summaryrefslogtreecommitdiff
path: root/sleekxmpp/util
diff options
context:
space:
mode:
authorLance Stout <lancestout@gmail.com>2012-07-24 20:01:18 -0700
committerLance Stout <lancestout@gmail.com>2012-07-24 20:01:18 -0700
commitc42f1ad4c79863261977a9c5ea3b33be0b51b946 (patch)
tree8eee86ddb082f51dea0866f16146bcd1f4f13c1f /sleekxmpp/util
parenta3ec1af2053bc0be4864ae290e6e5fc39f3fd5fe (diff)
parent9d8de7fc15afc39a666d2ac16b62a068dfc55112 (diff)
downloadslixmpp-c42f1ad4c79863261977a9c5ea3b33be0b51b946.tar.gz
slixmpp-c42f1ad4c79863261977a9c5ea3b33be0b51b946.tar.bz2
slixmpp-c42f1ad4c79863261977a9c5ea3b33be0b51b946.tar.xz
slixmpp-c42f1ad4c79863261977a9c5ea3b33be0b51b946.zip
Merge branch 'master' into develop
Diffstat (limited to 'sleekxmpp/util')
-rw-r--r--sleekxmpp/util/__init__.py23
-rw-r--r--sleekxmpp/util/stringprep_profiles.py119
2 files changed, 142 insertions, 0 deletions
diff --git a/sleekxmpp/util/__init__.py b/sleekxmpp/util/__init__.py
new file mode 100644
index 00000000..86a87222
--- /dev/null
+++ b/sleekxmpp/util/__init__.py
@@ -0,0 +1,23 @@
+# -*- coding: utf-8 -*-
+"""
+ sleekxmpp.util
+ ~~~~~~~~~~~~~~
+
+ Part of SleekXMPP: The Sleek XMPP Library
+
+ :copyright: (c) 2012 Nathanael C. Fritz, Lance J.T. Stout
+ :license: MIT, see LICENSE for more details
+"""
+
+
+# =====================================================================
+# Standardize import of Queue class:
+
+try:
+ import queue
+except ImportError:
+ import Queue as queue
+
+
+Queue = queue.Queue
+QueueEmpty = queue.Empty
diff --git a/sleekxmpp/util/stringprep_profiles.py b/sleekxmpp/util/stringprep_profiles.py
new file mode 100644
index 00000000..6844c9ac
--- /dev/null
+++ b/sleekxmpp/util/stringprep_profiles.py
@@ -0,0 +1,119 @@
+from __future__ import unicode_literals
+
+import sys
+import stringprep
+import unicodedata
+
+
+class StringPrepError(UnicodeError):
+ pass
+
+
+def to_unicode(data):
+ if sys.version_info < (3, 0):
+ return unicode(data)
+ else:
+ return str(data)
+
+
+def b1_mapping(char):
+ return '' if stringprep.in_table_c12(char) else None
+
+
+def c12_mapping(char):
+ return ' ' if stringprep.in_table_c12(char) else None
+
+
+def map_input(data, tables=None):
+ """
+ Each character in the input stream MUST be checked against
+ a mapping table.
+ """
+ result = []
+ for char in data:
+ replacement = None
+
+ for mapping in tables:
+ replacement = mapping(char)
+ if replacement is not None:
+ break
+
+ if replacement is None:
+ replacement = char
+ result.append(replacement)
+ return ''.join(result)
+
+
+def normalize(data, nfkc=True):
+ """
+ A profile can specify one of two options for Unicode normalization:
+ - no normalization
+ - Unicode normalization with form KC
+ """
+ if nfkc:
+ data = unicodedata.normalize('NFKC', data)
+ return data
+
+
+def prohibit_output(data, tables=None):
+ """
+ Before the text can be emitted, it MUST be checked for prohibited
+ code points.
+ """
+ for char in data:
+ for check in tables:
+ if check(char):
+ raise StringPrepError("Prohibited code point: %s" % char)
+
+
+def check_bidi(data):
+ """
+ 1) The characters in section 5.8 MUST be prohibited.
+
+ 2) If a string contains any RandALCat character, the string MUST NOT
+ contain any LCat character.
+
+ 3) If a string contains any RandALCat character, a RandALCat
+ character MUST be the first character of the string, and a
+ RandALCat character MUST be the last character of the string.
+ """
+ if not data:
+ return data
+
+ has_lcat = False
+ has_randal = False
+
+ for c in data:
+ if stringprep.in_table_c8(c):
+ raise StringPrepError("BIDI violation: seciton 6 (1)")
+ if stringprep.in_table_d1(c):
+ has_randal = True
+ elif stringprep.in_table_d2(c):
+ has_lcat = True
+
+ if has_randal and has_lcat:
+ raise StringPrepError("BIDI violation: section 6 (2)")
+
+ first_randal = stringprep.in_table_d1(data[0])
+ last_randal = stringprep.in_table_d1(data[-1])
+ if has_randal and not (first_randal and last_randal):
+ raise StringPrepError("BIDI violation: section 6 (3)")
+
+
+def create(nfkc=True, bidi=True, mappings=None,
+ prohibited=None, unassigned=None):
+ def profile(data, query=False):
+ try:
+ data = to_unicode(data)
+ except UnicodeError:
+ raise StringPrepError
+
+ data = map_input(data, mappings)
+ data = normalize(data, nfkc)
+ prohibit_output(data, prohibited)
+ if bidi:
+ check_bidi(data)
+ if query and unassigned:
+ check_unassigned(data, unassigned)
+ return data
+ return profile