Author: jukka
Date: Fri Oct 19 12:53:22 2007
New Revision: 586593
URL: http://svn.apache.org/viewvc?rev=586593&view=rev
Log:
TIKA-83 - Create a org.apache.tika.sax package for SAX utilities
Added:
incubator/tika/trunk/src/main/java/org/apache/tika/sax/
incubator/tika/trunk/src/main/java/org/apache/tika/sax/ContentHandlerDecorator.java
- copied, changed from r585898,
incubator/tika/trunk/src/main/java/org/apache/tika/parser/ContentHandlerDecorator.java
incubator/tika/trunk/src/main/java/org/apache/tika/sax/TeeContentHandler.java
- copied, changed from r585898,
incubator/tika/trunk/src/main/java/org/apache/tika/parser/TeeContentHandler.java
incubator/tika/trunk/src/main/java/org/apache/tika/sax/WriteOutContentHandler.java
- copied, changed from r585898,
incubator/tika/trunk/src/main/java/org/apache/tika/parser/WriteOutContentHandler.java
incubator/tika/trunk/src/main/java/org/apache/tika/sax/XHTMLContentHandler.java
- copied, changed from r585898,
incubator/tika/trunk/src/main/java/org/apache/tika/parser/XHTMLContentHandler.java
Removed:
incubator/tika/trunk/src/main/java/org/apache/tika/parser/ContentHandlerDecorator.java
incubator/tika/trunk/src/main/java/org/apache/tika/parser/TeeContentHandler.java
incubator/tika/trunk/src/main/java/org/apache/tika/parser/WriteOutContentHandler.java
incubator/tika/trunk/src/main/java/org/apache/tika/parser/XHTMLContentHandler.java
Modified:
incubator/tika/trunk/CHANGES.txt
incubator/tika/trunk/src/main/java/org/apache/tika/parser/EmptyParser.java
incubator/tika/trunk/src/main/java/org/apache/tika/parser/ParserPostProcessor.java
incubator/tika/trunk/src/main/java/org/apache/tika/parser/html/HtmlParser.java
incubator/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
incubator/tika/trunk/src/main/java/org/apache/tika/parser/opendocument/OpenOfficeParser.java
incubator/tika/trunk/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
incubator/tika/trunk/src/main/java/org/apache/tika/parser/rtf/RTFParser.java
incubator/tika/trunk/src/main/java/org/apache/tika/parser/txt/TXTParser.java
incubator/tika/trunk/src/main/java/org/apache/tika/parser/xml/XMLParser.java
incubator/tika/trunk/src/main/java/org/apache/tika/utils/ParseUtils.java
incubator/tika/trunk/src/test/java/org/apache/tika/parser/AutoDetectParserTest.java
incubator/tika/trunk/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java
incubator/tika/trunk/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
incubator/tika/trunk/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java
incubator/tika/trunk/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java
incubator/tika/trunk/src/test/java/org/apache/tika/parser/txt/TXTParserTest.java
Modified: incubator/tika/trunk/CHANGES.txt
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/CHANGES.txt?rev=586593&r1=586592&r2=586593&view=diff
==============================================================================
--- incubator/tika/trunk/CHANGES.txt (original)
+++ incubator/tika/trunk/CHANGES.txt Fri Oct 19 12:53:22 2007
@@ -119,3 +119,5 @@
53. TIKA-70 - Better MIME information for the Open Document formats (jukka)
54. TIKA-71 - Remove ParserConfig and ParserFactory (jukka)
+
+55. TIKA-83 - Create a org.apache.tika.sax package for SAX utilities (jukka)
Modified:
incubator/tika/trunk/src/main/java/org/apache/tika/parser/EmptyParser.java
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/src/main/java/org/apache/tika/parser/EmptyParser.java?rev=586593&r1=586592&r2=586593&view=diff
==============================================================================
--- incubator/tika/trunk/src/main/java/org/apache/tika/parser/EmptyParser.java
(original)
+++ incubator/tika/trunk/src/main/java/org/apache/tika/parser/EmptyParser.java
Fri Oct 19 12:53:22 2007
@@ -21,6 +21,7 @@
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
+import org.apache.tika.sax.XHTMLContentHandler;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
Modified:
incubator/tika/trunk/src/main/java/org/apache/tika/parser/ParserPostProcessor.java
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/src/main/java/org/apache/tika/parser/ParserPostProcessor.java?rev=586593&r1=586592&r2=586593&view=diff
==============================================================================
---
incubator/tika/trunk/src/main/java/org/apache/tika/parser/ParserPostProcessor.java
(original)
+++
incubator/tika/trunk/src/main/java/org/apache/tika/parser/ParserPostProcessor.java
Fri Oct 19 12:53:22 2007
@@ -23,6 +23,8 @@
import org.apache.oro.text.regex.MalformedPatternException;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
+import org.apache.tika.sax.TeeContentHandler;
+import org.apache.tika.sax.WriteOutContentHandler;
import org.apache.tika.utils.RegexUtils;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
Modified:
incubator/tika/trunk/src/main/java/org/apache/tika/parser/html/HtmlParser.java
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/src/main/java/org/apache/tika/parser/html/HtmlParser.java?rev=586593&r1=586592&r2=586593&view=diff
==============================================================================
---
incubator/tika/trunk/src/main/java/org/apache/tika/parser/html/HtmlParser.java
(original)
+++
incubator/tika/trunk/src/main/java/org/apache/tika/parser/html/HtmlParser.java
Fri Oct 19 12:53:22 2007
@@ -22,8 +22,8 @@
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.parser.ContentHandlerDecorator;
import org.apache.tika.parser.Parser;
+import org.apache.tika.sax.ContentHandlerDecorator;
import org.cyberneko.html.parsers.SAXParser;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
Modified:
incubator/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java?rev=586593&r1=586592&r2=586593&view=diff
==============================================================================
---
incubator/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
(original)
+++
incubator/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
Fri Oct 19 12:53:22 2007
@@ -29,7 +29,7 @@
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.Parser;
-import org.apache.tika.parser.XHTMLContentHandler;
+import org.apache.tika.sax.XHTMLContentHandler;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
Modified:
incubator/tika/trunk/src/main/java/org/apache/tika/parser/opendocument/OpenOfficeParser.java
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/src/main/java/org/apache/tika/parser/opendocument/OpenOfficeParser.java?rev=586593&r1=586592&r2=586593&view=diff
==============================================================================
---
incubator/tika/trunk/src/main/java/org/apache/tika/parser/opendocument/OpenOfficeParser.java
(original)
+++
incubator/tika/trunk/src/main/java/org/apache/tika/parser/opendocument/OpenOfficeParser.java
Fri Oct 19 12:53:22 2007
@@ -30,8 +30,8 @@
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.Parser;
-import org.apache.tika.parser.XHTMLContentHandler;
import org.apache.tika.parser.xml.XMLParser;
+import org.apache.tika.sax.XHTMLContentHandler;
import org.apache.log4j.Logger;
import org.jdom.Document;
Modified:
incubator/tika/trunk/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/src/main/java/org/apache/tika/parser/pdf/PDFParser.java?rev=586593&r1=586592&r2=586593&view=diff
==============================================================================
---
incubator/tika/trunk/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
(original)
+++
incubator/tika/trunk/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
Fri Oct 19 12:53:22 2007
@@ -24,7 +24,7 @@
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.Parser;
-import org.apache.tika.parser.XHTMLContentHandler;
+import org.apache.tika.sax.XHTMLContentHandler;
import org.pdfbox.pdmodel.PDDocument;
import org.pdfbox.pdmodel.PDDocumentInformation;
Modified:
incubator/tika/trunk/src/main/java/org/apache/tika/parser/rtf/RTFParser.java
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/src/main/java/org/apache/tika/parser/rtf/RTFParser.java?rev=586593&r1=586592&r2=586593&view=diff
==============================================================================
---
incubator/tika/trunk/src/main/java/org/apache/tika/parser/rtf/RTFParser.java
(original)
+++
incubator/tika/trunk/src/main/java/org/apache/tika/parser/rtf/RTFParser.java
Fri Oct 19 12:53:22 2007
@@ -26,7 +26,7 @@
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.Parser;
-import org.apache.tika.parser.XHTMLContentHandler;
+import org.apache.tika.sax.XHTMLContentHandler;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
Modified:
incubator/tika/trunk/src/main/java/org/apache/tika/parser/txt/TXTParser.java
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/src/main/java/org/apache/tika/parser/txt/TXTParser.java?rev=586593&r1=586592&r2=586593&view=diff
==============================================================================
---
incubator/tika/trunk/src/main/java/org/apache/tika/parser/txt/TXTParser.java
(original)
+++
incubator/tika/trunk/src/main/java/org/apache/tika/parser/txt/TXTParser.java
Fri Oct 19 12:53:22 2007
@@ -23,7 +23,7 @@
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.Parser;
-import org.apache.tika.parser.XHTMLContentHandler;
+import org.apache.tika.sax.XHTMLContentHandler;
import org.apache.tika.utils.Utils;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
Modified:
incubator/tika/trunk/src/main/java/org/apache/tika/parser/xml/XMLParser.java
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/src/main/java/org/apache/tika/parser/xml/XMLParser.java?rev=586593&r1=586592&r2=586593&view=diff
==============================================================================
---
incubator/tika/trunk/src/main/java/org/apache/tika/parser/xml/XMLParser.java
(original)
+++
incubator/tika/trunk/src/main/java/org/apache/tika/parser/xml/XMLParser.java
Fri Oct 19 12:53:22 2007
@@ -25,7 +25,7 @@
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.Parser;
-import org.apache.tika.parser.XHTMLContentHandler;
+import org.apache.tika.sax.XHTMLContentHandler;
import org.apache.tika.utils.Utils;
import org.apache.commons.lang.StringUtils;
Copied:
incubator/tika/trunk/src/main/java/org/apache/tika/sax/ContentHandlerDecorator.java
(from r585898,
incubator/tika/trunk/src/main/java/org/apache/tika/parser/ContentHandlerDecorator.java)
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/src/main/java/org/apache/tika/sax/ContentHandlerDecorator.java?p2=incubator/tika/trunk/src/main/java/org/apache/tika/sax/ContentHandlerDecorator.java&p1=incubator/tika/trunk/src/main/java/org/apache/tika/parser/ContentHandlerDecorator.java&r1=585898&r2=586593&rev=586593&view=diff
==============================================================================
---
incubator/tika/trunk/src/main/java/org/apache/tika/parser/ContentHandlerDecorator.java
(original)
+++
incubator/tika/trunk/src/main/java/org/apache/tika/sax/ContentHandlerDecorator.java
Fri Oct 19 12:53:22 2007
@@ -14,7 +14,7 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
-package org.apache.tika.parser;
+package org.apache.tika.sax;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
Copied:
incubator/tika/trunk/src/main/java/org/apache/tika/sax/TeeContentHandler.java
(from r585898,
incubator/tika/trunk/src/main/java/org/apache/tika/parser/TeeContentHandler.java)
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/src/main/java/org/apache/tika/sax/TeeContentHandler.java?p2=incubator/tika/trunk/src/main/java/org/apache/tika/sax/TeeContentHandler.java&p1=incubator/tika/trunk/src/main/java/org/apache/tika/parser/TeeContentHandler.java&r1=585898&r2=586593&rev=586593&view=diff
==============================================================================
---
incubator/tika/trunk/src/main/java/org/apache/tika/parser/TeeContentHandler.java
(original)
+++
incubator/tika/trunk/src/main/java/org/apache/tika/sax/TeeContentHandler.java
Fri Oct 19 12:53:22 2007
@@ -14,7 +14,7 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
-package org.apache.tika.parser;
+package org.apache.tika.sax;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
Copied:
incubator/tika/trunk/src/main/java/org/apache/tika/sax/WriteOutContentHandler.java
(from r585898,
incubator/tika/trunk/src/main/java/org/apache/tika/parser/WriteOutContentHandler.java)
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/src/main/java/org/apache/tika/sax/WriteOutContentHandler.java?p2=incubator/tika/trunk/src/main/java/org/apache/tika/sax/WriteOutContentHandler.java&p1=incubator/tika/trunk/src/main/java/org/apache/tika/parser/WriteOutContentHandler.java&r1=585898&r2=586593&rev=586593&view=diff
==============================================================================
---
incubator/tika/trunk/src/main/java/org/apache/tika/parser/WriteOutContentHandler.java
(original)
+++
incubator/tika/trunk/src/main/java/org/apache/tika/sax/WriteOutContentHandler.java
Fri Oct 19 12:53:22 2007
@@ -14,7 +14,7 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
-package org.apache.tika.parser;
+package org.apache.tika.sax;
import java.io.IOException;
import java.io.Writer;
Copied:
incubator/tika/trunk/src/main/java/org/apache/tika/sax/XHTMLContentHandler.java
(from r585898,
incubator/tika/trunk/src/main/java/org/apache/tika/parser/XHTMLContentHandler.java)
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/src/main/java/org/apache/tika/sax/XHTMLContentHandler.java?p2=incubator/tika/trunk/src/main/java/org/apache/tika/sax/XHTMLContentHandler.java&p1=incubator/tika/trunk/src/main/java/org/apache/tika/parser/XHTMLContentHandler.java&r1=585898&r2=586593&rev=586593&view=diff
==============================================================================
---
incubator/tika/trunk/src/main/java/org/apache/tika/parser/XHTMLContentHandler.java
(original)
+++
incubator/tika/trunk/src/main/java/org/apache/tika/sax/XHTMLContentHandler.java
Fri Oct 19 12:53:22 2007
@@ -14,7 +14,7 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
-package org.apache.tika.parser;
+package org.apache.tika.sax;
import org.apache.tika.metadata.Metadata;
import org.xml.sax.ContentHandler;
Modified:
incubator/tika/trunk/src/main/java/org/apache/tika/utils/ParseUtils.java
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/src/main/java/org/apache/tika/utils/ParseUtils.java?rev=586593&r1=586592&r2=586593&view=diff
==============================================================================
--- incubator/tika/trunk/src/main/java/org/apache/tika/utils/ParseUtils.java
(original)
+++ incubator/tika/trunk/src/main/java/org/apache/tika/utils/ParseUtils.java
Fri Oct 19 12:53:22 2007
@@ -33,7 +33,7 @@
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaMimeKeys;
import org.apache.tika.parser.Parser;
-import org.apache.tika.parser.WriteOutContentHandler;
+import org.apache.tika.sax.WriteOutContentHandler;
import org.xml.sax.SAXException;
/**
Modified:
incubator/tika/trunk/src/test/java/org/apache/tika/parser/AutoDetectParserTest.java
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/src/test/java/org/apache/tika/parser/AutoDetectParserTest.java?rev=586593&r1=586592&r2=586593&view=diff
==============================================================================
---
incubator/tika/trunk/src/test/java/org/apache/tika/parser/AutoDetectParserTest.java
(original)
+++
incubator/tika/trunk/src/test/java/org/apache/tika/parser/AutoDetectParserTest.java
Fri Oct 19 12:53:22 2007
@@ -23,6 +23,7 @@
import org.apache.commons.lang.builder.ReflectionToStringBuilder;
import org.apache.commons.lang.builder.ToStringStyle;
import org.apache.tika.metadata.Metadata;
+import org.apache.tika.sax.WriteOutContentHandler;
import org.xml.sax.ContentHandler;
import junit.framework.TestCase;
Modified:
incubator/tika/trunk/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java?rev=586593&r1=586592&r2=586593&view=diff
==============================================================================
---
incubator/tika/trunk/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java
(original)
+++
incubator/tika/trunk/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java
Fri Oct 19 12:53:22 2007
@@ -26,7 +26,7 @@
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.Parser;
-import org.apache.tika.parser.WriteOutContentHandler;
+import org.apache.tika.sax.WriteOutContentHandler;
import org.xml.sax.SAXException;
public class HtmlParserTest extends TestCase {
Modified:
incubator/tika/trunk/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java?rev=586593&r1=586592&r2=586593&view=diff
==============================================================================
---
incubator/tika/trunk/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
(original)
+++
incubator/tika/trunk/src/test/java/org/apache/tika/parser/microsoft/ExcelParserTest.java
Fri Oct 19 12:53:22 2007
@@ -20,7 +20,7 @@
import java.io.StringWriter;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.parser.WriteOutContentHandler;
+import org.apache.tika.sax.WriteOutContentHandler;
import org.xml.sax.ContentHandler;
import junit.framework.TestCase;
Modified:
incubator/tika/trunk/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java?rev=586593&r1=586592&r2=586593&view=diff
==============================================================================
---
incubator/tika/trunk/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java
(original)
+++
incubator/tika/trunk/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java
Fri Oct 19 12:53:22 2007
@@ -20,7 +20,7 @@
import java.io.StringWriter;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.parser.WriteOutContentHandler;
+import org.apache.tika.sax.WriteOutContentHandler;
import org.xml.sax.ContentHandler;
import junit.framework.TestCase;
Modified:
incubator/tika/trunk/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java?rev=586593&r1=586592&r2=586593&view=diff
==============================================================================
---
incubator/tika/trunk/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java
(original)
+++
incubator/tika/trunk/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java
Fri Oct 19 12:53:22 2007
@@ -20,7 +20,7 @@
import java.io.StringWriter;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.parser.WriteOutContentHandler;
+import org.apache.tika.sax.WriteOutContentHandler;
import org.xml.sax.ContentHandler;
import junit.framework.TestCase;
Modified:
incubator/tika/trunk/src/test/java/org/apache/tika/parser/txt/TXTParserTest.java
URL:
http://svn.apache.org/viewvc/incubator/tika/trunk/src/test/java/org/apache/tika/parser/txt/TXTParserTest.java?rev=586593&r1=586592&r2=586593&view=diff
==============================================================================
---
incubator/tika/trunk/src/test/java/org/apache/tika/parser/txt/TXTParserTest.java
(original)
+++
incubator/tika/trunk/src/test/java/org/apache/tika/parser/txt/TXTParserTest.java
Fri Oct 19 12:53:22 2007
@@ -21,7 +21,7 @@
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.Parser;
-import org.apache.tika.parser.WriteOutContentHandler;
+import org.apache.tika.sax.WriteOutContentHandler;
import junit.framework.TestCase;