Initial version of DataSpecLexer

i2p2www/extensions.py

@@ -9,6 +9,8 @@ from pygments.lexers import get_lexer_by_name, guess_lexer
 from pygments.formatters import HtmlFormatter
 from pygments.util import ClassNotFound
 
+from i2p2www.lexers import DataSpecLexer
+
 class HighlightExtension(Extension):
     """Highlight code blocks using Pygments
 
@@ -68,8 +70,11 @@ class HighlightExtension(Extension):
             else:
                 lexer = get_lexer_by_name(lang, stripall=False)
         except ClassNotFound as e:
-            print(e)
-            sys.exit(1)
+            if lang == 'dataspec':
+                lexer = DataSpecLexer(stripall=False)
+            else:
+                print(e)
+                sys.exit(1)
 
         formatter = HtmlFormatter(**parameters)
         code = highlight(Markup(body).unescape(), lexer, formatter)

i2p2www/lexers.py

@@ -0,0 +1,33 @@
+from pygments.lexer import RegexLexer, bygroups
+from pygments.token import *
+
+class DataSpecLexer(RegexLexer):
+    name = 'DataSpec'
+    aliases = ['dataspec']
+    filenames = []
+
+    tokens = {
+        'root': [
+            (r'(\s*)(\+-)', bygroups(Text, Text), 'boundary'),
+            (r'(\s+)([\+|])', bygroups(Text, Text), 'content'),
+            (r'~', Generic.Strong, 'content'),
+            (r'(\s*)(\w+)(\s)(::)(\s)', bygroups(Text, Name.Tag, Text, Operator, Text), 'definition'),
+        ],
+        'boundary': [
+            (r'---\+$', Text, '#pop'),
+            (r'(//)(-\+)?$', bygroups(Generic.Strong, Text), '#pop'),
+            (r'---\+-', Text),
+            (r'(//)(-\+-)', bygroups(Generic.Strong, Text)),
+        ],
+        'content': [
+            (r'(\s*)([\+|])$', bygroups(Text, Text), '#pop'),
+            (r'(\s*)(~)$', bygroups(Text, Generic.Strong), '#pop'),
+            (r'(\s*)(\w+)', bygroups(Text, Name.Tag)),
+            (r'(\s*)(\|)', bygroups(Text, Text)),
+        ],
+        'definition': [
+            (r'(\s*)(\w+)(\s)(::)(\s)', bygroups(Text, Name.Tag, Text, Operator, Text)),
+            (r'(\s*)((?:[A-Z][a-z]+)+)', bygroups(Text, Name.Class)),
+            (r'(\s*)(\w+)', bygroups(Text, Comment)),
+        ],
+    }