From b71de57b210cd3277b096b7124634be627386e8b Mon Sep 17 00:00:00 2001
From: Pablo Hoffman <pablo@pablohoffman.com>
Date: Mon, 24 Aug 2009 09:47:26 -0300
Subject: [PATCH] some simplifications to Request and Response classes

---
 scrapy/http/request/form.py      |  2 +-
 scrapy/http/request/rpc.py       |  4 +++-
 scrapy/http/response/__init__.py | 12 ++++++----
 scrapy/http/response/html.py     |  2 +-
 scrapy/http/response/text.py     | 41 +++++++++++++-------------------
 scrapy/http/response/xml.py      |  2 +-
 6 files changed, 31 insertions(+), 32 deletions(-)

diff --git a/scrapy/http/request/form.py b/scrapy/http/request/form.py
index ab4784d5d..0f3d85c8a 100644
--- a/scrapy/http/request/form.py
+++ b/scrapy/http/request/form.py
@@ -26,7 +26,7 @@ class FormRequest(Request):
 
     def __init__(self, *args, **kwargs):
         formdata = kwargs.pop('formdata', None)
-        Request.__init__(self, *args, **kwargs)
+        super(FormRequest, self).__init__(*args, **kwargs)
 
         if formdata:
             items = formdata.iteritems() if isinstance(formdata, dict) else formdata
diff --git a/scrapy/http/request/rpc.py b/scrapy/http/request/rpc.py
index e3dbd2816..e941bf70b 100644
--- a/scrapy/http/request/rpc.py
+++ b/scrapy/http/request/rpc.py
@@ -12,6 +12,8 @@ from scrapy.http.request import Request
 
 class XmlRpcRequest(Request):
 
+    __slots__ = ()
+
     def __init__(self, *args, **kwargs):
         if 'body' not in kwargs:
             params = kwargs.pop('params')
@@ -24,5 +26,5 @@ class XmlRpcRequest(Request):
         # xmlrpc query multiples times over the same url
         kwargs.setdefault('dont_filter', True)
 
-        Request.__init__(self, *args, **kwargs)
+        super(XmlRpcRequest, self).__init__(*args, **kwargs)
         self.headers.setdefault('Content-Type', 'text/xml')
diff --git a/scrapy/http/response/__init__.py b/scrapy/http/response/__init__.py
index 8c133ca59..49a57dc5a 100644
--- a/scrapy/http/response/__init__.py
+++ b/scrapy/http/response/__init__.py
@@ -44,17 +44,20 @@ class Response(object_ref):
         if isinstance(body, str):
             self._body = body
         elif isinstance(body, unicode):
-            raise TypeError("Cannot assign a unicode body to a raw Response. Use TextResponse, HtmlResponse, etc")
+            raise TypeError("Cannot assign a unicode body to a raw Response. " \
+                "Use TextResponse, HtmlResponse, etc")
         elif body is None:
             self._body = ''
         else:
-            raise TypeError("Response body must either str or unicode. Got: '%s'" % type(body).__name__)
+            raise TypeError("Response body must either str or unicode. Got: '%s'" \
+                % type(body).__name__)
 
     body = property(_get_body, _set_body)
 
     def __repr__(self):
         return "%s(url=%s, headers=%s, status=%s, body=%s)" % \
-                (type(self).__name__, repr(self.url), repr(self.headers), repr(self.status), repr(self.body))
+            (type(self).__name__, repr(self.url), repr(self.headers), \
+            repr(self.status), repr(self.body))
 
     def __str__(self):
         flags = "(%s) " % ",".join(self.flags) if self.flags else ""
@@ -65,7 +68,8 @@ class Response(object_ref):
         """Return a copy of this Response"""
         return self.replace()
 
-    def replace(self, url=None, status=None, headers=None, body=None, meta=None, flags=None, cls=None, **kwargs):
+    def replace(self, url=None, status=None, headers=None, body=None, meta=None, \
+            flags=None, cls=None, **kwargs):
         """Create a new Response with the same attributes except for those
         given new values.
         """
diff --git a/scrapy/http/response/html.py b/scrapy/http/response/html.py
index 6c7c43a10..61269f86c 100644
--- a/scrapy/http/response/html.py
+++ b/scrapy/http/response/html.py
@@ -24,7 +24,7 @@ class HtmlResponse(TextResponse):
     METATAG_RE2 = re.compile(r'<meta\s+%s\s+%s' % (_content_re, _httpequiv_re), re.I)
 
     def body_encoding(self):
-        return self._body_declared_encoding() or self._body_inferred_encoding()
+        return self._body_declared_encoding() or super(HtmlResponse, self).body_encoding()
 
     @memoizemethod('cache')
     def _body_declared_encoding(self):
diff --git a/scrapy/http/response/text.py b/scrapy/http/response/text.py
index 0c726df37..0fa5b54ef 100644
--- a/scrapy/http/response/text.py
+++ b/scrapy/http/response/text.py
@@ -16,27 +16,22 @@ class TextResponse(Response):
 
     _ENCODING_RE = re.compile(r'charset=([\w-]+)', re.I)
 
-    __slots__ = ['_encoding']
+    __slots__ = ['_encoding', '_body_inferred_encoding']
 
-    def __init__(self, url, status=200, headers=None, body=None, meta=None, flags=None, encoding=None):
+    def __init__(self, url, status=200, headers=None, body=None, meta=None, \
+            flags=None, encoding=None):
         self._encoding = encoding
-        if isinstance(body, unicode):
-            if encoding is None:
-                clsname = self.__class__.__name__
-                raise TypeError("To instantiate a %s with unicode body you must specify the encoding" % clsname)
-            body = body.encode(encoding)
-        Response.__init__(self, url, status, headers, body, meta, flags)
+        self._body_inferred_encoding = None
+        super(TextResponse, self).__init__(url, status, headers, body, meta, flags)
 
-    def set_body(self, body):
-        if isinstance(body, str):
-            self._body = body
-        elif isinstance(body, unicode):
+    def _set_body(self, body):
+        if isinstance(body, unicode):
+            if self._encoding is None:
+                raise TypeError("To instantiate a %s with unicode body you " \
+                    "must specify the encoding" % self.__class__.__name__)
             self._body = body.encode(self._encoding)
-        elif body is None:
-            self._body = None
         else:
-            raise TypeError("Request body must either str, unicode or None. Got: '%s'" % type(body).__name__)
-    body = property(lambda x: x._body, set_body)
+            super(TextResponse, self)._set_body(body)
 
     def replace(self, *args, **kwargs):
         kwargs.setdefault('encoding', getattr(self, '_encoding', None))
@@ -59,19 +54,17 @@ class TextResponse(Response):
     @memoizemethod('cache')
     def body_as_unicode(self):
         """Return body as unicode"""
-        possible_encodings = (self._encoding, self.headers_encoding(), self._body_declared_encoding())
+        possible_encodings = (self._encoding, self.headers_encoding(), \
+            self._body_declared_encoding())
         dammit = UnicodeDammit(self.body, possible_encodings)
-        self.cache['body_inferred_encoding'] = dammit.originalEncoding
-        # XXX: sometimes dammit.unicode fails, even when it recognizes the encoding correctly
+        self._body_inferred_encoding = dammit.originalEncoding
         return dammit.unicode
 
     def body_encoding(self):
-        return self._body_inferred_encoding()
-
-    def _body_inferred_encoding(self):
-        if 'body_inferred_encoding' not in self.cache:
+        if self._body_inferred_encoding is None:
             self.body_as_unicode()
-        return self.cache['body_inferred_encoding']
+        return self._body_inferred_encoding
 
     def _body_declared_encoding(self):
+        # implemented in subclasses (XmlResponse, HtmlResponse)
         return None
diff --git a/scrapy/http/response/xml.py b/scrapy/http/response/xml.py
index 95c4a7e8c..485514179 100644
--- a/scrapy/http/response/xml.py
+++ b/scrapy/http/response/xml.py
@@ -19,7 +19,7 @@ class XmlResponse(TextResponse):
     XMLDECL_RE  = re.compile(r'<\?xml\s.*?%s' % _encoding_re, re.I)
 
     def body_encoding(self):
-        return self._body_declared_encoding() or self._body_inferred_encoding()
+        return self._body_declared_encoding() or super(XmlResponse, self).body_encoding()
 
     @memoizemethod('cache')
     def _body_declared_encoding(self):