tools(common/uri): XMPP uri parsing module, first draft

src/tools/common/uri.py

@@ -0,0 +1,71 @@
+#!/usr/bin/env python2
+# -*- coding: utf-8 -*-
+
+# SAT: a jabber client
+# Copyright (C) 2009-2016 Jérôme Poisson (goffi@goffi.org)
+
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+""" XMPP uri parsing tools """
+
+import urlparse
+import urllib
+
+# FIXME: basic implementation, need to follow RFC 5122
+
+def parseXMPPUri(uri):
+    """Parse an XMPP uri and return a dict with various information
+
+    @param uri(unicode): uri to parse
+    @return dict(unicode, unicode): data depending of the URI where key can be:
+        type: one of ("pubsub", TODO)
+        sub_type: can be:
+            - microblog
+            only used for pubsub for now
+        path: XMPP path (jid of the service or entity)
+        node: node used
+        id: id of the element (item for pubsub)
+    @raise ValueError: the scheme is not xmpp
+    """
+    uri_split = urlparse.urlsplit(uri.encode('utf-8'))
+    if uri_split.scheme != 'xmpp':
+        raise ValueError(u'this is not a XMPP URI')
+
+    data = {u'path': urllib.unquote(uri_split.path).decode('utf-8')}
+
+    query_end = uri_split.query.find(';')
+    query_type = uri_split.query[:query_end]
+    if query_end == -1 or '=' in query_type:
+        raise ValueError('no query type, invalid XMPP URI')
+
+    pairs = urlparse.parse_qs(uri_split.geturl())
+    for k, v in pairs.items():
+        if len(v) != 1:
+            raise NotImplementedError(u"multiple values not managed")
+        if k in ('path', 'type', 'sub_type'):
+            raise NotImplementedError(u"reserved key used in URI, this is not supported")
+        data[k.decode('utf-8')] = urllib.unquote(v[0]).decode('utf-8')
+
+    if query_type:
+        data[u'type'] = query_type.decode('utf-8')
+    elif u'node' in data:
+        data[u'type'] = u'pubsub'
+    else:
+        data[u'type'] = ''
+
+    if u'node' in data:
+        if data[u'node'].startswith(u'urn:xmpp:microblog:'):
+            data[u'sub_type'] = 'microblog'
+
+    return data