docling 2.31.0__py3-none-any.whl → 2.31.1__py3-none-any.whl

docling/backend/html_backend.py

@@ -1,4 +1,5 @@
 import logging
+import traceback
 from io import BytesIO
 from pathlib import Path
 from typing import Final, Optional, Union, cast
@@ -137,7 +138,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
                     self.analyze_tag(cast(Tag, element), doc)
                 except Exception as exc_child:
                     _log.error(
-                        f"Error processing child from tag {tag.name}: {exc_child!r}"
+                        f"Error processing child from tag {tag.name}:\n{traceback.format_exc()}"
                     )
                     raise exc_child
             elif isinstance(element, NavigableString) and not isinstance(
@@ -390,46 +391,64 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
             _log.debug(f"list-item has no text: {element}")
 
     @staticmethod
-    def parse_table_data(element: Tag) -> Optional[TableData]:
+    def parse_table_data(element: Tag) -> Optional[TableData]:  # noqa: C901
         nested_tables = element.find("table")
         if nested_tables is not None:
             _log.debug("Skipping nested table.")
             return None
 
-        # Count the number of rows (number of <tr> elements)
-        num_rows = len(element("tr"))
-
-        # Find the number of columns (taking into account colspan)
+        # Find the number of rows and columns (taking into account spans)
+        num_rows = 0
         num_cols = 0
         for row in element("tr"):
             col_count = 0
+            is_row_header = True
             if not isinstance(row, Tag):
                 continue
             for cell in row(["td", "th"]):
                 if not isinstance(row, Tag):
                     continue
-                val = cast(Tag, cell).get("colspan", "1")
+                cell_tag = cast(Tag, cell)
+                val = cell_tag.get("colspan", "1")
                 colspan = int(val) if (isinstance(val, str) and val.isnumeric()) else 1
                 col_count += colspan
+                if cell_tag.name == "td" or cell_tag.get("rowspan") is None:
+                    is_row_header = False
             num_cols = max(num_cols, col_count)
+            if not is_row_header:
+                num_rows += 1
+
+        _log.debug(f"The table has {num_rows} rows and {num_cols} cols.")
 
         grid: list = [[None for _ in range(num_cols)] for _ in range(num_rows)]
 
         data = TableData(num_rows=num_rows, num_cols=num_cols, table_cells=[])
 
         # Iterate over the rows in the table
-        for row_idx, row in enumerate(element("tr")):
+        start_row_span = 0
+        row_idx = -1
+        for row in element("tr"):
             if not isinstance(row, Tag):
                 continue
 
             # For each row, find all the column cells (both <td> and <th>)
             cells = row(["td", "th"])
 
-            # Check if each cell in the row is a header -> means it is a column header
+            # Check if cell is in a column header or row header
             col_header = True
+            row_header = True
             for html_cell in cells:
-                if isinstance(html_cell, Tag) and html_cell.name == "td":
-                    col_header = False
+                if isinstance(html_cell, Tag):
+                    if html_cell.name == "td":
+                        col_header = False
+                        row_header = False
+                    elif html_cell.get("rowspan") is None:
+                        row_header = False
+            if not row_header:
+                row_idx += 1
+                start_row_span = 0
+            else:
+                start_row_span += 1
 
             # Extract the text content of each cell
             col_idx = 0
@@ -460,19 +479,24 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
                     if isinstance(row_val, str) and row_val.isnumeric()
                     else 1
                 )
-
-                while grid[row_idx][col_idx] is not None:
+                if row_header:
+                    row_span -= 1
+                while (
+                    col_idx < num_cols
+                    and grid[row_idx + start_row_span][col_idx] is not None
+                ):
                     col_idx += 1
-                for r in range(row_span):
+                for r in range(start_row_span, start_row_span + row_span):
                     for c in range(col_span):
-                        grid[row_idx + r][col_idx + c] = text
+                        if row_idx + r < num_rows and col_idx + c < num_cols:
+                            grid[row_idx + r][col_idx + c] = text
 
                 table_cell = TableCell(
                     text=text,
                     row_span=row_span,
                     col_span=col_span,
-                    start_row_offset_idx=row_idx,
-                    end_row_offset_idx=row_idx + row_span,
+                    start_row_offset_idx=start_row_span + row_idx,
+                    end_row_offset_idx=start_row_span + row_idx + row_span,
                     start_col_offset_idx=col_idx,
                     end_col_offset_idx=col_idx + col_span,
                     column_header=col_header,

docling/backend/md_backend.py

@@ -409,7 +409,7 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
                         )
                     return _txt
 
-                # restore original HTML by removing previouly added markers
+                # restore original HTML by removing previously added markers
                 for regex in [
                     rf"<pre>\s*<code>\s*{_START_MARKER}",
                     rf"{_STOP_MARKER}\s*</code>\s*</pre>",

docling/backend/msword_backend.py

@@ -436,7 +436,7 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
 
         # Common styles for bullet and numbered lists.
         # "List Bullet", "List Number", "List Paragraph"
-        # Identify wether list is a numbered list or not
+        # Identify whether list is a numbered list or not
         # is_numbered = "List Bullet" not in paragraph.style.name
         is_numbered = False
         p_style_id, p_level = self._get_label_and_level(paragraph)

docling/backend/xml/jats_backend.py

@@ -91,7 +91,7 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
         super().__init__(in_doc, path_or_stream)
         self.path_or_stream = path_or_stream
 
-        # Initialize the root of the document hiearchy
+        # Initialize the root of the document hierarchy
         self.root: Optional[NodeItem] = None
 
         self.valid = False

docling/backend/xml/uspto_backend.py

@@ -1,6 +1,6 @@
 """Backend to parse patents from the United States Patent Office (USPTO).
 
-The parsers included in this module can handle patent grants pubished since 1976 and
+The parsers included in this module can handle patent grants published since 1976 and
 patent applications since 2001.
 The original files can be found in https://bulkdata.uspto.gov.
 """
@@ -440,7 +440,7 @@ class PatentUsptoIce(PatentUspto):
                     )
 
             elif name == self.Element.PARAGRAPH.value and text:
-                # remmove blank spaces added in paragraphs
+                # remove blank spaces added in paragraphs
                 text = re.sub("\\s+", " ", text)
                 if self.Element.ABSTRACT.value in self.property:
                     self.abstract = (
@@ -1697,7 +1697,7 @@ class XmlTable:
 class HtmlEntity:
     """Provide utility functions to get the HTML entities of styled characters.
 
-    This class has been developped from:
+    This class has been developed from:
     https://unicode-table.com/en/html-entities/
     https://www.w3.org/TR/WD-math-970515/table03.html
     """
@@ -1896,7 +1896,7 @@ class HtmlEntity:
         """Get an HTML entity of a greek letter in ISO 8879.
 
         Args:
-            The text to transform, as an ISO 8879 entitiy.
+            The text to transform, as an ISO 8879 entity.
 
         Returns:
             The HTML entity representing a greek letter. If the input text is not

docling/cli/main.py

@@ -521,7 +521,7 @@ def convert(  # noqa: C901
             if image_export_mode != ImageRefMode.PLACEHOLDER:
                 pipeline_options.generate_page_images = True
                 pipeline_options.generate_picture_images = (
-                    True  # FIXME: to be deprecated in verson 3
+                    True  # FIXME: to be deprecated in version 3
                 )
                 pipeline_options.images_scale = 2
 

docling/cli/models.py

@@ -32,6 +32,8 @@ class _AvailableModels(str, Enum):
     CODE_FORMULA = "code_formula"
     PICTURE_CLASSIFIER = "picture_classifier"
     SMOLVLM = "smolvlm"
+    SMOLDOCLING = "smoldocling"
+    SMOLDOCLING_MLX = "smoldocling_mlx"
     GRANITE_VISION = "granite_vision"
     EASYOCR = "easyocr"
 
@@ -105,6 +107,8 @@ def download(
         with_code_formula=_AvailableModels.CODE_FORMULA in to_download,
         with_picture_classifier=_AvailableModels.PICTURE_CLASSIFIER in to_download,
         with_smolvlm=_AvailableModels.SMOLVLM in to_download,
+        with_smoldocling=_AvailableModels.SMOLDOCLING in to_download,
+        with_smoldocling_mlx=_AvailableModels.SMOLDOCLING_MLX in to_download,
         with_granite_vision=_AvailableModels.GRANITE_VISION in to_download,
         with_easyocr=_AvailableModels.EASYOCR in to_download,
     )

docling/datamodel/document.py

@@ -303,6 +303,14 @@ class _DocumentConversionInput(BaseModel):
                     else ""
                 )
                 mime = _DocumentConversionInput._mime_from_extension(ext)
+            if mime is not None and mime.lower() == "application/zip":
+                objname = obj.name.lower()
+                if objname.endswith(".xlsx"):
+                    mime = "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
+                elif objname.endswith(".docx"):
+                    mime = "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+                elif objname.endswith(".pptx"):
+                    mime = "application/vnd.openxmlformats-officedocument.presentationml.presentation"
 
         mime = mime or _DocumentConversionInput._detect_html_xhtml(content)
         mime = mime or _DocumentConversionInput._detect_csv(content)

docling/document_converter.py

@@ -189,7 +189,9 @@ class DocumentConverter:
     def _get_pipeline_options_hash(self, pipeline_options: PipelineOptions) -> str:
         """Generate a hash of pipeline options to use as part of the cache key."""
         options_str = str(pipeline_options.model_dump())
-        return hashlib.md5(options_str.encode("utf-8")).hexdigest()
+        return hashlib.md5(
+            options_str.encode("utf-8"), usedforsecurity=False
+        ).hexdigest()
 
     def initialize_pipeline(self, format: InputFormat):
         """Initialize the conversion pipeline for the selected format."""

docling/models/picture_description_vlm_model.py

@@ -57,7 +57,10 @@ class PictureDescriptionVlmModel(PictureDescriptionBaseModel):
                 artifacts_path,
                 torch_dtype=torch.bfloat16,
                 _attn_implementation=(
-                    "flash_attention_2" if self.device.startswith("cuda") else "eager"
+                    "flash_attention_2"
+                    if self.device.startswith("cuda")
+                    and accelerator_options.cuda_use_flash_attention2
+                    else "eager"
                 ),
             ).to(self.device)
 

docling/models/readingorder_model.py

@@ -346,7 +346,7 @@ class ReadingOrderModel:
         new_item.prov.append(prov)
 
     def __call__(self, conv_res: ConversionResult) -> DoclingDocument:
-        with TimeRecorder(conv_res, "glm", scope=ProfilingScope.DOCUMENT):
+        with TimeRecorder(conv_res, "reading_order", scope=ProfilingScope.DOCUMENT):
             page_elements = self._assembled_to_readingorder_elements(conv_res)
 
             # Apply reading order

docling/models/table_structure_model.py

@@ -234,7 +234,7 @@ class TableStructureModel(BasePageModel):
                                 tcells = table_cluster.cells
                             tokens = []
                             for c in tcells:
-                                # Only allow non empty stings (spaces) into the cells of a table
+                                # Only allow non empty strings (spaces) into the cells of a table
                                 if len(c.text.strip()) > 0:
                                     new_cell = copy.deepcopy(c)
                                     new_cell.rect = BoundingRectangle.from_bounding_box(
@@ -267,7 +267,7 @@ class TableStructureModel(BasePageModel):
                                     element["bbox"]["token"] = text_piece
 
                                 tc = TableCell.model_validate(element)
-                                if self.do_cell_matching and tc.bbox is not None:
+                                if tc.bbox is not None:
                                     tc.bbox = tc.bbox.scaled(1 / self.scale)
                                 table_cells.append(tc)
 

docling/models/tesseract_ocr_model.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import logging
 from collections.abc import Iterable
 from pathlib import Path
@@ -38,6 +40,8 @@ class TesseractOcrModel(BaseOcrModel):
         self.options: TesseractOcrOptions
 
         self.scale = 3  # multiplier for 72 dpi == 216 dpi.
+        self.reader = None
+        self.script_readers: dict[str, tesserocr.PyTessBaseAPI] = {}
 
         if self.enabled:
             install_errmsg = (
@@ -84,9 +88,7 @@ class TesseractOcrModel(BaseOcrModel):
                 "oem": tesserocr.OEM.DEFAULT,
             }
 
-            self.reader = None
             self.osd_reader = None
-            self.script_readers: dict[str, tesserocr.PyTessBaseAPI] = {}
 
             if self.options.path is not None:
                 tesserocr_kwargs["path"] = self.options.path
@@ -151,7 +153,7 @@ class TesseractOcrModel(BaseOcrModel):
                             script = map_tesseract_script(script)
                             lang = f"{self.script_prefix}{script}"
 
-                            # Check if the detected languge is present in the system
+                            # Check if the detected language is present in the system
                             if lang not in self._tesserocr_languages:
                                 msg = f"Tesseract detected the script '{script}' and language '{lang}'."
                                 msg += " However this language is not installed in your system and will be ignored."

docling/utils/model_downloader.py

@@ -4,12 +4,15 @@ from typing import Optional
 
 from docling.datamodel.pipeline_options import (
     granite_picture_description,
+    smoldocling_vlm_conversion_options,
+    smoldocling_vlm_mlx_conversion_options,
     smolvlm_picture_description,
 )
 from docling.datamodel.settings import settings
 from docling.models.code_formula_model import CodeFormulaModel
 from docling.models.document_picture_classifier import DocumentPictureClassifier
 from docling.models.easyocr_model import EasyOcrModel
+from docling.models.hf_vlm_model import HuggingFaceVlmModel
 from docling.models.layout_model import LayoutModel
 from docling.models.picture_description_vlm_model import PictureDescriptionVlmModel
 from docling.models.table_structure_model import TableStructureModel
@@ -27,6 +30,8 @@ def download_models(
     with_code_formula: bool = True,
     with_picture_classifier: bool = True,
     with_smolvlm: bool = False,
+    with_smoldocling: bool = False,
+    with_smoldocling_mlx: bool = False,
     with_granite_vision: bool = False,
     with_easyocr: bool = True,
 ):
@@ -77,6 +82,25 @@ def download_models(
             progress=progress,
         )
 
+    if with_smoldocling:
+        _log.info("Downloading SmolDocling model...")
+        HuggingFaceVlmModel.download_models(
+            repo_id=smoldocling_vlm_conversion_options.repo_id,
+            local_dir=output_dir / smoldocling_vlm_conversion_options.repo_cache_folder,
+            force=force,
+            progress=progress,
+        )
+
+    if with_smoldocling_mlx:
+        _log.info("Downloading SmolDocling MLX model...")
+        HuggingFaceVlmModel.download_models(
+            repo_id=smoldocling_vlm_mlx_conversion_options.repo_id,
+            local_dir=output_dir
+            / smoldocling_vlm_mlx_conversion_options.repo_cache_folder,
+            force=force,
+            progress=progress,
+        )
+
     if with_granite_vision:
         _log.info("Downloading Granite Vision model...")
         PictureDescriptionVlmModel.download_models(

docling/utils/utils.py

@@ -20,7 +20,7 @@ def create_file_hash(path_or_stream: Union[BytesIO, Path]) -> str:
     """Create a stable page_hash of the path_or_stream of a file"""
 
     block_size = 65536
-    hasher = hashlib.sha256()
+    hasher = hashlib.sha256(usedforsecurity=False)
 
     def _hash_buf(binary_stream):
         buf = binary_stream.read(block_size)  # read and page_hash in chunks
@@ -38,7 +38,7 @@ def create_file_hash(path_or_stream: Union[BytesIO, Path]) -> str:
 
 
 def create_hash(string: str):
-    hasher = hashlib.sha256()
+    hasher = hashlib.sha256(usedforsecurity=False)
     hasher.update(string.encode("utf-8"))
 
     return hasher.hexdigest()

{docling-2.31.0.dist-info → docling-2.31.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.31.0
+Version: 2.31.1
 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/docling-project/docling
 License: MIT

{docling-2.31.0.dist-info → docling-2.31.1.dist-info}/RECORD

@@ -10,29 +10,29 @@ docling/backend/docx/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hS
 docling/backend/docx/latex/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/backend/docx/latex/latex_dict.py,sha256=tFJp4ScT_AkY2ON7nLEa560p601Jq2glcZvMKxxjn7w,6593
 docling/backend/docx/latex/omml.py,sha256=nEpcfyyrOucJyj6cD7wfThrIa-q0CQCoqMb3dkrhCRg,12094
-docling/backend/html_backend.py,sha256=TBiMAp3s_QbQTRymFA7wScXECyHn_w-Kb8MbqRibTmE,20099
+docling/backend/html_backend.py,sha256=3K-l5SUAAyqISNEb7nPst_I51xzYOVOkgmwXh3lv9sw,21063
 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=EdGBXe0n8zniO1LSF3VIjviKs1VRUujpF8aFUpJ5D1k,17209
+docling/backend/md_backend.py,sha256=JkY1qTvQFXjKSZGfD-83d-fZelorUG_l6mpJdYGqvX8,17210
 docling/backend/msexcel_backend.py,sha256=3j0WQfqDpgPXdPMCguefdv7arcNVDedPD6gl54cmLn8,18110
 docling/backend/mspowerpoint_backend.py,sha256=RwqfvvzrtM56L9uf7PR9lvlHJ-LyYGpkS1iVxkTl72Q,17203
-docling/backend/msword_backend.py,sha256=Xdrs_k160-tDUmhcFGZ7MBbpiYkwPLT3wl3FUO2Ui1A,32476
+docling/backend/msword_backend.py,sha256=lVVMNwt0WIl4RD5wAf8pc8bJsb60x1BA8hTTkVmEVa8,32477
 docling/backend/pdf_backend.py,sha256=KE9TMuFO5WX-o5A_DAd4tEaLi4HMZ4XjKdpllItVkWM,2238
 docling/backend/pypdfium2_backend.py,sha256=pX8f0WbUb0KTDTKyQuLzP_lgHHubyGXWD33vmpefPy8,10805
 docling/backend/xml/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/backend/xml/jats_backend.py,sha256=g9YNSS8kqhVL7ceZF2jR7Aaqbh1F1Zn6jmte0HyEH20,24926
-docling/backend/xml/uspto_backend.py,sha256=iE1PSAgXqtHkqcsC1RUJiwuyKNlf2elucCV1V2sk0kQ,70926
+docling/backend/xml/jats_backend.py,sha256=ghGi9bHjx3BvaOtmzLw86-wZy4UxpQPOPQL4e73-BI8,24927
+docling/backend/xml/uspto_backend.py,sha256=nyAMr5ht7dclxkVDwsKNeiOhLQrUtRLS8JdscB2AVJg,70924
 docling/chunking/__init__.py,sha256=h83TDs0AuOV6oEPLAPrn9dpGKiU-2Vg6IRNo4cv6GDA,346
 docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/cli/main.py,sha256=Z6EdrwESOKUBHF6yJlzuwnznScBtdrlbU_xB0AT9cA4,26137
-docling/cli/models.py,sha256=Cyv7d_c8J62luGWsYvbcC9_3UpPp_TVsFo5vJAyr4kI,3940
+docling/cli/main.py,sha256=D7WEY4x6pQCVFRy3peK9KUDOb0Y5IVc-vTDqPnHPK00,26138
+docling/cli/models.py,sha256=9yLGp6QRJGpR86U3SjmWAXDt3MvBaJLLY4xDVdsu3O8,4160
 docling/cli/tools.py,sha256=QhtRxQG0TVrfsMqdv5i7J0_qQy1ZZyWYnHPwJl7b5oY,322
 docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/datamodel/base_models.py,sha256=DRE_XoldtCreWF4ucO0iK0l8uOnfvnhQaYjV0z1Qe0M,7921
-docling/datamodel/document.py,sha256=02QybqtnQ0genFU7UF9pVL3fIwguu9br0JbdtcUvu4o,14998
+docling/datamodel/document.py,sha256=_0Z4zUgCB5677ZW8Y7C1fv75enLZJOJUjcUkGTSiTBA,15553
 docling/datamodel/pipeline_options.py,sha256=-1QG8dY0RZkTJb66lXErEAnPq4F_1vgnk_5AcIr3cgU,13350
 docling/datamodel/settings.py,sha256=bNMdowIKv7RUchabQTo4rFNEsxfB6pGg2LoZSY634zo,1869
-docling/document_converter.py,sha256=zSaGp2zx73kiE1KHmEHwnG-wxJvcMiyyn2fCAM2vdYk,13804
+docling/document_converter.py,sha256=PRRr65nigQ3LZDl4G2fBMkOtJyswT7xyGt7fpUeDO3w,13849
 docling/exceptions.py,sha256=K1WnCS1leK2JtMB5ewZWKkb0EaijFgl-tRzrO9ntgPM,134
 docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/models/api_vlm_model.py,sha256=w1SzdG3Ypz_0iZGiX-skMwV1E1JnOHH2BJiNkcEEIAA,2478
@@ -53,14 +53,14 @@ docling/models/page_assemble_model.py,sha256=GO7JI1D6T6EkSW94cLQobPGNQUahkxQqTPR
 docling/models/page_preprocessing_model.py,sha256=6pOGXiFQ-oz06UmJdcaYMdVyfZ0YVLWS6efGcx7Mxws,3105
 docling/models/picture_description_api_model.py,sha256=qs3n0smC9DXhzwJeK_iQG08Y6ZFHInKtdGPVhzgvxgU,2091
 docling/models/picture_description_base_model.py,sha256=FbBVXzAOB87xpJN28tuGCxoAdcf6mZNUOqJR7ljUg5g,2946
-docling/models/picture_description_vlm_model.py,sha256=nS68qbJQCP94-gbgFfAzMLaEC-wquSLEwuDix287c9c,4067
+docling/models/picture_description_vlm_model.py,sha256=DiTjnehVy1n0N04xPUvZl8rx4TiNHzHn9Cnzy_ePGts,4177
 docling/models/plugins/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/models/plugins/defaults.py,sha256=qslXGnRX07Z3GGttNriqaox0v0vXp4zs4KLurHCZjp4,858
 docling/models/rapid_ocr_model.py,sha256=Tq_1Egu5Hjx7Y69Vox17QTtRXztSyflB1fhN08CWQwY,5894
-docling/models/readingorder_model.py,sha256=BxACJ-aIl2aUlyLcyl-uDtuSZH_mCLJgbkDG4Sx_www,14564
-docling/models/table_structure_model.py,sha256=dR3JkiPkdbScaNy6dia4_ZXPYESSiMDZztD-lLHE1uY,12591
+docling/models/readingorder_model.py,sha256=S9ru2ApY9sE-Uue3hptWHmbmElwo36bUbAikxCFpHYs,14574
+docling/models/table_structure_model.py,sha256=1gxLaooK0IKMrnmS8nT1BItKqt1GAKghfpmLKb3i53g,12566
 docling/models/tesseract_ocr_cli_model.py,sha256=iFdOud5ymoW9WV8bWLCDpd3LJBo9M5bTT5vc635zEDY,10229
-docling/models/tesseract_ocr_model.py,sha256=oPKOoTTcpYUTDNRteBG-MFcxB9SDC6dk4HuKjIODwMk,9310
+docling/models/tesseract_ocr_model.py,sha256=72009TJL_7tXTEnhlsGRiw_KibrQ0LjZlCBtW8NtwUc,9339
 docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/pipeline/base_pipeline.py,sha256=DnuxAf7EQusdSRae0QUVth-0f2mSff8JZjX-2vazk00,8751
 docling/pipeline/simple_pipeline.py,sha256=TXZOwR7hZRji462ZTIpte0VJjzbxvNVE8dbLFANDhSU,2253
@@ -74,13 +74,13 @@ docling/utils/export.py,sha256=VwVUnYDk3mhGmISDbVm306fwpGNnoojouStBD4UajXI,4673
 docling/utils/glm_utils.py,sha256=TKOWQqWAHsX_w4fvoAA7_2xCi_urhnp1DsmjY8_sk5w,12274
 docling/utils/layout_postprocessor.py,sha256=x7exVG3HYzV9M_O78FfyoG43Y2L7PPMMydvSNwjqh8s,24528
 docling/utils/locks.py,sha256=RzqQtD5UispgV71pGN_nU6GYfeN11BN0Sh_Dq9ycqGo,52
-docling/utils/model_downloader.py,sha256=AMqfHTmZzzsPrlcHFdX7hhW-a3Ki6ndjnTjQQYrDSxU,3206
+docling/utils/model_downloader.py,sha256=ocvud3G3qlBQhzMo69Q3RJMnvq5HPZ2DwNbMuEp8RCs,4142
 docling/utils/ocr_utils.py,sha256=F7iOOjqolUcImUzir4qjDQd4QWSO3s6JC4WRn3U7uY4,263
 docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
-docling/utils/utils.py,sha256=xxmVMhQWr7oVBy93IGGpr2x8FBVRHNDwD31kwAF5xK4,1866
+docling/utils/utils.py,sha256=kJtIYuzXeOyJHYlxmLAo7dGM5rEsDa1i84qEsUj1nio,1908
 docling/utils/visualization.py,sha256=tY2ylE2aiQKkmzlSLnFW-HTfFyqUUMguW18ldd1PLfo,2868
-docling-2.31.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.31.0.dist-info/METADATA,sha256=tScsMgyfrwtIaCKPl-ygViccYxnRADeUNuHKDGjw7ww,10108
-docling-2.31.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-docling-2.31.0.dist-info/entry_points.txt,sha256=pIxel-UeVo1S7FhoNG5xgEfPjLZfBLi_N9TsGPtJSLo,144
-docling-2.31.0.dist-info/RECORD,,
+docling-2.31.1.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.31.1.dist-info/METADATA,sha256=31fTxA8TvMdw_KdThEyn3Z5GAHAhNEtvFYlrPdzqV4w,10108
+docling-2.31.1.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+docling-2.31.1.dist-info/entry_points.txt,sha256=pIxel-UeVo1S7FhoNG5xgEfPjLZfBLi_N9TsGPtJSLo,144
+docling-2.31.1.dist-info/RECORD,,