Changes between Version 2 and Version 3 of waue/2010/0128

Timestamp:

Jan 29, 2010, 5:34:14 PM (14 years ago)

Author:

waue

Comment:

--

waue/2010/0128

@@ -14 +14 @@
 
 [http://mail-archives.apache.org/mod_mbox/hadoop-hbase-user/200908.mbox/%3C73d592f60908180339j3231f7f5w688260109ab3463@mail.gmail.com%3E]
+
+= what is secondary index (distinguished in primary index) =
+
+Explain the what is primary and secondary index.
+
+When you activate an object say ODS / DSO, the system automatically generate an index based on the key fields and this is primary index.
+
+In addition if you wish to create more indexes , then they are called secondary indexes.
+
+The primary index is distinguished from the secondary indexes of a table. The primary index contains the key fields of the table and a pointer to the non-key fields of the table. The primary index is created automatically when the table is created in the database.
+
+You can also create further indexes on a table. These are called secondary indexes. This is necessary if the table is frequently accessed in a way that does not take advantage of the sorting of the primary index for the access. Different indexes on the same table are distinguished with a three-place index identifier. 
+
+ = hbase's secondary index detail = 
 
 {{{
@@ -58 +72 @@
 }}}
 
-Hadoop HBase數據導入和索引測試 
-[http://bbs.telewiki.cn/blog/qianling/entry/hadoop_hbase%E6%95%B0%E6%8D%AE%E5%AF%BC%E5%85%A5%E5%92%8C%E7%B4%A2%E5%BC%95%E6%B5%8B%E8%AF%95]
-
-
-
-= Secondary indexes in HBase =
+
+ = Secondary indexes in HBase 程式碼說明 (v 0.19 ) =
+ == conf/hbase-site.xml ==
+{{{
+#!text
+$HBASE_INSTALL_DIR/conf/hbase-site.xml and add the following property to it.
+
+    <property>
+        <name>hbase.regionserver.class</name>
+        <value>org.apache.hadoop.hbase.ipc.IndexedRegionInterface</value>
+    </property>
+
+    <property>
+        <name>hbase.regionserver.impl</name>
+        <value>
+        org.apache.hadoop.hbase.regionserver.tableindexed.IndexedRegionServer
+        </value>
+    </property>
+}}}
+
+ == Adding secondary index while creating table  ==
+
+{{{
+#!java
+    HBaseConfiguration conf = new HBaseConfiguration();
+    conf.addResource(new Path("/opt/hbase-0.19.3/conf/hbase-site.xml"));
+
+    HTableDescriptor desc = new HTableDescriptor("test_table");
+
+    desc.addFamily(new HColumnDescriptor("columnfamily1:"));
+    desc.addFamily(new HColumnDescriptor("columnfamily2:"));
+
+    desc.addIndex(new IndexSpecification("column1",
+        Bytes.toBytes("columnfamily1:column1")));
+    desc.addIndex(new IndexSpecification("column2",
+        Bytes.toBytes("columnfamily1:column2")));
+
+    IndexedTableAdmin admin = null;
+    admin = new IndexedTableAdmin(conf);
+
+    admin.createTable(desc);
+
+}}}
+
+ ==  Adding index in an existing table ==
+{{{
+#!java
+    HBaseConfiguration conf = new HBaseConfiguration();
+    conf.addResource(new Path("/opt/hbase-0.19.3/conf/hbase-site.xml"));
+
+    IndexedTableAdmin admin = null;
+    admin = new IndexedTableAdmin(conf);
+
+    admin.addIndex(Bytes.toBytes("test_table"), new IndexSpecification("column2",
+    Bytes.toBytes("columnfamily1:column2")));
+}}}
+
+ == Deleting existing index from a table  ==
+{{{
+#!java
+   HBaseConfiguration conf = new HBaseConfiguration();
+    conf.addResource(new Path("/opt/hbase-0.19.3/conf/hbase-site.xml"));
+
+    IndexedTableAdmin admin = null;
+    admin = new IndexedTableAdmin(conf);
+
+    admin.removeIndex(Bytes.toBytes("test_table"), "column2");
+}}}
+
+ == read from a secondary index, get a scanner for the index and scan through the data  ==
+{{{
+#!java
+   HBaseConfiguration conf = new HBaseConfiguration();
+    conf.addResource(new Path("/opt/hbase-0.19.3/conf/hbase-site.xml"));
+
+    IndexedTable table = new IndexedTable(conf, Bytes.toBytes("test_table"));
+
+    // You need to specify which columns to get
+    Scanner scanner = table.getIndexedScanner("column1",
+        HConstants.EMPTY_START_ROW, null, null, new byte[][] {
+        Bytes.toBytes("columnfamily1:column1"),
+        Bytes.toBytes("columnfamily1:column2") });
+
+    for (RowResult rowResult : scanner) {
+        String value1 = new String(
+            rowResult.get(Bytes.toBytes("columnfamily1:column1")).getValue());
+        String value2 = new String(
+            rowResult.get(Bytes.toBytes("columnfamily1:column2")).getValue());
+        System.out.println(value1 + ", " + value2);
+    }
+
+    table.close();
+}}}
+
+ == get a scanner to a subset of the rows specify a column filter ==
+{{{
+#!java
+    ColumnValueFilter filter =
+        new ColumnValueFilter(Bytes.toBytes("columnfamily1:column1"),
+        CompareOp.LESS, Bytes.toBytes("value1-10"));
+
+    scanner = table.getIndexedScanner("column1", HConstants.EMPTY_START_ROW,
+        null, filter, new byte[][] { Bytes.toBytes("columnfamily1:column1"),
+        Bytes.toBytes("columnfamily1:column2"));
+
+    for (RowResult rowResult : scanner) {
+        String value1 = new String(
+            rowResult.get(Bytes.toBytes("columnfamily1:column1")).getValue());
+        String value2 = new String(
+            rowResult.get(Bytes.toBytes("columnfamily1:column2")).getValue());
+        System.out.println(value1 + ", " + value2);
+    }
+}}}
+
+ == Secondary indexes in HBase 完整程式碼 == 
+
 [http://rajeev1982.blogspot.com/2009/06/secondary-indexes-in-hbase.html]
 
@@ -226 +350 @@
 }
 }}}
+
+ = Hadoop HBase數據導入和索引測試  = 
+[http://bbs.telewiki.cn/blog/qianling/entry/hadoop_hbase%E6%95%B0%E6%8D%AE%E5%AF%BC%E5%85%A5%E5%92%8C%E7%B4%A2%E5%BC%95%E6%B5%8B%E8%AF%95]