docling 1.0.2__py3-none-any.whl → 1.1.1__py3-none-any.whl

docling/backend/pypdfium2_backend.py

@@ -201,13 +201,7 @@ class PyPdfiumPageBackend(PdfPageBackend):
 class PyPdfiumDocumentBackend(PdfDocumentBackend):
     def __init__(self, path_or_stream: Iterable[Union[BytesIO, Path]]):
         super().__init__(path_or_stream)
-
-        if isinstance(path_or_stream, Path):
-            self._pdoc = pdfium.PdfDocument(path_or_stream)
-        elif isinstance(path_or_stream, BytesIO):
-            self._pdoc = pdfium.PdfDocument(
-                path_or_stream
-            )  # TODO Fix me, won't accept bytes.
+        self._pdoc = pdfium.PdfDocument(path_or_stream)
 
     def page_count(self) -> int:
         return len(self._pdoc)

docling/document_converter.py

@@ -1,11 +1,15 @@
 import functools
 import logging
+import tempfile
 import time
 import traceback
 from pathlib import Path
 from typing import Iterable, Optional, Type, Union
 
+import requests
+from docling_core.types import Document
 from PIL import ImageDraw
+from pydantic import AnyHttpUrl, TypeAdapter, ValidationError
 
 from docling.backend.abstract_backend import PdfDocumentBackend
 from docling.datamodel.base_models import (
@@ -32,6 +36,7 @@ _log = logging.getLogger(__name__)
 class DocumentConverter:
     _layout_model_path = "model_artifacts/layout/beehive_v0.0.5"
     _table_model_path = "model_artifacts/tableformer"
+    _default_download_filename = "file.pdf"
 
     def __init__(
         self,
@@ -80,6 +85,57 @@ class DocumentConverter:
             # Note: Pdfium backend is not thread-safe, thread pool usage was disabled.
             yield from map(self.process_document, input_batch)
 
+    def convert_single(self, source: Path | AnyHttpUrl | str) -> Document:
+        """Convert a single document.
+
+        Args:
+            source (Path | AnyHttpUrl | str): The PDF input source. Can be a path or URL.
+
+        Raises:
+            ValueError: If source is of unexpected type.
+            RuntimeError: If conversion fails.
+
+        Returns:
+            Document: The converted document object.
+        """
+        with tempfile.TemporaryDirectory() as temp_dir:
+            try:
+                http_url: AnyHttpUrl = TypeAdapter(AnyHttpUrl).validate_python(source)
+                res = requests.get(http_url, stream=True)
+                res.raise_for_status()
+                fname = None
+                # try to get filename from response header
+                if cont_disp := res.headers.get("Content-Disposition"):
+                    for par in cont_disp.strip().split(";"):
+                        # currently only handling directive "filename" (not "*filename")
+                        if (split := par.split("=")) and split[0].strip() == "filename":
+                            fname = "=".join(split[1:]).strip().strip("'\"") or None
+                            break
+                # otherwise, use name from URL:
+                if fname is None:
+                    fname = Path(http_url.path).name or self._default_download_filename
+                local_path = Path(temp_dir) / fname
+                with open(local_path, "wb") as f:
+                    for chunk in res.iter_content(chunk_size=1024):  # using 1-KB chunks
+                        f.write(chunk)
+            except ValidationError:
+                try:
+                    local_path = TypeAdapter(Path).validate_python(source)
+                except ValidationError:
+                    raise ValueError(
+                        f"Unexpected file path type encountered: {type(source)}"
+                    )
+            conv_inp = DocumentConversionInput.from_paths(paths=[local_path])
+            converted_docs_iter = self.convert(conv_inp)
+            converted_doc: ConvertedDocument = next(converted_docs_iter)
+        if converted_doc.status not in {
+            ConversionStatus.SUCCESS,
+            ConversionStatus.SUCCESS_WITH_ERRORS,
+        }:
+            raise RuntimeError(f"Conversion failed with status: {converted_doc.status}")
+        doc = converted_doc.to_ds_document()
+        return doc
+
     def process_document(self, in_doc: InputDocument) -> ConvertedDocument:
         start_doc_time = time.time()
         converted_doc = ConvertedDocument(input=in_doc)

docling/models/table_structure_model.py

@@ -114,12 +114,15 @@ class TableStructureModel:
                     for element in table_out["tf_responses"]:
 
                         if not self.do_cell_matching:
-                            the_bbox = BoundingBox.model_validate(element["bbox"])
+                            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)
-                        tc.bbox = tc.bbox.scaled(1 / self.scale)
+                        if self.do_cell_matching:
+                            tc.bbox = tc.bbox.scaled(1 / self.scale)
                         table_cells.append(tc)
 
                     # Retrieving cols/rows, after post processing:

{docling-1.0.2.dist-info → docling-1.1.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 1.0.2
+Version: 1.1.1
 Summary: Docling PDF conversion package
 Home-page: https://github.com/DS4SD/docling
 License: MIT
@@ -30,6 +30,7 @@ Requires-Dist: huggingface_hub (>=0.23,<1)
 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)
+Requires-Dist: requests (>=2.32.3,<3.0.0)
 Project-URL: Repository, https://github.com/DS4SD/docling
 Description-Content-Type: text/markdown
 
@@ -65,19 +66,35 @@ To use Docling, simply install `docling` from your package manager, e.g. pip:
 pip install docling
 ```
 
-> [!NOTE]  
+> [!NOTE]
 > Works on macOS and Linux environments. Windows platforms are currently not tested.
 
 ### Development setup
 
 To develop for Docling, you need Python 3.10 / 3.11 / 3.12 and Poetry. You can then install from your local clone's root dir:
 ```bash
-poetry install
+poetry install --all-extras
 ```
 
 ## Usage
 
-For basic usage, see the [convert.py](https://github.com/DS4SD/docling/blob/main/examples/convert.py) example module. Run with:
+### Convert a single document
+
+To convert invidual PDF documents, use `convert_single()`, for example:
+```python
+from docling.document_converter import DocumentConverter
+
+source = "https://arxiv.org/pdf/2206.01062"  # PDF path or URL
+converter = DocumentConverter()
+doc = converter.convert_single(source)
+print(doc.export_to_markdown())  # output: "## DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis [...]"
+```
+
+### Convert a batch of documents
+
+For an example of converting multiple documents, see [convert.py](https://github.com/DS4SD/docling/blob/main/examples/convert.py).
+
+From a local repo clone, you can run it with:
 
 ```
 python examples/convert.py
@@ -93,7 +110,7 @@ You can control if table structure recognition or OCR should be performed by arg
 doc_converter = DocumentConverter(
     artifacts_path=artifacts_path,
     pipeline_options=PipelineOptions(
-        do_table_structure=False,  # controls if table structure is recovered 
+        do_table_structure=False,  # controls if table structure is recovered
         do_ocr=True,  # controls if OCR is applied (ignores programmatic content)
     ),
 )
@@ -125,7 +142,7 @@ conv_input = DocumentConversionInput.from_paths(
 )
 ```
 
-### Convert from binary PDF streams 
+### Convert from binary PDF streams
 
 You can convert PDFs from a binary stream instead of from the filesystem as follows:
 ```python

{docling-1.0.2.dist-info → docling-1.1.1.dist-info}/RECORD

@@ -1,25 +1,25 @@
 docling/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/backend/abstract_backend.py,sha256=dINr8oTax9Fq31Y1AR0CGWNZtAHN5aqB_M7TAPkJNVQ,1122
-docling/backend/pypdfium2_backend.py,sha256=sJMoActFyc3qdKB6RFly3auHXuXM4noQAG0ypUlj26o,7647
+docling/backend/pypdfium2_backend.py,sha256=cIQGFkwzceN57PzmACt06CytRo0A_t-im6rW804RC3M,7421
 docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/datamodel/base_models.py,sha256=k7gLFPnq3ArEMAFz6qUcp5qemlYzVhOmR9qtBTkAiX4,6862
 docling/datamodel/document.py,sha256=7caefzaii6itMQgtXfA4SJhB1TAF32v1c8zRwbiU03s,12497
 docling/datamodel/settings.py,sha256=t5g6wrEJnPa9gBzMMl8ppgBRUYz-8xgopEtfMS0ZH28,733
-docling/document_converter.py,sha256=MZw23oPlRmRi1ggzoD1PukUnqo-6boO3RZB06dZ5Xt0,7305
+docling/document_converter.py,sha256=I9vjTLCLahsMrcs9ozM3C5r_CtBN-9qHk7-ANma7fkc,9895
 docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/models/ds_glm_model.py,sha256=wmb--2JKFQby-kvidw6PyM8wURPXYPQ_Z_eKKCBAdYQ,3192
 docling/models/easyocr_model.py,sha256=NaHVs8IN0eW9KB076E2Kae1s-bq74_4IMWueze9QqtE,2290
 docling/models/layout_model.py,sha256=4AfPFiu6pXc8wIQ1sQlEZnHRt7SnBmfzDdctiRveOWw,10944
 docling/models/page_assemble_model.py,sha256=8eoG2WiFxPxq9TPvM-wkngb2gkr0tdtCRVXg1JcTETo,5550
-docling/models/table_structure_model.py,sha256=ryZrmkNkCbw5SCpgdQabkmcRAEi_4VqOMv2VGdpvGZo,5499
+docling/models/table_structure_model.py,sha256=xUmfunZNYC30P0fRdESdztqy1FVlMzlhJjLBp-xcn4A,5638
 docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/pipeline/base_model_pipeline.py,sha256=ozHdJak0yQAxQf7pQN_C480vI35A2e5KL5Qq1xSkq5c,560
 docling/pipeline/standard_model_pipeline.py,sha256=UTwodKUKrisLoVcntbNUBDhjzRyFvpdUvyVw-gNmBlM,1541
 docling/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/utils/layout_utils.py,sha256=FOFbL0hKzUoWXdZaeUvEtFqKv0IkPifIr4sdGW4suKs,31804
 docling/utils/utils.py,sha256=llhXSbIDNZ1MHOwBEfLHBAoJIAYI7QlPIonlI1jLUJ0,1208
-docling-1.0.2.dist-info/LICENSE,sha256=ACwmltkrXIz5VsEQcrqljq-fat6ZXAMepjXGoe40KtE,1069
-docling-1.0.2.dist-info/METADATA,sha256=U_gVZvm1gsFXII9a6INpjbH64zH00tiHbch3EaJFvgc,6188
-docling-1.0.2.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling-1.0.2.dist-info/RECORD,,
+docling-1.1.1.dist-info/LICENSE,sha256=ACwmltkrXIz5VsEQcrqljq-fat6ZXAMepjXGoe40KtE,1069
+docling-1.1.1.dist-info/METADATA,sha256=hnIPHm49bjWcFKBSCJ-aPsqim6aqHkWZiMdhkQli9Lk,6759
+docling-1.1.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling-1.1.1.dist-info/RECORD,,