kordoc 4.3.1 → 4.4.1
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/NOTICE +176 -0
- package/README.md +942 -922
- package/THIRD_PARTY/apache-2.0.LICENSE +201 -0
- package/THIRD_PARTY/claw-hwp.LICENSE +21 -0
- package/THIRD_PARTY/hml-equation-parser.LICENSE +201 -0
- package/THIRD_PARTY/hml-equation-parser.txt +35 -0
- package/THIRD_PARTY/opendataloader-pdf.txt +32 -0
- package/THIRD_PARTY/pix2text.txt +17 -0
- package/THIRD_PARTY/rhwp-forms.txt +35 -0
- package/dist/{-RH6BEVTT.js → -7X4H77Z7.js} +11 -11
- package/dist/{chunk-RO4Y4BFI.js → chunk-2352RXHG.js} +366 -51
- package/dist/chunk-2352RXHG.js.map +1 -0
- package/dist/{chunk-7DZPPUQD.cjs → chunk-3DX6VJGH.cjs} +9 -9
- package/dist/chunk-3DX6VJGH.cjs.map +1 -0
- package/dist/{chunk-3FFPHTXD.js → chunk-3H5X63BQ.js} +1 -1
- package/dist/chunk-3H5X63BQ.js.map +1 -0
- package/dist/{chunk-CD5X6UG5.js → chunk-5A2TGIN7.js} +2 -2
- package/dist/chunk-5A2TGIN7.js.map +1 -0
- package/dist/{chunk-SA22NK56.js → chunk-5PXCA3DN.js} +4 -4
- package/dist/chunk-5PXCA3DN.js.map +1 -0
- package/dist/{chunk-6GBLFQMA.js → chunk-5RPYBC2Q.js} +1 -1
- package/dist/chunk-5RPYBC2Q.js.map +1 -0
- package/dist/{chunk-VQB5P5KJ.cjs → chunk-7BIVNIK5.cjs} +2 -2
- package/dist/chunk-7BIVNIK5.cjs.map +1 -0
- package/dist/{chunk-W34QSJFF.js → chunk-7FCNOKOR.js} +1 -1
- package/dist/chunk-7FCNOKOR.js.map +1 -0
- package/dist/{chunk-ZYYTU7NY.js → chunk-7MDLAKVO.js} +2 -2
- package/dist/chunk-7MDLAKVO.js.map +1 -0
- package/dist/{chunk-ZSL6MQVE.js → chunk-A73RMJ6B.js} +1 -1
- package/dist/chunk-A73RMJ6B.js.map +1 -0
- package/dist/{chunk-PV3NVBGL.js → chunk-AYM6UHFX.js} +3 -3
- package/dist/chunk-AYM6UHFX.js.map +1 -0
- package/dist/chunk-DCZVOIEO.cjs.map +1 -1
- package/dist/{chunk-O5EK52TG.js → chunk-DZIXKL7E.js} +1 -1
- package/dist/chunk-DZIXKL7E.js.map +1 -0
- package/dist/{chunk-5F5UCACZ.cjs → chunk-FR65WNLF.cjs} +6 -6
- package/dist/chunk-FR65WNLF.cjs.map +1 -0
- package/dist/{chunk-ZMKTKJZN.cjs → chunk-GC7WBHAN.cjs} +26 -5
- package/dist/chunk-GC7WBHAN.cjs.map +1 -0
- package/dist/chunk-GS7T56RP.cjs.map +1 -1
- package/dist/{chunk-6XPXIG57.js → chunk-GZDOWYJM.js} +2 -2
- package/dist/chunk-GZDOWYJM.js.map +1 -0
- package/dist/{chunk-HPRK67YB.js → chunk-HGSO2H44.js} +3 -3
- package/dist/chunk-HGSO2H44.js.map +1 -0
- package/dist/{chunk-BYEQDLZS.js → chunk-IPOVUGXD.js} +6 -4
- package/dist/chunk-IPOVUGXD.js.map +1 -0
- package/dist/{chunk-HZU7Y22R.js → chunk-JGHQFUKI.js} +7 -4
- package/dist/chunk-JGHQFUKI.js.map +1 -0
- package/dist/chunk-MOL7MDBG.js +0 -0
- package/dist/{chunk-GTPEKBN6.js → chunk-NUGTEPKT.js} +2 -2
- package/dist/chunk-NUGTEPKT.js.map +1 -0
- package/dist/{chunk-BPJSTJBN.js → chunk-SMPEZINI.js} +24 -3
- package/dist/chunk-SMPEZINI.js.map +1 -0
- package/dist/{chunk-LEC2HG7A.js → chunk-T25FBUMN.js} +2 -2
- package/dist/chunk-T25FBUMN.js.map +1 -0
- package/dist/{chunk-YDCD4AV4.js → chunk-TGAWXMXB.js} +3 -3
- package/dist/chunk-TGAWXMXB.js.map +1 -0
- package/dist/{chunk-FUXDD36A.js → chunk-UA53AA7R.js} +24 -3
- package/dist/chunk-UA53AA7R.js.map +1 -0
- package/dist/{chunk-YNJDNP44.js → chunk-UAFSPWU7.js} +1 -1
- package/dist/chunk-UAFSPWU7.js.map +1 -0
- package/dist/{chunk-ZJ75YDW7.js → chunk-WA7XLWZW.js} +2 -2
- package/dist/chunk-WA7XLWZW.js.map +1 -0
- package/dist/{chunk-MGGU3ZRK.cjs → chunk-ZV5OKQ3Z.cjs} +1 -1
- package/dist/chunk-ZV5OKQ3Z.cjs.map +1 -0
- package/dist/chunks-FMZK4QHL.js +10 -0
- package/dist/cli.js +28 -24
- package/dist/cli.js.map +1 -1
- package/dist/{formula-IWV5IJ3Y.cjs → formula-CG4S7TWO.cjs} +8 -8
- package/dist/formula-CG4S7TWO.cjs.map +1 -0
- package/dist/{formula-7ZPC54JO.js → formula-JLYS73QL.js} +2 -2
- package/dist/formula-JLYS73QL.js.map +1 -0
- package/dist/{formula-EQRHSMYW.js → formula-LIVQSCMM.js} +2 -2
- package/dist/formula-LIVQSCMM.js.map +1 -0
- package/dist/{image-ocr-6MO4FXJK.js → image-ocr-AHHY42OI.js} +5 -5
- package/dist/image-ocr-AHHY42OI.js.map +1 -0
- package/dist/{image-ocr-TWUU2RNG.js → image-ocr-K4XCRBTY.js} +7 -7
- package/dist/image-ocr-K4XCRBTY.js.map +1 -0
- package/dist/{image-ocr-MGVXT6XD.cjs → image-ocr-VCXLT5Q6.cjs} +11 -11
- package/dist/image-ocr-VCXLT5Q6.cjs.map +1 -0
- package/dist/index.cjs +858 -537
- package/dist/index.cjs.map +1 -1
- package/dist/index.d.cts +7 -0
- package/dist/index.d.ts +7 -0
- package/dist/index.js +373 -52
- package/dist/index.js.map +1 -1
- package/dist/mcp.js +36 -32
- package/dist/mcp.js.map +1 -1
- package/dist/{models-6VMAVZR6.js → models-6SIKLKRH.js} +3 -3
- package/dist/page-range-737B4EZW.js +0 -0
- package/dist/page-range-P7SDW6LR.cjs.map +1 -1
- package/dist/{parser-JFGLN4DA.cjs → parser-ABYM2MVN.cjs} +25 -25
- package/dist/parser-ABYM2MVN.cjs.map +1 -0
- package/dist/{parser-VR2BTUT7.js → parser-I3ELUUOG.js} +8 -8
- package/dist/parser-I3ELUUOG.js.map +1 -0
- package/dist/{parser-YA7HSSPK.js → parser-IPVY56U3.js} +6 -6
- package/dist/parser-IPVY56U3.js.map +1 -0
- package/dist/pdf-ocr-EL3VSWWY.js +12 -0
- package/dist/pdf-ocr-FVLKQNAT.js +15 -0
- package/dist/pdf-ocr-VQ3QWXGE.cjs +13 -0
- package/dist/pdf-ocr-VQ3QWXGE.cjs.map +1 -0
- package/dist/{profile-io-QPIMGVO3.js → profile-io-YADU6SKH.js} +3 -3
- package/dist/{rasterize-AFYGNKXG.js → rasterize-YV5VDSQX.js} +2 -2
- package/dist/rasterize-YV5VDSQX.js.map +1 -0
- package/dist/{redact-W5K3ILQH.js → redact-7ILEAUTS.js} +2 -2
- package/dist/render-K6M3P24X.js +10 -0
- package/dist/seal-YW3U5BCY.js +10 -0
- package/dist/{setup-I4I75QJU.js → setup-GUQT5ELJ.js} +1 -1
- package/dist/setup-GUQT5ELJ.js.map +1 -0
- package/dist/{watch-D3JJEOAB.js → watch-5K2ZERXI.js} +11 -11
- package/dist/watch-5K2ZERXI.js.map +1 -0
- package/package.json +103 -101
- package/templates//352/260/204/354/235/264/352/270/260/354/225/210/353/254/270_/354/230/210/354/213/234/352/260/222.json +9 -9
- package/templates//354/235/274/353/260/230/352/270/260/354/225/210/353/254/270_/354/230/210/354/213/234/352/260/222.json +24 -24
- package/dist/chunk-3FFPHTXD.js.map +0 -1
- package/dist/chunk-5F5UCACZ.cjs.map +0 -1
- package/dist/chunk-6GBLFQMA.js.map +0 -1
- package/dist/chunk-6XPXIG57.js.map +0 -1
- package/dist/chunk-7DZPPUQD.cjs.map +0 -1
- package/dist/chunk-BPJSTJBN.js.map +0 -1
- package/dist/chunk-BYEQDLZS.js.map +0 -1
- package/dist/chunk-CD5X6UG5.js.map +0 -1
- package/dist/chunk-FUXDD36A.js.map +0 -1
- package/dist/chunk-GTPEKBN6.js.map +0 -1
- package/dist/chunk-HPRK67YB.js.map +0 -1
- package/dist/chunk-HZU7Y22R.js.map +0 -1
- package/dist/chunk-LEC2HG7A.js.map +0 -1
- package/dist/chunk-MGGU3ZRK.cjs.map +0 -1
- package/dist/chunk-O5EK52TG.js.map +0 -1
- package/dist/chunk-PV3NVBGL.js.map +0 -1
- package/dist/chunk-RO4Y4BFI.js.map +0 -1
- package/dist/chunk-SA22NK56.js.map +0 -1
- package/dist/chunk-VQB5P5KJ.cjs.map +0 -1
- package/dist/chunk-W34QSJFF.js.map +0 -1
- package/dist/chunk-YDCD4AV4.js.map +0 -1
- package/dist/chunk-YNJDNP44.js.map +0 -1
- package/dist/chunk-ZJ75YDW7.js.map +0 -1
- package/dist/chunk-ZMKTKJZN.cjs.map +0 -1
- package/dist/chunk-ZSL6MQVE.js.map +0 -1
- package/dist/chunk-ZYYTU7NY.js.map +0 -1
- package/dist/chunks-JEYQWXIZ.js +0 -10
- package/dist/formula-7ZPC54JO.js.map +0 -1
- package/dist/formula-EQRHSMYW.js.map +0 -1
- package/dist/formula-IWV5IJ3Y.cjs.map +0 -1
- package/dist/image-ocr-6MO4FXJK.js.map +0 -1
- package/dist/image-ocr-MGVXT6XD.cjs.map +0 -1
- package/dist/image-ocr-TWUU2RNG.js.map +0 -1
- package/dist/parser-JFGLN4DA.cjs.map +0 -1
- package/dist/parser-VR2BTUT7.js.map +0 -1
- package/dist/parser-YA7HSSPK.js.map +0 -1
- package/dist/pdf-ocr-4LISPZEM.cjs +0 -13
- package/dist/pdf-ocr-4LISPZEM.cjs.map +0 -1
- package/dist/pdf-ocr-AIWB2QCS.js +0 -12
- package/dist/pdf-ocr-QMOKUMC2.js +0 -15
- package/dist/rasterize-AFYGNKXG.js.map +0 -1
- package/dist/render-PSPTMZIZ.js +0 -10
- package/dist/seal-4XBJ7ISE.js +0 -10
- package/dist/setup-I4I75QJU.js.map +0 -1
- package/dist/watch-D3JJEOAB.js.map +0 -1
- /package/dist/{-RH6BEVTT.js.map → -7X4H77Z7.js.map} +0 -0
- /package/dist/{chunks-JEYQWXIZ.js.map → chunks-FMZK4QHL.js.map} +0 -0
- /package/dist/{models-6VMAVZR6.js.map → models-6SIKLKRH.js.map} +0 -0
- /package/dist/{pdf-ocr-AIWB2QCS.js.map → pdf-ocr-EL3VSWWY.js.map} +0 -0
- /package/dist/{pdf-ocr-QMOKUMC2.js.map → pdf-ocr-FVLKQNAT.js.map} +0 -0
- /package/dist/{profile-io-QPIMGVO3.js.map → profile-io-YADU6SKH.js.map} +0 -0
- /package/dist/{redact-W5K3ILQH.js.map → redact-7ILEAUTS.js.map} +0 -0
- /package/dist/{render-PSPTMZIZ.js.map → render-K6M3P24X.js.map} +0 -0
- /package/dist/{seal-4XBJ7ISE.js.map → seal-YW3U5BCY.js.map} +0 -0
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
|
|
6
6
|
|
|
7
|
-
var
|
|
7
|
+
var _chunk7BIVNIK5cjs = require('./chunk-7BIVNIK5.cjs');
|
|
8
8
|
|
|
9
9
|
// src/pdf/image-regions.ts
|
|
10
10
|
var _pdfmjs = require('pdfjs-dist/legacy/build/pdf.mjs');
|
|
@@ -1567,9 +1567,9 @@ function detectHeadings(blocks, medianFontSize) {
|
|
|
1567
1567
|
if (/^\d+$/.test(text)) continue;
|
|
1568
1568
|
const ratio = block.style.fontSize / medianFontSize;
|
|
1569
1569
|
let level = 0;
|
|
1570
|
-
if (ratio >=
|
|
1571
|
-
else if (ratio >=
|
|
1572
|
-
else if (ratio >=
|
|
1570
|
+
if (ratio >= _chunk7BIVNIK5cjs.HEADING_RATIO_H1) level = 1;
|
|
1571
|
+
else if (ratio >= _chunk7BIVNIK5cjs.HEADING_RATIO_H2) level = 2;
|
|
1572
|
+
else if (ratio >= _chunk7BIVNIK5cjs.HEADING_RATIO_H3) level = 3;
|
|
1573
1573
|
if (level > 0) {
|
|
1574
1574
|
block.type = "heading";
|
|
1575
1575
|
block.level = level;
|
|
@@ -2689,14 +2689,14 @@ function isProseSpread(items) {
|
|
|
2689
2689
|
for (let i = 1; i < sorted.length; i++) {
|
|
2690
2690
|
gaps.push(sorted[i].x - (sorted[i - 1].x + sorted[i - 1].w));
|
|
2691
2691
|
}
|
|
2692
|
-
const maxGap =
|
|
2692
|
+
const maxGap = _chunk7BIVNIK5cjs.safeMax.call(void 0, gaps);
|
|
2693
2693
|
const avgLen = items.reduce((s, i) => s + i.text.length, 0) / items.length;
|
|
2694
2694
|
return maxGap < 40 && avgLen < 5;
|
|
2695
2695
|
}
|
|
2696
2696
|
function detectColumns(yLines) {
|
|
2697
2697
|
const allItems = yLines.flat();
|
|
2698
2698
|
if (allItems.length === 0) return null;
|
|
2699
|
-
const pageWidth =
|
|
2699
|
+
const pageWidth = _chunk7BIVNIK5cjs.safeMax.call(void 0, allItems.map((i) => i.x + i.w)) - _chunk7BIVNIK5cjs.safeMin.call(void 0, allItems.map((i) => i.x));
|
|
2700
2700
|
if (pageWidth < 100) return null;
|
|
2701
2701
|
let bigoLineIdx = -1;
|
|
2702
2702
|
for (let i = 0; i < yLines.length; i++) {
|
|
@@ -3144,7 +3144,7 @@ function extractBlocksWithGrids(items, pageNum, grids, horizontals, verticals) {
|
|
|
3144
3144
|
let finalTextBlocks = [];
|
|
3145
3145
|
if (remaining.length > 0) {
|
|
3146
3146
|
const allY = remaining.map((i) => i.y);
|
|
3147
|
-
const pageH =
|
|
3147
|
+
const pageH = _chunk7BIVNIK5cjs.safeMax.call(void 0, allY) - _chunk7BIVNIK5cjs.safeMin.call(void 0, allY);
|
|
3148
3148
|
const groups = xyCutOrder(remaining, Math.max(15, pageH * 0.03));
|
|
3149
3149
|
const textBlocks = [];
|
|
3150
3150
|
for (const group of groups) {
|
|
@@ -3332,7 +3332,7 @@ function extractPageBlocksFallback(items, pageNum, fullPage = false) {
|
|
|
3332
3332
|
blocks.push({ type: "paragraph", text: tableText, pageNumber: pageNum, bbox, style: dominantStyle(items) });
|
|
3333
3333
|
} else {
|
|
3334
3334
|
const allY = items.map((i) => i.y);
|
|
3335
|
-
const pageHeight =
|
|
3335
|
+
const pageHeight = _chunk7BIVNIK5cjs.safeMax.call(void 0, allY) - _chunk7BIVNIK5cjs.safeMin.call(void 0, allY);
|
|
3336
3336
|
const gapThreshold = Math.max(15, pageHeight * 0.03);
|
|
3337
3337
|
const orderedGroups = proseCutX !== null ? splitTwoColumnProse(items, proseCutX) : xyCutOrder(items, gapThreshold);
|
|
3338
3338
|
for (const group of orderedGroups) {
|
|
@@ -3371,4 +3371,4 @@ function extractPageBlocksFallback(items, pageNum, fullPage = false) {
|
|
|
3371
3371
|
|
|
3372
3372
|
|
|
3373
3373
|
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;
|
|
3374
|
-
//# sourceMappingURL=chunk-
|
|
3374
|
+
//# sourceMappingURL=chunk-3DX6VJGH.cjs.map
|