summaryrefslogtreecommitdiff
path: root/sleekxmpp/xmlstream/tostring
diff options
context:
space:
mode:
authorLance Stout <lancestout@gmail.com>2010-08-05 20:26:41 -0400
committerLance Stout <lancestout@gmail.com>2010-08-05 20:26:41 -0400
commite077204a16c76df4af90ba067e94c31af3d9e372 (patch)
tree96d725f14af0f26f19241984a3d85d4555cf1111 /sleekxmpp/xmlstream/tostring
parent58f77d898f82ab108fa17d562a32c68d3ea35306 (diff)
downloadslixmpp-e077204a16c76df4af90ba067e94c31af3d9e372.tar.gz
slixmpp-e077204a16c76df4af90ba067e94c31af3d9e372.tar.bz2
slixmpp-e077204a16c76df4af90ba067e94c31af3d9e372.tar.xz
slixmpp-e077204a16c76df4af90ba067e94c31af3d9e372.zip
Replaced the ToString class with a tostring function.
The sleekxmpp.xmlstream.tostring and sleekxmpp.xmlstream.tostring26 packages have been merged to sleekxmpp.xmlstream.tostring. The __init__.py file will import the appropriate tostring function depending on the Python version. The setup.py file has been updated with the package changes. ElementBase is now a direct descendent of object and does not subclass ToString. Stanza objects now return their XML contents for __repr__.
Diffstat (limited to 'sleekxmpp/xmlstream/tostring')
-rw-r--r--sleekxmpp/xmlstream/tostring/__init__.py13
-rw-r--r--sleekxmpp/xmlstream/tostring/tostring.py149
-rw-r--r--sleekxmpp/xmlstream/tostring/tostring26.py157
3 files changed, 195 insertions, 124 deletions
diff --git a/sleekxmpp/xmlstream/tostring/__init__.py b/sleekxmpp/xmlstream/tostring/__init__.py
index d93fe4ea..5852cba2 100644
--- a/sleekxmpp/xmlstream/tostring/__init__.py
+++ b/sleekxmpp/xmlstream/tostring/__init__.py
@@ -1,14 +1,19 @@
"""
+ SleekXMPP: The Sleek XMPP Library
+ Copyright (C) 2010 Nathanael C. Fritz
+ This file is part of SleekXMPP.
+ See the file LICENSE for copying permission.
"""
import sys
+# Import the correct tostring and xml_escape functions based on the Python
+# version in order to properly handle Unicode.
-# Import the correct ToString class based on the Python version.
if sys.version_info < (3, 0):
- from sleekxmpp.xmlstream.tostring.tostring26 import ToString
+ from sleekxmpp.xmlstream.tostring.tostring26 import tostring, xml_escape
else:
- from sleekxmpp.xmlstream.tostring.tostring import ToString
+ from sleekxmpp.xmlstream.tostring.tostring import tostring, xml_escape
-__all__ = ['ToString']
+__all__ = ['tostring', 'xml_escape']
diff --git a/sleekxmpp/xmlstream/tostring/tostring.py b/sleekxmpp/xmlstream/tostring/tostring.py
index 6603cbb8..62ff1181 100644
--- a/sleekxmpp/xmlstream/tostring/tostring.py
+++ b/sleekxmpp/xmlstream/tostring/tostring.py
@@ -1,60 +1,91 @@
+"""
+ SleekXMPP: The Sleek XMPP Library
+ Copyright (C) 2010 Nathanael C. Fritz
+ This file is part of SleekXMPP.
-class ToString(object):
- def __str__(self, xml=None, xmlns='', stringbuffer=''):
- if xml is None:
- xml = self.xml
- newoutput = [stringbuffer]
- #TODO respect ET mapped namespaces
- itag = xml.tag.split('}', 1)[-1]
- if '}' in xml.tag:
- ixmlns = xml.tag.split('}', 1)[0][1:]
- else:
- ixmlns = ''
- nsbuffer = ''
- if xmlns != ixmlns and ixmlns != '' and ixmlns != self.namespace:
- if self.stream is not None and ixmlns in self.stream.namespace_map:
- if self.stream.namespace_map[ixmlns] != '':
- itag = "%s:%s" % (self.stream.namespace_map[ixmlns], itag)
- else:
- nsbuffer = """ xmlns="%s\"""" % ixmlns
- if ixmlns not in ('', xmlns, self.namespace):
- nsbuffer = """ xmlns="%s\"""" % ixmlns
- newoutput.append("<%s" % itag)
- newoutput.append(nsbuffer)
- for attrib in xml.attrib:
- if '{' not in attrib:
- newoutput.append(""" %s="%s\"""" % (attrib, self.xmlesc(xml.attrib[attrib])))
- if len(xml) or xml.text or xml.tail:
- newoutput.append(">")
- if xml.text:
- newoutput.append(self.xmlesc(xml.text))
- if len(xml):
- for child in xml.getchildren():
- newoutput.append(self.__str__(child, ixmlns))
- newoutput.append("</%s>" % (itag, ))
- if xml.tail:
- newoutput.append(self.xmlesc(xml.tail))
- elif xml.text:
- newoutput.append(">%s</%s>" % (self.xmlesc(xml.text), itag))
- else:
- newoutput.append(" />")
- return ''.join(newoutput)
-
- def xmlesc(self, text):
- text = list(text)
- cc = 0
- matches = ('&', '<', '"', '>', "'")
- for c in text:
- if c in matches:
- if c == '&':
- text[cc] = '&amp;'
- elif c == '<':
- text[cc] = '&lt;'
- elif c == '>':
- text[cc] = '&gt;'
- elif c == "'":
- text[cc] = '&apos;'
- else:
- text[cc] = '&quot;'
- cc += 1
- return ''.join(text)
+ See the file LICENSE for copying permission.
+"""
+
+
+def tostring(xml=None, xmlns='', stanza_ns='', stream=None, outbuffer=''):
+ """
+ Serialize an XML object to a Unicode string.
+
+ Arguments:
+ xml -- The XML object to serialize. If the value is None,
+ then the XML object contained in this stanza
+ object will be used.
+ xmlns -- Optional namespace of an element wrapping the XML
+ object.
+ stanza_ns -- The namespace of the stanza object that contains
+ the XML object.
+ stream -- The XML stream that generated the XML object.
+ outbuffer -- Optional buffer for storing serializations during
+ recursive calls.
+ """
+ # Add previous results to the start of the output.
+ output = [outbuffer]
+
+ # Extract the element's tag name.
+ tag_name = xml.tag.split('}', 1)[-1]
+
+ # Extract the element's namespace if it is defined.
+ if '}' in xml.tag:
+ tag_xmlns = xml.tag.split('}', 1)[0][1:]
+ else:
+ tag_xmlns = ''
+
+ # Output the tag name and derived namespace of the element.
+ namespace = ''
+ if tag_xmlns not in ['', xmlns, stanza_ns]:
+ namespace = ' xmlns="%s"' % tag_xmlns
+ if stream and tag_xmlns in stream.namespace_map:
+ mapped_namespace = stream.namespace_map[tag_xmlns]
+ if mapped_namespace:
+ tag = "%s:%s" % (mapped_namespace, tag_name)
+ output.append("<%s" % tag_name)
+ output.append(namespace)
+
+ # Output escaped attribute values.
+ for attrib, value in xml.attrib.items():
+ if '{' not in attrib:
+ value = xml_escape(value)
+ output.append(' %s="%s"' % (attrib, value))
+
+ if len(xml) or xml.text:
+ # If there are additional child elements to serialize.
+ output.append(">")
+ if xml.text:
+ output.append(xml_escape(xml.text))
+ if len(xml):
+ for child in xml.getchildren():
+ output.append(tostring(child, tag_xmlns, stanza_ns, stream))
+ output.append("</%s>" % tag_name)
+ elif xml.text:
+ # If we only have text content.
+ output.append(">%s</%s>" % (xml_escape(xml.text), tag_name))
+ else:
+ # Empty element.
+ output.append(" />")
+ if xml.tail:
+ # If there is additional text after the element.
+ output.append(xml_escape(xml.tail))
+ return ''.join(output)
+
+
+def xml_escape(text):
+ """
+ Convert special characters in XML to escape sequences.
+
+ Arguments:
+ text -- The XML text to convert.
+ """
+ text = list(text)
+ escapes = {'&': '&amp;',
+ '<': '&lt;',
+ '>': '&gt;',
+ "'": '&apos;',
+ '"': '&quot;'}
+ for i, c in enumerate(text):
+ text[i] = escapes.get(c, c)
+ return ''.join(text)
diff --git a/sleekxmpp/xmlstream/tostring/tostring26.py b/sleekxmpp/xmlstream/tostring/tostring26.py
index 9711c300..9dba2717 100644
--- a/sleekxmpp/xmlstream/tostring/tostring26.py
+++ b/sleekxmpp/xmlstream/tostring/tostring26.py
@@ -1,65 +1,100 @@
+"""
+ SleekXMPP: The Sleek XMPP Library
+ Copyright (C) 2010 Nathanael C. Fritz
+ This file is part of SleekXMPP.
+
+ See the file LICENSE for copying permission.
+"""
+
+from __future__ import unicode_literals
import types
-class ToString(object):
- def __str__(self, xml=None, xmlns='', stringbuffer=''):
- if xml is None:
- xml = self.xml
- newoutput = [stringbuffer]
- #TODO respect ET mapped namespaces
- itag = xml.tag.split('}', 1)[-1]
- if '}' in xml.tag:
- ixmlns = xml.tag.split('}', 1)[0][1:]
- else:
- ixmlns = ''
- nsbuffer = ''
- if xmlns != ixmlns and ixmlns != u'' and ixmlns != self.namespace:
- if self.stream is not None and ixmlns in self.stream.namespace_map:
- if self.stream.namespace_map[ixmlns] != u'':
- itag = "%s:%s" % (self.stream.namespace_map[ixmlns], itag)
- else:
- nsbuffer = """ xmlns="%s\"""" % ixmlns
- if ixmlns not in ('', xmlns, self.namespace):
- nsbuffer = """ xmlns="%s\"""" % ixmlns
- newoutput.append("<%s" % itag)
- newoutput.append(nsbuffer)
- for attrib in xml.attrib:
- if '{' not in attrib:
- newoutput.append(""" %s="%s\"""" % (attrib, self.xmlesc(xml.attrib[attrib])))
- if len(xml) or xml.text or xml.tail:
- newoutput.append(u">")
- if xml.text:
- newoutput.append(self.xmlesc(xml.text))
- if len(xml):
- for child in xml.getchildren():
- newoutput.append(self.__str__(child, ixmlns))
- newoutput.append(u"</%s>" % (itag, ))
- if xml.tail:
- newoutput.append(self.xmlesc(xml.tail))
- elif xml.text:
- newoutput.append(">%s</%s>" % (self.xmlesc(xml.text), itag))
- else:
- newoutput.append(" />")
- return u''.join(newoutput)
- def xmlesc(self, text):
- if type(text) != types.UnicodeType:
- text = list(unicode(text, 'utf-8', 'ignore'))
- else:
- text = list(text)
+def tostring(xml=None, xmlns='', stanza_ns='', stream=None, outbuffer=''):
+ """
+ Serialize an XML object to a Unicode string.
+
+ Arguments:
+ xml -- The XML object to serialize. If the value is None,
+ then the XML object contained in this stanza
+ object will be used.
+ xmlns -- Optional namespace of an element wrapping the XML
+ object.
+ stanza_ns -- The namespace of the stanza object that contains
+ the XML object.
+ stream -- The XML stream that generated the XML object.
+ outbuffer -- Optional buffer for storing serializations during
+ recursive calls.
+ """
+ # Add previous results to the start of the output.
+ output = [outbuffer]
+
+ # Extract the element's tag name.
+ tag_name = xml.tag.split('}', 1)[-1]
+
+ # Extract the element's namespace if it is defined.
+ if '}' in xml.tag:
+ tag_xmlns = xml.tag.split('}', 1)[0][1:]
+ else:
+ tag_xmlns = u''
+
+ # Output the tag name and derived namespace of the element.
+ namespace = u''
+ if tag_xmlns not in ['', xmlns, stanza_ns]:
+ namespace = u' xmlns="%s"' % tag_xmlns
+ if stream and tag_xmlns in stream.namespace_map:
+ mapped_namespace = stream.namespace_map[tag_xmlns]
+ if mapped_namespace:
+ tag = u"%s:%s" % (mapped_namespace, tag_name)
+ output.append(u"<%s" % tag_name)
+ output.append(namespace)
+
+ # Output escaped attribute values.
+ for attrib, value in xml.attrib.items():
+ if '{' not in attrib:
+ value = xml_escape(value)
+ output.append(u' %s="%s"' % (attrib, value))
+
+ if len(xml) or xml.text:
+ # If there are additional child elements to serialize.
+ output.append(u">")
+ if xml.text:
+ output.append(xml_escape(xml.text))
+ if len(xml):
+ for child in xml.getchildren():
+ output.append(tostring(child, tag_xmlns, stanza_ns, stream))
+ output.append(u"</%s>" % tag_name)
+ if xml.tail:
+ # If there is additional text after the element.
+ output.append(xml_escape(xml.tail))
+ elif xml.text:
+ # If we only have text content.
+ output.append(u">%s</%s>" % (xml_escape(xml.text), tag_name))
+ else:
+ # Empty element.
+ output.append(u" />")
+ if xml.tail:
+ # If there is additional text after the element.
+ output.append(xml_escape(xml.tail))
+ return u''.join(output)
+
+
+def xml_escape(text):
+ """
+ Convert special characters in XML to escape sequences.
- cc = 0
- matches = (u'&', u'<', u'"', u'>', u"'")
- for c in text:
- if c in matches:
- if c == u'&':
- text[cc] = u'&amp;'
- elif c == u'<':
- text[cc] = u'&lt;'
- elif c == u'>':
- text[cc] = u'&gt;'
- elif c == u"'":
- text[cc] = u'&apos;'
- else:
- text[cc] = u'&quot;'
- cc += 1
- return ''.join(text)
+ Arguments:
+ text -- The XML text to convert.
+ """
+ if type(text) != types.UnicodeType:
+ text = list(unicode(text, 'utf-8', 'ignore'))
+ else:
+ text = list(text)
+ escapes = {u'&': u'&amp;',
+ u'<': u'&lt;',
+ u'>': u'&gt;',
+ u"'": u'&apos;',
+ u'"': u'&quot;'}
+ for i, c in enumerate(text):
+ text[i] = escapes.get(c, c)
+ return u''.join(text)