docling 2.8.1__tar.gz → 2.8.2__tar.gz

{docling-2.8.1 → docling-2.8.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.8.1
+Version: 2.8.2
 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
@@ -26,7 +26,7 @@ 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 (>=2.5.1,<3.0.0)
+Requires-Dist: docling-core (>=2.6.1,<3.0.0)
 Requires-Dist: docling-ibm-models (>=2.0.6,<3.0.0)
 Requires-Dist: docling-parse (>=2.0.5,<3.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)

{docling-2.8.1 → docling-2.8.2}/docling/cli/main.py

@@ -2,6 +2,7 @@ import importlib
 import json
 import logging
 import re
+import tempfile
 import time
 import warnings
 from enum import Enum
@@ -9,7 +10,7 @@ from pathlib import Path
 from typing import Annotated, Dict, Iterable, List, Optional, Type
 
 import typer
-from docling_core.utils.file import resolve_file_source
+from docling_core.utils.file import resolve_source_to_path
 
 from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
 from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
@@ -256,95 +257,98 @@ def convert(
     if from_formats is None:
         from_formats = [e for e in InputFormat]
 
-    input_doc_paths: List[Path] = []
-    for src in input_sources:
-        source = resolve_file_source(source=src)
-        if not source.exists():
-            err_console.print(
-                f"[red]Error: The input file {source} does not exist.[/red]"
-            )
-            raise typer.Abort()
-        elif source.is_dir():
-            for fmt in from_formats:
-                for ext in FormatToExtensions[fmt]:
-                    input_doc_paths.extend(list(source.glob(f"**/*.{ext}")))
-                    input_doc_paths.extend(list(source.glob(f"**/*.{ext.upper()}")))
+    with tempfile.TemporaryDirectory() as tempdir:
+        input_doc_paths: List[Path] = []
+        for src in input_sources:
+            source = resolve_source_to_path(source=src, workdir=Path(tempdir))
+            if not source.exists():
+                err_console.print(
+                    f"[red]Error: The input file {source} does not exist.[/red]"
+                )
+                raise typer.Abort()
+            elif source.is_dir():
+                for fmt in from_formats:
+                    for ext in FormatToExtensions[fmt]:
+                        input_doc_paths.extend(list(source.glob(f"**/*.{ext}")))
+                        input_doc_paths.extend(list(source.glob(f"**/*.{ext.upper()}")))
+            else:
+                input_doc_paths.append(source)
+
+        if to_formats is None:
+            to_formats = [OutputFormat.MARKDOWN]
+
+        export_json = OutputFormat.JSON in to_formats
+        export_md = OutputFormat.MARKDOWN in to_formats
+        export_txt = OutputFormat.TEXT in to_formats
+        export_doctags = OutputFormat.DOCTAGS in to_formats
+
+        if ocr_engine == OcrEngine.EASYOCR:
+            ocr_options: OcrOptions = EasyOcrOptions(force_full_page_ocr=force_ocr)
+        elif ocr_engine == OcrEngine.TESSERACT_CLI:
+            ocr_options = TesseractCliOcrOptions(force_full_page_ocr=force_ocr)
+        elif ocr_engine == OcrEngine.TESSERACT:
+            ocr_options = TesseractOcrOptions(force_full_page_ocr=force_ocr)
+        elif ocr_engine == OcrEngine.OCRMAC:
+            ocr_options = OcrMacOptions(force_full_page_ocr=force_ocr)
+        elif ocr_engine == OcrEngine.RAPIDOCR:
+            ocr_options = RapidOcrOptions(force_full_page_ocr=force_ocr)
         else:
-            input_doc_paths.append(source)
-
-    if to_formats is None:
-        to_formats = [OutputFormat.MARKDOWN]
-
-    export_json = OutputFormat.JSON in to_formats
-    export_md = OutputFormat.MARKDOWN in to_formats
-    export_txt = OutputFormat.TEXT in to_formats
-    export_doctags = OutputFormat.DOCTAGS in to_formats
-
-    if ocr_engine == OcrEngine.EASYOCR:
-        ocr_options: OcrOptions = EasyOcrOptions(force_full_page_ocr=force_ocr)
-    elif ocr_engine == OcrEngine.TESSERACT_CLI:
-        ocr_options = TesseractCliOcrOptions(force_full_page_ocr=force_ocr)
-    elif ocr_engine == OcrEngine.TESSERACT:
-        ocr_options = TesseractOcrOptions(force_full_page_ocr=force_ocr)
-    elif ocr_engine == OcrEngine.OCRMAC:
-        ocr_options = OcrMacOptions(force_full_page_ocr=force_ocr)
-    elif ocr_engine == OcrEngine.RAPIDOCR:
-        ocr_options = RapidOcrOptions(force_full_page_ocr=force_ocr)
-    else:
-        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,
-        do_table_structure=True,
-    )
-    pipeline_options.table_structure_options.do_cell_matching = True  # do_cell_matching
-    pipeline_options.table_structure_options.mode = table_mode
-
-    if artifacts_path is not None:
-        pipeline_options.artifacts_path = artifacts_path
-
-    if pdf_backend == PdfBackend.DLPARSE_V1:
-        backend: Type[PdfDocumentBackend] = DoclingParseDocumentBackend
-    elif pdf_backend == PdfBackend.DLPARSE_V2:
-        backend = DoclingParseV2DocumentBackend
-    elif pdf_backend == PdfBackend.PYPDFIUM2:
-        backend = PyPdfiumDocumentBackend
-    else:
-        raise RuntimeError(f"Unexpected PDF backend type {pdf_backend}")
-
-    format_options: Dict[InputFormat, FormatOption] = {
-        InputFormat.PDF: PdfFormatOption(
-            pipeline_options=pipeline_options,
-            backend=backend,  # pdf_backend
+            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,
+            do_table_structure=True,
         )
-    }
-    doc_converter = DocumentConverter(
-        allowed_formats=from_formats,
-        format_options=format_options,
-    )
+        pipeline_options.table_structure_options.do_cell_matching = (
+            True  # do_cell_matching
+        )
+        pipeline_options.table_structure_options.mode = table_mode
 
-    start_time = time.time()
+        if artifacts_path is not None:
+            pipeline_options.artifacts_path = artifacts_path
 
-    conv_results = doc_converter.convert_all(
-        input_doc_paths, raises_on_error=abort_on_error
-    )
+        if pdf_backend == PdfBackend.DLPARSE_V1:
+            backend: Type[PdfDocumentBackend] = DoclingParseDocumentBackend
+        elif pdf_backend == PdfBackend.DLPARSE_V2:
+            backend = DoclingParseV2DocumentBackend
+        elif pdf_backend == PdfBackend.PYPDFIUM2:
+            backend = PyPdfiumDocumentBackend
+        else:
+            raise RuntimeError(f"Unexpected PDF backend type {pdf_backend}")
 
-    output.mkdir(parents=True, exist_ok=True)
-    export_documents(
-        conv_results,
-        output_dir=output,
-        export_json=export_json,
-        export_md=export_md,
-        export_txt=export_txt,
-        export_doctags=export_doctags,
-    )
+        format_options: Dict[InputFormat, FormatOption] = {
+            InputFormat.PDF: PdfFormatOption(
+                pipeline_options=pipeline_options,
+                backend=backend,  # pdf_backend
+            )
+        }
+        doc_converter = DocumentConverter(
+            allowed_formats=from_formats,
+            format_options=format_options,
+        )
+
+        start_time = time.time()
+
+        conv_results = doc_converter.convert_all(
+            input_doc_paths, raises_on_error=abort_on_error
+        )
+
+        output.mkdir(parents=True, exist_ok=True)
+        export_documents(
+            conv_results,
+            output_dir=output,
+            export_json=export_json,
+            export_md=export_md,
+            export_txt=export_txt,
+            export_doctags=export_doctags,
+        )
 
-    end_time = time.time() - start_time
+        end_time = time.time() - start_time
 
     _log.info(f"All documents were converted in {end_time:.2f} seconds.")
 

{docling-2.8.1 → docling-2.8.2}/docling/datamodel/base_models.py

@@ -1,5 +1,4 @@
 from enum import Enum, auto
-from io import BytesIO
 from typing import TYPE_CHECKING, Dict, List, Optional, Union
 
 from docling_core.types.doc import (
@@ -9,6 +8,9 @@ from docling_core.types.doc import (
     Size,
     TableCell,
 )
+from docling_core.types.io import (  # DO ΝΟΤ REMOVE; explicitly exposed from this location
+    DocumentStream,
+)
 from PIL.Image import Image
 from pydantic import BaseModel, ConfigDict
 
@@ -207,10 +209,3 @@ class Page(BaseModel):
     @property
     def image(self) -> Optional[Image]:
         return self.get_image(scale=self._default_image_scale)
-
-
-class DocumentStream(BaseModel):
-    model_config = ConfigDict(arbitrary_types_allowed=True)
-
-    name: str
-    stream: BytesIO

{docling-2.8.1 → docling-2.8.2}/docling/datamodel/document.py

@@ -32,7 +32,7 @@ from docling_core.types.legacy_doc.document import (
 )
 from docling_core.types.legacy_doc.document import CCSFileInfoObject as DsFileInfoObject
 from docling_core.types.legacy_doc.document import ExportedCCSDocument as DsDocument
-from docling_core.utils.file import resolve_file_source
+from docling_core.utils.file import resolve_source_to_stream
 from pydantic import BaseModel
 from typing_extensions import deprecated
 
@@ -459,7 +459,7 @@ class _DocumentConversionInput(BaseModel):
         self, format_options: Dict[InputFormat, "FormatOption"]
     ) -> Iterable[InputDocument]:
         for item in self.path_or_stream_iterator:
-            obj = resolve_file_source(item) if isinstance(item, str) else item
+            obj = resolve_source_to_stream(item) if isinstance(item, str) else item
             format = self._guess_format(obj)
             if format not in format_options.keys():
                 _log.info(

{docling-2.8.1 → docling-2.8.2}/docling/datamodel/pipeline_options.py

@@ -6,11 +6,15 @@ from pydantic import BaseModel, ConfigDict, Field
 
 
 class TableFormerMode(str, Enum):
+    """Modes for the TableFormer model."""
+
     FAST = "fast"
     ACCURATE = "accurate"
 
 
 class TableStructureOptions(BaseModel):
+    """Options for the table structure."""
+
     do_cell_matching: bool = (
         True
         # True:  Matches predictions back to PDF cells. Can break table output if PDF cells
@@ -21,6 +25,8 @@ class TableStructureOptions(BaseModel):
 
 
 class OcrOptions(BaseModel):
+    """OCR options."""
+
     kind: str
     lang: List[str]
     force_full_page_ocr: bool = False  # If enabled a full page OCR is always applied
@@ -30,6 +36,8 @@ class OcrOptions(BaseModel):
 
 
 class RapidOcrOptions(OcrOptions):
+    """Options for the RapidOCR engine."""
+
     kind: Literal["rapidocr"] = "rapidocr"
 
     # English and chinese are the most commly used models and have been tested with RapidOCR.
@@ -66,6 +74,8 @@ class RapidOcrOptions(OcrOptions):
 
 
 class EasyOcrOptions(OcrOptions):
+    """Options for the EasyOCR engine."""
+
     kind: Literal["easyocr"] = "easyocr"
     lang: List[str] = ["fr", "de", "es", "en"]
     use_gpu: bool = True  # same default as easyocr.Reader
@@ -79,6 +89,8 @@ class EasyOcrOptions(OcrOptions):
 
 
 class TesseractCliOcrOptions(OcrOptions):
+    """Options for the TesseractCli engine."""
+
     kind: Literal["tesseract"] = "tesseract"
     lang: List[str] = ["fra", "deu", "spa", "eng"]
     tesseract_cmd: str = "tesseract"
@@ -90,6 +102,8 @@ class TesseractCliOcrOptions(OcrOptions):
 
 
 class TesseractOcrOptions(OcrOptions):
+    """Options for the Tesseract engine."""
+
     kind: Literal["tesserocr"] = "tesserocr"
     lang: List[str] = ["fra", "deu", "spa", "eng"]
     path: Optional[str] = None
@@ -100,6 +114,8 @@ class TesseractOcrOptions(OcrOptions):
 
 
 class OcrMacOptions(OcrOptions):
+    """Options for the Mac OCR engine."""
+
     kind: Literal["ocrmac"] = "ocrmac"
     lang: List[str] = ["fr-FR", "de-DE", "es-ES", "en-US"]
     recognition: str = "accurate"
@@ -111,12 +127,16 @@ class OcrMacOptions(OcrOptions):
 
 
 class PipelineOptions(BaseModel):
+    """Base pipeline options."""
+
     create_legacy_output: bool = (
         True  # This defautl will be set to False on a future version of docling
     )
 
 
 class PdfPipelineOptions(PipelineOptions):
+    """Options for the PDF pipeline."""
+
     artifacts_path: Optional[Union[Path, str]] = None
     do_table_structure: bool = True  # True: perform table structure extraction
     do_ocr: bool = True  # True: perform OCR, replace programmatic PDF text

{docling-2.8.1 → docling-2.8.2}/docling/models/tesseract_ocr_cli_model.py

@@ -1,5 +1,7 @@
+import csv
 import io
 import logging
+import os
 import tempfile
 from subprocess import DEVNULL, PIPE, Popen
 from typing import Iterable, Optional, Tuple
@@ -95,7 +97,7 @@ class TesseractOcrCliModel(BaseOcrModel):
         # _log.info(decoded_data)
 
         # Read the TSV file generated by Tesseract
-        df = pd.read_csv(io.StringIO(decoded_data), sep="\t")
+        df = pd.read_csv(io.StringIO(decoded_data), quoting=csv.QUOTE_NONE, sep="\t")
 
         # Display the dataframe (optional)
         # _log.info("df: ", df.head())
@@ -130,14 +132,17 @@ class TesseractOcrCliModel(BaseOcrModel):
                         high_res_image = page._backend.get_page_image(
                             scale=self.scale, cropbox=ocr_rect
                         )
-
-                        with tempfile.NamedTemporaryFile(
-                            suffix=".png", mode="w"
-                        ) as image_file:
-                            fname = image_file.name
-                            high_res_image.save(fname)
+                        try:
+                            with tempfile.NamedTemporaryFile(
+                                suffix=".png", mode="w+b", delete=False
+                            ) as image_file:
+                                fname = image_file.name
+                                high_res_image.save(image_file)
 
                             df = self._run_tesseract(fname)
+                        finally:
+                            if os.path.exists(fname):
+                                os.remove(fname)
 
                         # _log.info(df)
 

{docling-2.8.1 → docling-2.8.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "2.8.1"  # DO NOT EDIT, updated automatically
+version = "2.8.2"  # 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 = "^3.9"
 pydantic = ">=2.0.0,<2.10"
-docling-core = "^2.5.1"
+docling-core = "^2.6.1"
 docling-ibm-models = "^2.0.6"
 deepsearch-glm = "^0.26.1"
 filetype = "^1.2.0"
@@ -80,6 +80,8 @@ types-openpyxl = "^3.1.5.20241114"
 mkdocs-material = "^9.5.40"
 mkdocs-jupyter = "^0.25.0"
 mkdocs-click = "^0.8.1"
+mkdocstrings = {extras = ["python"], version = "^0.27.0"}
+griffe-pydantic = "^1.1.0"
 
 [tool.poetry.group.examples.dependencies]
 datasets = "^2.21.0"
@@ -88,10 +90,13 @@ langchain-huggingface = "^0.0.3"
 langchain-milvus = "^0.1.4"
 langchain-text-splitters = "^0.2.4"
 
+[tool.poetry.group.constraints]
+optional = true
+
 [tool.poetry.group.constraints.dependencies]
 numpy = [
-    { version = "^2.1.0", markers = 'python_version >= "3.13"' },
-    { version = "^1.24.4", markers = 'python_version < "3.13"' },
+    { version = ">=1.24.4,<3.0.0", markers = 'python_version >= "3.10"' },
+    { version = ">=1.24.4,<2.1.0", markers = 'python_version < "3.10"' },
 ]
 
 [tool.poetry.group.mac_intel]