docling 2.8.3__tar.gz → 2.10.0__tar.gz

{docling-2.8.3 → docling-2.10.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.8.3
+Version: 2.10.0
 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/DS4SD/docling
 License: MIT
@@ -25,10 +25,10 @@ Provides-Extra: rapidocr
 Provides-Extra: tesserocr
 Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
 Requires-Dist: certifi (>=2024.7.4)
-Requires-Dist: deepsearch-glm (>=0.26.1,<0.27.0)
-Requires-Dist: docling-core (>=2.6.1,<3.0.0)
+Requires-Dist: deepsearch-glm (>=1.0.0,<2.0.0)
+Requires-Dist: docling-core[chunking] (>=2.9.0,<3.0.0)
 Requires-Dist: docling-ibm-models (>=2.0.6,<3.0.0)
-Requires-Dist: docling-parse (>=2.0.5,<3.0.0)
+Requires-Dist: docling-parse (>=3.0.0,<4.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)
 Requires-Dist: filetype (>=1.2.0,<2.0.0)
 Requires-Dist: huggingface_hub (>=0.23,<1)
@@ -39,7 +39,7 @@ Requires-Dist: onnxruntime (>=1.7.0,<1.20.0) ; (python_version < "3.10") and (ex
 Requires-Dist: onnxruntime (>=1.7.0,<2.0.0) ; (python_version >= "3.10") and (extra == "rapidocr")
 Requires-Dist: openpyxl (>=3.1.5,<4.0.0)
 Requires-Dist: pandas (>=2.1.4,<3.0.0)
-Requires-Dist: pydantic (>=2.0.0,<2.10)
+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: python-docx (>=1.1.2,<2.0.0)
@@ -59,7 +59,7 @@ Description-Content-Type: text/markdown
   </a>
 </p>
 
-# 🦆 Docling
+# Docling
 
 <p align="center">
   <a href="https://trendshift.io/repositories/12132" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12132" alt="DS4SD%2Fdocling | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
@@ -81,7 +81,7 @@ Docling parses documents and exports them to the desired format with ease and sp
 
 ## Features
 
-* 🗂️ Reads popular document formats (PDF, DOCX, PPTX, XLSX, Images, HTML, AsciiDoc & Markdown) and exports to Markdown and JSON
+* 🗂️ Reads popular document formats (PDF, DOCX, PPTX, XLSX, Images, HTML, AsciiDoc & Markdown) and exports to HTML, Markdown and JSON (with embedded and referenced images)
 * 📑 Advanced PDF document understanding including page layout, reading order & table structures
 * 🧩 Unified, expressive [DoclingDocument](https://ds4sd.github.io/docling/concepts/docling_document/) representation format
 * 🤖 Easy integration with 🦙 LlamaIndex & 🦜🔗 LangChain for powerful RAG / QA applications

{docling-2.8.3 → docling-2.10.0}/README.md

@@ -4,7 +4,7 @@
   </a>
 </p>
 
-# 🦆 Docling
+# Docling
 
 <p align="center">
   <a href="https://trendshift.io/repositories/12132" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12132" alt="DS4SD%2Fdocling | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
@@ -26,7 +26,7 @@ Docling parses documents and exports them to the desired format with ease and sp
 
 ## Features
 
-* 🗂️ Reads popular document formats (PDF, DOCX, PPTX, XLSX, Images, HTML, AsciiDoc & Markdown) and exports to Markdown and JSON
+* 🗂️ Reads popular document formats (PDF, DOCX, PPTX, XLSX, Images, HTML, AsciiDoc & Markdown) and exports to HTML, Markdown and JSON (with embedded and referenced images)
 * 📑 Advanced PDF document understanding including page layout, reading order & table structures
 * 🧩 Unified, expressive [DoclingDocument](https://ds4sd.github.io/docling/concepts/docling_document/) representation format
 * 🤖 Easy integration with 🦙 LlamaIndex & 🦜🔗 LangChain for powerful RAG / QA applications

{docling-2.8.3 → docling-2.10.0}/docling/backend/docling_parse_backend.py

@@ -6,7 +6,7 @@ from typing import Iterable, List, Optional, Union
 
 import pypdfium2 as pdfium
 from docling_core.types.doc import BoundingBox, CoordOrigin, Size
-from docling_parse.docling_parse import pdf_parser_v1
+from docling_parse.pdf_parsers import pdf_parser_v1
 from PIL import Image, ImageDraw
 from pypdfium2 import PdfPage
 

{docling-2.8.3 → docling-2.10.0}/docling/backend/docling_parse_v2_backend.py

@@ -6,7 +6,7 @@ from typing import TYPE_CHECKING, Iterable, List, Optional, Union
 
 import pypdfium2 as pdfium
 from docling_core.types.doc import BoundingBox, CoordOrigin
-from docling_parse.docling_parse import pdf_parser_v2
+from docling_parse.pdf_parsers import pdf_parser_v2
 from PIL import Image, ImageDraw
 from pypdfium2 import PdfPage
 
@@ -210,12 +210,14 @@ class DoclingParseV2DocumentBackend(PdfDocumentBackend):
         self.parser = pdf_parser_v2("fatal")
 
         success = False
-        if isinstance(path_or_stream, BytesIO):
+        if isinstance(self.path_or_stream, BytesIO):
             success = self.parser.load_document_from_bytesio(
-                self.document_hash, path_or_stream
+                self.document_hash, self.path_or_stream
+            )
+        elif isinstance(self.path_or_stream, Path):
+            success = self.parser.load_document(
+                self.document_hash, str(self.path_or_stream)
             )
-        elif isinstance(path_or_stream, Path):
-            success = self.parser.load_document(self.document_hash, str(path_or_stream))
 
         if not success:
             raise RuntimeError(

{docling-2.8.3 → docling-2.10.0}/docling/backend/msword_backend.py

@@ -1,4 +1,5 @@
 import logging
+import re
 from io import BytesIO
 from pathlib import Path
 from typing import Set, Union
@@ -133,7 +134,6 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
     def walk_linear(self, body, docx_obj, doc) -> DoclingDocument:
         for element in body:
             tag_name = etree.QName(element).localname
-
             # Check for Inline Images (blip elements)
             namespaces = {
                 "a": "http://schemas.openxmlformats.org/drawingml/2006/main",
@@ -153,6 +153,7 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
                 self.handle_pictures(element, docx_obj, drawing_blip, doc)
             # Check for Text
             elif tag_name in ["p"]:
+                # "tcPr", "sectPr"
                 self.handle_text_elements(element, docx_obj, doc)
             else:
                 _log.debug(f"Ignoring element in DOCX with tag: {tag_name}")
@@ -166,6 +167,14 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
         except ValueError:
             return default
 
+    def split_text_and_number(self, input_string):
+        match = re.match(r"(\D+)(\d+)$|^(\d+)(\D+)", input_string)
+        if match:
+            parts = list(filter(None, match.groups()))
+            return parts
+        else:
+            return [input_string]
+
     def get_numId_and_ilvl(self, paragraph):
         # Access the XML element of the paragraph
         numPr = paragraph._element.find(
@@ -188,7 +197,7 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
     def get_label_and_level(self, paragraph):
         if paragraph.style is None:
             return "Normal", None
-        label = paragraph.style.name
+        label = paragraph.style.style_id
         if label is None:
             return "Normal", None
         if ":" in label:
@@ -197,7 +206,7 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
             if len(parts) == 2:
                 return parts[0], int(parts[1])
 
-        parts = label.split(" ")
+        parts = self.split_text_and_number(label)
 
         if "Heading" in label and len(parts) == 2:
             parts.sort()
@@ -219,14 +228,13 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
         if paragraph.text is None:
             return
         text = paragraph.text.strip()
-        # if len(text)==0 # keep empty paragraphs, they seperate adjacent lists!
 
         # Common styles for bullet and numbered lists.
         # "List Bullet", "List Number", "List Paragraph"
         # Identify wether list is a numbered list or not
         # is_numbered = "List Bullet" not in paragraph.style.name
         is_numbered = False
-        p_style_name, p_level = self.get_label_and_level(paragraph)
+        p_style_id, p_level = self.get_label_and_level(paragraph)
         numid, ilevel = self.get_numId_and_ilvl(paragraph)
 
         if numid == 0:
@@ -238,14 +246,14 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
                 element,
                 docx_obj,
                 doc,
-                p_style_name,
+                p_style_id,
                 p_level,
                 numid,
                 ilevel,
                 text,
                 is_numbered,
             )
-            self.update_history(p_style_name, p_level, numid, ilevel)
+            self.update_history(p_style_id, p_level, numid, ilevel)
             return
         elif numid is None and self.prev_numid() is not None:  # Close list
             for key, val in self.parents.items():
@@ -253,23 +261,23 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
                     self.parents[key] = None
             self.level = self.level_at_new_list - 1
             self.level_at_new_list = None
-        if p_style_name in ["Title"]:
+        if p_style_id in ["Title"]:
             for key, val in self.parents.items():
                 self.parents[key] = None
             self.parents[0] = doc.add_text(
                 parent=None, label=DocItemLabel.TITLE, text=text
             )
-        elif "Heading" in p_style_name:
-            self.add_header(element, docx_obj, doc, p_style_name, p_level, text)
+        elif "Heading" in p_style_id:
+            self.add_header(element, docx_obj, doc, p_style_id, p_level, text)
 
-        elif p_style_name in [
+        elif p_style_id in [
             "Paragraph",
             "Normal",
             "Subtitle",
             "Author",
-            "Default Text",
-            "List Paragraph",
-            "List Bullet",
+            "DefaultText",
+            "ListParagraph",
+            "ListBullet",
             "Quote",
         ]:
             level = self.get_level()
@@ -285,15 +293,13 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
                 label=DocItemLabel.PARAGRAPH, parent=self.parents[level - 1], text=text
             )
 
-        self.update_history(p_style_name, p_level, numid, ilevel)
+        self.update_history(p_style_id, p_level, numid, ilevel)
         return
 
     def add_header(self, element, docx_obj, doc, curr_name, curr_level, text: str):
         level = self.get_level()
         if isinstance(curr_level, int):
-
             if curr_level > level:
-
                 # add invisible group
                 for i in range(level, curr_level):
                     self.parents[i] = doc.add_group(
@@ -301,9 +307,7 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
                         label=GroupLabel.SECTION,
                         name=f"header-{i}",
                     )
-
             elif curr_level < level:
-
                 # remove the tail
                 for key, val in self.parents.items():
                     if key >= curr_level:
@@ -314,7 +318,6 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
                 text=text,
                 level=curr_level,
             )
-
         else:
             self.parents[self.level] = doc.add_heading(
                 parent=self.parents[self.level - 1],
@@ -328,7 +331,7 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
         element,
         docx_obj,
         doc,
-        p_style_name,
+        p_style_id,
         p_level,
         numid,
         ilevel,
@@ -346,7 +349,7 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
                 label=GroupLabel.LIST, name="list", parent=self.parents[level - 1]
             )
 
-            # TODO: Set marker and enumerated arguments if this is an enumeration element.
+            # Set marker and enumerated arguments if this is an enumeration element.
             self.listIter += 1
             if is_numbered:
                 enum_marker = str(self.listIter) + "."
@@ -365,8 +368,8 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
                 self.level_at_new_list + self.prev_indent() + 1,
                 self.level_at_new_list + ilevel + 1,
             ):
-                # TODO: determine if this is an unordered list or an ordered list.
-                #  Set GroupLabel.ORDERED_LIST when it fits.
+                # Determine if this is an unordered list or an ordered list.
+                # Set GroupLabel.ORDERED_LIST when it fits.
                 self.listIter = 0
                 if is_numbered:
                     self.parents[i] = doc.add_group(
@@ -467,6 +470,19 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
                 row_span = get_rowspan(cell)
                 col_span = get_colspan(cell)
 
+                cell_text = cell.text
+                # In case cell doesn't return text via docx library:
+                if len(cell_text) == 0:
+                    cell_xml = cell._element
+
+                    texts = [""]
+                    for elem in cell_xml.iter():
+                        if elem.tag.endswith("t"):  # <w:t> tags that contain text
+                            if elem.text:
+                                texts.append(elem.text)
+                    # Join the collected text
+                    cell_text = " ".join(texts).strip()
+
                 # Find the next available column in the grid
                 while table_grid[row_idx][col_idx] is not None:
                     col_idx += 1
@@ -477,15 +493,15 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
                         table_grid[row_idx + i][col_idx + j] = ""
 
                 cell = TableCell(
-                    text=cell.text,
+                    text=cell_text,
                     row_span=row_span,
                     col_span=col_span,
                     start_row_offset_idx=row_idx,
                     end_row_offset_idx=row_idx + row_span,
                     start_col_offset_idx=col_idx,
                     end_col_offset_idx=col_idx + col_span,
-                    col_header=False,  # col_header,
-                    row_header=False,  # ((not col_header) and html_cell.name=='th')
+                    col_header=False,
+                    row_header=False,
                 )
 
                 data.table_cells.append(cell)

docling-2.10.0/docling/chunking/__init__.py

@@ -0,0 +1,12 @@
+#
+# Copyright IBM Corp. 2024 - 2024
+# SPDX-License-Identifier: MIT
+#
+
+from docling_core.transforms.chunker.base import BaseChunk, BaseChunker, BaseMeta
+from docling_core.transforms.chunker.hierarchical_chunker import (
+    DocChunk,
+    DocMeta,
+    HierarchicalChunker,
+)
+from docling_core.transforms.chunker.hybrid_chunker import HybridChunker

{docling-2.8.3 → docling-2.10.0}/docling/cli/main.py

@@ -10,7 +10,9 @@ from pathlib import Path
 from typing import Annotated, Dict, Iterable, List, Optional, Type
 
 import typer
+from docling_core.types.doc import ImageRefMode
 from docling_core.utils.file import resolve_source_to_path
+from pydantic import TypeAdapter, ValidationError
 
 from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
 from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
@@ -86,9 +88,11 @@ def export_documents(
     conv_results: Iterable[ConversionResult],
     output_dir: Path,
     export_json: bool,
+    export_html: bool,
     export_md: bool,
     export_txt: bool,
     export_doctags: bool,
+    image_export_mode: ImageRefMode,
 ):
 
     success_count = 0
@@ -99,33 +103,45 @@ def export_documents(
             success_count += 1
             doc_filename = conv_res.input.file.stem
 
-            # Export Deep Search document JSON format:
+            # Export JSON format:
             if export_json:
                 fname = output_dir / f"{doc_filename}.json"
-                with fname.open("w", encoding="utf8") as fp:
-                    _log.info(f"writing JSON output to {fname}")
-                    fp.write(json.dumps(conv_res.document.export_to_dict()))
+                _log.info(f"writing JSON output to {fname}")
+                conv_res.document.save_as_json(
+                    filename=fname, image_mode=image_export_mode
+                )
+
+            # Export HTML format:
+            if export_html:
+                fname = output_dir / f"{doc_filename}.html"
+                _log.info(f"writing HTML output to {fname}")
+                conv_res.document.save_as_html(
+                    filename=fname, image_mode=image_export_mode
+                )
 
             # Export Text format:
             if export_txt:
                 fname = output_dir / f"{doc_filename}.txt"
-                with fname.open("w", encoding="utf8") as fp:
-                    _log.info(f"writing Text output to {fname}")
-                    fp.write(conv_res.document.export_to_markdown(strict_text=True))
+                _log.info(f"writing TXT output to {fname}")
+                conv_res.document.save_as_markdown(
+                    filename=fname,
+                    strict_text=True,
+                    image_mode=ImageRefMode.PLACEHOLDER,
+                )
 
             # Export Markdown format:
             if export_md:
                 fname = output_dir / f"{doc_filename}.md"
-                with fname.open("w", encoding="utf8") as fp:
-                    _log.info(f"writing Markdown output to {fname}")
-                    fp.write(conv_res.document.export_to_markdown())
+                _log.info(f"writing Markdown output to {fname}")
+                conv_res.document.save_as_markdown(
+                    filename=fname, image_mode=image_export_mode
+                )
 
             # Export Document Tags format:
             if export_doctags:
                 fname = output_dir / f"{doc_filename}.doctags"
-                with fname.open("w", encoding="utf8") as fp:
-                    _log.info(f"writing Doc Tags output to {fname}")
-                    fp.write(conv_res.document.export_to_document_tokens())
+                _log.info(f"writing Doc Tags output to {fname}")
+                conv_res.document.save_as_document_tokens(filename=fname)
 
         else:
             _log.warning(f"Document {conv_res.input.file} failed to convert.")
@@ -160,6 +176,13 @@ def convert(
     to_formats: List[OutputFormat] = typer.Option(
         None, "--to", help="Specify output formats. Defaults to Markdown."
     ),
+    image_export_mode: Annotated[
+        ImageRefMode,
+        typer.Option(
+            ...,
+            help="Image export mode for the document (only in case of JSON, Markdown or HTML). With `placeholder`, only the position of the image is marked in the output. In `embedded` mode, the image is embedded as base64 encoded string. In `referenced` mode, the image is exported in PNG format and referenced from the main exported document.",
+        ),
+    ] = ImageRefMode.EMBEDDED,
     ocr: Annotated[
         bool,
         typer.Option(
@@ -185,7 +208,7 @@ def convert(
     ] = None,
     pdf_backend: Annotated[
         PdfBackend, typer.Option(..., help="The PDF backend to use.")
-    ] = PdfBackend.DLPARSE_V1,
+    ] = PdfBackend.DLPARSE_V2,
     table_mode: Annotated[
         TableFormerMode,
         typer.Option(..., help="The mode to use in the table structure model."),
@@ -260,24 +283,45 @@ def convert(
     with tempfile.TemporaryDirectory() as tempdir:
         input_doc_paths: List[Path] = []
         for src in input_sources:
-            source = resolve_source_to_path(source=src, workdir=Path(tempdir))
-            if not source.exists():
+            try:
+                # check if we can fetch some remote url
+                source = resolve_source_to_path(source=src, workdir=Path(tempdir))
+                input_doc_paths.append(source)
+            except FileNotFoundError:
                 err_console.print(
-                    f"[red]Error: The input file {source} does not exist.[/red]"
+                    f"[red]Error: The input file {src} does not exist.[/red]"
                 )
                 raise typer.Abort()
-            elif source.is_dir():
-                for fmt in from_formats:
-                    for ext in FormatToExtensions[fmt]:
-                        input_doc_paths.extend(list(source.glob(f"**/*.{ext}")))
-                        input_doc_paths.extend(list(source.glob(f"**/*.{ext.upper()}")))
-            else:
-                input_doc_paths.append(source)
+            except IsADirectoryError:
+                # if the input matches to a file or a folder
+                try:
+                    local_path = TypeAdapter(Path).validate_python(src)
+                    if local_path.exists() and local_path.is_dir():
+                        for fmt in from_formats:
+                            for ext in FormatToExtensions[fmt]:
+                                input_doc_paths.extend(
+                                    list(local_path.glob(f"**/*.{ext}"))
+                                )
+                                input_doc_paths.extend(
+                                    list(local_path.glob(f"**/*.{ext.upper()}"))
+                                )
+                    elif local_path.exists():
+                        input_doc_paths.append(local_path)
+                    else:
+                        err_console.print(
+                            f"[red]Error: The input file {src} does not exist.[/red]"
+                        )
+                        raise typer.Abort()
+                except Exception as err:
+                    err_console.print(f"[red]Error: Cannot read the input {src}.[/red]")
+                    _log.info(err)  # will print more details if verbose is activated
+                    raise typer.Abort()
 
         if to_formats is None:
             to_formats = [OutputFormat.MARKDOWN]
 
         export_json = OutputFormat.JSON in to_formats
+        export_html = OutputFormat.HTML in to_formats
         export_md = OutputFormat.MARKDOWN in to_formats
         export_txt = OutputFormat.TEXT in to_formats
         export_doctags = OutputFormat.DOCTAGS in to_formats
@@ -309,6 +353,13 @@ def convert(
         )
         pipeline_options.table_structure_options.mode = table_mode
 
+        if image_export_mode != ImageRefMode.PLACEHOLDER:
+            pipeline_options.generate_page_images = True
+            pipeline_options.generate_picture_images = (
+                True  # FIXME: to be deprecated in verson 3
+            )
+            pipeline_options.images_scale = 2
+
         if artifacts_path is not None:
             pipeline_options.artifacts_path = artifacts_path
 
@@ -321,11 +372,13 @@ def convert(
         else:
             raise RuntimeError(f"Unexpected PDF backend type {pdf_backend}")
 
+        pdf_format_option = PdfFormatOption(
+            pipeline_options=pipeline_options,
+            backend=backend,  # pdf_backend
+        )
         format_options: Dict[InputFormat, FormatOption] = {
-            InputFormat.PDF: PdfFormatOption(
-                pipeline_options=pipeline_options,
-                backend=backend,  # pdf_backend
-            )
+            InputFormat.PDF: pdf_format_option,
+            InputFormat.IMAGE: pdf_format_option,
         }
         doc_converter = DocumentConverter(
             allowed_formats=from_formats,
@@ -343,9 +396,11 @@ def convert(
             conv_results,
             output_dir=output,
             export_json=export_json,
+            export_html=export_html,
             export_md=export_md,
             export_txt=export_txt,
             export_doctags=export_doctags,
+            image_export_mode=image_export_mode,
         )
 
         end_time = time.time() - start_time

{docling-2.8.3 → docling-2.10.0}/docling/datamodel/base_models.py

@@ -41,6 +41,7 @@ class InputFormat(str, Enum):
 class OutputFormat(str, Enum):
     MARKDOWN = "md"
     JSON = "json"
+    HTML = "html"
     TEXT = "text"
     DOCTAGS = "doctags"