Author: jukka
Date: Fri May 22 16:43:52 2009
New Revision: 777613
URL: http://svn.apache.org/viewvc?rev=777613&view=rev
Log:
TIKA-230: [PATCH] Parent pom
Moved more generic settings to the parent POM and brought some per-component
dependency settings back to child POM level. The parent POM should only contain
settings shared by all Tika components.
Leverage ${project.groupId} and ${project.version} when referencing other Tika
components.
Use a ${poi.version} setting to keep all POI dependencies in sync.
Removed the simple commons-lang dependency from AutoDetectParserTest.
Modified:
lucene/tika/trunk/pom.xml
lucene/tika/trunk/tika-app/pom.xml
lucene/tika/trunk/tika-core/pom.xml
lucene/tika/trunk/tika-parent/pom.xml
lucene/tika/trunk/tika-parsers/pom.xml
lucene/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/AutoDetectParserTest.java
Modified: lucene/tika/trunk/pom.xml
URL:
http://svn.apache.org/viewvc/lucene/tika/trunk/pom.xml?rev=777613&r1=777612&r2=777613&view=diff
==============================================================================
--- lucene/tika/trunk/pom.xml (original)
+++ lucene/tika/trunk/pom.xml Fri May 22 16:43:52 2009
@@ -26,144 +26,19 @@
<modelVersion>4.0.0</modelVersion>
<parent>
- <groupId>org.apache</groupId>
- <artifactId>apache</artifactId>
- <version>4</version>
+ <groupId>org.apache.tika</groupId>
+ <artifactId>tika-parent</artifactId>
+ <version>0.4-SNAPSHOT</version>
+ <relativePath>tika-parent/pom.xml</relativePath>
</parent>
- <groupId>org.apache.tika</groupId>
<artifactId>tika-reactor</artifactId>
- <version>0.4-SNAPSHOT</version>
<packaging>pom</packaging>
<name>Apache Tika reactor</name>
<!-- Keep on a single line, see http://jira.codehaus.org/browse/MJAR-39 -->
<description>Tika is a toolkit for detecting and extracting metadata and
structured text content from various documents using existing parser
libraries.</description>
- <url>http://lucene.apache.org/tika/</url>
-
- <issueManagement>
- <system>JIRA</system>
- <url>https://issues.apache.org/jira/browse/TIKA</url>
- </issueManagement>
-
- <mailingLists>
- <mailingList>
- <name>Development mailing list</name>
- <subscribe>[email protected]</subscribe>
- <unsubscribe>[email protected]</unsubscribe>
- <post>[email protected]</post>
-
<archive>http://mail-archives.apache.org/mod_mbox/lucene-tika-dev/</archive>
- <otherArchives>
-
<otherArchive>http://www.mail-archive.com/[email protected]/</otherArchive>
-
<otherArchive>http://www.mail-archive.com/[email protected]/</otherArchive>
-
<otherArchive>http://www.nabble.com/Apache-Tika---Development-f20913.html</otherArchive>
-
<otherArchive>http://news.gmane.org/gmane.comp.apache.tika.devel</otherArchive>
- <otherArchive>http://tika.markmail.org/</otherArchive>
- </otherArchives>
- </mailingList>
- <mailingList>
- <name>Commit mailing list</name>
- <subscribe>[email protected]</subscribe>
- <unsubscribe>[email protected]</unsubscribe>
- <post>[email protected]</post>
-
<archive>http://mail-archives.apache.org/mod_mbox/lucene-tika-commits/</archive>
- <otherArchives>
-
<otherArchive>http://www.mail-archive.com/[email protected]/</otherArchive>
-
<otherArchive>http://www.mail-archive.com/[email protected]/</otherArchive>
- </otherArchives>
- </mailingList>
- <mailingList>
- <name>User mailing list</name>
- <subscribe>[email protected]</subscribe>
- <unsubscribe>[email protected]</unsubscribe>
- <post>[email protected]</post>
-
<archive>http://mail-archives.apache.org/mod_mbox/lucene-tika-user/</archive>
- <otherArchives>
-
<otherArchive>http://www.mail-archive.com/[email protected]/</otherArchive>
- </otherArchives>
- </mailingList>
- </mailingLists>
-
- <developers>
- <developer>
- <name>Rida Benjelloun</name>
- <id>ridabenjelloun</id>
- <email>[email protected]</email>
- <roles>
- <role>committer</role>
- </roles>
- </developer>
- <developer>
- <name>Keith Bennett</name>
- <id>kbennett</id>
- <roles>
- <role>committer</role>
- </roles>
- </developer>
- <developer>
- <name>Mark Harwood</name>
- <id>mharwood</id>
- <roles>
- <role>committer</role>
- </roles>
- </developer>
- <developer>
- <name>Chris A. Mattmann</name>
- <id>mattmann</id>
- <email>[email protected]</email>
- <url>http://people.apache.org/~mattmann/</url>
- <organization>NASA Jet Propulsion Laboratory</organization>
- <organizationUrl>http://www.jpl.nasa.gov</organizationUrl>
- <timezone>-8</timezone>
- <properties/>
- <roles>
- <role>committer</role>
- </roles>
- </developer>
- <developer>
- <name>Dave Meikle</name>
- <id>dmeikle</id>
- <roles>
- <role>committer</role>
- </roles>
- </developer>
- <developer>
- <name>Sami Siren</name>
- <id>siren</id>
- <roles>
- <role>committer</role>
- </roles>
- </developer>
- <developer>
- <name>Jukka Zitting</name>
- <id>jukka</id>
- <roles>
- <role>committer</role>
- </roles>
- </developer>
- </developers>
- <contributors>
- <contributor>
- <name>Doug Cutting</name>
- <roles>
- <role>mentor</role>
- </roles>
- </contributor>
- <contributor>
- <name>Bertrand Delacretaz</name>
- <roles>
- <role>mentor</role>
- </roles>
- </contributor>
- <contributor>
- <name>Niall Pemberton</name>
- <roles>
- <role>emeritus</role>
- </roles>
- </contributor>
- </contributors>
-
<scm>
<connection>
scm:svn:http://svn.apache.org/repos/asf/lucene/tika/trunk
Modified: lucene/tika/trunk/tika-app/pom.xml
URL:
http://svn.apache.org/viewvc/lucene/tika/trunk/tika-app/pom.xml?rev=777613&r1=777612&r2=777613&view=diff
==============================================================================
--- lucene/tika/trunk/tika-app/pom.xml (original)
+++ lucene/tika/trunk/tika-app/pom.xml Fri May 22 16:43:52 2009
@@ -32,17 +32,14 @@
<relativePath>../tika-parent/pom.xml</relativePath>
</parent>
- <groupId>org.apache.tika</groupId>
<artifactId>tika-app</artifactId>
- <version>0.4-SNAPSHOT</version>
-
<name>Apache Tika application</name>
<dependencies>
<dependency>
- <groupId>org.apache.tika</groupId>
+ <groupId>${project.groupId}</groupId>
<artifactId>tika-parsers</artifactId>
- <version>0.4-SNAPSHOT</version>
+ <version>${project.version}</version>
</dependency>
</dependencies>
Modified: lucene/tika/trunk/tika-core/pom.xml
URL:
http://svn.apache.org/viewvc/lucene/tika/trunk/tika-core/pom.xml?rev=777613&r1=777612&r2=777613&view=diff
==============================================================================
--- lucene/tika/trunk/tika-core/pom.xml (original)
+++ lucene/tika/trunk/tika-core/pom.xml Fri May 22 16:43:52 2009
@@ -32,10 +32,7 @@
<relativePath>../tika-parent/pom.xml</relativePath>
</parent>
- <groupId>org.apache.tika</groupId>
<artifactId>tika-core</artifactId>
- <version>0.4-SNAPSHOT</version>
-
<name>Apache Tika core</name>
<!-- Keep on a single line, see http://jira.codehaus.org/browse/MJAR-39 -->
<description>Tika is a toolkit for detecting and extracting metadata and
structured text content from various documents using existing parser
libraries.</description>
@@ -44,25 +41,25 @@
<dependency>
<groupId>commons-lang</groupId>
<artifactId>commons-lang</artifactId>
- <optional/>
+ <version>2.1</version>
+ <optional>true</optional>
</dependency>
<dependency>
<groupId>commons-logging</groupId>
<artifactId>commons-logging</artifactId>
+ <version>1.0.4</version>
</dependency>
<dependency>
<groupId>commons-io</groupId>
<artifactId>commons-io</artifactId>
+ <version>1.4</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
- <type>jar</type>
<scope>test</scope>
</dependency>
</dependencies>
- <build/>
-
</project>
Modified: lucene/tika/trunk/tika-parent/pom.xml
URL:
http://svn.apache.org/viewvc/lucene/tika/trunk/tika-parent/pom.xml?rev=777613&r1=777612&r2=777613&view=diff
==============================================================================
--- lucene/tika/trunk/tika-parent/pom.xml (original)
+++ lucene/tika/trunk/tika-parent/pom.xml Fri May 22 16:43:52 2009
@@ -36,84 +36,140 @@
<version>0.4-SNAPSHOT</version>
<packaging>pom</packaging>
- <name>Apache Tika Parent pom</name>
+ <name>Apache Tika parent</name>
<!-- Keep on a single line, see http://jira.codehaus.org/browse/MJAR-39 -->
<description>Tika is a toolkit for detecting and extracting metadata and
structured text content from various documents using existing parser
libraries.</description>
+ <url>http://lucene.apache.org/tika/</url>
+
+ <issueManagement>
+ <system>JIRA</system>
+ <url>https://issues.apache.org/jira/browse/TIKA</url>
+ </issueManagement>
+
+ <mailingLists>
+ <mailingList>
+ <name>Development mailing list</name>
+ <subscribe>[email protected]</subscribe>
+ <unsubscribe>[email protected]</unsubscribe>
+ <post>[email protected]</post>
+
<archive>http://mail-archives.apache.org/mod_mbox/lucene-tika-dev/</archive>
+ <otherArchives>
+
<otherArchive>http://www.mail-archive.com/[email protected]/</otherArchive>
+
<otherArchive>http://www.mail-archive.com/[email protected]/</otherArchive>
+
<otherArchive>http://www.nabble.com/Apache-Tika---Development-f20913.html</otherArchive>
+
<otherArchive>http://news.gmane.org/gmane.comp.apache.tika.devel</otherArchive>
+ <otherArchive>http://tika.markmail.org/</otherArchive>
+ </otherArchives>
+ </mailingList>
+ <mailingList>
+ <name>Commit mailing list</name>
+ <subscribe>[email protected]</subscribe>
+ <unsubscribe>[email protected]</unsubscribe>
+ <post>[email protected]</post>
+
<archive>http://mail-archives.apache.org/mod_mbox/lucene-tika-commits/</archive>
+ <otherArchives>
+
<otherArchive>http://www.mail-archive.com/[email protected]/</otherArchive>
+
<otherArchive>http://www.mail-archive.com/[email protected]/</otherArchive>
+ </otherArchives>
+ </mailingList>
+ <mailingList>
+ <name>User mailing list</name>
+ <subscribe>[email protected]</subscribe>
+ <unsubscribe>[email protected]</unsubscribe>
+ <post>[email protected]</post>
+
<archive>http://mail-archives.apache.org/mod_mbox/lucene-tika-user/</archive>
+ <otherArchives>
+
<otherArchive>http://www.mail-archive.com/[email protected]/</otherArchive>
+ </otherArchives>
+ </mailingList>
+ </mailingLists>
+
+ <developers>
+ <developer>
+ <name>Rida Benjelloun</name>
+ <id>ridabenjelloun</id>
+ <email>[email protected]</email>
+ <roles>
+ <role>committer</role>
+ </roles>
+ </developer>
+ <developer>
+ <name>Keith Bennett</name>
+ <id>kbennett</id>
+ <roles>
+ <role>committer</role>
+ </roles>
+ </developer>
+ <developer>
+ <name>Mark Harwood</name>
+ <id>mharwood</id>
+ <roles>
+ <role>committer</role>
+ </roles>
+ </developer>
+ <developer>
+ <name>Chris A. Mattmann</name>
+ <id>mattmann</id>
+ <email>[email protected]</email>
+ <url>http://people.apache.org/~mattmann/</url>
+ <organization>NASA Jet Propulsion Laboratory</organization>
+ <organizationUrl>http://www.jpl.nasa.gov</organizationUrl>
+ <timezone>-8</timezone>
+ <properties/>
+ <roles>
+ <role>committer</role>
+ </roles>
+ </developer>
+ <developer>
+ <name>Dave Meikle</name>
+ <id>dmeikle</id>
+ <roles>
+ <role>committer</role>
+ </roles>
+ </developer>
+ <developer>
+ <name>Sami Siren</name>
+ <id>siren</id>
+ <roles>
+ <role>committer</role>
+ </roles>
+ </developer>
+ <developer>
+ <name>Jukka Zitting</name>
+ <id>jukka</id>
+ <roles>
+ <role>committer</role>
+ </roles>
+ </developer>
+ </developers>
+ <contributors>
+ <contributor>
+ <name>Doug Cutting</name>
+ <roles>
+ <role>mentor</role>
+ </roles>
+ </contributor>
+ <contributor>
+ <name>Bertrand Delacretaz</name>
+ <roles>
+ <role>mentor</role>
+ </roles>
+ </contributor>
+ <contributor>
+ <name>Niall Pemberton</name>
+ <roles>
+ <role>emeritus</role>
+ </roles>
+ </contributor>
+ </contributors>
+
<dependencyManagement>
<dependencies>
<dependency>
- <groupId>commons-lang</groupId>
- <artifactId>commons-lang</artifactId>
- <version>2.1</version>
- <optional />
- </dependency>
- <dependency>
- <groupId>commons-logging</groupId>
- <artifactId>commons-logging</artifactId>
- <version>1.0.4</version>
- </dependency>
- <dependency>
- <groupId>commons-io</groupId>
- <artifactId>commons-io</artifactId>
- <version>1.4</version>
- </dependency>
- <dependency>
- <groupId>pdfbox</groupId>
- <artifactId>pdfbox</artifactId>
- <version>0.7.3</version>
- </dependency>
- <dependency>
- <groupId>org.apache.poi</groupId>
- <artifactId>poi</artifactId>
- <version>3.5-beta5</version>
- </dependency>
- <dependency>
- <groupId>org.apache.poi</groupId>
- <artifactId>poi-scratchpad</artifactId>
- <version>3.5-beta5</version>
- </dependency>
- <dependency>
- <groupId>org.apache.poi</groupId>
- <artifactId>poi-ooxml</artifactId>
- <version>3.5-beta5</version>
- <exclusions>
- <exclusion>
- <groupId>stax</groupId>
- <artifactId>stax-api</artifactId>
- </exclusion>
- </exclusions>
- </dependency>
- <dependency>
- <groupId>org.apache.geronimo.specs</groupId>
- <artifactId>geronimo-stax-api_1.0_spec</artifactId>
- <version>1.0</version>
- </dependency>
- <dependency>
- <groupId>net.sourceforge.nekohtml</groupId>
- <artifactId>nekohtml</artifactId>
- <version>1.9.9</version>
- </dependency>
- <dependency>
- <groupId>com.ibm.icu</groupId>
- <artifactId>icu4j</artifactId>
- <version>3.8</version>
- </dependency>
- <dependency>
- <groupId>asm</groupId>
- <artifactId>asm</artifactId>
- <version>3.1</version>
- </dependency>
- <dependency>
- <groupId>log4j</groupId>
- <artifactId>log4j</artifactId>
- <version>1.2.14</version>
- </dependency>
- <dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>3.8.1</version>
- <type>jar</type>
<scope>test</scope>
</dependency>
</dependencies>
Modified: lucene/tika/trunk/tika-parsers/pom.xml
URL:
http://svn.apache.org/viewvc/lucene/tika/trunk/tika-parsers/pom.xml?rev=777613&r1=777612&r2=777613&view=diff
==============================================================================
--- lucene/tika/trunk/tika-parsers/pom.xml (original)
+++ lucene/tika/trunk/tika-parsers/pom.xml Fri May 22 16:43:52 2009
@@ -32,58 +32,73 @@
<relativePath>../tika-parent/pom.xml</relativePath>
</parent>
- <groupId>org.apache.tika</groupId>
<artifactId>tika-parsers</artifactId>
- <version>0.4-SNAPSHOT</version>
-
<name>Apache Tika parsers</name>
+ <properties>
+ <poi.version>3.5-beta5</poi.version>
+ </properties>
+
<dependencies>
<dependency>
- <groupId>org.apache.tika</groupId>
+ <groupId>${project.groupId}</groupId>
<artifactId>tika-core</artifactId>
- <version>0.4-SNAPSHOT</version>
+ <version>${project.version}</version>
</dependency>
<dependency>
<groupId>pdfbox</groupId>
<artifactId>pdfbox</artifactId>
+ <version>0.7.3</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi</artifactId>
+ <version>${poi.version}</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-scratchpad</artifactId>
+ <version>${poi.version}</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml</artifactId>
+ <version>${poi.version}</version>
+ <exclusions>
+ <exclusion>
+ <groupId>stax</groupId>
+ <artifactId>stax-api</artifactId>
+ </exclusion>
+ </exclusions>
</dependency>
<dependency>
<groupId>org.apache.geronimo.specs</groupId>
<artifactId>geronimo-stax-api_1.0_spec</artifactId>
+ <version>1.0</version>
</dependency>
<dependency>
<groupId>net.sourceforge.nekohtml</groupId>
<artifactId>nekohtml</artifactId>
+ <version>1.9.9</version>
</dependency>
<dependency>
<groupId>com.ibm.icu</groupId>
<artifactId>icu4j</artifactId>
+ <version>3.8</version>
</dependency>
<dependency>
<groupId>asm</groupId>
<artifactId>asm</artifactId>
+ <version>3.1</version>
</dependency>
<dependency>
<groupId>log4j</groupId>
<artifactId>log4j</artifactId>
+ <version>1.2.14</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
- <type>jar</type>
<scope>test</scope>
</dependency>
</dependencies>
Modified:
lucene/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/AutoDetectParserTest.java
URL:
http://svn.apache.org/viewvc/lucene/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/AutoDetectParserTest.java?rev=777613&r1=777612&r2=777613&view=diff
==============================================================================
---
lucene/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/AutoDetectParserTest.java
(original)
+++
lucene/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/AutoDetectParserTest.java
Fri May 22 16:43:52 2009
@@ -19,13 +19,10 @@
import java.io.IOException;
import java.io.InputStream;
-import org.apache.commons.lang.builder.ReflectionToStringBuilder;
-import org.apache.commons.lang.builder.ToStringStyle;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.sax.BodyContentHandler;
import org.xml.sax.ContentHandler;
-import org.xml.sax.SAXException;
import junit.framework.TestCase;
@@ -120,7 +117,7 @@
// assertAutoDetect(resource, null, type, null, content);
// assertAutoDetect(resource, null, type, wrongMimeType, content);
- final String badResource = "a.xyz";
+// final String badResource = "a.xyz";
// assertAutoDetect(resource, badResource, type, type,
content);
// assertAutoDetect(resource, badResource, type, null,
content);
// assertAutoDetect(resource, badResource, type, wrongMimeType,
content);
@@ -217,20 +214,22 @@
/**
* Produces a string like the following:
*
- * org.apache.tika.parser.autodetectparsertest$testpar...@8fff06[
- * resourceRealName=/test-documents/testEXCEL.xls
- * resourceStatedName=<null>
- * realType=application/vnd.ms-excel
- * statedType=<null>
- * expectedContentFragment=Sample Excel Worksheet
- * ]
- *
- * @return
+ * <pre>
+ * Test parameters:
+ * resourceRealName = /test-documents/testEXCEL.xls
+ * resourceStatedName = null
+ * realType = application/vnd.ms-excel
+ * statedType = null
+ * expectedContentFragment = Sample Excel Worksheet
+ * </pre>
*/
-
public String toString() {
- return ReflectionToStringBuilder.toString(
- this, ToStringStyle.MULTI_LINE_STYLE);
+ return "Test parameters:\n"
+ + " resourceRealName = " + resourceRealName + "\n"
+ + " resourceStatedName = " + resourceStatedName + "\n"
+ + " realType = " + realType + "\n"
+ + " statedType = " + statedType + "\n"
+ + " expectedContentFragment = " + realType + "\n";
}
}
}
