Prevent "Lists" Folder from being listed for Sites
The Lists Folder is always present, but never actually exists. To
prevent these documents from showing up in Crawl Diagnostics as errors
we filter in Site listings.
diff --git a/src/com/google/enterprise/adaptor/sharepoint/SharePointAdaptor.java b/src/com/google/enterprise/adaptor/sharepoint/SharePointAdaptor.java
index 83d17ab..a08bca9 100644
--- a/src/com/google/enterprise/adaptor/sharepoint/SharePointAdaptor.java
+++ b/src/com/google/enterprise/adaptor/sharepoint/SharePointAdaptor.java
@@ -841,6 +841,10 @@
for (Folders folders : f.getFolders()) {
if (folders.getFolder() != null) {
for (Folders.Folder folder : folders.getFolder()) {
+ // Lists is always present in the listing but never exists.
+ if ("Lists".equals(folder.getURL())) {
+ continue;
+ }
writer.addLink(encodeDocId(folder.getURL()), null);
}
}
diff --git a/test/com/google/enterprise/adaptor/sharepoint/SharePointAdaptorTest.java b/test/com/google/enterprise/adaptor/sharepoint/SharePointAdaptorTest.java
index db75628..1a14c13 100644
--- a/test/com/google/enterprise/adaptor/sharepoint/SharePointAdaptorTest.java
+++ b/test/com/google/enterprise/adaptor/sharepoint/SharePointAdaptorTest.java
@@ -412,7 +412,7 @@
+ "/sites/SiteCollection/Shared Documents/Forms/AllItems.aspx</a>"
+ "</li></ul>"
+ "<p>Folders</p>"
- + "<ul><li><a href=\"SiteCollection/Lists\">Lists</a></li></ul>"
+ + "<ul></ul>"
+ "<p>List Items</p>"
+ "<ul><li><a href=\"SiteCollection/default.aspx\">"
+ "default.aspx</a></li></ul>"
