docling 2.15.1__py3-none-any.whl → 2.16.0__py3-none-any.whl

docling/models/tesseract_ocr_model.py

@@ -54,43 +54,56 @@ class TesseractOcrModel(BaseOcrModel):
             # Initialize the tesseractAPI
             _log.debug("Initializing TesserOCR: %s", tesseract_version)
             lang = "+".join(self.options.lang)
+
+            self.script_readers: dict[str, tesserocr.PyTessBaseAPI] = {}
+
+            if any([l.startswith("script/") for l in tesserocr_languages]):
+                self.script_prefix = "script/"
+            else:
+                self.script_prefix = ""
+
+            tesserocr_kwargs = {
+                "psm": tesserocr.PSM.AUTO,
+                "init": True,
+                "oem": tesserocr.OEM.DEFAULT,
+            }
+
             if self.options.path is not None:
+                tesserocr_kwargs["path"] = self.options.path
+
+            if lang == "auto":
                 self.reader = tesserocr.PyTessBaseAPI(
-                    path=self.options.path,
-                    lang=lang,
-                    psm=tesserocr.PSM.AUTO,
-                    init=True,
-                    oem=tesserocr.OEM.DEFAULT,
+                    **{"lang": "osd", "psm": tesserocr.PSM.OSD_ONLY} | tesserocr_kwargs
                 )
             else:
                 self.reader = tesserocr.PyTessBaseAPI(
-                    lang=lang,
-                    psm=tesserocr.PSM.AUTO,
-                    init=True,
-                    oem=tesserocr.OEM.DEFAULT,
+                    **{"lang": lang} | tesserocr_kwargs,
                 )
+
             self.reader_RIL = tesserocr.RIL
 
     def __del__(self):
         if self.reader is not None:
             # Finalize the tesseractAPI
             self.reader.End()
+        for script in self.script_readers:
+            self.script_readers[script].End()
 
     def __call__(
         self, conv_res: ConversionResult, page_batch: Iterable[Page]
     ) -> Iterable[Page]:
-
         if not self.enabled:
             yield from page_batch
             return
 
+        import tesserocr
+
         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"):
-
                     assert self.reader is not None
 
                     ocr_rects = self.get_ocr_rects(page)
@@ -106,20 +119,55 @@ class TesseractOcrModel(BaseOcrModel):
 
                         # Retrieve text snippets with their bounding boxes
                         self.reader.SetImage(high_res_image)
-                        boxes = self.reader.GetComponentImages(
+
+                        if self.options.lang == ["auto"]:
+                            osd = self.reader.DetectOrientationScript()
+
+                            # No text, probably
+                            if osd is None:
+                                continue
+
+                            script = osd["script_name"]
+
+                            if script == "Katakana" or script == "Hiragana":
+                                script = "Japanese"
+                            elif script == "Han":
+                                script = "HanS"
+                            elif script == "Korean":
+                                script = "Hangul"
+
+                            _log.debug(
+                                f'Using model for the detected script "{script}"'
+                            )
+
+                            if script not in self.script_readers:
+                                self.script_readers[script] = tesserocr.PyTessBaseAPI(
+                                    path=self.reader.GetDatapath(),
+                                    lang=f"{self.script_prefix}{script}",
+                                    psm=tesserocr.PSM.AUTO,
+                                    init=True,
+                                    oem=tesserocr.OEM.DEFAULT,
+                                )
+
+                            local_reader = self.script_readers[script]
+                            local_reader.SetImage(high_res_image)
+                        else:
+                            local_reader = self.reader
+
+                        boxes = local_reader.GetComponentImages(
                             self.reader_RIL.TEXTLINE, True
                         )
 
                         cells = []
                         for ix, (im, box, _, _) in enumerate(boxes):
                             # Set the area of interest. Tesseract uses Bottom-Left for the origin
-                            self.reader.SetRectangle(
+                            local_reader.SetRectangle(
                                 box["x"], box["y"], box["w"], box["h"]
                             )
 
                             # Extract text within the bounding box
-                            text = self.reader.GetUTF8Text().strip()
-                            confidence = self.reader.MeanTextConf()
+                            text = local_reader.GetUTF8Text().strip()
+                            confidence = local_reader.MeanTextConf()
                             left = box["x"] / self.scale
                             bottom = box["y"] / self.scale
                             right = (box["x"] + box["w"]) / self.scale

docling/pipeline/base_pipeline.py

@@ -3,7 +3,7 @@ import logging
 import time
 import traceback
 from abc import ABC, abstractmethod
-from typing import Callable, Iterable, List
+from typing import Any, Callable, Iterable, List
 
 from docling_core.types.doc import DoclingDocument, NodeItem
 
@@ -18,7 +18,7 @@ from docling.datamodel.base_models import (
 from docling.datamodel.document import ConversionResult, InputDocument
 from docling.datamodel.pipeline_options import PipelineOptions
 from docling.datamodel.settings import settings
-from docling.models.base_model import BaseEnrichmentModel
+from docling.models.base_model import GenericEnrichmentModel
 from docling.utils.profiling import ProfilingScope, TimeRecorder
 from docling.utils.utils import chunkify
 
@@ -28,8 +28,9 @@ _log = logging.getLogger(__name__)
 class BasePipeline(ABC):
     def __init__(self, pipeline_options: PipelineOptions):
         self.pipeline_options = pipeline_options
+        self.keep_images = False
         self.build_pipe: List[Callable] = []
-        self.enrichment_pipe: List[BaseEnrichmentModel] = []
+        self.enrichment_pipe: List[GenericEnrichmentModel[Any]] = []
 
     def execute(self, in_doc: InputDocument, raises_on_error: bool) -> ConversionResult:
         conv_res = ConversionResult(input=in_doc)
@@ -40,7 +41,7 @@ class BasePipeline(ABC):
                 conv_res, "pipeline_total", scope=ProfilingScope.DOCUMENT
             ):
                 # These steps are building and assembling the structure of the
-                # output DoclingDocument
+                # output DoclingDocument.
                 conv_res = self._build_document(conv_res)
                 conv_res = self._assemble_document(conv_res)
                 # From this stage, all operations should rely only on conv_res.output
@@ -50,6 +51,8 @@ class BasePipeline(ABC):
             conv_res.status = ConversionStatus.FAILURE
             if raises_on_error:
                 raise e
+        finally:
+            self._unload(conv_res)
 
         return conv_res
 
@@ -62,21 +65,22 @@ class BasePipeline(ABC):
 
     def _enrich_document(self, conv_res: ConversionResult) -> ConversionResult:
 
-        def _filter_elements(
-            doc: DoclingDocument, model: BaseEnrichmentModel
+        def _prepare_elements(
+            conv_res: ConversionResult, model: GenericEnrichmentModel[Any]
         ) -> Iterable[NodeItem]:
-            for element, _level in doc.iterate_items():
-                if model.is_processable(doc=doc, element=element):
-                    yield element
+            for doc_element, _level in conv_res.document.iterate_items():
+                prepared_element = model.prepare_element(
+                    conv_res=conv_res, element=doc_element
+                )
+                if prepared_element is not None:
+                    yield prepared_element
 
         with TimeRecorder(conv_res, "doc_enrich", scope=ProfilingScope.DOCUMENT):
             for model in self.enrichment_pipe:
                 for element_batch in chunkify(
-                    _filter_elements(conv_res.document, model),
+                    _prepare_elements(conv_res, model),
                     settings.perf.elements_batch_size,
                 ):
-                    # TODO: currently we assume the element itself is modified, because
-                    # we don't have an interface to save the element back to the document
                     for element in model(
                         doc=conv_res.document, element_batch=element_batch
                     ):  # Must exhaust!
@@ -88,6 +92,9 @@ class BasePipeline(ABC):
     def _determine_status(self, conv_res: ConversionResult) -> ConversionStatus:
         pass
 
+    def _unload(self, conv_res: ConversionResult):
+        pass
+
     @classmethod
     @abstractmethod
     def get_default_options(cls) -> PipelineOptions:
@@ -107,6 +114,10 @@ class BasePipeline(ABC):
 
 class PaginatedPipeline(BasePipeline):  # TODO this is a bad name.
 
+    def __init__(self, pipeline_options: PipelineOptions):
+        super().__init__(pipeline_options)
+        self.keep_backend = False
+
     def _apply_on_pages(
         self, conv_res: ConversionResult, page_batch: Iterable[Page]
     ) -> Iterable[Page]:
@@ -148,7 +159,14 @@ class PaginatedPipeline(BasePipeline):  # TODO this is a bad name.
                     pipeline_pages = self._apply_on_pages(conv_res, init_pages)
 
                     for p in pipeline_pages:  # Must exhaust!
-                        pass
+
+                        # Cleanup cached images
+                        if not self.keep_images:
+                            p._image_cache = {}
+
+                        # Cleanup page backends
+                        if not self.keep_backend and p._backend is not None:
+                            p._backend.unload()
 
                     end_batch_time = time.monotonic()
                     total_elapsed_time += end_batch_time - start_batch_time
@@ -177,10 +195,15 @@ class PaginatedPipeline(BasePipeline):  # TODO this is a bad name.
                 )
                 raise e
 
-            finally:
-                # Always unload the PDF backend, even in case of failure
-                if conv_res.input._backend:
-                    conv_res.input._backend.unload()
+        return conv_res
+
+    def _unload(self, conv_res: ConversionResult) -> ConversionResult:
+        for page in conv_res.pages:
+            if page._backend is not None:
+                page._backend.unload()
+
+        if conv_res.input._backend:
+            conv_res.input._backend.unload()
 
         return conv_res
 

docling/pipeline/standard_pdf_pipeline.py

@@ -18,6 +18,11 @@ from docling.datamodel.pipeline_options import (
     TesseractOcrOptions,
 )
 from docling.models.base_ocr_model import BaseOcrModel
+from docling.models.code_formula_model import CodeFormulaModel, CodeFormulaModelOptions
+from docling.models.document_picture_classifier import (
+    DocumentPictureClassifier,
+    DocumentPictureClassifierOptions,
+)
 from docling.models.ds_glm_model import GlmModel, GlmOptions
 from docling.models.easyocr_model import EasyOcrModel
 from docling.models.layout_model import LayoutModel
@@ -50,7 +55,7 @@ class StandardPdfPipeline(PaginatedPipeline):
         else:
             self.artifacts_path = Path(pipeline_options.artifacts_path)
 
-        keep_images = (
+        self.keep_images = (
             self.pipeline_options.generate_page_images
             or self.pipeline_options.generate_picture_images
             or self.pipeline_options.generate_table_images
@@ -87,13 +92,37 @@ class StandardPdfPipeline(PaginatedPipeline):
                 accelerator_options=pipeline_options.accelerator_options,
             ),
             # Page assemble
-            PageAssembleModel(options=PageAssembleOptions(keep_images=keep_images)),
+            PageAssembleModel(options=PageAssembleOptions()),
         ]
 
         self.enrichment_pipe = [
             # Other models working on `NodeItem` elements in the DoclingDocument
+            # Code Formula Enrichment Model
+            CodeFormulaModel(
+                enabled=pipeline_options.do_code_enrichment
+                or pipeline_options.do_formula_enrichment,
+                artifacts_path=pipeline_options.artifacts_path,
+                options=CodeFormulaModelOptions(
+                    do_code_enrichment=pipeline_options.do_code_enrichment,
+                    do_formula_enrichment=pipeline_options.do_formula_enrichment,
+                ),
+                accelerator_options=pipeline_options.accelerator_options,
+            ),
+            # Document Picture Classifier
+            DocumentPictureClassifier(
+                enabled=pipeline_options.do_picture_classification,
+                artifacts_path=pipeline_options.artifacts_path,
+                options=DocumentPictureClassifierOptions(),
+                accelerator_options=pipeline_options.accelerator_options,
+            ),
         ]
 
+        if (
+            self.pipeline_options.do_formula_enrichment
+            or self.pipeline_options.do_code_enrichment
+        ):
+            self.keep_backend = True
+
     @staticmethod
     def download_models_hf(
         local_dir: Optional[Path] = None, force: bool = False

docling/utils/glm_utils.py

@@ -270,7 +270,6 @@ def to_docling_document(doc_glm, update_name_label=False) -> DoclingDocument:
             container_el = doc.add_group(label=group_label)
 
             _add_child_elements(container_el, doc, obj, pelem)
-
         elif "text" in obj:
             text = obj["text"][span_i:span_j]
 
@@ -304,6 +303,10 @@ def to_docling_document(doc_glm, update_name_label=False) -> DoclingDocument:
                 current_list = None
 
                 doc.add_heading(text=text, prov=prov)
+            elif label == DocItemLabel.CODE:
+                current_list = None
+
+                doc.add_code(text=text, prov=prov)
             else:
                 current_list = None
 

docling/utils/visualization.py

@@ -0,0 +1,80 @@
+from docling_core.types.doc import DocItemLabel
+from PIL import Image, ImageDraw, ImageFont
+from PIL.ImageFont import FreeTypeFont
+
+from docling.datamodel.base_models import Cluster
+
+
+def draw_clusters(
+    image: Image.Image, clusters: list[Cluster], scale_x: float, scale_y: float
+) -> None:
+    """
+    Draw clusters on an image
+    """
+    draw = ImageDraw.Draw(image, "RGBA")
+    # Create a smaller font for the labels
+    font: ImageFont.ImageFont | FreeTypeFont
+    try:
+        font = ImageFont.truetype("arial.ttf", 12)
+    except OSError:
+        # Fallback to default font if arial is not available
+        font = ImageFont.load_default()
+    for c_tl in clusters:
+        all_clusters = [c_tl, *c_tl.children]
+        for c in all_clusters:
+            # Draw cells first (underneath)
+            cell_color = (0, 0, 0, 40)  # Transparent black for cells
+            for tc in c.cells:
+                cx0, cy0, cx1, cy1 = tc.bbox.as_tuple()
+                cx0 *= scale_x
+                cx1 *= scale_x
+                cy0 *= scale_x
+                cy1 *= scale_y
+
+                draw.rectangle(
+                    [(cx0, cy0), (cx1, cy1)],
+                    outline=None,
+                    fill=cell_color,
+                )
+            # Draw cluster rectangle
+            x0, y0, x1, y1 = c.bbox.as_tuple()
+            x0 *= scale_x
+            x1 *= scale_x
+            y0 *= scale_x
+            y1 *= scale_y
+
+            cluster_fill_color = (*list(DocItemLabel.get_color(c.label)), 70)
+            cluster_outline_color = (
+                *list(DocItemLabel.get_color(c.label)),
+                255,
+            )
+            draw.rectangle(
+                [(x0, y0), (x1, y1)],
+                outline=cluster_outline_color,
+                fill=cluster_fill_color,
+            )
+            # Add label name and confidence
+            label_text = f"{c.label.name} ({c.confidence:.2f})"
+            # Create semi-transparent background for text
+            text_bbox = draw.textbbox((x0, y0), label_text, font=font)
+            text_bg_padding = 2
+            draw.rectangle(
+                [
+                    (
+                        text_bbox[0] - text_bg_padding,
+                        text_bbox[1] - text_bg_padding,
+                    ),
+                    (
+                        text_bbox[2] + text_bg_padding,
+                        text_bbox[3] + text_bg_padding,
+                    ),
+                ],
+                fill=(255, 255, 255, 180),  # Semi-transparent white
+            )
+            # Draw text
+            draw.text(
+                (x0, y0),
+                label_text,
+                fill=(0, 0, 0, 255),  # Solid black
+                font=font,
+            )

{docling-2.15.1.dist-info → docling-2.16.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.15.1
+Version: 2.16.0
 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
@@ -26,9 +26,9 @@ Provides-Extra: tesserocr
 Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
 Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: deepsearch-glm (>=1.0.0,<2.0.0)
-Requires-Dist: docling-core[chunking] (>=2.13.1,<3.0.0)
-Requires-Dist: docling-ibm-models (>=3.1.0,<4.0.0)
-Requires-Dist: docling-parse (>=3.0.0,<4.0.0)
+Requires-Dist: docling-core[chunking] (>=2.15.1,<3.0.0)
+Requires-Dist: docling-ibm-models (>=3.3.0,<4.0.0)
+Requires-Dist: docling-parse (>=3.1.0,<4.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)
 Requires-Dist: filetype (>=1.2.0,<2.0.0)
 Requires-Dist: huggingface_hub (>=0.23,<1)
@@ -39,6 +39,7 @@ Requires-Dist: onnxruntime (>=1.7.0,<1.20.0) ; (python_version < "3.10") and (ex
 Requires-Dist: onnxruntime (>=1.7.0,<2.0.0) ; (python_version >= "3.10") and (extra == "rapidocr")
 Requires-Dist: openpyxl (>=3.1.5,<4.0.0)
 Requires-Dist: pandas (>=2.1.4,<3.0.0)
+Requires-Dist: pillow (>=10.0.0,<11.0.0)
 Requires-Dist: pydantic (>=2.0.0,<3.0.0)
 Requires-Dist: pydantic-settings (>=2.3.0,<3.0.0)
 Requires-Dist: pypdfium2 (>=4.30.0,<5.0.0)

docling-2.16.0.dist-info/RECORD

@@ -0,0 +1,61 @@
+docling/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/backend/abstract_backend.py,sha256=1lNxzwDTn303aXduPDVmTyXn-5ZIoWMLYqNxANGWmQQ,1658
+docling/backend/asciidoc_backend.py,sha256=zyHxlG_BvlLwvpdNca3P6aopxOJZw8wbDFkJQQknNXk,14050
+docling/backend/docling_parse_backend.py,sha256=hEEJibI1oJS0LAnFoIs6gMshS3bCqGtVxHnDNvBGZuA,7649
+docling/backend/docling_parse_v2_backend.py,sha256=IpwrBrtLGwNRl5AYO-o3NjEfNRsAkuMhzvDt2HXb9Ko,8655
+docling/backend/html_backend.py,sha256=vUEfx0h24gEaHO2taQyWNs8zCkDox7kopEeMbWBXss0,15560
+docling/backend/json/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/backend/json/docling_json_backend.py,sha256=LlFMVoZrrCfVwbDuRbNN4Xg96Lujh4xxrTBt9jGhY9I,1984
+docling/backend/md_backend.py,sha256=ajEooDWNnWPHnPQMgUDh-K44Ch1X-sTBHqa1xBp7yJs,14645
+docling/backend/msexcel_backend.py,sha256=lyJc4ShJGAN2ZfNTTuhdYTF-44cZsGyn_8Djstp3IEU,12700
+docling/backend/mspowerpoint_backend.py,sha256=kOGawhcn0BFq4M_C6kW0mY8vMIB24_6R6q6GaszbSt0,15957
+docling/backend/msword_backend.py,sha256=WcQmRYmpH8o2snGoWGxNRkCtUI3mf2JL3-9CxAfDAJg,19232
+docling/backend/pdf_backend.py,sha256=17Pr8dWsD1C4FYUprrwMM9trDGW-JYLjrcScx1Ul4io,2048
+docling/backend/pypdfium2_backend.py,sha256=QSPfp903ZtSpoNqPmcIek0HmvETrJ1kkwrdxnF5pjS0,9014
+docling/backend/xml/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/backend/xml/pubmed_backend.py,sha256=LMnpowjnxa5SydfNC00Ll840BYraL8dCJu-FfC9iSKk,20447
+docling/backend/xml/uspto_backend.py,sha256=2YsnB-WRARIAaHPL6gxHePP24GQGi-Up2_K8ZapD3k4,70974
+docling/chunking/__init__.py,sha256=h83TDs0AuOV6oEPLAPrn9dpGKiU-2Vg6IRNo4cv6GDA,346
+docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/cli/main.py,sha256=NR7NEt8Sf3FE9D7sHpEmABM9mFMTMO5w0VPwYIIvVsk,15481
+docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/datamodel/base_models.py,sha256=vewP1X99qfAwiUsiC2m8CBDGiQPsGyp_WkKJHYPoYn4,7026
+docling/datamodel/document.py,sha256=R748mLCFai4MeiE8ougQrQVJF_16t3f4CUrrEes5AV0,13202
+docling/datamodel/pipeline_options.py,sha256=GA5LwywfOkcBDvG2LhDHikqDQYlFlUPJa93tPSx-vFw,7820
+docling/datamodel/settings.py,sha256=Sw0rN_f8rdLV1eNvVeKiyET2Oe6oz9jtW3lJzniW9Do,1302
+docling/document_converter.py,sha256=qtYPEkWuMUUGmFko2in38iSHdYrjAFf_GHNoXRRvEVs,12631
+docling/exceptions.py,sha256=-FoP46rFJgz_jn5uDv2V052udEEg8gckk6uhoItchXc,85
+docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/models/base_model.py,sha256=H5X-exVaAN-XMTzxpgUc-rwH-D8Uk7-VuZtq2soNGXI,2567
+docling/models/base_ocr_model.py,sha256=YiUMvdjnHw9SHjnfJKT5INrPMoIGEf_Z2OApfl_VRTE,6919
+docling/models/code_formula_model.py,sha256=bOIKJvckZ0QpnDZ-CDiYv-CvuGvaGzJgp2PiYAidKBQ,8422
+docling/models/document_picture_classifier.py,sha256=RLB80ueqWZ86hdXtTKmSynCU13nT-T10vUp2sky9110,6078
+docling/models/ds_glm_model.py,sha256=CkhsP0cEWwm4wb1g3cLFriVGpVtELiUK3REDMkPwAMw,13028
+docling/models/easyocr_model.py,sha256=Kakb20ioBxDmNsIqoGvSSs_vbqAWN3QQNHYtEi-eErg,4990
+docling/models/layout_model.py,sha256=3Fw7OM6g0j7NgItKsQOgFOCd1q6lp1DacN_db7f6QCw,6090
+docling/models/ocr_mac_model.py,sha256=bLP14UUmZcSzjDe-HLj-mtksTuBmsCTg2C1wCxUpan0,4502
+docling/models/page_assemble_model.py,sha256=c5KLKwkUIdW0JcDHizWsqrpb5x_3DK28x82Q8o-3VJM,5968
+docling/models/page_preprocessing_model.py,sha256=1gVrZjObKxAvXkkKvXnIFApPOggzgiTFPtt1CGbMbSs,2763
+docling/models/rapid_ocr_model.py,sha256=LOIvczJs3_db2o8mtrKk-pIXgC-xqWqRLu2cjA3wvy4,4980
+docling/models/table_structure_model.py,sha256=fUpCHthO4Uk3BhA99a85BHBm51fmdE9kfqhAk3WjuBw,9392
+docling/models/tesseract_ocr_cli_model.py,sha256=FP9cnSkSyj6-EETHtabV720Fr3x9K_oBP2UuJi4VUwE,6621
+docling/models/tesseract_ocr_model.py,sha256=N27xjo8aPb5x276wKHkf_6VFwJObfosdHLo5_hCuf94,8055
+docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/pipeline/base_pipeline.py,sha256=J0ZjtincsJr-BbRgqoQozxIhDWxWFlWaS9CTPwypJFk,8621
+docling/pipeline/simple_pipeline.py,sha256=mZqANqUtAOFAyqQEShErQnAUz6tJFOl6zVoazEDJ_wE,2254
+docling/pipeline/standard_pdf_pipeline.py,sha256=Qefg1JSiFwipypi8TZPJ50WgXTLjwkC0wvYAl02RM2o,10480
+docling/py.typed,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+docling/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/utils/accelerator_utils.py,sha256=ZjULCn-qhxqx3frF-rJmAlWdzqgUMxH5utLHbSPev80,1367
+docling/utils/export.py,sha256=KyGF1BVDHPFfHVXZc8vegsWlFfOgGPP2YckWpTadyI8,4694
+docling/utils/glm_utils.py,sha256=Nfxdx0W-sl1owYncTeJmZdiPcn-jpTqK8f8TeQlDOMY,11683
+docling/utils/layout_postprocessor.py,sha256=urRzeF9PrKiMBvA6DdHHwyLxG06CMhelgJeV5B1l6l0,24258
+docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
+docling/utils/utils.py,sha256=llhXSbIDNZ1MHOwBEfLHBAoJIAYI7QlPIonlI1jLUJ0,1208
+docling/utils/visualization.py,sha256=4pn-80fVuE04ken7hUg5Ar47ndRSL9MWBgdHM-1g1zU,2735
+docling-2.16.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.16.0.dist-info/METADATA,sha256=wJgRO2R9Szl69jFE8gj-VGIBpkwwMWPfgytz9nDsT_E,7780
+docling-2.16.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling-2.16.0.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
+docling-2.16.0.dist-info/RECORD,,

docling-2.15.1.dist-info/RECORD

@@ -1,56 +0,0 @@
-docling/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/backend/abstract_backend.py,sha256=-or6kWVV7egQeyIuN-vI0Tr7Q1htalBZSlhgq_G2RdU,1678
-docling/backend/asciidoc_backend.py,sha256=kXZxOLk_LvLFVZwnJVVwjmvc3QWZ0iiG7VnwjgtC3hI,14051
-docling/backend/docling_parse_backend.py,sha256=cJLkuOmfCtshRrwsv7WWayRNeMQASZv76v3nUHucqgM,7636
-docling/backend/docling_parse_v2_backend.py,sha256=-lLsorxhK_Awrql_zXPen2LX0Gt9UvcDLMcmXf7_LKc,8642
-docling/backend/html_backend.py,sha256=O8qXaw7MzOIdaxbBcjHieM9Ce4GEdtBj9YW0vpJspuA,15560
-docling/backend/md_backend.py,sha256=tmuSCghjor9PqKIiVieCuZ4_t5JEjZMy3cq7u3yTgyU,14032
-docling/backend/msexcel_backend.py,sha256=23qUEScqr5GhY06xiqg-eBQ_JlAqO0FkPEmX6554sVA,12040
-docling/backend/mspowerpoint_backend.py,sha256=kOGawhcn0BFq4M_C6kW0mY8vMIB24_6R6q6GaszbSt0,15957
-docling/backend/msword_backend.py,sha256=K1D_h0ulLA6KQsPe62327cDVkQqV1f7EetCHo66wCKw,19233
-docling/backend/pdf_backend.py,sha256=unnw7QiRE1VXg6Pj-eYrtnFGrp5SSYiI324OlFxyv6c,2050
-docling/backend/pypdfium2_backend.py,sha256=Exb3NBp3x2YSLoNfmXq4NefShgooJXsxTXrJ4JbTzcc,9001
-docling/backend/xml/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/backend/xml/pubmed_backend.py,sha256=LMnpowjnxa5SydfNC00Ll840BYraL8dCJu-FfC9iSKk,20447
-docling/backend/xml/uspto_backend.py,sha256=2YsnB-WRARIAaHPL6gxHePP24GQGi-Up2_K8ZapD3k4,70974
-docling/chunking/__init__.py,sha256=h83TDs0AuOV6oEPLAPrn9dpGKiU-2Vg6IRNo4cv6GDA,346
-docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/cli/main.py,sha256=NR7NEt8Sf3FE9D7sHpEmABM9mFMTMO5w0VPwYIIvVsk,15481
-docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/datamodel/base_models.py,sha256=50Jf5zk9c4-zmnOzZLoPBnHQhTX0_OFQzIkKgnKK1o4,6229
-docling/datamodel/document.py,sha256=OHM6bm0a-62xnAZ8DFlMHzATmbgNcfMxQoQO2udaW5Q,13071
-docling/datamodel/pipeline_options.py,sha256=wKFzw8sAim6emQGsjuS12n7FfpMo8HVNoMOPhkXTkVo,7734
-docling/datamodel/settings.py,sha256=Sw0rN_f8rdLV1eNvVeKiyET2Oe6oz9jtW3lJzniW9Do,1302
-docling/document_converter.py,sha256=_pk0sHuPXJ14NEutatf5bK2VyNiU5cvYsVbh1HIgrIw,12431
-docling/exceptions.py,sha256=-FoP46rFJgz_jn5uDv2V052udEEg8gckk6uhoItchXc,85
-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=YiUMvdjnHw9SHjnfJKT5INrPMoIGEf_Z2OApfl_VRTE,6919
-docling/models/ds_glm_model.py,sha256=CkhsP0cEWwm4wb1g3cLFriVGpVtELiUK3REDMkPwAMw,13028
-docling/models/easyocr_model.py,sha256=Kakb20ioBxDmNsIqoGvSSs_vbqAWN3QQNHYtEi-eErg,4990
-docling/models/layout_model.py,sha256=Xo8sclRTOO_V8Cr4RwuxB67vSWKF0LZ5nJRYU1WI--k,9063
-docling/models/ocr_mac_model.py,sha256=bLP14UUmZcSzjDe-HLj-mtksTuBmsCTg2C1wCxUpan0,4502
-docling/models/page_assemble_model.py,sha256=qdEX0AIb76ZOqJV6O9j-7r67WmuIkUlwbb2PsL7eFK4,7608
-docling/models/page_preprocessing_model.py,sha256=1gVrZjObKxAvXkkKvXnIFApPOggzgiTFPtt1CGbMbSs,2763
-docling/models/rapid_ocr_model.py,sha256=LOIvczJs3_db2o8mtrKk-pIXgC-xqWqRLu2cjA3wvy4,4980
-docling/models/table_structure_model.py,sha256=fUpCHthO4Uk3BhA99a85BHBm51fmdE9kfqhAk3WjuBw,9392
-docling/models/tesseract_ocr_cli_model.py,sha256=aKQBaty4cYu6zG_C5uy6Zm3eeRQo5fxIierbKixa2kc,6622
-docling/models/tesseract_ocr_model.py,sha256=RDf6iV1q-oXaGfZXv0bW6SqjHNKQvBUDlUsOkuz0neY,6095
-docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/pipeline/base_pipeline.py,sha256=W1HgNp0vPp8vVY0vTX47Xe4m7j0lWT8XroCkTx5PyMw,7949
-docling/pipeline/simple_pipeline.py,sha256=mZqANqUtAOFAyqQEShErQnAUz6tJFOl6zVoazEDJ_wE,2254
-docling/pipeline/standard_pdf_pipeline.py,sha256=iXjVLy-9q82jrU_0AZTkbz3ccrqz4WiRLYD-epxG5BQ,9174
-docling/py.typed,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-docling/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/utils/accelerator_utils.py,sha256=ZjULCn-qhxqx3frF-rJmAlWdzqgUMxH5utLHbSPev80,1367
-docling/utils/export.py,sha256=KyGF1BVDHPFfHVXZc8vegsWlFfOgGPP2YckWpTadyI8,4694
-docling/utils/glm_utils.py,sha256=IB19wToGath97gD3jAA3G_rQSptnZKhQCWLvPUCnkww,11551
-docling/utils/layout_postprocessor.py,sha256=urRzeF9PrKiMBvA6DdHHwyLxG06CMhelgJeV5B1l6l0,24258
-docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
-docling/utils/utils.py,sha256=llhXSbIDNZ1MHOwBEfLHBAoJIAYI7QlPIonlI1jLUJ0,1208
-docling-2.15.1.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.15.1.dist-info/METADATA,sha256=6WRzA633us43nw7RHwhX_jwizh2JSpGWxNh0pJq2ZYs,7739
-docling-2.15.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling-2.15.1.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
-docling-2.15.1.dist-info/RECORD,,