Package org.apache.pig.test.utils

Examples of org.apache.pig.test.utils.LogicalPlanTester

282
283
284
285
286
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
    }
   
    @SuppressWarnings("unchecked")
    public void testPruneWithMapKey() throws Exception {
         // only foreach
        LogicalPlanTester lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id, v1, m:map[]);");
        lpt.buildPlan("b = foreach a generate id, m#'path';");       
        org.apache.pig.impl.logicalLayer.LogicalPlan plan = lpt.buildPlan("store b into 'empty';"); 
        LogicalPlan newLogicalPlan = migratePlan(plan);
              
        PlanOptimizer optimizer = new MyPlanOptimizer(newLogicalPlan, 3);
        optimizer.optimize();
       
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id, m:map[]);");
        lpt.buildPlan("b = foreach a generate id, m#'path';");       
        plan = lpt.buildPlan("store b into 'empty';"); 
        LogicalPlan expected = migratePlan(plan);
       
        assertTrue(expected.isEqual(newLogicalPlan));
       
        LOLoad op = (LOLoad)newLogicalPlan.getSources().get(0);
        Map<Integer,Set<String>> annotation =
                (Map<Integer, Set<String>>) op.getAnnotation(MapKeysPruneHelper.REQUIRED_MAPKEYS);
        assertEquals(annotation.size(), 1);
        Set<String> s = new HashSet<String>();
        s.add("path");
        assertEquals(annotation.get(2), s);
       
        // foreach with join
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id, v1, m:map[]);");
        lpt.buildPlan("b = load 'd.txt' as (id, v1, m:map[]);");
        lpt.buildPlan("c = join a by id, b by id;");
        lpt.buildPlan("d = filter c by a::m#'path' != NULL;");
        lpt.buildPlan("e = foreach d generate a::id, b::id, b::m#'path', a::m;");       
        plan = lpt.buildPlan("store e into 'empty';"); 
        newLogicalPlan = migratePlan(plan);
              
        optimizer = new MyPlanOptimizer(newLogicalPlan, 3);
        optimizer.optimize();
       
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id, m:map[]);");
        lpt.buildPlan("b = load 'd.txt' as (id, m:map[]);");
        lpt.buildPlan("c = join a by id, b by id;");
        lpt.buildPlan("d = filter c by a::m#'path' != NULL;");
        lpt.buildPlan("e = foreach d generate a::id, b::id, b::m#'path', a::m;");       
        plan = lpt.buildPlan("store e into 'empty';"); 
        expected = migratePlan(plan);
       
        assertTrue(expected.isEqual(newLogicalPlan));
       
        List<Operator> ll = newLogicalPlan.getSources();
View Full Code Here
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
        assertEquals(annotation.get(2), s);
    }
   
    public void testPruneWithBag() throws Exception  {
        // filter above foreach
        LogicalPlanTester lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id, v:bag{t:(s1,s2,s3)});");
        lpt.buildPlan("b = filter a by id>10;");
        lpt.buildPlan("c = foreach b generate id, FLATTEN(v);");   
        lpt.buildPlan("d = foreach c generate id, v::s2;");   
        org.apache.pig.impl.logicalLayer.LogicalPlan plan = lpt.buildPlan("store d into 'empty';"); 
        LogicalPlan newLogicalPlan = migratePlan(plan);
              
        PlanOptimizer optimizer = new MyPlanOptimizer(newLogicalPlan, 3);
        optimizer.optimize();
       
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id, v:bag{t:(s1,s2,s3)});");
        lpt.buildPlan("b = filter a by id>10;");
        lpt.buildPlan("c = foreach b generate id, FLATTEN(v);");   
        lpt.buildPlan("d = foreach c generate id, v::s2;");   
        plan = lpt.buildPlan("store d into 'empty';");
        LogicalPlan expected = migratePlan(plan);
       
        assertTrue(expected.isEqual(newLogicalPlan));
    }
View Full Code Here
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
        assertTrue(expected.isEqual(newLogicalPlan));
    }
   
    public void testAddForeach() throws Exception  {
        // filter above foreach
        LogicalPlanTester lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id, v1, v2);");
        lpt.buildPlan("b = filter a by v1>10;");
        lpt.buildPlan("c = foreach b generate id;");       
        org.apache.pig.impl.logicalLayer.LogicalPlan plan = lpt.buildPlan("store c into 'empty';"); 
        LogicalPlan newLogicalPlan = migratePlan(plan);
              
        PlanOptimizer optimizer = new MyPlanOptimizer(newLogicalPlan, 3);
        optimizer.optimize();
       
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id, v1);");
        lpt.buildPlan("b = filter a by v1>10;");
        lpt.buildPlan("c = foreach b generate id;");     
        plan = lpt.buildPlan("store c into 'empty';"); 
        LogicalPlan expected = migratePlan(plan);
       
        assertTrue(expected.isEqual(newLogicalPlan));
       
        // join with foreach
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id, v1, v2);");
        lpt.buildPlan("b = load 'd.txt' as (id, v1, v2);");
        lpt.buildPlan("c = join a by id, b by id;");
        lpt.buildPlan("d = filter c by a::v1>b::v1;");
        lpt.buildPlan("e = foreach d generate a::id;");       
        plan = lpt.buildPlan("store e into 'empty';"); 
        newLogicalPlan = migratePlan(plan);
              
        optimizer = new MyPlanOptimizer(newLogicalPlan, 3);
        optimizer.optimize();
       
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id, v1);");
        lpt.buildPlan("b = load 'd.txt' as (id, v1);");
        lpt.buildPlan("c = join a by id, b by id;");
        lpt.buildPlan("d = foreach c generate a::id, a::v1, b::v1;");       
        lpt.buildPlan("e = filter d by a::v1>b::v1;"); 
        lpt.buildPlan("f = foreach e generate a::id;");       
        plan = lpt.buildPlan("store f into 'empty';"); 
        expected = migratePlan(plan);
       
        assertTrue(expected.isEqual(newLogicalPlan));
    }
View Full Code Here
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
89
90
91
92
93
94
95
96
97
98
99
100
101
    }
   
  
    public void testNoPrune() throws Exception  {
        // no foreach
        LogicalPlanTester lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id, v1, v2);");
        lpt.buildPlan("b = filter a by v1==NULL;");       
        org.apache.pig.impl.logicalLayer.LogicalPlan plan = lpt.buildPlan("store b into 'empty';"); 
        LogicalPlan newLogicalPlan = migratePlan(plan);
              
        PlanOptimizer optimizer = new MyPlanOptimizer(newLogicalPlan, 3);
        optimizer.optimize();
       
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id, v1, v2);");
        lpt.buildPlan("b = filter a by v1==NULL;");       
        plan = lpt.buildPlan("store b into 'empty';"); 
        LogicalPlan expected = migratePlan(plan);
       
        assertTrue(expected.isEqual(newLogicalPlan));
       
        // no schema
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt';");
        lpt.buildPlan("b = foreach a generate $0, $1;");
        plan = lpt.buildPlan("store b into 'empty';"); 
        newLogicalPlan = migratePlan(plan);
              
        optimizer = new MyPlanOptimizer(newLogicalPlan, 3);
        optimizer.optimize();
       
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt';");
        lpt.buildPlan("b = foreach a generate $0, $1;");
        plan = lpt.buildPlan("store b into 'empty';"); 
        expected = migratePlan(plan);
        assertTrue(expected.isEqual(newLogicalPlan));
    }
View Full Code Here
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
131
132
133
134
135
136
137
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
186
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
229
230
231
232
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
        assertTrue(expected.isEqual(newLogicalPlan));
    }
      
    public void testPrune() throws Exception  {
        // only foreach
        LogicalPlanTester lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id, v1, v2);");
        lpt.buildPlan("b = foreach a generate id;");       
        org.apache.pig.impl.logicalLayer.LogicalPlan plan = lpt.buildPlan("store b into 'empty';"); 
        LogicalPlan newLogicalPlan = migratePlan(plan);
              
        PlanOptimizer optimizer = new MyPlanOptimizer(newLogicalPlan, 3);
        optimizer.optimize();
       
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id);");
        lpt.buildPlan("b = foreach a generate id;");       
        plan = lpt.buildPlan("store b into 'empty';"); 
        LogicalPlan expected = migratePlan(plan);
       
        assertTrue(expected.isEqual(newLogicalPlan));
       
        // with filter
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id, v1, v5, v3, v4, v2);");
        lpt.buildPlan("b = filter a by v1 != NULL AND (v2+v3)<100;");
        lpt.buildPlan("c = foreach b generate id;");
        plan = lpt.buildPlan("store c into 'empty';"); 
        newLogicalPlan = migratePlan(plan);
              
        optimizer = new MyPlanOptimizer(newLogicalPlan, 3);
        optimizer.optimize();
       
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id, v1, v3, v2);");
        lpt.buildPlan("b = filter a by v1 != NULL AND (v2+v3)<100;");
        lpt.buildPlan("c = foreach b generate id;");
        plan = lpt.buildPlan("store c into 'empty';");
        expected = migratePlan(plan);
        assertTrue(expected.isEqual(newLogicalPlan));
       
        // with 2 foreach
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id, v1, v5, v3, v4, v2);");
        lpt.buildPlan("b = foreach a generate v2, v5, v4;");
        lpt.buildPlan("c = foreach b generate v5, v4;");
        plan = lpt.buildPlan("store c into 'empty';"); 
        newLogicalPlan = migratePlan(plan);
              
        optimizer = new MyPlanOptimizer(newLogicalPlan, 3);
        optimizer.optimize();
       
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (v5, v4);");
        lpt.buildPlan("b = foreach a generate v5, v4;");
        lpt.buildPlan("c = foreach b generate v5, v4;");
        plan = lpt.buildPlan("store c into 'empty';");
        expected = migratePlan(plan);
        assertTrue(expected.isEqual(newLogicalPlan));
       
        // with 2 foreach
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id, v1, v5, v3, v4, v2);");
        lpt.buildPlan("b = foreach a generate id, v1, v5, v3, v4;");
        lpt.buildPlan("c = foreach b generate v5, v4;");
        plan = lpt.buildPlan("store c into 'empty';"); 
        newLogicalPlan = migratePlan(plan);
              
        optimizer = new MyPlanOptimizer(newLogicalPlan, 3);
        optimizer.optimize();
       
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (v5, v4);");
        lpt.buildPlan("b = foreach a generate v5, v4;");
        lpt.buildPlan("c = foreach b generate v5, v4;");
        plan = lpt.buildPlan("store c into 'empty';");
        expected = migratePlan(plan);
        assertTrue(expected.isEqual(newLogicalPlan));
       
        // with 2 foreach and filter in between
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id, v1, v5, v3, v4, v2);");
        lpt.buildPlan("b = foreach a generate v2, v5, v4;");
        lpt.buildPlan("c = filter b by v2 != NULL;");
        lpt.buildPlan("d = foreach c generate v5, v4;");
        plan = lpt.buildPlan("store d into 'empty';"); 
        newLogicalPlan = migratePlan(plan);
              
        optimizer = new MyPlanOptimizer(newLogicalPlan, 3);
        optimizer.optimize();
       
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (v5, v4, v2);");
        lpt.buildPlan("b = foreach a generate v2, v5, v4;");
        lpt.buildPlan("c = filter b by v2 != NULL;");
        lpt.buildPlan("d = foreach c generate v5, v4;");
        plan = lpt.buildPlan("store d into 'empty';"); 
        expected = migratePlan(plan);
        assertTrue(expected.isEqual(newLogicalPlan));
       
        // with 2 foreach after join
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id, v1, v2, v3);");
        lpt.buildPlan("b = load 'c.txt' as (id, v4, v5, v6);");
        lpt.buildPlan("c = join a by id, b by id;");      
        lpt.buildPlan("d = foreach c generate a::id, v5, v3, v4;");
        plan = lpt.buildPlan("store d into 'empty';"); 
        newLogicalPlan = migratePlan(plan);
              
        optimizer = new MyPlanOptimizer(newLogicalPlan, 3);
        optimizer.optimize();
       
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' as (id, v3);");
        lpt.buildPlan("b = load 'c.txt' as (id, v4, v5);");
        lpt.buildPlan("c = join a by id, b by id;"); 
        lpt.buildPlan("d = foreach c generate a::id, v5, v3, v4;");
        plan = lpt.buildPlan("store d into 'empty';"); 
        expected = migratePlan(plan);
        assertTrue(expected.isEqual(newLogicalPlan));
       
        // with BinStorage, insert foreach after load
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' using BinStorage() as (id, v1, v5, v3, v4, v2);");       
        lpt.buildPlan("c = filter a by v2 != NULL;");
        lpt.buildPlan("d = foreach c generate v5, v4;");
        plan = lpt.buildPlan("store d into 'empty';"); 
        newLogicalPlan = migratePlan(plan);
              
        optimizer = new MyPlanOptimizer(newLogicalPlan, 3);
        optimizer.optimize();
       
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' using BinStorage() as (id, v1, v5, v3, v4, v2);");
        lpt.buildPlan("b = foreach a generate v5, v4, v2;");
        lpt.buildPlan("c = filter b by v2 != NULL;");
        lpt.buildPlan("d = foreach c generate v5, v4;");
        plan = lpt.buildPlan("store d into 'empty';"); 
        expected = migratePlan(plan);
        assertTrue(expected.isEqual(newLogicalPlan));
       
       // with BinStorage, not to insert foreach after load if there is already one
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' using BinStorage() as (id, v1, v5, v3, v4, v2);");   
        lpt.buildPlan("b = foreach a generate v5, v4, v2;");
        lpt.buildPlan("c = filter b by v2 != NULL;");
        lpt.buildPlan("d = foreach c generate v5;");
        plan = lpt.buildPlan("store d into 'empty';"); 
        newLogicalPlan = migratePlan(plan);
              
        optimizer = new MyPlanOptimizer(newLogicalPlan, 3);
        optimizer.optimize();
       
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' using BinStorage() as (id, v1, v5, v3, v4, v2);");
        lpt.buildPlan("b = foreach a generate v5, v2;");
        lpt.buildPlan("c = filter b by v2 != NULL;");
        lpt.buildPlan("d = foreach c generate v5;");
        plan = lpt.buildPlan("store d into 'empty';"); 
        expected = migratePlan(plan);
        assertTrue(expected.isEqual(newLogicalPlan));
       
       // with BinStorage, not to insert foreach after load if there is already one
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' using BinStorage() as (id, v1, v5, v3, v4, v2);");   
        lpt.buildPlan("b = foreach a generate v5, v4, v2, 10;");
        lpt.buildPlan("c = filter b by v2 != NULL;");
        lpt.buildPlan("d = foreach c generate v5;");
        plan = lpt.buildPlan("store d into 'empty';"); 
        newLogicalPlan = migratePlan(plan);
              
        optimizer = new MyPlanOptimizer(newLogicalPlan, 3);
        optimizer.optimize();
       
        lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'd.txt' using BinStorage() as (id, v1, v5, v3, v4, v2);");
        lpt.buildPlan("b = foreach a generate v5, v2, 10;");
        lpt.buildPlan("c = filter b by v2 != NULL;");
        lpt.buildPlan("d = foreach c generate v5;");
        plan = lpt.buildPlan("store d into 'empty';"); 
        expected = migratePlan(plan);
        assertTrue(expected.isEqual(newLogicalPlan));
    }
View Full Code Here
73
74
75
76
77
78
79
80
    static PigContext pc = new PigContext(ExecType.LOCAL, new Properties());
    static LogicalPlanTester lpTester;
   
    @BeforeClass
    public static void setup() throws Exception {
        lpTester = new LogicalPlanTester(pc);
        lpTester.buildPlan("a = load 'foo' as (srcid, mrkt, dstid, name, age);");
    }
View Full Code Here
589
590
591
592
593
594
595
596
597
598
599
600
601
602
     * tests sortinfo for the case where order by is ascending on
     * all sort columns
     */
    @Test
    public void testSortInfoAsc() throws Exception {
        LogicalPlanTester lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'bla' as (i:int, n:chararray, d:double);");
        lpt.buildPlan("b = order a by i, d;");
        LogicalPlan lp = lpt.buildPlan("store b into 'foo';");
        PigServer.SortInfoSetter siSetter = new PigServer.SortInfoSetter(lp);
        siSetter.visit();
        PhysicalPlan pp = buildPhysicalPlan(lp);
        SortInfo si = ((POStore)(pp.getLeaves().get(0))).getSortInfo();
        SortInfo expected = getSortInfo(
View Full Code Here
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
     * tests sortInfo for mixed ascending and descending in order by
     * @throws Exception
     */
    @Test
    public void testSortInfoAscDesc() throws Exception {
        LogicalPlanTester lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'bla' as (i:int, n:chararray, d:double);");
        lpt.buildPlan("b = filter a by i > 10;");
        lpt.buildPlan("c = order b by i desc, d;");
        LogicalPlan lp = lpt.buildPlan("store c into 'foo';");
        PigServer.SortInfoSetter siSetter = new PigServer.SortInfoSetter(lp);
        siSetter.visit();
        PhysicalPlan pp = buildPhysicalPlan(lp);
        SortInfo si = ((POStore)(pp.getLeaves().get(0))).getSortInfo();
        SortInfo expected = getSortInfo(
View Full Code Here
637
638
639
640
641
642
643
644
645
646
647
648
649
650
     * before the store
     * @throws Exception
     */
    @Test
    public void testSortInfoNoOrderBy1() throws Exception {
        LogicalPlanTester lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'bla' as (i:int, n:chararray, d:double);");
        lpt.buildPlan("b = filter a by i > 10;");
        LogicalPlan lp = lpt.buildPlan("store b into 'foo';");
        PigServer.SortInfoSetter siSetter = new PigServer.SortInfoSetter(lp);
        siSetter.visit();
        PhysicalPlan pp = buildPhysicalPlan(lp);
        SortInfo si = ((POStore)(pp.getLeaves().get(0))).getSortInfo();
        assertEquals(null, si);
View Full Code Here
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
     * between order by and the store
     * @throws Exception
     */
    @Test
    public void testSortInfoNoOrderBy2() throws Exception {
        LogicalPlanTester lpt = new LogicalPlanTester(pc);
        lpt.buildPlan("a = load 'bla' as (i:int, n:chararray, d:double);");
        lpt.buildPlan("b = order a by i, d;");
        lpt.buildPlan("c = filter b by i > 10;");
        LogicalPlan lp = lpt.buildPlan("store c into 'foo';");
        PhysicalPlan pp = buildPhysicalPlan(lp);
        PigServer.SortInfoSetter siSetter = new PigServer.SortInfoSetter(lp);
        siSetter.visit();
        SortInfo si = ((POStore)(pp.getLeaves().get(0))).getSortInfo();
        assertEquals(null, si);
View Full Code Here
TOP

Related Classes of org.apache.pig.test.utils.LogicalPlanTester

  • org.apache.pig.impl.logicalLayer.optimizer.LogicalOptimizer
  • org.apache.pig.impl.logicalLayer.optimizer.SchemaCalculator
  • org.apache.pig.impl.logicalLayer.optimizer.SchemaRemover
  • org.apache.pig.impl.logicalLayer.validators.TypeCheckingValidator
  • org.apache.pig.impl.PigContext
  • org.apache.pig.impl.plan.CompilationMessageCollector
  • org.apache.pig.test.TestCollectedGroup
  • org.apache.pig.test.TestCombiner
  • org.apache.pig.test.TestExperimentalColumnPrune
  • org.apache.pig.test.TestExperimentalLogToPhyTranslationVisitor
    • 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.