docling 0.3.1__tar.gz → 1.0.0__tar.gz

{docling-0.3.1 → docling-1.0.0}/PKG-INFO

@@ -1,13 +1,13 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 0.3.1
+Version: 1.0.0
 Summary: Docling PDF conversion package
 Home-page: https://github.com/DS4SD/docling
 License: MIT
 Keywords: docling,convert,document,pdf,layout model,segmentation,table structure,table former
 Author: Christoph Auer
 Author-email: cau@zurich.ibm.com
-Requires-Python: >=3.11,<4.0
+Requires-Python: >=3.10,<4.0
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
@@ -15,13 +15,13 @@ Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: MacOS :: MacOS X
 Classifier: Operating System :: POSIX :: Linux
 Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Dist: deepsearch-glm (>=0.19.0,<1)
-Requires-Dist: deepsearch-toolkit (>=0.47.0,<1)
-Requires-Dist: docling-core (>=0.2.0,<0.3.0)
-Requires-Dist: docling-ibm-models (>=0.2.0,<0.3.0)
+Requires-Dist: docling-core (>=1.1.0,<2.0.0)
+Requires-Dist: docling-ibm-models (>=1.1.0,<2.0.0)
 Requires-Dist: filetype (>=1.2.0,<2.0.0)
 Requires-Dist: huggingface_hub (>=0.23,<1)
 Requires-Dist: pydantic (>=2.0.0,<3.0.0)
@@ -31,19 +31,21 @@ Project-URL: Repository, https://github.com/DS4SD/docling
 Description-Content-Type: text/markdown
 
 <p align="center">
-  <a href="https://github.com/ds4sd/docling"> <img loading="lazy" alt="Docling" src="https://github.com/DS4SD/docling/raw/main/logo.png" width="150" />
+  <a href="https://github.com/ds4sd/docling">
+    <img loading="lazy" alt="Docling" src="https://github.com/DS4SD/docling/raw/main/logo.png" width="150" />
+  </a>
 </p>
 
 # Docling
 
 [![PyPI version](https://img.shields.io/pypi/v/docling)](https://pypi.org/project/docling/)
-![Python](https://img.shields.io/badge/python-3.11%20%7C%203.12-blue)
+![Python](https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12-blue)
 [![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)](https://python-poetry.org/)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 [![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)
 [![Pydantic v2](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/pydantic/pydantic/main/docs/badge/v2.json)](https://pydantic.dev)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
-[![License MIT](https://img.shields.io/github/license/ds4sd/deepsearch-toolkit)](https://opensource.org/licenses/MIT)
+[![License MIT](https://img.shields.io/github/license/DS4SD/docling)](https://opensource.org/licenses/MIT)
 
 Docling bundles PDF document conversion to JSON and Markdown in an easy, self-contained package.
 
@@ -65,7 +67,7 @@ pip install docling
 
 ### Development setup
 
-To develop for Docling, you need Python 3.11 / 3.12 and Poetry. You can then install from your local clone's root dir:
+To develop for Docling, you need Python 3.10 / 3.11 / 3.12 and Poetry. You can then install from your local clone's root dir:
 ```bash
 poetry install
 ```
@@ -79,7 +81,9 @@ python examples/convert.py
 ```
 The output of the above command will be written to `./scratch`.
 
-### Enable or disable pipeline features
+### Adjust pipeline features
+
+#### Control pipeline options
 
 You can control if table structure recognition or OCR should be performed by arguments passed to `DocumentConverter`:
 ```python
@@ -92,6 +96,22 @@ doc_converter = DocumentConverter(
 )
 ```
 
+#### Control table extraction options
+
+You can control if table structure recognition should map the recognized structure back to PDF cells (default) or use text cells from the structure prediction itself.
+This can improve output quality if you find that multiple columns in extracted tables are erroneously merged into one.
+
+
+```python
+pipeline_options = PipelineOptions(do_table_structure=True)
+pipeline_options.table_structure_options.do_cell_matching = False  # uses text cells predicted from table structure model
+
+doc_converter = DocumentConverter(
+    artifacts_path=artifacts_path,
+    pipeline_options=pipeline_options,
+)
+```
+
 ### Impose limits on the document size
 
 You can limit the file size and number of pages which should be allowed to process per document:

{docling-0.3.1 → docling-1.0.0}/README.md

@@ -1,17 +1,19 @@
 <p align="center">
-  <a href="https://github.com/ds4sd/docling"> <img loading="lazy" alt="Docling" src="https://github.com/DS4SD/docling/raw/main/logo.png" width="150" />
+  <a href="https://github.com/ds4sd/docling">
+    <img loading="lazy" alt="Docling" src="https://github.com/DS4SD/docling/raw/main/logo.png" width="150" />
+  </a>
 </p>
 
 # Docling
 
 [![PyPI version](https://img.shields.io/pypi/v/docling)](https://pypi.org/project/docling/)
-![Python](https://img.shields.io/badge/python-3.11%20%7C%203.12-blue)
+![Python](https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12-blue)
 [![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)](https://python-poetry.org/)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 [![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)
 [![Pydantic v2](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/pydantic/pydantic/main/docs/badge/v2.json)](https://pydantic.dev)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
-[![License MIT](https://img.shields.io/github/license/ds4sd/deepsearch-toolkit)](https://opensource.org/licenses/MIT)
+[![License MIT](https://img.shields.io/github/license/DS4SD/docling)](https://opensource.org/licenses/MIT)
 
 Docling bundles PDF document conversion to JSON and Markdown in an easy, self-contained package.
 
@@ -33,7 +35,7 @@ pip install docling
 
 ### Development setup
 
-To develop for Docling, you need Python 3.11 / 3.12 and Poetry. You can then install from your local clone's root dir:
+To develop for Docling, you need Python 3.10 / 3.11 / 3.12 and Poetry. You can then install from your local clone's root dir:
 ```bash
 poetry install
 ```
@@ -47,7 +49,9 @@ python examples/convert.py
 ```
 The output of the above command will be written to `./scratch`.
 
-### Enable or disable pipeline features
+### Adjust pipeline features
+
+#### Control pipeline options
 
 You can control if table structure recognition or OCR should be performed by arguments passed to `DocumentConverter`:
 ```python
@@ -60,6 +64,22 @@ doc_converter = DocumentConverter(
 )
 ```
 
+#### Control table extraction options
+
+You can control if table structure recognition should map the recognized structure back to PDF cells (default) or use text cells from the structure prediction itself.
+This can improve output quality if you find that multiple columns in extracted tables are erroneously merged into one.
+
+
+```python
+pipeline_options = PipelineOptions(do_table_structure=True)
+pipeline_options.table_structure_options.do_cell_matching = False  # uses text cells predicted from table structure model
+
+doc_converter = DocumentConverter(
+    artifacts_path=artifacts_path,
+    pipeline_options=pipeline_options,
+)
+```
+
 ### Impose limits on the document size
 
 You can limit the file size and number of pages which should be allowed to process per document:

{docling-0.3.1 → docling-1.0.0}/docling/datamodel/base_models.py

@@ -1,3 +1,4 @@
+import copy
 from enum import Enum, auto
 from io import BytesIO
 from typing import Any, Dict, List, Optional, Tuple, Union
@@ -47,6 +48,15 @@ class BoundingBox(BaseModel):
     def height(self):
         return abs(self.t - self.b)
 
+    def scaled(self, scale: float) -> "BoundingBox":
+        out_bbox = copy.deepcopy(self)
+        out_bbox.l *= scale
+        out_bbox.r *= scale
+        out_bbox.t *= scale
+        out_bbox.b *= scale
+
+        return out_bbox
+
     def as_tuple(self):
         if self.coord_origin == CoordOrigin.TOPLEFT:
             return (self.l, self.t, self.r, self.b)
@@ -241,6 +251,17 @@ class DocumentStream(BaseModel):
     stream: BytesIO
 
 
+class TableStructureOptions(BaseModel):
+    do_cell_matching: bool = (
+        True
+        # True:  Matches predictions back to PDF cells. Can break table output if PDF cells
+        #        are merged across table columns.
+        # False: Let table structure model define the text cells, ignore PDF cells.
+    )
+
+
 class PipelineOptions(BaseModel):
-    do_table_structure: bool = True
-    do_ocr: bool = False
+    do_table_structure: bool = True  # True: perform table structure extraction
+    do_ocr: bool = False  # True: perform OCR, replace programmatic PDF text
+
+    table_structure_options: TableStructureOptions = TableStructureOptions()

{docling-0.3.1 → docling-1.0.0}/docling/datamodel/document.py

@@ -3,7 +3,6 @@ from io import BytesIO
 from pathlib import Path, PurePath
 from typing import ClassVar, Dict, Iterable, List, Optional, Type, Union
 
-from deepsearch.documents.core.export import export_to_markdown
 from docling_core.types import BaseCell, BaseText
 from docling_core.types import BoundingBox as DsBoundingBox
 from docling_core.types import Document as DsDocument
@@ -299,9 +298,7 @@ class ConvertedDocument(BaseModel):
 
     def render_as_markdown(self):
         if self.output:
-            return export_to_markdown(
-                self.output.model_dump(by_alias=True, exclude_none=True)
-            )
+            return self.output.export_to_markdown()
         else:
             return ""
 

{docling-0.3.1 → docling-1.0.0}/docling/models/page_assemble_model.py

@@ -19,18 +19,6 @@ class PageAssembleModel:
     def __init__(self, config):
         self.config = config
 
-        # self.line_wrap_pattern = re.compile(r'(?<=[^\W_])- \n(?=\w)')
-
-    # def sanitize_text_poor(self, lines):
-    #     text = '\n'.join(lines)
-    #
-    #     # treat line wraps.
-    #     sanitized_text = self.line_wrap_pattern.sub('', text)
-    #
-    #     sanitized_text = sanitized_text.replace('\n', ' ')
-    #
-    #     return sanitized_text
-
     def sanitize_text(self, lines):
         if len(lines) <= 1:
             return " ".join(lines)

{docling-0.3.1 → docling-1.0.0}/docling/models/table_structure_model.py

@@ -1,7 +1,10 @@
-from typing import Iterable
+import copy
+import random
+from typing import Iterable, List
 
 import numpy
 from docling_ibm_models.tableformer.data_management.tf_predictor import TFPredictor
+from PIL import ImageDraw
 
 from docling.datamodel.base_models import (
     BoundingBox,
@@ -28,6 +31,21 @@ class TableStructureModel:
             self.tm_model_type = self.tm_config["model"]["type"]
 
             self.tf_predictor = TFPredictor(self.tm_config)
+            self.scale = 2.0  # Scale up table input images to 144 dpi
+
+    def draw_table_and_cells(self, page: Page, tbl_list: List[TableElement]):
+        image = page._backend.get_page_image()
+        draw = ImageDraw.Draw(image)
+
+        for table_element in tbl_list:
+            x0, y0, x1, y1 = table_element.cluster.bbox.as_tuple()
+            draw.rectangle([(x0, y0), (x1, y1)], outline="red")
+
+            for tc in table_element.table_cells:
+                x0, y0, x1, y1 = tc.bbox.as_tuple()
+                draw.rectangle([(x0, y0), (x1, y1)], outline="blue")
+
+        image.show()
 
     def __call__(self, page_batch: Iterable[Page]) -> Iterable[Page]:
 
@@ -36,16 +54,17 @@ class TableStructureModel:
             return
 
         for page in page_batch:
+
             page.predictions.tablestructure = TableStructurePrediction()  # dummy
 
             in_tables = [
                 (
                     cluster,
                     [
-                        round(cluster.bbox.l),
-                        round(cluster.bbox.t),
-                        round(cluster.bbox.r),
-                        round(cluster.bbox.b),
+                        round(cluster.bbox.l) * self.scale,
+                        round(cluster.bbox.t) * self.scale,
+                        round(cluster.bbox.r) * self.scale,
+                        round(cluster.bbox.b) * self.scale,
                     ],
                 )
                 for cluster in page.predictions.layout.clusters
@@ -65,20 +84,29 @@ class TableStructureModel:
                         ):
                             # Only allow non empty stings (spaces) into the cells of a table
                             if len(c.text.strip()) > 0:
-                                tokens.append(c.model_dump())
+                                new_cell = copy.deepcopy(c)
+                                new_cell.bbox = new_cell.bbox.scaled(scale=self.scale)
+
+                                tokens.append(new_cell.model_dump())
 
-            iocr_page = {
-                "image": numpy.asarray(page.image),
+            page_input = {
                 "tokens": tokens,
-                "width": page.size.width,
-                "height": page.size.height,
+                "width": page.size.width * self.scale,
+                "height": page.size.height * self.scale,
             }
+            # add image to page input.
+            if self.scale == 1.0:
+                page_input["image"] = numpy.asarray(page.image)
+            else:  # render new page image on the fly at desired scale
+                page_input["image"] = numpy.asarray(
+                    page._backend.get_page_image(scale=self.scale)
+                )
 
             table_clusters, table_bboxes = zip(*in_tables)
 
             if len(table_bboxes):
                 tf_output = self.tf_predictor.multi_table_predict(
-                    iocr_page, table_bboxes, do_matching=self.do_cell_matching
+                    page_input, table_bboxes, do_matching=self.do_cell_matching
                 )
 
                 for table_cluster, table_out in zip(table_clusters, tf_output):
@@ -91,6 +119,7 @@ class TableStructureModel:
                             element["bbox"]["token"] = text_piece
 
                         tc = TableCell.model_validate(element)
+                        tc.bbox = tc.bbox.scaled(1 / self.scale)
                         table_cells.append(tc)
 
                     # Retrieving cols/rows, after post processing:
@@ -111,4 +140,7 @@ class TableStructureModel:
 
                     page.predictions.tablestructure.table_map[table_cluster.id] = tbl
 
+                # For debugging purposes:
+                # self.draw_table_and_cells(page, page.predictions.tablestructure.table_map.values())
+
             yield page

{docling-0.3.1 → docling-1.0.0}/docling/pipeline/standard_model_pipeline.py

@@ -34,7 +34,7 @@ class StandardModelPipeline(BaseModelPipeline):
                     "artifacts_path": artifacts_path
                     / StandardModelPipeline._table_model_path,
                     "enabled": pipeline_options.do_table_structure,
-                    "do_cell_matching": False,
+                    "do_cell_matching": pipeline_options.table_structure_options.do_cell_matching,
                 }
             ),
         ]

{docling-0.3.1 → docling-1.0.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "0.3.1"  # DO NOT EDIT, updated automatically
+version = "1.0.0"  # DO NOT EDIT, updated automatically
 description = "Docling PDF conversion package"
 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>", "Peter Staar <taa@zurich.ibm.com>"]
 license = "MIT"
@@ -21,12 +21,11 @@ keywords= ["docling", "convert", "document", "pdf", "layout model", "segmentatio
 packages = [{include = "docling"}]
 
 [tool.poetry.dependencies]
-python = "^3.11"
+python = "^3.10"
 pydantic = "^2.0.0"
-docling-core = "^0.2.0"
-docling-ibm-models = "^0.2.0"
+docling-core = "^1.1.0"
+docling-ibm-models = "^1.1.0"
 deepsearch-glm = ">=0.19.0,<1"
-deepsearch-toolkit = ">=0.47.0,<1"
 filetype = "^1.2.0"
 pypdfium2 = "^4.30.0"
 pydantic-settings = "^2.3.0"
@@ -55,7 +54,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.black]
 line-length = 88
-target-version = ["py311"]
+target-version = ["py310"]
 include = '\.pyi?$'
 
 [tool.isort]
@@ -67,7 +66,7 @@ py_version=311
 pretty = true
 # strict = true
 no_implicit_optional = true
-python_version = "3.11"
+python_version = "3.10"
 
 [tool.flake8]
 max-line-length = 88