Include debian patch for unicode codepoints over 0xffff

https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=806826

src/yaml/emitter.py

@@ -13,10 +13,13 @@
 __all__ = ['Emitter', 'EmitterError']
 
 import six
+import sys
 
 from .error import YAMLError
 from .events import *
 
+has_ucs4 = sys.maxunicode > 0xffff
+
 class EmitterError(YAMLError):
     pass
 
@@ -708,7 +711,8 @@ def analyze_scalar(self, scalar):
                 line_breaks = True
             if not (ch == '\n' or '\x20' <= ch <= '\x7E'):
                 if (ch == '\x85' or '\xA0' <= ch <= '\uD7FF'
-                        or '\uE000' <= ch <= '\uFFFD') and ch != '\uFEFF':
+                        or u'\uE000' <= ch <= u'\uFFFD'
+                        or ((not has_ucs4) or (u'\U00010000' <= ch < u'\U0010ffff'))) and ch != u'\uFEFF':
                     unicode_characters = True
                     if not self.allow_unicode:
                         special_characters = True

src/yaml/reader.py

@@ -24,8 +24,12 @@
 
 from .error import YAMLError, Mark
 
-import codecs, re
+import codecs
+import re
 import six
+import sys
+
+has_ucs4 = sys.maxunicode > 0xffff
 
 class ReaderError(YAMLError):
 
@@ -141,7 +145,11 @@ def determine_encoding(self):
                 self.encoding = 'utf-8'
         self.update(1)
 
-    NON_PRINTABLE = re.compile('[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD]')
+    if has_ucs4:
+        NON_PRINTABLE = re.compile(u'[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD\U00010000-\U0010ffff]')
+    else:
+        NON_PRINTABLE = re.compile(u'[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD]')
+
     def check_printable(self, data):
         match = self.NON_PRINTABLE.search(data)
         if match: