docling 2.6.0__py3-none-any.whl → 2.7.0__py3-none-any.whl

docling/cli/main.py

@@ -24,6 +24,7 @@ from docling.datamodel.base_models import (
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import (
     EasyOcrOptions,
+    OcrMacOptions,
     OcrOptions,
     PdfPipelineOptions,
     TableFormerMode,
@@ -74,6 +75,7 @@ class OcrEngine(str, Enum):
     EASYOCR = "easyocr"
     TESSERACT_CLI = "tesseract_cli"
     TESSERACT = "tesseract"
+    OCRMAC = "ocrmac"
 
 
 def export_documents(
@@ -252,15 +254,16 @@ def convert(
     export_txt = OutputFormat.TEXT in to_formats
     export_doctags = OutputFormat.DOCTAGS in to_formats
 
-    match ocr_engine:
-        case OcrEngine.EASYOCR:
-            ocr_options: OcrOptions = EasyOcrOptions(force_full_page_ocr=force_ocr)
-        case OcrEngine.TESSERACT_CLI:
-            ocr_options = TesseractCliOcrOptions(force_full_page_ocr=force_ocr)
-        case OcrEngine.TESSERACT:
-            ocr_options = TesseractOcrOptions(force_full_page_ocr=force_ocr)
-        case _:
-            raise RuntimeError(f"Unexpected OCR engine type {ocr_engine}")
+    if ocr_engine == OcrEngine.EASYOCR:
+        ocr_options: OcrOptions = EasyOcrOptions(force_full_page_ocr=force_ocr)
+    elif ocr_engine == OcrEngine.TESSERACT_CLI:
+        ocr_options = TesseractCliOcrOptions(force_full_page_ocr=force_ocr)
+    elif ocr_engine == OcrEngine.TESSERACT:
+        ocr_options = TesseractOcrOptions(force_full_page_ocr=force_ocr)
+    elif ocr_engine == OcrEngine.OCRMAC:
+        ocr_options = OcrMacOptions(force_full_page_ocr=force_ocr)
+    else:
+        raise RuntimeError(f"Unexpected OCR engine type {ocr_engine}")
 
     ocr_lang_list = _split_list(ocr_lang)
     if ocr_lang_list is not None:
@@ -277,15 +280,14 @@ def convert(
     if artifacts_path is not None:
         pipeline_options.artifacts_path = artifacts_path
 
-    match pdf_backend:
-        case PdfBackend.DLPARSE_V1:
-            backend: Type[PdfDocumentBackend] = DoclingParseDocumentBackend
-        case PdfBackend.DLPARSE_V2:
-            backend = DoclingParseV2DocumentBackend
-        case PdfBackend.PYPDFIUM2:
-            backend = PyPdfiumDocumentBackend
-        case _:
-            raise RuntimeError(f"Unexpected PDF backend type {pdf_backend}")
+    if pdf_backend == PdfBackend.DLPARSE_V1:
+        backend: Type[PdfDocumentBackend] = DoclingParseDocumentBackend
+    elif pdf_backend == PdfBackend.DLPARSE_V2:
+        backend = DoclingParseV2DocumentBackend
+    elif pdf_backend == PdfBackend.PYPDFIUM2:
+        backend = PyPdfiumDocumentBackend
+    else:
+        raise RuntimeError(f"Unexpected PDF backend type {pdf_backend}")
 
     format_options: Dict[InputFormat, FormatOption] = {
         InputFormat.PDF: PdfFormatOption(

docling/datamodel/pipeline_options.py

@@ -63,6 +63,17 @@ class TesseractOcrOptions(OcrOptions):
     )
 
 
+class OcrMacOptions(OcrOptions):
+    kind: Literal["ocrmac"] = "ocrmac"
+    lang: List[str] = ["fr-FR", "de-DE", "es-ES", "en-US"]
+    recognition: str = "accurate"
+    framework: str = "vision"
+
+    model_config = ConfigDict(
+        extra="forbid",
+    )
+
+
 class PipelineOptions(BaseModel):
     create_legacy_output: bool = (
         True  # This defautl will be set to False on a future version of docling
@@ -75,9 +86,9 @@ class PdfPipelineOptions(PipelineOptions):
     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")
-    )
+    ocr_options: Union[
+        EasyOcrOptions, TesseractCliOcrOptions, TesseractOcrOptions, OcrMacOptions
+    ] = Field(EasyOcrOptions(), discriminator="kind")
 
     images_scale: float = 1.0
     generate_page_images: bool = False

docling/document_converter.py

@@ -3,7 +3,7 @@ import sys
 import time
 from functools import partial
 from pathlib import Path
-from typing import Dict, Iterable, Iterator, List, Optional, Type
+from typing import Dict, Iterable, Iterator, List, Optional, Type, Union
 
 from pydantic import BaseModel, ConfigDict, model_validator, validate_call
 
@@ -155,7 +155,7 @@ class DocumentConverter:
     @validate_call(config=ConfigDict(strict=True))
     def convert(
         self,
-        source: Path | str | DocumentStream,  # TODO review naming
+        source: Union[Path, str, DocumentStream],  # TODO review naming
         raises_on_error: bool = True,
         max_num_pages: int = sys.maxsize,
         max_file_size: int = sys.maxsize,
@@ -172,7 +172,7 @@ class DocumentConverter:
     @validate_call(config=ConfigDict(strict=True))
     def convert_all(
         self,
-        source: Iterable[Path | str | DocumentStream],  # TODO review naming
+        source: Iterable[Union[Path, str, DocumentStream]],  # TODO review naming
         raises_on_error: bool = True,  # True: raises on first conversion error; False: does not raise on conv error
         max_num_pages: int = sys.maxsize,
         max_file_size: int = sys.maxsize,
@@ -183,7 +183,7 @@ class DocumentConverter:
         )
         conv_input = _DocumentConversionInput(
             path_or_stream_iterator=source,
-            limit=limits,
+            limits=limits,
         )
         conv_res_iter = self._convert(conv_input, raises_on_error=raises_on_error)
         for conv_res in conv_res_iter:

docling/models/ocr_mac_model.py

@@ -0,0 +1,118 @@
+import logging
+import tempfile
+from typing import Iterable, Optional, Tuple
+
+from docling_core.types.doc import BoundingBox, CoordOrigin
+
+from docling.datamodel.base_models import OcrCell, Page
+from docling.datamodel.document import ConversionResult
+from docling.datamodel.pipeline_options import OcrMacOptions
+from docling.datamodel.settings import settings
+from docling.models.base_ocr_model import BaseOcrModel
+from docling.utils.profiling import TimeRecorder
+
+_log = logging.getLogger(__name__)
+
+
+class OcrMacModel(BaseOcrModel):
+    def __init__(self, enabled: bool, options: OcrMacOptions):
+        super().__init__(enabled=enabled, options=options)
+        self.options: OcrMacOptions
+
+        self.scale = 3  # multiplier for 72 dpi == 216 dpi.
+
+        if self.enabled:
+            install_errmsg = (
+                "ocrmac is not correctly installed. "
+                "Please install it via `pip install ocrmac` to use this OCR engine. "
+                "Alternatively, Docling has support for other OCR engines. See the documentation: "
+                "https://ds4sd.github.io/docling/installation/"
+            )
+            try:
+                from ocrmac import ocrmac
+            except ImportError:
+                raise ImportError(install_errmsg)
+
+            self.reader_RIL = ocrmac.OCR
+
+    def __call__(
+        self, conv_res: ConversionResult, page_batch: Iterable[Page]
+    ) -> Iterable[Page]:
+
+        if not self.enabled:
+            yield from page_batch
+            return
+
+        for page in page_batch:
+            assert page._backend is not None
+            if not page._backend.is_valid():
+                yield page
+            else:
+                with TimeRecorder(conv_res, "ocr"):
+
+                    ocr_rects = self.get_ocr_rects(page)
+
+                    all_ocr_cells = []
+                    for ocr_rect in ocr_rects:
+                        # Skip zero area boxes
+                        if ocr_rect.area() == 0:
+                            continue
+                        high_res_image = page._backend.get_page_image(
+                            scale=self.scale, cropbox=ocr_rect
+                        )
+
+                        with tempfile.NamedTemporaryFile(
+                            suffix=".png", mode="w"
+                        ) as image_file:
+                            fname = image_file.name
+                            high_res_image.save(fname)
+
+                            boxes = self.reader_RIL(
+                                fname,
+                                recognition_level=self.options.recognition,
+                                framework=self.options.framework,
+                                language_preference=self.options.lang,
+                            ).recognize()
+
+                        im_width, im_height = high_res_image.size
+                        cells = []
+                        for ix, (text, confidence, box) in enumerate(boxes):
+                            x = float(box[0])
+                            y = float(box[1])
+                            w = float(box[2])
+                            h = float(box[3])
+
+                            x1 = x * im_width
+                            y2 = (1 - y) * im_height
+
+                            x2 = x1 + w * im_width
+                            y1 = y2 - h * im_height
+
+                            left = x1 / self.scale
+                            top = y1 / self.scale
+                            right = x2 / self.scale
+                            bottom = y2 / self.scale
+
+                            cells.append(
+                                OcrCell(
+                                    id=ix,
+                                    text=text,
+                                    confidence=confidence,
+                                    bbox=BoundingBox.from_tuple(
+                                        coord=(left, top, right, bottom),
+                                        origin=CoordOrigin.TOPLEFT,
+                                    ),
+                                )
+                            )
+
+                        # del high_res_image
+                        all_ocr_cells.extend(cells)
+
+                    # Post-process the cells
+                    page.cells = self.post_process_cells(all_ocr_cells, page.cells)
+
+                # DEBUG code:
+                if settings.debug.visualize_ocr:
+                    self.draw_ocr_rects_and_cells(conv_res, page, ocr_rects)
+
+                yield page

docling/pipeline/standard_pdf_pipeline.py

@@ -1,4 +1,5 @@
 import logging
+import sys
 from pathlib import Path
 from typing import Optional
 
@@ -10,6 +11,7 @@ from docling.datamodel.base_models import AssembledUnit, Page
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import (
     EasyOcrOptions,
+    OcrMacOptions,
     PdfPipelineOptions,
     TesseractCliOcrOptions,
     TesseractOcrOptions,
@@ -18,6 +20,7 @@ from docling.models.base_ocr_model import BaseOcrModel
 from docling.models.ds_glm_model import GlmModel, GlmOptions
 from docling.models.easyocr_model import EasyOcrModel
 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,
@@ -118,6 +121,15 @@ class StandardPdfPipeline(PaginatedPipeline):
                 enabled=self.pipeline_options.do_ocr,
                 options=self.pipeline_options.ocr_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 initialize_page(self, conv_res: ConversionResult, page: Page) -> Page:

{docling-2.6.0.dist-info → docling-2.7.0.dist-info}/METADATA

@@ -1,13 +1,13 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.6.0
+Version: 2.7.0
 Summary: SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications.
 Home-page: https://github.com/DS4SD/docling
 License: MIT
 Keywords: docling,convert,document,pdf,docx,html,markdown,layout model,segmentation,table structure,table former
 Author: Christoph Auer
 Author-email: cau@zurich.ibm.com
-Requires-Python: >=3.10,<4.0
+Requires-Python: >=3.9,<4.0
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
@@ -15,21 +15,24 @@ Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: MacOS :: MacOS X
 Classifier: Operating System :: POSIX :: Linux
 Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Provides-Extra: ocrmac
 Provides-Extra: tesserocr
 Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
 Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: deepsearch-glm (>=0.26.1,<0.27.0)
 Requires-Dist: docling-core (>=2.4.0,<3.0.0)
-Requires-Dist: docling-ibm-models (>=2.0.3,<3.0.0)
-Requires-Dist: docling-parse (>=2.0.2,<3.0.0)
+Requires-Dist: docling-ibm-models (>=2.0.6,<3.0.0)
+Requires-Dist: docling-parse (>=2.0.5,<3.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)
 Requires-Dist: filetype (>=1.2.0,<2.0.0)
 Requires-Dist: huggingface_hub (>=0.23,<1)
 Requires-Dist: marko (>=2.1.2,<3.0.0)
+Requires-Dist: ocrmac (>=1.0.0,<2.0.0) ; (sys_platform == "darwin") and (extra == "ocrmac")
 Requires-Dist: openpyxl (>=3.1.5,<4.0.0)
 Requires-Dist: pandas (>=2.1.4,<3.0.0)
 Requires-Dist: pyarrow (>=16.1.0,<17.0.0)
@@ -40,7 +43,7 @@ Requires-Dist: python-docx (>=1.1.2,<2.0.0)
 Requires-Dist: python-pptx (>=1.0.2,<2.0.0)
 Requires-Dist: requests (>=2.32.3,<3.0.0)
 Requires-Dist: rtree (>=1.3.0,<2.0.0)
-Requires-Dist: scipy (>=1.14.1,<2.0.0)
+Requires-Dist: scipy (>=1.6.0,<2.0.0)
 Requires-Dist: tesserocr (>=2.7.1,<3.0.0) ; extra == "tesserocr"
 Requires-Dist: typer (>=0.12.5,<0.13.0)
 Project-URL: Repository, https://github.com/DS4SD/docling
@@ -61,7 +64,7 @@ Description-Content-Type: text/markdown
 [![arXiv](https://img.shields.io/badge/arXiv-2408.09869-b31b1b.svg)](https://arxiv.org/abs/2408.09869)
 [![Docs](https://img.shields.io/badge/docs-live-brightgreen)](https://ds4sd.github.io/docling/)
 [![PyPI version](https://img.shields.io/pypi/v/docling)](https://pypi.org/project/docling/)
-![Python](https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12-blue)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/docling)](https://pypi.org/project/docling/)
 [![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)](https://python-poetry.org/)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 [![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)

{docling-2.6.0.dist-info → docling-2.7.0.dist-info}/RECORD

@@ -12,19 +12,20 @@ docling/backend/msword_backend.py,sha256=-cCEh4EhdGknHrxiVGFE4GDo_iYpAqP2QxRaeqr
 docling/backend/pdf_backend.py,sha256=unnw7QiRE1VXg6Pj-eYrtnFGrp5SSYiI324OlFxyv6c,2050
 docling/backend/pypdfium2_backend.py,sha256=B4bfv-dfzlWiKTfF8LN5fto_99YBu8A2c1_XIVwRUWI,8996
 docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/cli/main.py,sha256=nxwx4Ro4zKyK4fjiTNROtsGIKGU1opVSqBfNhno6lGQ,10603
+docling/cli/main.py,sha256=MpjbAXhOlbGnAnl5_OaKCdub61YPQBy1NOqroXQtNYE,10722
 docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/datamodel/base_models.py,sha256=6qlwPamDZ3XUsE2kTAyGKG6O2IJClVjCqaE7DZ74KHU,5533
 docling/datamodel/document.py,sha256=9dQf_J18X_MEWs-Mg3Ed6BykFPJ79ETmkkxcssY-vYo,20698
-docling/datamodel/pipeline_options.py,sha256=joR6_aBsZvLmK_K4RaKBLCnc1WZwobLGQRRY64XfPsM,2845
+docling/datamodel/pipeline_options.py,sha256=aC_CmtEhNLIbn9n3JuYhL_aA8UA0vFgw7HcGMUuOI4o,3117
 docling/datamodel/settings.py,sha256=JK8lZPBjUx2kD2q-Qpg-o3vOElADMcyQbRUL0EHZ7us,1263
-docling/document_converter.py,sha256=OaIiJLckHvXC_7DAZ6ZSYg3dJ7QWC5TtO2m4dSS80xI,10922
+docling/document_converter.py,sha256=L0A3g7IQBaKIK7dWpUFC72ZqKywIPYkyh71Qd6DiNPE,10940
 docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/models/base_model.py,sha256=Yq_-FmUhqhE20vXYG3WiQXDRTIPjik1CyuEZ8iYTGAY,701
 docling/models/base_ocr_model.py,sha256=rGSpBF4dByITcsBaRIgvFKpiu0CrhmZS_PHIo686Dw0,6428
 docling/models/ds_glm_model.py,sha256=hBRCx6oFGhxBbKEJlRSWVndDwFtB5IpeLOowFAVqFM0,12033
 docling/models/easyocr_model.py,sha256=c2m4x9dZpSc-cMgeEdFBRVBlB78uMGlYD8Q_2gzRuMU,3734
 docling/models/layout_model.py,sha256=ZvbTSyxvXB5yLHNEti0Wv3trz0vwGuHySI5TCdApb0U,14011
+docling/models/ocr_mac_model.py,sha256=bLP14UUmZcSzjDe-HLj-mtksTuBmsCTg2C1wCxUpan0,4502
 docling/models/page_assemble_model.py,sha256=kSGNiRKhmzkpFH7xCiT3rulMsgJmUXFa6Th_eB-cLEk,7103
 docling/models/page_preprocessing_model.py,sha256=1gVrZjObKxAvXkkKvXnIFApPOggzgiTFPtt1CGbMbSs,2763
 docling/models/table_structure_model.py,sha256=-ANSQpiN2avt3B9sbi7dHcoULUJbMBalAR5xxlrM7To,8421
@@ -33,14 +34,14 @@ docling/models/tesseract_ocr_model.py,sha256=RDf6iV1q-oXaGfZXv0bW6SqjHNKQvBUDlUs
 docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/pipeline/base_pipeline.py,sha256=IF1XWYgUGbdB4-teLkmM4Hvg_UNEfPrGuhExMRTUsk8,7168
 docling/pipeline/simple_pipeline.py,sha256=mZqANqUtAOFAyqQEShErQnAUz6tJFOl6zVoazEDJ_wE,2254
-docling/pipeline/standard_pdf_pipeline.py,sha256=h59eA0CLMYuuJoH-0SyCRkYEregNs6i0pa46Ioqf8kU,7947
+docling/pipeline/standard_pdf_pipeline.py,sha256=btm_y1ZsjUrtWvMbF6RA8BVM0ENrK4z_rqF0jjdeZmU,8473
 docling/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/utils/export.py,sha256=KyGF1BVDHPFfHVXZc8vegsWlFfOgGPP2YckWpTadyI8,4694
 docling/utils/layout_utils.py,sha256=vlN0rc8i0ayRGn3WnaG-pdmqEL00KKGl2zez3Gj-hrk,32074
 docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
 docling/utils/utils.py,sha256=llhXSbIDNZ1MHOwBEfLHBAoJIAYI7QlPIonlI1jLUJ0,1208
-docling-2.6.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.6.0.dist-info/METADATA,sha256=l4Fj3nRKRzZJ2GXWU7c4yLNhIO4NbwdeUofY5MvBPH8,6571
-docling-2.6.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling-2.6.0.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
-docling-2.6.0.dist-info/RECORD,,
+docling-2.7.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.7.0.dist-info/METADATA,sha256=6cpEQMbjK1tKCQ3kkzeOD7URm41HPx2xUSs-gxvlsM4,6761
+docling-2.7.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling-2.7.0.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
+docling-2.7.0.dist-info/RECORD,,