Update SystemVerilog literal constants (#1460)

The original implementation was missing some of the more arcane features
such as underbars, the character 's' for signed/unsigned, support for
spaces before/after the base specifier, capital letter base specifiers
(ie 'B 'D 'H), and the 4-state 'xXzZ?' characters.

For regular integers, the 'l' and 'L' suffixes are not valid.
That is, unlike C, in Verilog '42L' is not a valid int literal.

Create a new test that exercises most of the interesting kinds of
SystemVerilog numbers.

This fixes a couple minor issues with what type of number the lexer
returns. For example, Numbers like '42' used to return Integer.Hex,
but now return Integer.Decimal.

1 files changed, 14 insertions, 6 deletions

diff --git a/pygments/lexers/hdl.py b/pygments/lexers/hdl.py
index 2e64b8e9..1472b5df 100644
--- a/pygments/lexers/hdl.py
+++ b/pygments/lexers/hdl.py
@@ -162,14 +162,22 @@ class SystemVerilogLexer(RegexLexer):
             (r'[{}#@]', Punctuation),
             (r'L?"', String, 'string'),
             (r"L?'(\\.|\\[0-7]{1,3}|\\x[a-fA-F0-9]{1,2}|[^\\\'\n])'", String.Char),
+
             (r'(\d+\.\d*|\.\d+|\d+)[eE][+-]?\d+[lL]?', Number.Float),
             (r'(\d+\.\d*|\.\d+|\d+[fF])[fF]?', Number.Float),
-            (r'([0-9]+)|(\'h)[0-9a-fA-F]+', Number.Hex),
-            (r'([0-9]+)|(\'b)[01]+', Number.Bin),
-            (r'([0-9]+)|(\'d)[0-9]+', Number.Integer),
-            (r'([0-9]+)|(\'o)[0-7]+', Number.Oct),
-            (r'\'[01xz]', Number),
-            (r'\d+[Ll]?', Number.Integer),
+
+            (r'([1-9][_0-9]*)?\s*\'[sS]?[bB]\s*[xXzZ?01][_xXzZ?01]*',
+             Number.Bin),
+            (r'([1-9][_0-9]*)?\s*\'[sS]?[oO]\s*[xXzZ?0-7][_xXzZ?0-7]*',
+             Number.Oct),
+            (r'([1-9][_0-9]*)?\s*\'[sS]?[dD]\s*[xXzZ?0-9][_xXzZ?0-9]*',
+             Number.Integer),
+            (r'([1-9][_0-9]*)?\s*\'[sS]?[hH]\s*[xXzZ?0-9a-fA-F][_xXzZ?0-9a-fA-F]*',
+             Number.Hex),
+
+            (r'\'[01xXzZ]', Number),
+            (r'[0-9][_0-9]*', Number.Integer),
+
             (r'\*/', Error),
             (r'[~!%^&*+=|?:<>/-]', Operator),
             (r'[()\[\],.;\']', Punctuation),