def process_document(self, session, doc):
xml = doc.get_raw(session)
self.inputSource.setByteStream(cStringIO.StringIO(xml))
ch = self.contentHandler
ch.reinit()
try:
self.parser.parse(self.inputSource)
except:
# Splat. Reset self and reraise
if self.keepError:
# Work out path
path = []
for l in ch.pathLines:
line = ch.currentText[l]
elemName = line[2:line.index('{')-1]
path.append("%s[@SAXID='%s']" % (elemName, l))
self.errorPath = '/'.join(path)
else:
ch.reinit()
raise
rec = SaxRecord(ch.currentText, xml, wordCount=ch.recordWordCount)
rec.elementHash = ch.elementHash
rec.byteCount = len(xml)
self._copyData(doc, rec)
ch.reinit()
return rec
def process_document(self, session, doc):
xml = doc.get_raw(session)
self.inputSource.setByteStream(cStringIO.StringIO(xml))
ch = self.contentHandler
ch.reinit()
try:
self.parser.parse(self.inputSource)
except:
# Splat. Reset self and reraise
if self.keepError:
# Work out path
path = []
for l in ch.pathLines:
line = ch.currentText[l]
elemName = line[2:line.index('{') - 1]
path.append("%s[@SAXID='%s']" % (elemName, l))
self.errorPath = '/'.join(path)
else:
ch.reinit()
raise
rec = SaxRecord(ch.currentText, xml, wordCount=ch.recordWordCount)
rec.elementHash = ch.elementHash
rec.byteCount = len(xml)
self._copyData(doc, rec)
ch.reinit()
return rec
def process_document(self, session, doc):
data = doc.get_raw(session)
data = unicode(data, 'utf-8')
sax = data.split(nonTextToken)
if sax[-1][0] == "9":
line = sax.pop()
elemHash = pickle.loads(str(line[2:]))
else:
elemHash = {}
rec = SaxRecord(sax)
rec.elementHash = elemHash
return rec
def process_document(self, session, doc):
data = doc.get_raw(session)
data = unicode(data, 'utf-8')
sax = data.split(nonTextToken)
if sax[-1][0] == "9":
line = sax.pop()
elemHash = pickle.loads(str(line[2:]))
else:
elemHash = {}
rec = SaxRecord(sax)
rec.elementHash = elemHash
return rec
