unpdf 0.12.0 → 0.12.2

package/README.md

@@ -38,20 +38,23 @@ yarn add unpdf
 ### Extract Text From PDF
 
 ```ts
-import { extractText, getDocumentProxy } from "unpdf";
+import { extractText, getDocumentProxy } from 'unpdf'
 
 // Fetch a PDF file from the web
 const buffer = await fetch(
-  "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
-).then((res) => res.arrayBuffer());
+  'https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf',
+).then(res => res.arrayBuffer())
 
 // Or load it from the filesystem
-const buffer = await readFile("./dummy.pdf");
+const buffer = await readFile('./dummy.pdf')
 
 // Load PDF from buffer
-const pdf = await getDocumentProxy(new Uint8Array(buffer));
+const pdf = await getDocumentProxy(new Uint8Array(buffer))
 // Extract text from PDF
-const { totalPages, text } = await extractText(pdf, { mergePages: true });
+const { totalPages, text } = await extractText(pdf, { mergePages: true })
+
+console.log(`Total pages: ${totalPages}`)
+console.log(text)
 ```
 
 ### Access the PDF.js API
@@ -65,19 +68,19 @@ This will return the resolved PDF.js module and gives full access to the PDF.js
 Especially useful for platforms like 🦕 Deno or if you want to use the PDF.js API directly. If no custom build was defined beforehand, the serverless build bundled with `unpdf` will be initialized.
 
 ```ts
-import { getResolvedPDFJS } from "unpdf";
+import { getResolvedPDFJS } from 'unpdf'
 
-const { getDocument } = await getResolvedPDFJS();
-const data = Deno.readFileSync("dummy.pdf");
-const doc = await getDocument(data).promise;
+const { getDocument } = await getResolvedPDFJS()
+const data = Deno.readFileSync('dummy.pdf')
+const doc = await getDocument(data).promise
 
-console.log(await doc.getMetadata());
+console.log(await doc.getMetadata())
 
 for (let i = 1; i <= doc.numPages; i++) {
-  const page = await doc.getPage(i);
-  const textContent = await page.getTextContent();
-  const contents = textContent.items.map((item) => item.str).join(" ");
-  console.log(contents);
+  const page = await doc.getPage(i)
+  const textContent = await page.getTextContent()
+  const contents = textContent.items.map(item => item.str).join(' ')
+  console.log(contents)
 }
 ```
 
@@ -91,12 +94,12 @@ Generally speaking, you don't need to worry about the PDF.js build. `unpdf` ship
 ```ts
 // Before using any other method, define the PDF.js module
 // if you need another PDF.js build
-import { configureUnPDF } from "unpdf";
+import { configureUnPDF } from 'unpdf'
 
 await configureUnPDF({
   // Use the official PDF.js build (make sure to install it first)
-  pdfjs: () => import("pdfjs-dist"),
-});
+  pdfjs: () => import('pdfjs-dist'),
+})
 
 // Now, you can use the other methods
 // …
@@ -115,7 +118,7 @@ interface UnPDFConfiguration {
    * // Use the official PDF.js build (make sure to install it first)
    * () => import('pdfjs-dist')
    */
-  pdfjs?: () => Promise<PDFJS>;
+  pdfjs?: () => Promise<PDFJS>
 }
 ```
 
@@ -126,7 +129,7 @@ interface UnPDFConfiguration {
 Define a custom PDF.js module, like the legacy build. Make sure to call this method before using any other methods.
 
 ```ts
-function configureUnPDF(config: UnPDFConfiguration): Promise<void>;
+function configureUnPDF(config: UnPDFConfiguration): Promise<void>
 ```
 
 ### `getResolvedPDFJS`
@@ -134,18 +137,18 @@ function configureUnPDF(config: UnPDFConfiguration): Promise<void>;
 Returns the resolved PDF.js module. If no build is defined, the latest version will be initialized.
 
 ```ts
-function getResolvedPDFJS(): Promise<PDFJS>;
+function getResolvedPDFJS(): Promise<PDFJS>
 ```
 
 ### `getMeta`
 
 ```ts
 function getMeta(
-  data: DocumentInitParameters["data"] | PDFDocumentProxy,
+  data: DocumentInitParameters['data'] | PDFDocumentProxy,
 ): Promise<{
-  info: Record<string, any>;
-  metadata: Record<string, any>;
-}>;
+  info: Record<string, any>
+  metadata: Record<string, any>
+}>
 ```
 
 ### `extractText`
@@ -154,12 +157,12 @@ Extracts all text from a PDF. If `mergePages` is set to `true`, the text of all
 
 ```ts
 function extractText(
-  data: DocumentInitParameters["data"] | PDFDocumentProxy,
+  data: DocumentInitParameters['data'] | PDFDocumentProxy,
   { mergePages }?: { mergePages?: boolean },
 ): Promise<{
-  totalPages: number;
-  text: string | string[];
-}>;
+  totalPages: number
+  text: string | string[]
+}>
 ```
 
 ### `renderPageAsImage`
@@ -177,37 +180,37 @@ In order to use this method, you have to meet the following requirements:
 **Example**
 
 ```ts
-import { configureUnPDF, renderPageAsImage } from "unpdf";
+import { configureUnPDF, renderPageAsImage } from 'unpdf'
 
 await configureUnPDF({
   // Use the official PDF.js build
-  pdfjs: () => import("pdfjs-dist"),
-});
+  pdfjs: () => import('pdfjs-dist'),
+})
 
-const pdf = await readFile("./dummy.pdf");
-const buffer = new Uint8Array(pdf);
-const pageNumber = 1;
+const pdf = await readFile('./dummy.pdf')
+const buffer = new Uint8Array(pdf)
+const pageNumber = 1
 
 const result = await renderPageAsImage(buffer, pageNumber, {
-  canvas: () => import("canvas"),
-});
-await writeFile("dummy-page-1.png", Buffer.from(result));
+  canvas: () => import('canvas'),
+})
+await writeFile('dummy-page-1.png', result)
 ```
 
 **Type Declaration**
 
 ```ts
 declare function renderPageAsImage(
-  data: DocumentInitParameters["data"],
+  data: DocumentInitParameters['data'],
   pageNumber: number,
   options?: {
-    canvas?: () => Promise<typeof import("canvas")>;
+    canvas?: () => Promise<typeof import('canvas')>
     /** @default 1 */
-    scale?: number;
-    width?: number;
-    height?: number;
+    scale?: number
+    width?: number
+    height?: number
   },
-): Promise<ArrayBuffer>;
+): Promise<ArrayBuffer>
 ```
 
 ## FAQ

package/dist/index.cjs

@@ -33,19 +33,15 @@ async function resolvePDFJSImports(pdfjsResolver, { force = false } = {}) {
       return;
     } catch (error) {
       console.error(error);
-      throw new Error(
-        "Resolving failed. Please check the provided configuration."
-      );
+      throw new Error("Resolving failed. Please check the provided configuration.");
     }
   }
   try {
-    const { resolvePDFJS } = await Promise.resolve().then(function () { return pdfjs; });
+    const { resolvePDFJS } = await import('unpdf/pdfjs');
     resolvedModule = await resolvePDFJS();
   } catch (error) {
     console.error(error);
-    throw new Error(
-      "PDF.js is not available. Please add the package as a dependency."
-    );
+    throw new Error("PDF.js is not available. Please add the package as a dependency.");
   }
 }
 function isPDFDocumentProxy(data) {
@@ -56,40 +52,12 @@ async function interopDefault(m) {
   return resolved.default || resolved;
 }
 
-async function getMeta$1(data) {
-  const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
-  const meta = await pdf.getMetadata();
-  return {
-    info: meta?.info ?? {},
-    metadata: meta?.metadata?.getAll() ?? {}
-  };
-}
-
-async function extractText$1(data, options = {}) {
-  const { mergePages = false } = { ...options };
-  const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
-  const texts = await Promise.all(
-    Array.from({ length: pdf.numPages }, (_, i) => getPageText(pdf, i + 1))
-  );
-  return {
-    totalPages: pdf.numPages,
-    text: mergePages ? texts.join("\n").replace(/\s+/g, " ") : texts
-  };
-}
-async function getPageText(document, pageNumber) {
-  const page = await document.getPage(pageNumber);
-  const content = await page.getTextContent();
-  return content.items.filter((item) => item.str != null).map((item) => item.str + (item.hasEOL ? "\n" : "")).join("");
-}
-
 async function extractImages$1(data, pageNumber) {
   const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
-  const page = await pdf.getPage(pageNumber);
   if (pageNumber < 1 || pageNumber > pdf.numPages) {
-    throw new Error(
-      `Invalid page number. Must be between 1 and ${pdf.numPages}.`
-    );
+    throw new Error(`Invalid page number. Must be between 1 and ${pdf.numPages}.`);
   }
+  const page = await pdf.getPage(pageNumber);
   const operatorList = await page.getOperatorList();
   const { OPS } = await getResolvedPDFJS();
   const images = [];
@@ -100,7 +68,22 @@ async function extractImages$1(data, pageNumber) {
     }
     const imageKey = operatorList.argsArray[i][0];
     const image = await page.objs.get(imageKey);
-    images.push(image.data);
+    if (!image || !image.data || !image.width || !image.height) {
+      continue;
+    }
+    const { width, height, data: data2 } = image;
+    const calculatedChannels = data2.length / (width * height);
+    if (![1, 3, 4].includes(calculatedChannels)) {
+      continue;
+    }
+    const channels = calculatedChannels;
+    images.push({
+      data: data2,
+      width,
+      height,
+      channels,
+      key: imageKey
+    });
   }
   return images;
 }
@@ -109,9 +92,7 @@ async function renderPageAsImage$1(data, pageNumber, options = {}) {
   const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data, { canvasFactory });
   const page = await pdf.getPage(pageNumber);
   if (pageNumber < 1 || pageNumber > pdf.numPages) {
-    throw new Error(
-      `Invalid page number. Must be between 1 and ${pdf.numPages}.`
-    );
+    throw new Error(`Invalid page number. Must be between 1 and ${pdf.numPages}.`);
   }
   let outputScale = options.scale || 1;
   let viewport = page.getViewport({ scale: outputScale });
@@ -177,6 +158,32 @@ async function createIsomorphicCanvasFactory(canvas) {
   };
 }
 
+async function getMeta$1(data) {
+  const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
+  const meta = await pdf.getMetadata();
+  return {
+    info: meta?.info ?? {},
+    metadata: meta?.metadata?.getAll() ?? {}
+  };
+}
+
+async function extractText$1(data, options = {}) {
+  const { mergePages = false } = { ...options };
+  const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
+  const texts = await Promise.all(
+    Array.from({ length: pdf.numPages }, (_, i) => getPageText(pdf, i + 1))
+  );
+  return {
+    totalPages: pdf.numPages,
+    text: mergePages ? texts.join("\n").replace(/\s+/g, " ") : texts
+  };
+}
+async function getPageText(document, pageNumber) {
+  const page = await document.getPage(pageNumber);
+  const content = await page.getTextContent();
+  return content.items.filter((item) => item.str != null).map((item) => item.str + (item.hasEOL ? "\n" : "")).join("");
+}
+
 async function configureUnPDF(options) {
   const { pdfjs } = { ...options };
   if (pdfjs) {
@@ -201,10 +208,6 @@ const renderPageAsImage = async (...args) => {
   return await renderPageAsImage$1(...args);
 };
 
-const pdfjs = {
-  __proto__: null
-};
-
 exports.configureUnPDF = configureUnPDF;
 exports.createIsomorphicCanvasFactory = createIsomorphicCanvasFactory;
 exports.extractImages = extractImages;

package/dist/index.d.cts

@@ -1,28 +1,37 @@
-import { DocumentInitParameters, PDFDocumentProxy } from './types/src/display/api';
 import * as canvas from 'canvas';
 import { Canvas } from 'canvas';
+import { DocumentInitParameters, PDFDocumentProxy } from './types/src/display/api';
 import * as _PDFJS from './types/src/pdf';
 
-declare function getMeta$1(data: DocumentInitParameters["data"] | PDFDocumentProxy): Promise<{
-    info: Record<string, any>;
-    metadata: Record<string, any>;
-}>;
-
-declare function extractText$1(data: DocumentInitParameters["data"] | PDFDocumentProxy, options?: {
-    mergePages?: false;
-}): Promise<{
-    totalPages: number;
-    text: string[];
-}>;
-declare function extractText$1(data: DocumentInitParameters["data"] | PDFDocumentProxy, options: {
-    mergePages: true;
-}): Promise<{
-    totalPages: number;
-    text: string;
-}>;
-
-declare function extractImages$1(data: DocumentInitParameters["data"] | PDFDocumentProxy, pageNumber: number): Promise<Uint8ClampedArray[]>;
-declare function renderPageAsImage$1(data: DocumentInitParameters["data"] | PDFDocumentProxy, pageNumber: number, options?: {
+interface ExtractedImageObject {
+    data: Uint8ClampedArray;
+    width: number;
+    height: number;
+    channels: 1 | 3 | 4;
+    key: string;
+}
+/**
+ * Extracts images from a specific page of a PDF document, including necessary metadata,
+ * such as width, height, and calculated color channels.
+ *
+ * This version calculates channels based on image data length, width, and height,
+ * as the `kind` property provided by PDF.js might not reliably indicate the actual
+ * channel count of the raw pixel data (e.g., returning RGBA data even when kind is 3).
+ *
+ * @example
+ * const imagesData = await extractImages(pdf, pageNum)
+ *
+ * for (const imgData of imagesData) {
+ *   const imageIndex = totalImagesProcessed + 1;
+ *   await sharp(imgData.data, {
+ *     raw: { width: imgData.width, height: imgData.height, channels: imgData.channels }
+ *   })
+ *     .png()
+ *     .toFile(`${imageIndex}.png`);
+ * }
+ */
+declare function extractImages$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, pageNumber: number): Promise<ExtractedImageObject[]>;
+declare function renderPageAsImage$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, pageNumber: number, options?: {
     canvas?: () => Promise<typeof canvas>;
     /** @default 1 */
     scale?: number;
@@ -45,6 +54,24 @@ declare function createIsomorphicCanvasFactory(canvas?: () => Promise<typeof can
     }): void;
 }>;
 
+declare function getMeta$1(data: DocumentInitParameters['data'] | PDFDocumentProxy): Promise<{
+    info: Record<string, any>;
+    metadata: Record<string, any>;
+}>;
+
+declare function extractText$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, options?: {
+    mergePages?: false;
+}): Promise<{
+    totalPages: number;
+    text: string[];
+}>;
+declare function extractText$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, options: {
+    mergePages: true;
+}): Promise<{
+    totalPages: number;
+    text: string;
+}>;
+
 type PDFJS = typeof _PDFJS;
 interface UnPDFConfiguration {
     /**
@@ -59,6 +86,8 @@ interface UnPDFConfiguration {
     pdfjs?: () => Promise<any>;
 }
 
+declare function configureUnPDF(options: UnPDFConfiguration): Promise<void>;
+
 /**
  * Returns a PDFDocumentProxy instance from a given binary data.
  *
@@ -66,14 +95,12 @@ interface UnPDFConfiguration {
  * - `isEvalSupported: false`
  * - `useSystemFonts: true`
  */
-declare function getDocumentProxy(data: DocumentInitParameters["data"], options?: DocumentInitParameters): Promise<PDFDocumentProxy>;
+declare function getDocumentProxy(data: DocumentInitParameters['data'], options?: DocumentInitParameters): Promise<PDFDocumentProxy>;
 declare function getResolvedPDFJS(): Promise<PDFJS>;
 declare function resolvePDFJSImports(pdfjsResolver?: () => Promise<any>, { force }?: {
     force?: boolean | undefined;
 }): Promise<void>;
 
-declare function configureUnPDF(options: UnPDFConfiguration): Promise<void>;
-
 declare const getMeta: typeof getMeta$1;
 declare const extractText: typeof extractText$1;
 declare const extractImages: typeof extractImages$1;

package/dist/index.d.mts

@@ -1,28 +1,37 @@
-import { DocumentInitParameters, PDFDocumentProxy } from './types/src/display/api';
 import * as canvas from 'canvas';
 import { Canvas } from 'canvas';
+import { DocumentInitParameters, PDFDocumentProxy } from './types/src/display/api';
 import * as _PDFJS from './types/src/pdf';
 
-declare function getMeta$1(data: DocumentInitParameters["data"] | PDFDocumentProxy): Promise<{
-    info: Record<string, any>;
-    metadata: Record<string, any>;
-}>;
-
-declare function extractText$1(data: DocumentInitParameters["data"] | PDFDocumentProxy, options?: {
-    mergePages?: false;
-}): Promise<{
-    totalPages: number;
-    text: string[];
-}>;
-declare function extractText$1(data: DocumentInitParameters["data"] | PDFDocumentProxy, options: {
-    mergePages: true;
-}): Promise<{
-    totalPages: number;
-    text: string;
-}>;
-
-declare function extractImages$1(data: DocumentInitParameters["data"] | PDFDocumentProxy, pageNumber: number): Promise<Uint8ClampedArray[]>;
-declare function renderPageAsImage$1(data: DocumentInitParameters["data"] | PDFDocumentProxy, pageNumber: number, options?: {
+interface ExtractedImageObject {
+    data: Uint8ClampedArray;
+    width: number;
+    height: number;
+    channels: 1 | 3 | 4;
+    key: string;
+}
+/**
+ * Extracts images from a specific page of a PDF document, including necessary metadata,
+ * such as width, height, and calculated color channels.
+ *
+ * This version calculates channels based on image data length, width, and height,
+ * as the `kind` property provided by PDF.js might not reliably indicate the actual
+ * channel count of the raw pixel data (e.g., returning RGBA data even when kind is 3).
+ *
+ * @example
+ * const imagesData = await extractImages(pdf, pageNum)
+ *
+ * for (const imgData of imagesData) {
+ *   const imageIndex = totalImagesProcessed + 1;
+ *   await sharp(imgData.data, {
+ *     raw: { width: imgData.width, height: imgData.height, channels: imgData.channels }
+ *   })
+ *     .png()
+ *     .toFile(`${imageIndex}.png`);
+ * }
+ */
+declare function extractImages$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, pageNumber: number): Promise<ExtractedImageObject[]>;
+declare function renderPageAsImage$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, pageNumber: number, options?: {
     canvas?: () => Promise<typeof canvas>;
     /** @default 1 */
     scale?: number;
@@ -45,6 +54,24 @@ declare function createIsomorphicCanvasFactory(canvas?: () => Promise<typeof can
     }): void;
 }>;
 
+declare function getMeta$1(data: DocumentInitParameters['data'] | PDFDocumentProxy): Promise<{
+    info: Record<string, any>;
+    metadata: Record<string, any>;
+}>;
+
+declare function extractText$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, options?: {
+    mergePages?: false;
+}): Promise<{
+    totalPages: number;
+    text: string[];
+}>;
+declare function extractText$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, options: {
+    mergePages: true;
+}): Promise<{
+    totalPages: number;
+    text: string;
+}>;
+
 type PDFJS = typeof _PDFJS;
 interface UnPDFConfiguration {
     /**
@@ -59,6 +86,8 @@ interface UnPDFConfiguration {
     pdfjs?: () => Promise<any>;
 }
 
+declare function configureUnPDF(options: UnPDFConfiguration): Promise<void>;
+
 /**
  * Returns a PDFDocumentProxy instance from a given binary data.
  *
@@ -66,14 +95,12 @@ interface UnPDFConfiguration {
  * - `isEvalSupported: false`
  * - `useSystemFonts: true`
  */
-declare function getDocumentProxy(data: DocumentInitParameters["data"], options?: DocumentInitParameters): Promise<PDFDocumentProxy>;
+declare function getDocumentProxy(data: DocumentInitParameters['data'], options?: DocumentInitParameters): Promise<PDFDocumentProxy>;
 declare function getResolvedPDFJS(): Promise<PDFJS>;
 declare function resolvePDFJSImports(pdfjsResolver?: () => Promise<any>, { force }?: {
     force?: boolean | undefined;
 }): Promise<void>;
 
-declare function configureUnPDF(options: UnPDFConfiguration): Promise<void>;
-
 declare const getMeta: typeof getMeta$1;
 declare const extractText: typeof extractText$1;
 declare const extractImages: typeof extractImages$1;

package/dist/index.d.ts

@@ -1,28 +1,37 @@
-import { DocumentInitParameters, PDFDocumentProxy } from './types/src/display/api';
 import * as canvas from 'canvas';
 import { Canvas } from 'canvas';
+import { DocumentInitParameters, PDFDocumentProxy } from './types/src/display/api';
 import * as _PDFJS from './types/src/pdf';
 
-declare function getMeta$1(data: DocumentInitParameters["data"] | PDFDocumentProxy): Promise<{
-    info: Record<string, any>;
-    metadata: Record<string, any>;
-}>;
-
-declare function extractText$1(data: DocumentInitParameters["data"] | PDFDocumentProxy, options?: {
-    mergePages?: false;
-}): Promise<{
-    totalPages: number;
-    text: string[];
-}>;
-declare function extractText$1(data: DocumentInitParameters["data"] | PDFDocumentProxy, options: {
-    mergePages: true;
-}): Promise<{
-    totalPages: number;
-    text: string;
-}>;
-
-declare function extractImages$1(data: DocumentInitParameters["data"] | PDFDocumentProxy, pageNumber: number): Promise<Uint8ClampedArray[]>;
-declare function renderPageAsImage$1(data: DocumentInitParameters["data"] | PDFDocumentProxy, pageNumber: number, options?: {
+interface ExtractedImageObject {
+    data: Uint8ClampedArray;
+    width: number;
+    height: number;
+    channels: 1 | 3 | 4;
+    key: string;
+}
+/**
+ * Extracts images from a specific page of a PDF document, including necessary metadata,
+ * such as width, height, and calculated color channels.
+ *
+ * This version calculates channels based on image data length, width, and height,
+ * as the `kind` property provided by PDF.js might not reliably indicate the actual
+ * channel count of the raw pixel data (e.g., returning RGBA data even when kind is 3).
+ *
+ * @example
+ * const imagesData = await extractImages(pdf, pageNum)
+ *
+ * for (const imgData of imagesData) {
+ *   const imageIndex = totalImagesProcessed + 1;
+ *   await sharp(imgData.data, {
+ *     raw: { width: imgData.width, height: imgData.height, channels: imgData.channels }
+ *   })
+ *     .png()
+ *     .toFile(`${imageIndex}.png`);
+ * }
+ */
+declare function extractImages$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, pageNumber: number): Promise<ExtractedImageObject[]>;
+declare function renderPageAsImage$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, pageNumber: number, options?: {
     canvas?: () => Promise<typeof canvas>;
     /** @default 1 */
     scale?: number;
@@ -45,6 +54,24 @@ declare function createIsomorphicCanvasFactory(canvas?: () => Promise<typeof can
     }): void;
 }>;
 
+declare function getMeta$1(data: DocumentInitParameters['data'] | PDFDocumentProxy): Promise<{
+    info: Record<string, any>;
+    metadata: Record<string, any>;
+}>;
+
+declare function extractText$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, options?: {
+    mergePages?: false;
+}): Promise<{
+    totalPages: number;
+    text: string[];
+}>;
+declare function extractText$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, options: {
+    mergePages: true;
+}): Promise<{
+    totalPages: number;
+    text: string;
+}>;
+
 type PDFJS = typeof _PDFJS;
 interface UnPDFConfiguration {
     /**
@@ -59,6 +86,8 @@ interface UnPDFConfiguration {
     pdfjs?: () => Promise<any>;
 }
 
+declare function configureUnPDF(options: UnPDFConfiguration): Promise<void>;
+
 /**
  * Returns a PDFDocumentProxy instance from a given binary data.
  *
@@ -66,14 +95,12 @@ interface UnPDFConfiguration {
  * - `isEvalSupported: false`
  * - `useSystemFonts: true`
  */
-declare function getDocumentProxy(data: DocumentInitParameters["data"], options?: DocumentInitParameters): Promise<PDFDocumentProxy>;
+declare function getDocumentProxy(data: DocumentInitParameters['data'], options?: DocumentInitParameters): Promise<PDFDocumentProxy>;
 declare function getResolvedPDFJS(): Promise<PDFJS>;
 declare function resolvePDFJSImports(pdfjsResolver?: () => Promise<any>, { force }?: {
     force?: boolean | undefined;
 }): Promise<void>;
 
-declare function configureUnPDF(options: UnPDFConfiguration): Promise<void>;
-
 declare const getMeta: typeof getMeta$1;
 declare const extractText: typeof extractText$1;
 declare const extractImages: typeof extractImages$1;

package/dist/index.mjs

@@ -31,19 +31,15 @@ async function resolvePDFJSImports(pdfjsResolver, { force = false } = {}) {
       return;
     } catch (error) {
       console.error(error);
-      throw new Error(
-        "Resolving failed. Please check the provided configuration."
-      );
+      throw new Error("Resolving failed. Please check the provided configuration.");
     }
   }
   try {
-    const { resolvePDFJS } = await Promise.resolve().then(function () { return pdfjs; });
+    const { resolvePDFJS } = await import('unpdf/pdfjs');
     resolvedModule = await resolvePDFJS();
   } catch (error) {
     console.error(error);
-    throw new Error(
-      "PDF.js is not available. Please add the package as a dependency."
-    );
+    throw new Error("PDF.js is not available. Please add the package as a dependency.");
   }
 }
 function isPDFDocumentProxy(data) {
@@ -54,40 +50,12 @@ async function interopDefault(m) {
   return resolved.default || resolved;
 }
 
-async function getMeta$1(data) {
-  const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
-  const meta = await pdf.getMetadata();
-  return {
-    info: meta?.info ?? {},
-    metadata: meta?.metadata?.getAll() ?? {}
-  };
-}
-
-async function extractText$1(data, options = {}) {
-  const { mergePages = false } = { ...options };
-  const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
-  const texts = await Promise.all(
-    Array.from({ length: pdf.numPages }, (_, i) => getPageText(pdf, i + 1))
-  );
-  return {
-    totalPages: pdf.numPages,
-    text: mergePages ? texts.join("\n").replace(/\s+/g, " ") : texts
-  };
-}
-async function getPageText(document, pageNumber) {
-  const page = await document.getPage(pageNumber);
-  const content = await page.getTextContent();
-  return content.items.filter((item) => item.str != null).map((item) => item.str + (item.hasEOL ? "\n" : "")).join("");
-}
-
 async function extractImages$1(data, pageNumber) {
   const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
-  const page = await pdf.getPage(pageNumber);
   if (pageNumber < 1 || pageNumber > pdf.numPages) {
-    throw new Error(
-      `Invalid page number. Must be between 1 and ${pdf.numPages}.`
-    );
+    throw new Error(`Invalid page number. Must be between 1 and ${pdf.numPages}.`);
   }
+  const page = await pdf.getPage(pageNumber);
   const operatorList = await page.getOperatorList();
   const { OPS } = await getResolvedPDFJS();
   const images = [];
@@ -98,7 +66,22 @@ async function extractImages$1(data, pageNumber) {
     }
     const imageKey = operatorList.argsArray[i][0];
     const image = await page.objs.get(imageKey);
-    images.push(image.data);
+    if (!image || !image.data || !image.width || !image.height) {
+      continue;
+    }
+    const { width, height, data: data2 } = image;
+    const calculatedChannels = data2.length / (width * height);
+    if (![1, 3, 4].includes(calculatedChannels)) {
+      continue;
+    }
+    const channels = calculatedChannels;
+    images.push({
+      data: data2,
+      width,
+      height,
+      channels,
+      key: imageKey
+    });
   }
   return images;
 }
@@ -107,9 +90,7 @@ async function renderPageAsImage$1(data, pageNumber, options = {}) {
   const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data, { canvasFactory });
   const page = await pdf.getPage(pageNumber);
   if (pageNumber < 1 || pageNumber > pdf.numPages) {
-    throw new Error(
-      `Invalid page number. Must be between 1 and ${pdf.numPages}.`
-    );
+    throw new Error(`Invalid page number. Must be between 1 and ${pdf.numPages}.`);
   }
   let outputScale = options.scale || 1;
   let viewport = page.getViewport({ scale: outputScale });
@@ -175,6 +156,32 @@ async function createIsomorphicCanvasFactory(canvas) {
   };
 }
 
+async function getMeta$1(data) {
+  const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
+  const meta = await pdf.getMetadata();
+  return {
+    info: meta?.info ?? {},
+    metadata: meta?.metadata?.getAll() ?? {}
+  };
+}
+
+async function extractText$1(data, options = {}) {
+  const { mergePages = false } = { ...options };
+  const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
+  const texts = await Promise.all(
+    Array.from({ length: pdf.numPages }, (_, i) => getPageText(pdf, i + 1))
+  );
+  return {
+    totalPages: pdf.numPages,
+    text: mergePages ? texts.join("\n").replace(/\s+/g, " ") : texts
+  };
+}
+async function getPageText(document, pageNumber) {
+  const page = await document.getPage(pageNumber);
+  const content = await page.getTextContent();
+  return content.items.filter((item) => item.str != null).map((item) => item.str + (item.hasEOL ? "\n" : "")).join("");
+}
+
 async function configureUnPDF(options) {
   const { pdfjs } = { ...options };
   if (pdfjs) {
@@ -199,8 +206,4 @@ const renderPageAsImage = async (...args) => {
   return await renderPageAsImage$1(...args);
 };
 
-const pdfjs = {
-  __proto__: null
-};
-
 export { configureUnPDF, createIsomorphicCanvasFactory, extractImages, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImports };

package/package.json

@@ -1,8 +1,8 @@
 {
   "name": "unpdf",
   "type": "module",
-  "version": "0.12.0",
-  "packageManager": "pnpm@9.11.0",
+  "version": "0.12.2",
+  "packageManager": "pnpm@9.12.1",
   "description": "Utilities to work with PDFs in Node.js, browser and workers",
   "author": "Johann Schopplich <hello@johannschopplich.com>",
   "license": "MIT",
@@ -56,9 +56,7 @@
     "build:pdfjs": "rollup --config pdfjs.rollup.config.ts --configPlugin typescript && cp -R node_modules/pdfjs-dist/types dist",
     "dev": "unbuild --stub",
     "lint": "eslint .",
-    "lint:fix": "npm run lint -- --fix",
-    "format": "prettier \"**/*.{json,md,cjs,mjs,ts,yml}\" --write",
-    "format:check": "prettier \"**/*.{json,md,cjs,mjs,ts,yml}\" --check",
+    "lint:fix": "eslint . --fix",
     "release": "bumpp",
     "test": "vitest",
     "test:types": "tsc --noEmit"
@@ -67,6 +65,7 @@
     "canvas": "^2.11.2"
   },
   "devDependencies": {
+    "@antfu/eslint-config": "^3.7.3",
     "@rollup/plugin-alias": "^5.1.1",
     "@rollup/plugin-commonjs": "^28.0.0",
     "@rollup/plugin-inject": "^5.0.5",
@@ -74,19 +73,17 @@
     "@rollup/plugin-replace": "^6.0.1",
     "@rollup/plugin-terser": "^0.4.4",
     "@rollup/plugin-typescript": "^12.1.0",
-    "@types/node": "^20.16.10",
+    "@types/node": "^20.16.11",
     "bumpp": "^9.6.1",
-    "eslint": "^9.11.1",
-    "eslint-config-unjs": "^0.4.1",
+    "eslint": "^9.12.0",
     "fast-glob": "^3.3.2",
-    "pdfjs-dist": "^4.6.82",
-    "prettier": "^3.3.3",
-    "rollup": "^4.22.5",
+    "pdfjs-dist": "~4.6.82",
+    "rollup": "^4.24.0",
     "tslib": "^2.7.0",
     "typescript": "^5.5.4",
-    "unbuild": "^3.0.0-rc.8",
+    "unbuild": "^3.0.0-rc.11",
     "unenv": "^1.10.0",
-    "vitest": "^2.1.1"
+    "vitest": "^2.1.2"
   },
   "pnpm": {
     "patchedDependencies": {