["fra", "deu", "spa", "eng"]
     tesseract_cmd: str = "tesseract"
@@ -47,7 +47,7 @@ class TesseractCLIOptions(OcrOptions):
     )
 
 
-class TesseractOptions(OcrOptions):
+class TesseractOcrOptions(OcrOptions):
     kind: Literal["tesserocr"] = "tesserocr"
     lang: List[str] = ["fra", "deu", "spa", "eng"]
     path: Optional[str] = None
@@ -62,6 +62,6 @@ class PipelineOptions(BaseModel):
     do_ocr: bool = True  # True: perform OCR, replace programmatic PDF text
 
     table_structure_options: TableStructureOptions = TableStructureOptions()
-    ocr_options: Union[EasyOcrOptions, TesseractCLIOptions, TesseractOptions] = Field(
+    ocr_options: Union[EasyOcrOptions, TesseractCliOcrOptions, TesseractOcrOptions] = (
-        EasyOcrOptions(), discriminator="kind"
+        Field(EasyOcrOptions(), discriminator="kind")
     )

docling/models/tesseract_ocr_cli_model.py

@@ -7,17 +7,17 @@ from typing import Iterable, Tuple
 import pandas as pd
 
 from docling.datamodel.base_models import BoundingBox, CoordOrigin, OcrCell, Page
-from docling.datamodel.pipeline_options import TesseractCLIOptions
+from docling.datamodel.pipeline_options import TesseractCliOcrOptions
 from docling.models.base_ocr_model import BaseOcrModel
 
 _log = logging.getLogger(__name__)
 
 
-class TesseractCLIModel(BaseOcrModel):
+class TesseractOcrCliModel(BaseOcrModel):
 
-    def __init__(self, enabled: bool, options: TesseractCLIOptions):
+    def __init__(self, enabled: bool, options: TesseractCliOcrOptions):
         super().__init__(enabled=enabled, options=options)
-        self.options: TesseractCLIOptions
+        self.options: TesseractCliOcrOptions
 
         self.scale = 3  # multiplier for 72 dpi == 216 dpi.
 

docling/models/tesseract_ocr_model.py

@@ -4,16 +4,16 @@ from typing import Iterable
 import numpy
 
 from docling.datamodel.base_models import BoundingBox, CoordOrigin, OcrCell, Page
-from docling.datamodel.pipeline_options import TesseractCLIOptions
+from docling.datamodel.pipeline_options import TesseractCliOcrOptions
 from docling.models.base_ocr_model import BaseOcrModel
 
 _log = logging.getLogger(__name__)
 
 
-class TesseractModel(BaseOcrModel):
+class TesseractOcrModel(BaseOcrModel):
-    def __init__(self, enabled: bool, options: TesseractCLIOptions):
+    def __init__(self, enabled: bool, options: TesseractCliOcrOptions):
         super().__init__(enabled=enabled, options=options)
-        self.options: TesseractCLIOptions
+        self.options: TesseractCliOcrOptions
 
         self.scale = 3  # multiplier for 72 dpi == 216 dpi.
         self.reader = None

docling/pipeline/standard_model_pipeline.py

@@ -3,15 +3,15 @@ from pathlib import Path
 from docling.datamodel.pipeline_options import (
     EasyOcrOptions,
     PipelineOptions,
-    TesseractCLIOptions,
+    TesseractCliOcrOptions,
-    TesseractOptions,
+    TesseractOcrOptions,
 )
 from docling.models.base_ocr_model import BaseOcrModel
 from docling.models.easyocr_model import EasyOcrModel
 from docling.models.layout_model import LayoutModel
 from docling.models.table_structure_model import TableStructureModel
-from docling.models.tesseract_cli_model import TesseractCLIModel
+from docling.models.tesseract_ocr_cli_model import TesseractOcrCliModel
-from docling.models.tesseract_model import TesseractModel
+from docling.models.tesseract_ocr_model import TesseractOcrModel
 from docling.pipeline.base_model_pipeline import BaseModelPipeline
 
 
@@ -28,13 +28,13 @@ class StandardModelPipeline(BaseModelPipeline):
                 enabled=pipeline_options.do_ocr,
                 options=pipeline_options.ocr_options,
             )
-        elif isinstance(pipeline_options.ocr_options, TesseractCLIOptions):
+        elif isinstance(pipeline_options.ocr_options, TesseractCliOcrOptions):
-            ocr_model = TesseractCLIModel(
+            ocr_model = TesseractOcrCliModel(
                 enabled=pipeline_options.do_ocr,
                 options=pipeline_options.ocr_options,
             )
-        elif isinstance(pipeline_options.ocr_options, TesseractOptions):
+        elif isinstance(pipeline_options.ocr_options, TesseractOcrOptions):
-            ocr_model = TesseractModel(
+            ocr_model = TesseractOcrModel(
                 enabled=pipeline_options.do_ocr,
                 options=pipeline_options.ocr_options,
             )

examples/custom_convert.py

@@ -8,7 +8,10 @@ from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
 from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
 from docling.datamodel.base_models import ConversionStatus, PipelineOptions
 from docling.datamodel.document import ConversionResult, DocumentConversionInput
-from docling.datamodel.pipeline_options import TesseractCLIOptions, TesseractOptions
+from docling.datamodel.pipeline_options import (
+    TesseractCliOcrOptions,
+    TesseractOcrOptions,
+)
 from docling.document_converter import DocumentConverter
 
 _log = logging.getLogger(__name__)
@@ -126,7 +129,7 @@ def main():
     pipeline_options.do_ocr = True
     pipeline_options.do_table_structure = True
     pipeline_options.table_structure_options.do_cell_matching = True
-    pipeline_options.ocr_options = TesseractOptions()
+    pipeline_options.ocr_options = TesseractOcrOptions()
 
     # Docling Parse with Tesseract CLI
     # ----------------------
@@ -134,7 +137,7 @@ def main():
     pipeline_options.do_ocr = True
     pipeline_options.do_table_structure = True
     pipeline_options.table_structure_options.do_cell_matching = True
-    pipeline_options.ocr_options = TesseractCLIOptions()
+    pipeline_options.ocr_options = TesseractCliOcrOptions()
 
     doc_converter = DocumentConverter(
         pipeline_options=pipeline_options,

tests/test_e2e_ocr_conversion.py

@@ -7,8 +7,8 @@ from docling.datamodel.pipeline_options import (
     EasyOcrOptions,
     OcrOptions,
     PipelineOptions,
-    TesseractCLIOptions,
+    TesseractCliOcrOptions,
-    TesseractOptions,
+    TesseractOcrOptions,
 )
 from docling.document_converter import DocumentConverter
 
@@ -74,8 +74,8 @@ def test_e2e_conversions():
 
     engines: List[OcrOptions] = [
         EasyOcrOptions(),
-        TesseractOptions(),
+        TesseractOcrOptions(),
-        TesseractCLIOptions(),
+        TesseractCliOcrOptions(),
     ]
 
     for ocr_options in engines: