Syntax highlighting for C and Turtle code in documentation

2 files changed, 135 insertions, 11 deletions

diff --git a/doc/style.css b/doc/style.css
index e9bae98..c483e82 100644
--- a/doc/style.css
+++ b/doc/style.css
@@ -1,3 +1,5 @@
+/* Specgen style */
+
 html, body {
 	font-family: sans-serif;
 	font-size: 100%;
@@ -457,7 +459,7 @@ dt {
 hr {
 	background-color: silver;
 	border: 0;
-	color: silver;
+	color: gray;
 	height: 1px;
 	margin-bottom: 1.5ex;
 	margin-top: 1.5ex;
@@ -495,8 +497,8 @@ td {
 	padding-right: 1ex;
 }
 pre {
-	color: #373;
-	margin-left: 2em;
+    margin: 1em 1em 1em 4em;
+    padding: 0;
 }
 code {
 	color: #373;
@@ -513,11 +515,66 @@ code {
 h1, h2, h3, h4, h5, h6, th {
 	text-align: left;
 }
-@media aural {
-	dt {
-		pause-before: 20%;
-	}
-	pre {
-		speak-punctuation: code;
-	}
-}
+
+/* Pygments Style */
+.hll { background-color: #ffffcc }
+.c { color: #408080; font-style: italic } /* Comment */
+.err { border: 1px solid #FF0000 } /* Error */
+.k { color: #BB712B; } /* Keyword */
+.o { color: #666666 } /* Operator */
+.cm { color: #408080; font-style: italic } /* Comment.Multiline */
+.cp { color: #D33682 } /* Comment.Preproc */
+.c1 { color: #408080; font-style: italic } /* Comment.Single */
+.cs { color: #408080; font-style: italic } /* Comment.Special */
+.gd { color: #A00000 } /* Generic.Deleted */
+.ge { font-style: italic } /* Generic.Emph */
+.gr { color: #FF0000 } /* Generic.Error */
+.gh { color: #000080; font-weight: bold } /* Generic.Heading */
+.gi { color: #00A000 } /* Generic.Inserted */
+.go { color: #808080 } /* Generic.Output */
+.gp { color: #000080; font-weight: bold } /* Generic.Prompt */
+.gs { font-weight: bold } /* Generic.Strong */
+.gu { color: #800080; font-weight: bold } /* Generic.Subheading */
+.gt { color: #0040D0 } /* Generic.Traceback */
+.kc { color: #008000; font-weight: bold } /* Keyword.Constant */
+.kd { color: #008000; font-weight: bold } /* Keyword.Declaration */
+.kn { color: #008000; font-weight: bold } /* Keyword.Namespace */
+.kp { color: #008000 } /* Keyword.Pseudo */
+.kr { color: #008000; font-weight: bold } /* Keyword.Reserved */
+.kt { color: #3E873E } /* Keyword.Type */
+.m { color: #666666 } /* Literal.Number */
+.s { color: #BA2121 } /* Literal.String */
+.na { color: #7D9029 } /* Name.Attribute */
+.nb { color: #008000 } /* Name.Builtin */
+.nc { color: #000000; font-weight: bold } /* Name.Class */
+.no { color: #880000 } /* Name.Constant */
+.nd { color: #AA22FF } /* Name.Decorator */
+.ni { color: #999999; font-weight: bold } /* Name.Entity */
+.ne { color: #D2413A; font-weight: bold } /* Name.Exception */
+.nf { color: #222222; font-weight: bold } /* Name.Function */
+.nl { color: #A0A000 } /* Name.Label */
+.nn { color: #000000 } /* Name.Namespace */
+.nt { color: #008000; font-weight: bold } /* Name.Tag */
+.nv { color: #19177C } /* Name.Variable */
+.ow { color: #AA22FF; font-weight: bold } /* Operator.Word */
+.w { color: #bbbbbb } /* Text.Whitespace */
+.mf { color: #666666 } /* Literal.Number.Float */
+.mh { color: #666666 } /* Literal.Number.Hex */
+.mi { color: #666666 } /* Literal.Number.Integer */
+.mo { color: #666666 } /* Literal.Number.Oct */
+.sb { color: #BA2121 } /* Literal.String.Backtick */
+.sc { color: #BA2121 } /* Literal.String.Char */
+.sd { color: #BA2121; font-style: italic } /* Literal.String.Doc */
+.s2 { color: #BA2121 } /* Literal.String.Double */
+.se { color: #BB6622; font-weight: bold } /* Literal.String.Escape */
+.sh { color: #BA2121 } /* Literal.String.Heredoc */
+.si { color: #BB6688; font-weight: bold } /* Literal.String.Interpol */
+.sx { color: #008000 } /* Literal.String.Other */
+.sr { color: #BB6688 } /* Literal.String.Regex */
+.s1 { color: #BA2121 } /* Literal.String.Single */
+.ss { color: #19177C } /* Literal.String.Symbol */
+.bp { color: #008000 } /* Name.Builtin.Pseudo */
+.vc { color: #19177C } /* Name.Variable.Class */
+.vg { color: #19177C } /* Name.Variable.Global */
+.vi { color: #19177C } /* Name.Variable.Instance */
+.il { color: #666666 } /* Literal.Number.Integer.Long */
diff --git a/lv2specgen/lv2specgen.py b/lv2specgen/lv2specgen.py
index 3c6db71..404545f 100755
--- a/lv2specgen/lv2specgen.py
+++ b/lv2specgen/lv2specgen.py
@@ -50,6 +50,8 @@ try:
     import pygments
     import pygments.lexers
     import pygments.formatters
+    from pygments.lexer import RegexLexer, include, bygroups
+    from pygments.token import Text, Comment, Operator, Keyword, Name, String, Literal
     have_pygments = True
 except ImportError:
     print("Error importing pygments, syntax highlighting disabled")
@@ -158,6 +160,58 @@ def getLabel(m, urinode):
     else:
         return ''
 
+if have_pygments:
+    # Based on sw.py by Philip Cooper
+    class Notation3Lexer(RegexLexer):
+        """
+        Lexer for N3 / Turtle / NT
+        """
+        name = 'N3'
+        aliases = ['n3', 'turtle']
+        filenames = ['*.n3', '*.ttl', '*.nt']
+        mimetypes = ['text/rdf+n3','application/x-turtle','application/n3']
+    
+        tokens = {
+            'comments': [
+                (r'(\s*#.*)', Comment)
+            ],
+            'root': [
+                include('comments'),
+                (r'(\s*@(?:prefix|base|keywords)\s*)(\w*:\s+)?(<[^> ]*>\s*\.\s*)',bygroups(Keyword,Name.Variable,Name.Namespace)),
+                (r'\s*(<[^>]*\>)', Name.Class, ('triple','predObj')),
+                (r'(\s*[a-zA-Z_:][a-zA-Z0-9\-_:]*\s)', Name.Class, ('triple','predObj')),
+                (r'\s*\[\]\s*', Name.Class, ('triple','predObj')),
+            ],
+            'triple' : [
+                (r'\s*\.\s*', Text, '#pop')
+            ],
+            'predObj': [
+                include('comments'),
+                (r'(\s*[a-zA-Z_:][a-zA-Z0-9\-_:]*\b\s*)', Operator, 'object'),
+                (r'\s*(<[^>]*\>)', Operator, 'object'),
+                (r'\s*\]\s*', Text, '#pop'),
+                (r'(?=\s*\.\s*)', Keyword, '#pop'), 
+            ],
+            'objList': [
+                include('comments'),
+                (r'\s*\)', Text, '#pop'),
+                include('object')
+            ],
+            'object': [
+                include('comments'),
+                (r'\s*\[', Text, 'predObj'),
+                (r'\s*<[^> ]*>', Name.Attribute),
+                (r'\s*("""(?:.|\n)*?""")(\@[a-z]{2-4}|\^\^<?[a-zA-Z0-9\-\:_#/\.]*>?)?\s*', bygroups(Literal.String,Text)),
+                (r'\s*".*?[^\\]"(?:\@[a-z]{2-4}|\^\^<?[a-zA-Z0-9\-\:_#/\.]*>?)?\s*', Literal.String),
+                (r'\s*[a-zA-Z0-9\-_\:]\s*', Name.Attribute),
+                (r'\s*\(', Text, 'objList'),
+                (r'\s*;\s*\n?', Text, '#pop'),
+                (r'\s*,\s*\n?', Text, '#pop'),  # Added by drobilla so "," is not an error
+                (r'(?=\s*\])', Text, '#pop'),            
+                (r'(?=\s*\.)', Text, '#pop'),           
+            ],
+        }
+    
 
 def getComment(m, urinode):
     c = findOne(m, urinode, lv2.documentation, None)
@@ -178,6 +232,19 @@ def getComment(m, urinode):
                     pygments.formatters.HtmlFormatter())
                 markup = code_rgx.sub(code_str, markup, 1)
 
+        # Syntax highlight all Turtle code
+        if have_pygments:
+            code_rgx = re.compile('<pre class="turtle-code">(.*?)</pre>', re.DOTALL)
+            while True:
+                code = code_rgx.search(markup)
+                if not code:
+                    break
+                match_str = xml.sax.saxutils.unescape(code.group(1))
+                code_str = pygments.highlight(
+                    match_str,
+                    Notation3Lexer(),
+                    pygments.formatters.HtmlFormatter())
+                markup = code_rgx.sub(code_str, markup, 1)
 
         # Add links to code documentation for identifiers
         rgx = re.compile('([^a-zA-Z0-9_:])(' + \