kordoc 4.12.1 → 4.12.2

package/dist/{chunk-D2XNLIFU.js → chunk-MUYU4JI5.js}

@@ -1,5 +1,5 @@
 // src/utils.ts
-var VERSION = true ? "4.12.1" : "0.0.0-dev";
+var VERSION = true ? "4.12.2" : "0.0.0-dev";
 function toArrayBuffer(buf) {
   if (buf.byteOffset === 0 && buf.byteLength === buf.buffer.byteLength) {
     return buf.buffer;
@@ -121,4 +121,4 @@ export {
   safeMax,
   classifyError
 };
-//# sourceMappingURL=chunk-D2XNLIFU.js.map
+//# sourceMappingURL=chunk-MUYU4JI5.js.map

package/dist/{chunk-OS2IOI3W.js → chunk-OEYECZGV.js}

@@ -7,7 +7,7 @@ import {
 import {
   safeMax,
   safeMin
-} from "./chunk-E37VAV46.js";
+} from "./chunk-FBLMVHDK.js";
 
 // src/pdf/image-regions.ts
 import { OPS } from "pdfjs-dist/legacy/build/pdf.mjs";
@@ -1010,8 +1010,14 @@ function edgeStroked(lines, dir, pos, a1, a2) {
 }
 function buildClipCellGrids(rects, strokedH, strokedV, pageWidth, pageHeight) {
   const pageArea = pageWidth * pageHeight;
-  const cells = rects.filter((r) => r.x2 - r.x1 >= CLIP_MIN_W2 && r.y2 - r.y1 >= CLIP_MIN_H2 && (pageArea <= 0 || (r.x2 - r.x1) * (r.y2 - r.y1) < pageArea * CLIP_MAX_PAGE_FRAC));
-  if (cells.length < CLIP_MIN_GROUP) return { grids: [], containers: [] };
+  const sameRect = (a, b) => Math.abs(a.x1 - b.x1) <= CLIP_EDGE_TOL && Math.abs(a.x2 - b.x2) <= CLIP_EDGE_TOL && Math.abs(a.y1 - b.y1) <= CLIP_EDGE_TOL && Math.abs(a.y2 - b.y2) <= CLIP_EDGE_TOL;
+  const cells = [];
+  for (const r of rects) {
+    if (r.x2 - r.x1 < CLIP_MIN_W2 || r.y2 - r.y1 < CLIP_MIN_H2) continue;
+    if (pageArea > 0 && (r.x2 - r.x1) * (r.y2 - r.y1) >= pageArea * CLIP_MAX_PAGE_FRAC) continue;
+    if (!cells.some((c) => sameRect(c, r))) cells.push(r);
+  }
+  if (cells.length < 1) return { grids: [], containers: [] };
   const parent = new Array(cells.length).fill(-1);
   for (let i = 0; i < cells.length; i++) {
     for (let j = 0; j < cells.length; j++) {
@@ -1046,15 +1052,30 @@ function buildClipCellGrids(rects, strokedH, strokedV, pageWidth, pageHeight) {
     if (g) g.push(i);
     else groups.set(r, [i]);
   }
-  const containers = [];
-  for (let i = 0; i < cells.length; i++) {
-    if (!isContainer[i]) continue;
-    const r = cells[i];
-    if (!containers.some((c) => Math.abs(c.x1 - r.x1) <= CLIP_EDGE_TOL && Math.abs(c.x2 - r.x2) <= CLIP_EDGE_TOL && Math.abs(c.y1 - r.y1) <= CLIP_EDGE_TOL && Math.abs(c.y2 - r.y2) <= CLIP_EDGE_TOL)) containers.push(r);
-  }
+  const containers = cells.filter((_, i) => isContainer[i]);
+  const groupSize = (i) => groups.get(find(i))?.length ?? 0;
+  const isGridMember = (i) => groupSize(i) >= CLIP_MIN_GROUP;
+  const framed = (r) => edgeStroked(strokedH, "h", r.y1, r.x1, r.x2) && edgeStroked(strokedH, "h", r.y2, r.x1, r.x2) && edgeStroked(strokedV, "v", r.x1, r.y1, r.y2) && edgeStroked(strokedV, "v", r.x2, r.y1, r.y2);
+  const loneFrame = (i) => isContainer[i] && !isGridMember(i) && framed(cells[i]);
+  const parentAttachable = (i) => parent[i] >= 0 && (isGridMember(parent[i]) || loneFrame(parent[i]));
+  const onlyChild = (i) => parent[i] >= 0 && parent.filter((p) => p === parent[i]).length === 1;
   const grids = [];
   for (const idxs of groups.values()) {
-    if (idxs.length < CLIP_MIN_GROUP) continue;
+    const first = idxs[0];
+    const parentRect = parentAttachable(first) ? cells[parent[first]] : void 0;
+    if (idxs.length < CLIP_MIN_GROUP) {
+      if (!loneFrame(first) && !((parentRect || onlyChild(first)) && framed(cells[first]))) continue;
+      const r = cells[first];
+      grids.push({
+        rowYs: [r.y2, r.y1],
+        colXs: [r.x1, r.x2],
+        bbox: { x1: r.x1, y1: r.y1, x2: r.x2, y2: r.y2 },
+        vertexRadius: 1,
+        cells: [{ row: 0, col: 0, rowSpan: 1, colSpan: 1, bbox: { x1: r.x1, y1: r.y1, x2: r.x2, y2: r.y2 } }],
+        ...parentRect ? { clipParent: parentRect } : {}
+      });
+      continue;
+    }
     const members = idxs.map((i) => cells[i]);
     let edges = 0, invisible = 0;
     for (const r of members) {
@@ -1095,7 +1116,8 @@ function buildClipCellGrids(rects, strokedH, strokedV, pageWidth, pageHeight) {
       colXs,
       bbox: { x1: colXs[0], y1: rowYs[numRows], x2: colXs[numCols], y2: rowYs[0] },
       vertexRadius: 1,
-      cells: out
+      cells: out,
+      ...parentRect ? { clipParent: parentRect } : {}
     });
   }
   return { grids, containers };
@@ -3464,9 +3486,47 @@ function isProseBoxGrid(grid, verticals, table) {
   if (longCells < PROSEBOX_LONG_CELL_MIN || longCells < texts.length * PROSEBOX_LONG_CELL_RATIO) return false;
   return true;
 }
+function cleanCellText(text) {
+  const stripped = text.replace(/^[\s]*[-–—]\s*\d+\s*[-–—][\s]*$/gm, "").trim();
+  return stripped.split("\n").map((line) => collapseEvenSpacing(line)).join("\n");
+}
+var FRAME_RECT_TOL = 1.5;
+function takePendingNested(pending, cellBox) {
+  const out = [];
+  for (let i = pending.length - 1; i >= 0; i--) {
+    const p = pending[i].parent;
+    if (Math.abs(p.x1 - cellBox.x1) <= FRAME_RECT_TOL && Math.abs(p.x2 - cellBox.x2) <= FRAME_RECT_TOL && Math.abs(p.y1 - cellBox.y1) <= FRAME_RECT_TOL && Math.abs(p.y2 - cellBox.y2) <= FRAME_RECT_TOL) {
+      out.push(pending[i].block);
+      pending.splice(i, 1);
+    }
+  }
+  return out;
+}
+function buildFrameCellBlocks(cellItems, nested, pageNum) {
+  const tables = [...nested].sort((a, b) => b.bbox.y + b.bbox.height - (a.bbox.y + a.bbox.height));
+  const blocks = [];
+  let rest = [...cellItems];
+  const pushParagraphs = (items) => {
+    if (items.length === 0) return;
+    for (const line of cleanCellText(cellTextToString(items)).split("\n")) {
+      const t = line.trim();
+      if (t) blocks.push({ type: "paragraph", text: t, pageNumber: pageNum });
+    }
+  };
+  for (const tb of tables) {
+    const bottom = tb.bbox.y;
+    pushParagraphs(rest.filter((it) => it.y >= bottom));
+    rest = rest.filter((it) => it.y < bottom);
+    blocks.push(tb);
+  }
+  pushParagraphs(rest);
+  const text = blocks.map((b) => b.type === "table" && b.table ? b.table.cells.flat().map((c) => c.text).filter(Boolean).join("\n") : b.text ?? "").filter(Boolean).join("\n");
+  return { blocks, text };
+}
 function extractBlocksWithGrids(items, pageNum, grids, horizontals, verticals) {
   const blocks = [];
   const usedItems = /* @__PURE__ */ new Set();
+  const pendingNested = [];
   const gridArea = (g) => (g.bbox.x2 - g.bbox.x1) * (g.bbox.y2 - g.bbox.y1);
   const sortedGrids = [...grids].sort((a, b) => (b.cells ? 1 : 0) - (a.cells ? 1 : 0) || (a.cells && b.cells ? gridArea(a) - gridArea(b) : 0) || b.bbox.y2 - a.bbox.y2);
   for (const grid of sortedGrids) {
@@ -3506,13 +3566,18 @@ function extractBlocksWithGrids(items, pageNum, grids, horizontals, verticals) {
       { length: numRows },
       () => Array.from({ length: numCols }, () => ({ text: "", colSpan: 1, rowSpan: 1 }))
     );
+    let nestedAttached = false;
     for (const cell of cells) {
       const cellItems = cellTextMap.get(cell) || [];
-      let text = cellTextToString(cellItems);
-      text = text.replace(/^[\s]*[-–—]\s*\d+\s*[-–—][\s]*$/gm, "").trim();
-      text = text.split("\n").map((line) => collapseEvenSpacing(line)).join("\n");
+      const nested = grid.cells ? takePendingNested(pendingNested, cell.bbox) : [];
+      if (nested.length > 0) {
+        nestedAttached = true;
+        const built = buildFrameCellBlocks(cellItems, nested, pageNum);
+        irGrid[cell.row][cell.col] = { text: built.text, colSpan: cell.colSpan, rowSpan: cell.rowSpan, blocks: built.blocks };
+        continue;
+      }
       irGrid[cell.row][cell.col] = {
-        text,
+        text: cleanCellText(cellTextToString(cellItems)),
         colSpan: cell.colSpan,
         rowSpan: cell.rowSpan
       };
@@ -3520,18 +3585,11 @@ function extractBlocksWithGrids(items, pageNum, grids, horizontals, verticals) {
     let finalGrid = irGrid;
     let finalRows = numRows;
     let rebuiltUsed = false;
-    if (numRows <= 2 && numCols >= 3) {
+    if (numRows <= 2 && numCols >= 3 && !nestedAttached) {
       const rebuilt = normalizeUndersegmentedTable(irGrid, grid.colXs, textItems);
       if (rebuilt) {
         rebuiltUsed = true;
-        finalGrid = rebuilt.map((row) => row.map((rawText) => {
-          const cleaned = rawText.replace(/^[\s]*[-–—]\s*\d+\s*[-–—][\s]*$/gm, "").trim();
-          return {
-            text: cleaned.split("\n").map((line) => collapseEvenSpacing(line)).join("\n"),
-            colSpan: 1,
-            rowSpan: 1
-          };
-        }));
+        finalGrid = rebuilt.map((row) => row.map((rawText) => ({ text: cleanCellText(rawText), colSpan: 1, rowSpan: 1 })));
         finalRows = finalGrid.length;
       }
     }
@@ -3548,6 +3606,11 @@ function extractBlocksWithGrids(items, pageNum, grids, horizontals, verticals) {
     };
     const hasContent = finalGrid.some((row) => row.some((cell) => cell.text.trim() !== ""));
     if (!hasContent) continue;
+    if (grid.clipParent) {
+      const nb = { page: pageNum, x: grid.bbox.x1, y: grid.bbox.y1, width: grid.bbox.x2 - grid.bbox.x1, height: grid.bbox.y2 - grid.bbox.y1 };
+      pendingNested.push({ parent: grid.clipParent, block: { type: "table", table: irTable, pageNumber: pageNum, bbox: nb } });
+      continue;
+    }
     if (!grid.cells && isProseBoxGrid(grid, verticals, irTable)) {
       for (const it of tableItems) usedItems.delete(it);
       continue;
@@ -3569,6 +3632,7 @@ function extractBlocksWithGrids(items, pageNum, grids, horizontals, verticals) {
     }
     blocks.push({ type: "table", table: irTable, pageNumber: pageNum, bbox: tableBbox });
   }
+  for (const p of pendingNested) blocks.push(p.block);
   let remaining = items.filter((i) => !usedItems.has(i));
   const groupSizes = [];
   let finalTextBlocks = [];
@@ -3878,4 +3942,4 @@ export {
   extractPageBlocksWithLines,
   mergeCrossPageTables
 };
-//# sourceMappingURL=chunk-OS2IOI3W.js.map
+//# sourceMappingURL=chunk-OEYECZGV.js.map