docling 2.1.0__py3-none-any.whl → 2.2.1__py3-none-any.whl

docling/datamodel/document.py

@@ -45,6 +45,8 @@ from docling.datamodel.base_models import (
     ConversionStatus,
     DocumentStream,
     ErrorItem,
+    FormatToExtensions,
+    FormatToMimeType,
     InputFormat,
     MimeTypeToFormat,
     Page,
@@ -143,11 +145,13 @@ class InputDocument(BaseModel):
                         self.valid = False
 
         except (FileNotFoundError, OSError) as e:
+            self.valid = False
             _log.exception(
                 f"File {self.file.name} not found or cannot be opened.", exc_info=e
             )
             # raise
         except RuntimeError as e:
+            self.valid = False
             _log.exception(
                 f"An unexpected error occurred while opening the document {self.file.name}",
                 exc_info=e,
@@ -166,6 +170,8 @@ class InputDocument(BaseModel):
             )
 
         self._backend = backend(self, path_or_stream=path_or_stream)
+        if not self._backend.is_valid():
+            self.valid = False
 
 
 class DocumentFormat(str, Enum):
@@ -480,26 +486,48 @@ class _DocumentConversionInput(BaseModel):
             else:
                 raise RuntimeError(f"Unexpected obj type in iterator: {type(obj)}")
 
-    def _guess_format(self, obj):
-        content = None
+    def _guess_format(self, obj: Union[Path, DocumentStream]):
+        content = b""  # empty binary blob
+        format = None
+
         if isinstance(obj, Path):
             mime = filetype.guess_mime(str(obj))
             if mime is None:
+                ext = obj.suffix[1:]
+                mime = self._mime_from_extension(ext)
+            if mime is None:  # must guess from
                 with obj.open("rb") as f:
                     content = f.read(1024)  # Read first 1KB
 
         elif isinstance(obj, DocumentStream):
-            obj.stream.seek(0)
             content = obj.stream.read(8192)
             obj.stream.seek(0)
             mime = filetype.guess_mime(content)
+            if mime is None:
+                ext = (
+                    obj.name.rsplit(".", 1)[-1]
+                    if ("." in obj.name and not obj.name.startswith("."))
+                    else ""
+                )
+                mime = self._mime_from_extension(ext)
 
-        if mime is None:
-            mime = self._detect_html_xhtml(content)
+        mime = mime or self._detect_html_xhtml(content)
+        mime = mime or "text/plain"
 
         format = MimeTypeToFormat.get(mime)
         return format
 
+    def _mime_from_extension(self, ext):
+        mime = None
+        if ext in FormatToExtensions[InputFormat.ASCIIDOC]:
+            mime = FormatToMimeType[InputFormat.ASCIIDOC][0]
+        elif ext in FormatToExtensions[InputFormat.HTML]:
+            mime = FormatToMimeType[InputFormat.HTML][0]
+        elif ext in FormatToExtensions[InputFormat.MD]:
+            mime = FormatToMimeType[InputFormat.MD][0]
+
+        return mime
+
     def _detect_html_xhtml(self, content):
         content_str = content.decode("ascii", errors="ignore").lower()
         # Remove XML comments

docling/document_converter.py

@@ -8,8 +8,10 @@ from typing import Dict, Iterable, Iterator, List, Optional, Type
 from pydantic import BaseModel, ConfigDict, model_validator, validate_call
 
 from docling.backend.abstract_backend import AbstractDocumentBackend
+from docling.backend.asciidoc_backend import AsciiDocBackend
 from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
 from docling.backend.html_backend import HTMLDocumentBackend
+from docling.backend.md_backend import MarkdownDocumentBackend
 from docling.backend.mspowerpoint_backend import MsPowerpointDocumentBackend
 from docling.backend.msword_backend import MsWordDocumentBackend
 from docling.datamodel.base_models import ConversionStatus, DocumentStream, InputFormat
@@ -52,6 +54,16 @@ class PowerpointFormatOption(FormatOption):
     backend: Type[AbstractDocumentBackend] = MsPowerpointDocumentBackend
 
 
+class MarkdownFormatOption(FormatOption):
+    pipeline_cls: Type = SimplePipeline
+    backend: Type[AbstractDocumentBackend] = MarkdownDocumentBackend
+
+
+class AsciiDocFormatOption(FormatOption):
+    pipeline_cls: Type = SimplePipeline
+    backend: Type[AbstractDocumentBackend] = AsciiDocBackend
+
+
 class HTMLFormatOption(FormatOption):
     pipeline_cls: Type = SimplePipeline
     backend: Type[AbstractDocumentBackend] = HTMLDocumentBackend
@@ -74,6 +86,12 @@ _format_to_default_options = {
     InputFormat.PPTX: FormatOption(
         pipeline_cls=SimplePipeline, backend=MsPowerpointDocumentBackend
     ),
+    InputFormat.MD: FormatOption(
+        pipeline_cls=SimplePipeline, backend=MarkdownDocumentBackend
+    ),
+    InputFormat.ASCIIDOC: FormatOption(
+        pipeline_cls=SimplePipeline, backend=AsciiDocBackend
+    ),
     InputFormat.HTML: FormatOption(
         pipeline_cls=SimplePipeline, backend=HTMLDocumentBackend
     ),

{docling-2.1.0.dist-info → docling-2.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.1.0
+Version: 2.2.1
 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 (>=2.2.1,<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="docs/assets/docling_processing.png" width="100%"/>
+    <img loading="lazy" alt="Docling" src="https://github.com/DS4SD/docling/raw/main/docs/assets/docling_processing.png" width="100%"/>
   </a>
 </p>
 
@@ -100,7 +101,7 @@ 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[...]"
@@ -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-2.1.0.dist-info → docling-2.2.1.dist-info}/RECORD

@@ -1,21 +1,23 @@
 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/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=TUY5EVv3bo28A_w5CvBgNW4ZqL1d-VxOQPh1_taPHgU,15070
+docling/backend/md_backend.py,sha256=tmuSCghjor9PqKIiVieCuZ4_t5JEjZMy3cq7u3yTgyU,14032
+docling/backend/mspowerpoint_backend.py,sha256=J472AIH_IXvGg3D0FDmXhue1At_VSBD6n15c64Kxttw,15446
+docling/backend/msword_backend.py,sha256=FAUdP74QxGKo2xMZQ4WQGYwtpIBCTJ_FG17PBpRwhxI,17230
 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=FZQyJtHSeGBrZwFf-GGXDu-Dyp4iIl7VbVnTupmlUqk,19532
+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=S_t9hs2uZfXC38LC0hTaAihrSJIrCvnTiuY5SvUccgk,9587
+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
@@ -35,8 +37,8 @@ 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-2.1.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.1.0.dist-info/METADATA,sha256=SorLD4OMK1dU3bX5eqnw5GHqPrPwdhQ7JfYvOyajE20,6109
-docling-2.1.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling-2.1.0.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
-docling-2.1.0.dist-info/RECORD,,
+docling-2.2.1.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.2.1.dist-info/METADATA,sha256=BOYg-5kaA2Fjxc2bwaJOuAd9LmrQerOzQLHCyaiQ1aE,6205
+docling-2.2.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling-2.2.1.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
+docling-2.2.1.dist-info/RECORD,,