kordoc 4.2.6 → 4.2.7
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/dist/{-UYYP67I6.js → -7TEU6IRU.js} +8 -8
- package/dist/{chunk-6KT4B4QX.js → chunk-2CHFQQXM.js} +2 -2
- package/dist/{chunk-64DMMXFW.js → chunk-5HFKMCAX.js} +2 -2
- package/dist/{chunk-N4BFHNLA.js → chunk-62DHK6KT.js} +2 -2
- package/dist/{chunk-NVPCKSNL.js → chunk-AES6PHIG.js} +2 -2
- package/dist/chunk-DCZVOIEO.cjs.map +1 -1
- package/dist/{chunk-YF6JUAM7.js → chunk-ESV4KOSE.js} +3 -3
- package/dist/{chunk-EGQQVYKL.js → chunk-FSUCQ6ZM.js} +3 -3
- package/dist/{chunk-O5JOHYCV.js → chunk-G2AS6ICC.js} +2 -2
- package/dist/chunk-GS7T56RP.cjs.map +1 -1
- package/dist/chunk-H7OWEYH2.cjs.map +1 -1
- package/dist/{chunk-5FS4IZWY.cjs → chunk-HH4SD5RE.cjs} +2 -2
- package/dist/chunk-HH4SD5RE.cjs.map +1 -0
- package/dist/{chunk-TZLLCYDN.js → chunk-IVX3YLQH.js} +2 -2
- package/dist/{chunk-VQ5NQBL2.js → chunk-LPRNVK4G.js} +19 -10
- package/dist/{chunk-VQ5NQBL2.js.map → chunk-LPRNVK4G.js.map} +1 -1
- package/dist/{chunk-QPPOC6OL.js → chunk-NAWC6HTC.js} +2 -2
- package/dist/{chunk-SYJ6FPPQ.js → chunk-NKERQ6GB.js} +2 -2
- package/dist/{chunk-DSCSR6NE.js → chunk-PK5GLL5C.js} +2 -2
- package/dist/{chunk-ZB3WT7XX.cjs → chunk-RS5OID2J.cjs} +9 -9
- package/dist/chunk-RS5OID2J.cjs.map +1 -0
- package/dist/{chunk-YHAB7UP6.js → chunk-T6BTWUTC.js} +2 -2
- package/dist/{chunk-6XVQSILN.cjs → chunk-VWXA47AW.cjs} +4 -4
- package/dist/chunk-VWXA47AW.cjs.map +1 -0
- package/dist/{chunk-5E7ZMWDF.js → chunk-YAQRGQUJ.js} +2 -2
- package/dist/{chunk-LIG666DX.cjs → chunk-YTRJDQ4Q.cjs} +3 -3
- package/dist/chunk-YTRJDQ4Q.cjs.map +1 -0
- package/dist/chunks-TLAOHNPB.js +10 -0
- package/dist/cli.js +16 -16
- package/dist/formula-SB3NHDUM.cjs.map +1 -1
- package/dist/{image-ocr-WN3UO4UY.js → image-ocr-OS4ETBOL.js} +4 -4
- package/dist/{image-ocr-FXLX2GM6.js → image-ocr-PGQ7JPDP.js} +4 -4
- package/dist/{image-ocr-YOUVLJIH.cjs → image-ocr-UX4QM35J.cjs} +9 -9
- package/dist/image-ocr-UX4QM35J.cjs.map +1 -0
- package/dist/index.cjs +162 -153
- package/dist/index.cjs.map +1 -1
- package/dist/index.js +15 -6
- package/dist/index.js.map +1 -1
- package/dist/mcp.js +14 -14
- package/dist/page-range-P7SDW6LR.cjs.map +1 -1
- package/dist/{parser-KIXK2IEX.js → parser-2JAC5WMM.js} +5 -5
- package/dist/{parser-AUMEO4OU.cjs → parser-GAZROLSA.cjs} +24 -24
- package/dist/parser-GAZROLSA.cjs.map +1 -0
- package/dist/{parser-KYSMRSMJ.js → parser-T74C7Q57.js} +5 -5
- package/dist/pdf-ocr-2SKGRXIR.cjs +13 -0
- package/dist/pdf-ocr-2SKGRXIR.cjs.map +1 -0
- package/dist/{pdf-ocr-NQFV46WZ.js → pdf-ocr-3A3QLPID.js} +4 -4
- package/dist/pdf-ocr-WBOTDQ4D.js +12 -0
- package/dist/{profile-io-NKUXEPI4.js → profile-io-6GX564CO.js} +3 -3
- package/dist/{rasterize-OT5TROD4.js → rasterize-4V7PKE7A.js} +2 -2
- package/dist/render-2AF7GZVN.js +10 -0
- package/dist/seal-2ES6UAN6.js +10 -0
- package/dist/{watch-6KMSCCM5.js → watch-JVRAAJNA.js} +8 -8
- package/package.json +1 -1
- package/dist/chunk-5FS4IZWY.cjs.map +0 -1
- package/dist/chunk-6XVQSILN.cjs.map +0 -1
- package/dist/chunk-LIG666DX.cjs.map +0 -1
- package/dist/chunk-ZB3WT7XX.cjs.map +0 -1
- package/dist/chunks-G7YDTLNI.js +0 -10
- package/dist/image-ocr-YOUVLJIH.cjs.map +0 -1
- package/dist/parser-AUMEO4OU.cjs.map +0 -1
- package/dist/pdf-ocr-2QOASWPI.js +0 -12
- package/dist/pdf-ocr-BUKZ5R4P.cjs +0 -13
- package/dist/pdf-ocr-BUKZ5R4P.cjs.map +0 -1
- package/dist/render-HQTKZ3ZE.js +0 -10
- package/dist/seal-KH6IL23B.js +0 -10
- /package/dist/{-UYYP67I6.js.map → -7TEU6IRU.js.map} +0 -0
- /package/dist/{chunk-6KT4B4QX.js.map → chunk-2CHFQQXM.js.map} +0 -0
- /package/dist/{chunk-64DMMXFW.js.map → chunk-5HFKMCAX.js.map} +0 -0
- /package/dist/{chunk-N4BFHNLA.js.map → chunk-62DHK6KT.js.map} +0 -0
- /package/dist/{chunk-NVPCKSNL.js.map → chunk-AES6PHIG.js.map} +0 -0
- /package/dist/{chunk-YF6JUAM7.js.map → chunk-ESV4KOSE.js.map} +0 -0
- /package/dist/{chunk-EGQQVYKL.js.map → chunk-FSUCQ6ZM.js.map} +0 -0
- /package/dist/{chunk-O5JOHYCV.js.map → chunk-G2AS6ICC.js.map} +0 -0
- /package/dist/{chunk-TZLLCYDN.js.map → chunk-IVX3YLQH.js.map} +0 -0
- /package/dist/{chunk-QPPOC6OL.js.map → chunk-NAWC6HTC.js.map} +0 -0
- /package/dist/{chunk-SYJ6FPPQ.js.map → chunk-NKERQ6GB.js.map} +0 -0
- /package/dist/{chunk-DSCSR6NE.js.map → chunk-PK5GLL5C.js.map} +0 -0
- /package/dist/{chunk-YHAB7UP6.js.map → chunk-T6BTWUTC.js.map} +0 -0
- /package/dist/{chunk-5E7ZMWDF.js.map → chunk-YAQRGQUJ.js.map} +0 -0
- /package/dist/{chunks-G7YDTLNI.js.map → chunks-TLAOHNPB.js.map} +0 -0
- /package/dist/{image-ocr-WN3UO4UY.js.map → image-ocr-OS4ETBOL.js.map} +0 -0
- /package/dist/{image-ocr-FXLX2GM6.js.map → image-ocr-PGQ7JPDP.js.map} +0 -0
- /package/dist/{parser-KIXK2IEX.js.map → parser-2JAC5WMM.js.map} +0 -0
- /package/dist/{parser-KYSMRSMJ.js.map → parser-T74C7Q57.js.map} +0 -0
- /package/dist/{pdf-ocr-2QOASWPI.js.map → pdf-ocr-3A3QLPID.js.map} +0 -0
- /package/dist/{pdf-ocr-NQFV46WZ.js.map → pdf-ocr-WBOTDQ4D.js.map} +0 -0
- /package/dist/{profile-io-NKUXEPI4.js.map → profile-io-6GX564CO.js.map} +0 -0
- /package/dist/{rasterize-OT5TROD4.js.map → rasterize-4V7PKE7A.js.map} +0 -0
- /package/dist/{render-HQTKZ3ZE.js.map → render-2AF7GZVN.js.map} +0 -0
- /package/dist/{seal-KH6IL23B.js.map → seal-2ES6UAN6.js.map} +0 -0
- /package/dist/{watch-6KMSCCM5.js.map → watch-JVRAAJNA.js.map} +0 -0
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
#!/usr/bin/env node
|
|
2
2
|
import {
|
|
3
3
|
KordocError
|
|
4
|
-
} from "./chunk-
|
|
4
|
+
} from "./chunk-G2AS6ICC.js";
|
|
5
5
|
|
|
6
6
|
// src/hwpx/parser-shared.ts
|
|
7
7
|
import { DOMParser } from "@xmldom/xmldom";
|
|
@@ -273,4 +273,4 @@ export {
|
|
|
273
273
|
DEFAULT_CHAR,
|
|
274
274
|
parseRenderStyles
|
|
275
275
|
};
|
|
276
|
-
//# sourceMappingURL=chunk-
|
|
276
|
+
//# sourceMappingURL=chunk-NAWC6HTC.js.map
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
#!/usr/bin/env node
|
|
2
2
|
import {
|
|
3
3
|
KordocError
|
|
4
|
-
} from "./chunk-
|
|
4
|
+
} from "./chunk-G2AS6ICC.js";
|
|
5
5
|
|
|
6
6
|
// src/hwpx/profile-io.ts
|
|
7
7
|
import { z } from "zod";
|
|
@@ -89,4 +89,4 @@ export {
|
|
|
89
89
|
formatProfileSchema,
|
|
90
90
|
parseFormatProfileJson
|
|
91
91
|
};
|
|
92
|
-
//# sourceMappingURL=chunk-
|
|
92
|
+
//# sourceMappingURL=chunk-NKERQ6GB.js.map
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
#!/usr/bin/env node
|
|
2
2
|
import {
|
|
3
3
|
blocksToMarkdown
|
|
4
|
-
} from "./chunk-
|
|
4
|
+
} from "./chunk-T6BTWUTC.js";
|
|
5
5
|
|
|
6
6
|
// src/chunks.ts
|
|
7
7
|
var LIST_MARKER_RE = /^(?:[□■◇◆○◎●◦ㅇ•▪▸▶※-]|\d{1,3}[.)]|[가나다라마바사아자차카타파하][.)]|\([가나다라마바사아자차카타파하0-9]{1,3}\)|[①-⑳㉮-㉻㈎-㈛])\s/;
|
|
@@ -79,4 +79,4 @@ function blocksToChunks(blocks, options) {
|
|
|
79
79
|
export {
|
|
80
80
|
blocksToChunks
|
|
81
81
|
};
|
|
82
|
-
//# sourceMappingURL=chunk-
|
|
82
|
+
//# sourceMappingURL=chunk-PK5GLL5C.js.map
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
|
|
6
6
|
|
|
7
|
-
var
|
|
7
|
+
var _chunkHH4SD5REcjs = require('./chunk-HH4SD5RE.cjs');
|
|
8
8
|
|
|
9
9
|
// src/pdf/image-regions.ts
|
|
10
10
|
var _pdfmjs = require('pdfjs-dist/legacy/build/pdf.mjs');
|
|
@@ -1536,9 +1536,9 @@ function detectHeadings(blocks, medianFontSize) {
|
|
|
1536
1536
|
if (/^\d+$/.test(text)) continue;
|
|
1537
1537
|
const ratio = block.style.fontSize / medianFontSize;
|
|
1538
1538
|
let level = 0;
|
|
1539
|
-
if (ratio >=
|
|
1540
|
-
else if (ratio >=
|
|
1541
|
-
else if (ratio >=
|
|
1539
|
+
if (ratio >= _chunkHH4SD5REcjs.HEADING_RATIO_H1) level = 1;
|
|
1540
|
+
else if (ratio >= _chunkHH4SD5REcjs.HEADING_RATIO_H2) level = 2;
|
|
1541
|
+
else if (ratio >= _chunkHH4SD5REcjs.HEADING_RATIO_H3) level = 3;
|
|
1542
1542
|
if (level > 0) {
|
|
1543
1543
|
block.type = "heading";
|
|
1544
1544
|
block.level = level;
|
|
@@ -2658,14 +2658,14 @@ function isProseSpread(items) {
|
|
|
2658
2658
|
for (let i = 1; i < sorted.length; i++) {
|
|
2659
2659
|
gaps.push(sorted[i].x - (sorted[i - 1].x + sorted[i - 1].w));
|
|
2660
2660
|
}
|
|
2661
|
-
const maxGap =
|
|
2661
|
+
const maxGap = _chunkHH4SD5REcjs.safeMax.call(void 0, gaps);
|
|
2662
2662
|
const avgLen = items.reduce((s, i) => s + i.text.length, 0) / items.length;
|
|
2663
2663
|
return maxGap < 40 && avgLen < 5;
|
|
2664
2664
|
}
|
|
2665
2665
|
function detectColumns(yLines) {
|
|
2666
2666
|
const allItems = yLines.flat();
|
|
2667
2667
|
if (allItems.length === 0) return null;
|
|
2668
|
-
const pageWidth =
|
|
2668
|
+
const pageWidth = _chunkHH4SD5REcjs.safeMax.call(void 0, allItems.map((i) => i.x + i.w)) - _chunkHH4SD5REcjs.safeMin.call(void 0, allItems.map((i) => i.x));
|
|
2669
2669
|
if (pageWidth < 100) return null;
|
|
2670
2670
|
let bigoLineIdx = -1;
|
|
2671
2671
|
for (let i = 0; i < yLines.length; i++) {
|
|
@@ -3113,7 +3113,7 @@ function extractBlocksWithGrids(items, pageNum, grids, horizontals, verticals) {
|
|
|
3113
3113
|
let finalTextBlocks = [];
|
|
3114
3114
|
if (remaining.length > 0) {
|
|
3115
3115
|
const allY = remaining.map((i) => i.y);
|
|
3116
|
-
const pageH =
|
|
3116
|
+
const pageH = _chunkHH4SD5REcjs.safeMax.call(void 0, allY) - _chunkHH4SD5REcjs.safeMin.call(void 0, allY);
|
|
3117
3117
|
const groups = xyCutOrder(remaining, Math.max(15, pageH * 0.03));
|
|
3118
3118
|
const textBlocks = [];
|
|
3119
3119
|
for (const group of groups) {
|
|
@@ -3301,7 +3301,7 @@ function extractPageBlocksFallback(items, pageNum, fullPage = false) {
|
|
|
3301
3301
|
blocks.push({ type: "paragraph", text: tableText, pageNumber: pageNum, bbox, style: dominantStyle(items) });
|
|
3302
3302
|
} else {
|
|
3303
3303
|
const allY = items.map((i) => i.y);
|
|
3304
|
-
const pageHeight =
|
|
3304
|
+
const pageHeight = _chunkHH4SD5REcjs.safeMax.call(void 0, allY) - _chunkHH4SD5REcjs.safeMin.call(void 0, allY);
|
|
3305
3305
|
const gapThreshold = Math.max(15, pageHeight * 0.03);
|
|
3306
3306
|
const orderedGroups = proseCutX !== null ? splitTwoColumnProse(items, proseCutX) : xyCutOrder(items, gapThreshold);
|
|
3307
3307
|
for (const group of orderedGroups) {
|
|
@@ -3340,4 +3340,4 @@ function extractPageBlocksFallback(items, pageNum, fullPage = false) {
|
|
|
3340
3340
|
|
|
3341
3341
|
|
|
3342
3342
|
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;
|
|
3343
|
-
//# sourceMappingURL=chunk-
|
|
3343
|
+
//# sourceMappingURL=chunk-RS5OID2J.cjs.map
|