Remove python 3.7 support

.test-infra/metrics/sync/jenkins/syncjenkins.py

@@ -62,7 +62,7 @@ def fetchJobs():
   url = ('https://ci-beam.apache.org/api/json'
          '?tree=jobs[name,url,lastCompletedBuild[id]]&depth=1')
   r = requests.get(url)
-  jobs = r.json()[u'jobs']
+  jobs = r.json()['jobs']
   result = map(lambda x: (x['name'],
                           int(x['lastCompletedBuild']['id'])
                               if x['lastCompletedBuild'] is not None
@@ -122,31 +122,31 @@ def fetchBuildsForJob(jobUrl):
             f'estimatedDuration,fullDisplayName,actions[{durFields}]')
   url = f'{jobUrl}api/json?depth=1&tree=builds[{fields}]'
   r = requests.get(url)
-  return r.json()[u'builds']
+  return r.json()['builds']
 
 
 def buildRowValuesArray(jobName, build):
   timings = next((x
-                  for x in build[u'actions']
-                  if (u'_class' in x)
-                    and (x[u'_class'] == u'jenkins.metrics.impl.TimeInQueueAction')),
+                  for x in build['actions']
+                  if ('_class' in x)
+                    and (x['_class'] == 'jenkins.metrics.impl.TimeInQueueAction')),
                  None)
   values = [jobName,
-          int(build[u'id']),
-          build[u'url'],
-          build[u'result'],
-          datetime.fromtimestamp(build[u'timestamp'] / 1000),
-          build[u'builtOn'],
-          build[u'duration'],
-          build[u'estimatedDuration'],
-          build[u'fullDisplayName'],
-          timings[u'blockedDurationMillis'] if timings is not None else -1,
-          timings[u'buildableDurationMillis'] if timings is not None else -1,
-          timings[u'buildingDurationMillis'] if timings is not None else -1,
-          timings[u'executingTimeMillis'] if timings is not None else -1,
-          timings[u'queuingDurationMillis'] if timings is not None else -1,
-          timings[u'totalDurationMillis'] if timings is not None else -1,
-          timings[u'waitingDurationMillis'] if timings is not None else -1]
+          int(build['id']),
+          build['url'],
+          build['result'],
+          datetime.fromtimestamp(build['timestamp'] / 1000),
+          build['builtOn'],
+          build['duration'],
+          build['estimatedDuration'],
+          build['fullDisplayName'],
+          timings['blockedDurationMillis'] if timings is not None else -1,
+          timings['buildableDurationMillis'] if timings is not None else -1,
+          timings['buildingDurationMillis'] if timings is not None else -1,
+          timings['executingTimeMillis'] if timings is not None else -1,
+          timings['queuingDurationMillis'] if timings is not None else -1,
+          timings['totalDurationMillis'] if timings is not None else -1,
+          timings['waitingDurationMillis'] if timings is not None else -1]
   return values
 
 
@@ -168,16 +168,16 @@ def fetchNewData():
     syncedJobId = syncedJobs[newJobName] if newJobName in syncedJobs else -1
     if newJobLastBuildId > syncedJobId:
       builds = fetchBuildsForJob(newJobUrl)
-      builds = [x for x in builds if int(x[u'id']) > syncedJobId]
+      builds = [x for x in builds if int(x['id']) > syncedJobId]
 
       connection = initConnection()
       cursor = connection.cursor()
 
       for build in builds:
-        if build[u'building']:
+        if build['building']:
           continue;
         rowValues = buildRowValuesArray(newJobName, build)
-        print("inserting", newJobName, build[u'id'])
+        print("inserting", newJobName, build['id'])
         insertRow(cursor, rowValues)
 
       cursor.close()

sdks/python/apache_beam/coders/coders_test.py

@@ -76,7 +76,7 @@ def test_proto_coder(self):
     ma = test_message.MessageA()
     mb = ma.field2.add()
     mb.field1 = True
-    ma.field1 = u'hello world'
+    ma.field1 = 'hello world'
     expected_coder = coders.ProtoCoder(ma.__class__)
     real_coder = coders_registry.get_coder(ma.__class__)
     self.assertEqual(expected_coder, real_coder)
@@ -90,7 +90,7 @@ def test_deterministic_proto_coder(self):
     ma = test_message.MessageA()
     mb = ma.field2.add()
     mb.field1 = True
-    ma.field1 = u'hello world'
+    ma.field1 = 'hello world'
     expected_coder = coders.DeterministicProtoCoder(ma.__class__)
     real_coder = (
         coders_registry.get_coder(
@@ -130,7 +130,7 @@ class ProtoPlusCoderTest(unittest.TestCase):
   def test_proto_plus_coder(self):
     ma = ProtoPlusMessageA()
     ma.field2 = [ProtoPlusMessageB(field1=True)]
-    ma.field1 = u'hello world'
+    ma.field1 = 'hello world'
     expected_coder = coders.ProtoPlusCoder(ma.__class__)
     real_coder = coders_registry.get_coder(ma.__class__)
     self.assertTrue(issubclass(ma.__class__, proto.Message))

sdks/python/apache_beam/coders/coders_test_common.py

@@ -121,7 +121,7 @@ class CodersTest(unittest.TestCase):
       -1,
       1.5,
       b'str\0str',
-      u'unicode\0\u0101',
+      'unicode\0\u0101',
       (),
       (1, 2, 3),
       [],
@@ -407,7 +407,7 @@ def test_tuple_coder(self):
             coders.TupleCoder((coders.PickleCoder(), coders.VarIntCoder())),
             coders.StrUtf8Coder(),
             coders.BooleanCoder())), ((1, 2), 'a', True),
-        ((-2, 5), u'a\u0101' * 100, False), ((300, 1), 'abc\0' * 5, True))
+        ((-2, 5), 'a\u0101' * 100, False), ((300, 1), 'abc\0' * 5, True))
 
   def test_tuple_sequence_coder(self):
     int_tuple_coder = coders.TupleSequenceCoder(coders.VarIntCoder())
@@ -420,7 +420,7 @@ def test_base64_pickle_coder(self):
     self.check_coder(coders.Base64PickleCoder(), 'a', 1, 1.5, (1, 2, 3))
 
   def test_utf8_coder(self):
-    self.check_coder(coders.StrUtf8Coder(), 'a', u'ab\u00FF', u'\u0101\0')
+    self.check_coder(coders.StrUtf8Coder(), 'a', 'ab\u00FF', '\u0101\0')
 
   def test_iterable_coder(self):
     iterable_coder = coders.IterableCoder(coders.VarIntCoder())
@@ -604,10 +604,10 @@ def test_proto_coder(self):
     ma = test_message.MessageA()
     mab = ma.field2.add()
     mab.field1 = True
-    ma.field1 = u'hello world'
+    ma.field1 = 'hello world'
 
     mb = test_message.MessageA()
-    mb.field1 = u'beam'
+    mb.field1 = 'beam'
 
     proto_coder = coders.ProtoCoder(ma.__class__)
     self.check_coder(proto_coder, ma)
@@ -666,7 +666,7 @@ def __iter__(self):
 
     # Test nested tuple observable.
     coder = coders.TupleCoder((coders.StrUtf8Coder(), iter_coder))
-    value = (u'123', observ)
+    value = ('123', observ)
     self.assertEqual(
         coder.get_impl().get_estimated_size_and_observables(value)[1],
         [(observ, elem_coder.get_impl())])

sdks/python/apache_beam/dataframe/transforms_test.py

@@ -213,8 +213,8 @@ def test_batching_beam_row_input(self):
     with beam.Pipeline() as p:
       result = (
           p
-          | beam.Create([(u'Falcon', 380.), (u'Falcon', 370.), (u'Parrot', 24.),
-                         (u'Parrot', 26.)])
+          | beam.Create([('Falcon', 380.), ('Falcon', 370.), ('Parrot', 24.),
+                         ('Parrot', 26.)])
           | beam.Map(lambda tpl: beam.Row(Animal=tpl[0], Speed=tpl[1]))
           | transforms.DataframeTransform(
               lambda df: df.groupby('Animal').mean(), include_indexes=True))
@@ -225,8 +225,8 @@ def test_batching_beam_row_to_dataframe(self):
     with beam.Pipeline() as p:
       df = convert.to_dataframe(
           p
-          | beam.Create([(u'Falcon', 380.), (u'Falcon', 370.), (
-              u'Parrot', 24.), (u'Parrot', 26.)])
+          | beam.Create([('Falcon', 380.), ('Falcon', 370.), ('Parrot', 24.), (
+              'Parrot', 26.)])
           | beam.Map(lambda tpl: beam.Row(Animal=tpl[0], Speed=tpl[1])))
 
       result = convert.to_pcollection(
@@ -260,8 +260,8 @@ def test_unbatching_series(self):
     with beam.Pipeline() as p:
       result = (
           p
-          | beam.Create([(u'Falcon', 380.), (u'Falcon', 370.), (u'Parrot', 24.),
-                         (u'Parrot', 26.)])
+          | beam.Create([('Falcon', 380.), ('Falcon', 370.), ('Parrot', 24.),
+                         ('Parrot', 26.)])
           | beam.Map(lambda tpl: beam.Row(Animal=tpl[0], Speed=tpl[1]))
           | transforms.DataframeTransform(lambda df: df.Animal))
 

sdks/python/apache_beam/examples/cookbook/bigtableio_it_test.py

@@ -54,7 +54,7 @@
   import google.cloud.bigtable.instance
 
 EXISTING_INSTANCES = []  # type: List[google.cloud.bigtable.instance.Instance]
-LABEL_KEY = u'python-bigtable-beam'
+LABEL_KEY = 'python-bigtable-beam'
 label_stamp = datetime.datetime.utcnow().replace(tzinfo=UTC)
 label_stamp_micros = _microseconds_from_datetime(label_stamp)
 LABELS = {LABEL_KEY: str(label_stamp_micros)}

sdks/python/apache_beam/examples/snippets/snippets_test.py

@@ -614,7 +614,7 @@ def test_model_pipelines(self):
       snippets.model_pipelines()
     self.assertEqual(
         self.get_output(result_path),
-        [str(s) for s in [(u'aa', 1), (u'bb', 2), (u'cc', 3)]])
+        [str(s) for s in [('aa', 1), ('bb', 2), ('cc', 3)]])
 
   def test_model_pcollection(self):
     temp_path = self.create_temp_file()
@@ -863,7 +863,7 @@ def _inner(topic=None, subscription=None):
     input_topic = 'projects/fake-beam-test-project/topic/intopic'
     input_values = [
         TimestampedValue(b'a a b', 1),
-        TimestampedValue(u'🤷 ¯\\_(ツ)_/¯ b b '.encode('utf-8'), 12),
+        TimestampedValue('🤷 ¯\\_(ツ)_/¯ b b '.encode('utf-8'), 12),
         TimestampedValue(b'a b c c c', 20)
     ]
     output_topic = 'projects/fake-beam-test-project/topic/outtopic'

sdks/python/apache_beam/examples/wordcount_test.py

@@ -38,7 +38,7 @@
 class WordCountTest(unittest.TestCase):
 
   SAMPLE_TEXT = (
-      u'a b c a b a\nacento gráfico\nJuly 30, 2018\n\n aa bb cc aa bb aa')
+      'a b c a b a\nacento gráfico\nJuly 30, 2018\n\n aa bb cc aa bb aa')
 
   def test_basics(self):
     test_pipeline = TestPipeline(is_integration_test=True)

sdks/python/apache_beam/internal/cloudpickle_pickler_test.py

@@ -33,7 +33,7 @@ class PicklerTest(unittest.TestCase):
   NO_MAPPINGPROXYTYPE = not hasattr(types, "MappingProxyType")
 
   def test_basics(self):
-    self.assertEqual([1, 'a', (u'z', )], loads(dumps([1, 'a', (u'z', )])))
+    self.assertEqual([1, 'a', ('z', )], loads(dumps([1, 'a', ('z', )])))
     fun = lambda x: 'xyz-%s' % x
     self.assertEqual('xyz-abc', loads(dumps(fun))('abc'))
 

sdks/python/apache_beam/internal/pickler_test.py

@@ -34,7 +34,7 @@ class PicklerTest(unittest.TestCase):
   NO_MAPPINGPROXYTYPE = not hasattr(types, "MappingProxyType")
 
   def test_basics(self):
-    self.assertEqual([1, 'a', (u'z', )], loads(dumps([1, 'a', (u'z', )])))
+    self.assertEqual([1, 'a', ('z', )], loads(dumps([1, 'a', ('z', )])))
     fun = lambda x: 'xyz-%s' % x
     self.assertEqual('xyz-abc', loads(dumps(fun))('abc'))
 

sdks/python/apache_beam/io/external/xlang_parquetio_test.py

@@ -60,7 +60,7 @@ def test_xlang_parquetio_write(self):
               AvroRecord({"name": "ghi"})]) \
           | beam.ExternalTransform(
               PARQUET_WRITE_URN,
-              ImplicitSchemaPayloadBuilder({'data': u'/tmp/test.parquet'}),
+              ImplicitSchemaPayloadBuilder({'data': '/tmp/test.parquet'}),
               address)
     except RuntimeError as e:
       if re.search(PARQUET_WRITE_URN, str(e)):

sdks/python/apache_beam/io/gcp/big_query_query_to_table_it_test.py

@@ -83,7 +83,7 @@
 NEW_TYPES_QUERY = ('SELECT bytes, date, time FROM [%s.%s]')
 DIALECT_OUTPUT_SCHEMA = ('{"fields": [{"name": "fruit","type": "STRING"}]}')
 DIALECT_OUTPUT_VERIFY_QUERY = ('SELECT fruit from `%s`;')
-DIALECT_OUTPUT_EXPECTED = [(u'apple', ), (u'orange', )]
+DIALECT_OUTPUT_EXPECTED = [('apple', ), ('orange', )]
 
 
 class BigQueryQueryToTableIT(unittest.TestCase):

sdks/python/apache_beam/io/gcp/bigquery_read_it_test.py

@@ -125,9 +125,9 @@ class ReadTests(BigQueryReadIntegrationTests):
   }, {
       'number': 2, 'str': 'def'
   }, {
-      'number': 3, 'str': u'你好'
+      'number': 3, 'str': '你好'
   }, {
-      'number': 4, 'str': u'привет'
+      'number': 4, 'str': 'привет'
   }]
 
   @classmethod
@@ -309,14 +309,14 @@ def test_table_schema_retrieve_with_direct_read(self):
 class ReadUsingStorageApiTests(BigQueryReadIntegrationTests):
   TABLE_DATA = [{
       'number': 1,
-      'string': u'你好',
+      'string': '你好',
       'time': '12:44:31',
       'datetime': '2018-12-31 12:44:31',
       'rec': None
   },
                 {
                     'number': 4,
-                    'string': u'привет',
+                    'string': 'привет',
                     'time': '12:44:31',
                     'datetime': '2018-12-31 12:44:31',
                     'rec': {
@@ -425,14 +425,14 @@ def test_iobase_source(self):
     EXPECTED_TABLE_DATA = [
         {
             'number': 1,
-            'string': u'你好',
+            'string': '你好',
             'time': datetime.time(12, 44, 31),
             'datetime': '2018-12-31T12:44:31',
             'rec': None,
         },
         {
             'number': 4,
-            'string': u'привет',
+            'string': 'привет',
             'time': datetime.time(12, 44, 31),
             'datetime': '2018-12-31T12:44:31',
             'rec': {
@@ -455,14 +455,14 @@ def test_iobase_source_with_native_datetime(self):
     EXPECTED_TABLE_DATA = [
         {
             'number': 1,
-            'string': u'你好',
+            'string': '你好',
             'time': datetime.time(12, 44, 31),
             'datetime': datetime.datetime(2018, 12, 31, 12, 44, 31),
             'rec': None,
         },
         {
             'number': 4,
-            'string': u'привет',
+            'string': 'привет',
             'time': datetime.time(12, 44, 31),
             'datetime': datetime.datetime(2018, 12, 31, 12, 44, 31),
             'rec': {
@@ -497,7 +497,7 @@ def test_iobase_source_with_column_selection(self):
   def test_iobase_source_with_row_restriction(self):
     EXPECTED_TABLE_DATA = [{
         'number': 1,
-        'string': u'你好',
+        'string': '你好',
         'time': datetime.time(12, 44, 31),
         'datetime': datetime.datetime(2018, 12, 31, 12, 44, 31),
         'rec': None
@@ -513,7 +513,7 @@ def test_iobase_source_with_row_restriction(self):
 
   @pytest.mark.it_postcommit
   def test_iobase_source_with_column_selection_and_row_restriction(self):
-    EXPECTED_TABLE_DATA = [{'string': u'привет'}]
+    EXPECTED_TABLE_DATA = [{'string': 'привет'}]
     with beam.Pipeline(argv=self.args) as p:
       result = (
           p | 'Read with BigQuery Storage API' >> beam.io.ReadFromBigQuery(
@@ -541,14 +541,14 @@ def test_iobase_source_with_query(self):
     EXPECTED_TABLE_DATA = [
         {
             'number': 1,
-            'string': u'你好',
+            'string': '你好',
             'time': datetime.time(12, 44, 31),
             'datetime': datetime.datetime(2018, 12, 31, 12, 44, 31),
             'rec': None,
         },
         {
             'number': 4,
-            'string': u'привет',
+            'string': 'привет',
             'time': datetime.time(12, 44, 31),
             'datetime': datetime.datetime(2018, 12, 31, 12, 44, 31),
             'rec': {
@@ -573,7 +573,7 @@ def test_iobase_source_with_query(self):
 
   @pytest.mark.it_postcommit
   def test_iobase_source_with_query_and_filters(self):
-    EXPECTED_TABLE_DATA = [{'string': u'привет'}]
+    EXPECTED_TABLE_DATA = [{'string': 'привет'}]
     query = StaticValueProvider(str, self.query)
     with beam.Pipeline(argv=self.args) as p:
       result = (
@@ -713,19 +713,19 @@ class ReadAllBQTests(BigQueryReadIntegrationTests):
   }, {
       'number': 2, 'str': 'def'
   }, {
-      'number': 3, 'str': u'你好'
+      'number': 3, 'str': '你好'
   }, {
-      'number': 4, 'str': u'привет'
+      'number': 4, 'str': 'привет'
   }]
 
   TABLE_DATA_2 = [{
       'number': 10, 'str': 'abcd'
   }, {
       'number': 20, 'str': 'defg'
   }, {
-      'number': 30, 'str': u'你好'
+      'number': 30, 'str': '你好'
   }, {
-      'number': 40, 'str': u'привет'
+      'number': 40, 'str': 'привет'
   }]
 
   TABLE_DATA_3 = [{'number': 10, 'str': 'abcde', 'extra': 3}]