kordoc 4.16.2 → 4.16.3
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 +3 -6
- package/dist/{-4G6MA4X6.js → -5XQIJN3D.js} +10 -10
- package/dist/{chunk-UTP2WCHS.js → chunk-2EJ5YSFZ.js} +4 -4
- package/dist/{chunk-IQGIT2VX.js → chunk-3ZVZPYSA.js} +5 -5
- package/dist/{chunk-TXUKTOG2.js → chunk-46H2PPG7.js} +3 -3
- package/dist/{chunk-7KNGSQU7.js → chunk-4O5XQSCT.js} +2 -2
- package/dist/{chunk-MLIS253L.js → chunk-7NYRZI2Z.js} +2 -2
- package/dist/{chunk-GO5IFOUF.js → chunk-7USPM2VT.js} +2 -2
- package/dist/{chunk-XTFN5WKS.cjs → chunk-7WV3WETF.cjs} +6 -6
- package/dist/{chunk-XTFN5WKS.cjs.map → chunk-7WV3WETF.cjs.map} +1 -1
- package/dist/{chunk-KIOQ4N37.js → chunk-AL2WM6ZZ.js} +2 -2
- package/dist/{chunk-F4NRLLY4.js → chunk-AWWFGIBA.js} +2 -2
- package/dist/{chunk-QOCS7W7R.js → chunk-D2UGAEXY.js} +9 -9
- package/dist/{chunk-P6ZDXTV6.js → chunk-ENF34XNH.js} +2 -2
- package/dist/{chunk-5KS5PWJR.js → chunk-GGGO3OH2.js} +2 -2
- package/dist/{chunk-JFLAM3MM.js → chunk-GH2JGKWP.js} +2 -2
- package/dist/{chunk-S2PL227Q.js → chunk-IE6QX3T3.js} +2 -2
- package/dist/{chunk-LEIAEWZ7.js → chunk-JIFG35UT.js} +2 -2
- package/dist/{chunk-DES2LGFZ.js → chunk-LQAKDKSF.js} +2 -2
- package/dist/{chunk-SFEQYKYJ.js → chunk-MC2SRJXO.js} +2 -2
- package/dist/{chunk-STM3ORY7.cjs → chunk-PMULUMUF.cjs} +2 -2
- package/dist/{chunk-STM3ORY7.cjs.map → chunk-PMULUMUF.cjs.map} +1 -1
- package/dist/{chunk-FSDJLAOW.js → chunk-QPJXYJIK.js} +55 -1
- package/dist/chunk-QPJXYJIK.js.map +1 -0
- package/dist/{chunk-OXLPVQYK.js → chunk-T2QHY3S5.js} +3 -3
- package/dist/{chunk-4VODJKFL.js → chunk-UCGGVNTD.js} +3 -3
- package/dist/{chunk-AUWGDP4G.js → chunk-XPYK7Z73.js} +2 -2
- package/dist/{chunk-FKUDAIJI.cjs → chunk-YJECRT5Q.cjs} +12 -12
- package/dist/{chunk-FKUDAIJI.cjs.map → chunk-YJECRT5Q.cjs.map} +1 -1
- package/dist/{chunk-WDQTFAXY.cjs → chunk-YOCFY44Z.cjs} +11 -11
- package/dist/{chunk-WDQTFAXY.cjs.map → chunk-YOCFY44Z.cjs.map} +1 -1
- package/dist/{chunk-JELRWAZC.js → chunk-YUZZNS6E.js} +2 -2
- package/dist/{chunk-CEIATRDW.cjs → chunk-Z3RFAVZ2.cjs} +3 -3
- package/dist/{chunk-CEIATRDW.cjs.map → chunk-Z3RFAVZ2.cjs.map} +1 -1
- package/dist/chunks-GBPAQ6JM.js +10 -0
- package/dist/cli.js +31 -50
- package/dist/cli.js.map +1 -1
- package/dist/{formula-EPKLPDU7.js → formula-EUX2AHXG.js} +3 -3
- package/dist/{formula-NARUOXRX.js → formula-IMEE5OJR.js} +4 -4
- package/dist/{formula-WIMV5TUX.cjs → formula-NPOU4BSO.cjs} +9 -9
- package/dist/{formula-WIMV5TUX.cjs.map → formula-NPOU4BSO.cjs.map} +1 -1
- package/dist/{image-ocr-3WJ4QH3T.js → image-ocr-CCIE3SPX.js} +7 -7
- package/dist/{image-ocr-AXWXR6JV.cjs → image-ocr-LTSQRHCN.cjs} +14 -14
- package/dist/{image-ocr-AXWXR6JV.cjs.map → image-ocr-LTSQRHCN.cjs.map} +1 -1
- package/dist/{image-ocr-5BUJQ4TK.js → image-ocr-QLW5VL4M.js} +5 -5
- package/dist/index.cjs +237 -237
- package/dist/index.js +4 -4
- package/dist/mcp.js +30 -37
- package/dist/mcp.js.map +1 -1
- package/dist/{model-bundle-IMBW7D2Z.js → model-bundle-VRKRVD6Z.js} +5 -5
- package/dist/{models-SY75IBOE.js → models-GSZIPSV2.js} +5 -5
- package/dist/{parser-N6476XAC.js → parser-64C45UPQ.js} +10 -10
- package/dist/{parser-ZQM3664Z.js → parser-NARS2CF7.js} +7 -7
- package/dist/{parser-2LU4EVU3.cjs → parser-U52HRNOY.cjs} +81 -81
- package/dist/{parser-2LU4EVU3.cjs.map → parser-U52HRNOY.cjs.map} +1 -1
- package/dist/pdf-ocr-4QWLMFJQ.js +18 -0
- package/dist/pdf-ocr-C7RXT5YU.cjs +16 -0
- package/dist/{pdf-ocr-GHEJVPX2.cjs.map → pdf-ocr-C7RXT5YU.cjs.map} +1 -1
- package/dist/pdf-ocr-ZYRJLOWQ.js +15 -0
- package/dist/{profile-io-GJPKCYPT.js → profile-io-PZBOSV5X.js} +3 -3
- package/dist/{rasterize-UOALJQDS.js → rasterize-DXBWM6T2.js} +3 -3
- package/dist/{redact-doc-22SYW3KH.js → redact-doc-FLMBZ53F.js} +10 -10
- package/dist/{render-MJ4H3R23.js → render-QNWUOQXJ.js} +6 -6
- package/dist/seal-NNZUQPDJ.js +10 -0
- package/dist/{setup-2URYVUEO.js → setup-3OR4QZFF.js} +3 -3
- package/dist/visual-RDGSACGE.js +20 -0
- package/dist/{watch-ALXZGTOB.js → watch-5A52FP6G.js} +11 -11
- package/package.json +1 -1
- package/dist/chunk-FSDJLAOW.js.map +0 -1
- package/dist/chunks-NUNIKS2J.js +0 -10
- package/dist/pdf-ocr-6DEE23IP.js +0 -15
- package/dist/pdf-ocr-GHEJVPX2.cjs +0 -16
- package/dist/pdf-ocr-MQTWODVU.js +0 -18
- package/dist/seal-XWMRUTI4.js +0 -10
- package/dist/visual-USPS4QRC.js +0 -20
- /package/dist/{-4G6MA4X6.js.map → -5XQIJN3D.js.map} +0 -0
- /package/dist/{chunk-UTP2WCHS.js.map → chunk-2EJ5YSFZ.js.map} +0 -0
- /package/dist/{chunk-IQGIT2VX.js.map → chunk-3ZVZPYSA.js.map} +0 -0
- /package/dist/{chunk-TXUKTOG2.js.map → chunk-46H2PPG7.js.map} +0 -0
- /package/dist/{chunk-7KNGSQU7.js.map → chunk-4O5XQSCT.js.map} +0 -0
- /package/dist/{chunk-MLIS253L.js.map → chunk-7NYRZI2Z.js.map} +0 -0
- /package/dist/{chunk-GO5IFOUF.js.map → chunk-7USPM2VT.js.map} +0 -0
- /package/dist/{chunk-KIOQ4N37.js.map → chunk-AL2WM6ZZ.js.map} +0 -0
- /package/dist/{chunk-F4NRLLY4.js.map → chunk-AWWFGIBA.js.map} +0 -0
- /package/dist/{chunk-QOCS7W7R.js.map → chunk-D2UGAEXY.js.map} +0 -0
- /package/dist/{chunk-P6ZDXTV6.js.map → chunk-ENF34XNH.js.map} +0 -0
- /package/dist/{chunk-5KS5PWJR.js.map → chunk-GGGO3OH2.js.map} +0 -0
- /package/dist/{chunk-JFLAM3MM.js.map → chunk-GH2JGKWP.js.map} +0 -0
- /package/dist/{chunk-S2PL227Q.js.map → chunk-IE6QX3T3.js.map} +0 -0
- /package/dist/{chunk-LEIAEWZ7.js.map → chunk-JIFG35UT.js.map} +0 -0
- /package/dist/{chunk-DES2LGFZ.js.map → chunk-LQAKDKSF.js.map} +0 -0
- /package/dist/{chunk-SFEQYKYJ.js.map → chunk-MC2SRJXO.js.map} +0 -0
- /package/dist/{chunk-OXLPVQYK.js.map → chunk-T2QHY3S5.js.map} +0 -0
- /package/dist/{chunk-4VODJKFL.js.map → chunk-UCGGVNTD.js.map} +0 -0
- /package/dist/{chunk-AUWGDP4G.js.map → chunk-XPYK7Z73.js.map} +0 -0
- /package/dist/{chunk-JELRWAZC.js.map → chunk-YUZZNS6E.js.map} +0 -0
- /package/dist/{chunks-NUNIKS2J.js.map → chunks-GBPAQ6JM.js.map} +0 -0
- /package/dist/{formula-EPKLPDU7.js.map → formula-EUX2AHXG.js.map} +0 -0
- /package/dist/{formula-NARUOXRX.js.map → formula-IMEE5OJR.js.map} +0 -0
- /package/dist/{image-ocr-3WJ4QH3T.js.map → image-ocr-CCIE3SPX.js.map} +0 -0
- /package/dist/{image-ocr-5BUJQ4TK.js.map → image-ocr-QLW5VL4M.js.map} +0 -0
- /package/dist/{model-bundle-IMBW7D2Z.js.map → model-bundle-VRKRVD6Z.js.map} +0 -0
- /package/dist/{models-SY75IBOE.js.map → models-GSZIPSV2.js.map} +0 -0
- /package/dist/{parser-N6476XAC.js.map → parser-64C45UPQ.js.map} +0 -0
- /package/dist/{parser-ZQM3664Z.js.map → parser-NARS2CF7.js.map} +0 -0
- /package/dist/{pdf-ocr-6DEE23IP.js.map → pdf-ocr-4QWLMFJQ.js.map} +0 -0
- /package/dist/{pdf-ocr-MQTWODVU.js.map → pdf-ocr-ZYRJLOWQ.js.map} +0 -0
- /package/dist/{profile-io-GJPKCYPT.js.map → profile-io-PZBOSV5X.js.map} +0 -0
- /package/dist/{rasterize-UOALJQDS.js.map → rasterize-DXBWM6T2.js.map} +0 -0
- /package/dist/{redact-doc-22SYW3KH.js.map → redact-doc-FLMBZ53F.js.map} +0 -0
- /package/dist/{render-MJ4H3R23.js.map → render-QNWUOQXJ.js.map} +0 -0
- /package/dist/{seal-XWMRUTI4.js.map → seal-NNZUQPDJ.js.map} +0 -0
- /package/dist/{setup-2URYVUEO.js.map → setup-3OR4QZFF.js.map} +0 -0
- /package/dist/{visual-USPS4QRC.js.map → visual-RDGSACGE.js.map} +0 -0
- /package/dist/{watch-ALXZGTOB.js.map → watch-5A52FP6G.js.map} +0 -0
|
@@ -7,11 +7,11 @@ var _chunk62W7QCEXcjs = require('./chunk-62W7QCEX.cjs');
|
|
|
7
7
|
|
|
8
8
|
|
|
9
9
|
|
|
10
|
-
var
|
|
10
|
+
var _chunkZ3RFAVZ2cjs = require('./chunk-Z3RFAVZ2.cjs');
|
|
11
11
|
|
|
12
12
|
|
|
13
13
|
|
|
14
|
-
var
|
|
14
|
+
var _chunkPMULUMUFcjs = require('./chunk-PMULUMUF.cjs');
|
|
15
15
|
|
|
16
16
|
// src/ocr/models.ts
|
|
17
17
|
var _path = require('path');
|
|
@@ -39,10 +39,10 @@ var OCR_REC_DICT = {
|
|
|
39
39
|
};
|
|
40
40
|
var ALL_OCR_MODELS = [OCR_DET_MODEL, OCR_REC_MODEL, OCR_REC_DICT];
|
|
41
41
|
function getOcrModelsDir() {
|
|
42
|
-
return
|
|
42
|
+
return _chunkZ3RFAVZ2cjs.getModelsDir.call(void 0, "ppocr");
|
|
43
43
|
}
|
|
44
44
|
async function ensureOcrModels(onProgress) {
|
|
45
|
-
return
|
|
45
|
+
return _chunkZ3RFAVZ2cjs.ensureModelsIn.call(void 0, getOcrModelsDir(), ALL_OCR_MODELS, onProgress);
|
|
46
46
|
}
|
|
47
47
|
async function ocrModelsCached() {
|
|
48
48
|
const dir = getOcrModelsDir();
|
|
@@ -5227,16 +5227,16 @@ function isProseSpread(items) {
|
|
|
5227
5227
|
for (let i = 1; i < sorted.length; i++) {
|
|
5228
5228
|
gaps.push(sorted[i].x - (sorted[i - 1].x + sorted[i - 1].w));
|
|
5229
5229
|
}
|
|
5230
|
-
const maxGap =
|
|
5230
|
+
const maxGap = _chunkPMULUMUFcjs.safeMax.call(void 0, gaps);
|
|
5231
5231
|
const avgLen = items.reduce((s, i) => s + i.text.length, 0) / items.length;
|
|
5232
5232
|
if (items.length >= 4 && maxGap < 40 && avgLen < 5) return true;
|
|
5233
|
-
const minGap =
|
|
5233
|
+
const minGap = _chunkPMULUMUFcjs.safeMin.call(void 0, gaps);
|
|
5234
5234
|
return minGap > 0 && maxGap - minGap <= Math.max(2, maxGap * 0.15) && items.filter((i) => /^\P{L}*\p{Ll}/u.test(i.text)).length * 2 >= items.length;
|
|
5235
5235
|
}
|
|
5236
5236
|
function detectColumns(yLines) {
|
|
5237
5237
|
const allItems = yLines.flat();
|
|
5238
5238
|
if (allItems.length === 0) return null;
|
|
5239
|
-
const pageWidth =
|
|
5239
|
+
const pageWidth = _chunkPMULUMUFcjs.safeMax.call(void 0, allItems.map((i) => i.x + i.w)) - _chunkPMULUMUFcjs.safeMin.call(void 0, allItems.map((i) => i.x));
|
|
5240
5240
|
if (pageWidth < 100) return null;
|
|
5241
5241
|
let bigoLineIdx = -1;
|
|
5242
5242
|
for (let i = 0; i < yLines.length; i++) {
|
|
@@ -6763,7 +6763,7 @@ function extractBlocksWithGrids(items, pageNum, pageWidth, pageHeight, grids, ho
|
|
|
6763
6763
|
if (gutterX !== null) {
|
|
6764
6764
|
const gx = gutterX;
|
|
6765
6765
|
const allY = remaining.map((i) => i.y);
|
|
6766
|
-
const pageH =
|
|
6766
|
+
const pageH = _chunkPMULUMUFcjs.safeMax.call(void 0, allY) - _chunkPMULUMUFcjs.safeMin.call(void 0, allY);
|
|
6767
6767
|
const gapThreshold = Math.max(15, pageH * 0.03);
|
|
6768
6768
|
const sides = [
|
|
6769
6769
|
remaining.filter((i) => i.x + i.w <= gx),
|
|
@@ -6783,7 +6783,7 @@ function extractBlocksWithGrids(items, pageNum, pageWidth, pageHeight, grids, ho
|
|
|
6783
6783
|
finalTextBlocks = detectListBlocks(textBlocks);
|
|
6784
6784
|
} else {
|
|
6785
6785
|
const allY = remaining.map((i) => i.y);
|
|
6786
|
-
const pageH =
|
|
6786
|
+
const pageH = _chunkPMULUMUFcjs.safeMax.call(void 0, allY) - _chunkPMULUMUFcjs.safeMin.call(void 0, allY);
|
|
6787
6787
|
const groups = xyCutOrder(remaining, Math.max(15, pageH * 0.03));
|
|
6788
6788
|
const textBlocks = [];
|
|
6789
6789
|
for (const group of groups) {
|
|
@@ -7097,7 +7097,7 @@ function extractPageBlocksFallback(items, pageNum, fullPage = false, detectTable
|
|
|
7097
7097
|
blocks.push(...columnTextToBlocks(tableText, pageNum, bbox, dominantStyle(items)));
|
|
7098
7098
|
} else {
|
|
7099
7099
|
const allY = items.map((i) => i.y);
|
|
7100
|
-
const pageHeight =
|
|
7100
|
+
const pageHeight = _chunkPMULUMUFcjs.safeMax.call(void 0, allY) - _chunkPMULUMUFcjs.safeMin.call(void 0, allY);
|
|
7101
7101
|
const gapThreshold = Math.max(15, pageHeight * 0.03);
|
|
7102
7102
|
const orderedGroups = proseCutX !== null ? splitTwoColumnProse(items, proseCutX) : xyCutOrder(items, gapThreshold);
|
|
7103
7103
|
for (const group of orderedGroups) {
|
|
@@ -7159,4 +7159,4 @@ function extractPageBlocksFallback(items, pageNum, fullPage = false, detectTable
|
|
|
7159
7159
|
|
|
7160
7160
|
|
|
7161
7161
|
exports.OCR_DET_MODEL = OCR_DET_MODEL; exports.OCR_REC_MODEL = OCR_REC_MODEL; exports.OCR_REC_DICT = OCR_REC_DICT; exports.getOcrModelsDir = getOcrModelsDir; exports.ensureOcrModels = ensureOcrModels; exports.ocrModelsCached = ocrModelsCached; exports.parseCharacterDict = parseCharacterDict; exports.extractLines = extractLines; exports.extractImageRegions = extractImageRegions; exports.filterHiddenText = filterHiddenText; exports.collapseEvenSpacing = collapseEvenSpacing; exports.normalizeItems = normalizeItems; exports.WrapLexicon = WrapLexicon; exports.startsNewItem = startsNewItem; exports.wrapJoiner = wrapJoiner; exports.joinPageBreakWraps = joinPageBreakWraps; exports.latinSoftWrap = latinSoftWrap; exports.TOC_BLOCKS = TOC_BLOCKS; exports.computeMedianFontSizeFromFreq = computeMedianFontSizeFromFreq; exports.detectHeadings = detectHeadings; exports.mergeStackedHeadingLines = mergeStackedHeadingLines; exports.detectTypographyHeadings = detectTypographyHeadings; exports.detectDocumentStyleHeadings = detectDocumentStyleHeadings; exports.detectSiblingStyleHeadings = detectSiblingStyleHeadings; exports.detectRepeatedPageLabels = detectRepeatedPageLabels; exports.detectPageLeadHeadings = detectPageLeadHeadings; exports.refineDocumentStyleHeadings = refineDocumentStyleHeadings; exports.detectMarkerHeadings = detectMarkerHeadings; exports.detectTableCaptions = detectTableCaptions; exports.detectKoreanListBlocks = detectKoreanListBlocks; exports.removeHeaderFooterBlocks = removeHeaderFooterBlocks; exports.CLIP_TABLES = CLIP_TABLES; exports.TABLE_COLXS = TABLE_COLXS; exports.EMPTY_PARTS = EMPTY_PARTS; exports.IMAGE_CELLS = IMAGE_CELLS; exports.FILLER_CELLS = FILLER_CELLS; exports.CONT_PARTS = CONT_PARTS; exports.CELL_LINES = CELL_LINES; exports.trimTrailingEmptyTableCols = trimTrailingEmptyTableCols; exports.extractPageBlocksWithLines = extractPageBlocksWithLines;
|
|
7162
|
-
//# sourceMappingURL=chunk-
|
|
7162
|
+
//# sourceMappingURL=chunk-YOCFY44Z.cjs.map
|