Package org.apache.crunch

Examples of org.apache.crunch.Pipeline

122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
    savedRecord.put("name", "John Doe");
    savedRecord.put("age", 42);
    savedRecord.put("siblingnames", Lists.newArrayList("Jimmy", "Jane"));
    populateGenericParquetFile(Lists.newArrayList(savedRecord), Person.SCHEMA$);

    Pipeline pipeline = new MRPipeline(AvroParquetPipelineIT.class, tmpDir.getDefaultConfiguration());
    PCollection<Person> genericCollection = pipeline.read(
        new AvroParquetFileSource<Person>(new Path(avroFile.getAbsolutePath()), Avros.records(Person.class)));
    File outputFile = tmpDir.getFile("output");
    Target parquetFileTarget = new AvroParquetFileTarget(outputFile.getAbsolutePath());
    pipeline.write(genericCollection, parquetFileTarget);
    pipeline.run();

    Person person = genericCollection.materialize().iterator().next();

    Path parquetFile = new Path(new File(outputFile, "part-m-00000.parquet").getPath());
View Full Code Here
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
    savedRecord.put("name", "John Doe");
    savedRecord.put("age", 42);
    savedRecord.put("siblingnames", Lists.newArrayList("Jimmy", "Jane"));
    populateGenericFile(Lists.newArrayList(savedRecord), Person.SCHEMA$);

    Pipeline pipeline = new MRPipeline(AvroParquetPipelineIT.class, tmpDir.getDefaultConfiguration());
    PCollection<Person> genericCollection = pipeline.read(At.avroFile(avroFile.getAbsolutePath(),
        Avros.records(Person.class)));

    PCollection<Employee> employees = genericCollection.parallelDo(new DoFn<Person, Employee>() {
      @Override
      public void process(Person person, Emitter<Employee> emitter) {
        emitter.emit(new Employee(person.getName(), 0, "Eng"));
      }
    }, Avros.records(Employee.class));

    File output1File = tmpDir.getFile("output1");
    File output2File = tmpDir.getFile("output2");
    pipeline.write(genericCollection, new AvroParquetFileTarget(output1File.getAbsolutePath()));
    pipeline.write(employees, new AvroParquetFileSourceTarget(new Path(output2File.getAbsolutePath()),
        Avros.records(Employee.class)));
    pipeline.run();

    Person person = genericCollection.materialize().iterator().next();
    Employee employee = employees.materialize().iterator().next();

    Path parquet1File = new Path(new File(output1File, "part-m-00000.parquet").getPath());
View Full Code Here
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
    savedRecord.put("name", "John Doe");
    savedRecord.put("age", 42);
    savedRecord.put("siblingnames", Lists.newArrayList("Jimmy", "Jane"));
    populateGenericFile(Lists.newArrayList(savedRecord), Person.SCHEMA$);

    Pipeline pipeline = new MRPipeline(AvroParquetPipelineIT.class, tmpDir.getDefaultConfiguration());
    PCollection<Person> genericCollection = pipeline.read(At.avroFile(avroFile.getAbsolutePath(),
        Avros.records(Person.class)));
    File outputFile = tmpDir.getFile("output");
    Target parquetFileTarget = new AvroParquetFileTarget(outputFile.getAbsolutePath());
    pipeline.write(genericCollection, parquetFileTarget);
    pipeline.run();

    Person person = genericCollection.materialize().iterator().next();

    PCollection<Person> retrievedPeople = pipeline.read(new AvroParquetFileSource<Person>(
        new Path(outputFile.toURI()), Avros.records(Person.class)));

    Person retrievedPerson = retrievedPeople.materialize().iterator().next();

    assertThat(retrievedPerson, is(person));
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
92
    savedRecord.put("name", "John Doe");
    savedRecord.put("age", 42);
    savedRecord.put("siblingnames", Lists.newArrayList("Jimmy", "Jane"));
    populateGenericFile(Lists.newArrayList(savedRecord), Person.SCHEMA$);

    Pipeline pipeline = new MRPipeline(AvroParquetFileSourceTargetIT.class, tmpDir.getDefaultConfiguration());
    PCollection<Person> genericCollection = pipeline.read(new AvroParquetFileSource<Person>(new Path(avroFile.getAbsolutePath()),
        Avros.records(Person.class)));

    List<Person> personList = Lists.newArrayList(genericCollection.materialize());

    Person expectedPerson = new Person();
View Full Code Here
109
110
111
112
113
114
115
116
117
118
119
120
    savedRecord.put("name", "John Doe");
    savedRecord.put("age", 42);
    savedRecord.put("siblingnames", Lists.newArrayList("Jimmy", "Jane"));
    populateGenericFile(Lists.newArrayList(savedRecord), genericPersonSchema);

    Pipeline pipeline = new MRPipeline(AvroParquetFileSourceTargetIT.class, tmpDir.getDefaultConfiguration());
    PCollection<Record> genericCollection = pipeline.read(new AvroParquetFileSource<Record>(new Path
        (avroFile.getAbsolutePath()),
        Avros.generics(genericPersonSchema)));

    List<Record> recordList = Lists.newArrayList(genericCollection.materialize());
View Full Code Here
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
    savedRecord.put("name", "John Doe");
    savedRecord.put("age", 42);
    savedRecord.put("siblingnames", Lists.newArrayList("Jimmy", "Jane"));
    populateGenericFile(Lists.newArrayList(savedRecord), Person.SCHEMA$);

    Pipeline pipeline = new MRPipeline(AvroParquetFileSourceTargetIT.class, tmpDir.getDefaultConfiguration());
    PCollection<Person> genericCollection = pipeline.read(
        AvroParquetFileSource.builder(Person.class)
            .includeField("age")
            .build(new Path(avroFile.getAbsolutePath())));

    File outputFile = tmpDir.getFile("output");
    Target avroFile = To.avroFile(outputFile.getAbsolutePath());
    genericCollection.write(avroFile);
    pipeline.done();
   
    Pipeline pipeline2 = new MRPipeline(AvroParquetFileSourceTargetIT.class,
        tmpDir.getDefaultConfiguration());
    PCollection<Person> ageOnly = pipeline2.read(
        new AvroFileSource<Person>(new Path(outputFile.getAbsolutePath()), Avros.specifics(Person.class)));

    for (Person person : ageOnly.materialize()) {
      assertNull(person.getName());
      assertEquals(person.getAge(), new Integer(42));
View Full Code Here
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
    populateGenericFile(Lists.newArrayList(savedRecord), Person.SCHEMA$);

    AvroParquetFileSource<GenericRecord> src = AvroParquetFileSource.builder(Person.SCHEMA$)
        .includeField("age")
        .build(new Path(avroFile.getAbsolutePath()));
    Pipeline pipeline = new MRPipeline(AvroParquetFileSourceTargetIT.class, tmpDir.getDefaultConfiguration());
    PCollection<GenericRecord> genericCollection = pipeline.read(src);

    File outputFile = tmpDir.getFile("output");
    Target avroFile = To.avroFile(outputFile.getAbsolutePath());
    genericCollection.write(avroFile);
    pipeline.done();

    Pipeline pipeline2 = new MRPipeline(AvroParquetFileSourceTargetIT.class,
        tmpDir.getDefaultConfiguration());
    PCollection<Record> ageOnly = pipeline2.read(
        new AvroFileSource<Record>(new Path(outputFile.getAbsolutePath()), Avros.generics(src.getProjectedSchema())));

    for (Record person : ageOnly.materialize()) {
      assertEquals(person.get(0), 42);
      Object notAge = person.get(1);
View Full Code Here
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
    savedRecord.put("name", "John Doe");
    savedRecord.put("age", 42);
    savedRecord.put("siblingnames", Lists.newArrayList("Jimmy", "Jane"));
    populateGenericFile(Lists.newArrayList(savedRecord), Person.SCHEMA$);

    Pipeline pipeline = new MRPipeline(AvroParquetFileSourceTargetIT.class, tmpDir.getDefaultConfiguration());
    PCollection<Person> genericCollection = pipeline.read(
        AvroParquetFileSource.builder(Person.class)
            .includeField("age")
            .filterClass(RejectAllFilter.class)
            .build(new Path(avroFile.getAbsolutePath())));

    File outputFile = tmpDir.getFile("output");
    Target avroFile = To.avroFile(outputFile.getAbsolutePath());
    genericCollection.filter(new FilterFn<Person>() {
      @Override
      public boolean accept(Person input) {
        return input != null;
      }
    }).write(avroFile);
    pipeline.done();

    Pipeline pipeline2 = new MRPipeline(AvroParquetFileSourceTargetIT.class,
        tmpDir.getDefaultConfiguration());
    PCollection<Person> ageOnly = pipeline2.read(
        new AvroFileSource<Person>(new Path(outputFile.getAbsolutePath()), Avros.specifics(Person.class)));
    assertTrue(Lists.newArrayList(ageOnly.materialize()).isEmpty());
  }
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
86
87
88
  }

  @Test
  public void testMemPipelineFileWriter() throws Exception {
    File tmpDir = baseTmpDir.getFile("mempipe");
    Pipeline p = MemPipeline.getInstance();
    PCollection<String> lines = MemPipeline.collectionOf("hello", "world");
    p.writeTextFile(lines, tmpDir.toString());
    p.done();
    assertTrue(tmpDir.exists());
    File[] files = tmpDir.listFiles();
    assertTrue(files != null && files.length > 0);
    for (File f : files) {
      if (!f.getName().startsWith(".")) {
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
82
    savedRecord.put("name", "John Doe");
    savedRecord.put("age", 42);
    savedRecord.put("siblingnames", Lists.newArrayList("Jimmy", "Jane"));
    populateGenericFile(Lists.newArrayList(savedRecord), Person.SCHEMA$);

    Pipeline pipeline = new MRPipeline(AvroParquetFileSourceTargetIT.class, tmpDir.getDefaultConfiguration());
    PCollection<Person> genericCollection = pipeline.read(new AvroParquetFileSource<Person>(new Path(avroFile.getAbsolutePath()),
        Avros.records(Person.class)));

    List<Person> personList = Lists.newArrayList(genericCollection.materialize());

    Person expectedPerson = new Person();
View Full Code Here
TOP

Related Classes of org.apache.crunch.Pipeline

  • $.WordCount
  • com.cloudera.cdk.data.crunch.TestCrunchDatasets
  • org.apache.bigtop.bigpetstore.etl.CrunchETL
  • org.apache.crunch.contrib.io.jdbc.DataBaseSourceIT
  • org.apache.crunch.examples.AverageBytesByIP
  • org.apache.crunch.examples.SecondarySortExample
  • org.apache.crunch.examples.TotalBytesByIP
  • org.apache.crunch.examples.TotalWordCount
  • org.apache.crunch.examples.WordAggregationHBase
  • org.apache.crunch.examples.WordCount
    • 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.