formatferry 1.0.22 → 1.0.24

package/dist/index.js

@@ -22089,17 +22089,18 @@ function esc(str) {
 function isContent(node) {
   return "id" in node && !("role" in node);
 }
-function walkChildren(children, mcidMap, depth) {
-  return children.map((c) => walkNode(c, mcidMap, depth)).join("");
+function walkChildren(children, mcidMap, depth, visitedMcids) {
+  return children.map((c) => walkNode(c, mcidMap, depth, visitedMcids)).join("");
 }
-function walkNode(node, mcidMap, depth = 0) {
+function walkNode(node, mcidMap, depth = 0, visitedMcids = /* @__PURE__ */ new Set()) {
   if (depth > 50) return "";
   if (isContent(node)) {
+    visitedMcids.add(node.id);
     const text = mcidMap.get(node.id) ?? "";
     return esc(text);
   }
   const children = node.children ?? [];
-  const inner = walkChildren(children, mcidMap, depth + 1);
+  const inner = walkChildren(children, mcidMap, depth + 1, visitedMcids);
   switch (node.role) {
     case "H":
       return `<h1>${inner}</h1>`;
@@ -22182,10 +22183,11 @@ async function structTreeToHtml(page) {
     return null;
   }
   const mcidMap = buildMcidMap(textContent.items);
-  const html = walkNode(structTree, mcidMap);
+  const claimedMcids = /* @__PURE__ */ new Set();
+  const html = walkNode(structTree, mcidMap, 0, claimedMcids);
   const textOnly = html.replace(/<[^>]+>/g, "").trim();
   if (!textOnly) return null;
-  return html;
+  return { html, claimedMcids };
 }
 
 // ../../src/shared/adapters/pdf-adapter.ts
@@ -23071,7 +23073,10 @@ var PdfAdapter = class {
           let structHtml = null;
           try {
             if (hasStructTree(page)) {
-              structHtml = await structTreeToHtml(page);
+              const structResult = await structTreeToHtml(page);
+              if (structResult !== null) {
+                structHtml = structResult.html;
+              }
             }
           } catch {
           }
@@ -23170,7 +23175,7 @@ var PdfAdapter = class {
       const hasMinimalTextWithImages = totalTextLength < MIN_TEXT_CHARS_THRESHOLD && hasAnyImages;
       if (hasNoText || hasMinimalTextWithImages) {
         throw new PdfParseError(
-          "This PDF contains only images. Text extraction requires a text layer. OCR is not supported.",
+          "PDF contains only images \u2014 no text layer available.",
           "IMAGE_ONLY"
         );
       }
@@ -25500,8 +25505,8 @@ import { readFileSync as readFileSync4 } from "fs";
 import { resolve, dirname as dirname3 } from "path";
 import { fileURLToPath } from "url";
 var getVersion = () => {
-  if ("1.0.22") {
-    return "1.0.22";
+  if ("1.0.24") {
+    return "1.0.24";
   }
   try {
     const __dirname = dirname3(fileURLToPath(import.meta.url));

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "formatferry",
-  "version": "1.0.22",
+  "version": "1.0.24",
   "description": "FormatFerry CLI — Convert HTML, DOCX, PDF, XLSX, CSV, JSON, XML, PPTX to Markdown",
   "keywords": [
     "markdown",