Merge remote-tracking branch 'upstream/master'

README.md

@@ -27,6 +27,32 @@ For an online demo, visit:
 This demo provides an interactive interface for displaying and browsing PDFs
 using the pdf.js API.
 
+**Getting the code**
+
+To get a local copy of the current code, clone it using git:
+
+```bash
+    git clone git://github.com/andreasgal/pdf.js.git pdfjs
+    cd pdfjs
+```
+
+Next, you need to start a local web server as some browsers don't allow opening
+PDF files for a file:// url:
+
+```bash
+  make server
+```
+
+If everything worked out, you can now serve 
+
+  http://localhost:8888/web/viewer.html
+
+You can also view all the test pdf files on the right side serving
+
+  http://localhost:8888/test/pdfs/?frame
+
+
+
 **Hello world**
 
 For a "hello world" example, take a look at:
@@ -38,6 +64,20 @@ in a custom project.
 
 
 
+## Contributing
+
+pdf.js is a community-driver project, so contributors are always welcome. 
+Simply fork our repo and contribute away. A great place to start is our
+open issues. For better consistency and long-term stability, please do look around the 
+code and try to follow our conventions.
+
+If you __don't want to hack__ on the project or have short spare times, you still
+can help! Just open PDFs in the 
+[online demo](http://andreasgal.github.com/pdf.js/web/viewer.html) and report 
+any breakage in rendering.
+
+
+
 ## Running the Tests
 
 pdf.js comes with browser-level regression tests that allow one to probe 
@@ -64,16 +104,6 @@ images. The test type `load` simply tests whether the file loads without
 raising any errors.
 
 
-## Contributing
-
-pdf.js is a community-driver project, so contributors are always welcome. 
-Simply fork our repo and contribute away. A great place to start is our
-open issues. 
-
-For better consistency and long-term stability, please do look around the 
-code and try to follow our conventions.
-
-
 ## Additional resources
 
 Our demo site is here:
@@ -97,8 +127,28 @@ Join our mailing list:
 Subscribe either using lists.mozilla.org or Google Groups: 
   
   https://lists.mozilla.org/listinfo/dev-pdf-js
+
   https://groups.google.com/group/mozilla.dev.pdf-js/topics
 
 Talk to us on IRC:
 
   #pdfjs on irc.mozilla.org
+  
+## Additional resources to understand the structure of PDF
+
+A really basic overview of PDF is described here:
+
+  http://partners.adobe.com/public/developer/en/livecycle/lc_pdf_overview_format.pdf
+
+A more detailed file example:
+
+  http://gnupdf.org/Introduction_to_PDF
+  
+The PDF specification itself is an ISO and not free available. However, there is
+a "PDF Reference" from Adobe:
+
+  http://wwwimages.adobe.com/www.adobe.com/content/dam/Adobe/en/devnet/pdf/pdfs/pdf_reference_1-7.pdf
+
+Recommanded chapters to read: "2. Overview", "3.4 File Structure", 
+"4.1 Graphics Objects" that lists the PDF commands.
+

crypto.js

@@ -45,7 +45,7 @@ var ARCFourCipher = (function aRCFourCipher() {
   return constructor;
 })();
 
-var md5 = (function md5Md5() {
+var calculateMD5 = (function calculateMD5() {
   var r = new Uint8Array([
     7, 12, 17, 22, 7, 12, 17, 22, 7, 12, 17, 22, 7, 12, 17, 22,
     5, 9, 14, 20, 5, 9, 14, 20, 5, 9, 14, 20, 5, 9, 14, 20,
@@ -452,11 +452,11 @@ var CipherTransformFactory = (function cipherTransformFactory() {
       hashData[i++] = 0xFF;
       hashData[i++] = 0xFF;
     }
-    var hash = md5(hashData, 0, i);
+    var hash = calculateMD5(hashData, 0, i);
     var keyLengthInBytes = keyLength >> 3;
     if (revision >= 3) {
       for (j = 0; j < 50; ++j) {
-         hash = md5(hash, 0, keyLengthInBytes);
+         hash = calculateMD5(hash, 0, keyLengthInBytes);
       }
     }
     var encryptionKey = hash.subarray(0, keyLengthInBytes);
@@ -469,7 +469,7 @@ var CipherTransformFactory = (function cipherTransformFactory() {
       for (j = 0, n = fileId.length; j < n; ++j)
         hashData[i++] = fileId[j];
       cipher = new ARCFourCipher(encryptionKey);
-      var checkData = cipher.encryptBlock(md5(hashData, 0, i));
+      var checkData = cipher.encryptBlock(calculateMD5(hashData, 0, i));
       n = encryptionKey.length;
       var derrivedKey = new Uint8Array(n), k;
       for (j = 1; j <= 19; ++j) {
@@ -544,7 +544,7 @@ var CipherTransformFactory = (function cipherTransformFactory() {
       key[i++] = 0x6C;
       key[i++] = 0x54;
     }
-    var hash = md5(key, 0, i);
+    var hash = calculateMD5(key, 0, i);
     return hash.subarray(0, Math.min(encryptionKey.length + 5, 16));
   }
 

pdf.js

@@ -3324,8 +3324,10 @@ var Page = (function pagePage() {
     },
     get mediaBox() {
       var obj = this.inheritPageProp('MediaBox');
-      return shadow(this, 'mediaBox',
+      // Reset invalid media box to letter size.
-                    ((IsArray(obj) && obj.length == 4) ? obj : null));
+      if (!IsArray(obj) || obj.length !== 4)
+        obj = [0, 0, 612, 792];
+      return shadow(this, 'mediaBox', obj);
     },
     get view() {
       var obj = this.inheritPageProp('CropBox');
@@ -4819,7 +4821,65 @@ var CanvasGraphics = (function canvasGraphics() {
       TODO('set flatness: ' + flatness);
     },
     setGState: function canvasGraphicsSetGState(dictName) {
-      TODO('set graphics state from dict: ' + dictName);
+      var extGState = this.xref.fetchIfRef(this.res.get('ExtGState'));
+      if (IsDict(extGState) && extGState.has(dictName.name)) {
+        var gsState = this.xref.fetchIfRef(extGState.get(dictName.name));
+        var self = this;
+        gsState.forEach(function(key, value) {
+          switch (key) {
+            case 'Type':
+              break;
+            case 'LW':
+              self.setLineWidth(value);
+              break;
+            case 'LC':
+              self.setLineCap(value);
+              break;
+            case 'LJ':
+              self.setLineJoin(value);
+              break;
+            case 'ML':
+              self.setMiterLimit(value);
+              break;
+            case 'D':
+              self.setDash(value[0], value[1]);
+              break;
+            case 'RI':
+              self.setRenderingIntent(value);
+              break;
+            case 'FL':
+              self.setFlatness(value);
+              break;
+            case 'Font':
+              self.setFont(value[0], value[1]);
+              break;
+            case 'OP':
+            case 'op':
+            case 'OPM':
+            case 'BG':
+            case 'BG2':
+            case 'UCR':
+            case 'UCR2':
+            case 'TR':
+            case 'TR2':
+            case 'HT':
+            case 'SM':
+            case 'SA':
+            case 'BM':
+            case 'SMask':
+            case 'CA':
+            case 'ca':
+            case 'AIS':
+            case 'TK':
+              TODO('graphic state operator ' + key);
+              break;
+            default:
+              warn('Unknown graphic state operator ' + key);
+              break;
+          }
+        });
+      }
+
     },
     save: function canvasGraphicsSave() {
       this.ctx.save();
@@ -4986,11 +5046,17 @@ var CanvasGraphics = (function canvasGraphics() {
       this.current.leading = -leading;
     },
     setFont: function canvasGraphicsSetFont(fontRef, size) {
-      var font = this.xref.fetchIfRef(this.res.get('Font'));
+      var font;
-      if (!IsDict(font))
+      // the tf command uses a name, but graphics state uses a reference
-        return;
+      if (IsName(fontRef)) {
+        font = this.xref.fetchIfRef(this.res.get('Font'));
+        if (!IsDict(font))
+         return;
 
-      font = font.get(fontRef.name);
+        font = font.get(fontRef.name);
+      } else if (IsRef(fontRef)) {
+        font = fontRef;
+      }
       font = this.xref.fetchIfRef(font);
       if (!font)
         error('Referenced font is not found');

test/driver.js

@@ -50,7 +50,21 @@ function load() {
   r.send(null);
 }
 
+function cleanup() {
+  var styleSheet = document.styleSheets[0];
+  if (styleSheet) {
+    while (styleSheet.cssRules.length > 0)
+      styleSheet.deleteRule(0);
+  }
+  var guard = document.getElementById('content-end');
+  var body = document.body;
+  while (body.lastChild !== guard)
+    body.removeChild(body.lastChild);
+}
+
 function nextTask() {
+  cleanup();
+
   if (currentTaskIdx == manifest.length) {
     return done();
   }

test/pdfs/extgstate.pdf

@@ -0,0 +1,105 @@
+%PDF-1.4
+%öäüß
+1 0 obj
+<<
+/Type /Catalog
+/Version /1.4
+/Pages 2 0 R
+>>
+endobj
+2 0 obj
+<<
+/Type /Pages
+/Kids [3 0 R]
+/Count 1
+>>
+endobj
+3 0 obj
+<<
+/Type /Page
+/MediaBox [0 0 612 792]
+/Resources 4 0 R
+/Parent 2 0 R
+/Contents 5 0 R
+>>
+endobj
+4 0 obj
+<<
+/ExtGState 6 0 R
+/Font 7 0 R
+/XObject <<
+>>
+>>
+endobj
+5 0 obj
+<<
+/Length 8 0 R
+>>
+stream
+/GS1 gs
+/F0 12 Tf
+BT
+100 700 Td
+(I should be courier!) Tj
+ET
+50 600 m
+400 600 l
+S
+
+endstream
+endobj
+6 0 obj
+<<
+/GS1 9 0 R
+>>
+endobj
+7 0 obj
+<<
+/F0 10 0 R
+>>
+endobj
+8 0 obj
+82
+endobj
+9 0 obj
+<<
+/Type /ExtGState
+/LW 10
+/LC 1
+/LJ 2
+/ML 0.3000000119
+/D [[0.0917000026 183.3300018311]
+ 0]
+/Font [10 0 R 36]
+>>
+endobj
+10 0 obj
+<<
+/Type /Font
+/Subtype /Type1
+/BaseFont /Courier
+/Encoding /WinAnsiEncoding
+>>
+endobj
+xref
+0 11
+0000000000 65535 f
+0000000015 00000 n
+0000000078 00000 n
+0000000135 00000 n
+0000000239 00000 n
+0000000304 00000 n
+0000000441 00000 n
+0000000473 00000 n
+0000000505 00000 n
+0000000523 00000 n
+0000000653 00000 n
+trailer
+<<
+/Root 1 0 R
+/ID [<BFFF29B7D1C75EC69AC080682C2AFC5B> <BFFF29B7D1C75EC69AC080682C2AFC5B>]
+/Size 11
+>>
+startxref
+749
+%%EOF

test/test_manifest.json

@@ -151,5 +151,11 @@
        "link": true,
        "rounds": 1,
        "type": "load"
+    },
+    {  "id": "extgstate",
+       "file": "pdfs/extgstate.pdf",
+       "link": false,
+       "rounds": 1,
+       "type": "load"
     }
 ]

test/test_slave.html

@@ -14,6 +14,7 @@
 <body onload="load();">
   <pre style="width:800; height:800; overflow: scroll;"id="stdout"></pre>
   <p>Inflight requests: <span id="inFlightCount"></span></p>
+  <div id="content-end"><!-- cleanup() guard --></div>
 </body>
 
 </html>