From b9764cc120c48576be1fe6cadb11813d12f91f4c Mon Sep 17 00:00:00 2001 From: Lance Stout Date: Thu, 4 Aug 2011 11:41:36 -0700 Subject: Clean up and unify tostring once and for all. Packaging for Python3 just got easier. --- sleekxmpp/xmlstream/tostring.py | 123 +++++++++++++++++++++++++++++ sleekxmpp/xmlstream/tostring/__init__.py | 19 ----- sleekxmpp/xmlstream/tostring/tostring.py | 114 -------------------------- sleekxmpp/xmlstream/tostring/tostring26.py | 120 ---------------------------- 4 files changed, 123 insertions(+), 253 deletions(-) create mode 100644 sleekxmpp/xmlstream/tostring.py delete mode 100644 sleekxmpp/xmlstream/tostring/__init__.py delete mode 100644 sleekxmpp/xmlstream/tostring/tostring.py delete mode 100644 sleekxmpp/xmlstream/tostring/tostring26.py (limited to 'sleekxmpp') diff --git a/sleekxmpp/xmlstream/tostring.py b/sleekxmpp/xmlstream/tostring.py new file mode 100644 index 00000000..f9674b15 --- /dev/null +++ b/sleekxmpp/xmlstream/tostring.py @@ -0,0 +1,123 @@ +""" + 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 + +if sys.version_info < (3, 0): + import types + + +def tostring(xml=None, xmlns='', stanza_ns='', stream=None, + outbuffer='', top_level=False): + """ + Serialize an XML object to a Unicode string. + + If namespaces are provided using xmlns or stanza_ns, then elements + that use those namespaces will not include the xmlns attribute in + the output. + + 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. + top_level -- Indicates that the element is the outermost + element. + """ + # 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 = '' + + default_ns = '' + stream_ns = '' + if stream: + default_ns = stream.default_ns + stream_ns = stream.stream_ns + + # Output the tag name and derived namespace of the element. + namespace = '' + if top_level and tag_xmlns not in ['', default_ns, stream_ns] or \ + tag_xmlns not in ['', xmlns, stanza_ns, stream_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_name = "%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(): + value = xml_escape(value) + if '}' not in attrib: + output.append(' %s="%s"' % (attrib, value)) + else: + attrib_ns = attrib.split('}')[0][1:] + attrib = attrib.split('}')[1] + if stream and attrib_ns in stream.namespace_map: + mapped_ns = stream.namespace_map[attrib_ns] + if mapped_ns: + output.append(' %s:%s="%s"' % (mapped_ns, + 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("" % tag_name) + elif xml.text: + # If we only have text content. + output.append(">%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. + """ + if sys.version_info < (3, 0): + if type(text) != types.UnicodeType: + text = unicode(text, 'utf-8', 'ignore') + + text = list(text) + escapes = {'&': '&', + '<': '<', + '>': '>', + "'": ''', + '"': '"'} + for i, c in enumerate(text): + text[i] = escapes.get(c, c) + return ''.join(text) diff --git a/sleekxmpp/xmlstream/tostring/__init__.py b/sleekxmpp/xmlstream/tostring/__init__.py deleted file mode 100644 index 5852cba2..00000000 --- a/sleekxmpp/xmlstream/tostring/__init__.py +++ /dev/null @@ -1,19 +0,0 @@ -""" - 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. - -if sys.version_info < (3, 0): - from sleekxmpp.xmlstream.tostring.tostring26 import tostring, xml_escape -else: - from sleekxmpp.xmlstream.tostring.tostring import tostring, xml_escape - -__all__ = ['tostring', 'xml_escape'] diff --git a/sleekxmpp/xmlstream/tostring/tostring.py b/sleekxmpp/xmlstream/tostring/tostring.py deleted file mode 100644 index a6bb6ebc..00000000 --- a/sleekxmpp/xmlstream/tostring/tostring.py +++ /dev/null @@ -1,114 +0,0 @@ -""" - SleekXMPP: The Sleek XMPP Library - Copyright (C) 2010 Nathanael C. Fritz - This file is part of SleekXMPP. - - See the file LICENSE for copying permission. -""" - - -def tostring(xml=None, xmlns='', stanza_ns='', stream=None, - outbuffer='', top_level=False): - """ - Serialize an XML object to a Unicode string. - - If namespaces are provided using xmlns or stanza_ns, then elements - that use those namespaces will not include the xmlns attribute in - the output. - - 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. - top_level -- Indicates that the element is the outermost - element. - """ - # 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 = '' - - default_ns = '' - stream_ns = '' - if stream: - default_ns = stream.default_ns - stream_ns = stream.stream_ns - - # Output the tag name and derived namespace of the element. - namespace = '' - if top_level and tag_xmlns not in ['', default_ns, stream_ns] or \ - tag_xmlns not in ['', xmlns, stanza_ns, stream_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_name = "%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(): - value = xml_escape(value) - if '}' not in attrib: - output.append(' %s="%s"' % (attrib, value)) - else: - attrib_ns = attrib.split('}')[0][1:] - attrib = attrib.split('}')[1] - if stream and attrib_ns in stream.namespace_map: - mapped_ns = stream.namespace_map[attrib_ns] - if mapped_ns: - output.append(' %s:%s="%s"' % (mapped_ns, - 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("" % tag_name) - elif xml.text: - # If we only have text content. - output.append(">%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 = {'&': '&', - '<': '<', - '>': '>', - "'": ''', - '"': '"'} - 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 deleted file mode 100644 index 3d1ca3d7..00000000 --- a/sleekxmpp/xmlstream/tostring/tostring26.py +++ /dev/null @@ -1,120 +0,0 @@ -""" - 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 - - -def tostring(xml=None, xmlns='', stanza_ns='', stream=None, - outbuffer='', top_level=False): - """ - Serialize an XML object to a Unicode string. - - If namespaces are provided using xmlns or stanza_ns, then elements - that use those namespaces will not include the xmlns attribute in - the output. - - 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. - top_level -- Indicates that the element is the outermost - element. - """ - # 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'' - - default_ns = '' - stream_ns = '' - if stream: - default_ns = stream.default_ns - stream_ns = stream.stream_ns - - # Output the tag name and derived namespace of the element. - namespace = u'' - if top_level and tag_xmlns not in ['', default_ns, stream_ns] or \ - tag_xmlns not in ['', xmlns, stanza_ns, stream_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_name = 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(): - value = xml_escape(value) - if '}' not in attrib: - output.append(' %s="%s"' % (attrib, value)) - else: - attrib_ns = attrib.split('}')[0][1:] - attrib = attrib.split('}')[1] - if stream and attrib_ns in stream.namespace_map: - mapped_ns = stream.namespace_map[attrib_ns] - if mapped_ns: - output.append(' %s:%s="%s"' % (mapped_ns, - 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"" % tag_name) - elif xml.text: - # If we only have text content. - output.append(u">%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. - - 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'&', - u'<': u'<', - u'>': u'>', - u"'": u''', - u'"': u'"'} - for i, c in enumerate(text): - text[i] = escapes.get(c, c) - return u''.join(text) -- cgit v1.2.3