Examples of CGSchema

org.apache.hadoop.zebra.types.CGSchema
ColumnGroup Schema. This object is first written to a schema file when the ColumnGroup is initially created, and is used to communicate meta information among writers.

Examples of org.apache.hadoop.zebra.types.CGSchema

     */


    public static Schema getSchema(Path path, Configuration conf)
        throws IOException, ParseException {
      FileSystem fs = path.getFileSystem(conf);
      CGSchema cgschema = CGSchema.load(fs, path);
      return cgschema.getSchema();
    }

View Full Code Here

Examples of org.apache.hadoop.zebra.types.CGSchema

      System.out.println("********** Column Groups **********");
      for (int i = 0; i < cgschemas.length; i++) {
        System.out.println(cgschemas[i]);
        System.out.println("--------------------------------");
      }
      CGSchema cgs1 = cgschemas[0];
      CGSchema cgs2 = cgschemas[1];


      ColumnSchema f11 = cgs1.getSchema().getColumn(0);
      Assert.assertEquals("c1", f11.getName());
      Assert.assertEquals(ColumnType.COLLECTION, f11.getType());
      ColumnSchema f21 = cgs2.getSchema().getColumn(0);
      Assert.assertEquals("c2", f21.getName());
      Assert.assertEquals(ColumnType.COLLECTION, f21.getType());


      System.out.println("*********** Column Map **********");
      Map<String, HashSet<Partition.PartitionInfo.ColumnMappingEntry>> colmap = p

View Full Code Here

Examples of org.apache.hadoop.zebra.types.CGSchema

      System.out.println("********** Column Groups **********");
      for (int i = 0; i < cgschemas.length; i++) {
        System.out.println(cgschemas[i]);
        System.out.println("--------------------------------");
      }
      CGSchema cgs1 = cgschemas[0];
      CGSchema cgs2 = cgschemas[1];


      ColumnSchema f11 = cgs1.getSchema().getColumn(0);
      Assert.assertEquals("c1.f1", f11.getName());
      Assert.assertEquals(ColumnType.INT, f11.getType());
      ColumnSchema f21 = cgs2.getSchema().getColumn(0);
      Assert.assertEquals("c1.f2", f21.getName());
      Assert.assertEquals(ColumnType.INT, f21.getType());
      ColumnSchema f22 = cgs2.getSchema().getColumn(1);
      Assert.assertEquals("c2", f22.getName());
      Assert.assertEquals(ColumnType.COLLECTION, f22.getType());


      System.out.println("*********** Column Map **********");
      Map<String, HashSet<Partition.PartitionInfo.ColumnMappingEntry>> colmap = p

View Full Code Here

Examples of org.apache.hadoop.zebra.types.CGSchema

        fs.delete(path, true);
      }


      checkPath(path, true);


      cgschema = new CGSchema(schema, sorted, comparator, name, serializer, compressor, owner, group, perm);
      CGSchema sfNew = CGSchema.load(fs, path);
      if (sfNew != null) {
        // compare input with on-disk schema.
        if (!sfNew.equals(cgschema)) {
          throw new IOException("Schemes are different.");
        }
      }
      else {
        // create the schema file in FS

View Full Code Here

Examples of org.apache.hadoop.zebra.types.CGSchema

      System.out.println("********** Column Groups **********");
      for (int i = 0; i < cgschemas.length; i++) {
        System.out.println(cgschemas[i]);
        System.out.println("--------------------------------");
      }
      CGSchema cgs1 = cgschemas[0];
      CGSchema cgs2 = cgschemas[1];


      ColumnSchema f11 = cgs1.getSchema().getColumn(0);
      Assert.assertEquals("c", f11.getName());
      Assert.assertEquals(ColumnType.COLLECTION, f11.getType());


      ColumnSchema f21 = cgs2.getSchema().getColumn(0);
      Assert.assertEquals("m1", f21.getName());
      Assert.assertEquals(ColumnType.MAP, f21.getType());


      Assert.assertEquals(cgs1.getCompressor(), "gz");
      Assert.assertEquals(cgs2.getSerializer(), "avro");


      System.out.println("*********** Column Map **********");
      Map<String, HashSet<Partition.PartitionInfo.ColumnMappingEntry>> colmap = p
          .getPartitionInfo().getColMap();
      Assert.assertEquals(colmap.size(), 2);

View Full Code Here

Examples of org.apache.hadoop.zebra.types.CGSchema

      System.out.println("********** Column Groups **********");
      for (int i = 0; i < cgschemas.length; i++) {
        System.out.println(cgschemas[i]);
        System.out.println("--------------------------------");
      }
      CGSchema cgs1 = cgschemas[0];
      CGSchema cgs2 = cgschemas[1];


      ColumnSchema f11 = cgs1.getSchema().getColumn(0);
      Assert.assertEquals("c.r", f11.getName());
      Assert.assertEquals(ColumnType.RECORD, f11.getType());


      ColumnSchema f21 = cgs2.getSchema().getColumn(0);
      Assert.assertEquals("m1", f21.getName());
      Assert.assertEquals(ColumnType.MAP, f21.getType());


      Assert.assertEquals(cgs1.getCompressor(), "gz");
      Assert.assertEquals(cgs2.getSerializer(), "avro");


      System.out.println("*********** Column Map **********");
      Map<String, HashSet<Partition.PartitionInfo.ColumnMappingEntry>> colmap = p
          .getPartitionInfo().getColMap();
      Assert.assertEquals(colmap.size(), 2);

View Full Code Here

Examples of org.apache.hadoop.zebra.types.CGSchema

      System.out.println("********** Column Groups **********");
      for (int i = 0; i < cgschemas.length; i++) {
        System.out.println(cgschemas[i]);
        System.out.println("--------------------------------");
      }
      CGSchema cgs1 = cgschemas[0];
      CGSchema cgs2 = cgschemas[1];
      CGSchema cgs3 = cgschemas[2];


      ColumnSchema f11 = cgs1.getSchema().getColumn(0);
      Assert.assertEquals("c.r.f1", f11.getName());
      Assert.assertEquals(ColumnType.INT, f11.getType());


      ColumnSchema f21 = cgs2.getSchema().getColumn(0);
      Assert.assertEquals("m1", f21.getName());
      Assert.assertEquals(ColumnType.MAP, f21.getType());


      ColumnSchema f31 = cgs3.getSchema().getColumn(0);
      Assert.assertEquals("c.r.f2", f31.getName());
      Assert.assertEquals(ColumnType.INT, f31.getType());


      Assert.assertEquals(cgs1.getCompressor(), "gz");
      Assert.assertEquals(cgs1.getSerializer(), "pig");
      Assert.assertEquals(cgs2.getCompressor(), "lzo");
      Assert.assertEquals(cgs2.getSerializer(), "avro");
      Assert.assertEquals(cgs3.getCompressor(), "lzo");
      Assert.assertEquals(cgs3.getSerializer(), "pig");


      System.out.println("*********** Column Map **********");
      Map<String, HashSet<Partition.PartitionInfo.ColumnMappingEntry>> colmap = p
          .getPartitionInfo().getColMap();
      Assert.assertEquals(colmap.size(), 3);

View Full Code Here

Examples of org.apache.hadoop.zebra.types.CGSchema

      String strStorage = "[f1, f2] as C1 serialize by avro compress by gz; [f3, f4] as C2 SERIALIZE BY avro COMPRESS BY gz; as C3";
      Partition p = new Partition(schema.toString(), strStorage, null);
      CGSchema[] cgschemas = p.getCGSchemas();


      Assert.assertEquals(cgschemas.length, 3);
      CGSchema cgs1 = cgschemas[0];
      System.out.println(cgs1);
      CGSchema cgs2 = cgschemas[1];
      System.out.println(cgs2);
      CGSchema cgs3 = cgschemas[2];
      System.out.println(cgs3);


      Assert.assertEquals(cgs1.getName(), "C1");
      Assert.assertEquals(cgs2.getName(), "C2");
      Assert.assertEquals(cgs3.getName(), "C3");
    } catch (Exception e) {
      e.printStackTrace();
    }
  }

View Full Code Here

Examples of org.apache.hadoop.zebra.types.CGSchema

      String strStorage = "[f1, f2] as C1 serialize by avro compress by gz; [f3, f4] as C2 SERIALIZE BY avro COMPRESS BY gz;";
      Partition p = new Partition(schema.toString(), strStorage, null);
      CGSchema[] cgschemas = p.getCGSchemas();


      Assert.assertEquals(cgschemas.length, 3);
      CGSchema cgs1 = cgschemas[0];
      System.out.println(cgs1);
      CGSchema cgs2 = cgschemas[1];
      System.out.println(cgs2);
      CGSchema cgs3 = cgschemas[2];
      System.out.println(cgs3);


      Assert.assertEquals(cgs1.getName(), "C1");
      Assert.assertEquals(cgs2.getName(), "C2");
      Assert.assertEquals(cgs3.getName(), "CG0");
    } catch (Exception e) {
      e.printStackTrace();
    }
  }

View Full Code Here

Examples of org.apache.hadoop.zebra.types.CGSchema

      String strStorage = "[f1, f2] as PI serialize by avro compress by gz; [f3, f4] SERIALIZE BY avro COMPRESS BY gz; [f5, f6] as CG0";
      Partition p = new Partition(schema.toString(), strStorage, null);
      CGSchema[] cgschemas = p.getCGSchemas();


      Assert.assertEquals(cgschemas.length, 3);
      CGSchema cgs1 = cgschemas[0];
      System.out.println(cgs1);
      CGSchema cgs2 = cgschemas[1];
      System.out.println(cgs2);
      CGSchema cgs3 = cgschemas[2];
      System.out.println(cgs3);


      Assert.assertEquals(cgs1.getName(), "PI");
      Assert.assertEquals(cgs2.getName(), "CG1");
      Assert.assertEquals(cgs3.getName(), "CG0");
    } catch (Exception e) {
      e.printStackTrace();
    }
  }

View Full Code Here

0 1 2 3 4 5

TOP

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.