import unittest from os.path import join from w3lib.encoding import html_to_unicode from scrapy.utils.gz import gunzip, is_gzipped from scrapy.http import Response, Headers from tests import tests_datadir SAMPLEDIR = join(tests_datadir, 'compressed') class GunzipTest(unittest.TestCase): def test_gunzip_basic(self): with open(join(SAMPLEDIR, 'feed-sample1.xml.gz'), 'rb') as f: text = gunzip(f.read()) self.assertEqual(len(text), 9950) def test_gunzip_truncated(self): with open(join(SAMPLEDIR, 'truncated-crc-error.gz'), 'rb') as f: text = gunzip(f.read()) assert text.endswith(b'') def test_is_x_gzipped_right(self): hdrs = Headers({"Content-Type": "application/x-gzip"}) r1 = Response("http://www.example.com", headers=hdrs) self.assertTrue(is_gzipped(r1)) def test_is_gzipped_right(self): hdrs = Headers({"Content-Type": "application/gzip"}) r1 = Response("http://www.example.com", headers=hdrs) self.assertTrue(is_gzipped(r1)) def test_is_gzipped_not_quite(self): hdrs = Headers({"Content-Type": "application/gzippppp"}) r1 = Response("http://www.example.com", headers=hdrs) self.assertFalse(is_gzipped(r1)) def test_is_gzipped_case_insensitive(self): hdrs = Headers({"Content-Type": "Application/X-Gzip"}) r1 = Response("http://www.example.com", headers=hdrs) self.assertTrue(is_gzipped(r1)) hdrs = Headers({"Content-Type": "application/X-GZIP ; charset=utf-8"}) r1 = Response("http://www.example.com", headers=hdrs) self.assertTrue(is_gzipped(r1)) def test_is_gzipped_empty(self): r1 = Response("http://www.example.com") self.assertFalse(is_gzipped(r1)) def test_is_gzipped_wrong(self): hdrs = Headers({"Content-Type": "application/javascript"}) r1 = Response("http://www.example.com", headers=hdrs) self.assertFalse(is_gzipped(r1)) def test_is_gzipped_with_charset(self): hdrs = Headers({"Content-Type": "application/x-gzip;charset=utf-8"}) r1 = Response("http://www.example.com", headers=hdrs) self.assertTrue(is_gzipped(r1)) def test_gunzip_illegal_eof(self): with open(join(SAMPLEDIR, 'unexpected-eof.gz'), 'rb') as f: text = html_to_unicode('charset=cp1252', gunzip(f.read()))[1] with open(join(SAMPLEDIR, 'unexpected-eof-output.txt'), 'rb') as o: expected_text = o.read().decode("utf-8") self.assertEqual(len(text), len(expected_text)) self.assertEqual(text, expected_text)