Initial setups refine for ingestion_js #3 (upd module ver)

ingestion_js/lib/parser.ts

@@ -1,10 +1,6 @@
-import * as pdfjs from 'pdfjs-dist'
+import * as pdfjs from 'pdfjs-dist/legacy/build/pdf'
 import mammoth from 'mammoth'
 
-// Configure pdfjs in Node
-// @ts-ignore
-pdfjs.GlobalWorkerOptions.workerSrc = 'pdfjs-dist/build/pdf.worker.js'
-
 export type Page = { page_num: number; text: string; images: Buffer[] }
 
 export async function parsePdfBytes(buf: Buffer): Promise<Page[]> {
@@ -15,7 +11,7 @@ export async function parsePdfBytes(buf: Buffer): Promise<Page[]> {
   for (let i = 1; i <= num; i++) {
     const page = await pdf.getPage(i)
     const content = await page.getTextContent()
-    const text = content.items.map((it: any) => (it.str || '')).join(' ')
+    const text = (content.items as any[]).map((it: any) => (it.str || '')).join(' ')
     out.push({ page_num: i, text, images: [] })
   }
   return out

ingestion_js/next.config.js

@@ -1,10 +1,17 @@
 /** @type {import('next').NextConfig} */
 const nextConfig = {
   experimental: {
-    serverActions: {
-      bodySizeLimit: '50mb'
+    serverActions: { bodySizeLimit: '50mb' },
+    serverComponentsExternalPackages: ['pdfjs-dist']
+  },
+  webpack: (config) => {
+    config.resolve = config.resolve || {}
+    config.resolve.alias = {
+      ...(config.resolve.alias || {}),
+      canvas: false
     }
+    return config
   }
-};
+}
 
-module.exports = nextConfig;
+module.exports = nextConfig