Merge pull request #14626 from rmuir/epub

minor attachments cleanups: IDE test support and EPUB format

plugins/mapper-attachments/build.gradle

@@ -55,4 +55,5 @@ compileJava.options.compilerArgs << '-Xlint:-cast,-deprecation,-rawtypes'
 forbiddenPatterns {
   exclude '**/*.docx'
   exclude '**/*.pdf'
+  exclude '**/*.epub'
 }

plugins/mapper-attachments/src/main/java/org/elasticsearch/mapper/attachments/TikaImpl.java

@@ -67,6 +67,7 @@ final class TikaImpl {
         new org.apache.tika.parser.odf.OpenDocumentParser(),
         new org.apache.tika.parser.iwork.IWorkPackageParser(),
         new org.apache.tika.parser.xml.DcXMLParser(),
+        new org.apache.tika.parser.epub.EpubParser(),
     };
     
     /** autodetector based on this subset */

plugins/mapper-attachments/src/test/java/org/elasticsearch/mapper/attachments/VariousDocTests.java

@@ -96,6 +96,14 @@ public class VariousDocTests extends AttachmentUnitTestCase {
         assertParseable("text-in-english.txt");
         testMapper("text-in-english.txt", false);
     }
+    
+    /**
+     * Test for .epub
+     */
+    public void testEpubDocument() throws Exception {
+        assertParseable("testEPUB.epub");
+        testMapper("testEPUB.epub", false);
+    }
 
     /**
      * Test for ASCIIDOC

test-framework/build.gradle

@@ -33,7 +33,10 @@ dependencies {
   compile('org.hamcrest:hamcrest-all:1.3') {
     exclude group: 'org.hamcrest', module: 'hamcrest-core'
   }
-  compile "org.apache.httpcomponents:httpclient:${versions.httpclient}"
+  compile("org.apache.httpcomponents:httpclient:${versions.httpclient}") {
+    exclude group: 'commons-codec', module: 'commons-codec'
+  }
+  compile "commons-codec:commons-codec:1.9"
 }
 
 compileJava.options.compilerArgs << '-Xlint:-cast,-deprecation,-fallthrough,-overrides,-rawtypes,-serial,-try,-unchecked'