Merge with -main

4 files changed, 24 insertions, 27 deletions

diff --git a/pygments/formatters/other.py b/pygments/formatters/other.py
index d8e5f4f7..6100f70b 100644
--- a/pygments/formatters/other.py
+++ b/pygments/formatters/other.py
@@ -136,10 +136,8 @@ class TestcaseFormatter(Formatter):
 
     def __init__(self, **options):
         Formatter.__init__(self, **options)
-        #if self.encoding != 'utf-8':
-        #    print >>sys.stderr, "NOTICE: Forcing encoding to utf-8, as all Pygments source is"
         if self.encoding is not None and self.encoding != 'utf-8':
-            raise ValueError("Only None and utf-u are allowed encodings.")
+            raise ValueError("Only None and utf-8 are allowed encodings.")
 
     def format(self, tokensource, outfile):
         indentation = ' ' * 12
diff --git a/pygments/lexers/dotnet.py b/pygments/lexers/dotnet.py
index 204b4a71..0b395a40 100644
--- a/pygments/lexers/dotnet.py
+++ b/pygments/lexers/dotnet.py
@@ -54,14 +54,14 @@ class CSharpLexer(RegexLexer):
 
     flags = re.MULTILINE | re.DOTALL | re.UNICODE
 
-    # for the range of allowed unicode characters in identifiers,
-    # see http://www.ecma-international.org/publications/files/ECMA-ST/Ecma-334.pdf
+    # for the range of allowed unicode characters in identifiers, see
+    # http://www.ecma-international.org/publications/files/ECMA-ST/Ecma-334.pdf
 
     levels = {
         'none': '@?[_a-zA-Z]\w*',
-        'basic': ('@?[_' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl + ']' +
-                  '[' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl +
-                  uni.Nd + uni.Pc + uni.Cf + uni.Mn + uni.Mc + ']*'),
+        'basic': ('@?[_' + uni.combine('Lu', 'Ll', 'Lt', 'Lm', 'Nl') + ']' +
+                  '[' + uni.combine('Lu', 'Ll', 'Lt', 'Lm', 'Nl', 'Nd', 'Pc',
+                                    'Cf', 'Mn', 'Mc') + ']*'),
         'full': ('@?(?:_|[^' +
                  uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl') + '])'
                  + '[^' + uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl',
@@ -169,16 +169,16 @@ class NemerleLexer(RegexLexer):
     # for the range of allowed unicode characters in identifiers, see
     # http://www.ecma-international.org/publications/files/ECMA-ST/Ecma-334.pdf
 
-    levels = dict(
-        none='@?[_a-zA-Z]\w*',
-        basic=('@?[_' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl + ']' +
-               '[' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl +
-               uni.Nd + uni.Pc + uni.Cf + uni.Mn + uni.Mc + ']*'),
-        full=('@?(?:_|[^' + uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo',
-                                          'Nl') + '])'
-              + '[^' + uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl',
-                                     'Nd', 'Pc', 'Cf', 'Mn', 'Mc') + ']*'),
-    )
+    levels = {
+        'none': '@?[_a-zA-Z]\w*',
+        'basic': ('@?[_' + uni.combine('Lu', 'Ll', 'Lt', 'Lm', 'Nl') + ']' +
+                  '[' + uni.combine('Lu', 'Ll', 'Lt', 'Lm', 'Nl', 'Nd', 'Pc',
+                                    'Cf', 'Mn', 'Mc') + ']*'),
+        'full': ('@?(?:_|[^' +
+                 uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl') + '])'
+                 + '[^' + uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl',
+                                        'Nd', 'Pc', 'Cf', 'Mn', 'Mc') + ']*'),
+    }
 
     tokens = {}
     token_variants = True
diff --git a/pygments/lexers/javascript.py b/pygments/lexers/javascript.py
index 481243ef..57870009 100644
--- a/pygments/lexers/javascript.py
+++ b/pygments/lexers/javascript.py
@@ -22,12 +22,11 @@ __all__ = ['JavascriptLexer', 'KalLexer', 'LiveScriptLexer', 'DartLexer',
            'TypeScriptLexer', 'LassoLexer', 'ObjectiveJLexer',
            'CoffeeScriptLexer', 'MaskLexer']
 
-
-JS_IDENT_START = ('(?:[$_' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Lo + uni.Nl
-                  + ']|\\\\u[a-fA-F0-9]{4})')
-JS_IDENT_PART = ('(?:[$_' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Lo + uni.Nl
-                 + uni.Mn + uni.Mc + uni.Nd + uni.Pc
-                 + u'\u200c\u200d]|\\\\u[a-fA-F0-9]{4})')
+JS_IDENT_START = ('(?:[$_' + uni.combine('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl') +
+                  ']|\\\\u[a-fA-F0-9]{4})')
+JS_IDENT_PART = ('(?:[$_' + uni.combine('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl',
+                                        'Mn', 'Mc', 'Nd', 'Pc') +
+                 u'\u200c\u200d]|\\\\u[a-fA-F0-9]{4})')
 JS_IDENT = JS_IDENT_START + '(?:' + JS_IDENT_PART + ')*'
 
 
diff --git a/pygments/lexers/jvm.py b/pygments/lexers/jvm.py
index 898cf415..df54e714 100644
--- a/pygments/lexers/jvm.py
+++ b/pygments/lexers/jvm.py
@@ -999,9 +999,9 @@ class KotlinLexer(RegexLexer):
 
     flags = re.MULTILINE | re.DOTALL | re.UNICODE
 
-    kt_name = ('@?[_' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl + ']' +
-               '[' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl + uni.Nd +
-               uni.Pc + uni.Cf + uni.Mn + uni.Mc + ']*')
+    kt_name = ('@?[_' + uni.combine('Lu', 'Ll', 'Lt', 'Lm', 'Nl') + ']' +
+               '[' + uni.combine('Lu', 'Ll', 'Lt', 'Lm', 'Nl', 'Nd', 'Pc', 'Cf',
+                                 'Mn', 'Mc') + ']*')
     kt_id = '(' + kt_name + '|`' + kt_name + '`)'
 
     tokens = {