Github user HyukjinKwon commented on a diff in the pull request:

    https://github.com/apache/spark/pull/18702#discussion_r128892162
  
    --- Diff: sql/gen-sql-markdown.py ---
    @@ -0,0 +1,96 @@
    +#
    +# 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.
    +#
    +
    +import sys
    +import os
    +from collections import namedtuple
    +
    +from pyspark.sql import SparkSession
    +
    +ExpressionInfo = namedtuple("ExpressionInfo", "className usage name 
extended")
    +
    +
    +def _list_function_infos(spark):
    +    """
    +    Returns a list of function information from JVM. Sorts wrapped 
expression infos by name
    +    and returns them.
    +    """
    +
    +    jinfos = spark.sparkContext._jvm \
    +        
.org.apache.spark.sql.api.python.PythonSQLUtils.listBuiltinFunctionInfos()
    +    infos = []
    +    for jinfo in jinfos:
    +        name = jinfo.getName()
    +        usage = jinfo.getUsage()
    +        usage = usage.replace("_FUNC_", name) if usage is not None else 
usage
    +        extended = jinfo.getExtended()
    +        extended = extended.replace("_FUNC_", name) if extended is not 
None else extended
    +        infos.append(ExpressionInfo(
    +            className=jinfo.getClassName(),
    +            usage=usage,
    +            name=name,
    +            extended=extended))
    +    return sorted(infos, key=lambda i: i.name)
    +
    +
    +def _make_pretty_usage(usage):
    +    """
    +    Makes the function usage description pretty and returns the string.
    +    Otherwise, returns None.
    +    """
    +
    +    if usage is not None and usage.strip() != "":
    +        usage = "\n".join(map(lambda u: u.strip(), usage.split("\n")))
    +        return "%s\n\n" % usage
    +
    +
    +def _make_pretty_extended(extended):
    +    """
    +    Makes the function extended description pretty and returns the string.
    +    Otherwise, returns None.
    +    """
    +
    +    if extended is not None and extended.strip() != "":
    --- End diff --
    
    @rxin, I could make this prettier with manual parsing and tried many things 
but I just revert them back. I was thinking it'd be rather better if we make 
some changes within `ExpressionDescription` and `ExpressionInfo` and I was 
thinking I could do this in a followup. WDYT?
    
    If it does not sound good to you, I am willing to add some parsing logics 
here, mainly, to separate examples and arguments in extended description.


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to