def test_stream_case(self):
from pyflink.shell import s_env, st_env, FileSystem, OldCsv, DataTypes, Schema
# example begin
import tempfile
import os
import shutil
sink_path = tempfile.gettempdir() + '/streaming.csv'
if os.path.exists(sink_path):
if os.path.isfile(sink_path):
os.remove(sink_path)
else:
shutil.rmtree(sink_path)
s_env.set_parallelism(1)
t = st_env.from_elements([(1, 'hi', 'hello'), (2, 'hi', 'hello')], ['a', 'b', 'c'])
st_env.connect(FileSystem().path(sink_path))\
.with_format(OldCsv()
.field_delimiter(',')
.field("a", DataTypes.BIGINT())
.field("b", DataTypes.STRING())
.field("c", DataTypes.STRING()))\
.with_schema(Schema()
.field("a", DataTypes.BIGINT())
.field("b", DataTypes.STRING())
.field("c", DataTypes.STRING()))\
.create_temporary_table("stream_sink")
t.select("a + 1, b, c").execute_insert("stream_sink").wait()
# verify code, do not copy these code to shell.py
with open(sink_path, 'r') as f:
lines = f.read()
self.assertEqual(lines, '2,hi,hello\n' + '3,hi,hello\n')
# test pyflink shell environment
from pyflink.shell import b_env, bt_env, FileSystem, OldCsv, DataTypes, Schema
import tempfile
import os
import shutil
sink_path = tempfile.gettempdir() + '/batch.csv'
if os.path.exists(sink_path):
if os.path.isfile(sink_path):
os.remove(sink_path)
else:
shutil.rmtree(sink_path)
b_env.set_parallelism(1)
t = bt_env.from_elements([(1, 'hi', 'hello'), (2, 'hi', 'hello')], ['a', 'b', 'c'])
bt_env.connect(FileSystem().path(sink_path)) \
.with_format(OldCsv()
.field_delimiter(',')
.field("a", DataTypes.BIGINT())
.field("b", DataTypes.STRING())
.field("c", DataTypes.STRING())) \
.with_schema(Schema()
.field("a", DataTypes.BIGINT())
.field("b", DataTypes.STRING())
.field("c", DataTypes.STRING())) \
.create_temporary_table("batch_sink")
t.select("a + 1, b, c").execute_insert("batch_sink").get_job_client().get_job_execution_result().result()
with open(sink_path, 'r') as f:
lines = f.read()