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..9a0fa04620694be7fd52d4e25279993a9036c383 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 pair of {@link WebTag}s, |
+ // we only need to get the innerHTML, otherwise |
+ // 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")) { |
wychen
2015/08/05 19:46:15
UL and OL might need to use innerHTML as well.
Eve
Marcelo Correa
2015/08/05 20:31:24
Yes, You are right. We might need to prevent that.
wychen
2015/08/06 00:04:52
It would be cleaner to aggregate the tag list in o
Marcelo Correa
2015/08/06 01:17:59
That makes two of us :P
|
+ return elementClonedRoot.getInnerHTML(); |
} |
- return Element.as(clonedRoot).getString(); |
+ return elementClonedRoot.getString(); |
} |
public List<Node> getTextNodes() { |