docling 2.26.0__py3-none-any.whl → 2.28.0__py3-none-any.whl

docling/models/tesseract_ocr_model.py

@@ -1,11 +1,17 @@
 import logging
-from typing import Iterable
+from pathlib import Path
+from typing import Iterable, Optional, Type
 
 from docling_core.types.doc import BoundingBox, CoordOrigin
+from docling_core.types.doc.page import BoundingRectangle, TextCell
 
-from docling.datamodel.base_models import Cell, OcrCell, Page
+from docling.datamodel.base_models import Page
 from docling.datamodel.document import ConversionResult
-from docling.datamodel.pipeline_options import TesseractOcrOptions
+from docling.datamodel.pipeline_options import (
+    AcceleratorOptions,
+    OcrOptions,
+    TesseractOcrOptions,
+)
 from docling.datamodel.settings import settings
 from docling.models.base_ocr_model import BaseOcrModel
 from docling.utils.ocr_utils import map_tesseract_script
@@ -15,8 +21,19 @@ _log = logging.getLogger(__name__)
 
 
 class TesseractOcrModel(BaseOcrModel):
-    def __init__(self, enabled: bool, options: TesseractOcrOptions):
-        super().__init__(enabled=enabled, options=options)
+    def __init__(
+        self,
+        enabled: bool,
+        artifacts_path: Optional[Path],
+        options: TesseractOcrOptions,
+        accelerator_options: AcceleratorOptions,
+    ):
+        super().__init__(
+            enabled=enabled,
+            artifacts_path=artifacts_path,
+            options=options,
+            accelerator_options=accelerator_options,
+        )
         self.options: TesseractOcrOptions
 
         self.scale = 3  # multiplier for 72 dpi == 216 dpi.
@@ -31,14 +48,14 @@ class TesseractOcrModel(BaseOcrModel):
                 "Note that tesserocr might have to be manually compiled for working with "
                 "your Tesseract installation. The Docling documentation provides examples for it. "
                 "Alternatively, Docling has support for other OCR engines. See the documentation: "
-                "https://ds4sd.github.io/docling/installation/"
+                "https://docling-project.github.io/docling/installation/"
             )
             missing_langs_errmsg = (
                 "tesserocr is not correctly configured. No language models have been detected. "
                 "Please ensure that the TESSDATA_PREFIX envvar points to tesseract languages dir. "
                 "You can find more information how to setup other OCR engines in Docling "
                 "documentation: "
-                "https://ds4sd.github.io/docling/installation/"
+                "https://docling-project.github.io/docling/installation/"
             )
 
             try:
@@ -173,13 +190,17 @@ class TesseractOcrModel(BaseOcrModel):
                             top = (box["y"] + box["h"]) / self.scale
 
                             cells.append(
-                                OcrCell(
-                                    id=ix,
+                                TextCell(
+                                    index=ix,
                                     text=text,
+                                    orig=text,
+                                    from_ocr=True,
                                     confidence=confidence,
-                                    bbox=BoundingBox.from_tuple(
-                                        coord=(left, top, right, bottom),
-                                        origin=CoordOrigin.TOPLEFT,
+                                    rect=BoundingRectangle.from_bounding_box(
+                                        BoundingBox.from_tuple(
+                                            coord=(left, top, right, bottom),
+                                            origin=CoordOrigin.TOPLEFT,
+                                        ),
                                     ),
                                 )
                             )
@@ -195,3 +216,7 @@ class TesseractOcrModel(BaseOcrModel):
                     self.draw_ocr_rects_and_cells(conv_res, page, ocr_rects)
 
                 yield page
+
+    @classmethod
+    def get_options_type(cls) -> Type[OcrOptions]:
+        return TesseractOcrOptions

docling/pipeline/standard_pdf_pipeline.py

@@ -10,16 +10,7 @@ from docling.backend.abstract_backend import AbstractDocumentBackend
 from docling.backend.pdf_backend import PdfDocumentBackend
 from docling.datamodel.base_models import AssembledUnit, Page
 from docling.datamodel.document import ConversionResult
-from docling.datamodel.pipeline_options import (
-    EasyOcrOptions,
-    OcrMacOptions,
-    PdfPipelineOptions,
-    PictureDescriptionApiOptions,
-    PictureDescriptionVlmOptions,
-    RapidOcrOptions,
-    TesseractCliOcrOptions,
-    TesseractOcrOptions,
-)
+from docling.datamodel.pipeline_options import PdfPipelineOptions
 from docling.datamodel.settings import settings
 from docling.models.base_ocr_model import BaseOcrModel
 from docling.models.code_formula_model import CodeFormulaModel, CodeFormulaModelOptions
@@ -27,22 +18,16 @@ from docling.models.document_picture_classifier import (
     DocumentPictureClassifier,
     DocumentPictureClassifierOptions,
 )
-from docling.models.easyocr_model import EasyOcrModel
+from docling.models.factories import get_ocr_factory, get_picture_description_factory
 from docling.models.layout_model import LayoutModel
-from docling.models.ocr_mac_model import OcrMacModel
 from docling.models.page_assemble_model import PageAssembleModel, PageAssembleOptions
 from docling.models.page_preprocessing_model import (
     PagePreprocessingModel,
     PagePreprocessingOptions,
 )
-from docling.models.picture_description_api_model import PictureDescriptionApiModel
 from docling.models.picture_description_base_model import PictureDescriptionBaseModel
-from docling.models.picture_description_vlm_model import PictureDescriptionVlmModel
-from docling.models.rapid_ocr_model import RapidOcrModel
 from docling.models.readingorder_model import ReadingOrderModel, ReadingOrderOptions
 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.pipeline.base_pipeline import PaginatedPipeline
 from docling.utils.model_downloader import download_models
 from docling.utils.profiling import ProfilingScope, TimeRecorder
@@ -78,16 +63,14 @@ class StandardPdfPipeline(PaginatedPipeline):
 
         self.glm_model = ReadingOrderModel(options=ReadingOrderOptions())
 
-        if (ocr_model := self.get_ocr_model(artifacts_path=artifacts_path)) is None:
-            raise RuntimeError(
-                f"The specified OCR kind is not supported: {pipeline_options.ocr_options.kind}."
-            )
+        ocr_model = self.get_ocr_model(artifacts_path=artifacts_path)
 
         self.build_pipe = [
             # Pre-processing
             PagePreprocessingModel(
                 options=PagePreprocessingOptions(
-                    images_scale=pipeline_options.images_scale
+                    images_scale=pipeline_options.images_scale,
+                    create_parsed_page=pipeline_options.generate_parsed_pages,
                 )
             ),
             # OCR
@@ -163,66 +146,30 @@ class StandardPdfPipeline(PaginatedPipeline):
         output_dir = download_models(output_dir=local_dir, force=force, progress=False)
         return output_dir
 
-    def get_ocr_model(
-        self, artifacts_path: Optional[Path] = None
-    ) -> Optional[BaseOcrModel]:
-        if isinstance(self.pipeline_options.ocr_options, EasyOcrOptions):
-            return EasyOcrModel(
-                enabled=self.pipeline_options.do_ocr,
-                artifacts_path=artifacts_path,
-                options=self.pipeline_options.ocr_options,
-                accelerator_options=self.pipeline_options.accelerator_options,
-            )
-        elif isinstance(self.pipeline_options.ocr_options, TesseractCliOcrOptions):
-            return TesseractOcrCliModel(
-                enabled=self.pipeline_options.do_ocr,
-                options=self.pipeline_options.ocr_options,
-            )
-        elif isinstance(self.pipeline_options.ocr_options, TesseractOcrOptions):
-            return TesseractOcrModel(
-                enabled=self.pipeline_options.do_ocr,
-                options=self.pipeline_options.ocr_options,
-            )
-        elif isinstance(self.pipeline_options.ocr_options, RapidOcrOptions):
-            return RapidOcrModel(
-                enabled=self.pipeline_options.do_ocr,
-                options=self.pipeline_options.ocr_options,
-                accelerator_options=self.pipeline_options.accelerator_options,
-            )
-        elif isinstance(self.pipeline_options.ocr_options, OcrMacOptions):
-            if "darwin" != sys.platform:
-                raise RuntimeError(
-                    f"The specified OCR type is only supported on Mac: {self.pipeline_options.ocr_options.kind}."
-                )
-            return OcrMacModel(
-                enabled=self.pipeline_options.do_ocr,
-                options=self.pipeline_options.ocr_options,
-            )
-        return None
+    def get_ocr_model(self, artifacts_path: Optional[Path] = None) -> BaseOcrModel:
+        factory = get_ocr_factory(
+            allow_external_plugins=self.pipeline_options.allow_external_plugins
+        )
+        return factory.create_instance(
+            options=self.pipeline_options.ocr_options,
+            enabled=self.pipeline_options.do_ocr,
+            artifacts_path=artifacts_path,
+            accelerator_options=self.pipeline_options.accelerator_options,
+        )
 
     def get_picture_description_model(
         self, artifacts_path: Optional[Path] = None
     ) -> Optional[PictureDescriptionBaseModel]:
-        if isinstance(
-            self.pipeline_options.picture_description_options,
-            PictureDescriptionApiOptions,
-        ):
-            return PictureDescriptionApiModel(
-                enabled=self.pipeline_options.do_picture_description,
-                enable_remote_services=self.pipeline_options.enable_remote_services,
-                options=self.pipeline_options.picture_description_options,
-            )
-        elif isinstance(
-            self.pipeline_options.picture_description_options,
-            PictureDescriptionVlmOptions,
-        ):
-            return PictureDescriptionVlmModel(
-                enabled=self.pipeline_options.do_picture_description,
-                artifacts_path=artifacts_path,
-                options=self.pipeline_options.picture_description_options,
-                accelerator_options=self.pipeline_options.accelerator_options,
-            )
-        return None
+        factory = get_picture_description_factory(
+            allow_external_plugins=self.pipeline_options.allow_external_plugins
+        )
+        return factory.create_instance(
+            options=self.pipeline_options.picture_description_options,
+            enabled=self.pipeline_options.do_picture_description,
+            enable_remote_services=self.pipeline_options.enable_remote_services,
+            artifacts_path=artifacts_path,
+            accelerator_options=self.pipeline_options.accelerator_options,
+        )
 
     def initialize_page(self, conv_res: ConversionResult, page: Page) -> Page:
         with TimeRecorder(conv_res, "page_init"):