Author: jukka
Date: Wed Dec 19 02:57:58 2007
New Revision: 605511

URL: http://svn.apache.org/viewvc?rev=605511&view=rev
Log:
JCR-1247: Add Warnlog on Extraction Failure
    - Catch and log exceptions in all extractors
    - Introduced the required slf4j dependency

Modified:
    jackrabbit/trunk/jackrabbit-text-extractors/pom.xml
    jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/CompositeTextExtractor.java
    jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/HTMLTextExtractor.java
    jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsExcelTextExtractor.java
    jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsPowerPointTextExtractor.java
    jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsWordTextExtractor.java
    jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/OpenOfficeTextExtractor.java
    jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/PdfTextExtractor.java
    jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/PlainTextExtractor.java
    jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/RTFTextExtractor.java
    jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/XMLTextExtractor.java

Modified: jackrabbit/trunk/jackrabbit-text-extractors/pom.xml
URL: http://svn.apache.org/viewvc/jackrabbit/trunk/jackrabbit-text-extractors/pom.xml?rev=605511&r1=605510&r2=605511&view=diff
==============================================================================
--- jackrabbit/trunk/jackrabbit-text-extractors/pom.xml (original)
+++ jackrabbit/trunk/jackrabbit-text-extractors/pom.xml Wed Dec 19 02:57:58 2007
@@ -75,6 +75,15 @@
       <artifactId>xercesImpl</artifactId>
     </dependency>
     <dependency>
+      <groupId>org.slf4j</groupId>
+      <artifactId>slf4j-api</artifactId>
+    </dependency>
+    <dependency>
+      <groupId>org.slf4j</groupId>
+      <artifactId>slf4j-log4j12</artifactId>
+      <scope>test</scope>
+    </dependency>
+    <dependency>
       <groupId>junit</groupId>
       <artifactId>junit</artifactId>
       <scope>test</scope>

Modified: jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/CompositeTextExtractor.java
URL: http://svn.apache.org/viewvc/jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/CompositeTextExtractor.java?rev=605511&r1=605510&r2=605511&view=diff
==============================================================================
--- jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/CompositeTextExtractor.java (original)
+++ jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/CompositeTextExtractor.java Wed Dec 19 02:57:58 2007
@@ -24,6 +24,9 @@
 import java.util.Map;
 import java.util.Set;
 
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
 /**
  * Composite text extractor. This class presents a unified interface
  * for a set of {@link TextExtractor} instances. The composite extractor
@@ -33,6 +36,12 @@
 public class CompositeTextExtractor implements TextExtractor {
 
     /**
+     * Logger instance.
+     */
+    private static final Logger logger =
+        LoggerFactory.getLogger(CompositeTextExtractor.class);
+
+    /**
      * Configured {@link TextExtractor} instances, keyed by content types.
      */
     private final Map extractors = new HashMap();
@@ -77,9 +86,15 @@
             throws IOException {
         TextExtractor extractor = (TextExtractor) extractors.get(type);
         if (extractor != null) {
-            return extractor.extractText(stream, type, encoding);
+            try {
+                return extractor.extractText(stream, type, encoding);
+            } catch (RuntimeException e) {
+                logger.warn("Failed to extract text content", e);
+                return new StringReader("");
+            }
         } else {
             stream.close();
+            logger.info("No extractor available for content type {}", type);
             return new StringReader("");
         }
     }

Modified: jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/HTMLTextExtractor.java
URL: http://svn.apache.org/viewvc/jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/HTMLTextExtractor.java?rev=605511&r1=605510&r2=605511&view=diff
==============================================================================
--- jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/HTMLTextExtractor.java (original)
+++ jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/HTMLTextExtractor.java Wed Dec 19 02:57:58 2007
@@ -16,6 +16,8 @@
  */
 package org.apache.jackrabbit.extractor;
 
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
 import org.xml.sax.InputSource;
 import org.xml.sax.helpers.DefaultHandler;
 
@@ -36,6 +38,12 @@
 public class HTMLTextExtractor extends AbstractTextExtractor {
 
     /**
+     * Logger instance.
+     */
+    private static final Logger logger =
+        LoggerFactory.getLogger(HTMLTextExtractor.class);
+
+    /**
      * Creates a new <code>HTMLTextExtractor</code> instance.
      */
     public HTMLTextExtractor() {
@@ -61,8 +69,10 @@
 
             return new StringReader(parser.getContents());
         } catch (TransformerConfigurationException e) {
+            logger.warn("Failed to extract HTML text content", e);
             return new StringReader("");
         } catch (TransformerException e) {
+            logger.warn("Failed to extract HTML text content", e);
             return new StringReader("");
         } finally {
             stream.close();

Modified: jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsExcelTextExtractor.java
URL: http://svn.apache.org/viewvc/jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsExcelTextExtractor.java?rev=605511&r1=605510&r2=605511&view=diff
==============================================================================
--- jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsExcelTextExtractor.java (original)
+++ jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsExcelTextExtractor.java Wed Dec 19 02:57:58 2007
@@ -21,12 +21,15 @@
 import org.apache.poi.hssf.usermodel.HSSFSheet;
 import org.apache.poi.hssf.usermodel.HSSFRow;
 import org.apache.poi.hssf.usermodel.HSSFCell;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
 
 import java.io.Reader;
 import java.io.InputStream;
 import java.io.IOException;
 import java.io.CharArrayWriter;
 import java.io.CharArrayReader;
+import java.io.StringReader;
 import java.util.Iterator;
 
 /**
@@ -35,6 +38,12 @@
 public class MsExcelTextExtractor extends AbstractTextExtractor {
 
     /**
+     * Logger instance.
+     */
+    private static final Logger logger =
+        LoggerFactory.getLogger(MsExcelTextExtractor.class);
+
+    /**
      * Force loading of dependent class.
      */
     static {
@@ -90,6 +99,9 @@
             }
 
             return new CharArrayReader(writer.toCharArray());
+        } catch (RuntimeException e) {
+            logger.warn("Failed to extract Excel text content", e);
+            return new StringReader("");
         } finally {
             stream.close();
         }

Modified: jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsPowerPointTextExtractor.java
URL: http://svn.apache.org/viewvc/jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsPowerPointTextExtractor.java?rev=605511&r1=605510&r2=605511&view=diff
==============================================================================
--- jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsPowerPointTextExtractor.java (original)
+++ jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsPowerPointTextExtractor.java Wed Dec 19 02:57:58 2007
@@ -21,6 +21,8 @@
 import org.apache.poi.poifs.eventfilesystem.POIFSReaderEvent;
 import org.apache.poi.poifs.filesystem.DocumentInputStream;
 import org.apache.poi.util.LittleEndian;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
 
 import java.io.Reader;
 import java.io.InputStream;
@@ -29,6 +31,7 @@
 import java.io.ByteArrayOutputStream;
 import java.io.InputStreamReader;
 import java.io.ByteArrayInputStream;
+import java.io.StringReader;
 
 /**
  * Text extractor for Microsoft PowerPoint presentations.
@@ -36,6 +39,12 @@
 public class MsPowerPointTextExtractor extends AbstractTextExtractor {
 
     /**
+     * Logger instance.
+     */
+    private static final Logger logger =
+        LoggerFactory.getLogger(MsPowerPointTextExtractor.class);
+
+    /**
      * Force loading of dependent class.
      */
     static {
@@ -66,6 +75,9 @@
             reader.read(stream);
             return new InputStreamReader(
                     new ByteArrayInputStream(baos.toByteArray()));
+        } catch (RuntimeException e) {
+            logger.warn("Failed to extract PowerPoint text content", e);
+            return new StringReader("");
         } finally {
             stream.close();
         }

Modified: jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsWordTextExtractor.java
URL: http://svn.apache.org/viewvc/jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsWordTextExtractor.java?rev=605511&r1=605510&r2=605511&view=diff
==============================================================================
--- jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsWordTextExtractor.java (original)
+++ jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/MsWordTextExtractor.java Wed Dec 19 02:57:58 2007
@@ -16,6 +16,8 @@
  */
 package org.apache.jackrabbit.extractor;
 
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
 import org.textmining.text.extraction.WordExtractor;
 
 import java.io.Reader;
@@ -29,6 +31,12 @@
 public class MsWordTextExtractor extends AbstractTextExtractor {
 
     /**
+     * Logger instance.
+     */
+    private static final Logger logger =
+        LoggerFactory.getLogger(MsWordTextExtractor.class);
+
+    /**
      * Force loading of dependent class.
      */
     static {
@@ -60,6 +68,7 @@
 
             return new StringReader(text);
         } catch (Exception e) {
+            logger.warn("Failed to extract Word text content", e);
             return new StringReader("");
         } finally {
             stream.close();

Modified: jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/OpenOfficeTextExtractor.java
URL: http://svn.apache.org/viewvc/jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/OpenOfficeTextExtractor.java?rev=605511&r1=605510&r2=605511&view=diff
==============================================================================
--- jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/OpenOfficeTextExtractor.java (original)
+++ jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/OpenOfficeTextExtractor.java Wed Dec 19 02:57:58 2007
@@ -16,6 +16,8 @@
  */
 package org.apache.jackrabbit.extractor;
 
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
 import org.xml.sax.helpers.DefaultHandler;
 import org.xml.sax.Attributes;
 import org.xml.sax.SAXException;
@@ -38,6 +40,12 @@
 public class OpenOfficeTextExtractor extends AbstractTextExtractor {
 
     /**
+     * Logger instance.
+     */
+    private static final Logger logger =
+        LoggerFactory.getLogger(OpenOfficeTextExtractor.class);
+
+    /**
      * Creates a new <code>OpenOfficeTextExtractor</code> instance.
      */
     public OpenOfficeTextExtractor() {
@@ -82,8 +90,10 @@
 
             return new StringReader(contentHandler.getContent());
         } catch (ParserConfigurationException e) {
+            logger.warn("Failed to extract OpenOffice text content", e);
             return new StringReader("");
         } catch (SAXException e) {
+            logger.warn("Failed to extract OpenOffice text content", e);
             return new StringReader("");
         } finally {
             stream.close();

Modified: jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/PdfTextExtractor.java
URL: http://svn.apache.org/viewvc/jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/PdfTextExtractor.java?rev=605511&r1=605510&r2=605511&view=diff
==============================================================================
--- jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/PdfTextExtractor.java (original)
+++ jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/PdfTextExtractor.java Wed Dec 19 02:57:58 2007
@@ -19,6 +19,8 @@
 import org.pdfbox.pdfparser.PDFParser;
 import org.pdfbox.pdmodel.PDDocument;
 import org.pdfbox.util.PDFTextStripper;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
 
 import java.io.Reader;
 import java.io.InputStream;
@@ -34,6 +36,12 @@
 public class PdfTextExtractor extends AbstractTextExtractor {
 
     /**
+     * Logger instance.
+     */
+    private static final Logger logger =
+        LoggerFactory.getLogger(PdfTextExtractor.class);
+
+    /**
      * Force loading of dependent class.
      */
     static {
@@ -80,6 +88,7 @@
         } catch (Exception e) {
             // it may happen that PDFParser throws a runtime
             // exception when parsing certain pdf documents
+            logger.warn("Failed to extract PDF text content", e);
             return new StringReader("");
         } finally {
             stream.close();

Modified: jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/PlainTextExtractor.java
URL: http://svn.apache.org/viewvc/jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/PlainTextExtractor.java?rev=605511&r1=605510&r2=605511&view=diff
==============================================================================
--- jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/PlainTextExtractor.java (original)
+++ jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/PlainTextExtractor.java Wed Dec 19 02:57:58 2007
@@ -23,12 +23,21 @@
 import java.io.StringReader;
 import java.io.UnsupportedEncodingException;
 
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
 /**
  * Text extractor for plain text.
  */
 public class PlainTextExtractor extends AbstractTextExtractor {
 
     /**
+     * Logger instance.
+     */
+    private static final Logger logger =
+        LoggerFactory.getLogger(PlainTextExtractor.class);
+
+    /**
      * Creates a new <code>PlainTextExtractor</code> instance.
      */
     public PlainTextExtractor() {
@@ -59,6 +68,7 @@
                 return new InputStreamReader(stream);
             }
         } catch (UnsupportedEncodingException e) {
+            logger.warn("Failed to extract plain text content", e);
             stream.close();
             return new StringReader("");
         }

Modified: jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/RTFTextExtractor.java
URL: http://svn.apache.org/viewvc/jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/RTFTextExtractor.java?rev=605511&r1=605510&r2=605511&view=diff
==============================================================================
--- jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/RTFTextExtractor.java (original)
+++ jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/RTFTextExtractor.java Wed Dec 19 02:57:58 2007
@@ -19,6 +19,10 @@
 import javax.swing.text.BadLocationException;
 import javax.swing.text.DefaultStyledDocument;
 import javax.swing.text.rtf.RTFEditorKit;
+
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
 import java.io.Reader;
 import java.io.InputStream;
 import java.io.IOException;
@@ -30,6 +34,12 @@
 public class RTFTextExtractor extends AbstractTextExtractor {
 
     /**
+     * Logger instance.
+     */
+    private static final Logger logger =
+        LoggerFactory.getLogger(RTFTextExtractor.class);
+
+    /**
      * Creates a new <code>RTFTextExtractor</code> instance.
      */
     public RTFTextExtractor() {
@@ -52,7 +62,8 @@
             String text = doc.getText(0, doc.getLength());
             return new StringReader(text);
         } catch (BadLocationException e) {
-            throw new IOException(e.getMessage());
+            logger.warn("Failed to extract RTF text content", e);
+            return new StringReader("");
         } finally {
             stream.close();
         }

Modified: jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/XMLTextExtractor.java
URL: http://svn.apache.org/viewvc/jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/XMLTextExtractor.java?rev=605511&r1=605510&r2=605511&view=diff
==============================================================================
--- jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/XMLTextExtractor.java (original)
+++ jackrabbit/trunk/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/XMLTextExtractor.java Wed Dec 19 02:57:58 2007
@@ -28,6 +28,8 @@
 import javax.xml.parsers.SAXParser;
 import javax.xml.parsers.SAXParserFactory;
 
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
 import org.xml.sax.InputSource;
 import org.xml.sax.SAXException;
 import org.xml.sax.XMLReader;
@@ -45,6 +47,12 @@
 public class XMLTextExtractor extends AbstractTextExtractor {
 
     /**
+     * Logger instance.
+     */
+    private static final Logger logger =
+        LoggerFactory.getLogger(XMLTextExtractor.class);
+
+    /**
      * Creates a new <code>XMLTextExtractor</code> instance.
      */
     public XMLTextExtractor() {
@@ -93,8 +101,10 @@
 
             return new CharArrayReader(writer.toCharArray());
         } catch (ParserConfigurationException e) {
+            logger.warn("Failed to extract XML text content", e);
             return new StringReader("");
         } catch (SAXException e) {
+            logger.warn("Failed to extract XML text content", e);
             return new StringReader("");
         } finally {
             stream.close();