SOLR-2480: add ignoreTikaException flag

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1103120 13f79535-47bb-0310-9956-ffa450edef68

solr/contrib/extraction/CHANGES.txt

@@ -22,7 +22,7 @@ to your Solr Home lib directory.  See http://wiki.apache.org/solr/ExtractingRequ
 
 Current Version: Tika 0.8 (released 11/07/2010)
 
-$Id:$
+$Id$
 
 ================== Release 4.0-dev ==================
 
@@ -30,7 +30,8 @@ $Id:$
 
 ================== Release 3.2-dev ==================
 
-(No Changes)
+* SOLR-2480: Add ignoreTikaException flag so that users can ignore TikaException but index
+  meta data. (Shinichiro Abe, koji)
 
 ================== Release 3.1-dev ==================
 

solr/contrib/extraction/src/main/java/org/apache/solr/handler/extraction/ExtractingDocumentLoader.java

@@ -16,20 +16,27 @@
  */
 package org.apache.solr.handler.extraction;
 
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.StringWriter;
+import java.util.Locale;
+
 import org.apache.commons.io.IOUtils;
 import org.apache.solr.common.SolrException;
 import org.apache.solr.common.params.SolrParams;
 import org.apache.solr.common.params.UpdateParams;
 import org.apache.solr.common.util.ContentStream;
 import org.apache.solr.common.util.NamedList;
+import org.apache.solr.handler.ContentStreamLoader;
 import org.apache.solr.request.SolrQueryRequest;
 import org.apache.solr.response.SolrQueryResponse;
 import org.apache.solr.schema.IndexSchema;
 import org.apache.solr.update.AddUpdateCommand;
 import org.apache.solr.update.processor.UpdateRequestProcessor;
-import org.apache.solr.handler.ContentStreamLoader;
 import org.apache.tika.config.TikaConfig;
+import org.apache.tika.exception.TikaException;
 import org.apache.tika.metadata.Metadata;
+import org.apache.tika.mime.MediaType;
 import org.apache.tika.parser.AutoDetectParser;
 import org.apache.tika.parser.ParseContext;
 import org.apache.tika.parser.Parser;
@@ -37,26 +44,24 @@ import org.apache.tika.sax.XHTMLContentHandler;
 import org.apache.tika.sax.xpath.Matcher;
 import org.apache.tika.sax.xpath.MatchingContentHandler;
 import org.apache.tika.sax.xpath.XPathParser;
-import org.apache.tika.exception.TikaException;
-import org.apache.tika.mime.MediaType;
-import org.apache.xml.serialize.OutputFormat;
 import org.apache.xml.serialize.BaseMarkupSerializer;
-import org.apache.xml.serialize.XMLSerializer;
+import org.apache.xml.serialize.OutputFormat;
 import org.apache.xml.serialize.TextSerializer;
+import org.apache.xml.serialize.XMLSerializer;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
 import org.xml.sax.ContentHandler;
 import org.xml.sax.SAXException;
 
-import java.io.IOException;
-import java.io.InputStream;
-import java.io.StringWriter;
-import java.util.Locale;
-
 
 /**
  * The class responsible for loading extracted content into Solr.
  *
  **/
 public class ExtractingDocumentLoader extends ContentStreamLoader {
+
+  private static final Logger log = LoggerFactory.getLogger(ExtractingDocumentLoader.class);
+
   /**
    * Extract Only supported format
    */
@@ -74,6 +79,7 @@ public class ExtractingDocumentLoader extends ContentStreamLoader {
   final IndexSchema schema;
   final SolrParams params;
   final UpdateRequestProcessor processor;
+  final boolean ignoreTikaException;
   protected AutoDetectParser autoDetectParser;
 
   private final AddUpdateCommand templateAdd;
@@ -95,6 +101,8 @@ public class ExtractingDocumentLoader extends ContentStreamLoader {
     //this is lightweight
     autoDetectParser = new AutoDetectParser(config);
     this.factory = factory;
+    
+    ignoreTikaException = params.getBool(ExtractingParams.IGNORE_TIKA_EXCEPTION, false);
   }
 
 
@@ -180,9 +188,17 @@ public class ExtractingDocumentLoader extends ContentStreamLoader {
           parsingHandler = new MatchingContentHandler(handler, matcher);
         } //else leave it as is
 
+        try{
           //potentially use a wrapper handler for parsing, but we still need the SolrContentHandler for getting the document.
           ParseContext context = new ParseContext();//TODO: should we design a way to pass in parse context?
           parser.parse(inputStream, parsingHandler, metadata, context);
+        } catch (TikaException e) {
+          if(ignoreTikaException)
+            log.warn(new StringBuilder("skip extracting text due to ").append(e.getLocalizedMessage())
+                .append(". metadata=").append(metadata.toString()).toString());
+          else
+            throw new SolrException(SolrException.ErrorCode.SERVER_ERROR, e);
+        }
         if (extractOnly == false) {
           addDoc(handler);
         } else {
@@ -202,8 +218,6 @@ public class ExtractingDocumentLoader extends ContentStreamLoader {
         }
       } catch (SAXException e) {
         throw new SolrException(SolrException.ErrorCode.SERVER_ERROR, e);
-      } catch (TikaException e) {
-        throw new SolrException(SolrException.ErrorCode.SERVER_ERROR, e);
       } finally {
         IOUtils.closeQuietly(inputStream);
       }

solr/contrib/extraction/src/main/java/org/apache/solr/handler/extraction/ExtractingParams.java

@@ -28,6 +28,11 @@ public interface ExtractingParams {
    */
   public static final String LOWERNAMES = "lowernames";
 
+  /**
+   * if true, ignore TikaException (give up to extract text but index meta data)
+   */
+  public static final String IGNORE_TIKA_EXCEPTION = "ignoreTikaException";
+
 
   /**
    * The param prefix for mapping Tika metadata to Solr fields.

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

@@ -1,4 +1,4 @@
-package org.apache.solr.handler;
+package org.apache.solr.handler.extraction;
 /**
  * Licensed to the Apache Software Foundation (ASF) under one or more
  * contributor license agreements.  See the NOTICE file distributed with
@@ -16,25 +16,23 @@ package org.apache.solr.handler;
  * limitations under the License.
  */
 
+import java.util.ArrayList;
+import java.util.List;
+
 import org.apache.solr.SolrTestCaseJ4;
-import org.apache.solr.request.LocalSolrQueryRequest;
-import org.apache.solr.response.SolrQueryResponse;
+import org.apache.solr.common.SolrException;
 import org.apache.solr.common.util.ContentStream;
 import org.apache.solr.common.util.ContentStreamBase;
 import org.apache.solr.common.util.NamedList;
-import org.apache.solr.common.SolrException;
+import org.apache.solr.handler.extraction.ExtractingDocumentLoader;
 import org.apache.solr.handler.extraction.ExtractingParams;
 import org.apache.solr.handler.extraction.ExtractingRequestHandler;
-import org.apache.solr.handler.extraction.ExtractingDocumentLoader;
-
+import org.apache.solr.request.LocalSolrQueryRequest;
+import org.apache.solr.response.SolrQueryResponse;
 import org.junit.Before;
 import org.junit.BeforeClass;
 import org.junit.Test;
 
-import java.util.List;
-import java.util.ArrayList;
-import java.io.File;
-
 
 /**
  *
@@ -363,6 +361,40 @@ public class ExtractingRequestHandlerTest extends SolrTestCaseJ4 {
     assertQ(req("wdf_nocase:السلم"), "//result[@numFound=1]");
   }
 
+  @Test
+  public void testTikaExceptionHandling() throws Exception {
+    ExtractingRequestHandler handler = (ExtractingRequestHandler) 
+      h.getCore().getRequestHandler("/update/extract");
+    assertTrue("handler is null and it shouldn't be", handler != null);
+
+    try{
+      loadLocal("password-is-solrcell.docx",
+          "literal.id", "one");
+      fail("TikaException is expected because of trying to extract text from password protected word file.");
+    }
+    catch(Exception expected){}
+    assertU(commit());
+    assertQ(req("*:*"), "//result[@numFound=0]");
+
+    try{
+      loadLocal("password-is-solrcell.docx", "fmap.created", "extractedDate", "fmap.producer", "extractedProducer",
+          "fmap.creator", "extractedCreator", "fmap.Keywords", "extractedKeywords",
+          "fmap.Creation-Date", "extractedDate",
+          "fmap.AAPL:Keywords", "ignored_a",
+          "fmap.xmpTPg:NPages", "ignored_a",
+          "fmap.Author", "extractedAuthor",
+          "fmap.content", "wdf_nocase",
+          "literal.id", "one",
+          "ignoreTikaException", "true",  // set ignore flag
+          "fmap.Last-Modified", "extractedDate");
+    }
+    catch(Exception e){
+      fail("TikaException should be ignored.");
+    }
+    assertU(commit());
+    assertQ(req("*:*"), "//result[@numFound=1]");
+  }
+
   SolrQueryResponse loadLocal(String filename, String... args) throws Exception {
     LocalSolrQueryRequest req = (LocalSolrQueryRequest) req(args);
     try {