unpdf 1.0.3 → 1.0.5

package/README.md

@@ -69,12 +69,13 @@ Usually you don't need to worry about the PDF.js build. `unpdf` ships with a ser
 For example, if you want to use the official PDF.js build, you can do the following:
 
 ```ts
-import { definePDFJSModule } from 'unpdf'
+import { definePDFJSModule, extractText, getDocumentProxy } from 'unpdf'
 
 // Define the PDF.js build before using any other unpdf method
 await definePDFJSModule(() => import('pdfjs-dist'))
 
 // Now, you can use all unpdf methods with the official PDF.js build
+const pdf = await getDocumentProxy(/* … */)
 const { text } = await extractText(pdf)
 ```
 
@@ -93,23 +94,17 @@ const { version } = await getResolvedPDFJS()
 > [!NOTE]
 > If no other PDF.js build was defined, the serverless build will always be used.
 
-For example, you can use the `getDocument` method to load a PDF file and then use the `getPage` method to get a specific page. You can also use the `getTextContent` method to extract the text from the page.
+For example, you can use the `getDocument` method to load a PDF file and then use the `getMetadata` method to get the metadata of the PDF file:
 
 ```ts
+import { readFile } from 'node:fs/promises'
 import { getResolvedPDFJS } from 'unpdf'
 
 const { getDocument } = await getResolvedPDFJS()
-const data = Deno.readFileSync('dummy.pdf')
-const document = await getDocument(data).promise
+const data = await readFile('./dummy.pdf')
+const document = await getDocument(new Uint8Array(data)).promise
 
 console.log(await document.getMetadata())
-
-for (let i = 1; i <= document.numPages; i++) {
-  const page = await document.getPage(i)
-  const textContent = await page.getTextContent()
-  const contents = textContent.items.map(item => item.str).join(' ')
-  console.log(contents)
-}
 ```
 
 ## API

package/dist/index.cjs

@@ -145,7 +145,7 @@ async function extractImages$1(data, pageNumber) {
       continue;
     }
     const imageKey = operatorList.argsArray[i][0];
-    const image = await page.objs.get(imageKey);
+    const image = imageKey.startsWith("g_") ? await page.commonObjs.get(imageKey) : await page.objs.get(imageKey);
     if (!image || !image.data || !image.width || !image.height) {
       continue;
     }

package/dist/index.mjs

@@ -143,7 +143,7 @@ async function extractImages$1(data, pageNumber) {
       continue;
     }
     const imageKey = operatorList.argsArray[i][0];
-    const image = await page.objs.get(imageKey);
+    const image = imageKey.startsWith("g_") ? await page.commonObjs.get(imageKey) : await page.objs.get(imageKey);
     if (!image || !image.data || !image.width || !image.height) {
       continue;
     }

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "unpdf",
   "type": "module",
-  "version": "1.0.3",
+  "version": "1.0.5",
   "packageManager": "pnpm@10.10.0",
   "description": "PDF extraction and rendering across all JavaScript runtimes",
   "author": "Johann Schopplich <hello@johannschopplich.com>",
@@ -71,7 +71,7 @@
   },
   "devDependencies": {
     "@antfu/eslint-config": "^4.12.0",
-    "@napi-rs/canvas": "^0.1.69",
+    "@napi-rs/canvas": "^0.1.70",
     "@rollup/plugin-alias": "^5.1.1",
     "@rollup/plugin-inject": "^5.0.5",
     "@rollup/plugin-node-resolve": "^16.0.1",
@@ -80,7 +80,7 @@
     "@rollup/plugin-typescript": "^12.1.2",
     "@types/node": "^22.15.3",
     "bumpp": "^10.1.0",
-    "eslint": "^9.25.1",
+    "eslint": "^9.26.0",
     "fast-glob": "^3.3.3",
     "pdfjs-dist": "~5.2.133",
     "rollup": "^4.40.1",