github.com/apache/beam/sdks/v2@v2.48.2/python/apache_beam/examples/wordcount_debugging_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 debugging wordcount example."""
    19  
    20  # pytype: skip-file
    21  
    22  import logging
    23  import re
    24  import unittest
    25  import uuid
    26  
    27  import pytest
    28  
    29  from apache_beam.examples import wordcount_debugging
    30  from apache_beam.testing.test_pipeline import TestPipeline
    31  from apache_beam.testing.test_utils import create_file
    32  from apache_beam.testing.test_utils import read_files_from_pattern
    33  
    34  
    35  @pytest.mark.examples_postcommit
    36  class WordCountDebuggingTest(unittest.TestCase):
    37  
    38    SAMPLE_TEXT = 'xx yy Flourish\n zz Flourish Flourish stomach\n aa\n bb cc dd'
    39  
    40    def get_results(self, temp_path):
    41      results = []
    42      lines = read_files_from_pattern(temp_path + '.result*').splitlines()
    43      for line in lines:
    44        match = re.search(r'([A-Za-z]+): ([0-9]+)', line)
    45        if match is not None:
    46          results.append((match.group(1), int(match.group(2))))
    47      return results
    48  
    49    def test_basics(self):
    50      test_pipeline = TestPipeline(is_integration_test=True)
    51      # Setup the files with expected content.
    52      temp_location = test_pipeline.get_option('temp_location')
    53      temp_path = '/'.join([temp_location, str(uuid.uuid4())])
    54      input = create_file('/'.join([temp_path, 'input.txt']), self.SAMPLE_TEXT)
    55      extra_opts = {'input': input, 'output': '%s.result' % temp_path}
    56      expected_words = [('Flourish', 3), ('stomach', 1)]
    57      wordcount_debugging.run(
    58          test_pipeline.get_full_options_as_args(**extra_opts),
    59          save_main_session=False)
    60  
    61      # Parse result file and compare.
    62      results = self.get_results(temp_path)
    63      self.assertEqual(sorted(results), sorted(expected_words))
    64  
    65  
    66  if __name__ == '__main__':
    67    logging.getLogger().setLevel(logging.INFO)
    68    unittest.main()