Python doctest.REPORT_NDIFF Examples

def _test():
    import doctest
    from pyspark.sql import SparkSession
    import pyspark.sql.column
    globs = pyspark.sql.column.__dict__.copy()
    spark = SparkSession.builder\
        .master("local[4]")\
        .appName("sql.column tests")\
        .getOrCreate()
    sc = spark.sparkContext
    globs['spark'] = spark
    globs['df'] = sc.parallelize([(2, 'Alice'), (5, 'Bob')]) \
        .toDF(StructType([StructField('age', IntegerType()),
                          StructField('name', StringType())]))

    (failure_count, test_count) = doctest.testmod(
        pyspark.sql.column, globs=globs,
        optionflags=doctest.ELLIPSIS | doctest.NORMALIZE_WHITESPACE | doctest.REPORT_NDIFF)
    spark.stop()
    if failure_count:
        sys.exit(-1) 

def _get_report_choice(key):
    """
    This function returns the actual `doctest` module flag value, we want to do it as late as possible to avoid
    importing `doctest` and all its dependencies when parsing options, as it adds overhead and breaks tests.
    """
    import doctest

    return {
        DOCTEST_REPORT_CHOICE_UDIFF: doctest.REPORT_UDIFF,
        DOCTEST_REPORT_CHOICE_CDIFF: doctest.REPORT_CDIFF,
        DOCTEST_REPORT_CHOICE_NDIFF: doctest.REPORT_NDIFF,
        DOCTEST_REPORT_CHOICE_ONLY_FIRST_FAILURE: doctest.REPORT_ONLY_FIRST_FAILURE,
        DOCTEST_REPORT_CHOICE_NONE: 0,
    }[key] 

def _get_report_choice(key):
    """
    This function returns the actual `doctest` module flag value, we want to do it as late as possible to avoid
    importing `doctest` and all its dependencies when parsing options, as it adds overhead and breaks tests.
    """
    import doctest

    return {
        DOCTEST_REPORT_CHOICE_UDIFF: doctest.REPORT_UDIFF,
        DOCTEST_REPORT_CHOICE_CDIFF: doctest.REPORT_CDIFF,
        DOCTEST_REPORT_CHOICE_NDIFF: doctest.REPORT_NDIFF,
        DOCTEST_REPORT_CHOICE_ONLY_FIRST_FAILURE: doctest.REPORT_ONLY_FIRST_FAILURE,
        DOCTEST_REPORT_CHOICE_NONE: 0,
    }[key] 

def _get_report_choice(key: str) -> int:
    """
    This function returns the actual `doctest` module flag value, we want to do it as late as possible to avoid
    importing `doctest` and all its dependencies when parsing options, as it adds overhead and breaks tests.
    """
    import doctest

    return {
        DOCTEST_REPORT_CHOICE_UDIFF: doctest.REPORT_UDIFF,
        DOCTEST_REPORT_CHOICE_CDIFF: doctest.REPORT_CDIFF,
        DOCTEST_REPORT_CHOICE_NDIFF: doctest.REPORT_NDIFF,
        DOCTEST_REPORT_CHOICE_ONLY_FIRST_FAILURE: doctest.REPORT_ONLY_FIRST_FAILURE,
        DOCTEST_REPORT_CHOICE_NONE: 0,
    }[key] 

def _test():
    import doctest
    import os
    import tempfile
    from pyspark.sql import Row, SparkSession, SQLContext
    import pyspark.sql.streaming

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

    globs = pyspark.sql.streaming.__dict__.copy()
    try:
        spark = SparkSession.builder.getOrCreate()
    except py4j.protocol.Py4JError:
        spark = SparkSession(sc)

    globs['tempfile'] = tempfile
    globs['os'] = os
    globs['spark'] = spark
    globs['sqlContext'] = SQLContext.getOrCreate(spark.sparkContext)
    globs['sdf'] = \
        spark.readStream.format('text').load('python/test_support/sql/streaming')
    globs['sdf_schema'] = StructType([StructField("data", StringType(), False)])
    globs['df'] = \
        globs['spark'].readStream.format('text').load('python/test_support/sql/streaming')

    (failure_count, test_count) = doctest.testmod(
        pyspark.sql.streaming, globs=globs,
        optionflags=doctest.ELLIPSIS | doctest.NORMALIZE_WHITESPACE | doctest.REPORT_NDIFF)
    globs['spark'].stop()

    if failure_count:
        sys.exit(-1) 

def _test():
    import doctest
    from pyspark.context import SparkContext
    from pyspark.sql import Row, SQLContext, SparkSession
    import pyspark.sql.dataframe
    from pyspark.sql.functions import from_unixtime
    globs = pyspark.sql.dataframe.__dict__.copy()
    sc = SparkContext('local[4]', 'PythonTest')
    globs['sc'] = sc
    globs['sqlContext'] = SQLContext(sc)
    globs['spark'] = SparkSession(sc)
    globs['df'] = sc.parallelize([(2, 'Alice'), (5, 'Bob')])\
        .toDF(StructType([StructField('age', IntegerType()),
                          StructField('name', StringType())]))
    globs['df2'] = sc.parallelize([Row(name='Tom', height=80), Row(name='Bob', height=85)]).toDF()
    globs['df3'] = sc.parallelize([Row(name='Alice', age=2),
                                   Row(name='Bob', age=5)]).toDF()
    globs['df4'] = sc.parallelize([Row(name='Alice', age=10, height=80),
                                   Row(name='Bob', age=5, height=None),
                                   Row(name='Tom', age=None, height=None),
                                   Row(name=None, age=None, height=None)]).toDF()
    globs['df5'] = sc.parallelize([Row(name='Alice', spy=False, age=10),
                                   Row(name='Bob', spy=None, age=5),
                                   Row(name='Mallory', spy=True, age=None)]).toDF()
    globs['sdf'] = sc.parallelize([Row(name='Tom', time=1479441846),
                                   Row(name='Bob', time=1479442946)]).toDF()

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

def _test():
    import doctest
    from pyspark.sql import Row, SparkSession
    import pyspark.sql.group
    globs = pyspark.sql.group.__dict__.copy()
    spark = SparkSession.builder\
        .master("local[4]")\
        .appName("sql.group tests")\
        .getOrCreate()
    sc = spark.sparkContext
    globs['sc'] = sc
    globs['spark'] = spark
    globs['df'] = sc.parallelize([(2, 'Alice'), (5, 'Bob')]) \
        .toDF(StructType([StructField('age', IntegerType()),
                          StructField('name', StringType())]))
    globs['df3'] = sc.parallelize([Row(name='Alice', age=2, height=80),
                                   Row(name='Bob', age=5, height=85)]).toDF()
    globs['df4'] = sc.parallelize([Row(course="dotNET", year=2012, earnings=10000),
                                   Row(course="Java",   year=2012, earnings=20000),
                                   Row(course="dotNET", year=2012, earnings=5000),
                                   Row(course="dotNET", year=2013, earnings=48000),
                                   Row(course="Java",   year=2013, earnings=30000)]).toDF()
    globs['df5'] = sc.parallelize([
        Row(training="expert", sales=Row(course="dotNET", year=2012, earnings=10000)),
        Row(training="junior", sales=Row(course="Java",   year=2012, earnings=20000)),
        Row(training="expert", sales=Row(course="dotNET", year=2012, earnings=5000)),
        Row(training="junior", sales=Row(course="dotNET", year=2013, earnings=48000)),
        Row(training="expert", sales=Row(course="Java",   year=2013, earnings=30000))]).toDF()

    (failure_count, test_count) = doctest.testmod(
        pyspark.sql.group, globs=globs,
        optionflags=doctest.ELLIPSIS | doctest.NORMALIZE_WHITESPACE | doctest.REPORT_NDIFF)
    spark.stop()
    if failure_count:
        sys.exit(-1) 

def _test():
    import doctest
    import os
    import tempfile
    import py4j
    from pyspark.context import SparkContext
    from pyspark.sql import SparkSession, Row
    import pyspark.sql.readwriter

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

    globs = pyspark.sql.readwriter.__dict__.copy()
    sc = SparkContext('local[4]', 'PythonTest')
    try:
        spark = SparkSession.builder.getOrCreate()
    except py4j.protocol.Py4JError:
        spark = SparkSession(sc)

    globs['tempfile'] = tempfile
    globs['os'] = os
    globs['sc'] = sc
    globs['spark'] = spark
    globs['df'] = spark.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)
    sc.stop()
    if failure_count:
        sys.exit(-1) 

def test_acceptance(self):
        output = self.format_tree(ACCEPTANCE_INPUT)
        self.assertThat(
            output,
            DocTestMatches(
                ACCEPTANCE_OUTPUT,
                doctest.ELLIPSIS |
                doctest.NORMALIZE_WHITESPACE |
                doctest.REPORT_NDIFF)) 

def test_stopTestRun_shows_details(self):
        def run_tests():
            self.result.startTestRun()
            make_erroring_test().run(self.result)
            make_unexpectedly_successful_test().run(self.result)
            make_failing_test().run(self.result)
            self.reset_output()
            self.result.stopTestRun()
        run_with_stack_hidden(True, run_tests)
        self.assertThat(self.getvalue(),
            DocTestMatches("""...======================================================================
ERROR: testtools.tests.test_testresult.Test.error
----------------------------------------------------------------------
Traceback (most recent call last):
  File "...testtools...tests...test_testresult.py", line ..., in error
    1/0
ZeroDivisionError:... divi... by zero...
======================================================================
FAIL: testtools.tests.test_testresult.Test.failed
----------------------------------------------------------------------
Traceback (most recent call last):
  File "...testtools...tests...test_testresult.py", line ..., in failed
    self.fail("yo!")
AssertionError: yo!
======================================================================
UNEXPECTED SUCCESS: testtools.tests.test_testresult.Test.succeeded
----------------------------------------------------------------------
...""", doctest.ELLIPSIS | doctest.REPORT_NDIFF)) 

def test_suite():
    m =  doctest.Manuel(optionflags=REPORT_NDIFF|ELLIPSIS)
    return TestSuite(m, *tests,
                     setUp=setUp,
                     tearDown=tearDown) 

def test_other_docs(mod, capsys):
    fail, total = doctest.testmod(mod, optionflags=doctest.REPORT_NDIFF)
    if fail > 0:
        captured = capsys.readouterr()
        pytest.fail("{} out of {} examples failed:\n{}\n{}".format(
            fail, total, captured.err, captured.out), pytrace=False) 

def test_no_trailing_whitespace_stripping():
    r"""
    The fancy reports had a bug for a long time where any trailing whitespace on
    the reported diff lines was stripped, making it impossible to see the
    differences in line reported as different that differed only in the amount of
    trailing whitespace.  The whitespace still isn't particularly visible unless
    you use NDIFF, but at least it is now there to be found.

    *NOTE*: This snippet was intentionally put inside a raw string to get rid of
    leading whitespace error in executing the example below

    >>> def f(x):
    ...     r'''
    ...     >>> print('\n'.join(['a    ', 'b']))
    ...     a
    ...     b
    ...     '''
    """
    """
    *NOTE*: These doctest are not placed in raw string to depict the trailing whitespace
    using `\x20`

    >>> test = doctest.DocTestFinder().find(f)[0]
    >>> flags = doctest.REPORT_NDIFF
    >>> doctest.DocTestRunner(verbose=False, optionflags=flags).run(test)
    ... # doctest: +ELLIPSIS
    **********************************************************************
    File ..., line 3, in f
    Failed example:
        print('\n'.join(['a    ', 'b']))
    Differences (ndiff with -expected +actual):
        - a
        + a
          b
    TestResults(failed=1, attempted=1)

    *NOTE*: `\x20` is for checking the trailing whitespace on the +a line above.
    We cannot use actual spaces there, as a commit hook prevents from committing
    patches that contain trailing whitespace. More info on Issue 24746.
    """

######################################################################
## Main
###################################################################### 

def test_no_trailing_whitespace_stripping():
    r"""
    The fancy reports had a bug for a long time where any trailing whitespace on
    the reported diff lines was stripped, making it impossible to see the
    differences in line reported as different that differed only in the amount of
    trailing whitespace.  The whitespace still isn't particularly visible unless
    you use NDIFF, but at least it is now there to be found.

    *NOTE*: This snippet was intentionally put inside a raw string to get rid of
    leading whitespace error in executing the example below

    >>> def f(x):
    ...     r'''
    ...     >>> print('\n'.join(['a    ', 'b']))
    ...     a
    ...     b
    ...     '''
    """
    """
    *NOTE*: These doctest are not placed in raw string to depict the trailing whitespace
    using `\x20`

    >>> test = doctest.DocTestFinder().find(f)[0]
    >>> flags = doctest.REPORT_NDIFF
    >>> doctest.DocTestRunner(verbose=False, optionflags=flags).run(test)
    ... # doctest: +ELLIPSIS
    **********************************************************************
    File ..., line 3, in f
    Failed example:
        print('\n'.join(['a    ', 'b']))
    Differences (ndiff with -expected +actual):
        - a
        + a
          b
    TestResults(failed=1, attempted=1)

    *NOTE*: `\x20` is for checking the trailing whitespace on the +a line above.
    We cannot use actual spaces there, as a commit hook prevents from committing
    patches that contain trailing whitespace. More info on Issue 24746.
    """

######################################################################
## Main
######################################################################