@dragon708/docmind-node 1.12.2 → 1.13.0

package/dist/index.d.ts

@@ -6,7 +6,7 @@ import { AnalyzeDocxIncludeFlags, DocxToHtmlOptions, ExtractStructuredDataFromDo
 export { AnalyzeDocxIncludeFlags, DocxEmbeddedImage, DocxEmbeddedImageConversionOptions, DocxEmbeddedImageConversionResult, DocxEmbeddedImageWebSlice, DocxImageExtractionMode, ExtractImagesFromDocxOptions, ExtractImagesFromDocxResult, ExtractStructuredDataFromDocxOptions, convertDocxEmbeddedImageToWeb, convertDocxImagesForWeb, docxImageIsBrowserRenderable, docxImageRequiresConversion, docxImageSuggestedTargetFormat, docxImageToDataUri, extractImagesFromDocx, extractStructuredDataFromDocx, isNodeJsRuntime } from '@dragon708/docmind-docx';
 import { PdfAnalyzeOptions, ExtractStructuredDataFromPdfOptions } from '@dragon708/docmind-pdf';
 export { ExtractStructuredDataFromPdfIncludeFlags, ExtractStructuredDataFromPdfOptions, extractStructuredDataFromPdf } from '@dragon708/docmind-pdf';
-import { RenderLlmTextOptions, RenderMarkdownOptions, ConvertDocxToMarkdownOptions, ConvertPdfToMarkdownOptions, RenderMarkdownSectionsOptions, MarkdownSection } from '@dragon708/docmind-markdown';
+import { RenderLlmTextOptions, RenderMarkdownOptions, ConvertDocxToMarkdownOptions, ConvertPdfToMarkdownOptions, ExtractMarkdownStrategy, RenderMarkdownSectionsOptions, MarkdownSection } from '@dragon708/docmind-markdown';
 export { MarkdownSection } from '@dragon708/docmind-markdown';
 
 /**
@@ -63,6 +63,14 @@ interface NodeExtractMarkdownOptions extends NodeExtractStructuredDataOptions {
     readonly markdownDocx?: ConvertDocxToMarkdownOptions;
     /** Forwarded to `extractMarkdown` → `convertPdfToMarkdown` when bytes are PDF. */
     readonly markdownPdf?: ConvertPdfToMarkdownOptions;
+    /**
+     * Optional: receive `strategy` and merged `warnings` from `@dragon708/docmind-markdown` `extractMarkdown`
+     * (e.g. `pdf-opendataloader` vs `pdf-structured-fallback`) without changing the `Promise<string>` return type.
+     */
+    readonly onMarkdownExtract?: (info: {
+        strategy: ExtractMarkdownStrategy;
+        warnings: readonly string[];
+    }) => void;
 }
 /**
  * {@link extractLlmContent}: same structured fields; `llm` forwards to `renderLlmText`.

package/dist/index.js

@@ -620,7 +620,13 @@ async function runOcr(input, options) {
 }
 async function extractMarkdown(input, options) {
   throwIfAborted(options?.signal);
-  const { markdown: markdownOpts, markdownDocx, markdownPdf, ...structuredOpts } = options ?? {};
+  const {
+    markdown: markdownOpts,
+    markdownDocx,
+    markdownPdf,
+    onMarkdownExtract,
+    ...structuredOpts
+  } = options ?? {};
   const resolved = await resolveNodeAnalyzeInput(input);
   const structured = await extractStructuredData(resolved, structuredOpts);
   const data = await bytesFromDetectInput(resolved);
@@ -639,6 +645,7 @@ async function extractMarkdown(input, options) {
       structuredFallback: structured
     }
   );
+  onMarkdownExtract?.({ strategy: r.strategy, warnings: r.warnings });
   return r.markdown;
 }
 async function extractLlmContent(input, options) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@dragon708/docmind-node",
-  "version": "1.12.2",
+  "version": "1.13.0",
   "description": "Official DocMind Node facade: analyzeFile, intent APIs, PDF/DOCX/OCR, and fs helpers.",
   "type": "module",
   "main": "./dist/index.js",
@@ -33,7 +33,7 @@
   "license": "MIT",
   "dependencies": {
     "@dragon708/docmind-docx": "^1.8.0",
-    "@dragon708/docmind-markdown": "^1.1.2",
+    "@dragon708/docmind-markdown": "^1.2.0",
     "@dragon708/docmind-ocr": "^1.1.4",
     "@dragon708/docmind-pdf": "^2.2.0",
     "@dragon708/docmind-shared": "^1.2.0"