github.com/apache/beam/sdks/v2@v2.48.2/python/apache_beam/examples/wordcount_minimal_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 minimal wordcount example.""" 19 20 # pytype: skip-file 21 22 # beam-playground: 23 # name: WordCountMinimalTest 24 # description: Unit-test for the minimal WordCount example. 25 # multifile: false 26 # context_line: 43 27 # categories: 28 # - IO 29 # - Combiners 30 # complexity: MEDIUM 31 # tags: 32 # - count 33 # - test 34 35 import collections 36 import logging 37 import re 38 import unittest 39 import uuid 40 41 import pytest 42 43 from apache_beam.examples import wordcount_minimal 44 from apache_beam.testing.test_pipeline import TestPipeline 45 from apache_beam.testing.test_utils import create_file 46 from apache_beam.testing.test_utils import read_files_from_pattern 47 48 49 @pytest.mark.examples_postcommit 50 class WordCountMinimalTest(unittest.TestCase): 51 """Unit test for wordcount_minimal example with direct runner.""" 52 53 SAMPLE_TEXT = 'a b c a b a\n aa bb cc aa bb aa' 54 55 def test_basics(self): 56 test_pipeline = TestPipeline(is_integration_test=True) 57 58 # Setup the files with expected content. 59 temp_location = test_pipeline.get_option('temp_location') 60 temp_path = '/'.join([temp_location, str(uuid.uuid4())]) 61 input = create_file('/'.join([temp_path, 'input.txt']), self.SAMPLE_TEXT) 62 63 extra_opts = {'input': input, 'output': '%s.result' % temp_path} 64 expected_words = collections.defaultdict(int) 65 for word in re.findall(r'\w+', self.SAMPLE_TEXT): 66 expected_words[word] += 1 67 wordcount_minimal.main( 68 test_pipeline.get_full_options_as_args(**extra_opts), 69 save_main_session=False) 70 71 # Parse result file and compare. 72 results = [] 73 lines = read_files_from_pattern(temp_path + '.result*').splitlines() 74 for line in lines: 75 match = re.search(r'([a-z]+): ([0-9]+)', line) 76 if match is not None: 77 results.append((match.group(1), int(match.group(2)))) 78 self.assertEqual(sorted(results), sorted(expected_words.items())) 79 80 81 if __name__ == '__main__': 82 logging.getLogger().setLevel(logging.INFO) 83 unittest.main()