kordoc 4.16.1 → 4.16.2

package/dist/{chunk-OBRPYCIS.js → chunk-QOCS7W7R.js}

@@ -1,7 +1,7 @@
 #!/usr/bin/env node
 import {
   blocksToPages
-} from "./chunk-63YGGAQW.js";
+} from "./chunk-AUWGDP4G.js";
 import {
   allLinesegRemovalSplices,
   applySplices,
@@ -15,7 +15,7 @@ import {
   paraTextPureT,
   patchZipEntries,
   scanSectionXml
-} from "./chunk-EEVAPRPD.js";
+} from "./chunk-4VODJKFL.js";
 import {
   CONVERT_MAP,
   FLAG_COMPRESSED,
@@ -61,12 +61,16 @@ import {
   renderDocumentToScene,
   romanNumeral,
   simulateWrap
-} from "./chunk-BTO7ZEE4.js";
+} from "./chunk-IQGIT2VX.js";
 import {
   HEADING_RATIO_H1,
   HEADING_RATIO_H2,
-  HEADING_RATIO_H3
-} from "./chunk-T77M2QP7.js";
+  HEADING_RATIO_H3,
+  plainScripts,
+  stripScriptTags,
+  tidyScriptTags,
+  wrapScript
+} from "./chunk-J3IF6KGW.js";
 import {
   parsePageRange
 } from "./chunk-VQFA55IC.js";
@@ -85,7 +89,7 @@ import {
   findChildByLocalName,
   localName,
   rawTextContent
-} from "./chunk-CXWWX6BQ.js";
+} from "./chunk-JFLAM3MM.js";
 import {
   MAX_COLS,
   MAX_ROWS,
@@ -100,7 +104,7 @@ import {
   hasStructuredCellContent,
   mapPuaText,
   noteSuffix
-} from "./chunk-UZHT3LBF.js";
+} from "./chunk-LEIAEWZ7.js";
 import {
   KordocError,
   classifyError,
@@ -115,20 +119,20 @@ import {
   toArrayBuffer,
   unescapeHtml,
   unzipLimitBytes
-} from "./chunk-3VLVNKJV.js";
+} from "./chunk-P6ZDXTV6.js";
 
 // src/table/visual.ts
 import { readFile as readFile2 } from "fs/promises";
 
 // src/plain-markdown.ts
 function toPlainMarkdown(md) {
-  return md.replace(/!\[[^\]\n]*\]\([^)\n]*\)/g, "").replace(/<img\b[^>]*>/gi, "").replace(/(?<!!)\[([^\]\n]*)\]\((?:https?|mailto|ftp):[^)\s]*\)/g, "$1").replace(/<\/?u>/g, "").replace(/(?<!\\)\*\*(?=\S)([^\n]*?\S)(?<!\\)\*\*/g, "$1").replace(/(<br>)+(?=<\/t[dh]>)/g, "").replace(/[ \t]+$/gm, "").replace(/\n{3,}/g, "\n\n").trim();
+  return plainScripts(md).replace(/!\[[^\]\n]*\]\([^)\n]*\)/g, "").replace(/<img\b[^>]*>/gi, "").replace(/(?<!!)\[([^\]\n]*)\]\((?:https?|mailto|ftp):[^)\s]*\)/g, "$1").replace(/<\/?u>/g, "").replace(/(?<!\\)\*\*(?=\S)([^\n]*?\S)(?<!\\)\*\*/g, "$1").replace(/(<br>)+(?=<\/t[dh]>)/g, "").replace(/[ \t]+$/gm, "").replace(/\n{3,}/g, "\n\n").trim();
 }
 
 // src/html-tables.ts
 var TABLE_TAG = /(<\/?(?:table|tr|th|td)\b[^>]*>)/i;
 function pipeCellToHtml(cell2) {
-  return cell2.split(/(<br>|<\/?u>|<img\b[^>]*>)/).map((part, i) => i % 2 ? part : part.replace(/\\([\\`*_{}[\]()#+\-.!|~<>$])/g, "$1").replace(/&/g, "&amp;").replace(/</g, "&lt;").replace(/>/g, "&gt;")).join("");
+  return cell2.split(/(<br>|<\/?(?:u|sup|sub)>|<img\b[^>]*>)/).map((part, i) => i % 2 ? part : part.replace(/\\([\\`*_{}[\]()#+\-.!|~<>$])/g, "$1").replace(/&/g, "&amp;").replace(/</g, "&lt;").replace(/>/g, "&gt;")).join("");
 }
 function splitPipeRow(line) {
   const t = line.trim().replace(/^\|/, "").replace(/(?<!\\)\|$/, "");
@@ -476,7 +480,9 @@ function parseCharProperties(doc, map) {
         else if (localTag === "strikeout") {
           const shape = k.getAttribute("shape") || "";
           if (isRealStrikeShape(shape)) prop.strike = true;
-        } else if (localTag === "underline") {
+        } else if (localTag === "supscript") prop.script = "sup";
+        else if (localTag === "subscript") prop.script = "sub";
+        else if (localTag === "underline") {
           if (k.getAttribute("type") === "BOTTOM") prop.underline = true;
         }
       }
@@ -1039,6 +1045,7 @@ function extractRunSpans(para2, ctx, mode, requireMixed) {
     const span = { text };
     if (mode !== "foreign" && prId === KORDOC_CHAR_CODE) span.code = true;
     else {
+      if (cp?.script) span.text = wrapScript(text, cp.script);
       if (cp?.bold) span.bold = true;
       if (cp?.italic) span.italic = true;
       if (cp?.strike) span.strike = true;
@@ -1058,6 +1065,7 @@ function extractRunSpans(para2, ctx, mode, requireMixed) {
     }
   }
   if (requireMixed && !merged.some((s) => s.strike || s.underline) && !merged.some((s) => !(s.bold || s.italic || s.code))) return null;
+  for (const s of merged) s.text = tidyScriptTags(s.text);
   return merged;
 }
 function gongmunDepthFromIndent(para2, left, ctx) {
@@ -1707,6 +1715,16 @@ function extractHyperlinkHref(fieldBegin) {
 function isInDeletedRange(ctx) {
   return (ctx?.shared.track.deleteDepth ?? 0) > 0;
 }
+function runHasOnlyText(run) {
+  const kids = run.childNodes;
+  for (let i = 0; i < (kids?.length ?? 0); i++) {
+    const k = kids[i];
+    if (k.nodeType !== 1) continue;
+    const t = (k.tagName || k.localName || "").replace(/^[^:]+:/, "");
+    if (t !== "t" && t !== "linesegarray") return false;
+  }
+  return true;
+}
 function extractParagraphInfo(para2, styleMap, ctx) {
   let text = "";
   let href;
@@ -1963,11 +1981,19 @@ function extractParagraphInfo(para2, styleMap, ctx) {
           }
           break;
         }
-        // run 요소에서 charPrIDRef 추출
-        case "r": {
+        // run 요소 — hp:r 은 charPrIDRef 를 문단 대표 스타일로. 첨자 글자 모양이면 이 run 이 더한 글을 <sup>·<sub> 로
+        // (개체·각주 등 컨트롤을 품은 run·필드 경계가 걸친 run 은 글 위치가 섞여 감싸지 않는다)
+        case "r":
+        case "run": {
           const runCharPr = child.getAttribute("charPrIDRef");
-          if (runCharPr && !charPrId) charPrId = runCharPr;
+          if (tag === "r" && runCharPr && !charPrId) charPrId = runCharPr;
+          const script = runCharPr ? styleMap?.charProperties.get(runCharPr)?.script : void 0;
+          const start = text.length, nLinks = linkRanges.length, nOpen = openFields.length;
           walk(child, depth + 1);
+          if (script && linkRanges.length === nLinks && openFields.length === nOpen && runHasOnlyText(child)) {
+            const added = text.slice(start);
+            if (added && !/[\x1E\x1F\n$]/.test(added)) text = text.slice(0, start) + wrapScript(added, script);
+          }
           break;
         }
         default:
@@ -1991,6 +2017,7 @@ function extractParagraphInfo(para2, styleMap, ctx) {
   }
   const leaderIdx = text.indexOf("");
   if (leaderIdx >= 0) text = text.substring(0, leaderIdx);
+  text = tidyScriptTags(text);
   const cleanParaText = (raw) => {
     let t = raw.replace(/[ \t]+/g, " ").trim();
     if (/^그림입니다\.?\s*원본\s*그림의\s*(이름|크기)/.test(t)) t = "";
@@ -17157,6 +17184,9 @@ function extractRun(r) {
   if (rPrEls.length > 0) {
     bold = getChildElements(rPrEls[0], "b").length > 0;
     italic = getChildElements(rPrEls[0], "i").length > 0;
+    const va = getChildElements(rPrEls[0], "vertAlign")[0];
+    const v = va ? getAttr(va, "val") : null;
+    if (v === "superscript" || v === "subscript") text = wrapScript(text, v === "superscript" ? "sup" : "sub");
   }
   return { text, bold, italic };
 }
@@ -17254,7 +17284,7 @@ function collectInline(p, footnotes, rels) {
     if (isDisplayMath(om)) parts.push(" $$" + latex + "$$ ");
     else parts.push(" $" + latex + "$ ");
   }
-  const text = parts.join("").replace(/[ \t]{2,}/g, " ").trim();
+  const text = tidyScriptTags(parts.join("")).replace(/[ \t]{2,}/g, " ").trim();
   return { text, bold, italic, footnoteText };
 }
 var COUNTERS = /* @__PURE__ */ new WeakMap();
@@ -18127,7 +18157,7 @@ var ValueCursor = class {
   }
 };
 function normalizeLabel(label) {
-  return label.trim().replace(/[:：\s()（）·]/g, "");
+  return label.trim().replace(/<\/?su[bp]>/g, "").replace(/[:：\s()（）·]/g, "");
 }
 function findMatchingKey(cellLabel, values) {
   if (values.has(cellLabel)) return cellLabel;
@@ -20910,6 +20940,7 @@ function parseInlineMarkdown(text) {
   text = text.replace(/!\[([^\]]*)\]\([^)]*\)/g, "$1");
   text = text.replace(/~~([^~]+)~~/g, "$1");
   text = text.replace(/<u>([^<]*)<\/u>/g, "$1");
+  text = text.replace(/<(sup|sub)>([^<]*)<\/\1>/g, "$2");
   let spans;
   if (inlineDoc) {
     spans = [];
@@ -29483,10 +29514,14 @@ async function dispatch(format2, buffer, opts) {
       return { success: false, fileType: "unknown", error: "\uC9C0\uC6D0\uD558\uC9C0 \uC54A\uB294 \uD30C\uC77C \uD615\uC2DD\uC785\uB2C8\uB2E4.", code: "UNSUPPORTED_FORMAT" };
   }
 }
+function scriptsOff(r, off) {
+  return off ? stripScriptTags(r) : r;
+}
 async function parseImage(buffer, options) {
   try {
-    const { parseImageDocument } = await import("./image-ocr-3IJ25PS4.js");
+    const { parseImageDocument } = await import("./image-ocr-3WJ4QH3T.js");
     const { blocks, warnings } = await parseImageDocument(buffer, options);
+    stripScriptTags({ blocks });
     return {
       success: true,
       fileType: "image",
@@ -29510,7 +29545,7 @@ async function parseHwp3(buffer, options) {
 async function parseHwpx(buffer, options) {
   try {
     const { markdown, blocks, metadata, outline, warnings, images } = await parseHwpxDocument(buffer, options);
-    return { success: true, fileType: "hwpx", markdown, blocks, metadata, outline, warnings, images: images?.length ? images : void 0, pageCount: metadata?.pageCount };
+    return scriptsOff({ success: true, fileType: "hwpx", markdown, blocks, metadata, outline, warnings, images: images?.length ? images : void 0, pageCount: metadata?.pageCount }, options?.scriptTags === false);
   } catch (err) {
     return { success: false, fileType: "hwpx", error: sanitizeError(err), code: classifyError(err) };
   }
@@ -29536,7 +29571,7 @@ async function parseHwp(buffer, options) {
       } catch {
       }
     }
-    return { success: true, fileType: "hwp", markdown, blocks, metadata, outline, warnings, images: images?.length ? images : void 0, pageCount: metadata?.pageCount };
+    return scriptsOff({ success: true, fileType: "hwp", markdown, blocks, metadata, outline, warnings, images: images?.length ? images : void 0, pageCount: metadata?.pageCount }, options?.scriptTags === false);
   } catch (err) {
     return { success: false, fileType: "hwp", error: sanitizeError(err), code: classifyError(err) };
   }
@@ -29544,7 +29579,7 @@ async function parseHwp(buffer, options) {
 async function parsePdf(buffer, options) {
   let parsePdfDocument;
   try {
-    const mod = await import("./parser-T4RITZDP.js");
+    const mod = await import("./parser-N6476XAC.js");
     parsePdfDocument = mod.parsePdfDocument;
   } catch {
     return {
@@ -29556,7 +29591,7 @@ async function parsePdf(buffer, options) {
   }
   try {
     const { markdown, blocks, metadata, outline, warnings, isImageBased, pageQuality, qualitySummary, images, pages } = await parsePdfDocument(buffer, options);
-    return { success: true, fileType: "pdf", markdown, blocks, metadata, outline, warnings, isImageBased, pageQuality, qualitySummary, images, pages, pageCount: metadata?.pageCount };
+    return scriptsOff({ success: true, fileType: "pdf", markdown, blocks, metadata, outline, warnings, isImageBased, pageQuality, qualitySummary, images, pages, pageCount: metadata?.pageCount }, options?.scriptTags !== true);
   } catch (err) {
     const isImageBased = err instanceof Error && "isImageBased" in err ? true : void 0;
     return { success: false, fileType: "pdf", error: sanitizeError(err), code: classifyError(err), isImageBased };
@@ -29581,7 +29616,7 @@ async function parseXls(buffer, options) {
 async function parseDocx(buffer, options) {
   try {
     const { markdown, blocks, metadata, outline, warnings, images } = await parseDocxDocument(buffer, options);
-    return { success: true, fileType: "docx", markdown, blocks, metadata, outline, warnings, images: images?.length ? images : void 0, pageCount: metadata?.pageCount };
+    return scriptsOff({ success: true, fileType: "docx", markdown, blocks, metadata, outline, warnings, images: images?.length ? images : void 0, pageCount: metadata?.pageCount }, options?.scriptTags === false);
   } catch (err) {
     return { success: false, fileType: "docx", error: sanitizeError(err), code: classifyError(err) };
   }
@@ -29756,4 +29791,4 @@ export {
   parseHwpml,
   fillForm
 };
-//# sourceMappingURL=chunk-OBRPYCIS.js.map
+//# sourceMappingURL=chunk-QOCS7W7R.js.map