[BEAM-1251] Modernize Python 2 code to get ready for Python 3

.test-infra/jenkins/dependency_check/bigquery_client_utils.py

@@ -1,3 +1,4 @@
+from __future__ import print_function
 #
 # Licensed to the Apache Software Foundation (ASF) under one or more
 # contributor license agreements.  See the NOTICE file distributed with
@@ -101,7 +102,7 @@ def insert_dep_to_table(self, dep, version, release_date, is_currently_used=Fals
     try:
       query_job = self.bigquery_client.query(query)
       if not query_job.done():
-        print query_job.result()
+        print(query_job.result())
     except:
       raise
 
@@ -123,7 +124,7 @@ def delete_dep_from_table(self, dep, version):
     try:
       query_job = self.bigquery_client.query(query)
       if not query_job.done():
-        print query_job.result()
+        print(query_job.result())
     except:
       raise
 

.test-infra/jenkins/dependency_check/dependency_check_report_generator.py

@@ -56,7 +56,7 @@ def extract_results(file_path):
           see_oudated_deps = True
     raw_report.close()
     return outdated_deps
-  except Exception, e:
+  except Exception as e:
     raise
 
 
@@ -266,7 +266,7 @@ def generate_report(file_path, sdk_type, project_id, dataset_id, table_id):
     for dep in high_priority_deps:
       report.write("%s" % dep)
     report.write("</table>\n")
-  except Exception, e:
+  except Exception as e:
     report.write('<p> {0} </p>'.format(str(e)))
 
   report.close()

.test-infra/jenkins/dependency_check/dependency_check_report_generator_test.py

@@ -19,6 +19,7 @@
 #   This script performs testing of scenarios from verify_performance_test_results.py
 #
 
+from __future__ import print_function
 import unittest, mock
 from mock import patch
 from datetime import datetime
@@ -39,7 +40,7 @@ class DependencyCheckReportGeneratorTest(unittest.TestCase):
   """Tests for `dependency_check_report_generator.py`."""
 
   def setUp(self):
-    print "Test name:", self._testMethodName
+    print("Test name:", self._testMethodName)
 
 
   @patch('google.cloud.bigquery.Client')

sdks/python/apache_beam/runners/worker/sdk_worker.py

@@ -176,7 +176,7 @@ def _request_process_bundle_progress(self, request):
     def task():
       instruction_reference = getattr(
           request, request.WhichOneof('request')).instruction_reference
-      if self._instruction_id_vs_worker.has_key(instruction_reference):
+      if instruction_reference in self._instruction_id_vs_worker:
         self._execute(
             lambda: self._instruction_id_vs_worker[
                 instruction_reference

sdks/python/apache_beam/runners/worker/sdk_worker_main.py

@@ -158,10 +158,10 @@ def _get_worker_count(pipeline_options):
     an int containing the worker_threads to use. Default is 1
   """
   pipeline_options = pipeline_options.get(
-      'options') if pipeline_options.has_key('options') else {}
+      'options') if 'options' in pipeline_options else {}
   experiments = pipeline_options.get(
       'experiments'
-  ) if pipeline_options and pipeline_options.has_key('experiments') else []
+  ) if pipeline_options and 'experiments' in pipeline_options else []
 
   experiments = experiments if experiments else []
 

sdks/python/apache_beam/runners/worker/worker_id_interceptor.py

@@ -39,8 +39,7 @@ class WorkerIdInterceptor(grpc.StreamStreamClientInterceptor):
   # and throw exception in worker_id_interceptor.py after we have rolled out
   # the corresponding container changes.
   # Unique worker Id for this worker.
-  _worker_id = os.environ['WORKER_ID'] if os.environ.has_key(
-      'WORKER_ID') else str(uuid.uuid4())
+  _worker_id = os.environ.get('WORKER_ID', str(uuid.uuid4()))
 
   def __init__(self):
     pass

sdks/python/apache_beam/tools/map_fn_microbenchmark.py

@@ -56,7 +56,7 @@ def run_benchmark(num_maps=100, num_runs=10, num_elements_step=1000):
     print("%6d element%s %g sec" % (
         num_elements, " " if num_elements == 1 else "s", timings[num_elements]))
 
-  print
+  print()
   # pylint: disable=unused-variable
   gradient, intercept, r_value, p_value, std_err = stats.linregress(
       *list(zip(*list(timings.items()))))

website/.jenkins/append_index_html_to_internal_links.py

@@ -29,12 +29,18 @@
   'sudo apt-get install python-beautifulsoup4'.
 
 """
+from __future__ import print_function
 
 import fnmatch
 import os
 import re
 from bs4 import BeautifulSoup
 
+try:
+    unicode           # pylint: disable=unicode-builtin
+except NameError:
+    unicode = str
+
 # Original link match. Matches any string which starts with '/' and doesn't
 # have a file extension.
 linkMatch = r'^\/(.*\.(?!([^\/]+)$))?[^.]*$'
@@ -56,10 +62,10 @@
     if 'javadoc' not in root:
       matches.append(os.path.join(root, filename))
 
-print 'Matches: ' + str(len(matches))
+print('Matches: ' + str(len(matches)))
 # Iterates over each matched file looking for link matches.
 for match in matches:
-  print 'Fixing links in: ' + match
+  print('Fixing links in: ' + match)
   mf = open(match)
   soup = BeautifulSoup(mf)
   # Iterates over every <a>
@@ -86,7 +92,7 @@
         html = unicode(soup).encode('utf-8')
         # Write back to the file.
         with open(match, "wb") as f:
-          print 'Replacing ' + hr + ' with: ' + a['href']
+          print('Replacing ' + hr + ' with: ' + a['href'])
           f.write(html)
     except KeyError as e:
       # Some <a> tags don't have an href.