diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index 0951352a0fb..4e0e6af2ab8 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -106,6 +106,11 @@ Bug Fixes
 * SOLR-5107: Fixed NPE when using numTerms=0 in LukeRequestHandler
   (Ahmet Arslan, hossman)
 
+* SOLR-4679, SOLR-4908, SOLR-5124: Text extracted from HTML or PDF files
+  using Solr Cell was missing ignorable whitespace, which is inserted by
+  TIKA for convenience to support plain text extraction without using the
+  HTML elements. This bug resulted in glued words.  (hossman, Uwe Schindler)
+
 Optimizations
 ----------------------
 
diff --git a/solr/contrib/extraction/src/java/org/apache/solr/handler/extraction/SolrContentHandler.java b/solr/contrib/extraction/src/java/org/apache/solr/handler/extraction/SolrContentHandler.java
index ad84ad54d88..f0cc5d0a57e 100644
--- a/solr/contrib/extraction/src/java/org/apache/solr/handler/extraction/SolrContentHandler.java
+++ b/solr/contrib/extraction/src/java/org/apache/solr/handler/extraction/SolrContentHandler.java
@@ -303,6 +303,13 @@ public class SolrContentHandler extends DefaultHandler implements ExtractingPara
     bldrStack.getLast().append(chars, offset, length);
   }
 
+  /**
+   * Treat the same as any other characters
+   */
+  @Override
+  public void ignorableWhitespace(char[] chars, int offset, int length) throws SAXException {
+    characters(chars, offset, length);
+  }
 
   /**
    * Can be used to transform input values based on their {@link org.apache.solr.schema.SchemaField}
diff --git a/solr/contrib/extraction/src/test-files/extraction/simple.html b/solr/contrib/extraction/src/test-files/extraction/simple.html
index f33cf92677e..656b656b6ab 100644
--- a/solr/contrib/extraction/src/test-files/extraction/simple.html
+++ b/solr/contrib/extraction/src/test-files/extraction/simple.html
@@ -6,6 +6,7 @@
 <p>
   Here is some text
 </p>
+<p>distinct<br/>words</p>
 <div>Here is some text in a div</div>
 <div>This has a <a href="http://www.apache.org">link</a>.</div>
 </body>
diff --git a/solr/contrib/extraction/src/test/org/apache/solr/handler/extraction/ExtractingRequestHandlerTest.java b/solr/contrib/extraction/src/test/org/apache/solr/handler/extraction/ExtractingRequestHandlerTest.java
index dbdb370348d..eabddd6b398 100644
--- a/solr/contrib/extraction/src/test/org/apache/solr/handler/extraction/ExtractingRequestHandlerTest.java
+++ b/solr/contrib/extraction/src/test/org/apache/solr/handler/extraction/ExtractingRequestHandlerTest.java
@@ -88,6 +88,10 @@ public class ExtractingRequestHandlerTest extends SolrTestCaseJ4 {
     assertU(commit());
     assertQ(req("title:Welcome"), "//*[@numFound='1']");
 
+    assertQ(req("extractedContent:distinctwords"),      "//*[@numFound='0']");
+    assertQ(req("extractedContent:distinct"),           "//*[@numFound='1']");
+    assertQ(req("extractedContent:words"),              "//*[@numFound='2']");
+    assertQ(req("extractedContent:\"distinct words\""), "//*[@numFound='1']");
 
     loadLocal("extraction/simple.html",
       "literal.id","simple2",