RomanNum3ral
/
scrapy
mirror of https://github.com/scrapy/scrapy.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Changed TextResponse.replace() behaviour by keeping previous encoding when not specified

This commit is contained in:
Pablo Hoffman 2010-09-09 18:01:00 -03:00
parent b9ea9dcf1a
commit ad2b979e0f
2 changed files with 7 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
scrapy/http/response/text.py
View File

@ -53,7 +53,7 @@ class TextResponse(Response):
super(TextResponse, self)._set_body(body)
def replace(self, *args, **kwargs):
kwargs.setdefault('encoding', getattr(self, '_encoding', None))
kwargs.setdefault('encoding', self.encoding)
return Response.replace(self, *args, **kwargs)
@property

9
scrapy/tests/test_http_response.py
View File

@ -287,13 +287,16 @@ class XmlResponseTest(TextResponseTest):
r4 = r3.replace(body=body2)
self._assert_response_values(r4, 'utf-8', body2)
# make sure replace() rediscovers the encoding (if not given explicitly) when changing the body
def test_replace_encoding(self):
# make sure replace() keeps the previous encoding unless overridden explicitly
body = """<?xml version="1.0" encoding="iso-8859-1"?><xml></xml>"""
r5 = self.response_class("http://www.example.com", body=body)
body2 = """<?xml version="1.0" encoding="utf-8"?><xml></xml>"""
r5 = self.response_class("http://www.example.com", body=body)
r6 = r5.replace(body=body2)
r7 = r5.replace(body=body2, encoding='utf-8')
self._assert_response_values(r5, 'iso-8859-1', body)
self._assert_response_values(r6, 'utf-8', body2)
self._assert_response_values(r6, 'iso-8859-1', body2)
self._assert_response_values(r7, 'utf-8', body2)
if __name__ == "__main__":