def convert(self, orig, data, cache=None, filename=None, context=None, **kwargs): data = str(orig) doc = OOOdCommandTransform(context, filename, data, self.inputs[0]) pdf = doc.convertTo('pdf') if cache is not None: cache.setData(pdf) return cache else: stream = OOoDocumentDataStream() stream.setData(pdf) return stream
def convert(self, orig, data, cache=None, filename=None, context=None, **kwargs): data = str(orig) doc = OOOdCommandTransform(context, filename, data, self.inputs[0]) builder = OOoBuilder(doc) content = builder.extract('content.xml') if cache is not None: cache.setData(content) return cache else: stream = OOoDocumentDataStream() stream.setData(content) return stream
def convert(self, orig, data, cache=None, filename=None, context=None, **kwargs): # Try to recover broken HTML documents, specially regarding encoding used html_node = etree.XML(orig, parser=html_parser) includeMetaContentType(html_node) orig = html.tostring(html_node, encoding='utf-8', include_meta_content_type=True) doc = OOOdCommandTransform(context, filename, orig, self.inputs[0]) odt = doc.convertTo('odt') if cache is not None: cache.setData(odt) return cache else: stream = OOoDocumentDataStream() stream.setData(odt) return stream
def convert(self, orig, data, cache=None, filename=None, context=None, **kwargs): data = str(orig) doc = OOOdCommandTransform(context, filename, data, self.inputs[0]) msword = doc.convertTo('doc') if cache is not None: cache.setData(msword) return cache else: stream = OOoDocumentDataStream() stream.setData(msword) return stream