kordoc 4.18.7 → 4.18.9
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 +74 -561
- package/dist/{-3AJPADNH.js → -OOORB3ZM.js} +11 -11
- package/dist/{chunk-6FGSSCXN.js → chunk-2ZATWIWX.js} +3 -3
- package/dist/{chunk-X6RQA2ZJ.js → chunk-44LAZYCW.js} +2 -2
- package/dist/{chunk-MKARDNWJ.js → chunk-5K7M5QCG.js} +2 -2
- package/dist/{chunk-32H2UKEZ.js → chunk-5XMZU77R.js} +2 -2
- package/dist/{chunk-HR7QNQOQ.cjs → chunk-5Z5VIVZ4.cjs} +3 -3
- package/dist/{chunk-HR7QNQOQ.cjs.map → chunk-5Z5VIVZ4.cjs.map} +1 -1
- package/dist/{chunk-M6UIEUUU.cjs → chunk-A66VFXSS.cjs} +12 -12
- package/dist/{chunk-M6UIEUUU.cjs.map → chunk-A66VFXSS.cjs.map} +1 -1
- package/dist/{chunk-T4TXPUOX.js → chunk-BBMS5Z7N.js} +2 -2
- package/dist/{chunk-MPUJQOCK.js → chunk-CGRLQJC2.js} +27 -4
- package/dist/chunk-CGRLQJC2.js.map +1 -0
- package/dist/{chunk-TQN4QRL7.cjs → chunk-FFUNCANU.cjs} +47 -24
- package/dist/chunk-FFUNCANU.cjs.map +1 -0
- package/dist/{chunk-2M7WLIUZ.js → chunk-H3MGECXS.js} +2 -2
- package/dist/{chunk-AOOQK3RX.js → chunk-IPJ5SVNH.js} +2 -2
- package/dist/{chunk-UHK47KXY.js → chunk-J6KBWT5D.js} +89 -10
- package/dist/chunk-J6KBWT5D.js.map +1 -0
- package/dist/{chunk-IM77QPKN.js → chunk-L3YW7ATL.js} +2 -2
- package/dist/{chunk-JXVVOSWW.js → chunk-L65DR4EY.js} +2 -2
- package/dist/{chunk-LUZF5ESP.js → chunk-LZJ4HHFE.js} +4 -4
- package/dist/{chunk-U4MI7XTO.js → chunk-MSGQ6DFT.js} +2 -2
- package/dist/{chunk-EB5T5SC6.js → chunk-MW2G24XL.js} +2 -2
- package/dist/{chunk-LFB3XTIK.js → chunk-NEQC7PV5.js} +2 -2
- package/dist/{chunk-AKQRKMY5.js → chunk-NMKCOSXN.js} +2 -2
- package/dist/{chunk-NCVMV4MR.js → chunk-O345LTOL.js} +3 -3
- package/dist/{chunk-5DKDP42Q.js → chunk-OJGHM3YD.js} +2 -2
- package/dist/{chunk-YROJFVJI.js → chunk-S7ED7QP2.js} +28 -5
- package/dist/chunk-S7ED7QP2.js.map +1 -0
- package/dist/{chunk-SD5DGUD4.js → chunk-SO66Q6ST.js} +2 -2
- package/dist/{chunk-ZCOZENWU.cjs → chunk-SOIGY5LM.cjs} +2 -2
- package/dist/{chunk-ZCOZENWU.cjs.map → chunk-SOIGY5LM.cjs.map} +1 -1
- package/dist/{chunk-5EXCACRC.cjs → chunk-VMGLV3P3.cjs} +3 -3
- package/dist/{chunk-5EXCACRC.cjs.map → chunk-VMGLV3P3.cjs.map} +1 -1
- package/dist/{chunk-7ELJ2VQW.js → chunk-XB6VRTM3.js} +2 -2
- package/dist/{chunk-T2VQWNMK.cjs → chunk-XMULZUPH.cjs} +6 -6
- package/dist/{chunk-T2VQWNMK.cjs.map → chunk-XMULZUPH.cjs.map} +1 -1
- package/dist/{chunk-KLOQU3SZ.js → chunk-ZMHMIXTU.js} +6 -6
- package/dist/chunks-2AMQTIMX.js +10 -0
- package/dist/cli.js +26 -26
- package/dist/{formula-WOW5NIIX.cjs → formula-5EGP7AVC.cjs} +9 -9
- package/dist/{formula-WOW5NIIX.cjs.map → formula-5EGP7AVC.cjs.map} +1 -1
- package/dist/{formula-BDPM3Q37.js → formula-CLVKOQCO.js} +4 -4
- package/dist/{formula-K2CIXI4G.js → formula-KOOZT2QS.js} +3 -3
- package/dist/{image-ocr-IGO6GXW4.js → image-ocr-AKSRUDIT.js} +9 -9
- package/dist/{image-ocr-PXFOI5HL.cjs → image-ocr-BHJFBQ2T.cjs} +15 -15
- package/dist/{image-ocr-PXFOI5HL.cjs.map → image-ocr-BHJFBQ2T.cjs.map} +1 -1
- package/dist/{image-ocr-SACGXUVC.js → image-ocr-LLMYXDAL.js} +6 -6
- package/dist/index.cjs +460 -381
- package/dist/index.cjs.map +1 -1
- package/dist/index.js +84 -5
- package/dist/index.js.map +1 -1
- package/dist/mcp.js +22 -22
- package/dist/{model-bundle-Y64X36ZK.js → model-bundle-NT6KCK6Y.js} +5 -5
- package/dist/{models-NMOGNW7R.js → models-SWD6AIAB.js} +5 -5
- package/dist/{parser-CH4MBHEZ.js → parser-ANGCUOPB.js} +10 -9
- package/dist/{parser-CZWBWP7H.js.map → parser-ANGCUOPB.js.map} +1 -1
- package/dist/{parser-NMWMCBWM.cjs → parser-N5MYD4XA.cjs} +127 -126
- package/dist/parser-N5MYD4XA.cjs.map +1 -0
- package/dist/{parser-CZWBWP7H.js → parser-RYDOM6KM.js} +13 -12
- package/dist/{parser-CH4MBHEZ.js.map → parser-RYDOM6KM.js.map} +1 -1
- package/dist/pdf-ocr-B23SDZDD.js +20 -0
- package/dist/pdf-ocr-RX3CQENG.cjs +17 -0
- package/dist/{pdf-ocr-RPBTK6XS.cjs.map → pdf-ocr-RX3CQENG.cjs.map} +1 -1
- package/dist/pdf-ocr-SMFPZJGJ.js +16 -0
- package/dist/{profile-io-UFU7APWM.js → profile-io-CZE4YTYD.js} +3 -3
- package/dist/{rasterize-NL6RCQWN.js → rasterize-KBBEPWJN.js} +3 -3
- package/dist/{redact-doc-FEM3AGUQ.js → redact-doc-K7HCORXE.js} +11 -11
- package/dist/{render-WDCKVMGY.js → render-TXGEQCW6.js} +7 -7
- package/dist/seal-QBDRMEQ3.js +10 -0
- package/dist/{setup-E3E4LDKQ.js → setup-EHCY4PGN.js} +3 -3
- package/dist/visual-66VQETYB.js +20 -0
- package/dist/{watch-6UYWJ6UG.js → watch-54O2O32S.js} +12 -12
- package/package.json +1 -1
- package/dist/chunk-MPUJQOCK.js.map +0 -1
- package/dist/chunk-TQN4QRL7.cjs.map +0 -1
- package/dist/chunk-UHK47KXY.js.map +0 -1
- package/dist/chunk-YROJFVJI.js.map +0 -1
- package/dist/chunks-JOLLBBQL.js +0 -10
- package/dist/parser-NMWMCBWM.cjs.map +0 -1
- package/dist/pdf-ocr-BLU34LTG.js +0 -16
- package/dist/pdf-ocr-L4LJUSZ3.js +0 -20
- package/dist/pdf-ocr-RPBTK6XS.cjs +0 -17
- package/dist/seal-XHUWDRIW.js +0 -10
- package/dist/visual-74WYDXEK.js +0 -20
- /package/dist/{-3AJPADNH.js.map → -OOORB3ZM.js.map} +0 -0
- /package/dist/{chunk-6FGSSCXN.js.map → chunk-2ZATWIWX.js.map} +0 -0
- /package/dist/{chunk-X6RQA2ZJ.js.map → chunk-44LAZYCW.js.map} +0 -0
- /package/dist/{chunk-MKARDNWJ.js.map → chunk-5K7M5QCG.js.map} +0 -0
- /package/dist/{chunk-32H2UKEZ.js.map → chunk-5XMZU77R.js.map} +0 -0
- /package/dist/{chunk-T4TXPUOX.js.map → chunk-BBMS5Z7N.js.map} +0 -0
- /package/dist/{chunk-2M7WLIUZ.js.map → chunk-H3MGECXS.js.map} +0 -0
- /package/dist/{chunk-AOOQK3RX.js.map → chunk-IPJ5SVNH.js.map} +0 -0
- /package/dist/{chunk-IM77QPKN.js.map → chunk-L3YW7ATL.js.map} +0 -0
- /package/dist/{chunk-JXVVOSWW.js.map → chunk-L65DR4EY.js.map} +0 -0
- /package/dist/{chunk-LUZF5ESP.js.map → chunk-LZJ4HHFE.js.map} +0 -0
- /package/dist/{chunk-U4MI7XTO.js.map → chunk-MSGQ6DFT.js.map} +0 -0
- /package/dist/{chunk-EB5T5SC6.js.map → chunk-MW2G24XL.js.map} +0 -0
- /package/dist/{chunk-LFB3XTIK.js.map → chunk-NEQC7PV5.js.map} +0 -0
- /package/dist/{chunk-AKQRKMY5.js.map → chunk-NMKCOSXN.js.map} +0 -0
- /package/dist/{chunk-NCVMV4MR.js.map → chunk-O345LTOL.js.map} +0 -0
- /package/dist/{chunk-5DKDP42Q.js.map → chunk-OJGHM3YD.js.map} +0 -0
- /package/dist/{chunk-SD5DGUD4.js.map → chunk-SO66Q6ST.js.map} +0 -0
- /package/dist/{chunk-7ELJ2VQW.js.map → chunk-XB6VRTM3.js.map} +0 -0
- /package/dist/{chunk-KLOQU3SZ.js.map → chunk-ZMHMIXTU.js.map} +0 -0
- /package/dist/{chunks-JOLLBBQL.js.map → chunks-2AMQTIMX.js.map} +0 -0
- /package/dist/{formula-BDPM3Q37.js.map → formula-CLVKOQCO.js.map} +0 -0
- /package/dist/{formula-K2CIXI4G.js.map → formula-KOOZT2QS.js.map} +0 -0
- /package/dist/{image-ocr-IGO6GXW4.js.map → image-ocr-AKSRUDIT.js.map} +0 -0
- /package/dist/{image-ocr-SACGXUVC.js.map → image-ocr-LLMYXDAL.js.map} +0 -0
- /package/dist/{model-bundle-Y64X36ZK.js.map → model-bundle-NT6KCK6Y.js.map} +0 -0
- /package/dist/{models-NMOGNW7R.js.map → models-SWD6AIAB.js.map} +0 -0
- /package/dist/{pdf-ocr-BLU34LTG.js.map → pdf-ocr-B23SDZDD.js.map} +0 -0
- /package/dist/{pdf-ocr-L4LJUSZ3.js.map → pdf-ocr-SMFPZJGJ.js.map} +0 -0
- /package/dist/{profile-io-UFU7APWM.js.map → profile-io-CZE4YTYD.js.map} +0 -0
- /package/dist/{rasterize-NL6RCQWN.js.map → rasterize-KBBEPWJN.js.map} +0 -0
- /package/dist/{redact-doc-FEM3AGUQ.js.map → redact-doc-K7HCORXE.js.map} +0 -0
- /package/dist/{render-WDCKVMGY.js.map → render-TXGEQCW6.js.map} +0 -0
- /package/dist/{seal-XHUWDRIW.js.map → seal-QBDRMEQ3.js.map} +0 -0
- /package/dist/{setup-E3E4LDKQ.js.map → setup-EHCY4PGN.js.map} +0 -0
- /package/dist/{visual-74WYDXEK.js.map → visual-66VQETYB.js.map} +0 -0
- /package/dist/{watch-6UYWJ6UG.js.map → watch-54O2O32S.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-H3MGECXS.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-BBMS5Z7N.js.map
|
|
@@ -5,11 +5,11 @@ import {
|
|
|
5
5
|
HEADING_RATIO_H2,
|
|
6
6
|
HEADING_RATIO_H3,
|
|
7
7
|
tidyScriptTags
|
|
8
|
-
} from "./chunk-
|
|
8
|
+
} from "./chunk-MSGQ6DFT.js";
|
|
9
9
|
import {
|
|
10
10
|
safeMax,
|
|
11
11
|
safeMin
|
|
12
|
-
} from "./chunk-
|
|
12
|
+
} from "./chunk-H3MGECXS.js";
|
|
13
13
|
|
|
14
14
|
// src/pdf/line-extract.ts
|
|
15
15
|
import { OPS } from "pdfjs-dist/legacy/build/pdf.mjs";
|
|
@@ -2169,6 +2169,7 @@ function wrapJoiner(prevText, nextText, lex) {
|
|
|
2169
2169
|
return " ";
|
|
2170
2170
|
}
|
|
2171
2171
|
var PARA_LAST_LINE = /* @__PURE__ */ new WeakMap();
|
|
2172
|
+
var PAGE_BREAK_JOINS = /* @__PURE__ */ new WeakMap();
|
|
2172
2173
|
function joinPageBreakWraps(blocks, lex) {
|
|
2173
2174
|
const pageRight = /* @__PURE__ */ new Map();
|
|
2174
2175
|
for (const b of blocks) {
|
|
@@ -2183,13 +2184,34 @@ function joinPageBreakWraps(blocks, lex) {
|
|
|
2183
2184
|
if (!last || fs <= 0 || (pageRight.get(a.pageNumber) ?? Infinity) - last.right >= BODY_FULL_TOL * fs) continue;
|
|
2184
2185
|
if (last.width < BODY_MIN_WIDTH_EM * fs || Math.abs((b.style?.fontSize ?? 0) - fs) > 0.15 * fs) continue;
|
|
2185
2186
|
if (startsNewItem(a.text, b.text)) continue;
|
|
2186
|
-
a.text
|
|
2187
|
+
const head = a.text, joiner = wrapJoiner(a.text, b.text, lex);
|
|
2188
|
+
a.text += joiner + b.text;
|
|
2189
|
+
const later = b.bbox && PAGE_BREAK_JOINS.get(b.bbox) || [];
|
|
2190
|
+
PAGE_BREAK_JOINS.set(a.bbox, [{ head, gap: joiner.length, tail: b }, ...later.map((c) => ({ ...c, head: head + joiner + c.head }))]);
|
|
2187
2191
|
const bl = b.bbox && PARA_LAST_LINE.get(b.bbox);
|
|
2188
2192
|
if (bl) PARA_LAST_LINE.set(a.bbox, bl);
|
|
2189
2193
|
else PARA_LAST_LINE.delete(a.bbox);
|
|
2190
2194
|
blocks.splice(i, 1);
|
|
2191
2195
|
}
|
|
2192
2196
|
}
|
|
2197
|
+
function splitPageBreakWraps(blocks) {
|
|
2198
|
+
return blocks.flatMap((b) => {
|
|
2199
|
+
const cuts = b.bbox && PAGE_BREAK_JOINS.get(b.bbox);
|
|
2200
|
+
const text = b.text;
|
|
2201
|
+
if (!cuts || !text) return [b];
|
|
2202
|
+
const out = [];
|
|
2203
|
+
let from = 0, cur = b;
|
|
2204
|
+
for (const c of cuts) {
|
|
2205
|
+
if (c.head.length < from || !text.startsWith(c.head)) break;
|
|
2206
|
+
out.push({ ...cur, text: text.slice(from, c.head.length) });
|
|
2207
|
+
from = c.head.length + c.gap;
|
|
2208
|
+
cur = c.tail;
|
|
2209
|
+
}
|
|
2210
|
+
if (!out.length) return [b];
|
|
2211
|
+
out.push({ ...cur, text: text.slice(from) });
|
|
2212
|
+
return out;
|
|
2213
|
+
});
|
|
2214
|
+
}
|
|
2193
2215
|
var HANGING = /[,。、:;!?)」』】〕》〉.]\s*$/;
|
|
2194
2216
|
var MULTI_LEVEL_NUMBER = /^\d{1,2}(?:\.\d{1,3})+\.?\s/;
|
|
2195
2217
|
var BODY_FULL_TOL = 0.25;
|
|
@@ -8215,6 +8237,7 @@ export {
|
|
|
8215
8237
|
startsNewItem,
|
|
8216
8238
|
wrapJoiner,
|
|
8217
8239
|
joinPageBreakWraps,
|
|
8240
|
+
splitPageBreakWraps,
|
|
8218
8241
|
latinSoftWrap,
|
|
8219
8242
|
TOC_BLOCKS,
|
|
8220
8243
|
computeMedianFontSizeFromFreq,
|
|
@@ -8252,4 +8275,4 @@ export {
|
|
|
8252
8275
|
removeSideTabs,
|
|
8253
8276
|
extractPageBlocksWithLines
|
|
8254
8277
|
};
|
|
8255
|
-
//# sourceMappingURL=chunk-
|
|
8278
|
+
//# sourceMappingURL=chunk-CGRLQJC2.js.map
|