def test_read_7z():
# file was created with:
# 7z a tests/data.7z tests/readme_example.py
# (brew install p7zip)
rdd = Context().textFile('{}/data.7z'.format(LOCAL_TEST_PATH))
print(rdd.collect())
assert 'from fast_pyspark_tester import Context' in rdd.collect()
def test_saveAsTextFile_zip():
tempFile = tempfile.NamedTemporaryFile(delete=True)
tempFile.close()
Context().parallelize(range(10)).saveAsTextFile(tempFile.name + '.zip')
read_rdd = Context().textFile(tempFile.name + '.zip')
print(read_rdd.collect())
assert '5' in read_rdd.collect()
def test_cache():
# this crashes in version 0.2.28
lines = Context().textFile('{}/*textFil*.py'.format(LOCAL_TEST_PATH))
lines = lines.map(lambda l: '-' + l).cache()
print(len(lines.collect()))
lines = lines.map(lambda l: '+' + l)
lines = lines.map(lambda l: '-' + l).cache()
lines = lines.collect()
print(lines)
assert '-+-from fast_pyspark_tester import Context' in lines
def test_hdfs_textFile_loop():
random.seed()
fn = '{}/pysparkling_test_{:d}.txt'.format(HDFS_TEST_PATH, random.random() * 999999.0)
print('HDFS test file: {0}'.format(fn))
rdd = Context().parallelize('Hello World {0}'.format(x) for x in range(10))
rdd.saveAsTextFile(fn)
read_rdd = Context().textFile(fn)
print(rdd.collect())
print(read_rdd.collect())
assert rdd.count() == read_rdd.count() and all(r1 == r2 for r1, r2 in zip(rdd.collect(), read_rdd.collect()))
def test_s3_textFile():
myrdd = Context().textFile('s3n://aws-publicdatasets/common-crawl/crawl-data/' 'CC-MAIN-2015-11/warc.paths.*')
assert (
'common-crawl/crawl-data/CC-MAIN-2015-11/segments/1424937481488.49/'
'warc/CC-MAIN-20150226075801-00329-ip-10-28-5-156.ec2.'
'internal.warc.gz' in myrdd.collect()
)
def test_s3_textFile_loop():
random.seed()
fn = '{}/pysparkling_test_{:d}.txt'.format(S3_TEST_PATH, random.random() * 999999.0)
rdd = Context().parallelize('Line {0}'.format(n) for n in range(200))
rdd.saveAsTextFile(fn)
rdd_check = Context().textFile(fn)
assert rdd.count() == rdd_check.count() and all(e1 == e2 for e1, e2 in zip(rdd.collect(), rdd_check.collect()))
from __future__ import print_function
from fast_pyspark_tester import Context
# read all the paths of warc and wat files of the latest Common Crawl
paths_rdd = Context().textFile(
's3n://aws-publicdatasets/common-crawl/crawl-data/CC-MAIN-2015-11/'
'warc.paths.*,'
's3n://aws-publicdatasets/common-crawl/crawl-data/CC-MAIN-2015-11/'
'wat.paths.gz',
)
print(paths_rdd.collect())
def test_local_textFile_1():
lines = Context().textFile('{}/*textFil*.py'.format(LOCAL_TEST_PATH))
lines = lines.collect()
print(lines)
assert 'from fast_pyspark_tester import Context' in lines
def test_read_tar_gz():
# file was created with:
# tar -cvzf data.tar.gz hello.txt
rdd = Context().textFile('{}/data.tar.gz'.format(LOCAL_TEST_PATH))
print(rdd.collect())
assert 'Hello fast_pyspark_tester!' in rdd.collect()
def test_http_textFile():
myrdd = Context().textFile(
'https://s3-us-west-2.amazonaws.com/human-microbiome-project/DEMO/' 'HM16STR/46333/by_subject/1139.fsa'
)
assert 'TGCTGCGGTGAATGCGTTCCCGGGTCT' in myrdd.collect()
