docling 2.25.2__py3-none-any.whl → 2.26.0__py3-none-any.whl

docling/cli/main.py

@@ -210,7 +210,7 @@ def convert(
     table_mode: Annotated[
         TableFormerMode,
         typer.Option(..., help="The mode to use in the table structure model."),
-    ] = TableFormerMode.FAST,
+    ] = TableFormerMode.ACCURATE,
     enrich_code: Annotated[
         bool,
         typer.Option(..., help="Enable the code enrichment model in the pipeline."),
@@ -245,7 +245,7 @@ def convert(
         typer.Option(
             ...,
             "--abort-on-error/--no-abort-on-error",
-            help="If enabled, the bitmap content will be processed using OCR.",
+            help="If enabled, the processing will be aborted when the first error is encountered.",
         ),
     ] = False,
     output: Annotated[

docling/datamodel/pipeline_options.py

@@ -99,7 +99,7 @@ class TableStructureOptions(BaseModel):
         #        are merged across table columns.
         # False: Let table structure model define the text cells, ignore PDF cells.
     )
-    mode: TableFormerMode = TableFormerMode.FAST
+    mode: TableFormerMode = TableFormerMode.ACCURATE
 
 
 class OcrOptions(BaseModel):

docling/models/code_formula_model.py

@@ -1,4 +1,5 @@
 import re
+from collections import Counter
 from pathlib import Path
 from typing import Iterable, List, Literal, Optional, Tuple, Union
 
@@ -11,7 +12,7 @@ from docling_core.types.doc import (
     TextItem,
 )
 from docling_core.types.doc.labels import CodeLanguageLabel
-from PIL import Image
+from PIL import Image, ImageOps
 from pydantic import BaseModel
 
 from docling.datamodel.base_models import ItemAndImageEnrichmentElement
@@ -65,7 +66,7 @@ class CodeFormulaModel(BaseItemAndImageEnrichmentModel):
     _model_repo_folder = "ds4sd--CodeFormula"
     elements_batch_size = 5
     images_scale = 1.66  # = 120 dpi, aligned with training data resolution
-    expansion_factor = 0.03
+    expansion_factor = 0.18
 
     def __init__(
         self,
@@ -124,7 +125,7 @@ class CodeFormulaModel(BaseItemAndImageEnrichmentModel):
             repo_id="ds4sd/CodeFormula",
             force_download=force,
             local_dir=local_dir,
-            revision="v1.0.1",
+            revision="v1.0.2",
         )
 
         return Path(download_path)
@@ -175,7 +176,7 @@ class CodeFormulaModel(BaseItemAndImageEnrichmentModel):
                 - The second element is the extracted language if a match is found;
                 otherwise, `None`.
         """
-        pattern = r"^<_([^>]+)_>\s*(.*)"
+        pattern = r"^<_([^_>]+)_>\s(.*)"
         match = re.match(pattern, input_string, flags=re.DOTALL)
         if match:
             language = str(match.group(1))  # the captured programming language
@@ -206,6 +207,82 @@ class CodeFormulaModel(BaseItemAndImageEnrichmentModel):
         except ValueError:
             return CodeLanguageLabel.UNKNOWN
 
+    def _get_most_frequent_edge_color(self, pil_img: Image.Image):
+        """
+        Compute the most frequent color along the outer edges of a PIL image.
+
+        Parameters
+        ----------
+            pil_img : Image.Image
+                A PIL Image in any mode (L, RGB, RGBA, etc.).
+
+        Returns
+        -------
+            (int) or (tuple): The most common edge color as a scalar (for grayscale) or
+                tuple (for RGB/RGBA).
+        """
+        # Convert to NumPy array for easy pixel access
+        img_np = np.array(pil_img)
+
+        if img_np.ndim == 2:
+            # Grayscale-like image: shape (H, W)
+            # Extract edges: top row, bottom row, left col, right col
+            top = img_np[0, :]  # shape (W,)
+            bottom = img_np[-1, :]  # shape (W,)
+            left = img_np[:, 0]  # shape (H,)
+            right = img_np[:, -1]  # shape (H,)
+
+            # Concatenate all edges
+            edges = np.concatenate([top, bottom, left, right])
+
+            # Count frequencies
+            freq = Counter(edges.tolist())
+            most_common_value, _ = freq.most_common(1)[0]
+            return int(most_common_value)  # single channel color
+
+        else:
+            # Color image: shape (H, W, C)
+            top = img_np[0, :, :]  # shape (W, C)
+            bottom = img_np[-1, :, :]  # shape (W, C)
+            left = img_np[:, 0, :]  # shape (H, C)
+            right = img_np[:, -1, :]  # shape (H, C)
+
+            # Concatenate edges along first axis
+            edges = np.concatenate([top, bottom, left, right], axis=0)
+
+            # Convert each color to a tuple for counting
+            edges_as_tuples = [tuple(pixel) for pixel in edges]
+            freq = Counter(edges_as_tuples)
+            most_common_value, _ = freq.most_common(1)[0]
+            return most_common_value  # e.g. (R, G, B) or (R, G, B, A)
+
+    def _pad_with_most_frequent_edge_color(
+        self, img: Union[Image.Image, np.ndarray], padding: Tuple[int, int, int, int]
+    ):
+        """
+        Pads an image (PIL or NumPy array) using the most frequent edge color.
+
+        Parameters
+        ----------
+            img : Union[Image.Image, np.ndarray]
+                The original image.
+            padding : tuple
+                Padding (left, top, right, bottom) in pixels.
+
+        Returns
+        -------
+            Image.Image: A new PIL image with the specified padding.
+        """
+        if isinstance(img, np.ndarray):
+            pil_img = Image.fromarray(img)
+        else:
+            pil_img = img
+
+        most_freq_color = self._get_most_frequent_edge_color(pil_img)
+
+        padded_img = ImageOps.expand(pil_img, border=padding, fill=most_freq_color)
+        return padded_img
+
     def __call__(
         self,
         doc: DoclingDocument,
@@ -238,7 +315,9 @@ class CodeFormulaModel(BaseItemAndImageEnrichmentModel):
             assert isinstance(el.item, TextItem)
             elements.append(el.item)
             labels.append(el.item.label)
-            images.append(el.image)
+            images.append(
+                self._pad_with_most_frequent_edge_color(el.image, (20, 10, 20, 10))
+            )
 
         outputs = self.code_formula_model.predict(images, labels)
 

docling/models/document_picture_classifier.py

@@ -113,7 +113,7 @@ class DocumentPictureClassifier(BaseEnrichmentModel):
             repo_id="ds4sd/DocumentFigureClassifier",
             force_download=force,
             local_dir=local_dir,
-            revision="v1.0.0",
+            revision="v1.0.1",
         )
 
         return Path(download_path)

docling/models/table_structure_model.py

@@ -95,7 +95,7 @@ class TableStructureModel(BasePageModel):
             repo_id="ds4sd/docling-models",
             force_download=force,
             local_dir=local_dir,
-            revision="v2.1.0",
+            revision="v2.2.0",
         )
 
         return Path(download_path)

{docling-2.25.2.dist-info → docling-2.26.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.25.2
+Version: 2.26.0
 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

{docling-2.25.2.dist-info → docling-2.26.0.dist-info}/RECORD

@@ -19,21 +19,21 @@ docling/backend/xml/jats_backend.py,sha256=HXailrDjiwu4swwFnXy3lNfRtLZmkBBp4yqaf
 docling/backend/xml/uspto_backend.py,sha256=IGUNeF2xpLeaVrX6nKb-jXgtSYD2ozULsrDPcrI1IbQ,71040
 docling/chunking/__init__.py,sha256=h83TDs0AuOV6oEPLAPrn9dpGKiU-2Vg6IRNo4cv6GDA,346
 docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/cli/main.py,sha256=pCJ_GFgxsgZ0soz32OhMl-CWi7YXIrvax_m9Qw4UhMs,16839
+docling/cli/main.py,sha256=unokSvmqZqFE_yLUQGBIo7q9QjdFrrE8EqnHxnqpGtM,16863
 docling/cli/models.py,sha256=DDnz-boX2MexPxC8OnOMPgSPG0iwseT3xkkCfgPrZis,3969
 docling/cli/tools.py,sha256=QhtRxQG0TVrfsMqdv5i7J0_qQy1ZZyWYnHPwJl7b5oY,322
 docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/datamodel/base_models.py,sha256=kMDT-rFhtJUFOOOry4wd2PzCMTLFixFklgSgmRDMS64,7201
 docling/datamodel/document.py,sha256=DbJifyMgBEkAk80BMYXTuSgqH2vijDENDkU7Fmr6j_g,14567
-docling/datamodel/pipeline_options.py,sha256=YpWqCqkA44YUFPhiBg_LYcfOAXxNhv10vZKrkfLtJ_I,11987
+docling/datamodel/pipeline_options.py,sha256=L5ZmMZOkE0T2419uk_butX3ZoY8GhLJcmuGm2Gf1OHU,11991
 docling/datamodel/settings.py,sha256=bNMdowIKv7RUchabQTo4rFNEsxfB6pGg2LoZSY634zo,1869
 docling/document_converter.py,sha256=AeiSmKzWcnOkZm8O-KIBG72g3l4W2CAsq3yEbfC1tiE,13184
 docling/exceptions.py,sha256=K1WnCS1leK2JtMB5ewZWKkb0EaijFgl-tRzrO9ntgPM,134
 docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/models/base_model.py,sha256=q_lKeQ0FT70idXlZ3JgyAv8dA8J3bZWBSDBkqTzy0lo,2679
 docling/models/base_ocr_model.py,sha256=YiUMvdjnHw9SHjnfJKT5INrPMoIGEf_Z2OApfl_VRTE,6919
-docling/models/code_formula_model.py,sha256=6grbRPWaLljadheT5s4omdT6hmXfin4gJU17csWvhjY,8611
-docling/models/document_picture_classifier.py,sha256=6I_j6fG5fnhIV6rqN31LYikNTZyg5isXrVs0GIqHDaY,6235
+docling/models/code_formula_model.py,sha256=mOu5luYMzyrCCr8MRGOciNcSvULpQysDd_FXn96WPc8,11477
+docling/models/document_picture_classifier.py,sha256=fz77RsTdlnA_yC47O-KUq2xVWMKX0_9jm_EGcHliw-E,6235
 docling/models/easyocr_model.py,sha256=ePg1exAXeOzkBRBT-6PBSmqKFmnNFkCEd4HNDsGVgLM,6860
 docling/models/hf_vlm_model.py,sha256=NUtLEuG-kNGJeDHWmQKAAOZG4WF0a5hn-KXUUM1mHBQ,6820
 docling/models/layout_model.py,sha256=7fQWipGV1HDrvbP4uOKa9QAicQl89jp7lailQmbFL3w,7804
@@ -45,7 +45,7 @@ docling/models/picture_description_base_model.py,sha256=rZLIW1_CaRAw_EP3zuI8ktC0
 docling/models/picture_description_vlm_model.py,sha256=EvKn4zWgTsQnbMFEoDhU3Ox4Pu5DkPqd2QewsGoXULU,3641
 docling/models/rapid_ocr_model.py,sha256=2HXmurNRPP6qyqn7U5h9NQIs8zi0TMHf56CpcKQk0fU,5038
 docling/models/readingorder_model.py,sha256=hNWbBX3uZv1FxMwKNKn2JFQuQqTspBLsJBVEidXr6Wk,14869
-docling/models/table_structure_model.py,sha256=UIqWlw_9JNfGsO86c00rPb4GCg-yNliKEwyhCqlsZbM,11225
+docling/models/table_structure_model.py,sha256=gEXHRtHlLFUsP_Gs2EPaBJL-3KlMHa5HLUwzr3kN4_Y,11225
 docling/models/tesseract_ocr_cli_model.py,sha256=F5EhS4NDEmLkPq-a0P7o2LrzjmJgACzlYXTDvtD3NtY,9343
 docling/models/tesseract_ocr_model.py,sha256=ikGu6QNknLG64c9yYIb0Ix6MGhBzOoa1ODbNc8MT5r8,8508
 docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -65,8 +65,8 @@ docling/utils/ocr_utils.py,sha256=F7iOOjqolUcImUzir4qjDQd4QWSO3s6JC4WRn3U7uY4,26
 docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
 docling/utils/utils.py,sha256=0ozCk7zUkYzxRVmYoIB2zA1lqjQOuaQzxfGuf1wmKW4,1866
 docling/utils/visualization.py,sha256=cmbIroPQXPmJdFrNIfpC26WpijBwx05qmpu3QhiG1EI,2850
-docling-2.25.2.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.25.2.dist-info/METADATA,sha256=NsR1pyqk-Q5G5pHrpaLf6TCQEE-r-hGrEB9Hpqdgykk,8803
-docling-2.25.2.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-docling-2.25.2.dist-info/entry_points.txt,sha256=cFrINXsORijdm2EWJzf1m9_rDxH9G9W1fP385-9atY4,84
-docling-2.25.2.dist-info/RECORD,,
+docling-2.26.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.26.0.dist-info/METADATA,sha256=IPh-vv9mpl1sHnl4pkEsLGrdYeBlaJ-mfN28sn_zito,8803
+docling-2.26.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+docling-2.26.0.dist-info/entry_points.txt,sha256=cFrINXsORijdm2EWJzf1m9_rDxH9G9W1fP385-9atY4,84
+docling-2.26.0.dist-info/RECORD,,