docling 2.28.0__tar.gz → 2.28.2__tar.gz

{docling-2.28.0 → docling-2.28.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.28.0
+Version: 2.28.2
 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

{docling-2.28.0 → docling-2.28.2}/docling/backend/html_backend.py

@@ -206,9 +206,9 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
         hlevel = int(element.name.replace("h", ""))
         text = element.text.strip()
 
-        if hlevel == 1:
-            self.content_layer = ContentLayer.BODY
+        self.content_layer = ContentLayer.BODY
 
+        if hlevel == 1:
             for key in self.parents.keys():
                 self.parents[key] = None
 
@@ -243,7 +243,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
             self.parents[hlevel] = doc.add_heading(
                 parent=self.parents[hlevel - 1],
                 text=text,
-                level=hlevel,
+                level=hlevel - 1,
                 content_layer=self.content_layer,
             )
 

{docling-2.28.0 → docling-2.28.2}/docling/backend/md_backend.py

@@ -212,9 +212,16 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
             traverse(element)
             snippet_text = "".join(strings)
             if len(snippet_text) > 0:
-                parent_item = doc.add_text(
-                    label=doc_label, parent=parent_item, text=snippet_text
-                )
+                if doc_label == DocItemLabel.SECTION_HEADER:
+                    parent_item = doc.add_heading(
+                        text=snippet_text,
+                        level=element.level - 1,
+                        parent=parent_item,
+                    )
+                else:
+                    parent_item = doc.add_text(
+                        label=doc_label, parent=parent_item, text=snippet_text
+                    )
 
         elif isinstance(element, marko.block.List):
             has_non_empty_list_items = False
@@ -232,12 +239,15 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
                     label=label, name=f"list", parent=parent_item
                 )
 
-        elif isinstance(element, marko.block.ListItem) and len(element.children) > 0:
+        elif (
+            isinstance(element, marko.block.ListItem)
+            and len(element.children) > 0
+            and isinstance((first_child := element.children[0]), marko.block.Paragraph)
+        ):
             self._close_table(doc)
             self._process_inline_text(parent_item, doc)
             _log.debug(" - List item")
 
-            first_child = element.children[0]
             snippet_text = str(first_child.children[0].children)  # type: ignore
             is_numbered = False
             if (

{docling-2.28.0 → docling-2.28.2}/docling/backend/msword_backend.py

@@ -53,6 +53,7 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
         self.max_levels: int = 10
         self.level_at_new_list: Optional[int] = None
         self.parents: dict[int, Optional[NodeItem]] = {}
+        self.numbered_headers: dict[int, int] = {}
         for i in range(-1, self.max_levels):
             self.parents[i] = None
 
@@ -346,7 +347,14 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
                 parent=None, label=DocItemLabel.TITLE, text=text
             )
         elif "Heading" in p_style_id:
-            self.add_header(doc, p_level, text)
+            style_element = getattr(paragraph.style, "element", None)
+            if style_element:
+                is_numbered_style = (
+                    "<w:numPr>" in style_element.xml or "<w:numPr>" in element.xml
+                )
+            else:
+                is_numbered_style = False
+            self.add_header(doc, p_level, text, is_numbered_style)
 
         elif len(equations) > 0:
             if (raw_text is None or len(raw_text) == 0) and len(text) > 0:
@@ -415,7 +423,11 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
         return
 
     def add_header(
-        self, doc: DoclingDocument, curr_level: Optional[int], text: str
+        self,
+        doc: DoclingDocument,
+        curr_level: Optional[int],
+        text: str,
+        is_numbered_style: bool = False,
     ) -> None:
         level = self.get_level()
         if isinstance(curr_level, int):
@@ -433,17 +445,44 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
                     if key >= curr_level:
                         self.parents[key] = None
 
-            self.parents[curr_level] = doc.add_heading(
-                parent=self.parents[curr_level - 1],
-                text=text,
-                level=curr_level,
-            )
+            current_level = curr_level
+            parent_level = curr_level - 1
+            add_level = curr_level
         else:
-            self.parents[self.level] = doc.add_heading(
-                parent=self.parents[self.level - 1],
-                text=text,
-                level=1,
-            )
+            current_level = self.level
+            parent_level = self.level - 1
+            add_level = 1
+
+        if is_numbered_style:
+            if add_level in self.numbered_headers:
+                self.numbered_headers[add_level] += 1
+            else:
+                self.numbered_headers[add_level] = 1
+            text = f"{self.numbered_headers[add_level]} {text}"
+
+            # Reset deeper levels
+            next_level = add_level + 1
+            while next_level in self.numbered_headers:
+                self.numbered_headers[next_level] = 0
+                next_level += 1
+
+            # Scan upper levels
+            previous_level = add_level - 1
+            while previous_level in self.numbered_headers:
+                # MSWord convention: no empty sublevels
+                # I.e., sub-sub section (2.0.1) without a sub-section (2.1)
+                # is processed as 2.1.1
+                if self.numbered_headers[previous_level] == 0:
+                    self.numbered_headers[previous_level] += 1
+
+                text = f"{self.numbered_headers[previous_level]}.{text}"
+                previous_level -= 1
+
+        self.parents[current_level] = doc.add_heading(
+            parent=self.parents[parent_level],
+            text=text,
+            level=add_level,
+        )
         return
 
     def add_listitem(

{docling-2.28.0 → docling-2.28.2}/docling/document_converter.py

@@ -1,3 +1,4 @@
+import hashlib
 import logging
 import math
 import sys
@@ -181,7 +182,14 @@ class DocumentConverter:
             )
             for format in self.allowed_formats
         }
-        self.initialized_pipelines: Dict[Type[BasePipeline], BasePipeline] = {}
+        self.initialized_pipelines: Dict[
+            Tuple[Type[BasePipeline], str], BasePipeline
+        ] = {}
+
+    def _get_pipeline_options_hash(self, pipeline_options: PipelineOptions) -> str:
+        """Generate a hash of pipeline options to use as part of the cache key."""
+        options_str = str(pipeline_options.model_dump())
+        return hashlib.md5(options_str.encode("utf-8")).hexdigest()
 
     def initialize_pipeline(self, format: InputFormat):
         """Initialize the conversion pipeline for the selected format."""
@@ -279,31 +287,36 @@ class DocumentConverter:
                 yield item
 
     def _get_pipeline(self, doc_format: InputFormat) -> Optional[BasePipeline]:
+        """Retrieve or initialize a pipeline, reusing instances based on class and options."""
         fopt = self.format_to_options.get(doc_format)
 
-        if fopt is None:
+        if fopt is None or fopt.pipeline_options is None:
             return None
-        else:
-            pipeline_class = fopt.pipeline_cls
-            pipeline_options = fopt.pipeline_options
 
-        if pipeline_options is None:
-            return None
-        # TODO this will ignore if different options have been defined for the same pipeline class.
-        if (
-            pipeline_class not in self.initialized_pipelines
-            or self.initialized_pipelines[pipeline_class].pipeline_options
-            != pipeline_options
-        ):
-            self.initialized_pipelines[pipeline_class] = pipeline_class(
+        pipeline_class = fopt.pipeline_cls
+        pipeline_options = fopt.pipeline_options
+        options_hash = self._get_pipeline_options_hash(pipeline_options)
+
+        # Use a composite key to cache pipelines
+        cache_key = (pipeline_class, options_hash)
+
+        if cache_key not in self.initialized_pipelines:
+            _log.info(
+                f"Initializing pipeline for {pipeline_class.__name__} with options hash {options_hash}"
+            )
+            self.initialized_pipelines[cache_key] = pipeline_class(
                 pipeline_options=pipeline_options
             )
-        return self.initialized_pipelines[pipeline_class]
+        else:
+            _log.debug(
+                f"Reusing cached pipeline for {pipeline_class.__name__} with options hash {options_hash}"
+            )
+
+        return self.initialized_pipelines[cache_key]
 
     def _process_document(
         self, in_doc: InputDocument, raises_on_error: bool
     ) -> ConversionResult:
-
         valid = (
             self.allowed_formats is not None and in_doc.format in self.allowed_formats
         )
@@ -345,7 +358,6 @@ class DocumentConverter:
         else:
             if raises_on_error:
                 raise ConversionError(f"Input document {in_doc.file} is not valid.")
-
             else:
                 # invalid doc or not of desired format
                 conv_res = ConversionResult(

{docling-2.28.0 → docling-2.28.2}/docling/models/page_preprocessing_model.py

@@ -63,7 +63,13 @@ class PagePreprocessingModel(BasePageModel):
         def draw_text_boxes(image, cells, show: bool = False):
             draw = ImageDraw.Draw(image)
             for c in cells:
-                x0, y0, x1, y1 = c.bbox.as_tuple()
+                x0, y0, x1, y1 = (
+                    c.to_bounding_box().l,
+                    c.to_bounding_box().t,
+                    c.to_bounding_box().r,
+                    c.to_bounding_box().b,
+                )
+
                 draw.rectangle([(x0, y0), (x1, y1)], outline="red")
             if show:
                 image.show()

{docling-2.28.0 → docling-2.28.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "2.28.0"  # DO NOT EDIT, updated automatically
+version = "2.28.2"  # DO NOT EDIT, updated automatically
 description = "SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications."
 authors = [
   "Christoph Auer <cau@zurich.ibm.com>",