chore: fix or catch deprecation warnings

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>

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()]

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}"