CFamily: improve label detection (#2022)

* Remove unused variable

This variable is unused since the first commit to this file
in the commit history, so it's probably safe to remove it.

* Lex identifier as label only if it's at line start

* Stop matching identifiers that begin with a digit

This is so we don't match numbers as labels with the new labels rule.

* Add label tests

* Fix existing tests

pygments/lexers/c_cpp.py

@@ -25,9 +25,6 @@ class CFamilyLexer(RegexLexer):
     definitions.
     """
 
-    #: optional Comment or Whitespace
-    _ws = r'(?:\s|//.*?\n|/[*].*?[*]/)+'
-
     # The trailing ?, rather than *, avoids a geometric performance drop here.
     #: only one /* */ style comment
     _ws1 = r'\s*(?:/[*].*?[*]/\s*)?'
@@ -42,8 +39,8 @@ class CFamilyLexer(RegexLexer):
     _intsuffix = r'(([uU][lL]{0,2})|[lL]{1,2}[uU]?)?'
 
     # Identifier regex with C and C++ Universal Character Name (UCN) support.
-    _ident = r'(?:[\w$]|\\u[0-9a-fA-F]{4}|\\U[0-9a-fA-F]{8})+'
-    _namespaced_ident = r'(?:[\w$]|\\u[0-9a-fA-F]{4}|\\U[0-9a-fA-F]{8}|::)+'
+    _ident = r'(?!\d)(?:[\w$]|\\u[0-9a-fA-F]{4}|\\U[0-9a-fA-F]{8})+'
+    _namespaced_ident = r'(?!\d)(?:[\w$]|\\u[0-9a-fA-F]{4}|\\U[0-9a-fA-F]{8}|::)+'
 
     tokens = {
         'whitespace': [
@@ -55,6 +52,8 @@ class CFamilyLexer(RegexLexer):
              bygroups(using(this), Comment.Preproc), 'if0'),
             ('^(' + _ws1 + ')(#)',
              bygroups(using(this), Comment.Preproc), 'macro'),
+            (r'(^[ \t]*)(?!(?:public|private|protected|default)\b)(case\b\s+)?(' + _ident + r')(\s*)(:)(?!:)',
+             bygroups(Whitespace, using(this), Name.Label, Whitespace, Punctuation)),
             (r'\n', Whitespace),
             (r'[^\S\n]+', Whitespace),
             (r'\\\n', Text),  # line continuation
@@ -82,7 +81,6 @@ class CFamilyLexer(RegexLexer):
             (r'[~!%^&*+=|?:<>/-]', Operator),
             (r'[()\[\],.]', Punctuation),
             (r'(true|false|NULL)\b', Name.Builtin),
-            (r'(' + _ident + r')(\s*)(:)(?!:)', bygroups(Name.Label, Whitespace, Punctuation)),
             (_ident, Name)
         ],
         'types': [

tests/examplefiles/c/labels.c

@@ -0,0 +1,14 @@
+int id() {
+    id:
+    int i = true ? 1 : 2;
+    default_value:
+
+    switch (2) {
+        case Qfalse:
+            break;
+        case Qnil:
+            return Qnil;
+        default:
+            return 0;
+    }
+}