kordoc 4.21.21 → 4.21.23
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 +6 -4
- package/dist/{-ZYF6HX4M.js → -FLEBKE6V.js} +25 -25
- package/dist/{chunk-QHNVH4TC.js → chunk-2S37CQUJ.js} +21 -21
- package/dist/{chunk-YM3K3LCD.js → chunk-4F6OVO2A.js} +122 -46
- package/dist/chunk-4F6OVO2A.js.map +1 -0
- package/dist/{chunk-ZZIQWSGC.js → chunk-75J4Y5ZQ.js} +2 -2
- package/dist/{chunk-7YAJCXCD.js → chunk-7MTKOSAF.js} +2 -2
- package/dist/{chunk-KBV4WFZ6.js → chunk-C3RR6Z3M.js} +4 -4
- package/dist/{chunk-KBV4WFZ6.js.map → chunk-C3RR6Z3M.js.map} +1 -1
- package/dist/{chunk-TRO4CQHJ.js → chunk-CA742RMF.js} +4 -4
- package/dist/{chunk-CY4QM2KQ.js → chunk-DACTHSPR.js} +2 -2
- package/dist/{chunk-DTZIZ5PP.cjs → chunk-EGYLKSA4.cjs} +13 -13
- package/dist/{chunk-DTZIZ5PP.cjs.map → chunk-EGYLKSA4.cjs.map} +1 -1
- package/dist/{chunk-T7PN5D4D.cjs → chunk-EVPP2BSO.cjs} +6 -6
- package/dist/{chunk-T7PN5D4D.cjs.map → chunk-EVPP2BSO.cjs.map} +1 -1
- package/dist/{chunk-TMUUDMDH.cjs → chunk-GELBKBGQ.cjs} +23 -23
- package/dist/{chunk-TMUUDMDH.cjs.map → chunk-GELBKBGQ.cjs.map} +1 -1
- package/dist/{chunk-FBJVDBMO.js → chunk-GNIOEZDG.js} +2 -2
- package/dist/{chunk-RBRHO7WL.js → chunk-GPIMKPEI.js} +2 -2
- package/dist/{chunk-MCUX2Y2C.cjs → chunk-GUU7OHIH.cjs} +2 -2
- package/dist/{chunk-MCUX2Y2C.cjs.map → chunk-GUU7OHIH.cjs.map} +1 -1
- package/dist/{chunk-5HTFWUJE.js → chunk-J25WF6DP.js} +2 -2
- package/dist/{chunk-HWIW3WK2.js → chunk-JA4ZWCYL.js} +3 -3
- package/dist/{chunk-2ZGP7A5T.js → chunk-JLG7KK4M.js} +2 -2
- package/dist/{chunk-3TCF5HPP.js → chunk-JUA7IACQ.js} +2 -2
- package/dist/{chunk-YQZOPT3A.js → chunk-L4NFUEWJ.js} +5 -5
- package/dist/{chunk-YQZOPT3A.js.map → chunk-L4NFUEWJ.js.map} +1 -1
- package/dist/{chunk-T3DTTK23.js → chunk-QRIGJUOQ.js} +26 -25
- package/dist/chunk-QRIGJUOQ.js.map +1 -0
- package/dist/{chunk-J5PBI3ZC.js → chunk-RDV2RHVH.js} +3 -3
- package/dist/{chunk-YHPJTLCA.js → chunk-RKWJMA2B.js} +2 -2
- package/dist/{chunk-FZMGF6XU.js → chunk-TAU45SJK.js} +2 -2
- package/dist/{chunk-BG6LUCQL.js → chunk-U6D7LUCR.js} +2 -2
- package/dist/{chunk-BC54LBST.js → chunk-UKLNKY7Q.js} +3 -3
- package/dist/{chunk-H2MS4VG3.cjs → chunk-VA43X5N4.cjs} +3 -3
- package/dist/{chunk-H2MS4VG3.cjs.map → chunk-VA43X5N4.cjs.map} +1 -1
- package/dist/{chunk-7FCNOKOR.js → chunk-VKVDMH7X.js} +2 -1
- package/dist/{chunk-KTLHADU4.js → chunk-XEUBMLAS.js} +2 -2
- package/dist/{chunk-57VNFMMS.cjs → chunk-Y7XHHV55.cjs} +28 -27
- package/dist/chunk-Y7XHHV55.cjs.map +1 -0
- package/dist/{chunk-PTF4NCFM.js → chunk-YA6UGARL.js} +2 -2
- package/dist/{chunk-WGMYVRSA.js → chunk-ZE77KLKN.js} +2 -2
- package/dist/chunks-PR2GRNLX.js +10 -0
- package/dist/cli.js +34 -34
- package/dist/{formula-P7M7IH2L.js → formula-2MTBKZKO.js} +4 -4
- package/dist/{formula-A3I5VAP7.cjs → formula-CY2HF27M.cjs} +9 -9
- package/dist/{formula-A3I5VAP7.cjs.map → formula-CY2HF27M.cjs.map} +1 -1
- package/dist/{formula-6XNIXZ5L.js → formula-LGLSIYDI.js} +3 -3
- package/dist/{image-ocr-ITNY454I.js → image-ocr-BKRQVMW6.js} +9 -9
- package/dist/{image-ocr-UJRSQ2T3.cjs → image-ocr-HJM5IJKU.cjs} +15 -15
- package/dist/{image-ocr-UJRSQ2T3.cjs.map → image-ocr-HJM5IJKU.cjs.map} +1 -1
- package/dist/{image-ocr-3C6W3KZO.js → image-ocr-HP65O2CC.js} +6 -6
- package/dist/index.cjs +653 -577
- package/dist/index.cjs.map +1 -1
- package/dist/index.js +83 -7
- package/dist/index.js.map +1 -1
- package/dist/mcp.js +28 -28
- package/dist/{model-bundle-LAWQH75O.js → model-bundle-M7YMF4L4.js} +5 -5
- package/dist/{models-6QTD2CFM.js → models-AMPRHBYB.js} +5 -5
- package/dist/{parse-worker-v2-FEPJG3ER.js → parse-worker-v2-NMYEMVYX.js} +14 -14
- package/dist/{parser-VKWUMUML.cjs → parser-J6M4WG3I.cjs} +136 -136
- package/dist/{parser-VKWUMUML.cjs.map → parser-J6M4WG3I.cjs.map} +1 -1
- package/dist/{parser-56I364YM.js → parser-LX5MOE6Q.js} +8 -8
- package/dist/{parser-KFCY3NIN.js → parser-M45SFXWF.js} +22 -22
- package/dist/pdf-ocr-4YVV5PT4.cjs +19 -0
- package/dist/{pdf-ocr-OKAHNEJA.cjs.map → pdf-ocr-4YVV5PT4.cjs.map} +1 -1
- package/dist/pdf-ocr-D73YYQJ5.js +18 -0
- package/dist/pdf-ocr-SLWZO4D2.js +22 -0
- package/dist/{profile-io-OCITHUQF.js → profile-io-CUMSC3TD.js} +3 -3
- package/dist/{rasterize-SFCG4YOI.js → rasterize-W6NY4ADH.js} +3 -3
- package/dist/{redact-doc-5SMPXIGG.js → redact-doc-7HVCZT3C.js} +25 -25
- package/dist/{render-FGPG5A2N.js → render-FPMJX4CU.js} +9 -9
- package/dist/seal-YTRVR373.js +10 -0
- package/dist/{setup-JQVYZO7I.js → setup-UKIYOUT6.js} +3 -3
- package/dist/visual-DG5EVBZD.js +20 -0
- package/dist/{watch-C77BUSP7.js → watch-YHKMAVJ6.js} +16 -16
- package/package.json +1 -1
- package/dist/chunk-57VNFMMS.cjs.map +0 -1
- package/dist/chunk-T3DTTK23.js.map +0 -1
- package/dist/chunk-YM3K3LCD.js.map +0 -1
- package/dist/chunks-MDMJRCJ7.js +0 -10
- package/dist/pdf-ocr-MME37BL4.js +0 -18
- package/dist/pdf-ocr-OKAHNEJA.cjs +0 -19
- package/dist/pdf-ocr-ZZ6AJL6Z.js +0 -22
- package/dist/seal-GA7NZDTG.js +0 -10
- package/dist/visual-YMG644YW.js +0 -20
- /package/dist/{-ZYF6HX4M.js.map → -FLEBKE6V.js.map} +0 -0
- /package/dist/{chunk-QHNVH4TC.js.map → chunk-2S37CQUJ.js.map} +0 -0
- /package/dist/{chunk-ZZIQWSGC.js.map → chunk-75J4Y5ZQ.js.map} +0 -0
- /package/dist/{chunk-7YAJCXCD.js.map → chunk-7MTKOSAF.js.map} +0 -0
- /package/dist/{chunk-TRO4CQHJ.js.map → chunk-CA742RMF.js.map} +0 -0
- /package/dist/{chunk-CY4QM2KQ.js.map → chunk-DACTHSPR.js.map} +0 -0
- /package/dist/{chunk-FBJVDBMO.js.map → chunk-GNIOEZDG.js.map} +0 -0
- /package/dist/{chunk-RBRHO7WL.js.map → chunk-GPIMKPEI.js.map} +0 -0
- /package/dist/{chunk-5HTFWUJE.js.map → chunk-J25WF6DP.js.map} +0 -0
- /package/dist/{chunk-HWIW3WK2.js.map → chunk-JA4ZWCYL.js.map} +0 -0
- /package/dist/{chunk-2ZGP7A5T.js.map → chunk-JLG7KK4M.js.map} +0 -0
- /package/dist/{chunk-3TCF5HPP.js.map → chunk-JUA7IACQ.js.map} +0 -0
- /package/dist/{chunk-J5PBI3ZC.js.map → chunk-RDV2RHVH.js.map} +0 -0
- /package/dist/{chunk-YHPJTLCA.js.map → chunk-RKWJMA2B.js.map} +0 -0
- /package/dist/{chunk-FZMGF6XU.js.map → chunk-TAU45SJK.js.map} +0 -0
- /package/dist/{chunk-BG6LUCQL.js.map → chunk-U6D7LUCR.js.map} +0 -0
- /package/dist/{chunk-BC54LBST.js.map → chunk-UKLNKY7Q.js.map} +0 -0
- /package/dist/{chunk-7FCNOKOR.js.map → chunk-VKVDMH7X.js.map} +0 -0
- /package/dist/{chunk-KTLHADU4.js.map → chunk-XEUBMLAS.js.map} +0 -0
- /package/dist/{chunk-PTF4NCFM.js.map → chunk-YA6UGARL.js.map} +0 -0
- /package/dist/{chunk-WGMYVRSA.js.map → chunk-ZE77KLKN.js.map} +0 -0
- /package/dist/{chunks-MDMJRCJ7.js.map → chunks-PR2GRNLX.js.map} +0 -0
- /package/dist/{formula-P7M7IH2L.js.map → formula-2MTBKZKO.js.map} +0 -0
- /package/dist/{formula-6XNIXZ5L.js.map → formula-LGLSIYDI.js.map} +0 -0
- /package/dist/{image-ocr-ITNY454I.js.map → image-ocr-BKRQVMW6.js.map} +0 -0
- /package/dist/{image-ocr-3C6W3KZO.js.map → image-ocr-HP65O2CC.js.map} +0 -0
- /package/dist/{model-bundle-LAWQH75O.js.map → model-bundle-M7YMF4L4.js.map} +0 -0
- /package/dist/{models-6QTD2CFM.js.map → models-AMPRHBYB.js.map} +0 -0
- /package/dist/{parse-worker-v2-FEPJG3ER.js.map → parse-worker-v2-NMYEMVYX.js.map} +0 -0
- /package/dist/{parser-56I364YM.js.map → parser-LX5MOE6Q.js.map} +0 -0
- /package/dist/{parser-KFCY3NIN.js.map → parser-M45SFXWF.js.map} +0 -0
- /package/dist/{pdf-ocr-MME37BL4.js.map → pdf-ocr-D73YYQJ5.js.map} +0 -0
- /package/dist/{pdf-ocr-ZZ6AJL6Z.js.map → pdf-ocr-SLWZO4D2.js.map} +0 -0
- /package/dist/{profile-io-OCITHUQF.js.map → profile-io-CUMSC3TD.js.map} +0 -0
- /package/dist/{rasterize-SFCG4YOI.js.map → rasterize-W6NY4ADH.js.map} +0 -0
- /package/dist/{redact-doc-5SMPXIGG.js.map → redact-doc-7HVCZT3C.js.map} +0 -0
- /package/dist/{render-FGPG5A2N.js.map → render-FPMJX4CU.js.map} +0 -0
- /package/dist/{seal-GA7NZDTG.js.map → seal-YTRVR373.js.map} +0 -0
- /package/dist/{setup-JQVYZO7I.js.map → setup-UKIYOUT6.js.map} +0 -0
- /package/dist/{visual-YMG644YW.js.map → visual-DG5EVBZD.js.map} +0 -0
- /package/dist/{watch-C77BUSP7.js.map → watch-YHKMAVJ6.js.map} +0 -0
|
@@ -5,7 +5,7 @@ import {
|
|
|
5
5
|
import {
|
|
6
6
|
UNRULED_REGION_TABLES,
|
|
7
7
|
extractPageBlocksWithLines
|
|
8
|
-
} from "./chunk-
|
|
8
|
+
} from "./chunk-C3RR6Z3M.js";
|
|
9
9
|
import {
|
|
10
10
|
OCR_DET_MODEL,
|
|
11
11
|
OCR_REC_DICT,
|
|
@@ -13,10 +13,10 @@ import {
|
|
|
13
13
|
ensureOcrModels,
|
|
14
14
|
getOcrModelsDir,
|
|
15
15
|
parseCharacterDict
|
|
16
|
-
} from "./chunk-
|
|
16
|
+
} from "./chunk-ZE77KLKN.js";
|
|
17
17
|
import {
|
|
18
18
|
OPTIONAL_DEP_INSTALL_HINT
|
|
19
|
-
} from "./chunk-
|
|
19
|
+
} from "./chunk-TAU45SJK.js";
|
|
20
20
|
|
|
21
21
|
// src/ocr/ruling-lines.ts
|
|
22
22
|
var INK_LUMA_MAX = 205;
|
|
@@ -2133,4 +2133,4 @@ export {
|
|
|
2133
2133
|
groupOcrLines,
|
|
2134
2134
|
ocrItemsToBlocks
|
|
2135
2135
|
};
|
|
2136
|
-
//# sourceMappingURL=chunk-
|
|
2136
|
+
//# sourceMappingURL=chunk-CA742RMF.js.map
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
#!/usr/bin/env node
|
|
2
2
|
import {
|
|
3
3
|
KordocError
|
|
4
|
-
} from "./chunk-
|
|
4
|
+
} from "./chunk-TAU45SJK.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-DACTHSPR.js.map
|
|
@@ -10,10 +10,10 @@ var _chunkTK3FDAEEcjs = require('./chunk-TK3FDAEE.cjs');
|
|
|
10
10
|
|
|
11
11
|
|
|
12
12
|
|
|
13
|
-
var
|
|
13
|
+
var _chunkGELBKBGQcjs = require('./chunk-GELBKBGQ.cjs');
|
|
14
14
|
|
|
15
15
|
|
|
16
|
-
var
|
|
16
|
+
var _chunkGUU7OHIHcjs = require('./chunk-GUU7OHIH.cjs');
|
|
17
17
|
|
|
18
18
|
// src/ocr/ruling-lines.ts
|
|
19
19
|
var INK_LUMA_MAX = 205;
|
|
@@ -1415,7 +1415,7 @@ var OcrEngine = class _OcrEngine {
|
|
|
1415
1415
|
]);
|
|
1416
1416
|
const sharpAny = sharpModRaw;
|
|
1417
1417
|
const sharpMod = typeof sharpAny === "function" ? sharpAny : _nullishCoalesce(sharpAny.default, () => ( sharpAny));
|
|
1418
|
-
const dir =
|
|
1418
|
+
const dir = _chunkGELBKBGQcjs.getOcrModelsDir.call(void 0, );
|
|
1419
1419
|
const sessionOpts = {
|
|
1420
1420
|
graphOptimizationLevel: "all",
|
|
1421
1421
|
executionProviders: ["cpu"],
|
|
@@ -1423,11 +1423,11 @@ var OcrEngine = class _OcrEngine {
|
|
|
1423
1423
|
// paddle2onnx 변환 잔여물 W 로그 폭주 억제
|
|
1424
1424
|
};
|
|
1425
1425
|
const [det, rec, dictYml] = await Promise.all([
|
|
1426
|
-
ortMod.InferenceSession.create(_path.join.call(void 0, dir,
|
|
1427
|
-
ortMod.InferenceSession.create(_path.join.call(void 0, dir,
|
|
1428
|
-
_promises.readFile.call(void 0, _path.join.call(void 0, dir,
|
|
1426
|
+
ortMod.InferenceSession.create(_path.join.call(void 0, dir, _chunkGELBKBGQcjs.OCR_DET_MODEL.filename), sessionOpts),
|
|
1427
|
+
ortMod.InferenceSession.create(_path.join.call(void 0, dir, _chunkGELBKBGQcjs.OCR_REC_MODEL.filename), sessionOpts),
|
|
1428
|
+
_promises.readFile.call(void 0, _path.join.call(void 0, dir, _chunkGELBKBGQcjs.OCR_REC_DICT.filename), "utf-8")
|
|
1429
1429
|
]);
|
|
1430
|
-
const dict =
|
|
1430
|
+
const dict = _chunkGELBKBGQcjs.parseCharacterDict.call(void 0, dictYml);
|
|
1431
1431
|
if (dict.length === 0) throw 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");
|
|
1432
1432
|
return new _OcrEngine({ det, rec, dict, ort: ortMod, sharp: sharpMod });
|
|
1433
1433
|
}
|
|
@@ -1755,7 +1755,7 @@ async function tryImport(name, loader) {
|
|
|
1755
1755
|
return await loader();
|
|
1756
1756
|
} catch (e) {
|
|
1757
1757
|
throw new Error(
|
|
1758
|
-
`\uB0B4\uC7A5 OCR \uC744 \uC0AC\uC6A9\uD558\uB824\uBA74 optional dependency '${name}' \uC774 \uD544\uC694\uD569\uB2C8\uB2E4. \`npm install ${name}\` \uD6C4 \uB2E4\uC2DC \uC2E4\uD589\uD558\uC138\uC694.${
|
|
1758
|
+
`\uB0B4\uC7A5 OCR \uC744 \uC0AC\uC6A9\uD558\uB824\uBA74 optional dependency '${name}' \uC774 \uD544\uC694\uD569\uB2C8\uB2E4. \`npm install ${name}\` \uD6C4 \uB2E4\uC2DC \uC2E4\uD589\uD558\uC138\uC694.${_chunkGUU7OHIHcjs.OPTIONAL_DEP_INSTALL_HINT} \uC6D0\uC778: ${e.message}`
|
|
1759
1759
|
);
|
|
1760
1760
|
}
|
|
1761
1761
|
}
|
|
@@ -1869,7 +1869,7 @@ async function runPdfOcr(buffer, targets, mode, warnings, onProgress, detectTabl
|
|
|
1869
1869
|
() => Promise.resolve().then(() => _interopRequireWildcard(require("@hyzyla/pdfium")))
|
|
1870
1870
|
);
|
|
1871
1871
|
if (mode === "builtin") {
|
|
1872
|
-
await
|
|
1872
|
+
await _chunkGELBKBGQcjs.ensureOcrModels.call(void 0, (p) => {
|
|
1873
1873
|
if (p.phase === "download" && p.downloaded === 0) {
|
|
1874
1874
|
process.stderr.write(`[kordoc-ocr] ${p.spec.name} \uB2E4\uC6B4\uB85C\uB4DC \uC911 (~${p.spec.sizeMb}MB)...
|
|
1875
1875
|
`);
|
|
@@ -1950,7 +1950,7 @@ async function ocrOnePage(page, pageNo, mode, engine, warnings, detectTables, ve
|
|
|
1950
1950
|
const x1 = r.x1 * scale - 2, x2 = r.x2 * scale + 2, y1 = (pdfH - r.y2) * scale - 2, y2 = (pdfH - r.y1) * scale + 2;
|
|
1951
1951
|
const columnRules = _nullishCoalesce(_optionalChain([ruling, 'optionalAccess', _21 => _21.verticals, 'access', _22 => _22.filter, 'call', _23 => _23((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', _24 => _24.length]), () => ( 0));
|
|
1952
1952
|
if (columnRules < 2) {
|
|
1953
|
-
for (const b of blocks) if (b.type === "table")
|
|
1953
|
+
for (const b of blocks) if (b.type === "table") _chunkGELBKBGQcjs.UNRULED_REGION_TABLES.add(b);
|
|
1954
1954
|
}
|
|
1955
1955
|
return blocks;
|
|
1956
1956
|
});
|
|
@@ -2083,14 +2083,14 @@ function ocrItemsToBlocks(items, pageNumber, pdfW, pdfH, scale, extraLines, dete
|
|
|
2083
2083
|
...xs[i].space ? { hasSpaceBefore: true } : {}
|
|
2084
2084
|
};
|
|
2085
2085
|
});
|
|
2086
|
-
return
|
|
2086
|
+
return _chunkGELBKBGQcjs.extractPageBlocksWithLines.call(void 0, norm, pageNumber, opList, pdfW, pdfH, extraLines, detectTables);
|
|
2087
2087
|
}
|
|
2088
2088
|
async function tryImport2(name, loader) {
|
|
2089
2089
|
try {
|
|
2090
2090
|
return await loader();
|
|
2091
2091
|
} catch (e) {
|
|
2092
2092
|
throw new Error(
|
|
2093
|
-
`OCR \uC744 \uC0AC\uC6A9\uD558\uB824\uBA74 optional dependency '${name}' \uC774 \uD544\uC694\uD569\uB2C8\uB2E4. \`npm install ${name}\` \uD6C4 \uB2E4\uC2DC \uC2E4\uD589\uD558\uC138\uC694.${
|
|
2093
|
+
`OCR \uC744 \uC0AC\uC6A9\uD558\uB824\uBA74 optional dependency '${name}' \uC774 \uD544\uC694\uD569\uB2C8\uB2E4. \`npm install ${name}\` \uD6C4 \uB2E4\uC2DC \uC2E4\uD589\uD558\uC138\uC694.${_chunkGUU7OHIHcjs.OPTIONAL_DEP_INSTALL_HINT} \uC6D0\uC778: ${e.message}`
|
|
2094
2094
|
);
|
|
2095
2095
|
}
|
|
2096
2096
|
}
|
|
@@ -2130,4 +2130,4 @@ function bgraToRgba(bgra) {
|
|
|
2130
2130
|
|
|
2131
2131
|
|
|
2132
2132
|
exports.getOcrEngine = getOcrEngine; exports.detectRulingLines = detectRulingLines; exports.rulingToPdfLines = rulingToPdfLines; exports.deskewPage = deskewPage; exports.MAX_OCR_PIXELS = MAX_OCR_PIXELS; exports.runPdfOcr = runPdfOcr; exports.groupOcrLines = groupOcrLines; exports.ocrItemsToBlocks = ocrItemsToBlocks;
|
|
2133
|
-
//# sourceMappingURL=chunk-
|
|
2133
|
+
//# sourceMappingURL=chunk-EGYLKSA4.cjs.map
|