first commit

examples/node/getinfo.mjs

@@ -0,0 +1,76 @@
+/* Any copyright is dedicated to the Public Domain.
+ * http://creativecommons.org/publicdomain/zero/1.0/ */
+
+//
+// Basic node example that prints document metadata and text content.
+//
+
+// Run `gulp dist-install` to generate 'pdfjs-dist' npm package files.
+import { getDocument } from "pdfjs-dist/legacy/build/pdf.mjs";
+
+// Loading file from file system into typed array
+const pdfPath =
+  process.argv[2] || "../../web/compressed.tracemonkey-pldi-09.pdf";
+
+// Will be using promises to load document, pages and misc data instead of
+// callback.
+const loadingTask = getDocument(pdfPath);
+loadingTask.promise
+  .then(function (doc) {
+    const numPages = doc.numPages;
+    console.log("# Document Loaded");
+    console.log("Number of Pages: " + numPages);
+    console.log();
+
+    let lastPromise; // will be used to chain promises
+    lastPromise = doc.getMetadata().then(function (data) {
+      console.log("# Metadata Is Loaded");
+      console.log("## Info");
+      console.log(JSON.stringify(data.info, null, 2));
+      console.log();
+      if (data.metadata) {
+        console.log("## Metadata");
+        console.log(JSON.stringify(data.metadata.getAll(), null, 2));
+        console.log();
+      }
+    });
+
+    const loadPage = function (pageNum) {
+      return doc.getPage(pageNum).then(function (page) {
+        console.log("# Page " + pageNum);
+        const viewport = page.getViewport({ scale: 1.0 });
+        console.log("Size: " + viewport.width + "x" + viewport.height);
+        console.log();
+        return page
+          .getTextContent()
+          .then(function (content) {
+            // Content contains lots of information about the text layout and
+            // styles, but we need only strings at the moment
+            const strings = content.items.map(function (item) {
+              return item.str;
+            });
+            console.log("## Text Content");
+            console.log(strings.join(" "));
+            // Release page resources.
+            page.cleanup();
+          })
+          .then(function () {
+            console.log();
+          });
+      });
+    };
+    // Loading of the first page will wait on metadata and subsequent loadings
+    // will wait on the previous pages.
+    for (let i = 1; i <= numPages; i++) {
+      lastPromise = lastPromise.then(loadPage.bind(null, i));
+    }
+    return lastPromise;
+  })
+  .then(
+    function () {
+      console.log("# End of Document");
+    },
+    function (err) {
+      console.error("Error: " + err);
+    }
+  );

examples/node/pdf2png/README.md

@@ -0,0 +1,15 @@
+## Overview
+
+Example to demonstrate converting a PDF file to a PNG image using the PDF.js library.
+
+## Getting started
+
+Install the dependencies and build the PDF.js library:
+
+    $ npm install
+    $ gulp dist-install
+
+Run the example to convert the first page of a PDF file to a PNG image:
+
+    $ cd examples/node/pdf2png
+    $ node pdf2png.mjs

examples/node/pdf2png/pdf2png.mjs

@@ -0,0 +1,72 @@
+/* Copyright 2017 Mozilla Foundation
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import fs from "fs";
+import { getDocument } from "pdfjs-dist/legacy/build/pdf.mjs";
+
+// Some PDFs need external cmaps.
+const CMAP_URL = "../../../node_modules/pdfjs-dist/cmaps/";
+const CMAP_PACKED = true;
+
+// Where the standard fonts are located.
+const STANDARD_FONT_DATA_URL =
+  "../../../node_modules/pdfjs-dist/standard_fonts/";
+
+// Loading file from file system into typed array.
+const pdfPath =
+  process.argv[2] || "../../../web/compressed.tracemonkey-pldi-09.pdf";
+const data = new Uint8Array(fs.readFileSync(pdfPath));
+
+// Load the PDF file.
+const loadingTask = getDocument({
+  data,
+  cMapUrl: CMAP_URL,
+  cMapPacked: CMAP_PACKED,
+  standardFontDataUrl: STANDARD_FONT_DATA_URL,
+});
+
+try {
+  const pdfDocument = await loadingTask.promise;
+  console.log("# PDF document loaded.");
+  // Get the first page.
+  const page = await pdfDocument.getPage(1);
+  // Render the page on a Node canvas with 100% scale.
+  const canvasFactory = pdfDocument.canvasFactory;
+  const viewport = page.getViewport({ scale: 1.0 });
+  const canvasAndContext = canvasFactory.create(
+    viewport.width,
+    viewport.height
+  );
+  const renderContext = {
+    canvasContext: canvasAndContext.context,
+    viewport,
+  };
+
+  const renderTask = page.render(renderContext);
+  await renderTask.promise;
+  // Convert the canvas to an image buffer.
+  const image = canvasAndContext.canvas.toBuffer("image/png");
+  fs.writeFile("output.png", image, function (error) {
+    if (error) {
+      console.error("Error: " + error);
+    } else {
+      console.log("Finished converting first page of PDF file to a PNG image.");
+    }
+  });
+  // Release page resources.
+  page.cleanup();
+} catch (reason) {
+  console.log(reason);
+}