SOLR-5365: Fix bug with compressed files in ExtractingRequestHandler by upgrading commons-compress to 1.7

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1567824 13f79535-47bb-0310-9956-ffa450edef68

lucene/ivy-versions.properties

@@ -83,7 +83,7 @@ com.sun.jersey.version = 1.8
 /org.antlr/antlr-runtime = 3.5
 /org.apache.ant/ant = 1.8.2
 /org.apache.avro/avro = 1.7.4
-/org.apache.commons/commons-compress = 1.4.1
+/org.apache.commons/commons-compress = 1.7
 /org.apache.derby/derby = 10.9.1.0
 
 org.apache.hadoop.version = 2.2.0

lucene/licenses/commons-compress-1.4.1.jar.sha1

@@ -1 +0,0 @@
-b02e84a993d88568417536240e970c4b809126fd

lucene/licenses/commons-compress-1.7.jar.sha1

@@ -0,0 +1 @@
+ab365c96ee9bc88adcc6fa40d185c8e15a31410d

solr/CHANGES.txt

@@ -322,6 +322,9 @@ Bug Fixes
 * SOLR-5649: Clean up some minor ConnectionManager issues. 
   (Mark Miller, Gregory Chanan)
 
+* SOLR-5365: Fix bug with compressed files in ExtractingRequestHandler by
+  upgrading commons-compress to 1.7 (Jan Høydahl, hossman)
+
 Optimizations
 ----------------------
 

solr/contrib/extraction/src/test/org/apache/solr/handler/extraction/ExtractingRequestHandlerTest.java

@@ -165,6 +165,25 @@ public class ExtractingRequestHandlerTest extends SolrTestCaseJ4 {
     assertQ(req("title:\"Word 2003 Title\""), "//*[@numFound='1']");
     // now 2 of them:
     assertQ(req("extractedContent:\"This is a test of PDF and Word extraction in Solr, it is only a test\""), "//*[@numFound='2']");
+
+    // compressed file
+    loadLocal("extraction/tiny.txt.gz", 
+              "fmap.created", "extractedDate", 
+              "fmap.producer", "extractedProducer",
+              "fmap.creator", "extractedCreator", 
+              "fmap.Keywords", "extractedKeywords",
+              "fmap.Author", "extractedAuthor",
+              "uprefix", "ignored_",
+              "fmap.content", "extractedContent",
+              "fmap.language", "extractedLanguage",
+              "fmap.Last-Modified", "extractedDate",
+              "literal.id", "tiny.txt.gz");
+    assertU(commit());
+    assertQ(req("id:tiny.txt.gz")
+            , "//*[@numFound='1']"
+            , "//*/arr[@name='stream_name']/str[.='tiny.txt.gz']"
+            );
+
   }
 
 

solr/licenses/commons-compress-1.4.1.jar.sha1

@@ -1 +0,0 @@
-b02e84a993d88568417536240e970c4b809126fd

solr/licenses/commons-compress-1.7.jar.sha1

@@ -0,0 +1 @@
+ab365c96ee9bc88adcc6fa40d185c8e15a31410d