ATTRIBUTION.json

[
  {
    "format": "odt",
    "path": "documents/odt/pandoc/*.odt",
    "title": "Pandoc ODT Test Suite",
    "author": "John MacFarlane and Pandoc contributors",
    "license": "GPL-2.0-or-later",
    "source": "https://github.com/jgm/pandoc",
    "tags": [
      "pandoc"
    ],
    "donated": "2026-02-17",
    "notes": "Test set from Pandoc"
  },
  {
    "format": "docx",
    "path": "documents/docx/pandoc/*.docx",
    "title": "Pandoc DOCX Test Suite",
    "author": "John MacFarlane and Pandoc contributors",
    "license": "GPL-2.0-or-later",
    "source": "https://github.com/jgm/pandoc",
    "tags": [
      "pandoc"
    ],
    "donated": "2026-02-17",
    "notes": "Test set from Pandoc"
  },
  {
    "format": "docx",
    "path": "documents/docx/vng-ibd/*.docx",
    "title": "Various documents from VNG Informatiebeveiligingsdiensnt",
    "author": "Vereniging van Nederlandse Gemeenten / Informatiebeveiligingsdienst voor gemeenten",
    "license": "CC-BY-NC-SA-4.0",
    "source": "https://www.informatiebeveiligingsdienst.nl/",
    "tags": [
      "vng-ibd",
      "vng"
    ],
    "donated": "2026-02-17",
    "notes": "Scraped from their website"
  },
  {
    "format": "docx",
    "path": "documents/docx/docspec/*.docx",
    "title": "DocSpec DOCX Test Suite",
    "author": "DocSpec",
    "license": "CC-BY-NC-SA-4.0",
    "source": "https://github.com/docspec/documents",
    "tags": [
      "docspec"
    ],
    "donated": "2026-02-17",
    "notes": "Test fixtures originating from NLdoc"
  },
  {
    "format": "rtf",
    "path": "documents/rtf/pandoc/*.rtf",
    "title": "Pandoc RTF Test Suite",
    "author": "John MacFarlane and Pandoc contributors",
    "license": "GPL-2.0-or-later",
    "source": "https://github.com/jgm/pandoc",
    "tags": [
      "pandoc",
      "rtf",
      "test-fixtures"
    ],
    "donated": "2026-04-01",
    "notes": "RTF test fixtures from the Pandoc document converter test suite"
  },
  {
    "format": "rtf",
    "path": "documents/rtf/libreoffice/*.rtf",
    "title": "LibreOffice Writer RTF Test Data",
    "author": "The Document Foundation and LibreOffice contributors",
    "license": "MPL-2.0",
    "source": "https://github.com/LibreOffice/core",
    "tags": [
      "libreoffice",
      "rtf",
      "test-fixtures"
    ],
    "donated": "2026-04-01",
    "notes": "RTF import/export test data from LibreOffice Writer QA (triple-licensed MPL-2.0/LGPL-3.0+/GPL-3.0+; redistributed under MPL-2.0)"
  },
  {
    "format": "doc",
    "path": "documents/doc/apache-poi/*.doc",
    "title": "Apache POI HWPF Test Documents",
    "author": "Apache POI contributors",
    "license": "Apache-2.0",
    "source": "https://github.com/apache/poi",
    "tags": [
      "apache-poi",
      "hwpf",
      "test-fixtures"
    ],
    "donated": "2026-04-01",
    "notes": "Test fixtures for the Apache POI HWPF Word processor module"
  },
  {
    "format": "epub",
    "path": "documents/epub/standard-ebooks/*.epub",
    "title": "Standard Ebooks Collection",
    "author": "Various (original works in public domain; ebook production by Standard Ebooks contributors)",
    "license": "CC0-1.0",
    "source": "https://standardebooks.org",
    "tags": [
      "standard-ebooks",
      "epub",
      "public-domain",
      "literature"
    ],
    "donated": "2026-04-01",
    "notes": "High-quality EPUB ebooks from Standard Ebooks (CC0-1.0 production, public domain source texts)"
  },
  {
    "format": "html",
    "path": "documents/html/mdn-learning-area/*.html",
    "title": "MDN Learning Area HTML Examples",
    "author": "Mozilla Developer Network contributors",
    "license": "CC0-1.0",
    "source": "https://github.com/mdn/learning-area",
    "tags": [
      "mdn",
      "html",
      "examples",
      "educational"
    ],
    "donated": "2026-04-01",
    "notes": "Standalone HTML examples from MDN Web Docs learning area (introduction-to-html, multimedia-and-embedding, tables, forms)"
  },
  {
    "format": "html",
    "path": "documents/html/wpt/*.html",
    "title": "W3C Web Platform Tests HTML Fixtures",
    "author": "W3C Web Platform Tests contributors",
    "license": "BSD-3-Clause",
    "source": "https://github.com/web-platform-tests/wpt",
    "tags": [
      "w3c",
      "wpt",
      "html",
      "test-fixtures",
      "semantics"
    ],
    "donated": "2026-04-01",
    "notes": "HTML test fixtures from the W3C Web Platform Tests project (html/semantics subdirectories)"
  },
  {
    "format": "html",
    "path": "documents/html/html5-boilerplate/*.html",
    "title": "HTML5 Boilerplate Templates",
    "author": "HTML5 Boilerplate contributors",
    "license": "MIT",
    "source": "https://github.com/h5bp/html5-boilerplate",
    "tags": [
      "h5bp",
      "html5",
      "boilerplate",
      "template"
    ],
    "donated": "2026-04-01",
    "notes": "Starter HTML templates from the HTML5 Boilerplate project (v6, v7, main)"
  },
  {
    "format": "markdown",
    "path": "documents/markdown/commonmark/*.md",
    "title": "CommonMark Spec Sections",
    "author": "John MacFarlane and CommonMark contributors",
    "license": "CC-BY-SA-4.0",
    "source": "https://github.com/commonmark/commonmark-spec",
    "tags": [
      "commonmark",
      "spec",
      "markdown"
    ],
    "donated": "2026-04-01",
    "notes": "Sections extracted from the CommonMark specification (spec.txt)"
  },
  {
    "format": "markdown",
    "path": "documents/markdown/rust-book/*.md",
    "title": "The Rust Programming Language Book",
    "author": "Steve Klabnik, Carol Nichols, and the Rust community",
    "license": "MIT",
    "source": "https://github.com/rust-lang/book",
    "tags": [
      "rust",
      "book",
      "programming"
    ],
    "donated": "2026-04-01",
    "notes": "Chapter files from the official Rust programming language book (dual-licensed MIT/Apache-2.0)"
  },
  {
    "format": "markdown",
    "path": "documents/markdown/docusaurus/*.md",
    "title": "Docusaurus Documentation",
    "author": "Meta Platforms, Inc. and Docusaurus contributors",
    "license": "CC-BY-4.0",
    "source": "https://github.com/facebook/docusaurus",
    "tags": [
      "docusaurus",
      "documentation",
      "static-site"
    ],
    "donated": "2026-04-01",
    "notes": "Documentation pages from the Docusaurus website docs (MDX saved as .md; docs are CC-BY-4.0 per LICENSE-docs, code is MIT)"
  },
  {
    "format": "odt",
    "path": "documents/odt/libreoffice/*.odt",
    "title": "LibreOffice Writer ODF Test Data",
    "author": "The Document Foundation and LibreOffice contributors",
    "license": "MPL-2.0",
    "source": "https://github.com/LibreOffice/core",
    "tags": [
      "libreoffice",
      "odt",
      "odf",
      "test-fixtures"
    ],
    "donated": "2026-04-01",
    "notes": "ODF import/export test data from LibreOffice Writer QA (triple-licensed MPL-2.0/LGPL-3.0+/GPL-3.0+; redistributed under MPL-2.0)"
  },
  {
    "format": "odt",
    "path": "documents/odt/odftoolkit/*.odt",
    "title": "ODF Toolkit Test Documents",
    "author": "The Apache Software Foundation and ODF Toolkit contributors",
    "license": "Apache-2.0",
    "source": "https://github.com/tdf/odftoolkit",
    "tags": [
      "odftoolkit",
      "odt",
      "odf",
      "test-fixtures"
    ],
    "donated": "2026-04-01",
    "notes": "ODF DOM, validation, and specification compliance test fixtures from the ODF Toolkit project"
  },
  {
    "format": "pdf",
    "path": "documents/pdf/pdf-js/*.pdf",
    "title": "Mozilla pdf.js Test PDFs",
    "author": "Mozilla Corporation and pdf.js contributors",
    "license": "Apache-2.0",
    "source": "https://github.com/mozilla/pdf.js",
    "tags": [
      "pdf-js",
      "test-fixtures",
      "annotations",
      "forms",
      "images",
      "text-rendering",
      "encryption"
    ],
    "donated": "2026-04-03",
    "notes": "PDF test fixtures from Mozilla pdf.js viewer (Apache-2.0, pinned to v4.9.155)"
  },
  {
    "format": "pdf",
    "path": "documents/pdf/qpdf/*.pdf",
    "title": "qpdf PDF Transformation Tool Test PDFs",
    "author": "Jay Berkenbilt and qpdf contributors",
    "license": "Apache-2.0",
    "source": "https://github.com/qpdf/qpdf",
    "tags": [
      "qpdf",
      "test-fixtures",
      "encryption",
      "page-operations",
      "compression",
      "edge-cases"
    ],
    "donated": "2026-04-03",
    "notes": "PDF test fixtures from the qpdf PDF transformation tool (Apache-2.0, pinned to v12.3.2)"
  },
  {
    "format": "pdf",
    "path": "documents/pdf/apache-pdfbox/*.pdf",
    "title": "Apache PDFBox Test PDFs",
    "author": "The Apache Software Foundation and PDFBox contributors",
    "license": "Apache-2.0",
    "source": "https://github.com/apache/pdfbox",
    "tags": [
      "apache-pdfbox",
      "test-fixtures",
      "forms",
      "text-extraction",
      "images"
    ],
    "donated": "2026-04-03",
    "notes": "PDF test fixtures from Apache PDFBox Java PDF library (Apache-2.0, pinned to 3.0.7)"
  },
  {
    "format": "pdf",
    "path": "documents/pdf/pikepdf/*.pdf",
    "title": "pikepdf Test PDFs",
    "author": "James R. Barlow and pikepdf contributors",
    "license": "MPL-2.0",
    "source": "https://github.com/pikepdf/pikepdf",
    "tags": [
      "pikepdf",
      "test-fixtures",
      "color-spaces",
      "pdf-a"
    ],
    "donated": "2026-04-03",
    "notes": "PDF test fixtures from the pikepdf Python PDF library (MPL-2.0)"
  },
  {
    "format": "pdf",
    "path": "documents/pdf/arxiv/*.pdf",
    "title": "arXiv CC-BY-4.0 Open Access Papers",
    "author": "Various authors (see individual papers at arxiv.org)",
    "license": "CC-BY-4.0",
    "source": "https://arxiv.org",
    "tags": [
      "arxiv",
      "academic",
      "text-heavy",
      "equations",
      "figures",
      "multi-column"
    ],
    "donated": "2026-04-03",
    "notes": "CC-BY-4.0 papers from arXiv (strictly filtered by license metadata) across CS, Math, Physics, Biology, Economics, Statistics"
  },
  {
    "format": "pdf",
    "path": "documents/pdf/openstax/*.pdf",
    "title": "OpenStax Textbook PDFs",
    "author": "OpenStax, Rice University",
    "license": "CC-BY-4.0",
    "source": "https://openstax.org",
    "tags": [
      "openstax",
      "textbooks",
      "educational",
      "tables",
      "images",
      "equations",
      "multi-column"
    ],
    "donated": "2026-04-03",
    "notes": "Open educational textbook PDFs from OpenStax (CC-BY-4.0). Chapter excerpts extracted to meet size limits."
  },
  {
    "format": "pdf",
    "path": "documents/pdf/irs-forms/*.pdf",
    "title": "IRS Tax Form PDFs",
    "author": "Internal Revenue Service, U.S. Department of the Treasury",
    "license": "CC0-1.0",
    "source": "https://www.irs.gov/forms-instructions",
    "tags": [
      "irs",
      "government",
      "forms",
      "fillable-forms",
      "tables",
      "public-domain"
    ],
    "donated": "2026-04-03",
    "notes": "U.S. federal tax forms and instructions (public domain as U.S. government works; attributed as CC0-1.0)"
  },
  {
    "format": "pdf",
    "path": "documents/pdf/nasa-ntrs/*.pdf",
    "title": "NASA Technical Reports",
    "author": "National Aeronautics and Space Administration",
    "license": "CC0-1.0",
    "source": "https://ntrs.nasa.gov",
    "tags": [
      "nasa",
      "government",
      "technical-reports",
      "text-heavy",
      "images",
      "tables",
      "public-domain"
    ],
    "donated": "2026-04-03",
    "notes": "NASA technical reports and publications (public domain as U.S. government works; attributed as CC0-1.0)"
  },
  {
    "format": "pdf",
    "path": "documents/pdf/gutenberg/*.pdf",
    "title": "Project Gutenberg Public Domain Books",
    "author": "Various (original works in public domain)",
    "license": "CC0-1.0",
    "source": "https://www.gutenberg.org",
    "tags": [
      "gutenberg",
      "public-domain",
      "books",
      "text-heavy",
      "multilingual",
      "literature"
    ],
    "donated": "2026-04-03",
    "notes": "Public domain books from Project Gutenberg in PDF format (multiple languages: English, German, French, Spanish, Italian)"
  },
  {
    "format": "pdf",
    "path": "documents/pdf/internet-archive/*.pdf",
    "title": "Internet Archive Public Domain Scanned Books",
    "author": "Various (original works in public domain; digitization by Internet Archive)",
    "license": "CC0-1.0",
    "source": "https://archive.org",
    "tags": [
      "internet-archive",
      "scanned",
      "ocr",
      "public-domain",
      "multilingual",
      "rtl",
      "cjk",
      "books"
    ],
    "donated": "2026-04-03",
    "notes": "Scanned public domain books from Internet Archive. Includes OCR text layers and multilingual content (Arabic, Chinese, French, German, Spanish, Russian, English) for testing scanned PDF handling and non-Latin script support."
  },
  {
    "author": "AbiSource Community and AbiWord contributors",
    "license": "GPL-2.0-or-later",
    "source": "https://github.com/AbiWord/abiword",
    "donated": "2026-04-03",
    "notes": "ODT test fixtures from AbiWord covering complex scripts, bidirectional text, and accessibility features",
    "path": "documents/odt/abiword/*.odt",
    "format": "odt",
    "title": "Abiword",
    "tags": []
  },
  {
    "author": "The Apache Software Foundation and Apache Tika contributors",
    "license": "Apache-2.0",
    "source": "https://github.com/apache/tika",
    "donated": "2026-04-03",
    "notes": "DOC parser test documents from Apache Tika, covering embedded objects, protected documents, and special character handling",
    "path": "documents/doc/apache-tika/*.doc",
    "format": "doc",
    "title": "Apache Tika",
    "tags": []
  },
  {
    "author": "The Apache Software Foundation and Apache Tika contributors",
    "license": "Apache-2.0",
    "source": "https://github.com/apache/tika",
    "donated": "2026-04-03",
    "notes": "DOCX parser test documents from Apache Tika, covering edge cases and parsing robustness scenarios",
    "path": "documents/docx/apache-tika/*.docx",
    "format": "docx",
    "title": "Apache Tika",
    "tags": []
  },
  {
    "author": "Aspose Pty Ltd and Aspose.Words contributors",
    "license": "MIT",
    "source": "https://github.com/aspose-words/Aspose.Words-for-Java",
    "donated": "2026-04-03",
    "notes": "Legacy DOC (Word 97-2003) example documents from Aspose.Words-for-Java, covering smart tags, legacy fields, document versions, and mail merge",
    "path": "documents/doc/aspose-words/*.doc",
    "format": "doc",
    "title": "Aspose Words",
    "tags": []
  },
  {
    "author": "Aspose Pty Ltd and Aspose.Words contributors",
    "license": "MIT",
    "source": "https://github.com/aspose-words/Aspose.Words-for-Java",
    "donated": "2026-04-03",
    "notes": "DOCX example documents from Aspose.Words-for-Java, covering enterprise formatting, tables, images, and complex document layouts",
    "path": "documents/docx/aspose-words/*.docx",
    "format": "docx",
    "title": "Aspose Words",
    "tags": []
  },
  {
    "author": "GitHub, Inc. and cmark-gfm contributors",
    "license": "CC-BY-SA-4.0",
    "source": "https://github.com/github/cmark-gfm",
    "donated": "2026-04-03",
    "notes": "GFM specification test cases covering tables, strikethrough, autolinks, task lists, and footnotes. Spec and extension files (spec.md, extensions.md, extensions-table-prefer-style-attributes.md) are CC-BY-SA-4.0 per YAML frontmatter; remaining benchmark/test files are BSD-2-Clause per repo COPYING. Using CC-BY-SA-4.0 for the whole group (most restrictive present).",
    "path": "documents/markdown/cmark-gfm/*.md",
    "format": "md",
    "title": "Cmark Gfm",
    "tags": []
  },
  {
    "author": "Collabora Productivity and Collabora Online contributors",
    "license": "MPL-2.0",
    "source": "https://github.com/CollaboraOnline/online",
    "donated": "2026-04-03",
    "notes": "ODT test fixtures from Collabora Online covering change tracking, revision marks, and collaborative editing features",
    "path": "documents/odt/collabora/*.odt",
    "format": "odt",
    "title": "Collabora",
    "tags": []
  },
  {
    "author": "Plutext Pty Ltd and docx4j contributors",
    "license": "Apache-2.0",
    "source": "https://github.com/plutext/docx4j",
    "donated": "2026-04-03",
    "notes": "OOXML test fixtures from docx4j, covering SmartArt, bookmarks, OpenDoPE templates, and multilingual documents",
    "path": "documents/docx/docx4j/*.docx",
    "format": "docx",
    "title": "Docx4j",
    "tags": []
  },
  {
    "author": "4teamwork AG and docxcompose contributors",
    "license": "MIT",
    "source": "https://github.com/4teamwork/docxcompose",
    "donated": "2026-04-03",
    "notes": "DOCX test fixtures for document composition and merging scenarios",
    "path": "documents/docx/docxcompose/*.docx",
    "format": "docx",
    "title": "Docxcompose",
    "tags": []
  },
  {
    "author": "The Hugo Authors",
    "license": "Apache-2.0",
    "source": "https://github.com/gohugoio/hugoDocs",
    "donated": "2026-04-03",
    "notes": "Hugo static site generator documentation with complex YAML/TOML frontmatter, shortcodes, and code annotations",
    "path": "documents/markdown/hugo-docs/*.md",
    "format": "md",
    "title": "Hugo Docs",
    "tags": []
  },
  {
    "author": "The Document Foundation and LibreOffice contributors",
    "license": "MPL-2.0",
    "source": "https://github.com/LibreOffice/core",
    "donated": "2026-04-03",
    "notes": "WW8 (Word 97-2003) test fixtures from LibreOffice Writer QA (triple-licensed MPL-2.0/LGPL-3.0+/GPL-3.0+; redistributed under MPL-2.0)",
    "path": "documents/doc/libreoffice/*.doc",
    "format": "doc",
    "title": "Libreoffice",
    "tags": []
  },
  {
    "author": "The Document Foundation and LibreOffice contributors",
    "license": "MPL-2.0",
    "source": "https://github.com/LibreOffice/core",
    "donated": "2026-04-03",
    "notes": "OOXML import/export test data from LibreOffice Writer QA (triple-licensed MPL-2.0/LGPL-3.0+/GPL-3.0+; redistributed under MPL-2.0)",
    "path": "documents/docx/libreoffice/*.docx",
    "format": "docx",
    "title": "Libreoffice",
    "tags": []
  },
  {
    "author": "Vitaly Puzrin, Alex Kocharin, and markdown-it contributors",
    "license": "MIT",
    "source": "https://github.com/markdown-it/markdown-it",
    "donated": "2026-04-03",
    "notes": "CommonMark-compliant parser test fixtures covering emphasis, code blocks, tables, and parsing edge cases",
    "path": "documents/markdown/markdown-it/*.md",
    "format": "md",
    "title": "Markdown It",
    "tags": []
  },
  {
    "author": "Mark Harrison and markdownlint contributors",
    "license": "MIT",
    "source": "https://github.com/markdownlint/markdownlint",
    "donated": "2026-04-03",
    "notes": "Markdown linting test fixtures with intentional style violations and formatting edge cases",
    "path": "documents/markdown/markdownlint/*.md",
    "format": "md",
    "title": "Markdownlint",
    "tags": []
  },
  {
    "author": "Martin Donath and mkdocs-material contributors",
    "license": "MIT",
    "source": "https://github.com/squidfunk/mkdocs-material",
    "donated": "2026-04-03",
    "notes": "MkDocs Material theme documentation with admonitions, content tabs, mermaid diagrams, and code annotations",
    "path": "documents/markdown/mkdocs-material/*.md",
    "format": "md",
    "title": "Mkdocs Material",
    "tags": []
  },
  {
    "author": "Open Preservation Foundation",
    "license": "CC0-1.0",
    "source": "https://github.com/openpreserve/format-corpus",
    "donated": "2026-04-03",
    "notes": "RTF samples from the digital preservation format corpus",
    "path": "documents/rtf/openpreserve/*.rtf",
    "format": "rtf",
    "title": "Openpreserve",
    "tags": []
  },
  {
    "author": "John MacFarlane and Pandoc contributors",
    "license": "GPL-2.0-or-later",
    "source": "https://github.com/jgm/pandoc",
    "donated": "2026-04-03",
    "notes": "Markdown test fixtures from Pandoc covering citations, footnotes, definition lists, LaTeX math, tables, and Pandoc-specific extensions",
    "path": "documents/markdown/pandoc-md/*.md",
    "format": "md",
    "title": "Pandoc Md",
    "tags": []
  },
  {
    "author": "Steve Canny and python-docx contributors",
    "license": "MIT",
    "source": "https://github.com/python-openxml/python-docx",
    "donated": "2026-04-03",
    "notes": "OOXML test fixtures from the python-docx library, covering tables, styles, hyperlinks, and document structure",
    "path": "documents/docx/python-docx/*.docx",
    "format": "docx",
    "title": "Python Docx",
    "tags": []
  },
  {
    "author": "Titus Wormer and remark contributors",
    "license": "MIT",
    "source": "https://github.com/remarkjs/remark",
    "donated": "2026-04-03",
    "notes": "Markdown AST parser test fixtures covering GFM extensions, frontmatter, and markdown processing edge cases",
    "path": "documents/markdown/remark/*.md",
    "format": "md",
    "title": "Remark",
    "tags": []
  },
  {
    "author": "Jon Iles and RTF Parser Kit contributors",
    "license": "Apache-2.0",
    "source": "https://github.com/joniles/rtfparserkit",
    "donated": "2026-04-03",
    "notes": "RTF parser test fixtures covering diverse RTF formatting features",
    "path": "documents/rtf/rtfparserkit/*.rtf",
    "format": "rtf",
    "title": "Rtfparserkit",
    "tags": []
  },
  {
    "author": "AbiSource Community and AbiWord contributors",
    "license": "GPL-2.0-or-later",
    "source": "https://github.com/AbiWord/abiword",
    "donated": "2026-04-03",
    "notes": "Word 97-2003 DOC test fixtures from AbiWord including import/export tests, bug regression files, and format compatibility tests",
    "path": "documents/doc/abiword/*.doc",
    "format": "doc",
    "title": "AbiWord DOC Test Files",
    "tags": [
      "abiword",
      "doc",
      "word97",
      "test-fixtures"
    ]
  },
  {
    "path": "documents/odt/openoffice/*.odt",
    "format": "odt",
    "title": "Apache OpenOffice Writer Test Corpus",
    "author": "Apache OpenOffice Contributors",
    "license": "Apache-2.0",
    "source": "https://github.com/apache/openoffice",
    "tags": [
      "odt",
      "writer",
      "test-fixtures",
      "openoffice",
      "import-export"
    ],
    "donated": "2026-04-03",
    "notes": "ODF Writer test fixtures from Apache OpenOffice sw/qa test suite, SDK examples, and templates. Covers import/export compatibility, formatting edge cases, and regression tests."
  }
]