undefined

---

import { parse } from "kordoc"
import { readFileSync } from "fs"

const buffer = readFileSync("document.hwpx")
const result = await parse(buffer.buffer) // ArrayBuffer required

if (result.success) {
  console.log(result.markdown)   // string: full Markdown
  console.log(result.blocks)     // IRBlock[]: structured data
  console.log(result.metadata)   // { title, author, createdAt, pageCount, ... }
  console.log(result.outline)    // OutlineItem[]: document structure
  console.log(result.warnings)   // ParseWarning[]: skipped elements
} else {
  console.error(result.error)    // string message
  console.error(result.code)     // ErrorCode: "ENCRYPTED" | "ZIP_BOMB" | "IMAGE_BASED_PDF" | ...
}

import { parseHwpx, parseHwp, parsePdf, detectFormat } from "kordoc"

// Detect format first
const fmt = detectFormat(buffer.buffer) // "hwpx" | "hwp" | "pdf" | "unknown"

// Parse by format
const hwpxResult = await parseHwpx(buffer.buffer)
const hwpResult  = await parseHwp(buffer.buffer)
const pdfResult  = await parsePdf(buffer.buffer)

import { parse, ParseOptions } from "kordoc"

const result = await parse(buffer.buffer, {
  pages: "1-3",          // page range string
  // pages: [1, 5, 10], // or specific page numbers
  ocr: async (pageImage, pageNumber, mimeType) => {
    // Pluggable OCR for image-based PDFs
    // pageImage: ArrayBuffer of the page image
    return await myOcrService.recognize(pageImage)
  }
})

import type { IRBlock, IRBlockType, IRTable, IRCell } from "kordoc"

// IRBlock types: "heading" | "paragraph" | "table" | "list" | "image" | "separator"
for (const block of result.blocks) {
  if (block.type === "heading") {
    console.log(`H${block.level}: ${block.text}`)
    console.log(block.bbox)       // { x, y, width, height, page }
  }

  if (block.type === "table") {
    const table = block as IRTable
    for (const row of table.rows) {
      for (const cell of row) {
        console.log(cell.text, cell.colspan, cell.rowspan)
      }
    }
  }

  if (block.type === "paragraph") {
    console.log(block.text)
    console.log(block.style)      // InlineStyle: { bold, italic, fontSize, ... }
    console.log(block.pageNumber)
  }
}

import { blocksToMarkdown } from "kordoc"

const markdown = blocksToMarkdown(result.blocks)

import { compare } from "kordoc"

const bufA = readFileSync("v1.hwp").buffer
const bufB = readFileSync("v2.hwpx").buffer  // cross-format supported

const diff = await compare(bufA, bufB)

console.log(diff.stats)
// { added: 3, removed: 1, modified: 5, unchanged: 42 }

for (const d of diff.diffs) {
  // d.type: "added" | "removed" | "modified" | "unchanged"
  // d.blockA, d.blockB: IRBlock
  // d.cellDiffs: CellDiff[] for table blocks
  console.log(d.type, d.blockA?.text ?? d.blockB?.text)
}

import { parse, extractFormFields } from "kordoc"

const result = await parse(buffer.buffer)
if (result.success) {
  const form = extractFormFields(result.blocks)

  console.log(form.confidence)  // 0.0–1.0
  for (const field of form.fields) {
    // { label: "성명", value: "홍길동", row: 0, col: 0 }
    console.log(`${field.label}: ${field.value}`)
  }
}

import { markdownToHwpx } from "kordoc"
import { writeFileSync } from "fs"

const markdown = `

---

undefined

---

{
  "mcpServers": {
    "kordoc": {
      "command": "npx",
      "args": ["-y", "kordoc-mcp"]
    }
  }
}

import type {
  // Results
  ParseResult, ParseSuccess, ParseFailure,
  ErrorCode,        // "ENCRYPTED" | "ZIP_BOMB" | "IMAGE_BASED_PDF" | ...

  // Blocks
  IRBlock, IRBlockType, IRTable, IRCell, CellContext,

  // Metadata & structure
  DocumentMetadata, OutlineItem,
  ParseWarning, WarningCode,
  BoundingBox,      // { x, y, width, height, page }
  InlineStyle,      // { bold, italic, fontSize, color, ... }

  // Options
  ParseOptions, FileType,
  OcrProvider,      // async (image, pageNum, mime) => string
  WatchOptions,

  // Diff
  DiffResult, BlockDiff, CellDiff, DiffChangeType,

  // Forms
  FormField, FormResult,
} from "kordoc"

import { parse, detectFormat } from "kordoc"
import { readFileSync } from "fs"
import { glob } from "glob"

const files = await glob("./docs/**/*.{hwp,hwpx,pdf}")

for (const file of files) {
  const buffer = readFileSync(file)
  const fmt = detectFormat(buffer.buffer)

  if (fmt === "unknown") {
    console.warn(`Skipping unknown format: ${file}`)
    continue
  }

  const result = await parse(buffer.buffer)

  if (!result.success) {
    if (result.code === "ENCRYPTED") {
      console.warn(`Encrypted, skipping: ${file}`)
    } else if (result.code === "IMAGE_BASED_PDF") {
      console.warn(`Image-based PDF needs OCR: ${file}`)
    } else {
      console.error(`Failed: ${file} — ${result.error}`)
    }
    continue
  }

  console.log(`Parsed ${file}: ${result.blocks.length} blocks`)
}

import { parse } from "kordoc"
import type { IRTable } from "kordoc"

const result = await parse(buffer.buffer)
if (result.success) {
  const tables = result.blocks.filter(b => b.type === "table") as IRTable[]

  tables.forEach((table, i) => {
    console.log(`\n--- Table ${i + 1} ---`)
    for (const row of table.rows) {
      const cells = row.map(cell => cell.text.trim()).join(" | ")
      console.log(`| ${cells} |`)
    }
  })
}

import { parse } from "kordoc"
import Tesseract from "tesseract.js"

const result = await parse(buffer.buffer, {
  ocr: async (pageImage, pageNumber, mimeType) => {
    const blob = new Blob([pageImage], { type: mimeType })
    const url = URL.createObjectURL(blob)
    const { data } = await Tesseract.recognize(url, "kor+eng")
    URL.revokeObjectURL(url)
    return data.text
  }
})

import { watch } from "kordoc"

const watcher = watch("./incoming", {
  output: "./converted",
  webhook: process.env.WEBHOOK_URL,
  onFile: async (file, result) => {
    if (result.success) {
      console.log(`Converted: ${file}`)
    }
  }
})

// Stop watching
watcher.stop()