DOCX Parsing API

Your DOCX Is Already Structured Data

A .docx file is a zip archive containing XML. Paragraphs, styles, tables, revisions, comments — all encoded in document.xml, styles.xml, and relationship files. Most parsers ignore this and render the document to PDF or plain text first, destroying the structure in the process.

AILANG Parse reads the Office Open XML directly. Track changes get author and timestamp. Merged cells get explicit gridSpan/vMerge metadata. Comments stay anchored to their text ranges. Nothing is flattened, nothing is lost.

Raw Office XML vs Structured Output

<w:p>
  <w:pPr><w:pStyle w:val="Heading1"/></w:pPr>
  <w:r><w:t>Q1 Revenue</w:t></w:r>
</w:p>
<w:p>
  <w:r><w:rPr><w:b/></w:rPr>
    <w:t>Total: </w:t></w:r>
  <w:ins w:id="1" w:author="Alice"
         w:date="2026-03-15T10:30:00Z">
    <w:r><w:t>$2.4M</w:t></w:r>
  </w:ins>
  <w:del w:id="2" w:author="Alice"
         w:date="2026-03-15T10:30:00Z">
    <w:r><w:delText>$2.1M</w:delText></w:r>
  </w:del>
</w:p>
<w:tbl>
  <w:tr>
    <w:tc><w:tcPr><w:gridSpan w:val="2"/>
    </w:tcPr>
    <w:p><w:r><w:t>Region</w:t>...
  </w:tc></w:tr>
</w:tbl>

{
  "metadata": {
    "title": "Q1 Revenue Report",
    "author": "Finance Team",
    "created": "2026-03-01T09:00:00Z"
  },
  "blocks": [
    {
      "type": "heading",
      "level": 1,
      "text": "Q1 Revenue"
    },
    {
      "type": "text",
      "text": "Total: $2.4M",
      "style": "Normal",
      "changes": [
        {
          "type": "insert",
          "author": "Alice",
          "date": "2026-03-15T10:30:00Z",
          "text": "$2.4M"
        },
        {
          "type": "delete",
          "author": "Alice",
          "date": "2026-03-15T10:30:00Z",
          "text": "$2.1M"
        }
      ]
    },
    {
      "type": "table",
      "headers": [{"text":"Region","gridSpan":2}],
      "rows": [...]
    }
  ]
}

What Gets Extracted

Track Changes

DOCX track changes encode the full editing history: who changed what, when, and what the text looked like before. AILANG Parse extracts every revision as a structured change block with type (insert/delete/formatChange), author, date, and the affected text.

This is the metadata that disappears when you render to PDF. A legal team reviewing a contract needs to see that "Alice deleted net-30 and inserted net-60 on March 15th" — not just the final text.

{
  "type": "text",
  "text": "Payment terms: net-60 days from invoice date.",
  "changes": [
    {"type": "delete", "author": "Alice Chen", "date": "2026-03-15T14:22:00Z", "text": "net-30"},
    {"type": "insert", "author": "Alice Chen", "date": "2026-03-15T14:22:00Z", "text": "net-60"}
  ]
}

See Track Changes extraction for the full specification.

Tables & Merged Cells

Office tables use gridSpan for horizontal merges and vMerge for vertical merges. AILANG Parse resolves these into a clean row/column structure with explicit merge metadata — no heuristic guessing from visual alignment.

{
  "type": "table",
  "headers": [
    {"text": "Region", "gridSpan": 2},
    {"text": "Q1"},
    {"text": "Q2"}
  ],
  "rows": [
    [{"text": "EMEA"}, {"text": "UK"}, {"text": "$125K"}, {"text": "$140K"}],
    [{"text": "EMEA", "vMerge": "continue"}, {"text": "DE"}, {"text": "$98K"}, {"text": "$112K"}]
  ]
}

See Tables & Merged Cells for the full specification.

Comments

DOCX comments are anchored to specific text ranges via w:commentRangeStart/w:commentRangeEnd markers. AILANG Parse extracts each comment with its author, timestamp, the anchored text, and any reply threads.

{
  "type": "text",
  "text": "The delivery timeline is aggressive.",
  "comments": [
    {
      "author": "Bob Martinez",
      "date": "2026-03-20T09:15:00Z",
      "text": "Can we push this to Q3?",
      "replies": [
        {"author": "Alice Chen", "date": "2026-03-20T10:02:00Z", "text": "Agreed, updated."}
      ]
    }
  ]
}

See Comment extraction for the full specification.

Use Cases

Try It

CLI

# Parse a DOCX file
ailang run --entry main --caps IO,FS,Env \
  docparse/main.ail report.docx

# Convert DOCX to Markdown
./bin/docparse report.docx --convert output.md

# Convert DOCX to HTML
./bin/docparse report.docx --convert output.html

API

curl -X POST https://docparse.ailang.sunholo.com/api/v1/parse \
  -H "Content-Type: application/json" \
  -d '{"filepath":"sample_docx_formatting","outputFormat":"markdown","apiKey":"YOUR_API_KEY"}'

Python SDK

from ailang_parse import DocParse

client = DocParse(api_key="YOUR_API_KEY")
result = client.parse("contract.docx", output_format="json")

# Document metadata
print(result.metadata.title)
print(result.metadata.author)

# Iterate structured blocks
for block in result.blocks:
    if block.type == "table":
        print(f"Table: {len(block.rows)} rows, merged={block.has_merges}")
    if hasattr(block, "changes") and block.changes:
        for change in block.changes:
            print(f"{change.author} {change.type}d: {change.text}")

Parse in Browser    API Reference