Fix final content and title extraction.

src/com/dom_distiller/client/ContentExtractor.java

Index: src/com/dom_distiller/client/ContentExtractor.java
diff --git a/src/com/dom_distiller/client/ContentExtractor.java b/src/com/dom_distiller/client/ContentExtractor.java
index f107e66f615960e667cab6beece10da68bd615a5..44d384332c04de248ee526fdc748cfcf58a7471e 100644
--- a/src/com/dom_distiller/client/ContentExtractor.java
+++ b/src/com/dom_distiller/client/ContentExtractor.java
@@ -73,7 +73,7 @@ public class ContentExtractor implements Exportable {
         }
 
         Node clonedSubtree = NodeListExpander.expand(contentAndImages).cloneSubtree();
-
+        LogUtil.logToConsole(clonedSubtree.getNodeType() + " node:" + Node.ELEMENT_NODE);

[cjhopman, 2014/05/22 00:27:21]

probably don't need this. If it's been useful, at least guard it with some debug
flag.

[Yaron, 2014/05/22 17:05:24]

err right that was supposed to go. I was trying to investigate something with
small pages. I believe you can fail the below test if we return just a single
text node but can't repro it now.

         if (clonedSubtree.getNodeType() != Node.ELEMENT_NODE) {
             return "";
         }
@@ -99,6 +99,9 @@ public class ContentExtractor implements Exportable {
             TextDocument document, List<Node> textNodes) {
         List<Integer> contentTextIndexes = new ArrayList<Integer>();
         for (TextBlock tb : document.getTextBlocks()) {
+            if (!tb.isContent()) {
+                continue;
+            }
             if (!tb.hasLabel(DefaultLabels.TITLE)) {
                 contentTextIndexes.addAll(tb.getContainedTextElements());
             }