docling 2.5.2__tar.gz → 2.6.0__tar.gz

{docling-2.5.2 → docling-2.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.5.2
+Version: 2.6.0
 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
@@ -23,13 +23,14 @@ 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 (>=2.3.0,<3.0.0)
+Requires-Dist: docling-core (>=2.4.0,<3.0.0)
 Requires-Dist: docling-ibm-models (>=2.0.3,<3.0.0)
 Requires-Dist: docling-parse (>=2.0.2,<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: openpyxl (>=3.1.5,<4.0.0)
 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)

docling-2.6.0/docling/backend/msexcel_backend.py

@@ -0,0 +1,374 @@
+import logging
+from io import BytesIO
+from pathlib import Path
+from typing import Dict, Set, Tuple, Union
+
+from docling_core.types.doc import (
+    DoclingDocument,
+    DocumentOrigin,
+    GroupLabel,
+    ImageRef,
+    TableCell,
+    TableData,
+)
+
+# from lxml import etree
+from openpyxl import Workbook, load_workbook
+from openpyxl.cell.cell import Cell
+from openpyxl.drawing.image import Image
+from openpyxl.worksheet.worksheet import Worksheet
+
+from docling.backend.abstract_backend import DeclarativeDocumentBackend
+from docling.datamodel.base_models import InputFormat
+from docling.datamodel.document import InputDocument
+
+_log = logging.getLogger(__name__)
+
+from typing import Any, List
+
+from pydantic import BaseModel
+
+
+class ExcelCell(BaseModel):
+    row: int
+    col: int
+    text: str
+    row_span: int
+    col_span: int
+
+
+class ExcelTable(BaseModel):
+    num_rows: int
+    num_cols: int
+    data: List[ExcelCell]
+
+
+class MsExcelDocumentBackend(DeclarativeDocumentBackend):
+
+    def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
+        super().__init__(in_doc, path_or_stream)
+
+        # Initialise the parents for the hierarchy
+        self.max_levels = 10
+
+        self.parents: Dict[int, Any] = {}
+        for i in range(-1, self.max_levels):
+            self.parents[i] = None
+
+        self.workbook = None
+        try:
+            if isinstance(self.path_or_stream, BytesIO):
+                self.workbook = load_workbook(filename=self.path_or_stream)
+
+            elif isinstance(self.path_or_stream, Path):
+                self.workbook = load_workbook(filename=str(self.path_or_stream))
+
+            self.valid = True
+        except Exception as e:
+            self.valid = False
+
+            raise RuntimeError(
+                f"MsPowerpointDocumentBackend could not load document with hash {self.document_hash}"
+            ) from e
+
+    def is_valid(self) -> bool:
+        _log.info(f"valid: {self.valid}")
+        return self.valid
+
+    @classmethod
+    def supports_pagination(cls) -> bool:
+        return True
+
+    def unload(self):
+        if isinstance(self.path_or_stream, BytesIO):
+            self.path_or_stream.close()
+
+        self.path_or_stream = None
+
+    @classmethod
+    def supported_formats(cls) -> Set[InputFormat]:
+        return {InputFormat.XLSX}
+
+    def convert(self) -> DoclingDocument:
+        # Parses the XLSX into a structured document model.
+
+        origin = DocumentOrigin(
+            filename=self.file.name or "file.xlsx",
+            mimetype="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+            binary_hash=self.document_hash,
+        )
+
+        doc = DoclingDocument(name=self.file.stem or "file.xlsx", origin=origin)
+
+        if self.is_valid():
+            doc = self._convert_workbook(doc)
+        else:
+            raise RuntimeError(
+                f"Cannot convert doc with {self.document_hash} because the backend failed to init."
+            )
+
+        return doc
+
+    def _convert_workbook(self, doc: DoclingDocument) -> DoclingDocument:
+
+        if self.workbook is not None:
+
+            # Iterate over all sheets
+            for sheet_name in self.workbook.sheetnames:
+                _log.info(f"Processing sheet: {sheet_name}")
+
+                # Access the sheet by name
+                sheet = self.workbook[sheet_name]
+
+                self.parents[0] = doc.add_group(
+                    parent=None,
+                    label=GroupLabel.SECTION,
+                    name=f"sheet: {sheet_name}",
+                )
+
+                doc = self._convert_sheet(doc, sheet)
+        else:
+            _log.error("Workbook is not initialized.")
+
+        return doc
+
+    def _convert_sheet(self, doc: DoclingDocument, sheet: Worksheet):
+
+        doc = self._find_tables_in_sheet(doc, sheet)
+
+        doc = self._find_images_in_sheet(doc, sheet)
+
+        return doc
+
+    def _find_tables_in_sheet(self, doc: DoclingDocument, sheet: Worksheet):
+
+        tables = self._find_data_tables(sheet)
+
+        for excel_table in tables:
+            num_rows = excel_table.num_rows
+            num_cols = excel_table.num_cols
+
+            table_data = TableData(
+                num_rows=num_rows,
+                num_cols=num_cols,
+                table_cells=[],
+            )
+
+            for excel_cell in excel_table.data:
+
+                cell = TableCell(
+                    text=excel_cell.text,
+                    row_span=excel_cell.row_span,
+                    col_span=excel_cell.col_span,
+                    start_row_offset_idx=excel_cell.row,
+                    end_row_offset_idx=excel_cell.row + excel_cell.row_span,
+                    start_col_offset_idx=excel_cell.col,
+                    end_col_offset_idx=excel_cell.col + excel_cell.col_span,
+                    col_header=False,
+                    row_header=False,
+                )
+                table_data.table_cells.append(cell)
+
+            doc.add_table(data=table_data, parent=self.parents[0])
+
+        return doc
+
+    def _find_data_tables(self, sheet: Worksheet):
+        """
+        Find all compact rectangular data tables in a sheet.
+        """
+        # _log.info("find_data_tables")
+
+        tables = []  # List to store found tables
+        visited: set[Tuple[int, int]] = set()  # Track already visited cells
+
+        # Iterate over all cells in the sheet
+        for ri, row in enumerate(sheet.iter_rows(values_only=False)):
+            for rj, cell in enumerate(row):
+
+                # Skip empty or already visited cells
+                if cell.value is None or (ri, rj) in visited:
+                    continue
+
+                # If the cell starts a new table, find its bounds
+                table_bounds, visited_cells = self._find_table_bounds(
+                    sheet, ri, rj, visited
+                )
+
+                visited.update(visited_cells)  # Mark these cells as visited
+                tables.append(table_bounds)
+
+        return tables
+
+    def _find_table_bounds(
+        self,
+        sheet: Worksheet,
+        start_row: int,
+        start_col: int,
+        visited: set[Tuple[int, int]],
+    ):
+        """
+        Determine the bounds of a compact rectangular table.
+        Returns:
+        - A dictionary with the bounds and data.
+        - A set of visited cell coordinates.
+        """
+        _log.info("find_table_bounds")
+
+        max_row = self._find_table_bottom(sheet, start_row, start_col)
+        max_col = self._find_table_right(sheet, start_row, start_col)
+
+        # Collect the data within the bounds
+        data = []
+        visited_cells = set()
+        for ri in range(start_row, max_row + 1):
+            for rj in range(start_col, max_col + 1):
+
+                cell = sheet.cell(row=ri + 1, column=rj + 1)  # 1-based indexing
+
+                # Check if the cell belongs to a merged range
+                row_span = 1
+                col_span = 1
+
+                # _log.info(sheet.merged_cells.ranges)
+                for merged_range in sheet.merged_cells.ranges:
+
+                    if (
+                        merged_range.min_row <= ri + 1
+                        and ri + 1 <= merged_range.max_row
+                        and merged_range.min_col <= rj + 1
+                        and rj + 1 <= merged_range.max_col
+                    ):
+
+                        row_span = merged_range.max_row - merged_range.min_row + 1
+                        col_span = merged_range.max_col - merged_range.min_col + 1
+                        break
+
+                if (ri, rj) not in visited_cells:
+                    data.append(
+                        ExcelCell(
+                            row=ri - start_row,
+                            col=rj - start_col,
+                            text=str(cell.value),
+                            row_span=row_span,
+                            col_span=col_span,
+                        )
+                    )
+                    # _log.info(f"cell: {ri}, {rj} -> {ri - start_row}, {rj - start_col}, {row_span}, {col_span}: {str(cell.value)}")
+
+                    # Mark all cells in the span as visited
+                    for span_row in range(ri, ri + row_span):
+                        for span_col in range(rj, rj + col_span):
+                            visited_cells.add((span_row, span_col))
+
+        return (
+            ExcelTable(
+                num_rows=max_row + 1 - start_row,
+                num_cols=max_col + 1 - start_col,
+                data=data,
+            ),
+            visited_cells,
+        )
+
+    def _find_table_bottom(self, sheet: Worksheet, start_row: int, start_col: int):
+        """Function to find the bottom boundary of the table"""
+
+        max_row = start_row
+
+        while max_row < sheet.max_row - 1:
+            # Get the cell value or check if it is part of a merged cell
+            cell = sheet.cell(row=max_row + 2, column=start_col + 1)
+
+            # Check if the cell is part of a merged range
+            merged_range = next(
+                (mr for mr in sheet.merged_cells.ranges if cell.coordinate in mr),
+                None,
+            )
+
+            if cell.value is None and not merged_range:
+                break  # Stop if the cell is empty and not merged
+
+            # Expand max_row to include the merged range if applicable
+            if merged_range:
+                max_row = max(max_row, merged_range.max_row - 1)
+            else:
+                max_row += 1
+
+        return max_row
+
+    def _find_table_right(self, sheet: Worksheet, start_row: int, start_col: int):
+        """Function to find the right boundary of the table"""
+
+        max_col = start_col
+
+        while max_col < sheet.max_column - 1:
+            # Get the cell value or check if it is part of a merged cell
+            cell = sheet.cell(row=start_row + 1, column=max_col + 2)
+
+            # Check if the cell is part of a merged range
+            merged_range = next(
+                (mr for mr in sheet.merged_cells.ranges if cell.coordinate in mr),
+                None,
+            )
+
+            if cell.value is None and not merged_range:
+                break  # Stop if the cell is empty and not merged
+
+            # Expand max_col to include the merged range if applicable
+            if merged_range:
+                max_col = max(max_col, merged_range.max_col - 1)
+            else:
+                max_col += 1
+
+        return max_col
+
+    def _find_images_in_sheet(
+        self, doc: DoclingDocument, sheet: Worksheet
+    ) -> DoclingDocument:
+
+        # FIXME: mypy does not agree with _images ...
+        """
+        # Iterate over images in the sheet
+        for idx, image in enumerate(sheet._images):  # Access embedded images
+
+            image_bytes = BytesIO(image.ref.blob)
+            pil_image = Image.open(image_bytes)
+
+            doc.add_picture(
+                parent=self.parents[0],
+                image=ImageRef.from_pil(image=pil_image, dpi=72),
+                caption=None,
+            )
+        """
+
+        # FIXME: mypy does not agree with _charts ...
+        """
+        for idx, chart in enumerate(sheet._charts):  # Access embedded charts
+            chart_path = f"chart_{idx + 1}.png"
+            _log.info(
+                f"Chart found, but dynamic rendering is required for: {chart_path}"
+            )
+
+            _log.info(f"Chart {idx + 1}:")
+        
+            # Chart type
+            _log.info(f"Type: {type(chart).__name__}")
+            
+            # Title
+            if chart.title:
+                _log.info(f"Title: {chart.title}")
+            else:
+                _log.info("No title")
+            
+            # Data series
+            for series in chart.series:
+                _log.info(" => series ...")
+                _log.info(f"Data Series: {series.title}")
+                _log.info(f"Values: {series.values}")
+                _log.info(f"Categories: {series.categories}")
+                
+            # Position
+            # _log.info(f"Anchor Cell: {chart.anchor}")
+        """
+
+        return doc

{docling-2.5.2 → docling-2.6.0}/docling/backend/mspowerpoint_backend.py

@@ -10,11 +10,13 @@ from docling_core.types.doc import (
     DoclingDocument,
     DocumentOrigin,
     GroupLabel,
+    ImageRef,
     ProvenanceItem,
     Size,
     TableCell,
     TableData,
 )
+from PIL import Image
 from pptx import Presentation
 from pptx.enum.shapes import MSO_SHAPE_TYPE, PP_PLACEHOLDER
 
@@ -268,9 +270,22 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
         return
 
     def handle_pictures(self, shape, parent_slide, slide_ind, doc):
+        # Get the image bytes
+        image = shape.image
+        image_bytes = image.blob
+        im_dpi, _ = image.dpi
+
+        # Open it with PIL
+        pil_image = Image.open(BytesIO(image_bytes))
+
         # shape has picture
         prov = self.generate_prov(shape, slide_ind, "")
-        doc.add_picture(parent=parent_slide, caption=None, prov=prov)
+        doc.add_picture(
+            parent=parent_slide,
+            image=ImageRef.from_pil(image=pil_image, dpi=im_dpi),
+            caption=None,
+            prov=prov,
+        )
         return
 
     def handle_tables(self, shape, parent_slide, slide_ind, doc):

{docling-2.5.2 → docling-2.6.0}/docling/backend/msword_backend.py

@@ -9,10 +9,12 @@ from docling_core.types.doc import (
     DoclingDocument,
     DocumentOrigin,
     GroupLabel,
+    ImageRef,
     TableCell,
     TableData,
 )
 from lxml import etree
+from PIL import Image
 
 from docling.backend.abstract_backend import DeclarativeDocumentBackend
 from docling.datamodel.base_models import InputFormat
@@ -130,13 +132,8 @@ 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 (drawings or blip elements)
-            found_drawing = etree.ElementBase.xpath(
-                element, ".//w:drawing", namespaces=self.xml_namespaces
-            )
-            found_pict = etree.ElementBase.xpath(
-                element, ".//w:pict", namespaces=self.xml_namespaces
-            )
+            # Check for Inline Images (blip elements)
+            drawing_blip = element.xpath(".//a:blip")
 
             # Check for Tables
             if element.tag.endswith("tbl"):
@@ -145,8 +142,8 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
                 except Exception:
                     _log.debug("could not parse a table, broken docx table")
 
-            elif found_drawing or found_pict:
-                self.handle_pictures(element, docx_obj, doc)
+            elif drawing_blip:
+                self.handle_pictures(element, docx_obj, drawing_blip, doc)
             # Check for Text
             elif tag_name in ["p"]:
                 self.handle_text_elements(element, docx_obj, doc)
@@ -491,6 +488,24 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
         doc.add_table(data=data, parent=self.parents[level - 1])
         return
 
-    def handle_pictures(self, element, docx_obj, doc):
-        doc.add_picture(parent=self.parents[self.level], caption=None)
+    def handle_pictures(self, element, docx_obj, drawing_blip, doc):
+        def get_docx_image(element, drawing_blip):
+            rId = drawing_blip[0].get(
+                "{http://schemas.openxmlformats.org/officeDocument/2006/relationships}embed"
+            )
+            if rId in docx_obj.part.rels:
+                # Access the image part using the relationship ID
+                image_part = docx_obj.part.rels[rId].target_part
+                image_data = image_part.blob  # Get the binary image data
+            return image_data
+
+        image_data = get_docx_image(element, drawing_blip)
+        image_bytes = BytesIO(image_data)
+        # Open the BytesIO object with PIL to create an Image
+        pil_image = Image.open(image_bytes)
+        doc.add_picture(
+            parent=self.parents[self.level],
+            image=ImageRef.from_pil(image=pil_image, dpi=72),
+            caption=None,
+        )
         return

{docling-2.5.2 → docling-2.6.0}/docling/cli/main.py

@@ -1,6 +1,7 @@
 import importlib
 import json
 import logging
+import re
 import time
 import warnings
 from enum import Enum
@@ -129,6 +130,12 @@ def export_documents(
     )
 
 
+def _split_list(raw: Optional[str]) -> Optional[List[str]]:
+    if raw is None:
+        return None
+    return re.split(r"[;,]", raw)
+
+
 @app.command(no_args_is_help=True)
 def convert(
     input_sources: Annotated[
@@ -163,6 +170,13 @@ def convert(
     ocr_engine: Annotated[
         OcrEngine, typer.Option(..., help="The OCR engine to use.")
     ] = OcrEngine.EASYOCR,
+    ocr_lang: Annotated[
+        Optional[str],
+        typer.Option(
+            ...,
+            help="Provide a comma-separated list of languages used by the OCR engine. Note that each OCR engine has different values for the language names.",
+        ),
+    ] = None,
     pdf_backend: Annotated[
         PdfBackend, typer.Option(..., help="The PDF backend to use.")
     ] = PdfBackend.DLPARSE_V1,
@@ -185,6 +199,15 @@ def convert(
     output: Annotated[
         Path, typer.Option(..., help="Output directory where results are saved.")
     ] = Path("."),
+    verbose: Annotated[
+        int,
+        typer.Option(
+            "--verbose",
+            "-v",
+            count=True,
+            help="Set the verbosity level. -v for info logging, -vv for debug logging.",
+        ),
+    ] = 0,
     version: Annotated[
         Optional[bool],
         typer.Option(
@@ -195,7 +218,12 @@ def convert(
         ),
     ] = None,
 ):
-    logging.basicConfig(level=logging.INFO)
+    if verbose == 0:
+        logging.basicConfig(level=logging.WARNING)
+    elif verbose == 1:
+        logging.basicConfig(level=logging.INFO)
+    elif verbose == 2:
+        logging.basicConfig(level=logging.DEBUG)
 
     if from_formats is None:
         from_formats = [e for e in InputFormat]
@@ -234,6 +262,10 @@ def convert(
         case _:
             raise RuntimeError(f"Unexpected OCR engine type {ocr_engine}")
 
+    ocr_lang_list = _split_list(ocr_lang)
+    if ocr_lang_list is not None:
+        ocr_options.lang = ocr_lang_list
+
     pipeline_options = PdfPipelineOptions(
         do_ocr=ocr,
         ocr_options=ocr_options,
@@ -287,5 +319,7 @@ def convert(
     _log.info(f"All documents were converted in {end_time:.2f} seconds.")
 
 
+click_app = typer.main.get_command(app)
+
 if __name__ == "__main__":
     app()

{docling-2.5.2 → docling-2.6.0}/docling/datamodel/base_models.py

@@ -32,6 +32,7 @@ class InputFormat(str, Enum):
     PDF = "pdf"
     ASCIIDOC = "asciidoc"
     MD = "md"
+    XLSX = "xlsx"
 
 
 class OutputFormat(str, Enum):
@@ -49,6 +50,7 @@ FormatToExtensions: Dict[InputFormat, List[str]] = {
     InputFormat.HTML: ["html", "htm", "xhtml"],
     InputFormat.IMAGE: ["jpg", "jpeg", "png", "tif", "tiff", "bmp"],
     InputFormat.ASCIIDOC: ["adoc", "asciidoc", "asc"],
+    InputFormat.XLSX: ["xlsx"],
 }
 
 FormatToMimeType: Dict[InputFormat, List[str]] = {
@@ -72,7 +74,11 @@ FormatToMimeType: Dict[InputFormat, List[str]] = {
     InputFormat.PDF: ["application/pdf"],
     InputFormat.ASCIIDOC: ["text/asciidoc"],
     InputFormat.MD: ["text/markdown", "text/x-markdown"],
+    InputFormat.XLSX: [
+        "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
+    ],
 }
+
 MimeTypeToFormat = {
     mime: fmt for fmt, mimes in FormatToMimeType.items() for mime in mimes
 }

{docling-2.5.2 → docling-2.6.0}/docling/datamodel/pipeline_options.py

@@ -22,6 +22,7 @@ class TableStructureOptions(BaseModel):
 
 class OcrOptions(BaseModel):
     kind: str
+    lang: List[str]
     force_full_page_ocr: bool = False  # If enabled a full page OCR is always applied
     bitmap_area_threshold: float = (
         0.05  # percentage of the area for a bitmap to processed with OCR
@@ -81,4 +82,11 @@ class PdfPipelineOptions(PipelineOptions):
     images_scale: float = 1.0
     generate_page_images: bool = False
     generate_picture_images: bool = False
-    generate_table_images: bool = False
+    generate_table_images: bool = Field(
+        default=False,
+        deprecated=(
+            "Field `generate_table_images` is deprecated. "
+            "To obtain table images, set `PdfPipelineOptions.generate_page_images = True` "
+            "before conversion and then use the `TableItem.get_image` function."
+        ),
+    )

{docling-2.5.2 → docling-2.6.0}/docling/document_converter.py

@@ -12,6 +12,7 @@ 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.msexcel_backend import MsExcelDocumentBackend
 from docling.backend.mspowerpoint_backend import MsPowerpointDocumentBackend
 from docling.backend.msword_backend import MsWordDocumentBackend
 from docling.datamodel.base_models import ConversionStatus, DocumentStream, InputFormat
@@ -44,6 +45,11 @@ class FormatOption(BaseModel):
         return self
 
 
+class ExcelFormatOption(FormatOption):
+    pipeline_cls: Type = SimplePipeline
+    backend: Type[AbstractDocumentBackend] = MsExcelDocumentBackend
+
+
 class WordFormatOption(FormatOption):
     pipeline_cls: Type = SimplePipeline
     backend: Type[AbstractDocumentBackend] = MsWordDocumentBackend
@@ -80,6 +86,9 @@ class ImageFormatOption(FormatOption):
 
 
 _format_to_default_options = {
+    InputFormat.XLSX: FormatOption(
+        pipeline_cls=SimplePipeline, backend=MsExcelDocumentBackend
+    ),
     InputFormat.DOCX: FormatOption(
         pipeline_cls=SimplePipeline, backend=MsWordDocumentBackend
     ),

{docling-2.5.2 → docling-2.6.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "2.5.2"  # DO NOT EDIT, updated automatically
+version = "2.6.0"  # 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>", "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 = "MIT"
@@ -26,7 +26,7 @@ packages = [{include = "docling"}]
 ######################
 python = "^3.10"
 pydantic = "^2.0.0"
-docling-core = "^2.3.0"
+docling-core = "^2.4.0"
 docling-ibm-models = "^2.0.3"
 deepsearch-glm = "^0.26.1"
 filetype = "^1.2.0"
@@ -47,6 +47,7 @@ python-pptx = "^1.0.2"
 beautifulsoup4 = "^4.12.3"
 pandas = "^2.1.4"
 marko = "^2.1.2"
+openpyxl = "^3.1.5"
 
 [tool.poetry.group.dev.dependencies]
 black = {extras = ["jupyter"], version = "^24.4.2"}
@@ -65,10 +66,12 @@ pandas-stubs = "^2.1.4.231227"
 ipykernel = "^6.29.5"
 ipywidgets = "^8.1.5"
 nbqa = "^1.9.0"
+types-openpyxl = "^3.1.5.20241114"
 
 [tool.poetry.group.docs.dependencies]
 mkdocs-material = "^9.5.40"
 mkdocs-jupyter = "^0.25.0"
+mkdocs-click = "^0.8.1"
 
 [tool.poetry.group.examples.dependencies]
 datasets = "^2.21.0"