lesyk
c6308dc822
* Add OCR test data and implement tests for various document formats - Created HTML file with multiple images for testing OCR extraction. - Added several PDF files with different layouts and image placements to validate OCR functionality. - Introduced PPTX files with complex layouts and images at various positions for comprehensive testing. - Included XLSX files with multiple images and complex layouts to ensure accurate OCR extraction. - Implemented a new test suite in `test_ocr.py` to validate OCR functionality across all document types, ensuring context preservation and accuracy. * Enhance OCR functionality and validation in document converters - Refactor image extraction and processing in PDF, PPTX, and XLSX converters for improved readability and consistency. - Implement detailed validation for OCR text positioning relative to surrounding text in test cases. - Introduce comprehensive tests for expected OCR results across various document types, ensuring no base64 images are present. - Improve error handling and logging for better debugging during OCR extraction. * Add support for scanned PDFs with full-page OCR fallback and implement tests * Bump version to 0.1.6b1 in __about__.py * Refactor OCR services to support LLM Vision, update README and tests accordingly * Add OCR-enabled converters and ensure consistent OCR format across document types * Refactor converters to improve import organization and enhance OCR functionality across DOCX, PDF, PPTX, and XLSX converters * Refactor exception imports for consistency across converters and tests * Fix OCR tests to match MockOCRService output and fix cross-platform file URI handling * Bump version to 0.1.6b1 in __about__.py * Skip DOCX/XLSX/PPTX OCR tests when optional dependencies are missing * Add comprehensive OCR test suite for various document formats - Introduced multiple test documents for PDF, DOCX, XLSX, and PPTX formats, covering scenarios with images at the start, middle, and end. - Implemented tests for complex layouts, multi-page documents, and documents with multiple images. - Created a new test script `test_ocr.py` to validate OCR functionality, ensuring context preservation and accurate text extraction. - Added expected OCR results for validation against ground truth. - Included tests for scanned documents to verify OCR fallback mechanisms. * Remove obsolete HTML test files and refactor test cases for file URIs and OCR format consistency - Deleted `html_image_start.html` and `html_multiple_images.html` as they are no longer needed. - Updated `test_file_uris` in `test_module_misc.py` to simplify assertions by removing unnecessary `url2pathname` usage. - Removed `test_ocr_format_consistency.py` as it is no longer relevant to the current testing framework. * Refactor OCR processing in PdfConverterWithOCR and enhance unit tests for multipage PDFs * Revert * Revert * Update REDMEs * Refactor import statements for consistency and improve formatting in converter and test files
58 lines
1.7 KiB
TOML
58 lines
1.7 KiB
TOML
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[project]
|
|
name = "markitdown-ocr"
|
|
dynamic = ["version"]
|
|
description = 'OCR plugin for MarkItDown - Extracts text from images in PDF, DOCX, PPTX, and XLSX via LLM Vision'
|
|
readme = "README.md"
|
|
requires-python = ">=3.10"
|
|
license = "MIT"
|
|
keywords = ["markitdown", "ocr", "pdf", "docx", "xlsx", "pptx", "llm", "vision"]
|
|
authors = [
|
|
{ name = "Contributors", email = "noreply@github.com" },
|
|
]
|
|
classifiers = [
|
|
"Development Status :: 4 - Beta",
|
|
"Programming Language :: Python",
|
|
"Programming Language :: Python :: 3.10",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Programming Language :: Python :: 3.13",
|
|
"Programming Language :: Python :: Implementation :: CPython",
|
|
]
|
|
|
|
# Core dependencies — matches the file-format libraries markitdown already uses
|
|
dependencies = [
|
|
"markitdown>=0.1.0",
|
|
"pdfminer.six>=20251230",
|
|
"pdfplumber>=0.11.9",
|
|
"PyMuPDF>=1.24.0",
|
|
"mammoth~=1.11.0",
|
|
"python-docx",
|
|
"python-pptx",
|
|
"pandas",
|
|
"openpyxl",
|
|
"Pillow>=9.0.0",
|
|
]
|
|
|
|
# llm_client is passed in by the user (same as for markitdown image descriptions);
|
|
# install openai or any OpenAI-compatible SDK separately.
|
|
[project.optional-dependencies]
|
|
llm = [
|
|
"openai>=1.0.0",
|
|
]
|
|
|
|
[project.urls]
|
|
Documentation = "https://github.com/microsoft/markitdown#readme"
|
|
Issues = "https://github.com/microsoft/markitdown/issues"
|
|
Source = "https://github.com/microsoft/markitdown"
|
|
|
|
[tool.hatch.version]
|
|
path = "src/markitdown_ocr/__about__.py"
|
|
|
|
# CRITICAL: Plugin entry point - MarkItDown will discover this plugin through this entry point
|
|
[project.entry-points."markitdown.plugin"]
|
|
ocr = "markitdown_ocr"
|