rattail/appypod-rattail
1
0
Fork 0
Code Issues Pull requests Actions Packages Projects Releases Wiki Activity

[pod] Bugfix for https://bugs.launchpad.net/appy/+bug/1083533 (thanks Gauthier).

Browse source
This commit is contained in:
Gaetan Delannay 2012-12-07 12:05:39 +01:00
parent 68ae08b75a
commit d0da6740b1
1 changed files with 8 additions and 13 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
shared/xml_parser.py
View file

@ -19,9 +19,11 @@
# ------------------------------------------------------------------------------ # ------------------------------------------------------------------------------
import xml.sax, difflib, types, cgi import xml.sax, difflib, types, cgi
from xml.parsers.expat import XML_PARAM_ENTITY_PARSING_NEVER
from xml.sax.handler import ContentHandler, ErrorHandler, feature_external_ges from xml.sax.handler import ContentHandler, ErrorHandler, feature_external_ges
from xml.sax.xmlreader import InputSource from xml.sax.xmlreader import InputSource
from xml.sax import SAXParseException from xml.sax import SAXParseException
from appy.shared import UnicodeBuffer from appy.shared import UnicodeBuffer
from appy.shared.errors import AppyError from appy.shared.errors import AppyError
from appy.shared.utils import sequenceTypes from appy.shared.utils import sequenceTypes
@ -176,7 +178,9 @@ class XmlParser(ContentHandler, ErrorHandler):
# ContentHandler methods --------------------------------------------------- # ContentHandler methods ---------------------------------------------------
def startDocument(self): def startDocument(self):
self.parser._parser.UseForeignDTD(True) parser = self.parser._parser
parser.UseForeignDTD(True)
parser.SetParamEntityParsing(XML_PARAM_ENTITY_PARSING_NEVER)
def setDocumentLocator(self, locator): def setDocumentLocator(self, locator):
self.locator = locator self.locator = locator
return self.env return self.env
@ -311,6 +315,7 @@ class XmlUnmarshaller(XmlParser):
return res return res
def startDocument(self): def startDocument(self):
XmlParser.startDocument(self)
self.res = None # The resulting web of Python objects (Object instances) self.res = None # The resulting web of Python objects (Object instances)
self.env.containerStack = [] # The stack of current "containers" where self.env.containerStack = [] # The stack of current "containers" where
# to store the next parsed element. A container can be a list, a tuple, # to store the next parsed element. A container can be a list, a tuple,
@ -978,17 +983,6 @@ class XhtmlCleaner(XmlParser):
# Tags that required a line break to be inserted after them. # Tags that required a line break to be inserted after them.
lineBreakTags = ('p', 'li', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'td') lineBreakTags = ('p', 'li', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'td')
# A pre-cleaning phase consists in performing some replacements before
# running the XML SAX parsing. The dict below contains such repls.
preCleanRepls = {' ': ' '}
def preClean(self, s):
'''Before true XHTML cleaning, this method performs pre-cleaning by
performing, on p_s, replacements as defined in self.preCleanRepls.'''
for item, repl in self.preCleanRepls.iteritems():
if item in s:
s = s.replace(item, repl)
return s
def clean(self, s, keepStyles=True): def clean(self, s, keepStyles=True):
'''Cleaning XHTML code is done for 2 reasons: '''Cleaning XHTML code is done for 2 reasons:
@ -1017,7 +1011,7 @@ class XhtmlCleaner(XmlParser):
# also ignore its content. # also ignore its content.
self.env.ignoreContent = False self.env.ignoreContent = False
try: try:
res = self.parse('<x>%s</x>' % self.preClean(s)).encode('utf-8') res = self.parse('<x>%s</x>' % s).encode('utf-8')
except SAXParseException, e: except SAXParseException, e:
raise self.Error(str(e)) raise self.Error(str(e))
return res return res
@ -1033,6 +1027,7 @@ class XhtmlCleaner(XmlParser):
def startDocument(self): def startDocument(self):
# The result will be cleaned XHTML, joined from self.res. # The result will be cleaned XHTML, joined from self.res.
XmlParser.startDocument(self)
self.res = [] self.res = []
def endDocument(self): def endDocument(self):