AILANG Parse

Universal document parsing in AILANG. Extracts structured content from DOCX, PPTX, XLSX, PDF, and image files into JSON and markdown.

Office formats (DOCX, PPTX, XLSX) use deterministic XML parsing — no AI, no cloud, instant results. PDFs and images delegate to whatever AI model you plug in (Gemini, Claude, local Ollama). AILANG Parse is AI-agnostic: swap --ai to change the backend, zero code changes.

Install

Requires AILANG CLI.

# Clone and symlink
git clone https://github.com/sunholo-data/ailang-parse.git
ln -s "$(pwd)/ailang-parse/bin/docparse" /usr/local/bin/docparse

SDKs

Use AILANG Parse from your language of choice:

pip install ailang-parse          # Python
npm install @ailang/parse         # JavaScript/TypeScript
go get github.com/sunholo-data/ailang-parse-go  # Go

Quick Start

# Office documents (deterministic, no AI needed)
docparse report.docx
docparse slides.pptx
docparse spreadsheet.xlsx

# PDF and images (AI auto-enabled)
docparse document.pdf
docparse photo.png

# Options
docparse report.docx describe        # AI image descriptions
docparse report.docx summarize       # AI document summary
docparse scan.pdf --ai gemini-2.5-flash  # Choose AI backend

# Format conversion
docparse report.docx --convert output.html
docparse data.csv --convert report.docx
docparse notes.md --convert slides.pptx

# AI document generation
ailang run --entry main --caps IO,FS,Env,AI --ai gemini-2.5-flash \
  docparse/main.ail --generate report.docx --prompt "Q1 sales report with tables"

Output

Every run produces:

• docparse/data/output.json — Structured JSON with typed blocks
• docparse/data/output.md — LLM-ready markdown

What AILANG Parse Extracts

Feature	DOCX	PPTX	XLSX	Best Competitor
Tables with merged cells	Yes	Yes	Yes	Raw OOXML only
Track changes (redlining)	Yes	—	—	Pandoc (3/3)
Comments (interleaved)	Yes	—	—	Raw OOXML (2/2)
Headers/footers	Yes	—	—	Kreuzberg (2/3)
Text boxes / VML shapes	Yes	Yes	—	Raw OOXML (1/2)
Equations (§22.1)	Yes	—	—	None
Field codes (§17.16)	Yes	—	—	Kreuzberg, OOXML
Speaker notes	—	Yes	—	None
Multi-sheet extraction	—	—	Yes	Kreuzberg

OfficeDocBench (69 files, 11 formats, 7 metrics): AILANG Parse 93.9% composite with 100% coverage vs nearest competitor 68.0% coverage-adjusted. 8 parsers compared including Raw OOXML, Pandoc, Kreuzberg, MarkItDown, Unstructured, Docling. Scores include aspirational ECMA-376 spec targets that intentionally lower our score.

Supported Formats

Parsing (15 formats): DOCX, PPTX, XLSX, ODT, ODP, ODS, HTML, Markdown, CSV, EPUB, EML, MBOX, TEX, PDF, images (JPG/PNG)

Generation (9 formats): DOCX, PPTX, XLSX, ODT, ODP, ODS, HTML, Markdown, QMD (Quarto)

Architecture

docparse/
├── types/document.ail           # Block ADT (9 variants)
├── services/
│   ├── format_router.ail        # Format detection (36 inline tests)
│   ├── zip_extract.ail          # ZIP layer (9 inline tests)
│   ├── docx_parser.ail          # DOCX XML → Blocks (6 inline tests)
│   ├── pptx_parser.ail          # PPTX slides → Blocks
│   ├── xlsx_parser.ail          # XLSX worksheets → Blocks
│   ├── direct_ai_parser.ail     # PDF/image → Blocks (AI)
│   ├── layout_ai.ail            # AI self-healing (optional)
│   ├── output_formatter.ail     # JSON + markdown output
│   └── docparse_browser.ail     # WASM browser adapter
└── main.ail                     # CLI entry point

28+ contracts, 50+ inline tests.

AI Configuration

AILANG Parse uses AILANG's AI effect — any model AILANG supports works:

docparse scan.pdf --ai gemini-2.5-flash          # Google (default; fast)
docparse scan.pdf --ai gemini-3-flash-preview    # Google (slower; thinking model)
docparse scan.pdf --ai granite-docling           # Local Ollama (free)
docparse scan.pdf --ai claude-haiku-4-5          # Anthropic

AI usage is bounded by capability budgets (AI @limit=30), so costs are predictable.

Dev Commands

docparse --check       # Type-check all modules
docparse --test        # Run inline tests
docparse --prove       # Static Z3 contract verification

Benchmarks

uv run benchmarks/run_benchmarks.py --suite office     # Structural (no API, instant)
uv run benchmarks/run_benchmarks.py --suite pdf         # PDF extraction (needs AI)
uv run benchmarks/run_benchmarks.py --competitors       # Compare to Docling etc.

See benchmarks/ for details.

License

Apache 2.0