add a new method iter_process_result which does the same as proces_result but is a generator (closes #1625374)
process_result is reimplemented using the new method, and the two helper
methods are turned into generators.
These generators use cursor.fetchmany instead of cursor.fetchall after setting
cursor.arraysize to 100. This means that the whole result set should never
loaded in memory when using the iter_process_result method. This is used in the
"portable" database dump implementation when we typically to 'SELECT * FROM
table', but could probably be used too in other parts of cubicweb.
# copyright 2003-2010 LOGILAB S.A. (Paris, FRANCE), all rights reserved.# contact http://www.logilab.fr/ -- mailto:contact@logilab.fr## This file is part of CubicWeb.## CubicWeb is free software: you can redistribute it and/or modify it under the# terms of the GNU Lesser General Public License as published by the Free# Software Foundation, either version 2.1 of the License, or (at your option)# any later version.## CubicWeb is distributed in the hope that it will be useful, but WITHOUT# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS# FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License for more# details.## You should have received a copy of the GNU Lesser General Public License along# with CubicWeb. If not, see <http://www.gnu.org/licenses/>."""WSGI request adapter for cubicwebNOTE: each docstring tagged with ``COME FROM DJANGO`` means thatthe code has been taken (or adapted) from Djanco source code : http://www.djangoproject.com/"""__docformat__="restructuredtext en"fromStringIOimportStringIOfromurllibimportquotefromlogilab.common.decoratorsimportcachedfromcubicweb.web.requestimportCubicWebRequestBasefromcubicweb.wsgiimport(pformat,qs2dict,safe_copyfileobj,parse_file_upload,normalize_header)classCubicWebWsgiRequest(CubicWebRequestBase):"""most of this code COMES FROM DJANO """def__init__(self,environ,vreg,base_url=None):self.environ=environself.path=environ['PATH_INFO']self.method=environ['REQUEST_METHOD'].upper()self._headers=dict([(normalize_header(k[5:]),v)fork,vinself.environ.items()ifk.startswith('HTTP_')])https=environ.get("HTTPS")in('yes','on','1')self._base_url=base_urlorself.instance_uri()post,files=self.get_posted_data()super(CubicWebWsgiRequest,self).__init__(vreg,https,post)iffilesisnotNone:forkey,(name,_,stream)infiles.iteritems():name=unicode(name,self.encoding)self.form[key]=(name,stream)# prepare output headersself.headers_out={}def__repr__(self):# Since this is called as part of error handling, we need to be very# robust against potentially malformed input.form=pformat(self.form)meta=pformat(self.environ)return'<CubicWebWsgiRequest\FORM:%s,\nMETA:%s>'% \(form,meta)## cubicweb request interface ################################################defbase_url(self):returnself._base_urldefhttp_method(self):"""returns 'POST', 'GET', 'HEAD', etc."""returnself.methoddefrelative_path(self,includeparams=True):"""return the normalized path of the request (ie at least relative to the instance's root, but some other normalization may be needed so that the returned path may be used to compare to generated urls :param includeparams: boolean indicating if GET form parameters should be kept in the path """path=self.environ['PATH_INFO']path=path[1:]# remove leading '/'ifincludeparams:qs=self.environ.get('QUERY_STRING')ifqs:return'%s?%s'%(path,qs)returnpathdefget_header(self,header,default=None):"""return the value associated with the given input HTTP header, raise KeyError if the header is not set """returnself._headers.get(normalize_header(header),default)defset_header(self,header,value,raw=True):"""set an output HTTP header"""assertraw,"don't know anything about non-raw headers for wsgi requests"self.headers_out[header]=valuedefadd_header(self,header,value):"""add an output HTTP header"""self.headers_out[header]=valuedefremove_header(self,header):"""remove an output HTTP header"""self.headers_out.pop(header,None)defheader_if_modified_since(self):"""If the HTTP header If-modified-since is set, return the equivalent mx date time value (GMT), else return None """returnNone## wsgi request helpers ###################################################definstance_uri(self):"""Return the instance's base URI (no PATH_INFO or QUERY_STRING) see python2.5's wsgiref.util.instance_uri code """environ=self.environurl=environ['wsgi.url_scheme']+'://'ifenviron.get('HTTP_HOST'):url+=environ['HTTP_HOST']else:url+=environ['SERVER_NAME']ifenviron['wsgi.url_scheme']=='https':ifenviron['SERVER_PORT']!='443':url+=':'+environ['SERVER_PORT']else:ifenviron['SERVER_PORT']!='80':url+=':'+environ['SERVER_PORT']url+=quote(environ.get('SCRIPT_NAME')or'/')returnurldefget_full_path(self):return'%s%s'%(self.path,self.environ.get('QUERY_STRING','')and('?'+self.environ.get('QUERY_STRING',''))or'')defis_secure(self):return'wsgi.url_scheme'inself.environ \andself.environ['wsgi.url_scheme']=='https'defget_posted_data(self):files=Noneifself.method=='POST':ifself.environ.get('CONTENT_TYPE','').startswith('multipart'):header_dict=dict((normalize_header(k[5:]),v)fork,vinself.environ.items()ifk.startswith('HTTP_'))header_dict['Content-Type']=self.environ.get('CONTENT_TYPE','')post,files=parse_file_upload(header_dict,self.raw_post_data)else:post=qs2dict(self.raw_post_data)else:# The WSGI spec says 'QUERY_STRING' may be absent.post=qs2dict(self.environ.get('QUERY_STRING',''))returnpost,files@property@cacheddefraw_post_data(self):buf=StringIO()try:# CONTENT_LENGTH might be absent if POST doesn't have content at all (lighttpd)content_length=int(self.environ.get('CONTENT_LENGTH',0))exceptValueError:# if CONTENT_LENGTH was empty string or not an integercontent_length=0ifcontent_length>0:safe_copyfileobj(self.environ['wsgi.input'],buf,size=content_length)postdata=buf.getvalue()buf.close()returnpostdatadef_validate_cache(self):"""raise a `DirectResponse` exception if a cached page along the way exists and is still usable """# XXX# if self.get_header('Cache-Control') in ('max-age=0', 'no-cache'):# # Expires header seems to be required by IE7# self.add_header('Expires', 'Sat, 01 Jan 2000 00:00:00 GMT')# return# try:# http.checkPreconditions(self._twreq, _PreResponse(self))# except http.HTTPError, ex:# self.info('valid http cache, no actual rendering')# raise DirectResponse(ex.response)# Expires header seems to be required by IE7self.add_header('Expires','Sat, 01 Jan 2000 00:00:00 GMT')