Merge branch 'master' into issue-1090

Makefile

@@ -36,6 +36,7 @@ PDF_JS_FILES = \
   stream.js \
   worker.js \
   ../external/jpgjs/jpg.js \
+  jpx.js \
 	$(NULL)
 
 # make server

README.md

@@ -1,9 +1,6 @@
-# pdf.js
+# PDF.JS
 
 
-
-## Overview
-
 pdf.js is an HTML5 technology experiment that explores building a faithful
 and efficient Portable Document Format (PDF) renderer without native code 
 assistance.
@@ -16,7 +13,7 @@ successful.
 
 
 
-## Getting started
+# Getting started
 
 ### Online demo
 
@@ -29,11 +26,12 @@ using the pdf.js API.
 
 ### Extension
 
-An up-to-date Firefox extension is also available:
+A Firefox extension is also available:
 
 + http://mozilla.github.com/pdf.js/extensions/firefox/pdf.js.xpi
 
-(The above link is updated upon every merge to our master branch).
+Note that this extension is self-updating, and by default Firefox will auto-update extensions on a 
+daily basis (you can change this through the `extensions.update.interval` option in `about:config`).
 
 For an experimental Chrome extension, get the code as explained below and issue `make extension`. 
 Then open Chrome with the flag `--enable-experimental-extension-apis`, go to `Tools > Extension`
@@ -68,12 +66,12 @@ In order to bundle all `src/` files into a final `pdf.js`, issue:
 This will generate the file `build/pdf.js` that can be included in your final project. (WARNING: That's a large file! Consider minifying it).
 
 
-## Learning
+# Learning
 
 Here are some initial pointers to help contributors get off the ground. 
 Additional resources are available in a separate section below.
 
-#### Hello world
+### Hello world
 
 For a "hello world" example, take a look at:
 
@@ -82,7 +80,7 @@ For a "hello world" example, take a look at:
 This example illustrates the bare minimum ingredients for integrating pdf.js
 in a custom project.
 
-#### Introductory video
+### Introductory video
 
 Check out the presentation by our contributor Julian Viereck on the inner 
 workings of PDF and pdf.js:
@@ -92,7 +90,7 @@ workings of PDF and pdf.js:
 
 
 
-## Contributing
+# Contributing
 
 pdf.js is a community-driven project, so contributors are always welcome. 
 Simply fork our repo and contribute away. Good starting places for picking
@@ -122,7 +120,7 @@ You can add your name to it! :)
 
 
 
-## Running the tests
+# Running the tests
 
 pdf.js comes with browser-level regression tests that allow one to probe 
 whether it's able to successfully parse PDFs, as well as compare its output
@@ -148,7 +146,7 @@ images. The test type `load` simply tests whether the file loads without
 raising any errors.
 
 
-## Running tests through our bot
+### Running tests through our bot
 
 If you are a reviewer, you can use our remote bot to issue comprehensive tests 
 against reference images before merging pull requests.
@@ -158,7 +156,7 @@ See the bot repo for details:
 + https://github.com/mozilla/pdf.js-bot
 
 
-## Additional resources
+# Additional resources
 
 Gallery of user projects and modifications:
 
@@ -188,7 +186,7 @@ Follow us on twitter: @pdfjs
   
   
   
-## PDF-related resources
+### PDF-related resources
 
 A really basic overview of PDF is described here:
 

examples/acroforms/index.html

@@ -23,6 +23,7 @@
   <script type="text/javascript" src="../../src/stream.js"></script>
   <script type="text/javascript" src="../../src/worker.js"></script>
   <script type="text/javascript" src="../../external/jpgjs/jpg.js"></script>
+  <script type="text/javascript" src="../../src/jpx.js"></script>
 
   <script type="text/javascript">
     // Specify the main script used to create a new PDF.JS web worker.

examples/helloworld/index.html

@@ -23,6 +23,7 @@
   <script type="text/javascript" src="../../src/stream.js"></script>
   <script type="text/javascript" src="../../src/worker.js"></script>
   <script type="text/javascript" src="../../external/jpgjs/jpg.js"></script>
+  <script type="text/javascript" src="../../src/jpx.js"></script>
 
   <script type="text/javascript">
     // Specify the main script used to create a new PDF.JS web worker.

src/fonts.js

@@ -3340,15 +3340,9 @@ var Type2CFF = (function Type2CFFClosure() {
         inverseEncoding[encoding[charcode]] = charcode | 0;
       for (var i = 0, ii = charsets.length; i < ii; i++) {
         var glyph = charsets[i];
-        if (glyph == '.notdef') {
-          charstrings.push({
-            unicode: 0,
-            code: 0,
-            gid: i,
-            glyph: glyph
-          });
+        if (glyph == '.notdef')
           continue;
-        }
+
         var code = inverseEncoding[i];
         if (!code || isSpecialUnicode(code)) {
           unassignedUnicodeItems.push(i);

src/parser.js

@@ -240,6 +240,10 @@ var Parser = (function ParserClosure() {
         var bytes = stream.getBytes(length);
         return new JpegStream(bytes, stream.dict, this.xref);
       }
+      if (name == 'JPXDecode' || name == 'JPX') {
+        var bytes = stream.getBytes(length);
+        return new JpxStream(bytes, stream.dict);
+      }
       if (name == 'ASCII85Decode' || name == 'A85') {
         return new Ascii85Stream(stream);
       }
@@ -249,6 +253,9 @@ var Parser = (function ParserClosure() {
       if (name == 'CCITTFaxDecode' || name == 'CCF') {
         return new CCITTFaxStream(stream, params);
       }
+      if (name == 'RunLengthDecode') {
+        return new RunLengthStream(stream);
+      }
       warn('filter "' + name + '" not supported yet');
       return stream;
     }

src/stream.js

@@ -835,7 +835,7 @@ var JpegStream = (function JpegStreamClosure() {
     return bytesToString(this.bytes);
   };
   JpegStream.prototype.getChar = function jpegStreamGetChar() {
-      error('internal error: getChar is not valid on JpegStream');
+    error('internal error: getChar is not valid on JpegStream');
   };
   /**
    * Checks if the image can be decoded and displayed by the browser without any
@@ -869,6 +869,107 @@ var JpegStream = (function JpegStreamClosure() {
   return JpegStream;
 })();
 
+/**
+ * For JPEG 2000's we use a library to decode these images and
+ * the stream behaves like all the other DecodeStreams.
+ */
+var JpxStream = (function JpxStreamClosure() {
+  function JpxStream(bytes, dict) {
+    this.dict = dict;
+    this.bytes = bytes;
+
+    DecodeStream.call(this);
+  }
+
+  JpxStream.prototype = Object.create(DecodeStream.prototype);
+
+  JpxStream.prototype.ensureBuffer = function jpxStreamEnsureBuffer(req) {
+    if (this.bufferLength)
+      return;
+
+    var jpxImage = new JpxImage();
+    jpxImage.parse(this.bytes);
+
+    var width = jpxImage.width;
+    var height = jpxImage.height;
+    var componentsCount = jpxImage.componentsCount;
+    if (componentsCount != 1 && componentsCount != 3 && componentsCount != 4)
+      error('JPX with ' + componentsCount + ' components is not supported');
+
+    var data = new Uint8Array(width * height * componentsCount);
+
+    for (var k = 0, kk = jpxImage.tiles.length; k < kk; k++) {
+      var tileCompoments = jpxImage.tiles[k];
+      var tileWidth = tileCompoments[0].width;
+      var tileHeight = tileCompoments[0].height;
+      var tileLeft = tileCompoments[0].left;
+      var tileTop = tileCompoments[0].top;
+
+      var dataPosition, sourcePosition, data0, data1, data2, data3, rowFeed;
+      switch (componentsCount) {
+        case 1:
+          data0 = tileCompoments[0].items;
+
+          dataPosition = width * tileTop + tileLeft;
+          rowFeed = width - tileWidth;
+          sourcePosition = 0;
+          for (var j = 0; j < tileHeight; j++) {
+            for (var i = 0; i < tileWidth; i++)
+              data[dataPosition++] = data0[sourcePosition++];
+            dataPosition += rowFeed;
+          }
+          break;
+        case 3:
+          data0 = tileCompoments[0].items;
+          data1 = tileCompoments[1].items;
+          data2 = tileCompoments[2].items;
+
+          dataPosition = (width * tileTop + tileLeft) * 3;
+          rowFeed = (width - tileWidth) * 3;
+          sourcePosition = 0;
+          for (var j = 0; j < tileHeight; j++) {
+            for (var i = 0; i < tileWidth; i++) {
+              data[dataPosition++] = data0[sourcePosition];
+              data[dataPosition++] = data1[sourcePosition];
+              data[dataPosition++] = data2[sourcePosition];
+              sourcePosition++;
+            }
+            dataPosition += rowFeed;
+          }
+          break;
+        case 4:
+          data0 = tileCompoments[0].items;
+          data1 = tileCompoments[1].items;
+          data2 = tileCompoments[2].items;
+          data3 = tileCompoments[3].items;
+
+          dataPosition = (width * tileTop + tileLeft) * 4;
+          rowFeed = (width - tileWidth) * 4;
+          sourcePosition = 0;
+          for (var j = 0; j < tileHeight; j++) {
+            for (var i = 0; i < tileWidth; i++) {
+              data[dataPosition++] = data0[sourcePosition];
+              data[dataPosition++] = data1[sourcePosition];
+              data[dataPosition++] = data2[sourcePosition];
+              data[dataPosition++] = data3[sourcePosition];
+              sourcePosition++;
+            }
+            dataPosition += rowFeed;
+          }
+          break;
+      }
+    }
+
+    this.buffer = data;
+    this.bufferLength = data.length;
+  };
+  JpxStream.prototype.getChar = function jpxStreamGetChar() {
+    error('internal error: getChar is not valid on JpxStream');
+  };
+
+  return JpxStream;
+})();
+
 var DecryptStream = (function DecryptStreamClosure() {
   function DecryptStream(str, decrypt) {
     this.str = str;
@@ -1041,6 +1142,51 @@ var AsciiHexStream = (function AsciiHexStreamClosure() {
   return AsciiHexStream;
 })();
 
+var RunLengthStream = (function RunLengthStreamClosure() {
+  function RunLengthStream(str) {
+    this.str = str;
+    this.dict = str.dict;
+
+    DecodeStream.call(this);
+  }
+
+  RunLengthStream.prototype = Object.create(DecodeStream.prototype);
+
+  RunLengthStream.prototype.readBlock = function runLengthStreamReadBlock() {
+    // The repeatHeader has following format. The first byte defines type of run
+    // and amount of bytes to repeat/copy: n = 0 through 127 - copy next n bytes
+    // (in addition to the second byte from the header), n = 129 through 255 -
+    // duplicate the second byte from the header (257 - n) times, n = 128 - end.
+    var repeatHeader = this.str.getBytes(2);
+    if (!repeatHeader || repeatHeader.length < 2 || repeatHeader[0] == 128) {
+      this.eof = true;
+      return;
+    }
+
+    var bufferLength = this.bufferLength;
+    var n = repeatHeader[0];
+    if (n < 128) {
+      // copy n bytes
+      var buffer = this.ensureBuffer(bufferLength + n + 1);
+      buffer[bufferLength++] = repeatHeader[1];
+      if (n > 0) {
+        var source = this.str.getBytes(n);
+        buffer.set(source, bufferLength);
+        bufferLength += n;
+      }
+    } else {
+      n = 257 - n;
+      var b = repeatHeader[1];
+      var buffer = this.ensureBuffer(bufferLength + n + 1);
+      for (var i = 0; i < n; i++)
+        buffer[bufferLength++] = b;
+    }
+    this.bufferLength = bufferLength;
+  };
+
+  return RunLengthStream;
+})();
+
 var CCITTFaxStream = (function CCITTFaxStreamClosure() {
 
   var ccittEOL = -2;

src/worker_loader.js

@@ -23,7 +23,8 @@ var files = [
   'pattern.js',
   'stream.js',
   'worker.js',
-  '../external/jpgjs/jpg.js'
+  '../external/jpgjs/jpg.js',
+  'jpx.js'
 ];
 
 // Load all the files.

test/pdfs/.gitignore

@@ -22,4 +22,5 @@
 !issue918.pdf
 !smaskdim.pdf
 !type4psfunc.pdf
+!S2.pdf
 !zerowidthline.pdf

test/test_manifest.json

@@ -176,7 +176,6 @@
        "md5": "eb7b224107205db4fea9f7df0185f77d",
        "link": true,
        "rounds": 1,
-       "skipPages": [12,31],
        "type": "eq"
     },
     {  "id": "fips197",
@@ -411,6 +410,12 @@
       "link": true,
       "type": "load"
     },
+    {  "id": "S2-eq",
+       "file": "pdfs/S2.pdf",
+       "md5": "d0b6137846df6e0fe058f234a87fb588",
+       "rounds": 1,
+       "type": "eq"
+    },
     {  "id": "issue1055",
       "file": "pdfs/issue1055.pdf",
       "md5": "3ba56c2e48dce81da8669b1b9cf98ff0",

test/test_slave.html

@@ -22,6 +22,7 @@
     <script type="text/javascript" src="/src/stream.js"></script>
     <script type="text/javascript" src="/src/worker.js"></script>
     <script type="text/javascript" src="/external/jpgjs/jpg.js"></script>
+    <script type="text/javascript" src="/src/jpx.js"></script>
     <script type="text/javascript" src="driver.js"></script>
 
     <script type="text/javascript">

web/viewer.html

@@ -26,6 +26,7 @@
         <script type="text/javascript" src="../src/stream.js"></script>  <!-- PDFJSSCRIPT_REMOVE -->
         <script type="text/javascript" src="../src/worker.js"></script>  <!-- PDFJSSCRIPT_REMOVE -->
         <script type="text/javascript" src="../external/jpgjs/jpg.js"></script>  <!-- PDFJSSCRIPT_REMOVE -->
+        <script type="text/javascript" src="../src/jpx.js"></script>  <!-- PDFJSSCRIPT_REMOVE -->
         <script type="text/javascript">PDFJS.workerSrc = '../src/worker_loader.js';</script> <!-- PDFJSSCRIPT_REMOVE -->
         <script type="text/javascript" src="viewer.js"></script>
 

web/viewer.js

@@ -960,22 +960,55 @@ var TextLayerBuilder = function textLayerBuilder(textLayerDiv) {
     var self = this;
     var textDivs = this.textDivs;
     var textLayerDiv = this.textLayerDiv;
-    this.textLayerTimer = setInterval(function renderTextLayer() {
+    var renderTimer = null;
+    var renderingDone = false;
+    var renderInterval = 0;
+    var resumeInterval = 500; // in ms
+
+    // Render the text layer, one div at a time
+    function renderTextLayer() {
       if (textDivs.length === 0) {
-        clearInterval(self.textLayerTimer);
+        clearInterval(renderTimer);
+        renderingDone = true;
         return;
       }
       var textDiv = textDivs.shift();
-      if (textDiv.dataset.textLength >= 1) { // avoid div by zero
+      if (textDiv.dataset.textLength > 0) {
         textLayerDiv.appendChild(textDiv);
-        // Adjust div width (via letterSpacing) to match canvas text
-        // Due to the .offsetWidth calls, this is slow
-        textDiv.style.letterSpacing =
-          ((textDiv.dataset.canvasWidth - textDiv.offsetWidth) /
-            (textDiv.dataset.textLength - 1)) + 'px';
+
+        if (textDiv.dataset.textLength > 1) { // avoid div by zero
+          // Adjust div width (via letterSpacing) to match canvas text
+          // Due to the .offsetWidth calls, this is slow
+          // This needs to come after appending to the DOM
+          textDiv.style.letterSpacing =
+            ((textDiv.dataset.canvasWidth - textDiv.offsetWidth) /
+              (textDiv.dataset.textLength - 1)) + 'px';
+        }
+      } // textLength > 0
+    }
+    renderTimer = setInterval(renderTextLayer, renderInterval);
+
+    // Stop rendering when user scrolls. Resume after XXX milliseconds
+    // of no scroll events
+    var scrollTimer = null;
+    function textLayerOnScroll() {
+      if (renderingDone) {
+        window.removeEventListener('scroll', textLayerOnScroll, false);
+        return;
       }
-    }, 0);
-  };
+
+      // Immediately pause rendering
+      clearInterval(renderTimer);
+
+      clearTimeout(scrollTimer);
+      scrollTimer = setTimeout(function textLayerScrollTimer() {
+        // Resume rendering
+        renderTimer = setInterval(renderTextLayer, renderInterval);
+      }, resumeInterval);
+    }; // textLayerOnScroll
+
+    window.addEventListener('scroll', textLayerOnScroll, false);
+  }; // endLayout
 
   this.appendText = function textLayerBuilderAppendText(text,
                                                         fontName, fontSize) {