unpdf 1.6.1 → 1.7.0

package/README.md

@@ -7,7 +7,7 @@ Ships with a serverless build of Mozilla's [PDF.js](https://github.com/mozilla/p
 ## Features
 
 - 🏗️ Works in Node.js, browser and serverless environments
-- 🪭 Includes serverless build of PDF.js ([`unpdf/pdfjs`](./package.json#L34))
+- 🪭 Includes serverless build of PDF.js ([`unpdf/pdfjs`](./package.json))
 - 💬 Extract [text](#extract-text-from-pdf), [links](#extractlinks), and [images](#extractimages) from PDF files
 - 🧠 Perfect for AI applications and PDF summarization
 - 🧱 Opt-in to official or legacy PDF.js build
@@ -97,7 +97,7 @@ Heart and soul of this package is the [`pdfjs.rollup.config.ts`](./pdfjs.rollup.
 
 - **String replacements** strip browser-specific references from the PDF.js source.
 - **Worker inlining** embeds the PDF.js worker directly into the main bundle, since serverless runtimes can't load separate worker files.
-- **Global polyfills** provide missing APIs like `FinalizationRegistry` (unavailable in Cloudflare Workers).
+- **Global polyfills** provide missing APIs like `Promise.withResolvers` and `FinalizationRegistry` (unavailable in Node.js < 22 and Cloudflare Workers, respectively).
 
 ## API
 
@@ -121,6 +121,21 @@ Returns the resolved PDF.js module. If no other PDF.js build was defined, the se
 function getResolvedPDFJS(): Promise<PDFJS>
 ```
 
+### `getDocumentProxy`
+
+Creates a `PDFDocumentProxy` from binary PDF data. Every extraction method accepts either raw data or an existing proxy – use this when you want to reuse one document across multiple calls.
+
+Applies sensible defaults: `isEvalSupported: false` and `useSystemFonts: true`; in Node.js additionally `disableFontFace: true`, plus `standardFontDataUrl` and `cMapUrl`/`cMapPacked` resolved from the local `pdfjs-dist` package for standard font and CJK character map support (see the font rendering tip in [`renderPageAsImage`](#renderpageasimage)).
+
+**Type Declaration**
+
+```ts
+function getDocumentProxy(
+  data: DocumentInitParameters['data'],
+  options?: DocumentInitParameters,
+): Promise<PDFDocumentProxy>
+```
+
 ### `getMeta`
 
 Extracts metadata from a PDF. If `parseDates` is set to `true`, the date properties will be parsed into `Date` objects.
@@ -141,7 +156,7 @@ function getMeta(
 
 ### `extractText`
 
-Extracts all text from a PDF. If `mergePages` is set to `true`, the text of all pages will be merged into a single string. Otherwise, an array of strings for each page will be returned.
+Extracts all text from a PDF. If `mergePages` is set to `true`, the text of all pages will be merged into a single string with line breaks preserved and at most one blank line in a row. Otherwise, an array of strings for each page will be returned.
 
 **Type Declaration**
 
@@ -149,20 +164,42 @@ Extracts all text from a PDF. If `mergePages` is set to `true`, the text of all
 function extractText(
   data: DocumentInitParameters['data'] | PDFDocumentProxy,
   options?: {
-    mergePages?: false
+    mergePages?: boolean
   }
 ): Promise<{
   totalPages: number
-  text: string[]
+  text: string | string[]
 }>
-function extractText(
+```
+
+### `extractTextItems`
+
+Extracts text with layout information – one array of positioned items per page. Useful when plain text is not enough and you need coordinates, font sizes, or reading direction, e.g. for table detection or positional parsing.
+
+**Type Declaration**
+
+```ts
+interface StructuredTextItem {
+  str: string
+  /** X position in PDF coordinate space (origin: bottom-left). */
+  x: number
+  /** Y position in PDF coordinate space (origin: bottom-left). */
+  y: number
+  width: number
+  height: number
+  fontSize: number
+  fontFamily: string
+  /** Text direction: `"ltr"`, `"rtl"`, or `"ttb"`. */
+  dir: string
+  /** Whether the text item is followed by a line break. */
+  hasEOL: boolean
+}
+
+function extractTextItems(
   data: DocumentInitParameters['data'] | PDFDocumentProxy,
-  options: {
-    mergePages: true
-  }
 ): Promise<{
   totalPages: number
-  text: string
+  items: StructuredTextItem[][]
 }>
 ```
 
@@ -294,26 +331,15 @@ function renderPageAsImage(
     scale?: number
     width?: number
     height?: number
-    toDataURL?: false
+    toDataURL?: boolean
   },
-): Promise<ArrayBuffer>
-function renderPageAsImage(
-  data: DocumentInitParameters['data'] | PDFDocumentProxy,
-  pageNumber: number,
-  options: {
-    canvasImport?: () => Promise<typeof import('@napi-rs/canvas')>
-    /** @default 1.0 */
-    scale?: number
-    width?: number
-    height?: number
-    toDataURL: true
-  },
-): Promise<string>
+): Promise<ArrayBuffer | string>
 ```
 
 **Examples**
 
 ```ts
+import { readFile, writeFile } from 'node:fs/promises'
 import { definePDFJSModule, renderPageAsImage } from 'unpdf'
 
 // Use the official PDF.js build
@@ -331,6 +357,7 @@ await writeFile('dummy-page-1.png', new Uint8Array(result))
 ```
 
 ```ts
+import { readFile, writeFile } from 'node:fs/promises'
 import { definePDFJSModule, renderPageAsImage } from 'unpdf'
 
 await definePDFJSModule(() => import('pdfjs-dist'))
@@ -360,6 +387,15 @@ const html = `<!DOCTYPE html>
 await writeFile('dummy-page-1.html', html)
 ```
 
+## Processing Untrusted PDFs
+
+The `getDocumentProxy` defaults are safe against script execution (`isEvalSupported: false`), but resource limits are your job:
+
+- **Image decoding:** `maxImageSize` is unlimited by default – pass e.g. `maxImageSize: 16_777_216` (~16 MP) so a single declared image can't allocate gigabytes.
+- **Page fan-out:** `extractText`, `extractTextItems`, and `extractLinks` process all pages in one call – check `pdf.numPages` against a limit first.
+- **Timeouts:** with the serverless build, parsing runs on your event loop (no worker) – race extraction calls against a timeout.
+- The raw `getDocument` from `unpdf/pdfjs` applies none of these defaults.
+
 ## License
 
 [MIT](./LICENSE) License © 2023-PRESENT [Johann Schopplich](https://github.com/johannschopplich)

package/dist/index.cjs

@@ -57,7 +57,9 @@ async function getDocumentProxy(data, options = {}) {
       const base = undefined("pdfjs-dist/package.json");
       nodeDefaults = {
         disableFontFace: true,
-        standardFontDataUrl: new URL("./standard_fonts/", base).href
+        standardFontDataUrl: new URL("./standard_fonts/", base).href,
+        cMapUrl: new URL("./cmaps/", base).href,
+        cMapPacked: true
       };
     } catch {
     }
@@ -72,6 +74,15 @@ async function getDocumentProxy(data, options = {}) {
   }).promise;
   return pdf;
 }
+async function withDocument(data, operation, options) {
+  const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data, options);
+  try {
+    return await operation(pdf);
+  } finally {
+    if (pdf !== data)
+      await pdf.destroy();
+  }
+}
 async function getResolvedPDFJS() {
   if (!resolvedModule) {
     await resolvePDFJSImport();
@@ -177,6 +188,7 @@ class NodeCanvasFactory extends BaseCanvasFactory {
 }
 async function resolveCanvasModule(canvasImport) {
   resolvedCanvasModule ??= await interopDefault(canvasImport());
+  globalThis[Symbol.for("unpdf.canvasModule")] = resolvedCanvasModule;
 }
 function injectCanvasConstructors() {
   if (!resolvedCanvasModule)
@@ -189,69 +201,85 @@ function injectCanvasConstructors() {
 }
 
 async function extractImages$1(data, pageNumber) {
-  const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
-  if (pageNumber < 1 || pageNumber > 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 = [];
-  for (let i = 0; i < operatorList.fnArray.length; i++) {
-    const op = operatorList.fnArray[i];
-    if (op !== OPS.paintImageXObject) {
-      continue;
-    }
-    const imageKey = operatorList.argsArray[i][0];
-    const image = await new Promise(
-      (resolve) => (imageKey.startsWith("g_") ? page.commonObjs : page.objs).get(imageKey, resolve)
-    );
-    if (!image || !image.data || !image.width || !image.height) {
-      continue;
+  return await withDocument(data, async (pdf) => {
+    if (pageNumber < 1 || pageNumber > pdf.numPages) {
+      throw new Error(`Invalid page number. Must be between 1 and ${pdf.numPages}.`);
     }
-    const { width, height, data: data2 } = image;
-    const calculatedChannels = data2.length / (width * height);
-    if (![1, 3, 4].includes(calculatedChannels)) {
-      continue;
+    const page = await pdf.getPage(pageNumber);
+    const operatorList = await page.getOperatorList();
+    const { OPS } = await getResolvedPDFJS();
+    const images = [];
+    for (let i = 0; i < operatorList.fnArray.length; i++) {
+      const op = operatorList.fnArray[i];
+      if (op !== OPS.paintImageXObject) {
+        continue;
+      }
+      const imageKey = operatorList.argsArray[i][0];
+      const image = await new Promise(
+        (resolve) => (imageKey.startsWith("g_") ? page.commonObjs : page.objs).get(imageKey, resolve)
+      );
+      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
+      });
     }
-    const channels = calculatedChannels;
-    images.push({
-      data: data2,
-      width,
-      height,
-      channels,
-      key: imageKey
-    });
-  }
-  return images;
+    return images;
+  });
 }
 async function renderPageAsImage$1(data, pageNumber, options = {}) {
   const CanvasFactory = await createIsomorphicCanvasFactory(options.canvasImport);
-  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}.`);
-  }
-  const defaultViewport = page.getViewport({ scale: 1 });
-  let scale = options.scale || 1;
-  if (options.width) {
-    scale = options.width / defaultViewport.width;
-  } else if (options.height) {
-    scale = options.height / defaultViewport.height;
-  }
-  const viewport = page.getViewport({ scale: Math.max(0, scale) });
-  const drawingContext = new CanvasFactory().create(viewport.width, viewport.height);
-  await page.render({
-    canvas: drawingContext.canvas,
-    canvasContext: drawingContext.context,
-    viewport
-  }).promise;
-  const dataUrl = drawingContext.canvas.toDataURL();
-  if (options.toDataURL) {
-    return dataUrl;
-  }
-  const response = await fetch(dataUrl);
-  return await response.arrayBuffer();
+  return await withDocument(data, async (pdf) => {
+    if (pageNumber < 1 || pageNumber > pdf.numPages) {
+      throw new Error(`Invalid page number. Must be between 1 and ${pdf.numPages}.`);
+    }
+    const page = await pdf.getPage(pageNumber);
+    const defaultViewport = page.getViewport({ scale: 1 });
+    let scale = options.scale || 1;
+    if (options.width) {
+      scale = options.width / defaultViewport.width;
+    } else if (options.height) {
+      scale = options.height / defaultViewport.height;
+    }
+    const viewport = page.getViewport({ scale: Math.max(0, scale) });
+    const canvasFactory = new CanvasFactory();
+    const drawingContext = canvasFactory.create(viewport.width, viewport.height);
+    try {
+      await page.render({
+        canvas: drawingContext.canvas,
+        canvasContext: drawingContext.context,
+        viewport
+      }).promise;
+      const { canvas } = drawingContext;
+      if (options.toDataURL) {
+        return canvas.toDataURL();
+      }
+      if ("encode" in canvas) {
+        const buffer = await canvas.encode("png");
+        return buffer.buffer.slice(buffer.byteOffset, buffer.byteOffset + buffer.byteLength);
+      }
+      const blob = await new Promise((resolve) => {
+        canvas.toBlob(resolve);
+      });
+      if (!blob) {
+        throw new Error("Failed to encode canvas to a PNG blob.");
+      }
+      return await blob.arrayBuffer();
+    } finally {
+      canvasFactory.destroy(drawingContext);
+    }
+  }, { CanvasFactory });
 }
 async function createIsomorphicCanvasFactory(canvasImport) {
   if (isBrowser)
@@ -268,14 +296,15 @@ async function createIsomorphicCanvasFactory(canvasImport) {
 }
 
 async function extractLinks$1(data) {
-  const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
-  const pageLinks = await Promise.all(
-    Array.from({ length: pdf.numPages }, (_, i) => getPageLinks(pdf, i + 1))
-  );
-  return {
-    totalPages: pdf.numPages,
-    links: pageLinks.flat()
-  };
+  return await withDocument(data, async (pdf) => {
+    const pageLinks = await Promise.all(
+      Array.from({ length: pdf.numPages }, (_, i) => getPageLinks(pdf, i + 1))
+    );
+    return {
+      totalPages: pdf.numPages,
+      links: pageLinks.flat()
+    };
+  });
 }
 async function getPageLinks(document, pageNumber) {
   const page = await document.getPage(pageNumber);
@@ -298,38 +327,39 @@ const XMP_DATE_PROPERTIES = [
   "xap:metadatadate"
 ];
 async function getMeta$1(data, options = {}) {
-  const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
-  const meta = await pdf.getMetadata();
-  const info = meta?.info || {};
-  if (options.parseDates) {
-    const { PDFDateString } = await getResolvedPDFJS();
-    if (info?.CreationDate) {
-      info.CreationDate = PDFDateString.toDateObject(info?.CreationDate);
-    }
-    if (info?.ModDate) {
-      info.ModDate = PDFDateString.toDateObject(info?.ModDate);
-    }
-    if (meta.metadata) {
-      meta.metadata = new Proxy(meta.metadata, {
-        get(target, prop) {
-          if (prop === "get") {
-            return (name) => {
-              const value = target.get(name);
-              if (XMP_DATE_PROPERTIES.includes(name) && value) {
-                return parseISODateString(value);
-              }
-              return value;
-            };
+  return await withDocument(data, async (pdf) => {
+    const meta = await pdf.getMetadata();
+    const info = meta?.info || {};
+    if (options.parseDates) {
+      const { PDFDateString } = await getResolvedPDFJS();
+      if (info?.CreationDate) {
+        info.CreationDate = PDFDateString.toDateObject(info?.CreationDate);
+      }
+      if (info?.ModDate) {
+        info.ModDate = PDFDateString.toDateObject(info?.ModDate);
+      }
+      if (meta.metadata) {
+        meta.metadata = new Proxy(meta.metadata, {
+          get(target, prop) {
+            if (prop === "get") {
+              return (name) => {
+                const value = target.get(name);
+                if (XMP_DATE_PROPERTIES.includes(name) && value) {
+                  return parseISODateString(value);
+                }
+                return value;
+              };
+            }
+            return target[prop];
           }
-          return target[prop];
-        }
-      });
+        });
+      }
     }
-  }
-  return {
-    info,
-    metadata: meta?.metadata || {}
-  };
+    return {
+      info,
+      metadata: meta?.metadata || {}
+    };
+  });
 }
 function parseISODateString(isoDateString) {
   if (!isoDateString)
@@ -341,11 +371,12 @@ function parseISODateString(isoDateString) {
 }
 
 async function extractTextItems$1(data) {
-  const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
-  const items = await Promise.all(
-    Array.from({ length: pdf.numPages }, (_, i) => getPageTextItems(pdf, i + 1))
-  );
-  return { totalPages: pdf.numPages, items };
+  return await withDocument(data, async (pdf) => {
+    const items = await Promise.all(
+      Array.from({ length: pdf.numPages }, (_, i) => getPageTextItems(pdf, i + 1))
+    );
+    return { totalPages: pdf.numPages, items };
+  });
 }
 async function getPageTextItems(document, pageNumber) {
   const page = await document.getPage(pageNumber);
@@ -368,20 +399,24 @@ async function getPageTextItems(document, pageNumber) {
 }
 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
-  };
+  return await withDocument(data, async (pdf) => {
+    const texts = await Promise.all(
+      Array.from({ length: pdf.numPages }, (_, i) => getPageText(pdf, i + 1))
+    );
+    return {
+      totalPages: pdf.numPages,
+      text: mergePages ? normalizeMergedText(texts) : 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("");
 }
+function normalizeMergedText(texts) {
+  return texts.join("\n").replace(/[^\S\n]+/g, " ").replace(/ ?\n ?/g, "\n").replace(/\n{3,}/g, "\n\n");
+}
 
 async function definePDFJSModule(pdfjs) {
   await resolvePDFJSImport(pdfjs, { reload: true });

package/dist/index.d.cts

@@ -1,12 +1,12 @@
 import * as _napi_rs_canvas from '@napi-rs/canvas';
-import { Canvas, CanvasRenderingContext2D } from '@napi-rs/canvas';
-import { DocumentInitParameters, PDFDocumentProxy } from './types/src/display/api';
-import * as pdfjs_dist_types_src_display_metadata from './types/src/display/metadata';
-import * as PDFJS from './types/src/pdf';
+import { Canvas, SKRSContext2D } from '@napi-rs/canvas';
+import { DocumentInitParameters, PDFDocumentProxy } from './types/src/display/api.js';
+import * as pdfjs_dist_types_src_display_metadata from './types/src/display/metadata.js';
+import * as PDFJS from './types/src/pdf.js';
 
 interface CanvasFactoryContext {
     canvas?: HTMLCanvasElement | Canvas;
-    context?: CanvasRenderingContext2D | CanvasRenderingContext2D;
+    context?: CanvasRenderingContext2D | SKRSContext2D | null;
 }
 /**
  * Derived from the PDF.js project by the Mozilla Foundation.
@@ -20,7 +20,7 @@ declare class BaseCanvasFactory {
     });
     create(width: number, height: number): {
         canvas: Canvas | HTMLCanvasElement;
-        context: _napi_rs_canvas.SKRSContext2D | globalThis.CanvasRenderingContext2D | null;
+        context: SKRSContext2D | CanvasRenderingContext2D | null;
     };
     reset({ canvas }: CanvasFactoryContext, width: number, height: number): void;
     destroy(context: CanvasFactoryContext): void;
@@ -136,6 +136,12 @@ declare function extractText$1(data: DocumentInitParameters['data'] | PDFDocumen
     totalPages: number;
     text: string;
 }>;
+declare function extractText$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, options?: {
+    mergePages?: boolean;
+}): Promise<{
+    totalPages: number;
+    text: string | string[];
+}>;
 
 /**
  * By default, unpdf will use the latest version of PDF.js compiled for
@@ -164,6 +170,7 @@ declare function configureUnPDF(options: {
  * In Node.js environments, additionally applies:
  * - `disableFontFace: true`
  * - `standardFontDataUrl` resolved from the local `pdfjs-dist` package
+ * - `cMapUrl` and `cMapPacked` resolved from the local `pdfjs-dist` package
  */
 declare function getDocumentProxy(data: DocumentInitParameters['data'], options?: DocumentInitParameters): Promise<PDFDocumentProxy>;
 declare function getResolvedPDFJS(): Promise<typeof PDFJS>;

package/dist/index.d.mts

@@ -1,12 +1,12 @@
 import * as _napi_rs_canvas from '@napi-rs/canvas';
-import { Canvas, CanvasRenderingContext2D } from '@napi-rs/canvas';
-import { DocumentInitParameters, PDFDocumentProxy } from './types/src/display/api';
-import * as pdfjs_dist_types_src_display_metadata from './types/src/display/metadata';
-import * as PDFJS from './types/src/pdf';
+import { Canvas, SKRSContext2D } from '@napi-rs/canvas';
+import { DocumentInitParameters, PDFDocumentProxy } from './types/src/display/api.js';
+import * as pdfjs_dist_types_src_display_metadata from './types/src/display/metadata.js';
+import * as PDFJS from './types/src/pdf.js';
 
 interface CanvasFactoryContext {
     canvas?: HTMLCanvasElement | Canvas;
-    context?: CanvasRenderingContext2D | CanvasRenderingContext2D;
+    context?: CanvasRenderingContext2D | SKRSContext2D | null;
 }
 /**
  * Derived from the PDF.js project by the Mozilla Foundation.
@@ -20,7 +20,7 @@ declare class BaseCanvasFactory {
     });
     create(width: number, height: number): {
         canvas: Canvas | HTMLCanvasElement;
-        context: _napi_rs_canvas.SKRSContext2D | globalThis.CanvasRenderingContext2D | null;
+        context: SKRSContext2D | CanvasRenderingContext2D | null;
     };
     reset({ canvas }: CanvasFactoryContext, width: number, height: number): void;
     destroy(context: CanvasFactoryContext): void;
@@ -136,6 +136,12 @@ declare function extractText$1(data: DocumentInitParameters['data'] | PDFDocumen
     totalPages: number;
     text: string;
 }>;
+declare function extractText$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, options?: {
+    mergePages?: boolean;
+}): Promise<{
+    totalPages: number;
+    text: string | string[];
+}>;
 
 /**
  * By default, unpdf will use the latest version of PDF.js compiled for
@@ -164,6 +170,7 @@ declare function configureUnPDF(options: {
  * In Node.js environments, additionally applies:
  * - `disableFontFace: true`
  * - `standardFontDataUrl` resolved from the local `pdfjs-dist` package
+ * - `cMapUrl` and `cMapPacked` resolved from the local `pdfjs-dist` package
  */
 declare function getDocumentProxy(data: DocumentInitParameters['data'], options?: DocumentInitParameters): Promise<PDFDocumentProxy>;
 declare function getResolvedPDFJS(): Promise<typeof PDFJS>;

package/dist/index.d.ts

@@ -1,12 +1,12 @@
 import * as _napi_rs_canvas from '@napi-rs/canvas';
-import { Canvas, CanvasRenderingContext2D } from '@napi-rs/canvas';
-import { DocumentInitParameters, PDFDocumentProxy } from './types/src/display/api';
-import * as pdfjs_dist_types_src_display_metadata from './types/src/display/metadata';
-import * as PDFJS from './types/src/pdf';
+import { Canvas, SKRSContext2D } from '@napi-rs/canvas';
+import { DocumentInitParameters, PDFDocumentProxy } from './types/src/display/api.js';
+import * as pdfjs_dist_types_src_display_metadata from './types/src/display/metadata.js';
+import * as PDFJS from './types/src/pdf.js';
 
 interface CanvasFactoryContext {
     canvas?: HTMLCanvasElement | Canvas;
-    context?: CanvasRenderingContext2D | CanvasRenderingContext2D;
+    context?: CanvasRenderingContext2D | SKRSContext2D | null;
 }
 /**
  * Derived from the PDF.js project by the Mozilla Foundation.
@@ -20,7 +20,7 @@ declare class BaseCanvasFactory {
     });
     create(width: number, height: number): {
         canvas: Canvas | HTMLCanvasElement;
-        context: _napi_rs_canvas.SKRSContext2D | globalThis.CanvasRenderingContext2D | null;
+        context: SKRSContext2D | CanvasRenderingContext2D | null;
     };
     reset({ canvas }: CanvasFactoryContext, width: number, height: number): void;
     destroy(context: CanvasFactoryContext): void;
@@ -136,6 +136,12 @@ declare function extractText$1(data: DocumentInitParameters['data'] | PDFDocumen
     totalPages: number;
     text: string;
 }>;
+declare function extractText$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, options?: {
+    mergePages?: boolean;
+}): Promise<{
+    totalPages: number;
+    text: string | string[];
+}>;
 
 /**
  * By default, unpdf will use the latest version of PDF.js compiled for
@@ -164,6 +170,7 @@ declare function configureUnPDF(options: {
  * In Node.js environments, additionally applies:
  * - `disableFontFace: true`
  * - `standardFontDataUrl` resolved from the local `pdfjs-dist` package
+ * - `cMapUrl` and `cMapPacked` resolved from the local `pdfjs-dist` package
  */
 declare function getDocumentProxy(data: DocumentInitParameters['data'], options?: DocumentInitParameters): Promise<PDFDocumentProxy>;
 declare function getResolvedPDFJS(): Promise<typeof PDFJS>;