You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@nutch.apache.org by le...@apache.org on 2014/06/05 02:18:02 UTC
svn commit: r1600546 - in /nutch/branches/2.x: CHANGES.txt
conf/gora-accumulo-mapping.xml conf/gora-cassandra-mapping.xml
conf/gora-hbase-mapping.xml conf/gora.properties
Author: lewismc
Date: Thu Jun 5 00:18:02 2014
New Revision: 1600546
URL: http://svn.apache.org/r1600546
Log:
NUTCH-1781 Update gora-*-mapping.xml and gora.proeprties to reflect Gora 0.4
Modified:
nutch/branches/2.x/CHANGES.txt
nutch/branches/2.x/conf/gora-accumulo-mapping.xml
nutch/branches/2.x/conf/gora-cassandra-mapping.xml
nutch/branches/2.x/conf/gora-hbase-mapping.xml
nutch/branches/2.x/conf/gora.properties
Modified: nutch/branches/2.x/CHANGES.txt
URL: http://svn.apache.org/viewvc/nutch/branches/2.x/CHANGES.txt?rev=1600546&r1=1600545&r2=1600546&view=diff
==============================================================================
--- nutch/branches/2.x/CHANGES.txt (original)
+++ nutch/branches/2.x/CHANGES.txt Thu Jun 5 00:18:02 2014
@@ -2,6 +2,8 @@ Nutch Change Log
Current Development
+* NUTCH-1781 Update gora-*-mapping.xml and gora.proeprties to reflect Gora 0.4 (lewismc)
+
* NUTCH-1768 Upgrade to ElasticSearch 1.1.0 (jnioche)
* NUTCH-1634 readdb -stats shows the result twice (kaveh minooie via jnioche)
Modified: nutch/branches/2.x/conf/gora-accumulo-mapping.xml
URL: http://svn.apache.org/viewvc/nutch/branches/2.x/conf/gora-accumulo-mapping.xml?rev=1600546&r1=1600545&r2=1600546&view=diff
==============================================================================
--- nutch/branches/2.x/conf/gora-accumulo-mapping.xml (original)
+++ nutch/branches/2.x/conf/gora-accumulo-mapping.xml Thu Jun 5 00:18:02 2014
@@ -15,10 +15,19 @@
See the License for the specific language governing permissions and
limitations under the License.
-->
+
+<!-- A comprehensive account of the entire gora-accumulo mapping
+ options can be found on the Gora website at:
+ http://gora.apache.org/current/gora-accumulo.html
+ Users are strongly advised to consult this documentation
+ prior to working with the default mapping configuration
+ provided below.
+-->
+
<gora-orm>
<table name="webpage">
- <family name="p" /> <!-- This can also have params like compression, bloom filters -->
+ <family name="p" />
<family name="f" />
<family name="s" />
<family name="il" />
Modified: nutch/branches/2.x/conf/gora-cassandra-mapping.xml
URL: http://svn.apache.org/viewvc/nutch/branches/2.x/conf/gora-cassandra-mapping.xml?rev=1600546&r1=1600545&r2=1600546&view=diff
==============================================================================
--- nutch/branches/2.x/conf/gora-cassandra-mapping.xml (original)
+++ nutch/branches/2.x/conf/gora-cassandra-mapping.xml Thu Jun 5 00:18:02 2014
@@ -31,7 +31,9 @@
The value used here for 'gc_grace_seconds' of '0' is ONLY VIABLE FOR SINGLE NODE
CLUSTER. you should update this value according to your cluster configuration.
https://wiki.apache.org/cassandra/StorageConfiguration
-
+
+ More information on gora-cassandra configuration and mapping's can be found
+ at http://gora.apache.org/current/gora-cassandra.html
-->
<gora-orm>
Modified: nutch/branches/2.x/conf/gora-hbase-mapping.xml
URL: http://svn.apache.org/viewvc/nutch/branches/2.x/conf/gora-hbase-mapping.xml?rev=1600546&r1=1600545&r2=1600546&view=diff
==============================================================================
--- nutch/branches/2.x/conf/gora-hbase-mapping.xml (original)
+++ nutch/branches/2.x/conf/gora-hbase-mapping.xml Thu Jun 5 00:18:02 2014
@@ -14,11 +14,34 @@
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
+-->i
+
+<!--
+In addition to family 'name' and 'maxVersions' attributes,
+individual table families can ve defined with several other
+attributes such as
+ compression="$$$" - the compression option to use in HBase.
+ blockCache="$$$" - an LRU cache that contains three levels of block priority
+ to allow for scan-resistance and in-memory ColumnFamilies.
+ blockSize="$$$" - The blocksize can be configured for each ColumnFamily in
+ a table, and this defaults to 64k.
+ bloomFilter="$$$" - Bloom Filters can be enabled per-ColumnFamily.
+ maxVersions="$$$" - The maximum number of row versions to store is configured
+ per column family via HColumnDescriptor.
+ timeToLive="$$$" - ColumnFamilies can set a TTL length in seconds, and HBase
+ will automatically delete rows once the expiration time is
+ reached.
+ inMemory="$$$" - ColumnFamilies can optionally be defined as in-memory.
+
+You should consult the current Gora gora-hbase documentation
+for further information on properties and mapping configurtion.
+http://gora.apache.org/current/gora-hbase.html
-->
+
<gora-orm>
<table name="webpage">
- <family name="p" maxVersions="1"/> <!-- This can also have params like compression, bloom filters -->
+ <family name="p" maxVersions="1"/>
<family name="f" maxVersions="1"/>
<family name="s" maxVersions="1"/>
<family name="il" maxVersions="1"/>
Modified: nutch/branches/2.x/conf/gora.properties
URL: http://svn.apache.org/viewvc/nutch/branches/2.x/conf/gora.properties?rev=1600546&r1=1600545&r2=1600546&view=diff
==============================================================================
--- nutch/branches/2.x/conf/gora.properties (original)
+++ nutch/branches/2.x/conf/gora.properties Thu Jun 5 00:18:02 2014
@@ -20,10 +20,10 @@
# Default SqlStore properties #
###############################
-gora.sqlstore.jdbc.driver=org.hsqldb.jdbc.JDBCDriver
-gora.sqlstore.jdbc.url=jdbc:hsqldb:hsql://localhost/nutchtest
-gora.sqlstore.jdbc.user=sa
-gora.sqlstore.jdbc.password=
+#gora.sqlstore.jdbc.driver=org.hsqldb.jdbc.JDBCDriver
+#gora.sqlstore.jdbc.url=jdbc:hsqldb:hsql://localhost/nutchtest
+#gora.sqlstore.jdbc.user=sa
+#gora.sqlstore.jdbc.password=
################################
# Default AvroStore properties #
@@ -56,6 +56,9 @@ gora.sqlstore.jdbc.password=
# Available since Gora 0.2. Defaults to disabled.
# hbase.client.autoflush.default=false
+# HBase client cache that improves the scan in HBase (default 0)
+# gora.datastore.scanner.caching=1000
+
#############################
# CassandraStore properties #
#############################
@@ -73,6 +76,7 @@ gora.sqlstore.jdbc.password=
# AccumuloStore properties #
############################
#gora.datastore.default=org.apache.gora.accumulo.store.AccumuloStore
+#gora.accumulo.mapping.file=gora-accumulo-mapping.xml
#gora.datastore.accumulo.mock=true
#gora.datastore.accumulo.instance=a14
#gora.datastore.accumulo.zookeepers=localhost