kordoc 4.7.3 → 4.8.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +90 -20
- package/dist/{-WYNJOQ6P.js → -BPSOA7WX.js} +11 -9
- package/dist/{chunk-P663PYWV.js → chunk-4CUEYYQF.js} +2 -2
- package/dist/{chunk-W5NZYPRQ.js → chunk-5EWPDL7S.js} +41 -9
- package/dist/chunk-5EWPDL7S.js.map +1 -0
- package/dist/{chunk-HJV4BVQI.js → chunk-66BZATFV.js} +2 -2
- package/dist/{chunk-JKJEBDP7.js → chunk-6KFW772K.js} +3 -3
- package/dist/{chunk-4HZN7EZZ.js → chunk-A6EAUP2J.js} +2 -2
- package/dist/{chunk-KSATSTC5.js → chunk-BN33O25L.js} +1 -1
- package/dist/{chunk-4KGGVCYX.js.map → chunk-BN33O25L.js.map} +1 -1
- package/dist/{chunk-LMHVMGEC.js → chunk-C5IU7Q3W.js} +3 -3
- package/dist/{chunk-E6DONLTM.cjs → chunk-D6NDAA72.cjs} +2 -2
- package/dist/{chunk-E6DONLTM.cjs.map → chunk-D6NDAA72.cjs.map} +1 -1
- package/dist/{chunk-3NKSSL44.js → chunk-DIB2I2HP.js} +3 -3
- package/dist/{chunk-QETZP25M.cjs → chunk-DVEJRBFI.cjs} +3 -3
- package/dist/{chunk-QETZP25M.cjs.map → chunk-DVEJRBFI.cjs.map} +1 -1
- package/dist/{chunk-46F5RMU7.js → chunk-ETMMB6O2.js} +2 -2
- package/dist/{chunk-R4LXZRYP.cjs → chunk-FZA5HW4K.cjs} +4 -4
- package/dist/{chunk-R4LXZRYP.cjs.map → chunk-FZA5HW4K.cjs.map} +1 -1
- package/dist/{chunk-QGATKC4R.cjs → chunk-H25XAYE4.cjs} +6 -6
- package/dist/{chunk-QGATKC4R.cjs.map → chunk-H25XAYE4.cjs.map} +1 -1
- package/dist/{chunk-RQVFFSAO.js → chunk-I6EWYT3Y.js} +2 -2
- package/dist/{chunk-IMFIACHP.js → chunk-I6Q5K2YF.js} +2 -2
- package/dist/{chunk-TXQQ7URG.js → chunk-KTAWKNYX.js} +2 -2
- package/dist/{chunk-EV53YE3W.cjs → chunk-L5CDTOC3.cjs} +1 -1
- package/dist/chunk-L5CDTOC3.cjs.map +1 -0
- package/dist/{chunk-KEGAEHWO.js → chunk-MYOGZQMD.js} +2 -2
- package/dist/{chunk-NYLYIN55.js → chunk-N7HKWVGP.js} +3 -3
- package/dist/{chunk-XOO6YEZE.js → chunk-NJMWYRLY.js} +3 -3
- package/dist/{chunk-CGJDCZA3.js → chunk-XGXKICRN.js} +2 -2
- package/dist/{chunk-4KGGVCYX.js → chunk-XINP35F4.js} +1 -1
- package/dist/{chunk-KSATSTC5.js.map → chunk-XINP35F4.js.map} +1 -1
- package/dist/{chunk-KE6DLZAW.cjs → chunk-XZEDL6B4.cjs} +11 -11
- package/dist/{chunk-KE6DLZAW.cjs.map → chunk-XZEDL6B4.cjs.map} +1 -1
- package/dist/{chunk-VZ3AQVBN.js → chunk-Y4H75LKS.js} +2 -2
- package/dist/{chunk-3P5YCJQE.js → chunk-YCSXG6SY.js} +2 -2
- package/dist/{chunk-Y7T5Z4DC.js → chunk-YOFMKKCA.js} +3 -3
- package/dist/chunks-HYXNV3WP.js +10 -0
- package/dist/cli.js +34 -22
- package/dist/cli.js.map +1 -1
- package/dist/{formula-V6EAYHMF.js → formula-7XQLPNSO.js} +3 -3
- package/dist/{formula-PDMZMBIP.cjs → formula-ODJ7GSUH.cjs} +9 -9
- package/dist/{formula-PDMZMBIP.cjs.map → formula-ODJ7GSUH.cjs.map} +1 -1
- package/dist/{formula-IFKZZPD2.js → formula-T4AIR2LX.js} +4 -4
- package/dist/{image-ocr-B7TMIG3F.js → image-ocr-EJLWGR3B.js} +8 -8
- package/dist/{image-ocr-XHBZONFZ.js → image-ocr-TZU64JJF.js} +6 -6
- package/dist/{image-ocr-75WGMVU6.cjs → image-ocr-WMTQ357I.cjs} +12 -12
- package/dist/{image-ocr-75WGMVU6.cjs.map → image-ocr-WMTQ357I.cjs.map} +1 -1
- package/dist/index.cjs +396 -364
- package/dist/index.cjs.map +1 -1
- package/dist/index.d.cts +42 -1
- package/dist/index.d.ts +42 -1
- package/dist/index.js +37 -5
- package/dist/index.js.map +1 -1
- package/dist/mcp.js +16 -16
- package/dist/{model-bundle-Q4HQXJQG.js → model-bundle-OT2OTSGH.js} +5 -5
- package/dist/{models-QQA7OQHY.js → models-MUVFWN7M.js} +5 -5
- package/dist/{parser-Z36MZUHS.js → parser-E6NQ666P.js} +7 -7
- package/dist/{parser-HT7GZOF2.js → parser-ERSNBILY.js} +7 -7
- package/dist/{parser-4CBOPTVY.cjs → parser-XVUFA35I.cjs} +27 -27
- package/dist/{parser-4CBOPTVY.cjs.map → parser-XVUFA35I.cjs.map} +1 -1
- package/dist/pdf-ocr-KG7X7WRC.js +13 -0
- package/dist/pdf-ocr-KMM24YFF.cjs +14 -0
- package/dist/{pdf-ocr-6ZNGDVC6.cjs.map → pdf-ocr-KMM24YFF.cjs.map} +1 -1
- package/dist/pdf-ocr-YTZL2UL4.js +16 -0
- package/dist/{profile-io-ACYRLCSR.js → profile-io-IRW6XCXH.js} +3 -3
- package/dist/{rasterize-QYCLEH2J.js → rasterize-BNF6QTLY.js} +2 -2
- package/dist/render-T7QXFTZA.js +10 -0
- package/dist/seal-ITE2NNNH.js +10 -0
- package/dist/{setup-MG3YYKXU.js → setup-BXOXVBU3.js} +3 -3
- package/dist/{watch-AZIY6AWC.js → watch-7PYYGQUJ.js} +10 -10
- package/package.json +2 -2
- package/dist/chunk-EV53YE3W.cjs.map +0 -1
- package/dist/chunk-W5NZYPRQ.js.map +0 -1
- package/dist/chunks-LWAOHTK2.js +0 -10
- package/dist/pdf-ocr-6ZNGDVC6.cjs +0 -14
- package/dist/pdf-ocr-NTXRJI4T.js +0 -13
- package/dist/pdf-ocr-TYMCEUPH.js +0 -16
- package/dist/render-5Y2US4IM.js +0 -10
- package/dist/seal-VU6JS2QD.js +0 -10
- /package/dist/{-WYNJOQ6P.js.map → -BPSOA7WX.js.map} +0 -0
- /package/dist/{chunk-P663PYWV.js.map → chunk-4CUEYYQF.js.map} +0 -0
- /package/dist/{chunk-HJV4BVQI.js.map → chunk-66BZATFV.js.map} +0 -0
- /package/dist/{chunk-JKJEBDP7.js.map → chunk-6KFW772K.js.map} +0 -0
- /package/dist/{chunk-4HZN7EZZ.js.map → chunk-A6EAUP2J.js.map} +0 -0
- /package/dist/{chunk-LMHVMGEC.js.map → chunk-C5IU7Q3W.js.map} +0 -0
- /package/dist/{chunk-3NKSSL44.js.map → chunk-DIB2I2HP.js.map} +0 -0
- /package/dist/{chunk-46F5RMU7.js.map → chunk-ETMMB6O2.js.map} +0 -0
- /package/dist/{chunk-RQVFFSAO.js.map → chunk-I6EWYT3Y.js.map} +0 -0
- /package/dist/{chunk-IMFIACHP.js.map → chunk-I6Q5K2YF.js.map} +0 -0
- /package/dist/{chunk-TXQQ7URG.js.map → chunk-KTAWKNYX.js.map} +0 -0
- /package/dist/{chunk-KEGAEHWO.js.map → chunk-MYOGZQMD.js.map} +0 -0
- /package/dist/{chunk-NYLYIN55.js.map → chunk-N7HKWVGP.js.map} +0 -0
- /package/dist/{chunk-XOO6YEZE.js.map → chunk-NJMWYRLY.js.map} +0 -0
- /package/dist/{chunk-CGJDCZA3.js.map → chunk-XGXKICRN.js.map} +0 -0
- /package/dist/{chunk-VZ3AQVBN.js.map → chunk-Y4H75LKS.js.map} +0 -0
- /package/dist/{chunk-3P5YCJQE.js.map → chunk-YCSXG6SY.js.map} +0 -0
- /package/dist/{chunk-Y7T5Z4DC.js.map → chunk-YOFMKKCA.js.map} +0 -0
- /package/dist/{chunks-LWAOHTK2.js.map → chunks-HYXNV3WP.js.map} +0 -0
- /package/dist/{formula-V6EAYHMF.js.map → formula-7XQLPNSO.js.map} +0 -0
- /package/dist/{formula-IFKZZPD2.js.map → formula-T4AIR2LX.js.map} +0 -0
- /package/dist/{image-ocr-B7TMIG3F.js.map → image-ocr-EJLWGR3B.js.map} +0 -0
- /package/dist/{image-ocr-XHBZONFZ.js.map → image-ocr-TZU64JJF.js.map} +0 -0
- /package/dist/{model-bundle-Q4HQXJQG.js.map → model-bundle-OT2OTSGH.js.map} +0 -0
- /package/dist/{models-QQA7OQHY.js.map → models-MUVFWN7M.js.map} +0 -0
- /package/dist/{parser-Z36MZUHS.js.map → parser-E6NQ666P.js.map} +0 -0
- /package/dist/{parser-HT7GZOF2.js.map → parser-ERSNBILY.js.map} +0 -0
- /package/dist/{pdf-ocr-NTXRJI4T.js.map → pdf-ocr-KG7X7WRC.js.map} +0 -0
- /package/dist/{pdf-ocr-TYMCEUPH.js.map → pdf-ocr-YTZL2UL4.js.map} +0 -0
- /package/dist/{profile-io-ACYRLCSR.js.map → profile-io-IRW6XCXH.js.map} +0 -0
- /package/dist/{rasterize-QYCLEH2J.js.map → rasterize-BNF6QTLY.js.map} +0 -0
- /package/dist/{render-5Y2US4IM.js.map → render-T7QXFTZA.js.map} +0 -0
- /package/dist/{seal-VU6JS2QD.js.map → seal-ITE2NNNH.js.map} +0 -0
- /package/dist/{setup-MG3YYKXU.js.map → setup-BXOXVBU3.js.map} +0 -0
- /package/dist/{watch-AZIY6AWC.js.map → watch-7PYYGQUJ.js.map} +0 -0
|
@@ -2,11 +2,11 @@
|
|
|
2
2
|
|
|
3
3
|
|
|
4
4
|
|
|
5
|
-
var
|
|
5
|
+
var _chunkL5CDTOC3cjs = require('./chunk-L5CDTOC3.cjs');
|
|
6
6
|
|
|
7
7
|
|
|
8
8
|
|
|
9
|
-
var
|
|
9
|
+
var _chunkD6NDAA72cjs = require('./chunk-D6NDAA72.cjs');
|
|
10
10
|
|
|
11
11
|
// src/pdf/image-regions.ts
|
|
12
12
|
var _pdfmjs = require('pdfjs-dist/legacy/build/pdf.mjs');
|
|
@@ -1569,9 +1569,9 @@ function detectHeadings(blocks, medianFontSize) {
|
|
|
1569
1569
|
if (/^\d+$/.test(text)) continue;
|
|
1570
1570
|
const ratio = block.style.fontSize / medianFontSize;
|
|
1571
1571
|
let level = 0;
|
|
1572
|
-
if (ratio >=
|
|
1573
|
-
else if (ratio >=
|
|
1574
|
-
else if (ratio >=
|
|
1572
|
+
if (ratio >= _chunkL5CDTOC3cjs.HEADING_RATIO_H1) level = 1;
|
|
1573
|
+
else if (ratio >= _chunkL5CDTOC3cjs.HEADING_RATIO_H2) level = 2;
|
|
1574
|
+
else if (ratio >= _chunkL5CDTOC3cjs.HEADING_RATIO_H3) level = 3;
|
|
1575
1575
|
if (level > 0) {
|
|
1576
1576
|
block.type = "heading";
|
|
1577
1577
|
block.level = level;
|
|
@@ -2834,14 +2834,14 @@ function isProseSpread(items) {
|
|
|
2834
2834
|
for (let i = 1; i < sorted.length; i++) {
|
|
2835
2835
|
gaps.push(sorted[i].x - (sorted[i - 1].x + sorted[i - 1].w));
|
|
2836
2836
|
}
|
|
2837
|
-
const maxGap =
|
|
2837
|
+
const maxGap = _chunkD6NDAA72cjs.safeMax.call(void 0, gaps);
|
|
2838
2838
|
const avgLen = items.reduce((s, i) => s + i.text.length, 0) / items.length;
|
|
2839
2839
|
return maxGap < 40 && avgLen < 5;
|
|
2840
2840
|
}
|
|
2841
2841
|
function detectColumns(yLines) {
|
|
2842
2842
|
const allItems = yLines.flat();
|
|
2843
2843
|
if (allItems.length === 0) return null;
|
|
2844
|
-
const pageWidth =
|
|
2844
|
+
const pageWidth = _chunkD6NDAA72cjs.safeMax.call(void 0, allItems.map((i) => i.x + i.w)) - _chunkD6NDAA72cjs.safeMin.call(void 0, allItems.map((i) => i.x));
|
|
2845
2845
|
if (pageWidth < 100) return null;
|
|
2846
2846
|
let bigoLineIdx = -1;
|
|
2847
2847
|
for (let i = 0; i < yLines.length; i++) {
|
|
@@ -3419,7 +3419,7 @@ function extractBlocksWithGrids(items, pageNum, grids, horizontals, verticals) {
|
|
|
3419
3419
|
if (gutterX !== null) {
|
|
3420
3420
|
const gx = gutterX;
|
|
3421
3421
|
const allY = remaining.map((i) => i.y);
|
|
3422
|
-
const pageH =
|
|
3422
|
+
const pageH = _chunkD6NDAA72cjs.safeMax.call(void 0, allY) - _chunkD6NDAA72cjs.safeMin.call(void 0, allY);
|
|
3423
3423
|
const gapThreshold = Math.max(15, pageH * 0.03);
|
|
3424
3424
|
const sides = [
|
|
3425
3425
|
remaining.filter((i) => i.x + i.w <= gx),
|
|
@@ -3439,7 +3439,7 @@ function extractBlocksWithGrids(items, pageNum, grids, horizontals, verticals) {
|
|
|
3439
3439
|
finalTextBlocks = detectListBlocks(textBlocks);
|
|
3440
3440
|
} else {
|
|
3441
3441
|
const allY = remaining.map((i) => i.y);
|
|
3442
|
-
const pageH =
|
|
3442
|
+
const pageH = _chunkD6NDAA72cjs.safeMax.call(void 0, allY) - _chunkD6NDAA72cjs.safeMin.call(void 0, allY);
|
|
3443
3443
|
const groups = xyCutOrder(remaining, Math.max(15, pageH * 0.03));
|
|
3444
3444
|
const textBlocks = [];
|
|
3445
3445
|
for (const group of groups) {
|
|
@@ -3647,7 +3647,7 @@ function extractPageBlocksFallback(items, pageNum, fullPage = false, detectTable
|
|
|
3647
3647
|
blocks.push({ type: "paragraph", text: tableText, pageNumber: pageNum, bbox, style: dominantStyle(items) });
|
|
3648
3648
|
} else {
|
|
3649
3649
|
const allY = items.map((i) => i.y);
|
|
3650
|
-
const pageHeight =
|
|
3650
|
+
const pageHeight = _chunkD6NDAA72cjs.safeMax.call(void 0, allY) - _chunkD6NDAA72cjs.safeMin.call(void 0, allY);
|
|
3651
3651
|
const gapThreshold = Math.max(15, pageHeight * 0.03);
|
|
3652
3652
|
const orderedGroups = proseCutX !== null ? splitTwoColumnProse(items, proseCutX) : xyCutOrder(items, gapThreshold);
|
|
3653
3653
|
for (const group of orderedGroups) {
|
|
@@ -3686,4 +3686,4 @@ function extractPageBlocksFallback(items, pageNum, fullPage = false, detectTable
|
|
|
3686
3686
|
|
|
3687
3687
|
|
|
3688
3688
|
exports.extractImageRegions = extractImageRegions; exports.filterHiddenText = filterHiddenText; exports.collapseEvenSpacing = collapseEvenSpacing; exports.normalizeItems = normalizeItems; exports.computeMedianFontSizeFromFreq = computeMedianFontSizeFromFreq; exports.detectHeadings = detectHeadings; exports.detectMarkerHeadings = detectMarkerHeadings; exports.detectTableCaptions = detectTableCaptions; exports.detectKoreanListBlocks = detectKoreanListBlocks; exports.removeHeaderFooterBlocks = removeHeaderFooterBlocks; exports.extractPageBlocksWithLines = extractPageBlocksWithLines; exports.mergeCrossPageTables = mergeCrossPageTables;
|
|
3689
|
-
//# sourceMappingURL=chunk-
|
|
3689
|
+
//# sourceMappingURL=chunk-XZEDL6B4.cjs.map
|