Fix for keeping lists structure

java/org/chromium/distiller/webdocument/filters/RelevantElements.java

 // Copyright 2015 The Chromium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 package org.chromium.distiller.webdocument.filters;
 
 import org.chromium.distiller.webdocument.WebDocument;
 import org.chromium.distiller.webdocument.WebElement;
 import org.chromium.distiller.webdocument.WebText;
+import org.chromium.distiller.webdocument.PlaceHolderStart;
+import org.chromium.distiller.webdocument.PlaceHolderEnd;
+import java.util.List;
+import java.util.Stack;
 
 public class RelevantElements {
     public static boolean process(WebDocument document) {
         boolean changes = false;
         boolean inContent = false;
 
         for (WebElement e : document.getElements()) {
             if (e.getIsContent()) {
                 inContent = true;
             } else if (e instanceof WebText) {
                 inContent = false;
             } else {
                 if (inContent) {
                     e.setIsContent(true);
                     changes = true;
                 }
             }
         }
+        handlePlaceHolderElements(document.getElements());
         return changes;
     }
+
+    public static void handlePlaceHolderElements(List<WebElement> elements) {
+        class PlaceHolder {
+            public PlaceHolder(WebElement start, boolean flush) {

[mdjones, 2015/07/29 17:12:16]

What if there were only one class for a placeholder, something like:

public class PlaceHolder extends WebElement {
  // Maybe instead of enum just pass element.getTagName()
  public static enum PlaceHolderType{UL, OL, LI};
  private bool isStartTag;

  public PlaceHolder(PlaceHolderType type, bool isStart) {...}
  public bool isStart() {...}
  public PlaceHolderType getType() {...}
  ...
}

You could compile the eight classes you have into one and eliminate the need for
this PlaceHolder class.

+                this.start = start;
+                this.flush = flush;
+            }
+
+            WebElement start;
+            boolean flush;
+        }
+        boolean flush = false;
+        int stackMark = -1;

[mdjones, 2015/07/29 17:12:16]

I don't understand what this var is for. The only place it is used is to check
if it should modify itself.

+        Stack<PlaceHolder> holderStack = new Stack<>();
+
+        for (WebElement e : elements) {
+            if (e instanceof WebText) {
+                if (!flush) {
+                    flush = e.getIsContent();
+                }
+            } else if (e instanceof PlaceHolderStart) {
+                holderStack.push(new PlaceHolder(e, flush));
+                flush = false;
+            } else if (e instanceof PlaceHolderEnd) {
+                PlaceHolder placeHolder = holderStack.pop();
+                boolean isContent;

[mdjones, 2015/07/29 21:00:24]

Set isContent to flush here instead, or just use flush below since it is not
changed until the end of the block.

+                if ((isContent = flush || stackMark >= holderStack.size())) {
+                    stackMark = holderStack.size() - 1;
+                }
+                placeHolder.start.setIsContent(isContent);
+                e.setIsContent(isContent);
+                flush = placeHolder.flush;
+            }
+        }
+    }
 }