Package org.apache.hadoop.zebra.types

Examples of org.apache.hadoop.zebra.types.Partition$PartitionedColumn

1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
        ;
        throw new IOException("Schema build failed :" + e.getMessage());
      }
      storage = WritableUtils.readString(in);
      try {
        partition = new Partition(logicalStr, storage);
      }
      catch (Exception e) {
        throw new IOException("Partition constructor failed :" + e.getMessage());
      }
      int numCGs = WritableUtils.readVInt(in);
View Full Code Here
192
193
194
195
196
197
198
199
200
    if (schema == null)
      throw new ParseException("Schema has not been set");

    // for sanity check purpose only
    Partition partition = new Partition(schema, storehint);

    conf.set(OUTPUT_STORAGEHINT, storehint);
  }
View Full Code Here
160
161
162
163
164
165
166
167
168
169
170
        cgTuples = new Tuple[numCGs];
        // set default projection that contains everything
        schema = schemaFile.getLogical();
        projection = new Projection(schema);
        String storage = schemaFile.getStorageString();
        partition = new Partition(schema, projection, storage);
        for (int nx = 0; nx < numCGs; nx++) {
          colGroups[nx] =
              new ColumnGroup.Reader(BasicTable.makeCGPath(path, numCGs, nx),
                  conf);
          if (partition.isCGNeeded(nx))
View Full Code Here
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
    public synchronized void setProjection(String projection)
        throws ParseException, IOException {
      if (projection == null) {
        this.projection = new Projection(schemaFile.getLogical());
        partition =
            new Partition(schemaFile.getLogical(), this.projection, schemaFile
                .getStorageString());
      }
      else {
        /**
         * the typed schema from projection which is untyped or actually typed
         * as "bytes"
         */
        this.projection =
            new Projection(schemaFile.getLogical(), projection);
        partition =
            new Partition(schemaFile.getLogical(), this.projection, schemaFile
                .getStorageString());
      }
      inferredMapping = false;
    }
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
  @Test
  public void testStorageValid1() {
    try {
      String strStorage = "[r.r.f1,r.f2#{k1}] COMPRESS BY gzip ; [r.r.f2, r.f2#{k2}] COMPRESS BY lzo2 SERIALIZE BY avro";
      Partition p = new Partition(schema.toString(), strStorage);
      CGSchema[] cgschemas = p.getCGSchemas();

      // 3 column group;
      int size = cgschemas.length;
      Assert.assertEquals(size, 3);
      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("r.r.f1", f11.name);
      Assert.assertEquals(ColumnType.INT, f11.type);
      ColumnSchema f12 = cgs1.getSchema().getColumn(1);
      Assert.assertEquals("r.f2", f12.name);
      Assert.assertEquals(ColumnType.MAP, f12.type);

      ColumnSchema f21 = cgs2.getSchema().getColumn(0);
      Assert.assertEquals("r.r.f2", f21.name);
      Assert.assertEquals(ColumnType.INT, f21.type);
      ColumnSchema f22 = cgs2.getSchema().getColumn(1);
      Assert.assertEquals("r.f2", f22.name);
      Assert.assertEquals(ColumnType.MAP, f22.type);

      ColumnSchema f31 = cgs3.getSchema().getColumn(0);
      Assert.assertEquals("r.f2", f31.name);
      Assert.assertEquals(ColumnType.MAP, f31.type);

      System.out.println("*********** Column Map **********");
      Map<String, HashSet<Partition.PartitionInfo.ColumnMappingEntry>> colmap = p
          .getPartitionInfo().getColMap();
      Assert.assertEquals(colmap.size(), 3);
      Iterator<Map.Entry<String, HashSet<Partition.PartitionInfo.ColumnMappingEntry>>> it = colmap
          .entrySet().iterator();
      for (int i = 0; i < colmap.size(); i++) {
View Full Code Here
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
  @Test
  public void testStorageValid1() {
    try {
      String strStorage = "[c] compress by gzip; [m1] serialize by avro";
      Partition p = new Partition(schema.toString(), strStorage);
      CGSchema[] cgschemas = p.getCGSchemas();

      // 2 column group;
      int size = cgschemas.length;
      Assert.assertEquals(size, 2);
      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.name);
      Assert.assertEquals(ColumnType.COLLECTION, f11.type);

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

      Assert.assertEquals(cgs1.getCompressor(), "gzip");
      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);
      Iterator<Map.Entry<String, HashSet<Partition.PartitionInfo.ColumnMappingEntry>>> it = colmap
          .entrySet().iterator();
      for (int i = 0; i < colmap.size(); i++) {
View Full Code Here
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
  @Test
  public void testStorageValid2() {
    try {
      String strStorage = "[c] compress by gzip; [m1#{k1}] serialize by avro";
      Partition p = new Partition(schema.toString(), strStorage);
      CGSchema[] cgschemas = p.getCGSchemas();

      // 3 column group;
      int size = cgschemas.length;
      Assert.assertEquals(size, 3);
      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", f11.name);
      Assert.assertEquals(ColumnType.COLLECTION, f11.type);

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

      ColumnSchema f31 = cgs3.getSchema().getColumn(0);
      Assert.assertEquals("m1", f31.name);
      Assert.assertEquals(ColumnType.MAP, f31.type);

      System.out.println("*********** Column Map **********");
      Map<String, HashSet<Partition.PartitionInfo.ColumnMappingEntry>> colmap = p
          .getPartitionInfo().getColMap();
      Assert.assertEquals(colmap.size(), 2);
      Iterator<Map.Entry<String, HashSet<Partition.PartitionInfo.ColumnMappingEntry>>> it = colmap
          .entrySet().iterator();
      for (int i = 0; i < colmap.size(); i++) {
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
  @Test
  public void testStorageValid1() {
    try {
      String strStorage = "[f1, f2]; [f3, f4] COMPRESS BY gzip SERIALIZE BY avro";
      Partition p = new Partition(schema.toString(), strStorage);
      CGSchema[] cgschemas = p.getCGSchemas();

      // 3 column group;
      int size = cgschemas.length;
      Assert.assertEquals(size, 3);
      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("f1", f11.name);
      Assert.assertEquals(ColumnType.INT, f11.type);
      ColumnSchema f12 = cgs1.getSchema().getColumn(1);
      Assert.assertEquals("f2", f12.name);
      Assert.assertEquals(ColumnType.LONG, f12.type);
      ColumnSchema f21 = cgs2.getSchema().getColumn(0);
      Assert.assertEquals("f3", f21.name);
      Assert.assertEquals(ColumnType.FLOAT, f21.type);
      ColumnSchema f22 = cgs2.getSchema().getColumn(1);
      Assert.assertEquals("f4", f22.name);
      Assert.assertEquals(ColumnType.BOOL, f22.type);
      ColumnSchema f31 = cgs3.getSchema().getColumn(0);
      Assert.assertEquals("f5", f31.name);
      Assert.assertEquals(ColumnType.STRING, f31.type);
      ColumnSchema f32 = cgs3.getSchema().getColumn(1);
      Assert.assertEquals("f6", f32.name);
      Assert.assertEquals(ColumnType.BYTES, f32.type);

      Assert.assertEquals(cgs1.getCompressor(), "lzo2");
      Assert.assertEquals(cgs1.getSerializer(), "pig");
      Assert.assertEquals(cgs2.getCompressor(), "gzip");
      Assert.assertEquals(cgs2.getSerializer(), "avro");
      Assert.assertEquals(cgs3.getCompressor(), "lzo2");
      Assert.assertEquals(cgs3.getSerializer(), "pig");

      System.out.println("*********** Column Map **********");
      Map<String, HashSet<Partition.PartitionInfo.ColumnMappingEntry>> colmap = p
          .getPartitionInfo().getColMap();
      Assert.assertEquals(colmap.size(), 6);
      Iterator<Map.Entry<String, HashSet<Partition.PartitionInfo.ColumnMappingEntry>>> it = colmap
          .entrySet().iterator();
      for (int i = 0; i < colmap.size(); i++) {
View Full Code Here
167
168
169
170
171
172
173
174
175
176
177
178
  @Test
  public void testStorageValid2() {
    try {
      String strStorage = "[f1, f2] serialize by avro compress by gzip; [f3, f4] SERIALIZE BY avro COMPRESS BY gzip";
      Partition p = new Partition(schema.toString(), strStorage);
      CGSchema[] cgschemas = p.getCGSchemas();

      Assert.assertEquals(cgschemas.length, 3);
      CGSchema cgs1 = cgschemas[0];
      System.out.println(cgs1);
    } catch (Exception e) {
View Full Code Here
182
183
184
185
186
187
188
189
190
191
192
193
  @Test
  public void testStorageValid3() {
    try {
      String strStorage = "";
      Partition p = new Partition(schema.toString(), strStorage);
      CGSchema[] cgschemas = p.getCGSchemas();
      Assert.assertEquals(cgschemas.length, 1);
      CGSchema cgs1 = cgschemas[0];
      System.out.println(cgs1);
    } catch (Exception e) {
      e.printStackTrace();
View Full Code Here
TOP

Related Classes of org.apache.hadoop.zebra.types.Partition$PartitionedColumn

  • org.apache.hadoop.zebra.io.BasicTable$Reader
  • org.apache.hadoop.zebra.io.BasicTable$SchemaFile
  • org.apache.hadoop.zebra.mapred.BasicTableOutputFormat
  • org.apache.hadoop.zebra.mapreduce.BasicTableOutputFormat
  • org.apache.hadoop.zebra.parser.TableSchemaParser
  • org.apache.hadoop.zebra.parser.TableStorageParser
  • org.apache.hadoop.zebra.schema.Schema
  • org.apache.hadoop.zebra.types.TestColumnGroupName
  • org.apache.hadoop.zebra.types.TestStorageCollection
  • org.apache.hadoop.zebra.types.TestStorageMap
    • Copyright © 2018 www.massapicom. All rights reserved.
    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.