Add a Markup plugin.markup

4 files changed, 419 insertions, 0 deletions

diff --git a/examples/markup.py b/examples/markup.py
new file mode 100755
index 00000000..a72cbdb8
--- /dev/null
+++ b/examples/markup.py
@@ -0,0 +1,120 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+"""
+    Slixmpp: The Slick XMPP Library
+    Copyright (C) 2010  Nathanael C. Fritz
+    This file is part of Slixmpp.
+
+    See the file LICENSE for copying permission.
+"""
+
+import logging
+from getpass import getpass
+from argparse import ArgumentParser
+
+import slixmpp
+from slixmpp.plugins.xep_0394 import stanza as markup_stanza
+
+
+class EchoBot(slixmpp.ClientXMPP):
+
+    """
+    A simple Slixmpp bot that will echo messages it
+    receives, along with a short thank you message.
+    """
+
+    def __init__(self, jid, password):
+        slixmpp.ClientXMPP.__init__(self, jid, password)
+
+        # The session_start event will be triggered when
+        # the bot establishes its connection with the server
+        # and the XML streams are ready for use. We want to
+        # listen for this event so that we we can initialize
+        # our roster.
+        self.add_event_handler("session_start", self.start)
+
+        # The message event is triggered whenever a message
+        # stanza is received. Be aware that that includes
+        # MUC messages and error messages.
+        self.add_event_handler("message", self.message)
+
+    def start(self, event):
+        """
+        Process the session_start event.
+
+        Typical actions for the session_start event are
+        requesting the roster and broadcasting an initial
+        presence stanza.
+
+        Arguments:
+            event -- An empty dictionary. The session_start
+                     event does not provide any additional
+                     data.
+        """
+        self.send_presence()
+        self.get_roster()
+
+    def message(self, msg):
+        """
+        Process incoming message stanzas. Be aware that this also
+        includes MUC messages and error messages. It is usually
+        a good idea to check the messages's type before processing
+        or sending replies.
+
+        Arguments:
+            msg -- The received message stanza. See the documentation
+                   for stanza objects and the Message stanza to see
+                   how it may be used.
+        """
+        body = msg['body']
+        new_body = self['xep_0394'].to_plain_text(body, msg['markup'])
+        xhtml = self['xep_0394'].to_xhtml_im(body, msg['markup'])
+        print('Plain text:', new_body)
+        print('XHTML-IM:', xhtml['body'])
+        message = msg.reply()
+        message['body'] = new_body
+        message['html']['body'] = xhtml['body']
+        self.send(message)
+
+
+if __name__ == '__main__':
+    # Setup the command line arguments.
+    parser = ArgumentParser(description=EchoBot.__doc__)
+
+    # Output verbosity options.
+    parser.add_argument("-q", "--quiet", help="set logging to ERROR",
+                        action="store_const", dest="loglevel",
+                        const=logging.ERROR, default=logging.INFO)
+    parser.add_argument("-d", "--debug", help="set logging to DEBUG",
+                        action="store_const", dest="loglevel",
+                        const=logging.DEBUG, default=logging.INFO)
+
+    # JID and password options.
+    parser.add_argument("-j", "--jid", dest="jid",
+                        help="JID to use")
+    parser.add_argument("-p", "--password", dest="password",
+                        help="password to use")
+
+    args = parser.parse_args()
+
+    # Setup logging.
+    logging.basicConfig(level=args.loglevel,
+                        format='%(levelname)-8s %(message)s')
+
+    if args.jid is None:
+        args.jid = input("Username: ")
+    if args.password is None:
+        args.password = getpass("Password: ")
+
+    # Setup the EchoBot and register plugins. Note that while plugins may
+    # have interdependencies, the order in which you register them does
+    # not matter.
+    xmpp = EchoBot(args.jid, args.password)
+    xmpp.register_plugin('xep_0030') # Service Discovery
+    xmpp.register_plugin('xep_0199') # XMPP Ping
+    xmpp.register_plugin('xep_0394') # Message Markup
+
+    # Connect to the XMPP server and start processing XMPP stanzas.
+    xmpp.connect()
+    xmpp.process()
diff --git a/slixmpp/plugins/xep_0394/__init__.py b/slixmpp/plugins/xep_0394/__init__.py
new file mode 100644
index 00000000..f3a9b635
--- /dev/null
+++ b/slixmpp/plugins/xep_0394/__init__.py
@@ -0,0 +1,15 @@
+"""
+    Slixmpp: The Slick XMPP Library
+    Copyright (C) 2017 Emmanuel Gil Peyrot <linkmauve@linkmauve.fr>
+    This file is part of Slixmpp.
+
+    See the file LICENSE for copying permission.
+"""
+
+from slixmpp.plugins.base import register_plugin
+
+from slixmpp.plugins.xep_0394.stanza import Markup, Span, BlockCode, List, Li, BlockQuote
+from slixmpp.plugins.xep_0394.markup import XEP_0394
+
+
+register_plugin(XEP_0394)
diff --git a/slixmpp/plugins/xep_0394/markup.py b/slixmpp/plugins/xep_0394/markup.py
new file mode 100644
index 00000000..d3ec69e6
--- /dev/null
+++ b/slixmpp/plugins/xep_0394/markup.py
@@ -0,0 +1,161 @@
+"""
+    Slixmpp: The Slick XMPP Library
+    Copyright (C) 2017 Emmanuel Gil Peyrot <linkmauve@linkmauve.fr>
+    This file is part of Slixmpp.
+
+    See the file LICENSE for copying permission.
+"""
+
+
+from slixmpp.stanza import Message
+from slixmpp.plugins import BasePlugin
+from slixmpp.xmlstream import register_stanza_plugin, ET, tostring
+from slixmpp.plugins.xep_0394 import stanza, Markup, Span, BlockCode, List, Li, BlockQuote
+from slixmpp.plugins.xep_0071 import XHTML_IM
+
+
+class Start:
+    def __init__(self, elem):
+        self.elem = elem
+
+    def __repr__(self):
+        return 'Start(%s)' % self.elem
+
+
+class End:
+    def __init__(self, elem):
+        self.elem = elem
+
+    def __repr__(self):
+        return 'End(%s)' % self.elem
+
+
+class XEP_0394(BasePlugin):
+
+    name = 'xep_0394'
+    description = 'XEP-0394: Message Markup'
+    dependencies = {'xep_0030', 'xep_0071'}
+    stanza = stanza
+
+    def plugin_init(self):
+        register_stanza_plugin(Message, Markup)
+
+    def session_bind(self, jid):
+        self.xmpp['xep_0030'].add_feature(feature=Markup.namespace)
+
+    def plugin_end(self):
+        self.xmpp['xep_0030'].del_feature(feature=Markup.namespace)
+
+    @staticmethod
+    def _split_first_level(body, markup_elem):
+        split_points = []
+        elements = {}
+        for markup in markup_elem['substanzas']:
+            start = markup['start']
+            end = markup['end']
+            split_points.append(start)
+            split_points.append(end)
+            elements.setdefault(start, []).append(Start(markup))
+            elements.setdefault(end, []).append(End(markup))
+            if isinstance(markup, List):
+                lis = markup['lis']
+                for i, li in enumerate(lis):
+                    start = li['start']
+                    split_points.append(start)
+                    li_end = lis[i + 1]['start'] if i < len(lis) - 1 else end
+                    elements.setdefault(li_end, []).append(End(li))
+                    elements.setdefault(start, []).append(Start(li))
+        split_points = set(split_points)
+        new_body = [[]]
+        for i, letter in enumerate(body + '\x00'):
+            if i in split_points:
+                body_elements = []
+                for elem in elements[i]:
+                    body_elements.append(elem)
+                new_body.append(body_elements)
+                new_body.append([])
+            new_body[-1].append(letter)
+        new_body[-1] = new_body[-1][:-1]
+        final = []
+        for chunk in new_body:
+            if not chunk:
+                continue
+            final.append(''.join(chunk) if isinstance(chunk[0], str) else chunk)
+        return final
+
+    def to_plain_text(self, body, markup_elem):
+        chunks = self._split_first_level(body, markup_elem)
+        final = []
+        for chunk in chunks:
+            if isinstance(chunk, str):
+                final.append(chunk)
+        return ''.join(final)
+
+    def to_xhtml_im(self, body, markup_elem):
+        chunks = self._split_first_level(body, markup_elem)
+        final = []
+        stack = []
+        for chunk in chunks:
+            if isinstance(chunk, str):
+                chunk = (chunk.replace("&", '&amp;')
+                              .replace('<', '&lt;')
+                              .replace('>', '&gt;')
+                              .replace('"', '&quot;')
+                              .replace("'", '&apos;')
+                              .replace('\n', '<br/>'))
+                final.append(chunk)
+                continue
+            num_end = 0
+            for elem in chunk:
+                if isinstance(elem, End):
+                    num_end += 1
+
+            for i in range(num_end):
+                stack_top = stack.pop()
+                for elem in chunk:
+                    if not isinstance(elem, End):
+                        continue
+                    elem = elem.elem
+                    if elem is stack_top:
+                        if isinstance(elem, Span):
+                            final.append('</span>')
+                        elif isinstance(elem, BlockCode):
+                            final.append('</code></pre>')
+                        elif isinstance(elem, List):
+                            final.append('</ul>')
+                        elif isinstance(elem, Li):
+                            final.append('</li>')
+                        elif isinstance(elem, BlockQuote):
+                            final.append('</blockquote>')
+                        break
+                else:
+                    assert False
+            for elem in chunk:
+                if not isinstance(elem, Start):
+                    continue
+                elem = elem.elem
+                stack.append(elem)
+                if isinstance(elem, Span):
+                    style = []
+                    for type_ in elem['types']:
+                        if type_ == 'emphasis':
+                            style.append('font-style: italic;')
+                        if type_ == 'code':
+                            style.append('font-family: monospace;')
+                        if type_ == 'deleted':
+                            style.append('text-decoration: line-through;')
+                    final.append("<span style='%s'>" % ' '.join(style))
+                elif isinstance(elem, BlockCode):
+                    final.append('<pre><code>')
+                elif isinstance(elem, List):
+                    final.append('<ul>')
+                elif isinstance(elem, Li):
+                    final.append('<li>')
+                elif isinstance(elem, BlockQuote):
+                    final.append('<blockquote>')
+        p = "<p xmlns='http://www.w3.org/1999/xhtml'>%s</p>" % ''.join(final)
+        p2 = ET.fromstring(p)
+        print('coucou', p, tostring(p2))
+        xhtml_im = XHTML_IM()
+        xhtml_im['body'] = p2
+        return xhtml_im
diff --git a/slixmpp/plugins/xep_0394/stanza.py b/slixmpp/plugins/xep_0394/stanza.py
new file mode 100644
index 00000000..f15a9ba1
--- /dev/null
+++ b/slixmpp/plugins/xep_0394/stanza.py
@@ -0,0 +1,123 @@
+"""
+    Slixmpp: The Slick XMPP Library
+    Copyright (C) 2017 Emmanuel Gil Peyrot <linkmauve@linkmauve.fr>
+    This file is part of Slixmpp.
+
+    See the file LICENSE for copying permission.
+"""
+
+from slixmpp.xmlstream import ElementBase, register_stanza_plugin, ET
+
+
+class Markup(ElementBase):
+    namespace = 'urn:xmpp:markup:0'
+    name = 'markup'
+    plugin_attrib = 'markup'
+
+
+class _FirstLevel(ElementBase):
+    namespace = 'urn:xmpp:markup:0'
+    interfaces = {'start', 'end'}
+
+    def get_start(self):
+        return int(self._get_attr('start'))
+
+    def set_start(self, value):
+        self._set_attr('start', '%d' % value)
+
+    def get_end(self):
+        return int(self._get_attr('end'))
+
+    def set_end(self, value):
+        self._set_attr('end', '%d' % value)
+
+class Span(_FirstLevel):
+    name = 'span'
+    plugin_attrib = 'span'
+    plugin_multi_attrib = 'spans'
+    interfaces = {'start', 'end', 'types'}
+
+    def get_types(self):
+        types = []
+        if self.xml.find('{urn:xmpp:markup:0}emphasis') is not None:
+            types.append('emphasis')
+        if self.xml.find('{urn:xmpp:markup:0}code') is not None:
+            types.append('code')
+        if self.xml.find('{urn:xmpp:markup:0}deleted') is not None:
+            types.append('deleted')
+        return types
+
+    def set_types(self, value):
+        del self['types']
+        for type_ in value:
+            if type_ == 'emphasis':
+                self.xml.append(ET.Element('{urn:xmpp:markup:0}emphasis'))
+            elif type_ == 'code':
+                self.xml.append(ET.Element('{urn:xmpp:markup:0}code'))
+            elif type_ == 'deleted':
+                self.xml.append(ET.Element('{urn:xmpp:markup:0}deleted'))
+
+    def det_types(self):
+        for child in self.xml:
+            self.xml.remove(child)
+
+
+class _SpanType(ElementBase):
+    namespace = 'urn:xmpp:markup:0'
+
+
+class EmphasisType(_SpanType):
+    name = 'emphasis'
+    plugin_attrib = 'emphasis'
+
+
+class CodeType(_SpanType):
+    name = 'code'
+    plugin_attrib = 'code'
+
+
+class DeletedType(_SpanType):
+    name = 'deleted'
+    plugin_attrib = 'deleted'
+
+
+class BlockCode(_FirstLevel):
+    name = 'bcode'
+    plugin_attrib = 'bcode'
+    plugin_multi_attrib = 'bcodes'
+
+
+class List(_FirstLevel):
+    name = 'list'
+    plugin_attrib = 'list'
+    plugin_multi_attrib = 'lists'
+    interfaces = {'start', 'end', 'li'}
+
+
+class Li(ElementBase):
+    namespace = 'urn:xmpp:markup:0'
+    name = 'li'
+    plugin_attrib = 'li'
+    plugin_multi_attrib = 'lis'
+    interfaces = {'start'}
+
+    def get_start(self):
+        return int(self._get_attr('start'))
+
+    def set_start(self, value):
+        self._set_attr('start', '%d' % value)
+
+
+class BlockQuote(_FirstLevel):
+    name = 'bquote'
+    plugin_attrib = 'bquote'
+    plugin_multi_attrib = 'bquotes'
+
+register_stanza_plugin(Markup, Span, iterable=True)
+register_stanza_plugin(Markup, BlockCode, iterable=True)
+register_stanza_plugin(Markup, List, iterable=True)
+register_stanza_plugin(Markup, BlockQuote, iterable=True)
+register_stanza_plugin(Span, EmphasisType)
+register_stanza_plugin(Span, CodeType)
+register_stanza_plugin(Span, DeletedType)
+register_stanza_plugin(List, Li, iterable=True)