docling 2.30.0__py3-none-any.whl → 2.31.1__py3-none-any.whl

docling/models/tesseract_ocr_cli_model.py

@@ -3,9 +3,10 @@ import io
 import logging
 import os
 import tempfile
+from collections.abc import Iterable
 from pathlib import Path
 from subprocess import DEVNULL, PIPE, Popen
-from typing import Iterable, List, Optional, Tuple, Type
+from typing import List, Optional, Tuple, Type
 
 import pandas as pd
 from docling_core.types.doc import BoundingBox, CoordOrigin
@@ -63,8 +64,7 @@ class TesseractOcrCliModel(BaseOcrModel):
                 )
 
     def _get_name_and_version(self) -> Tuple[str, str]:
-
-        if self._name != None and self._version != None:
+        if self._name is not None and self._version is not None:
             return self._name, self._version  # type: ignore
 
         cmd = [self.options.tesseract_cmd, "--version"]
@@ -125,14 +125,16 @@ class TesseractOcrCliModel(BaseOcrModel):
         # _log.info(decoded_data)
 
         # Read the TSV file generated by Tesseract
-        df = pd.read_csv(io.StringIO(decoded_data), quoting=csv.QUOTE_NONE, sep="\t")
+        df_result = pd.read_csv(
+            io.StringIO(decoded_data), quoting=csv.QUOTE_NONE, sep="\t"
+        )
 
         # Display the dataframe (optional)
         # _log.info("df: ", df.head())
 
         # Filter rows that contain actual text (ignore header or empty rows)
-        df_filtered = df[
-            df["text"].notnull() & (df["text"].apply(str).str.strip() != "")
+        df_filtered = df_result[
+            df_result["text"].notna() & (df_result["text"].apply(str).str.strip() != "")
         ]
 
         return df_filtered
@@ -149,10 +151,10 @@ class TesseractOcrCliModel(BaseOcrModel):
         proc = Popen(cmd, stdout=PIPE, stderr=DEVNULL)
         output, _ = proc.communicate()
         decoded_data = output.decode("utf-8")
-        df = pd.read_csv(
+        df_detected = pd.read_csv(
             io.StringIO(decoded_data), sep=":", header=None, names=["key", "value"]
         )
-        scripts = df.loc[df["key"] == "Script"].value.tolist()
+        scripts = df_detected.loc[df_detected["key"] == "Script"].value.tolist()
         if len(scripts) == 0:
             _log.warning("Tesseract cannot detect the script of the page")
             return None
@@ -183,11 +185,11 @@ class TesseractOcrCliModel(BaseOcrModel):
         proc = Popen(cmd, stdout=PIPE, stderr=DEVNULL)
         output, _ = proc.communicate()
         decoded_data = output.decode("utf-8")
-        df = pd.read_csv(io.StringIO(decoded_data), header=None)
-        self._tesseract_languages = df[0].tolist()[1:]
+        df_list = pd.read_csv(io.StringIO(decoded_data), header=None)
+        self._tesseract_languages = df_list[0].tolist()[1:]
 
         # Decide the script prefix
-        if any([l.startswith("script/") for l in self._tesseract_languages]):
+        if any(lang.startswith("script/") for lang in self._tesseract_languages):
             script_prefix = "script/"
         else:
             script_prefix = ""
@@ -197,7 +199,6 @@ class TesseractOcrCliModel(BaseOcrModel):
     def __call__(
         self, conv_res: ConversionResult, page_batch: Iterable[Page]
     ) -> Iterable[Page]:
-
         if not self.enabled:
             yield from page_batch
             return
@@ -225,19 +226,19 @@ class TesseractOcrCliModel(BaseOcrModel):
                                 fname = image_file.name
                                 high_res_image.save(image_file)
 
-                            df = self._run_tesseract(fname)
+                            df_result = self._run_tesseract(fname)
                         finally:
                             if os.path.exists(fname):
                                 os.remove(fname)
 
-                        # _log.info(df)
+                        # _log.info(df_result)
 
                         # Print relevant columns (bounding box and text)
-                        for ix, row in df.iterrows():
+                        for ix, row in df_result.iterrows():
                             text = row["text"]
                             conf = row["conf"]
 
-                            l = float(row["left"])
+                            l = float(row["left"])  # noqa: E741
                             b = float(row["top"])
                             w = float(row["width"])
                             h = float(row["height"])

docling/models/tesseract_ocr_model.py

@@ -1,6 +1,9 @@
+from __future__ import annotations
+
 import logging
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Iterable, Optional, Type
+from typing import Optional, Type
 
 from docling_core.types.doc import BoundingBox, CoordOrigin
 from docling_core.types.doc.page import BoundingRectangle, TextCell
@@ -38,7 +41,6 @@ class TesseractOcrModel(BaseOcrModel):
 
         self.scale = 3  # multiplier for 72 dpi == 216 dpi.
         self.reader = None
-        self.osd_reader = None
         self.script_readers: dict[str, tesserocr.PyTessBaseAPI] = {}
 
         if self.enabled:
@@ -64,7 +66,7 @@ class TesseractOcrModel(BaseOcrModel):
                 raise ImportError(install_errmsg)
             try:
                 tesseract_version = tesserocr.tesseract_version()
-            except:
+            except Exception:
                 raise ImportError(install_errmsg)
 
             _, self._tesserocr_languages = tesserocr.get_languages()
@@ -75,7 +77,7 @@ class TesseractOcrModel(BaseOcrModel):
             _log.debug("Initializing TesserOCR: %s", tesseract_version)
             lang = "+".join(self.options.lang)
 
-            if any([l.startswith("script/") for l in self._tesserocr_languages]):
+            if any(lang.startswith("script/") for lang in self._tesserocr_languages):
                 self.script_prefix = "script/"
             else:
                 self.script_prefix = ""
@@ -86,6 +88,8 @@ class TesseractOcrModel(BaseOcrModel):
                 "oem": tesserocr.OEM.DEFAULT,
             }
 
+            self.osd_reader = None
+
             if self.options.path is not None:
                 tesserocr_kwargs["path"] = self.options.path
 
@@ -149,7 +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/pipeline/base_pipeline.py

@@ -3,9 +3,10 @@ import logging
 import time
 import traceback
 from abc import ABC, abstractmethod
-from typing import Any, Callable, Iterable, List
+from collections.abc import Iterable
+from typing import Any, Callable, List
 
-from docling_core.types.doc import DoclingDocument, NodeItem
+from docling_core.types.doc import NodeItem
 
 from docling.backend.abstract_backend import AbstractDocumentBackend
 from docling.backend.pdf_backend import PdfDocumentBackend
@@ -64,7 +65,6 @@ class BasePipeline(ABC):
         return conv_res
 
     def _enrich_document(self, conv_res: ConversionResult) -> ConversionResult:
-
         def _prepare_elements(
             conv_res: ConversionResult, model: GenericEnrichmentModel[Any]
         ) -> Iterable[NodeItem]:
@@ -113,7 +113,6 @@ 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
@@ -127,7 +126,6 @@ class PaginatedPipeline(BasePipeline):  # TODO this is a bad name.
         yield from page_batch
 
     def _build_document(self, conv_res: ConversionResult) -> ConversionResult:
-
         if not isinstance(conv_res.input._backend, PdfDocumentBackend):
             raise RuntimeError(
                 f"The selected backend {type(conv_res.input._backend).__name__} for {conv_res.input.file} is not a PDF backend. "
@@ -139,8 +137,7 @@ class PaginatedPipeline(BasePipeline):  # TODO this is a bad name.
 
         total_elapsed_time = 0.0
         with TimeRecorder(conv_res, "doc_build", scope=ProfilingScope.DOCUMENT):
-
-            for i in range(0, conv_res.input.page_count):
+            for i in range(conv_res.input.page_count):
                 start_page, end_page = conv_res.input.limits.page_range
                 if (start_page - 1) <= i <= (end_page - 1):
                     conv_res.pages.append(Page(page_no=i))
@@ -161,7 +158,6 @@ 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!
-
                         # Cleanup cached images
                         if not self.keep_images:
                             p._image_cache = {}

docling/pipeline/simple_pipeline.py

@@ -24,7 +24,6 @@ class SimplePipeline(BasePipeline):
         super().__init__(pipeline_options)
 
     def _build_document(self, conv_res: ConversionResult) -> ConversionResult:
-
         if not isinstance(conv_res.input._backend, DeclarativeDocumentBackend):
             raise RuntimeError(
                 f"The selected backend {type(conv_res.input._backend).__name__} for {conv_res.input.file} is not a declarative backend. "

docling/pipeline/standard_pdf_pipeline.py

@@ -1,5 +1,4 @@
 import logging
-import sys
 import warnings
 from pathlib import Path
 from typing import Optional, cast

docling/pipeline/vlm_pipeline.py

@@ -1,5 +1,4 @@
 import logging
-import warnings
 from io import BytesIO
 from pathlib import Path
 from typing import List, Optional, Union, cast
@@ -32,7 +31,6 @@ _log = logging.getLogger(__name__)
 
 
 class VlmPipeline(PaginatedPipeline):
-
     def __init__(self, pipeline_options: VlmPipelineOptions):
         super().__init__(pipeline_options)
         self.keep_backend = True
@@ -114,7 +112,6 @@ class VlmPipeline(PaginatedPipeline):
 
     def _assemble_document(self, conv_res: ConversionResult) -> ConversionResult:
         with TimeRecorder(conv_res, "doc_assemble", scope=ProfilingScope.DOCUMENT):
-
             if (
                 self.pipeline_options.vlm_options.response_format
                 == ResponseFormat.DOCTAGS

docling/utils/export.py

@@ -1,8 +1,8 @@
 import logging
-from typing import Any, Dict, Iterable, List, Tuple, Union
+from collections.abc import Iterable
+from typing import Any, Dict, List, Tuple, Union
 
 from docling_core.types.doc import BoundingBox, CoordOrigin
-from docling_core.types.doc.page import TextCell
 from docling_core.types.legacy_doc.base import BaseCell, BaseText, Ref, Table
 
 from docling.datamodel.document import ConversionResult, Page
@@ -13,7 +13,6 @@ _log = logging.getLogger(__name__)
 def generate_multimodal_pages(
     doc_result: ConversionResult,
 ) -> Iterable[Tuple[str, str, List[Dict[str, Any]], List[Dict[str, Any]], Page]]:
-
     label_to_doclaynet = {
         "title": "title",
         "table-of-contents": "document_index",
@@ -122,7 +121,6 @@ def generate_multimodal_pages(
     if doc.main_text is None:
         return
     for ix, orig_item in enumerate(doc.main_text):
-
         item = doc._resolve_ref(orig_item) if isinstance(orig_item, Ref) else orig_item
         if item is None or item.prov is None or len(item.prov) == 0:
             _log.debug(f"Skipping item {orig_item}")

docling/utils/glm_utils.py

@@ -29,7 +29,7 @@ def resolve_item(paths, obj):
 
     try:
         key = int(paths[0])
-    except:
+    except Exception:
         key = paths[0]
 
     if len(paths) == 1:
@@ -67,7 +67,7 @@ def _flatten_table_grid(grid: List[List[dict]]) -> List[dict]:
     return unique_objects
 
 
-def to_docling_document(doc_glm, update_name_label=False) -> DoclingDocument:
+def to_docling_document(doc_glm, update_name_label=False) -> DoclingDocument:  # noqa: C901
     origin = DocumentOrigin(
         mimetype="application/pdf",
         filename=doc_glm["file-info"]["filename"],

docling/utils/layout_postprocessor.py

@@ -18,7 +18,7 @@ class UnionFind:
 
     def __init__(self, elements):
         self.parent = {elem: elem for elem in elements}
-        self.rank = {elem: 0 for elem in elements}
+        self.rank = dict.fromkeys(elements, 0)
 
     def find(self, x):
         if self.parent[x] != x:
@@ -484,7 +484,9 @@ class LayoutPostprocessor:
         spatial_index = (
             self.regular_index
             if cluster_type == "regular"
-            else self.picture_index if cluster_type == "picture" else self.wrapper_index
+            else self.picture_index
+            if cluster_type == "picture"
+            else self.wrapper_index
         )
 
         # Map of currently valid clusters

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,
 ):
@@ -37,7 +42,7 @@ def download_models(
     output_dir.mkdir(exist_ok=True, parents=True)
 
     if with_layout:
-        _log.info(f"Downloading layout model...")
+        _log.info("Downloading layout model...")
         LayoutModel.download_models(
             local_dir=output_dir / LayoutModel._model_repo_folder,
             force=force,
@@ -45,7 +50,7 @@ def download_models(
         )
 
     if with_tableformer:
-        _log.info(f"Downloading tableformer model...")
+        _log.info("Downloading tableformer model...")
         TableStructureModel.download_models(
             local_dir=output_dir / TableStructureModel._model_repo_folder,
             force=force,
@@ -53,7 +58,7 @@ def download_models(
         )
 
     if with_picture_classifier:
-        _log.info(f"Downloading picture classifier model...")
+        _log.info("Downloading picture classifier model...")
         DocumentPictureClassifier.download_models(
             local_dir=output_dir / DocumentPictureClassifier._model_repo_folder,
             force=force,
@@ -61,7 +66,7 @@ def download_models(
         )
 
     if with_code_formula:
-        _log.info(f"Downloading code formula model...")
+        _log.info("Downloading code formula model...")
         CodeFormulaModel.download_models(
             local_dir=output_dir / CodeFormulaModel._model_repo_folder,
             force=force,
@@ -69,7 +74,7 @@ def download_models(
         )
 
     if with_smolvlm:
-        _log.info(f"Downloading SmolVlm model...")
+        _log.info("Downloading SmolVlm model...")
         PictureDescriptionVlmModel.download_models(
             repo_id=smolvlm_picture_description.repo_id,
             local_dir=output_dir / smolvlm_picture_description.repo_cache_folder,
@@ -77,8 +82,27 @@ 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(f"Downloading Granite Vision model...")
+        _log.info("Downloading Granite Vision model...")
         PictureDescriptionVlmModel.download_models(
             repo_id=granite_picture_description.repo_id,
             local_dir=output_dir / granite_picture_description.repo_cache_folder,
@@ -87,7 +111,7 @@ def download_models(
         )
 
     if with_easyocr:
-        _log.info(f"Downloading easyocr models...")
+        _log.info("Downloading easyocr models...")
         EasyOcrModel.download_models(
             local_dir=output_dir / EasyOcrModel._model_repo_folder,
             force=force,

docling/utils/utils.py

@@ -13,14 +13,14 @@ def chunkify(iterator, chunk_size):
     if isinstance(iterator, List):
         iterator = iter(iterator)
     for first in iterator:  # Take the first element from the iterator
-        yield [first] + list(islice(iterator, chunk_size - 1))
+        yield [first, *list(islice(iterator, chunk_size - 1))]
 
 
 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-2.30.0.dist-info → docling-2.31.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.30.0
+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
@@ -86,6 +86,7 @@ Description-Content-Type: text/markdown
 [![License MIT](https://img.shields.io/github/license/docling-project/docling)](https://opensource.org/licenses/MIT)
 [![PyPI Downloads](https://static.pepy.tech/badge/docling/month)](https://pepy.tech/projects/docling)
 [![Docling Actor](https://apify.com/actor-badge?actor=vancura/docling?fpr=docling)](https://apify.com/vancura/docling)
+[![OpenSSF Best Practices](https://www.bestpractices.dev/projects/10101/badge)](https://www.bestpractices.dev/projects/10101)
 [![LF AI & Data](https://img.shields.io/badge/LF%20AI%20%26%20Data-003778?logo=linuxfoundation&logoColor=fff&color=0094ff&labelColor=003778)](https://lfaidata.foundation/projects/)
 
 Docling simplifies document processing, parsing diverse formats — including advanced PDF understanding — and providing seamless integrations with the gen AI ecosystem.

docling-2.31.1.dist-info/RECORD

@@ -0,0 +1,86 @@
+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=VZ8Xk1VHGHRqBo_TdtMzRAu1NFaFaJ8dk4CaEcBaEm0,14038
+docling/backend/csv_backend.py,sha256=2g9famYG2W-ID9jEdZPxc6O8QGv1vWQfjN8pL-QMBE0,4536
+docling/backend/docling_parse_backend.py,sha256=V_CsUdN5RkGQBBq7A_ReAiUW4CQVh0-1Ur157Ozurdg,8017
+docling/backend/docling_parse_v2_backend.py,sha256=6fokgqb1hMbZua33gL46EFamrwPTC7ms6ZuEHw-Dv28,9395
+docling/backend/docling_parse_v4_backend.py,sha256=-WJZs0IsdN6blhkvTS1eh_qhujYLyJ3XcOMqS6AaXxg,6282
+docling/backend/docx/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+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=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=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=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=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=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=_0Z4zUgCB5677ZW8Y7C1fv75enLZJOJUjcUkGTSiTBA,15553
+docling/datamodel/pipeline_options.py,sha256=-1QG8dY0RZkTJb66lXErEAnPq4F_1vgnk_5AcIr3cgU,13350
+docling/datamodel/settings.py,sha256=bNMdowIKv7RUchabQTo4rFNEsxfB6pGg2LoZSY634zo,1869
+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
+docling/models/base_model.py,sha256=Zx_nByGYkubTvvYiQxwiB6P8lc7wOD4ZTC2QIw6vCEg,2950
+docling/models/base_ocr_model.py,sha256=_iD8QCKQdv2VWrIuSRPyGP4oCz94h84WriHg9F2k-Z0,7172
+docling/models/code_formula_model.py,sha256=9cplJFvP7jcJGz-p-MmL8_lqUhmaXZu7wKyX2aOTujs,11504
+docling/models/document_picture_classifier.py,sha256=tyOnyM0vh8-pjh9PiHa_67YpK-3pc_vGQKlnfAyraBs,6255
+docling/models/easyocr_model.py,sha256=3rgXMeB7LbMjevCAVDMG3voe3PQhQ7B-RyYrXzefUlQ,7365
+docling/models/factories/__init__.py,sha256=x_EM5dDg_A3HBcBYzOoqwmA2AFLtJ1IzYDPX-R1A-Sg,868
+docling/models/factories/base_factory.py,sha256=MfWIljMETi5aaVR-6qLTelW8u1gwDAQsOwg3fu7O4Qc,4028
+docling/models/factories/ocr_factory.py,sha256=G5RkmkKvkl-ihpo6qSj8WC77VdlVSQ1s0ekwUX2ILts,316
+docling/models/factories/picture_description_factory.py,sha256=Ru3-TnVVEKf5O07C_UpGf2HCOHc7j20AJzfficw3agM,385
+docling/models/hf_mlx_model.py,sha256=B_B4hFU-jU0g_DQtQD8w4Ejorn10mkDuFI93wR_WhGk,4897
+docling/models/hf_vlm_model.py,sha256=SiPMTLghMUjJ66dA2yN4UujpLO6PiOhLEPInWtXV_5s,6912
+docling/models/layout_model.py,sha256=0fiJXJ4aPmcMsYY7rbN9LJ2mZ0_8G0ODY9kyNTAN3Ws,7823
+docling/models/ocr_mac_model.py,sha256=A3TlEbvvwhkWiq9YARos3Y9yNcpPYQ7JGc_4hFtAK-8,5370
+docling/models/page_assemble_model.py,sha256=GO7JI1D6T6EkSW94cLQobPGNQUahkxQqTPRwj5CnmFE,6304
+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=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=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=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
+docling/pipeline/standard_pdf_pipeline.py,sha256=iNZMMGiHTwV6I4u_jjqXhVJ_DiPn_O9qnnee3PQxidc,10773
+docling/pipeline/vlm_pipeline.py,sha256=g3bxPEqxK8x-B5S6pOpNNo5GxCMCRDZgPJUFqsBA1eg,9720
+docling/py.typed,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+docling/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+docling/utils/accelerator_utils.py,sha256=ONNRrC8fH-8E93WUCNhfOq1t7WrQ1T7-YsmExTOY5f0,2292
+docling/utils/api_image_request.py,sha256=_CgdzmPqdsyXmyYUFGLZcXcoH586qC6A1p5vsNbj1Q0,1416
+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=ocvud3G3qlBQhzMo69Q3RJMnvq5HPZ2DwNbMuEp8RCs,4142
+docling/utils/ocr_utils.py,sha256=F7iOOjqolUcImUzir4qjDQd4QWSO3s6JC4WRn3U7uY4,263
+docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
+docling/utils/utils.py,sha256=kJtIYuzXeOyJHYlxmLAo7dGM5rEsDa1i84qEsUj1nio,1908
+docling/utils/visualization.py,sha256=tY2ylE2aiQKkmzlSLnFW-HTfFyqUUMguW18ldd1PLfo,2868
+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,,

docling-2.30.0.dist-info/RECORD

@@ -1,86 +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=1lNxzwDTn303aXduPDVmTyXn-5ZIoWMLYqNxANGWmQQ,1658
-docling/backend/asciidoc_backend.py,sha256=xBtmYkRkPICIfMbB8AFIw_or4IZGB17mP_LhXorvZ1k,14060
-docling/backend/csv_backend.py,sha256=lCNSkgB55IbAig7w4IyXRkX23aM3Nojj6GdXNoaNjY4,4536
-docling/backend/docling_parse_backend.py,sha256=tcy4cPD_dtGD37CjivbFvwzwXVcrb3HVmofyasxLum8,7991
-docling/backend/docling_parse_v2_backend.py,sha256=70kXqYhht-A8zb9z5emMe_1i0l9dyQGrM8lg1cmAvqc,9369
-docling/backend/docling_parse_v4_backend.py,sha256=IECMJQWEvYqQv043_1Ho6dLkCbuaK8cMUsqcxwqruXo,6287
-docling/backend/docx/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/backend/docx/latex/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/backend/docx/latex/latex_dict.py,sha256=5pOMY_KyxYmgBZ40IrA4q0t5L6JvXOCx5cVwoQE1lls,6690
-docling/backend/docx/latex/omml.py,sha256=5zuXYOQ10e9nSTKFURBjoU-XSQZVHsVyIiCsGYGVAk8,12127
-docling/backend/html_backend.py,sha256=ghPLZfdBEPBzLIO9IWzzx0t1Os9B9r4VyGyEZtMsZVI,19468
-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=lqDiKIBHGsA0u-H1n9oVpPlrcpVT4gYRuNXXcyGlftM,17219
-docling/backend/msexcel_backend.py,sha256=KRPoHRDv-mqko9RUHGQCzdRrvDo7g7zSU2Z5zoL_Hzo,18106
-docling/backend/mspowerpoint_backend.py,sha256=X55-1anXm562wxAuYn5uwQkqKjirmgrn1KfbeaKUbXw,17273
-docling/backend/msword_backend.py,sha256=CgNPjU8SQ7rkAYH_BGiUyv568MGhoH3R0M39WBT8gkc,32468
-docling/backend/pdf_backend.py,sha256=odWb1rxk3WCUIEJMhq-dYFNUQ1pSDuNHbU9wlTZIRAs,2211
-docling/backend/pypdfium2_backend.py,sha256=wRwhA5XHRqL7vyNhCAHM6P-ONkwtyjKG9LgC4NJ-4i8,10784
-docling/backend/xml/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/backend/xml/jats_backend.py,sha256=HXailrDjiwu4swwFnXy3lNfRtLZmkBBp4yqafCvdr7s,24945
-docling/backend/xml/uspto_backend.py,sha256=H0jwIt2skOke_yEUk0wfXCtodrB-hrj2ygLtB3jMWaI,71056
-docling/chunking/__init__.py,sha256=h83TDs0AuOV6oEPLAPrn9dpGKiU-2Vg6IRNo4cv6GDA,346
-docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/cli/main.py,sha256=TD-cEf4giuk1O5NPoB-heXHHteUqKoLsj4Rg4xsBUrs,26119
-docling/cli/models.py,sha256=tM_qbMM3YOPxFU7JlME96MLbtd1CX_bOAK7FS-NhJvY,3979
-docling/cli/tools.py,sha256=QhtRxQG0TVrfsMqdv5i7J0_qQy1ZZyWYnHPwJl7b5oY,322
-docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/datamodel/base_models.py,sha256=fJfFMaHXc-CUrAVfhPF8lKrdb-gaXr2tohx6dHldvRU,7926
-docling/datamodel/document.py,sha256=V0iK1MYOkPIzd4eQa-G8unp-t01fktlG9wwQ1IwE6Zg,15109
-docling/datamodel/pipeline_options.py,sha256=iGLijZR-YOtmg0RQs59pqoG_1uGsDYbg5wMDD0FWYx4,13351
-docling/datamodel/settings.py,sha256=bNMdowIKv7RUchabQTo4rFNEsxfB6pGg2LoZSY634zo,1869
-docling/document_converter.py,sha256=LCX92FzgmXNJLFVSQfjqH9SGe3zA7FGwARedSigFIpY,13798
-docling/exceptions.py,sha256=K1WnCS1leK2JtMB5ewZWKkb0EaijFgl-tRzrO9ntgPM,134
-docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/models/api_vlm_model.py,sha256=6SxMsFPf0SbT365P67KspdpF3TXZSeu5kmPE3lXAhW4,2470
-docling/models/base_model.py,sha256=9xJ0VIlpR2BzqoEWMC8LYp5Y96QAEKip4b_HCwCDltY,2931
-docling/models/base_ocr_model.py,sha256=xvKMhE4ZOGkL2GAhpDvrAHLLFps3ZUfxXZ5ctL1lXUw,7226
-docling/models/code_formula_model.py,sha256=mOu5luYMzyrCCr8MRGOciNcSvULpQysDd_FXn96WPc8,11477
-docling/models/document_picture_classifier.py,sha256=fz77RsTdlnA_yC47O-KUq2xVWMKX0_9jm_EGcHliw-E,6235
-docling/models/easyocr_model.py,sha256=ezq3yv5lORe7T1bbSoTZALck2oHqyEHq57cRfhMYCCQ,7401
-docling/models/factories/__init__.py,sha256=e4lFmRfmW5hWqvJjY5xaVFbvCQhDBCrVeSq85Q2K_aM,872
-docling/models/factories/base_factory.py,sha256=pNR9-B_BKs2sYNyHnp2ON2l3r6Dy9lcof4qmwHlAryI,4032
-docling/models/factories/ocr_factory.py,sha256=G5RkmkKvkl-ihpo6qSj8WC77VdlVSQ1s0ekwUX2ILts,316
-docling/models/factories/picture_description_factory.py,sha256=Ru3-TnVVEKf5O07C_UpGf2HCOHc7j20AJzfficw3agM,385
-docling/models/hf_mlx_model.py,sha256=2eSHphJm5LAfiSA24blVMc2znJlKMYrtmmzq8ffc-rU,4924
-docling/models/hf_vlm_model.py,sha256=NUtLEuG-kNGJeDHWmQKAAOZG4WF0a5hn-KXUUM1mHBQ,6820
-docling/models/layout_model.py,sha256=7fQWipGV1HDrvbP4uOKa9QAicQl89jp7lailQmbFL3w,7804
-docling/models/ocr_mac_model.py,sha256=2pZaUWg19go_u88mKWr5y_52PAYEN__GsbyUYLdY4zo,5353
-docling/models/page_assemble_model.py,sha256=ivkCdbZJpFcGl7CazLegcP1tLK8ZixDfVhQXqsdW_UA,6359
-docling/models/page_preprocessing_model.py,sha256=Ja7RE1K-2fWxWrxOzNm6QDSGqFf-MY6_uY5OAZ7AQSo,3078
-docling/models/picture_description_api_model.py,sha256=DowWOU93MXAjj3N1A9ex88Sa3Nic2c3dfoOYir5jZEA,2064
-docling/models/picture_description_base_model.py,sha256=khuhQZDAZemZMe4BsrBMpjEwkY3nhMFXuczjQpSQrVY,2971
-docling/models/picture_description_vlm_model.py,sha256=I2Un3vfhQVeWEyZ3Sd3Kygw9la2QSZCwDfl_7XVlMm4,4042
-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=C_I0Ek9mAPIyTFRHuNbqtXg1c15rLNDE1tJ6_hPIi4c,5869
-docling/models/readingorder_model.py,sha256=hNWbBX3uZv1FxMwKNKn2JFQuQqTspBLsJBVEidXr6Wk,14869
-docling/models/table_structure_model.py,sha256=pvTsqUa5QIANBUfot0XXG1UUeku-eaUi04EPE-Yh2g0,12597
-docling/models/tesseract_ocr_cli_model.py,sha256=CZ1W0QbvveIpXO0qSXmXFqz71P4PfLfJBQIqU_Wlg_E,10072
-docling/models/tesseract_ocr_model.py,sha256=UpLAgKgJtBgbKtJELmKBNMcejJJKBCyFK0q-WgZN1Eg,9256
-docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/pipeline/base_pipeline.py,sha256=9ABK-Cr235bxE5vweoIA5rgBZV_EF8qFxAqLI27H_Pg,8749
-docling/pipeline/simple_pipeline.py,sha256=mZqANqUtAOFAyqQEShErQnAUz6tJFOl6zVoazEDJ_wE,2254
-docling/pipeline/standard_pdf_pipeline.py,sha256=gPNqUparhIONG4AyMekW9OfZ7t8YMs0odhtbE6Z-Hxw,10784
-docling/pipeline/vlm_pipeline.py,sha256=dqQYAd3viW577TVSZltnB4P-f-ZUWQh0J8SSFDuQN6Q,9738
-docling/py.typed,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-docling/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/utils/accelerator_utils.py,sha256=ONNRrC8fH-8E93WUCNhfOq1t7WrQ1T7-YsmExTOY5f0,2292
-docling/utils/api_image_request.py,sha256=_CgdzmPqdsyXmyYUFGLZcXcoH586qC6A1p5vsNbj1Q0,1416
-docling/utils/export.py,sha256=4W-ptI1fLdVrtoqHdHY1RF9Xn2Yescs-hunITqxJ7Is,4697
-docling/utils/glm_utils.py,sha256=W4JRoP0xQ6SJmhhIoAfcKxm5dr1CFvLHp8pqI1kdhxs,12250
-docling/utils/layout_postprocessor.py,sha256=Q36DfcIYMuMfC6LzCBIrYtHK7pBE-Xyvjepz660s9UM,24508
-docling/utils/locks.py,sha256=RzqQtD5UispgV71pGN_nU6GYfeN11BN0Sh_Dq9ycqGo,52
-docling/utils/model_downloader.py,sha256=sxAQvjiIu9m2Ur5Ot5C5SATmgWJAHi0xSjzxj8QXYJk,3213
-docling/utils/ocr_utils.py,sha256=F7iOOjqolUcImUzir4qjDQd4QWSO3s6JC4WRn3U7uY4,263
-docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
-docling/utils/utils.py,sha256=0ozCk7zUkYzxRVmYoIB2zA1lqjQOuaQzxfGuf1wmKW4,1866
-docling/utils/visualization.py,sha256=tY2ylE2aiQKkmzlSLnFW-HTfFyqUUMguW18ldd1PLfo,2868
-docling-2.30.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.30.0.dist-info/METADATA,sha256=HSI154YUnSDJE8BMMjOuu-U3EXQg0ksFuyuyzv7-UdU,9982
-docling-2.30.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-docling-2.30.0.dist-info/entry_points.txt,sha256=pIxel-UeVo1S7FhoNG5xgEfPjLZfBLi_N9TsGPtJSLo,144
-docling-2.30.0.dist-info/RECORD,,