Package org.apache.pig.impl.logicalLayer.schema.Schema

Examples of org.apache.pig.impl.logicalLayer.schema.Schema.FieldSchema

1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
        Schema expectedSch =
            Schema.generateNestedSchema(DataType.BAG, DataType.INTEGER);

        //check schema of TOBAG when given input tuple having only integers
        Schema inputSch = new Schema();
        inputSch.add(new FieldSchema(null, DataType.INTEGER));
        assertEquals("schema of tobag when input has only ints",
                expectedSch, tb.outputSchema(inputSch));

        //add another int column
        inputSch.add(new FieldSchema(null, DataType.INTEGER));
        assertEquals("schema of tobag when input has only ints",
                expectedSch, tb.outputSchema(inputSch));

        //add a long column
        inputSch.add(new FieldSchema(null, DataType.LONG));
        //expect null inner schema
        expectedSch =
            Schema.generateNestedSchema(DataType.BAG, DataType.NULL);
        assertEquals("schema of tobag when input has ints and long",
                expectedSch, tb.outputSchema(inputSch));

       
        //test schema when input is a tuple with inner schema
        Schema tupInSchema = new Schema(new FieldSchema("x", DataType.CHARARRAY));
        inputSch = new Schema();
        inputSch.add(new FieldSchema("a", tupInSchema, DataType.TUPLE));
        Schema inputSchCp = new Schema(inputSch);
        inputSchCp.getField(0).alias = null;
        expectedSch = new Schema(new FieldSchema(null, inputSchCp, DataType.BAG));
        assertEquals("schema of tobag when input has cols of type tuple ",
                expectedSch, tb.outputSchema(inputSch));
       
        inputSch.add(new FieldSchema("b", tupInSchema, DataType.TUPLE));
        assertEquals("schema of tobag when input has cols of type tuple ",
                expectedSch, tb.outputSchema(inputSch));
       
        //add a column of type tuple with different inner schema
        tupInSchema = new Schema(new FieldSchema("x", DataType.BYTEARRAY));
        inputSch.add(new FieldSchema("c", tupInSchema, DataType.TUPLE));
        //expect null inner schema
        expectedSch =
            Schema.generateNestedSchema(DataType.BAG, DataType.NULL);
        assertEquals("schema of tobag when input has cols of type tuple with diff inner schema",
                expectedSch, tb.outputSchema(inputSch));
View Full Code Here
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
            return null;
        }
       
        @Override
        public Schema outputSchema(Schema input) {
            Schema.FieldSchema charFs = new FieldSchema(null, DataType.CHARARRAY);
            Schema.FieldSchema intFs = new FieldSchema(null, DataType.INTEGER);
            Schema.FieldSchema floatFs = new FieldSchema(null, DataType.FLOAT);
            Schema bagSchema = new Schema();
            bagSchema.add(charFs);
            bagSchema.add(intFs);
            bagSchema.add(floatFs);
            Schema.FieldSchema bagFs;
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
91
92
93
                tschema.getColumn(col);
            if (columnSchema != null) {
                ColumnType ct = columnSchema.getType();
                if (ct == org.apache.hadoop.zebra.schema.ColumnType.RECORD ||
                        ct == org.apache.hadoop.zebra.schema.ColumnType.COLLECTION)
                    ret.add(new FieldSchema(col, toPigSchema(columnSchema.getSchema()), ct.pigDataType()));
                else
                    ret.add(new FieldSchema(col, ct.pigDataType()));
            } else {
                ret.add(new FieldSchema(null, null));
            }
        }
        return ret;
    }
View Full Code Here
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
        Schema expectedSch =
            Schema.generateNestedSchema(DataType.BAG, DataType.INTEGER);

        //check schema of TOBAG when given input tuple having only integers
        Schema inputSch = new Schema();
        inputSch.add(new FieldSchema(null, DataType.INTEGER));
        assertEquals("schema of tobag when input has only ints",
                expectedSch, tb.outputSchema(inputSch));

        //add another int column
        inputSch.add(new FieldSchema(null, DataType.INTEGER));
        assertEquals("schema of tobag when input has only ints",
                expectedSch, tb.outputSchema(inputSch));

        //add a long column
        inputSch.add(new FieldSchema(null, DataType.LONG));
        //expect null inner schema
        expectedSch =
            Schema.generateNestedSchema(DataType.BAG, DataType.NULL);
        assertEquals("schema of tobag when input has ints and long",
                expectedSch, tb.outputSchema(inputSch));

       
        //test schema when input is a tuple with inner schema
        Schema tupInSchema = new Schema(new FieldSchema("x", DataType.CHARARRAY));
        inputSch = new Schema();
        inputSch.add(new FieldSchema("a", tupInSchema, DataType.TUPLE));
        Schema inputSchCp = new Schema(inputSch);
        inputSchCp.getField(0).alias = null;
        expectedSch = new Schema(new FieldSchema(null, inputSchCp, DataType.BAG));
        assertEquals("schema of tobag when input has cols of type tuple ",
                expectedSch, tb.outputSchema(inputSch));
       
        inputSch.add(new FieldSchema("b", tupInSchema, DataType.TUPLE));
        assertEquals("schema of tobag when input has cols of type tuple ",
                expectedSch, tb.outputSchema(inputSch));
       
        //add a column of type tuple with different inner schema
        tupInSchema = new Schema(new FieldSchema("x", DataType.BYTEARRAY));
        inputSch.add(new FieldSchema("c", tupInSchema, DataType.TUPLE));
        //expect null inner schema
        expectedSch =
            Schema.generateNestedSchema(DataType.BAG, DataType.NULL);
        assertEquals("schema of tobag when input has cols of type tuple with diff inner schema",
                expectedSch, tb.outputSchema(inputSch));
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
   
    @Test
    public void testSchemaEqual1() {
       
        List<FieldSchema> innerList1 = new ArrayList<FieldSchema>() ;
        innerList1.add(new FieldSchema("11a", DataType.INTEGER)) ;
        innerList1.add(new FieldSchema("11b", DataType.LONG)) ;
       
        List<FieldSchema> innerList2 = new ArrayList<FieldSchema>() ;
        innerList2.add(new FieldSchema("11a", DataType.INTEGER)) ;
        innerList2.add(new FieldSchema("11b", DataType.LONG)) ;
       
        Schema innerSchema1 = new Schema(innerList1) ;
        Schema innerSchema2 = new Schema(innerList2) ;
               
        List<FieldSchema> list1 = new ArrayList<FieldSchema>() ;
        list1.add(new FieldSchema("1a", DataType.BYTEARRAY)) ;
        list1.add(new FieldSchema("1b", innerSchema1)) ;
        list1.add(new FieldSchema("1c", DataType.INTEGER)) ;
       
        List<FieldSchema> list2 = new ArrayList<FieldSchema>() ;
        list2.add(new FieldSchema("1a", DataType.BYTEARRAY)) ;
        list2.add(new FieldSchema("1b", innerSchema2)) ;
        list2.add(new FieldSchema("1c", DataType.INTEGER)) ;
       
        Schema schema1 = new Schema(list1) ;
        Schema schema2 = new Schema(list2) ;
       
        Assert.assertTrue(Schema.equals(schema1, schema2, false, false)) ;
View Full Code Here
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
    // Positive test
    @Test
    public void testSchemaEqualWithNullSchema1() {

        List<FieldSchema> list1 = new ArrayList<FieldSchema>() ;
        list1.add(new FieldSchema("1a", DataType.BYTEARRAY)) ;
        list1.add(new FieldSchema("1b", null)) ;
        list1.add(new FieldSchema("1c", DataType.INTEGER)) ;

        List<FieldSchema> list2 = new ArrayList<FieldSchema>() ;
        list2.add(new FieldSchema("1a", DataType.BYTEARRAY)) ;
        list2.add(new FieldSchema("1b", null)) ;
        list2.add(new FieldSchema("1c", DataType.INTEGER)) ;

        Schema schema1 = new Schema(list1) ;
        Schema schema2 = new Schema(list2) ;

        // First check
View Full Code Here
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
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
    @Test
    public void testNormalNestedMerge1() {
       
        // Generate two schemas
        List<FieldSchema> innerList1 = new ArrayList<FieldSchema>() ;
        innerList1.add(new FieldSchema("11a", DataType.INTEGER)) ;
        innerList1.add(new FieldSchema("11b", DataType.FLOAT)) ;
       
        List<FieldSchema> innerList2 = new ArrayList<FieldSchema>() ;
        innerList2.add(new FieldSchema("22a", DataType.DOUBLE)) ;
        innerList2.add(new FieldSchema(null, DataType.LONG)) ;
       
        Schema innerSchema1 = new Schema(innerList1) ;
        Schema innerSchema2 = new Schema(innerList2) ;
               
        List<FieldSchema> list1 = new ArrayList<FieldSchema>() ;
        list1.add(new FieldSchema("1a", DataType.BYTEARRAY)) ;
        list1.add(new FieldSchema("1b", innerSchema1)) ;
        list1.add(new FieldSchema("1c", DataType.LONG)) ;
       
        List<FieldSchema> list2 = new ArrayList<FieldSchema>() ;
        list2.add(new FieldSchema("2a", DataType.BYTEARRAY)) ;
        list2.add(new FieldSchema("2b", innerSchema2)) ;
        list2.add(new FieldSchema("2c", DataType.INTEGER)) ;
       
        Schema schema1 = new Schema(list1) ;
        Schema schema2 = new Schema(list2) ;
       
        // Merge
        Schema mergedSchema = schema1.merge(schema2, true) ;
       
       
        // Generate expected schema
        List<FieldSchema> expectedInnerList = new ArrayList<FieldSchema>() ;
        expectedInnerList.add(new FieldSchema("22a", DataType.DOUBLE)) ;
        expectedInnerList.add(new FieldSchema("11b", DataType.FLOAT)) ;
       
        Schema expectedInner = new Schema(expectedInnerList) ;
       
        List<FieldSchema> expectedList = new ArrayList<FieldSchema>() ;
        expectedList.add(new FieldSchema("2a", DataType.BYTEARRAY)) ;
        expectedList.add(new FieldSchema("2b", expectedInner)) ;
        expectedList.add(new FieldSchema("2c", DataType.LONG)) ;
       
        Schema expected = new Schema(expectedList) ;
       
        // Compare
        Assert.assertTrue(Schema.equals(mergedSchema, expected, false, false)) ;
View Full Code Here
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
    @Test
    public void testMergeNullSchemas1() throws Throwable {

        List<FieldSchema> innerList2 = new ArrayList<FieldSchema>() ;
        innerList2.add(new FieldSchema("22a", DataType.DOUBLE)) ;
        innerList2.add(new FieldSchema(null, DataType.LONG)) ;

        Schema innerSchema2 = new Schema(innerList2) ;

        List<FieldSchema> list1 = new ArrayList<FieldSchema>() ;
        list1.add(new FieldSchema("1a", DataType.BYTEARRAY)) ;
        list1.add(new FieldSchema("1b", null)) ;
        list1.add(new FieldSchema("1c", DataType.LONG)) ;

        List<FieldSchema> list2 = new ArrayList<FieldSchema>() ;
        list2.add(new FieldSchema("2a", DataType.BYTEARRAY)) ;
        list2.add(new FieldSchema("2b", innerSchema2)) ;
        list2.add(new FieldSchema("2c", DataType.INTEGER)) ;

        Schema schema1 = new Schema(list1) ;
        Schema schema2 = new Schema(list2) ;

        // Merge
        Schema mergedSchema = Schema.mergeSchema(schema1,
                                                 schema2,
                                                 true,
                                                 false,
                                                 true) ;


        // Generate expected schema

        List<FieldSchema> expectedList = new ArrayList<FieldSchema>() ;
        expectedList.add(new FieldSchema("2a", DataType.BYTEARRAY)) ;
        expectedList.add(new FieldSchema("2b", null)) ;
        expectedList.add(new FieldSchema("2c", DataType.LONG)) ;

        Schema expected = new Schema(expectedList) ;

        // Compare
        Assert.assertTrue(Schema.equals(mergedSchema, expected, false, false)) ;
View Full Code Here
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
        // Inner of inner schema
        Schema innerInner = new Schema(new ArrayList<FieldSchema>()) ;

        // Generate two schemas
        List<FieldSchema> innerList1 = new ArrayList<FieldSchema>() ;
        innerList1.add(new FieldSchema("11a", innerInner)) ;
        innerList1.add(new FieldSchema("11b", DataType.FLOAT)) ;

        List<FieldSchema> innerList2 = new ArrayList<FieldSchema>() ;
        innerList2.add(new FieldSchema("22a", null)) ;
        innerList2.add(new FieldSchema(null, DataType.LONG)) ;

        Schema innerSchema1 = new Schema(innerList1) ;
        Schema innerSchema2 = new Schema(innerList2) ;

        List<FieldSchema> list1 = new ArrayList<FieldSchema>() ;
        list1.add(new FieldSchema("1a", DataType.BYTEARRAY)) ;
        list1.add(new FieldSchema("1b", innerSchema1)) ;
        list1.add(new FieldSchema("1c", DataType.LONG)) ;

        List<FieldSchema> list2 = new ArrayList<FieldSchema>() ;
        list2.add(new FieldSchema("2a", DataType.BYTEARRAY)) ;
        list2.add(new FieldSchema("2b", innerSchema2)) ;
        list2.add(new FieldSchema("2c", DataType.INTEGER)) ;

        Schema schema1 = new Schema(list1) ;
        Schema schema2 = new Schema(list2) ;

        // Merge
        Schema mergedSchema = Schema.mergeSchema(schema1,
                                                 schema2,
                                                 true,
                                                 false,
                                                 true) ;


        // Generate expected schema
        List<FieldSchema> expectedInnerList = new ArrayList<FieldSchema>() ;
        expectedInnerList.add(new FieldSchema("22a", null)) ;
        expectedInnerList.add(new FieldSchema("11b", DataType.FLOAT)) ;

        Schema expectedInner = new Schema(expectedInnerList) ;

        List<FieldSchema> expectedList = new ArrayList<FieldSchema>() ;
        expectedList.add(new FieldSchema("2a", DataType.BYTEARRAY)) ;
        expectedList.add(new FieldSchema("2b", expectedInner)) ;
        expectedList.add(new FieldSchema("2c", DataType.LONG)) ;

        Schema expected = new Schema(expectedList) ;

        // Compare
        Assert.assertTrue(Schema.equals(mergedSchema, expected, false, false)) ;
View Full Code Here
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
    @Test
    public void testMergeDifferentSize1() throws Throwable {

        // Generate two schemas
        List<FieldSchema> innerList1 = new ArrayList<FieldSchema>() ;
        innerList1.add(new FieldSchema("11a", DataType.INTEGER)) ;
        innerList1.add(new FieldSchema("11b", DataType.FLOAT)) ;
        innerList1.add(new FieldSchema("11c", DataType.CHARARRAY)) ;

        List<FieldSchema> innerList2 = new ArrayList<FieldSchema>() ;
        innerList2.add(new FieldSchema("22a", DataType.DOUBLE)) ;
        innerList2.add(new FieldSchema(null, DataType.LONG)) ;

        Schema innerSchema1 = new Schema(innerList1) ;
        Schema innerSchema2 = new Schema(innerList2) ;

        List<FieldSchema> list1 = new ArrayList<FieldSchema>() ;
        list1.add(new FieldSchema("1a", DataType.BYTEARRAY)) ;
        list1.add(new FieldSchema("1b", innerSchema1)) ;
        list1.add(new FieldSchema("1c", DataType.LONG)) ;

        List<FieldSchema> list2 = new ArrayList<FieldSchema>() ;
        list2.add(new FieldSchema("2a", DataType.BYTEARRAY)) ;
        list2.add(new FieldSchema("2b", innerSchema2)) ;
        list2.add(new FieldSchema("2c", DataType.INTEGER)) ;
        list2.add(new FieldSchema("2d", DataType.MAP)) ;

        Schema schema1 = new Schema(list1) ;
        Schema schema2 = new Schema(list2) ;

        // Merge
        Schema mergedSchema = Schema.mergeSchema(schema1,
                                                 schema2,
                                                 true,
                                                 true,
                                                 false) ;


        // Generate expected schema
        List<FieldSchema> expectedInnerList = new ArrayList<FieldSchema>() ;
        expectedInnerList.add(new FieldSchema("22a", DataType.DOUBLE)) ;
        expectedInnerList.add(new FieldSchema("11b", DataType.FLOAT)) ;
        expectedInnerList.add(new FieldSchema("11c", DataType.CHARARRAY)) ;

        Schema expectedInner = new Schema(expectedInnerList) ;

        List<FieldSchema> expectedList = new ArrayList<FieldSchema>() ;
        expectedList.add(new FieldSchema("2a", DataType.BYTEARRAY)) ;
        expectedList.add(new FieldSchema("2b", expectedInner)) ;
        expectedList.add(new FieldSchema("2c", DataType.LONG)) ;
        expectedList.add(new FieldSchema("2d", DataType.MAP)) ;

        Schema expected = new Schema(expectedList) ;

        // Compare
        Assert.assertTrue(Schema.equals(mergedSchema, expected, false, false)) ;
View Full Code Here
TOP

Related Classes of org.apache.pig.impl.logicalLayer.schema.Schema.FieldSchema

  • com.acme.math.Pow
  • com.cloudera.science.pig.Bin
  • com.cloudera.science.pig.Combinatorial
  • com.cloudera.science.pig.Quantile
  • com.mozilla.pig.eval.Coalesce
  • com.twitter.elephantbird.pig.load.LocationAsTuple
  • com.twitter.elephantbird.pig.load.LzoW3CLogLoader
  • com.twitter.elephantbird.pig.mahout.VectorWritableConverter
  • com.twitter.elephantbird.pig.piggybank.GenericInvoker
  • com.twitter.elephantbird.pig.util.ProtobufToPig
    • 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.