Author: jukka
Date: Sun Mar 29 20:10:17 2009
New Revision: 759776
URL: http://svn.apache.org/viewvc?rev=759776&view=rev
Log:
TIKA-204: Use commons-compress for parsing packages
Replace embedded bzip2 and tar parsing classes with a dependency to
commons-compress 1.0-SNAPSHOT.
Removed:
lucene/tika/branches/TIKA-204/src/main/java/org/apache/tika/parser/pkg/bzip2/
lucene/tika/branches/TIKA-204/src/main/java/org/apache/tika/parser/pkg/tar/
Modified:
lucene/tika/branches/TIKA-204/pom.xml
lucene/tika/branches/TIKA-204/src/main/java/org/apache/tika/parser/pkg/Bzip2Parser.java
lucene/tika/branches/TIKA-204/src/main/java/org/apache/tika/parser/pkg/TarParser.java
Modified: lucene/tika/branches/TIKA-204/pom.xml
URL:
http://svn.apache.org/viewvc/lucene/tika/branches/TIKA-204/pom.xml?rev=759776&r1=759775&r2=759776&view=diff
==============================================================================
--- lucene/tika/branches/TIKA-204/pom.xml (original)
+++ lucene/tika/branches/TIKA-204/pom.xml Sun Mar 29 20:10:17 2009
@@ -196,6 +196,11 @@
<version>1.4</version>
</dependency>
<dependency>
+ <groupId>org.apache.commons</groupId>
+ <artifactId>commons-compress</artifactId>
+ <version>1.0-SNAPSHOT</version>
+ </dependency>
+ <dependency>
<groupId>pdfbox</groupId>
<artifactId>pdfbox</artifactId>
<version>0.7.3</version>
Modified:
lucene/tika/branches/TIKA-204/src/main/java/org/apache/tika/parser/pkg/Bzip2Parser.java
URL:
http://svn.apache.org/viewvc/lucene/tika/branches/TIKA-204/src/main/java/org/apache/tika/parser/pkg/Bzip2Parser.java?rev=759776&r1=759775&r2=759776&view=diff
==============================================================================
---
lucene/tika/branches/TIKA-204/src/main/java/org/apache/tika/parser/pkg/Bzip2Parser.java
(original)
+++
lucene/tika/branches/TIKA-204/src/main/java/org/apache/tika/parser/pkg/Bzip2Parser.java
Sun Mar 29 20:10:17 2009
@@ -19,10 +19,10 @@
import java.io.IOException;
import java.io.InputStream;
+import
org.apache.commons.compress.compressors.bzip2.BZip2CompressorInputStream;
import org.apache.commons.io.input.CloseShieldInputStream;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.parser.pkg.bzip2.CBZip2InputStream;
import org.apache.tika.sax.XHTMLContentHandler;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
@@ -38,11 +38,6 @@
public void parse(
InputStream stream, ContentHandler handler, Metadata metadata)
throws IOException, SAXException, TikaException {
- // The CBZip2InputStream class does not want to see the magic BZ header
- if (stream.read() != 'B' || stream.read() != 'Z') {
- throw new TikaException("Invalid BZip2 magic header");
- }
-
metadata.set(Metadata.CONTENT_TYPE, "application/x-bzip");
XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
@@ -51,7 +46,7 @@
// At the end we want to close the bzip2 stream to release any
associated
// resources, but the underlying document stream should not be closed
InputStream gzip =
- new CBZip2InputStream(new CloseShieldInputStream(stream));
+ new BZip2CompressorInputStream(new CloseShieldInputStream(stream));
try {
Metadata entrydata = new Metadata();
String name = metadata.get(Metadata.RESOURCE_NAME_KEY);
Modified:
lucene/tika/branches/TIKA-204/src/main/java/org/apache/tika/parser/pkg/TarParser.java
URL:
http://svn.apache.org/viewvc/lucene/tika/branches/TIKA-204/src/main/java/org/apache/tika/parser/pkg/TarParser.java?rev=759776&r1=759775&r2=759776&view=diff
==============================================================================
---
lucene/tika/branches/TIKA-204/src/main/java/org/apache/tika/parser/pkg/TarParser.java
(original)
+++
lucene/tika/branches/TIKA-204/src/main/java/org/apache/tika/parser/pkg/TarParser.java
Sun Mar 29 20:10:17 2009
@@ -19,11 +19,11 @@
import java.io.IOException;
import java.io.InputStream;
+import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
+import org.apache.commons.compress.archivers.tar.TarArchiveInputStream;
import org.apache.commons.io.input.CloseShieldInputStream;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
-import org.apache.tika.parser.pkg.tar.TarEntry;
-import org.apache.tika.parser.pkg.tar.TarInputStream;
import org.apache.tika.sax.XHTMLContentHandler;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
@@ -46,17 +46,17 @@
// At the end we want to close the tar stream to release any associated
// resources, but the underlying document stream should not be closed
- TarInputStream tar =
- new TarInputStream(new CloseShieldInputStream(stream));
+ TarArchiveInputStream tar =
+ new TarArchiveInputStream(new CloseShieldInputStream(stream));
try {
- TarEntry entry = tar.getNextEntry();
+ TarArchiveEntry entry = tar.getNextTarEntry();
while (entry != null) {
if (!entry.isDirectory()) {
Metadata entrydata = new Metadata();
entrydata.set(Metadata.RESOURCE_NAME_KEY, entry.getName());
parseEntry(tar, xhtml, entrydata);
}
- entry = tar.getNextEntry();
+ entry = tar.getNextTarEntry();
}
} finally {
tar.close();