kordoc 4.12.3 → 4.13.0
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 +21 -1
- package/dist/{-FWGDIOV4.js → -UZDRUWTX.js} +43 -22
- package/dist/{chunk-PUZZFYLV.js → chunk-27QN27I3.js} +2 -2
- package/dist/{chunk-KRE2SREV.js → chunk-2B45S7FM.js} +2 -2
- package/dist/{chunk-INFYDSZL.js → chunk-2RREQZ44.js} +1562 -641
- package/dist/chunk-2RREQZ44.js.map +1 -0
- package/dist/{chunk-2DAFWDV2.js → chunk-3ABHPKYA.js} +3 -3
- package/dist/{chunk-TWKXX343.js → chunk-3MCFJIN2.js} +5 -5
- package/dist/{chunk-BAZMKQZW.js → chunk-5VHLKNCE.js} +2 -2
- package/dist/{chunk-YBZJMAE2.js → chunk-6JXMIX3G.js} +2 -2
- package/dist/chunk-6JXMIX3G.js.map +1 -0
- package/dist/{chunk-3KQOI6R6.js → chunk-6NLXGGNH.js} +11 -5
- package/dist/chunk-6NLXGGNH.js.map +1 -0
- package/dist/{chunk-HB56YANA.js → chunk-AGBFCFQY.js} +7 -6
- package/dist/chunk-AGBFCFQY.js.map +1 -0
- package/dist/{rasterize-ALCNU53T.js → chunk-BQLZOQES.js} +22 -6
- package/dist/chunk-BQLZOQES.js.map +1 -0
- package/dist/{chunk-7BIXTQZ3.cjs → chunk-CKMK42FV.cjs} +11 -11
- package/dist/{chunk-7BIXTQZ3.cjs.map → chunk-CKMK42FV.cjs.map} +1 -1
- package/dist/{chunk-T7GRHAIW.cjs → chunk-COUGOFT3.cjs} +1 -1
- package/dist/chunk-COUGOFT3.cjs.map +1 -0
- package/dist/{chunk-SJEPQOVW.js → chunk-F3FEIYI7.js} +2 -2
- package/dist/{chunk-ZASGH5EN.js → chunk-GWFX5ZD7.js} +8 -7
- package/dist/{chunk-ZASGH5EN.js.map → chunk-GWFX5ZD7.js.map} +1 -1
- package/dist/{chunk-IC6HHXFL.js → chunk-H5JWPWQP.js} +2 -2
- package/dist/{chunk-N3DLQ2YH.js → chunk-HG5LXXCC.js} +1 -1
- package/dist/chunk-HG5LXXCC.js.map +1 -0
- package/dist/{chunk-CKYDP34A.js → chunk-IEJR23OA.js} +3 -3
- package/dist/{chunk-DUGUCM7K.js → chunk-ILDTN72S.js} +3 -3
- package/dist/{chunk-OJDMMZ5Z.js → chunk-L3CEPNQS.js} +2 -2
- package/dist/{chunk-KLO6RHX2.js → chunk-LP5RTYFM.js} +2 -2
- package/dist/{chunk-FFITS3NY.cjs → chunk-MCD45IHO.cjs} +6 -6
- package/dist/{chunk-FFITS3NY.cjs.map → chunk-MCD45IHO.cjs.map} +1 -1
- package/dist/{chunk-BOATAEXU.cjs → chunk-OJV7HNGJ.cjs} +10 -9
- package/dist/chunk-OJV7HNGJ.cjs.map +1 -0
- package/dist/{chunk-6L3B44DH.js → chunk-OSLJ3A6D.js} +2 -2
- package/dist/{chunk-W3H2H55O.cjs → chunk-S2VKZKUX.cjs} +3 -3
- package/dist/{chunk-W3H2H55O.cjs.map → chunk-S2VKZKUX.cjs.map} +1 -1
- package/dist/{chunk-B63QEHYL.js → chunk-T7AFLXGA.js} +786 -19
- package/dist/chunk-T7AFLXGA.js.map +1 -0
- package/dist/{chunk-PL4V523B.js → chunk-TA2LEFOF.js} +3 -3
- package/dist/{chunk-ISCI5LKN.cjs → chunk-TAYCQE6K.cjs} +2 -2
- package/dist/{chunk-ISCI5LKN.cjs.map → chunk-TAYCQE6K.cjs.map} +1 -1
- package/dist/{chunk-ONQHGZTS.js → chunk-XVIJLHCW.js} +1 -1
- package/dist/chunk-XVIJLHCW.js.map +1 -0
- package/dist/chunks-G3GK536Y.js +10 -0
- package/dist/cli.js +179 -37
- package/dist/cli.js.map +1 -1
- package/dist/{formula-YJWKEPUK.js → formula-3T7HQA4O.js} +4 -4
- package/dist/{formula-R7IWAAYR.js → formula-FWVAOSIK.js} +3 -3
- package/dist/{formula-ZYHUXTK5.cjs → formula-YALEMZMF.cjs} +9 -9
- package/dist/{formula-ZYHUXTK5.cjs.map → formula-YALEMZMF.cjs.map} +1 -1
- package/dist/{image-ocr-G4JVF2UH.js → image-ocr-2M7K3CE5.js} +8 -8
- package/dist/{image-ocr-6O6ZXKUD.cjs → image-ocr-4EUZIF6M.cjs} +12 -12
- package/dist/{image-ocr-6O6ZXKUD.cjs.map → image-ocr-4EUZIF6M.cjs.map} +1 -1
- package/dist/{image-ocr-OLTSKQWD.js → image-ocr-X3I2HUK2.js} +6 -6
- package/dist/index.cjs +2259 -575
- package/dist/index.cjs.map +1 -1
- package/dist/index.d.cts +288 -12
- package/dist/index.d.ts +288 -12
- package/dist/index.js +1880 -196
- package/dist/index.js.map +1 -1
- package/dist/mcp.js +106 -35
- package/dist/mcp.js.map +1 -1
- package/dist/{model-bundle-IFD2D5CW.js → model-bundle-XXYZ6ELQ.js} +5 -5
- package/dist/{models-FJ3IUNTB.js → models-APDSXJW7.js} +5 -5
- package/dist/{parser-YLLIYOIZ.cjs → parser-4KE2FR5F.cjs} +27 -27
- package/dist/{parser-YLLIYOIZ.cjs.map → parser-4KE2FR5F.cjs.map} +1 -1
- package/dist/{parser-I7TC35V6.js → parser-T5R4YVZS.js} +7 -7
- package/dist/{parser-JRT3B6OK.js → parser-XKSOS6GY.js} +7 -7
- package/dist/pdf-ocr-JZKCEKWX.cjs +14 -0
- package/dist/{pdf-ocr-ADUP2LPU.cjs.map → pdf-ocr-JZKCEKWX.cjs.map} +1 -1
- package/dist/pdf-ocr-X62B7YDV.js +13 -0
- package/dist/pdf-ocr-YDJQEGDS.js +16 -0
- package/dist/{profile-io-BPJQQZLQ.js → profile-io-Y24GOHWM.js} +3 -3
- package/dist/rasterize-QCOBWHAG.js +13 -0
- package/dist/render-DHFQQCSV.js +38 -0
- package/dist/seal-UTHFQPLO.js +10 -0
- package/dist/seal-UTHFQPLO.js.map +1 -0
- package/dist/{setup-O2DALZKF.js → setup-UWX3KH3G.js} +3 -3
- package/dist/visual-DF2KSPEC.js +19 -0
- package/dist/visual-DF2KSPEC.js.map +1 -0
- package/dist/{watch-GPWYJAS2.js → watch-4ZUTMC3Q.js} +15 -13
- package/dist/{watch-GPWYJAS2.js.map → watch-4ZUTMC3Q.js.map} +1 -1
- package/package.json +1 -1
- package/dist/chunk-3KQOI6R6.js.map +0 -1
- package/dist/chunk-B63QEHYL.js.map +0 -1
- package/dist/chunk-BOATAEXU.cjs.map +0 -1
- package/dist/chunk-HB56YANA.js.map +0 -1
- package/dist/chunk-INFYDSZL.js.map +0 -1
- package/dist/chunk-N3DLQ2YH.js.map +0 -1
- package/dist/chunk-ONQHGZTS.js.map +0 -1
- package/dist/chunk-T7GRHAIW.cjs.map +0 -1
- package/dist/chunk-YBZJMAE2.js.map +0 -1
- package/dist/chunks-VICNQMNE.js +0 -10
- package/dist/pdf-ocr-ADUP2LPU.cjs +0 -14
- package/dist/pdf-ocr-ATJTB2B3.js +0 -13
- package/dist/pdf-ocr-P75KSZFV.js +0 -16
- package/dist/rasterize-ALCNU53T.js.map +0 -1
- package/dist/render-MDLTQUUV.js +0 -10
- package/dist/seal-K4K3KPE3.js +0 -10
- /package/dist/{-FWGDIOV4.js.map → -UZDRUWTX.js.map} +0 -0
- /package/dist/{chunk-PUZZFYLV.js.map → chunk-27QN27I3.js.map} +0 -0
- /package/dist/{chunk-KRE2SREV.js.map → chunk-2B45S7FM.js.map} +0 -0
- /package/dist/{chunk-2DAFWDV2.js.map → chunk-3ABHPKYA.js.map} +0 -0
- /package/dist/{chunk-TWKXX343.js.map → chunk-3MCFJIN2.js.map} +0 -0
- /package/dist/{chunk-BAZMKQZW.js.map → chunk-5VHLKNCE.js.map} +0 -0
- /package/dist/{chunk-SJEPQOVW.js.map → chunk-F3FEIYI7.js.map} +0 -0
- /package/dist/{chunk-IC6HHXFL.js.map → chunk-H5JWPWQP.js.map} +0 -0
- /package/dist/{chunk-CKYDP34A.js.map → chunk-IEJR23OA.js.map} +0 -0
- /package/dist/{chunk-DUGUCM7K.js.map → chunk-ILDTN72S.js.map} +0 -0
- /package/dist/{chunk-OJDMMZ5Z.js.map → chunk-L3CEPNQS.js.map} +0 -0
- /package/dist/{chunk-KLO6RHX2.js.map → chunk-LP5RTYFM.js.map} +0 -0
- /package/dist/{chunk-6L3B44DH.js.map → chunk-OSLJ3A6D.js.map} +0 -0
- /package/dist/{chunk-PL4V523B.js.map → chunk-TA2LEFOF.js.map} +0 -0
- /package/dist/{chunks-VICNQMNE.js.map → chunks-G3GK536Y.js.map} +0 -0
- /package/dist/{formula-YJWKEPUK.js.map → formula-3T7HQA4O.js.map} +0 -0
- /package/dist/{formula-R7IWAAYR.js.map → formula-FWVAOSIK.js.map} +0 -0
- /package/dist/{image-ocr-G4JVF2UH.js.map → image-ocr-2M7K3CE5.js.map} +0 -0
- /package/dist/{image-ocr-OLTSKQWD.js.map → image-ocr-X3I2HUK2.js.map} +0 -0
- /package/dist/{model-bundle-IFD2D5CW.js.map → model-bundle-XXYZ6ELQ.js.map} +0 -0
- /package/dist/{models-FJ3IUNTB.js.map → models-APDSXJW7.js.map} +0 -0
- /package/dist/{parser-I7TC35V6.js.map → parser-T5R4YVZS.js.map} +0 -0
- /package/dist/{parser-JRT3B6OK.js.map → parser-XKSOS6GY.js.map} +0 -0
- /package/dist/{pdf-ocr-ATJTB2B3.js.map → pdf-ocr-X62B7YDV.js.map} +0 -0
- /package/dist/{pdf-ocr-P75KSZFV.js.map → pdf-ocr-YDJQEGDS.js.map} +0 -0
- /package/dist/{profile-io-BPJQQZLQ.js.map → profile-io-Y24GOHWM.js.map} +0 -0
- /package/dist/{render-MDLTQUUV.js.map → rasterize-QCOBWHAG.js.map} +0 -0
- /package/dist/{seal-K4K3KPE3.js.map → render-DHFQQCSV.js.map} +0 -0
- /package/dist/{setup-O2DALZKF.js.map → setup-UWX3KH3G.js.map} +0 -0
|
@@ -2,11 +2,11 @@
|
|
|
2
2
|
|
|
3
3
|
|
|
4
4
|
|
|
5
|
-
var
|
|
5
|
+
var _chunkCOUGOFT3cjs = require('./chunk-COUGOFT3.cjs');
|
|
6
6
|
|
|
7
7
|
|
|
8
8
|
|
|
9
|
-
var
|
|
9
|
+
var _chunkTAYCQE6Kcjs = require('./chunk-TAYCQE6K.cjs');
|
|
10
10
|
|
|
11
11
|
// src/pdf/image-regions.ts
|
|
12
12
|
var _pdfmjs = require('pdfjs-dist/legacy/build/pdf.mjs');
|
|
@@ -1781,9 +1781,9 @@ function detectHeadings(blocks, medianFontSize) {
|
|
|
1781
1781
|
if (/^\d+$/.test(text)) continue;
|
|
1782
1782
|
const ratio = block.style.fontSize / medianFontSize;
|
|
1783
1783
|
let level = 0;
|
|
1784
|
-
if (ratio >=
|
|
1785
|
-
else if (ratio >=
|
|
1786
|
-
else if (ratio >=
|
|
1784
|
+
if (ratio >= _chunkCOUGOFT3cjs.HEADING_RATIO_H1) level = 1;
|
|
1785
|
+
else if (ratio >= _chunkCOUGOFT3cjs.HEADING_RATIO_H2) level = 2;
|
|
1786
|
+
else if (ratio >= _chunkCOUGOFT3cjs.HEADING_RATIO_H3) level = 3;
|
|
1787
1787
|
if (level > 0) {
|
|
1788
1788
|
block.type = "heading";
|
|
1789
1789
|
block.level = level;
|
|
@@ -3046,14 +3046,14 @@ function isProseSpread(items) {
|
|
|
3046
3046
|
for (let i = 1; i < sorted.length; i++) {
|
|
3047
3047
|
gaps.push(sorted[i].x - (sorted[i - 1].x + sorted[i - 1].w));
|
|
3048
3048
|
}
|
|
3049
|
-
const maxGap =
|
|
3049
|
+
const maxGap = _chunkTAYCQE6Kcjs.safeMax.call(void 0, gaps);
|
|
3050
3050
|
const avgLen = items.reduce((s, i) => s + i.text.length, 0) / items.length;
|
|
3051
3051
|
return maxGap < 40 && avgLen < 5;
|
|
3052
3052
|
}
|
|
3053
3053
|
function detectColumns(yLines) {
|
|
3054
3054
|
const allItems = yLines.flat();
|
|
3055
3055
|
if (allItems.length === 0) return null;
|
|
3056
|
-
const pageWidth =
|
|
3056
|
+
const pageWidth = _chunkTAYCQE6Kcjs.safeMax.call(void 0, allItems.map((i) => i.x + i.w)) - _chunkTAYCQE6Kcjs.safeMin.call(void 0, allItems.map((i) => i.x));
|
|
3057
3057
|
if (pageWidth < 100) return null;
|
|
3058
3058
|
let bigoLineIdx = -1;
|
|
3059
3059
|
for (let i = 0; i < yLines.length; i++) {
|
|
@@ -3678,7 +3678,7 @@ function extractBlocksWithGrids(items, pageNum, grids, horizontals, verticals) {
|
|
|
3678
3678
|
if (gutterX !== null) {
|
|
3679
3679
|
const gx = gutterX;
|
|
3680
3680
|
const allY = remaining.map((i) => i.y);
|
|
3681
|
-
const pageH =
|
|
3681
|
+
const pageH = _chunkTAYCQE6Kcjs.safeMax.call(void 0, allY) - _chunkTAYCQE6Kcjs.safeMin.call(void 0, allY);
|
|
3682
3682
|
const gapThreshold = Math.max(15, pageH * 0.03);
|
|
3683
3683
|
const sides = [
|
|
3684
3684
|
remaining.filter((i) => i.x + i.w <= gx),
|
|
@@ -3698,7 +3698,7 @@ function extractBlocksWithGrids(items, pageNum, grids, horizontals, verticals) {
|
|
|
3698
3698
|
finalTextBlocks = detectListBlocks(textBlocks);
|
|
3699
3699
|
} else {
|
|
3700
3700
|
const allY = remaining.map((i) => i.y);
|
|
3701
|
-
const pageH =
|
|
3701
|
+
const pageH = _chunkTAYCQE6Kcjs.safeMax.call(void 0, allY) - _chunkTAYCQE6Kcjs.safeMin.call(void 0, allY);
|
|
3702
3702
|
const groups = xyCutOrder(remaining, Math.max(15, pageH * 0.03));
|
|
3703
3703
|
const textBlocks = [];
|
|
3704
3704
|
for (const group of groups) {
|
|
@@ -3906,7 +3906,7 @@ function extractPageBlocksFallback(items, pageNum, fullPage = false, detectTable
|
|
|
3906
3906
|
blocks.push({ type: "paragraph", text: tableText, pageNumber: pageNum, bbox, style: dominantStyle(items) });
|
|
3907
3907
|
} else {
|
|
3908
3908
|
const allY = items.map((i) => i.y);
|
|
3909
|
-
const pageHeight =
|
|
3909
|
+
const pageHeight = _chunkTAYCQE6Kcjs.safeMax.call(void 0, allY) - _chunkTAYCQE6Kcjs.safeMin.call(void 0, allY);
|
|
3910
3910
|
const gapThreshold = Math.max(15, pageHeight * 0.03);
|
|
3911
3911
|
const orderedGroups = proseCutX !== null ? splitTwoColumnProse(items, proseCutX) : xyCutOrder(items, gapThreshold);
|
|
3912
3912
|
for (const group of orderedGroups) {
|
|
@@ -3945,4 +3945,4 @@ function extractPageBlocksFallback(items, pageNum, fullPage = false, detectTable
|
|
|
3945
3945
|
|
|
3946
3946
|
|
|
3947
3947
|
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;
|
|
3948
|
-
//# sourceMappingURL=chunk-
|
|
3948
|
+
//# sourceMappingURL=chunk-CKMK42FV.cjs.map
|