Add Nemerle lexer

2 files changed, 141 insertions, 1 deletions

diff --git a/pygments/lexers/_mapping.py b/pygments/lexers/_mapping.py
index ed23cbdb..503eb9f9 100644
--- a/pygments/lexers/_mapping.py
+++ b/pygments/lexers/_mapping.py
@@ -144,6 +144,7 @@ LEXERS = {
     'MyghtyLexer': ('pygments.lexers.templates', 'Myghty', ('myghty',), ('*.myt', 'autodelegate'), ('application/x-myghty',)),
     'MyghtyXmlLexer': ('pygments.lexers.templates', 'XML+Myghty', ('xml+myghty',), (), ('application/xml+myghty',)),
     'NasmLexer': ('pygments.lexers.asm', 'NASM', ('nasm',), ('*.asm', '*.ASM'), ('text/x-nasm',)),
+    'NemerleLexer': ('pygments.lexers.dotnet', 'Nemerle', ('nemerle',), ('*.n',), ('text/x-nemerle',)),
     'NewspeakLexer': ('pygments.lexers.other', 'Newspeak', ('newspeak',), ('*.ns2',), ('text/x-newspeak',)),
     'NginxConfLexer': ('pygments.lexers.text', 'Nginx configuration file', ('nginx',), (), ('text/x-nginx-conf',)),
     'NumPyLexer': ('pygments.lexers.math', 'NumPy', ('numpy',), (), ()),
diff --git a/pygments/lexers/dotnet.py b/pygments/lexers/dotnet.py
index 48feeb85..21990122 100644
--- a/pygments/lexers/dotnet.py
+++ b/pygments/lexers/dotnet.py
@@ -18,7 +18,7 @@ from pygments import unistring as uni
 
 from pygments.lexers.web import XmlLexer
 
-__all__ = ['CSharpLexer', 'BooLexer', 'VbNetLexer', 'CSharpAspxLexer',
+__all__ = ['CSharpLexer', 'NemerleLexer', 'BooLexer', 'VbNetLexer', 'CSharpAspxLexer',
            'VbNetAspxLexer']
 
 
@@ -137,6 +137,145 @@ class CSharpLexer(RegexLexer):
 
         RegexLexer.__init__(self, **options)
 
+class NemerleLexer(RegexLexer):
+    """
+    For `Nemerle <http://nemerle.org>`_
+    source code.
+
+    Additional options accepted:
+
+    `unicodelevel`
+      Determines which Unicode characters this lexer allows for identifiers.
+      The possible values are:
+
+      * ``none`` -- only the ASCII letters and numbers are allowed. This
+        is the fastest selection.
+      * ``basic`` -- all Unicode characters from the specification except
+        category ``Lo`` are allowed.
+      * ``full`` -- all Unicode characters as specified in the C# specs
+        are allowed.  Note that this means a considerable slowdown since the
+        ``Lo`` category has more than 40,000 characters in it!
+
+      The default value is ``basic``.
+
+      *New in Pygments 1.4.*
+    """
+
+    name = 'Nemerle'
+    aliases = ['nemerle']
+    filenames = ['*.n']
+    mimetypes = ['text/x-nemerle'] # inferred
+
+    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
+
+    levels = {
+        'none': '@?[_a-zA-Z][a-zA-Z0-9_]*',
+        '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': ('@?(?:_|[^' +
+                 _escape(uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl')) + '])'
+                 + '[^' + _escape(uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo',
+                                                'Nl', 'Nd', 'Pc', 'Cf', 'Mn',
+                                                'Mc')) + ']*'),
+    }
+
+    tokens = {}
+    token_variants = True
+
+    for levelname, cs_ident in levels.items():
+        tokens[levelname] = {
+            'root': [
+                # method names
+                (r'^([ \t]*(?:' + cs_ident + r'(?:\[\])?\s+)+?)' # return type
+                 r'(' + cs_ident + ')'                           # method name
+                 r'(\s*)(\()',                               # signature start
+                 bygroups(using(this), Name.Function, Text, Punctuation)),
+                (r'^\s*\[.*?\]', Name.Attribute),
+                (r'[^\S\n]+', Text),
+                (r'\\\n', Text), # line continuation
+                (r'//.*?\n', Comment.Single),
+                (r'/[*](.|\n)*?[*]/', Comment.Multiline),
+                (r'\n', Text),
+                (r'\$\s*"', String, 'splice-string'),
+                (r'\$\s*<#', String, 'splice-string2'),
+                (r'<#(?:[^#>])*#>', String),
+                (r'[~!%^&*()+=|\[\]:;,.<>/?-]', Punctuation),
+                (r'[{}]', Punctuation),
+                (r'@"(\\\\|\\"|[^"])*"', String),
+                (r'"(\\\\|\\"|[^"\n])*["\n]', String),
+                (r"'\\.'|'[^\\]'", String.Char),
+                (r"[0-9](\.[0-9]*)?([eE][+-][0-9]+)?"
+                 r"[flFLdD]?|0[xX][0-9a-fA-F]+[Ll]?", Number),
+                (r'#[ \t]*(if|endif|else|elif|define|undef|'
+                 r'line|error|warning|region|endregion|pragma)\b.*?\n',
+                 Comment.Preproc),
+                (r'\b(extern)(\s+)(alias)\b', bygroups(Keyword, Text,
+                 Keyword)),
+                (r'(abstract|and|as|base|catch|def|delegate|'
+                r'enum|event|extern|false|finally|'
+                r'fun|implements|interface|internal|'
+                r'is|macro|match|matches|module|mutable|new|'
+                r'null|out|override|params|partial|private|'
+                r'protected|public|ref|sealed|static|'
+                r'syntax|this|throw|true|try|type|typeof|'
+                r'virtual|volatile|when|where|with|'
+                r'assert|assert2|async|break|checked|continue|do|else|'
+                r'ensures|for|foreach|if|late|lock|new|nolate|'
+                r'otherwise|regexp|repeat|requires|return|surroundwith|unchecked|unless|using|while|yield)\b', Keyword),
+                (r'(global)(::)', bygroups(Keyword, Punctuation)),
+                (r'(bool|byte|char|decimal|double|float|int|long|object|sbyte|'
+                 r'short|string|uint|ulong|ushort)\b\??', Keyword.Type),
+                (r'(class|struct|variant|module)(\s+)', bygroups(Keyword, Text), 'class'),
+                (r'(namespace|using)(\s+)', bygroups(Keyword, Text), 'namespace'),
+                (cs_ident, Name),
+            ],
+            'class': [
+                (cs_ident, Name.Class, '#pop')
+            ],
+            'namespace': [
+                (r'(?=\()', Text, '#pop'), # using (resource)
+                ('(' + cs_ident + r'|\.)+', Name.Namespace, '#pop')
+            ],
+            'splice-string': [
+                (r'[^"$]',  String), 
+                (r'\$\(', Name, 'splice-string-content'),
+                (r'\$', Name, 'splice-string-ident'),
+                (r'\\"',  String),
+                (r'"',  String, '#pop')
+            ],
+            'splice-string2': [
+                (r'[^#>$]',  String), 
+                (r'\$\(', Name, 'splice-string-content'),
+                (r'\$', Name, 'splice-string-ident'),
+                (r'#>',  String, '#pop')
+            ],
+            'splice-string-content': [
+                (r'if|match', Keyword), 
+                (r'[~!%^&*+=|\[\]:;,.<>/?-]', Punctuation),
+                (cs_ident, Name), 
+                (r'\(', Name, '#push'),
+                (r'\)', Name, '#pop')
+            ],
+            'splice-string-ident': [
+                (cs_ident,  Name, '#pop'), 
+                (r'.',  String, '#pop')
+            ],
+        }
+
+    def __init__(self, **options):
+        level = get_choice_opt(options, 'unicodelevel', self.tokens.keys(), 'basic')
+        if level not in self._all_tokens:
+            # compile the regexes now
+            self._tokens = self.__class__.process_tokendef(level)
+        else:
+            self._tokens = self._all_tokens[level]
+
+        RegexLexer.__init__(self, **options)
+
 
 class BooLexer(RegexLexer):
     """