docling 1.2.0__tar.gz → 1.2.1__tar.gz

{docling-1.2.0 → docling-1.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 1.2.0
+Version: 1.2.1
 Summary: Docling PDF conversion package
 Home-page: https://github.com/DS4SD/docling
 License: MIT
@@ -21,6 +21,7 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Provides-Extra: easyocr
 Provides-Extra: ocr
+Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: deepsearch-glm (>=0.19.0,<1)
 Requires-Dist: docling-core (>=1.1.2,<2.0.0)
 Requires-Dist: docling-ibm-models (>=1.1.0,<2.0.0)
@@ -93,17 +94,21 @@ print(doc.export_to_markdown())  # output: "## DocLayNet: A Large Human-Annotate
 
 ### Convert a batch of documents
 
-For an example of batch-converting documents, see [convert.py](https://github.com/DS4SD/docling/blob/main/examples/convert.py).
+For an example of batch-converting documents, see [batch_convert.py](https://github.com/DS4SD/docling/blob/main/examples/batch_convert.py).
 
 From a local repo clone, you can run it with:
 
 ```
-python examples/convert.py
+python examples/batch_convert.py
 ```
 The output of the above command will be written to `./scratch`.
 
 ### Adjust pipeline features
 
+The example file [custom_convert.py](https://github.com/DS4SD/docling/blob/main/examples/custom_convert.py) contains multiple ways
+one can adjust the conversion pipeline and features.
+
+
 #### Control pipeline options
 
 You can control if table structure recognition or OCR should be performed by arguments passed to `DocumentConverter`:

{docling-1.2.0 → docling-1.2.1}/README.md

@@ -56,17 +56,21 @@ print(doc.export_to_markdown())  # output: "## DocLayNet: A Large Human-Annotate
 
 ### Convert a batch of documents
 
-For an example of batch-converting documents, see [convert.py](https://github.com/DS4SD/docling/blob/main/examples/convert.py).
+For an example of batch-converting documents, see [batch_convert.py](https://github.com/DS4SD/docling/blob/main/examples/batch_convert.py).
 
 From a local repo clone, you can run it with:
 
 ```
-python examples/convert.py
+python examples/batch_convert.py
 ```
 The output of the above command will be written to `./scratch`.
 
 ### Adjust pipeline features
 
+The example file [custom_convert.py](https://github.com/DS4SD/docling/blob/main/examples/custom_convert.py) contains multiple ways
+one can adjust the conversion pipeline and features.
+
+
 #### Control pipeline options
 
 You can control if table structure recognition or OCR should be performed by arguments passed to `DocumentConverter`:

{docling-1.2.0 → docling-1.2.1}/docling/backend/abstract_backend.py

@@ -35,7 +35,7 @@ class PdfPageBackend(ABC):
 
 class PdfDocumentBackend(ABC):
     @abstractmethod
-    def __init__(self, path_or_stream: Iterable[Union[BytesIO, Path]]):
+    def __init__(self, path_or_stream: Union[BytesIO, Path]):
         pass
 
     @abstractmethod

{docling-1.2.0 → docling-1.2.1}/docling/backend/docling_parse_backend.py

@@ -146,11 +146,12 @@ class DoclingParsePageBackend(PdfPageBackend):
 
 
 class DoclingParseDocumentBackend(PdfDocumentBackend):
-    def __init__(self, path_or_stream: Iterable[Union[BytesIO, Path]]):
+    def __init__(self, path_or_stream: Union[BytesIO, Path]):
         super().__init__(path_or_stream)
         self._pdoc = pdfium.PdfDocument(path_or_stream)
         # Parsing cells with docling_parser call
-        print("PARSING WITH DOCLING PARSE")
+        if isinstance(path_or_stream, BytesIO):
+            raise NotImplemented("This backend does not support byte streams yet.")
         parser = pdf_parser()
         self._parser_doc = parser.find_cells(str(path_or_stream))
 

{docling-1.2.0 → docling-1.2.1}/docling/backend/pypdfium2_backend.py

@@ -199,7 +199,7 @@ class PyPdfiumPageBackend(PdfPageBackend):
 
 
 class PyPdfiumDocumentBackend(PdfDocumentBackend):
-    def __init__(self, path_or_stream: Iterable[Union[BytesIO, Path]]):
+    def __init__(self, path_or_stream: Union[BytesIO, Path]):
         super().__init__(path_or_stream)
         self._pdoc = pdfium.PdfDocument(path_or_stream)
 

{docling-1.2.0 → docling-1.2.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "1.2.0"  # DO NOT EDIT, updated automatically
+version = "1.2.1"  # DO NOT EDIT, updated automatically
 description = "Docling PDF conversion package"
 authors = ["Christoph Auer <cau@zurich.ibm.com>", "Michele Dolfi <dol@zurich.ibm.com>", "Maxim Lysak <mly@zurich.ibm.com>", "Nikos Livathinos <nli@zurich.ibm.com>", "Ahmed Nassar <ahn@zurich.ibm.com>", "Peter Staar <taa@zurich.ibm.com>"]
 license = "MIT"
@@ -33,6 +33,7 @@ huggingface_hub = ">=0.23,<1"
 requests = "^2.32.3"
 easyocr = { version = "^1.7", optional = true }
 docling-parse = "^0.0.1"
+certifi = ">=2024.7.4"
 
 [tool.poetry.group.dev.dependencies]
 black = {extras = ["jupyter"], version = "^24.4.2"}