readwriter.py 文件源码

def _test():
    import doctest
    import os
    import tempfile
    from pyspark.context import SparkContext
    from pyspark.sql import Row, SQLContext, HiveContext
    import pyspark.sql.readwriter

    os.chdir(os.environ["SPARK_HOME"])

    globs = pyspark.sql.readwriter.__dict__.copy()
    sc = SparkContext('local[4]', 'PythonTest')

    globs['tempfile'] = tempfile
    globs['os'] = os
    globs['sc'] = sc
    globs['sqlContext'] = SQLContext(sc)
    globs['hiveContext'] = HiveContext(sc)
    globs['df'] = globs['sqlContext'].read.parquet('python/test_support/sql/parquet_partitioned')

    (failure_count, test_count) = doctest.testmod(
        pyspark.sql.readwriter, globs=globs,
        optionflags=doctest.ELLIPSIS | doctest.NORMALIZE_WHITESPACE | doctest.REPORT_NDIFF)
    globs['sc'].stop()
    if failure_count:
        exit(-1)