Fix for keeping lists structure

java/org/chromium/distiller/webdocument/WebText.java

Index: java/org/chromium/distiller/webdocument/WebText.java
diff --git a/java/org/chromium/distiller/webdocument/WebText.java b/java/org/chromium/distiller/webdocument/WebText.java
index ae81ee6f97f2d9ca41ddfa00be521cf7646ab7bb..52f4eeea513695315f6f3223e74f94a423e21c0a 100644
--- a/java/org/chromium/distiller/webdocument/WebText.java
+++ b/java/org/chromium/distiller/webdocument/WebText.java
@@ -69,10 +69,16 @@ public class WebText extends WebElement {
         DomUtil.stripIds(clonedRoot);
         DomUtil.stripFontColorAttributes(clonedRoot);
 
+        // Since LI Tag is being wrapped by a WebTag instance,

[wychen, 2015/08/05 00:01:02]

by a pair of |WebTag|s

[Marcelo Correa, 2015/08/05 00:26:35]

You mean {@link WebTag}s or |WebTag|s?

[wychen, 2015/08/05 00:52:15]

Oh. Should be {@link WebTag}s. Thanks for pointing it out.

+        // We only need to get the innerHTML, otherwise

[wychen, 2015/08/05 00:01:02]

nit: we

+        // LI tag would be duplicated.
+        Element elementClonedRoot = Element.as(clonedRoot);
         if (textOnly) {
-            return Element.as(clonedRoot).getInnerText();
+            return elementClonedRoot.getInnerText();
+        } else if (elementClonedRoot.getTagName().equals("LI")) {
+            return elementClonedRoot.getInnerHTML();
         }
-        return Element.as(clonedRoot).getString();
+        return elementClonedRoot.getString();
     }
 
     public List<Node> getTextNodes() {