fix: python3.9 support (#396)

* fixes for python3.9 Signed-off-by: Michele Dolfi <[email protected]> * pin docling-parse with python3.9 wheels Signed-off-by: Michele Dolfi <[email protected]> * update deps Signed-off-by: Michele Dolfi <[email protected]> --------- Signed-off-by: Michele Dolfi <[email protected]>
DS4SD · Nov 20, 2024 · 7b013ab · 7b013ab
1 parent 6efa96c
commit 7b013ab
Show file tree

Hide file tree

Showing 6 changed files with 241 additions and 250 deletions.
diff --git a/.github/workflows/checks.yml b/.github/workflows/checks.yml
@@ -6,7 +6,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ['3.10', '3.11', '3.12']
+        python-version: ['3.9', '3.10', '3.11', '3.12']
     steps:
       - uses: actions/checkout@v3
       - name: Install tesseract

diff --git a/README.md b/README.md
@@ -13,7 +13,7 @@
 [![arXiv](https://img.shields.io/badge/arXiv-2408.09869-b31b1b.svg)](https://arxiv.org/abs/2408.09869)
 [![Docs](https://img.shields.io/badge/docs-live-brightgreen)](https://ds4sd.github.io/docling/)
 [![PyPI version](https://img.shields.io/pypi/v/docling)](https://pypi.org/project/docling/)
-![Python](https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12-blue)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/docling)](https://pypi.org/project/docling/)
 [![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/)

diff --git a/docling/cli/main.py b/docling/cli/main.py
@@ -254,17 +254,16 @@ def convert(
     export_txt = OutputFormat.TEXT in to_formats
     export_doctags = OutputFormat.DOCTAGS in to_formats
 
-    match ocr_engine:
-        case OcrEngine.EASYOCR:
-            ocr_options: OcrOptions = EasyOcrOptions(force_full_page_ocr=force_ocr)
-        case OcrEngine.TESSERACT_CLI:
-            ocr_options = TesseractCliOcrOptions(force_full_page_ocr=force_ocr)
-        case OcrEngine.TESSERACT:
-            ocr_options = TesseractOcrOptions(force_full_page_ocr=force_ocr)
-        case OcrEngine.OCRMAC:
-            ocr_options = OcrMacOptions(force_full_page_ocr=force_ocr)
-        case _:
-            raise RuntimeError(f"Unexpected OCR engine type {ocr_engine}")
+    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)
+    else:
+        raise RuntimeError(f"Unexpected OCR engine type {ocr_engine}")
 
     ocr_lang_list = _split_list(ocr_lang)
     if ocr_lang_list is not None:
@@ -281,15 +280,14 @@ def convert(
     if artifacts_path is not None:
         pipeline_options.artifacts_path = artifacts_path
 
-    match pdf_backend:
-        case PdfBackend.DLPARSE_V1:
-            backend: Type[PdfDocumentBackend] = DoclingParseDocumentBackend
-        case PdfBackend.DLPARSE_V2:
-            backend = DoclingParseV2DocumentBackend
-        case PdfBackend.PYPDFIUM2:
-            backend = PyPdfiumDocumentBackend
-        case _:
-            raise RuntimeError(f"Unexpected PDF backend type {pdf_backend}")
+    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(

diff --git a/docling/document_converter.py b/docling/document_converter.py
@@ -3,7 +3,7 @@
 import time
 from functools import partial
 from pathlib import Path
-from typing import Dict, Iterable, Iterator, List, Optional, Type
+from typing import Dict, Iterable, Iterator, List, Optional, Type, Union
 
 from pydantic import BaseModel, ConfigDict, model_validator, validate_call
 
@@ -155,7 +155,7 @@ def initialize_pipeline(self, format: InputFormat):
     @validate_call(config=ConfigDict(strict=True))
     def convert(
         self,
-        source: Path | str | DocumentStream,  # TODO review naming
+        source: Union[Path, str, DocumentStream],  # TODO review naming
         raises_on_error: bool = True,
         max_num_pages: int = sys.maxsize,
         max_file_size: int = sys.maxsize,
@@ -172,7 +172,7 @@ def convert(
     @validate_call(config=ConfigDict(strict=True))
     def convert_all(
         self,
-        source: Iterable[Path | str | DocumentStream],  # TODO review naming
+        source: Iterable[Union[Path, str, DocumentStream]],  # TODO review naming
         raises_on_error: bool = True,  # True: raises on first conversion error; False: does not raise on conv error
         max_num_pages: int = sys.maxsize,
         max_file_size: int = sys.maxsize,