def _prettywrite(self, file, node, encoding, namespaces, depth=0): # write XML to file tag = node.tag if tag is Comment: file.write("\r\n" + " " * depth) file.write("<!-- %s -->" % _escape_cdata(node.text, encoding)) elif tag is ProcessingInstruction: file.write("\r\n" + " " * depth) file.write("<?%s?>" % _escape_cdata(node.text, encoding)) else: items = node.items() xmlns_items = [] # new namespaces in this scope try: if isinstance(tag, QName) or tag[:1] == "{": tag, xmlns = myfixtag(tag, namespaces) if xmlns: xmlns_items.append(xmlns) except TypeError: _raise_serialization_error(tag) file.write("\r\n" + " " * depth) file.write("<" + _encode(tag, encoding)) if items or xmlns_items: items.sort() # lexical order for k, v in items: try: if isinstance(k, QName) or k[:1] == "{": k, xmlns = myfixtag(k, namespaces) if xmlns: xmlns_items.append(xmlns) except TypeError: _raise_serialization_error(k) try: if isinstance(v, QName): v, xmlns = myfixtag(v, namespaces) if xmlns: xmlns_items.append(xmlns) except TypeError: _raise_serialization_error(v) file.write(" %s=\"%s\"" % (_encode(k, encoding), _escape_attrib(v, encoding))) for k, v in xmlns_items: file.write(" %s=\"%s\"" % (_encode(k, encoding), _escape_attrib(v, encoding))) if node.text or len(node): file.write(">") if node.text: file.write(_escape_cdata(node.text, encoding)) for n in node: self._prettywrite(file, n, encoding, namespaces, depth=depth + 1) if not node.text or len(node): file.write("\r\n" + " " * depth) file.write("</" + _encode(tag, encoding) + ">") else: file.write(" />") for k, v in xmlns_items: del namespaces[v] if node.tail: file.write(_escape_cdata(node.tail, encoding))
def Etree_pretty__write(self, file, node, encoding, namespaces, level=0, identator=" "): tag = node.tag if tag is Comment: file.write(level * identator + "<!-- %s -->" % _escape_cdata(node.text, encoding)) elif tag is ProcessingInstruction: file.write("<?%s?>" % _escape_cdata(node.text, encoding)) else: items = node.items() xmlns_items = [] # new namespaces in this scope try: if isinstance(tag, QName) or tag[:1] == "{": tag, xmlns = fixtag(tag, namespaces) if xmlns: xmlns_items.append(xmlns) except TypeError: raise #_raise_serialization_error(tag) file.write("\n" + level * identator + "<" + _encode(tag, encoding)) if items or xmlns_items: items.sort() # lexical order for k, v in items: try: if isinstance(k, QName) or k[:1] == "{": k, xmlns = fixtag(k, namespaces) if xmlns: xmlns_items.append(xmlns) except TypeError: raise #_raise_serialization_error(k) try: if isinstance(v, QName): v, xmlns = fixtag(v, namespaces) if xmlns: xmlns_items.append(xmlns) except TypeError: raise #_raise_serialization_error(v) file.write(u" %s=\"%s\"" % (_encode(k, encoding), _escape_attrib(v, encoding))) for k, v in xmlns_items: file.write(u" %s=\"%s\"" % (_encode(k, encoding), _escape_attrib(v, encoding))) if node.text or len(node): file.write(">") if node.text: file.write(_escape_cdata(node.text.replace("\n", (level + 1) * identator + "\n"), encoding)) for n in node: self._write(file, n, encoding, namespaces, level + 1, identator) if node.text and len(node.text) < 125: file.write("</" + _encode(tag, encoding) + ">") else: file.write("\n" + level * identator + "</" + _encode(tag, encoding) + ">") else: file.write(" />") for k, v in xmlns_items: del namespaces[v] if node.tail: file.write(_escape_cdata(node.tail.replace("\n", level * identator + "\n"), encoding))
def Etree_pretty__write(self, file, node, encoding, namespaces, level=0, identator=" "): tag = node.tag if tag is Comment: file.write(level * identator + "<!-- %s -->" % _escape_cdata(node.text, encoding)) elif tag is ProcessingInstruction: file.write("<?%s?>" % _escape_cdata(node.text, encoding)) else: items = node.items() xmlns_items = [] # new namespaces in this scope try: if isinstance(tag, QName) or tag[:1] == "{": tag, xmlns = fixtag(tag, namespaces) if xmlns: xmlns_items.append(xmlns) except TypeError: raise #_raise_serialization_error(tag) file.write("\n" + level * identator + "<" + _encode(tag, encoding)) if items or xmlns_items: items.sort() # lexical order for k, v in items: try: if isinstance(k, QName) or k[:1] == "{": k, xmlns = fixtag(k, namespaces) if xmlns: xmlns_items.append(xmlns) except TypeError: raise #_raise_serialization_error(k) try: if isinstance(v, QName): v, xmlns = fixtag(v, namespaces) if xmlns: xmlns_items.append(xmlns) except TypeError: raise #_raise_serialization_error(v) file.write(u" %s=\"%s\"" % (_encode(k, encoding), _escape_attrib(v, encoding))) for k, v in xmlns_items: file.write(u" %s=\"%s\"" % (_encode(k, encoding), _escape_attrib(v, encoding))) if node.text or len(node): file.write(">") if node.text: file.write(_escape_cdata(node.text, encoding)) for n in node: self._write(file, n, encoding, namespaces, level + 1, identator) if node.text and len(node.text) < 125: file.write("</" + _encode(tag, encoding) + ">") else: file.write("\n" + level * identator + "</" + _encode(tag, encoding) + ">") else: file.write(" />") for k, v in xmlns_items: del namespaces[v] if node.tail: file.write(_escape_cdata(node.tail.replace("\n", (level * identator )+ "\n"), encoding))
def _write(self, file, node, encoding, namespaces): # write XML to file tag = node.tag if tag is Comment: file.write("\n<!-- %s -->" % _escape_cdata(node.text, encoding)) elif tag is ProcessingInstruction: file.write("\n<?%s?>" % _escape_cdata(node.text, encoding)) else: items = node.items() xmlns_items = [] # new namespaces in this scope try: if isinstance(tag, QName) or tag[:1] == "{": tag, xmlns = fixtag(tag, namespaces) if xmlns: xmlns_items.append(xmlns) except TypeError: _raise_serialization_error(tag) file.write("\n<" + _encode(tag, encoding)) if items or xmlns_items: items.sort() # lexical order for k, v in items: try: if isinstance(k, QName) or k[:1] == "{": k, xmlns = fixtag(k, namespaces) if xmlns: xmlns_items.append(xmlns) except TypeError: _raise_serialization_error(k) try: if isinstance(v, QName): v, xmlns = fixtag(v, namespaces) if xmlns: xmlns_items.append(xmlns) except TypeError: _raise_serialization_error(v) file.write( " %s=\"%s\"" % (_encode(k, encoding), _escape_attrib(v, encoding))) for k, v in xmlns_items: file.write( " %s=\"%s\"" % (_encode(k, encoding), _escape_attrib(v, encoding))) if node.text or len(node): file.write(">") if node.text: file.write(_escape_cdata(node.text, encoding)) for n in node: self._write(file, n, encoding, namespaces) file.write("</" + _encode(tag, encoding) + ">") else: file.write(" />") for k, v in xmlns_items: del namespaces[v] if node.tail: file.write(_escape_cdata(node.tail, encoding))
def _print_node(self, node, encoding): tree_string = "" tag = node.tag if tag is Comment: tree_string += "<!-- %s -->" % _escape_cdata(node.text, encoding) elif tag is ProcessingInstruction: tree_string += "<?%s?>" % _escape_cdata(node.text, encoding) else: items = node.items() xmlns_items = [] # new namespaces in this scope try: if isinstance(tag, QName) or tag[:1] == "{": tag, xmlns = fixtag(tag, namespaces) if xmlns: xmlns_items.append(xmlns) except TypeError: _raise_serialization_error(tag) tree_string += "<" + _encode(tag, encoding) if items or xmlns_items: items.sort() # lexical order for k, v in items: try: if isinstance(k, QName) or k[:1] == "{": k, xmlns = fixtag(k, namespaces) if xmlns: xmlns_items.append(xmlns) except TypeError: _raise_serialization_error(k) try: if isinstance(v, QName): v, xmlns = fixtag(v, namespaces) if xmlns: xmlns_items.append(xmlns) except TypeError: _raise_serialization_error(v) tree_string += " %s=\"%s\"" % (_encode(k, encoding), _escape_attrib(v, encoding)) for k, v in xmlns_items: tree_string += " %s=\"%s\"" % (_encode(k, encoding), _escape_attrib(v, encoding)) tree_string += ">" if node.text: tree_string += _escape_cdata(node.text, encoding).replace('"', '"') for n in node: tree_string += self._print_node(n, encoding) tree_string += "</" + _encode(tag, encoding) + ">" for k, v in xmlns_items: del namespaces[v] if node.tail: tree_string += _escape_cdata(node.tail, encoding) return tree_string
def _escape_cdata(text, encoding=None, replace=string.replace): try: if encoding: text = _encode(text, encoding) text = replace(text, "&", "&") text = replace(text, "<", "<") text = replace(text, ">", ">") return text except (TypeError, AttributeError): _raise_serialization_error(text)
def _escape_attrib(attr_val, encoding=None, replace=string.replace): # escape attribute value text = str(attr_val) try: if encoding: text = _encode(text, encoding) text = replace(text, "&", "&") #text = replace(text, "'", "'") # FIXME: overkill text = replace(text, "\"", """) text = replace(text, "<", "<") text = replace(text, ">", ">") return text except (TypeError, AttributeError): _raise_serialization_error(text)
def write( self, file_or_filename, # keyword arguments encoding=None, xml_declaration=None, default_namespace=None, method=None): if not method: method = "xml" elif method not in _serialize: # FIXME: raise an ImportError for c14n if ElementC14N is missing? raise ValueError("unknown method %r" % method) if hasattr(file_or_filename, "write"): file = file_or_filename else: file = open(file_or_filename, "wb") write = file.write if not encoding: if method == "c14n": encoding = "utf-8" else: encoding = "us-ascii" elif xml_declaration or (xml_declaration is None and encoding not in ("utf-8", "us-ascii")): if method == "xml": write("<?xml version='1.0' encoding='%s'?>\n" % encoding) # !!! Print ugly comments prior to root node !!! for ugly_comment in self._comments_prior_root: write("<!--%s-->\n" % _encode(ugly_comment.text, encoding)) # !!! end of ugly part if method == "text": _serialize[method](write, self._root, encoding) else: qnames, namespaces = _namespaces(self._root, encoding, default_namespace) serialize = _serialize[method] serialize(write, self._root, encoding, qnames, namespaces) if file_or_filename is not file: file.close()
def _write(self, file, node, encoding, namespaces, sortflag="default", sortcmp=None): # don't break existing code that relies on _write()s parameters, if any # write XML to file tag = node.tag if tag is Comment: file.write("<!-- %s -->" % _escape_cdata(node.text, encoding)) elif tag is ProcessingInstruction: file.write("<?%s?>" % _escape_cdata(node.text, encoding)) else: items = node.items() xmlns_items = [] # new namespaces in this scope try: if isinstance(tag, QName) or tag[:1] == "{": tag, xmlns = fixtag(tag, namespaces) if xmlns: xmlns_items.append(xmlns) except TypeError: _raise_serialization_error(tag) file.write("<" + _encode(tag, encoding)) if items or xmlns_items: ##NEW if sortflag!="default": if ":" not in sortflag: sortflag = ":"+sortflag sortitems = sortflag.split(";") try: sortitems = [[tagdef.split(":")[0], tagdef.split(":")[1].split(",")] for tagdef in sortitems] temp = [] for tagdef in sortitems: if tagdef[0] in node.tag: for sortitem in tagdef[1]: temp.extend([i for i in items if sortitem in i]) # add what matches pattern break # then sort and add what's left items.sort(cmp=sortcmp) temp.extend([i for i in items if i not in temp]) items = temp except IndexError: sys.stderr.write("sortflag not formatted correctly, order won't be applied") try: items.sort(cmp=sortcmp) except: sys.stderr.write("sortcmp not a valid comparator, sorting alphabetically instead") items.sort() else: try: items.sort(cmp=sortcmp) except: sys.stderr.write("sortcmp not a valid comparator, sorting alphabetically instead") items.sort() ### for k, v in items: try: if isinstance(k, QName) or k[:1] == "{": k, xmlns = fixtag(k, namespaces) if xmlns: xmlns_items.append(xmlns) except TypeError: _raise_serialization_error(k) try: if isinstance(v, QName): v, xmlns = fixtag(v, namespaces) if xmlns: xmlns_items.append(xmlns) except TypeError: _raise_serialization_error(v) file.write(" %s=\"%s\"" % (_encode(k, encoding), _escape_attrib(v, encoding))) for k, v in xmlns_items: file.write(" %s=\"%s\"" % (_encode(k, encoding), _escape_attrib(v, encoding))) if node.text or len(node): file.write(">") if node.text: file.write(_escape_cdata(node.text, encoding)) for n in node: self._write(file, n, encoding, namespaces, sortflag, sortcmp) file.write("</" + _encode(tag, encoding) + ">") else: file.write(" />") for k, v in xmlns_items: del namespaces[v] if node.tail: file.write(_escape_cdata(node.tail, encoding))