[
https://issues.apache.org/jira/browse/BEAM-10708?focusedWorklogId=642912&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-642912
]
ASF GitHub Bot logged work on BEAM-10708:
-----------------------------------------
Author: ASF GitHub Bot
Created on: 27/Aug/21 16:56
Start Date: 27/Aug/21 16:56
Worklog Time Spent: 10m
Work Description: KevinGG commented on a change in pull request #15368:
URL: https://github.com/apache/beam/pull/15368#discussion_r697588097
##########
File path: sdks/python/apache_beam/runners/interactive/sql/beam_sql_magics.py
##########
@@ -0,0 +1,283 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+"""Module of beam_sql cell magic that executes a Beam SQL.
+
+Only works within an IPython kernel.
+"""
+
+import importlib
+import logging
+from typing import Dict
+from typing import Optional
+from typing import Tuple
+from typing import Union
+
+import apache_beam as beam
+from apache_beam.pvalue import PValue
+from apache_beam.runners.interactive import cache_manager as cache
+from apache_beam.runners.interactive import interactive_beam as ib
+from apache_beam.runners.interactive import interactive_environment as ie
+from apache_beam.runners.interactive import pipeline_instrument as inst
+from apache_beam.runners.interactive.cache_manager import FileBasedCacheManager
+from apache_beam.runners.interactive.caching.streaming_cache import
StreamingCache
+from apache_beam.runners.interactive.sql.utils import find_pcolls
+from apache_beam.runners.interactive.sql.utils import is_namedtuple
+from apache_beam.runners.interactive.sql.utils import pcolls_by_name
+from apache_beam.runners.interactive.sql.utils import register_coder_for_schema
+from apache_beam.runners.interactive.sql.utils import
replace_single_pcoll_token
+from apache_beam.runners.interactive.utils import obfuscate
+from apache_beam.runners.interactive.utils import progress_indicated
+from apache_beam.testing import test_stream
+from apache_beam.testing.test_stream_service import TestStreamServiceController
+from apache_beam.transforms.sql import SqlTransform
+from IPython.core.magic import Magics
+from IPython.core.magic import cell_magic
+from IPython.core.magic import magics_class
+
+_LOGGER = logging.getLogger(__name__)
+
+_EXAMPLE_USAGE = """Usage:
+ %%%%beam_sql [output_name]
+ Calcite SQL statement
+ Syntax:
https://beam.apache.org/documentation/dsls/sql/calcite/query-syntax/
+ Please make sure that there is no conflicts between your variable names and
+ the SQL key words, such as "SELECT", "FROM", "WHERE" and etc.
+
+ output_name is optional. If not supplied, a variable name is automatically
+ assigned to the output of the magic.
+
+ The output of the magic is usually a PCollection or similar PValue,
+ depending on the SQL statement executed.
+"""
+
+
+def on_error(self, error_msg, *args):
+ """Logs the error and the usage example."""
+ _LOGGER.error(error_msg, *args)
+ _LOGGER.info(_EXAMPLE_USAGE)
+
+
+@magics_class
+class BeamSqlMagics(Magics):
+ @cell_magic
+ def beam_sql(self, line: str, cell: str) -> Union[None, PValue]:
+ """The beam_sql cell magic that executes a Beam SQL.
+
+ Args:
+ line: (optional) the string on the same line after the beam_sql magic.
+ Used as the output variable name in the __main__ module.
+ cell: everything else in the same notebook cell as a string. Used as a
+ Beam SQL query.
+
+ Returns None if running into an error, otherwise a PValue as if a
+ SqlTransform is applied.
+ """
+ if line and ' ' in line:
+ on_error(
+ 'Please make sure the output_name %s contains no whitespace.', line)
+ return
+ if not cell or cell.isspace():
+ on_error('Please supply the sql to be executed.')
+ return
+ found = find_pcolls(cell, pcolls_by_name())
+ for _, pcoll in found.items():
+ if not is_namedtuple(pcoll.element_type):
+ on_error(
+ 'PCollection %s of type %s is not a NamedTuple. See '
+ 'https://beam.apache.org/documentation/programming-guide/#schemas '
+ 'for more details.',
+ pcoll,
+ pcoll.element_type)
+ return
+ register_coder_for_schema(pcoll.element_type)
+
+ return apply_sql(cell, line, found)
+
+
+@progress_indicated
+def apply_sql(
+ query: str, output_name: Optional[str],
+ found: Dict[str, beam.PCollection]) -> PValue:
+ """Applies a SqlTransform with the given sql and queried PCollections.
+
+ Args:
+ query: The SQL query executed in the magic.
+ output_name: (optional) The output variable name in __main__ module.
+ found: The PCollections with variable names found to be used in the query.
+
+ Returns:
+ A PValue, mostly a PCollection, depending on the query.
+ """
+ output_name = _generate_output_name(output_name, query, found)
+ query, sql_source = _build_query_components(query, found)
+ try:
+ output = sql_source | SqlTransform(query)
+ setattr(importlib.import_module('__main__'), output_name, output)
+ ib.watch({output_name: output})
+ _LOGGER.info("The output PCollection is %s: %s", output_name, output)
Review comment:
Done.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: github-unsubscr...@beam.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
Issue Time Tracking
-------------------
Worklog Id: (was: 642912)
Time Spent: 26h 10m (was: 26h)
> InteractiveRunner cannot execute pipeline with cross-language transform
> -----------------------------------------------------------------------
>
> Key: BEAM-10708
> URL: https://issues.apache.org/jira/browse/BEAM-10708
> Project: Beam
> Issue Type: Bug
> Components: cross-language
> Reporter: Brian Hulette
> Assignee: Ning
> Priority: P2
> Time Spent: 26h 10m
> Remaining Estimate: 0h
>
> The InteractiveRunner crashes when given a pipeline that includes a
> cross-language transform.
> Here's the example I tried to run in a jupyter notebook:
> {code:python}
> p = beam.Pipeline(InteractiveRunner())
> pc = (p | SqlTransform("""SELECT
> CAST(1 AS INT) AS `id`,
> CAST('foo' AS VARCHAR) AS `str`,
> CAST(3.14 AS DOUBLE) AS `flt`"""))
> df = interactive_beam.collect(pc)
> {code}
> The problem occurs when
> [pipeline_fragment.py|https://github.com/apache/beam/blob/dce1eb83b8d5137c56ac58568820c24bd8fda526/sdks/python/apache_beam/runners/interactive/pipeline_fragment.py#L66]
> creates a copy of the pipeline by [writing it to proto and reading it
> back|https://github.com/apache/beam/blob/dce1eb83b8d5137c56ac58568820c24bd8fda526/sdks/python/apache_beam/runners/interactive/pipeline_fragment.py#L120].
> Reading it back fails because some of the pipeline is not written in Python.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
