docling 2.38.0__py3-none-any.whl → 2.38.1__py3-none-any.whl

docling/backend/md_backend.py

@@ -2,9 +2,10 @@ import logging
 import re
 import warnings
 from copy import deepcopy
+from enum import Enum
 from io import BytesIO
 from pathlib import Path
-from typing import List, Optional, Set, Union
+from typing import List, Literal, Optional, Set, Union
 
 import marko
 import marko.element
@@ -21,7 +22,8 @@ from docling_core.types.doc import (
 )
 from docling_core.types.doc.document import Formatting, OrderedList, UnorderedList
 from marko import Markdown
-from pydantic import AnyUrl, TypeAdapter
+from pydantic import AnyUrl, BaseModel, Field, TypeAdapter
+from typing_extensions import Annotated
 
 from docling.backend.abstract_backend import DeclarativeDocumentBackend
 from docling.backend.html_backend import HTMLDocumentBackend
@@ -35,6 +37,31 @@ _START_MARKER = f"#_#_{_MARKER_BODY}_START_#_#"
 _STOP_MARKER = f"#_#_{_MARKER_BODY}_STOP_#_#"
 
 
+class _PendingCreationType(str, Enum):
+    """CoordOrigin."""
+
+    HEADING = "heading"
+    LIST_ITEM = "list_item"
+
+
+class _HeadingCreationPayload(BaseModel):
+    kind: Literal["heading"] = "heading"
+    level: int
+
+
+class _ListItemCreationPayload(BaseModel):
+    kind: Literal["list_item"] = "list_item"
+
+
+_CreationPayload = Annotated[
+    Union[
+        _HeadingCreationPayload,
+        _ListItemCreationPayload,
+    ],
+    Field(discriminator="kind"),
+]
+
+
 class MarkdownDocumentBackend(DeclarativeDocumentBackend):
     def _shorten_underscore_sequences(self, markdown_text: str, max_length: int = 10):
         # This regex will match any sequence of underscores
@@ -155,6 +182,52 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
                 doc.add_table(data=table_data)
         return
 
+    def _create_list_item(
+        self,
+        doc: DoclingDocument,
+        parent_item: Optional[NodeItem],
+        text: str,
+        formatting: Optional[Formatting] = None,
+        hyperlink: Optional[Union[AnyUrl, Path]] = None,
+    ):
+        if not isinstance(parent_item, (OrderedList, UnorderedList)):
+            _log.warning("ListItem would have not had a list parent, adding one.")
+            parent_item = doc.add_unordered_list(parent=parent_item)
+        item = doc.add_list_item(
+            text=text,
+            enumerated=(isinstance(parent_item, OrderedList)),
+            parent=parent_item,
+            formatting=formatting,
+            hyperlink=hyperlink,
+        )
+        return item
+
+    def _create_heading_item(
+        self,
+        doc: DoclingDocument,
+        parent_item: Optional[NodeItem],
+        text: str,
+        level: int,
+        formatting: Optional[Formatting] = None,
+        hyperlink: Optional[Union[AnyUrl, Path]] = None,
+    ):
+        if level == 1:
+            item = doc.add_title(
+                text=text,
+                parent=parent_item,
+                formatting=formatting,
+                hyperlink=hyperlink,
+            )
+        else:
+            item = doc.add_heading(
+                text=text,
+                level=level - 1,
+                parent=parent_item,
+                formatting=formatting,
+                hyperlink=hyperlink,
+            )
+        return item
+
     def _iterate_elements(  # noqa: C901
         self,
         *,
@@ -162,6 +235,9 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
         depth: int,
         doc: DoclingDocument,
         visited: Set[marko.element.Element],
+        creation_stack: list[
+            _CreationPayload
+        ],  # stack for lazy item creation triggered deep in marko's AST (on RawText)
         parent_item: Optional[NodeItem] = None,
         formatting: Optional[Formatting] = None,
         hyperlink: Optional[Union[AnyUrl, Path]] = None,
@@ -177,28 +253,17 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
                 f" - Heading level {element.level}, content: {element.children[0].children}"  # type: ignore
             )
 
-            if len(element.children) == 1:
-                child = element.children[0]
-                snippet_text = str(child.children)  # type: ignore
-                visited.add(child)
-            else:
-                snippet_text = ""  # inline group will be created
-
-            if element.level == 1:
-                parent_item = doc.add_title(
-                    text=snippet_text,
-                    parent=parent_item,
+            if len(element.children) > 1:  # inline group will be created further down
+                parent_item = self._create_heading_item(
+                    doc=doc,
+                    parent_item=parent_item,
+                    text="",
+                    level=element.level,
                     formatting=formatting,
                     hyperlink=hyperlink,
                 )
             else:
-                parent_item = doc.add_heading(
-                    text=snippet_text,
-                    level=element.level - 1,
-                    parent=parent_item,
-                    formatting=formatting,
-                    hyperlink=hyperlink,
-                )
+                creation_stack.append(_HeadingCreationPayload(level=element.level))
 
         elif isinstance(element, marko.block.List):
             has_non_empty_list_items = False
@@ -224,22 +289,16 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
             self._close_table(doc)
             _log.debug(" - List item")
 
-            if len(child.children) == 1:
-                snippet_text = str(child.children[0].children)  # type: ignore
-                visited.add(child)
+            if len(child.children) > 1:  # inline group will be created further down
+                parent_item = self._create_list_item(
+                    doc=doc,
+                    parent_item=parent_item,
+                    text="",
+                    formatting=formatting,
+                    hyperlink=hyperlink,
+                )
             else:
-                snippet_text = ""  # inline group will be created
-            is_numbered = isinstance(parent_item, OrderedList)
-            if not isinstance(parent_item, (OrderedList, UnorderedList)):
-                _log.warning("ListItem would have not had a list parent, adding one.")
-                parent_item = doc.add_unordered_list(parent=parent_item)
-            parent_item = doc.add_list_item(
-                enumerated=is_numbered,
-                parent=parent_item,
-                text=snippet_text,
-                formatting=formatting,
-                hyperlink=hyperlink,
-            )
+                creation_stack.append(_ListItemCreationPayload())
 
         elif isinstance(element, marko.inline.Image):
             self._close_table(doc)
@@ -285,13 +344,38 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
                     self.md_table_buffer.append(snippet_text)
             elif snippet_text:
                 self._close_table(doc)
-                doc.add_text(
-                    label=DocItemLabel.TEXT,
-                    parent=parent_item,
-                    text=snippet_text,
-                    formatting=formatting,
-                    hyperlink=hyperlink,
-                )
+
+                if creation_stack:
+                    while len(creation_stack) > 0:
+                        to_create = creation_stack.pop()
+                        if isinstance(to_create, _ListItemCreationPayload):
+                            parent_item = self._create_list_item(
+                                doc=doc,
+                                parent_item=parent_item,
+                                text=snippet_text,
+                                formatting=formatting,
+                                hyperlink=hyperlink,
+                            )
+                        elif isinstance(to_create, _HeadingCreationPayload):
+                            # not keeping as parent_item as logic for correctly tracking
+                            # that not implemented yet (section components not captured
+                            # as heading children in marko)
+                            self._create_heading_item(
+                                doc=doc,
+                                parent_item=parent_item,
+                                text=snippet_text,
+                                level=to_create.level,
+                                formatting=formatting,
+                                hyperlink=hyperlink,
+                            )
+                else:
+                    doc.add_text(
+                        label=DocItemLabel.TEXT,
+                        parent=parent_item,
+                        text=snippet_text,
+                        formatting=formatting,
+                        hyperlink=hyperlink,
+                    )
 
         elif isinstance(element, marko.inline.CodeSpan):
             self._close_table(doc)
@@ -353,7 +437,6 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
             parent_item = doc.add_inline_group(parent=parent_item)
 
         processed_block_types = (
-            # marko.block.Heading,
             marko.block.CodeBlock,
             marko.block.FencedCode,
             marko.inline.RawText,
@@ -369,6 +452,7 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
                     depth=depth + 1,
                     doc=doc,
                     visited=visited,
+                    creation_stack=creation_stack,
                     parent_item=parent_item,
                     formatting=formatting,
                     hyperlink=hyperlink,
@@ -412,6 +496,7 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
                 doc=doc,
                 parent_item=None,
                 visited=set(),
+                creation_stack=[],
             )
             self._close_table(doc=doc)  # handle any last hanging table
 

docling/backend/msword_backend.py

@@ -397,7 +397,11 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
             if isinstance(c, Hyperlink):
                 text = c.text
                 hyperlink = Path(c.address)
-                format = self._get_format_from_run(c.runs[0])
+                format = (
+                    self._get_format_from_run(c.runs[0])
+                    if c.runs and len(c.runs) > 0
+                    else None
+                )
             elif isinstance(c, Run):
                 text = c.text
                 hyperlink = None

docling/datamodel/base_models.py

@@ -301,7 +301,7 @@ class OpenAiChatMessage(BaseModel):
 class OpenAiResponseChoice(BaseModel):
     index: int
     message: OpenAiChatMessage
-    finish_reason: str
+    finish_reason: Optional[str]
 
 
 class OpenAiResponseUsage(BaseModel):

docling/datamodel/pipeline_options.py

@@ -207,7 +207,7 @@ smolvlm_picture_description = PictureDescriptionVlmOptions(
 
 # GraniteVision
 granite_picture_description = PictureDescriptionVlmOptions(
-    repo_id="ibm-granite/granite-vision-3.1-2b-preview",
+    repo_id="ibm-granite/granite-vision-3.2-2b-preview",
     prompt="What is shown in this image?",
 )
 

{docling-2.38.0.dist-info → docling-2.38.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docling
-Version: 2.38.0
+Version: 2.38.1
 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.
 Author-email: 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>, Panos Vagenas <pva@zurich.ibm.com>, Peter Staar <taa@zurich.ibm.com>
 License-Expression: MIT

{docling-2.38.0.dist-info → docling-2.38.1.dist-info}/RECORD

@@ -10,10 +10,10 @@ docling/backend/docling_parse_backend.py,sha256=9rUo1vPxX6QLzGqF-2B2iEYglZg6YQ3U
 docling/backend/docling_parse_v2_backend.py,sha256=3ckTfke8IICjaImlIzc3TRhG7KDuxDDba0AuCEcjA-M,9500
 docling/backend/docling_parse_v4_backend.py,sha256=7tQvpCwpYoq98PNszDkrXaFhy5eWmQqMP4RjWWPLPgw,6197
 docling/backend/html_backend.py,sha256=3K-l5SUAAyqISNEb7nPst_I51xzYOVOkgmwXh3lv9sw,21063
-docling/backend/md_backend.py,sha256=ghIU_NSaENKrRu49Dn5GvjYtcAgEU7ZHbf-TeYg49nY,17673
+docling/backend/md_backend.py,sha256=kSQ7dn_IrAmt53kL_0Z5LnpE2fWif9RkBAGtqzgfQaM,20514
 docling/backend/msexcel_backend.py,sha256=3j0WQfqDpgPXdPMCguefdv7arcNVDedPD6gl54cmLn8,18110
 docling/backend/mspowerpoint_backend.py,sha256=0lsb8ZeQFxbDt7jZpSQyk5wYHYa3SP2T2y2dMI-o30o,15216
-docling/backend/msword_backend.py,sha256=C4qs4mQEt1JzonCg5v6_yUxdngzcTzSO9k1ik8_DW5Q,44855
+docling/backend/msword_backend.py,sha256=xj009k1s7uzmNx3yGZZelsSgxa6ylaJ1yYHxYfHVLOo,44975
 docling/backend/noop_backend.py,sha256=EOPbD86FzZPX-K_DpNrJh0_lC0bZz--4DpG-OagDNGY,1688
 docling/backend/pdf_backend.py,sha256=KE9TMuFO5WX-o5A_DAd4tEaLi4HMZ4XjKdpllItVkWM,2238
 docling/backend/pypdfium2_backend.py,sha256=8dVniLHgiTdJuDbYr66kPp6Ccv5ZDlqDMEbA2xIfS7U,13370
@@ -34,9 +34,9 @@ docling/cli/tools.py,sha256=QhtRxQG0TVrfsMqdv5i7J0_qQy1ZZyWYnHPwJl7b5oY,322
 docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/datamodel/accelerator_options.py,sha256=wv6dOFTVAwr9onkE-0pfUqX_fDb6gX53iPPE6o8nKjI,2511
 docling/datamodel/asr_model_specs.py,sha256=L7ETXsUKVbPsVcPLhEIMxQjd4UzMGZBVsy74CLsZBkU,2181
-docling/datamodel/base_models.py,sha256=L35qXLmADZQNEzBC0M6K2xrfLyqrTqDlbPD6E6DkWMc,11146
+docling/datamodel/base_models.py,sha256=67o1ptOTT8tW7i-g6gM2JKEX_1CDbmKEMQ_B9ZYM2z0,11156
 docling/datamodel/document.py,sha256=CA_dgt4V_phze5HXpfgfKNBKd1cPC1o3WE_IENX63EM,16252
-docling/datamodel/pipeline_options.py,sha256=N7my7hmvuX6EzlujHeF6RObPSrG_HjN_nfPzILTqP-E,9479
+docling/datamodel/pipeline_options.py,sha256=7mKv1IThXYpu3osggp_Y2h7E5C8nbxJLQXS7JJPMvYQ,9479
 docling/datamodel/pipeline_options_asr_model.py,sha256=7X068xl-qpbyPxC7-TwX7Q6tLyZXGT5h1osZ_xLNLM0,1454
 docling/datamodel/pipeline_options_vlm_model.py,sha256=rtDMVtKFZbgQD269w8FvHMXEhdRBrsA4rVYk6A-M-b4,2063
 docling/datamodel/settings.py,sha256=ajMz7Ao2m0ZGYkfArqTDDbiF89O408mtgeh06PUi0MA,1900
@@ -90,9 +90,9 @@ docling/utils/orientation.py,sha256=xXlOfowL54FKwjsTFrM7y3ogk1wChLNn_-u74tYIf1s,
 docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
 docling/utils/utils.py,sha256=kJtIYuzXeOyJHYlxmLAo7dGM5rEsDa1i84qEsUj1nio,1908
 docling/utils/visualization.py,sha256=tY2ylE2aiQKkmzlSLnFW-HTfFyqUUMguW18ldd1PLfo,2868
-docling-2.38.0.dist-info/licenses/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.38.0.dist-info/METADATA,sha256=vT8Zko4wD8iyKUjLAJ83Cm7ntscjEk5ojHvcJXlvT5A,10273
-docling-2.38.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-docling-2.38.0.dist-info/entry_points.txt,sha256=hzVlbeE0aMSTQ9S0-NTYN0Hmgsn6qL_EA2qX4UbkAuY,149
-docling-2.38.0.dist-info/top_level.txt,sha256=vkIywP-USjFyYo1AIRQbWQQaL3xB5jf8vkCYdTIfNic,8
-docling-2.38.0.dist-info/RECORD,,
+docling-2.38.1.dist-info/licenses/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.38.1.dist-info/METADATA,sha256=14E9MwQXlyuB4nWa31ZTjW6vvv5p2eCs2xxVTE4-qT4,10273
+docling-2.38.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+docling-2.38.1.dist-info/entry_points.txt,sha256=hzVlbeE0aMSTQ9S0-NTYN0Hmgsn6qL_EA2qX4UbkAuY,149
+docling-2.38.1.dist-info/top_level.txt,sha256=vkIywP-USjFyYo1AIRQbWQQaL3xB5jf8vkCYdTIfNic,8
+docling-2.38.1.dist-info/RECORD,,