def stringForEntity(node):
"""Replaces entities in the node."""
text = node.serialize('utf-8')
try:
# Lets add document DTD so entities are resolved
dtd = node.doc.intSubset()
tmp = dtd.serialize('utf-8') + '<norm>%s</norm>' % text
next = 1
except:
tmp = '<norm>%s</norm>' % text
next = 0
ctxt = libxml2.createDocParserCtxt(tmp)
if expand_entities:
ctxt.replaceEntities(1)
ctxt.parseDocument()
tree = ctxt.doc()
if next:
newnode = tree.children.next
else:
newnode = tree.children
result = ''
child = newnode.children
while child:
result += child.serialize('utf-8')
child = child.next
return result
def replaceNodeContentsWithText(node,text):
"""Replaces all subnodes of a node with contents of text treated as XML."""
if node.children:
starttag = startTagForNode(node)
endtag = endTagForNode(node)
# Lets add document DTD so entities are resolved
tmp = '<?xml version="1.0" encoding="utf-8" ?>'
try:
dtd = doc.intSubset()
tmp = tmp + dtd.serialize('utf-8')
except libxml2.treeError:
pass
content = '<%s>%s</%s>' % (starttag, text, endtag)
tmp = tmp + content.encode('utf-8')
newnode = None
try:
ctxt = libxml2.createDocParserCtxt(tmp)
ctxt.replaceEntities(0)
ctxt.parseDocument()
newnode = ctxt.doc()
except:
pass
if not newnode:
print >> sys.stderr, """Error while parsing translation as XML:\n"%s"\n""" % (text.encode('utf-8'))
return
newelem = newnode.getRootElement()
if newelem and newelem.children:
free = node.children
while free:
next = free.next
free.unlinkNode()
free = next
if node:
copy = newelem.copyNodeList()
next = node.next
node.replaceNode(newelem.copyNodeList())
node.next = next
else:
# In practice, this happens with tags such as "<para> </para>" (only whitespace in between)
pass
else:
node.setContent(text)
def replaceNodeContentsWithText(node,text):
"""Replaces all subnodes of a node with contents of text treated as XML."""
if node.children:
starttag = node.name #startTagForNode(node)
endtag = endTagForNode(node)
try:
# Lets add document DTD so entities are resolved
dtd = doc.intSubset()
tmp = ''
if expand_entities: # FIXME: we get a "Segmentation fault" in libxml2.parseMemory() when we include DTD otherwise
tmp = dtd.serialize('utf-8')
tmp = tmp + '<%s>%s</%s>' % (starttag, text, endtag)
except:
tmp = '<%s>%s</%s>' % (starttag, text, endtag)
try:
ctxt = libxml2.createDocParserCtxt(tmp.encode('utf-8'))
ctxt.replaceEntities(0)
ctxt.parseDocument()
newnode = ctxt.doc()
except:
print >> sys.stderr, """Error while parsing translation as XML:\n"%s"\n""" % (text.encode('utf-8'))
return
newelem = newnode.getRootElement()
if newelem and newelem.children:
free = node.children
while free:
next = free.next
free.unlinkNode()
free = next
node.addChildList(newelem.children)
else:
# In practice, this happens with tags such as "<para> </para>" (only whitespace in between)
pass
else:
node.setContent(text)
def validate(self,xml,container,line_offset=0,char_offset=0):
dtd=self.plugin.settings["dtd"]
xml=(u"<!DOCTYPE %s %s>\n<%s>\n%s\n</%s>"
% (container,dtd,container,xml,container))
xml=xml.encode("utf-8")
self.plugin.debug("validating %r",xml)
self.xml=xml
self.xml_line_offset=line_offset;
self.xml_char_offset=char_offset;
self.xml_line_char_offsets=[]
self.xml_errors=0
self.parser=libxml2.createDocParserCtxt(xml)
self.parser.lineNumbers(1)
self.parser.validate(1)
self.parser.setErrorHandler(self.xml_error,None)
if " HTML " in dtd:
self.parser.htmlParseDocument()
else:
self.parser.parseDocument()
ok=self.parser.isValid() and self.xml_errors==0
self.parser=None
self.plugin.debug("validation result: %r",ok)
return ok
def normalizeString(text, ignorewhitespace = 1):
"""Normalizes string to be used as key for gettext lookup.
Removes all unnecessary whitespace."""
if not ignorewhitespace:
return text
try:
# Lets add document DTD so entities are resolved
dtd = doc.intSubset()
tmp = dtd.serialize('utf-8')
tmp = tmp + '<norm>%s</norm>' % text
except:
tmp = '<norm>%s</norm>' % text
try:
ctxt = libxml2.createDocParserCtxt(tmp)
if expand_entities:
ctxt.replaceEntities(1)
ctxt.parseDocument()
tree = ctxt.doc()
newnode = tree.getRootElement()
except:
print >> sys.stderr, """Error while normalizing string as XML:\n"%s"\n""" % (text)
return text
normalizeNode(newnode)
result = ''
child = newnode.children
while child:
result += child.serialize('utf-8')
child = child.next
result = re.sub('^ ','', result)
result = re.sub(' $','', result)
return result
