nutch-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Lewis John Mcgibbney <lewis.mcgibb...@gmail.com>
Subject Re: svn commit: r1387363 - in /nutch/branches/2.1: CHANGES.txt build.xml pom.xml
Date Wed, 19 Sep 2012 19:50:48 GMT
Hi All,

As you will have seen I managed to branch 2.x into 2.1 and forward
port Seb's most recent commit.

I am however quite concerned about a recent thread on user@ [0] which
looked kinda dodgy to me and I would therefore like to hold off a wee
while until this is either resolved or whether compatability between
2.x & the gora-cassandra module is is need of some attention.
It is unfortunate that the Cassandra module is so under utilised but I
suppose it is the nature of the data and use cases people have thats
why traditional use cases make sense for HBase adoption.

Anyway, please bear with me and I'll update this thread once we get
further down the line.

Best

Lewis

[0] http://www.mail-archive.com/user%40nutch.apache.org/msg07606.html

On Wed, Sep 19, 2012 at 2:52 AM, Mattmann, Chris A (388J)
<chris.a.mattmann@jpl.nasa.gov> wrote:
> Lewis you beat me to it, you ROCK!
>
> Cheers,
> Chris
>
> On Sep 18, 2012, at 5:11 PM, <lewismc@apache.org>
>  <lewismc@apache.org> wrote:
>
>> Author: lewismc
>> Date: Tue Sep 18 21:11:06 2012
>> New Revision: 1387363
>>
>> URL: http://svn.apache.org/viewvc?rev=1387363&view=rev
>> Log:
>> forward port of NUTCH-1415
>>
>> Modified:
>>    nutch/branches/2.1/CHANGES.txt
>>    nutch/branches/2.1/build.xml
>>    nutch/branches/2.1/pom.xml
>>
>> Modified: nutch/branches/2.1/CHANGES.txt
>> URL: http://svn.apache.org/viewvc/nutch/branches/2.1/CHANGES.txt?rev=1387363&r1=1387362&r2=1387363&view=diff
>> ==============================================================================
>> --- nutch/branches/2.1/CHANGES.txt (original)
>> +++ nutch/branches/2.1/CHANGES.txt Tue Sep 18 21:11:06 2012
>> @@ -3,6 +3,8 @@ Nutch Change Log
>> Release 2.1 (19/09/2012) ddmmyyyy
>> Full Jira Report - https://issues.apache.org/jira/secure/ReleaseNote.jspa?projectId=10680&version=12321040
>>
>> +* NUTCH-1415 release packages to contain top level folder apache-nutch-x.x (snagel)
>> +
>> * NUTCH-1432 property storage.schema does not work anymore, should be storage.schema.webpage
and storage.schema.host (lewismc)
>>
>> * NUTCH-1468 Redirects that are external links not adhering to db.ignore.external.links
(Matt MacDonald via ferdy)
>>
>> Modified: nutch/branches/2.1/build.xml
>> URL: http://svn.apache.org/viewvc/nutch/branches/2.1/build.xml?rev=1387363&r1=1387362&r2=1387363&view=diff
>> ==============================================================================
>> --- nutch/branches/2.1/build.xml (original)
>> +++ nutch/branches/2.1/build.xml Tue Sep 18 21:11:06 2012
>> @@ -700,14 +700,13 @@
>>   <!-- ================================================================== -->
>>   <target name="tar-src" depends="package-src" description="--> generate src.tar.gz
distribution package">
>>     <tar compression="gzip" longfile="gnu"
>> -      destfile="${src.dist.version.dir}.tar.gz" basedir="${src.dist.version.dir}">
>> -      <tarfileset dir="${dist.dir}" mode="664">
>> -     <exclude name="${src.dist.version.dir}/bin/*" />
>> -     <exclude name="${src.dist.version.dir}/runtime/*" />
>> -        <include name="${src.dist.version.dir}/**" />
>> +      destfile="${src.dist.version.dir}.tar.gz">
>> +      <tarfileset dir="${src.dist.version.dir}" mode="664" prefix="${final.name}">
>> +        <exclude name="src/bin/*" />
>> +        <include name="**" />
>>       </tarfileset>
>> -      <tarfileset dir="${dist.dir}" mode="755">
>> -        <include name="${src.dist.version.dir}/bin/*" />
>> +      <tarfileset dir="${src.dist.version.dir}" mode="755" prefix="${final.name}">
>> +        <include name="src/bin/*" />
>>       </tarfileset>
>>     </tar>
>>   </target>
>> @@ -717,13 +716,13 @@
>>   <!-- ================================================================== -->
>>   <target name="tar-bin" depends="package-bin" description="--> generate bin.tar.gz
distribution package">
>>     <tar compression="gzip" longfile="gnu"
>> -      destfile="${bin.dist.version.dir}.tar.gz" basedir="${bin.dist.version.dir}">
>> -      <tarfileset dir="${dist.dir}" mode="664">
>> -     <exclude name="${bin.dist.version.dir}/bin/*" />
>> -        <include name="${bin.dist.version.dir}/**" />
>> +      destfile="${bin.dist.version.dir}.tar.gz">
>> +      <tarfileset dir="${bin.dist.version.dir}" mode="664" prefix="${final.name}">
>> +        <exclude name="bin/*" />
>> +        <include name="**" />
>>       </tarfileset>
>> -      <tarfileset dir="${dist.dir}" mode="755">
>> -        <include name="${bin.dist.version.dir}/bin/*" />
>> +      <tarfileset dir="${bin.dist.version.dir}" mode="755" prefix="${final.name}">
>> +        <include name="bin/*" />
>>       </tarfileset>
>>     </tar>
>>   </target>
>> @@ -733,14 +732,13 @@
>>   <!-- ================================================================== -->
>>   <target name="zip-src" depends="package-src" description="--> generate src.zip
distribution package">
>>    <zip compress="true" casesensitive="yes"
>> -   destfile="${src.dist.version.dir}.zip" basedir="${src.dist.version.dir}">
>> -   <zipfileset dir="${dist.dir}" filemode="664">
>> -       <exclude name="${src.dist.version.dir}/bin/*" />
>> -       <exclude name="${src.dist.version.dir}/runtime/*" />
>> -       <include name="${src.dist.version.dir}/**" />
>> +     destfile="${src.dist.version.dir}.zip">
>> +   <zipfileset dir="${src.dist.version.dir}" filemode="664" prefix="${final.name}">
>> +       <exclude name="src/bin/*" />
>> +       <include name="**" />
>>    </zipfileset>
>> -   <zipfileset dir="${dist.dir}" filemode="755">
>> -       <include name="${src.dist.version.dir}/bin/*" />
>> +   <zipfileset dir="${src.dist.version.dir}" filemode="755" prefix="${final.name}">
>> +       <include name="src/bin/*" />
>>    </zipfileset>
>>    </zip>
>>   </target>
>> @@ -750,13 +748,13 @@
>>   <!-- ================================================================== -->
>>   <target name="zip-bin" depends="package-bin" description="--> generate bin.zip
distribution package">
>>    <zip compress="true" casesensitive="yes"
>> -   destfile="${bin.dist.version.dir}.zip" basedir="${bin.dist.version.dir}">
>> -   <zipfileset dir="${dist.dir}" filemode="664">
>> -       <exclude name="${bin.dist.version.dir}/bin/*" />
>> -       <include name="${bin.dist.version.dir}/**" />
>> +     destfile="${bin.dist.version.dir}.zip">
>> +   <zipfileset dir="${bin.dist.version.dir}" filemode="664" prefix="${final.name}">
>> +       <exclude name="bin/*" />
>> +       <include name="**" />
>>    </zipfileset>
>> -   <zipfileset dir="${dist.dir}" filemode="755">
>> -       <include name="${bin.dist.version.dir}/bin/*" />
>> +   <zipfileset dir="${bin.dist.version.dir}" filemode="755" prefix="${final.name}">
>> +       <include name="bin/*" />
>>    </zipfileset>
>>    </zip>
>>   </target>
>>
>> Modified: nutch/branches/2.1/pom.xml
>> URL: http://svn.apache.org/viewvc/nutch/branches/2.1/pom.xml?rev=1387363&r1=1387362&r2=1387363&view=diff
>> ==============================================================================
>> --- nutch/branches/2.1/pom.xml (original)
>> +++ nutch/branches/2.1/pom.xml Tue Sep 18 21:11:06 2012
>> @@ -22,7 +22,7 @@
>>   <groupId>org.apache.nutch</groupId>
>>   <artifactId>nutch</artifactId>
>>   <packaging>jar</packaging>
>> -  <version>2.0</version>
>> +  <version>2.1</version>
>>   <name>Apache Nutch</name>
>>   <url>http://nutch.apache.org</url>
>>   <licenses>
>> @@ -109,6 +109,12 @@
>>         </build>
>>         <dependencies>
>>                 <dependency>
>> +                        <groupId>org.elasticsearch</groupId>
>> +                        <artifactId>elasticsearch</artifactId>
>> +                        <version>0.19.4</version>
>> +                        <optional>true</optional>
>> +                </dependency>
>> +                <dependency>
>>                         <groupId>org.apache.solr</groupId>
>>                         <artifactId>solr-solrj</artifactId>
>>                         <version>3.4.0</version>
>> @@ -165,7 +171,7 @@
>>                 <dependency>
>>                         <groupId>org.apache.gora</groupId>
>>                         <artifactId>gora-core</artifactId>
>> -                        <version>0.2</version>
>> +                        <version>0.2.1</version>
>>                         <optional>true</optional>
>>                 </dependency>
>>                 <dependency>
>>
>>
>
>
> ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
> Chris Mattmann, Ph.D.
> Senior Computer Scientist
> NASA Jet Propulsion Laboratory Pasadena, CA 91109 USA
> Office: 171-266B, Mailstop: 171-246
> Email: chris.a.mattmann@nasa.gov
> WWW:   http://sunset.usc.edu/~mattmann/
> ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
> Adjunct Assistant Professor, Computer Science Department
> University of Southern California, Los Angeles, CA 90089 USA
> ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
>



-- 
Lewis

Mime
View raw message