What's Changed

• feat(model): add xycut algorithm for block sorting by @myhloli in https://github.com/opendatalab/MinerU/pull/898
• refactor(pdf_parse): adjust line count threshold for layoutreader by @myhloli in https://github.com/opendatalab/MinerU/pull/902
• Feat/add en docs by @icecraft in https://github.com/opendatalab/MinerU/pull/906
• feat: using next_docs by @icecraft in https://github.com/opendatalab/MinerU/pull/907
• feat(table): integrate RapidTable model for table recognition by @myhloli in https://github.com/opendatalab/MinerU/pull/910
• fix(gradio-app): add missing file type in upload by @myhloli in https://github.com/opendatalab/MinerU/pull/911
• refactor(magic_pdf_parse_main): optimize model data handling and JSON output by @myhloli in https://github.com/opendatalab/MinerU/pull/912
• Modify the test directory by @DTwz in https://github.com/opendatalab/MinerU/pull/913
• test(table): improve ppTableModel test coverage by @myhloli in https://github.com/opendatalab/MinerU/pull/914
• feat(table): add RapidOCR support for RapidTable model by @myhloli in https://github.com/opendatalab/MinerU/pull/915
• 新增DocLayout-YOLO超链接 by @qiangqiang199 in https://github.com/opendatalab/MinerU/pull/889
• fix: remove classes hierarchy diagram by @icecraft in https://github.com/opendatalab/MinerU/pull/919
• refactor(model download script) by @myhloli in https://github.com/opendatalab/MinerU/pull/922
• docs(readme): update table recognition configuration and documentation by @myhloli in https://github.com/opendatalab/MinerU/pull/924
• docs(README_ja-JP.md): update warning message and remove outdated content by @myhloli in https://github.com/opendatalab/MinerU/pull/925
• 更新 para_split_v3.py by @hyastar in https://github.com/opendatalab/MinerU/pull/923
• Style/docs by @icecraft in https://github.com/opendatalab/MinerU/pull/927
• docs: rewrite zh_cn docs without translate by @icecraft in https://github.com/opendatalab/MinerU/pull/928
• fix: typo by @icecraft in https://github.com/opendatalab/MinerU/pull/931
• fix: 修复Dockerfile文件中download_models.py脚本路径问题 by @kimi360 in https://github.com/opendatalab/MinerU/pull/938
• build(Dockerfile): update model download script and dependencies by @myhloli in https://github.com/opendatalab/MinerU/pull/941
• fix(ocr_mkcontent): improve handling of single-character content #937 by @myhloli in https://github.com/opendatalab/MinerU/pull/943
• feat: tune docs by @icecraft in https://github.com/opendatalab/MinerU/pull/948
• fix(parse_pipeline): Resolve post-processing exceptions caused by partial PDFs due to file corruption or non-standard format by forcing a re-print. by @myhloli in https://github.com/opendatalab/MinerU/pull/957
• refactor(model): rename and restructure model modules by @myhloli in https://github.com/opendatalab/MinerU/pull/964
• docs：update docs for 0.9.3 by @myhloli in https://github.com/opendatalab/MinerU/pull/965
• docs(README): update project references and translations by @myhloli in https://github.com/opendatalab/MinerU/pull/967

New Contributors

• @DTwz made their first contribution in https://github.com/opendatalab/MinerU/pull/913
• @qiangqiang199 made their first contribution in https://github.com/opendatalab/MinerU/pull/889
• @hyastar made their first contribution in https://github.com/opendatalab/MinerU/pull/923
• @kimi360 made their first contribution in https://github.com/opendatalab/MinerU/pull/938

Full Changelog: https://github.com/opendatalab/MinerU/compare/magic_pdf-0.9.2-released...magic_pdf-0.9.3-released