sds-converter

CLI tool for bidirectional conversion between Safety Data Sheet (SDS) documents (Word/PDF) and the Japanese Ministry of Health, Labour and Welfare (MHLW) standard JSON format.

Supports Japanese, English, Simplified Chinese, and Traditional Chinese.

Embedding in your Rust project? Use sds-converter-core directly.

Installation

cargo install sds-converter

Commands

to-json — Convert PDF/Word → MHLW standard JSON

# Single file (Anthropic Claude, default)
export ANTHROPIC_API_KEY=sk-ant-...
sds-converter to-json --input input.pdf --output output.json

# Specify source language
sds-converter to-json --input sds_en.pdf --output output.json --lang en

# Batch mode — process a whole directory
sds-converter to-json --input-dir ./pdfs/ --output-dir ./json/ --lang ja

# OpenAI GPT (defaults to gpt-4o-mini)
sds-converter to-json --input input.pdf --output output.json \
  --provider openai --api-key $OPENAI_API_KEY

# Google Gemini (defaults to gemini-2.0-flash)
sds-converter to-json --input input.pdf --output output.json \
  --provider gemini --api-key $GEMINI_API_KEY

# Local LLM via Ollama (any OpenAI-compatible endpoint)
sds-converter to-json --input input.pdf --output output.json \
  --provider local --base-url http://localhost:11434/v1 \
  --model llama3.2 --api-key dummy

# From pre-extracted text (skip PDF parsing)
sds-converter to-json --input extracted.txt --output output.json --lang ja

Provider defaults:

to-docx — Convert MHLW standard JSON → Word document

# Single file (built-in layout)
sds-converter to-docx --input output.json --output result.docx --lang ja

# Batch mode (built-in layout)
sds-converter to-docx --input-dir ./json/ --output-dir ./docx/ --lang en

# Fill a Word template with {{Placeholder}} substitution
sds-converter to-docx --input output.json --output result.docx \
  --template my_template.docx

# Batch mode with template
sds-converter to-docx --input-dir ./json/ --output-dir ./docx/ \
  --template my_template.docx

Word template format

Prepare a .docx file with {{FieldName}} placeholders where FieldName is a leaf key from the MHLW JSON schema. The full dot-path is also accepted for disambiguation.

{{TradeNameJP}}          → 製品和名
{{CompanyName}}          → 会社名
{{Phone}}                → 電話番号
{{IssueDate}}            → 発行日
{{Identification.SupplierInformation.CompanyName}}  → フルパス指定

Placeholders can appear anywhere in the document — paragraphs, table cells, headers, and footers. Word sometimes splits typed text across internal runs; the tool automatically merges such splits before substitution.

extract-text — Extract raw text from PDF/DOCX

Extracts the text that the LLM would receive, without making any API call. Useful for inspecting extraction quality or running the LLM step separately.

# Save to file
sds-converter extract-text --input input.pdf --output extracted.txt

# Print to stdout
sds-converter extract-text --input input.pdf

# Then feed back into to-json
sds-converter to-json --input extracted.txt --output output.json --lang ja

validate — Check a JSON file for structural issues

# Human-readable output (exits 0 = OK, 1 = warnings found)
sds-converter validate --input output.json

# JSON array output for CI/scripting
sds-converter validate --input output.json --json

Checks that key sections (Identification, HazardIdentification, ToxicologicalInformation, etc.) are populated. Exits with code 1 if any issues are found.

Language Support

Requirements

• Rust 1.75+
• An LLM API key (for to-json only) — set the provider's environment variable or pass --api-key
  • Anthropic: ANTHROPIC_API_KEY
  • OpenAI: OPENAI_API_KEY
  • Google Gemini: GEMINI_API_KEY
  • Mistral: MISTRAL_API_KEY
  • Groq: GROQ_API_KEY
  • Cohere: COHERE_API_KEY
  • Local LLM (Ollama etc.): use --provider local --base-url <url> (no API key required)
• Input files must be text-based PDF or DOCX
  • Encrypted PDFs are not supported
  • Scanned/image-only PDFs are not supported (no text to extract)

License

Licensed under either of:

• Apache License, Version 2.0
• MIT License

at your option.