docling 2.0.0__py3-none-any.whl → 2.2.0__py3-none-any.whl

docling/models/table_structure_model.py

@@ -71,92 +71,101 @@ class TableStructureModel(BasePageModel):
 
         for page in page_batch:
             assert page._backend is not None
-            assert page.predictions.layout is not None
-            assert page.size is not None
-
-            page.predictions.tablestructure = TableStructurePrediction()  # dummy
-
-            in_tables = [
-                (
-                    cluster,
-                    [
-                        round(cluster.bbox.l) * self.scale,
-                        round(cluster.bbox.t) * self.scale,
-                        round(cluster.bbox.r) * self.scale,
-                        round(cluster.bbox.b) * self.scale,
-                    ],
-                )
-                for cluster in page.predictions.layout.clusters
-                if cluster.label == DocItemLabel.TABLE
-            ]
-            if not len(in_tables):
+            if not page._backend.is_valid():
                 yield page
-                continue
-
-            tokens = []
-            for c in page.cells:
-                for cluster, _ in in_tables:
-                    if c.bbox.area() > 0:
-                        if (
-                            c.bbox.intersection_area_with(cluster.bbox) / c.bbox.area()
-                            > 0.2
-                        ):
-                            # Only allow non empty stings (spaces) into the cells of a table
-                            if len(c.text.strip()) > 0:
-                                new_cell = copy.deepcopy(c)
-                                new_cell.bbox = new_cell.bbox.scaled(scale=self.scale)
-
-                                tokens.append(new_cell.model_dump())
-
-            page_input = {
-                "tokens": tokens,
-                "width": page.size.width * self.scale,
-                "height": page.size.height * self.scale,
-            }
-            page_input["image"] = numpy.asarray(page.get_image(scale=self.scale))
-
-            table_clusters, table_bboxes = zip(*in_tables)
-
-            if len(table_bboxes):
-                tf_output = self.tf_predictor.multi_table_predict(
-                    page_input, table_bboxes, do_matching=self.do_cell_matching
-                )
-
-                for table_cluster, table_out in zip(table_clusters, tf_output):
-                    table_cells = []
-                    for element in table_out["tf_responses"]:
-
-                        if not self.do_cell_matching:
-                            the_bbox = BoundingBox.model_validate(
-                                element["bbox"]
-                            ).scaled(1 / self.scale)
-                            text_piece = page._backend.get_text_in_rect(the_bbox)
-                            element["bbox"]["token"] = text_piece
-
-                        tc = TableCell.model_validate(element)
-                        if self.do_cell_matching and tc.bbox is not None:
-                            tc.bbox = tc.bbox.scaled(1 / self.scale)
-                        table_cells.append(tc)
-
-                    # Retrieving cols/rows, after post processing:
-                    num_rows = table_out["predict_details"]["num_rows"]
-                    num_cols = table_out["predict_details"]["num_cols"]
-                    otsl_seq = table_out["predict_details"]["prediction"]["rs_seq"]
-
-                    tbl = Table(
-                        otsl_seq=otsl_seq,
-                        table_cells=table_cells,
-                        num_rows=num_rows,
-                        num_cols=num_cols,
-                        id=table_cluster.id,
-                        page_no=page.page_no,
-                        cluster=table_cluster,
-                        label=DocItemLabel.TABLE,
+            else:
+
+                assert page.predictions.layout is not None
+                assert page.size is not None
+
+                page.predictions.tablestructure = TableStructurePrediction()  # dummy
+
+                in_tables = [
+                    (
+                        cluster,
+                        [
+                            round(cluster.bbox.l) * self.scale,
+                            round(cluster.bbox.t) * self.scale,
+                            round(cluster.bbox.r) * self.scale,
+                            round(cluster.bbox.b) * self.scale,
+                        ],
+                    )
+                    for cluster in page.predictions.layout.clusters
+                    if cluster.label == DocItemLabel.TABLE
+                ]
+                if not len(in_tables):
+                    yield page
+                    continue
+
+                tokens = []
+                for c in page.cells:
+                    for cluster, _ in in_tables:
+                        if c.bbox.area() > 0:
+                            if (
+                                c.bbox.intersection_area_with(cluster.bbox)
+                                / c.bbox.area()
+                                > 0.2
+                            ):
+                                # Only allow non empty stings (spaces) into the cells of a table
+                                if len(c.text.strip()) > 0:
+                                    new_cell = copy.deepcopy(c)
+                                    new_cell.bbox = new_cell.bbox.scaled(
+                                        scale=self.scale
+                                    )
+
+                                    tokens.append(new_cell.model_dump())
+
+                page_input = {
+                    "tokens": tokens,
+                    "width": page.size.width * self.scale,
+                    "height": page.size.height * self.scale,
+                }
+                page_input["image"] = numpy.asarray(page.get_image(scale=self.scale))
+
+                table_clusters, table_bboxes = zip(*in_tables)
+
+                if len(table_bboxes):
+                    tf_output = self.tf_predictor.multi_table_predict(
+                        page_input, table_bboxes, do_matching=self.do_cell_matching
                     )
 
-                    page.predictions.tablestructure.table_map[table_cluster.id] = tbl
-
-                # For debugging purposes:
-                # self.draw_table_and_cells(page, page.predictions.tablestructure.table_map.values())
+                    for table_cluster, table_out in zip(table_clusters, tf_output):
+                        table_cells = []
+                        for element in table_out["tf_responses"]:
+
+                            if not self.do_cell_matching:
+                                the_bbox = BoundingBox.model_validate(
+                                    element["bbox"]
+                                ).scaled(1 / self.scale)
+                                text_piece = page._backend.get_text_in_rect(the_bbox)
+                                element["bbox"]["token"] = text_piece
+
+                            tc = TableCell.model_validate(element)
+                            if self.do_cell_matching and tc.bbox is not None:
+                                tc.bbox = tc.bbox.scaled(1 / self.scale)
+                            table_cells.append(tc)
+
+                        # Retrieving cols/rows, after post processing:
+                        num_rows = table_out["predict_details"]["num_rows"]
+                        num_cols = table_out["predict_details"]["num_cols"]
+                        otsl_seq = table_out["predict_details"]["prediction"]["rs_seq"]
+
+                        tbl = Table(
+                            otsl_seq=otsl_seq,
+                            table_cells=table_cells,
+                            num_rows=num_rows,
+                            num_cols=num_cols,
+                            id=table_cluster.id,
+                            page_no=page.page_no,
+                            cluster=table_cluster,
+                            label=DocItemLabel.TABLE,
+                        )
+
+                        page.predictions.tablestructure.table_map[table_cluster.id] = (
+                            tbl
+                        )
+
+                    # For debugging purposes:
+                    # self.draw_table_and_cells(page, page.predictions.tablestructure.table_map.values())
 
-            yield page
+                yield page

docling/models/tesseract_ocr_cli_model.py

@@ -110,61 +110,65 @@ class TesseractOcrCliModel(BaseOcrModel):
 
         for page in page_batch:
             assert page._backend is not None
+            if not page._backend.is_valid():
+                yield page
+            else:
+                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
+                    )
 
-            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)
-
-                    df = self._run_tesseract(fname)
-
-                # _log.info(df)
-
-                # Print relevant columns (bounding box and text)
-                for ix, row in df.iterrows():
-                    text = row["text"]
-                    conf = row["conf"]
-
-                    l = float(row["left"])
-                    b = float(row["top"])
-                    w = float(row["width"])
-                    h = float(row["height"])
-
-                    t = b + h
-                    r = l + w
-
-                    cell = OcrCell(
-                        id=ix,
-                        text=text,
-                        confidence=conf / 100.0,
-                        bbox=BoundingBox.from_tuple(
-                            coord=(
-                                (l / self.scale) + ocr_rect.l,
-                                (b / self.scale) + ocr_rect.t,
-                                (r / self.scale) + ocr_rect.l,
-                                (t / self.scale) + ocr_rect.t,
+                    with tempfile.NamedTemporaryFile(
+                        suffix=".png", mode="w"
+                    ) as image_file:
+                        fname = image_file.name
+                        high_res_image.save(fname)
+
+                        df = self._run_tesseract(fname)
+
+                    # _log.info(df)
+
+                    # Print relevant columns (bounding box and text)
+                    for ix, row in df.iterrows():
+                        text = row["text"]
+                        conf = row["conf"]
+
+                        l = float(row["left"])
+                        b = float(row["top"])
+                        w = float(row["width"])
+                        h = float(row["height"])
+
+                        t = b + h
+                        r = l + w
+
+                        cell = OcrCell(
+                            id=ix,
+                            text=text,
+                            confidence=conf / 100.0,
+                            bbox=BoundingBox.from_tuple(
+                                coord=(
+                                    (l / self.scale) + ocr_rect.l,
+                                    (b / self.scale) + ocr_rect.t,
+                                    (r / self.scale) + ocr_rect.l,
+                                    (t / self.scale) + ocr_rect.t,
+                                ),
+                                origin=CoordOrigin.TOPLEFT,
                             ),
-                            origin=CoordOrigin.TOPLEFT,
-                        ),
-                    )
-                    all_ocr_cells.append(cell)
+                        )
+                        all_ocr_cells.append(cell)
 
-            ## Remove OCR cells which overlap with programmatic cells.
-            filtered_ocr_cells = self.filter_ocr_cells(all_ocr_cells, page.cells)
+                ## Remove OCR cells which overlap with programmatic cells.
+                filtered_ocr_cells = self.filter_ocr_cells(all_ocr_cells, page.cells)
 
-            page.cells.extend(filtered_ocr_cells)
+                page.cells.extend(filtered_ocr_cells)
 
-            # DEBUG code:
-            # self.draw_ocr_rects_and_cells(page, ocr_rects)
+                # DEBUG code:
+                # self.draw_ocr_rects_and_cells(page, ocr_rects)
 
-            yield page
+                yield page

docling/models/tesseract_ocr_model.py

@@ -69,57 +69,62 @@ class TesseractOcrModel(BaseOcrModel):
 
         for page in page_batch:
             assert page._backend is not None
-            assert self.reader is not None
+            if not page._backend.is_valid():
+                yield page
+            else:
+                assert self.reader is not None
 
-            ocr_rects = self.get_ocr_rects(page)
+                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
-                )
+                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
+                    )
 
-                # Retrieve text snippets with their bounding boxes
-                self.reader.SetImage(high_res_image)
-                boxes = self.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(box["x"], box["y"], box["w"], box["h"])
-
-                    # Extract text within the bounding box
-                    text = self.reader.GetUTF8Text().strip()
-                    confidence = self.reader.MeanTextConf()
-                    left = box["x"] / self.scale
-                    bottom = box["y"] / self.scale
-                    right = (box["x"] + box["w"]) / self.scale
-                    top = (box["y"] + box["h"]) / self.scale
-
-                    cells.append(
-                        OcrCell(
-                            id=ix,
-                            text=text,
-                            confidence=confidence,
-                            bbox=BoundingBox.from_tuple(
-                                coord=(left, top, right, bottom),
-                                origin=CoordOrigin.TOPLEFT,
-                            ),
-                        )
+                    # Retrieve text snippets with their bounding boxes
+                    self.reader.SetImage(high_res_image)
+                    boxes = self.reader.GetComponentImages(
+                        self.reader_RIL.TEXTLINE, True
                     )
 
-                # del high_res_image
-                all_ocr_cells.extend(cells)
+                    cells = []
+                    for ix, (im, box, _, _) in enumerate(boxes):
+                        # Set the area of interest. Tesseract uses Bottom-Left for the origin
+                        self.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()
+                        left = box["x"] / self.scale
+                        bottom = box["y"] / self.scale
+                        right = (box["x"] + box["w"]) / self.scale
+                        top = (box["y"] + box["h"]) / 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)
 
-            ## Remove OCR cells which overlap with programmatic cells.
-            filtered_ocr_cells = self.filter_ocr_cells(all_ocr_cells, page.cells)
+                ## Remove OCR cells which overlap with programmatic cells.
+                filtered_ocr_cells = self.filter_ocr_cells(all_ocr_cells, page.cells)
 
-            page.cells.extend(filtered_ocr_cells)
+                page.cells.extend(filtered_ocr_cells)
 
-            # DEBUG code:
-            # self.draw_ocr_rects_and_cells(page, ocr_rects)
+                # DEBUG code:
+                # self.draw_ocr_rects_and_cells(page, ocr_rects)
 
-            yield page
+                yield page

docling/pipeline/standard_pdf_pipeline.py

@@ -134,13 +134,13 @@ class StandardPdfPipeline(PaginatedPipeline):
         all_body = []
 
         for p in conv_res.pages:
-            assert p.assembled is not None
-            for el in p.assembled.body:
-                all_body.append(el)
-            for el in p.assembled.headers:
-                all_headers.append(el)
-            for el in p.assembled.elements:
-                all_elements.append(el)
+            if p.assembled is not None:
+                for el in p.assembled.body:
+                    all_body.append(el)
+                for el in p.assembled.headers:
+                    all_headers.append(el)
+                for el in p.assembled.elements:
+                    all_elements.append(el)
 
         conv_res.assembled = AssembledUnit(
             elements=all_elements, headers=all_headers, body=all_body

{docling-2.0.0.dist-info → docling-2.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.0.0
+Version: 2.2.0
 Summary: Docling PDF conversion package
 Home-page: https://github.com/DS4SD/docling
 License: MIT
@@ -22,13 +22,14 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Provides-Extra: tesserocr
 Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
 Requires-Dist: certifi (>=2024.7.4)
-Requires-Dist: deepsearch-glm (>=0.25.0,<0.26.0)
-Requires-Dist: docling-core (>=2.0.0,<3.0.0)
+Requires-Dist: deepsearch-glm (>=0.26.1,<0.27.0)
+Requires-Dist: docling-core (>=2.1.0,<3.0.0)
 Requires-Dist: docling-ibm-models (>=2.0.1,<3.0.0)
-Requires-Dist: docling-parse (>=1.6.0,<2.0.0)
+Requires-Dist: docling-parse (>=2.0.0,<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: pandas (>=2.1.4,<3.0.0)
 Requires-Dist: pyarrow (>=16.1.0,<17.0.0)
 Requires-Dist: pydantic (>=2.0.0,<3.0.0)
@@ -50,7 +51,7 @@ Description-Content-Type: text/markdown
 
 <p align="center">
   <a href="https://github.com/ds4sd/docling">
-    <img loading="lazy" alt="Docling" src="https://github.com/DS4SD/docling/raw/main/docs/assets/logo.png" width="150" />
+    <img loading="lazy" alt="Docling" src="https://github.com/DS4SD/docling/raw/main/docs/assets/docling_processing.png" width="100%"/>
   </a>
 </p>
 
@@ -69,6 +70,7 @@ Description-Content-Type: text/markdown
 
 Docling parses documents and exports them to the desired format with ease and speed.
 
+
 ## Features
 
 * 🗂️ Multi-format support for input (PDF, DOCX etc.) & output (Markdown, JSON etc.)
@@ -94,16 +96,15 @@ More [detailed installation instructions](https://ds4sd.github.io/docling/instal
 
 ## Getting started
 
-To convert invidual documents, use `convert()`, for example:
+To convert individual documents, use `convert()`, for example:
 
 ```python
 from docling.document_converter import DocumentConverter
 
-source = "https://arxiv.org/pdf/2408.09869"  # PDF path or URL
+source = "https://arxiv.org/pdf/2408.09869"  # document per local path or URL
 converter = DocumentConverter()
 result = converter.convert(source)
 print(result.document.export_to_markdown())  # output: "## Docling Technical Report[...]"
-print(result.document.export_to_document_tokens())  # output: "<document><title><page_1><loc_20>..."
 ```
 
 
@@ -144,6 +145,6 @@ If you use Docling in your projects, please consider citing the following:
 
 ## License
 
-The Docling codebase is under MIT license.
+The Docling codebase is under MIT license. 
 For individual model usage, please refer to the model licenses found in the original packages.
 

docling-2.2.0.dist-info/RECORD

@@ -0,0 +1,44 @@
+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=WW0eIanPIObcg5ci9YcnqFxwipmqRFsRY8zjZDdKvJA,14116
+docling/backend/docling_parse_backend.py,sha256=TaIMli9vePd3fz9L6S4t75JPYZDpgYBLRGfWjbc9Hbk,7632
+docling/backend/docling_parse_v2_backend.py,sha256=QlVU8NgqKvVCa99E8oDa2Xvy__kq30C-myGY3o9Qoq4,8588
+docling/backend/html_backend.py,sha256=wfh5PWEwoqsCXxFCQbFBdJvEtlqZhXgqfPfTYETWHfE,14974
+docling/backend/md_backend.py,sha256=osYiNLnep9UgLq8mUH9bmwG3kP9RXxt69I8LlyeJN6g,11505
+docling/backend/mspowerpoint_backend.py,sha256=J472AIH_IXvGg3D0FDmXhue1At_VSBD6n15c64Kxttw,15446
+docling/backend/msword_backend.py,sha256=6bY0ebOaeSbpskUJY5t5pOf4a2VclWzeHeSo-vzsaO0,17470
+docling/backend/pdf_backend.py,sha256=unnw7QiRE1VXg6Pj-eYrtnFGrp5SSYiI324OlFxyv6c,2050
+docling/backend/pypdfium2_backend.py,sha256=MJX6fQqwK3r967fyAAs-RA_YIkeQvhgsLkQAgaBTgaE,8995
+docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/cli/main.py,sha256=NRVGz0z-3EBwYNMJGVnLtDBcfOeutaUyYdkM0ymRnGA,8008
+docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/datamodel/base_models.py,sha256=Mx0xR6YmRP8thu8CjOxjbGHLUJctqIvFwRZQ-8tQowY,5380
+docling/datamodel/document.py,sha256=mkPXDms9jtPFY1pfBSicNaVRZwbbfzYFUj0dJDbMgG8,20612
+docling/datamodel/pipeline_options.py,sha256=WNjluKC-Ww63ifkGMHwws8zIDHnOS1z5Hw7_j3S0qao,2446
+docling/datamodel/settings.py,sha256=KBFVeQviR1hoCFjA1ZwuLuQ6EAAYR7saIa6EUYiOkHI,767
+docling/document_converter.py,sha256=T-Y2pWwbCIofW209XJ3wlc5TiGeQqMbDqgzcVWyZ_0Y,10227
+docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/models/base_model.py,sha256=wSBGAIAbLqrqP_SMtkzXMuyFvvzjVU6iCqgSNnGIR4Y,603
+docling/models/base_ocr_model.py,sha256=SYelQRValiUo6M_p_9-J7CqNIOFO-EkK58j90SMsKQY,5028
+docling/models/ds_glm_model.py,sha256=vJLngchZonqFzGWbUr2izFSXk9DloPDhAfN2c3nkzNU,11254
+docling/models/easyocr_model.py,sha256=YfvdodjZ20WuOfouQXJmDyQL78QDOqWYsWSs2zSxWFc,3327
+docling/models/layout_model.py,sha256=zd2ULW3U6v9OJl4TnjWFEY6Q2O-lBfrIqtvrnDzF7HU,12596
+docling/models/page_assemble_model.py,sha256=LOKHho-r-RpeIVh8CpJ9tid_QIp5um3ukcrucZsyUlY,6645
+docling/models/page_preprocessing_model.py,sha256=cfhUIlGAGaX1RxILi69ZEV9Kmhhd3Y0XaSlQnGo18o4,1964
+docling/models/table_structure_model.py,sha256=YWSZKOz56gvicjTzVgSE-8Z_hI3NcRD5EN0yOUoM-_g,6979
+docling/models/tesseract_ocr_cli_model.py,sha256=fKc05V73ibMvAeuA4PForhYNtunpT5rR0k_xHZsew-E,5980
+docling/models/tesseract_ocr_model.py,sha256=v6td0vq8NogePuRTJRZhKF0DtZXITj70r9rKJKO5u9k,4984
+docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/pipeline/base_pipeline.py,sha256=7DTzVvM_jVHCxyY-BuuGRhmUsD_sgX4DD00oBFJWdB8,6723
+docling/pipeline/simple_pipeline.py,sha256=pxce0-3He5Lqa-xXT-7h173XVOSMZiMHl6HOfAJmQ7o,2162
+docling/pipeline/standard_pdf_pipeline.py,sha256=AVNSxGc6kPmBPDLWDc9eI8fryc25eOtiIVrOyVhZMZM,7527
+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/utils.py,sha256=llhXSbIDNZ1MHOwBEfLHBAoJIAYI7QlPIonlI1jLUJ0,1208
+docling-2.2.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.2.0.dist-info/METADATA,sha256=TkaywA2l2ImdMc9WpUYWUQy3n50zG9Y9eC7ziElBlU0,6205
+docling-2.2.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling-2.2.0.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
+docling-2.2.0.dist-info/RECORD,,

docling-2.0.0.dist-info/RECORD

@@ -1,42 +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=8Lh1gf1P9AnzlwB989OVBgLmokTpfI0LxYRfuvYTqoo,1646
-docling/backend/docling_parse_backend.py,sha256=UgBpopZIP5YkhwhybiqDnqVsSqv9DAAPFkafhfL0pPo,7623
-docling/backend/docling_parse_v2_backend.py,sha256=VY7MsiyqjN3Vl0UkyezriiVJMLbLRrQVuKjWaTgIUwY,8336
-docling/backend/html_backend.py,sha256=MlhEXaA0tgX_tLuQLnkex43gsKqpqHWnbkssxY4n_kc,14753
-docling/backend/mspowerpoint_backend.py,sha256=2UYfMMeWwgDtvIKQELCA-bYv5Z-rGvbMiBNcidNL_uE,14332
-docling/backend/msword_backend.py,sha256=4SDqZAZxLr6VV50OU3MRBAV8SwZMCyJCUbNVMVUpitc,17659
-docling/backend/pdf_backend.py,sha256=unnw7QiRE1VXg6Pj-eYrtnFGrp5SSYiI324OlFxyv6c,2050
-docling/backend/pypdfium2_backend.py,sha256=MJX6fQqwK3r967fyAAs-RA_YIkeQvhgsLkQAgaBTgaE,8995
-docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/cli/main.py,sha256=NRVGz0z-3EBwYNMJGVnLtDBcfOeutaUyYdkM0ymRnGA,8008
-docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/datamodel/base_models.py,sha256=Ha-DoRZoksjHSZHWqUSiQ79MTBEfY5ur8U_LVtyBRYU,5153
-docling/datamodel/document.py,sha256=GCARkUuv8TNtFO934E7KujOsTkBFqLXX5bogNprVXEM,19411
-docling/datamodel/pipeline_options.py,sha256=mez7CiJMtm-xhOmZ-2-M_Q3YwC6EzHytWfg0E3tiVio,2329
-docling/datamodel/settings.py,sha256=KBFVeQviR1hoCFjA1ZwuLuQ6EAAYR7saIa6EUYiOkHI,767
-docling/document_converter.py,sha256=S_t9hs2uZfXC38LC0hTaAihrSJIrCvnTiuY5SvUccgk,9587
-docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/models/base_model.py,sha256=wSBGAIAbLqrqP_SMtkzXMuyFvvzjVU6iCqgSNnGIR4Y,603
-docling/models/base_ocr_model.py,sha256=N5pOQ4RQSWPU-bPZ81FySDdBnwNG64-6K0ldK6ENU0U,4672
-docling/models/ds_glm_model.py,sha256=nUBHTsE-eRtrtPE6v_N4iZGr43bXIsOfb_8NFUMWJQk,11057
-docling/models/easyocr_model.py,sha256=URhHzxwnBuErf6sskWyEWauX-Kne0upnrAguzKQi3SI,3090
-docling/models/layout_model.py,sha256=B4Veff9V0WxcQXTBYzJM6rE7B3lszUI7zmg7EFE0WxU,12245
-docling/models/page_assemble_model.py,sha256=ovwSki52w1rlrc7MgMbjh1Uc5H8XBCz9S2nHE44mzYU,6030
-docling/models/page_preprocessing_model.py,sha256=PJ_jASz3w0Lus_Ep4NN5Vq_Redq7x8vAyVR8qXCb6Eg,1817
-docling/models/table_structure_model.py,sha256=qcjXXiNZcMWjr6ys02sToKZlAr8S0rAJNICbBjK9Ijo,6426
-docling/models/tesseract_ocr_cli_model.py,sha256=l-gRDU273opgack9fAxHaXPEdX5IdD5ZTnu6VsfKIWc,5665
-docling/models/tesseract_ocr_model.py,sha256=tEEq-URSYnyQru7RoD5fx-s1trwMxPCcwJx94M4iuxc,4676
-docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/pipeline/base_pipeline.py,sha256=7DTzVvM_jVHCxyY-BuuGRhmUsD_sgX4DD00oBFJWdB8,6723
-docling/pipeline/simple_pipeline.py,sha256=pxce0-3He5Lqa-xXT-7h173XVOSMZiMHl6HOfAJmQ7o,2162
-docling/pipeline/standard_pdf_pipeline.py,sha256=_gRGR9tsy55_tptFj-AiEJEedxhJ0iIjHb5qaj36d28,7506
-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/utils.py,sha256=llhXSbIDNZ1MHOwBEfLHBAoJIAYI7QlPIonlI1jLUJ0,1208
-docling-2.0.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.0.0.dist-info/METADATA,sha256=RyawmIT2dz9la0DH8KsW749TNq4BpiSIndVEz83wauQ,6235
-docling-2.0.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling-2.0.0.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
-docling-2.0.0.dist-info/RECORD,,