kordoc 2.2.0 → 2.2.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/LICENSE +21 -21
- package/README.md +318 -302
- package/dist/{chunk-MOL7MDBG.js → chunk-3TBUDJDE.js} +1 -1
- package/dist/chunk-3TBUDJDE.js.map +1 -0
- package/dist/{chunk-LYFG7AUT.js → chunk-FINXMRCH.js} +15 -12
- package/dist/chunk-FINXMRCH.js.map +1 -0
- package/dist/{chunk-5Y2Q3BRW.js → chunk-MUAWCQDY.js} +1 -1
- package/dist/chunk-MUAWCQDY.js.map +1 -0
- package/dist/cli.js +4 -4
- package/dist/cli.js.map +1 -1
- package/dist/{detect-GYK3HKD5.js → detect-63IGCXTH.js} +2 -2
- package/dist/index.cjs +11 -8
- package/dist/index.cjs.map +1 -1
- package/dist/index.js +11 -8
- package/dist/index.js.map +1 -1
- package/dist/mcp.js +4 -4
- package/dist/mcp.js.map +1 -1
- package/dist/page-range-OF5I4PQY.js +8 -0
- package/dist/{watch-Q5OXA73S.js → watch-Q6L4UBTC.js} +4 -4
- package/package.json +1 -1
- package/dist/chunk-5Y2Q3BRW.js.map +0 -1
- package/dist/chunk-LYFG7AUT.js.map +0 -1
- package/dist/chunk-MOL7MDBG.js.map +0 -1
- package/dist/page-range-737B4EZW.js +0 -8
- /package/dist/{detect-GYK3HKD5.js.map → detect-63IGCXTH.js.map} +0 -0
- /package/dist/{page-range-737B4EZW.js.map → page-range-OF5I4PQY.js.map} +0 -0
- /package/dist/{watch-Q5OXA73S.js.map → watch-Q6L4UBTC.js.map} +0 -0
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"sources":["../src/detect.ts"],"sourcesContent":["/** 매직 바이트 기반 파일 포맷 감지 */\r\n\r\nimport JSZip from \"jszip\"\r\nimport type { FileType } from \"./types.js\"\r\n\r\n/** 매직 바이트 뷰 생성 (복사 없이 view) */\r\nfunction magicBytes(buffer: ArrayBuffer): Uint8Array {\r\n return new Uint8Array(buffer, 0, Math.min(4, buffer.byteLength))\r\n}\r\n\r\n/** ZIP 파일 여부: PK\\x03\\x04 */\r\nexport function isZipFile(buffer: ArrayBuffer): boolean {\r\n const b = magicBytes(buffer)\r\n return b[0] === 0x50 && b[1] === 0x4b && b[2] === 0x03 && b[3] === 0x04\r\n}\r\n\r\n/** HWPX (ZIP 기반 한컴 문서): PK\\x03\\x04 — 하위 호환용 */\r\nexport function isHwpxFile(buffer: ArrayBuffer): boolean {\r\n return isZipFile(buffer)\r\n}\r\n\r\n/** HWP 5.x (OLE2 바이너리 한컴 문서): \\xD0\\xCF\\x11\\xE0 */\r\nexport function isOldHwpFile(buffer: ArrayBuffer): boolean {\r\n const b = magicBytes(buffer)\r\n return b[0] === 0xd0 && b[1] === 0xcf && b[2] === 0x11 && b[3] === 0xe0\r\n}\r\n\r\n/** PDF 문서: %PDF */\r\nexport function isPdfFile(buffer: ArrayBuffer): boolean {\r\n const b = magicBytes(buffer)\r\n return b[0] === 0x25 && b[1] === 0x50 && b[2] === 0x44 && b[3] === 0x46\r\n}\r\n\r\n/** 동기 포맷 감지 — ZIP은 모두 \"hwpx\"로 반환 (하위 호환) */\r\nexport function detectFormat(buffer: ArrayBuffer): FileType {\r\n if (buffer.byteLength < 4) return \"unknown\"\r\n if (isZipFile(buffer)) return \"hwpx\"\r\n if (isOldHwpFile(buffer)) return \"hwp\"\r\n if (isPdfFile(buffer)) return \"pdf\"\r\n return \"unknown\"\r\n}\r\n\r\n/**\r\n * ZIP 내부 구조 기반 포맷 세분화.\r\n * HWPX, XLSX, DOCX 모두 ZIP이므로 내부 파일로 구분.\r\n */\r\nexport async function detectZipFormat(buffer: ArrayBuffer): Promise<\"hwpx\" | \"xlsx\" | \"docx\" | \"unknown\"> {\r\n try {\r\n const zip = await JSZip.loadAsync(buffer)\r\n // XLSX: xl/workbook.xml\r\n if (zip.file(\"xl/workbook.xml\")) return \"xlsx\"\r\n // DOCX: word/document.xml\r\n if (zip.file(\"word/document.xml\")) return \"docx\"\r\n // HWPX: Contents/ 또는 content.hpf 또는 mimetype\r\n if (zip.file(\"Contents/content.hpf\") || zip.file(\"mimetype\")) return \"hwpx\"\r\n // 기타 ZIP 내에 section 파일이 있으면 HWPX로 추정\r\n const hasSection = Object.keys(zip.files).some(f => f.startsWith(\"Contents/\"))\r\n if (hasSection) return \"hwpx\"\r\n return \"unknown\"\r\n } catch {\r\n return \"unknown\"\r\n }\r\n}\r\n"],"mappings":";;;AAEA,OAAO,WAAW;AAIlB,SAAS,WAAW,QAAiC;AACnD,SAAO,IAAI,WAAW,QAAQ,GAAG,KAAK,IAAI,GAAG,OAAO,UAAU,CAAC;AACjE;AAGO,SAAS,UAAU,QAA8B;AACtD,QAAM,IAAI,WAAW,MAAM;AAC3B,SAAO,EAAE,CAAC,MAAM,MAAQ,EAAE,CAAC,MAAM,MAAQ,EAAE,CAAC,MAAM,KAAQ,EAAE,CAAC,MAAM;AACrE;AAGO,SAAS,WAAW,QAA8B;AACvD,SAAO,UAAU,MAAM;AACzB;AAGO,SAAS,aAAa,QAA8B;AACzD,QAAM,IAAI,WAAW,MAAM;AAC3B,SAAO,EAAE,CAAC,MAAM,OAAQ,EAAE,CAAC,MAAM,OAAQ,EAAE,CAAC,MAAM,MAAQ,EAAE,CAAC,MAAM;AACrE;AAGO,SAAS,UAAU,QAA8B;AACtD,QAAM,IAAI,WAAW,MAAM;AAC3B,SAAO,EAAE,CAAC,MAAM,MAAQ,EAAE,CAAC,MAAM,MAAQ,EAAE,CAAC,MAAM,MAAQ,EAAE,CAAC,MAAM;AACrE;AAGO,SAAS,aAAa,QAA+B;AAC1D,MAAI,OAAO,aAAa,EAAG,QAAO;AAClC,MAAI,UAAU,MAAM,EAAG,QAAO;AAC9B,MAAI,aAAa,MAAM,EAAG,QAAO;AACjC,MAAI,UAAU,MAAM,EAAG,QAAO;AAC9B,SAAO;AACT;AAMA,eAAsB,gBAAgB,QAAoE;AACxG,MAAI;AACF,UAAM,MAAM,MAAM,MAAM,UAAU,MAAM;AAExC,QAAI,IAAI,KAAK,iBAAiB,EAAG,QAAO;AAExC,QAAI,IAAI,KAAK,mBAAmB,EAAG,QAAO;AAE1C,QAAI,IAAI,KAAK,sBAAsB,KAAK,IAAI,KAAK,UAAU,EAAG,QAAO;AAErE,UAAM,aAAa,OAAO,KAAK,IAAI,KAAK,EAAE,KAAK,OAAK,EAAE,WAAW,WAAW,CAAC;AAC7E,QAAI,WAAY,QAAO;AACvB,WAAO;AAAA,EACT,QAAQ;AACN,WAAO;AAAA,EACT;AACF;","names":[]}
|
package/dist/cli.js
CHANGED
|
@@ -4,11 +4,11 @@ import {
|
|
|
4
4
|
parse,
|
|
5
5
|
sanitizeError,
|
|
6
6
|
toArrayBuffer
|
|
7
|
-
} from "./chunk-
|
|
7
|
+
} from "./chunk-FINXMRCH.js";
|
|
8
8
|
import {
|
|
9
9
|
detectFormat
|
|
10
|
-
} from "./chunk-
|
|
11
|
-
import "./chunk-
|
|
10
|
+
} from "./chunk-MUAWCQDY.js";
|
|
11
|
+
import "./chunk-3TBUDJDE.js";
|
|
12
12
|
|
|
13
13
|
// src/cli.ts
|
|
14
14
|
import { readFileSync, writeFileSync, mkdirSync, statSync } from "fs";
|
|
@@ -105,7 +105,7 @@ program.name("kordoc").description("\uBAA8\uB450 \uD30C\uC2F1\uD574\uBC84\uB9AC\
|
|
|
105
105
|
}
|
|
106
106
|
});
|
|
107
107
|
program.command("watch <dir>").description("\uB514\uB809\uD1A0\uB9AC \uAC10\uC2DC \u2014 \uC0C8 \uBB38\uC11C \uC790\uB3D9 \uBCC0\uD658").option("--webhook <url>", "\uACB0\uACFC \uC804\uC1A1 \uC6F9\uD6C5 URL").option("-d, --out-dir <dir>", "\uBCC0\uD658 \uACB0\uACFC \uCD9C\uB825 \uB514\uB809\uD1A0\uB9AC").option("-p, --pages <range>", "\uD398\uC774\uC9C0/\uC139\uC158 \uBC94\uC704").option("--format <type>", "\uCD9C\uB825 \uD615\uC2DD: markdown \uB610\uB294 json", "markdown").option("--silent", "\uC9C4\uD589 \uBA54\uC2DC\uC9C0 \uC228\uAE30\uAE30").action(async (dir, opts) => {
|
|
108
|
-
const { watchDirectory } = await import("./watch-
|
|
108
|
+
const { watchDirectory } = await import("./watch-Q6L4UBTC.js");
|
|
109
109
|
await watchDirectory({
|
|
110
110
|
dir,
|
|
111
111
|
outDir: opts.outDir,
|
package/dist/cli.js.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"sources":["../src/cli.ts"],"sourcesContent":["/** kordoc CLI — 모두 파싱해버리겠다 */\n\nimport { readFileSync, writeFileSync, mkdirSync, statSync } from \"fs\"\nimport { basename, resolve } from \"path\"\nimport { Command } from \"commander\"\nimport { parse, detectFormat } from \"./index.js\"\nimport type { ParseOptions } from \"./types.js\"\nimport { VERSION, toArrayBuffer, sanitizeError } from \"./utils.js\"\n\nconst program = new Command()\n\nprogram\n .name(\"kordoc\")\n .description(\"모두 파싱해버리겠다 — HWP, HWPX, PDF, XLSX, DOCX → Markdown\")\n .version(VERSION)\n .argument(\"<files...>\", \"변환할 파일 경로 (HWP, HWPX, PDF, XLSX, DOCX)\")\n .option(\"-o, --output <path>\", \"출력 파일 경로 (단일 파일 시)\")\n .option(\"-d, --out-dir <dir>\", \"출력 디렉토리 (다중 파일 시)\")\n .option(\"-p, --pages <range>\", \"페이지/섹션 범위 (예: 1-3, 1,3,5)\")\n .option(\"--format <type>\", \"출력 형식: markdown (기본) 또는 json\", \"markdown\")\n .option(\"--no-header-footer\", \"PDF 머리글/바닥글 자동 제거\")\n .option(\"--silent\", \"진행 메시지 숨기기\")\n .action(async (files: string[], opts) => {\n const validFormats = [\"markdown\", \"json\"]\n if (!validFormats.includes(opts.format)) {\n process.stderr.write(`[kordoc] 지원하지 않는 형식: ${opts.format} (markdown 또는 json)\\n`)\n process.exit(1)\n }\n for (let fi = 0; fi < files.length; fi++) {\n const filePath = files[fi]\n const absPath = resolve(filePath)\n const fileName = basename(absPath)\n const filePrefix = files.length > 1 ? `[${fi + 1}/${files.length}] ` : \"\"\n\n try {\n const fileSize = statSync(absPath).size\n if (fileSize > 500 * 1024 * 1024) {\n process.stderr.write(`\\n[kordoc] SKIP: ${fileName} — 파일이 너무 큽니다 (${(fileSize / 1024 / 1024).toFixed(1)}MB)\\n`)\n process.exitCode = 1\n continue\n }\n const buffer = readFileSync(absPath)\n const arrayBuffer = toArrayBuffer(buffer)\n const format = detectFormat(arrayBuffer)\n\n if (!opts.silent) {\n process.stderr.write(`[kordoc] ${filePrefix}${fileName} (${format}) ...`)\n }\n\n const parseOptions: ParseOptions = {}\n if (opts.pages) parseOptions.pages = opts.pages as string\n if (opts.headerFooter === false) parseOptions.removeHeaderFooter = false\n if (!opts.silent) {\n parseOptions.onProgress = (current: number, total: number) => {\n process.stderr.write(`\\r[kordoc] ${filePrefix}${fileName} (${format}) [${current}/${total}]`)\n }\n }\n const result = await parse(arrayBuffer, parseOptions)\n\n if (!result.success) {\n process.stderr.write(` FAIL\\n`)\n process.stderr.write(` → ${result.error}\\n`)\n process.exitCode = 1\n continue\n }\n\n if (!opts.silent) process.stderr.write(` OK\\n`)\n\n let markdown = result.markdown\n // --out-dir 시 이미지 참조 경로에 images/ 접두사 추가\n if (opts.outDir && result.images?.length) {\n markdown = markdown.replace(/!\\[image\\]\\(image_/g, \"\n }\n const output = opts.format === \"json\"\n ? JSON.stringify(result, (_key, value) =>\n value instanceof Uint8Array ? Buffer.from(value).toString(\"base64\") : value\n , 2)\n : markdown\n\n // 이미지 저장 (--out-dir 또는 --output 시)\n const saveImages = (dir: string) => {\n if (!result.images?.length) return\n const imgDir = resolve(dir, \"images\")\n mkdirSync(imgDir, { recursive: true })\n for (const img of result.images) {\n writeFileSync(resolve(imgDir, img.filename), img.data)\n }\n if (!opts.silent) process.stderr.write(` → ${result.images.length}개 이미지 → ${imgDir}\\n`)\n }\n\n if (opts.output && files.length === 1) {\n writeFileSync(opts.output, output, \"utf-8\")\n if (!opts.silent) process.stderr.write(` → ${opts.output}\\n`)\n saveImages(resolve(opts.output, \"..\"))\n } else if (opts.outDir) {\n mkdirSync(opts.outDir, { recursive: true })\n const outExt = opts.format === \"json\" ? \".json\" : \".md\"\n const outPath = resolve(opts.outDir, fileName.replace(/\\.[^.]+$/, outExt))\n writeFileSync(outPath, output, \"utf-8\")\n if (!opts.silent) process.stderr.write(` → ${outPath}\\n`)\n saveImages(opts.outDir)\n } else {\n process.stdout.write(output + \"\\n\")\n }\n } catch (err) {\n process.stderr.write(`\\n[kordoc] ERROR: ${fileName} — ${sanitizeError(err)}\\n`)\n process.exitCode = 1\n }\n }\n })\n\nprogram\n .command(\"watch <dir>\")\n .description(\"디렉토리 감시 — 새 문서 자동 변환\")\n .option(\"--webhook <url>\", \"결과 전송 웹훅 URL\")\n .option(\"-d, --out-dir <dir>\", \"변환 결과 출력 디렉토리\")\n .option(\"-p, --pages <range>\", \"페이지/섹션 범위\")\n .option(\"--format <type>\", \"출력 형식: markdown 또는 json\", \"markdown\")\n .option(\"--silent\", \"진행 메시지 숨기기\")\n .action(async (dir: string, opts) => {\n const { watchDirectory } = await import(\"./watch.js\")\n await watchDirectory({\n dir,\n outDir: opts.outDir,\n webhook: opts.webhook,\n format: opts.format,\n pages: opts.pages,\n silent: opts.silent,\n })\n })\n\nprogram.parse()\n"],"mappings":";;;;;;;;;;;;;AAEA,SAAS,cAAc,eAAe,WAAW,gBAAgB;AACjE,SAAS,UAAU,eAAe;AAClC,SAAS,eAAe;AAKxB,IAAM,UAAU,IAAI,QAAQ;AAE5B,QACG,KAAK,QAAQ,EACb,YAAY,2GAAoD,EAChE,QAAQ,OAAO,EACf,SAAS,cAAc,2EAAwC,EAC/D,OAAO,uBAAuB,2EAAoB,EAClD,OAAO,uBAAuB,0EAAmB,EACjD,OAAO,uBAAuB,mEAA2B,EACzD,OAAO,mBAAmB,wEAAgC,UAAU,EACpE,OAAO,sBAAsB,qEAAmB,EAChD,OAAO,YAAY,oDAAY,EAC/B,OAAO,OAAO,OAAiB,SAAS;AACvC,QAAM,eAAe,CAAC,YAAY,MAAM;AACxC,MAAI,CAAC,aAAa,SAAS,KAAK,MAAM,GAAG;AACvC,YAAQ,OAAO,MAAM,gEAAwB,KAAK,MAAM;AAAA,CAAuB;AAC/E,YAAQ,KAAK,CAAC;AAAA,EAChB;AACA,WAAS,KAAK,GAAG,KAAK,MAAM,QAAQ,MAAM;AACxC,UAAM,WAAW,MAAM,EAAE;AACzB,UAAM,UAAU,QAAQ,QAAQ;AAChC,UAAM,WAAW,SAAS,OAAO;AACjC,UAAM,aAAa,MAAM,SAAS,IAAI,IAAI,KAAK,CAAC,IAAI,MAAM,MAAM,OAAO;AAEvE,QAAI;AACF,YAAM,WAAW,SAAS,OAAO,EAAE;AACnC,UAAI,WAAW,MAAM,OAAO,MAAM;AAChC,gBAAQ,OAAO,MAAM;AAAA,iBAAoB,QAAQ,gEAAmB,WAAW,OAAO,MAAM,QAAQ,CAAC,CAAC;AAAA,CAAO;AAC7G,gBAAQ,WAAW;AACnB;AAAA,MACF;AACA,YAAM,SAAS,aAAa,OAAO;AACnC,YAAM,cAAc,cAAc,MAAM;AACxC,YAAM,SAAS,aAAa,WAAW;AAEvC,UAAI,CAAC,KAAK,QAAQ;AAChB,gBAAQ,OAAO,MAAM,YAAY,UAAU,GAAG,QAAQ,KAAK,MAAM,OAAO;AAAA,MAC1E;AAEA,YAAM,eAA6B,CAAC;AACpC,UAAI,KAAK,MAAO,cAAa,QAAQ,KAAK;AAC1C,UAAI,KAAK,iBAAiB,MAAO,cAAa,qBAAqB;AACnE,UAAI,CAAC,KAAK,QAAQ;AAChB,qBAAa,aAAa,CAAC,SAAiB,UAAkB;AAC5D,kBAAQ,OAAO,MAAM,cAAc,UAAU,GAAG,QAAQ,KAAK,MAAM,MAAM,OAAO,IAAI,KAAK,GAAG;AAAA,QAC9F;AAAA,MACF;AACA,YAAM,SAAS,MAAM,MAAM,aAAa,YAAY;AAEpD,UAAI,CAAC,OAAO,SAAS;AACnB,gBAAQ,OAAO,MAAM;AAAA,CAAS;AAC9B,gBAAQ,OAAO,MAAM,YAAO,OAAO,KAAK;AAAA,CAAI;AAC5C,gBAAQ,WAAW;AACnB;AAAA,MACF;AAEA,UAAI,CAAC,KAAK,OAAQ,SAAQ,OAAO,MAAM;AAAA,CAAO;AAE9C,UAAI,WAAW,OAAO;AAEtB,UAAI,KAAK,UAAU,OAAO,QAAQ,QAAQ;AACxC,mBAAW,SAAS,QAAQ,uBAAuB,wBAAwB;AAAA,MAC7E;AACA,YAAM,SAAS,KAAK,WAAW,SAC3B,KAAK;AAAA,QAAU;AAAA,QAAQ,CAAC,MAAM,UAC5B,iBAAiB,aAAa,OAAO,KAAK,KAAK,EAAE,SAAS,QAAQ,IAAI;AAAA,QACtE;AAAA,MAAC,IACH;AAGJ,YAAM,aAAa,CAAC,QAAgB;AAClC,YAAI,CAAC,OAAO,QAAQ,OAAQ;AAC5B,cAAM,SAAS,QAAQ,KAAK,QAAQ;AACpC,kBAAU,QAAQ,EAAE,WAAW,KAAK,CAAC;AACrC,mBAAW,OAAO,OAAO,QAAQ;AAC/B,wBAAc,QAAQ,QAAQ,IAAI,QAAQ,GAAG,IAAI,IAAI;AAAA,QACvD;AACA,YAAI,CAAC,KAAK,OAAQ,SAAQ,OAAO,MAAM,YAAO,OAAO,OAAO,MAAM,oCAAW,MAAM;AAAA,CAAI;AAAA,MACzF;AAEA,UAAI,KAAK,UAAU,MAAM,WAAW,GAAG;AACrC,sBAAc,KAAK,QAAQ,QAAQ,OAAO;AAC1C,YAAI,CAAC,KAAK,OAAQ,SAAQ,OAAO,MAAM,YAAO,KAAK,MAAM;AAAA,CAAI;AAC7D,mBAAW,QAAQ,KAAK,QAAQ,IAAI,CAAC;AAAA,MACvC,WAAW,KAAK,QAAQ;AACtB,kBAAU,KAAK,QAAQ,EAAE,WAAW,KAAK,CAAC;AAC1C,cAAM,SAAS,KAAK,WAAW,SAAS,UAAU;AAClD,cAAM,UAAU,QAAQ,KAAK,QAAQ,SAAS,QAAQ,YAAY,MAAM,CAAC;AACzE,sBAAc,SAAS,QAAQ,OAAO;AACtC,YAAI,CAAC,KAAK,OAAQ,SAAQ,OAAO,MAAM,YAAO,OAAO;AAAA,CAAI;AACzD,mBAAW,KAAK,MAAM;AAAA,MACxB,OAAO;AACL,gBAAQ,OAAO,MAAM,SAAS,IAAI;AAAA,MACpC;AAAA,IACF,SAAS,KAAK;AACZ,cAAQ,OAAO,MAAM;AAAA,kBAAqB,QAAQ,WAAM,cAAc,GAAG,CAAC;AAAA,CAAI;AAC9E,cAAQ,WAAW;AAAA,IACrB;AAAA,EACF;AACF,CAAC;AAEH,QACG,QAAQ,aAAa,EACrB,YAAY,4FAAsB,EAClC,OAAO,mBAAmB,4CAAc,EACxC,OAAO,uBAAuB,iEAAe,EAC7C,OAAO,uBAAuB,8CAAW,EACzC,OAAO,mBAAmB,yDAA2B,UAAU,EAC/D,OAAO,YAAY,oDAAY,EAC/B,OAAO,OAAO,KAAa,SAAS;AACnC,QAAM,EAAE,eAAe,IAAI,MAAM,OAAO,qBAAY;AACpD,QAAM,eAAe;AAAA,IACnB;AAAA,IACA,QAAQ,KAAK;AAAA,IACb,SAAS,KAAK;AAAA,IACd,QAAQ,KAAK;AAAA,IACb,OAAO,KAAK;AAAA,IACZ,QAAQ,KAAK;AAAA,EACf,CAAC;AACH,CAAC;AAEH,QAAQ,MAAM;","names":[]}
|
|
1
|
+
{"version":3,"sources":["../src/cli.ts"],"sourcesContent":["/** kordoc CLI — 모두 파싱해버리겠다 */\r\n\r\nimport { readFileSync, writeFileSync, mkdirSync, statSync } from \"fs\"\r\nimport { basename, resolve } from \"path\"\r\nimport { Command } from \"commander\"\r\nimport { parse, detectFormat } from \"./index.js\"\r\nimport type { ParseOptions } from \"./types.js\"\r\nimport { VERSION, toArrayBuffer, sanitizeError } from \"./utils.js\"\r\n\r\nconst program = new Command()\r\n\r\nprogram\r\n .name(\"kordoc\")\r\n .description(\"모두 파싱해버리겠다 — HWP, HWPX, PDF, XLSX, DOCX → Markdown\")\r\n .version(VERSION)\r\n .argument(\"<files...>\", \"변환할 파일 경로 (HWP, HWPX, PDF, XLSX, DOCX)\")\r\n .option(\"-o, --output <path>\", \"출력 파일 경로 (단일 파일 시)\")\r\n .option(\"-d, --out-dir <dir>\", \"출력 디렉토리 (다중 파일 시)\")\r\n .option(\"-p, --pages <range>\", \"페이지/섹션 범위 (예: 1-3, 1,3,5)\")\r\n .option(\"--format <type>\", \"출력 형식: markdown (기본) 또는 json\", \"markdown\")\r\n .option(\"--no-header-footer\", \"PDF 머리글/바닥글 자동 제거\")\r\n .option(\"--silent\", \"진행 메시지 숨기기\")\r\n .action(async (files: string[], opts) => {\r\n const validFormats = [\"markdown\", \"json\"]\r\n if (!validFormats.includes(opts.format)) {\r\n process.stderr.write(`[kordoc] 지원하지 않는 형식: ${opts.format} (markdown 또는 json)\\n`)\r\n process.exit(1)\r\n }\r\n for (let fi = 0; fi < files.length; fi++) {\r\n const filePath = files[fi]\r\n const absPath = resolve(filePath)\r\n const fileName = basename(absPath)\r\n const filePrefix = files.length > 1 ? `[${fi + 1}/${files.length}] ` : \"\"\r\n\r\n try {\r\n const fileSize = statSync(absPath).size\r\n if (fileSize > 500 * 1024 * 1024) {\r\n process.stderr.write(`\\n[kordoc] SKIP: ${fileName} — 파일이 너무 큽니다 (${(fileSize / 1024 / 1024).toFixed(1)}MB)\\n`)\r\n process.exitCode = 1\r\n continue\r\n }\r\n const buffer = readFileSync(absPath)\r\n const arrayBuffer = toArrayBuffer(buffer)\r\n const format = detectFormat(arrayBuffer)\r\n\r\n if (!opts.silent) {\r\n process.stderr.write(`[kordoc] ${filePrefix}${fileName} (${format}) ...`)\r\n }\r\n\r\n const parseOptions: ParseOptions = {}\r\n if (opts.pages) parseOptions.pages = opts.pages as string\r\n if (opts.headerFooter === false) parseOptions.removeHeaderFooter = false\r\n if (!opts.silent) {\r\n parseOptions.onProgress = (current: number, total: number) => {\r\n process.stderr.write(`\\r[kordoc] ${filePrefix}${fileName} (${format}) [${current}/${total}]`)\r\n }\r\n }\r\n const result = await parse(arrayBuffer, parseOptions)\r\n\r\n if (!result.success) {\r\n process.stderr.write(` FAIL\\n`)\r\n process.stderr.write(` → ${result.error}\\n`)\r\n process.exitCode = 1\r\n continue\r\n }\r\n\r\n if (!opts.silent) process.stderr.write(` OK\\n`)\r\n\r\n let markdown = result.markdown\r\n // --out-dir 시 이미지 참조 경로에 images/ 접두사 추가\r\n if (opts.outDir && result.images?.length) {\r\n markdown = markdown.replace(/!\\[image\\]\\(image_/g, \"\r\n }\r\n const output = opts.format === \"json\"\r\n ? JSON.stringify(result, (_key, value) =>\r\n value instanceof Uint8Array ? Buffer.from(value).toString(\"base64\") : value\r\n , 2)\r\n : markdown\r\n\r\n // 이미지 저장 (--out-dir 또는 --output 시)\r\n const saveImages = (dir: string) => {\r\n if (!result.images?.length) return\r\n const imgDir = resolve(dir, \"images\")\r\n mkdirSync(imgDir, { recursive: true })\r\n for (const img of result.images) {\r\n writeFileSync(resolve(imgDir, img.filename), img.data)\r\n }\r\n if (!opts.silent) process.stderr.write(` → ${result.images.length}개 이미지 → ${imgDir}\\n`)\r\n }\r\n\r\n if (opts.output && files.length === 1) {\r\n writeFileSync(opts.output, output, \"utf-8\")\r\n if (!opts.silent) process.stderr.write(` → ${opts.output}\\n`)\r\n saveImages(resolve(opts.output, \"..\"))\r\n } else if (opts.outDir) {\r\n mkdirSync(opts.outDir, { recursive: true })\r\n const outExt = opts.format === \"json\" ? \".json\" : \".md\"\r\n const outPath = resolve(opts.outDir, fileName.replace(/\\.[^.]+$/, outExt))\r\n writeFileSync(outPath, output, \"utf-8\")\r\n if (!opts.silent) process.stderr.write(` → ${outPath}\\n`)\r\n saveImages(opts.outDir)\r\n } else {\r\n process.stdout.write(output + \"\\n\")\r\n }\r\n } catch (err) {\r\n process.stderr.write(`\\n[kordoc] ERROR: ${fileName} — ${sanitizeError(err)}\\n`)\r\n process.exitCode = 1\r\n }\r\n }\r\n })\r\n\r\nprogram\r\n .command(\"watch <dir>\")\r\n .description(\"디렉토리 감시 — 새 문서 자동 변환\")\r\n .option(\"--webhook <url>\", \"결과 전송 웹훅 URL\")\r\n .option(\"-d, --out-dir <dir>\", \"변환 결과 출력 디렉토리\")\r\n .option(\"-p, --pages <range>\", \"페이지/섹션 범위\")\r\n .option(\"--format <type>\", \"출력 형식: markdown 또는 json\", \"markdown\")\r\n .option(\"--silent\", \"진행 메시지 숨기기\")\r\n .action(async (dir: string, opts) => {\r\n const { watchDirectory } = await import(\"./watch.js\")\r\n await watchDirectory({\r\n dir,\r\n outDir: opts.outDir,\r\n webhook: opts.webhook,\r\n format: opts.format,\r\n pages: opts.pages,\r\n silent: opts.silent,\r\n })\r\n })\r\n\r\nprogram.parse()\r\n"],"mappings":";;;;;;;;;;;;;AAEA,SAAS,cAAc,eAAe,WAAW,gBAAgB;AACjE,SAAS,UAAU,eAAe;AAClC,SAAS,eAAe;AAKxB,IAAM,UAAU,IAAI,QAAQ;AAE5B,QACG,KAAK,QAAQ,EACb,YAAY,2GAAoD,EAChE,QAAQ,OAAO,EACf,SAAS,cAAc,2EAAwC,EAC/D,OAAO,uBAAuB,2EAAoB,EAClD,OAAO,uBAAuB,0EAAmB,EACjD,OAAO,uBAAuB,mEAA2B,EACzD,OAAO,mBAAmB,wEAAgC,UAAU,EACpE,OAAO,sBAAsB,qEAAmB,EAChD,OAAO,YAAY,oDAAY,EAC/B,OAAO,OAAO,OAAiB,SAAS;AACvC,QAAM,eAAe,CAAC,YAAY,MAAM;AACxC,MAAI,CAAC,aAAa,SAAS,KAAK,MAAM,GAAG;AACvC,YAAQ,OAAO,MAAM,gEAAwB,KAAK,MAAM;AAAA,CAAuB;AAC/E,YAAQ,KAAK,CAAC;AAAA,EAChB;AACA,WAAS,KAAK,GAAG,KAAK,MAAM,QAAQ,MAAM;AACxC,UAAM,WAAW,MAAM,EAAE;AACzB,UAAM,UAAU,QAAQ,QAAQ;AAChC,UAAM,WAAW,SAAS,OAAO;AACjC,UAAM,aAAa,MAAM,SAAS,IAAI,IAAI,KAAK,CAAC,IAAI,MAAM,MAAM,OAAO;AAEvE,QAAI;AACF,YAAM,WAAW,SAAS,OAAO,EAAE;AACnC,UAAI,WAAW,MAAM,OAAO,MAAM;AAChC,gBAAQ,OAAO,MAAM;AAAA,iBAAoB,QAAQ,gEAAmB,WAAW,OAAO,MAAM,QAAQ,CAAC,CAAC;AAAA,CAAO;AAC7G,gBAAQ,WAAW;AACnB;AAAA,MACF;AACA,YAAM,SAAS,aAAa,OAAO;AACnC,YAAM,cAAc,cAAc,MAAM;AACxC,YAAM,SAAS,aAAa,WAAW;AAEvC,UAAI,CAAC,KAAK,QAAQ;AAChB,gBAAQ,OAAO,MAAM,YAAY,UAAU,GAAG,QAAQ,KAAK,MAAM,OAAO;AAAA,MAC1E;AAEA,YAAM,eAA6B,CAAC;AACpC,UAAI,KAAK,MAAO,cAAa,QAAQ,KAAK;AAC1C,UAAI,KAAK,iBAAiB,MAAO,cAAa,qBAAqB;AACnE,UAAI,CAAC,KAAK,QAAQ;AAChB,qBAAa,aAAa,CAAC,SAAiB,UAAkB;AAC5D,kBAAQ,OAAO,MAAM,cAAc,UAAU,GAAG,QAAQ,KAAK,MAAM,MAAM,OAAO,IAAI,KAAK,GAAG;AAAA,QAC9F;AAAA,MACF;AACA,YAAM,SAAS,MAAM,MAAM,aAAa,YAAY;AAEpD,UAAI,CAAC,OAAO,SAAS;AACnB,gBAAQ,OAAO,MAAM;AAAA,CAAS;AAC9B,gBAAQ,OAAO,MAAM,YAAO,OAAO,KAAK;AAAA,CAAI;AAC5C,gBAAQ,WAAW;AACnB;AAAA,MACF;AAEA,UAAI,CAAC,KAAK,OAAQ,SAAQ,OAAO,MAAM;AAAA,CAAO;AAE9C,UAAI,WAAW,OAAO;AAEtB,UAAI,KAAK,UAAU,OAAO,QAAQ,QAAQ;AACxC,mBAAW,SAAS,QAAQ,uBAAuB,wBAAwB;AAAA,MAC7E;AACA,YAAM,SAAS,KAAK,WAAW,SAC3B,KAAK;AAAA,QAAU;AAAA,QAAQ,CAAC,MAAM,UAC5B,iBAAiB,aAAa,OAAO,KAAK,KAAK,EAAE,SAAS,QAAQ,IAAI;AAAA,QACtE;AAAA,MAAC,IACH;AAGJ,YAAM,aAAa,CAAC,QAAgB;AAClC,YAAI,CAAC,OAAO,QAAQ,OAAQ;AAC5B,cAAM,SAAS,QAAQ,KAAK,QAAQ;AACpC,kBAAU,QAAQ,EAAE,WAAW,KAAK,CAAC;AACrC,mBAAW,OAAO,OAAO,QAAQ;AAC/B,wBAAc,QAAQ,QAAQ,IAAI,QAAQ,GAAG,IAAI,IAAI;AAAA,QACvD;AACA,YAAI,CAAC,KAAK,OAAQ,SAAQ,OAAO,MAAM,YAAO,OAAO,OAAO,MAAM,oCAAW,MAAM;AAAA,CAAI;AAAA,MACzF;AAEA,UAAI,KAAK,UAAU,MAAM,WAAW,GAAG;AACrC,sBAAc,KAAK,QAAQ,QAAQ,OAAO;AAC1C,YAAI,CAAC,KAAK,OAAQ,SAAQ,OAAO,MAAM,YAAO,KAAK,MAAM;AAAA,CAAI;AAC7D,mBAAW,QAAQ,KAAK,QAAQ,IAAI,CAAC;AAAA,MACvC,WAAW,KAAK,QAAQ;AACtB,kBAAU,KAAK,QAAQ,EAAE,WAAW,KAAK,CAAC;AAC1C,cAAM,SAAS,KAAK,WAAW,SAAS,UAAU;AAClD,cAAM,UAAU,QAAQ,KAAK,QAAQ,SAAS,QAAQ,YAAY,MAAM,CAAC;AACzE,sBAAc,SAAS,QAAQ,OAAO;AACtC,YAAI,CAAC,KAAK,OAAQ,SAAQ,OAAO,MAAM,YAAO,OAAO;AAAA,CAAI;AACzD,mBAAW,KAAK,MAAM;AAAA,MACxB,OAAO;AACL,gBAAQ,OAAO,MAAM,SAAS,IAAI;AAAA,MACpC;AAAA,IACF,SAAS,KAAK;AACZ,cAAQ,OAAO,MAAM;AAAA,kBAAqB,QAAQ,WAAM,cAAc,GAAG,CAAC;AAAA,CAAI;AAC9E,cAAQ,WAAW;AAAA,IACrB;AAAA,EACF;AACF,CAAC;AAEH,QACG,QAAQ,aAAa,EACrB,YAAY,4FAAsB,EAClC,OAAO,mBAAmB,4CAAc,EACxC,OAAO,uBAAuB,iEAAe,EAC7C,OAAO,uBAAuB,8CAAW,EACzC,OAAO,mBAAmB,yDAA2B,UAAU,EAC/D,OAAO,YAAY,oDAAY,EAC/B,OAAO,OAAO,KAAa,SAAS;AACnC,QAAM,EAAE,eAAe,IAAI,MAAM,OAAO,qBAAY;AACpD,QAAM,eAAe;AAAA,IACnB;AAAA,IACA,QAAQ,KAAK;AAAA,IACb,SAAS,KAAK;AAAA,IACd,QAAQ,KAAK;AAAA,IACb,OAAO,KAAK;AAAA,IACZ,QAAQ,KAAK;AAAA,EACf,CAAC;AACH,CAAC;AAEH,QAAQ,MAAM;","names":[]}
|
|
@@ -6,7 +6,7 @@ import {
|
|
|
6
6
|
isOldHwpFile,
|
|
7
7
|
isPdfFile,
|
|
8
8
|
isZipFile
|
|
9
|
-
} from "./chunk-
|
|
9
|
+
} from "./chunk-MUAWCQDY.js";
|
|
10
10
|
export {
|
|
11
11
|
detectFormat,
|
|
12
12
|
detectZipFormat,
|
|
@@ -15,4 +15,4 @@ export {
|
|
|
15
15
|
isPdfFile,
|
|
16
16
|
isZipFile
|
|
17
17
|
};
|
|
18
|
-
//# sourceMappingURL=detect-
|
|
18
|
+
//# sourceMappingURL=detect-63IGCXTH.js.map
|
package/dist/index.cjs
CHANGED
|
@@ -183,7 +183,7 @@ var import_zlib = require("zlib");
|
|
|
183
183
|
var import_xmldom = require("@xmldom/xmldom");
|
|
184
184
|
|
|
185
185
|
// src/utils.ts
|
|
186
|
-
var VERSION = true ? "2.2.
|
|
186
|
+
var VERSION = true ? "2.2.1" : "0.0.0-dev";
|
|
187
187
|
function toArrayBuffer(buf) {
|
|
188
188
|
if (buf.byteOffset === 0 && buf.byteLength === buf.buffer.byteLength) {
|
|
189
189
|
return buf.buffer;
|
|
@@ -372,9 +372,12 @@ function trimAndReturn(grid, numRows, maxCols) {
|
|
|
372
372
|
}
|
|
373
373
|
function convertTableToText(rows) {
|
|
374
374
|
return rows.map(
|
|
375
|
-
(row) => row.map((c) => c.text.trim().replace(/\n/g, " ")).filter(Boolean).join("
|
|
375
|
+
(row) => row.map((c) => c.text.trim().replace(/\n/g, " ").replace(/\|/g, "\\|")).filter(Boolean).join(" / ")
|
|
376
376
|
).filter(Boolean).join("\n");
|
|
377
377
|
}
|
|
378
|
+
function escapeGfm(text) {
|
|
379
|
+
return text.replace(/~/g, "\\~");
|
|
380
|
+
}
|
|
378
381
|
var HWP_SHAPE_ALT_TEXT_RE = /(?:모서리가 둥근 |둥근 )?(?:사각형|직사각형|정사각형|원|타원|삼각형|이등변 삼각형|직각 삼각형|선|직선|곡선|화살표|굵은 화살표|이중 화살표|오각형|육각형|팔각형|별|[4-8]점별|십자|십자형|구름|구름형|마름모|도넛|평행사변형|사다리꼴|부채꼴|호|반원|물결|번개|하트|빗금|블록 화살표|수식|표|그림|개체|그리기\s?개체|묶음\s?개체|글상자|수식\s?개체|OLE\s?개체)\s?입니다\.?/g;
|
|
379
382
|
function sanitizeText(text) {
|
|
380
383
|
let result = text.replace(/[\u{F0000}-\u{FFFFD}]/gu, "").replace(HWP_SHAPE_ALT_TEXT_RE, "").replace(/ +/g, " ").trim();
|
|
@@ -484,7 +487,7 @@ function blocksToMarkdown(blocks) {
|
|
|
484
487
|
if (block.footnoteText) {
|
|
485
488
|
text += ` (\uC8FC: ${block.footnoteText})`;
|
|
486
489
|
}
|
|
487
|
-
lines.push(text);
|
|
490
|
+
lines.push(escapeGfm(text), "");
|
|
488
491
|
} else if (block.type === "table" && block.table) {
|
|
489
492
|
if (lines.length > 0 && lines[lines.length - 1] !== "") {
|
|
490
493
|
lines.push("");
|
|
@@ -507,13 +510,13 @@ function tableToMarkdown(table) {
|
|
|
507
510
|
return content.split(/\n/).map((line) => {
|
|
508
511
|
const trimmed = line.trim();
|
|
509
512
|
if (!trimmed) return "";
|
|
510
|
-
if (/^\d+\.\s/.test(trimmed)) return `**${trimmed}**`;
|
|
511
|
-
if (/^[가-힣]\.\s/.test(trimmed)) return ` ${trimmed}`;
|
|
512
|
-
return trimmed;
|
|
513
|
+
if (/^\d+\.\s/.test(trimmed)) return `**${escapeGfm(trimmed)}**`;
|
|
514
|
+
if (/^[가-힣]\.\s/.test(trimmed)) return ` ${escapeGfm(trimmed)}`;
|
|
515
|
+
return escapeGfm(trimmed);
|
|
513
516
|
}).filter(Boolean).join("\n");
|
|
514
517
|
}
|
|
515
518
|
if (numCols === 1 && numRows >= 2) {
|
|
516
|
-
return cells.map((row) => sanitizeText(row[0].text).replace(/\n/g, " ")).filter(Boolean).join("\n");
|
|
519
|
+
return cells.map((row) => escapeGfm(sanitizeText(row[0].text)).replace(/\n/g, " ")).filter(Boolean).join("\n");
|
|
517
520
|
}
|
|
518
521
|
const display = Array.from({ length: numRows }, () => Array(numCols).fill(""));
|
|
519
522
|
const skip = /* @__PURE__ */ new Set();
|
|
@@ -522,7 +525,7 @@ function tableToMarkdown(table) {
|
|
|
522
525
|
if (skip.has(`${r},${c}`)) continue;
|
|
523
526
|
const cell = cells[r]?.[c];
|
|
524
527
|
if (!cell) continue;
|
|
525
|
-
display[r][c] = sanitizeText(cell.text).replace(/\n/g, "<br>");
|
|
528
|
+
display[r][c] = escapeGfm(sanitizeText(cell.text)).replace(/\|/g, "\\|").replace(/\n/g, "<br>");
|
|
526
529
|
for (let dr = 0; dr < cell.rowSpan; dr++) {
|
|
527
530
|
for (let dc = 0; dc < cell.colSpan; dc++) {
|
|
528
531
|
if (dr === 0 && dc === 0) continue;
|