Scrapy, a fast high-level web crawling & scraping framework for Python.
Remove deprecated scrapy.utils.gz.is_gzipped function
Eugenio Lacuesta51ca4d0138e5
diff --git a/scrapy/utils/gz.py b/scrapy/utils/gz.pyindex 11d433cf5..76156a4b8 100644--- a/scrapy/utils/gz.py+++ b/scrapy/utils/gz.py@@ -1,7 +1,6 @@+import structfrom gzip import GzipFilefrom io import BytesIO-import re-import structfrom scrapy.utils.decorators import deprecated@@ -42,17 +41,5 @@ def gunzip(data):return b''.join(output_list)-_is_gzipped = re.compile(br'^application/(x-)?gzip\b', re.I).search-_is_octetstream = re.compile(br'^(application|binary)/octet-stream\b', re.I).search---@deprecated-def is_gzipped(response):- """Return True if the response is gzipped, or False otherwise"""- ctype = response.headers.get('Content-Type', b'')- cenc = response.headers.get('Content-Encoding', b'').lower()- return _is_gzipped(ctype) or _is_octetstream(ctype) and cenc in (b'gzip', b'x-gzip')--def gzip_magic_number(response):return response.body[:3] == b'\x1f\x8b\x08'diff --git a/tests/test_utils_gz.py b/tests/test_utils_gz.pyindex 7148185f4..4943731cb 100644--- a/tests/test_utils_gz.py+++ b/tests/test_utils_gz.py@@ -3,10 +3,11 @@ from os.path import joinfrom w3lib.encoding import html_to_unicode-from scrapy.utils.gz import gunzip, is_gzipped-from scrapy.http import Response, Headers+from scrapy.utils.gz import gunzip, gzip_magic_number+from scrapy.http import Responsefrom tests import tests_datadir+SAMPLEDIR = join(tests_datadir, 'compressed')@@ -14,8 +15,12 @@ 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)+ r1 = Response("http://www.example.com", body=f.read())+ self.assertTrue(gzip_magic_number(r1))++ r2 = Response("http://www.example.com", body=gunzip(r1.body))+ self.assertFalse(gzip_magic_number(r2))+ self.assertEqual(len(r2.body), 9950)def test_gunzip_truncated(self):with open(join(SAMPLEDIR, 'truncated-crc-error.gz'), 'rb') as f:@@ -28,46 +33,16 @@ class GunzipTest(unittest.TestCase):def test_gunzip_truncated_short(self):with open(join(SAMPLEDIR, 'truncated-crc-error-short.gz'), 'rb') as f:- text = gunzip(f.read())- assert text.endswith(b'</html>')-- 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))+ r1 = Response("http://www.example.com", body=f.read())+ self.assertTrue(gzip_magic_number(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))+ r2 = Response("http://www.example.com", body=gunzip(r1.body))+ assert r2.body.endswith(b'</html>')+ self.assertFalse(gzip_magic_number(r2))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))+ self.assertFalse(gzip_magic_number(r1))def test_gunzip_illegal_eof(self):with open(join(SAMPLEDIR, 'unexpected-eof.gz'), 'rb') as f: