def test_read_gunzip_file(self):
bucket, myfile = s3grep._parse_url(TestBotoStream.url)
resource = boto3.resource('s3')
obj3 = resource.Object(bucket, myfile)
datadict = obj3.get()
buffr = io.BufferedReader(boto_stream.BotoStreamBody(datadict['Body']))
reader = io.TextIOWrapper(gzip.GzipFile(fileobj=buffr, mode='rb'))
# check the first line
self.assertEqual(next(reader),
"common-crawl/crawl-data/CC-MAIN-2015-40/segments/"
"1443736672328.14/\n")
def test_grep_a_file(self):
bucket, myfile = s3grep._parse_url(TestS3Grep.url)
output = io.StringIO()
s3grep._grep_a_file(bucketstr=bucket, key=myfile,
regex=r'.*1443737929054.*', output=output)
self.assertEqual(output.getvalue(),
"common-crawl/crawl-data/CC-MAIN-2015-40/"
"segment.paths.gz:"
"common-crawl/crawl-data/CC-MAIN-2015-40/segments/"
"1443737929054.69/\n")
def test_read_full_binary_file(self):
bucket, myfile = s3grep._parse_url(TestBotoStream.url)
resource = boto3.resource('s3')
obj = resource.Object(bucket, myfile)
datadict = obj.get()
botostream = boto_stream.BotoStreamBody(body=datadict['Body'])
reader = io.BufferedReader(botostream)
# use the regular boto3 api
with tempfile.NamedTemporaryFile('wb') as tfile:
obj2 = resource.Object(bucket, myfile)
obj2.download_file(tfile.name)
with open(tfile.name, 'rb') as rtfile:
self.assertEqual(rtfile.read(), reader.read())
def test_parse_url(self):
bucket, myflie = s3grep._parse_url("s3://mybucket/myfile")
self.assertEqual(bucket, "mybucket")
self.assertEqual(myflie, "myfile")
