extract annotations v2

examples/extract/README.md

@@ -0,0 +1,14 @@
+## "Extract" overview
+
+This example is a minimalistic application for the extraction of annotations from pdfs using pdf.js. 
+
+## Getting started
+
+Point your browser to `index.html`. Voila. Take a peek at `extract.js` to see
+how to make basic calls to `pdf.js`.
+
+
+## Additional resources
+
++ [GNUpdf - Introduction to PDF](http://gnupdf.org/Introduction_to_PDF)
+

examples/extract/extract.js

@@ -0,0 +1,101 @@
+/* -*- Mode: Java; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
+/* vim: set shiftwidth=2 tabstop=2 autoindent cindent expandtab: */
+
+'use strict';
+
+// example to extract annotations
+// cd to pdf.js folder
+// python -m SimpleHTTPServer 8888
+// http://localhost:8888/examples/extract/index.html
+
+const SUPPORTED_ANNOTS = ["Text", "Highlight", "Underline"]
+
+// Fetch the PDF document from the URL using promices
+PDFJS.getDocument('/examples/extract/pdf/test.pdf').then(function(pdf) {
+
+  var n_annos = 0,
+      numPages = pdf.numPages;
+      // PDF data: pdf.pdfInfo, pdf.isEncrypted(), pdf.getMetadata().then(function(meta) {console.log('Metadata: ' + JSON.stringify(meta));});
+
+  // function to handle page (render and extract annotations)
+  var extract = function(page) {
+      var scale = 1;
+      var viewport = page.getViewport(scale);
+      // Prepare canvas using PDF page dimensions
+      var canvas = document.getElementById('the-canvas');
+      var context = canvas.getContext('2d');
+      canvas.height = viewport.height;
+      canvas.width = viewport.width;
+      // Render PDF page into canvas context
+      var renderContext = {
+        canvasContext: context,
+        viewport: viewport
+      };
+
+      // get annotations
+      var annotations;
+      page.getAnnotations().then(function extractAnno(annos) {
+        console.log('Page: '+page.pageNumber + " ("+annos.length+" annotations " + JSON.stringify(annos.map(function(a) {return a.type;})) + ")");
+        // filter for supported annotations
+        annotations = annos.filter(function(anno) {return SUPPORTED_ANNOTS.indexOf(anno.type) >= 0;});
+        // skip page if there is nothing interesting
+        if (annotations.length==0) {
+          if(numPages>page.pageNumber) pdf.getPage(page.pageNumber+1).then(extract,function(err) {console.log('error getting the page:' + err)});
+          return;
+        }
+        // render page
+        page.render(renderContext).then(function() {
+          console.log('Page: '+page.pageNumber + " (page rendered)");
+          // console.log(annotations);
+          // show annotations
+          var markup = annotations
+            .filter(function(anno) {return typeof anno.markup !== 'undefined';})
+            .map(function(anno) {
+              return anno.markup.join(' ').trim()
+                .replace('\ufb00','ff').replace('\ufb01','fi').replace('\ufb02','fl')
+                .replace(/\ufb03/g,'ffi').replace(/\ufb04/g,'ffl').replace(/\ufb05/g,'ft')
+                .replace(/\ufb06/g,'st').replace(/\uFB00/g,'ff').replace(/\uFB01/g,'fi')
+                .replace(/\uFB02/g,'fl').replace(/\uFB03/g,'ffi').replace(/\uFB04/g,'ffl')
+                .replace(/\uFB05/g,'ft').replace(/\uFB06/g,'st')
+                .replace(/\u201D/g,'"').replace(/\u201C/g,'"').replace(/\u2019/g,"'")
+                .replace(/\u2013/g,"-");
+            });
+          var content = annotations
+            .filter(function(anno) {return typeof anno.content !== 'undefined';})
+            .map(function(anno) {
+              return anno.content;
+            });
+
+          for (var i = 0; i < annotations.length; i++) {
+            if(markup[i]!==undefined)  console.log(markup[i]);
+            if(content[i]!==undefined) console.log(content[i]);
+          }
+
+          // render next page
+          if(numPages>page.pageNumber) pdf.getPage(page.pageNumber+1).then(extract,function(err) {console.log('error getting the page:' + err)});
+        },
+        // error handler for page
+        function(error) {
+          console.log('Error rendering the page: ', error);
+          // continue with next page
+          if(numPages>page.pageNumber) pdf.getPage(page.pageNumber+1).then(extract,function(err) {console.log('error getting the page:' + err)});
+        });
+
+      },
+      // error handler for page
+      function(error) {
+        console.log(error);
+        // continue with next page
+        if(numPages>page.pageNumber) pdf.getPage(page.pageNumber+1).then(extract,function(err) {console.log('error getting the page:' + err)});
+      });
+    };
+
+  // Using promise to fetch the page
+  pdf.getPage(1).then(extract,function(err) {console.log('error getting the page:' + err)});
+
+},
+function(err) {
+  console.log('unable to open pdf: ' + err);
+});
+
+

examples/extract/index.html

@@ -0,0 +1,45 @@
+<!doctype html>
+<html>
+
+<head>
+  <!-- In production, only one script (pdf.js) is necessary -->
+  <!-- In production, change the content of PDFJS.workerSrc below -->
+  <script type="text/javascript" src="../../src/network.js"></script>
+  <script type="text/javascript" src="../../src/chunked_stream.js"></script>
+  <script type="text/javascript" src="../../src/pdf_manager.js"></script>
+  <script type="text/javascript" src="../../src/core.js"></script>
+  <script type="text/javascript" src="../../src/util.js"></script>
+  <script type="text/javascript" src="../../src/api.js"></script>
+  <script type="text/javascript" src="../../src/canvas.js"></script>
+  <script type="text/javascript" src="../../src/obj.js"></script>
+  <script type="text/javascript" src="../../src/function.js"></script>
+  <script type="text/javascript" src="../../src/charsets.js"></script>
+  <script type="text/javascript" src="../../src/cidmaps.js"></script>
+  <script type="text/javascript" src="../../src/colorspace.js"></script>
+  <script type="text/javascript" src="../../src/crypto.js"></script>
+  <script type="text/javascript" src="../../src/evaluator.js"></script>
+  <script type="text/javascript" src="../../src/fonts.js"></script>
+  <script type="text/javascript" src="../../src/glyphlist.js"></script>
+  <script type="text/javascript" src="../../src/image.js"></script>
+  <script type="text/javascript" src="../../src/metrics.js"></script>
+  <script type="text/javascript" src="../../src/parser.js"></script>
+  <script type="text/javascript" src="../../src/pattern.js"></script>
+  <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="../../src/jbig2.js"></script>
+
+  <script type="text/javascript">
+    // Specify the main script used to create a new PDF.JS web worker.
+    // In production, change this to point to the combined `pdf.js` file.
+    PDFJS.workerSrc = '../../src/worker_loader.js';
+  </script>
+  <script type="text/javascript" src="extract.js"></script>
+</head>
+
+<body>
+  <canvas id="the-canvas" style="border:1px solid black;"/>
+</body>
+
+</html>

extensions/firefox/components/PdfStreamConverter.js

@@ -713,6 +713,7 @@ PdfStreamConverter.prototype = {
       var hash = aRequest.URI.ref;
       rangeRequest = contentEncoding === 'identity' &&
                      acceptRanges === 'bytes' &&
+                     aRequest.contentLength >= 0 &&
                      hash.indexOf('disableRange=true') < 0;
     }
 
@@ -764,33 +765,28 @@ PdfStreamConverter.prototype = {
         // We get the DOM window here instead of before the request since it
         // may have changed during a redirect.
         var domWindow = getDOMWindow(channel);
-        // Double check the url is still the correct one.
-        if (domWindow.document.documentURIObject.equals(aRequest.URI)) {
-          var actions;
-          if (rangeRequest) {
-            // We are going to be issuing range requests, so cancel the
-            // original request
-            aRequest.resume();
-            aRequest.cancel(Cr.NS_BINDING_ABORTED);
-            actions = new RangedChromeActions(domWindow,
-                contentDispositionFilename, aRequest);
-          } else {
-            actions = new StandardChromeActions(
-                domWindow, contentDispositionFilename, dataListener);
-          }
-          var requestListener = new RequestListener(actions);
-          domWindow.addEventListener(PDFJS_EVENT_ID, function(event) {
-            requestListener.receive(event);
-          }, false, true);
-          if (actions.supportsIntegratedFind()) {
-            var chromeWindow = getChromeWindow(domWindow);
-            var findEventManager = new FindEventManager(chromeWindow.gFindBar,
-                                                        domWindow,
-                                                        chromeWindow);
-            findEventManager.bind();
-          }
+        var actions;
+        if (rangeRequest) {
+          // We are going to be issuing range requests, so cancel the
+          // original request
+          aRequest.resume();
+          aRequest.cancel(Cr.NS_BINDING_ABORTED);
+          actions = new RangedChromeActions(domWindow,
+              contentDispositionFilename, aRequest);
         } else {
-          log('Dom window url did not match request url.');
+          actions = new StandardChromeActions(
+              domWindow, contentDispositionFilename, dataListener);
+        }
+        var requestListener = new RequestListener(actions);
+        domWindow.addEventListener(PDFJS_EVENT_ID, function(event) {
+          requestListener.receive(event);
+        }, false, true);
+        if (actions.supportsIntegratedFind()) {
+          var chromeWindow = getChromeWindow(domWindow);
+          var findEventManager = new FindEventManager(chromeWindow.gFindBar,
+                                                      domWindow,
+                                                      chromeWindow);
+          findEventManager.bind();
         }
         listener.onStopRequest(aRequest, context, statusCode);
       }

l10n/cs/viewer.properties

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-bookmark.title=Aktuální zobrazení(zkopírovat nebo otevřít v novém okně)
+bookmark.title=Aktuální zobrazení (zkopírovat nebo otevřít v novém okně)
 previous.title=Předchozí stránka
 next.title=Další stránka
 print.title=Tisk

src/api.js

@@ -311,25 +311,27 @@ var PDFPageProxy = (function PDFPageProxyClosure() {
       var continueCallback = params.continueCallback;
 
       // Once the operatorList and fonts are loaded, do the actual rendering.
-      this.displayReadyPromise.then(
-        function pageDisplayReadyPromise() {
-          if (self.destroyed) {
-            complete();
-            return;
-          }
+      this.getAnnotations().then(function(annos) {
+        this.displayReadyPromise.then(
+          function pageDisplayReadyPromise() {
+            if (self.destroyed) {
+              complete();
+              return;
+            }
+            var gfx = new CanvasGraphics(params.canvasContext, this.commonObjs,
+              this.objs, params.textLayer, params.imageLayer, annos);
+            try {
+              this.display(gfx, params.viewport, complete, continueCallback);
+            } catch (e) {
+              complete(e);
+            }
 
-          var gfx = new CanvasGraphics(params.canvasContext, this.commonObjs,
-            this.objs, params.textLayer, params.imageLayer);
-          try {
-            this.display(gfx, params.viewport, complete, continueCallback);
-          } catch (e) {
-            complete(e);
+          }.bind(this),
+          function pageDisplayReadPromiseError(reason) {
+            complete(reason);
           }
-        }.bind(this),
-        function pageDisplayReadPromiseError(reason) {
-          complete(reason);
-        }
-      );
+        );
+      }.bind(this));
 
       return promise;
     },