kordoc 4.22.18 → 4.23.0
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 +3 -2
- package/dist/{-OTAPIBUW.js → -YNDBG7XO.js} +17 -11
- package/dist/{chunk-HX24KLQN.js → chunk-2CHTPRDU.js} +2 -2
- package/dist/{chunk-N5QRS6VT.js → chunk-2EVBM5NZ.js} +2 -2
- package/dist/{chunk-VCGGP7SY.js → chunk-2URKNOOQ.js} +2 -2
- package/dist/{chunk-3GVPNEIG.js → chunk-4AI32TFY.js} +2 -2
- package/dist/{chunk-G4PPT5CR.js → chunk-4XLDFJGY.js} +6 -6
- package/dist/{chunk-B3Z2PY4R.cjs → chunk-5KLO56CJ.cjs} +2 -2
- package/dist/{chunk-B3Z2PY4R.cjs.map → chunk-5KLO56CJ.cjs.map} +1 -1
- package/dist/{chunk-3AVHW7UT.js → chunk-5NBUT7GX.js} +2 -2
- package/dist/{chunk-MW42GCQ4.js → chunk-67DVZL4W.js} +2 -2
- package/dist/{chunk-7QLKNWMN.js → chunk-6BUW4PJ3.js} +4 -4
- package/dist/{chunk-XOX5L7WN.js → chunk-6O2AUXFB.js} +2 -2
- package/dist/{chunk-WITGYMV5.js → chunk-A5HW2Z5T.js} +4 -4
- package/dist/{chunk-MKEBORZM.js → chunk-GZFL6UOS.js} +2 -2
- package/dist/{chunk-TLGOPNMC.cjs → chunk-I22NWH6W.cjs} +24 -24
- package/dist/{chunk-TLGOPNMC.cjs.map → chunk-I22NWH6W.cjs.map} +1 -1
- package/dist/{chunk-BXZW4Q5G.cjs → chunk-IOBVLL5A.cjs} +6 -6
- package/dist/{chunk-BXZW4Q5G.cjs.map → chunk-IOBVLL5A.cjs.map} +1 -1
- package/dist/{chunk-DKZZVFTK.cjs → chunk-KLVN3EW7.cjs} +3 -3
- package/dist/{chunk-DKZZVFTK.cjs.map → chunk-KLVN3EW7.cjs.map} +1 -1
- package/dist/{chunk-TLU4OKIO.js → chunk-LJSKKGWU.js} +2 -2
- package/dist/{chunk-NUQG356J.cjs → chunk-M6QZYQRH.cjs} +3 -3
- package/dist/{chunk-NUQG356J.cjs.map → chunk-M6QZYQRH.cjs.map} +1 -1
- package/dist/{chunk-RTFUKVOX.js → chunk-MA4NIAYO.js} +3 -3
- package/dist/{chunk-MI2YNEQJ.js → chunk-MSUBZT53.js} +4025 -2640
- package/dist/chunk-MSUBZT53.js.map +1 -0
- package/dist/{chunk-3YHUMMZ5.js → chunk-QE2XH2ZI.js} +8 -1
- package/dist/chunk-QE2XH2ZI.js.map +1 -0
- package/dist/{chunk-SJYHFKKB.js → chunk-QO4PT3NN.js} +2 -2
- package/dist/{chunk-XIDMSNU2.cjs → chunk-QXIZ5XSB.cjs} +23 -23
- package/dist/{chunk-XIDMSNU2.cjs.map → chunk-QXIZ5XSB.cjs.map} +1 -1
- package/dist/{chunk-DQBY4PQ4.js → chunk-S7B74SOM.js} +8 -6
- package/dist/{chunk-DQBY4PQ4.js.map → chunk-S7B74SOM.js.map} +1 -1
- package/dist/{chunk-JO5OR4F5.js → chunk-TFXWP5QI.js} +2 -2
- package/dist/{chunk-S2WH5IZ3.js → chunk-UIZYWW3J.js} +2 -2
- package/dist/{chunk-S2WH5IZ3.js.map → chunk-UIZYWW3J.js.map} +1 -1
- package/dist/{chunk-OWO3RVJY.js → chunk-VRIHNSYF.js} +2 -2
- package/dist/{chunk-M7SCUHXE.js → chunk-W67KQWMU.js} +4 -4
- package/dist/{chunk-NV3WEN4C.js → chunk-XCSWST2A.js} +3 -3
- package/dist/{chunk-VROCP4X4.js → chunk-Y3LLNEU3.js} +2 -2
- package/dist/{chunk-VROCP4X4.js.map → chunk-Y3LLNEU3.js.map} +1 -1
- package/dist/{chunk-6LTGCEGP.js → chunk-YFCE7J37.js} +2 -2
- package/dist/chunks-LX2EPPSD.js +10 -0
- package/dist/cli.js +148 -141
- package/dist/cli.js.map +1 -1
- package/dist/{formula-E5G3A3NZ.js → formula-JASN5ELL.js} +3 -3
- package/dist/{formula-2ISHDHXF.cjs → formula-Z7JPTFAV.cjs} +9 -9
- package/dist/{formula-2ISHDHXF.cjs.map → formula-Z7JPTFAV.cjs.map} +1 -1
- package/dist/{formula-WHYRNHRE.js → formula-ZULPRKJR.js} +4 -4
- package/dist/{image-ocr-5WJQITNQ.js → image-ocr-2ZWU6O5O.js} +6 -6
- package/dist/{image-ocr-6J7B5UVA.js → image-ocr-IYFAHFQH.js} +9 -9
- package/dist/{image-ocr-MRTNIUZQ.cjs → image-ocr-MJVZFMXW.cjs} +17 -17
- package/dist/{image-ocr-MRTNIUZQ.cjs.map → image-ocr-MJVZFMXW.cjs.map} +1 -1
- package/dist/index.cjs +3318 -1931
- package/dist/index.cjs.map +1 -1
- package/dist/index.d.cts +114 -3
- package/dist/index.d.ts +114 -3
- package/dist/index.js +2734 -1347
- package/dist/index.js.map +1 -1
- package/dist/mcp.js +134 -32
- package/dist/mcp.js.map +1 -1
- package/dist/{model-bundle-CNNDBCIQ.js → model-bundle-FD5ORLT4.js} +5 -5
- package/dist/{models-PQYMCKFR.js → models-CNXDF4BB.js} +5 -5
- package/dist/{parse-worker-v2-Z3W53OUZ.js → parse-worker-v2-GZIAKU6M.js} +12 -12
- package/dist/{parser-2YUGVORR.cjs → parser-MTUCDPDX.cjs} +157 -157
- package/dist/{parser-2YUGVORR.cjs.map → parser-MTUCDPDX.cjs.map} +1 -1
- package/dist/{parser-UYBCCGY4.js → parser-OQ4FLNBE.js} +12 -12
- package/dist/{parser-YHUWM4KF.js → parser-WTOPH3C2.js} +9 -9
- package/dist/pdf-ocr-EW34T34R.cjs +31 -0
- package/dist/{pdf-ocr-6Q34QQ7A.cjs.map → pdf-ocr-EW34T34R.cjs.map} +1 -1
- package/dist/{pdf-ocr-6JSBUWUO.js → pdf-ocr-IBZRT65M.js} +9 -9
- package/dist/{pdf-ocr-DE7PYWN7.js → pdf-ocr-V346MK77.js} +6 -6
- package/dist/{profile-io-DCZ4DINU.js → profile-io-UFTSKMWU.js} +3 -3
- package/dist/{rasterize-6XD2LLEN.js → rasterize-SXIF5J5K.js} +3 -3
- package/dist/{redact-doc-2BLB3IOP.js → redact-doc-P6XQ6B6U.js} +11 -11
- package/dist/{render-YPZMJSZL.js → render-QW56QMUE.js} +7 -7
- package/dist/seal-HMXHWFBA.js +10 -0
- package/dist/{setup-GUE2OUWB.js → setup-RIZUPKAE.js} +3 -3
- package/dist/visual-X7OFXY4M.js +21 -0
- package/dist/{watch-EILA6XGX.js → watch-TAHHXY7Z.js} +12 -12
- package/package.json +1 -1
- package/THIRD_PARTY/hwp-auto-docfit.LICENSE +0 -23
- package/dist/chunk-3YHUMMZ5.js.map +0 -1
- package/dist/chunk-MI2YNEQJ.js.map +0 -1
- package/dist/chunks-GMADIKNS.js +0 -10
- package/dist/pdf-ocr-6Q34QQ7A.cjs +0 -31
- package/dist/seal-32KIG7OS.js +0 -10
- package/dist/visual-Y32AKOM4.js +0 -21
- /package/dist/{-OTAPIBUW.js.map → -YNDBG7XO.js.map} +0 -0
- /package/dist/{chunk-HX24KLQN.js.map → chunk-2CHTPRDU.js.map} +0 -0
- /package/dist/{chunk-N5QRS6VT.js.map → chunk-2EVBM5NZ.js.map} +0 -0
- /package/dist/{chunk-VCGGP7SY.js.map → chunk-2URKNOOQ.js.map} +0 -0
- /package/dist/{chunk-3GVPNEIG.js.map → chunk-4AI32TFY.js.map} +0 -0
- /package/dist/{chunk-G4PPT5CR.js.map → chunk-4XLDFJGY.js.map} +0 -0
- /package/dist/{chunk-3AVHW7UT.js.map → chunk-5NBUT7GX.js.map} +0 -0
- /package/dist/{chunk-MW42GCQ4.js.map → chunk-67DVZL4W.js.map} +0 -0
- /package/dist/{chunk-7QLKNWMN.js.map → chunk-6BUW4PJ3.js.map} +0 -0
- /package/dist/{chunk-XOX5L7WN.js.map → chunk-6O2AUXFB.js.map} +0 -0
- /package/dist/{chunk-WITGYMV5.js.map → chunk-A5HW2Z5T.js.map} +0 -0
- /package/dist/{chunk-MKEBORZM.js.map → chunk-GZFL6UOS.js.map} +0 -0
- /package/dist/{chunk-TLU4OKIO.js.map → chunk-LJSKKGWU.js.map} +0 -0
- /package/dist/{chunk-RTFUKVOX.js.map → chunk-MA4NIAYO.js.map} +0 -0
- /package/dist/{chunk-SJYHFKKB.js.map → chunk-QO4PT3NN.js.map} +0 -0
- /package/dist/{chunk-JO5OR4F5.js.map → chunk-TFXWP5QI.js.map} +0 -0
- /package/dist/{chunk-OWO3RVJY.js.map → chunk-VRIHNSYF.js.map} +0 -0
- /package/dist/{chunk-M7SCUHXE.js.map → chunk-W67KQWMU.js.map} +0 -0
- /package/dist/{chunk-NV3WEN4C.js.map → chunk-XCSWST2A.js.map} +0 -0
- /package/dist/{chunk-6LTGCEGP.js.map → chunk-YFCE7J37.js.map} +0 -0
- /package/dist/{chunks-GMADIKNS.js.map → chunks-LX2EPPSD.js.map} +0 -0
- /package/dist/{formula-E5G3A3NZ.js.map → formula-JASN5ELL.js.map} +0 -0
- /package/dist/{formula-WHYRNHRE.js.map → formula-ZULPRKJR.js.map} +0 -0
- /package/dist/{image-ocr-5WJQITNQ.js.map → image-ocr-2ZWU6O5O.js.map} +0 -0
- /package/dist/{image-ocr-6J7B5UVA.js.map → image-ocr-IYFAHFQH.js.map} +0 -0
- /package/dist/{model-bundle-CNNDBCIQ.js.map → model-bundle-FD5ORLT4.js.map} +0 -0
- /package/dist/{models-PQYMCKFR.js.map → models-CNXDF4BB.js.map} +0 -0
- /package/dist/{parse-worker-v2-Z3W53OUZ.js.map → parse-worker-v2-GZIAKU6M.js.map} +0 -0
- /package/dist/{parser-UYBCCGY4.js.map → parser-OQ4FLNBE.js.map} +0 -0
- /package/dist/{parser-YHUWM4KF.js.map → parser-WTOPH3C2.js.map} +0 -0
- /package/dist/{pdf-ocr-6JSBUWUO.js.map → pdf-ocr-IBZRT65M.js.map} +0 -0
- /package/dist/{pdf-ocr-DE7PYWN7.js.map → pdf-ocr-V346MK77.js.map} +0 -0
- /package/dist/{profile-io-DCZ4DINU.js.map → profile-io-UFTSKMWU.js.map} +0 -0
- /package/dist/{rasterize-6XD2LLEN.js.map → rasterize-SXIF5J5K.js.map} +0 -0
- /package/dist/{redact-doc-2BLB3IOP.js.map → redact-doc-P6XQ6B6U.js.map} +0 -0
- /package/dist/{render-YPZMJSZL.js.map → render-QW56QMUE.js.map} +0 -0
- /package/dist/{seal-32KIG7OS.js.map → seal-HMXHWFBA.js.map} +0 -0
- /package/dist/{setup-GUE2OUWB.js.map → setup-RIZUPKAE.js.map} +0 -0
- /package/dist/{visual-Y32AKOM4.js.map → visual-X7OFXY4M.js.map} +0 -0
- /package/dist/{watch-EILA6XGX.js.map → watch-TAHHXY7Z.js.map} +0 -0
package/README.md
CHANGED
|
@@ -38,7 +38,7 @@ CLI는 설치 없이 `npx kordoc`으로 실행할 수 있습니다. PDF·OCR 의
|
|
|
38
38
|
npx -y kordoc setup
|
|
39
39
|
```
|
|
40
40
|
|
|
41
|
-
Claude Desktop·Claude Code·Cursor·Codex 등 설치된 클라이언트에 MCP를 등록합니다. 클라이언트를 재시작하면 파싱·비교·생성·렌더 등 **
|
|
41
|
+
Claude Desktop·Claude Code·Cursor·Codex 등 설치된 클라이언트에 MCP를 등록합니다. 클라이언트를 재시작하면 파싱·비교·생성·렌더 등 **18개 도구**를 사용할 수 있습니다.
|
|
42
42
|
|
|
43
43
|
Claude Code 플러그인:
|
|
44
44
|
|
|
@@ -126,10 +126,11 @@ await writeFile("보고서.hwpx", Buffer.from(hwpx))
|
|
|
126
126
|
|
|
127
127
|
## 최근 업데이트
|
|
128
128
|
|
|
129
|
-
최신 배포: **[4.
|
|
129
|
+
최신 배포: **[4.23.0](https://github.com/chrisryugj/kordoc/releases/tag/v4.23.0)** · 2026-10-21
|
|
130
130
|
|
|
131
131
|
| 버전 | 주요 변경 |
|
|
132
132
|
| --- | --- |
|
|
133
|
+
| 4.23.0 | 부서 서식 견본으로 새 문서 생성(`generate --template`), 예산 문서 검수(`lint --budget` — 산출근거 검산·표 합계·외화·증감 기준), MCP `lint_document`(줄·글자 위치), 공문 표 합계 행 맨 위(`--total-row`), `generate --json`, 일정 줄 두 자리 연도 허용, 정규식 폭주·견본 zip 보안 수정 |
|
|
133
134
|
| 4.22.18 | 패치 정확도 — kordoc 이 만든 보고서·계획서의 제목 틀·장 띠·요약 상자를 고치지 못하던 것(그 뒤 표 칸까지 막힘), 변경 추적 HWP 를 패치하면 한글에 고친 글이 안 보이던 것(한글은 지운 글 사본을 그림 — 추적 표시를 끄고 알림), markdown-it 이차 시간 DoS 권고 대응(14.3.3), 앱에 라이브러리로 넣을 때 뺄 수 있는 MCP·CLI 전용 의존 안내 — 파서·조판 코드는 4.22.17과 같음 |
|
|
134
135
|
| 4.22.17 | 공문서 게이트 — 보고서·계획서의 논리 구조(왜 → 무엇을 → 어떻게, 문제점↔방안 짝, 배경 사실·기대효과 목표치)와 생성형 AI 문체를 검수해 `lint --gate`·`generate --gate`·MCP `gate` 로 막음, 공문서 스킬은 구성 설계 → 게이트 통과 뒤 변환. 실결재·방침서 337건 미통과 5.9%, AI 초안 24건 70.8% — 파서·조판 코드는 4.22.16과 같음 |
|
|
135
136
|
| 4.22.16 | HWP 5.x 패치가 글이 바뀐 문단의 줄 나눔 정보를 지워 한컴이 다시 짜게 함 — 원본 줄 자리에서 끊겨 줄 앞 빈칸(들여쓰기처럼)·줄 첫 마침표가 나던 문제(#167), 종전 동작은 `--keep-lineseg`. 보도자료 HWP 30건 실문서 패치에서 빠진 줄 나눔 정보 수 = 적용 수 — 파서·렌더 코드는 4.22.15와 같음 |
|
|
@@ -23,6 +23,7 @@ import {
|
|
|
23
23
|
hwpxToProfile,
|
|
24
24
|
incompatibleGongmunWarnings,
|
|
25
25
|
isKnownFont,
|
|
26
|
+
lintBudgetText,
|
|
26
27
|
lintGongmunText,
|
|
27
28
|
lintLogicText,
|
|
28
29
|
lintMuncheText,
|
|
@@ -46,18 +47,20 @@ import {
|
|
|
46
47
|
patchHwp,
|
|
47
48
|
patchHwpx,
|
|
48
49
|
patchHwpxBlocks,
|
|
50
|
+
placeTotalRow,
|
|
49
51
|
readBuiltinTemplate,
|
|
50
52
|
readBuiltinTemplateSample,
|
|
51
53
|
resolveBuiltinTemplate,
|
|
54
|
+
runLintSuite,
|
|
52
55
|
slopLintWarnings,
|
|
53
56
|
unknownFontWarnings,
|
|
54
57
|
usesGaejosikMunche,
|
|
55
58
|
usesLogicStructure,
|
|
56
59
|
validateHwpx
|
|
57
|
-
} from "./chunk-
|
|
60
|
+
} from "./chunk-MSUBZT53.js";
|
|
58
61
|
import {
|
|
59
62
|
blocksToChunks
|
|
60
|
-
} from "./chunk-
|
|
63
|
+
} from "./chunk-QO4PT3NN.js";
|
|
61
64
|
import {
|
|
62
65
|
SPACE_EM_FIXED,
|
|
63
66
|
SPACE_EM_FONT,
|
|
@@ -82,20 +85,20 @@ import {
|
|
|
82
85
|
renderSceneToHtml,
|
|
83
86
|
simulateWrap,
|
|
84
87
|
simulateWrapKeepWord
|
|
85
|
-
} from "./chunk-
|
|
86
|
-
import "./chunk-
|
|
88
|
+
} from "./chunk-4XLDFJGY.js";
|
|
89
|
+
import "./chunk-6O2AUXFB.js";
|
|
87
90
|
import {
|
|
88
91
|
blocksToPages
|
|
89
|
-
} from "./chunk-
|
|
92
|
+
} from "./chunk-LJSKKGWU.js";
|
|
90
93
|
import "./chunk-VKVDMH7X.js";
|
|
91
94
|
import "./chunk-VQFA55IC.js";
|
|
92
95
|
import "./chunk-BYMPPVT3.js";
|
|
93
|
-
import "./chunk-
|
|
96
|
+
import "./chunk-GZFL6UOS.js";
|
|
94
97
|
import {
|
|
95
98
|
blocksToMarkdown,
|
|
96
99
|
flattenLayoutTables,
|
|
97
100
|
hasStructuredCellContent
|
|
98
|
-
} from "./chunk-
|
|
101
|
+
} from "./chunk-5NBUT7GX.js";
|
|
99
102
|
import {
|
|
100
103
|
ValueCursor,
|
|
101
104
|
applySplices,
|
|
@@ -109,11 +112,11 @@ import {
|
|
|
109
112
|
isLabelCell,
|
|
110
113
|
placeSealHwpx,
|
|
111
114
|
scanSectionXml
|
|
112
|
-
} from "./chunk-
|
|
113
|
-
import "./chunk-
|
|
115
|
+
} from "./chunk-S7B74SOM.js";
|
|
116
|
+
import "./chunk-VRIHNSYF.js";
|
|
114
117
|
import {
|
|
115
118
|
VERSION
|
|
116
|
-
} from "./chunk-
|
|
119
|
+
} from "./chunk-UIZYWW3J.js";
|
|
117
120
|
import {
|
|
118
121
|
DEFAULT_REDACT_RULES,
|
|
119
122
|
redactMarkdown,
|
|
@@ -173,6 +176,7 @@ export {
|
|
|
173
176
|
isOldHwpFile,
|
|
174
177
|
isPdfFile,
|
|
175
178
|
isZipFile,
|
|
179
|
+
lintBudgetText,
|
|
176
180
|
lintGongmunText,
|
|
177
181
|
lintLogicText,
|
|
178
182
|
lintMuncheText,
|
|
@@ -199,6 +203,7 @@ export {
|
|
|
199
203
|
patchHwpx,
|
|
200
204
|
patchHwpxBlocks,
|
|
201
205
|
placeSealHwpx,
|
|
206
|
+
placeTotalRow,
|
|
202
207
|
readBuiltinTemplate,
|
|
203
208
|
readBuiltinTemplateSample,
|
|
204
209
|
redactMarkdown,
|
|
@@ -210,6 +215,7 @@ export {
|
|
|
210
215
|
renderHwpxToSvg,
|
|
211
216
|
renderSceneToHtml,
|
|
212
217
|
resolveBuiltinTemplate,
|
|
218
|
+
runLintSuite,
|
|
213
219
|
scanSectionXml,
|
|
214
220
|
simulateWrap,
|
|
215
221
|
simulateWrapKeepWord,
|
|
@@ -219,4 +225,4 @@ export {
|
|
|
219
225
|
usesLogicStructure,
|
|
220
226
|
validateHwpx
|
|
221
227
|
};
|
|
222
|
-
//# sourceMappingURL=-
|
|
228
|
+
//# sourceMappingURL=-YNDBG7XO.js.map
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
import {
|
|
2
2
|
KordocError
|
|
3
|
-
} from "./chunk-
|
|
3
|
+
} from "./chunk-Y3LLNEU3.js";
|
|
4
4
|
|
|
5
5
|
// src/pdf/formula/models.ts
|
|
6
6
|
import { createHash as createHash2 } from "crypto";
|
|
@@ -310,4 +310,4 @@ export {
|
|
|
310
310
|
ensureFormulaModels,
|
|
311
311
|
ensureSingleModel
|
|
312
312
|
};
|
|
313
|
-
//# sourceMappingURL=chunk-
|
|
313
|
+
//# sourceMappingURL=chunk-2CHTPRDU.js.map
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
#!/usr/bin/env node
|
|
2
2
|
import {
|
|
3
3
|
assertNetworkAllowed
|
|
4
|
-
} from "./chunk-
|
|
4
|
+
} from "./chunk-4AI32TFY.js";
|
|
5
5
|
|
|
6
6
|
// src/pdf/formula/models.ts
|
|
7
7
|
import { createHash as createHash2 } from "crypto";
|
|
@@ -296,4 +296,4 @@ export {
|
|
|
296
296
|
ensureFormulaModels,
|
|
297
297
|
ensureSingleModel
|
|
298
298
|
};
|
|
299
|
-
//# sourceMappingURL=chunk-
|
|
299
|
+
//# sourceMappingURL=chunk-2EVBM5NZ.js.map
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
import {
|
|
2
2
|
escapeHtml,
|
|
3
3
|
sanitizeHref
|
|
4
|
-
} from "./chunk-
|
|
4
|
+
} from "./chunk-Y3LLNEU3.js";
|
|
5
5
|
|
|
6
6
|
// src/script-tags.ts
|
|
7
7
|
var LITERAL_TAG = /<(?=\/?(?:u|sup|sub)>)/g;
|
|
@@ -1539,4 +1539,4 @@ export {
|
|
|
1539
1539
|
HEADING_RATIO_H3,
|
|
1540
1540
|
validateOcrOptions
|
|
1541
1541
|
};
|
|
1542
|
-
//# sourceMappingURL=chunk-
|
|
1542
|
+
//# sourceMappingURL=chunk-2URKNOOQ.js.map
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
#!/usr/bin/env node
|
|
2
2
|
import {
|
|
3
3
|
KordocError
|
|
4
|
-
} from "./chunk-
|
|
4
|
+
} from "./chunk-UIZYWW3J.js";
|
|
5
5
|
|
|
6
6
|
// src/shared/offline.ts
|
|
7
7
|
import { realpathSync } from "fs";
|
|
@@ -49,4 +49,4 @@ export {
|
|
|
49
49
|
getAccessRoot,
|
|
50
50
|
assertWithinRoot
|
|
51
51
|
};
|
|
52
|
-
//# sourceMappingURL=chunk-
|
|
52
|
+
//# sourceMappingURL=chunk-4AI32TFY.js.map
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
import {
|
|
3
3
|
loadSharp,
|
|
4
4
|
rasterizePageSvg
|
|
5
|
-
} from "./chunk-
|
|
5
|
+
} from "./chunk-6O2AUXFB.js";
|
|
6
6
|
import {
|
|
7
7
|
inlineImagesIntoMarkdown
|
|
8
8
|
} from "./chunk-VKVDMH7X.js";
|
|
@@ -16,7 +16,7 @@ import {
|
|
|
16
16
|
HEADING_RATIO_H3,
|
|
17
17
|
tidyScriptTags,
|
|
18
18
|
unframeLayoutTables
|
|
19
|
-
} from "./chunk-
|
|
19
|
+
} from "./chunk-GZFL6UOS.js";
|
|
20
20
|
import {
|
|
21
21
|
MAX_COLS,
|
|
22
22
|
MAX_ROWS,
|
|
@@ -32,7 +32,7 @@ import {
|
|
|
32
32
|
mapPuaText,
|
|
33
33
|
markNonLayoutTable,
|
|
34
34
|
romanNumeral
|
|
35
|
-
} from "./chunk-
|
|
35
|
+
} from "./chunk-5NBUT7GX.js";
|
|
36
36
|
import {
|
|
37
37
|
DEFAULT_CHAR,
|
|
38
38
|
DEFAULT_PARA_GEOM,
|
|
@@ -46,7 +46,7 @@ import {
|
|
|
46
46
|
hwpxAppMajor,
|
|
47
47
|
parseRenderStyles,
|
|
48
48
|
readZipEntry
|
|
49
|
-
} from "./chunk-
|
|
49
|
+
} from "./chunk-VRIHNSYF.js";
|
|
50
50
|
import {
|
|
51
51
|
KordocError,
|
|
52
52
|
compareSectionPaths,
|
|
@@ -54,7 +54,7 @@ import {
|
|
|
54
54
|
precheckZipSize,
|
|
55
55
|
sanitizeHref,
|
|
56
56
|
toArrayBuffer
|
|
57
|
-
} from "./chunk-
|
|
57
|
+
} from "./chunk-UIZYWW3J.js";
|
|
58
58
|
|
|
59
59
|
// src/render/svg-render.ts
|
|
60
60
|
import JSZip from "jszip";
|
|
@@ -19918,4 +19918,4 @@ export {
|
|
|
19918
19918
|
cropRect,
|
|
19919
19919
|
extractRenderedRegions
|
|
19920
19920
|
};
|
|
19921
|
-
//# sourceMappingURL=chunk-
|
|
19921
|
+
//# sourceMappingURL=chunk-4XLDFJGY.js.map
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
"use strict";Object.defineProperty(exports, "__esModule", {value: true}); function _nullishCoalesce(lhs, rhsFn) { if (lhs != null) { return lhs; } else { return rhsFn(); } } function _optionalChain(ops) { let lastAccessLHS = undefined; let value = ops[0]; let i = 1; while (i < ops.length) { const op = ops[i]; const fn = ops[i + 1]; i += 2; if ((op === 'optionalAccess' || op === 'optionalCall') && value == null) { return undefined; } if (op === 'access' || op === 'optionalAccess') { lastAccessLHS = value; value = fn(value); } else if (op === 'call' || op === 'optionalCall') { value = fn((...args) => value.call(lastAccessLHS, ...args)); lastAccessLHS = undefined; } } return value; }// src/utils.ts
|
|
2
|
-
var VERSION = true ? "4.
|
|
2
|
+
var VERSION = true ? "4.23.0" : "0.0.0-dev";
|
|
3
3
|
function toArrayBuffer(buf) {
|
|
4
4
|
if (buf.byteOffset === 0 && buf.byteLength === buf.buffer.byteLength) {
|
|
5
5
|
return buf.buffer;
|
|
@@ -161,4 +161,4 @@ function partExtension(path) {
|
|
|
161
161
|
|
|
162
162
|
|
|
163
163
|
exports.VERSION = VERSION; exports.toArrayBuffer = toArrayBuffer; exports.KordocError = KordocError; exports.sanitizeError = sanitizeError; exports.isPathTraversal = isPathTraversal; exports.normalizeSectionHref = normalizeSectionHref; exports.compareSectionPaths = compareSectionPaths; exports.unzipLimitBytes = unzipLimitBytes; exports.precheckZipSize = precheckZipSize; exports.stripDtd = stripDtd; exports.sanitizeHref = sanitizeHref; exports.escapeHtml = escapeHtml; exports.unescapeHtml = unescapeHtml; exports.safeMin = safeMin; exports.safeMax = safeMax; exports.OPTIONAL_DEP_INSTALL_HINT = OPTIONAL_DEP_INSTALL_HINT; exports.classifyError = classifyError; exports.partExtension = partExtension;
|
|
164
|
-
//# sourceMappingURL=chunk-
|
|
164
|
+
//# sourceMappingURL=chunk-5KLO56CJ.cjs.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"sources":["/Users/mong-e/workspace/kordoc/dist/chunk-B3Z2PY4R.cjs","../src/utils.ts"],"names":[],"mappings":"AAAA;ACMO,IAAM,QAAA,EAAkB,KAAA,EAA4C,UAAA,EAAqB,WAAA;AAOzF,SAAS,aAAA,CAAc,GAAA,EAA0B;AACtD,EAAA,GAAA,CAAI,GAAA,CAAI,WAAA,IAAe,EAAA,GAAK,GAAA,CAAI,WAAA,IAAe,GAAA,CAAI,MAAA,CAAO,UAAA,EAAY;AACpE,IAAA,OAAO,GAAA,CAAI,MAAA;AAAA,EACb;AACA,EAAA,OAAO,GAAA,CAAI,MAAA,CAAO,KAAA,CAAM,GAAA,CAAI,UAAA,EAAY,GAAA,CAAI,WAAA,EAAa,GAAA,CAAI,UAAU,CAAA;AACzE;AAMO,IAAM,YAAA,EAAN,MAAA,QAA0B,MAAM;AAAA,EACrC,WAAA,CAAY,OAAA,EAAiB;AAC3B,IAAA,KAAA,CAAM,OAAO,CAAA;AACb,IAAA,IAAA,CAAK,KAAA,EAAO,aAAA;AAAA,EACd;AACF,CAAA;AAMA,SAAS,cAAA,CAAe,GAAA,EAAuB;AAC7C,EAAA,GAAA,CAAI,OAAO,IAAA,IAAQ,SAAA,GAAY,IAAA,IAAQ,IAAA,EAAM,OAAO,KAAA;AACpD,EAAA,GAAA,CAAK,GAAA,CAA8B,KAAA,IAAS,QAAA,EAAU,OAAO,IAAA;AAC7D,EAAA,MAAM,IAAA,EAAO,GAAA,CAAc,OAAA;AAC3B,EAAA,OAAO,OAAO,IAAA,IAAQ,SAAA,GAAY,mCAAA,CAAoC,IAAA,CAAK,GAAG,CAAA;AAChF;AAMO,SAAS,aAAA,CAAc,GAAA,EAAsB;AAClD,EAAA,GAAA,CAAI,IAAA,WAAe,WAAA,EAAa,OAAO,GAAA,CAAI,OAAA;AAI3C,EAAA,GAAA,CAAI,cAAA,CAAe,GAAG,CAAA,EAAG,OAAO,uGAAA;AAChC,EAAA,OAAO,0FAAA;AACT;AAMO,SAAS,eAAA,CAAgB,IAAA,EAAuB;AACrD,EAAA,GAAA,CAAI,IAAA,CAAK,QAAA,CAAS,IAAM,CAAA,EAAG,OAAO,IAAA;AAClC,EAAA,MAAM,WAAA,EAAa,IAAA,CAAK,OAAA,CAAQ,KAAA,EAAO,GAAG,CAAA;AAC1C,EAAA,MAAM,SAAA,EAAW,UAAA,CAAW,KAAA,CAAM,GAAG,CAAA;AACrC,EAAA,OAAO,QAAA,CAAS,IAAA,CAAK,CAAA,CAAA,EAAA,GAAK,EAAA,IAAM,IAAI,EAAA,GAAK,UAAA,CAAW,UAAA,CAAW,GAAG,EAAA,GAAK,YAAA,CAAa,IAAA,CAAK,UAAU,CAAA;AACrG;AASO,SAAS,oBAAA,CAAqB,IAAA,EAA6B;AAChE,EAAA,GAAA,CAAI,CAAC,IAAA,EAAM,OAAO,IAAA;AAClB,EAAA,IAAI,WAAA,EAAa,IAAA,CAAK,OAAA,CAAQ,KAAA,EAAO,GAAG,CAAA,CAAE,OAAA,CAAQ,MAAA,EAAQ,EAAE,CAAA;AAC5D,EAAA,GAAA,CAAI,eAAA,CAAgB,UAAU,CAAA,EAAG,OAAO,IAAA;AACxC,EAAA,GAAA,CAAI,sBAAA,CAAuB,IAAA,CAAK,UAAU,CAAA,EAAG,WAAA,EAAa,YAAA,EAAc,UAAA;AACxE,EAAA,OAAO,6BAAA,CAA8B,IAAA,CAAK,UAAU,EAAA,EAAI,WAAA,EAAa,IAAA;AACvE;AAGO,SAAS,mBAAA,CAAoB,CAAA,EAAW,CAAA,EAAmB;AAChE,EAAA,MAAM,GAAA,EAAK,MAAA,kCAAO,CAAA,qBAAE,KAAA,mBAAM,uBAAuB,CAAA,4BAAA,CAAI,CAAC,GAAA,UAAK,MAAA,CAAO,kBAAgB,CAAA;AAClF,EAAA,MAAM,GAAA,EAAK,MAAA,kCAAO,CAAA,qBAAE,KAAA,mBAAM,uBAAuB,CAAA,4BAAA,CAAI,CAAC,GAAA,UAAK,MAAA,CAAO,kBAAgB,CAAA;AAClF,EAAA,OAAO,GAAA,IAAO,GAAA,EAAK,CAAA,CAAE,aAAA,CAAc,CAAC,EAAA,EAAI,GAAA,EAAK,EAAA;AAC/C;AAKA,IAAM,iBAAA,EAAmB,IAAA;AAMlB,SAAS,eAAA,CAAgB,YAAA,EAA8B;AAC5D,EAAA,MAAM,GAAA,EAAK,MAAA,CAAO,OAAA,CAAQ,GAAA,CAAI,mBAAmB,CAAA;AACjD,EAAA,OAAO,MAAA,CAAO,QAAA,CAAS,EAAE,EAAA,GAAK,GAAA,EAAK,EAAA,EAAI,IAAA,CAAK,GAAA,CAAI,EAAA,EAAI,gBAAgB,EAAA,EAAI,KAAA,EAAO,KAAA,EAAO,YAAA;AACxF;AAMO,SAAS,eAAA,CACd,MAAA,EACA,oBAAA,EAAsB,IAAA,EAAM,KAAA,EAAO,IAAA,EACnC,WAAA,EAAa,GAAA,EAGb,KAAA,EACmD;AACnD,EAAA,IAAI;AACF,IAAA,MAAM,KAAA,EAAO,IAAI,QAAA,CAAS,MAAM,CAAA;AAChC,IAAA,MAAM,IAAA,EAAM,MAAA,CAAO,UAAA;AAEnB,IAAA,IAAI,WAAA,EAAa,CAAA,CAAA;AACjB,IAAA,IAAA,CAAA,IAAS,EAAA,EAAI,IAAA,EAAM,EAAA,EAAI,EAAA,GAAK,IAAA,CAAK,GAAA,CAAI,CAAA,EAAG,IAAA,EAAM,KAAK,CAAA,EAAG,CAAA,EAAA,EAAK;AACzD,MAAA,GAAA,CAAI,IAAA,CAAK,SAAA,CAAU,CAAA,EAAG,IAAI,EAAA,IAAM,SAAA,EAAY;AAAE,QAAA,WAAA,EAAa,CAAA;AAAG,QAAA,KAAA;AAAA,MAAM;AAAA,IACtE;AACA,IAAA,GAAA,CAAI,WAAA,EAAa,CAAA,EAAG,OAAO,EAAE,iBAAA,EAAmB,CAAA,EAAG,UAAA,EAAY,EAAE,CAAA;AAEjE,IAAA,MAAM,WAAA,EAAa,IAAA,CAAK,SAAA,CAAU,WAAA,EAAa,EAAA,EAAI,IAAI,CAAA;AACvD,IAAA,GAAA,CAAI,WAAA,EAAa,UAAA,EAAY;AAC3B,MAAA,MAAM,IAAI,WAAA,CAAY,CAAA,4CAAA,EAAiB,UAAU,CAAA,eAAA,EAAQ,UAAU,CAAA,CAAA,CAAG,CAAA;AAAA,IACxE;AAEA,IAAA,MAAM,OAAA,EAAS,IAAA,CAAK,SAAA,CAAU,WAAA,EAAa,EAAA,EAAI,IAAI,CAAA;AACnD,IAAA,MAAM,SAAA,EAAW,IAAA,CAAK,SAAA,CAAU,WAAA,EAAa,EAAA,EAAI,IAAI,CAAA;AACrD,IAAA,GAAA,CAAI,SAAA,EAAW,OAAA,EAAS,GAAA,EAAK,OAAO,EAAE,iBAAA,EAAmB,CAAA,EAAG,WAAW,CAAA;AAEvE,IAAA,IAAI,kBAAA,EAAoB,CAAA;AACxB,IAAA,IAAI,kBAAA,EAAoB,CAAA;AACxB,IAAA,IAAI,IAAA,EAAM,QAAA;AACV,IAAA,IAAA,CAAA,IAAS,EAAA,EAAI,CAAA,EAAG,EAAA,EAAI,WAAA,GAAc,IAAA,EAAM,GAAA,GAAM,SAAA,EAAW,MAAA,EAAQ,CAAA,EAAA,EAAK;AACpE,MAAA,GAAA,CAAI,IAAA,CAAK,SAAA,CAAU,GAAA,EAAK,IAAI,EAAA,IAAM,QAAA,EAAY,KAAA;AAG9C,MAAA,MAAM,SAAA,EAAW,IAAA,CAAK,SAAA,CAAU,IAAA,EAAM,EAAA,EAAI,IAAI,CAAA;AAC9C,MAAA,MAAM,UAAA,EAAY,SAAA,EAAW,GAAA,GAAM,IAAA,GAAO,IAAA,CAAK,SAAA,CAAU,QAAA,EAAU,IAAI,EAAA,IAAM,SAAA,EAAa,IAAA,CAAK,SAAA,CAAU,SAAA,EAAW,EAAA,EAAI,IAAI,EAAA,EAAI,CAAA;AAChI,MAAA,MAAM,KAAA,EAAO,IAAA,CAAK,GAAA,CAAI,IAAA,CAAK,SAAA,CAAU,IAAA,EAAM,EAAA,EAAI,IAAI,CAAA,EAAG,SAAS,CAAA;AAC/D,MAAA,MAAM,QAAA,EAAU,IAAA,CAAK,SAAA,CAAU,IAAA,EAAM,EAAA,EAAI,IAAI,CAAA;AAC7C,MAAA,MAAM,SAAA,EAAW,IAAA,CAAK,SAAA,CAAU,IAAA,EAAM,EAAA,EAAI,IAAI,CAAA;AAC9C,MAAA,MAAM,WAAA,EAAa,IAAA,CAAK,SAAA,CAAU,IAAA,EAAM,EAAA,EAAI,IAAI,CAAA;AAEhD,MAAA,MAAM,QAAA,EAAU,CAAC,CAAC,MAAA,GAAS,IAAA,EAAM,GAAA,EAAK,QAAA,GAAW,IAAA,GAC/C,KAAA,CAAM,EAAA,CAAG,IAAA,CAAK,IAAI,WAAA,CAAY,CAAA,CAAE,MAAA,CAAO,IAAI,UAAA,CAAW,MAAA,EAAQ,IAAA,EAAM,EAAA,EAAI,OAAO,CAAC,CAAC,CAAA;AACnF,MAAA,MAAM,MAAA,EAAQ,QAAA,GAAW,CAAC,iBAAC,KAAA,6BAAO,QAAA,GAAS,KAAA,CAAM,KAAA,CAAM,IAAA,CAAK,IAAI,WAAA,CAAY,CAAA,CAAE,MAAA,CAAO,IAAI,UAAA,CAAW,MAAA,EAAQ,IAAA,EAAM,EAAA,EAAI,OAAO,CAAC,CAAC,CAAA;AAC/H,MAAA,GAAA,CAAI,QAAA,GAAW,CAAC,KAAA,EAAO,kBAAA,GAAqB,IAAA;AAC5C,MAAA,GAAA,CAAI,CAAA,CAAE,QAAA,GAAA,iBAAY,KAAA,6BAAO,OAAA,GAAQ,KAAA,CAAA,CAAA,EAAS,kBAAA,GAAqB,IAAA;AAC/D,MAAA,IAAA,GAAO,GAAA,EAAK,QAAA,EAAU,SAAA,EAAW,UAAA;AAAA,IACnC;AAEA,IAAA,GAAA,CAAI,kBAAA,EAAoB,mBAAA,EAAqB;AAC3C,MAAA,MAAM,GAAA,EAAK,CAAC,CAAA,EAAA,GAAA,CAAe,EAAA,EAAI,KAAA,EAAO,IAAA,CAAA,CAAM,OAAA,CAAQ,CAAC,CAAA;AACrD,MAAA,MAAM,UAAA,EAAY,MAAA,GAAS,CAAC,KAAA,CAAM,KAAA,GAAQ,kBAAA,EAAoB,EAAA,EAC1D,CAAA,wDAAA,EAAgB,EAAA,CAAG,iBAAiB,CAAC,CAAA,oHAAA,EAAA,EAAqD,EAAA;AAC9F,MAAA,MAAM,IAAI,WAAA,CAAY,CAAA,kDAAA,EAAkB,EAAA,CAAG,iBAAiB,CAAC,CAAA,iBAAA,EAAU,oBAAA,EAAsB,KAAA,EAAO,IAAI,CAAA,GAAA,EAAM,SAAS,CAAA,CAAA;AACzH,IAAA;AAEuC,IAAA;AAC3B,EAAA;AAC0B,IAAA;AACO,IAAA;AAC/C,EAAA;AACF;AAS8C;AAC0C,EAAA;AACxF;AAGqB;AAC6G;AACxE;AAC9B,EAAA;AAC0B,EAAA;AAK+C,EAAA;AACrG;AAM+D;AACmB,EAAA;AACtC,EAAA;AAC5C;AAGmD;AAC8B,EAAA;AACjF;AACiG;AAiBlD;AACnC,EAAA;AACwD,EAAA;AAC3D,EAAA;AACT;AAG+C;AACnC,EAAA;AACwD,EAAA;AAC3D,EAAA;AACT;AAUE;AAGqD;AACjB,EAAA;AACpB,EAAA;AAEgB,EAAA;AAEA,EAAA;AAC0B,EAAA;AACV,EAAA;AAEmD,EAAA;AACG,EAAA;AACnB,EAAA;AAChD,EAAA;AAC8C,EAAA;AACrB,EAAA;AACrD,EAAA;AACT;AAIoD;AACqD,EAAA;AACzG;ADhI2K;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA","file":"/Users/mong-e/workspace/kordoc/dist/chunk-B3Z2PY4R.cjs","sourcesContent":[null,"/** kordoc 공용 유틸리티 */\n\nimport { format } from \"util\"\n\n/** 빌드 타임에 tsup define으로 주입되는 버전 */\ndeclare const __KORDOC_VERSION__: string\nexport const VERSION: string = typeof __KORDOC_VERSION__ !== \"undefined\" ? __KORDOC_VERSION__ : \"0.0.0-dev\"\n\n/**\n * Node.js Buffer → ArrayBuffer 변환\n * pool Buffer의 공유 ArrayBuffer 문제를 안전하게 처리.\n * offset=0이고 전체 ArrayBuffer를 차지하면 복사 없이 직접 반환.\n */\nexport function toArrayBuffer(buf: Buffer): ArrayBuffer {\n if (buf.byteOffset === 0 && buf.byteLength === buf.buffer.byteLength) {\n return buf.buffer as ArrayBuffer\n }\n return buf.buffer.slice(buf.byteOffset, buf.byteOffset + buf.byteLength) as ArrayBuffer\n}\n\n/**\n * kordoc 내부 에러 클래스 — 사용자에게 노출해도 안전한 메시지만 포함.\n * MCP 에러 정제에서 instanceof로 판별하여 allowlist 패턴 매칭 없이 안전하게 통과.\n */\nexport class KordocError extends Error {\n constructor(message: string) {\n super(message)\n this.name = \"KordocError\"\n }\n}\n\n/**\n * ENOENT 판별 — 입력 경로가 존재하지 않음.\n * 래핑된 KordocError 를 뚫고 올라온 경우도 있으므로 메시지까지 함께 본다.\n */\nfunction isFileNotFound(err: unknown): boolean {\n if (typeof err !== \"object\" || err === null) return false\n if ((err as NodeJS.ErrnoException).code === \"ENOENT\") return true\n const msg = (err as Error).message\n return typeof msg === \"string\" && /ENOENT|no such file or directory/i.test(msg)\n}\n\n/**\n * 에러 메시지 정제 — KordocError는 그대로, ENOENT 만 구분 문구, 나머지는 일반 메시지로 대체.\n * 파일시스템 경로, 스택 트레이스 등 내부 정보 노출 방지.\n */\nexport function sanitizeError(err: unknown): string {\n if (err instanceof KordocError) return err.message\n // 없는 파일은 문서 문제가 아니라 고칠 수 있는 입력 문제다 — 사유를 숨기지 않는다.\n // 경로는 노출하지 않는다(어느 파일인지는 stderr·실패 JSON 의 basename 이 알린다).\n // 문구는 MCP describeError 의 ENOENT 힌트와 같은 표현을 쓴다.\n if (isFileNotFound(err)) return \"파일 또는 디렉토리를 찾을 수 없습니다\"\n return \"문서 처리 중 오류가 발생했습니다\"\n}\n\n/**\n * ZIP 엔트리 경로의 경로 순회 여부 판별.\n * 백슬래시 정규화, .., 절대경로, Windows 드라이브 문자 모두 차단.\n */\nexport function isPathTraversal(name: string): boolean {\n if (name.includes(\"\\x00\")) return true\n const normalized = name.replace(/\\\\/g, \"/\")\n const segments = normalized.split(\"/\")\n return segments.some(s => s === \"..\") || normalized.startsWith(\"/\") || /^[A-Za-z]:/.test(normalized)\n}\n\n// ─── HWPX 섹션 href 해석 (parser/roundtrip 공용) ────────────────────\n\n/**\n * manifest href를 본문 섹션 경로(`Contents/sectionN.xml`)로 정규화.\n * 비본문 XML(header/script/settings)·path traversal·드라이브 경로는 null로 거른다.\n * 백슬래시 구분자를 슬래시로 통일해 parser와 roundtrip이 동일한 목록을 만든다.\n */\nexport function normalizeSectionHref(href: string): string | null {\n if (!href) return null\n let normalized = href.replace(/\\\\/g, \"/\").replace(/^\\/+/, \"\")\n if (isPathTraversal(normalized)) return null\n if (/^[Ss]ection\\d+\\.xml$/.test(normalized)) normalized = \"Contents/\" + normalized\n return /(?:^|\\/)[Ss]ection\\d+\\.xml$/.test(normalized) ? normalized : null\n}\n\n/** sectionN.xml을 N 숫자 순서로 정렬 (section10 > section2). */\nexport function compareSectionPaths(a: string, b: string): number {\n const ai = Number(a.match(/[Ss]ection(\\d+)\\.xml$/)?.[1] ?? Number.MAX_SAFE_INTEGER)\n const bi = Number(b.match(/[Ss]ection(\\d+)\\.xml$/)?.[1] ?? Number.MAX_SAFE_INTEGER)\n return ai === bi ? a.localeCompare(b) : ai - bi\n}\n\n// ─── ZIP 안전 로딩 (ZIP bomb 방지) ────────────────────\n\n/** ZIP 비압축 상한 env 의 최대값 (MB) — 오타로 사실상 무제한이 되지 않게 */\nconst MAX_UNZIP_ENV_MB = 8192\n\n/**\n * ZIP 비압축 크기 상한 — `KORDOC_MAX_UNZIP_MB` 가 양수면 그 값(MB, 최대 8192), 아니면 포맷 기본값.\n * 빈 행이 수백만 개인 XLSX 처럼 내용은 작고 XML 만 큰 실문서를 폐쇄망 대량 적재에서 받으려는 설정 (#91)\n */\nexport function unzipLimitBytes(defaultBytes: number): number {\n const mb = Number(process.env.KORDOC_MAX_UNZIP_MB)\n return Number.isFinite(mb) && mb > 0 ? Math.min(mb, MAX_UNZIP_ENV_MB) * 1024 * 1024 : defaultBytes\n}\n\n/**\n * ZIP bomb 사전 검사 — Central Directory에서 비압축 합계와 엔트리 수 확인.\n * HWPX/XLSX/DOCX 등 모든 ZIP 기반 포맷에서 공통 사용.\n */\nexport function precheckZipSize(\n buffer: ArrayBuffer,\n maxUncompressedSize = 256 * 1024 * 1024, // parser-shared MAX_DECOMPRESS_SIZE 와 동기\n maxEntries = 500,\n /** 그림·개체 파트(엔트리 이름 re) — skip 이면 합계에서 뺀다(파서가 풀지 않는다), 아니면 한도 초과 메시지에 크기를 적는다 (#108).\n * never — 파서가 어느 때도 풀지 않는 파트(동영상·음성·OLE 임베드)는 늘 뺀다: 110MB 동영상 하나로 발표 자료가 통째 거부됐다 */\n media?: { re: RegExp; skip: boolean; never?: RegExp },\n): { totalUncompressed: number; entryCount: number } {\n try {\n const data = new DataView(buffer)\n const len = buffer.byteLength\n // EOCD 시그니처 역방향 스캔\n let eocdOffset = -1\n for (let i = len - 22; i >= Math.max(0, len - 65557); i--) {\n if (data.getUint32(i, true) === 0x06054b50) { eocdOffset = i; break }\n }\n if (eocdOffset < 0) return { totalUncompressed: 0, entryCount: 0 }\n\n const entryCount = data.getUint16(eocdOffset + 10, true)\n if (entryCount > maxEntries) {\n throw new KordocError(`ZIP 엔트리 수 초과: ${entryCount} (최대 ${maxEntries})`)\n }\n\n const cdSize = data.getUint32(eocdOffset + 12, true)\n const cdOffset = data.getUint32(eocdOffset + 16, true)\n if (cdOffset + cdSize > len) return { totalUncompressed: 0, entryCount }\n\n let totalUncompressed = 0\n let mediaUncompressed = 0\n let pos = cdOffset\n for (let i = 0; i < entryCount && pos + 46 <= cdOffset + cdSize; i++) {\n if (data.getUint32(pos, true) !== 0x02014b50) break\n // 비압축 크기는 중앙 디렉터리와 지역 헤더 중 큰 값 — JSZip 은 지역 헤더 크기로 풀고(readZipEntry 가 그 크기를 넘으면 끊는다),\n // 한쪽만 작게 속여 합계 검사를 비켜 가지 못하게 둘 다 본다\n const localOff = data.getUint32(pos + 42, true)\n const localSize = localOff + 30 <= len && data.getUint32(localOff, true) === 0x04034b50 ? data.getUint32(localOff + 22, true) : 0\n const size = Math.max(data.getUint32(pos + 24, true), localSize)\n const nameLen = data.getUint16(pos + 28, true)\n const extraLen = data.getUint16(pos + 30, true)\n const commentLen = data.getUint16(pos + 32, true)\n // 이름이 버퍼 밖이면 그림 파트로 치지 않는다(합계에서 빠지지 않게)\n const isMedia = !!media && pos + 46 + nameLen <= len &&\n media.re.test(new TextDecoder().decode(new Uint8Array(buffer, pos + 46, nameLen)))\n const never = isMedia && !!media?.never && media.never.test(new TextDecoder().decode(new Uint8Array(buffer, pos + 46, nameLen)))\n if (isMedia && !never) mediaUncompressed += size\n if (!(isMedia && (media?.skip || never))) totalUncompressed += size\n pos += 46 + nameLen + extraLen + commentLen\n }\n\n if (totalUncompressed > maxUncompressedSize) {\n const mb = (n: number) => (n / 1024 / 1024).toFixed(1)\n const mediaNote = media && !media.skip && mediaUncompressed > 0\n ? ` — 그림·개체 파트가 ${mb(mediaUncompressed)}MB, 이미지 추출을 끄면(images: false·--no-images) 세지 않는다` : \"\"\n throw new KordocError(`ZIP 비압축 크기 초과: ${mb(totalUncompressed)}MB (최대 ${maxUncompressedSize / 1024 / 1024}MB)${mediaNote}`)\n }\n\n return { totalUncompressed, entryCount }\n } catch (err) {\n if (err instanceof KordocError) throw err\n return { totalUncompressed: 0, entryCount: 0 }\n }\n}\n\n/**\n * XML 파싱 전 프롤로그 정리 — 선두 BOM 제거 + DOCTYPE 제거(XXE/Billion Laughs 방지).\n *\n * BOM: 일부 OpenXML 라이터가 `[Content_Types].xml`·`.rels` 앞에 EF BB BF를 붙인다.\n * XML 스펙상 적법(엔티티는 BOM으로 시작할 수 있음)이고 엑셀·리브레오피스는 여는데,\n * xmldom은 \"선언이 문서 시작이 아님\" fatalError로 파일 전체를 거부했다 (#63).\n */\nexport function stripDtd(xml: string): string {\n return xml.replace(/^\\uFEFF/, \"\").replace(/<!DOCTYPE\\s[^[>]*(\\[[\\s\\S]*?\\])?\\s*>/gi, \"\")\n}\n\n/** 하이퍼링크 URL 살균 — javascript: 등 XSS 위험 스킴 차단 */\nconst SAFE_HREF_RE = /^(?:https?:|mailto:|tel:|#)/i\nconst HREF_ESCAPE: Record<string, string> = { \"(\": \"%28\", \")\": \"%29\", \"<\": \"%3C\", \">\": \"%3E\", \"\\\"\": \"%22\", \"'\": \"%27\", \"`\": \"%60\" }\nexport function sanitizeHref(href: string): string | null {\n const trimmed = href.trim()\n if (!trimmed || !SAFE_HREF_RE.test(trimmed)) return null\n // 괄호 percent-encoding — 마크다운 링크 목적지에서 불균형 ')'는 링크를 조기 종료시켜\n // 문법이 깨진다 (원문 하이퍼링크에 ')'가 박힌 실문서 존재). %28/%29는 의미 동일.\n // 공백·<>\"'` 도 — 스킴만 보고 통과시키면 \"mailto:a <img src=x onerror=…>\" 가 링크 목적지를 깨고 날 태그로\n // 렌더됐다(pdfjs 는 mailto·tel URI 를 정규화하지 않는다, v4.14.4 리뷰 재현). 인코딩해도 같은 주소다\n return trimmed.replace(/[()<>\"'`]/g, c => HREF_ESCAPE[c]).replace(/\\s/g, c => encodeURIComponent(c))\n}\n\n/**\n * HTML 엔티티 이스케이프 — 글은 `& < >`, 속성값(attr)은 `\"` 까지. HTML 표 경로(builder tableToHtml)와\n * 인쇄 렌더러가 같이 쓰는 한 벌. 읽는 쪽은 unescapeHtml 로 푼다\n */\nexport function escapeHtml(text: string, attr = false): string {\n const s = text.replace(/&/g, \"&\").replace(/</g, \"<\").replace(/>/g, \">\")\n return attr ? s.replace(/\"/g, \""\") : s\n}\n\n/** escapeHtml 의 역 (+ 손으로 쓴 HTML 표의 ') — 한 번에 풀어 \"&lt;\" 는 \"<\" 로 남는다 */\nexport function unescapeHtml(text: string): string {\n return text.replace(/&(lt|gt|quot|#39|amp);/g, (_, e: string) => HTML_ENTITY[e])\n}\nconst HTML_ENTITY: Record<string, string> = { lt: \"<\", gt: \">\", quot: \"\\\"\", \"#39\": \"'\", amp: \"&\" }\n\n/**\n * console.log·info·warn·debug 를 stderr 로 — stdout 이 기계 출력 채널(MCP JSON-RPC·CLI 마크다운/JSON·parse-worker\n * NDJSON)인 진입점용. 라이브러리(pdfjs 등)가 console 로 찍는 경고가 그 채널을 깨지 않게 한다\n */\nexport function routeConsoleToStderr(): void {\n const toStderr = (...args: unknown[]): void => void process.stderr.write(format(...args) + \"\\n\")\n console.log = toStderr\n console.info = toStderr\n console.warn = toStderr\n console.debug = toStderr\n}\n\n// ─── 안전한 min/max (스택 오버플로 방지) ─────────────\n\n/** Math.min(...arr) 대체 — 대형 배열에서 스택 오버플로 방지 */\nexport function safeMin(arr: number[]): number {\n let min = Infinity\n for (let i = 0; i < arr.length; i++) if (arr[i] < min) min = arr[i]\n return min\n}\n\n/** Math.max(...arr) 대체 — 대형 배열에서 스택 오버플로 방지 */\nexport function safeMax(arr: number[]): number {\n let max = -Infinity\n for (let i = 0; i < arr.length; i++) if (arr[i] > max) max = arr[i]\n return max\n}\n\n// ─── 에러 분류 ──────────────────────────────────────\n\nimport type { ErrorCode } from \"./types.js\"\n\n/** 에러를 구조화된 ErrorCode로 분류 — KordocError 메시지 패턴 매칭 */\n/** 선택 의존 설치 실패 안내 꼬리 — 네트워크가 막힌 linux/x64 에서 onnxruntime-node 설치 스크립트가 CUDA 바이너리를 받다 실패하면\n * npm 이 sharp·@huggingface/tokenizers 까지 선택 의존 설치에서 뺀다(#99). npx 캐시 실행은 npm install 로 못 고친다 */\nexport const OPTIONAL_DEP_INSTALL_HINT =\n \" 네트워크가 제한된 linux/x64 에서 npx 로 설치했다면 onnxruntime-node 의 CUDA 다운로드 실패로 함께 빠졌을 수 있습니다 — \" +\n \"`ONNXRUNTIME_NODE_INSTALL=skip npx -y kordoc@^4 …` 로 다시 설치하세요.\"\n\nexport function classifyError(err: unknown): ErrorCode {\n if (!(err instanceof Error)) return \"PARSE_ERROR\"\n const msg = err.message\n // 입력 파일 없음 — 문서 내용 문제가 아니라 호출자의 경로 문제라 PARSE_ERROR 로 덮지 않는다.\n if (isFileNotFound(err)) return \"FILE_NOT_FOUND\"\n // DRM 을 암호화보다 먼저 — \"DRM 암호화된 HWPX…\" 류 메시지가 ENCRYPTED 로 떨어지지 않도록\n if (msg.includes(\"DRM\")) return \"DRM_PROTECTED\"\n if (msg.includes(\"암호화\") || msg.includes(\"암호로 보호\")) return \"ENCRYPTED\"\n if (msg.includes(\"optional dependency\")) return \"MISSING_DEPENDENCY\"\n // V8 문자열 한계 초과 — 이미지 base64 총량이 큰 문서의 JSON 직렬화 (#65)\n if (msg.includes(\"Invalid string length\") || msg.includes(\"Cannot create a string longer\")) return \"OUTPUT_TOO_LARGE\"\n if (msg.includes(\"ZIP bomb\") || msg.includes(\"ZIP 비압축 크기 초과\") || msg.includes(\"ZIP 엔트리 수 초과\")) return \"ZIP_BOMB\"\n if (msg.includes(\"bomb\") || msg.includes(\"크기 초과\") || msg.includes(\"압축 해제\")) return \"DECOMPRESSION_BOMB\"\n if (msg.includes(\"이미지 기반\")) return \"IMAGE_BASED_PDF\"\n if (msg.includes(\"섹션\") && (msg.includes(\"찾을 수 없\") || msg.includes(\"없음\"))) return \"NO_SECTIONS\"\n if (msg.includes(\"시그니처\") || msg.includes(\"복구할 수 없\")) return \"CORRUPTED\"\n return \"PARSE_ERROR\"\n}\n\n/** ZIP 파트 경로의 확장자 — 마지막 경로 조각에서만, 없으면 \"bin\". \"ppt/media.v2/image1\" 의 \"v2/image1\" 이 그림 파일 이름에 들어가\n * 저장 경로가 깨졌다 */\nexport function partExtension(path: string): string {\n return (/\\.([A-Za-z0-9]{1,5})$/.exec(path.slice(path.lastIndexOf(\"/\") + 1))?.[1] ?? \"bin\").toLowerCase()\n}\n"]}
|
|
1
|
+
{"version":3,"sources":["/Users/mong-e/workspace/kordoc/dist/chunk-5KLO56CJ.cjs","../src/utils.ts"],"names":[],"mappings":"AAAA;ACMO,IAAM,QAAA,EAAkB,KAAA,EAA4C,SAAA,EAAqB,WAAA;AAOzF,SAAS,aAAA,CAAc,GAAA,EAA0B;AACtD,EAAA,GAAA,CAAI,GAAA,CAAI,WAAA,IAAe,EAAA,GAAK,GAAA,CAAI,WAAA,IAAe,GAAA,CAAI,MAAA,CAAO,UAAA,EAAY;AACpE,IAAA,OAAO,GAAA,CAAI,MAAA;AAAA,EACb;AACA,EAAA,OAAO,GAAA,CAAI,MAAA,CAAO,KAAA,CAAM,GAAA,CAAI,UAAA,EAAY,GAAA,CAAI,WAAA,EAAa,GAAA,CAAI,UAAU,CAAA;AACzE;AAMO,IAAM,YAAA,EAAN,MAAA,QAA0B,MAAM;AAAA,EACrC,WAAA,CAAY,OAAA,EAAiB;AAC3B,IAAA,KAAA,CAAM,OAAO,CAAA;AACb,IAAA,IAAA,CAAK,KAAA,EAAO,aAAA;AAAA,EACd;AACF,CAAA;AAMA,SAAS,cAAA,CAAe,GAAA,EAAuB;AAC7C,EAAA,GAAA,CAAI,OAAO,IAAA,IAAQ,SAAA,GAAY,IAAA,IAAQ,IAAA,EAAM,OAAO,KAAA;AACpD,EAAA,GAAA,CAAK,GAAA,CAA8B,KAAA,IAAS,QAAA,EAAU,OAAO,IAAA;AAC7D,EAAA,MAAM,IAAA,EAAO,GAAA,CAAc,OAAA;AAC3B,EAAA,OAAO,OAAO,IAAA,IAAQ,SAAA,GAAY,mCAAA,CAAoC,IAAA,CAAK,GAAG,CAAA;AAChF;AAMO,SAAS,aAAA,CAAc,GAAA,EAAsB;AAClD,EAAA,GAAA,CAAI,IAAA,WAAe,WAAA,EAAa,OAAO,GAAA,CAAI,OAAA;AAI3C,EAAA,GAAA,CAAI,cAAA,CAAe,GAAG,CAAA,EAAG,OAAO,uGAAA;AAChC,EAAA,OAAO,0FAAA;AACT;AAMO,SAAS,eAAA,CAAgB,IAAA,EAAuB;AACrD,EAAA,GAAA,CAAI,IAAA,CAAK,QAAA,CAAS,IAAM,CAAA,EAAG,OAAO,IAAA;AAClC,EAAA,MAAM,WAAA,EAAa,IAAA,CAAK,OAAA,CAAQ,KAAA,EAAO,GAAG,CAAA;AAC1C,EAAA,MAAM,SAAA,EAAW,UAAA,CAAW,KAAA,CAAM,GAAG,CAAA;AACrC,EAAA,OAAO,QAAA,CAAS,IAAA,CAAK,CAAA,CAAA,EAAA,GAAK,EAAA,IAAM,IAAI,EAAA,GAAK,UAAA,CAAW,UAAA,CAAW,GAAG,EAAA,GAAK,YAAA,CAAa,IAAA,CAAK,UAAU,CAAA;AACrG;AASO,SAAS,oBAAA,CAAqB,IAAA,EAA6B;AAChE,EAAA,GAAA,CAAI,CAAC,IAAA,EAAM,OAAO,IAAA;AAClB,EAAA,IAAI,WAAA,EAAa,IAAA,CAAK,OAAA,CAAQ,KAAA,EAAO,GAAG,CAAA,CAAE,OAAA,CAAQ,MAAA,EAAQ,EAAE,CAAA;AAC5D,EAAA,GAAA,CAAI,eAAA,CAAgB,UAAU,CAAA,EAAG,OAAO,IAAA;AACxC,EAAA,GAAA,CAAI,sBAAA,CAAuB,IAAA,CAAK,UAAU,CAAA,EAAG,WAAA,EAAa,YAAA,EAAc,UAAA;AACxE,EAAA,OAAO,6BAAA,CAA8B,IAAA,CAAK,UAAU,EAAA,EAAI,WAAA,EAAa,IAAA;AACvE;AAGO,SAAS,mBAAA,CAAoB,CAAA,EAAW,CAAA,EAAmB;AAChE,EAAA,MAAM,GAAA,EAAK,MAAA,kCAAO,CAAA,qBAAE,KAAA,mBAAM,uBAAuB,CAAA,4BAAA,CAAI,CAAC,GAAA,UAAK,MAAA,CAAO,kBAAgB,CAAA;AAClF,EAAA,MAAM,GAAA,EAAK,MAAA,kCAAO,CAAA,qBAAE,KAAA,mBAAM,uBAAuB,CAAA,4BAAA,CAAI,CAAC,GAAA,UAAK,MAAA,CAAO,kBAAgB,CAAA;AAClF,EAAA,OAAO,GAAA,IAAO,GAAA,EAAK,CAAA,CAAE,aAAA,CAAc,CAAC,EAAA,EAAI,GAAA,EAAK,EAAA;AAC/C;AAKA,IAAM,iBAAA,EAAmB,IAAA;AAMlB,SAAS,eAAA,CAAgB,YAAA,EAA8B;AAC5D,EAAA,MAAM,GAAA,EAAK,MAAA,CAAO,OAAA,CAAQ,GAAA,CAAI,mBAAmB,CAAA;AACjD,EAAA,OAAO,MAAA,CAAO,QAAA,CAAS,EAAE,EAAA,GAAK,GAAA,EAAK,EAAA,EAAI,IAAA,CAAK,GAAA,CAAI,EAAA,EAAI,gBAAgB,EAAA,EAAI,KAAA,EAAO,KAAA,EAAO,YAAA;AACxF;AAMO,SAAS,eAAA,CACd,MAAA,EACA,oBAAA,EAAsB,IAAA,EAAM,KAAA,EAAO,IAAA,EACnC,WAAA,EAAa,GAAA,EAGb,KAAA,EACmD;AACnD,EAAA,IAAI;AACF,IAAA,MAAM,KAAA,EAAO,IAAI,QAAA,CAAS,MAAM,CAAA;AAChC,IAAA,MAAM,IAAA,EAAM,MAAA,CAAO,UAAA;AAEnB,IAAA,IAAI,WAAA,EAAa,CAAA,CAAA;AACjB,IAAA,IAAA,CAAA,IAAS,EAAA,EAAI,IAAA,EAAM,EAAA,EAAI,EAAA,GAAK,IAAA,CAAK,GAAA,CAAI,CAAA,EAAG,IAAA,EAAM,KAAK,CAAA,EAAG,CAAA,EAAA,EAAK;AACzD,MAAA,GAAA,CAAI,IAAA,CAAK,SAAA,CAAU,CAAA,EAAG,IAAI,EAAA,IAAM,SAAA,EAAY;AAAE,QAAA,WAAA,EAAa,CAAA;AAAG,QAAA,KAAA;AAAA,MAAM;AAAA,IACtE;AACA,IAAA,GAAA,CAAI,WAAA,EAAa,CAAA,EAAG,OAAO,EAAE,iBAAA,EAAmB,CAAA,EAAG,UAAA,EAAY,EAAE,CAAA;AAEjE,IAAA,MAAM,WAAA,EAAa,IAAA,CAAK,SAAA,CAAU,WAAA,EAAa,EAAA,EAAI,IAAI,CAAA;AACvD,IAAA,GAAA,CAAI,WAAA,EAAa,UAAA,EAAY;AAC3B,MAAA,MAAM,IAAI,WAAA,CAAY,CAAA,4CAAA,EAAiB,UAAU,CAAA,eAAA,EAAQ,UAAU,CAAA,CAAA,CAAG,CAAA;AAAA,IACxE;AAEA,IAAA,MAAM,OAAA,EAAS,IAAA,CAAK,SAAA,CAAU,WAAA,EAAa,EAAA,EAAI,IAAI,CAAA;AACnD,IAAA,MAAM,SAAA,EAAW,IAAA,CAAK,SAAA,CAAU,WAAA,EAAa,EAAA,EAAI,IAAI,CAAA;AACrD,IAAA,GAAA,CAAI,SAAA,EAAW,OAAA,EAAS,GAAA,EAAK,OAAO,EAAE,iBAAA,EAAmB,CAAA,EAAG,WAAW,CAAA;AAEvE,IAAA,IAAI,kBAAA,EAAoB,CAAA;AACxB,IAAA,IAAI,kBAAA,EAAoB,CAAA;AACxB,IAAA,IAAI,IAAA,EAAM,QAAA;AACV,IAAA,IAAA,CAAA,IAAS,EAAA,EAAI,CAAA,EAAG,EAAA,EAAI,WAAA,GAAc,IAAA,EAAM,GAAA,GAAM,SAAA,EAAW,MAAA,EAAQ,CAAA,EAAA,EAAK;AACpE,MAAA,GAAA,CAAI,IAAA,CAAK,SAAA,CAAU,GAAA,EAAK,IAAI,EAAA,IAAM,QAAA,EAAY,KAAA;AAG9C,MAAA,MAAM,SAAA,EAAW,IAAA,CAAK,SAAA,CAAU,IAAA,EAAM,EAAA,EAAI,IAAI,CAAA;AAC9C,MAAA,MAAM,UAAA,EAAY,SAAA,EAAW,GAAA,GAAM,IAAA,GAAO,IAAA,CAAK,SAAA,CAAU,QAAA,EAAU,IAAI,EAAA,IAAM,SAAA,EAAa,IAAA,CAAK,SAAA,CAAU,SAAA,EAAW,EAAA,EAAI,IAAI,EAAA,EAAI,CAAA;AAChI,MAAA,MAAM,KAAA,EAAO,IAAA,CAAK,GAAA,CAAI,IAAA,CAAK,SAAA,CAAU,IAAA,EAAM,EAAA,EAAI,IAAI,CAAA,EAAG,SAAS,CAAA;AAC/D,MAAA,MAAM,QAAA,EAAU,IAAA,CAAK,SAAA,CAAU,IAAA,EAAM,EAAA,EAAI,IAAI,CAAA;AAC7C,MAAA,MAAM,SAAA,EAAW,IAAA,CAAK,SAAA,CAAU,IAAA,EAAM,EAAA,EAAI,IAAI,CAAA;AAC9C,MAAA,MAAM,WAAA,EAAa,IAAA,CAAK,SAAA,CAAU,IAAA,EAAM,EAAA,EAAI,IAAI,CAAA;AAEhD,MAAA,MAAM,QAAA,EAAU,CAAC,CAAC,MAAA,GAAS,IAAA,EAAM,GAAA,EAAK,QAAA,GAAW,IAAA,GAC/C,KAAA,CAAM,EAAA,CAAG,IAAA,CAAK,IAAI,WAAA,CAAY,CAAA,CAAE,MAAA,CAAO,IAAI,UAAA,CAAW,MAAA,EAAQ,IAAA,EAAM,EAAA,EAAI,OAAO,CAAC,CAAC,CAAA;AACnF,MAAA,MAAM,MAAA,EAAQ,QAAA,GAAW,CAAC,iBAAC,KAAA,6BAAO,QAAA,GAAS,KAAA,CAAM,KAAA,CAAM,IAAA,CAAK,IAAI,WAAA,CAAY,CAAA,CAAE,MAAA,CAAO,IAAI,UAAA,CAAW,MAAA,EAAQ,IAAA,EAAM,EAAA,EAAI,OAAO,CAAC,CAAC,CAAA;AAC/H,MAAA,GAAA,CAAI,QAAA,GAAW,CAAC,KAAA,EAAO,kBAAA,GAAqB,IAAA;AAC5C,MAAA,GAAA,CAAI,CAAA,CAAE,QAAA,GAAA,iBAAY,KAAA,6BAAO,OAAA,GAAQ,KAAA,CAAA,CAAA,EAAS,kBAAA,GAAqB,IAAA;AAC/D,MAAA,IAAA,GAAO,GAAA,EAAK,QAAA,EAAU,SAAA,EAAW,UAAA;AAAA,IACnC;AAEA,IAAA,GAAA,CAAI,kBAAA,EAAoB,mBAAA,EAAqB;AAC3C,MAAA,MAAM,GAAA,EAAK,CAAC,CAAA,EAAA,GAAA,CAAe,EAAA,EAAI,KAAA,EAAO,IAAA,CAAA,CAAM,OAAA,CAAQ,CAAC,CAAA;AACrD,MAAA,MAAM,UAAA,EAAY,MAAA,GAAS,CAAC,KAAA,CAAM,KAAA,GAAQ,kBAAA,EAAoB,EAAA,EAC1D,CAAA,wDAAA,EAAgB,EAAA,CAAG,iBAAiB,CAAC,CAAA,oHAAA,EAAA,EAAqD,EAAA;AAC9F,MAAA,MAAM,IAAI,WAAA,CAAY,CAAA,kDAAA,EAAkB,EAAA,CAAG,iBAAiB,CAAC,CAAA,iBAAA,EAAU,oBAAA,EAAsB,KAAA,EAAO,IAAI,CAAA,GAAA,EAAM,SAAS,CAAA,CAAA;AACzH,IAAA;AAEuC,IAAA;AAC3B,EAAA;AAC0B,IAAA;AACO,IAAA;AAC/C,EAAA;AACF;AAS8C;AAC0C,EAAA;AACxF;AAGqB;AAC6G;AACxE;AAC9B,EAAA;AAC0B,EAAA;AAK+C,EAAA;AACrG;AAM+D;AACmB,EAAA;AACtC,EAAA;AAC5C;AAGmD;AAC8B,EAAA;AACjF;AACiG;AAiBlD;AACnC,EAAA;AACwD,EAAA;AAC3D,EAAA;AACT;AAG+C;AACnC,EAAA;AACwD,EAAA;AAC3D,EAAA;AACT;AAUE;AAGqD;AACjB,EAAA;AACpB,EAAA;AAEgB,EAAA;AAEA,EAAA;AAC0B,EAAA;AACV,EAAA;AAEmD,EAAA;AACG,EAAA;AACnB,EAAA;AAChD,EAAA;AAC8C,EAAA;AACrB,EAAA;AACrD,EAAA;AACT;AAIoD;AACqD,EAAA;AACzG;ADhI2K;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA","file":"/Users/mong-e/workspace/kordoc/dist/chunk-5KLO56CJ.cjs","sourcesContent":[null,"/** kordoc 공용 유틸리티 */\n\nimport { format } from \"util\"\n\n/** 빌드 타임에 tsup define으로 주입되는 버전 */\ndeclare const __KORDOC_VERSION__: string\nexport const VERSION: string = typeof __KORDOC_VERSION__ !== \"undefined\" ? __KORDOC_VERSION__ : \"0.0.0-dev\"\n\n/**\n * Node.js Buffer → ArrayBuffer 변환\n * pool Buffer의 공유 ArrayBuffer 문제를 안전하게 처리.\n * offset=0이고 전체 ArrayBuffer를 차지하면 복사 없이 직접 반환.\n */\nexport function toArrayBuffer(buf: Buffer): ArrayBuffer {\n if (buf.byteOffset === 0 && buf.byteLength === buf.buffer.byteLength) {\n return buf.buffer as ArrayBuffer\n }\n return buf.buffer.slice(buf.byteOffset, buf.byteOffset + buf.byteLength) as ArrayBuffer\n}\n\n/**\n * kordoc 내부 에러 클래스 — 사용자에게 노출해도 안전한 메시지만 포함.\n * MCP 에러 정제에서 instanceof로 판별하여 allowlist 패턴 매칭 없이 안전하게 통과.\n */\nexport class KordocError extends Error {\n constructor(message: string) {\n super(message)\n this.name = \"KordocError\"\n }\n}\n\n/**\n * ENOENT 판별 — 입력 경로가 존재하지 않음.\n * 래핑된 KordocError 를 뚫고 올라온 경우도 있으므로 메시지까지 함께 본다.\n */\nfunction isFileNotFound(err: unknown): boolean {\n if (typeof err !== \"object\" || err === null) return false\n if ((err as NodeJS.ErrnoException).code === \"ENOENT\") return true\n const msg = (err as Error).message\n return typeof msg === \"string\" && /ENOENT|no such file or directory/i.test(msg)\n}\n\n/**\n * 에러 메시지 정제 — KordocError는 그대로, ENOENT 만 구분 문구, 나머지는 일반 메시지로 대체.\n * 파일시스템 경로, 스택 트레이스 등 내부 정보 노출 방지.\n */\nexport function sanitizeError(err: unknown): string {\n if (err instanceof KordocError) return err.message\n // 없는 파일은 문서 문제가 아니라 고칠 수 있는 입력 문제다 — 사유를 숨기지 않는다.\n // 경로는 노출하지 않는다(어느 파일인지는 stderr·실패 JSON 의 basename 이 알린다).\n // 문구는 MCP describeError 의 ENOENT 힌트와 같은 표현을 쓴다.\n if (isFileNotFound(err)) return \"파일 또는 디렉토리를 찾을 수 없습니다\"\n return \"문서 처리 중 오류가 발생했습니다\"\n}\n\n/**\n * ZIP 엔트리 경로의 경로 순회 여부 판별.\n * 백슬래시 정규화, .., 절대경로, Windows 드라이브 문자 모두 차단.\n */\nexport function isPathTraversal(name: string): boolean {\n if (name.includes(\"\\x00\")) return true\n const normalized = name.replace(/\\\\/g, \"/\")\n const segments = normalized.split(\"/\")\n return segments.some(s => s === \"..\") || normalized.startsWith(\"/\") || /^[A-Za-z]:/.test(normalized)\n}\n\n// ─── HWPX 섹션 href 해석 (parser/roundtrip 공용) ────────────────────\n\n/**\n * manifest href를 본문 섹션 경로(`Contents/sectionN.xml`)로 정규화.\n * 비본문 XML(header/script/settings)·path traversal·드라이브 경로는 null로 거른다.\n * 백슬래시 구분자를 슬래시로 통일해 parser와 roundtrip이 동일한 목록을 만든다.\n */\nexport function normalizeSectionHref(href: string): string | null {\n if (!href) return null\n let normalized = href.replace(/\\\\/g, \"/\").replace(/^\\/+/, \"\")\n if (isPathTraversal(normalized)) return null\n if (/^[Ss]ection\\d+\\.xml$/.test(normalized)) normalized = \"Contents/\" + normalized\n return /(?:^|\\/)[Ss]ection\\d+\\.xml$/.test(normalized) ? normalized : null\n}\n\n/** sectionN.xml을 N 숫자 순서로 정렬 (section10 > section2). */\nexport function compareSectionPaths(a: string, b: string): number {\n const ai = Number(a.match(/[Ss]ection(\\d+)\\.xml$/)?.[1] ?? Number.MAX_SAFE_INTEGER)\n const bi = Number(b.match(/[Ss]ection(\\d+)\\.xml$/)?.[1] ?? Number.MAX_SAFE_INTEGER)\n return ai === bi ? a.localeCompare(b) : ai - bi\n}\n\n// ─── ZIP 안전 로딩 (ZIP bomb 방지) ────────────────────\n\n/** ZIP 비압축 상한 env 의 최대값 (MB) — 오타로 사실상 무제한이 되지 않게 */\nconst MAX_UNZIP_ENV_MB = 8192\n\n/**\n * ZIP 비압축 크기 상한 — `KORDOC_MAX_UNZIP_MB` 가 양수면 그 값(MB, 최대 8192), 아니면 포맷 기본값.\n * 빈 행이 수백만 개인 XLSX 처럼 내용은 작고 XML 만 큰 실문서를 폐쇄망 대량 적재에서 받으려는 설정 (#91)\n */\nexport function unzipLimitBytes(defaultBytes: number): number {\n const mb = Number(process.env.KORDOC_MAX_UNZIP_MB)\n return Number.isFinite(mb) && mb > 0 ? Math.min(mb, MAX_UNZIP_ENV_MB) * 1024 * 1024 : defaultBytes\n}\n\n/**\n * ZIP bomb 사전 검사 — Central Directory에서 비압축 합계와 엔트리 수 확인.\n * HWPX/XLSX/DOCX 등 모든 ZIP 기반 포맷에서 공통 사용.\n */\nexport function precheckZipSize(\n buffer: ArrayBuffer,\n maxUncompressedSize = 256 * 1024 * 1024, // parser-shared MAX_DECOMPRESS_SIZE 와 동기\n maxEntries = 500,\n /** 그림·개체 파트(엔트리 이름 re) — skip 이면 합계에서 뺀다(파서가 풀지 않는다), 아니면 한도 초과 메시지에 크기를 적는다 (#108).\n * never — 파서가 어느 때도 풀지 않는 파트(동영상·음성·OLE 임베드)는 늘 뺀다: 110MB 동영상 하나로 발표 자료가 통째 거부됐다 */\n media?: { re: RegExp; skip: boolean; never?: RegExp },\n): { totalUncompressed: number; entryCount: number } {\n try {\n const data = new DataView(buffer)\n const len = buffer.byteLength\n // EOCD 시그니처 역방향 스캔\n let eocdOffset = -1\n for (let i = len - 22; i >= Math.max(0, len - 65557); i--) {\n if (data.getUint32(i, true) === 0x06054b50) { eocdOffset = i; break }\n }\n if (eocdOffset < 0) return { totalUncompressed: 0, entryCount: 0 }\n\n const entryCount = data.getUint16(eocdOffset + 10, true)\n if (entryCount > maxEntries) {\n throw new KordocError(`ZIP 엔트리 수 초과: ${entryCount} (최대 ${maxEntries})`)\n }\n\n const cdSize = data.getUint32(eocdOffset + 12, true)\n const cdOffset = data.getUint32(eocdOffset + 16, true)\n if (cdOffset + cdSize > len) return { totalUncompressed: 0, entryCount }\n\n let totalUncompressed = 0\n let mediaUncompressed = 0\n let pos = cdOffset\n for (let i = 0; i < entryCount && pos + 46 <= cdOffset + cdSize; i++) {\n if (data.getUint32(pos, true) !== 0x02014b50) break\n // 비압축 크기는 중앙 디렉터리와 지역 헤더 중 큰 값 — JSZip 은 지역 헤더 크기로 풀고(readZipEntry 가 그 크기를 넘으면 끊는다),\n // 한쪽만 작게 속여 합계 검사를 비켜 가지 못하게 둘 다 본다\n const localOff = data.getUint32(pos + 42, true)\n const localSize = localOff + 30 <= len && data.getUint32(localOff, true) === 0x04034b50 ? data.getUint32(localOff + 22, true) : 0\n const size = Math.max(data.getUint32(pos + 24, true), localSize)\n const nameLen = data.getUint16(pos + 28, true)\n const extraLen = data.getUint16(pos + 30, true)\n const commentLen = data.getUint16(pos + 32, true)\n // 이름이 버퍼 밖이면 그림 파트로 치지 않는다(합계에서 빠지지 않게)\n const isMedia = !!media && pos + 46 + nameLen <= len &&\n media.re.test(new TextDecoder().decode(new Uint8Array(buffer, pos + 46, nameLen)))\n const never = isMedia && !!media?.never && media.never.test(new TextDecoder().decode(new Uint8Array(buffer, pos + 46, nameLen)))\n if (isMedia && !never) mediaUncompressed += size\n if (!(isMedia && (media?.skip || never))) totalUncompressed += size\n pos += 46 + nameLen + extraLen + commentLen\n }\n\n if (totalUncompressed > maxUncompressedSize) {\n const mb = (n: number) => (n / 1024 / 1024).toFixed(1)\n const mediaNote = media && !media.skip && mediaUncompressed > 0\n ? ` — 그림·개체 파트가 ${mb(mediaUncompressed)}MB, 이미지 추출을 끄면(images: false·--no-images) 세지 않는다` : \"\"\n throw new KordocError(`ZIP 비압축 크기 초과: ${mb(totalUncompressed)}MB (최대 ${maxUncompressedSize / 1024 / 1024}MB)${mediaNote}`)\n }\n\n return { totalUncompressed, entryCount }\n } catch (err) {\n if (err instanceof KordocError) throw err\n return { totalUncompressed: 0, entryCount: 0 }\n }\n}\n\n/**\n * XML 파싱 전 프롤로그 정리 — 선두 BOM 제거 + DOCTYPE 제거(XXE/Billion Laughs 방지).\n *\n * BOM: 일부 OpenXML 라이터가 `[Content_Types].xml`·`.rels` 앞에 EF BB BF를 붙인다.\n * XML 스펙상 적법(엔티티는 BOM으로 시작할 수 있음)이고 엑셀·리브레오피스는 여는데,\n * xmldom은 \"선언이 문서 시작이 아님\" fatalError로 파일 전체를 거부했다 (#63).\n */\nexport function stripDtd(xml: string): string {\n return xml.replace(/^\\uFEFF/, \"\").replace(/<!DOCTYPE\\s[^[>]*(\\[[\\s\\S]*?\\])?\\s*>/gi, \"\")\n}\n\n/** 하이퍼링크 URL 살균 — javascript: 등 XSS 위험 스킴 차단 */\nconst SAFE_HREF_RE = /^(?:https?:|mailto:|tel:|#)/i\nconst HREF_ESCAPE: Record<string, string> = { \"(\": \"%28\", \")\": \"%29\", \"<\": \"%3C\", \">\": \"%3E\", \"\\\"\": \"%22\", \"'\": \"%27\", \"`\": \"%60\" }\nexport function sanitizeHref(href: string): string | null {\n const trimmed = href.trim()\n if (!trimmed || !SAFE_HREF_RE.test(trimmed)) return null\n // 괄호 percent-encoding — 마크다운 링크 목적지에서 불균형 ')'는 링크를 조기 종료시켜\n // 문법이 깨진다 (원문 하이퍼링크에 ')'가 박힌 실문서 존재). %28/%29는 의미 동일.\n // 공백·<>\"'` 도 — 스킴만 보고 통과시키면 \"mailto:a <img src=x onerror=…>\" 가 링크 목적지를 깨고 날 태그로\n // 렌더됐다(pdfjs 는 mailto·tel URI 를 정규화하지 않는다, v4.14.4 리뷰 재현). 인코딩해도 같은 주소다\n return trimmed.replace(/[()<>\"'`]/g, c => HREF_ESCAPE[c]).replace(/\\s/g, c => encodeURIComponent(c))\n}\n\n/**\n * HTML 엔티티 이스케이프 — 글은 `& < >`, 속성값(attr)은 `\"` 까지. HTML 표 경로(builder tableToHtml)와\n * 인쇄 렌더러가 같이 쓰는 한 벌. 읽는 쪽은 unescapeHtml 로 푼다\n */\nexport function escapeHtml(text: string, attr = false): string {\n const s = text.replace(/&/g, \"&\").replace(/</g, \"<\").replace(/>/g, \">\")\n return attr ? s.replace(/\"/g, \""\") : s\n}\n\n/** escapeHtml 의 역 (+ 손으로 쓴 HTML 표의 ') — 한 번에 풀어 \"&lt;\" 는 \"<\" 로 남는다 */\nexport function unescapeHtml(text: string): string {\n return text.replace(/&(lt|gt|quot|#39|amp);/g, (_, e: string) => HTML_ENTITY[e])\n}\nconst HTML_ENTITY: Record<string, string> = { lt: \"<\", gt: \">\", quot: \"\\\"\", \"#39\": \"'\", amp: \"&\" }\n\n/**\n * console.log·info·warn·debug 를 stderr 로 — stdout 이 기계 출력 채널(MCP JSON-RPC·CLI 마크다운/JSON·parse-worker\n * NDJSON)인 진입점용. 라이브러리(pdfjs 등)가 console 로 찍는 경고가 그 채널을 깨지 않게 한다\n */\nexport function routeConsoleToStderr(): void {\n const toStderr = (...args: unknown[]): void => void process.stderr.write(format(...args) + \"\\n\")\n console.log = toStderr\n console.info = toStderr\n console.warn = toStderr\n console.debug = toStderr\n}\n\n// ─── 안전한 min/max (스택 오버플로 방지) ─────────────\n\n/** Math.min(...arr) 대체 — 대형 배열에서 스택 오버플로 방지 */\nexport function safeMin(arr: number[]): number {\n let min = Infinity\n for (let i = 0; i < arr.length; i++) if (arr[i] < min) min = arr[i]\n return min\n}\n\n/** Math.max(...arr) 대체 — 대형 배열에서 스택 오버플로 방지 */\nexport function safeMax(arr: number[]): number {\n let max = -Infinity\n for (let i = 0; i < arr.length; i++) if (arr[i] > max) max = arr[i]\n return max\n}\n\n// ─── 에러 분류 ──────────────────────────────────────\n\nimport type { ErrorCode } from \"./types.js\"\n\n/** 에러를 구조화된 ErrorCode로 분류 — KordocError 메시지 패턴 매칭 */\n/** 선택 의존 설치 실패 안내 꼬리 — 네트워크가 막힌 linux/x64 에서 onnxruntime-node 설치 스크립트가 CUDA 바이너리를 받다 실패하면\n * npm 이 sharp·@huggingface/tokenizers 까지 선택 의존 설치에서 뺀다(#99). npx 캐시 실행은 npm install 로 못 고친다 */\nexport const OPTIONAL_DEP_INSTALL_HINT =\n \" 네트워크가 제한된 linux/x64 에서 npx 로 설치했다면 onnxruntime-node 의 CUDA 다운로드 실패로 함께 빠졌을 수 있습니다 — \" +\n \"`ONNXRUNTIME_NODE_INSTALL=skip npx -y kordoc@^4 …` 로 다시 설치하세요.\"\n\nexport function classifyError(err: unknown): ErrorCode {\n if (!(err instanceof Error)) return \"PARSE_ERROR\"\n const msg = err.message\n // 입력 파일 없음 — 문서 내용 문제가 아니라 호출자의 경로 문제라 PARSE_ERROR 로 덮지 않는다.\n if (isFileNotFound(err)) return \"FILE_NOT_FOUND\"\n // DRM 을 암호화보다 먼저 — \"DRM 암호화된 HWPX…\" 류 메시지가 ENCRYPTED 로 떨어지지 않도록\n if (msg.includes(\"DRM\")) return \"DRM_PROTECTED\"\n if (msg.includes(\"암호화\") || msg.includes(\"암호로 보호\")) return \"ENCRYPTED\"\n if (msg.includes(\"optional dependency\")) return \"MISSING_DEPENDENCY\"\n // V8 문자열 한계 초과 — 이미지 base64 총량이 큰 문서의 JSON 직렬화 (#65)\n if (msg.includes(\"Invalid string length\") || msg.includes(\"Cannot create a string longer\")) return \"OUTPUT_TOO_LARGE\"\n if (msg.includes(\"ZIP bomb\") || msg.includes(\"ZIP 비압축 크기 초과\") || msg.includes(\"ZIP 엔트리 수 초과\")) return \"ZIP_BOMB\"\n if (msg.includes(\"bomb\") || msg.includes(\"크기 초과\") || msg.includes(\"압축 해제\")) return \"DECOMPRESSION_BOMB\"\n if (msg.includes(\"이미지 기반\")) return \"IMAGE_BASED_PDF\"\n if (msg.includes(\"섹션\") && (msg.includes(\"찾을 수 없\") || msg.includes(\"없음\"))) return \"NO_SECTIONS\"\n if (msg.includes(\"시그니처\") || msg.includes(\"복구할 수 없\")) return \"CORRUPTED\"\n return \"PARSE_ERROR\"\n}\n\n/** ZIP 파트 경로의 확장자 — 마지막 경로 조각에서만, 없으면 \"bin\". \"ppt/media.v2/image1\" 의 \"v2/image1\" 이 그림 파일 이름에 들어가\n * 저장 경로가 깨졌다 */\nexport function partExtension(path: string): string {\n return (/\\.([A-Za-z0-9]{1,5})$/.exec(path.slice(path.lastIndexOf(\"/\") + 1))?.[1] ?? \"bin\").toLowerCase()\n}\n"]}
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
import {
|
|
3
3
|
escapeHtml,
|
|
4
4
|
sanitizeHref
|
|
5
|
-
} from "./chunk-
|
|
5
|
+
} from "./chunk-UIZYWW3J.js";
|
|
6
6
|
|
|
7
7
|
// src/shared/symbol-fonts.ts
|
|
8
8
|
var WINGDINGS = [
|
|
@@ -1179,4 +1179,4 @@ export {
|
|
|
1179
1179
|
visibleText,
|
|
1180
1180
|
escapeHtmlCellText
|
|
1181
1181
|
};
|
|
1182
|
-
//# sourceMappingURL=chunk-
|
|
1182
|
+
//# sourceMappingURL=chunk-5NBUT7GX.js.map
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
import {
|
|
2
2
|
blocksToMarkdown
|
|
3
|
-
} from "./chunk-
|
|
3
|
+
} from "./chunk-2URKNOOQ.js";
|
|
4
4
|
|
|
5
5
|
// src/image/transcode.ts
|
|
6
6
|
import { deflateSync } from "zlib";
|
|
@@ -168,4 +168,4 @@ export {
|
|
|
168
168
|
inlineImagesIntoMarkdown,
|
|
169
169
|
blocksToPages
|
|
170
170
|
};
|
|
171
|
-
//# sourceMappingURL=chunk-
|
|
171
|
+
//# sourceMappingURL=chunk-67DVZL4W.js.map
|
|
@@ -5,7 +5,7 @@ import {
|
|
|
5
5
|
import {
|
|
6
6
|
UNRULED_REGION_TABLES,
|
|
7
7
|
extractPageBlocksWithLines
|
|
8
|
-
} from "./chunk-
|
|
8
|
+
} from "./chunk-XCSWST2A.js";
|
|
9
9
|
import {
|
|
10
10
|
validateOcrOptions
|
|
11
11
|
} from "./chunk-BYMPPVT3.js";
|
|
@@ -16,11 +16,11 @@ import {
|
|
|
16
16
|
ocrSourcePath,
|
|
17
17
|
parseCharacterDict,
|
|
18
18
|
resolveOcrModels
|
|
19
|
-
} from "./chunk-
|
|
19
|
+
} from "./chunk-YFCE7J37.js";
|
|
20
20
|
import {
|
|
21
21
|
KordocError,
|
|
22
22
|
OPTIONAL_DEP_INSTALL_HINT
|
|
23
|
-
} from "./chunk-
|
|
23
|
+
} from "./chunk-UIZYWW3J.js";
|
|
24
24
|
|
|
25
25
|
// src/ocr/ruling-lines.ts
|
|
26
26
|
var INK_LUMA_MAX = 205;
|
|
@@ -2215,4 +2215,4 @@ export {
|
|
|
2215
2215
|
groupOcrLines,
|
|
2216
2216
|
ocrItemsToBlocks
|
|
2217
2217
|
};
|
|
2218
|
-
//# sourceMappingURL=chunk-
|
|
2218
|
+
//# sourceMappingURL=chunk-6BUW4PJ3.js.map
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
import {
|
|
3
3
|
KordocError,
|
|
4
4
|
OPTIONAL_DEP_INSTALL_HINT
|
|
5
|
-
} from "./chunk-
|
|
5
|
+
} from "./chunk-UIZYWW3J.js";
|
|
6
6
|
|
|
7
7
|
// src/render/rasterize.ts
|
|
8
8
|
var densityExponent = null;
|
|
@@ -88,4 +88,4 @@ export {
|
|
|
88
88
|
rasterizeSvg,
|
|
89
89
|
rasterizePageSvg
|
|
90
90
|
};
|
|
91
|
-
//# sourceMappingURL=chunk-
|
|
91
|
+
//# sourceMappingURL=chunk-6O2AUXFB.js.map
|
|
@@ -4,15 +4,15 @@ import {
|
|
|
4
4
|
HEADING_RATIO_H2,
|
|
5
5
|
HEADING_RATIO_H3,
|
|
6
6
|
tidyScriptTags
|
|
7
|
-
} from "./chunk-
|
|
7
|
+
} from "./chunk-2URKNOOQ.js";
|
|
8
8
|
import {
|
|
9
9
|
ensureModelsIn,
|
|
10
10
|
getModelsDir
|
|
11
|
-
} from "./chunk-
|
|
11
|
+
} from "./chunk-2CHTPRDU.js";
|
|
12
12
|
import {
|
|
13
13
|
safeMax,
|
|
14
14
|
safeMin
|
|
15
|
-
} from "./chunk-
|
|
15
|
+
} from "./chunk-Y3LLNEU3.js";
|
|
16
16
|
|
|
17
17
|
// src/ocr/models.ts
|
|
18
18
|
import { join } from "path";
|
|
@@ -9118,4 +9118,4 @@ export {
|
|
|
9118
9118
|
UNRULED_REGION_TABLES,
|
|
9119
9119
|
mergeOcrImageRegions
|
|
9120
9120
|
};
|
|
9121
|
-
//# sourceMappingURL=chunk-
|
|
9121
|
+
//# sourceMappingURL=chunk-A5HW2Z5T.js.map
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
#!/usr/bin/env node
|
|
2
2
|
import {
|
|
3
3
|
visibleText
|
|
4
|
-
} from "./chunk-
|
|
4
|
+
} from "./chunk-5NBUT7GX.js";
|
|
5
5
|
|
|
6
6
|
// src/script-tags.ts
|
|
7
7
|
var LITERAL_TAG = /<(?=\/?(?:u|sup|sub)>)/g;
|
|
@@ -328,4 +328,4 @@ export {
|
|
|
328
328
|
HEADING_RATIO_H2,
|
|
329
329
|
HEADING_RATIO_H3
|
|
330
330
|
};
|
|
331
|
-
//# sourceMappingURL=chunk-
|
|
331
|
+
//# sourceMappingURL=chunk-GZFL6UOS.js.map
|
|
@@ -10,14 +10,14 @@ var _chunkTK3FDAEEcjs = require('./chunk-TK3FDAEE.cjs');
|
|
|
10
10
|
|
|
11
11
|
|
|
12
12
|
|
|
13
|
-
var
|
|
13
|
+
var _chunkQXIZ5XSBcjs = require('./chunk-QXIZ5XSB.cjs');
|
|
14
14
|
|
|
15
15
|
|
|
16
|
-
var
|
|
16
|
+
var _chunkIOBVLL5Acjs = require('./chunk-IOBVLL5A.cjs');
|
|
17
17
|
|
|
18
18
|
|
|
19
19
|
|
|
20
|
-
var
|
|
20
|
+
var _chunk5KLO56CJcjs = require('./chunk-5KLO56CJ.cjs');
|
|
21
21
|
|
|
22
22
|
// src/ocr/ruling-lines.ts
|
|
23
23
|
var INK_LUMA_MAX = 205;
|
|
@@ -1410,7 +1410,7 @@ var OcrEngine = class _OcrEngine {
|
|
|
1410
1410
|
this.ort = parts.ort;
|
|
1411
1411
|
this.sharp = parts.sharp;
|
|
1412
1412
|
}
|
|
1413
|
-
static async create(models =
|
|
1413
|
+
static async create(models = _chunkQXIZ5XSBcjs.DEFAULT_OCR_MODELS) {
|
|
1414
1414
|
_chunkTK3FDAEEcjs.disableOrtTelemetry.call(void 0, );
|
|
1415
1415
|
const [ortMod, sharpModRaw] = await Promise.all([
|
|
1416
1416
|
tryImport("onnxruntime-node", () => Promise.resolve().then(() => _interopRequireWildcard(require("onnxruntime-node")))),
|
|
@@ -1430,16 +1430,16 @@ var OcrEngine = class _OcrEngine {
|
|
|
1430
1430
|
const local = (s) => "spec" in s ? Promise.resolve(null) : verifiedBytes(s);
|
|
1431
1431
|
const [detBytes, recBytes, dictBytes] = await Promise.all([local(models.det), local(models.rec), local(models.dict)]);
|
|
1432
1432
|
const session = (s, bytes) => bytes ? ortMod.InferenceSession.create(bytes, sessionOpts).catch(() => {
|
|
1433
|
-
throw new (0,
|
|
1434
|
-
}) : ortMod.InferenceSession.create(
|
|
1433
|
+
throw new (0, _chunk5KLO56CJcjs.KordocError)(`OCR \uBAA8\uB378\uC744 \uC5F4\uC9C0 \uBABB\uD588\uC2B5\uB2C8\uB2E4: ${_path.basename.call(void 0, _chunkQXIZ5XSBcjs.ocrSourcePath.call(void 0, s))} \u2014 ONNX \uBAA8\uB378\uC774 \uC544\uB2C8\uAC70\uB098 \uC190\uC0C1\uB410\uC2B5\uB2C8\uB2E4`);
|
|
1434
|
+
}) : ortMod.InferenceSession.create(_chunkQXIZ5XSBcjs.ocrSourcePath.call(void 0, s), sessionOpts);
|
|
1435
1435
|
const [det, rec, dictYml] = await Promise.all([
|
|
1436
1436
|
session(models.det, detBytes),
|
|
1437
1437
|
session(models.rec, recBytes),
|
|
1438
|
-
dictBytes ? new TextDecoder().decode(dictBytes) : _promises.readFile.call(void 0,
|
|
1438
|
+
dictBytes ? new TextDecoder().decode(dictBytes) : _promises.readFile.call(void 0, _chunkQXIZ5XSBcjs.ocrSourcePath.call(void 0, models.dict), "utf-8")
|
|
1439
1439
|
]);
|
|
1440
|
-
const dict =
|
|
1440
|
+
const dict = _chunkQXIZ5XSBcjs.parseCharacterDict.call(void 0, dictYml);
|
|
1441
1441
|
if (dict.length === 0) {
|
|
1442
|
-
throw "spec" in models.dict ? new Error("OCR \uC0AC\uC804 \uD30C\uC2F1 \uC2E4\uD328 \u2014 \uBAA8\uB378 \uCE90\uC2DC\uB97C \uC0AD\uC81C \uD6C4 \uC7AC\uB2E4\uC6B4\uB85C\uB4DC\uD558\uC138\uC694") : new (0,
|
|
1442
|
+
throw "spec" in models.dict ? new Error("OCR \uC0AC\uC804 \uD30C\uC2F1 \uC2E4\uD328 \u2014 \uBAA8\uB378 \uCE90\uC2DC\uB97C \uC0AD\uC81C \uD6C4 \uC7AC\uB2E4\uC6B4\uB85C\uB4DC\uD558\uC138\uC694") : new (0, _chunk5KLO56CJcjs.KordocError)(`OCR \uC0AC\uC804 \uD30C\uC2F1 \uC2E4\uD328 \u2014 ${_path.basename.call(void 0, models.dict.file.path)} \uC5D0 PostProcess.character_dict \uBAA9\uB85D\uC774 \uC5C6\uC2B5\uB2C8\uB2E4`);
|
|
1443
1443
|
}
|
|
1444
1444
|
return new _OcrEngine({ det, rec, dict, ort: ortMod, sharp: sharpMod });
|
|
1445
1445
|
}
|
|
@@ -1648,7 +1648,7 @@ var OcrEngine = class _OcrEngine {
|
|
|
1648
1648
|
const out = await this.rec.run({ [this.rec.inputNames[0]]: tensor });
|
|
1649
1649
|
const logits = out[this.rec.outputNames[0]];
|
|
1650
1650
|
const [, T, C] = logits.dims;
|
|
1651
|
-
if (C !== this.dict.length + 2) throw new (0,
|
|
1651
|
+
if (C !== this.dict.length + 2) throw new (0, _chunk5KLO56CJcjs.KordocError)(`OCR rec \uCD9C\uB825 \uD074\uB798\uC2A4 ${C}\uAC1C\uAC00 \uC0AC\uC804 ${this.dict.length}\uC790 + 2 \uC640 \uB2E4\uB985\uB2C8\uB2E4 \u2014 \uBAA8\uB378\uC5D0 \uB9DE\uB294 \uC0AC\uC804(ocrRecDict)\uC744 \uC9C0\uC815\uD558\uC138\uC694`);
|
|
1652
1652
|
const data = logits.data;
|
|
1653
1653
|
idx.forEach((ci, k) => {
|
|
1654
1654
|
const r = ctcDecode(data.subarray(k * T * C, (k + 1) * T * C), T, C, this.dict);
|
|
@@ -1771,13 +1771,13 @@ async function tryImport(name, loader) {
|
|
|
1771
1771
|
return await loader();
|
|
1772
1772
|
} catch (e) {
|
|
1773
1773
|
throw new Error(
|
|
1774
|
-
`\uB0B4\uC7A5 OCR \uC744 \uC0AC\uC6A9\uD558\uB824\uBA74 optional dependency '${name}' \uC774 \uD544\uC694\uD569\uB2C8\uB2E4. \`npm install ${name}\` \uD6C4 \uB2E4\uC2DC \uC2E4\uD589\uD558\uC138\uC694.${
|
|
1774
|
+
`\uB0B4\uC7A5 OCR \uC744 \uC0AC\uC6A9\uD558\uB824\uBA74 optional dependency '${name}' \uC774 \uD544\uC694\uD569\uB2C8\uB2E4. \`npm install ${name}\` \uD6C4 \uB2E4\uC2DC \uC2E4\uD589\uD558\uC138\uC694.${_chunk5KLO56CJcjs.OPTIONAL_DEP_INSTALL_HINT} \uC6D0\uC778: ${e.message}`
|
|
1775
1775
|
);
|
|
1776
1776
|
}
|
|
1777
1777
|
}
|
|
1778
1778
|
async function verifiedBytes(s) {
|
|
1779
1779
|
const name = _path.basename.call(void 0, s.file.path);
|
|
1780
|
-
const fail = (why2) => new (0,
|
|
1780
|
+
const fail = (why2) => new (0, _chunk5KLO56CJcjs.KordocError)(`OCR \uBAA8\uB378 \uD30C\uC77C\uC744 \uC77D\uC9C0 \uBABB\uD588\uC2B5\uB2C8\uB2E4: ${name} (${why2})`);
|
|
1781
1781
|
const why = (e) => {
|
|
1782
1782
|
const code = e.code;
|
|
1783
1783
|
return code === "ENOENT" ? "\uD30C\uC77C\uC774 \uC5C6\uC74C" : code === "EACCES" || code === "EPERM" ? "\uAD8C\uD55C \uC5C6\uC74C" : "\uC77D\uAE30 \uC2E4\uD328";
|
|
@@ -1798,13 +1798,13 @@ async function verifiedBytes(s) {
|
|
|
1798
1798
|
}
|
|
1799
1799
|
const actual = _crypto.createHash.call(void 0, "sha256").update(bytes).digest("hex");
|
|
1800
1800
|
if (actual !== s.file.sha256) {
|
|
1801
|
-
throw new (0,
|
|
1801
|
+
throw new (0, _chunk5KLO56CJcjs.KordocError)(`OCR \uBAA8\uB378 SHA256 mismatch: ${_path.basename.call(void 0, s.file.path)} \u2014 expected ${s.file.sha256}, got ${actual} (\uB85C\uB4DC \uAC70\uBD80)`);
|
|
1802
1802
|
}
|
|
1803
1803
|
return bytes;
|
|
1804
1804
|
}
|
|
1805
1805
|
var engines = /* @__PURE__ */ new Map();
|
|
1806
|
-
function getOcrEngine(models =
|
|
1807
|
-
const key =
|
|
1806
|
+
function getOcrEngine(models = _chunkQXIZ5XSBcjs.DEFAULT_OCR_MODELS) {
|
|
1807
|
+
const key = _chunkQXIZ5XSBcjs.ocrSelectionKey.call(void 0, models);
|
|
1808
1808
|
let p = engines.get(key);
|
|
1809
1809
|
if (!p) {
|
|
1810
1810
|
p = OcrEngine.create(models).catch((err) => {
|
|
@@ -1907,13 +1907,13 @@ function rotateRgba(rgba, width, height, deg) {
|
|
|
1907
1907
|
var OCR_RENDER_SCALE = 3;
|
|
1908
1908
|
var MAX_OCR_PIXELS = 24e6;
|
|
1909
1909
|
var PAGE_TIMEOUT_MS = 12e4;
|
|
1910
|
-
var DEFAULT_BUILTIN_OCR = Object.freeze({ models:
|
|
1910
|
+
var DEFAULT_BUILTIN_OCR = Object.freeze({ models: _chunkQXIZ5XSBcjs.DEFAULT_OCR_MODELS, tuning: DEFAULT_OCR_TUNING });
|
|
1911
1911
|
function builtinOcrConfig(o) {
|
|
1912
1912
|
if (!o || o.ocrDet === void 0 && o.ocrDetLongSide === void 0 && o.ocrRec === void 0 && o.ocrRecDict === void 0 && !o.ocrLines) return DEFAULT_BUILTIN_OCR;
|
|
1913
|
-
const bad =
|
|
1914
|
-
if (bad) throw new (0,
|
|
1913
|
+
const bad = _chunkIOBVLL5Acjs.validateOcrOptions.call(void 0, o);
|
|
1914
|
+
if (bad) throw new (0, _chunk5KLO56CJcjs.KordocError)(bad);
|
|
1915
1915
|
return {
|
|
1916
|
-
models:
|
|
1916
|
+
models: _chunkQXIZ5XSBcjs.resolveOcrModels.call(void 0, o),
|
|
1917
1917
|
tuning: o.ocrDetLongSide === void 0 ? DEFAULT_OCR_TUNING : { ...DEFAULT_OCR_TUNING, detLongSide: o.ocrDetLongSide },
|
|
1918
1918
|
lines: o.ocrLines === "all" ? "all" : o.ocrLines ? "kept" : void 0
|
|
1919
1919
|
};
|
|
@@ -1939,7 +1939,7 @@ async function runPdfOcr(buffer, targets, mode, warnings, onProgress, detectTabl
|
|
|
1939
1939
|
"@hyzyla/pdfium",
|
|
1940
1940
|
() => Promise.resolve().then(() => _interopRequireWildcard(require("@hyzyla/pdfium")))
|
|
1941
1941
|
);
|
|
1942
|
-
if (mode === "builtin") await
|
|
1942
|
+
if (mode === "builtin") await _chunkQXIZ5XSBcjs.ensureOcrModelsFor.call(void 0, config.models, reportModelDownload);
|
|
1943
1943
|
const engine = mode === "builtin" ? await getOcrEngine(config.models) : null;
|
|
1944
1944
|
const pdfium = await pdfiumMod.PDFiumLibrary.init();
|
|
1945
1945
|
const doc = await pdfium.loadDocument(new Uint8Array(buffer));
|
|
@@ -2023,7 +2023,7 @@ async function ocrOnePage(page, pageNo, mode, engine, warnings, detectTables, ve
|
|
|
2023
2023
|
const x1 = r.x1 * scale - 2, x2 = r.x2 * scale + 2, y1 = (pdfH - r.y2) * scale - 2, y2 = (pdfH - r.y1) * scale + 2;
|
|
2024
2024
|
const columnRules = _nullishCoalesce(_optionalChain([ruling, 'optionalAccess', _26 => _26.verticals, 'access', _27 => _27.filter, 'call', _28 => _28((s) => Math.min(s.x1, s.x2) >= x1 && Math.max(s.x1, s.x2) <= x2 && Math.min(s.y1, s.y2) >= y1 && Math.max(s.y1, s.y2) <= y2), 'access', _29 => _29.length]), () => ( 0));
|
|
2025
2025
|
if (columnRules < 2) {
|
|
2026
|
-
for (const b of blocks) if (b.type === "table")
|
|
2026
|
+
for (const b of blocks) if (b.type === "table") _chunkQXIZ5XSBcjs.UNRULED_REGION_TABLES.add(b);
|
|
2027
2027
|
}
|
|
2028
2028
|
return blocks;
|
|
2029
2029
|
});
|
|
@@ -2159,14 +2159,14 @@ function ocrItemsToBlocks(items, pageNumber, pdfW, pdfH, scale, extraLines, dete
|
|
|
2159
2159
|
...xs[i].space ? { hasSpaceBefore: true } : {}
|
|
2160
2160
|
};
|
|
2161
2161
|
});
|
|
2162
|
-
return
|
|
2162
|
+
return _chunkQXIZ5XSBcjs.extractPageBlocksWithLines.call(void 0, norm, pageNumber, opList, pdfW, pdfH, extraLines, detectTables);
|
|
2163
2163
|
}
|
|
2164
2164
|
async function tryImport2(name, loader) {
|
|
2165
2165
|
try {
|
|
2166
2166
|
return await loader();
|
|
2167
2167
|
} catch (e) {
|
|
2168
2168
|
throw new Error(
|
|
2169
|
-
`OCR \uC744 \uC0AC\uC6A9\uD558\uB824\uBA74 optional dependency '${name}' \uC774 \uD544\uC694\uD569\uB2C8\uB2E4. \`npm install ${name}\` \uD6C4 \uB2E4\uC2DC \uC2E4\uD589\uD558\uC138\uC694.${
|
|
2169
|
+
`OCR \uC744 \uC0AC\uC6A9\uD558\uB824\uBA74 optional dependency '${name}' \uC774 \uD544\uC694\uD569\uB2C8\uB2E4. \`npm install ${name}\` \uD6C4 \uB2E4\uC2DC \uC2E4\uD589\uD558\uC138\uC694.${_chunk5KLO56CJcjs.OPTIONAL_DEP_INSTALL_HINT} \uC6D0\uC778: ${e.message}`
|
|
2170
2170
|
);
|
|
2171
2171
|
}
|
|
2172
2172
|
}
|
|
@@ -2212,4 +2212,4 @@ function bgraToRgba(bgra) {
|
|
|
2212
2212
|
|
|
2213
2213
|
|
|
2214
2214
|
exports.getOcrEngine = getOcrEngine; exports.detectRulingLines = detectRulingLines; exports.rulingToPdfLines = rulingToPdfLines; exports.deskewPage = deskewPage; exports.MAX_OCR_PIXELS = MAX_OCR_PIXELS; exports.DEFAULT_BUILTIN_OCR = DEFAULT_BUILTIN_OCR; exports.builtinOcrConfig = builtinOcrConfig; exports.reportModelDownload = reportModelDownload; exports.toOcrLine = toOcrLine; exports.pageLines = pageLines; exports.runPdfOcr = runPdfOcr; exports.ocrOnePage = ocrOnePage; exports.groupOcrLines = groupOcrLines; exports.ocrItemsToBlocks = ocrItemsToBlocks;
|
|
2215
|
-
//# sourceMappingURL=chunk-
|
|
2215
|
+
//# sourceMappingURL=chunk-I22NWH6W.cjs.map
|