kordoc 4.7.1 → 4.7.3
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 +19 -1
- package/dist/{-O42BMYNX.js → -WYNJOQ6P.js} +9 -9
- package/dist/{chunk-PLEGO474.js → chunk-3NKSSL44.js} +3 -3
- package/dist/{chunk-UZB3UGC5.js → chunk-3P5YCJQE.js} +2 -2
- package/dist/{chunk-IZEUWEEY.js → chunk-46F5RMU7.js} +3 -11
- package/dist/chunk-46F5RMU7.js.map +1 -0
- package/dist/{chunk-UAFSPWU7.js → chunk-4HZN7EZZ.js} +8 -1
- package/dist/chunk-4HZN7EZZ.js.map +1 -0
- package/dist/{chunk-4VNUQYUE.js → chunk-4KGGVCYX.js} +1 -1
- package/dist/chunk-4KGGVCYX.js.map +1 -0
- package/dist/{chunk-AFX6ZXER.js → chunk-CGJDCZA3.js} +2 -2
- package/dist/{chunk-DJKLOLBT.cjs → chunk-E6DONLTM.cjs} +3 -11
- package/dist/chunk-E6DONLTM.cjs.map +1 -0
- package/dist/chunk-EV53YE3W.cjs +11 -0
- package/dist/chunk-EV53YE3W.cjs.map +1 -0
- package/dist/{chunk-3H5X63BQ.js → chunk-HJV4BVQI.js} +27 -1
- package/dist/chunk-HJV4BVQI.js.map +1 -0
- package/dist/{chunk-J3W6Q3AX.js → chunk-IMFIACHP.js} +2 -2
- package/dist/{chunk-BQENBAUC.js → chunk-JKJEBDP7.js} +3 -3
- package/dist/{chunk-ZDWP3LLY.cjs → chunk-KE6DLZAW.cjs} +12 -10
- package/dist/chunk-KE6DLZAW.cjs.map +1 -0
- package/dist/{chunk-YWDN5PQC.js → chunk-KEGAEHWO.js} +2 -2
- package/dist/chunk-KSATSTC5.js +11 -0
- package/dist/chunk-KSATSTC5.js.map +1 -0
- package/dist/{chunk-3UIT4PPQ.js → chunk-LMHVMGEC.js} +5 -3
- package/dist/{chunk-3UIT4PPQ.js.map → chunk-LMHVMGEC.js.map} +1 -1
- package/dist/{chunk-VECVLIWE.js → chunk-NYLYIN55.js} +3 -3
- package/dist/{chunk-IMEMTJ76.js → chunk-P663PYWV.js} +2 -2
- package/dist/{chunk-ZV5OKQ3Z.cjs → chunk-QETZP25M.cjs} +28 -2
- package/dist/chunk-QETZP25M.cjs.map +1 -0
- package/dist/{chunk-TZ3WCAJZ.cjs → chunk-QGATKC4R.cjs} +6 -6
- package/dist/{chunk-TZ3WCAJZ.cjs.map → chunk-QGATKC4R.cjs.map} +1 -1
- package/dist/{chunk-USGC3ZKU.cjs → chunk-R4LXZRYP.cjs} +4 -4
- package/dist/{chunk-USGC3ZKU.cjs.map → chunk-R4LXZRYP.cjs.map} +1 -1
- package/dist/chunk-RQVFFSAO.js +52 -0
- package/dist/chunk-RQVFFSAO.js.map +1 -0
- package/dist/{chunk-GZDOWYJM.js → chunk-TXQQ7URG.js} +2 -2
- package/dist/{chunk-7ZIOZ6PU.js → chunk-VZ3AQVBN.js} +8 -3
- package/dist/chunk-VZ3AQVBN.js.map +1 -0
- package/dist/{chunk-5KPNXBNR.js → chunk-W5NZYPRQ.js} +386 -80
- package/dist/chunk-W5NZYPRQ.js.map +1 -0
- package/dist/{chunk-JEX5P66D.js → chunk-XOO6YEZE.js} +3 -3
- package/dist/{chunk-6663UXPE.js → chunk-Y7T5Z4DC.js} +3 -3
- package/dist/chunks-LWAOHTK2.js +10 -0
- package/dist/cli.js +57 -21
- package/dist/cli.js.map +1 -1
- package/dist/{formula-JLYS73QL.js → formula-IFKZZPD2.js} +4 -2
- package/dist/{formula-LIVQSCMM.js.map → formula-IFKZZPD2.js.map} +1 -1
- package/dist/{formula-CG4S7TWO.cjs → formula-PDMZMBIP.cjs} +9 -8
- package/dist/formula-PDMZMBIP.cjs.map +1 -0
- package/dist/{formula-LIVQSCMM.js → formula-V6EAYHMF.js} +3 -2
- package/dist/{image-ocr-MKD6MKWO.cjs → image-ocr-75WGMVU6.cjs} +12 -11
- package/dist/image-ocr-75WGMVU6.cjs.map +1 -0
- package/dist/{image-ocr-5QRZBNOF.js → image-ocr-B7TMIG3F.js} +10 -9
- package/dist/{image-ocr-5QRZBNOF.js.map → image-ocr-B7TMIG3F.js.map} +1 -1
- package/dist/{image-ocr-TAJHRZ5T.js → image-ocr-XHBZONFZ.js} +6 -5
- package/dist/{image-ocr-TAJHRZ5T.js.map → image-ocr-XHBZONFZ.js.map} +1 -1
- package/dist/index.cjs +865 -552
- package/dist/index.cjs.map +1 -1
- package/dist/index.d.cts +10 -2
- package/dist/index.d.ts +10 -2
- package/dist/index.js +390 -77
- package/dist/index.js.map +1 -1
- package/dist/mcp.js +36 -18
- package/dist/mcp.js.map +1 -1
- package/dist/model-bundle-Q4HQXJQG.js +104 -0
- package/dist/model-bundle-Q4HQXJQG.js.map +1 -0
- package/dist/{models-6SIKLKRH.js → models-QQA7OQHY.js} +5 -3
- package/dist/{parser-SWY4RKGD.cjs → parser-4CBOPTVY.cjs} +28 -27
- package/dist/parser-4CBOPTVY.cjs.map +1 -0
- package/dist/{parser-UMFBJG2D.js → parser-HT7GZOF2.js} +8 -8
- package/dist/{parser-RCEHB2EV.js.map → parser-HT7GZOF2.js.map} +1 -1
- package/dist/{parser-RCEHB2EV.js → parser-Z36MZUHS.js} +8 -7
- package/dist/{parser-UMFBJG2D.js.map → parser-Z36MZUHS.js.map} +1 -1
- package/dist/pdf-ocr-6ZNGDVC6.cjs +14 -0
- package/dist/pdf-ocr-6ZNGDVC6.cjs.map +1 -0
- package/dist/pdf-ocr-NTXRJI4T.js +13 -0
- package/dist/pdf-ocr-TYMCEUPH.js +16 -0
- package/dist/{profile-io-HT62OAEU.js → profile-io-ACYRLCSR.js} +3 -3
- package/dist/{rasterize-GL67HQC7.js → rasterize-QYCLEH2J.js} +2 -2
- package/dist/render-5Y2US4IM.js +10 -0
- package/dist/seal-VU6JS2QD.js +10 -0
- package/dist/{setup-GUQT5ELJ.js → setup-MG3YYKXU.js} +30 -7
- package/dist/setup-MG3YYKXU.js.map +1 -0
- package/dist/{watch-5ST75Q7Q.js → watch-AZIY6AWC.js} +13 -9
- package/dist/watch-AZIY6AWC.js.map +1 -0
- package/package.json +7 -3
- package/dist/chunk-3H5X63BQ.js.map +0 -1
- package/dist/chunk-4VNUQYUE.js.map +0 -1
- package/dist/chunk-5KPNXBNR.js.map +0 -1
- package/dist/chunk-7ZIOZ6PU.js.map +0 -1
- package/dist/chunk-DJKLOLBT.cjs.map +0 -1
- package/dist/chunk-IZEUWEEY.js.map +0 -1
- package/dist/chunk-UAFSPWU7.js.map +0 -1
- package/dist/chunk-ZDWP3LLY.cjs.map +0 -1
- package/dist/chunk-ZV5OKQ3Z.cjs.map +0 -1
- package/dist/chunks-C7DJL4RE.js +0 -10
- package/dist/formula-CG4S7TWO.cjs.map +0 -1
- package/dist/image-ocr-MKD6MKWO.cjs.map +0 -1
- package/dist/parser-SWY4RKGD.cjs.map +0 -1
- package/dist/pdf-ocr-3NTV3MYP.js +0 -12
- package/dist/pdf-ocr-7BOO4JA7.js +0 -15
- package/dist/pdf-ocr-JDHELYBY.cjs +0 -13
- package/dist/pdf-ocr-JDHELYBY.cjs.map +0 -1
- package/dist/render-IQ4IZLY4.js +0 -10
- package/dist/seal-AGSZ6MUR.js +0 -10
- package/dist/setup-GUQT5ELJ.js.map +0 -1
- package/dist/watch-5ST75Q7Q.js.map +0 -1
- /package/dist/{-O42BMYNX.js.map → -WYNJOQ6P.js.map} +0 -0
- /package/dist/{chunk-PLEGO474.js.map → chunk-3NKSSL44.js.map} +0 -0
- /package/dist/{chunk-UZB3UGC5.js.map → chunk-3P5YCJQE.js.map} +0 -0
- /package/dist/{chunk-AFX6ZXER.js.map → chunk-CGJDCZA3.js.map} +0 -0
- /package/dist/{chunk-J3W6Q3AX.js.map → chunk-IMFIACHP.js.map} +0 -0
- /package/dist/{chunk-BQENBAUC.js.map → chunk-JKJEBDP7.js.map} +0 -0
- /package/dist/{chunk-YWDN5PQC.js.map → chunk-KEGAEHWO.js.map} +0 -0
- /package/dist/{chunk-VECVLIWE.js.map → chunk-NYLYIN55.js.map} +0 -0
- /package/dist/{chunk-IMEMTJ76.js.map → chunk-P663PYWV.js.map} +0 -0
- /package/dist/{chunk-GZDOWYJM.js.map → chunk-TXQQ7URG.js.map} +0 -0
- /package/dist/{chunk-JEX5P66D.js.map → chunk-XOO6YEZE.js.map} +0 -0
- /package/dist/{chunk-6663UXPE.js.map → chunk-Y7T5Z4DC.js.map} +0 -0
- /package/dist/{chunks-C7DJL4RE.js.map → chunks-LWAOHTK2.js.map} +0 -0
- /package/dist/{formula-JLYS73QL.js.map → formula-V6EAYHMF.js.map} +0 -0
- /package/dist/{models-6SIKLKRH.js.map → models-QQA7OQHY.js.map} +0 -0
- /package/dist/{pdf-ocr-3NTV3MYP.js.map → pdf-ocr-NTXRJI4T.js.map} +0 -0
- /package/dist/{pdf-ocr-7BOO4JA7.js.map → pdf-ocr-TYMCEUPH.js.map} +0 -0
- /package/dist/{profile-io-HT62OAEU.js.map → profile-io-ACYRLCSR.js.map} +0 -0
- /package/dist/{rasterize-GL67HQC7.js.map → rasterize-QYCLEH2J.js.map} +0 -0
- /package/dist/{render-IQ4IZLY4.js.map → render-5Y2US4IM.js.map} +0 -0
- /package/dist/{seal-AGSZ6MUR.js.map → seal-VU6JS2QD.js.map} +0 -0
|
@@ -2,9 +2,11 @@
|
|
|
2
2
|
|
|
3
3
|
|
|
4
4
|
|
|
5
|
+
var _chunkEV53YE3Wcjs = require('./chunk-EV53YE3W.cjs');
|
|
5
6
|
|
|
6
7
|
|
|
7
|
-
|
|
8
|
+
|
|
9
|
+
var _chunkE6DONLTMcjs = require('./chunk-E6DONLTM.cjs');
|
|
8
10
|
|
|
9
11
|
// src/pdf/image-regions.ts
|
|
10
12
|
var _pdfmjs = require('pdfjs-dist/legacy/build/pdf.mjs');
|
|
@@ -1567,9 +1569,9 @@ function detectHeadings(blocks, medianFontSize) {
|
|
|
1567
1569
|
if (/^\d+$/.test(text)) continue;
|
|
1568
1570
|
const ratio = block.style.fontSize / medianFontSize;
|
|
1569
1571
|
let level = 0;
|
|
1570
|
-
if (ratio >=
|
|
1571
|
-
else if (ratio >=
|
|
1572
|
-
else if (ratio >=
|
|
1572
|
+
if (ratio >= _chunkEV53YE3Wcjs.HEADING_RATIO_H1) level = 1;
|
|
1573
|
+
else if (ratio >= _chunkEV53YE3Wcjs.HEADING_RATIO_H2) level = 2;
|
|
1574
|
+
else if (ratio >= _chunkEV53YE3Wcjs.HEADING_RATIO_H3) level = 3;
|
|
1573
1575
|
if (level > 0) {
|
|
1574
1576
|
block.type = "heading";
|
|
1575
1577
|
block.level = level;
|
|
@@ -2832,14 +2834,14 @@ function isProseSpread(items) {
|
|
|
2832
2834
|
for (let i = 1; i < sorted.length; i++) {
|
|
2833
2835
|
gaps.push(sorted[i].x - (sorted[i - 1].x + sorted[i - 1].w));
|
|
2834
2836
|
}
|
|
2835
|
-
const maxGap =
|
|
2837
|
+
const maxGap = _chunkE6DONLTMcjs.safeMax.call(void 0, gaps);
|
|
2836
2838
|
const avgLen = items.reduce((s, i) => s + i.text.length, 0) / items.length;
|
|
2837
2839
|
return maxGap < 40 && avgLen < 5;
|
|
2838
2840
|
}
|
|
2839
2841
|
function detectColumns(yLines) {
|
|
2840
2842
|
const allItems = yLines.flat();
|
|
2841
2843
|
if (allItems.length === 0) return null;
|
|
2842
|
-
const pageWidth =
|
|
2844
|
+
const pageWidth = _chunkE6DONLTMcjs.safeMax.call(void 0, allItems.map((i) => i.x + i.w)) - _chunkE6DONLTMcjs.safeMin.call(void 0, allItems.map((i) => i.x));
|
|
2843
2845
|
if (pageWidth < 100) return null;
|
|
2844
2846
|
let bigoLineIdx = -1;
|
|
2845
2847
|
for (let i = 0; i < yLines.length; i++) {
|
|
@@ -3417,7 +3419,7 @@ function extractBlocksWithGrids(items, pageNum, grids, horizontals, verticals) {
|
|
|
3417
3419
|
if (gutterX !== null) {
|
|
3418
3420
|
const gx = gutterX;
|
|
3419
3421
|
const allY = remaining.map((i) => i.y);
|
|
3420
|
-
const pageH =
|
|
3422
|
+
const pageH = _chunkE6DONLTMcjs.safeMax.call(void 0, allY) - _chunkE6DONLTMcjs.safeMin.call(void 0, allY);
|
|
3421
3423
|
const gapThreshold = Math.max(15, pageH * 0.03);
|
|
3422
3424
|
const sides = [
|
|
3423
3425
|
remaining.filter((i) => i.x + i.w <= gx),
|
|
@@ -3437,7 +3439,7 @@ function extractBlocksWithGrids(items, pageNum, grids, horizontals, verticals) {
|
|
|
3437
3439
|
finalTextBlocks = detectListBlocks(textBlocks);
|
|
3438
3440
|
} else {
|
|
3439
3441
|
const allY = remaining.map((i) => i.y);
|
|
3440
|
-
const pageH =
|
|
3442
|
+
const pageH = _chunkE6DONLTMcjs.safeMax.call(void 0, allY) - _chunkE6DONLTMcjs.safeMin.call(void 0, allY);
|
|
3441
3443
|
const groups = xyCutOrder(remaining, Math.max(15, pageH * 0.03));
|
|
3442
3444
|
const textBlocks = [];
|
|
3443
3445
|
for (const group of groups) {
|
|
@@ -3645,7 +3647,7 @@ function extractPageBlocksFallback(items, pageNum, fullPage = false, detectTable
|
|
|
3645
3647
|
blocks.push({ type: "paragraph", text: tableText, pageNumber: pageNum, bbox, style: dominantStyle(items) });
|
|
3646
3648
|
} else {
|
|
3647
3649
|
const allY = items.map((i) => i.y);
|
|
3648
|
-
const pageHeight =
|
|
3650
|
+
const pageHeight = _chunkE6DONLTMcjs.safeMax.call(void 0, allY) - _chunkE6DONLTMcjs.safeMin.call(void 0, allY);
|
|
3649
3651
|
const gapThreshold = Math.max(15, pageHeight * 0.03);
|
|
3650
3652
|
const orderedGroups = proseCutX !== null ? splitTwoColumnProse(items, proseCutX) : xyCutOrder(items, gapThreshold);
|
|
3651
3653
|
for (const group of orderedGroups) {
|
|
@@ -3684,4 +3686,4 @@ function extractPageBlocksFallback(items, pageNum, fullPage = false, detectTable
|
|
|
3684
3686
|
|
|
3685
3687
|
|
|
3686
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;
|
|
3687
|
-
//# sourceMappingURL=chunk-
|
|
3689
|
+
//# sourceMappingURL=chunk-KE6DLZAW.cjs.map
|