From 7f1700400ba2b7464ace0c1896c736e151e3fb4b Mon Sep 17 00:00:00 2001
From: Hunter Stern <hunter@archive.org>
Date: Fri, 1 Aug 2014 17:37:31 -0700
Subject: [PATCH 1/2] Allow xml extractor to handle urls in CDATA.

---
 .../main/java/org/archive/modules/extractor/ExtractorXML.java  | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/modules/src/main/java/org/archive/modules/extractor/ExtractorXML.java b/modules/src/main/java/org/archive/modules/extractor/ExtractorXML.java
index 64a1d500..92baf805 100644
--- a/modules/src/main/java/org/archive/modules/extractor/ExtractorXML.java
+++ b/modules/src/main/java/org/archive/modules/extractor/ExtractorXML.java
@@ -56,7 +56,8 @@ public class ExtractorXML extends ContentExtractor {
         Logger.getLogger(ExtractorXML.class.getName());
 
     static final Pattern XML_URI_EXTRACTOR = Pattern
-            .compile("(?s)[\"\'>]\\s*([^<>\\s'\"@]+)\\s*[\"\'<]");
+            .compile("(?s)[\"\'>]\\s*(?:<!\\[CDATA\\[)?([^<>\\s\'\"@]+)\\s*(?:\\]\\]>)?[\"\'<]");    
+    
     // GROUPS:
     // (G1) possible uri
 

From 27d632159d6addc2836f1c41076bc18904367121 Mon Sep 17 00:00:00 2001
From: Hunter Stern <hunter@archive.org>
Date: Mon, 1 Sep 2014 10:13:25 -0700
Subject: [PATCH 2/2] Add test case for ExtractorXML

---
 .../modules/extractor/ExtractorXMLTest.java   | 58 ++++++++++++++++++-
 1 file changed, 55 insertions(+), 3 deletions(-)

diff --git a/modules/src/test/java/org/archive/modules/extractor/ExtractorXMLTest.java b/modules/src/test/java/org/archive/modules/extractor/ExtractorXMLTest.java
index a77842a4..9933298b 100644
--- a/modules/src/test/java/org/archive/modules/extractor/ExtractorXMLTest.java
+++ b/modules/src/test/java/org/archive/modules/extractor/ExtractorXMLTest.java
@@ -18,15 +18,67 @@
  */
 package org.archive.modules.extractor;
 
-import org.archive.modules.ProcessorTestBase;
+import java.util.ArrayList;
+import java.util.Collection;
+import java.util.List;
+
+import org.archive.modules.CrawlMetadata;
+import org.archive.modules.CrawlURI;
+import org.archive.modules.extractor.StringExtractorTestBase.TestData;
+import org.archive.net.UURI;
+import org.archive.net.UURIFactory;
+import org.archive.util.Recorder;
 
 /**
  * Unit test for {@link ExtractorXML}.
  *
  * @author pjack
  */
-public class ExtractorXMLTest extends ProcessorTestBase {
+public class ExtractorXMLTest extends StringExtractorTestBase {
 
-    // TODO TESTME!
+    final public static String[] VALID_TEST_DATA = new String[] {
+        "<link>http://conservation.org</link>",
+        "http://conservation.org",
+
+        "<CI:imagePath><![CDATA[http://sp10.conservation.org/CIFMGPhotos/790x444_skerry_gallery_02.jpg]]></CI:imagePath>",
+        "http://sp10.conservation.org/CIFMGPhotos/790x444_skerry_gallery_02.jpg",
+        
+    };
     
+    @Override
+    protected String[] getValidTestData() {
+        return VALID_TEST_DATA;
+    }
+
+    @Override
+    protected Extractor makeExtractor() {
+        ExtractorXML result = new ExtractorXML();
+        UriErrorLoggerModule ulm = new UnitTestUriLoggerModule();  
+        result.setLoggerModule(ulm);
+        return result;
+    }
+
+    protected ExtractorXML getExtractor() {
+        return (ExtractorXML) extractor;
+    }
+    
+    @Override
+    protected Collection<TestData> makeData(String content, String destURI)
+    throws Exception {
+        List<TestData> result = new ArrayList<TestData>();
+        UURI src = UURIFactory.getInstance("http://www.archive.org/start/");
+        CrawlURI euri = new CrawlURI(src, null, null, 
+        		LinkContext.SPECULATIVE_MISC);
+        Recorder recorder = createRecorder(content, "UTF-8");
+        euri.setContentType("text/xml");
+        euri.setRecorder(recorder);
+        euri.setContentSize(content.length());
+                
+        UURI dest = UURIFactory.getInstance(destURI);
+        CrawlURI link = euri.createCrawlURI(dest, LinkContext.SPECULATIVE_MISC, Hop.SPECULATIVE);
+        result.add(new TestData(euri, link));
+        
+        return result;
+    }
+
 }