summaryrefslogtreecommitdiff
path: root/sleekxmpp/thirdparty/suelta/saslprep.py
diff options
context:
space:
mode:
authorLance Stout <lancestout@gmail.com>2011-08-04 11:52:17 -0700
committerLance Stout <lancestout@gmail.com>2011-08-04 11:52:17 -0700
commit89cffd43f48cfc835b70e137776eb8c2e73a0b67 (patch)
tree088035aeb688edc6a0f5675de31eedf169f87fd3 /sleekxmpp/thirdparty/suelta/saslprep.py
parentad978700fc891602c826dea03615c396f39364a0 (diff)
parentb9764cc120c48576be1fe6cadb11813d12f91f4c (diff)
downloadslixmpp-89cffd43f48cfc835b70e137776eb8c2e73a0b67.tar.gz
slixmpp-89cffd43f48cfc835b70e137776eb8c2e73a0b67.tar.bz2
slixmpp-89cffd43f48cfc835b70e137776eb8c2e73a0b67.tar.xz
slixmpp-89cffd43f48cfc835b70e137776eb8c2e73a0b67.zip
Merge branch 'develop' into roster
Conflicts: setup.py
Diffstat (limited to 'sleekxmpp/thirdparty/suelta/saslprep.py')
-rw-r--r--sleekxmpp/thirdparty/suelta/saslprep.py78
1 files changed, 78 insertions, 0 deletions
diff --git a/sleekxmpp/thirdparty/suelta/saslprep.py b/sleekxmpp/thirdparty/suelta/saslprep.py
new file mode 100644
index 00000000..fe58d58b
--- /dev/null
+++ b/sleekxmpp/thirdparty/suelta/saslprep.py
@@ -0,0 +1,78 @@
+from __future__ import unicode_literals
+
+import sys
+import stringprep
+import unicodedata
+
+
+def saslprep(text, strict=True):
+ """
+ Return a processed version of the given string, using the SASLPrep
+ profile of stringprep.
+
+ :param text: The string to process, in UTF-8.
+ :param strict: If ``True``, prevent the use of unassigned code points.
+ """
+
+ if sys.version_info < (3, 0):
+ if type(text) == str:
+ text = text.decode('us-ascii')
+
+ # Mapping:
+ #
+ # - non-ASCII space characters [StringPrep, C.1.2] that can be
+ # mapped to SPACE (U+0020), and
+ #
+ # - the 'commonly mapped to nothing' characters [StringPrep, B.1]
+ # that can be mapped to nothing.
+ buffer = ''
+ for char in text:
+ if stringprep.in_table_c12(char):
+ buffer += ' '
+ elif not stringprep.in_table_b1(char):
+ buffer += char
+
+ # Normalization using form KC
+ text = unicodedata.normalize('NFKC', buffer)
+
+ # Check for bidirectional string
+ buffer = ''
+ first_is_randal = False
+ if text:
+ first_is_randal = stringprep.in_table_d1(text[0])
+ if first_is_randal and not stringprep.in_table_d1(text[-1]):
+ raise UnicodeError('Section 6.3 [end]')
+
+ # Check for prohibited characters
+ for x in range(len(text)):
+ if strict and stringprep.in_table_a1(text[x]):
+ raise UnicodeError('Unassigned Codepoint')
+ if stringprep.in_table_c12(text[x]):
+ raise UnicodeError('In table C.1.2')
+ if stringprep.in_table_c21(text[x]):
+ raise UnicodeError('In table C.2.1')
+ if stringprep.in_table_c22(text[x]):
+ raise UnicodeError('In table C.2.2')
+ if stringprep.in_table_c3(text[x]):
+ raise UnicodeError('In table C.3')
+ if stringprep.in_table_c4(text[x]):
+ raise UnicodeError('In table C.4')
+ if stringprep.in_table_c5(text[x]):
+ raise UnicodeError('In table C.5')
+ if stringprep.in_table_c6(text[x]):
+ raise UnicodeError('In table C.6')
+ if stringprep.in_table_c7(text[x]):
+ raise UnicodeError('In table C.7')
+ if stringprep.in_table_c8(text[x]):
+ raise UnicodeError('In table C.8')
+ if stringprep.in_table_c9(text[x]):
+ raise UnicodeError('In table C.9')
+ if x:
+ if first_is_randal and stringprep.in_table_d2(text[x]):
+ raise UnicodeError('Section 6.2')
+ if not first_is_randal and \
+ x != len(text) - 1 and \
+ stringprep.in_table_d1(text[x]):
+ raise UnicodeError('Section 6.3')
+
+ return text