pygments.rb 3.0.0 → 5.0.0

data/vendor/pygments-main/pygments/lexers/scripting.py

@@ -4,7 +4,7 @@
 
     Lexer for scripting and embedded languages.
 
-    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -21,6 +21,10 @@ __all__ = ['LuaLexer', 'LuauLexer', 'MoonScriptLexer', 'ChaiscriptLexer', 'LSLLe
            'EasytrieveLexer', 'JclLexer', 'MiniScriptLexer']
 
 
+def all_lua_builtins():
+    from pygments.lexers._lua_builtins import MODULES
+    return [w for values in MODULES.values() for w in values]
+
 class LuaLexer(RegexLexer):
     """
     For Lua source code.
@@ -53,8 +57,14 @@ class LuaLexer(RegexLexer):
 
     _comment_multiline = r'(?:--\[(?P<level>=*)\[[\w\W]*?\](?P=level)\])'
     _comment_single = r'(?:--.*$)'
-    _space = r'(?:\s+)'
+    _space = r'(?:\s+(?!\s))'
     _s = rf'(?:{_comment_multiline}|{_comment_single}|{_space})'
+    # A lookahead-safe version of _s that avoids catastrophic backtracking.
+    # The _comment_multiline pattern contains [\w\W]*? which, when used
+    # inside a lookahead with a * quantifier, causes exponential blowup.
+    # This version skips only whitespace; comments between an identifier
+    # and a following [.:] or ( are rare enough to sacrifice.
+    _s_la = r'\s'
     _name = r'(?:[^\W\d]\w*)'
 
     tokens = {
@@ -66,7 +76,7 @@ class LuaLexer(RegexLexer):
         'ws': [
             (_comment_multiline, Comment.Multiline),
             (_comment_single, Comment.Single),
-            (_space, Text),
+            (_space, Whitespace),
         ],
         'base': [
             include('ws'),
@@ -82,27 +92,41 @@ class LuaLexer(RegexLexer):
             (r'::', Punctuation, 'label'),
             (r'\.{3}', Punctuation),
             (r'[=<>|~&+\-*/%#^]+|\.\.', Operator),
-            (r'[\[\]{}().,:;]', Punctuation),
+            (r'[\[\]{}().,:;]+', Punctuation),
             (r'(and|or|not)\b', Operator.Word),
 
-            ('(break|do|else|elseif|end|for|if|in|repeat|return|then|until|'
-             r'while)\b', Keyword.Reserved),
+            (words([
+                'break', 'do', 'else', 'elseif', 'end', 'for', 'if', 'in',
+                'repeat', 'return', 'then', 'until', 'while'
+            ], suffix=r'\b'), Keyword.Reserved),
             (r'goto\b', Keyword.Reserved, 'goto'),
             (r'(local)\b', Keyword.Declaration),
             (r'(true|false|nil)\b', Keyword.Constant),
 
             (r'(function)\b', Keyword.Reserved, 'funcname'),
 
-            (r'[A-Za-z_]\w*(\.[A-Za-z_]\w*)?', Name),
+            (words(all_lua_builtins(), suffix=r"\b"), Name.Builtin),
+            (fr'[A-Za-z_]\w*(?={_s_la}*[.:])', Name.Variable, 'varname'),
+            (fr'[A-Za-z_]\w*(?={_s_la}*\()', Name.Function),
+            (r'[A-Za-z_]\w*', Name.Variable),
 
             ("'", String.Single, combined('stringescape', 'sqs')),
             ('"', String.Double, combined('stringescape', 'dqs'))
         ],
 
+        'varname': [
+            include('ws'),
+            (r'\.\.', Operator, '#pop'),
+            (r'[.:]', Punctuation),
+            (rf'{_name}(?={_s_la}*[.:])', Name.Property),
+            (rf'{_name}(?={_s_la}*\()', Name.Function, '#pop'),
+            (_name, Name.Property, '#pop'),
+        ],
+
         'funcname': [
             include('ws'),
             (r'[.:]', Punctuation),
-            (rf'{_name}(?={_s}*[.:])', Name.Class),
+            (rf'{_name}(?={_s_la}*[.:])', Name.Class),
             (_name, Name.Function, '#pop'),
             # inline function
             (r'\(', Punctuation, '#pop'),
@@ -151,19 +175,18 @@ class LuaLexer(RegexLexer):
     def get_tokens_unprocessed(self, text):
         for index, token, value in \
                 RegexLexer.get_tokens_unprocessed(self, text):
-            if token is Name:
-                if value in self._functions:
-                    yield index, Name.Builtin, value
-                    continue
-                elif '.' in value:
+            if token is Name.Builtin and value not in self._functions:
+                if '.' in value:
                     a, b = value.split('.')
                     yield index, Name, a
                     yield index + len(a), Punctuation, '.'
                     yield index + len(a) + 1, Name, b
-                    continue
+                else:
+                    yield index, Name, value
+                continue
             yield index, token, value
 
-def _luau_make_expression(should_pop, _s):
+def _luau_make_expression(should_pop, _s, _s_la):
     temp_list = [
         (r'0[xX][\da-fA-F_]*', Number.Hex, '#pop'),
         (r'0[bB][\d_]*', Number.Bin, '#pop'),
@@ -178,7 +201,7 @@ def _luau_make_expression(should_pop, _s):
         (r'(\.)([a-zA-Z_]\w*)(?=%s*[({"\'])', bygroups(Punctuation, Name.Function), '#pop'),
         (r'(\.)([a-zA-Z_]\w*)', bygroups(Punctuation, Name.Variable), '#pop'),
 
-        (rf'[a-zA-Z_]\w*(?:\.[a-zA-Z_]\w*)*(?={_s}*[({{"\'])', Name.Other, '#pop'),
+        (rf'[a-zA-Z_]\w*(?:\.[a-zA-Z_]\w*)*(?={_s_la}*[({{"\'])', Name.Other, '#pop'),
         (r'[a-zA-Z_]\w*(?:\.[a-zA-Z_]\w*)*', Name, '#pop'),
     ]
     if should_pop:
@@ -227,6 +250,9 @@ class LuauLexer(RegexLexer):
     _comment_multiline = r'(?:--\[(?P<level>=*)\[[\w\W]*?\](?P=level)\])'
     _comment_single = r'(?:--.*$)'
     _s = r'(?:{}|{}|{})'.format(_comment_multiline, _comment_single, r'\s+')
+    # Lookahead-safe version — avoids catastrophic backtracking from
+    # [\w\W]*? inside _comment_multiline when combined with * quantifier.
+    _s_la = r'\s'
 
     tokens = {
         'root': [
@@ -266,7 +292,7 @@ class LuauLexer(RegexLexer):
             (r'[\])};]+', Punctuation),
 
             include('expression_static'),
-            *_luau_make_expression(False, _s),
+            *_luau_make_expression(False, _s, _s_la),
 
             (r'[\[.,]', Punctuation, 'expression'),
         ],
@@ -288,7 +314,7 @@ class LuauLexer(RegexLexer):
             (r'function\b', Keyword.Reserved, 'func_name'),
 
             include('expression_static'),
-            *_luau_make_expression(True, _s),
+            *_luau_make_expression(True, _s, _s_la),
 
             default('#pop'),
         ],
@@ -364,7 +390,7 @@ class LuauLexer(RegexLexer):
             include('ws'),
 
             (r'[.:]', Punctuation),
-            (rf'[a-zA-Z_]\w*(?={_s}*[.:])', Name.Class),
+            (rf'[a-zA-Z_]\w*(?={_s_la}*[.:])', Name.Class),
             (r'[a-zA-Z_]\w*', Name.Function),
 
             (r'<', Punctuation, 'closing_gt_type'),
@@ -521,20 +547,34 @@ class MoonScriptLexer(LuaLexer):
             (r'(self)\b', Name.Builtin.Pseudo),
             (r'@@?([a-zA-Z_]\w*)?', Name.Variable.Class),
             (r'[A-Z]\w*', Name.Class),  # proper name
-            (r'[A-Za-z_]\w*(\.[A-Za-z_]\w*)?', Name),
+            (words(all_lua_builtins(), suffix=r"\b"), Name.Builtin),
+            (r'[A-Za-z_]\w*', Name),
             ("'", String.Single, combined('stringescape', 'sqs')),
             ('"', String.Double, combined('stringescape', 'dqs'))
         ],
         'stringescape': [
             (r'''\\([abfnrtv\\"']|\d{1,3})''', String.Escape)
         ],
-        'sqs': [
-            ("'", String.Single, '#pop'),
-            ("[^']+", String)
+        'strings': [
+            (r'[^#\\\'"]+', String),
+            # note that strings are multi-line.
+            # hashmarks, quotes and backslashes must be parsed one at a time
+        ],
+        'interpoling_string': [
+            (r'\}', String.Interpol, "#pop"),
+            include('base')
         ],
         'dqs': [
-            ('"', String.Double, '#pop'),
-            ('[^"]+', String)
+            (r'"', String.Double, '#pop'),
+            (r'\\.|\'', String),  # double-quoted string don't need ' escapes
+            (r'#\{', String.Interpol, "interpoling_string"),
+            (r'#', String),
+            include('strings')
+        ],
+        'sqs': [
+            (r"'", String.Single, '#pop'),
+            (r'#|\\.|"', String),  # single quoted strings don't need " escapses
+            include('strings')
         ]
     }
 

data/vendor/pygments-main/pygments/lexers/sgf.py

@@ -4,7 +4,7 @@
 
     Lexer for Smart Game Format (sgf) file format.
 
-    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 

data/vendor/pygments-main/pygments/lexers/shell.py

@@ -4,7 +4,7 @@
 
     Lexers for various shells.
 
-    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -232,6 +232,7 @@ class BashSessionLexer(ShellSessionBaseLexer):
     mimetypes = ['application/x-shell-session', 'application/x-sh-session']
     url = 'https://en.wikipedia.org/wiki/Unix_shell'
     version_added = '1.1'
+    _example = "console/example.sh-session"
 
     _innerLexerCls = BashLexer
     _ps1rgx = re.compile(
@@ -542,6 +543,7 @@ class MSDOSSessionLexer(ShellSessionBaseLexer):
     mimetypes = []
     url = 'https://en.wikipedia.org/wiki/MS-DOS'
     version_added = '2.1'
+    _example = "doscon/session"
 
     _innerLexerCls = BatchLexer
     _ps1rgx = re.compile(r'^([^>]*>)(.*\n?)')
@@ -628,6 +630,7 @@ class TcshSessionLexer(ShellSessionBaseLexer):
     mimetypes = []
     url = 'https://www.tcsh.org'
     version_added = '2.1'
+    _example = "tcshcon/session"
 
     _innerLexerCls = TcshLexer
     _ps1rgx = re.compile(r'^([^>]+>)(.*\n?)')
@@ -760,6 +763,7 @@ class PowerShellSessionLexer(ShellSessionBaseLexer):
     mimetypes = []
     url = 'https://learn.microsoft.com/en-us/powershell'
     version_added = '2.1'
+    _example = "pwsh-session/session"
 
     _innerLexerCls = PowerShellLexer
     _bare_continuation = True

data/vendor/pygments-main/pygments/lexers/sieve.py

@@ -13,7 +13,7 @@
     https://tools.ietf.org/html/rfc5429
     https://tools.ietf.org/html/rfc8580
 
-    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 

data/vendor/pygments-main/pygments/lexers/slash.py

@@ -4,7 +4,7 @@
 
     Lexer for the Slash programming language.
 
-    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 

data/vendor/pygments-main/pygments/lexers/smalltalk.py

@@ -4,7 +4,7 @@
 
     Lexers for Smalltalk and related languages.
 
-    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 

data/vendor/pygments-main/pygments/lexers/smithy.py

@@ -4,7 +4,7 @@
 
     Lexers for the Smithy IDL.
 
-    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 

data/vendor/pygments-main/pygments/lexers/smv.py

@@ -4,7 +4,7 @@
 
     Lexers for the SMV languages.
 
-    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 

data/vendor/pygments-main/pygments/lexers/snobol.py

@@ -4,7 +4,7 @@
 
     Lexers for the SNOBOL language.
 
-    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 

data/vendor/pygments-main/pygments/lexers/solidity.py

@@ -4,7 +4,7 @@
 
     Lexers for Solidity.
 
-    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 

data/vendor/pygments-main/pygments/lexers/soong.py

@@ -4,7 +4,7 @@
 
     Lexers for Soong (Android.bp Blueprint) files.
 
-    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 

data/vendor/pygments-main/pygments/lexers/sophia.py

@@ -6,7 +6,7 @@
 
     Derived from pygments/lexers/reason.py.
 
-    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 

data/vendor/pygments-main/pygments/lexers/special.py

@@ -4,7 +4,7 @@
 
     Special lexers.
 
-    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -46,6 +46,7 @@ class OutputLexer(Lexer):
     aliases = ['output']
     url = ""
     version_added = '2.10'
+    _example = "output/output"
 
     def get_tokens_unprocessed(self, text):
         yield 0, Generic.Output, text

data/vendor/pygments-main/pygments/lexers/spice.py

@@ -4,7 +4,7 @@
 
     Lexers for the Spice programming language.
 
-    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -40,7 +40,7 @@ class SpiceLexer(RegexLexer):
             (r'(f|p|type|struct|interface|enum|alias|operator)\b', Keyword.Declaration),
             (words(('if', 'else', 'switch', 'case', 'default', 'for', 'foreach', 'do',
                     'while', 'break', 'continue', 'fallthrough', 'return', 'assert',
-                    'unsafe', 'ext'), suffix=r'\b'), Keyword),
+                    'unsafe', 'ext', 'cast'), suffix=r'\b'), Keyword),
             (words(('const', 'signed', 'unsigned', 'inline', 'public', 'heap', 'compose'),
                    suffix=r'\b'), Keyword.Pseudo),
             (words(('new', 'yield', 'stash', 'pick', 'sync', 'class'), suffix=r'\b'),