kordoc 4.0.8 → 4.1.0
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/README.md +25 -11
- package/dist/{-LE4RLXVA.js → -AS4IABL2.js} +23 -10
- package/dist/{chunk-2DZQF6YJ.js → chunk-37HJHCPA.js} +24 -15
- package/dist/chunk-37HJHCPA.js.map +1 -0
- package/dist/{chunk-6XAAYAWL.cjs → chunk-37VKMUST.cjs} +47 -37
- package/dist/chunk-37VKMUST.cjs.map +1 -0
- package/dist/{chunk-OQPILS7B.js → chunk-4KI23VHA.js} +33 -23
- package/dist/chunk-4KI23VHA.js.map +1 -0
- package/dist/{chunk-D35VBACN.js → chunk-AX2R5Q2N.js} +7 -4
- package/dist/chunk-AX2R5Q2N.js.map +1 -0
- package/dist/chunk-DZIXKL7E.js +145 -0
- package/dist/chunk-DZIXKL7E.js.map +1 -0
- package/dist/chunk-F2ZU3IZG.js +82 -0
- package/dist/chunk-F2ZU3IZG.js.map +1 -0
- package/dist/{chunk-BNU5QGIZ.js → chunk-GQVSHGG4.js} +12 -4
- package/dist/chunk-GQVSHGG4.js.map +1 -0
- package/dist/{chunk-7S3M4N4E.js → chunk-L2XQQTOY.js} +566 -189
- package/dist/chunk-L2XQQTOY.js.map +1 -0
- package/dist/{chunk-HMUEU7D7.js → chunk-O5VS7RIR.js} +2 -2
- package/dist/{chunk-UEIYETCQ.js → chunk-SSTK6IKK.js} +18 -160
- package/dist/chunk-SSTK6IKK.js.map +1 -0
- package/dist/chunk-UOO7LSDG.js +152 -0
- package/dist/chunk-UOO7LSDG.js.map +1 -0
- package/dist/{chunk-RROH5WHO.js → chunk-WO52HVQJ.js} +2 -2
- package/dist/{chunk-MEPHGCPQ.js → chunk-YOO6ET6M.js} +7 -3
- package/dist/chunk-YOO6ET6M.js.map +1 -0
- package/dist/chunks-WVMGF7JL.js +10 -0
- package/dist/cli.js +170 -35
- package/dist/cli.js.map +1 -1
- package/dist/{detect-RI2MQ33K.js → detect-YEZX2XCF.js} +2 -2
- package/dist/index.cjs +1142 -531
- package/dist/index.cjs.map +1 -1
- package/dist/index.d.cts +105 -1
- package/dist/index.d.ts +105 -1
- package/dist/index.js +802 -191
- package/dist/index.js.map +1 -1
- package/dist/mcp.js +273 -65
- package/dist/mcp.js.map +1 -1
- package/dist/{parser-ITMU2WN5.cjs → parser-N4A7UGDK.cjs} +127 -45
- package/dist/parser-N4A7UGDK.cjs.map +1 -0
- package/dist/{parser-TCTCSBYZ.js → parser-PEOYBXBO.js} +118 -34
- package/dist/parser-PEOYBXBO.js.map +1 -0
- package/dist/{parser-KMMUS73Q.js → parser-XX4QTDFQ.js} +114 -32
- package/dist/parser-XX4QTDFQ.js.map +1 -0
- package/dist/{profile-io-SLN4P76T.js → profile-io-PLDQFPJA.js} +3 -3
- package/dist/{provider-G4C2V2PD.cjs → provider-4FAYHJ6N.cjs} +3 -3
- package/dist/provider-4FAYHJ6N.cjs.map +1 -0
- package/dist/{provider-4ZJKV3DC.js → provider-C6IOGIS5.js} +3 -3
- package/dist/provider-C6IOGIS5.js.map +1 -0
- package/dist/{provider-AKROB7WQ.js → provider-UIBW2MIH.js} +3 -3
- package/dist/provider-UIBW2MIH.js.map +1 -0
- package/dist/rasterize-WWNQLKYW.js +40 -0
- package/dist/rasterize-WWNQLKYW.js.map +1 -0
- package/dist/redact-7ILEAUTS.js +12 -0
- package/dist/render-T7S6H6AN.js +10 -0
- package/dist/render-T7S6H6AN.js.map +1 -0
- package/dist/seal-7PTL6MXH.js +10 -0
- package/dist/seal-7PTL6MXH.js.map +1 -0
- package/dist/{setup-57FB3LSP.js → setup-Q2PRE7UA.js} +5 -3
- package/dist/setup-Q2PRE7UA.js.map +1 -0
- package/dist/{watch-OHQWSVPE.js → watch-SFHXZALC.js} +77 -23
- package/dist/watch-SFHXZALC.js.map +1 -0
- package/package.json +1 -1
- package/dist/chunk-2DZQF6YJ.js.map +0 -1
- package/dist/chunk-6XAAYAWL.cjs.map +0 -1
- package/dist/chunk-7S3M4N4E.js.map +0 -1
- package/dist/chunk-BNU5QGIZ.js.map +0 -1
- package/dist/chunk-D35VBACN.js.map +0 -1
- package/dist/chunk-MEPHGCPQ.js.map +0 -1
- package/dist/chunk-OQPILS7B.js.map +0 -1
- package/dist/chunk-UEIYETCQ.js.map +0 -1
- package/dist/parser-ITMU2WN5.cjs.map +0 -1
- package/dist/parser-KMMUS73Q.js.map +0 -1
- package/dist/parser-TCTCSBYZ.js.map +0 -1
- package/dist/provider-4ZJKV3DC.js.map +0 -1
- package/dist/provider-AKROB7WQ.js.map +0 -1
- package/dist/provider-G4C2V2PD.cjs.map +0 -1
- package/dist/render-25BT623I.js +0 -10
- package/dist/seal-R4TETA4C.js +0 -10
- package/dist/setup-57FB3LSP.js.map +0 -1
- package/dist/watch-OHQWSVPE.js.map +0 -1
- /package/dist/{-LE4RLXVA.js.map → -AS4IABL2.js.map} +0 -0
- /package/dist/{chunk-HMUEU7D7.js.map → chunk-O5VS7RIR.js.map} +0 -0
- /package/dist/{chunk-RROH5WHO.js.map → chunk-WO52HVQJ.js.map} +0 -0
- /package/dist/{detect-RI2MQ33K.js.map → chunks-WVMGF7JL.js.map} +0 -0
- /package/dist/{profile-io-SLN4P76T.js.map → detect-YEZX2XCF.js.map} +0 -0
- /package/dist/{render-25BT623I.js.map → profile-io-PLDQFPJA.js.map} +0 -0
- /package/dist/{seal-R4TETA4C.js.map → redact-7ILEAUTS.js.map} +0 -0
|
@@ -19,8 +19,11 @@ function parseLenientCfb(data) {
|
|
|
19
19
|
const miniSectorSizeShift = data.readUInt16LE(32);
|
|
20
20
|
if (miniSectorSizeShift > 16) throw new Error("\uC720\uD6A8\uD558\uC9C0 \uC54A\uC740 \uBBF8\uB2C8 \uC139\uD130 \uD06C\uAE30 \uC2DC\uD504\uD2B8: " + miniSectorSizeShift);
|
|
21
21
|
const miniSectorSize = 1 << miniSectorSizeShift;
|
|
22
|
-
const
|
|
23
|
-
if (
|
|
22
|
+
const headerFatSectorCount = data.readUInt32LE(44);
|
|
23
|
+
if (headerFatSectorCount > 1e4) throw new Error("FAT \uC139\uD130 \uC218\uAC00 \uB108\uBB34 \uB9CE\uC2B5\uB2C8\uB2E4: " + headerFatSectorCount);
|
|
24
|
+
const maxRealSectors = Math.ceil(Math.max(0, data.length - 512) / sectorSize);
|
|
25
|
+
const maxFatSectors = Math.max(1, Math.ceil(maxRealSectors / (sectorSize / 4)));
|
|
26
|
+
const fatSectorCount = Math.min(headerFatSectorCount, maxFatSectors);
|
|
24
27
|
const firstDirSector = data.readUInt32LE(48);
|
|
25
28
|
const miniStreamCutoff = data.readUInt32LE(56);
|
|
26
29
|
const firstMiniFatSector = data.readUInt32LE(60);
|
|
@@ -47,6 +50,7 @@ function parseLenientCfb(data) {
|
|
|
47
50
|
if (visitedDifat.has(difatSector)) break;
|
|
48
51
|
visitedDifat.add(difatSector);
|
|
49
52
|
const buf = readSectorData(difatSector);
|
|
53
|
+
if (buf.length < sectorSize) break;
|
|
50
54
|
const entriesPerSector = sectorSize / 4 - 1;
|
|
51
55
|
for (let i = 0; i < entriesPerSector && fatSectors.length < fatSectorCount; i++) {
|
|
52
56
|
const sid = buf.readUInt32LE(i * 4);
|
|
@@ -263,4 +267,4 @@ export {
|
|
|
263
267
|
detectOle2Format,
|
|
264
268
|
detectZipFormat
|
|
265
269
|
};
|
|
266
|
-
//# sourceMappingURL=chunk-
|
|
270
|
+
//# sourceMappingURL=chunk-YOO6ET6M.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"sources":["../src/detect.ts","../src/hwp5/cfb-lenient.ts"],"sourcesContent":["/** 매직 바이트 기반 파일 포맷 감지 */\n\nimport JSZip from \"jszip\"\nimport type { FileType } from \"./types.js\"\nimport { parseLenientCfb } from \"./hwp5/cfb-lenient.js\"\n\n/** 매직 바이트 뷰 생성 (복사 없이 view) */\nfunction magicBytes(buffer: ArrayBuffer): Uint8Array {\n return new Uint8Array(buffer, 0, Math.min(4, buffer.byteLength))\n}\n\n/** ZIP 파일 여부: PK\\x03\\x04 */\nexport function isZipFile(buffer: ArrayBuffer): boolean {\n const b = magicBytes(buffer)\n return b[0] === 0x50 && b[1] === 0x4b && b[2] === 0x03 && b[3] === 0x04\n}\n\n/** HWPX (ZIP 기반 한컴 문서): PK\\x03\\x04 — 하위 호환용 */\nexport function isHwpxFile(buffer: ArrayBuffer): boolean {\n return isZipFile(buffer)\n}\n\n/** HWP 5.x (OLE2 바이너리 한컴 문서): \\xD0\\xCF\\x11\\xE0 */\nexport function isOldHwpFile(buffer: ArrayBuffer): boolean {\n const b = magicBytes(buffer)\n return b[0] === 0xd0 && b[1] === 0xcf && b[2] === 0x11 && b[3] === 0xe0\n}\n\n/**\n * HWP 3.x (한글 워드프로세서 3.0): \"HWP Document File V3.00 \\x1A\\x01\\x02\\x03\\x04\\x05\" 30 byte.\n * CFB(OLE2) 컨테이너 아닌 단일 binary stream — isOldHwpFile 과 magic 이 다르다.\n */\nconst HWP3_PREFIX = new TextEncoder().encode(\"HWP Document File V3.00\")\nexport function isHwp3File(buffer: ArrayBuffer): boolean {\n if (buffer.byteLength < HWP3_PREFIX.length) return false\n const head = new Uint8Array(buffer, 0, HWP3_PREFIX.length)\n for (let i = 0; i < HWP3_PREFIX.length; i++) {\n if (head[i] !== HWP3_PREFIX[i]) return false\n }\n return true\n}\n\n/** PDF 문서: %PDF */\nexport function isPdfFile(buffer: ArrayBuffer): boolean {\n const b = magicBytes(buffer)\n return b[0] === 0x25 && b[1] === 0x50 && b[2] === 0x44 && b[3] === 0x46\n}\n\n/** HWPML (XML 기반 한컴 문서): <?xml ... <HWPML */\nexport function isHwpmlFile(buffer: ArrayBuffer): boolean {\n const bytes = new Uint8Array(buffer, 0, Math.min(512, buffer.byteLength))\n const head = new TextDecoder(\"utf-8\", { fatal: false }).decode(bytes).replace(/^\\uFEFF/, \"\")\n return head.trimStart().startsWith(\"<?xml\") && head.includes(\"<HWPML\")\n}\n\n/** 동기 포맷 감지 — ZIP은 모두 \"hwpx\"로 반환 (하위 호환) */\nexport function detectFormat(buffer: ArrayBuffer): FileType {\n if (buffer.byteLength < 4) return \"unknown\"\n if (isHwp3File(buffer)) return \"hwp3\"\n if (isZipFile(buffer)) return \"hwpx\"\n if (isOldHwpFile(buffer)) return \"hwp\"\n if (isPdfFile(buffer)) return \"pdf\"\n if (isHwpmlFile(buffer)) return \"hwpml\"\n return \"unknown\"\n}\n\n/**\n * OLE2 컨테이너 내부 스트림 기반 포맷 세분화.\n * HWP 5.x, XLS 모두 OLE2이므로 스트림 이름으로 구분.\n * - \"Workbook\" 또는 \"Book\" → 'xls'\n * - 그 외 (FileHeader 등) → 'hwp'\n */\nexport function detectOle2Format(buffer: ArrayBuffer): \"hwp\" | \"xls\" | \"unknown\" {\n try {\n const cfb = parseLenientCfb(Buffer.from(buffer))\n const names = cfb.entries().map(e => e.name)\n if (names.includes(\"Workbook\") || names.includes(\"Book\")) return \"xls\"\n if (names.includes(\"FileHeader\")) return \"hwp\"\n // FileHeader 없어도 BodyText/DocInfo 있으면 hwp\n if (names.some(n => n === \"DocInfo\" || n.startsWith(\"Section\"))) return \"hwp\"\n return \"unknown\"\n } catch {\n return \"unknown\"\n }\n}\n\n/**\n * ZIP 내부 구조 기반 포맷 세분화.\n * HWPX, XLSX, DOCX 모두 ZIP이므로 내부 파일로 구분.\n */\nexport async function detectZipFormat(buffer: ArrayBuffer): Promise<\"hwpx\" | \"xlsx\" | \"docx\" | \"unknown\"> {\n try {\n const zip = await JSZip.loadAsync(buffer)\n // XLSX: xl/workbook.xml\n if (zip.file(\"xl/workbook.xml\")) return \"xlsx\"\n // DOCX: word/document.xml\n if (zip.file(\"word/document.xml\")) return \"docx\"\n // HWPX: Contents/ 또는 content.hpf 또는 mimetype\n if (zip.file(\"Contents/content.hpf\") || zip.file(\"mimetype\")) return \"hwpx\"\n // 기타 ZIP 내에 section 파일이 있으면 HWPX로 추정\n const hasSection = Object.keys(zip.files).some(f => f.startsWith(\"Contents/\"))\n if (hasSection) return \"hwpx\"\n return \"unknown\"\n } catch {\n return \"unknown\"\n }\n}\n","/**\n * Lenient CFB (Compound File Binary / OLE2) 파서.\n *\n * 표준 cfb 모듈이 FAT 검증 실패로 거부하는 손상된 HWP 파일을 열기 위한 폴백.\n * 직접 헤더/FAT/디렉토리를 파싱하여 스트림 데이터를 추출.\n *\n * 참조: rhwp (MIT) src/parser/cfb_reader.rs (LenientCfbReader)\n * 참조: MS-CFB spec (https://learn.microsoft.com/en-us/openspecs/windows_protocols/ms-cfb)\n */\n\nimport { decompressStream } from \"./record.js\"\n\n// ── 상수 ──\n\nconst CFB_MAGIC = Buffer.from([0xd0, 0xcf, 0x11, 0xe0, 0xa1, 0xb1, 0x1a, 0xe1])\nconst END_OF_CHAIN = 0xfffffffe\nconst FREE_SECT = 0xffffffff\n\n/** 순환 감지용 최대 체인 길이 */\nconst MAX_CHAIN_LENGTH = 1_000_000\n/** 최대 디렉토리 엔트리 수 */\nconst MAX_DIR_ENTRIES = 100_000\n/** 최대 스트림 크기 (100MB) */\nconst MAX_STREAM_SIZE = 100 * 1024 * 1024\n\n// ── 디렉토리 엔트리 ──\n\ninterface DirEntry {\n name: string\n type: number // 0=unknown, 1=storage, 2=stream, 5=root\n startSector: number\n size: number\n}\n\n// ── CFB 컨테이너 ──\n\nexport interface LenientCfbContainer {\n /** 이름 기반 스트림 탐색 */\n findStream(path: string): Buffer | null\n /** 디렉토리 엔트리 목록 */\n entries(): DirEntry[]\n}\n\n// ── 구현 ──\n\nexport function parseLenientCfb(data: Buffer): LenientCfbContainer {\n if (data.length < 512) throw new Error(\"CFB 파일이 너무 짧습니다 (최소 512바이트)\")\n if (!data.subarray(0, 8).equals(CFB_MAGIC)) throw new Error(\"CFB 매직 바이트 불일치\")\n\n // ── 헤더 파싱 ──\n\n const sectorSizeShift = data.readUInt16LE(30)\n if (sectorSizeShift < 7 || sectorSizeShift > 16) throw new Error(\"유효하지 않은 섹터 크기 시프트: \" + sectorSizeShift)\n const sectorSize = 1 << sectorSizeShift // 보통 512\n const miniSectorSizeShift = data.readUInt16LE(32)\n if (miniSectorSizeShift > 16) throw new Error(\"유효하지 않은 미니 섹터 크기 시프트: \" + miniSectorSizeShift)\n const miniSectorSize = 1 << miniSectorSizeShift // 보통 64\n\n const headerFatSectorCount = data.readUInt32LE(44)\n if (headerFatSectorCount > 10000) throw new Error(\"FAT 섹터 수가 너무 많습니다: \" + headerFatSectorCount)\n // 실 파일 크기 sanity — FAT 엔트리는 파일 내 실존 섹터 수를 넘을 수 없다\n // (헤더 카운트 뻥튀기로 인한 fatTable 할당 증폭 방지: ~130KB 파일이 655MB 할당하던 버그)\n const maxRealSectors = Math.ceil(Math.max(0, data.length - 512) / sectorSize)\n const maxFatSectors = Math.max(1, Math.ceil(maxRealSectors / (sectorSize / 4)))\n const fatSectorCount = Math.min(headerFatSectorCount, maxFatSectors)\n const firstDirSector = data.readUInt32LE(48)\n const miniStreamCutoff = data.readUInt32LE(56) // 보통 4096\n const firstMiniFatSector = data.readUInt32LE(60)\n const miniFatSectorCount = data.readUInt32LE(64)\n const firstDifatSector = data.readUInt32LE(68)\n const difatSectorCount = data.readUInt32LE(72)\n\n // ── 유틸 ──\n\n function sectorOffset(id: number): number {\n return 512 + id * sectorSize\n }\n\n function readSectorData(id: number): Buffer {\n const off = sectorOffset(id)\n if (off + sectorSize > data.length) return Buffer.alloc(0)\n return data.subarray(off, off + sectorSize)\n }\n\n // ── DIFAT → FAT 섹터 목록 ──\n\n const fatSectors: number[] = []\n\n // 헤더 내 DIFAT (최대 109개)\n for (let i = 0; i < 109 && fatSectors.length < fatSectorCount; i++) {\n const sid = data.readUInt32LE(76 + i * 4)\n if (sid === FREE_SECT || sid === END_OF_CHAIN) break\n fatSectors.push(sid)\n }\n\n // 추가 DIFAT 섹터 체인\n let difatSector = firstDifatSector\n const visitedDifat = new Set<number>()\n for (let d = 0; d < difatSectorCount && difatSector !== END_OF_CHAIN && difatSector !== FREE_SECT; d++) {\n if (visitedDifat.has(difatSector)) break\n visitedDifat.add(difatSector)\n\n const buf = readSectorData(difatSector)\n if (buf.length < sectorSize) break // 파일 범위 밖 DIFAT 섹터(빈 버퍼) — readUInt32LE RangeError 방지, lenient 중단\n const entriesPerSector = (sectorSize / 4) - 1 // 마지막 4바이트는 다음 DIFAT 포인터\n for (let i = 0; i < entriesPerSector && fatSectors.length < fatSectorCount; i++) {\n const sid = buf.readUInt32LE(i * 4)\n if (sid === FREE_SECT || sid === END_OF_CHAIN) continue\n fatSectors.push(sid)\n }\n difatSector = buf.readUInt32LE(entriesPerSector * 4)\n }\n\n // ── FAT 테이블 구축 ──\n\n const entriesPerFatSector = sectorSize / 4\n const fatTable = new Uint32Array(fatSectors.length * entriesPerFatSector)\n\n for (let fi = 0; fi < fatSectors.length; fi++) {\n const buf = readSectorData(fatSectors[fi])\n for (let i = 0; i < entriesPerFatSector; i++) {\n fatTable[fi * entriesPerFatSector + i] = i * 4 + 3 < buf.length\n ? buf.readUInt32LE(i * 4)\n : FREE_SECT\n }\n }\n\n // ── 체인 리더 (순환 방지) ──\n\n function readChain(startSector: number, maxBytes: number): Buffer {\n if (startSector === END_OF_CHAIN || startSector === FREE_SECT) return Buffer.alloc(0)\n if (maxBytes > MAX_STREAM_SIZE) throw new Error(\"스트림이 너무 큽니다\")\n\n const chunks: Buffer[] = []\n let current = startSector\n let totalRead = 0\n const visited = new Set<number>()\n\n while (current !== END_OF_CHAIN && current !== FREE_SECT && totalRead < maxBytes) {\n if (visited.has(current)) break // 순환 감지\n if (visited.size > MAX_CHAIN_LENGTH) break\n visited.add(current)\n\n const buf = readSectorData(current)\n const remaining = maxBytes - totalRead\n chunks.push(remaining < sectorSize ? buf.subarray(0, remaining) : buf)\n totalRead += Math.min(buf.length, remaining)\n\n current = current < fatTable.length ? fatTable[current] : END_OF_CHAIN\n }\n\n return Buffer.concat(chunks)\n }\n\n // ── Mini-FAT 테이블 ──\n\n let miniFatTable: Uint32Array | null = null\n\n function getMiniFatTable(): Uint32Array {\n if (miniFatTable) return miniFatTable\n\n if (miniFatSectorCount === 0 || firstMiniFatSector === END_OF_CHAIN) {\n miniFatTable = new Uint32Array(0)\n return miniFatTable\n }\n\n const miniFatData = readChain(firstMiniFatSector, miniFatSectorCount * sectorSize)\n const entries = miniFatData.length / 4\n miniFatTable = new Uint32Array(entries)\n for (let i = 0; i < entries; i++) {\n miniFatTable[i] = miniFatData.readUInt32LE(i * 4)\n }\n return miniFatTable\n }\n\n // ── 디렉토리 엔트리 파싱 ──\n\n const dirData = readChain(firstDirSector, MAX_DIR_ENTRIES * 128)\n const dirEntries: DirEntry[] = []\n\n for (let offset = 0; offset + 128 <= dirData.length && dirEntries.length < MAX_DIR_ENTRIES; offset += 128) {\n const nameLen = dirData.readUInt16LE(offset + 64) // 바이트 수 (null 포함)\n if (nameLen <= 0 || nameLen > 64) {\n dirEntries.push({ name: \"\", type: 0, startSector: 0, size: 0 })\n continue\n }\n\n const nameBytes = nameLen - 2 // null terminator 제외\n const name = nameBytes > 0\n ? dirData.subarray(offset, offset + nameBytes).toString(\"utf16le\")\n : \"\"\n\n const type = dirData[offset + 66]\n const startSector = dirData.readUInt32LE(offset + 116)\n // CFBv3에서는 size가 u32 (offset 120), v4에서는 u64\n const size = dirData.readUInt32LE(offset + 120)\n\n dirEntries.push({ name, type, startSector, size })\n }\n\n // ── Root 엔트리에서 미니 스트림 추출 ──\n\n let miniStreamData: Buffer | null = null\n\n function getMiniStream(): Buffer {\n if (miniStreamData) return miniStreamData\n const root = dirEntries[0]\n if (!root || root.type !== 5) {\n miniStreamData = Buffer.alloc(0)\n return miniStreamData\n }\n miniStreamData = readChain(root.startSector, root.size || MAX_STREAM_SIZE)\n return miniStreamData\n }\n\n // ── 미니 스트림에서 읽기 ──\n\n function readMiniStream(startSector: number, size: number): Buffer {\n const mft = getMiniFatTable()\n const ms = getMiniStream()\n if (mft.length === 0 || ms.length === 0) return Buffer.alloc(0)\n\n const chunks: Buffer[] = []\n let current = startSector\n let totalRead = 0\n const visited = new Set<number>()\n\n while (current !== END_OF_CHAIN && current !== FREE_SECT && totalRead < size) {\n if (visited.has(current)) break\n if (visited.size > MAX_CHAIN_LENGTH) break\n visited.add(current)\n\n const off = current * miniSectorSize\n const remaining = size - totalRead\n const chunkSize = Math.min(miniSectorSize, remaining)\n if (off + chunkSize <= ms.length) {\n chunks.push(ms.subarray(off, off + chunkSize))\n }\n totalRead += chunkSize\n\n current = current < mft.length ? mft[current] : END_OF_CHAIN\n }\n\n return Buffer.concat(chunks)\n }\n\n // ── 스트림 읽기 (일반/미니 자동 분기) ──\n\n function readStreamData(entry: DirEntry): Buffer {\n if (entry.size === 0) return Buffer.alloc(0)\n if (entry.size < miniStreamCutoff) {\n const miniResult = readMiniStream(entry.startSector, entry.size)\n // 미니스트림이 비어있으면 일반 체인으로 폴백 (lenient)\n if (miniResult.length > 0) return miniResult\n }\n return readChain(entry.startSector, entry.size)\n }\n\n // ── 경로 기반 탐색 ──\n\n // 전체 경로 맵 구축 (간이: 이름 기반 flat lookup)\n // HWP 파일의 디렉토리 구조는 보통 1~2 depth이므로 이름 매칭으로 충분\n function findEntryByPath(path: string): DirEntry | null {\n // \"/FileHeader\" → \"FileHeader\"\n // \"/BodyText/Section0\" → path component matching\n const parts = path.replace(/^\\//, \"\").split(\"/\")\n\n if (parts.length === 1) {\n // 단일 이름 매칭\n return dirEntries.find(e => e.name === parts[0] && e.type === 2) ?? null\n }\n\n // 2-depth: storage/stream\n // HWP 구조: Root/BodyText/Section0, Root/DocInfo, Root/BinData/BIN0001 등\n const storageName = parts[0]\n const streamName = parts.slice(1).join(\"/\")\n\n // 디렉토리 구조 대신 이름 패턴으로 찾기 (lenient)\n for (const e of dirEntries) {\n if (e.type === 2 && e.name === streamName) {\n // 부모 확인은 생략 (lenient) — 중복 이름 시 첫 번째 반환\n return e\n }\n }\n\n // 정확한 이름이 아닌 경우 (ViewText/Section0 등)\n const lastPart = parts[parts.length - 1]\n return dirEntries.find(e => e.type === 2 && e.name === lastPart) ?? null\n }\n\n // ── 공개 API ──\n\n return {\n findStream(path: string): Buffer | null {\n // \\005 prefix 처리 (SummaryInformation)\n const normalized = path.replace(/^\\//, \"\")\n const entry = findEntryByPath(normalized)\n if (!entry || entry.type !== 2) return null\n const stream = readStreamData(entry)\n return stream.length > 0 ? stream : null\n },\n\n entries(): DirEntry[] {\n return dirEntries.filter(e => e.type === 2) // stream만\n },\n }\n}\n"],"mappings":";;;AAEA,OAAO,WAAW;;;ACYlB,IAAM,YAAY,OAAO,KAAK,CAAC,KAAM,KAAM,IAAM,KAAM,KAAM,KAAM,IAAM,GAAI,CAAC;AAC9E,IAAM,eAAe;AACrB,IAAM,YAAY;AAGlB,IAAM,mBAAmB;AAEzB,IAAM,kBAAkB;AAExB,IAAM,kBAAkB,MAAM,OAAO;AAsB9B,SAAS,gBAAgB,MAAmC;AACjE,MAAI,KAAK,SAAS,IAAK,OAAM,IAAI,MAAM,mGAA6B;AACpE,MAAI,CAAC,KAAK,SAAS,GAAG,CAAC,EAAE,OAAO,SAAS,EAAG,OAAM,IAAI,MAAM,wDAAgB;AAI5E,QAAM,kBAAkB,KAAK,aAAa,EAAE;AAC5C,MAAI,kBAAkB,KAAK,kBAAkB,GAAI,OAAM,IAAI,MAAM,yFAAwB,eAAe;AACxG,QAAM,aAAa,KAAK;AACxB,QAAM,sBAAsB,KAAK,aAAa,EAAE;AAChD,MAAI,sBAAsB,GAAI,OAAM,IAAI,MAAM,sGAA2B,mBAAmB;AAC5F,QAAM,iBAAiB,KAAK;AAE5B,QAAM,uBAAuB,KAAK,aAAa,EAAE;AACjD,MAAI,uBAAuB,IAAO,OAAM,IAAI,MAAM,0EAAwB,oBAAoB;AAG9F,QAAM,iBAAiB,KAAK,KAAK,KAAK,IAAI,GAAG,KAAK,SAAS,GAAG,IAAI,UAAU;AAC5E,QAAM,gBAAgB,KAAK,IAAI,GAAG,KAAK,KAAK,kBAAkB,aAAa,EAAE,CAAC;AAC9E,QAAM,iBAAiB,KAAK,IAAI,sBAAsB,aAAa;AACnE,QAAM,iBAAiB,KAAK,aAAa,EAAE;AAC3C,QAAM,mBAAmB,KAAK,aAAa,EAAE;AAC7C,QAAM,qBAAqB,KAAK,aAAa,EAAE;AAC/C,QAAM,qBAAqB,KAAK,aAAa,EAAE;AAC/C,QAAM,mBAAmB,KAAK,aAAa,EAAE;AAC7C,QAAM,mBAAmB,KAAK,aAAa,EAAE;AAI7C,WAAS,aAAa,IAAoB;AACxC,WAAO,MAAM,KAAK;AAAA,EACpB;AAEA,WAAS,eAAe,IAAoB;AAC1C,UAAM,MAAM,aAAa,EAAE;AAC3B,QAAI,MAAM,aAAa,KAAK,OAAQ,QAAO,OAAO,MAAM,CAAC;AACzD,WAAO,KAAK,SAAS,KAAK,MAAM,UAAU;AAAA,EAC5C;AAIA,QAAM,aAAuB,CAAC;AAG9B,WAAS,IAAI,GAAG,IAAI,OAAO,WAAW,SAAS,gBAAgB,KAAK;AAClE,UAAM,MAAM,KAAK,aAAa,KAAK,IAAI,CAAC;AACxC,QAAI,QAAQ,aAAa,QAAQ,aAAc;AAC/C,eAAW,KAAK,GAAG;AAAA,EACrB;AAGA,MAAI,cAAc;AAClB,QAAM,eAAe,oBAAI,IAAY;AACrC,WAAS,IAAI,GAAG,IAAI,oBAAoB,gBAAgB,gBAAgB,gBAAgB,WAAW,KAAK;AACtG,QAAI,aAAa,IAAI,WAAW,EAAG;AACnC,iBAAa,IAAI,WAAW;AAE5B,UAAM,MAAM,eAAe,WAAW;AACtC,QAAI,IAAI,SAAS,WAAY;AAC7B,UAAM,mBAAoB,aAAa,IAAK;AAC5C,aAAS,IAAI,GAAG,IAAI,oBAAoB,WAAW,SAAS,gBAAgB,KAAK;AAC/E,YAAM,MAAM,IAAI,aAAa,IAAI,CAAC;AAClC,UAAI,QAAQ,aAAa,QAAQ,aAAc;AAC/C,iBAAW,KAAK,GAAG;AAAA,IACrB;AACA,kBAAc,IAAI,aAAa,mBAAmB,CAAC;AAAA,EACrD;AAIA,QAAM,sBAAsB,aAAa;AACzC,QAAM,WAAW,IAAI,YAAY,WAAW,SAAS,mBAAmB;AAExE,WAAS,KAAK,GAAG,KAAK,WAAW,QAAQ,MAAM;AAC7C,UAAM,MAAM,eAAe,WAAW,EAAE,CAAC;AACzC,aAAS,IAAI,GAAG,IAAI,qBAAqB,KAAK;AAC5C,eAAS,KAAK,sBAAsB,CAAC,IAAI,IAAI,IAAI,IAAI,IAAI,SACrD,IAAI,aAAa,IAAI,CAAC,IACtB;AAAA,IACN;AAAA,EACF;AAIA,WAAS,UAAU,aAAqB,UAA0B;AAChE,QAAI,gBAAgB,gBAAgB,gBAAgB,UAAW,QAAO,OAAO,MAAM,CAAC;AACpF,QAAI,WAAW,gBAAiB,OAAM,IAAI,MAAM,0DAAa;AAE7D,UAAM,SAAmB,CAAC;AAC1B,QAAI,UAAU;AACd,QAAI,YAAY;AAChB,UAAM,UAAU,oBAAI,IAAY;AAEhC,WAAO,YAAY,gBAAgB,YAAY,aAAa,YAAY,UAAU;AAChF,UAAI,QAAQ,IAAI,OAAO,EAAG;AAC1B,UAAI,QAAQ,OAAO,iBAAkB;AACrC,cAAQ,IAAI,OAAO;AAEnB,YAAM,MAAM,eAAe,OAAO;AAClC,YAAM,YAAY,WAAW;AAC7B,aAAO,KAAK,YAAY,aAAa,IAAI,SAAS,GAAG,SAAS,IAAI,GAAG;AACrE,mBAAa,KAAK,IAAI,IAAI,QAAQ,SAAS;AAE3C,gBAAU,UAAU,SAAS,SAAS,SAAS,OAAO,IAAI;AAAA,IAC5D;AAEA,WAAO,OAAO,OAAO,MAAM;AAAA,EAC7B;AAIA,MAAI,eAAmC;AAEvC,WAAS,kBAA+B;AACtC,QAAI,aAAc,QAAO;AAEzB,QAAI,uBAAuB,KAAK,uBAAuB,cAAc;AACnE,qBAAe,IAAI,YAAY,CAAC;AAChC,aAAO;AAAA,IACT;AAEA,UAAM,cAAc,UAAU,oBAAoB,qBAAqB,UAAU;AACjF,UAAM,UAAU,YAAY,SAAS;AACrC,mBAAe,IAAI,YAAY,OAAO;AACtC,aAAS,IAAI,GAAG,IAAI,SAAS,KAAK;AAChC,mBAAa,CAAC,IAAI,YAAY,aAAa,IAAI,CAAC;AAAA,IAClD;AACA,WAAO;AAAA,EACT;AAIA,QAAM,UAAU,UAAU,gBAAgB,kBAAkB,GAAG;AAC/D,QAAM,aAAyB,CAAC;AAEhC,WAAS,SAAS,GAAG,SAAS,OAAO,QAAQ,UAAU,WAAW,SAAS,iBAAiB,UAAU,KAAK;AACzG,UAAM,UAAU,QAAQ,aAAa,SAAS,EAAE;AAChD,QAAI,WAAW,KAAK,UAAU,IAAI;AAChC,iBAAW,KAAK,EAAE,MAAM,IAAI,MAAM,GAAG,aAAa,GAAG,MAAM,EAAE,CAAC;AAC9D;AAAA,IACF;AAEA,UAAM,YAAY,UAAU;AAC5B,UAAM,OAAO,YAAY,IACrB,QAAQ,SAAS,QAAQ,SAAS,SAAS,EAAE,SAAS,SAAS,IAC/D;AAEJ,UAAM,OAAO,QAAQ,SAAS,EAAE;AAChC,UAAM,cAAc,QAAQ,aAAa,SAAS,GAAG;AAErD,UAAM,OAAO,QAAQ,aAAa,SAAS,GAAG;AAE9C,eAAW,KAAK,EAAE,MAAM,MAAM,aAAa,KAAK,CAAC;AAAA,EACnD;AAIA,MAAI,iBAAgC;AAEpC,WAAS,gBAAwB;AAC/B,QAAI,eAAgB,QAAO;AAC3B,UAAM,OAAO,WAAW,CAAC;AACzB,QAAI,CAAC,QAAQ,KAAK,SAAS,GAAG;AAC5B,uBAAiB,OAAO,MAAM,CAAC;AAC/B,aAAO;AAAA,IACT;AACA,qBAAiB,UAAU,KAAK,aAAa,KAAK,QAAQ,eAAe;AACzE,WAAO;AAAA,EACT;AAIA,WAAS,eAAe,aAAqB,MAAsB;AACjE,UAAM,MAAM,gBAAgB;AAC5B,UAAM,KAAK,cAAc;AACzB,QAAI,IAAI,WAAW,KAAK,GAAG,WAAW,EAAG,QAAO,OAAO,MAAM,CAAC;AAE9D,UAAM,SAAmB,CAAC;AAC1B,QAAI,UAAU;AACd,QAAI,YAAY;AAChB,UAAM,UAAU,oBAAI,IAAY;AAEhC,WAAO,YAAY,gBAAgB,YAAY,aAAa,YAAY,MAAM;AAC5E,UAAI,QAAQ,IAAI,OAAO,EAAG;AAC1B,UAAI,QAAQ,OAAO,iBAAkB;AACrC,cAAQ,IAAI,OAAO;AAEnB,YAAM,MAAM,UAAU;AACtB,YAAM,YAAY,OAAO;AACzB,YAAM,YAAY,KAAK,IAAI,gBAAgB,SAAS;AACpD,UAAI,MAAM,aAAa,GAAG,QAAQ;AAChC,eAAO,KAAK,GAAG,SAAS,KAAK,MAAM,SAAS,CAAC;AAAA,MAC/C;AACA,mBAAa;AAEb,gBAAU,UAAU,IAAI,SAAS,IAAI,OAAO,IAAI;AAAA,IAClD;AAEA,WAAO,OAAO,OAAO,MAAM;AAAA,EAC7B;AAIA,WAAS,eAAe,OAAyB;AAC/C,QAAI,MAAM,SAAS,EAAG,QAAO,OAAO,MAAM,CAAC;AAC3C,QAAI,MAAM,OAAO,kBAAkB;AACjC,YAAM,aAAa,eAAe,MAAM,aAAa,MAAM,IAAI;AAE/D,UAAI,WAAW,SAAS,EAAG,QAAO;AAAA,IACpC;AACA,WAAO,UAAU,MAAM,aAAa,MAAM,IAAI;AAAA,EAChD;AAMA,WAAS,gBAAgB,MAA+B;AAGtD,UAAM,QAAQ,KAAK,QAAQ,OAAO,EAAE,EAAE,MAAM,GAAG;AAE/C,QAAI,MAAM,WAAW,GAAG;AAEtB,aAAO,WAAW,KAAK,OAAK,EAAE,SAAS,MAAM,CAAC,KAAK,EAAE,SAAS,CAAC,KAAK;AAAA,IACtE;AAIA,UAAM,cAAc,MAAM,CAAC;AAC3B,UAAM,aAAa,MAAM,MAAM,CAAC,EAAE,KAAK,GAAG;AAG1C,eAAW,KAAK,YAAY;AAC1B,UAAI,EAAE,SAAS,KAAK,EAAE,SAAS,YAAY;AAEzC,eAAO;AAAA,MACT;AAAA,IACF;AAGA,UAAM,WAAW,MAAM,MAAM,SAAS,CAAC;AACvC,WAAO,WAAW,KAAK,OAAK,EAAE,SAAS,KAAK,EAAE,SAAS,QAAQ,KAAK;AAAA,EACtE;AAIA,SAAO;AAAA,IACL,WAAW,MAA6B;AAEtC,YAAM,aAAa,KAAK,QAAQ,OAAO,EAAE;AACzC,YAAM,QAAQ,gBAAgB,UAAU;AACxC,UAAI,CAAC,SAAS,MAAM,SAAS,EAAG,QAAO;AACvC,YAAM,SAAS,eAAe,KAAK;AACnC,aAAO,OAAO,SAAS,IAAI,SAAS;AAAA,IACtC;AAAA,IAEA,UAAsB;AACpB,aAAO,WAAW,OAAO,OAAK,EAAE,SAAS,CAAC;AAAA,IAC5C;AAAA,EACF;AACF;;;AD3SA,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;AAMA,IAAM,cAAc,IAAI,YAAY,EAAE,OAAO,yBAAyB;AAC/D,SAAS,WAAW,QAA8B;AACvD,MAAI,OAAO,aAAa,YAAY,OAAQ,QAAO;AACnD,QAAM,OAAO,IAAI,WAAW,QAAQ,GAAG,YAAY,MAAM;AACzD,WAAS,IAAI,GAAG,IAAI,YAAY,QAAQ,KAAK;AAC3C,QAAI,KAAK,CAAC,MAAM,YAAY,CAAC,EAAG,QAAO;AAAA,EACzC;AACA,SAAO;AACT;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,YAAY,QAA8B;AACxD,QAAM,QAAQ,IAAI,WAAW,QAAQ,GAAG,KAAK,IAAI,KAAK,OAAO,UAAU,CAAC;AACxE,QAAM,OAAO,IAAI,YAAY,SAAS,EAAE,OAAO,MAAM,CAAC,EAAE,OAAO,KAAK,EAAE,QAAQ,WAAW,EAAE;AAC3F,SAAO,KAAK,UAAU,EAAE,WAAW,OAAO,KAAK,KAAK,SAAS,QAAQ;AACvE;AAGO,SAAS,aAAa,QAA+B;AAC1D,MAAI,OAAO,aAAa,EAAG,QAAO;AAClC,MAAI,WAAW,MAAM,EAAG,QAAO;AAC/B,MAAI,UAAU,MAAM,EAAG,QAAO;AAC9B,MAAI,aAAa,MAAM,EAAG,QAAO;AACjC,MAAI,UAAU,MAAM,EAAG,QAAO;AAC9B,MAAI,YAAY,MAAM,EAAG,QAAO;AAChC,SAAO;AACT;AAQO,SAAS,iBAAiB,QAAgD;AAC/E,MAAI;AACF,UAAM,MAAM,gBAAgB,OAAO,KAAK,MAAM,CAAC;AAC/C,UAAM,QAAQ,IAAI,QAAQ,EAAE,IAAI,OAAK,EAAE,IAAI;AAC3C,QAAI,MAAM,SAAS,UAAU,KAAK,MAAM,SAAS,MAAM,EAAG,QAAO;AACjE,QAAI,MAAM,SAAS,YAAY,EAAG,QAAO;AAEzC,QAAI,MAAM,KAAK,OAAK,MAAM,aAAa,EAAE,WAAW,SAAS,CAAC,EAAG,QAAO;AACxE,WAAO;AAAA,EACT,QAAQ;AACN,WAAO;AAAA,EACT;AACF;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
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
#!/usr/bin/env node
|
|
2
2
|
import {
|
|
3
3
|
parseFormatProfileJson
|
|
4
|
-
} from "./chunk-
|
|
4
|
+
} from "./chunk-WO52HVQJ.js";
|
|
5
5
|
import {
|
|
6
6
|
BODY_FONTS,
|
|
7
7
|
BULLET2_CHARS,
|
|
@@ -13,6 +13,7 @@ import {
|
|
|
13
13
|
extractFormFields,
|
|
14
14
|
fillFormFields,
|
|
15
15
|
fillHwpx,
|
|
16
|
+
fillWithUniqueGuard,
|
|
16
17
|
gongmunLintWarnings,
|
|
17
18
|
hwpxToProfile,
|
|
18
19
|
incompatibleGongmunWarnings,
|
|
@@ -20,36 +21,43 @@ import {
|
|
|
20
21
|
markdownToHwpx,
|
|
21
22
|
parse,
|
|
22
23
|
unknownFontWarnings
|
|
23
|
-
} from "./chunk-
|
|
24
|
-
import
|
|
25
|
-
blocksToMarkdown
|
|
26
|
-
} from "./chunk-UEIYETCQ.js";
|
|
24
|
+
} from "./chunk-L2XQQTOY.js";
|
|
25
|
+
import "./chunk-UOO7LSDG.js";
|
|
27
26
|
import {
|
|
28
27
|
detectFormat,
|
|
29
28
|
detectZipFormat
|
|
30
|
-
} from "./chunk-
|
|
29
|
+
} from "./chunk-YOO6ET6M.js";
|
|
31
30
|
import "./chunk-MOL7MDBG.js";
|
|
32
|
-
import "./chunk-
|
|
33
|
-
import "./chunk-
|
|
34
|
-
import "./chunk-
|
|
31
|
+
import "./chunk-AX2R5Q2N.js";
|
|
32
|
+
import "./chunk-DZIXKL7E.js";
|
|
33
|
+
import "./chunk-F2ZU3IZG.js";
|
|
34
|
+
import {
|
|
35
|
+
blocksToMarkdown
|
|
36
|
+
} from "./chunk-SSTK6IKK.js";
|
|
37
|
+
import "./chunk-37HJHCPA.js";
|
|
38
|
+
import "./chunk-GQVSHGG4.js";
|
|
35
39
|
import {
|
|
36
40
|
VERSION,
|
|
37
41
|
sanitizeError,
|
|
38
42
|
toArrayBuffer
|
|
39
|
-
} from "./chunk-
|
|
43
|
+
} from "./chunk-O5VS7RIR.js";
|
|
40
44
|
|
|
41
45
|
// src/cli.ts
|
|
42
46
|
import { readFileSync, writeFileSync, mkdirSync, statSync } from "fs";
|
|
43
47
|
import { basename, dirname, resolve, extname } from "path";
|
|
44
48
|
import { Command } from "commander";
|
|
45
49
|
var program = new Command();
|
|
46
|
-
program.name("kordoc").description("\uBAA8\uB450 \uD30C\uC2F1\uD574\uBC84\uB9AC\uACA0\uB2E4 \u2014 HWP, HWPX, PDF, XLSX, DOCX \u2192 Markdown").version(VERSION).argument("<files...>", "\uBCC0\uD658\uD560 \uD30C\uC77C \uACBD\uB85C (HWP, HWPX, PDF, XLSX, DOCX)").option("-o, --output <path>", "\uCD9C\uB825 \uD30C\uC77C \uACBD\uB85C (\uB2E8\uC77C \uD30C\uC77C \uC2DC)").option("-d, --out-dir <dir>", "\uCD9C\uB825 \uB514\uB809\uD1A0\uB9AC (\uB2E4\uC911 \uD30C\uC77C \uC2DC)").option("-p, --pages <range>", "\uD398\uC774\uC9C0/\uC139\uC158 \uBC94\uC704 (\uC608: 1-3, 1,3,5)").option("--format <type>", "\uCD9C\uB825 \uD615\uC2DD: markdown (\uAE30\uBCF8) \
|
|
47
|
-
const validFormats = ["markdown", "json"];
|
|
50
|
+
program.name("kordoc").description("\uBAA8\uB450 \uD30C\uC2F1\uD574\uBC84\uB9AC\uACA0\uB2E4 \u2014 HWP, HWPX, PDF, XLSX, DOCX \u2192 Markdown").version(VERSION).argument("<files...>", "\uBCC0\uD658\uD560 \uD30C\uC77C \uACBD\uB85C (HWP, HWPX, PDF, XLSX, DOCX)").option("-o, --output <path>", "\uCD9C\uB825 \uD30C\uC77C \uACBD\uB85C (\uB2E8\uC77C \uD30C\uC77C \uC2DC)").option("-d, --out-dir <dir>", "\uCD9C\uB825 \uB514\uB809\uD1A0\uB9AC (\uB2E4\uC911 \uD30C\uC77C \uC2DC)").option("-p, --pages <range>", "\uD398\uC774\uC9C0/\uC139\uC158 \uBC94\uC704 (\uC608: 1-3, 1,3,5)").option("--format <type>", "\uCD9C\uB825 \uD615\uC2DD: markdown (\uAE30\uBCF8), json, chunks (RAG\uC6A9 \uAD6C\uC870 \uCCAD\uD06C JSON \u2014 \uD5E4\uB529\xB7\uAC1C\uC870\uC2DD \uC704\uACC4 breadcrumb + \uD45C \uB3C5\uB9BD \uCCAD\uD06C)", "markdown").option("--no-header-footer", "PDF \uBA38\uB9AC\uAE00/\uBC14\uB2E5\uAE00 \uC790\uB3D9 \uC81C\uAC70 \uB044\uAE30 (\uAE30\uBCF8: \uC81C\uAC70\uD568)").option("--formula-ocr", "PDF \uC218\uC2DD OCR \uD65C\uC131\uD654 (MFD+MFR ONNX, \uCCAB \uC0AC\uC6A9 \uC2DC \uBAA8\uB378 ~155MB \uC790\uB3D9 \uB2E4\uC6B4\uB85C\uB4DC)").option("--dedupe-headers", "HWP5 \uB808\uC774\uC544\uC6C3 \uD45C \uD398\uC774\uC9C0 \uBC18\uBCF5 \uB7EC\uB2DD \uD5E4\uB354 \uC911\uBCF5 \uC81C\uAC70 (\uAE30\uBCF8 off \u2014 \uBD99\uC784\uBCC4 \uC7AC\uBC88\uD638 \uC624\uC0AD\uC81C \uC8FC\uC758)").option("--keep-empty-cols", "\uD45C \uC624\uB978\uCABD \uB05D \uBE48 \uC5F4(\uC11C\uC2DD \uC785\uB825\uB780) \uBCF4\uC874 (#47, \uAE30\uBCF8 off: \uD6C4\uD589 \uBE48 \uC5F4 \uD2B8\uB9BC)").option("--inline-images", "\uC774\uBBF8\uC9C0\uB97C base64 data URI \uB85C \uB9C8\uD06C\uB2E4\uC6B4\uC5D0 \uC778\uB77C\uC778 (BMP\u2192PNG \uC555\uCD95, HWP5 \uC804\uC6A9 \u2014 \uC778\uB77C\uC778\uB41C \uACBD\uC6B0\uB9CC \uD30C\uC77C \uBBF8\uC800\uC7A5, \uADF8 \uC678 \uD3EC\uB9F7\uC740 \uC800\uC7A5 \uC720\uC9C0)").option("--silent", "\uC9C4\uD589 \uBA54\uC2DC\uC9C0 \uC228\uAE30\uAE30").action(async (files, opts) => {
|
|
51
|
+
const validFormats = ["markdown", "json", "chunks"];
|
|
48
52
|
if (!validFormats.includes(opts.format)) {
|
|
49
|
-
process.stderr.write(`[kordoc] \uC9C0\uC6D0\uD558\uC9C0 \uC54A\uB294 \uD615\uC2DD: ${opts.format} (markdown
|
|
53
|
+
process.stderr.write(`[kordoc] \uC9C0\uC6D0\uD558\uC9C0 \uC54A\uB294 \uD615\uC2DD: ${opts.format} (markdown, json, chunks)
|
|
50
54
|
`);
|
|
51
55
|
process.exit(1);
|
|
52
56
|
}
|
|
57
|
+
if (opts.output && files.length > 1) {
|
|
58
|
+
process.stderr.write(`[kordoc] \u26A0\uFE0F -o/--output \uC740 \uB2E8\uC77C \uD30C\uC77C \uC804\uC6A9\uC774\uB77C \uBB34\uC2DC\uB429\uB2C8\uB2E4 \u2014 \uB2E4\uC911 \uD30C\uC77C\uC740 -d/--out-dir \uB97C \uC0AC\uC6A9\uD558\uC138\uC694
|
|
59
|
+
`);
|
|
60
|
+
}
|
|
53
61
|
for (let fi = 0; fi < files.length; fi++) {
|
|
54
62
|
const filePath = files[fi];
|
|
55
63
|
const absPath = resolve(filePath);
|
|
@@ -75,6 +83,7 @@ program.name("kordoc").description("\uBAA8\uB450 \uD30C\uC2F1\uD574\uBC84\uB9AC\
|
|
|
75
83
|
if (opts.headerFooter === false) parseOptions.removeHeaderFooter = false;
|
|
76
84
|
if (opts.formulaOcr) parseOptions.formulaOcr = true;
|
|
77
85
|
if (opts.dedupeHeaders) parseOptions.dedupeRunningHeaders = true;
|
|
86
|
+
if (opts.keepEmptyCols) parseOptions.keepTrailingEmptyCols = true;
|
|
78
87
|
if (opts.inlineImages) parseOptions.inlineImages = true;
|
|
79
88
|
if (!opts.silent) {
|
|
80
89
|
parseOptions.onProgress = (current, total) => {
|
|
@@ -97,11 +106,19 @@ program.name("kordoc").description("\uBAA8\uB450 \uD30C\uC2F1\uD574\uBC84\uB9AC\
|
|
|
97
106
|
if (opts.outDir && result.images?.length && !imagesInlined) {
|
|
98
107
|
markdown = markdown.replace(/!\[image\]\(image_/g, ".replace(/(<img\b[^>]*\bsrc=")image_/g, "$1images/image_");
|
|
99
108
|
}
|
|
100
|
-
|
|
101
|
-
|
|
102
|
-
|
|
103
|
-
|
|
104
|
-
|
|
109
|
+
let output;
|
|
110
|
+
if (opts.format === "json") {
|
|
111
|
+
output = JSON.stringify(
|
|
112
|
+
result,
|
|
113
|
+
(_key, value) => value instanceof Uint8Array ? Buffer.from(value).toString("base64") : value,
|
|
114
|
+
2
|
|
115
|
+
);
|
|
116
|
+
} else if (opts.format === "chunks") {
|
|
117
|
+
const { blocksToChunks } = await import("./chunks-WVMGF7JL.js");
|
|
118
|
+
output = JSON.stringify(blocksToChunks(result.blocks), null, 2);
|
|
119
|
+
} else {
|
|
120
|
+
output = markdown;
|
|
121
|
+
}
|
|
105
122
|
const saveImages = (dir) => {
|
|
106
123
|
if (!result.images?.length || imagesInlined) return;
|
|
107
124
|
const imgDir = resolve(dir, "images");
|
|
@@ -119,7 +136,7 @@ program.name("kordoc").description("\uBAA8\uB450 \uD30C\uC2F1\uD574\uBC84\uB9AC\
|
|
|
119
136
|
saveImages(resolve(opts.output, ".."));
|
|
120
137
|
} else if (opts.outDir) {
|
|
121
138
|
mkdirSync(opts.outDir, { recursive: true });
|
|
122
|
-
const outExt = opts.format === "json" ? ".json" : ".md";
|
|
139
|
+
const outExt = opts.format === "json" ? ".json" : opts.format === "chunks" ? ".chunks.json" : ".md";
|
|
123
140
|
const outPath = resolve(opts.outDir, fileName.replace(/\.[^.]+$/, outExt));
|
|
124
141
|
writeFileSync(outPath, output, "utf-8");
|
|
125
142
|
if (!opts.silent) process.stderr.write(` \u2192 ${outPath}
|
|
@@ -144,7 +161,7 @@ program.command("watch <dir>").description("\uB514\uB809\uD1A0\uB9AC \uAC10\uC2D
|
|
|
144
161
|
if (command.getOptionValueSource("format") === "default" && program.getOptionValueSource("format") === "cli") {
|
|
145
162
|
opts.format = rootOpts.format;
|
|
146
163
|
}
|
|
147
|
-
const { watchDirectory } = await import("./watch-
|
|
164
|
+
const { watchDirectory } = await import("./watch-SFHXZALC.js");
|
|
148
165
|
await watchDirectory({
|
|
149
166
|
dir,
|
|
150
167
|
outDir: opts.outDir,
|
|
@@ -154,7 +171,7 @@ program.command("watch <dir>").description("\uB514\uB809\uD1A0\uB9AC \uAC10\uC2D
|
|
|
154
171
|
silent: opts.silent
|
|
155
172
|
});
|
|
156
173
|
});
|
|
157
|
-
program.command("fill <template>").description("\uC11C\uC2DD \uBB38\uC11C\uC758 \uBE48\uCE78\uC744 \uCC44\uC6CC\uC11C \uCD9C\uB825 \u2014 kordoc fill \uC2E0\uCCAD\uC11C.hwpx -f '\uC131\uBA85=\uD64D\uAE38\uB3D9,\uC804\uD654=010-1234-5678' -o \uACB0\uACFC.hwpx").option("-f, --fields <pairs>", "\uCC44\uC6B8 \uD544\uB4DC (key=value \uC27C\uD45C \uAD6C\uBD84 \uB610\uB294 JSON)").option("-j, --json <path>", "\uCC44\uC6B8 \uD544\uB4DC JSON \uD30C\uC77C \uACBD\uB85C").option("-o, --output <path>", "\uCD9C\uB825 \uD30C\uC77C \uACBD\uB85C (\uD655\uC7A5\uC790\uB85C \uD3EC\uB9F7 \uACB0\uC815: .md, .hwpx)").option("--format <type>", "\uCD9C\uB825 \uD3EC\uB9F7: hwpx-preserve (\uAE30\uBCF8, \uC6D0\uBCF8 \uC2A4\uD0C0\uC77C \uBCF4\uC874), hwpx, markdown", "hwpx-preserve").option("--dry-run", "\uCC44\uC6B0\uC9C0 \uC54A\uACE0 \uC11C\uC2DD \uD544\uB4DC \uBAA9\uB85D\uB9CC \uCD9C\uB825").option("--silent", "\uC9C4\uD589 \uBA54\uC2DC\uC9C0 \uC228\uAE30\uAE30").action(async (template, opts, command) => {
|
|
174
|
+
program.command("fill <template>").description("\uC11C\uC2DD \uBB38\uC11C\uC758 \uBE48\uCE78\uC744 \uCC44\uC6CC\uC11C \uCD9C\uB825 \u2014 kordoc fill \uC2E0\uCCAD\uC11C.hwpx -f '\uC131\uBA85=\uD64D\uAE38\uB3D9,\uC804\uD654=010-1234-5678' -o \uACB0\uACFC.hwpx").option("-f, --fields <pairs>", "\uCC44\uC6B8 \uD544\uB4DC (key=value \uC27C\uD45C \uAD6C\uBD84 \uB610\uB294 JSON)").option("-j, --json <path>", "\uCC44\uC6B8 \uD544\uB4DC JSON \uD30C\uC77C \uACBD\uB85C").option("-o, --output <path>", "\uCD9C\uB825 \uD30C\uC77C \uACBD\uB85C (\uD655\uC7A5\uC790\uB85C \uD3EC\uB9F7 \uACB0\uC815: .md, .hwpx)").option("--format <type>", "\uCD9C\uB825 \uD3EC\uB9F7: hwpx-preserve (\uAE30\uBCF8, \uC6D0\uBCF8 \uC2A4\uD0C0\uC77C \uBCF4\uC874), hwpx, markdown", "hwpx-preserve").option("--formats <json>", `\uD544\uB4DC\uBCC4 \uAC12 \uC11C\uC2DD JSON (\uB77C\uBCA8\u2192\uD3EC\uB9F7) \u2014 \uC608: '{"\uB0A0\uC9DC":"yy.mm.dd","\uC8FC\uBBFC\uB4F1\uB85D\uBC88\uD638":"rrn:masked"}'`).option("--require-unique", "\uD55C \uD0A4\uAC00 \uC11C\uC2DD\uC758 2\uACF3 \uC774\uC0C1\uC5D0 \uB9E4\uCE6D\uB418\uBA74 \uCC44\uC6B0\uC9C0 \uC54A\uACE0 \uAC70\uBD80 (\uBC18\uBCF5 \uB77C\uBCA8 \uC591\uC2DD \uC624\uC5FC \uBC29\uC9C0)").option("--mask", "\uCC44\uC6B4 \uAC12 \uBBF8\uB178\uCD9C \u2014 \uCD9C\uB825 \uD30C\uC77C \uC5C6\uC774 markdown\uC744 stdout\uC73C\uB85C \uB0BC \uB54C \uBCF8\uBB38 \uB300\uC2E0 \uC548\uB0B4\uB9CC \uD45C\uC2DC").option("--dry-run", "\uCC44\uC6B0\uC9C0 \uC54A\uACE0 \uC11C\uC2DD \uD544\uB4DC \uBAA9\uB85D\uB9CC \uCD9C\uB825").option("--silent", "\uC9C4\uD589 \uBA54\uC2DC\uC9C0 \uC228\uAE30\uAE30").action(async (template, opts, command) => {
|
|
158
175
|
try {
|
|
159
176
|
const rootOpts = program.opts();
|
|
160
177
|
opts.output ??= rootOpts.output;
|
|
@@ -174,7 +191,7 @@ program.command("fill <template>").description("\uC11C\uC2DD \uBB38\uC11C\uC758
|
|
|
174
191
|
if (!opts.silent) process.stderr.write(`[kordoc] ${basename(absPath)} \uD30C\uC2F1 \uC911...
|
|
175
192
|
`);
|
|
176
193
|
if (opts.dryRun) {
|
|
177
|
-
const result2 = await parse(arrayBuffer);
|
|
194
|
+
const result2 = await parse(arrayBuffer, { keepTrailingEmptyCols: true });
|
|
178
195
|
if (!result2.success) {
|
|
179
196
|
process.stderr.write(`[kordoc] \uD30C\uC2F1 \uC2E4\uD328: ${result2.error}
|
|
180
197
|
`);
|
|
@@ -214,11 +231,32 @@ program.command("fill <template>").description("\uC11C\uC2DD \uBB38\uC11C\uC758
|
|
|
214
231
|
`);
|
|
215
232
|
process.exit(1);
|
|
216
233
|
}
|
|
234
|
+
let inputs = values;
|
|
235
|
+
if (opts.formats) {
|
|
236
|
+
let formatMap;
|
|
237
|
+
try {
|
|
238
|
+
formatMap = JSON.parse(String(opts.formats));
|
|
239
|
+
} catch {
|
|
240
|
+
process.stderr.write(`[kordoc] --formats \uB294 JSON \uAC1D\uCCB4\uC5EC\uC57C \uD569\uB2C8\uB2E4 (\uB77C\uBCA8\u2192\uD3EC\uB9F7)
|
|
241
|
+
`);
|
|
242
|
+
process.exit(1);
|
|
243
|
+
}
|
|
244
|
+
inputs = Object.fromEntries(Object.entries(values).map(([k, v]) => {
|
|
245
|
+
const format = formatMap[k];
|
|
246
|
+
return [k, format ? { value: v, format } : v];
|
|
247
|
+
}));
|
|
248
|
+
}
|
|
217
249
|
let outputFormat = opts.format;
|
|
218
250
|
if (opts.output) {
|
|
219
251
|
const ext = extname(opts.output).toLowerCase();
|
|
252
|
+
const explicitFormat = command.getOptionValueSource("format") === "cli" || program.getOptionValueSource("format") === "cli";
|
|
253
|
+
const before = outputFormat;
|
|
220
254
|
if (ext === ".hwpx") outputFormat = outputFormat === "markdown" ? "hwpx-preserve" : outputFormat;
|
|
221
255
|
else if (ext === ".md") outputFormat = "markdown";
|
|
256
|
+
if (explicitFormat && before !== outputFormat) {
|
|
257
|
+
process.stderr.write(`[kordoc] \u26A0\uFE0F --format ${before} \uAC00 \uCD9C\uB825 \uD655\uC7A5\uC790(${ext})\uC640 \uCDA9\uB3CC\uD569\uB2C8\uB2E4 \u2014 \uD655\uC7A5\uC790 \uAE30\uC900 ${outputFormat} \uB85C \uC9C4\uD589
|
|
258
|
+
`);
|
|
259
|
+
}
|
|
222
260
|
}
|
|
223
261
|
if (outputFormat === "hwpx-preserve") {
|
|
224
262
|
const format = detectFormat(arrayBuffer);
|
|
@@ -232,10 +270,14 @@ program.command("fill <template>").description("\uC11C\uC2DD \uBB38\uC11C\uC758
|
|
|
232
270
|
`);
|
|
233
271
|
outputFormat = "hwpx";
|
|
234
272
|
} else {
|
|
235
|
-
const hwpxResult = await fillHwpx(arrayBuffer,
|
|
273
|
+
const hwpxResult = opts.requireUnique ? await fillWithUniqueGuard(inputs, (vals, blocked) => fillHwpx(arrayBuffer, vals, blocked)) : { ...await fillHwpx(arrayBuffer, inputs), rejected: [] };
|
|
236
274
|
if (!opts.silent) {
|
|
237
275
|
process.stderr.write(`[kordoc] ${hwpxResult.filled.length}\uAC1C \uD544\uB4DC \uCC44\uC6C0 (\uC6D0\uBCF8 \uC2A4\uD0C0\uC77C \uBCF4\uC874)
|
|
238
276
|
`);
|
|
277
|
+
if (hwpxResult.rejected.length > 0) {
|
|
278
|
+
process.stderr.write(`[kordoc] \u26A0\uFE0F \uBAA8\uD638 \uB77C\uBCA8 \uAC70\uBD80(2\uACF3+ \uB9E4\uCE6D): ${hwpxResult.rejected.join(", ")}
|
|
279
|
+
`);
|
|
280
|
+
}
|
|
239
281
|
if (hwpxResult.unmatched.length > 0) {
|
|
240
282
|
process.stderr.write(`[kordoc] \u26A0\uFE0F \uB9E4\uCE6D \uC2E4\uD328: ${hwpxResult.unmatched.join(", ")}
|
|
241
283
|
`);
|
|
@@ -252,7 +294,7 @@ program.command("fill <template>").description("\uC11C\uC2DD \uBB38\uC11C\uC758
|
|
|
252
294
|
return;
|
|
253
295
|
}
|
|
254
296
|
}
|
|
255
|
-
const result = await parse(arrayBuffer);
|
|
297
|
+
const result = await parse(arrayBuffer, { keepTrailingEmptyCols: true });
|
|
256
298
|
if (!result.success) {
|
|
257
299
|
process.stderr.write(`[kordoc] \uD30C\uC2F1 \uC2E4\uD328: ${result.error}
|
|
258
300
|
`);
|
|
@@ -263,10 +305,14 @@ program.command("fill <template>").description("\uC11C\uC2DD \uBB38\uC11C\uC758
|
|
|
263
305
|
process.stderr.write(`[kordoc] \uC11C\uC2DD \uD544\uB4DC ${formInfo.fields.length}\uAC1C \uAC10\uC9C0 (\uD655\uC2E0\uB3C4 ${(formInfo.confidence * 100).toFixed(0)}%)
|
|
264
306
|
`);
|
|
265
307
|
}
|
|
266
|
-
const fillResult = fillFormFields(result.blocks,
|
|
308
|
+
const fillResult = opts.requireUnique ? await fillWithUniqueGuard(inputs, (vals, blocked) => fillFormFields(result.blocks, vals, blocked)) : { ...fillFormFields(result.blocks, inputs), rejected: [] };
|
|
267
309
|
if (!opts.silent) {
|
|
268
310
|
process.stderr.write(`[kordoc] ${fillResult.filled.length}\uAC1C \uD544\uB4DC \uCC44\uC6C0
|
|
269
311
|
`);
|
|
312
|
+
if (fillResult.rejected.length > 0) {
|
|
313
|
+
process.stderr.write(`[kordoc] \u26A0\uFE0F \uBAA8\uD638 \uB77C\uBCA8 \uAC70\uBD80(2\uACF3+ \uB9E4\uCE6D): ${fillResult.rejected.join(", ")}
|
|
314
|
+
`);
|
|
315
|
+
}
|
|
270
316
|
if (fillResult.unmatched.length > 0) {
|
|
271
317
|
process.stderr.write(`[kordoc] \u26A0\uFE0F \uB9E4\uCE6D \uC2E4\uD328: ${fillResult.unmatched.join(", ")}
|
|
272
318
|
`);
|
|
@@ -288,6 +334,9 @@ program.command("fill <template>").description("\uC11C\uC2DD \uBB38\uC11C\uC758
|
|
|
288
334
|
mkdirSync(dirname(resolve(opts.output)), { recursive: true });
|
|
289
335
|
writeFileSync(resolve(opts.output), markdown, "utf-8");
|
|
290
336
|
if (!opts.silent) process.stderr.write(`[kordoc] \u2192 ${resolve(opts.output)}
|
|
337
|
+
`);
|
|
338
|
+
} else if (opts.mask) {
|
|
339
|
+
process.stdout.write(`\u26A0\uFE0F --mask \uD65C\uC131 \u2014 \uAC1C\uC778\uC815\uBCF4 \uB178\uCD9C \uBC29\uC9C0\uB97C \uC704\uD574 \uBCF8\uBB38\uC744 \uCD9C\uB825\uD558\uC9C0 \uC54A\uC2B5\uB2C8\uB2E4. -o \uB85C \uD30C\uC77C \uC800\uC7A5 \uD6C4 \uD655\uC778\uD558\uC138\uC694.
|
|
291
340
|
`);
|
|
292
341
|
} else {
|
|
293
342
|
process.stdout.write(markdown + "\n");
|
|
@@ -301,7 +350,7 @@ program.command("fill <template>").description("\uC11C\uC2DD \uBB38\uC11C\uC758
|
|
|
301
350
|
});
|
|
302
351
|
program.command("seal <file>").description('\uB3C4\uC7A5/\uC11C\uBA85 \uC774\uBBF8\uC9C0\uB97C \uC575\uCEE4 \uBB38\uAD6C \uC704\uC5D0 \uBD80\uC720 \uBC30\uCE58 (\uD45C/\uD398\uC774\uC9C0 \uBD88\uD655\uC7A5) \u2014 kordoc seal \uC2E0\uCCAD\uC11C.hwpx --image \uB3C4\uC7A5.png --anchor "(\uC778)" -o \uACB0\uACFC.hwpx').requiredOption("--image <path>", "\uB3C4\uC7A5/\uC11C\uBA85 \uC774\uBBF8\uC9C0 (\uD22C\uBA85 \uBC30\uACBD PNG \uAD8C\uC7A5)").option("--anchor <text>", "\uC575\uCEE4 \uBB38\uAD6C", "(\uC778)").option("-n, --occurrence <num>", "\uAC19\uC740 \uC575\uCEE4\uAC00 \uC5EC\uB7FF\uC77C \uB54C 0-based \uC120\uD0DD", "0").option("--size-mm <num>", "\uB3C4\uC7A5 \uD55C \uBCC0 \uD06C\uAE30 mm (\uAE30\uBCF8: \uC904\uB192\uC774\xD71.6, 7~18 \uD074\uB7A8\uD504)").option("--mode <mode>", "overlap(\uBB38\uAD6C \uC704 \uACB9\uCE68) | right(\uC624\uB978\uCABD \uC606) | auto", "auto").option("--dx <mm>", "x \uBBF8\uC138\uC870\uC815 mm", "0").option("--dy <mm>", "y \uBBF8\uC138\uC870\uC815 mm", "0").option("-o, --output <path>", "\uCD9C\uB825 \uACBD\uB85C (\uAE30\uBCF8: <\uC785\uB825>.sealed.hwpx)").option("--silent", "\uC9C4\uD589 \uBA54\uC2DC\uC9C0 \uC228\uAE30\uAE30").action(async (file, opts) => {
|
|
303
352
|
try {
|
|
304
|
-
const { placeSealHwpx, detectFormat: detectFormat2 } = await import("./-
|
|
353
|
+
const { placeSealHwpx, detectFormat: detectFormat2 } = await import("./-AS4IABL2.js");
|
|
305
354
|
const rootOpts = program.opts();
|
|
306
355
|
const output = opts.output ?? rootOpts.output;
|
|
307
356
|
const silent = opts.silent ?? rootOpts.silent;
|
|
@@ -377,9 +426,9 @@ program.command("seal <file>").description('\uB3C4\uC7A5/\uC11C\uBA85 \uC774\uBB
|
|
|
377
426
|
process.exit(1);
|
|
378
427
|
}
|
|
379
428
|
});
|
|
380
|
-
program.command("patch <original> <edited>").description("\uC11C\uC2DD \uBCF4\uC874 \uB77C\uC6B4\uB4DC\uD2B8\uB9BD \uD328\uCE58 \u2014 \uD3B8\uC9D1\uB41C \uB9C8\uD06C\uB2E4\uC6B4\uC744 \uC6D0\uBCF8 HWPX/HWP\uC5D0 in-place \uBC18\uC601 (kordoc patch \uC6D0\uBCF8.hwpx \uD3B8\uC9D1.md -o \uCD9C\uB825.hwpx)").option("-o, --output <path>", "\uCD9C\uB825 \uACBD\uB85C (\uAE30\uBCF8: <\uC6D0\uBCF8>.patched.hwpx|.hwp)").option("--no-verify", "\uD328\uCE58 \uD6C4 \uC7AC\uD30C\uC2F1 \uC790\uB3D9 \uAC80\uC99D \uC0DD\uB7B5").option("--silent", "\uC9C4\uD589 \uBA54\uC2DC\uC9C0 \uC228\uAE30\uAE30").action(async (original, edited, opts) => {
|
|
429
|
+
program.command("patch <original> <edited>").description("\uC11C\uC2DD \uBCF4\uC874 \uB77C\uC6B4\uB4DC\uD2B8\uB9BD \uD328\uCE58 \u2014 \uD3B8\uC9D1\uB41C \uB9C8\uD06C\uB2E4\uC6B4\uC744 \uC6D0\uBCF8 HWPX/HWP\uC5D0 in-place \uBC18\uC601 (kordoc patch \uC6D0\uBCF8.hwpx \uD3B8\uC9D1.md -o \uCD9C\uB825.hwpx). \uBBF8\uC801\uC6A9(skip) \uD3B8\uC9D1\uC774 \uC788\uC73C\uBA74 exit 2").option("-o, --output <path>", "\uCD9C\uB825 \uACBD\uB85C (\uAE30\uBCF8: <\uC6D0\uBCF8>.patched.hwpx|.hwp)").option("--no-verify", "\uD328\uCE58 \uD6C4 \uC7AC\uD30C\uC2F1 \uC790\uB3D9 \uAC80\uC99D \uC0DD\uB7B5").option("--silent", "\uC9C4\uD589 \uBA54\uC2DC\uC9C0 \uC228\uAE30\uAE30").action(async (original, edited, opts) => {
|
|
381
430
|
try {
|
|
382
|
-
const { patchHwpx, patchHwp, detectFormat: detectFormat2 } = await import("./-
|
|
431
|
+
const { patchHwpx, patchHwp, detectFormat: detectFormat2 } = await import("./-AS4IABL2.js");
|
|
383
432
|
const rootOpts = program.opts();
|
|
384
433
|
const output = opts.output ?? rootOpts.output;
|
|
385
434
|
const silent = opts.silent ?? rootOpts.silent;
|
|
@@ -420,7 +469,7 @@ program.command("patch <original> <edited>").description("\uC11C\uC2DD \uBCF4\uC
|
|
|
420
469
|
});
|
|
421
470
|
program.command("validate <file>").description("HWPX \uAD6C\uC870 \uAC80\uC99D \u2014 ZIP\xB7mimetype\xB7\uD544\uC218 \uD30C\uC77C\xB7XML \uC6F0\uD3FC\uB4DC\xB7secCnt\xB7manifest \uCC38\uC870 (\uD55C\uCEF4\uB3C5\uC2A4 \uAC70\uBD80 \uC694\uC778 \uC0AC\uC804 \uCC28\uB2E8)").option("--json", "\uACB0\uACFC\uB97C JSON\uC73C\uB85C stdout\uC5D0 \uCD9C\uB825").action(async (file, opts) => {
|
|
422
471
|
try {
|
|
423
|
-
const { validateHwpx } = await import("./-
|
|
472
|
+
const { validateHwpx } = await import("./-AS4IABL2.js");
|
|
424
473
|
const buf = new Uint8Array(readFileSync(resolve(file)));
|
|
425
474
|
const result = await validateHwpx(buf);
|
|
426
475
|
if (opts.json) {
|
|
@@ -584,10 +633,10 @@ program.command("lint <file>").description("\uACF5\uBB38\uC11C \uD45C\uAE30\uBC9
|
|
|
584
633
|
if (opts.json) {
|
|
585
634
|
process.stdout.write(JSON.stringify({ findings, summary: { total: findings.length, errors, ok: errors === 0 } }, null, 2) + "\n");
|
|
586
635
|
} else {
|
|
587
|
-
process.
|
|
636
|
+
process.stderr.write(`[kordoc] \uD45C\uAE30\uBC95 \uAC80\uC218: \uC704\uBC18 ${findings.length}\uAC74 (error ${errors}, warning ${findings.length - errors})
|
|
588
637
|
`);
|
|
589
638
|
for (const f of findings) {
|
|
590
|
-
process.
|
|
639
|
+
process.stderr.write(` L${f.line} [${f.severity}] ${f.rule}: "${f.match}" \u2014 ${f.message}${f.suggest ? ` \u2192 ${f.suggest}` : ""}
|
|
591
640
|
`);
|
|
592
641
|
}
|
|
593
642
|
}
|
|
@@ -598,12 +647,97 @@ program.command("lint <file>").description("\uACF5\uBB38\uC11C \uD45C\uAE30\uBC9
|
|
|
598
647
|
process.exit(1);
|
|
599
648
|
}
|
|
600
649
|
});
|
|
650
|
+
program.command("redact <files...>").description("\uAC1C\uC778\uC815\uBCF4 \uC11C\uC2DD \uBCF4\uC874 \uB9C8\uC2A4\uD0B9 \u2014 \uC8FC\uBBFC\uBC88\uD638\xB7\uC804\uD654\xB7\uC774\uBA54\uC77C\xB7\uCE74\uB4DC\xB7\uACC4\uC88C\uB97C \uD0D0\uC9C0\uD574 HWPX/HWP\uB294 \uC6D0\uBCF8 \uC11C\uC2DD \uADF8\uB300\uB85C patch, \uADF8 \uC678 \uD3EC\uB9F7\uC740 \uB9C8\uC2A4\uD0B9\uB41C \uB9C8\uD06C\uB2E4\uC6B4 \uCD9C\uB825. \uC790\uB3D9 \uAC80\uCD9C \uBCF4\uC870 \uB3C4\uAD6C\uC774\uBBC0\uB85C \uACB0\uACFC\uB294 \uBC18\uB4DC\uC2DC \uC0AC\uB78C\uC774 \uCD5C\uC885 \uD655\uC778\uD558\uC138\uC694 (\uC774\uBBF8\uC9C0 \uC548 \uD14D\uC2A4\uD2B8\uB294 \uD0D0\uC9C0 \uBD88\uAC00)").option("--rules <csv>", "\uC801\uC6A9 \uB8F0 (\uAE30\uBCF8: rrn,phone,email,card,account \u2014 passport,driver\uB294 opt-in)").option("--mask-char <ch>", "\uB9C8\uC2A4\uD06C \uBB38\uC790 1\uAE00\uC790 (\uAE30\uBCF8: \u25CF)").option("-o, --output <path>", "\uCD9C\uB825 \uACBD\uB85C (\uB2E8\uC77C \uD30C\uC77C \uC2DC)").option("-d, --out-dir <dir>", "\uCD9C\uB825 \uB514\uB809\uD1A0\uB9AC (\uB2E4\uC911 \uD30C\uC77C \uC2DC)").option("--dry-run", "\uD0D0\uC9C0 \uB9AC\uD3EC\uD2B8\uB9CC \uCD9C\uB825, \uD30C\uC77C \uBBF8\uC0DD\uC131").option("--json", "\uB9AC\uD3EC\uD2B8\uB97C JSON\uC73C\uB85C stdout \uCD9C\uB825").option("--silent", "\uC9C4\uD589 \uBA54\uC2DC\uC9C0 \uC228\uAE30\uAE30").action(async (files, opts) => {
|
|
651
|
+
const { redactMarkdown, DEFAULT_REDACT_RULES, patchHwpx, patchHwp } = await import("./-AS4IABL2.js");
|
|
652
|
+
const rootOpts = program.opts();
|
|
653
|
+
const output = opts.output ?? rootOpts.output;
|
|
654
|
+
const silent = opts.silent ?? rootOpts.silent;
|
|
655
|
+
const KNOWN_RULES = /* @__PURE__ */ new Set(["rrn", "phone", "email", "card", "account", "passport", "driver"]);
|
|
656
|
+
const rules = opts.rules ? String(opts.rules).split(",").map((r) => r.trim()).filter(Boolean) : [...DEFAULT_REDACT_RULES];
|
|
657
|
+
const badRule = rules.find((r) => !KNOWN_RULES.has(r));
|
|
658
|
+
if (badRule) {
|
|
659
|
+
process.stderr.write(`[kordoc] \uC54C \uC218 \uC5C6\uB294 \uB8F0: ${badRule} (\uD5C8\uC6A9: ${[...KNOWN_RULES].join(", ")})
|
|
660
|
+
`);
|
|
661
|
+
process.exit(1);
|
|
662
|
+
}
|
|
663
|
+
if (output && files.length > 1) {
|
|
664
|
+
process.stderr.write(`[kordoc] \u26A0\uFE0F -o/--output \uC740 \uB2E8\uC77C \uD30C\uC77C \uC804\uC6A9\uC774\uB77C \uBB34\uC2DC\uB429\uB2C8\uB2E4 \u2014 \uB2E4\uC911 \uD30C\uC77C\uC740 -d/--out-dir \uB97C \uC0AC\uC6A9\uD558\uC138\uC694
|
|
665
|
+
`);
|
|
666
|
+
}
|
|
667
|
+
const jsonReports = [];
|
|
668
|
+
for (const filePath of files) {
|
|
669
|
+
const absPath = resolve(filePath);
|
|
670
|
+
const fileName = basename(absPath);
|
|
671
|
+
try {
|
|
672
|
+
const buffer = readFileSync(absPath);
|
|
673
|
+
const arrayBuffer = toArrayBuffer(buffer);
|
|
674
|
+
const format = detectFormat(arrayBuffer);
|
|
675
|
+
const parsed = await parse(arrayBuffer, { filePath: absPath });
|
|
676
|
+
if (!parsed.success) {
|
|
677
|
+
process.stderr.write(`[kordoc] FAIL: ${fileName} \u2014 ${parsed.error}
|
|
678
|
+
`);
|
|
679
|
+
process.exitCode = 1;
|
|
680
|
+
continue;
|
|
681
|
+
}
|
|
682
|
+
const r = redactMarkdown(parsed.markdown, { rules, maskChar: opts.maskChar });
|
|
683
|
+
const byRule = /* @__PURE__ */ new Map();
|
|
684
|
+
for (const h of r.hits) byRule.set(h.rule, (byRule.get(h.rule) ?? 0) + 1);
|
|
685
|
+
const ruleSummary = [...byRule.entries()].map(([k, v]) => `${k} ${v}\uAC74`).join(", ") || "0\uAC74";
|
|
686
|
+
let outPath = null;
|
|
687
|
+
let patchNote = "";
|
|
688
|
+
if (!opts.dryRun && r.hits.length > 0) {
|
|
689
|
+
const patchable = format === "hwpx" || format === "hwp";
|
|
690
|
+
if (patchable) {
|
|
691
|
+
const original = new Uint8Array(arrayBuffer);
|
|
692
|
+
const result = format === "hwp" ? await patchHwp(original, r.text) : await patchHwpx(original, r.text);
|
|
693
|
+
if (!result.success || !result.data) {
|
|
694
|
+
process.stderr.write(`[kordoc] \uD328\uCE58 \uC2E4\uD328: ${fileName} \u2014 ${result.error ?? "\uC54C \uC218 \uC5C6\uB294 \uC624\uB958"}
|
|
695
|
+
`);
|
|
696
|
+
process.exitCode = 1;
|
|
697
|
+
continue;
|
|
698
|
+
}
|
|
699
|
+
const ext = format === "hwp" ? ".hwp" : ".hwpx";
|
|
700
|
+
outPath = resolve(
|
|
701
|
+
output && files.length === 1 ? output : resolve(opts.outDir ?? dirname(absPath), fileName.replace(/\.[^.]+$/, "") + ".redacted" + ext)
|
|
702
|
+
);
|
|
703
|
+
mkdirSync(dirname(outPath), { recursive: true });
|
|
704
|
+
writeFileSync(outPath, result.data);
|
|
705
|
+
if (result.skipped.length > 0) {
|
|
706
|
+
patchNote = ` (\u26A0\uFE0F \uBBF8\uC801\uC6A9 ${result.skipped.length}\uAC74 \u2014 \uD574\uB2F9 \uC704\uCE58\uB294 \uC6D0\uBB38 \uC794\uC874, \uC218\uB3D9 \uD655\uC778 \uD544\uC694)`;
|
|
707
|
+
process.exitCode = 2;
|
|
708
|
+
}
|
|
709
|
+
} else {
|
|
710
|
+
outPath = resolve(
|
|
711
|
+
output && files.length === 1 ? output : resolve(opts.outDir ?? dirname(absPath), fileName.replace(/\.[^.]+$/, "") + ".redacted.md")
|
|
712
|
+
);
|
|
713
|
+
mkdirSync(dirname(outPath), { recursive: true });
|
|
714
|
+
writeFileSync(outPath, r.text, "utf-8");
|
|
715
|
+
patchNote = ` (${format}\uB294 \uC11C\uC2DD \uBCF4\uC874 \uBBF8\uC9C0\uC6D0 \u2014 \uB9C8\uC2A4\uD0B9\uB41C \uB9C8\uD06C\uB2E4\uC6B4\uC73C\uB85C \uCD9C\uB825)`;
|
|
716
|
+
}
|
|
717
|
+
}
|
|
718
|
+
if (opts.json) {
|
|
719
|
+
jsonReports.push({ file: absPath, format, rules, hits: r.hits, output: outPath });
|
|
720
|
+
}
|
|
721
|
+
if (!silent) {
|
|
722
|
+
process.stderr.write(`[kordoc] ${fileName}: ${ruleSummary}${outPath ? ` \u2192 ${outPath}` : opts.dryRun ? " (dry-run)" : ""}${patchNote}
|
|
723
|
+
`);
|
|
724
|
+
for (const h of r.hits) process.stderr.write(` - [${h.rule}] ${h.masked}
|
|
725
|
+
`);
|
|
726
|
+
}
|
|
727
|
+
} catch (err) {
|
|
728
|
+
process.stderr.write(`[kordoc] ERROR: ${fileName} \u2014 ${sanitizeError(err)}
|
|
729
|
+
`);
|
|
730
|
+
process.exitCode = 1;
|
|
731
|
+
}
|
|
732
|
+
}
|
|
733
|
+
if (opts.json) process.stdout.write(JSON.stringify(files.length === 1 ? jsonReports[0] ?? null : jsonReports, null, 2) + "\n");
|
|
734
|
+
});
|
|
601
735
|
program.command("render <file>").description("\uB808\uC774\uC544\uC6C3 \uBCF4\uC874 \uB80C\uB354 \u2014 \uD55C\uCEF4 \uC800\uC7A5 HWPX\uC758 \uC870\uD310 \uCE90\uC2DC\uB97C SVG\uB85C (\uC804\uCCB4 \uD398\uC774\uC9C0 \uC138\uB85C \uC2A4\uD0DD) \u2014 kordoc render \uBB38\uC11C.hwpx -o \uBB38\uC11C.svg").option("-o, --output <path>", "\uCD9C\uB825 SVG \uACBD\uB85C (\uAE30\uBCF8: <\uC785\uB825>.svg)").option("--highlight <terms>", "\uAC80\uC0C9\uC5B4 \uD615\uAD11\uD39C (\uC27C\uD45C \uAD6C\uBD84)").option("--reflow", "\uC870\uD310 \uCE90\uC2DC \uC5C6\uB294 HWPX\uB3C4 \uC21C\uC218 TS \uC870\uD310\uC73C\uB85C \uB80C\uB354 (markdownToHwpx \uC0B0\uCD9C\uBB3C\xB7\uD3B8\uC9D1\uBCF8)").option("--reflow-mode <mode>", "reflow \uC904\uBC14\uAFC8 \uBAA8\uB4DC: keep(\uC5B4\uC808) | charAll(\uAE00\uC790)", "keep").option("--silent", "\uC9C4\uD589 \uBA54\uC2DC\uC9C0 \uC228\uAE30\uAE30").action(async (file, opts) => {
|
|
602
736
|
try {
|
|
603
737
|
const rootOpts = program.opts();
|
|
604
738
|
const output = opts.output ?? rootOpts.output;
|
|
605
739
|
const silent = opts.silent ?? rootOpts.silent;
|
|
606
|
-
const { renderHwpxToSvg } = await import("./render-
|
|
740
|
+
const { renderHwpxToSvg } = await import("./render-T7S6H6AN.js");
|
|
607
741
|
const absPath = resolve(file);
|
|
608
742
|
const buffer = readFileSync(absPath);
|
|
609
743
|
const highlights = opts.highlight ? String(opts.highlight).split(",") : void 0;
|
|
@@ -625,7 +759,7 @@ program.command("render <file>").description("\uB808\uC774\uC544\uC6C3 \uBCF4\uC
|
|
|
625
759
|
});
|
|
626
760
|
program.command("render-worker").description("persistent \uB80C\uB354 \uC6CC\uCEE4 \u2014 stdin NDJSON \uC694\uCCAD \u2192 \uC870\uD310 SVG \uD30C\uC77C \uCD9C\uB825 (\uD504\uB85C\uC138\uC2A4 \uC720\uC9C0, \uCF5C\uB4DC\uC2A4\uD0C0\uD2B8 \uC81C\uAC70)").action(async () => {
|
|
627
761
|
const { createInterface } = await import("readline");
|
|
628
|
-
const { renderHwpxToSvg } = await import("./render-
|
|
762
|
+
const { renderHwpxToSvg } = await import("./render-T7S6H6AN.js");
|
|
629
763
|
const rl = createInterface({ input: process.stdin });
|
|
630
764
|
const write = (o) => void process.stdout.write(JSON.stringify(o) + "\n");
|
|
631
765
|
write({ ready: true, version: VERSION });
|
|
@@ -666,10 +800,11 @@ program.command("render-worker").description("persistent \uB80C\uB354 \uC6CC\uCE
|
|
|
666
800
|
}
|
|
667
801
|
});
|
|
668
802
|
program.command("mcp").description("MCP \uC11C\uBC84 \uC2E4\uD589 (Claude / Cursor / Windsurf \uC5F0\uB3D9)").action(async () => {
|
|
669
|
-
await import("./mcp.js");
|
|
803
|
+
const { startMcpServer } = await import("./mcp.js");
|
|
804
|
+
await startMcpServer();
|
|
670
805
|
});
|
|
671
806
|
program.command("setup").description("\uB300\uD654\uD615 \uC124\uCE58 \uB9C8\uBC95\uC0AC \u2014 AI \uD074\uB77C\uC774\uC5B8\uD2B8 \uC790\uB3D9 \uB4F1\uB85D (Mac/Win/Linux)").action(async () => {
|
|
672
|
-
const { runSetup } = await import("./setup-
|
|
807
|
+
const { runSetup } = await import("./setup-Q2PRE7UA.js");
|
|
673
808
|
await runSetup();
|
|
674
809
|
});
|
|
675
810
|
program.command("check-formula-models").description("PDF \uC218\uC2DD OCR \uBAA8\uB378(MFD + MFR + tokenizer, ~155MB) \uC0C1\uD0DC \uD655\uC778 \u2014 \uC5C6\uAC70\uB098 SHA \uBD88\uC77C\uCE58\uBA74 \uB2E4\uC6B4\uB85C\uB4DC").option("--status-only", "\uC0C1\uD0DC\uB9CC JSON \uC73C\uB85C \uCD9C\uB825 (\uB2E4\uC6B4\uB85C\uB4DC \uC548 \uD568)").action(async (opts) => {
|