github.com/apache/beam/sdks/v2@v2.48.2/python/apache_beam/examples/complete/top_wikipedia_sessions_test.py (about)

     1  #
     2  # Licensed to the Apache Software Foundation (ASF) under one or more
     3  # contributor license agreements.  See the NOTICE file distributed with
     4  # this work for additional information regarding copyright ownership.
     5  # The ASF licenses this file to You under the Apache License, Version 2.0
     6  # (the "License"); you may not use this file except in compliance with
     7  # the License.  You may obtain a copy of the License at
     8  #
     9  #    http://www.apache.org/licenses/LICENSE-2.0
    10  #
    11  # Unless required by applicable law or agreed to in writing, software
    12  # distributed under the License is distributed on an "AS IS" BASIS,
    13  # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    14  # See the License for the specific language governing permissions and
    15  # limitations under the License.
    16  #
    17  
    18  """Test for the top wikipedia sessions example."""
    19  
    20  # pytype: skip-file
    21  
    22  import json
    23  import unittest
    24  
    25  import apache_beam as beam
    26  from apache_beam.examples.complete import top_wikipedia_sessions
    27  from apache_beam.testing.test_pipeline import TestPipeline
    28  from apache_beam.testing.util import assert_that
    29  from apache_beam.testing.util import equal_to
    30  
    31  
    32  class ComputeTopSessionsTest(unittest.TestCase):
    33  
    34    EDITS = [
    35        json.dumps({
    36            'timestamp': 0.0, 'contributor_username': 'user1'
    37        }),
    38        json.dumps({
    39            'timestamp': 0.001, 'contributor_username': 'user1'
    40        }),
    41        json.dumps({
    42            'timestamp': 0.002, 'contributor_username': 'user1'
    43        }),
    44        json.dumps({
    45            'timestamp': 0.0, 'contributor_username': 'user2'
    46        }),
    47        json.dumps({
    48            'timestamp': 0.001, 'contributor_username': 'user2'
    49        }),
    50        json.dumps({
    51            'timestamp': 3.601, 'contributor_username': 'user2'
    52        }),
    53        json.dumps({
    54            'timestamp': 3.602, 'contributor_username': 'user2'
    55        }),
    56        json.dumps({
    57            'timestamp': 2 * 3600.0, 'contributor_username': 'user2'
    58        }),
    59        json.dumps({
    60            'timestamp': 35 * 24 * 3.600, 'contributor_username': 'user3'
    61        })
    62    ]
    63  
    64    EXPECTED = [
    65        'user1 : [0.0, 3600.002) : 3 : [0.0, 2592000.0)',
    66        'user2 : [0.0, 3603.602) : 4 : [0.0, 2592000.0)',
    67        'user2 : [7200.0, 10800.0) : 1 : [0.0, 2592000.0)',
    68        'user3 : [3024.0, 6624.0) : 1 : [0.0, 2592000.0)',
    69    ]
    70  
    71    def test_compute_top_sessions(self):
    72      with TestPipeline() as p:
    73        edits = p | beam.Create(self.EDITS)
    74        result = edits | top_wikipedia_sessions.ComputeTopSessions(1.0)
    75  
    76        assert_that(result, equal_to(self.EXPECTED))
    77  
    78  
    79  if __name__ == '__main__':
    80    unittest.main()