Merge remote-tracking branch 'origin/main' into dev/add-other-vlm-models

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

.gitattributes

@@ -0,0 +1,3 @@
+tests/data/** linguist-vendored
+tests/data_scanned/** linguist-vendored
+docs/** linguist-vendored

docling/cli/main.py

@@ -12,6 +12,12 @@ from typing import Annotated, Dict, List, Optional, Type
 
 import rich.table
 import typer
+from docling_core.transforms.serializer.html import (
+    HTMLDocSerializer,
+    HTMLOutputStyle,
+    HTMLParams,
+)
+from docling_core.transforms.visualizer.layout_visualizer import LayoutVisualizer
 from docling_core.types.doc import ImageRefMode
 from docling_core.utils.file import resolve_source_to_path
 from pydantic import TypeAdapter
@@ -157,6 +163,7 @@ def export_documents(
     export_json: bool,
     export_html: bool,
     export_html_split_page: bool,
+    show_layout: bool,
     export_md: bool,
     export_txt: bool,
     export_doctags: bool,
@@ -190,8 +197,26 @@ def export_documents(
             if export_html_split_page:
                 fname = output_dir / f"{doc_filename}.html"
                 _log.info(f"writing HTML output to {fname}")
+                if show_layout:
+                    ser = HTMLDocSerializer(
+                        doc=conv_res.document,
+                        params=HTMLParams(
+                            image_mode=image_export_mode,
+                            output_style=HTMLOutputStyle.SPLIT_PAGE,
+                        ),
+                    )
+                    visualizer = LayoutVisualizer()
+                    visualizer.params.show_label = False
+                    ser_res = ser.serialize(
+                        visualizer=visualizer,
+                    )
+                    with open(fname, "w") as fw:
+                        fw.write(ser_res.text)
+                else:
                     conv_res.document.save_as_html(
-                    filename=fname, image_mode=image_export_mode, split_page_view=True
+                        filename=fname,
+                        image_mode=image_export_mode,
+                        split_page_view=True,
                     )
 
             # Export Text format:
@@ -251,6 +276,13 @@ def convert(  # noqa: C901
     to_formats: List[OutputFormat] = typer.Option(
         None, "--to", help="Specify output formats. Defaults to Markdown."
     ),
+    show_layout: Annotated[
+        bool,
+        typer.Option(
+            ...,
+            help="If enabled, the page images will show the bounding-boxes of the items.",
+        ),
+    ] = False,
     headers: str = typer.Option(
         None,
         "--headers",
@@ -593,6 +625,7 @@ def convert(  # noqa: C901
             export_json=export_json,
             export_html=export_html,
             export_html_split_page=export_html_split_page,
+            show_layout=show_layout,
             export_md=export_md,
             export_txt=export_txt,
             export_doctags=export_doctags,

docling/datamodel/document.py

@@ -334,9 +334,9 @@ class _DocumentConversionInput(BaseModel):
     ) -> Optional[InputFormat]:
         """Guess the input format of a document by checking part of its content."""
         input_format: Optional[InputFormat] = None
-        content_str = content.decode("utf-8")
 
         if mime == "application/xml":
+            content_str = content.decode("utf-8")
             match_doctype = re.search(r"<!DOCTYPE [^>]+>", content_str)
             if match_doctype:
                 xml_doctype = match_doctype.group()
@@ -358,6 +358,7 @@ class _DocumentConversionInput(BaseModel):
                     input_format = InputFormat.XML_JATS
 
         elif mime == "text/plain":
+            content_str = content.decode("utf-8")
             if InputFormat.XML_USPTO in formats and content_str.startswith("PATN\r\n"):
                 input_format = InputFormat.XML_USPTO
 

docling/models/layout_model.py

@@ -185,12 +185,22 @@ class LayoutModel(BasePageModel):
                     ).postprocess()
                     # processed_clusters, processed_cells = clusters, page.cells
 
+                    with warnings.catch_warnings():
+                        warnings.filterwarnings(
+                            "ignore",
+                            "Mean of empty slice|invalid value encountered in scalar divide",
+                            RuntimeWarning,
+                            "numpy",
+                        )
+
                         conv_res.confidence.pages[page.page_no].layout_score = float(
                             np.mean([c.confidence for c in processed_clusters])
                         )
 
                         conv_res.confidence.pages[page.page_no].ocr_score = float(
-                        np.mean([c.confidence for c in processed_cells if c.from_ocr])
+                            np.mean(
+                                [c.confidence for c in processed_cells if c.from_ocr]
+                            )
                         )
 
                     page.cells = processed_cells

docling/models/page_preprocessing_model.py

@@ -1,4 +1,5 @@
 import re
+import warnings
 from collections.abc import Iterable
 from pathlib import Path
 from typing import Optional
@@ -7,7 +8,7 @@ import numpy as np
 from PIL import ImageDraw
 from pydantic import BaseModel
 
-from docling.datamodel.base_models import Page, ScoreValue
+from docling.datamodel.base_models import Page
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.settings import settings
 from docling.models.base_model import BasePageModel
@@ -76,6 +77,10 @@ class PagePreprocessingModel(BasePageModel):
             score = self.rate_text_quality(c.text)
             text_scores.append(score)
 
+        with warnings.catch_warnings():
+            warnings.filterwarnings(
+                "ignore", "Mean of empty slice", RuntimeWarning, "numpy"
+            )
             conv_res.confidence.pages[page.page_no].parse_score = float(
                 np.nanquantile(
                     text_scores, q=0.10

docling/pipeline/standard_pdf_pipeline.py

@@ -8,7 +8,7 @@ from docling_core.types.doc import DocItem, ImageRef, PictureItem, TableItem
 
 from docling.backend.abstract_backend import AbstractDocumentBackend
 from docling.backend.pdf_backend import PdfDocumentBackend
-from docling.datamodel.base_models import AssembledUnit, Page, PageConfidenceScores
+from docling.datamodel.base_models import AssembledUnit, Page
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import PdfPipelineOptions
 from docling.datamodel.settings import settings
@@ -55,6 +55,8 @@ class StandardPdfPipeline(PaginatedPipeline):
                 "When defined, it must point to a folder containing all models required by the pipeline."
             )
 
+        with warnings.catch_warnings():  # deprecated generate_table_images
+            warnings.filterwarnings("ignore", category=DeprecationWarning)
             self.keep_images = (
                 self.pipeline_options.generate_page_images
                 or self.pipeline_options.generate_picture_images
@@ -210,6 +212,8 @@ class StandardPdfPipeline(PaginatedPipeline):
                     )
 
             # Generate images of the requested element types
+            with warnings.catch_warnings():  # deprecated generate_table_images
+                warnings.filterwarnings("ignore", category=DeprecationWarning)
                 if (
                     self.pipeline_options.generate_picture_images
                     or self.pipeline_options.generate_table_images
@@ -237,7 +241,9 @@ class StandardPdfPipeline(PaginatedPipeline):
                             crop_bbox = (
                                 element.prov[0]
                                 .bbox.scaled(scale=scale)
-                            .to_top_left_origin(page_height=page.size.height * scale)
+                                .to_top_left_origin(
+                                    page_height=page.size.height * scale
+                                )
                             )
 
                             cropped_im = page.image.crop(crop_bbox.as_tuple())
@@ -247,6 +253,12 @@ class StandardPdfPipeline(PaginatedPipeline):
 
             # Aggregate confidence values for document:
             if len(conv_res.pages) > 0:
+                with warnings.catch_warnings():
+                    warnings.filterwarnings(
+                        "ignore",
+                        category=RuntimeWarning,
+                        message="Mean of empty slice|All-NaN slice encountered",
+                    )
                     conv_res.confidence.layout_score = float(
                         np.nanmean(
                             [c.layout_score for c in conv_res.confidence.pages.values()]

pyproject.toml

@@ -46,7 +46,7 @@ packages = [{ include = "docling" }]
 ######################
 python = "^3.9"
 pydantic = "^2.0.0"
-docling-core = {version = "^2.29.0", extras = ["chunking"]}
+docling-core = {version = "^2.31.2", extras = ["chunking"]}
 docling-ibm-models = "^3.4.0"
 docling-parse = "^4.0.0"
 filetype = "^1.2.0"

tests/data/groundtruth/docling_v2/example_08.html.itxt

@@ -0,0 +1,8 @@
+item-0 at level 0: unspecified: group _root_
+  item-1 at level 1: section: group header-1
+    item-2 at level 2: section_header: Pivot table with with 1 row header
+      item-3 at level 3: table with [6x4]
+    item-4 at level 2: section_header: Pivot table with 2 row headers
+      item-5 at level 3: table with [6x5]
+    item-6 at level 2: section_header: Equivalent pivot table
+      item-7 at level 3: table with [6x5]

tests/data/groundtruth/docling_v2/example_08.html.md

@@ -0,0 +1,29 @@
+## Pivot table with with 1 row header
+
+|   Year | Month    | Revenue   | Cost   |
+|--------|----------|-----------|--------|
+|   2025 | January  | $134      | $162   |
+|   2025 | February | $150      | $155   |
+|   2025 | March    | $160      | $143   |
+|   2025 | April    | $210      | $150   |
+|   2025 | May      | $280      | $120   |
+
+## Pivot table with 2 row headers
+
+|   Year | Quarter   | Month    | Revenue   | Cost   |
+|--------|-----------|----------|-----------|--------|
+|   2025 | Q1        | January  | $134      | $162   |
+|   2025 | Q1        | February | $150      | $155   |
+|   2025 | Q1        | March    | $160      | $143   |
+|   2025 | Q2        | April    | $210      | $150   |
+|   2025 | Q2        | May      | $280      | $120   |
+
+## Equivalent pivot table
+
+|   Year | Quarter   | Month    | Revenue   | Cost   |
+|--------|-----------|----------|-----------|--------|
+|   2025 | Q1        | January  | $134      | $162   |
+|   2025 | Q1        | February | $150      | $155   |
+|   2025 | Q1        | March    | $160      | $143   |
+|   2025 | Q2        | April    | $210      | $150   |
+|   2025 | Q2        | May      | $280      | $120   |

tests/data/groundtruth/docling_v2/textbox.docx.itxt

@@ -0,0 +1,94 @@
+item-0 at level 0: unspecified: group _root_
+  item-1 at level 1: paragraph: Chiayi County Shuishang Township ... mentary School Affiliated Kindergarten
+  item-2 at level 1: paragraph: Infectious Disease Reporting Pro ... r the 113th Academic Year Kindergarten
+  item-3 at level 1: paragraph: 
+  item-4 at level 1: section: group textbox
+    item-5 at level 2: paragraph: Student falls ill
+    item-6 at level 2: paragraph: 
+    item-7 at level 2: paragraph: 
+    item-8 at level 2: list: group list
+      item-9 at level 3: list_item: Suggested Reportable Symptoms:
+＊ ... sh
+＊ Blisters
+＊ Headache
+＊ Sore throat
+  item-10 at level 1: list_item: 
+  item-11 at level 1: paragraph: 
+  item-12 at level 1: paragraph: 
+  item-13 at level 1: section: group textbox
+    item-14 at level 2: paragraph: If a caregiver suspects that wit ... the same suggested reportable symptoms
+  item-15 at level 1: paragraph: 
+  item-16 at level 1: paragraph: 
+  item-17 at level 1: paragraph: 
+  item-18 at level 1: paragraph: 
+  item-19 at level 1: section: group textbox
+    item-20 at level 2: paragraph: Yes
+  item-21 at level 1: paragraph: 
+  item-22 at level 1: paragraph: 
+  item-23 at level 1: section: group textbox
+    item-24 at level 2: paragraph:   A report must be submitted wi ... saster Prevention Information Network.
+    item-25 at level 2: paragraph:   A report must also be submitt ... d Infectious Disease Reporting System.
+    item-26 at level 2: paragraph: 
+    item-27 at level 2: paragraph: 
+  item-28 at level 1: paragraph: 
+  item-29 at level 1: paragraph: 
+  item-30 at level 1: paragraph: 
+  item-31 at level 1: paragraph: 
+  item-32 at level 1: paragraph: 
+  item-33 at level 1: paragraph: 
+  item-34 at level 1: section: group textbox
+    item-35 at level 2: paragraph: Health Bureau:
+    item-36 at level 2: paragraph: Upon receiving a report from the ... rt to the Centers for Disease Control.
+    item-37 at level 2: list: group list
+      item-38 at level 3: list_item: If necessary, provide health edu ... vidual to undergo specimen collection.
+      item-39 at level 3: list_item: Implement appropriate epidemic p ...  the Communicable Disease Control Act.
+    item-40 at level 2: paragraph: 
+    item-41 at level 2: paragraph: 
+  item-42 at level 1: list: group list
+    item-43 at level 2: list_item: 
+  item-44 at level 1: paragraph: 
+  item-45 at level 1: section: group textbox
+    item-46 at level 2: paragraph: Department of Education:
+Collabo ... vention measures at all school levels.
+  item-47 at level 1: paragraph: 
+  item-48 at level 1: paragraph: 
+  item-49 at level 1: paragraph: 
+  item-50 at level 1: paragraph: 
+  item-51 at level 1: paragraph: 
+  item-52 at level 1: paragraph: 
+  item-53 at level 1: paragraph: 
+  item-54 at level 1: section: group textbox
+    item-55 at level 2: inline: group group
+      item-56 at level 3: paragraph: The Health Bureau will handle
+      item-57 at level 3: paragraph: reporting and specimen collection
+      item-58 at level 3: paragraph: .
+    item-59 at level 2: paragraph: 
+    item-60 at level 2: paragraph: 
+  item-61 at level 1: paragraph: 
+  item-62 at level 1: paragraph: 
+  item-63 at level 1: paragraph: 
+  item-64 at level 1: section: group textbox
+    item-65 at level 2: paragraph: Whether the epidemic has eased.
+    item-66 at level 2: paragraph: 
+    item-67 at level 2: paragraph: 
+  item-68 at level 1: paragraph: 
+  item-69 at level 1: section: group textbox
+    item-70 at level 2: paragraph: Whether the test results are pos ... legally designated infectious disease.
+    item-71 at level 2: paragraph: No
+  item-72 at level 1: paragraph: 
+  item-73 at level 1: paragraph: 
+  item-74 at level 1: section: group textbox
+  item-75 at level 1: paragraph: 
+  item-76 at level 1: section: group textbox
+  item-77 at level 1: paragraph: 
+  item-78 at level 1: paragraph: 
+  item-79 at level 1: section: group textbox
+    item-80 at level 2: paragraph: Case closed.
+    item-81 at level 2: paragraph: 
+    item-82 at level 2: paragraph: 
+    item-83 at level 2: paragraph: The Health Bureau will carry out ... ters for Disease Control if necessary.
+  item-84 at level 1: paragraph: 
+  item-85 at level 1: section: group textbox
+  item-86 at level 1: paragraph: 
+  item-87 at level 1: paragraph: 
+  item-88 at level 1: paragraph: 

tests/data/groundtruth/docling_v2/textbox.docx.md

@@ -0,0 +1,46 @@
+**Chiayi County Shuishang Township Nanjing Elementary School Affiliated Kindergarten**
+
+**Infectious Disease Reporting Procedure for the 113th Academic Year Kindergarten**
+
+**Student falls ill**
+
+- Suggested Reportable Symptoms:
+＊ Fever
+＊ Cough
+＊ Diarrhea
+＊ Vomiting
+＊ Rash
+＊ Blisters
+＊ Headache
+＊ Sore throat
+
+If a caregiver suspects that within one week, a fifth of the class (for classes with more than 15 students) or more than three students (for classes with 15 or fewer students)
+show the same suggested reportable symptoms
+
+Yes
+
+  A report must be submitted within 24 hours via the Ministry of Education’s Campus Safety and Disaster Prevention Information Network.
+
+  A report must also be submitted within 48 hours through Chiayi County’s School Suspected Infectious Disease Reporting System.
+
+**Health Bureau:**
+
+Upon receiving a report from the kindergarten, conduct a preliminary assessment of the case, and depending on the situation and type of illness, carry out an epidemiological investigation and report to the Centers for Disease Control.
+
+- If necessary, provide health education and important reminders at the kindergarten, or notify the individual to undergo specimen collection.
+- Implement appropriate epidemic prevention measures in accordance with the Communicable Disease Control Act.
+
+Department of Education:
+Collaborate with the Health Bureau in conducting epidemiological investigations and assist Health Bureau personnel in implementing necessary epidemic prevention measures at all school levels.
+
+The Health Bureau will handle **reporting and specimen collection** .
+
+**Whether the epidemic has eased.**
+
+**Whether the test results are positive for a legally designated infectious disease.**
+
+No
+
+**Case closed.**
+
+The Health Bureau will carry out subsequent related epidemic prevention measures and follow-up, and will request assistance from the Centers for Disease Control if necessary.

tests/test_backend_csv.py

@@ -39,7 +39,14 @@ def test_e2e_valid_csv_conversions():
         print(f"converting {csv_path}")
 
         gt_path = csv_path.parent.parent / "groundtruth" / "docling_v2" / csv_path.name
-
+        if csv_path.stem in (
+            "csv-too-few-columns",
+            "csv-too-many-columns",
+            "csv-inconsistent-header",
+        ):
+            with warns(UserWarning, match="Inconsistent column lengths"):
+                conv_result: ConversionResult = converter.convert(csv_path)
+        else:
             conv_result: ConversionResult = converter.convert(csv_path)
 
         doc: DoclingDocument = conv_result.document

tests/test_legacy_format_transform.py

@@ -38,11 +38,10 @@ def get_converter():
 
 def test_compare_legacy_output(test_doc_paths):
     converter = get_converter()
-
     res = converter.convert_all(test_doc_paths, raises_on_error=True)
-
     for conv_res in res:
         print(f"Results for {conv_res.input.file}")
+        with pytest.warns(DeprecationWarning, match="Use document instead"):
             print(
                 json.dumps(
                     conv_res.legacy_document.model_dump(
@@ -50,5 +49,4 @@ def test_compare_legacy_output(test_doc_paths):
                     )
                 )
             )
-
     # assert res.legacy_output == res.legacy_output_transformed

tests/verify_utils.py

@@ -4,6 +4,7 @@ import warnings
 from pathlib import Path
 from typing import List, Optional
 
+import pytest
 from docling_core.types.doc import (
     DocItem,
     DoclingDocument,
@@ -302,9 +303,8 @@ def verify_conversion_result_v1(
     )
 
     doc_pred_pages: List[Page] = doc_result.pages
+    with pytest.warns(DeprecationWarning, match="Use document instead"):
         doc_pred: DsDocument = doc_result.legacy_document
-    with warnings.catch_warnings():
-        warnings.simplefilter("ignore", DeprecationWarning)
         doc_pred_md = doc_result.legacy_document.export_to_markdown()
         doc_pred_dt = doc_result.legacy_document.export_to_document_tokens()
 
@@ -391,7 +391,7 @@ def verify_conversion_result_v2(
     doc_pred_pages: List[Page] = doc_result.pages
     doc_pred: DoclingDocument = doc_result.document
     doc_pred_md = doc_result.document.export_to_markdown()
-    doc_pred_dt = doc_result.document.export_to_document_tokens()
+    doc_pred_dt = doc_result.document.export_to_doctags()
 
     engine_suffix = "" if ocr_engine is None else f".{ocr_engine}"