Return-Path: 
 <commits-return-8593-apmail-manifoldcf-commits-archive=manifoldcf.apache.org@manifoldcf.apache.org>
X-Original-To: apmail-manifoldcf-commits-archive@www.apache.org
Delivered-To: apmail-manifoldcf-commits-archive@www.apache.org
Received: from mail.apache.org (hermes.apache.org [140.211.11.3])
	by minotaur.apache.org (Postfix) with SMTP id F31E018CD4
	for <apmail-manifoldcf-commits-archive@www.apache.org>;
 Mon, 22 Feb 2016 13:11:43 +0000 (UTC)
Received: (qmail 19667 invoked by uid 500); 22 Feb 2016 12:54:22 -0000
Delivered-To: apmail-manifoldcf-commits-archive@manifoldcf.apache.org
Received: (qmail 18876 invoked by uid 500); 22 Feb 2016 12:54:21 -0000
Mailing-List: contact commits-help@manifoldcf.apache.org; run by ezmlm
Precedence: bulk
List-Help: <mailto:commits-help@manifoldcf.apache.org>
List-Unsubscribe: <mailto:commits-unsubscribe@manifoldcf.apache.org>
List-Post: <mailto:commits@manifoldcf.apache.org>
List-Id: <commits.manifoldcf.apache.org>
Reply-To: dev@manifoldcf.apache.org
Delivered-To: mailing list commits@manifoldcf.apache.org
Received: (qmail 17203 invoked by uid 99); 22 Feb 2016 12:50:12 -0000
Received: from pnap-us-west-generic-nat.apache.org (HELO
 spamd2-us-west.apache.org) (209.188.14.142)
    by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 22 Feb 2016 12:50:12 +0000
Received: from localhost (localhost [127.0.0.1])
	by spamd2-us-west.apache.org (ASF Mail Server at spamd2-us-west.apache.org)
 with ESMTP id 4BBA21A41B0
	for <commits@manifoldcf.apache.org>; Mon, 22 Feb 2016 12:50:12 +0000 (UTC)
X-Virus-Scanned: Debian amavisd-new at spamd2-us-west.apache.org
X-Spam-Flag: NO
X-Spam-Score: 0.671
X-Spam-Level: 
X-Spam-Status: No, score=0.671 tagged_above=-999 required=6.31
	tests=[KAM_LAZY_DOMAIN_SECURITY=1, RP_MATCHES_RCVD=-0.329]
	autolearn=disabled
Received: from mx1-lw-eu.apache.org ([10.40.0.8])
	by localhost (spamd2-us-west.apache.org [10.40.0.9]) (amavisd-new,
 port 10024)
	with ESMTP id nR7a6S9aY5uY for <commits@manifoldcf.apache.org>;
	Mon, 22 Feb 2016 12:50:09 +0000 (UTC)
Received: from mailrelay1-us-west.apache.org (mailrelay1-us-west.apache.org
 [209.188.14.139])
	by mx1-lw-eu.apache.org (ASF Mail Server at mx1-lw-eu.apache.org) with ESMTP
 id 27CF95F1E3
	for <commits@manifoldcf.apache.org>; Mon, 22 Feb 2016 12:50:09 +0000 (UTC)
Received: from svn01-us-west.apache.org (svn.apache.org [10.41.0.6])
	by mailrelay1-us-west.apache.org (ASF Mail Server at
 mailrelay1-us-west.apache.org) with ESMTP id 79F17E0288
	for <commits@manifoldcf.apache.org>; Mon, 22 Feb 2016 12:50:07 +0000 (UTC)
Received: from svn01-us-west.apache.org (localhost [127.0.0.1])
	by svn01-us-west.apache.org (ASF Mail Server at svn01-us-west.apache.org)
 with ESMTP id 0F7A33A0249
	for <commits@manifoldcf.apache.org>; Mon, 22 Feb 2016 12:50:08 +0000 (UTC)
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Subject: svn commit: r1731633 -
 /manifoldcf/trunk/connectors/sharepoint/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/sharepoint/SPSProxyHelper.java
Date: Mon, 22 Feb 2016 12:50:07 -0000
To: commits@manifoldcf.apache.org
From: kwright@apache.org
X-Mailer: svnmailer-1.0.9
Message-Id: <20160222125008.0F7A33A0249@svn01-us-west.apache.org>

Author: kwright
Date: Mon Feb 22 12:50:04 2016
New Revision: 1731633

URL: http://svn.apache.org/viewvc?rev=1731633&view=rev
Log:
SharePoint connector: check for 302 response and treat like 404.  This is a stopgap solution for external site references in SharePoint.

Modified:
    manifoldcf/trunk/connectors/sharepoint/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/sharepoint/SPSProxyHelper.java

Modified: manifoldcf/trunk/connectors/sharepoint/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/sharepoint/SPSProxyHelper.java
URL: http://svn.apache.org/viewvc/manifoldcf/trunk/connectors/sharepoint/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/sharepoint/SPSProxyHelper.java?rev=1731633&r1=1731632&r2=1731633&view=diff
==============================================================================
--- manifoldcf/trunk/connectors/sharepoint/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/sharepoint/SPSProxyHelper.java (original)
+++ manifoldcf/trunk/connectors/sharepoint/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/sharepoint/SPSProxyHelper.java Mon Feb 22 12:50:04 2016
@@ -228,11 +228,12 @@ public class SPSProxyHelper {
         {
           elem.normalize();
           String httpErrorCode = elem.getFirstChild().getNodeValue().trim();
-          if (httpErrorCode.equals("404"))
+          // 302 is what SharePoint returns for external sites
+          if (httpErrorCode.equals("404") || httpErrorCode.equals("302"))
           {
-            // Page did not exist
+            // Page did not exist or was external reference
             if (Logging.connectors.isDebugEnabled())
-              Logging.connectors.debug("SharePoint: The page at "+baseUrl+site+" did not exist; assuming list/library deleted");
+              Logging.connectors.debug("SharePoint: The page at "+baseUrl+site+" did not exist or was external; skipping list/library");
             return null;
           }
           else if (httpErrorCode.equals("401"))
@@ -260,7 +261,7 @@ public class SPSProxyHelper {
           {
             // List did not exist
             if (Logging.connectors.isDebugEnabled())
-              Logging.connectors.debug("SharePoint: The list "+guid+" in site "+site+" did not exist; assuming list/library deleted");
+              Logging.connectors.debug("SharePoint: The list "+guid+" in site "+site+" did not exist or was external; skipping list/library");
             return null;
           }
           else
@@ -439,11 +440,12 @@ public class SPSProxyHelper {
         {
           elem.normalize();
           String httpErrorCode = elem.getFirstChild().getNodeValue().trim();
-          if (httpErrorCode.equals("404"))
+          // 302 is what SharePoint returns for external sites
+          if (httpErrorCode.equals("404") || httpErrorCode.equals("302"))
           {
             // Page did not exist
             if (Logging.connectors.isDebugEnabled())
-              Logging.connectors.debug("SharePoint: The page at "+baseUrl+site+" did not exist; assuming library deleted");
+              Logging.connectors.debug("SharePoint: The page at "+baseUrl+site+" did not exist or was external; skipping library");
             return null;
           }
           else if (httpErrorCode.equals("401"))
@@ -471,7 +473,7 @@ public class SPSProxyHelper {
           {
             // List did not exist
             if (Logging.connectors.isDebugEnabled())
-              Logging.connectors.debug("SharePoint: The file "+file+" in site "+site+" did not exist; assuming file deleted");
+              Logging.connectors.debug("SharePoint: The file "+file+" in site "+site+" did not exist or was external; skipping file");
             return null;
           }
           else
@@ -692,11 +694,12 @@ public class SPSProxyHelper {
         {
           elem.normalize();
           String httpErrorCode = elem.getFirstChild().getNodeValue().trim();
-          if (httpErrorCode.equals("404"))
+          // 302 is what SharePoint returns for external sites
+          if (httpErrorCode.equals("404") || httpErrorCode.equals("302"))
           {
             // Page did not exist
             if (Logging.connectors.isDebugEnabled())
-              Logging.connectors.debug("SharePoint: The page at "+baseUrl+site+" did not exist; assuming library deleted");
+              Logging.connectors.debug("SharePoint: The page at "+baseUrl+site+" did not exist or was external; skipping library");
             return false;
           }
           else if (httpErrorCode.equals("401"))
@@ -724,7 +727,7 @@ public class SPSProxyHelper {
           {
             // List did not exist
             if (Logging.connectors.isDebugEnabled())
-              Logging.connectors.debug("SharePoint: The list "+guid+" in site "+site+" did not exist; assuming library deleted");
+              Logging.connectors.debug("SharePoint: The list "+guid+" in site "+site+" did not exist or was external; skipping library");
             return false;
           }
           else
@@ -895,11 +898,12 @@ public class SPSProxyHelper {
         {
           elem.normalize();
           String httpErrorCode = elem.getFirstChild().getNodeValue().trim();
-          if (httpErrorCode.equals("404"))
+          // 302 is what SharePoint returns for external sites
+          if (httpErrorCode.equals("404") || httpErrorCode.equals("302"))
           {
             // Page did not exist
             if (Logging.connectors.isDebugEnabled())
-              Logging.connectors.debug("SharePoint: The page at "+baseUrl+parentSite+" did not exist; assuming library deleted");
+              Logging.connectors.debug("SharePoint: The page at "+baseUrl+parentSite+" did not exist or was external; skipping library");
             return null;
           }
           else if (httpErrorCode.equals("401"))
@@ -927,7 +931,7 @@ public class SPSProxyHelper {
           {
             // List did not exist
             if (Logging.connectors.isDebugEnabled())
-              Logging.connectors.debug("SharePoint: The list "+docLibrary+" in site "+parentSite+" did not exist; assuming library deleted");
+              Logging.connectors.debug("SharePoint: The list "+docLibrary+" in site "+parentSite+" did not exist or was external; skipping library");
             return null;
           }
           else
@@ -1104,11 +1108,12 @@ public class SPSProxyHelper {
         {
           elem.normalize();
           String httpErrorCode = elem.getFirstChild().getNodeValue().trim();
-          if (httpErrorCode.equals("404"))
+          // 302 is what SharePoint returns for external sites
+          if (httpErrorCode.equals("404") || httpErrorCode.equals("302"))
           {
             // Page did not exist
             if (Logging.connectors.isDebugEnabled())
-              Logging.connectors.debug("SharePoint: The page at "+baseUrl+parentSite+" did not exist; assuming list deleted");
+              Logging.connectors.debug("SharePoint: The page at "+baseUrl+parentSite+" did not exist or was external; skipping list");
             return null;
           }
           else if (httpErrorCode.equals("401"))
@@ -1136,7 +1141,7 @@ public class SPSProxyHelper {
           {
             // List did not exist
             if (Logging.connectors.isDebugEnabled())
-              Logging.connectors.debug("SharePoint: The list "+listName+" in site "+parentSite+" did not exist; assuming list deleted");
+              Logging.connectors.debug("SharePoint: The list "+listName+" in site "+parentSite+" did not exist or was external; skipping list");
             return null;
           }
           else
@@ -1248,11 +1253,12 @@ public class SPSProxyHelper {
         {
           elem.normalize();
           String httpErrorCode = elem.getFirstChild().getNodeValue().trim();
-          if (httpErrorCode.equals("404"))
+          // 302 is what SharePoint returns for external sites
+          if (httpErrorCode.equals("404") || httpErrorCode.equals("302"))
           {
             // Page did not exist
             if (Logging.connectors.isDebugEnabled())
-              Logging.connectors.debug("SharePoint: The page at "+baseUrl+site+" did not exist; assuming library deleted");
+              Logging.connectors.debug("SharePoint: The page at "+baseUrl+site+" did not exist or was external; skipping library");
             return null;
           }
           else if (httpErrorCode.equals("401"))
@@ -1280,7 +1286,7 @@ public class SPSProxyHelper {
           {
             // List did not exist
             if (Logging.connectors.isDebugEnabled())
-              Logging.connectors.debug("SharePoint: The docpath "+docPath+" in site "+site+" did not exist; assuming library deleted");
+              Logging.connectors.debug("SharePoint: The docpath "+docPath+" in site "+site+" did not exist or was external; skipping library");
             return null;
           }
           else
@@ -1555,10 +1561,11 @@ public class SPSProxyHelper {
         {
           elem.normalize();
           String httpErrorCode = elem.getFirstChild().getNodeValue().trim();
-          if (httpErrorCode.equals("404"))
+          // 302 is what SharePoint returns for external sites
+          if (httpErrorCode.equals("404") || httpErrorCode.equals("302"))
           {
             // Page did not exist
-            throw new ManifoldCFException("The site at "+baseUrl+site+" did not exist");
+            throw new ManifoldCFException("The site at "+baseUrl+site+" did not exist or was external; skipping");
           }
           else if (httpErrorCode.equals("401"))
             throw new ManifoldCFException("Crawl user did not authenticate properly, or has insufficient permissions to access "+baseUrl+site+": "+e.getMessage(),e);
@@ -1689,7 +1696,8 @@ public class SPSProxyHelper {
         {
           elem.normalize();
           String httpErrorCode = elem.getFirstChild().getNodeValue().trim();
-          if (httpErrorCode.equals("404"))
+          // 302 is what SharePoint returns for external sites
+          if (httpErrorCode.equals("404") || httpErrorCode.equals("302"))
             return null;
           else if (httpErrorCode.equals("403"))
             throw new ManifoldCFException("Remote procedure exception: "+e.getMessage(),e);
@@ -1822,7 +1830,8 @@ public class SPSProxyHelper {
         {
           elem.normalize();
           String httpErrorCode = elem.getFirstChild().getNodeValue().trim();
-          if (httpErrorCode.equals("404"))
+          // 302 is what SharePoint returns for external sites
+          if (httpErrorCode.equals("404") || httpErrorCode.equals("302"))
             return null;
           else if (httpErrorCode.equals("403"))
             throw new ManifoldCFException("Remote procedure exception: "+e.getMessage(),e);
@@ -2099,7 +2108,8 @@ public class SPSProxyHelper {
         {
           elem.normalize();
           String httpErrorCode = elem.getFirstChild().getNodeValue().trim();
-          if (httpErrorCode.equals("404"))
+          // 302 is what SharePoint returns for external sites
+          if (httpErrorCode.equals("404") || httpErrorCode.equals("302"))
             return null;
           else if (httpErrorCode.equals("403"))
             throw new ManifoldCFException("Remote procedure exception: "+e.getMessage(),e);
@@ -2233,7 +2243,8 @@ public class SPSProxyHelper {
         {
           elem.normalize();
           String httpErrorCode = elem.getFirstChild().getNodeValue().trim();
-          if (httpErrorCode.equals("404"))
+          // 302 is what SharePoint returns for external sites
+          if (httpErrorCode.equals("404") || httpErrorCode.equals("302"))
             return null;
           else if (httpErrorCode.equals("403"))
             throw new ManifoldCFException("Remote procedure exception: "+e.getMessage(),e);
@@ -2394,7 +2405,8 @@ public class SPSProxyHelper {
         {
           elem.normalize();
           String httpErrorCode = elem.getFirstChild().getNodeValue().trim();
-          if (httpErrorCode.equals("404"))
+          // 302 is what SharePoint returns for external sites
+          if (httpErrorCode.equals("404") || httpErrorCode.equals("302"))
             return null;
           else if (httpErrorCode.equals("403"))
             throw new ManifoldCFException("Remote procedure exception: "+e.getMessage(),e);
@@ -2559,7 +2571,8 @@ public class SPSProxyHelper {
         {
           elem.normalize();
           String httpErrorCode = elem.getFirstChild().getNodeValue().trim();
-          if (httpErrorCode.equals("404"))
+          // 302 is what SharePoint returns for external sites
+          if (httpErrorCode.equals("404") || httpErrorCode.equals("302"))
             return null;
           else if (httpErrorCode.equals("403"))
             throw new ManifoldCFException("Remote procedure exception: "+e.getMessage(),e);