Add files using upload-large-folder tool

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/agile.py

@@ -0,0 +1,25 @@
+"""
+    pygments.lexers.agile
+    ~~~~~~~~~~~~~~~~~~~~~
+
+    Just export lexer classes previously contained in this module.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+# ruff: noqa: F401
+
+from pygments.lexers.lisp import SchemeLexer
+from pygments.lexers.jvm import IokeLexer, ClojureLexer
+from pygments.lexers.python import PythonLexer, PythonConsoleLexer, \
+    PythonTracebackLexer, Python3Lexer, Python3TracebackLexer, DgLexer
+from pygments.lexers.ruby import RubyLexer, RubyConsoleLexer, FancyLexer
+from pygments.lexers.perl import PerlLexer, Perl6Lexer
+from pygments.lexers.d import CrocLexer, MiniDLexer
+from pygments.lexers.iolang import IoLexer
+from pygments.lexers.tcl import TclLexer
+from pygments.lexers.factor import FactorLexer
+from pygments.lexers.scripting import LuaLexer, MoonScriptLexer
+
+__all__ = []

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/arturo.py

@@ -0,0 +1,249 @@
+"""
+    pygments.lexers.arturo
+    ~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexer for the Arturo language.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import RegexLexer, bygroups, do_insertions, include, \
+    this, using, words
+from pygments.token import Comment, Error, Keyword, Name, Number, Operator, \
+    Punctuation, String, Text
+
+from pygments.util import ClassNotFound, get_bool_opt
+
+__all__ = ['ArturoLexer']
+
+
+class ArturoLexer(RegexLexer):
+    """
+    For Arturo source code.
+
+    See `Arturo's Github <https://github.com/arturo-lang/arturo>`_
+    and `Arturo's Website <https://arturo-lang.io/>`_.
+    """
+
+    name = 'Arturo'
+    aliases = ['arturo', 'art']
+    filenames = ['*.art']
+    url = 'https://arturo-lang.io/'
+    version_added = '2.14'
+
+    def __init__(self, **options):
+        self.handle_annotateds = get_bool_opt(options, 'handle_annotateds',
+                                              True)
+        RegexLexer.__init__(self, **options)
+
+    def handle_annotated_strings(self, match):
+        """Adds syntax from another languages inside annotated strings
+
+        match args:
+            1:open_string,
+            2:exclamation_mark,
+            3:lang_name,
+            4:space_or_newline,
+            5:code,
+            6:close_string
+        """
+        from pygments.lexers import get_lexer_by_name
+
+        # Header's section
+        yield match.start(1), String.Double,   match.group(1)
+        yield match.start(2), String.Interpol, match.group(2)
+        yield match.start(3), String.Interpol, match.group(3)
+        yield match.start(4), Text.Whitespace, match.group(4)
+
+        lexer = None
+        if self.handle_annotateds:
+            try:
+                lexer = get_lexer_by_name(match.group(3).strip())
+            except ClassNotFound:
+                pass
+        code = match.group(5)
+
+        if lexer is None:
+            yield match.group(5), String, code
+        else:
+            yield from do_insertions([], lexer.get_tokens_unprocessed(code))
+
+        yield match.start(6), String.Double, match.group(6)
+
+    tokens = {
+        'root': [
+            (r';.*?$', Comment.Single),
+            (r'^((\s#!)|(#!)).*?$', Comment.Hashbang),
+
+            # Constants
+            (words(('false', 'true', 'maybe'),      # boolean
+                   suffix=r'\b'), Name.Constant),
+            (words(('this', 'init'),                # class related keywords
+                   prefix=r'\b', suffix=r'\b\??:?'), Name.Builtin.Pseudo),
+            (r'`.`', String.Char),                  # character
+            (r'\\\w+\b\??:?', Name.Property),       # array index
+            (r'#\w+', Name.Constant),               # color
+            (r'\b[0-9]+\.[0-9]+', Number.Float),    # float
+            (r'\b[0-9]+', Number.Integer),          # integer
+            (r'\w+\b\??:', Name.Label),             # label
+            # Note: Literals can be labeled too
+            (r'\'(?:\w+\b\??:?)', Keyword.Declaration),  # literal
+            (r'\:\w+', Keyword.Type),               # type
+            # Note: Attributes can be labeled too
+            (r'\.\w+\??:?', Name.Attribute),        # attributes
+
+            # Switch structure
+            (r'(\()(.*?)(\)\?)',
+             bygroups(Punctuation, using(this), Punctuation)),
+
+            # Single Line Strings
+            (r'"',   String.Double, 'inside-simple-string'),
+            (r'»',   String.Single, 'inside-smart-string'),
+            (r'«««', String.Double, 'inside-safe-string'),
+            (r'\{\/', String.Single, 'inside-regex-string'),
+
+            # Multi Line Strings
+            (r'\{\:', String.Double, 'inside-curly-verb-string'),
+            (r'(\{)(\!)(\w+)(\s|\n)([\w\W]*?)(^\})', handle_annotated_strings),
+            (r'\{', String.Single, 'inside-curly-string'),
+            (r'\-{3,}', String.Single, 'inside-eof-string'),
+
+            include('builtin-functions'),
+
+            # Operators
+            (r'[()[\],]', Punctuation),
+            (words(('->', '==>', '|', '::', '@', '#',  # sugar syntax
+                    '$', '&', '!', '!!', './')), Name.Decorator),
+            (words(('<:', ':>', ':<', '>:', '<\\', '<>', '<', '>',
+                    'ø', '∞',
+                    '+', '-', '*', '~', '=', '^', '%', '/', '//',
+                    '==>', '<=>', '<==>',
+                    '=>>', '<<=>>', '<<==>>',
+                    '-->', '<->', '<-->',
+                    '=|', '|=', '-:', ':-',
+                    '_', '.', '..', '\\')), Operator),
+
+            (r'\b\w+', Name),
+            (r'\s+', Text.Whitespace),
+            (r'.+$', Error),
+        ],
+
+        'inside-interpol': [
+            (r'\|', String.Interpol, '#pop'),
+            (r'[^|]+', using(this)),
+        ],
+        'inside-template': [
+            (r'\|\|\>', String.Interpol, '#pop'),
+            (r'[^|]+', using(this)),
+        ],
+        'string-escape': [
+            (words(('\\\\', '\\n', '\\t', '\\"')), String.Escape),
+        ],
+
+        'inside-simple-string': [
+            include('string-escape'),
+            (r'\|', String.Interpol, 'inside-interpol'),        # Interpolation
+            (r'\<\|\|', String.Interpol, 'inside-template'),    # Templates
+            (r'"', String.Double, '#pop'),   # Closing Quote
+            (r'[^|"]+', String)              # String Content
+        ],
+        'inside-smart-string': [
+            include('string-escape'),
+            (r'\|', String.Interpol, 'inside-interpol'),        # Interpolation
+            (r'\<\|\|', String.Interpol, 'inside-template'),    # Templates
+            (r'\n', String.Single, '#pop'),  # Closing Quote
+            (r'[^|\n]+', String)             # String Content
+        ],
+        'inside-safe-string': [
+            include('string-escape'),
+            (r'\|', String.Interpol, 'inside-interpol'),        # Interpolation
+            (r'\<\|\|', String.Interpol, 'inside-template'),    # Templates
+            (r'»»»', String.Double, '#pop'),    # Closing Quote
+            (r'[^|»]+', String)                 # String Content
+        ],
+        'inside-regex-string': [
+            (r'\\[sSwWdDbBZApPxucItnvfr0]+', String.Escape),
+            (r'\|', String.Interpol, 'inside-interpol'),        # Interpolation
+            (r'\<\|\|', String.Interpol, 'inside-template'),    # Templates
+            (r'\/\}', String.Single, '#pop'),  # Closing Quote
+            (r'[^|\/]+', String.Regex),        # String Content
+        ],
+        'inside-curly-verb-string': [
+            include('string-escape'),
+            (r'\|', String.Interpol, 'inside-interpol'),        # Interpolation
+            (r'\<\|\|', String.Interpol, 'inside-template'),    # Templates
+            (r'\:\}', String.Double, '#pop'),  # Closing Quote
+            (r'[^|<:]+', String),              # String Content
+        ],
+        'inside-curly-string': [
+            include('string-escape'),
+            (r'\|', String.Interpol, 'inside-interpol'),        # Interpolation
+            (r'\<\|\|', String.Interpol, 'inside-template'),    # Templates
+            (r'\}', String.Single, '#pop'),   # Closing Quote
+            (r'[^|<}]+', String),             # String Content
+        ],
+        'inside-eof-string': [
+            include('string-escape'),
+            (r'\|', String.Interpol, 'inside-interpol'),        # Interpolation
+            (r'\<\|\|', String.Interpol, 'inside-template'),    # Templates
+            (r'\Z', String.Single, '#pop'),   # Closing Quote
+            (r'[^|<]+', String),              # String Content
+        ],
+
+        'builtin-functions': [
+            (words((
+                'all', 'and', 'any', 'ascii', 'attr', 'attribute',
+                'attributeLabel', 'binary', 'block' 'char', 'contains',
+                'database', 'date', 'dictionary', 'empty', 'equal', 'even',
+                'every', 'exists', 'false', 'floatin', 'function', 'greater',
+                'greaterOrEqual', 'if', 'in', 'inline', 'integer', 'is',
+                'key', 'label', 'leap', 'less', 'lessOrEqual', 'literal',
+                'logical', 'lower', 'nand', 'negative', 'nor', 'not',
+                'notEqual', 'null', 'numeric', 'odd', 'or', 'path',
+                'pathLabel', 'positive', 'prefix', 'prime', 'set', 'some',
+                'sorted', 'standalone', 'string', 'subset', 'suffix',
+                'superset', 'ymbol', 'true', 'try', 'type', 'unless', 'upper',
+                'when', 'whitespace', 'word', 'xnor', 'xor', 'zero',
+            ), prefix=r'\b', suffix=r'\b\?'), Name.Builtin),
+            (words((
+                'abs', 'acos', 'acosh', 'acsec', 'acsech', 'actan', 'actanh',
+                'add', 'after', 'alphabet', 'and', 'angle', 'append', 'arg',
+                'args', 'arity', 'array', 'as', 'asec', 'asech', 'asin',
+                'asinh', 'atan', 'atan2', 'atanh', 'attr', 'attrs', 'average',
+                'before', 'benchmark', 'blend', 'break', 'builtins1',
+                'builtins2', 'call', 'capitalize', 'case', 'ceil', 'chop',
+                'chunk', 'clear', 'close', 'cluster', 'color', 'combine',
+                'conj', 'continue', 'copy', 'cos', 'cosh', 'couple', 'csec',
+                'csech', 'ctan', 'ctanh', 'cursor', 'darken', 'dec', 'decode',
+                'decouple', 'define', 'delete', 'desaturate', 'deviation',
+                'dictionary', 'difference', 'digest', 'digits', 'div', 'do',
+                'download', 'drop', 'dup', 'e', 'else', 'empty', 'encode',
+                'ensure', 'env', 'epsilon', 'escape', 'execute', 'exit', 'exp',
+                'extend', 'extract', 'factors', 'false', 'fdiv', 'filter',
+                'first', 'flatten', 'floor', 'fold', 'from', 'function',
+                'gamma', 'gcd', 'get', 'goto', 'hash', 'help', 'hypot', 'if',
+                'in', 'inc', 'indent', 'index', 'infinity', 'info', 'input',
+                'insert', 'inspect', 'intersection', 'invert', 'join', 'keys',
+                'kurtosis', 'last', 'let', 'levenshtein', 'lighten', 'list',
+                'ln', 'log', 'loop', 'lower', 'mail', 'map', 'match', 'max',
+                'maybe', 'median', 'min', 'mod', 'module', 'mul', 'nand',
+                'neg', 'new', 'nor', 'normalize', 'not', 'now', 'null', 'open',
+                'or', 'outdent', 'pad', 'panic', 'path', 'pause',
+                'permissions', 'permutate', 'pi', 'pop', 'pow', 'powerset',
+                'powmod', 'prefix', 'print', 'prints', 'process', 'product',
+                'query', 'random', 'range', 'read', 'relative', 'remove',
+                'rename', 'render', 'repeat', 'replace', 'request', 'return',
+                'reverse', 'round', 'sample', 'saturate', 'script', 'sec',
+                'sech', 'select', 'serve', 'set', 'shl', 'shr', 'shuffle',
+                'sin', 'sinh', 'size', 'skewness', 'slice', 'sort', 'split',
+                'sqrt', 'squeeze', 'stack', 'strip', 'sub', 'suffix', 'sum',
+                'switch', 'symbols', 'symlink', 'sys', 'take', 'tan', 'tanh',
+                'terminal', 'to', 'true', 'truncate', 'try', 'type', 'union',
+                'unique', 'unless', 'until', 'unzip', 'upper', 'values', 'var',
+                'variance', 'volume', 'webview', 'while', 'with', 'wordwrap',
+                'write', 'xnor', 'xor', 'zip'
+            ), prefix=r'\b', suffix=r'\b'), Name.Builtin)
+        ],
+
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/bqn.py

@@ -0,0 +1,112 @@
+"""
+    pygments.lexers.bqn
+    ~~~~~~~~~~~~~~~~~~~
+
+    Lexer for BQN.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import RegexLexer
+from pygments.token import Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation, Whitespace
+
+__all__ = ['BQNLexer']
+
+
+class BQNLexer(RegexLexer):
+    """
+    A simple BQN lexer.
+    """
+    name = 'BQN'
+    url = 'https://mlochbaum.github.io/BQN/index.html'
+    aliases = ['bqn']
+    filenames = ['*.bqn']
+    mimetypes = []
+    version_added = '2.16'
+
+    # An inter_word_char. Necessary because \w matches all alphanumeric
+    # Unicode characters, including ones (e.g., 𝕊) that BQN treats special.
+    _iwc = r'((?=[^𝕎𝕏𝔽𝔾𝕊𝕨𝕩𝕗𝕘𝕤𝕣])\w)'
+
+    tokens = {
+        'root': [
+            # Whitespace
+            # ==========
+            (r'\s+', Whitespace),
+            #
+            # Comment
+            # =======
+            # '#' is a comment that continues to the end of the line
+            (r'#.*$', Comment.Single),
+            #
+            # Strings
+            # =======
+            (r'\'((\'\')|[^\'])*\'', String.Single),
+            (r'"(("")|[^"])*"', String.Double),
+            #
+            # Null Character
+            # ==============
+            # Literal representation of the null character
+            (r'@', String.Symbol),
+            #
+            # Punctuation
+            # ===========
+            # This token type is used for diamond, commas
+            # and  array and list brackets and strand syntax
+            (r'[\.⋄,\[\]⟨⟩‿]', Punctuation),
+            #
+            # Expression Grouping
+            # ===================
+            # Since this token type is important in BQN, it is not included in
+            # the punctuation token type but rather in the following one
+            (r'[\(\)]', String.Regex),
+            #
+            # Numbers
+            # =======
+            # Includes the numeric literals and the Nothing character
+            (r'¯?[0-9](([0-9]|_)*\.?([0-9]|_)+|([0-9]|_)*)([Ee][¯]?([0-9]|_)+)?|¯|∞|π|·', Number),
+            #
+            # Variables
+            # =========
+            (r'[a-z]' + _iwc + r'*', Name.Variable),
+            #
+            # 2-Modifiers
+            # ===========
+            # Needs to come before the 1-modifiers due to _𝕣 and _𝕣_
+            (r'[∘○⊸⟜⌾⊘◶⎉⚇⍟⎊]', Name.Property),
+            (r'_(𝕣|[a-zA-Z0-9]+)_', Name.Property),
+            #
+            # 1-Modifiers
+            # ===========
+            (r'[˙˜˘¨⌜⁼´˝`𝕣]', Name.Attribute),
+            (r'_(𝕣|[a-zA-Z0-9]+)', Name.Attribute),
+            #
+            # Functions
+            # =========
+            # The monadic or dyadic function primitives and function
+            # operands and arguments, along with function self-reference
+            (r'[+\-×÷\⋆√⌊⌈∧∨¬|≤<>≥=≠≡≢⊣⊢⥊∾≍⋈↑↓↕«»⌽⍉/⍋⍒⊏⊑⊐⊒∊⍷⊔!𝕎𝕏𝔽𝔾𝕊]',
+             Operator),
+            (r'[A-Z]' + _iwc + r'*|•' + _iwc + r'+', Operator),
+            #
+            # Constant
+            # ========
+            (r'˙', Name.Constant),
+            #
+            # Define/Export/Change
+            # ====================
+            (r'[←↩⇐]', Keyword.Declaration),
+            #
+            # Blocks
+            # ======
+            (r'[{}]', Keyword.Type),
+            #
+            # Extra characters
+            # ================
+            (r'[;:?𝕨𝕩𝕗𝕘𝕤]', Name.Entity),
+            #
+
+        ],
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/configs.py

@@ -0,0 +1,1433 @@
+"""
+    pygments.lexers.configs
+    ~~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexers for configuration file formats.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import ExtendedRegexLexer, RegexLexer, default, words, \
+    bygroups, include, using, line_re
+from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation, Whitespace, Literal, Error, Generic
+from pygments.lexers.shell import BashLexer
+from pygments.lexers.data import JsonLexer
+
+__all__ = ['IniLexer', 'SystemdLexer', 'DesktopLexer', 'RegeditLexer', 'PropertiesLexer',
+           'KconfigLexer', 'Cfengine3Lexer', 'ApacheConfLexer', 'SquidConfLexer',
+           'NginxConfLexer', 'LighttpdConfLexer', 'DockerLexer',
+           'TerraformLexer', 'TermcapLexer', 'TerminfoLexer',
+           'PkgConfigLexer', 'PacmanConfLexer', 'AugeasLexer', 'TOMLLexer',
+           'NestedTextLexer', 'SingularityLexer', 'UnixConfigLexer']
+
+
+class IniLexer(RegexLexer):
+    """
+    Lexer for configuration files in INI style.
+    """
+
+    name = 'INI'
+    aliases = ['ini', 'cfg', 'dosini']
+    filenames = [
+        '*.ini', '*.cfg', '*.inf', '.editorconfig',
+    ]
+    mimetypes = ['text/x-ini', 'text/inf']
+    url = 'https://en.wikipedia.org/wiki/INI_file'
+    version_added = ''
+
+    tokens = {
+        'root': [
+            (r'\s+', Whitespace),
+            (r'[;#].*', Comment.Single),
+            (r'(\[.*?\])([ \t]*)$', bygroups(Keyword, Whitespace)),
+            (r'''(.*?)([ \t]*)([=:])([ \t]*)(["'])''',
+             bygroups(Name.Attribute, Whitespace, Operator, Whitespace, String),
+             "quoted_value"),
+            (r'(.*?)([ \t]*)([=:])([ \t]*)([^;#\n]*)(\\)(\s+)',
+             bygroups(Name.Attribute, Whitespace, Operator, Whitespace, String,
+                      Text, Whitespace),
+             "value"),
+            (r'(.*?)([ \t]*)([=:])([ \t]*)([^ ;#\n]*(?: +[^ ;#\n]+)*)',
+             bygroups(Name.Attribute, Whitespace, Operator, Whitespace, String)),
+            # standalone option, supported by some INI parsers
+            (r'(.+?)$', Name.Attribute),
+        ],
+        'quoted_value': [
+            (r'''([^"'\n]*)(["'])(\s*)''',
+             bygroups(String, String, Whitespace), "#pop"),
+            (r'[;#].*', Comment.Single),
+            (r'$', String, "#pop"),
+        ],
+        'value': [     # line continuation
+            (r'\s+', Whitespace),
+            (r'(\s*)(.*)(\\)([ \t]*)',
+             bygroups(Whitespace, String, Text, Whitespace)),
+            (r'.*$', String, "#pop"),
+        ],
+    }
+
+    def analyse_text(text):
+        npos = text.find('\n')
+        if npos < 3:
+            return False
+        if text[0] == '[' and text[npos-1] == ']':
+            return 0.8
+        return False
+
+
+class DesktopLexer(RegexLexer):
+    """
+    Lexer for .desktop files.
+    """
+
+    name = 'Desktop file'
+    url = "https://specifications.freedesktop.org/desktop-entry-spec/desktop-entry-spec-latest.html"
+    aliases = ['desktop']
+    filenames = ['*.desktop']
+    mimetypes = ['application/x-desktop']
+    version_added = '2.16'
+
+    tokens = {
+        'root': [
+            (r'^[ \t]*\n', Whitespace),
+            (r'^(#.*)(\n)', bygroups(Comment.Single, Whitespace)),
+            (r'(\[[^\]\n]+\])(\n)', bygroups(Keyword, Whitespace)),
+            (r'([-A-Za-z0-9]+)(\[[^\] \t=]+\])?([ \t]*)(=)([ \t]*)([^\n]*)([ \t\n]*\n)',
+             bygroups(Name.Attribute, Name.Namespace, Whitespace, Operator, Whitespace, String, Whitespace)),
+        ],
+    }
+
+    def analyse_text(text):
+        if text.startswith("[Desktop Entry]"):
+            return 1.0
+        if re.search(r"^\[Desktop Entry\][ \t]*$", text[:500], re.MULTILINE) is not None:
+            return 0.9
+        return 0.0
+
+
+class SystemdLexer(RegexLexer):
+    """
+    Lexer for systemd unit files.
+    """
+
+    name = 'Systemd'
+    url = "https://www.freedesktop.org/software/systemd/man/systemd.syntax.html"
+    aliases = ['systemd']
+    filenames = [
+        '*.service', '*.socket', '*.device', '*.mount', '*.automount',
+        '*.swap', '*.target', '*.path', '*.timer', '*.slice', '*.scope',
+    ]
+    version_added = '2.16'
+
+    tokens = {
+        'root': [
+            (r'^[ \t]*\n', Whitespace),
+            (r'^([;#].*)(\n)', bygroups(Comment.Single, Whitespace)),
+            (r'(\[[^\]\n]+\])(\n)', bygroups(Keyword, Whitespace)),
+            (r'([^=]+)([ \t]*)(=)([ \t]*)([^\n]*)(\\)(\n)',
+             bygroups(Name.Attribute, Whitespace, Operator, Whitespace, String,
+                      Text, Whitespace),
+             "value"),
+            (r'([^=]+)([ \t]*)(=)([ \t]*)([^\n]*)(\n)',
+             bygroups(Name.Attribute, Whitespace, Operator, Whitespace, String, Whitespace)),
+        ],
+        'value': [
+            # line continuation
+            (r'^([;#].*)(\n)', bygroups(Comment.Single, Whitespace)),
+            (r'([ \t]*)([^\n]*)(\\)(\n)',
+             bygroups(Whitespace, String, Text, Whitespace)),
+            (r'([ \t]*)([^\n]*)(\n)',
+             bygroups(Whitespace, String, Whitespace), "#pop"),
+        ],
+    }
+
+    def analyse_text(text):
+        if text.startswith("[Unit]"):
+            return 1.0
+        if re.search(r"^\[Unit\][ \t]*$", text[:500], re.MULTILINE) is not None:
+            return 0.9
+        return 0.0
+
+
+class RegeditLexer(RegexLexer):
+    """
+    Lexer for Windows Registry files produced by regedit.
+    """
+
+    name = 'reg'
+    url = 'http://en.wikipedia.org/wiki/Windows_Registry#.REG_files'
+    aliases = ['registry']
+    filenames = ['*.reg']
+    mimetypes = ['text/x-windows-registry']
+    version_added = '1.6'
+
+    tokens = {
+        'root': [
+            (r'Windows Registry Editor.*', Text),
+            (r'\s+', Whitespace),
+            (r'[;#].*', Comment.Single),
+            (r'(\[)(-?)(HKEY_[A-Z_]+)(.*?\])$',
+             bygroups(Keyword, Operator, Name.Builtin, Keyword)),
+            # String keys, which obey somewhat normal escaping
+            (r'("(?:\\"|\\\\|[^"])+")([ \t]*)(=)([ \t]*)',
+             bygroups(Name.Attribute, Whitespace, Operator, Whitespace),
+             'value'),
+            # Bare keys (includes @)
+            (r'(.*?)([ \t]*)(=)([ \t]*)',
+             bygroups(Name.Attribute, Whitespace, Operator, Whitespace),
+             'value'),
+        ],
+        'value': [
+            (r'-', Operator, '#pop'),  # delete value
+            (r'(dword|hex(?:\([0-9a-fA-F]\))?)(:)([0-9a-fA-F,]+)',
+             bygroups(Name.Variable, Punctuation, Number), '#pop'),
+            # As far as I know, .reg files do not support line continuation.
+            (r'.+', String, '#pop'),
+            default('#pop'),
+        ]
+    }
+
+    def analyse_text(text):
+        return text.startswith('Windows Registry Editor')
+
+
+class PropertiesLexer(RegexLexer):
+    """
+    Lexer for configuration files in Java's properties format.
+
+    Note: trailing whitespace counts as part of the value as per spec
+    """
+
+    name = 'Properties'
+    aliases = ['properties', 'jproperties']
+    filenames = ['*.properties']
+    mimetypes = ['text/x-java-properties']
+    url = 'https://en.wikipedia.org/wiki/.properties'
+    version_added = '1.4'
+
+    tokens = {
+        'root': [
+            # comments
+            (r'[!#].*|/{2}.*', Comment.Single),
+            # ending a comment or whitespace-only line
+            (r'\n', Whitespace),
+            # eat whitespace at the beginning of a line
+            (r'^[^\S\n]+', Whitespace),
+            # start lexing a key
+            default('key'),
+        ],
+        'key': [
+            # non-escaped key characters
+            (r'[^\\:=\s]+', Name.Attribute),
+            # escapes
+            include('escapes'),
+            # separator is the first non-escaped whitespace or colon or '=' on the line;
+            # if it's whitespace, = and : are gobbled after it
+            (r'([^\S\n]*)([:=])([^\S\n]*)',
+             bygroups(Whitespace, Operator, Whitespace),
+             ('#pop', 'value')),
+            (r'[^\S\n]+', Whitespace, ('#pop', 'value')),
+            # maybe we got no value after all
+            (r'\n', Whitespace, '#pop'),
+        ],
+        'value': [
+            # non-escaped value characters
+            (r'[^\\\n]+', String),
+            # escapes
+            include('escapes'),
+            # end the value on an unescaped newline
+            (r'\n', Whitespace, '#pop'),
+        ],
+        'escapes': [
+            # line continuations; these gobble whitespace at the beginning of the next line
+            (r'(\\\n)([^\S\n]*)', bygroups(String.Escape, Whitespace)),
+            # other escapes
+            (r'\\(.|\n)', String.Escape),
+        ],
+    }
+
+
+def _rx_indent(level):
+    # Kconfig *always* interprets a tab as 8 spaces, so this is the default.
+    # Edit this if you are in an environment where KconfigLexer gets expanded
+    # input (tabs expanded to spaces) and the expansion tab width is != 8,
+    # e.g. in connection with Trac (trac.ini, [mimeviewer], tab_width).
+    # Value range here is 2 <= {tab_width} <= 8.
+    tab_width = 8
+    # Regex matching a given indentation {level}, assuming that indentation is
+    # a multiple of {tab_width}. In other cases there might be problems.
+    if tab_width == 2:
+        space_repeat = '+'
+    else:
+        space_repeat = '{1,%d}' % (tab_width - 1)
+    if level == 1:
+        level_repeat = ''
+    else:
+        level_repeat = f'{{{level}}}'
+    return rf'(?:\t| {space_repeat}\t| {{{tab_width}}}){level_repeat}.*\n'
+
+
+class KconfigLexer(RegexLexer):
+    """
+    For Linux-style Kconfig files.
+    """
+
+    name = 'Kconfig'
+    aliases = ['kconfig', 'menuconfig', 'linux-config', 'kernel-config']
+    version_added = '1.6'
+    # Adjust this if new kconfig file names appear in your environment
+    filenames = ['Kconfig*', '*Config.in*', 'external.in*',
+                 'standard-modules.in']
+    mimetypes = ['text/x-kconfig']
+    url = 'https://www.kernel.org/doc/html/latest/kbuild/kconfig-language.html'
+
+    # No re.MULTILINE, indentation-aware help text needs line-by-line handling
+    flags = 0
+
+    def call_indent(level):
+        # If indentation >= {level} is detected, enter state 'indent{level}'
+        return (_rx_indent(level), String.Doc, f'indent{level}')
+
+    def do_indent(level):
+        # Print paragraphs of indentation level >= {level} as String.Doc,
+        # ignoring blank lines. Then return to 'root' state.
+        return [
+            (_rx_indent(level), String.Doc),
+            (r'\s*\n', Text),
+            default('#pop:2')
+        ]
+
+    tokens = {
+        'root': [
+            (r'\s+', Whitespace),
+            (r'#.*?\n', Comment.Single),
+            (words((
+                'mainmenu', 'config', 'menuconfig', 'choice', 'endchoice',
+                'comment', 'menu', 'endmenu', 'visible if', 'if', 'endif',
+                'source', 'prompt', 'select', 'depends on', 'default',
+                'range', 'option'), suffix=r'\b'),
+             Keyword),
+            (r'(---help---|help)[\t ]*\n', Keyword, 'help'),
+            (r'(bool|tristate|string|hex|int|defconfig_list|modules|env)\b',
+             Name.Builtin),
+            (r'[!=&|]', Operator),
+            (r'[()]', Punctuation),
+            (r'[0-9]+', Number.Integer),
+            (r"'(''|[^'])*'", String.Single),
+            (r'"(""|[^"])*"', String.Double),
+            (r'\S+', Text),
+        ],
+        # Help text is indented, multi-line and ends when a lower indentation
+        # level is detected.
+        'help': [
+            # Skip blank lines after help token, if any
+            (r'\s*\n', Text),
+            # Determine the first help line's indentation level heuristically(!).
+            # Attention: this is not perfect, but works for 99% of "normal"
+            # indentation schemes up to a max. indentation level of 7.
+            call_indent(7),
+            call_indent(6),
+            call_indent(5),
+            call_indent(4),
+            call_indent(3),
+            call_indent(2),
+            call_indent(1),
+            default('#pop'),  # for incomplete help sections without text
+        ],
+        # Handle text for indentation levels 7 to 1
+        'indent7': do_indent(7),
+        'indent6': do_indent(6),
+        'indent5': do_indent(5),
+        'indent4': do_indent(4),
+        'indent3': do_indent(3),
+        'indent2': do_indent(2),
+        'indent1': do_indent(1),
+    }
+
+
+class Cfengine3Lexer(RegexLexer):
+    """
+    Lexer for CFEngine3 policy files.
+    """
+
+    name = 'CFEngine3'
+    url = 'http://cfengine.org'
+    aliases = ['cfengine3', 'cf3']
+    filenames = ['*.cf']
+    mimetypes = []
+    version_added = '1.5'
+
+    tokens = {
+        'root': [
+            (r'#.*?\n', Comment),
+            (r'(body)(\s+)(\S+)(\s+)(control)',
+             bygroups(Keyword, Whitespace, Keyword, Whitespace, Keyword)),
+            (r'(body|bundle)(\s+)(\S+)(\s+)(\w+)(\()',
+             bygroups(Keyword, Whitespace, Keyword, Whitespace, Name.Function, Punctuation),
+             'arglist'),
+            (r'(body|bundle)(\s+)(\S+)(\s+)(\w+)',
+             bygroups(Keyword, Whitespace, Keyword, Whitespace, Name.Function)),
+            (r'(")([^"]+)(")(\s+)(string|slist|int|real)(\s*)(=>)(\s*)',
+             bygroups(Punctuation, Name.Variable, Punctuation,
+                      Whitespace, Keyword.Type, Whitespace, Operator, Whitespace)),
+            (r'(\S+)(\s*)(=>)(\s*)',
+             bygroups(Keyword.Reserved, Whitespace, Operator, Text)),
+            (r'"', String, 'string'),
+            (r'(\w+)(\()', bygroups(Name.Function, Punctuation)),
+            (r'([\w.!&|()]+)(::)', bygroups(Name.Class, Punctuation)),
+            (r'(\w+)(:)', bygroups(Keyword.Declaration, Punctuation)),
+            (r'@[{(][^)}]+[})]', Name.Variable),
+            (r'[(){},;]', Punctuation),
+            (r'=>', Operator),
+            (r'->', Operator),
+            (r'\d+\.\d+', Number.Float),
+            (r'\d+', Number.Integer),
+            (r'\w+', Name.Function),
+            (r'\s+', Whitespace),
+        ],
+        'string': [
+            (r'\$[{(]', String.Interpol, 'interpol'),
+            (r'\\.', String.Escape),
+            (r'"', String, '#pop'),
+            (r'\n', String),
+            (r'.', String),
+        ],
+        'interpol': [
+            (r'\$[{(]', String.Interpol, '#push'),
+            (r'[})]', String.Interpol, '#pop'),
+            (r'[^${()}]+', String.Interpol),
+        ],
+        'arglist': [
+            (r'\)', Punctuation, '#pop'),
+            (r',', Punctuation),
+            (r'\w+', Name.Variable),
+            (r'\s+', Whitespace),
+        ],
+    }
+
+
+class ApacheConfLexer(RegexLexer):
+    """
+    Lexer for configuration files following the Apache config file
+    format.
+    """
+
+    name = 'ApacheConf'
+    aliases = ['apacheconf', 'aconf', 'apache']
+    filenames = ['.htaccess', 'apache.conf', 'apache2.conf']
+    mimetypes = ['text/x-apacheconf']
+    url = 'https://httpd.apache.org/docs/current/configuring.html'
+    version_added = '0.6'
+    flags = re.MULTILINE | re.IGNORECASE
+
+    tokens = {
+        'root': [
+            (r'\s+', Whitespace),
+            (r'#(.*\\\n)+.*$|(#.*?)$', Comment),
+            (r'(<[^\s>/][^\s>]*)(?:(\s+)(.*))?(>)',
+             bygroups(Name.Tag, Whitespace, String, Name.Tag)),
+            (r'(</[^\s>]+)(>)',
+             bygroups(Name.Tag, Name.Tag)),
+            (r'[a-z]\w*', Name.Builtin, 'value'),
+            (r'\.+', Text),
+        ],
+        'value': [
+            (r'\\\n', Text),
+            (r'\n+', Whitespace, '#pop'),
+            (r'\\', Text),
+            (r'[^\S\n]+', Whitespace),
+            (r'\d+\.\d+\.\d+\.\d+(?:/\d+)?', Number),
+            (r'\d+', Number),
+            (r'/([*a-z0-9][*\w./-]+)', String.Other),
+            (r'(on|off|none|any|all|double|email|dns|min|minimal|'
+             r'os|productonly|full|emerg|alert|crit|error|warn|'
+             r'notice|info|debug|registry|script|inetd|standalone|'
+             r'user|group)\b', Keyword),
+            (r'"([^"\\]*(?:\\(.|\n)[^"\\]*)*)"', String.Double),
+            (r'[^\s"\\]+', Text)
+        ],
+    }
+
+
+class SquidConfLexer(RegexLexer):
+    """
+    Lexer for squid configuration files.
+    """
+
+    name = 'SquidConf'
+    url = 'http://www.squid-cache.org/'
+    aliases = ['squidconf', 'squid.conf', 'squid']
+    filenames = ['squid.conf']
+    mimetypes = ['text/x-squidconf']
+    version_added = '0.9'
+    flags = re.IGNORECASE
+
+    keywords = (
+        "access_log", "acl", "always_direct", "announce_host",
+        "announce_period", "announce_port", "announce_to", "anonymize_headers",
+        "append_domain", "as_whois_server", "auth_param_basic",
+        "authenticate_children", "authenticate_program", "authenticate_ttl",
+        "broken_posts", "buffered_logs", "cache_access_log", "cache_announce",
+        "cache_dir", "cache_dns_program", "cache_effective_group",
+        "cache_effective_user", "cache_host", "cache_host_acl",
+        "cache_host_domain", "cache_log", "cache_mem", "cache_mem_high",
+        "cache_mem_low", "cache_mgr", "cachemgr_passwd", "cache_peer",
+        "cache_peer_access", "cache_replacement_policy", "cache_stoplist",
+        "cache_stoplist_pattern", "cache_store_log", "cache_swap",
+        "cache_swap_high", "cache_swap_log", "cache_swap_low", "client_db",
+        "client_lifetime", "client_netmask", "connect_timeout", "coredump_dir",
+        "dead_peer_timeout", "debug_options", "delay_access", "delay_class",
+        "delay_initial_bucket_level", "delay_parameters", "delay_pools",
+        "deny_info", "dns_children", "dns_defnames", "dns_nameservers",
+        "dns_testnames", "emulate_httpd_log", "err_html_text",
+        "fake_user_agent", "firewall_ip", "forwarded_for", "forward_snmpd_port",
+        "fqdncache_size", "ftpget_options", "ftpget_program", "ftp_list_width",
+        "ftp_passive", "ftp_user", "half_closed_clients", "header_access",
+        "header_replace", "hierarchy_stoplist", "high_response_time_warning",
+        "high_page_fault_warning", "hosts_file", "htcp_port", "http_access",
+        "http_anonymizer", "httpd_accel", "httpd_accel_host",
+        "httpd_accel_port", "httpd_accel_uses_host_header",
+        "httpd_accel_with_proxy", "http_port", "http_reply_access",
+        "icp_access", "icp_hit_stale", "icp_port", "icp_query_timeout",
+        "ident_lookup", "ident_lookup_access", "ident_timeout",
+        "incoming_http_average", "incoming_icp_average", "inside_firewall",
+        "ipcache_high", "ipcache_low", "ipcache_size", "local_domain",
+        "local_ip", "logfile_rotate", "log_fqdn", "log_icp_queries",
+        "log_mime_hdrs", "maximum_object_size", "maximum_single_addr_tries",
+        "mcast_groups", "mcast_icp_query_timeout", "mcast_miss_addr",
+        "mcast_miss_encode_key", "mcast_miss_port", "memory_pools",
+        "memory_pools_limit", "memory_replacement_policy", "mime_table",
+        "min_http_poll_cnt", "min_icp_poll_cnt", "minimum_direct_hops",
+        "minimum_object_size", "minimum_retry_timeout", "miss_access",
+        "negative_dns_ttl", "negative_ttl", "neighbor_timeout",
+        "neighbor_type_domain", "netdb_high", "netdb_low", "netdb_ping_period",
+        "netdb_ping_rate", "never_direct", "no_cache", "passthrough_proxy",
+        "pconn_timeout", "pid_filename", "pinger_program", "positive_dns_ttl",
+        "prefer_direct", "proxy_auth", "proxy_auth_realm", "query_icmp",
+        "quick_abort", "quick_abort_max", "quick_abort_min",
+        "quick_abort_pct", "range_offset_limit", "read_timeout",
+        "redirect_children", "redirect_program",
+        "redirect_rewrites_host_header", "reference_age",
+        "refresh_pattern", "reload_into_ims", "request_body_max_size",
+        "request_size", "request_timeout", "shutdown_lifetime",
+        "single_parent_bypass", "siteselect_timeout", "snmp_access",
+        "snmp_incoming_address", "snmp_port", "source_ping", "ssl_proxy",
+        "store_avg_object_size", "store_objects_per_bucket",
+        "strip_query_terms", "swap_level1_dirs", "swap_level2_dirs",
+        "tcp_incoming_address", "tcp_outgoing_address", "tcp_recv_bufsize",
+        "test_reachability", "udp_hit_obj", "udp_hit_obj_size",
+        "udp_incoming_address", "udp_outgoing_address", "unique_hostname",
+        "unlinkd_program", "uri_whitespace", "useragent_log",
+        "visible_hostname", "wais_relay", "wais_relay_host", "wais_relay_port",
+    )
+
+    opts = (
+        "proxy-only", "weight", "ttl", "no-query", "default", "round-robin",
+        "multicast-responder", "on", "off", "all", "deny", "allow", "via",
+        "parent", "no-digest", "heap", "lru", "realm", "children", "q1", "q2",
+        "credentialsttl", "none", "disable", "offline_toggle", "diskd",
+    )
+
+    actions = (
+        "shutdown", "info", "parameter", "server_list", "client_list",
+        r'squid.conf',
+    )
+
+    actions_stats = (
+        "objects", "vm_objects", "utilization", "ipcache", "fqdncache", "dns",
+        "redirector", "io", "reply_headers", "filedescriptors", "netdb",
+    )
+
+    actions_log = ("status", "enable", "disable", "clear")
+
+    acls = (
+        "url_regex", "urlpath_regex", "referer_regex", "port", "proto",
+        "req_mime_type", "rep_mime_type", "method", "browser", "user", "src",
+        "dst", "time", "dstdomain", "ident", "snmp_community",
+    )
+
+    ipv4_group = r'(\d+|0x[0-9a-f]+)'
+    ipv4 = rf'({ipv4_group}(\.{ipv4_group}){{3}})'
+    ipv6_group = r'([0-9a-f]{0,4})'
+    ipv6 = rf'({ipv6_group}(:{ipv6_group}){{1,7}})'
+    bare_ip = rf'({ipv4}|{ipv6})'
+    # XXX: /integer is a subnet mark, but what is /IP ?
+    # There is no test where it is used.
+    ip = rf'{bare_ip}(/({bare_ip}|\d+))?'
+
+    tokens = {
+        'root': [
+            (r'\s+', Whitespace),
+            (r'#', Comment, 'comment'),
+            (words(keywords, prefix=r'\b', suffix=r'\b'), Keyword),
+            (words(opts, prefix=r'\b', suffix=r'\b'), Name.Constant),
+            # Actions
+            (words(actions, prefix=r'\b', suffix=r'\b'), String),
+            (words(actions_stats, prefix=r'stats/', suffix=r'\b'), String),
+            (words(actions_log, prefix=r'log/', suffix=r'='), String),
+            (words(acls, prefix=r'\b', suffix=r'\b'), Keyword),
+            (ip, Number.Float),
+            (r'(?:\b\d+\b(?:-\b\d+|%)?)', Number),
+            (r'\S+', Text),
+        ],
+        'comment': [
+            (r'\s*TAG:.*', String.Escape, '#pop'),
+            (r'.+', Comment, '#pop'),
+            default('#pop'),
+        ],
+    }
+
+
+class NginxConfLexer(RegexLexer):
+    """
+    Lexer for Nginx configuration files.
+    """
+    name = 'Nginx configuration file'
+    url = 'http://nginx.net/'
+    aliases = ['nginx']
+    filenames = ['nginx.conf']
+    mimetypes = ['text/x-nginx-conf']
+    version_added = '0.11'
+
+    tokens = {
+        'root': [
+            (r'(include)(\s+)([^\s;]+)', bygroups(Keyword, Whitespace, Name)),
+            (r'[^\s;#]+', Keyword, 'stmt'),
+            include('base'),
+        ],
+        'block': [
+            (r'\}', Punctuation, '#pop:2'),
+            (r'[^\s;#]+', Keyword.Namespace, 'stmt'),
+            include('base'),
+        ],
+        'stmt': [
+            (r'\{', Punctuation, 'block'),
+            (r';', Punctuation, '#pop'),
+            include('base'),
+        ],
+        'base': [
+            (r'#.*\n', Comment.Single),
+            (r'on|off', Name.Constant),
+            (r'\$[^\s;#()]+', Name.Variable),
+            (r'([a-z0-9.-]+)(:)([0-9]+)',
+             bygroups(Name, Punctuation, Number.Integer)),
+            (r'[a-z-]+/[a-z-+]+', String),  # mimetype
+            # (r'[a-zA-Z._-]+', Keyword),
+            (r'[0-9]+[km]?\b', Number.Integer),
+            (r'(~)(\s*)([^\s{]+)', bygroups(Punctuation, Whitespace, String.Regex)),
+            (r'[:=~]', Punctuation),
+            (r'[^\s;#{}$]+', String),  # catch all
+            (r'/[^\s;#]*', Name),  # pathname
+            (r'\s+', Whitespace),
+            (r'[$;]', Text),  # leftover characters
+        ],
+    }
+
+
+class LighttpdConfLexer(RegexLexer):
+    """
+    Lexer for Lighttpd configuration files.
+    """
+    name = 'Lighttpd configuration file'
+    url = 'http://lighttpd.net/'
+    aliases = ['lighttpd', 'lighty']
+    filenames = ['lighttpd.conf']
+    mimetypes = ['text/x-lighttpd-conf']
+    version_added = '0.11'
+
+    tokens = {
+        'root': [
+            (r'#.*\n', Comment.Single),
+            (r'/\S*', Name),  # pathname
+            (r'[a-zA-Z._-]+', Keyword),
+            (r'\d+\.\d+\.\d+\.\d+(?:/\d+)?', Number),
+            (r'[0-9]+', Number),
+            (r'=>|=~|\+=|==|=|\+', Operator),
+            (r'\$[A-Z]+', Name.Builtin),
+            (r'[(){}\[\],]', Punctuation),
+            (r'"([^"\\]*(?:\\.[^"\\]*)*)"', String.Double),
+            (r'\s+', Whitespace),
+        ],
+
+    }
+
+
+class DockerLexer(RegexLexer):
+    """
+    Lexer for Docker configuration files.
+    """
+    name = 'Docker'
+    url = 'http://docker.io'
+    aliases = ['docker', 'dockerfile']
+    filenames = ['Dockerfile', '*.docker']
+    mimetypes = ['text/x-dockerfile-config']
+    version_added = '2.0'
+
+    _keywords = (r'(?:MAINTAINER|EXPOSE|WORKDIR|USER|STOPSIGNAL)')
+    _bash_keywords = (r'(?:RUN|CMD|ENTRYPOINT|ENV|ARG|LABEL|ADD|COPY)')
+    _lb = r'(?:\s*\\?\s*)'  # dockerfile line break regex
+    flags = re.IGNORECASE | re.MULTILINE
+
+    tokens = {
+        'root': [
+            (r'#.*', Comment),
+            (r'(FROM)([ \t]*)(\S*)([ \t]*)(?:(AS)([ \t]*)(\S*))?',
+             bygroups(Keyword, Whitespace, String, Whitespace, Keyword, Whitespace, String)),
+            (rf'(ONBUILD)(\s+)({_lb})', bygroups(Keyword, Whitespace, using(BashLexer))),
+            (rf'(HEALTHCHECK)(\s+)(({_lb}--\w+=\w+{_lb})*)',
+                bygroups(Keyword, Whitespace, using(BashLexer))),
+            (rf'(VOLUME|ENTRYPOINT|CMD|SHELL)(\s+)({_lb})(\[.*?\])',
+                bygroups(Keyword, Whitespace, using(BashLexer), using(JsonLexer))),
+            (rf'(LABEL|ENV|ARG)(\s+)(({_lb}\w+=\w+{_lb})*)',
+                bygroups(Keyword, Whitespace, using(BashLexer))),
+            (rf'({_keywords}|VOLUME)\b(\s+)(.*)', bygroups(Keyword, Whitespace, String)),
+            (rf'({_bash_keywords})(\s+)', bygroups(Keyword, Whitespace)),
+            (r'(.*\\\n)*.+', using(BashLexer)),
+        ]
+    }
+
+
+class TerraformLexer(ExtendedRegexLexer):
+    """
+    Lexer for terraformi ``.tf`` files.
+    """
+
+    name = 'Terraform'
+    url = 'https://www.terraform.io/'
+    aliases = ['terraform', 'tf', 'hcl']
+    filenames = ['*.tf', '*.hcl']
+    mimetypes = ['application/x-tf', 'application/x-terraform']
+    version_added = '2.1'
+
+    classes = ('backend', 'data', 'module', 'output', 'provider',
+               'provisioner', 'resource', 'variable')
+    classes_re = "({})".format(('|').join(classes))
+
+    types = ('string', 'number', 'bool', 'list', 'tuple', 'map', 'set', 'object', 'null')
+
+    numeric_functions = ('abs', 'ceil', 'floor', 'log', 'max',
+                         'mix', 'parseint', 'pow', 'signum')
+
+    string_functions = ('chomp', 'format', 'formatlist', 'indent',
+                        'join', 'lower', 'regex', 'regexall', 'replace',
+                        'split', 'strrev', 'substr', 'title', 'trim',
+                        'trimprefix', 'trimsuffix', 'trimspace', 'upper'
+                        )
+
+    collection_functions = ('alltrue', 'anytrue', 'chunklist', 'coalesce',
+                            'coalescelist', 'compact', 'concat', 'contains',
+                            'distinct', 'element', 'flatten', 'index', 'keys',
+                            'length', 'list', 'lookup', 'map', 'matchkeys',
+                            'merge', 'range', 'reverse', 'setintersection',
+                            'setproduct', 'setsubtract', 'setunion', 'slice',
+                            'sort', 'sum', 'transpose', 'values', 'zipmap'
+                            )
+
+    encoding_functions = ('base64decode', 'base64encode', 'base64gzip',
+                          'csvdecode', 'jsondecode', 'jsonencode', 'textdecodebase64',
+                          'textencodebase64', 'urlencode', 'yamldecode', 'yamlencode')
+
+    filesystem_functions = ('abspath', 'dirname', 'pathexpand', 'basename',
+                            'file', 'fileexists', 'fileset', 'filebase64', 'templatefile')
+
+    date_time_functions = ('formatdate', 'timeadd', 'timestamp')
+
+    hash_crypto_functions = ('base64sha256', 'base64sha512', 'bcrypt', 'filebase64sha256',
+                             'filebase64sha512', 'filemd5', 'filesha1', 'filesha256', 'filesha512',
+                             'md5', 'rsadecrypt', 'sha1', 'sha256', 'sha512', 'uuid', 'uuidv5')
+
+    ip_network_functions = ('cidrhost', 'cidrnetmask', 'cidrsubnet', 'cidrsubnets')
+
+    type_conversion_functions = ('can', 'defaults', 'tobool', 'tolist', 'tomap',
+                                 'tonumber', 'toset', 'tostring', 'try')
+
+    builtins = numeric_functions + string_functions + collection_functions + encoding_functions +\
+        filesystem_functions + date_time_functions + hash_crypto_functions + ip_network_functions +\
+        type_conversion_functions
+    builtins_re = "({})".format(('|').join(builtins))
+
+    def heredoc_callback(self, match, ctx):
+        # Parse a terraform heredoc
+        # match: 1 = <<[-]?, 2 = name 3 = rest of line
+
+        start = match.start(1)
+        yield start, Operator, match.group(1)        # <<[-]?
+        yield match.start(2), String.Delimiter, match.group(2)  # heredoc name
+
+        ctx.pos = match.start(3)
+        ctx.end = match.end(3)
+        yield ctx.pos, String.Heredoc, match.group(3)
+        ctx.pos = match.end()
+
+        hdname = match.group(2)
+        tolerant = True  # leading whitespace is always accepted
+
+        lines = []
+
+        for match in line_re.finditer(ctx.text, ctx.pos):
+            if tolerant:
+                check = match.group().strip()
+            else:
+                check = match.group().rstrip()
+            if check == hdname:
+                for amatch in lines:
+                    yield amatch.start(), String.Heredoc, amatch.group()
+                yield match.start(), String.Delimiter, match.group()
+                ctx.pos = match.end()
+                break
+            else:
+                lines.append(match)
+        else:
+            # end of heredoc not found -- error!
+            for amatch in lines:
+                yield amatch.start(), Error, amatch.group()
+        ctx.end = len(ctx.text)
+
+    tokens = {
+        'root': [
+            include('basic'),
+            include('whitespace'),
+
+            # Strings
+            (r'(".*")', bygroups(String.Double)),
+
+            # Constants
+            (words(('true', 'false'), prefix=r'\b', suffix=r'\b'), Name.Constant),
+
+            # Types
+            (words(types, prefix=r'\b', suffix=r'\b'), Keyword.Type),
+
+            include('identifier'),
+            include('punctuation'),
+            (r'[0-9]+', Number),
+        ],
+        'basic': [
+            (r'\s*/\*', Comment.Multiline, 'comment'),
+            (r'\s*(#|//).*\n', Comment.Single),
+            include('whitespace'),
+
+            # e.g. terraform {
+            # e.g. egress {
+            (r'(\s*)([0-9a-zA-Z-_]+)(\s*)(=?)(\s*)(\{)',
+             bygroups(Whitespace, Name.Builtin, Whitespace, Operator, Whitespace, Punctuation)),
+
+            # Assignment with attributes, e.g. something = ...
+            (r'(\s*)([0-9a-zA-Z-_]+)(\s*)(=)(\s*)',
+             bygroups(Whitespace, Name.Attribute, Whitespace, Operator, Whitespace)),
+
+            # Assignment with environment variables and similar, e.g. "something" = ...
+            # or key value assignment, e.g. "SlotName" : ...
+            (r'(\s*)("\S+")(\s*)([=:])(\s*)',
+             bygroups(Whitespace, Literal.String.Double, Whitespace, Operator, Whitespace)),
+
+            # Functions, e.g. jsonencode(element("value"))
+            (builtins_re + r'(\()', bygroups(Name.Function, Punctuation)),
+
+            # List of attributes, e.g. ignore_changes = [last_modified, filename]
+            (r'(\[)([a-z_,\s]+)(\])', bygroups(Punctuation, Name.Builtin, Punctuation)),
+
+            # e.g. resource "aws_security_group" "allow_tls" {
+            # e.g. backend "consul" {
+            (classes_re + r'(\s+)("[0-9a-zA-Z-_]+")?(\s*)("[0-9a-zA-Z-_]+")(\s+)(\{)',
+             bygroups(Keyword.Reserved, Whitespace, Name.Class, Whitespace, Name.Variable, Whitespace, Punctuation)),
+
+            # here-doc style delimited strings
+            (r'(<<-?)\s*([a-zA-Z_]\w*)(.*?\n)', heredoc_callback),
+        ],
+        'identifier': [
+            (r'\b(var\.[0-9a-zA-Z-_\.\[\]]+)\b', bygroups(Name.Variable)),
+            (r'\b([0-9a-zA-Z-_\[\]]+\.[0-9a-zA-Z-_\.\[\]]+)\b',
+             bygroups(Name.Variable)),
+        ],
+        'punctuation': [
+            (r'[\[\]()\{\},.?:!=]', Punctuation),
+        ],
+        'comment': [
+            (r'[^*/]', Comment.Multiline),
+            (r'/\*', Comment.Multiline, '#push'),
+            (r'\*/', Comment.Multiline, '#pop'),
+            (r'[*/]', Comment.Multiline)
+        ],
+        'whitespace': [
+            (r'\n', Whitespace),
+            (r'\s+', Whitespace),
+            (r'(\\)(\n)', bygroups(Text, Whitespace)),
+        ],
+    }
+
+
+class TermcapLexer(RegexLexer):
+    """
+    Lexer for termcap database source.
+
+    This is very simple and minimal.
+    """
+    name = 'Termcap'
+    aliases = ['termcap']
+    filenames = ['termcap', 'termcap.src']
+    mimetypes = []
+    url = 'https://en.wikipedia.org/wiki/Termcap'
+    version_added = '2.1'
+
+    # NOTE:
+    #   * multiline with trailing backslash
+    #   * separator is ':'
+    #   * to embed colon as data, we must use \072
+    #   * space after separator is not allowed (mayve)
+    tokens = {
+        'root': [
+            (r'^#.*', Comment),
+            (r'^[^\s#:|]+', Name.Tag, 'names'),
+            (r'\s+', Whitespace),
+        ],
+        'names': [
+            (r'\n', Whitespace, '#pop'),
+            (r':', Punctuation, 'defs'),
+            (r'\|', Punctuation),
+            (r'[^:|]+', Name.Attribute),
+        ],
+        'defs': [
+            (r'(\\)(\n[ \t]*)', bygroups(Text, Whitespace)),
+            (r'\n[ \t]*', Whitespace, '#pop:2'),
+            (r'(#)([0-9]+)', bygroups(Operator, Number)),
+            (r'=', Operator, 'data'),
+            (r':', Punctuation),
+            (r'[^\s:=#]+', Name.Class),
+        ],
+        'data': [
+            (r'\\072', Literal),
+            (r':', Punctuation, '#pop'),
+            (r'[^:\\]+', Literal),  # for performance
+            (r'.', Literal),
+        ],
+    }
+
+
+class TerminfoLexer(RegexLexer):
+    """
+    Lexer for terminfo database source.
+
+    This is very simple and minimal.
+    """
+    name = 'Terminfo'
+    aliases = ['terminfo']
+    filenames = ['terminfo', 'terminfo.src']
+    mimetypes = []
+    url = 'https://en.wikipedia.org/wiki/Terminfo'
+    version_added = '2.1'
+
+    # NOTE:
+    #   * multiline with leading whitespace
+    #   * separator is ','
+    #   * to embed comma as data, we can use \,
+    #   * space after separator is allowed
+    tokens = {
+        'root': [
+            (r'^#.*$', Comment),
+            (r'^[^\s#,|]+', Name.Tag, 'names'),
+            (r'\s+', Whitespace),
+        ],
+        'names': [
+            (r'\n', Whitespace, '#pop'),
+            (r'(,)([ \t]*)', bygroups(Punctuation, Whitespace), 'defs'),
+            (r'\|', Punctuation),
+            (r'[^,|]+', Name.Attribute),
+        ],
+        'defs': [
+            (r'\n[ \t]+', Whitespace),
+            (r'\n', Whitespace, '#pop:2'),
+            (r'(#)([0-9]+)', bygroups(Operator, Number)),
+            (r'=', Operator, 'data'),
+            (r'(,)([ \t]*)', bygroups(Punctuation, Whitespace)),
+            (r'[^\s,=#]+', Name.Class),
+        ],
+        'data': [
+            (r'\\[,\\]', Literal),
+            (r'(,)([ \t]*)', bygroups(Punctuation, Whitespace), '#pop'),
+            (r'[^\\,]+', Literal),  # for performance
+            (r'.', Literal),
+        ],
+    }
+
+
+class PkgConfigLexer(RegexLexer):
+    """
+    Lexer for pkg-config
+    (see also `manual page <http://linux.die.net/man/1/pkg-config>`_).
+    """
+
+    name = 'PkgConfig'
+    url = 'http://www.freedesktop.org/wiki/Software/pkg-config/'
+    aliases = ['pkgconfig']
+    filenames = ['*.pc']
+    mimetypes = []
+    version_added = '2.1'
+
+    tokens = {
+        'root': [
+            (r'#.*$', Comment.Single),
+
+            # variable definitions
+            (r'^(\w+)(=)', bygroups(Name.Attribute, Operator)),
+
+            # keyword lines
+            (r'^([\w.]+)(:)',
+             bygroups(Name.Tag, Punctuation), 'spvalue'),
+
+            # variable references
+            include('interp'),
+
+            # fallback
+            (r'\s+', Whitespace),
+            (r'[^${}#=:\n.]+', Text),
+            (r'.', Text),
+        ],
+        'interp': [
+            # you can escape literal "$" as "$$"
+            (r'\$\$', Text),
+
+            # variable references
+            (r'\$\{', String.Interpol, 'curly'),
+        ],
+        'curly': [
+            (r'\}', String.Interpol, '#pop'),
+            (r'\w+', Name.Attribute),
+        ],
+        'spvalue': [
+            include('interp'),
+
+            (r'#.*$', Comment.Single, '#pop'),
+            (r'\n', Whitespace, '#pop'),
+
+            # fallback
+            (r'\s+', Whitespace),
+            (r'[^${}#\n\s]+', Text),
+            (r'.', Text),
+        ],
+    }
+
+
+class PacmanConfLexer(RegexLexer):
+    """
+    Lexer for pacman.conf.
+
+    Actually, IniLexer works almost fine for this format,
+    but it yield error token. It is because pacman.conf has
+    a form without assignment like:
+
+        UseSyslog
+        Color
+        TotalDownload
+        CheckSpace
+        VerbosePkgLists
+
+    These are flags to switch on.
+    """
+
+    name = 'PacmanConf'
+    url = 'https://www.archlinux.org/pacman/pacman.conf.5.html'
+    aliases = ['pacmanconf']
+    filenames = ['pacman.conf']
+    mimetypes = []
+    version_added = '2.1'
+
+    tokens = {
+        'root': [
+            # comment
+            (r'#.*$', Comment.Single),
+
+            # section header
+            (r'^(\s*)(\[.*?\])(\s*)$', bygroups(Whitespace, Keyword, Whitespace)),
+
+            # variable definitions
+            # (Leading space is allowed...)
+            (r'(\w+)(\s*)(=)',
+             bygroups(Name.Attribute, Whitespace, Operator)),
+
+            # flags to on
+            (r'^(\s*)(\w+)(\s*)$',
+             bygroups(Whitespace, Name.Attribute, Whitespace)),
+
+            # built-in special values
+            (words((
+                '$repo',  # repository
+                '$arch',  # architecture
+                '%o',     # outfile
+                '%u',     # url
+                ), suffix=r'\b'),
+             Name.Variable),
+
+            # fallback
+            (r'\s+', Whitespace),
+            (r'.', Text),
+        ],
+    }
+
+
+class AugeasLexer(RegexLexer):
+    """
+    Lexer for Augeas.
+    """
+    name = 'Augeas'
+    url = 'http://augeas.net'
+    aliases = ['augeas']
+    filenames = ['*.aug']
+    version_added = '2.4'
+
+    tokens = {
+        'root': [
+            (r'(module)(\s*)([^\s=]+)', bygroups(Keyword.Namespace, Whitespace, Name.Namespace)),
+            (r'(let)(\s*)([^\s=]+)', bygroups(Keyword.Declaration, Whitespace, Name.Variable)),
+            (r'(del|store|value|counter|seq|key|label|autoload|incl|excl|transform|test|get|put)(\s+)', bygroups(Name.Builtin, Whitespace)),
+            (r'(\()([^:]+)(\:)(unit|string|regexp|lens|tree|filter)(\))', bygroups(Punctuation, Name.Variable, Punctuation, Keyword.Type, Punctuation)),
+            (r'\(\*', Comment.Multiline, 'comment'),
+            (r'[*+\-.;=?|]', Operator),
+            (r'[()\[\]{}]', Operator),
+            (r'"', String.Double, 'string'),
+            (r'\/', String.Regex, 'regex'),
+            (r'([A-Z]\w*)(\.)(\w+)', bygroups(Name.Namespace, Punctuation, Name.Variable)),
+            (r'.', Name.Variable),
+            (r'\s+', Whitespace),
+        ],
+        'string': [
+            (r'\\.', String.Escape),
+            (r'[^"]', String.Double),
+            (r'"', String.Double, '#pop'),
+        ],
+        'regex': [
+            (r'\\.', String.Escape),
+            (r'[^/]', String.Regex),
+            (r'\/', String.Regex, '#pop'),
+        ],
+        'comment': [
+            (r'[^*)]', Comment.Multiline),
+            (r'\(\*', Comment.Multiline, '#push'),
+            (r'\*\)', Comment.Multiline, '#pop'),
+            (r'[)*]', Comment.Multiline)
+        ],
+    }
+
+
+class TOMLLexer(RegexLexer):
+    """
+    Lexer for TOML, a simple language for config files.
+    """
+
+    name = 'TOML'
+    aliases = ['toml']
+    filenames = ['*.toml', 'Pipfile', 'poetry.lock']
+    mimetypes = ['application/toml']
+    url = 'https://toml.io'
+    version_added = '2.4'
+
+    # Based on the TOML spec: https://toml.io/en/v1.0.0
+
+    # The following is adapted from CPython's tomllib:
+    _time = r"\d\d:\d\d(:\d\d(\.\d+)?)?"
+    _datetime = rf"""(?x)
+                  \d\d\d\d-\d\d-\d\d # date, e.g., 1988-10-27
+                (
+                  [Tt ] {_time} # optional time
+                  (
+                    [Zz]|[+-]\d\d:\d\d # optional time offset
+                  )?
+                )?
+              """
+
+    tokens = {
+        'root': [
+            # Note that we make an effort in order to distinguish
+            # moments at which we're parsing a key and moments at
+            # which we're parsing a value. In the TOML code
+            #
+            #   1234 = 1234
+            #
+            # the first "1234" should be Name, the second Integer.
+
+            # Whitespace
+            (r'\s+', Whitespace),
+
+            # Comment
+            (r'#.*', Comment.Single),
+
+            # Assignment keys
+            include('key'),
+
+            # After "=", find a value
+            (r'(=)(\s*)', bygroups(Operator, Whitespace), 'value'),
+
+            # Table header
+            (r'\[\[?', Keyword, 'table-key'),
+        ],
+        'key': [
+            # Start of bare key (only ASCII is allowed here).
+            (r'[A-Za-z0-9_-]+', Name),
+            # Quoted key
+            (r'"', String.Double, 'basic-string'),
+            (r"'", String.Single, 'literal-string'),
+            # Dots act as separators in keys
+            (r'\.', Punctuation),
+        ],
+        'table-key': [
+            # This is like 'key', but highlights the name components
+            # and separating dots as Keyword because it looks better
+            # when the whole table header is Keyword. We do highlight
+            # strings as strings though.
+            # Start of bare key (only ASCII is allowed here).
+            (r'[A-Za-z0-9_-]+', Keyword),
+            (r'"', String.Double, 'basic-string'),
+            (r"'", String.Single, 'literal-string'),
+            (r'\.', Keyword),
+            (r'\]\]?', Keyword, '#pop'),
+
+            # Inline whitespace allowed
+            (r'[ \t]+', Whitespace),
+        ],
+        'value': [
+            # Datetime, baretime
+            (_datetime, Literal.Date, '#pop'),
+            (_time, Literal.Date, '#pop'),
+
+            # Recognize as float if there is a fractional part
+            # and/or an exponent.
+            (r'[+-]?\d[0-9_]*[eE][+-]?\d[0-9_]*', Number.Float, '#pop'),
+            (r'[+-]?\d[0-9_]*\.\d[0-9_]*([eE][+-]?\d[0-9_]*)?',
+             Number.Float, '#pop'),
+
+            # Infinities and NaN
+            (r'[+-]?(inf|nan)', Number.Float, '#pop'),
+
+            # Integers
+            (r'-?0b[01_]+', Number.Bin, '#pop'),
+            (r'-?0o[0-7_]+', Number.Oct, '#pop'),
+            (r'-?0x[0-9a-fA-F_]+', Number.Hex, '#pop'),
+            (r'[+-]?[0-9_]+', Number.Integer, '#pop'),
+
+            # Strings
+            (r'"""', String.Double, ('#pop', 'multiline-basic-string')),
+            (r'"', String.Double, ('#pop', 'basic-string')),
+            (r"'''", String.Single, ('#pop', 'multiline-literal-string')),
+            (r"'", String.Single, ('#pop', 'literal-string')),
+
+            # Booleans
+            (r'true|false', Keyword.Constant, '#pop'),
+
+            # Start of array
+            (r'\[', Punctuation, ('#pop', 'array')),
+
+            # Start of inline table
+            (r'\{', Punctuation, ('#pop', 'inline-table')),
+        ],
+        'array': [
+            # Whitespace, including newlines, is ignored inside arrays,
+            # and comments are allowed.
+            (r'\s+', Whitespace),
+            (r'#.*', Comment.Single),
+
+            # Delimiters
+            (r',', Punctuation),
+
+            # End of array
+            (r'\]', Punctuation, '#pop'),
+
+            # Parse a value and come back
+            default('value'),
+        ],
+        'inline-table': [
+            # Whitespace (since TOML 1.1.0, same as in array)
+            (r'\s+', Whitespace),
+            (r'#.*', Comment.Single),
+
+            # Keys
+            include('key'),
+
+            # Values
+            (r'(=)(\s*)', bygroups(Punctuation, Whitespace), 'value'),
+
+            # Delimiters
+            (r',', Punctuation),
+
+            # End of inline table
+            (r'\}', Punctuation, '#pop'),
+        ],
+        'basic-string': [
+            (r'"', String.Double, '#pop'),
+            include('escapes'),
+            (r'[^"\\]+', String.Double),
+        ],
+        'literal-string': [
+            (r".*?'", String.Single, '#pop'),
+        ],
+        'multiline-basic-string': [
+            (r'"""', String.Double, '#pop'),
+            (r'(\\)(\n)', bygroups(String.Escape, Whitespace)),
+            include('escapes'),
+            (r'[^"\\]+', String.Double),
+            (r'"', String.Double),
+        ],
+        'multiline-literal-string': [
+            (r"'''", String.Single, '#pop'),
+            (r"[^']+", String.Single),
+            (r"'", String.Single),
+        ],
+        'escapes': [
+            (r'\\x[0-9a-fA-F]{2}|\\u[0-9a-fA-F]{4}|\\U[0-9a-fA-F]{8}', String.Escape),
+            (r'\\.', String.Escape),
+        ],
+    }
+
+class NestedTextLexer(RegexLexer):
+    """
+    Lexer for *NextedText*, a human-friendly data format.
+
+    .. versionchanged:: 2.16
+        Added support for *NextedText* v3.0.
+    """
+
+    name = 'NestedText'
+    url = 'https://nestedtext.org'
+    aliases = ['nestedtext', 'nt']
+    filenames = ['*.nt']
+    version_added = '2.9'
+
+    tokens = {
+        'root': [
+            # Comment: # ...
+            (r'^([ ]*)(#.*)$', bygroups(Whitespace, Comment)),
+
+            # Inline dictionary: {...}
+            (r'^([ ]*)(\{)', bygroups(Whitespace, Punctuation), 'inline_dict'),
+
+            # Inline list: [...]
+            (r'^([ ]*)(\[)', bygroups(Whitespace, Punctuation), 'inline_list'),
+
+            # empty multiline string item: >
+            (r'^([ ]*)(>)$', bygroups(Whitespace, Punctuation)),
+
+            # multiline string item: > ...
+            (r'^([ ]*)(>)( )(.*?)([ \t]*)$', bygroups(Whitespace, Punctuation, Whitespace, Text, Whitespace)),
+
+            # empty list item: -
+            (r'^([ ]*)(-)$', bygroups(Whitespace, Punctuation)),
+
+            # list item: - ...
+            (r'^([ ]*)(-)( )(.*?)([ \t]*)$', bygroups(Whitespace, Punctuation, Whitespace, Text, Whitespace)),
+
+            # empty multiline key item: :
+            (r'^([ ]*)(:)$', bygroups(Whitespace, Punctuation)),
+
+            # multiline key item: : ...
+            (r'^([ ]*)(:)( )([^\n]*?)([ \t]*)$', bygroups(Whitespace, Punctuation, Whitespace, Name.Tag, Whitespace)),
+
+            # empty dict key item: ...:
+            (r'^([ ]*)([^\{\[\s].*?)(:)$', bygroups(Whitespace, Name.Tag, Punctuation)),
+
+            # dict key item: ...: ...
+            (r'^([ ]*)([^\{\[\s].*?)(:)( )(.*?)([ \t]*)$', bygroups(Whitespace, Name.Tag, Punctuation, Whitespace, Text, Whitespace)),
+        ],
+        'inline_list': [
+            include('whitespace'),
+            (r'[^\{\}\[\],\s]+', Text),
+            include('inline_value'),
+            (r',', Punctuation),
+            (r'\]', Punctuation, '#pop'),
+            (r'\n', Error, '#pop'),
+        ],
+        'inline_dict': [
+            include('whitespace'),
+            (r'[^\{\}\[\],:\s]+', Name.Tag),
+            (r':', Punctuation, 'inline_dict_value'),
+            (r'\}', Punctuation, '#pop'),
+            (r'\n', Error, '#pop'),
+        ],
+        'inline_dict_value': [
+            include('whitespace'),
+            (r'[^\{\}\[\],:\s]+', Text),
+            include('inline_value'),
+            (r',', Punctuation, '#pop'),
+            (r'\}', Punctuation, '#pop:2'),
+        ],
+        'inline_value': [
+            include('whitespace'),
+            (r'\{', Punctuation, 'inline_dict'),
+            (r'\[', Punctuation, 'inline_list'),
+        ],
+        'whitespace': [
+            (r'[ \t]+', Whitespace),
+        ],
+    }
+
+
+class SingularityLexer(RegexLexer):
+    """
+    Lexer for Singularity definition files.
+    """
+
+    name = 'Singularity'
+    url = 'https://www.sylabs.io/guides/3.0/user-guide/definition_files.html'
+    aliases = ['singularity']
+    filenames = ['*.def', 'Singularity']
+    version_added = '2.6'
+    flags = re.IGNORECASE | re.MULTILINE | re.DOTALL
+
+    _headers = r'^(\s*)(bootstrap|from|osversion|mirrorurl|include|registry|namespace|includecmd)(:)'
+    _section = r'^(%(?:pre|post|setup|environment|help|labels|test|runscript|files|startscript))(\s*)'
+    _appsect = r'^(%app(?:install|help|run|labels|env|test|files))(\s*)'
+
+    tokens = {
+        'root': [
+            (_section, bygroups(Generic.Heading, Whitespace), 'script'),
+            (_appsect, bygroups(Generic.Heading, Whitespace), 'script'),
+            (_headers, bygroups(Whitespace, Keyword, Text)),
+            (r'\s*#.*?\n', Comment),
+            (r'\b(([0-9]+\.?[0-9]*)|(\.[0-9]+))\b', Number),
+            (r'[ \t]+', Whitespace),
+            (r'(?!^\s*%).', Text),
+        ],
+        'script': [
+            (r'(.+?(?=^\s*%))|(.*)', using(BashLexer), '#pop'),
+        ],
+    }
+
+    def analyse_text(text):
+        """This is a quite simple script file, but there are a few keywords
+        which seem unique to this language."""
+        result = 0
+        if re.search(r'\b(?:osversion|includecmd|mirrorurl)\b', text, re.IGNORECASE):
+            result += 0.5
+
+        if re.search(SingularityLexer._section[1:], text):
+            result += 0.49
+
+        return result
+
+
+class UnixConfigLexer(RegexLexer):
+    """
+    Lexer for Unix/Linux config files using colon-separated values, e.g.
+
+    * ``/etc/group``
+    * ``/etc/passwd``
+    * ``/etc/shadow``
+    """
+
+    name = 'Unix/Linux config files'
+    aliases = ['unixconfig', 'linuxconfig']
+    filenames = []
+    url = 'https://en.wikipedia.org/wiki/Configuration_file#Unix_and_Unix-like_operating_systems'
+    version_added = '2.12'
+
+    tokens = {
+        'root': [
+            (r'^#.*', Comment),
+            (r'\n', Whitespace),
+            (r':', Punctuation),
+            (r'[0-9]+', Number),
+            (r'((?!\n)[a-zA-Z0-9\_\-\s\(\),]){2,}', Text),
+            (r'[^:\n]+', String),
+        ],
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/factor.py

@@ -0,0 +1,363 @@
+"""
+    pygments.lexers.factor
+    ~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexers for the Factor language.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import RegexLexer, bygroups, default, words
+from pygments.token import Text, Comment, Keyword, Name, String, Number, \
+    Whitespace, Punctuation
+
+__all__ = ['FactorLexer']
+
+
+class FactorLexer(RegexLexer):
+    """
+    Lexer for the Factor language.
+    """
+    name = 'Factor'
+    url = 'http://factorcode.org'
+    aliases = ['factor']
+    filenames = ['*.factor']
+    mimetypes = ['text/x-factor']
+    version_added = '1.4'
+
+    builtin_kernel = words((
+        '-rot', '2bi', '2bi@', '2bi*', '2curry', '2dip', '2drop', '2dup', '2keep', '2nip',
+        '2over', '2tri', '2tri@', '2tri*', '3bi', '3curry', '3dip', '3drop', '3dup', '3keep',
+        '3tri', '4dip', '4drop', '4dup', '4keep', '<wrapper>', '=', '>boolean', 'clone',
+        '?', '?execute', '?if', 'and', 'assert', 'assert=', 'assert?', 'bi', 'bi-curry',
+        'bi-curry@', 'bi-curry*', 'bi@', 'bi*', 'boa', 'boolean', 'boolean?', 'both?',
+        'build', 'call', 'callstack', 'callstack>array', 'callstack?', 'clear', '(clone)',
+        'compose', 'compose?', 'curry', 'curry?', 'datastack', 'die', 'dip', 'do', 'drop',
+        'dup', 'dupd', 'either?', 'eq?', 'equal?', 'execute', 'hashcode', 'hashcode*',
+        'identity-hashcode', 'identity-tuple', 'identity-tuple?', 'if', 'if*',
+        'keep', 'loop', 'most', 'new', 'nip', 'not', 'null', 'object', 'or', 'over',
+        'pick', 'prepose', 'retainstack', 'rot', 'same?', 'swap', 'swapd', 'throw',
+        'tri', 'tri-curry', 'tri-curry@', 'tri-curry*', 'tri@', 'tri*', 'tuple',
+        'tuple?', 'unless', 'unless*', 'until', 'when', 'when*', 'while', 'with',
+        'wrapper', 'wrapper?', 'xor'), suffix=r'(\s+)')
+
+    builtin_assocs = words((
+        '2cache', '<enum>', '>alist', '?at', '?of', 'assoc', 'assoc-all?',
+        'assoc-any?', 'assoc-clone-like', 'assoc-combine', 'assoc-diff',
+        'assoc-diff!', 'assoc-differ', 'assoc-each', 'assoc-empty?',
+        'assoc-filter', 'assoc-filter!', 'assoc-filter-as', 'assoc-find',
+        'assoc-hashcode', 'assoc-intersect', 'assoc-like', 'assoc-map',
+        'assoc-map-as', 'assoc-partition', 'assoc-refine', 'assoc-size',
+        'assoc-stack', 'assoc-subset?', 'assoc-union', 'assoc-union!',
+        'assoc=', 'assoc>map', 'assoc?', 'at', 'at+', 'at*', 'cache', 'change-at',
+        'clear-assoc', 'delete-at', 'delete-at*', 'enum', 'enum?', 'extract-keys',
+        'inc-at', 'key?', 'keys', 'map>assoc', 'maybe-set-at', 'new-assoc', 'of',
+        'push-at', 'rename-at', 'set-at', 'sift-keys', 'sift-values', 'substitute',
+        'unzip', 'value-at', 'value-at*', 'value?', 'values', 'zip'), suffix=r'(\s+)')
+
+    builtin_combinators = words((
+        '2cleave', '2cleave>quot', '3cleave', '3cleave>quot', '4cleave',
+        '4cleave>quot', 'alist>quot', 'call-effect', 'case', 'case-find',
+        'case>quot', 'cleave', 'cleave>quot', 'cond', 'cond>quot', 'deep-spread>quot',
+        'execute-effect', 'linear-case-quot', 'no-case', 'no-case?', 'no-cond',
+        'no-cond?', 'recursive-hashcode', 'shallow-spread>quot', 'spread',
+        'to-fixed-point', 'wrong-values', 'wrong-values?'), suffix=r'(\s+)')
+
+    builtin_math = words((
+        '-', '/', '/f', '/i', '/mod', '2/', '2^', '<', '<=', '<fp-nan>', '>',
+        '>=', '>bignum', '>fixnum', '>float', '>integer', '(all-integers?)',
+        '(each-integer)', '(find-integer)', '*', '+', '?1+',
+        'abs', 'align', 'all-integers?', 'bignum', 'bignum?', 'bit?', 'bitand',
+        'bitnot', 'bitor', 'bits>double', 'bits>float', 'bitxor', 'complex',
+        'complex?', 'denominator', 'double>bits', 'each-integer', 'even?',
+        'find-integer', 'find-last-integer', 'fixnum', 'fixnum?', 'float',
+        'float>bits', 'float?', 'fp-bitwise=', 'fp-infinity?', 'fp-nan-payload',
+        'fp-nan?', 'fp-qnan?', 'fp-sign', 'fp-snan?', 'fp-special?',
+        'if-zero', 'imaginary-part', 'integer', 'integer>fixnum',
+        'integer>fixnum-strict', 'integer?', 'log2', 'log2-expects-positive',
+        'log2-expects-positive?', 'mod', 'neg', 'neg?', 'next-float',
+        'next-power-of-2', 'number', 'number=', 'number?', 'numerator', 'odd?',
+        'out-of-fixnum-range', 'out-of-fixnum-range?', 'power-of-2?',
+        'prev-float', 'ratio', 'ratio?', 'rational', 'rational?', 'real',
+        'real-part', 'real?', 'recip', 'rem', 'sgn', 'shift', 'sq', 'times',
+        'u<', 'u<=', 'u>', 'u>=', 'unless-zero', 'unordered?', 'when-zero',
+        'zero?'), suffix=r'(\s+)')
+
+    builtin_sequences = words((
+        '1sequence', '2all?', '2each', '2map', '2map-as', '2map-reduce', '2reduce',
+        '2selector', '2sequence', '3append', '3append-as', '3each', '3map', '3map-as',
+        '3sequence', '4sequence', '<repetition>', '<reversed>', '<slice>', '?first',
+        '?last', '?nth', '?second', '?set-nth', 'accumulate', 'accumulate!',
+        'accumulate-as', 'all?', 'any?', 'append', 'append!', 'append-as',
+        'assert-sequence', 'assert-sequence=', 'assert-sequence?',
+        'binary-reduce', 'bounds-check', 'bounds-check?', 'bounds-error',
+        'bounds-error?', 'but-last', 'but-last-slice', 'cartesian-each',
+        'cartesian-map', 'cartesian-product', 'change-nth', 'check-slice',
+        'check-slice-error', 'clone-like', 'collapse-slice', 'collector',
+        'collector-for', 'concat', 'concat-as', 'copy', 'count', 'cut', 'cut-slice',
+        'cut*', 'delete-all', 'delete-slice', 'drop-prefix', 'each', 'each-from',
+        'each-index', 'empty?', 'exchange', 'filter', 'filter!', 'filter-as', 'find',
+        'find-from', 'find-index', 'find-index-from', 'find-last', 'find-last-from',
+        'first', 'first2', 'first3', 'first4', 'flip', 'follow', 'fourth', 'glue', 'halves',
+        'harvest', 'head', 'head-slice', 'head-slice*', 'head*', 'head?',
+        'if-empty', 'immutable', 'immutable-sequence', 'immutable-sequence?',
+        'immutable?', 'index', 'index-from', 'indices', 'infimum', 'infimum-by',
+        'insert-nth', 'interleave', 'iota', 'iota-tuple', 'iota-tuple?', 'join',
+        'join-as', 'last', 'last-index', 'last-index-from', 'length', 'lengthen',
+        'like', 'longer', 'longer?', 'longest', 'map', 'map!', 'map-as', 'map-find',
+        'map-find-last', 'map-index', 'map-integers', 'map-reduce', 'map-sum',
+        'max-length', 'member-eq?', 'member?', 'midpoint@', 'min-length',
+        'mismatch', 'move', 'new-like', 'new-resizable', 'new-sequence',
+        'non-negative-integer-expected', 'non-negative-integer-expected?',
+        'nth', 'nths', 'pad-head', 'pad-tail', 'padding', 'partition', 'pop', 'pop*',
+        'prefix', 'prepend', 'prepend-as', 'produce', 'produce-as', 'product', 'push',
+        'push-all', 'push-either', 'push-if', 'reduce', 'reduce-index', 'remove',
+        'remove!', 'remove-eq', 'remove-eq!', 'remove-nth', 'remove-nth!', 'repetition',
+        'repetition?', 'replace-slice', 'replicate', 'replicate-as', 'rest',
+        'rest-slice', 'reverse', 'reverse!', 'reversed', 'reversed?', 'second',
+        'selector', 'selector-for', 'sequence', 'sequence-hashcode', 'sequence=',
+        'sequence?', 'set-first', 'set-fourth', 'set-last', 'set-length', 'set-nth',
+        'set-second', 'set-third', 'short', 'shorten', 'shorter', 'shorter?',
+        'shortest', 'sift', 'slice', 'slice-error', 'slice-error?', 'slice?',
+        'snip', 'snip-slice', 'start', 'start*', 'subseq', 'subseq?', 'suffix',
+        'suffix!', 'sum', 'sum-lengths', 'supremum', 'supremum-by', 'surround', 'tail',
+        'tail-slice', 'tail-slice*', 'tail*', 'tail?', 'third', 'trim',
+        'trim-head', 'trim-head-slice', 'trim-slice', 'trim-tail', 'trim-tail-slice',
+        'unclip', 'unclip-last', 'unclip-last-slice', 'unclip-slice', 'unless-empty',
+        'virtual-exemplar', 'virtual-sequence', 'virtual-sequence?', 'virtual@',
+        'when-empty'), suffix=r'(\s+)')
+
+    builtin_namespaces = words((
+        '+@', 'change', 'change-global', 'counter', 'dec', 'get', 'get-global',
+        'global', 'inc', 'init-namespaces', 'initialize', 'is-global', 'make-assoc',
+        'namespace', 'namestack', 'off', 'on', 'set', 'set-global', 'set-namestack',
+        'toggle', 'with-global', 'with-scope', 'with-variable', 'with-variables'),
+        suffix=r'(\s+)')
+
+    builtin_arrays = words((
+        '1array', '2array', '3array', '4array', '<array>', '>array', 'array',
+        'array?', 'pair', 'pair?', 'resize-array'), suffix=r'(\s+)')
+
+    builtin_io = words((
+        '(each-stream-block-slice)', '(each-stream-block)',
+        '(stream-contents-by-block)', '(stream-contents-by-element)',
+        '(stream-contents-by-length-or-block)',
+        '(stream-contents-by-length)', '+byte+', '+character+',
+        'bad-seek-type', 'bad-seek-type?', 'bl', 'contents', 'each-block',
+        'each-block-size', 'each-block-slice', 'each-line', 'each-morsel',
+        'each-stream-block', 'each-stream-block-slice', 'each-stream-line',
+        'error-stream', 'flush', 'input-stream', 'input-stream?',
+        'invalid-read-buffer', 'invalid-read-buffer?', 'lines', 'nl',
+        'output-stream', 'output-stream?', 'print', 'read', 'read-into',
+        'read-partial', 'read-partial-into', 'read-until', 'read1', 'readln',
+        'seek-absolute', 'seek-absolute?', 'seek-end', 'seek-end?',
+        'seek-input', 'seek-output', 'seek-relative', 'seek-relative?',
+        'stream-bl', 'stream-contents', 'stream-contents*', 'stream-copy',
+        'stream-copy*', 'stream-element-type', 'stream-flush',
+        'stream-length', 'stream-lines', 'stream-nl', 'stream-print',
+        'stream-read', 'stream-read-into', 'stream-read-partial',
+        'stream-read-partial-into', 'stream-read-partial-unsafe',
+        'stream-read-unsafe', 'stream-read-until', 'stream-read1',
+        'stream-readln', 'stream-seek', 'stream-seekable?', 'stream-tell',
+        'stream-write', 'stream-write1', 'tell-input', 'tell-output',
+        'with-error-stream', 'with-error-stream*', 'with-error>output',
+        'with-input-output+error-streams',
+        'with-input-output+error-streams*', 'with-input-stream',
+        'with-input-stream*', 'with-output-stream', 'with-output-stream*',
+        'with-output>error', 'with-output+error-stream',
+        'with-output+error-stream*', 'with-streams', 'with-streams*',
+        'write', 'write1'), suffix=r'(\s+)')
+
+    builtin_strings = words((
+        '1string', '<string>', '>string', 'resize-string', 'string',
+        'string?'), suffix=r'(\s+)')
+
+    builtin_vectors = words((
+        '1vector', '<vector>', '>vector', '?push', 'vector', 'vector?'),
+        suffix=r'(\s+)')
+
+    builtin_continuations = words((
+        '<condition>', '<continuation>', '<restart>', 'attempt-all',
+        'attempt-all-error', 'attempt-all-error?', 'callback-error-hook',
+        'callcc0', 'callcc1', 'cleanup', 'compute-restarts', 'condition',
+        'condition?', 'continuation', 'continuation?', 'continue',
+        'continue-restart', 'continue-with', 'current-continuation',
+        'error', 'error-continuation', 'error-in-thread', 'error-thread',
+        'ifcc', 'ignore-errors', 'in-callback?', 'original-error', 'recover',
+        'restart', 'restart?', 'restarts', 'rethrow', 'rethrow-restarts',
+        'return', 'return-continuation', 'thread-error-hook', 'throw-continue',
+        'throw-restarts', 'with-datastack', 'with-return'), suffix=r'(\s+)')
+
+    tokens = {
+        'root': [
+            # factor allows a file to start with a shebang
+            (r'#!.*$', Comment.Preproc),
+            default('base'),
+        ],
+        'base': [
+            (r'\s+', Whitespace),
+
+            # defining words
+            (r'((?:MACRO|MEMO|TYPED)?:[:]?)(\s+)(\S+)',
+             bygroups(Keyword, Whitespace, Name.Function)),
+            (r'(M:[:]?)(\s+)(\S+)(\s+)(\S+)',
+             bygroups(Keyword, Whitespace, Name.Class, Whitespace,
+                 Name.Function)),
+            (r'(C:)(\s+)(\S+)(\s+)(\S+)',
+             bygroups(Keyword, Whitespace, Name.Function, Whitespace,
+                 Name.Class)),
+            (r'(GENERIC:)(\s+)(\S+)',
+             bygroups(Keyword, Whitespace, Name.Function)),
+            (r'(HOOK:|GENERIC#)(\s+)(\S+)(\s+)(\S+)',
+             bygroups(Keyword, Whitespace, Name.Function, Whitespace,
+                 Name.Function)),
+            (r'(\()(\s)', bygroups(Name.Function, Whitespace), 'stackeffect'),
+            (r'(;)(\s)', bygroups(Keyword, Whitespace)),
+
+            # imports and namespaces
+            (r'(USING:)(\s+)',
+             bygroups(Keyword.Namespace, Whitespace), 'vocabs'),
+            (r'(USE:|UNUSE:|IN:|QUALIFIED:)(\s+)(\S+)',
+             bygroups(Keyword.Namespace, Whitespace, Name.Namespace)),
+            (r'(QUALIFIED-WITH:)(\s+)(\S+)(\s+)(\S+)',
+             bygroups(Keyword.Namespace, Whitespace, Name.Namespace,
+                 Whitespace, Name.Namespace)),
+            (r'(FROM:|EXCLUDE:)(\s+)(\S+)(\s+=>\s)',
+             bygroups(Keyword.Namespace, Whitespace, Name.Namespace,
+                 Whitespace), 'words'),
+            (r'(RENAME:)(\s+)(\S+)(\s+)(\S+)(\s+)(=>)(\s+)(\S+)',
+             bygroups(Keyword.Namespace, Whitespace, Name.Function, Whitespace,
+                 Name.Namespace, Whitespace, Punctuation, Whitespace,
+                 Name.Function)),
+            (r'(ALIAS:|TYPEDEF:)(\s+)(\S+)(\s+)(\S+)',
+             bygroups(Keyword.Namespace, Whitespace, Name.Function, Whitespace,
+                 Name.Function)),
+            (r'(DEFER:|FORGET:|POSTPONE:)(\s+)(\S+)',
+             bygroups(Keyword.Namespace, Whitespace, Name.Function)),
+
+            # tuples and classes
+            (r'(TUPLE:|ERROR:)(\s+)(\S+)(\s+)(<)(\s+)(\S+)',
+             bygroups(Keyword, Whitespace, Name.Class, Whitespace, Punctuation,
+                 Whitespace, Name.Class), 'slots'),
+            (r'(TUPLE:|ERROR:|BUILTIN:)(\s+)(\S+)',
+             bygroups(Keyword, Whitespace, Name.Class), 'slots'),
+            (r'(MIXIN:|UNION:|INTERSECTION:)(\s+)(\S+)',
+             bygroups(Keyword, Whitespace, Name.Class)),
+            (r'(PREDICATE:)(\s+)(\S+)(\s+)(<)(\s+)(\S+)',
+             bygroups(Keyword, Whitespace, Name.Class, Whitespace,
+                 Punctuation, Whitespace, Name.Class)),
+            (r'(C:)(\s+)(\S+)(\s+)(\S+)',
+             bygroups(Keyword, Whitespace, Name.Function, Whitespace, Name.Class)),
+            (r'(INSTANCE:)(\s+)(\S+)(\s+)(\S+)',
+             bygroups(Keyword, Whitespace, Name.Class, Whitespace, Name.Class)),
+            (r'(SLOT:)(\s+)(\S+)', bygroups(Keyword, Whitespace, Name.Function)),
+            (r'(SINGLETON:)(\s+)(\S+)', bygroups(Keyword, Whitespace, Name.Class)),
+            (r'SINGLETONS:', Keyword, 'classes'),
+
+            # other syntax
+            (r'(CONSTANT:|SYMBOL:|MAIN:|HELP:)(\s+)(\S+)',
+             bygroups(Keyword, Whitespace, Name.Function)),
+            (r'(SYMBOLS:)(\s+)', bygroups(Keyword, Whitespace), 'words'),
+            (r'(SYNTAX:)(\s+)', bygroups(Keyword, Whitespace)),
+            (r'(ALIEN:)(\s+)', bygroups(Keyword, Whitespace)),
+            (r'(STRUCT:)(\s+)(\S+)', bygroups(Keyword, Whitespace, Name.Class)),
+            (r'(FUNCTION:)(\s+)'
+                r'(\S+)(\s+)(\S+)(\s+)'
+                r'(\()(\s+)([^)]+)(\))(\s)',
+             bygroups(Keyword.Namespace, Whitespace,
+                 Text, Whitespace, Name.Function, Whitespace,
+                 Punctuation, Whitespace, Text, Punctuation, Whitespace)),
+            (r'(FUNCTION-ALIAS:)(\s+)'
+                r'(\S+)(\s+)(\S+)(\s+)'
+                r'(\S+)(\s+)'
+                r'(\()(\s+)([^)]+)(\))(\s)',
+             bygroups(Keyword.Namespace, Whitespace,
+                 Text, Whitespace, Name.Function, Whitespace,
+                 Name.Function, Whitespace,
+                 Punctuation, Whitespace, Text, Punctuation, Whitespace)),
+
+            # vocab.private
+            (r'(<PRIVATE|PRIVATE>)(\s)', bygroups(Keyword.Namespace, Whitespace)),
+
+            # strings
+            (r'"""\s(?:.|\n)*?\s"""', String),
+            (r'"(?:\\\\|\\"|[^"])*"', String),
+            (r'(\S+")(\s+)((?:\\\\|\\"|[^"])*")',
+                bygroups(String, Whitespace, String)),
+            (r'(CHAR:)(\s+)(\\[\\abfnrstv]|[^\\]\S*)(\s)',
+                bygroups(String.Char, Whitespace, String.Char, Whitespace)),
+
+            # comments
+            (r'!\s+.*$', Comment),
+            (r'#!\s+.*$', Comment),
+            (r'/\*\s+(?:.|\n)*?\s\*/', Comment),
+
+            # boolean constants
+            (r'[tf]\b', Name.Constant),
+
+            # symbols and literals
+            (r'[\\$]\s+\S+', Name.Constant),
+            (r'M\\\s+\S+\s+\S+', Name.Constant),
+
+            # numbers
+            (r'[+-]?(?:[\d,]*\d)?\.(?:\d([\d,]*\d)?)?(?:[eE][+-]?\d+)?\s', Number),
+            (r'[+-]?\d(?:[\d,]*\d)?(?:[eE][+-]?\d+)?\s', Number),
+            (r'0x[a-fA-F\d](?:[a-fA-F\d,]*[a-fA-F\d])?(?:p\d([\d,]*\d)?)?\s', Number),
+            (r'NAN:\s+[a-fA-F\d](?:[a-fA-F\d,]*[a-fA-F\d])?(?:p\d([\d,]*\d)?)?\s', Number),
+            (r'0b[01]+\s', Number.Bin),
+            (r'0o[0-7]+\s', Number.Oct),
+            (r'(?:\d([\d,]*\d)?)?\+\d(?:[\d,]*\d)?/\d(?:[\d,]*\d)?\s', Number),
+            (r'(?:\-\d([\d,]*\d)?)?\-\d(?:[\d,]*\d)?/\d(?:[\d,]*\d)?\s', Number),
+
+            # keywords
+            (r'(?:deprecated|final|foldable|flushable|inline|recursive)\s',
+             Keyword),
+
+            # builtins
+            (builtin_kernel, bygroups(Name.Builtin, Whitespace)),
+            (builtin_assocs, bygroups(Name.Builtin, Whitespace)),
+            (builtin_combinators, bygroups(Name.Builtin, Whitespace)),
+            (builtin_math, bygroups(Name.Builtin, Whitespace)),
+            (builtin_sequences, bygroups(Name.Builtin, Whitespace)),
+            (builtin_namespaces, bygroups(Name.Builtin, Whitespace)),
+            (builtin_arrays, bygroups(Name.Builtin, Whitespace)),
+            (builtin_io, bygroups(Name.Builtin, Whitespace)),
+            (builtin_strings, bygroups(Name.Builtin, Whitespace)),
+            (builtin_vectors, bygroups(Name.Builtin, Whitespace)),
+            (builtin_continuations, bygroups(Name.Builtin, Whitespace)),
+
+            # everything else is text
+            (r'\S+', Text),
+        ],
+        'stackeffect': [
+            (r'\s+', Whitespace),
+            (r'(\()(\s+)', bygroups(Name.Function, Whitespace), 'stackeffect'),
+            (r'(\))(\s+)', bygroups(Name.Function, Whitespace), '#pop'),
+            (r'(--)(\s+)', bygroups(Name.Function, Whitespace)),
+            (r'\S+', Name.Variable),
+        ],
+        'slots': [
+            (r'\s+', Whitespace),
+            (r'(;)(\s+)', bygroups(Keyword, Whitespace), '#pop'),
+            (r'(\{)(\s+)(\S+)(\s+)([^}]+)(\s+)(\})(\s+)',
+             bygroups(Text, Whitespace, Name.Variable, Whitespace,
+                 Text, Whitespace, Text, Whitespace)),
+            (r'\S+', Name.Variable),
+        ],
+        'vocabs': [
+            (r'\s+', Whitespace),
+            (r'(;)(\s+)', bygroups(Keyword, Whitespace), '#pop'),
+            (r'\S+', Name.Namespace),
+        ],
+        'classes': [
+            (r'\s+', Whitespace),
+            (r'(;)(\s+)', bygroups(Keyword, Whitespace), '#pop'),
+            (r'\S+', Name.Class),
+        ],
+        'words': [
+            (r'\s+', Whitespace),
+            (r'(;)(\s+)', bygroups(Keyword, Whitespace), '#pop'),
+            (r'\S+', Name.Function),
+        ],
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/fantom.py

@@ -0,0 +1,251 @@
+"""
+    pygments.lexers.fantom
+    ~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexer for the Fantom language.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from string import Template
+
+from pygments.lexer import RegexLexer, include, bygroups, using, \
+    this, default, words
+from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation, Literal, Whitespace
+
+__all__ = ['FantomLexer']
+
+
+class FantomLexer(RegexLexer):
+    """
+    For Fantom source code.
+    """
+    name = 'Fantom'
+    aliases = ['fan']
+    filenames = ['*.fan']
+    mimetypes = ['application/x-fantom']
+    url = 'https://www.fantom.org'
+    version_added = '1.5'
+
+    # often used regexes
+    def s(str):
+        return Template(str).substitute(
+            dict(
+                pod=r'[\"\w\.]+',
+                eos=r'\n|;',
+                id=r'[a-zA-Z_]\w*',
+                # all chars which can be part of type definition. Starts with
+                # either letter, or [ (maps), or | (funcs)
+                type=r'(?:\[|[a-zA-Z_]|\|)[:\w\[\]|\->?]*?',
+            )
+        )
+
+    tokens = {
+        'comments': [
+            (r'(?s)/\*.*?\*/', Comment.Multiline),           # Multiline
+            (r'//.*?$', Comment.Single),                    # Single line
+            # TODO: highlight references in fandocs
+            (r'\*\*.*?$', Comment.Special),                 # Fandoc
+            (r'#.*$', Comment.Single)                       # Shell-style
+        ],
+        'literals': [
+            (r'\b-?[\d_]+(ns|ms|sec|min|hr|day)', Number),   # Duration
+            (r'\b-?[\d_]*\.[\d_]+(ns|ms|sec|min|hr|day)', Number),  # Duration with dot
+            (r'\b-?(\d+)?\.\d+(f|F|d|D)?', Number.Float),    # Float/Decimal
+            (r'\b-?0x[0-9a-fA-F_]+', Number.Hex),            # Hex
+            (r'\b-?[\d_]+', Number.Integer),                 # Int
+            (r"'\\.'|'[^\\]'|'\\u[0-9a-f]{4}'", String.Char),  # Char
+            (r'"', Punctuation, 'insideStr'),                # Opening quote
+            (r'`', Punctuation, 'insideUri'),                # Opening accent
+            (r'\b(true|false|null)\b', Keyword.Constant),    # Bool & null
+            (r'(?:(\w+)(::))?(\w+)(<\|)(.*?)(\|>)',          # DSL
+             bygroups(Name.Namespace, Punctuation, Name.Class,
+                      Punctuation, String, Punctuation)),
+            (r'(?:(\w+)(::))?(\w+)?(#)(\w+)?',               # Type/slot literal
+             bygroups(Name.Namespace, Punctuation, Name.Class,
+                      Punctuation, Name.Function)),
+            (r'\[,\]', Literal),                             # Empty list
+            (s(r'($type)(\[,\])'),                           # Typed empty list
+             bygroups(using(this, state='inType'), Literal)),
+            (r'\[:\]', Literal),                             # Empty Map
+            (s(r'($type)(\[:\])'),
+             bygroups(using(this, state='inType'), Literal)),
+        ],
+        'insideStr': [
+            (r'\\\\', String.Escape),                        # Escaped backslash
+            (r'\\"', String.Escape),                         # Escaped "
+            (r'\\`', String.Escape),                         # Escaped `
+            (r'\$\w+', String.Interpol),                     # Subst var
+            (r'\$\{.*?\}', String.Interpol),                 # Subst expr
+            (r'"', Punctuation, '#pop'),                     # Closing quot
+            (r'.', String)                                   # String content
+        ],
+        'insideUri': [  # TODO: remove copy/paste str/uri
+            (r'\\\\', String.Escape),                        # Escaped backslash
+            (r'\\"', String.Escape),                         # Escaped "
+            (r'\\`', String.Escape),                         # Escaped `
+            (r'\$\w+', String.Interpol),                     # Subst var
+            (r'\$\{.*?\}', String.Interpol),                 # Subst expr
+            (r'`', Punctuation, '#pop'),                     # Closing tick
+            (r'.', String.Backtick)                          # URI content
+        ],
+        'protectionKeywords': [
+            (r'\b(public|protected|private|internal)\b', Keyword),
+        ],
+        'typeKeywords': [
+            (r'\b(abstract|final|const|native|facet|enum)\b', Keyword),
+        ],
+        'methodKeywords': [
+            (r'\b(abstract|native|once|override|static|virtual|final)\b',
+             Keyword),
+        ],
+        'fieldKeywords': [
+            (r'\b(abstract|const|final|native|override|static|virtual|'
+             r'readonly)\b', Keyword)
+        ],
+        'otherKeywords': [
+            (words((
+                'try', 'catch', 'throw', 'finally', 'for', 'if', 'else', 'while',
+                'as', 'is', 'isnot', 'switch', 'case', 'default', 'continue',
+                'break', 'do', 'return', 'get', 'set'), prefix=r'\b', suffix=r'\b'),
+             Keyword),
+            (r'\b(it|this|super)\b', Name.Builtin.Pseudo),
+        ],
+        'operators': [
+            (r'\+\+|\-\-|\+|\-|\*|/|\|\||&&|<=>|<=|<|>=|>|=|!|\[|\]', Operator)
+        ],
+        'inType': [
+            (r'[\[\]|\->:?]', Punctuation),
+            (s(r'$id'), Name.Class),
+            default('#pop'),
+
+        ],
+        'root': [
+            include('comments'),
+            include('protectionKeywords'),
+            include('typeKeywords'),
+            include('methodKeywords'),
+            include('fieldKeywords'),
+            include('literals'),
+            include('otherKeywords'),
+            include('operators'),
+            (r'using\b', Keyword.Namespace, 'using'),         # Using stmt
+            (r'@\w+', Name.Decorator, 'facet'),               # Symbol
+            (r'(class|mixin)(\s+)(\w+)', bygroups(Keyword, Whitespace, Name.Class),
+             'inheritance'),                                  # Inheritance list
+
+            # Type var := val
+            (s(r'($type)([ \t]+)($id)(\s*)(:=)'),
+             bygroups(using(this, state='inType'), Whitespace,
+                      Name.Variable, Whitespace, Operator)),
+
+            # var := val
+            (s(r'($id)(\s*)(:=)'),
+             bygroups(Name.Variable, Whitespace, Operator)),
+
+            # .someId( or ->someId( ###
+            (s(r'(\.|(?:\->))($id)(\s*)(\()'),
+             bygroups(Operator, Name.Function, Whitespace, Punctuation),
+             'insideParen'),
+
+            # .someId  or ->someId
+            (s(r'(\.|(?:\->))($id)'),
+             bygroups(Operator, Name.Function)),
+
+            # new makeXXX (
+            (r'(new)(\s+)(make\w*)(\s*)(\()',
+             bygroups(Keyword, Whitespace, Name.Function, Whitespace, Punctuation),
+             'insideMethodDeclArgs'),
+
+            # Type name (
+            (s(r'($type)([ \t]+)'  # Return type and whitespace
+               r'($id)(\s*)(\()'),  # method name + open brace
+             bygroups(using(this, state='inType'), Whitespace,
+                      Name.Function, Whitespace, Punctuation),
+             'insideMethodDeclArgs'),
+
+            # ArgType argName,
+            (s(r'($type)(\s+)($id)(\s*)(,)'),
+             bygroups(using(this, state='inType'), Whitespace, Name.Variable,
+                      Whitespace, Punctuation)),
+
+            # ArgType argName)
+            # Covered in 'insideParen' state
+
+            # ArgType argName -> ArgType|
+            (s(r'($type)(\s+)($id)(\s*)(\->)(\s*)($type)(\|)'),
+             bygroups(using(this, state='inType'), Whitespace, Name.Variable,
+                      Whitespace, Punctuation, Whitespace, using(this, state='inType'),
+                      Punctuation)),
+
+            # ArgType argName|
+            (s(r'($type)(\s+)($id)(\s*)(\|)'),
+             bygroups(using(this, state='inType'), Whitespace, Name.Variable,
+                      Whitespace, Punctuation)),
+
+            # Type var
+            (s(r'($type)([ \t]+)($id)'),
+             bygroups(using(this, state='inType'), Whitespace,
+                      Name.Variable)),
+
+            (r'\(', Punctuation, 'insideParen'),
+            (r'\{', Punctuation, 'insideBrace'),
+            (r'\s+', Whitespace),
+            (r'.', Text)
+        ],
+        'insideParen': [
+            (r'\)', Punctuation, '#pop'),
+            include('root'),
+        ],
+        'insideMethodDeclArgs': [
+            (r'\)', Punctuation, '#pop'),
+            (s(r'($type)(\s+)($id)(\s*)(\))'),
+             bygroups(using(this, state='inType'), Whitespace, Name.Variable,
+                      Whitespace, Punctuation), '#pop'),
+            include('root'),
+        ],
+        'insideBrace': [
+            (r'\}', Punctuation, '#pop'),
+            include('root'),
+        ],
+        'inheritance': [
+            (r'\s+', Whitespace),                                      # Whitespace
+            (r':|,', Punctuation),
+            (r'(?:(\w+)(::))?(\w+)',
+             bygroups(Name.Namespace, Punctuation, Name.Class)),
+            (r'\{', Punctuation, '#pop')
+        ],
+        'using': [
+            (r'[ \t]+', Whitespace),  # consume whitespaces
+            (r'(\[)(\w+)(\])',
+             bygroups(Punctuation, Comment.Special, Punctuation)),  # ffi
+            (r'(\")?([\w.]+)(\")?',
+             bygroups(Punctuation, Name.Namespace, Punctuation)),  # podname
+            (r'::', Punctuation, 'usingClass'),
+            default('#pop')
+        ],
+        'usingClass': [
+            (r'[ \t]+', Whitespace),  # consume whitespaces
+            (r'(as)(\s+)(\w+)',
+             bygroups(Keyword.Declaration, Whitespace, Name.Class), '#pop:2'),
+            (r'[\w$]+', Name.Class),
+            default('#pop:2')  # jump out to root state
+        ],
+        'facet': [
+            (r'\s+', Whitespace),
+            (r'\{', Punctuation, 'facetFields'),
+            default('#pop')
+        ],
+        'facetFields': [
+            include('comments'),
+            include('literals'),
+            include('operators'),
+            (r'\s+', Whitespace),
+            (r'(\s*)(\w+)(\s*)(=)', bygroups(Whitespace, Name, Whitespace, Operator)),
+            (r'\}', Punctuation, '#pop'),
+            (r'\s+', Whitespace),
+            (r'.', Text)
+        ],
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/functional.py

@@ -0,0 +1,21 @@
+"""
+    pygments.lexers.functional
+    ~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+    Just export lexer classes previously contained in this module.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+# ruff: noqa: F401
+from pygments.lexers.lisp import SchemeLexer, CommonLispLexer, RacketLexer, \
+    NewLispLexer, ShenLexer
+from pygments.lexers.haskell import HaskellLexer, LiterateHaskellLexer, \
+    KokaLexer
+from pygments.lexers.theorem import RocqLexer
+from pygments.lexers.erlang import ErlangLexer, ErlangShellLexer, \
+    ElixirConsoleLexer, ElixirLexer
+from pygments.lexers.ml import SMLLexer, OcamlLexer, OpaLexer
+
+__all__ = []

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/futhark.py

@@ -0,0 +1,105 @@
+"""
+    pygments.lexers.futhark
+    ~~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexer for the Futhark language
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import RegexLexer, bygroups
+from pygments.token import Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation, Whitespace
+from pygments import unistring as uni
+
+__all__ = ['FutharkLexer']
+
+
+class FutharkLexer(RegexLexer):
+    """
+    A Futhark lexer
+    """
+    name = 'Futhark'
+    url = 'https://futhark-lang.org/'
+    aliases = ['futhark']
+    filenames = ['*.fut']
+    mimetypes = ['text/x-futhark']
+    version_added = '2.8'
+
+    num_types = ('i8', 'i16', 'i32', 'i64', 'u8', 'u16', 'u32', 'u64', 'f32', 'f64')
+
+    other_types = ('bool', )
+
+    reserved = ('if', 'then', 'else', 'def', 'let', 'loop', 'in', 'with',
+                'type', 'type~', 'type^',
+                'val', 'entry', 'for', 'while', 'do', 'case', 'match',
+                'include', 'import', 'module', 'open', 'local', 'assert', '_')
+
+    ascii = ('NUL', 'SOH', '[SE]TX', 'EOT', 'ENQ', 'ACK',
+             'BEL', 'BS', 'HT', 'LF', 'VT', 'FF', 'CR', 'S[OI]', 'DLE',
+             'DC[1-4]', 'NAK', 'SYN', 'ETB', 'CAN',
+             'EM', 'SUB', 'ESC', '[FGRU]S', 'SP', 'DEL')
+
+    num_postfix = r'({})?'.format('|'.join(num_types))
+
+    identifier_re = '[a-zA-Z_][a-zA-Z_0-9\']*'
+
+    # opstart_re = '+\-\*/%=\!><\|&\^'
+
+    tokens = {
+        'root': [
+            (r'--(.*?)$', Comment.Single),
+            (r'\s+', Whitespace),
+            (r'\(\)', Punctuation),
+            (r'\b({})(?!\')\b'.format('|'.join(reserved)), Keyword.Reserved),
+            (r'\b({})(?!\')\b'.format('|'.join(num_types + other_types)), Keyword.Type),
+
+            # Identifiers
+            (r'#\[([a-zA-Z_\(\) ]*)\]', Comment.Preproc),
+            (rf'[#!]?({identifier_re}\.)*{identifier_re}', Name),
+
+            (r'\\', Operator),
+            (r'[-+/%=!><|&*^][-+/%=!><|&*^.]*', Operator),
+            (r'[][(),:;`{}?.\'~^]', Punctuation),
+
+            #  Numbers
+            (r'0[xX]_*[\da-fA-F](_*[\da-fA-F])*_*[pP][+-]?\d(_*\d)*' + num_postfix,
+             Number.Float),
+            (r'0[xX]_*[\da-fA-F](_*[\da-fA-F])*\.[\da-fA-F](_*[\da-fA-F])*'
+             r'(_*[pP][+-]?\d(_*\d)*)?' + num_postfix, Number.Float),
+            (r'\d(_*\d)*_*[eE][+-]?\d(_*\d)*' + num_postfix, Number.Float),
+            (r'\d(_*\d)*\.\d(_*\d)*(_*[eE][+-]?\d(_*\d)*)?' + num_postfix, Number.Float),
+            (r'0[bB]_*[01](_*[01])*' + num_postfix, Number.Bin),
+            (r'0[xX]_*[\da-fA-F](_*[\da-fA-F])*' + num_postfix, Number.Hex),
+            (r'\d(_*\d)*' + num_postfix, Number.Integer),
+
+            #  Character/String Literals
+            (r"'", String.Char, 'character'),
+            (r'"', String, 'string'),
+            #  Special
+            (r'\[[a-zA-Z_\d]*\]', Keyword.Type),
+            (r'\(\)', Name.Builtin),
+        ],
+        'character': [
+            # Allows multi-chars, incorrectly.
+            (r"[^\\']'", String.Char, '#pop'),
+            (r"\\", String.Escape, 'escape'),
+            ("'", String.Char, '#pop'),
+        ],
+        'string': [
+            (r'[^\\"]+', String),
+            (r"\\", String.Escape, 'escape'),
+            ('"', String, '#pop'),
+        ],
+
+        'escape': [
+            (r'[abfnrtv"\'&\\]', String.Escape, '#pop'),
+            (r'\^[][' + uni.Lu + r'@^_]', String.Escape, '#pop'),
+            ('|'.join(ascii), String.Escape, '#pop'),
+            (r'o[0-7]+', String.Escape, '#pop'),
+            (r'x[\da-fA-F]+', String.Escape, '#pop'),
+            (r'\d+', String.Escape, '#pop'),
+            (r'(\s+)(\\)', bygroups(Whitespace, String.Escape), '#pop'),
+        ],
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/gdscript.py

@@ -0,0 +1,189 @@
+"""
+    pygments.lexers.gdscript
+    ~~~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexer for GDScript.
+
+    Modified by Daniel J. Ramirez <djrmuv@gmail.com> based on the original
+    python.py.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import RegexLexer, include, bygroups, default, words, \
+    combined
+from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation, Whitespace
+
+__all__ = ["GDScriptLexer"]
+
+
+class GDScriptLexer(RegexLexer):
+    """
+    For GDScript source code.
+    """
+
+    name = "GDScript"
+    url = 'https://www.godotengine.org'
+    aliases = ["gdscript", "gd"]
+    filenames = ["*.gd"]
+    mimetypes = ["text/x-gdscript", "application/x-gdscript"]
+    version_added = ''
+
+    def innerstring_rules(ttype):
+        return [
+            # the old style '%s' % (...) string formatting
+            (r"%(\(\w+\))?[-#0 +]*([0-9]+|[*])?(\.([0-9]+|[*]))?"
+             "[hlL]?[E-GXc-giorsux%]",
+             String.Interpol),
+            # backslashes, quotes and formatting signs must be parsed one at a time
+            (r'[^\\\'"%\n]+', ttype),
+            (r'[\'"\\]', ttype),
+            # unhandled string formatting sign
+            (r"%", ttype),
+            # newlines are an error (use "nl" state)
+        ]
+
+    tokens = {
+        "root": [
+            (r"\n", Whitespace),
+            (r'^(\s*)([rRuUbB]{,2})("""(?:.|\n)*?""")',
+             bygroups(Whitespace, String.Affix, String.Doc)),
+            (r"^(\s*)([rRuUbB]{,2})('''(?:.|\n)*?''')",
+             bygroups(Whitespace, String.Affix, String.Doc)),
+            (r"[^\S\n]+", Whitespace),
+            (r"#.*$", Comment.Single),
+            (r"[]{}:(),;[]", Punctuation),
+            (r"(\\)(\n)", bygroups(Text, Whitespace)),
+            (r"\\", Text),
+            (r"(in|and|or|not)\b", Operator.Word),
+            (r"!=|==|<<|>>|&&|\+=|-=|\*=|/=|%=|&=|\|=|\|\||[-~+/*%=<>&^.!|$]",
+             Operator),
+            include("keywords"),
+            (r"(func)(\s+)", bygroups(Keyword, Whitespace), "funcname"),
+            (r"(class)(\s+)", bygroups(Keyword, Whitespace), "classname"),
+            include("builtins"),
+            ('([rR]|[uUbB][rR]|[rR][uUbB])(""")',
+             bygroups(String.Affix, String.Double),
+             "tdqs"),
+            ("([rR]|[uUbB][rR]|[rR][uUbB])(''')",
+             bygroups(String.Affix, String.Single),
+             "tsqs"),
+            ('([rR]|[uUbB][rR]|[rR][uUbB])(")',
+             bygroups(String.Affix, String.Double),
+             "dqs"),
+            ("([rR]|[uUbB][rR]|[rR][uUbB])(')",
+             bygroups(String.Affix, String.Single),
+             "sqs"),
+            ('([uUbB]?)(""")',
+             bygroups(String.Affix, String.Double),
+             combined("stringescape", "tdqs")),
+            ("([uUbB]?)(''')",
+             bygroups(String.Affix, String.Single),
+             combined("stringescape", "tsqs")),
+            ('([uUbB]?)(")',
+             bygroups(String.Affix, String.Double),
+             combined("stringescape", "dqs")),
+            ("([uUbB]?)(')",
+             bygroups(String.Affix, String.Single),
+             combined("stringescape", "sqs")),
+            include("name"),
+            include("numbers"),
+        ],
+        "keywords": [
+            (words(("and", "in", "not", "or", "as", "breakpoint", "class",
+                    "class_name", "extends", "is", "func", "setget", "signal",
+                    "tool", "const", "enum", "export", "onready", "static",
+                    "var", "break", "continue", "if", "elif", "else", "for",
+                    "pass", "return", "match", "while", "remote", "master",
+                    "puppet", "remotesync", "mastersync", "puppetsync"),
+                   suffix=r"\b"), Keyword),
+        ],
+        "builtins": [
+            (words(("Color8", "ColorN", "abs", "acos", "asin", "assert", "atan",
+                    "atan2", "bytes2var", "ceil", "char", "clamp", "convert",
+                    "cos", "cosh", "db2linear", "decimals", "dectime", "deg2rad",
+                    "dict2inst", "ease", "exp", "floor", "fmod", "fposmod",
+                    "funcref", "hash", "inst2dict", "instance_from_id", "is_inf",
+                    "is_nan", "lerp", "linear2db", "load", "log", "max", "min",
+                    "nearest_po2", "pow", "preload", "print", "print_stack",
+                    "printerr", "printraw", "prints", "printt", "rad2deg",
+                    "rand_range", "rand_seed", "randf", "randi", "randomize",
+                    "range", "round", "seed", "sign", "sin", "sinh", "sqrt",
+                    "stepify", "str", "str2var", "tan", "tan", "tanh",
+                    "type_exist", "typeof", "var2bytes", "var2str", "weakref",
+                    "yield"), prefix=r"(?<!\.)", suffix=r"\b"),
+             Name.Builtin),
+            (r"((?<!\.)(self|false|true)|(PI|TAU|NAN|INF)" r")\b",
+             Name.Builtin.Pseudo),
+            (words(("bool", "int", "float", "String", "NodePath", "Vector2",
+                    "Rect2", "Transform2D", "Vector3", "Rect3", "Plane", "Quat",
+                    "Basis", "Transform", "Color", "RID", "Object", "NodePath",
+                    "Dictionary", "Array", "PackedByteArray", "PackedInt32Array",
+                    "PackedInt64Array", "PackedFloat32Array", "PackedFloat64Array",
+                    "PackedStringArray", "PackedVector2Array", "PackedVector3Array",
+                    "PackedColorArray", "null", "void"),
+                   prefix=r"(?<!\.)", suffix=r"\b"),
+             Name.Builtin.Type),
+        ],
+        "numbers": [
+            (r"(\d+\.\d*|\d*\.\d+)([eE][+-]?[0-9]+)?j?", Number.Float),
+            (r"\d+[eE][+-]?[0-9]+j?", Number.Float),
+            (r"0[xX][a-fA-F0-9]+", Number.Hex),
+            (r"\d+j?", Number.Integer),
+        ],
+        "name": [(r"[a-zA-Z_]\w*", Name)],
+        "funcname": [(r"[a-zA-Z_]\w*", Name.Function, "#pop"), default("#pop")],
+        "classname": [(r"[a-zA-Z_]\w*", Name.Class, "#pop")],
+        "stringescape": [
+            (
+                r'\\([\\abfnrtv"\']|\n|N\{.*?\}|u[a-fA-F0-9]{4}|'
+                r"U[a-fA-F0-9]{8}|x[a-fA-F0-9]{2}|[0-7]{1,3})",
+                String.Escape,
+            )
+        ],
+        "strings-single": innerstring_rules(String.Single),
+        "strings-double": innerstring_rules(String.Double),
+        "dqs": [
+            (r'"', String.Double, "#pop"),
+            (r'\\\\|\\"|\\\n', String.Escape),  # included here for raw strings
+            include("strings-double"),
+        ],
+        "sqs": [
+            (r"'", String.Single, "#pop"),
+            (r"\\\\|\\'|\\\n", String.Escape),  # included here for raw strings
+            include("strings-single"),
+        ],
+        "tdqs": [
+            (r'"""', String.Double, "#pop"),
+            include("strings-double"),
+            (r"\n", Whitespace),
+        ],
+        "tsqs": [
+            (r"'''", String.Single, "#pop"),
+            include("strings-single"),
+            (r"\n", Whitespace),
+        ],
+    }
+
+    def analyse_text(text):
+        score = 0.0
+
+        if re.search(
+            r"func (_ready|_init|_input|_process|_unhandled_input)", text
+        ):
+            score += 0.8
+
+        if re.search(
+            r"(extends |class_name |onready |preload|load|setget|func [^_])",
+            text
+        ):
+            score += 0.4
+
+        if re.search(r"(var|const|enum|export|signal|tool)", text):
+            score += 0.2
+
+        return min(score, 1.0)

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/graphics.py

@@ -0,0 +1,794 @@
+"""
+    pygments.lexers.graphics
+    ~~~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexers for computer graphics and plotting related languages.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import RegexLexer, words, include, bygroups, using, \
+    this, default
+from pygments.token import Text, Comment, Operator, Keyword, Name, \
+    Number, Punctuation, String, Whitespace
+
+__all__ = ['GLShaderLexer', 'PostScriptLexer', 'AsymptoteLexer', 'GnuplotLexer',
+           'PovrayLexer', 'HLSLShaderLexer']
+
+
+class GLShaderLexer(RegexLexer):
+    """
+    GLSL (OpenGL Shader) lexer.
+    """
+    name = 'GLSL'
+    aliases = ['glsl']
+    filenames = ['*.vert', '*.frag', '*.geo']
+    mimetypes = ['text/x-glslsrc']
+    url = 'https://www.khronos.org/api/opengl'
+    version_added = '1.1'
+
+    tokens = {
+        'root': [
+            (r'#(?:.*\\\n)*.*$', Comment.Preproc),
+            (r'//.*$', Comment.Single),
+            (r'/(\\\n)?[*](.|\n)*?[*](\\\n)?/', Comment.Multiline),
+            (r'\+|-|~|!=?|\*|/|%|<<|>>|<=?|>=?|==?|&&?|\^|\|\|?',
+             Operator),
+            (r'[?:]', Operator),  # quick hack for ternary
+            (r'\bdefined\b', Operator),
+            (r'[;{}(),\[\]]', Punctuation),
+            # FIXME when e is present, no decimal point needed
+            (r'[+-]?\d*\.\d+([eE][-+]?\d+)?', Number.Float),
+            (r'[+-]?\d+\.\d*([eE][-+]?\d+)?', Number.Float),
+            (r'0[xX][0-9a-fA-F]*', Number.Hex),
+            (r'0[0-7]*', Number.Oct),
+            (r'[1-9][0-9]*', Number.Integer),
+            (words((
+                # Storage qualifiers
+                'attribute', 'const', 'uniform', 'varying',
+                'buffer', 'shared', 'in', 'out',
+                # Layout qualifiers
+                'layout',
+                # Interpolation qualifiers
+                'flat', 'smooth', 'noperspective',
+                # Auxiliary qualifiers
+                'centroid', 'sample', 'patch',
+                # Parameter qualifiers. Some double as Storage qualifiers
+                'inout',
+                # Precision qualifiers
+                'lowp', 'mediump', 'highp', 'precision',
+                # Invariance qualifiers
+                'invariant',
+                # Precise qualifiers
+                'precise',
+                # Memory qualifiers
+                'coherent', 'volatile', 'restrict', 'readonly', 'writeonly',
+                # Statements
+                'break', 'continue', 'do', 'for', 'while', 'switch',
+                'case', 'default', 'if', 'else', 'subroutine',
+                'discard', 'return', 'struct'),
+                prefix=r'\b', suffix=r'\b'),
+             Keyword),
+            (words((
+                # Boolean values
+                'true', 'false'),
+                prefix=r'\b', suffix=r'\b'),
+             Keyword.Constant),
+            (words((
+                # Miscellaneous types
+                'void', 'atomic_uint',
+                # Floating-point scalars and vectors
+                'float', 'vec2', 'vec3', 'vec4',
+                'double', 'dvec2', 'dvec3', 'dvec4',
+                # Integer scalars and vectors
+                'int', 'ivec2', 'ivec3', 'ivec4',
+                'uint', 'uvec2', 'uvec3', 'uvec4',
+                # Boolean scalars and vectors
+                'bool', 'bvec2', 'bvec3', 'bvec4',
+                # Matrices
+                'mat2', 'mat3', 'mat4', 'dmat2', 'dmat3', 'dmat4',
+                'mat2x2', 'mat2x3', 'mat2x4', 'dmat2x2', 'dmat2x3', 'dmat2x4',
+                'mat3x2', 'mat3x3', 'mat3x4', 'dmat3x2', 'dmat3x3',
+                'dmat3x4', 'mat4x2', 'mat4x3', 'mat4x4', 'dmat4x2', 'dmat4x3', 'dmat4x4',
+                # Floating-point samplers
+                'sampler1D', 'sampler2D', 'sampler3D', 'samplerCube',
+                'sampler1DArray', 'sampler2DArray', 'samplerCubeArray',
+                'sampler2DRect', 'samplerBuffer',
+                'sampler2DMS', 'sampler2DMSArray',
+                # Shadow samplers
+                'sampler1DShadow', 'sampler2DShadow', 'samplerCubeShadow',
+                'sampler1DArrayShadow', 'sampler2DArrayShadow',
+                'samplerCubeArrayShadow', 'sampler2DRectShadow',
+                # Signed integer samplers
+                'isampler1D', 'isampler2D', 'isampler3D', 'isamplerCube',
+                'isampler1DArray', 'isampler2DArray', 'isamplerCubeArray',
+                'isampler2DRect', 'isamplerBuffer',
+                'isampler2DMS', 'isampler2DMSArray',
+                # Unsigned integer samplers
+                'usampler1D', 'usampler2D', 'usampler3D', 'usamplerCube',
+                'usampler1DArray', 'usampler2DArray', 'usamplerCubeArray',
+                'usampler2DRect', 'usamplerBuffer',
+                'usampler2DMS', 'usampler2DMSArray',
+                # Floating-point image types
+                'image1D', 'image2D', 'image3D', 'imageCube',
+                'image1DArray', 'image2DArray', 'imageCubeArray',
+                'image2DRect', 'imageBuffer',
+                'image2DMS', 'image2DMSArray',
+                # Signed integer image types
+                'iimage1D', 'iimage2D', 'iimage3D', 'iimageCube',
+                'iimage1DArray', 'iimage2DArray', 'iimageCubeArray',
+                'iimage2DRect', 'iimageBuffer',
+                'iimage2DMS', 'iimage2DMSArray',
+                # Unsigned integer image types
+                'uimage1D', 'uimage2D', 'uimage3D', 'uimageCube',
+                'uimage1DArray', 'uimage2DArray', 'uimageCubeArray',
+                'uimage2DRect', 'uimageBuffer',
+                'uimage2DMS', 'uimage2DMSArray'),
+                prefix=r'\b', suffix=r'\b'),
+             Keyword.Type),
+            (words((
+                # Reserved for future use.
+                'common', 'partition', 'active', 'asm', 'class',
+                'union', 'enum', 'typedef', 'template', 'this',
+                'resource', 'goto', 'inline', 'noinline', 'public',
+                'static', 'extern', 'external', 'interface', 'long',
+                'short', 'half', 'fixed', 'unsigned', 'superp', 'input',
+                'output', 'hvec2', 'hvec3', 'hvec4', 'fvec2', 'fvec3',
+                'fvec4', 'sampler3DRect', 'filter', 'sizeof', 'cast',
+                'namespace', 'using'),
+                prefix=r'\b', suffix=r'\b'),
+             Keyword.Reserved),
+            # All names beginning with "gl_" are reserved.
+            (r'gl_\w*', Name.Builtin),
+            (r'[a-zA-Z_]\w*', Name),
+            (r'\.', Punctuation),
+            (r'\s+', Whitespace),
+        ],
+    }
+
+
+class HLSLShaderLexer(RegexLexer):
+    """
+    HLSL (Microsoft Direct3D Shader) lexer.
+    """
+    name = 'HLSL'
+    aliases = ['hlsl']
+    filenames = ['*.hlsl', '*.hlsli']
+    mimetypes = ['text/x-hlsl']
+    url = 'https://learn.microsoft.com/en-us/windows/win32/direct3dhlsl/dx-graphics-hlsl'
+    version_added = '2.3'
+
+    tokens = {
+        'root': [
+            (r'#(?:.*\\\n)*.*$', Comment.Preproc),
+            (r'//.*$', Comment.Single),
+            (r'/(\\\n)?[*](.|\n)*?[*](\\\n)?/', Comment.Multiline),
+            (r'\+|-|~|!=?|\*|/|%|<<|>>|<=?|>=?|==?|&&?|\^|\|\|?',
+             Operator),
+            (r'[?:]', Operator),  # quick hack for ternary
+            (r'\bdefined\b', Operator),
+            (r'[;{}(),.\[\]]', Punctuation),
+            # FIXME when e is present, no decimal point needed
+            (r'[+-]?\d*\.\d+([eE][-+]?\d+)?f?', Number.Float),
+            (r'[+-]?\d+\.\d*([eE][-+]?\d+)?f?', Number.Float),
+            (r'0[xX][0-9a-fA-F]*', Number.Hex),
+            (r'0[0-7]*', Number.Oct),
+            (r'[1-9][0-9]*', Number.Integer),
+            (r'"', String, 'string'),
+            (words((
+                'asm','asm_fragment','break','case','cbuffer','centroid','class',
+                'column_major','compile','compile_fragment','const','continue',
+                'default','discard','do','else','export','extern','for','fxgroup',
+                'globallycoherent','groupshared','if','in','inline','inout',
+                'interface','line','lineadj','linear','namespace','nointerpolation',
+                'noperspective','NULL','out','packoffset','pass','pixelfragment',
+                'point','precise','return','register','row_major','sample',
+                'sampler','shared','stateblock','stateblock_state','static',
+                'struct','switch','tbuffer','technique','technique10',
+                'technique11','texture','typedef','triangle','triangleadj',
+                'uniform','vertexfragment','volatile','while'),
+                prefix=r'\b', suffix=r'\b'),
+             Keyword),
+            (words(('true','false'), prefix=r'\b', suffix=r'\b'),
+             Keyword.Constant),
+            (words((
+                'auto','catch','char','const_cast','delete','dynamic_cast','enum',
+                'explicit','friend','goto','long','mutable','new','operator',
+                'private','protected','public','reinterpret_cast','short','signed',
+                'sizeof','static_cast','template','this','throw','try','typename',
+                'union','unsigned','using','virtual'),
+                prefix=r'\b', suffix=r'\b'),
+             Keyword.Reserved),
+            (words((
+                'dword','matrix','snorm','string','unorm','unsigned','void','vector',
+                'BlendState','Buffer','ByteAddressBuffer','ComputeShader',
+                'DepthStencilState','DepthStencilView','DomainShader',
+                'GeometryShader','HullShader','InputPatch','LineStream',
+                'OutputPatch','PixelShader','PointStream','RasterizerState',
+                'RenderTargetView','RasterizerOrderedBuffer',
+                'RasterizerOrderedByteAddressBuffer',
+                'RasterizerOrderedStructuredBuffer','RasterizerOrderedTexture1D',
+                'RasterizerOrderedTexture1DArray','RasterizerOrderedTexture2D',
+                'RasterizerOrderedTexture2DArray','RasterizerOrderedTexture3D',
+                'RWBuffer','RWByteAddressBuffer','RWStructuredBuffer',
+                'RWTexture1D','RWTexture1DArray','RWTexture2D','RWTexture2DArray',
+                'RWTexture3D','SamplerState','SamplerComparisonState',
+                'StructuredBuffer','Texture1D','Texture1DArray','Texture2D',
+                'Texture2DArray','Texture2DMS','Texture2DMSArray','Texture3D',
+                'TextureCube','TextureCubeArray','TriangleStream','VertexShader'),
+                prefix=r'\b', suffix=r'\b'),
+             Keyword.Type),
+            (words((
+                'bool','double','float','int','half','min16float','min10float',
+                'min16int','min12int','min16uint','uint'),
+                prefix=r'\b', suffix=r'([1-4](x[1-4])?)?\b'),
+             Keyword.Type),     # vector and matrix types
+            (words((
+                'abort','abs','acos','all','AllMemoryBarrier',
+                'AllMemoryBarrierWithGroupSync','any','AppendStructuredBuffer',
+                'asdouble','asfloat','asin','asint','asuint','asuint','atan',
+                'atan2','ceil','CheckAccessFullyMapped','clamp','clip',
+                'CompileShader','ConsumeStructuredBuffer','cos','cosh','countbits',
+                'cross','D3DCOLORtoUBYTE4','ddx','ddx_coarse','ddx_fine','ddy',
+                'ddy_coarse','ddy_fine','degrees','determinant',
+                'DeviceMemoryBarrier','DeviceMemoryBarrierWithGroupSync','distance',
+                'dot','dst','errorf','EvaluateAttributeAtCentroid',
+                'EvaluateAttributeAtSample','EvaluateAttributeSnapped','exp',
+                'exp2','f16tof32','f32tof16','faceforward','firstbithigh',
+                'firstbitlow','floor','fma','fmod','frac','frexp','fwidth',
+                'GetRenderTargetSampleCount','GetRenderTargetSamplePosition',
+                'GlobalOrderedCountIncrement','GroupMemoryBarrier',
+                'GroupMemoryBarrierWithGroupSync','InterlockedAdd','InterlockedAnd',
+                'InterlockedCompareExchange','InterlockedCompareStore',
+                'InterlockedExchange','InterlockedMax','InterlockedMin',
+                'InterlockedOr','InterlockedXor','isfinite','isinf','isnan',
+                'ldexp','length','lerp','lit','log','log10','log2','mad','max',
+                'min','modf','msad4','mul','noise','normalize','pow','printf',
+                'Process2DQuadTessFactorsAvg','Process2DQuadTessFactorsMax',
+                'Process2DQuadTessFactorsMin','ProcessIsolineTessFactors',
+                'ProcessQuadTessFactorsAvg','ProcessQuadTessFactorsMax',
+                'ProcessQuadTessFactorsMin','ProcessTriTessFactorsAvg',
+                'ProcessTriTessFactorsMax','ProcessTriTessFactorsMin',
+                'QuadReadLaneAt','QuadSwapX','QuadSwapY','radians','rcp',
+                'reflect','refract','reversebits','round','rsqrt','saturate',
+                'sign','sin','sincos','sinh','smoothstep','sqrt','step','tan',
+                'tanh','tex1D','tex1D','tex1Dbias','tex1Dgrad','tex1Dlod',
+                'tex1Dproj','tex2D','tex2D','tex2Dbias','tex2Dgrad','tex2Dlod',
+                'tex2Dproj','tex3D','tex3D','tex3Dbias','tex3Dgrad','tex3Dlod',
+                'tex3Dproj','texCUBE','texCUBE','texCUBEbias','texCUBEgrad',
+                'texCUBElod','texCUBEproj','transpose','trunc','WaveAllBitAnd',
+                'WaveAllMax','WaveAllMin','WaveAllBitOr','WaveAllBitXor',
+                'WaveAllEqual','WaveAllProduct','WaveAllSum','WaveAllTrue',
+                'WaveAnyTrue','WaveBallot','WaveGetLaneCount','WaveGetLaneIndex',
+                'WaveGetOrderedIndex','WaveIsHelperLane','WaveOnce',
+                'WavePrefixProduct','WavePrefixSum','WaveReadFirstLane',
+                'WaveReadLaneAt'),
+                prefix=r'\b', suffix=r'\b'),
+             Name.Builtin),     # built-in functions
+            (words((
+                'SV_ClipDistance','SV_ClipDistance0','SV_ClipDistance1',
+                'SV_Culldistance','SV_CullDistance0','SV_CullDistance1',
+                'SV_Coverage','SV_Depth','SV_DepthGreaterEqual',
+                'SV_DepthLessEqual','SV_DispatchThreadID','SV_DomainLocation',
+                'SV_GroupID','SV_GroupIndex','SV_GroupThreadID','SV_GSInstanceID',
+                'SV_InnerCoverage','SV_InsideTessFactor','SV_InstanceID',
+                'SV_IsFrontFace','SV_OutputControlPointID','SV_Position',
+                'SV_PrimitiveID','SV_RenderTargetArrayIndex','SV_SampleIndex',
+                'SV_StencilRef','SV_TessFactor','SV_VertexID',
+                'SV_ViewportArrayIndex'),
+                prefix=r'\b', suffix=r'\b'),
+             Name.Decorator),   # system-value semantics
+            (r'\bSV_Target[0-7]?\b', Name.Decorator),
+            (words((
+                'allow_uav_condition','branch','call','domain','earlydepthstencil',
+                'fastopt','flatten','forcecase','instance','loop','maxtessfactor',
+                'numthreads','outputcontrolpoints','outputtopology','partitioning',
+                'patchconstantfunc','unroll'),
+                prefix=r'\b', suffix=r'\b'),
+             Name.Decorator),   # attributes
+            (r'[a-zA-Z_]\w*', Name),
+            (r'\\$', Comment.Preproc),  # backslash at end of line -- usually macro continuation
+            (r'\s+', Whitespace),
+        ],
+        'string': [
+            (r'"', String, '#pop'),
+            (r'\\([\\abfnrtv"\']|x[a-fA-F0-9]{2,4}|'
+             r'u[a-fA-F0-9]{4}|U[a-fA-F0-9]{8}|[0-7]{1,3})', String.Escape),
+            (r'[^\\"\n]+', String),  # all other characters
+            (r'\\\n', String),  # line continuation
+            (r'\\', String),  # stray backslash
+        ],
+    }
+
+
+class PostScriptLexer(RegexLexer):
+    """
+    Lexer for PostScript files.
+    """
+    name = 'PostScript'
+    url = 'https://en.wikipedia.org/wiki/PostScript'
+    aliases = ['postscript', 'postscr']
+    filenames = ['*.ps', '*.eps']
+    mimetypes = ['application/postscript']
+    version_added = '1.4'
+
+    delimiter = r'()<>\[\]{}/%\s'
+    delimiter_end = rf'(?=[{delimiter}])'
+
+    valid_name_chars = rf'[^{delimiter}]'
+    valid_name = rf"{valid_name_chars}+{delimiter_end}"
+
+    tokens = {
+        'root': [
+            # All comment types
+            (r'^%!.+$', Comment.Preproc),
+            (r'%%.*$', Comment.Special),
+            (r'(^%.*\n){2,}', Comment.Multiline),
+            (r'%.*$', Comment.Single),
+
+            # String literals are awkward; enter separate state.
+            (r'\(', String, 'stringliteral'),
+
+            (r'[{}<>\[\]]', Punctuation),
+
+            # Numbers
+            (r'<[0-9A-Fa-f]+>' + delimiter_end, Number.Hex),
+            # Slight abuse: use Oct to signify any explicit base system
+            (r'[0-9]+\#(\-|\+)?([0-9]+\.?|[0-9]*\.[0-9]+|[0-9]+\.[0-9]*)'
+             r'((e|E)[0-9]+)?' + delimiter_end, Number.Oct),
+            (r'(\-|\+)?([0-9]+\.?|[0-9]*\.[0-9]+|[0-9]+\.[0-9]*)((e|E)[0-9]+)?'
+             + delimiter_end, Number.Float),
+            (r'(\-|\+)?[0-9]+' + delimiter_end, Number.Integer),
+
+            # References
+            (rf'\/{valid_name}', Name.Variable),
+
+            # Names
+            (valid_name, Name.Function),      # Anything else is executed
+
+            # These keywords taken from
+            # <http://www.math.ubc.ca/~cass/graphics/manual/pdf/a1.pdf>
+            # Is there an authoritative list anywhere that doesn't involve
+            # trawling documentation?
+
+            (r'(false|true)' + delimiter_end, Keyword.Constant),
+
+            # Conditionals / flow control
+            (r'(eq|ne|g[et]|l[et]|and|or|not|if(?:else)?|for(?:all)?)'
+             + delimiter_end, Keyword.Reserved),
+
+            (words((
+                'abs', 'add', 'aload', 'arc', 'arcn', 'array', 'atan', 'begin',
+                'bind', 'ceiling', 'charpath', 'clip', 'closepath', 'concat',
+                'concatmatrix', 'copy', 'cos', 'currentlinewidth', 'currentmatrix',
+                'currentpoint', 'curveto', 'cvi', 'cvs', 'def', 'defaultmatrix',
+                'dict', 'dictstackoverflow', 'div', 'dtransform', 'dup', 'end',
+                'exch', 'exec', 'exit', 'exp', 'fill', 'findfont', 'floor', 'get',
+                'getinterval', 'grestore', 'gsave', 'gt', 'identmatrix', 'idiv',
+                'idtransform', 'index', 'invertmatrix', 'itransform', 'length',
+                'lineto', 'ln', 'load', 'log', 'loop', 'matrix', 'mod', 'moveto',
+                'mul', 'neg', 'newpath', 'pathforall', 'pathbbox', 'pop', 'print',
+                'pstack', 'put', 'quit', 'rand', 'rangecheck', 'rcurveto', 'repeat',
+                'restore', 'rlineto', 'rmoveto', 'roll', 'rotate', 'round', 'run',
+                'save', 'scale', 'scalefont', 'setdash', 'setfont', 'setgray',
+                'setlinecap', 'setlinejoin', 'setlinewidth', 'setmatrix',
+                'setrgbcolor', 'shfill', 'show', 'showpage', 'sin', 'sqrt',
+                'stack', 'stringwidth', 'stroke', 'strokepath', 'sub', 'syntaxerror',
+                'transform', 'translate', 'truncate', 'typecheck', 'undefined',
+                'undefinedfilename', 'undefinedresult'), suffix=delimiter_end),
+             Name.Builtin),
+
+            (r'\s+', Whitespace),
+        ],
+
+        'stringliteral': [
+            (r'[^()\\]+', String),
+            (r'\\', String.Escape, 'escape'),
+            (r'\(', String, '#push'),
+            (r'\)', String, '#pop'),
+        ],
+
+        'escape': [
+            (r'[0-8]{3}|n|r|t|b|f|\\|\(|\)', String.Escape, '#pop'),
+            default('#pop'),
+        ],
+    }
+
+
+class AsymptoteLexer(RegexLexer):
+    """
+    For Asymptote source code.
+    """
+    name = 'Asymptote'
+    url = 'http://asymptote.sf.net/'
+    aliases = ['asymptote', 'asy']
+    filenames = ['*.asy']
+    mimetypes = ['text/x-asymptote']
+    version_added = '1.2'
+
+    #: optional Comment or Whitespace
+    _ws = r'(?:\s|//.*?\n|/\*.*?\*/)+'
+
+    tokens = {
+        'whitespace': [
+            (r'\n', Whitespace),
+            (r'\s+', Whitespace),
+            (r'(\\)(\n)', bygroups(Text, Whitespace)),  # line continuation
+            (r'//(\n|(.|\n)*?[^\\]\n)', Comment),
+            (r'/(\\\n)?\*(.|\n)*?\*(\\\n)?/', Comment),
+        ],
+        'statements': [
+            # simple string (TeX friendly)
+            (r'"(\\\\|\\[^\\]|[^"\\])*"', String),
+            # C style string (with character escapes)
+            (r"'", String, 'string'),
+            (r'(\d+\.\d*|\.\d+|\d+)[eE][+-]?\d+[lL]?', Number.Float),
+            (r'(\d+\.\d*|\.\d+|\d+[fF])[fF]?', Number.Float),
+            (r'0x[0-9a-fA-F]+[Ll]?', Number.Hex),
+            (r'0[0-7]+[Ll]?', Number.Oct),
+            (r'\d+[Ll]?', Number.Integer),
+            (r'[~!%^&*+=|?:<>/-]', Operator),
+            (r'[()\[\],.]', Punctuation),
+            (r'\b(case)(.+?)(:)', bygroups(Keyword, using(this), Text)),
+            (r'(and|controls|tension|atleast|curl|if|else|while|for|do|'
+             r'return|break|continue|struct|typedef|new|access|import|'
+             r'unravel|from|include|quote|static|public|private|restricted|'
+             r'this|explicit|true|false|null|cycle|newframe|operator)\b', Keyword),
+            # Since an asy-type-name can be also an asy-function-name,
+            # in the following we test if the string "  [a-zA-Z]" follows
+            # the Keyword.Type.
+            # Of course it is not perfect !
+            (r'(Braid|FitResult|Label|Legend|TreeNode|abscissa|arc|arrowhead|'
+             r'binarytree|binarytreeNode|block|bool|bool3|bounds|bqe|circle|'
+             r'conic|coord|coordsys|cputime|ellipse|file|filltype|frame|grid3|'
+             r'guide|horner|hsv|hyperbola|indexedTransform|int|inversion|key|'
+             r'light|line|linefit|marginT|marker|mass|object|pair|parabola|path|'
+             r'path3|pen|picture|point|position|projection|real|revolution|'
+             r'scaleT|scientific|segment|side|slice|splitface|string|surface|'
+             r'tensionSpecifier|ticklocate|ticksgridT|tickvalues|transform|'
+             r'transformation|tree|triangle|trilinear|triple|vector|'
+             r'vertex|void)(?=\s+[a-zA-Z])', Keyword.Type),
+            # Now the asy-type-name which are not asy-function-name
+            # except yours !
+            # Perhaps useless
+            (r'(Braid|FitResult|TreeNode|abscissa|arrowhead|block|bool|bool3|'
+             r'bounds|coord|frame|guide|horner|int|linefit|marginT|pair|pen|'
+             r'picture|position|real|revolution|slice|splitface|ticksgridT|'
+             r'tickvalues|tree|triple|vertex|void)\b', Keyword.Type),
+            (r'[a-zA-Z_]\w*:(?!:)', Name.Label),
+            (r'[a-zA-Z_]\w*', Name),
+        ],
+        'root': [
+            include('whitespace'),
+            # functions
+            (r'((?:[\w*\s])+?(?:\s|\*))'  # return arguments
+             r'([a-zA-Z_]\w*)'            # method name
+             r'(\s*\([^;]*?\))'           # signature
+             r'(' + _ws + r')(\{)',
+             bygroups(using(this), Name.Function, using(this), using(this),
+                      Punctuation),
+             'function'),
+            # function declarations
+            (r'((?:[\w*\s])+?(?:\s|\*))'  # return arguments
+             r'([a-zA-Z_]\w*)'            # method name
+             r'(\s*\([^;]*?\))'           # signature
+             r'(' + _ws + r')(;)',
+             bygroups(using(this), Name.Function, using(this), using(this),
+                      Punctuation)),
+            default('statement'),
+        ],
+        'statement': [
+            include('whitespace'),
+            include('statements'),
+            ('[{}]', Punctuation),
+            (';', Punctuation, '#pop'),
+        ],
+        'function': [
+            include('whitespace'),
+            include('statements'),
+            (';', Punctuation),
+            (r'\{', Punctuation, '#push'),
+            (r'\}', Punctuation, '#pop'),
+        ],
+        'string': [
+            (r"'", String, '#pop'),
+            (r'\\([\\abfnrtv"\'?]|x[a-fA-F0-9]{2,4}|[0-7]{1,3})', String.Escape),
+            (r'\n', String),
+            (r"[^\\'\n]+", String),  # all other characters
+            (r'\\\n', String),
+            (r'\\n', String),        # line continuation
+            (r'\\', String),         # stray backslash
+        ],
+    }
+
+    def get_tokens_unprocessed(self, text):
+        from pygments.lexers._asy_builtins import ASYFUNCNAME, ASYVARNAME
+        for index, token, value in \
+                RegexLexer.get_tokens_unprocessed(self, text):
+            if token is Name and value in ASYFUNCNAME:
+                token = Name.Function
+            elif token is Name and value in ASYVARNAME:
+                token = Name.Variable
+            yield index, token, value
+
+
+def _shortened(word):
+    dpos = word.find('$')
+    return '|'.join(word[:dpos] + word[dpos+1:i] + r'\b'
+                    for i in range(len(word), dpos, -1))
+
+
+def _shortened_many(*words):
+    return '|'.join(map(_shortened, words))
+
+
+class GnuplotLexer(RegexLexer):
+    """
+    For Gnuplot plotting scripts.
+    """
+
+    name = 'Gnuplot'
+    url = 'http://gnuplot.info/'
+    aliases = ['gnuplot']
+    filenames = ['*.plot', '*.plt']
+    mimetypes = ['text/x-gnuplot']
+    version_added = '0.11'
+
+    tokens = {
+        'root': [
+            include('whitespace'),
+            (_shortened('bi$nd'), Keyword, 'bind'),
+            (_shortened_many('ex$it', 'q$uit'), Keyword, 'quit'),
+            (_shortened('f$it'), Keyword, 'fit'),
+            (r'(if)(\s*)(\()', bygroups(Keyword, Text, Punctuation), 'if'),
+            (r'else\b', Keyword),
+            (_shortened('pa$use'), Keyword, 'pause'),
+            (_shortened_many('p$lot', 'rep$lot', 'sp$lot'), Keyword, 'plot'),
+            (_shortened('sa$ve'), Keyword, 'save'),
+            (_shortened('se$t'), Keyword, ('genericargs', 'optionarg')),
+            (_shortened_many('sh$ow', 'uns$et'),
+             Keyword, ('noargs', 'optionarg')),
+            (_shortened_many('low$er', 'ra$ise', 'ca$ll', 'cd$', 'cl$ear',
+                             'h$elp', '\\?$', 'hi$story', 'l$oad', 'pr$int',
+                             'pwd$', 're$read', 'res$et', 'scr$eendump',
+                             'she$ll', 'sy$stem', 'up$date'),
+             Keyword, 'genericargs'),
+            (_shortened_many('pwd$', 're$read', 'res$et', 'scr$eendump',
+                             'she$ll', 'test$'),
+             Keyword, 'noargs'),
+            (r'([a-zA-Z_]\w*)(\s*)(=)',
+             bygroups(Name.Variable, Whitespace, Operator), 'genericargs'),
+            (r'([a-zA-Z_]\w*)(\s*)(\()(.*?)(\))(\s*)(=)',
+             bygroups(Name.Function, Whitespace, Punctuation,
+                      Text, Punctuation, Whitespace, Operator), 'genericargs'),
+            (r'@[a-zA-Z_]\w*', Name.Constant),  # macros
+            (r';', Keyword),
+        ],
+        'comment': [
+            (r'[^\\\n]+', Comment),
+            (r'\\\n', Comment),
+            (r'\\', Comment),
+            # don't add the newline to the Comment token
+            default('#pop'),
+        ],
+        'whitespace': [
+            ('#', Comment, 'comment'),
+            (r'[ \t\v\f]+', Whitespace),
+        ],
+        'noargs': [
+            include('whitespace'),
+            # semicolon and newline end the argument list
+            (r';', Punctuation, '#pop'),
+            (r'\n', Whitespace, '#pop'),
+        ],
+        'dqstring': [
+            (r'"', String, '#pop'),
+            (r'\\([\\abfnrtv"\']|x[a-fA-F0-9]{2,4}|[0-7]{1,3})', String.Escape),
+            (r'[^\\"\n]+', String),   # all other characters
+            (r'\\\n', String),        # line continuation
+            (r'\\', String),          # stray backslash
+            (r'\n', Whitespace, '#pop'),  # newline ends the string too
+        ],
+        'sqstring': [
+            (r"''", String),          # escaped single quote
+            (r"'", String, '#pop'),
+            (r"[^\\'\n]+", String),   # all other characters
+            (r'\\\n', String),        # line continuation
+            (r'\\', String),          # normal backslash
+            (r'\n', Whitespace, '#pop'),  # newline ends the string too
+        ],
+        'genericargs': [
+            include('noargs'),
+            (r'"', String, 'dqstring'),
+            (r"'", String, 'sqstring'),
+            (r'(\d+\.\d*|\.\d+|\d+)[eE][+-]?\d+', Number.Float),
+            (r'(\d+\.\d*|\.\d+)', Number.Float),
+            (r'-?\d+', Number.Integer),
+            ('[,.~!%^&*+=|?:<>/-]', Operator),
+            (r'[{}()\[\]]', Punctuation),
+            (r'(eq|ne)\b', Operator.Word),
+            (r'([a-zA-Z_]\w*)(\s*)(\()',
+             bygroups(Name.Function, Text, Punctuation)),
+            (r'[a-zA-Z_]\w*', Name),
+            (r'@[a-zA-Z_]\w*', Name.Constant),  # macros
+            (r'(\\)(\n)', bygroups(Text, Whitespace)),
+        ],
+        'optionarg': [
+            include('whitespace'),
+            (_shortened_many(
+                "a$ll", "an$gles", "ar$row", "au$toscale", "b$ars", "bor$der",
+                "box$width", "cl$abel", "c$lip", "cn$trparam", "co$ntour", "da$ta",
+                "data$file", "dg$rid3d", "du$mmy", "enc$oding", "dec$imalsign",
+                "fit$", "font$path", "fo$rmat", "fu$nction", "fu$nctions", "g$rid",
+                "hid$den3d", "his$torysize", "is$osamples", "k$ey", "keyt$itle",
+                "la$bel", "li$nestyle", "ls$", "loa$dpath", "loc$ale", "log$scale",
+                "mac$ros", "map$ping", "map$ping3d", "mar$gin", "lmar$gin",
+                "rmar$gin", "tmar$gin", "bmar$gin", "mo$use", "multi$plot",
+                "mxt$ics", "nomxt$ics", "mx2t$ics", "nomx2t$ics", "myt$ics",
+                "nomyt$ics", "my2t$ics", "nomy2t$ics", "mzt$ics", "nomzt$ics",
+                "mcbt$ics", "nomcbt$ics", "of$fsets", "or$igin", "o$utput",
+                "pa$rametric", "pm$3d", "pal$ette", "colorb$ox", "p$lot",
+                "poi$ntsize", "pol$ar", "pr$int", "obj$ect", "sa$mples", "si$ze",
+                "st$yle", "su$rface", "table$", "t$erminal", "termo$ptions", "ti$cs",
+                "ticsc$ale", "ticsl$evel", "timef$mt", "tim$estamp", "tit$le",
+                "v$ariables", "ve$rsion", "vi$ew", "xyp$lane", "xda$ta", "x2da$ta",
+                "yda$ta", "y2da$ta", "zda$ta", "cbda$ta", "xl$abel", "x2l$abel",
+                "yl$abel", "y2l$abel", "zl$abel", "cbl$abel", "xti$cs", "noxti$cs",
+                "x2ti$cs", "nox2ti$cs", "yti$cs", "noyti$cs", "y2ti$cs", "noy2ti$cs",
+                "zti$cs", "nozti$cs", "cbti$cs", "nocbti$cs", "xdti$cs", "noxdti$cs",
+                "x2dti$cs", "nox2dti$cs", "ydti$cs", "noydti$cs", "y2dti$cs",
+                "noy2dti$cs", "zdti$cs", "nozdti$cs", "cbdti$cs", "nocbdti$cs",
+                "xmti$cs", "noxmti$cs", "x2mti$cs", "nox2mti$cs", "ymti$cs",
+                "noymti$cs", "y2mti$cs", "noy2mti$cs", "zmti$cs", "nozmti$cs",
+                "cbmti$cs", "nocbmti$cs", "xr$ange", "x2r$ange", "yr$ange",
+                "y2r$ange", "zr$ange", "cbr$ange", "rr$ange", "tr$ange", "ur$ange",
+                "vr$ange", "xzeroa$xis", "x2zeroa$xis", "yzeroa$xis", "y2zeroa$xis",
+                "zzeroa$xis", "zeroa$xis", "z$ero"), Name.Builtin, '#pop'),
+        ],
+        'bind': [
+            ('!', Keyword, '#pop'),
+            (_shortened('all$windows'), Name.Builtin),
+            include('genericargs'),
+        ],
+        'quit': [
+            (r'gnuplot\b', Keyword),
+            include('noargs'),
+        ],
+        'fit': [
+            (r'via\b', Name.Builtin),
+            include('plot'),
+        ],
+        'if': [
+            (r'\)', Punctuation, '#pop'),
+            include('genericargs'),
+        ],
+        'pause': [
+            (r'(mouse|any|button1|button2|button3)\b', Name.Builtin),
+            (_shortened('key$press'), Name.Builtin),
+            include('genericargs'),
+        ],
+        'plot': [
+            (_shortened_many('ax$es', 'axi$s', 'bin$ary', 'ev$ery', 'i$ndex',
+                             'mat$rix', 's$mooth', 'thru$', 't$itle',
+                             'not$itle', 'u$sing', 'w$ith'),
+             Name.Builtin),
+            include('genericargs'),
+        ],
+        'save': [
+            (_shortened_many('f$unctions', 's$et', 't$erminal', 'v$ariables'),
+             Name.Builtin),
+            include('genericargs'),
+        ],
+    }
+
+
+class PovrayLexer(RegexLexer):
+    """
+    For Persistence of Vision Raytracer files.
+    """
+    name = 'POVRay'
+    url = 'http://www.povray.org/'
+    aliases = ['pov']
+    filenames = ['*.pov', '*.inc']
+    mimetypes = ['text/x-povray']
+    version_added = '0.11'
+
+    tokens = {
+        'root': [
+            (r'/\*[\w\W]*?\*/', Comment.Multiline),
+            (r'//.*$', Comment.Single),
+            (r'(?s)"(?:\\.|[^"\\])+"', String.Double),
+            (words((
+                'break', 'case', 'debug', 'declare', 'default', 'define', 'else',
+                'elseif', 'end', 'error', 'fclose', 'fopen', 'for', 'if', 'ifdef',
+                'ifndef', 'include', 'local', 'macro', 'range', 'read', 'render',
+                'statistics', 'switch', 'undef', 'version', 'warning', 'while',
+                'write'), prefix=r'#', suffix=r'\b'),
+             Comment.Preproc),
+            (words((
+                'aa_level', 'aa_threshold', 'abs', 'acos', 'acosh', 'adaptive', 'adc_bailout',
+                'agate', 'agate_turb', 'all', 'alpha', 'ambient', 'ambient_light', 'angle',
+                'aperture', 'arc_angle', 'area_light', 'asc', 'asin', 'asinh', 'assumed_gamma',
+                'atan', 'atan2', 'atanh', 'atmosphere', 'atmospheric_attenuation',
+                'attenuating', 'average', 'background', 'black_hole', 'blue', 'blur_samples',
+                'bounded_by', 'box_mapping', 'bozo', 'break', 'brick', 'brick_size',
+                'brightness', 'brilliance', 'bumps', 'bumpy1', 'bumpy2', 'bumpy3', 'bump_map',
+                'bump_size', 'case', 'caustics', 'ceil', 'checker', 'chr', 'clipped_by', 'clock',
+                'color', 'color_map', 'colour', 'colour_map', 'component', 'composite', 'concat',
+                'confidence', 'conic_sweep', 'constant', 'control0', 'control1', 'cos', 'cosh',
+                'count', 'crackle', 'crand', 'cube', 'cubic_spline', 'cylindrical_mapping',
+                'debug', 'declare', 'default', 'degrees', 'dents', 'diffuse', 'direction',
+                'distance', 'distance_maximum', 'div', 'dust', 'dust_type', 'eccentricity',
+                'else', 'emitting', 'end', 'error', 'error_bound', 'exp', 'exponent',
+                'fade_distance', 'fade_power', 'falloff', 'falloff_angle', 'false',
+                'file_exists', 'filter', 'finish', 'fisheye', 'flatness', 'flip', 'floor',
+                'focal_point', 'fog', 'fog_alt', 'fog_offset', 'fog_type', 'frequency', 'gif',
+                'global_settings', 'glowing', 'gradient', 'granite', 'gray_threshold',
+                'green', 'halo', 'hexagon', 'hf_gray_16', 'hierarchy', 'hollow', 'hypercomplex',
+                'if', 'ifdef', 'iff', 'image_map', 'incidence', 'include', 'int', 'interpolate',
+                'inverse', 'ior', 'irid', 'irid_wavelength', 'jitter', 'lambda', 'leopard',
+                'linear', 'linear_spline', 'linear_sweep', 'location', 'log', 'looks_like',
+                'look_at', 'low_error_factor', 'mandel', 'map_type', 'marble', 'material_map',
+                'matrix', 'max', 'max_intersections', 'max_iteration', 'max_trace_level',
+                'max_value', 'metallic', 'min', 'minimum_reuse', 'mod', 'mortar',
+                'nearest_count', 'no', 'normal', 'normal_map', 'no_shadow', 'number_of_waves',
+                'octaves', 'off', 'offset', 'omega', 'omnimax', 'on', 'once', 'onion', 'open',
+                'orthographic', 'panoramic', 'pattern1', 'pattern2', 'pattern3',
+                'perspective', 'pgm', 'phase', 'phong', 'phong_size', 'pi', 'pigment',
+                'pigment_map', 'planar_mapping', 'png', 'point_at', 'pot', 'pow', 'ppm',
+                'precision', 'pwr', 'quadratic_spline', 'quaternion', 'quick_color',
+                'quick_colour', 'quilted', 'radial', 'radians', 'radiosity', 'radius', 'rainbow',
+                'ramp_wave', 'rand', 'range', 'reciprocal', 'recursion_limit', 'red',
+                'reflection', 'refraction', 'render', 'repeat', 'rgb', 'rgbf', 'rgbft', 'rgbt',
+                'right', 'ripples', 'rotate', 'roughness', 'samples', 'scale', 'scallop_wave',
+                'scattering', 'seed', 'shadowless', 'sin', 'sine_wave', 'sinh', 'sky', 'sky_sphere',
+                'slice', 'slope_map', 'smooth', 'specular', 'spherical_mapping', 'spiral',
+                'spiral1', 'spiral2', 'spotlight', 'spotted', 'sqr', 'sqrt', 'statistics', 'str',
+                'strcmp', 'strength', 'strlen', 'strlwr', 'strupr', 'sturm', 'substr', 'switch', 'sys',
+                't', 'tan', 'tanh', 'test_camera_1', 'test_camera_2', 'test_camera_3',
+                'test_camera_4', 'texture', 'texture_map', 'tga', 'thickness', 'threshold',
+                'tightness', 'tile2', 'tiles', 'track', 'transform', 'translate', 'transmit',
+                'triangle_wave', 'true', 'ttf', 'turbulence', 'turb_depth', 'type',
+                'ultra_wide_angle', 'up', 'use_color', 'use_colour', 'use_index', 'u_steps',
+                'val', 'variance', 'vaxis_rotate', 'vcross', 'vdot', 'version', 'vlength',
+                'vnormalize', 'volume_object', 'volume_rendered', 'vol_with_light',
+                'vrotate', 'v_steps', 'warning', 'warp', 'water_level', 'waves', 'while', 'width',
+                'wood', 'wrinkles', 'yes'), prefix=r'\b', suffix=r'\b'),
+             Keyword),
+            (words((
+                'bicubic_patch', 'blob', 'box', 'camera', 'cone', 'cubic', 'cylinder', 'difference',
+                'disc', 'height_field', 'intersection', 'julia_fractal', 'lathe',
+                'light_source', 'merge', 'mesh', 'object', 'plane', 'poly', 'polygon', 'prism',
+                'quadric', 'quartic', 'smooth_triangle', 'sor', 'sphere', 'superellipsoid',
+                'text', 'torus', 'triangle', 'union'), suffix=r'\b'),
+             Name.Builtin),
+            (r'\b(x|y|z|u|v)\b', Name.Builtin.Pseudo),
+            (r'[a-zA-Z_]\w*', Name),
+            (r'[0-9]*\.[0-9]+', Number.Float),
+            (r'[0-9]+', Number.Integer),
+            (r'[\[\](){}<>;,]', Punctuation),
+            (r'[-+*/=.|&]|<=|>=|!=', Operator),
+            (r'"(\\\\|\\[^\\]|[^"\\])*"', String),
+            (r'\s+', Whitespace),
+        ]
+    }
+
+    def analyse_text(text):
+        """POVRAY is similar to JSON/C, but the combination of camera and
+        light_source is probably not very likely elsewhere. HLSL or GLSL
+        are similar (GLSL even has #version), but they miss #declare, and
+        light_source/camera are not keywords anywhere else -- it's fair
+        to assume though that any POVRAY scene must have a camera and
+        lightsource."""
+        result = 0
+        if '#version' in text:
+            result += 0.05
+        if '#declare' in text:
+            result += 0.05
+        if 'camera' in text:
+            result += 0.05
+        if 'light_source' in text:
+            result += 0.1
+
+        return result

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/nit.py

@@ -0,0 +1,63 @@
+"""
+    pygments.lexers.nit
+    ~~~~~~~~~~~~~~~~~~~
+
+    Lexer for the Nit language.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import RegexLexer, words
+from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation
+
+__all__ = ['NitLexer']
+
+
+class NitLexer(RegexLexer):
+    """
+    For nit source.
+    """
+
+    name = 'Nit'
+    url = 'http://nitlanguage.org'
+    aliases = ['nit']
+    filenames = ['*.nit']
+    version_added = '2.0'
+    tokens = {
+        'root': [
+            (r'#.*?$', Comment.Single),
+            (words((
+                'package', 'module', 'import', 'class', 'abstract', 'interface',
+                'universal', 'enum', 'end', 'fun', 'type', 'init', 'redef',
+                'isa', 'do', 'readable', 'writable', 'var', 'intern', 'extern',
+                'public', 'protected', 'private', 'intrude', 'if', 'then',
+                'else', 'while', 'loop', 'for', 'in', 'and', 'or', 'not',
+                'implies', 'return', 'continue', 'break', 'abort', 'assert',
+                'new', 'is', 'once', 'super', 'self', 'true', 'false', 'nullable',
+                'null', 'as', 'isset', 'label', '__debug__'), suffix=r'(?=[\r\n\t( ])'),
+             Keyword),
+            (r'[A-Z]\w*', Name.Class),
+            (r'"""(([^\'\\]|\\.)|\\r|\\n)*((\{\{?)?(""?\{\{?)*""""*)', String),  # Simple long string
+            (r'\'\'\'(((\\.|[^\'\\])|\\r|\\n)|\'((\\.|[^\'\\])|\\r|\\n)|'
+             r'\'\'((\\.|[^\'\\])|\\r|\\n))*\'\'\'', String),  # Simple long string alt
+            (r'"""(([^\'\\]|\\.)|\\r|\\n)*((""?)?(\{\{?""?)*\{\{\{\{*)', String),  # Start long string
+            (r'\}\}\}(((\\.|[^\'\\])|\\r|\\n))*(""?)?(\{\{?""?)*\{\{\{\{*', String),  # Mid long string
+            (r'\}\}\}(((\\.|[^\'\\])|\\r|\\n))*(\{\{?)?(""?\{\{?)*""""*', String),  # End long string
+            (r'"(\\.|([^"}{\\]))*"', String),  # Simple String
+            (r'"(\\.|([^"}{\\]))*\{', String),  # Start string
+            (r'\}(\\.|([^"}{\\]))*\{', String),  # Mid String
+            (r'\}(\\.|([^"}{\\]))*"', String),  # End String
+            (r'(\'[^\'\\]\')|(\'\\.\')', String.Char),
+            (r'[0-9]+', Number.Integer),
+            (r'[0-9]*.[0-9]+', Number.Float),
+            (r'0(x|X)[0-9A-Fa-f]+', Number.Hex),
+            (r'[a-z]\w*', Name),
+            (r'_\w+', Name.Variable.Instance),
+            (r'==|!=|<==>|>=|>>|>|<=|<<|<|\+|-|=|/|\*|%|\+=|-=|!|@', Operator),
+            (r'\(|\)|\[|\]|,|\.\.\.|\.\.|\.|::|:', Punctuation),
+            (r'`\{[^`]*`\}', Text),  # Extern blocks won't be Lexed by Nit
+            (r'[\r\n\t ]+', Text),
+        ],
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/procfile.py

@@ -0,0 +1,41 @@
+"""
+    pygments.lexers.procfile
+    ~~~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexer for Procfile file format.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import RegexLexer, bygroups
+from pygments.token import Name, Number, String, Text, Punctuation
+
+__all__ = ["ProcfileLexer"]
+
+
+class ProcfileLexer(RegexLexer):
+    """
+    Lexer for Procfile file format.
+
+    The format is used to run processes on Heroku or is used by Foreman or
+    Honcho tools.
+    """
+    name = 'Procfile'
+    url = 'https://devcenter.heroku.com/articles/procfile#procfile-format'
+    aliases = ['procfile']
+    filenames = ['Procfile']
+    version_added = '2.10'
+
+    tokens = {
+        'root': [
+            (r'^([a-z]+)(:)', bygroups(Name.Label, Punctuation)),
+            (r'\s+', Text.Whitespace),
+            (r'"[^"]*"', String),
+            (r"'[^']*'", String),
+            (r'[0-9]+', Number.Integer),
+            (r'\$[a-zA-Z_][\w]*', Name.Variable),
+            (r'(\w+)(=)(\w+)', bygroups(Name.Variable, Punctuation, String)),
+            (r'([\w\-\./]+)', Text),
+        ],
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/rell.py

@@ -0,0 +1,68 @@
+"""
+    pygments.lexers.rell
+    ~~~~~~~~~~~~~~~~~~~~
+
+    Lexers for the Rell language.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import RegexLexer, bygroups, default, words
+from pygments.token import Comment, Keyword, Name, String, Number, \
+        Punctuation, Whitespace
+
+__all__ = ['RellLexer']
+
+
+class RellLexer(RegexLexer):
+    """
+    A Lexer for Rell.
+    """
+    name = 'Rell'
+    url = 'https://docs.chromia.com/rell/rell-intro'
+    aliases = ['rell']
+    filenames = ['*.rell']
+    mimetypes = ['text/x-rell']
+    version_added = '2.20'
+
+    ident = r'[a-zA-Z_][a-zA-Z0-9_]*'
+
+    tokens = {
+        'root': [
+            (words((
+                'big_integer', 'boolean', 'byte_array', 'decimal', 'gtv',
+                'integer', 'json', 'list', 'map', 'mutable', 'set', 'text',
+                'virtual'), suffix=r'\b'),
+             Keyword.Type),
+            (r'(false|true|null)\b', Keyword.Constant),
+            (r'(entity|enum|namespace|object|struct)\b', Keyword.Declaration),
+            (r'(function|operation|query)\b', Keyword.Declaration, 'function'),
+            (words((
+                'abstract', 'and', 'break', 'continue', 'create', 'delete',
+                'else', 'for', 'if', 'import', 'in', 'index', 'key', 'limit',
+                'module', 'not', 'offset', 'or', 'override', 'return', 'update',
+                'val', 'var', 'when', 'while'), suffix=r'\b'),
+             Keyword.Reserved),
+            (r'//.*?$', Comment.Single),
+            (r'/\*(.|\n|\r)*?\*/', Comment.Multiline),
+            (r'"(\\\\|\\"|[^"])*"', String.Double),
+            (r'\'(\\\\|\\\'|[^\\\'])*\'', String.Single),
+            (r'-?[0-9]*\.[0-9]+([eE][+-][0-9]+)?', Number.Float),
+            (r'-?[0-9]+([eE][+-][0-9]+|[lL])?', Number.Integer),
+            (r'x(\'[a-fA-F0-9]*\'|"[a-fA-F0-9]*")', String.Binary),
+            (r'(\.)([ \n\t\r]*)(' + ident + ')',
+                bygroups(Punctuation, Whitespace, Name.Attribute)),
+            (r'[{}():;,]+', Punctuation),
+            (r'[ \n\t\r]+', Whitespace),
+            (r'@[a-zA-Z_][a-zA-Z0-9_]*', Name.Decorator),
+            (r'[~^*!%&\[\]<>|+=/?\-@\$]', Punctuation.Marker),
+            (ident, Name),
+            (r'(\.)+', Punctuation),
+        ],
+        'function': [
+            (r'[ \n\t\r]+', Whitespace),
+            (ident, Name.Function, '#pop'),
+            default('#pop'),
+        ],
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/rust.py

@@ -0,0 +1,222 @@
+"""
+    pygments.lexers.rust
+    ~~~~~~~~~~~~~~~~~~~~
+
+    Lexers for the Rust language.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import RegexLexer, include, bygroups, words, default
+from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation, Whitespace
+
+__all__ = ['RustLexer']
+
+
+class RustLexer(RegexLexer):
+    """
+    Lexer for the Rust programming language (version 1.47).
+    """
+    name = 'Rust'
+    url = 'https://www.rust-lang.org/'
+    filenames = ['*.rs', '*.rs.in']
+    aliases = ['rust', 'rs']
+    mimetypes = ['text/rust', 'text/x-rust']
+    version_added = '1.6'
+
+    keyword_types = (words((
+        'u8', 'u16', 'u32', 'u64', 'u128', 'i8', 'i16', 'i32', 'i64', 'i128',
+        'usize', 'isize', 'f32', 'f64', 'char', 'str', 'bool',
+    ), suffix=r'\b'), Keyword.Type)
+
+    builtin_funcs_types = (words((
+        'Copy', 'Send', 'Sized', 'Sync', 'Unpin',
+        'Drop', 'Fn', 'FnMut', 'FnOnce', 'drop',
+        'Box', 'ToOwned', 'Clone',
+        'PartialEq', 'PartialOrd', 'Eq', 'Ord',
+        'AsRef', 'AsMut', 'Into', 'From', 'Default',
+        'Iterator', 'Extend', 'IntoIterator', 'DoubleEndedIterator',
+        'ExactSizeIterator',
+        'Option', 'Some', 'None',
+        'Result', 'Ok', 'Err',
+        'String', 'ToString', 'Vec',
+    ), suffix=r'\b'), Name.Builtin)
+
+    builtin_macros = (words((
+        'asm', 'assert', 'assert_eq', 'assert_ne', 'cfg', 'column',
+        'compile_error', 'concat', 'concat_idents', 'dbg', 'debug_assert',
+        'debug_assert_eq', 'debug_assert_ne', 'env', 'eprint', 'eprintln',
+        'file', 'format', 'format_args', 'format_args_nl', 'global_asm',
+        'include', 'include_bytes', 'include_str',
+        'is_aarch64_feature_detected',
+        'is_arm_feature_detected',
+        'is_mips64_feature_detected',
+        'is_mips_feature_detected',
+        'is_powerpc64_feature_detected',
+        'is_powerpc_feature_detected',
+        'is_x86_feature_detected',
+        'line', 'llvm_asm', 'log_syntax', 'macro_rules', 'matches',
+        'module_path', 'option_env', 'panic', 'print', 'println', 'stringify',
+        'thread_local', 'todo', 'trace_macros', 'unimplemented', 'unreachable',
+        'vec', 'write', 'writeln',
+    ), suffix=r'!'), Name.Function.Magic)
+
+    tokens = {
+        'root': [
+            # rust allows a file to start with a shebang, but if the first line
+            # starts with #![ then it's not a shebang but a crate attribute.
+            (r'#![^[\r\n].*$', Comment.Preproc),
+            default('base'),
+        ],
+        'base': [
+            # Whitespace and Comments
+            (r'\n', Whitespace),
+            (r'\s+', Whitespace),
+            (r'//!.*?\n', String.Doc),
+            (r'///(\n|[^/].*?\n)', String.Doc),
+            (r'//(.*?)\n', Comment.Single),
+            (r'/\*\*(\n|[^/*])', String.Doc, 'doccomment'),
+            (r'/\*!', String.Doc, 'doccomment'),
+            (r'/\*', Comment.Multiline, 'comment'),
+
+            # Macro parameters
+            (r"""\$([a-zA-Z_]\w*|\(,?|\),?|,?)""", Comment.Preproc),
+            # Keywords
+            (words(('as', 'async', 'await', 'box', 'const', 'crate', 'dyn',
+                    'else', 'extern', 'for', 'if', 'impl', 'in', 'loop',
+                    'match', 'move', 'mut', 'pub', 'ref', 'return', 'static',
+                    'super', 'trait', 'unsafe', 'use', 'where', 'while'),
+                   suffix=r'\b'), Keyword),
+            (words(('abstract', 'become', 'do', 'final', 'macro', 'override',
+                    'priv', 'typeof', 'try', 'unsized', 'virtual', 'yield'),
+                   suffix=r'\b'), Keyword.Reserved),
+            (r'(true|false)\b', Keyword.Constant),
+            (r'self\b', Name.Builtin.Pseudo),
+            (r'mod\b', Keyword, 'modname'),
+            (r'let\b', Keyword.Declaration),
+            (r'fn\b', Keyword, 'funcname'),
+            (r'(struct|enum|type|union)\b', Keyword, 'typename'),
+            (r'(default)(\s+)(type|fn)\b', bygroups(Keyword, Whitespace, Keyword)),
+            keyword_types,
+            (r'[sS]elf\b', Name.Builtin.Pseudo),
+            # Prelude (taken from Rust's src/libstd/prelude.rs)
+            builtin_funcs_types,
+            builtin_macros,
+            # Path separators, so types don't catch them.
+            (r'::\b', Punctuation),
+            # Types in positions.
+            (r'(?::|->)', Punctuation, 'typename'),
+            # Labels
+            (r'(break|continue)(\b\s*)(\'[A-Za-z_]\w*)?',
+             bygroups(Keyword, Text.Whitespace, Name.Label)),
+
+            # Character literals
+            (r"""'(\\['"\\nrt]|\\x[0-7][0-9a-fA-F]|\\0"""
+             r"""|\\u\{[0-9a-fA-F]{1,6}\}|.)'""",
+             String.Char),
+            (r"""b'(\\['"\\nrt]|\\x[0-9a-fA-F]{2}|\\0"""
+             r"""|\\u\{[0-9a-fA-F]{1,6}\}|.)'""",
+             String.Char),
+
+            # Binary literals
+            (r'0b[01_]+', Number.Bin, 'number_lit'),
+            # Octal literals
+            (r'0o[0-7_]+', Number.Oct, 'number_lit'),
+            # Hexadecimal literals
+            (r'0[xX][0-9a-fA-F_]+', Number.Hex, 'number_lit'),
+            # Decimal literals
+            (r'[0-9][0-9_]*(\.[0-9_]+[eE][+\-]?[0-9_]+|'
+             r'\.[0-9_]*(?!\.)|[eE][+\-]?[0-9_]+)', Number.Float,
+             'number_lit'),
+            (r'[0-9][0-9_]*', Number.Integer, 'number_lit'),
+
+            # String literals
+            (r'b"', String, 'bytestring'),
+            (r'"', String, 'string'),
+            (r'(?s)b?r(#*)".*?"\1', String),
+
+            # Lifetime names
+            (r"'", Operator, 'lifetime'),
+
+            # Operators and Punctuation
+            (r'\.\.=?', Operator),
+            (r'[{}()\[\],.;]', Punctuation),
+            (r'[+\-*/%&|<>^!~@=:?]', Operator),
+
+            # Identifiers
+            (r'[a-zA-Z_]\w*', Name),
+            # Raw identifiers
+            (r'r#[a-zA-Z_]\w*', Name),
+
+            # Attributes
+            (r'#!?\[', Comment.Preproc, 'attribute['),
+
+            # Misc
+            # Lone hashes: not used in Rust syntax, but allowed in macro
+            # arguments, most famously for quote::quote!()
+            (r'#', Punctuation),
+        ],
+        'comment': [
+            (r'[^*/]+', Comment.Multiline),
+            (r'/\*', Comment.Multiline, '#push'),
+            (r'\*/', Comment.Multiline, '#pop'),
+            (r'[*/]', Comment.Multiline),
+        ],
+        'doccomment': [
+            (r'[^*/]+', String.Doc),
+            (r'/\*', String.Doc, '#push'),
+            (r'\*/', String.Doc, '#pop'),
+            (r'[*/]', String.Doc),
+        ],
+        'modname': [
+            (r'\s+', Whitespace),
+            (r'[a-zA-Z_]\w*', Name.Namespace, '#pop'),
+            default('#pop'),
+        ],
+        'funcname': [
+            (r'\s+', Whitespace),
+            (r'[a-zA-Z_]\w*', Name.Function, '#pop'),
+            default('#pop'),
+        ],
+        'typename': [
+            (r'\s+', Whitespace),
+            (r'&', Keyword.Pseudo),
+            (r"'", Operator, 'lifetime'),
+            builtin_funcs_types,
+            keyword_types,
+            (r'[a-zA-Z_]\w*', Name.Class, '#pop'),
+            default('#pop'),
+        ],
+        'lifetime': [
+            (r"(static|_)", Name.Builtin),
+            (r"[a-zA-Z_]+\w*", Name.Attribute),
+            default('#pop'),
+        ],
+        'number_lit': [
+            (r'[ui](8|16|32|64|size)', Keyword, '#pop'),
+            (r'f(32|64)', Keyword, '#pop'),
+            default('#pop'),
+        ],
+        'string': [
+            (r'"', String, '#pop'),
+            (r"""\\['"\\nrt]|\\x[0-7][0-9a-fA-F]|\\0"""
+             r"""|\\u\{[0-9a-fA-F]{1,6}\}""", String.Escape),
+            (r'[^\\"]+', String),
+            (r'\\', String),
+        ],
+        'bytestring': [
+            (r"""\\x[89a-fA-F][0-9a-fA-F]""", String.Escape),
+            include('string'),
+        ],
+        'attribute_common': [
+            (r'"', String, 'string'),
+            (r'\[', Comment.Preproc, 'attribute['),
+        ],
+        'attribute[': [
+            include('attribute_common'),
+            (r'\]', Comment.Preproc, '#pop'),
+            (r'[^"\]\[]+', Comment.Preproc),
+        ],
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/shell.py

@@ -0,0 +1,902 @@
+"""
+    pygments.lexers.shell
+    ~~~~~~~~~~~~~~~~~~~~~
+
+    Lexers for various shells.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import Lexer, RegexLexer, do_insertions, bygroups, \
+    include, default, this, using, words, line_re
+from pygments.token import Punctuation, Whitespace, \
+    Text, Comment, Operator, Keyword, Name, String, Number, Generic
+from pygments.util import shebang_matches
+
+__all__ = ['BashLexer', 'BashSessionLexer', 'TcshLexer', 'BatchLexer',
+           'SlurmBashLexer', 'MSDOSSessionLexer', 'PowerShellLexer',
+           'PowerShellSessionLexer', 'TcshSessionLexer', 'FishShellLexer',
+           'ExeclineLexer']
+
+
+class BashLexer(RegexLexer):
+    """
+    Lexer for (ba|k|z|)sh shell scripts.
+    """
+
+    name = 'Bash'
+    aliases = ['bash', 'sh', 'ksh', 'zsh', 'shell', 'openrc']
+    filenames = ['*.sh', '*.ksh', '*.bash', '*.ebuild', '*.eclass',
+                 '*.exheres-0', '*.exlib', '*.zsh',
+                 '.bashrc', 'bashrc', '.bash_*', 'bash_*', 'zshrc', '.zshrc',
+                 '.kshrc', 'kshrc',
+                 'PKGBUILD']
+    mimetypes = ['application/x-sh', 'application/x-shellscript', 'text/x-shellscript']
+    url = 'https://en.wikipedia.org/wiki/Unix_shell'
+    version_added = '0.6'
+
+    tokens = {
+        'root': [
+            include('basic'),
+            (r'`', String.Backtick, 'backticks'),
+            include('data'),
+            include('interp'),
+        ],
+        'interp': [
+            (r'\$\(\(', Keyword, 'math'),
+            (r'\$\(', Keyword, 'paren'),
+            (r'\$\{#?', String.Interpol, 'curly'),
+            (r'\$[a-zA-Z_]\w*', Name.Variable),  # user variable
+            (r'\$(?:\d+|[#$?!_*@-])', Name.Variable),      # builtin
+            (r'\$', Text),
+        ],
+        'basic': [
+            (r'\b(if|fi|else|while|in|do|done|for|then|return|function|case|'
+             r'select|break|continue|until|esac|elif)(\s*)\b',
+             bygroups(Keyword, Whitespace)),
+            (r'\b(alias|bg|bind|builtin|caller|cd|command|compgen|'
+             r'complete|declare|dirs|disown|echo|enable|eval|exec|exit|'
+             r'export|false|fc|fg|getopts|hash|help|history|jobs|kill|let|'
+             r'local|logout|popd|printf|pushd|pwd|read|readonly|set|shift|'
+             r'shopt|source|suspend|test|time|times|trap|true|type|typeset|'
+             r'ulimit|umask|unalias|unset|wait)(?=[\s)`])',
+             Name.Builtin),
+            (r'\A#!.+\n', Comment.Hashbang),
+            (r'#.*\n', Comment.Single),
+            (r'\\[\w\W]', String.Escape),
+            (r'(\b\w+)(\s*)(\+?=)', bygroups(Name.Variable, Whitespace, Operator)),
+            (r'[\[\]{}()=]', Operator),
+            (r'<<<', Operator),  # here-string
+            (r'<<-?\s*(\'?)\\?(\w+)[\w\W]+?\2', String),
+            (r'&&|\|\|', Operator),
+        ],
+        'data': [
+            (r'(?s)\$?"(\\.|[^"\\$])*"', String.Double),
+            (r'"', String.Double, 'string'),
+            (r"(?s)\$'(\\\\|\\[0-7]+|\\.|[^'\\])*'", String.Single),
+            (r"(?s)'.*?'", String.Single),
+            (r';', Punctuation),
+            (r'&', Punctuation),
+            (r'\|', Punctuation),
+            (r'\s+', Whitespace),
+            (r'\d+\b', Number),
+            (r'[^=\s\[\]{}()$"\'`\\<&|;]+', Text),
+            (r'<', Text),
+        ],
+        'string': [
+            (r'"', String.Double, '#pop'),
+            (r'(?s)(\\\\|\\[0-7]+|\\.|[^"\\$])+', String.Double),
+            include('interp'),
+        ],
+        'curly': [
+            (r'\}', String.Interpol, '#pop'),
+            (r':-', Keyword),
+            (r'\w+', Name.Variable),
+            (r'[^}:"\'`$\\]+', Punctuation),
+            (r':', Punctuation),
+            include('root'),
+        ],
+        'paren': [
+            (r'\)', Keyword, '#pop'),
+            include('root'),
+        ],
+        'math': [
+            (r'\)\)', Keyword, '#pop'),
+            (r'\*\*|\|\||<<|>>|[-+*/%^|&<>]', Operator),
+            (r'\d+#[\da-zA-Z]+', Number),
+            (r'\d+#(?! )', Number),
+            (r'0[xX][\da-fA-F]+', Number),
+            (r'\d+', Number),
+            (r'[a-zA-Z_]\w*', Name.Variable),  # user variable
+            include('root'),
+        ],
+        'backticks': [
+            (r'`', String.Backtick, '#pop'),
+            include('root'),
+        ],
+    }
+
+    def analyse_text(text):
+        if shebang_matches(text, r'(ba|z|)sh'):
+            return 1
+        if text.startswith('$ '):
+            return 0.2
+
+
+class SlurmBashLexer(BashLexer):
+    """
+    Lexer for (ba|k|z|)sh Slurm scripts.
+    """
+
+    name = 'Slurm'
+    aliases = ['slurm', 'sbatch']
+    filenames = ['*.sl']
+    mimetypes = []
+    version_added = '2.4'
+    EXTRA_KEYWORDS = {'srun'}
+
+    def get_tokens_unprocessed(self, text):
+        for index, token, value in BashLexer.get_tokens_unprocessed(self, text):
+            if token is Text and value in self.EXTRA_KEYWORDS:
+                yield index, Name.Builtin, value
+            elif token is Comment.Single and 'SBATCH' in value:
+                yield index, Keyword.Pseudo, value
+            else:
+                yield index, token, value
+
+
+class ShellSessionBaseLexer(Lexer):
+    """
+    Base lexer for shell sessions.
+
+    .. versionadded:: 2.1
+    """
+
+    _bare_continuation = False
+    _venv = re.compile(r'^(\([^)]*\))(\s*)')
+
+    def get_tokens_unprocessed(self, text):
+        innerlexer = self._innerLexerCls(**self.options)
+
+        pos = 0
+        curcode = ''
+        insertions = []
+        backslash_continuation = False
+
+        for match in line_re.finditer(text):
+            line = match.group()
+
+            venv_match = self._venv.match(line)
+            if venv_match:
+                venv = venv_match.group(1)
+                venv_whitespace = venv_match.group(2)
+                insertions.append((len(curcode),
+                                   [(0, Generic.Prompt.VirtualEnv, venv)]))
+                if venv_whitespace:
+                    insertions.append((len(curcode),
+                                       [(0, Text, venv_whitespace)]))
+                line = line[venv_match.end():]
+
+            m = self._ps1rgx.match(line)
+            if m:
+                # To support output lexers (say diff output), the output
+                # needs to be broken by prompts whenever the output lexer
+                # changes.
+                if not insertions:
+                    pos = match.start()
+
+                insertions.append((len(curcode),
+                                   [(0, Generic.Prompt, m.group(1))]))
+                curcode += m.group(2)
+                backslash_continuation = curcode.endswith('\\\n')
+            elif backslash_continuation:
+                if line.startswith(self._ps2):
+                    insertions.append((len(curcode),
+                                       [(0, Generic.Prompt,
+                                         line[:len(self._ps2)])]))
+                    curcode += line[len(self._ps2):]
+                else:
+                    curcode += line
+                backslash_continuation = curcode.endswith('\\\n')
+            elif self._bare_continuation and line.startswith(self._ps2):
+                insertions.append((len(curcode),
+                                   [(0, Generic.Prompt,
+                                     line[:len(self._ps2)])]))
+                curcode += line[len(self._ps2):]
+            else:
+                if insertions:
+                    toks = innerlexer.get_tokens_unprocessed(curcode)
+                    for i, t, v in do_insertions(insertions, toks):
+                        yield pos+i, t, v
+                yield match.start(), Generic.Output, line
+                insertions = []
+                curcode = ''
+        if insertions:
+            for i, t, v in do_insertions(insertions,
+                                         innerlexer.get_tokens_unprocessed(curcode)):
+                yield pos+i, t, v
+
+
+class BashSessionLexer(ShellSessionBaseLexer):
+    """
+    Lexer for Bash shell sessions, i.e. command lines, including a
+    prompt, interspersed with output.
+    """
+
+    name = 'Bash Session'
+    aliases = ['console', 'shell-session']
+    filenames = ['*.sh-session', '*.shell-session']
+    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(
+        r'^((?:(?:\[.*?\])|(?:\(\S+\))?(?:| |sh\S*?|\w+\S+[@:]\S+(?:\s+\S+)' \
+        r'?|\[\S+[@:][^\n]+\].+))\s*[$#%]\s*)(.*\n?)')
+    _ps2 = '> '
+
+
+class BatchLexer(RegexLexer):
+    """
+    Lexer for the DOS/Windows Batch file format.
+    """
+    name = 'Batchfile'
+    aliases = ['batch', 'bat', 'dosbatch', 'winbatch']
+    filenames = ['*.bat', '*.cmd']
+    mimetypes = ['application/x-dos-batch']
+    url = 'https://en.wikipedia.org/wiki/Batch_file'
+    version_added = '0.7'
+
+    flags = re.MULTILINE | re.IGNORECASE
+
+    _nl = r'\n\x1a'
+    _punct = r'&<>|'
+    _ws = r'\t\v\f\r ,;=\xa0'
+    _nlws = r'\s\x1a\xa0,;='
+    _space = rf'(?:(?:(?:\^[{_nl}])?[{_ws}])+)'
+    _keyword_terminator = (rf'(?=(?:\^[{_nl}]?)?[{_ws}+./:[\\\]]|[{_nl}{_punct}(])')
+    _token_terminator = rf'(?=\^?[{_ws}]|[{_punct}{_nl}])'
+    _start_label = rf'((?:(?<=^[^:])|^[^:]?)[{_ws}]*)(:)'
+    _label = rf'(?:(?:[^{_nlws}{_punct}+:^]|\^[{_nl}]?[\w\W])*)'
+    _label_compound = rf'(?:(?:[^{_nlws}{_punct}+:^)]|\^[{_nl}]?[^)])*)'
+    _number = rf'(?:-?(?:0[0-7]+|0x[\da-f]+|\d+){_token_terminator})'
+    _opword = r'(?:equ|geq|gtr|leq|lss|neq)'
+    _string = rf'(?:"[^{_nl}"]*(?:"|(?=[{_nl}])))'
+    _variable = (r'(?:(?:%(?:\*|(?:~[a-z]*(?:\$[^:]+:)?)?\d|'
+                 rf'[^%:{_nl}]+(?::(?:~(?:-?\d+)?(?:,(?:-?\d+)?)?|(?:[^%{_nl}^]|'
+                 rf'\^[^%{_nl}])[^={_nl}]*=(?:[^%{_nl}^]|\^[^%{_nl}])*)?)?%))|'
+                 rf'(?:\^?![^!:{_nl}]+(?::(?:~(?:-?\d+)?(?:,(?:-?\d+)?)?|(?:'
+                 rf'[^!{_nl}^]|\^[^!{_nl}])[^={_nl}]*=(?:[^!{_nl}^]|\^[^!{_nl}])*)?)?\^?!))')
+    _core_token = rf'(?:(?:(?:\^[{_nl}]?)?[^"{_nlws}{_punct}])+)'
+    _core_token_compound = rf'(?:(?:(?:\^[{_nl}]?)?[^"{_nlws}{_punct})])+)'
+    _token = rf'(?:[{_punct}]+|{_core_token})'
+    _token_compound = rf'(?:[{_punct}]+|{_core_token_compound})'
+    _stoken = (rf'(?:[{_punct}]+|(?:{_string}|{_variable}|{_core_token})+)')
+
+    def _make_begin_state(compound, _core_token=_core_token,
+                          _core_token_compound=_core_token_compound,
+                          _keyword_terminator=_keyword_terminator,
+                          _nl=_nl, _punct=_punct, _string=_string,
+                          _space=_space, _start_label=_start_label,
+                          _stoken=_stoken, _token_terminator=_token_terminator,
+                          _variable=_variable, _ws=_ws):
+        rest = '(?:{}|{}|[^"%{}{}{}])*'.format(_string, _variable, _nl, _punct,
+                                            ')' if compound else '')
+        rest_of_line = rf'(?:(?:[^{_nl}^]|\^[{_nl}]?[\w\W])*)'
+        rest_of_line_compound = rf'(?:(?:[^{_nl}^)]|\^[{_nl}]?[^)])*)'
+        set_space = rf'((?:(?:\^[{_nl}]?)?[^\S\n])*)'
+        suffix = ''
+        if compound:
+            _keyword_terminator = rf'(?:(?=\))|{_keyword_terminator})'
+            _token_terminator = rf'(?:(?=\))|{_token_terminator})'
+            suffix = '/compound'
+        return [
+            ((r'\)', Punctuation, '#pop') if compound else
+             (rf'\)((?=\()|{_token_terminator}){rest_of_line}',
+              Comment.Single)),
+            (rf'(?={_start_label})', Text, f'follow{suffix}'),
+            (_space, using(this, state='text')),
+            include(f'redirect{suffix}'),
+            (rf'[{_nl}]+', Text),
+            (r'\(', Punctuation, 'root/compound'),
+            (r'@+', Punctuation),
+            (rf'((?:for|if|rem)(?:(?=(?:\^[{_nl}]?)?/)|(?:(?!\^)|'
+             rf'(?<=m))(?:(?=\()|{_token_terminator})))({_space}?{_core_token_compound if compound else _core_token}?(?:\^[{_nl}]?)?/(?:\^[{_nl}]?)?\?)',
+             bygroups(Keyword, using(this, state='text')),
+             f'follow{suffix}'),
+            (rf'(goto{_keyword_terminator})({rest}(?:\^[{_nl}]?)?/(?:\^[{_nl}]?)?\?{rest})',
+             bygroups(Keyword, using(this, state='text')),
+             f'follow{suffix}'),
+            (words(('assoc', 'break', 'cd', 'chdir', 'cls', 'color', 'copy',
+                    'date', 'del', 'dir', 'dpath', 'echo', 'endlocal', 'erase',
+                    'exit', 'ftype', 'keys', 'md', 'mkdir', 'mklink', 'move',
+                    'path', 'pause', 'popd', 'prompt', 'pushd', 'rd', 'ren',
+                    'rename', 'rmdir', 'setlocal', 'shift', 'start', 'time',
+                    'title', 'type', 'ver', 'verify', 'vol'),
+                   suffix=_keyword_terminator), Keyword, f'follow{suffix}'),
+            (rf'(call)({_space}?)(:)',
+             bygroups(Keyword, using(this, state='text'), Punctuation),
+             f'call{suffix}'),
+            (rf'call{_keyword_terminator}', Keyword),
+            (rf'(for{_token_terminator}(?!\^))({_space})(/f{_token_terminator})',
+             bygroups(Keyword, using(this, state='text'), Keyword),
+             ('for/f', 'for')),
+            (rf'(for{_token_terminator}(?!\^))({_space})(/l{_token_terminator})',
+             bygroups(Keyword, using(this, state='text'), Keyword),
+             ('for/l', 'for')),
+            (rf'for{_token_terminator}(?!\^)', Keyword, ('for2', 'for')),
+            (rf'(goto{_keyword_terminator})({_space}?)(:?)',
+             bygroups(Keyword, using(this, state='text'), Punctuation),
+             f'label{suffix}'),
+            (rf'(if(?:(?=\()|{_token_terminator})(?!\^))({_space}?)((?:/i{_token_terminator})?)({_space}?)((?:not{_token_terminator})?)({_space}?)',
+             bygroups(Keyword, using(this, state='text'), Keyword,
+                      using(this, state='text'), Keyword,
+                      using(this, state='text')), ('(?', 'if')),
+            (rf'rem(((?=\()|{_token_terminator}){_space}?{_stoken}?.*|{_keyword_terminator}{rest_of_line_compound if compound else rest_of_line})',
+             Comment.Single, f'follow{suffix}'),
+            (rf'(set{_keyword_terminator}){set_space}(/a)',
+             bygroups(Keyword, using(this, state='text'), Keyword),
+             f'arithmetic{suffix}'),
+            (r'(set{}){}((?:/p)?){}((?:(?:(?:\^[{}]?)?[^"{}{}^={}]|'
+             r'\^[{}]?[^"=])+)?)((?:(?:\^[{}]?)?=)?)'.format(_keyword_terminator, set_space, set_space, _nl, _nl, _punct,
+              ')' if compound else '', _nl, _nl),
+             bygroups(Keyword, using(this, state='text'), Keyword,
+                      using(this, state='text'), using(this, state='variable'),
+                      Punctuation),
+             f'follow{suffix}'),
+            default(f'follow{suffix}')
+        ]
+
+    def _make_follow_state(compound, _label=_label,
+                           _label_compound=_label_compound, _nl=_nl,
+                           _space=_space, _start_label=_start_label,
+                           _token=_token, _token_compound=_token_compound,
+                           _ws=_ws):
+        suffix = '/compound' if compound else ''
+        state = []
+        if compound:
+            state.append((r'(?=\))', Text, '#pop'))
+        state += [
+            (rf'{_start_label}([{_ws}]*)({_label_compound if compound else _label})(.*)',
+             bygroups(Text, Punctuation, Text, Name.Label, Comment.Single)),
+            include(f'redirect{suffix}'),
+            (rf'(?=[{_nl}])', Text, '#pop'),
+            (r'\|\|?|&&?', Punctuation, '#pop'),
+            include('text')
+        ]
+        return state
+
+    def _make_arithmetic_state(compound, _nl=_nl, _punct=_punct,
+                               _string=_string, _variable=_variable,
+                               _ws=_ws, _nlws=_nlws):
+        op = r'=+\-*/!~'
+        state = []
+        if compound:
+            state.append((r'(?=\))', Text, '#pop'))
+        state += [
+            (r'0[0-7]+', Number.Oct),
+            (r'0x[\da-f]+', Number.Hex),
+            (r'\d+', Number.Integer),
+            (r'[(),]+', Punctuation),
+            (rf'([{op}]|%|\^\^)+', Operator),
+            (r'({}|{}|(\^[{}]?)?[^(){}%\^"{}{}]|\^[{}]?{})+'.format(_string, _variable, _nl, op, _nlws, _punct, _nlws,
+              r'[^)]' if compound else r'[\w\W]'),
+             using(this, state='variable')),
+            (r'(?=[\x00|&])', Text, '#pop'),
+            include('follow')
+        ]
+        return state
+
+    def _make_call_state(compound, _label=_label,
+                         _label_compound=_label_compound):
+        state = []
+        if compound:
+            state.append((r'(?=\))', Text, '#pop'))
+        state.append((r'(:?)(%s)' % (_label_compound if compound else _label),
+                      bygroups(Punctuation, Name.Label), '#pop'))
+        return state
+
+    def _make_label_state(compound, _label=_label,
+                          _label_compound=_label_compound, _nl=_nl,
+                          _punct=_punct, _string=_string, _variable=_variable):
+        state = []
+        if compound:
+            state.append((r'(?=\))', Text, '#pop'))
+        state.append((r'({}?)((?:{}|{}|\^[{}]?{}|[^"%^{}{}{}])*)'.format(_label_compound if compound else _label, _string,
+                       _variable, _nl, r'[^)]' if compound else r'[\w\W]', _nl,
+                       _punct, r')' if compound else ''),
+                      bygroups(Name.Label, Comment.Single), '#pop'))
+        return state
+
+    def _make_redirect_state(compound,
+                             _core_token_compound=_core_token_compound,
+                             _nl=_nl, _punct=_punct, _stoken=_stoken,
+                             _string=_string, _space=_space,
+                             _variable=_variable, _nlws=_nlws):
+        stoken_compound = (rf'(?:[{_punct}]+|(?:{_string}|{_variable}|{_core_token_compound})+)')
+        return [
+            (rf'((?:(?<=[{_nlws}])\d)?)(>>?&|<&)([{_nlws}]*)(\d)',
+             bygroups(Number.Integer, Punctuation, Text, Number.Integer)),
+            (rf'((?:(?<=[{_nlws}])(?<!\^[{_nl}])\d)?)(>>?|<)({_space}?{stoken_compound if compound else _stoken})',
+             bygroups(Number.Integer, Punctuation, using(this, state='text')))
+        ]
+
+    tokens = {
+        'root': _make_begin_state(False),
+        'follow': _make_follow_state(False),
+        'arithmetic': _make_arithmetic_state(False),
+        'call': _make_call_state(False),
+        'label': _make_label_state(False),
+        'redirect': _make_redirect_state(False),
+        'root/compound': _make_begin_state(True),
+        'follow/compound': _make_follow_state(True),
+        'arithmetic/compound': _make_arithmetic_state(True),
+        'call/compound': _make_call_state(True),
+        'label/compound': _make_label_state(True),
+        'redirect/compound': _make_redirect_state(True),
+        'variable-or-escape': [
+            (_variable, Name.Variable),
+            (rf'%%|\^[{_nl}]?(\^!|[\w\W])', String.Escape)
+        ],
+        'string': [
+            (r'"', String.Double, '#pop'),
+            (_variable, Name.Variable),
+            (r'\^!|%%', String.Escape),
+            (rf'[^"%^{_nl}]+|[%^]', String.Double),
+            default('#pop')
+        ],
+        'sqstring': [
+            include('variable-or-escape'),
+            (r'[^%]+|%', String.Single)
+        ],
+        'bqstring': [
+            include('variable-or-escape'),
+            (r'[^%]+|%', String.Backtick)
+        ],
+        'text': [
+            (r'"', String.Double, 'string'),
+            include('variable-or-escape'),
+            (rf'[^"%^{_nlws}{_punct}\d)]+|.', Text)
+        ],
+        'variable': [
+            (r'"', String.Double, 'string'),
+            include('variable-or-escape'),
+            (rf'[^"%^{_nl}]+|.', Name.Variable)
+        ],
+        'for': [
+            (rf'({_space})(in)({_space})(\()',
+             bygroups(using(this, state='text'), Keyword,
+                      using(this, state='text'), Punctuation), '#pop'),
+            include('follow')
+        ],
+        'for2': [
+            (r'\)', Punctuation),
+            (rf'({_space})(do{_token_terminator})',
+             bygroups(using(this, state='text'), Keyword), '#pop'),
+            (rf'[{_nl}]+', Text),
+            include('follow')
+        ],
+        'for/f': [
+            (rf'(")((?:{_variable}|[^"])*?")([{_nlws}]*)(\))',
+             bygroups(String.Double, using(this, state='string'), Text,
+                      Punctuation)),
+            (r'"', String.Double, ('#pop', 'for2', 'string')),
+            (rf"('(?:%%|{_variable}|[\w\W])*?')([{_nlws}]*)(\))",
+             bygroups(using(this, state='sqstring'), Text, Punctuation)),
+            (rf'(`(?:%%|{_variable}|[\w\W])*?`)([{_nlws}]*)(\))',
+             bygroups(using(this, state='bqstring'), Text, Punctuation)),
+            include('for2')
+        ],
+        'for/l': [
+            (r'-?\d+', Number.Integer),
+            include('for2')
+        ],
+        'if': [
+            (rf'((?:cmdextversion|errorlevel){_token_terminator})({_space})(\d+)',
+             bygroups(Keyword, using(this, state='text'),
+                      Number.Integer), '#pop'),
+            (rf'(defined{_token_terminator})({_space})({_stoken})',
+             bygroups(Keyword, using(this, state='text'),
+                      using(this, state='variable')), '#pop'),
+            (rf'(exist{_token_terminator})({_space}{_stoken})',
+             bygroups(Keyword, using(this, state='text')), '#pop'),
+            (rf'({_number}{_space})({_opword})({_space}{_number})',
+             bygroups(using(this, state='arithmetic'), Operator.Word,
+                      using(this, state='arithmetic')), '#pop'),
+            (_stoken, using(this, state='text'), ('#pop', 'if2')),
+        ],
+        'if2': [
+            (rf'({_space}?)(==)({_space}?{_stoken})',
+             bygroups(using(this, state='text'), Operator,
+                      using(this, state='text')), '#pop'),
+            (rf'({_space})({_opword})({_space}{_stoken})',
+             bygroups(using(this, state='text'), Operator.Word,
+                      using(this, state='text')), '#pop')
+        ],
+        '(?': [
+            (_space, using(this, state='text')),
+            (r'\(', Punctuation, ('#pop', 'else?', 'root/compound')),
+            default('#pop')
+        ],
+        'else?': [
+            (_space, using(this, state='text')),
+            (rf'else{_token_terminator}', Keyword, '#pop'),
+            default('#pop')
+        ]
+    }
+
+
+class MSDOSSessionLexer(ShellSessionBaseLexer):
+    """
+    Lexer for MS DOS shell sessions, i.e. command lines, including a
+    prompt, interspersed with output.
+    """
+
+    name = 'MSDOS Session'
+    aliases = ['doscon']
+    filenames = []
+    mimetypes = []
+    url = 'https://en.wikipedia.org/wiki/MS-DOS'
+    version_added = '2.1'
+    _example = "doscon/session"
+
+    _innerLexerCls = BatchLexer
+    _ps1rgx = re.compile(r'^([^>]*>)(.*\n?)')
+    _ps2 = 'More? '
+
+
+class TcshLexer(RegexLexer):
+    """
+    Lexer for tcsh scripts.
+    """
+
+    name = 'Tcsh'
+    aliases = ['tcsh', 'csh']
+    filenames = ['*.tcsh', '*.csh']
+    mimetypes = ['application/x-csh']
+    url = 'https://www.tcsh.org'
+    version_added = '0.10'
+
+    tokens = {
+        'root': [
+            include('basic'),
+            (r'\$\(', Keyword, 'paren'),
+            (r'\$\{#?', Keyword, 'curly'),
+            (r'`', String.Backtick, 'backticks'),
+            include('data'),
+        ],
+        'basic': [
+            (r'\b(if|endif|else|while|then|foreach|case|default|'
+             r'break|continue|goto|breaksw|end|switch|endsw)\s*\b',
+             Keyword),
+            (r'\b(alias|alloc|bg|bindkey|builtins|bye|caller|cd|chdir|'
+             r'complete|dirs|echo|echotc|eval|exec|exit|fg|filetest|getxvers|'
+             r'glob|getspath|hashstat|history|hup|inlib|jobs|kill|'
+             r'limit|log|login|logout|ls-F|migrate|newgrp|nice|nohup|notify|'
+             r'onintr|popd|printenv|pushd|rehash|repeat|rootnode|popd|pushd|'
+             r'set|shift|sched|setenv|setpath|settc|setty|setxvers|shift|'
+             r'source|stop|suspend|source|suspend|telltc|time|'
+             r'umask|unalias|uncomplete|unhash|universe|unlimit|unset|unsetenv|'
+             r'ver|wait|warp|watchlog|where|which)\s*\b',
+             Name.Builtin),
+            (r'#.*', Comment),
+            (r'\\[\w\W]', String.Escape),
+            (r'(\b\w+)(\s*)(=)', bygroups(Name.Variable, Text, Operator)),
+            (r'[\[\]{}()=]+', Operator),
+            (r'<<\s*(\'?)\\?(\w+)[\w\W]+?\2', String),
+            (r';', Punctuation),
+        ],
+        'data': [
+            (r'(?s)"(\\\\|\\[0-7]+|\\.|[^"\\])*"', String.Double),
+            (r"(?s)'(\\\\|\\[0-7]+|\\.|[^'\\])*'", String.Single),
+            (r'\s+', Text),
+            (r'[^=\s\[\]{}()$"\'`\\;#]+', Text),
+            (r'\d+(?= |\Z)', Number),
+            (r'\$#?(\w+|.)', Name.Variable),
+        ],
+        'curly': [
+            (r'\}', Keyword, '#pop'),
+            (r':-', Keyword),
+            (r'\w+', Name.Variable),
+            (r'[^}:"\'`$]+', Punctuation),
+            (r':', Punctuation),
+            include('root'),
+        ],
+        'paren': [
+            (r'\)', Keyword, '#pop'),
+            include('root'),
+        ],
+        'backticks': [
+            (r'`', String.Backtick, '#pop'),
+            include('root'),
+        ],
+    }
+
+
+class TcshSessionLexer(ShellSessionBaseLexer):
+    """
+    Lexer for Tcsh sessions, i.e. command lines, including a
+    prompt, interspersed with output.
+    """
+
+    name = 'Tcsh Session'
+    aliases = ['tcshcon']
+    filenames = []
+    mimetypes = []
+    url = 'https://www.tcsh.org'
+    version_added = '2.1'
+    _example = "tcshcon/session"
+
+    _innerLexerCls = TcshLexer
+    _ps1rgx = re.compile(r'^([^>]+>)(.*\n?)')
+    _ps2 = '? '
+
+
+class PowerShellLexer(RegexLexer):
+    """
+    For Windows PowerShell code.
+    """
+    name = 'PowerShell'
+    aliases = ['powershell', 'pwsh', 'posh', 'ps1', 'psm1']
+    filenames = ['*.ps1', '*.psm1']
+    mimetypes = ['text/x-powershell']
+    url = 'https://learn.microsoft.com/en-us/powershell'
+    version_added = '1.5'
+
+    flags = re.DOTALL | re.IGNORECASE | re.MULTILINE
+
+    keywords = (
+        'while validateset validaterange validatepattern validatelength '
+        'validatecount until trap switch return ref process param parameter in '
+        'if global: local: function foreach for finally filter end elseif else '
+        'dynamicparam do default continue cmdletbinding break begin alias \\? '
+        '% #script #private #local #global mandatory parametersetname position '
+        'valuefrompipeline valuefrompipelinebypropertyname '
+        'valuefromremainingarguments helpmessage try catch throw').split()
+
+    operators = (
+        'and as band bnot bor bxor casesensitive ccontains ceq cge cgt cle '
+        'clike clt cmatch cne cnotcontains cnotlike cnotmatch contains '
+        'creplace eq exact f file ge gt icontains ieq ige igt ile ilike ilt '
+        'imatch ine inotcontains inotlike inotmatch ireplace is isnot le like '
+        'lt match ne not notcontains notlike notmatch or regex replace '
+        'wildcard').split()
+
+    verbs = (
+        'write where watch wait use update unregister unpublish unprotect '
+        'unlock uninstall undo unblock trace test tee take sync switch '
+        'suspend submit stop step start split sort skip show set send select '
+        'search scroll save revoke resume restore restart resolve resize '
+        'reset request repair rename remove register redo receive read push '
+        'publish protect pop ping out optimize open new move mount merge '
+        'measure lock limit join invoke install initialize import hide group '
+        'grant get format foreach find export expand exit enter enable edit '
+        'dismount disconnect disable deny debug cxnew copy convertto '
+        'convertfrom convert connect confirm compress complete compare close '
+        'clear checkpoint block backup assert approve aggregate add').split()
+
+    aliases_ = (
+        'ac asnp cat cd cfs chdir clc clear clhy cli clp cls clv cnsn '
+        'compare copy cp cpi cpp curl cvpa dbp del diff dir dnsn ebp echo epal '
+        'epcsv epsn erase etsn exsn fc fhx fl foreach ft fw gal gbp gc gci gcm '
+        'gcs gdr ghy gi gjb gl gm gmo gp gps gpv group gsn gsnp gsv gu gv gwmi '
+        'h history icm iex ihy ii ipal ipcsv ipmo ipsn irm ise iwmi iwr kill lp '
+        'ls man md measure mi mount move mp mv nal ndr ni nmo npssc nsn nv ogv '
+        'oh popd ps pushd pwd r rbp rcjb rcsn rd rdr ren ri rjb rm rmdir rmo '
+        'rni rnp rp rsn rsnp rujb rv rvpa rwmi sajb sal saps sasv sbp sc select '
+        'set shcm si sl sleep sls sort sp spjb spps spsv start sujb sv swmi tee '
+        'trcm type wget where wjb write').split()
+
+    commenthelp = (
+        'component description example externalhelp forwardhelpcategory '
+        'forwardhelptargetname functionality inputs link '
+        'notes outputs parameter remotehelprunspace role synopsis').split()
+
+    tokens = {
+        'root': [
+            # we need to count pairs of parentheses for correct highlight
+            # of '$(...)' blocks in strings
+            (r'\(', Punctuation, 'child'),
+            (r'\s+', Text),
+            (r'^(\s*#[#\s]*)(\.(?:{}))([^\n]*$)'.format('|'.join(commenthelp)),
+             bygroups(Comment, String.Doc, Comment)),
+            (r'#[^\n]*?$', Comment),
+            (r'(&lt;|<)#', Comment.Multiline, 'multline'),
+            (r'@"\n', String.Heredoc, 'heredoc-double'),
+            (r"@'\n.*?\n'@", String.Heredoc),
+            # escaped syntax
+            (r'`[\'"$@-]', Punctuation),
+            (r'"', String.Double, 'string'),
+            (r"'([^']|'')*'", String.Single),
+            (r'(\$|@@|@)((global|script|private|env):)?\w+',
+             Name.Variable),
+            (r'({})\b'.format('|'.join(keywords)), Keyword),
+            (r'-({})\b'.format('|'.join(operators)), Operator),
+            (r'({})-[a-z_]\w*\b'.format('|'.join(verbs)), Name.Builtin),
+            (r'({})\s'.format('|'.join(aliases_)), Name.Builtin),
+            (r'\[[a-z_\[][\w. `,\[\]]*\]', Name.Constant),  # .net [type]s
+            (r'-[a-z_]\w*', Name),
+            (r'\w+', Name),
+            (r'[.,;:@{}\[\]$()=+*/\\&%!~?^`|<>-]', Punctuation),
+        ],
+        'child': [
+            (r'\)', Punctuation, '#pop'),
+            include('root'),
+        ],
+        'multline': [
+            (r'[^#&.]+', Comment.Multiline),
+            (r'#(>|&gt;)', Comment.Multiline, '#pop'),
+            (r'\.({})'.format('|'.join(commenthelp)), String.Doc),
+            (r'[#&.]', Comment.Multiline),
+        ],
+        'string': [
+            (r"`[0abfnrtv'\"$`]", String.Escape),
+            (r'[^$`"]+', String.Double),
+            (r'\$\(', Punctuation, 'child'),
+            (r'""', String.Double),
+            (r'[`$]', String.Double),
+            (r'"', String.Double, '#pop'),
+        ],
+        'heredoc-double': [
+            (r'\n"@', String.Heredoc, '#pop'),
+            (r'\$\(', Punctuation, 'child'),
+            (r'[^@\n]+"]', String.Heredoc),
+            (r".", String.Heredoc),
+        ]
+    }
+
+
+class PowerShellSessionLexer(ShellSessionBaseLexer):
+    """
+    Lexer for PowerShell sessions, i.e. command lines, including a
+    prompt, interspersed with output.
+    """
+
+    name = 'PowerShell Session'
+    aliases = ['pwsh-session', 'ps1con']
+    filenames = []
+    mimetypes = []
+    url = 'https://learn.microsoft.com/en-us/powershell'
+    version_added = '2.1'
+    _example = "pwsh-session/session"
+
+    _innerLexerCls = PowerShellLexer
+    _bare_continuation = True
+    _ps1rgx = re.compile(r'^((?:\[[^]]+\]: )?PS[^>]*> ?)(.*\n?)')
+    _ps2 = '> '
+
+
+class FishShellLexer(RegexLexer):
+    """
+    Lexer for Fish shell scripts.
+    """
+
+    name = 'Fish'
+    aliases = ['fish', 'fishshell']
+    filenames = ['*.fish', '*.load']
+    mimetypes = ['application/x-fish']
+    url = 'https://fishshell.com'
+    version_added = '2.1'
+
+    tokens = {
+        'root': [
+            include('basic'),
+            include('data'),
+            include('interp'),
+        ],
+        'interp': [
+            (r'\$\(\(', Keyword, 'math'),
+            (r'\(', Keyword, 'paren'),
+            (r'\$#?(\w+|.)', Name.Variable),
+        ],
+        'basic': [
+            (r'\b(begin|end|if|else|while|break|for|in|return|function|block|'
+             r'case|continue|switch|not|and|or|set|echo|exit|pwd|true|false|'
+             r'cd|count|test)(\s*)\b',
+             bygroups(Keyword, Text)),
+            (r'\b(alias|bg|bind|breakpoint|builtin|command|commandline|'
+             r'complete|contains|dirh|dirs|emit|eval|exec|fg|fish|fish_config|'
+             r'fish_indent|fish_pager|fish_prompt|fish_right_prompt|'
+             r'fish_update_completions|fishd|funced|funcsave|functions|help|'
+             r'history|isatty|jobs|math|mimedb|nextd|open|popd|prevd|psub|'
+             r'pushd|random|read|set_color|source|status|trap|type|ulimit|'
+             r'umask|vared|fc|getopts|hash|kill|printf|time|wait)\s*\b(?!\.)',
+             Name.Builtin),
+            (r'#.*\n', Comment),
+            (r'\\[\w\W]', String.Escape),
+            (r'(\b\w+)(\s*)(=)', bygroups(Name.Variable, Whitespace, Operator)),
+            (r'[\[\]()=]', Operator),
+            (r'<<-?\s*(\'?)\\?(\w+)[\w\W]+?\2', String),
+        ],
+        'data': [
+            (r'(?s)\$?"(\\\\|\\[0-7]+|\\.|[^"\\$])*"', String.Double),
+            (r'"', String.Double, 'string'),
+            (r"(?s)\$'(\\\\|\\[0-7]+|\\.|[^'\\])*'", String.Single),
+            (r"(?s)'.*?'", String.Single),
+            (r';', Punctuation),
+            (r'&|\||\^|<|>', Operator),
+            (r'\s+', Text),
+            (r'\d+(?= |\Z)', Number),
+            (r'[^=\s\[\]{}()$"\'`\\<&|;]+', Text),
+        ],
+        'string': [
+            (r'"', String.Double, '#pop'),
+            (r'(?s)(\\\\|\\[0-7]+|\\.|[^"\\$])+', String.Double),
+            include('interp'),
+        ],
+        'paren': [
+            (r'\)', Keyword, '#pop'),
+            include('root'),
+        ],
+        'math': [
+            (r'\)\)', Keyword, '#pop'),
+            (r'[-+*/%^|&]|\*\*|\|\|', Operator),
+            (r'\d+#\d+', Number),
+            (r'\d+#(?! )', Number),
+            (r'\d+', Number),
+            include('root'),
+        ],
+    }
+
+class ExeclineLexer(RegexLexer):
+    """
+    Lexer for Laurent Bercot's execline language.
+    """
+
+    name = 'execline'
+    aliases = ['execline']
+    filenames = ['*.exec']
+    url = 'https://skarnet.org/software/execline'
+    version_added = '2.7'
+
+    tokens = {
+        'root': [
+            include('basic'),
+            include('data'),
+            include('interp')
+        ],
+        'interp': [
+            (r'\$\{', String.Interpol, 'curly'),
+            (r'\$[\w@#]+', Name.Variable),  # user variable
+            (r'\$', Text),
+        ],
+        'basic': [
+            (r'\b(background|backtick|cd|define|dollarat|elgetopt|'
+             r'elgetpositionals|elglob|emptyenv|envfile|exec|execlineb|'
+             r'exit|export|fdblock|fdclose|fdmove|fdreserve|fdswap|'
+             r'forbacktickx|foreground|forstdin|forx|getcwd|getpid|heredoc|'
+             r'homeof|if|ifelse|ifte|ifthenelse|importas|loopwhilex|'
+             r'multidefine|multisubstitute|pipeline|piperw|posix-cd|'
+             r'redirfd|runblock|shift|trap|tryexec|umask|unexport|wait|'
+             r'withstdinas)\b', Name.Builtin),
+            (r'\A#!.+\n', Comment.Hashbang),
+            (r'#.*\n', Comment.Single),
+            (r'[{}]', Operator)
+        ],
+        'data': [
+            (r'(?s)"(\\.|[^"\\$])*"', String.Double),
+            (r'"', String.Double, 'string'),
+            (r'\s+', Text),
+            (r'[^\s{}$"\\]+', Text)
+        ],
+        'string': [
+            (r'"', String.Double, '#pop'),
+            (r'(?s)(\\\\|\\.|[^"\\$])+', String.Double),
+            include('interp'),
+        ],
+        'curly': [
+            (r'\}', String.Interpol, '#pop'),
+            (r'[\w#@]+', Name.Variable),
+            include('root')
+        ]
+
+    }
+
+    def analyse_text(text):
+        if shebang_matches(text, r'execlineb'):
+            return 1

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/smalltalk.py

@@ -0,0 +1,194 @@
+"""
+    pygments.lexers.smalltalk
+    ~~~~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexers for Smalltalk and related languages.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import RegexLexer, include, bygroups, default
+from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation
+
+__all__ = ['SmalltalkLexer', 'NewspeakLexer']
+
+
+class SmalltalkLexer(RegexLexer):
+    """
+    For Smalltalk syntax.
+    Contributed by Stefan Matthias Aust.
+    Rewritten by Nils Winter.
+    """
+    name = 'Smalltalk'
+    url = 'http://www.smalltalk.org/'
+    filenames = ['*.st']
+    aliases = ['smalltalk', 'squeak', 'st']
+    mimetypes = ['text/x-smalltalk']
+    version_added = '0.10'
+
+    tokens = {
+        'root': [
+            (r'(<)(\w+:)(.*?)(>)', bygroups(Text, Keyword, Text, Text)),
+            include('squeak fileout'),
+            include('whitespaces'),
+            include('method definition'),
+            (r'(\|)([\w\s]*)(\|)', bygroups(Operator, Name.Variable, Operator)),
+            include('objects'),
+            (r'\^|\:=|\_', Operator),
+            # temporaries
+            (r'[\]({}.;!]', Text),
+        ],
+        'method definition': [
+            # Not perfect can't allow whitespaces at the beginning and the
+            # without breaking everything
+            (r'([a-zA-Z]+\w*:)(\s*)(\w+)',
+             bygroups(Name.Function, Text, Name.Variable)),
+            (r'^(\b[a-zA-Z]+\w*\b)(\s*)$', bygroups(Name.Function, Text)),
+            (r'^([-+*/\\~<>=|&!?,@%]+)(\s*)(\w+)(\s*)$',
+             bygroups(Name.Function, Text, Name.Variable, Text)),
+        ],
+        'blockvariables': [
+            include('whitespaces'),
+            (r'(:)(\s*)(\w+)',
+             bygroups(Operator, Text, Name.Variable)),
+            (r'\|', Operator, '#pop'),
+            default('#pop'),  # else pop
+        ],
+        'literals': [
+            (r"'(''|[^'])*'", String, 'afterobject'),
+            (r'\$.', String.Char, 'afterobject'),
+            (r'#\(', String.Symbol, 'parenth'),
+            (r'\)', Text, 'afterobject'),
+            (r'(\d+r)?-?\d+(\.\d+)?(e-?\d+)?', Number, 'afterobject'),
+        ],
+        '_parenth_helper': [
+            include('whitespaces'),
+            (r'(\d+r)?-?\d+(\.\d+)?(e-?\d+)?', Number),
+            (r'[-+*/\\~<>=|&#!?,@%\w:]+', String.Symbol),
+            # literals
+            (r"'(''|[^'])*'", String),
+            (r'\$.', String.Char),
+            (r'#*\(', String.Symbol, 'inner_parenth'),
+        ],
+        'parenth': [
+            # This state is a bit tricky since
+            # we can't just pop this state
+            (r'\)', String.Symbol, ('root', 'afterobject')),
+            include('_parenth_helper'),
+        ],
+        'inner_parenth': [
+            (r'\)', String.Symbol, '#pop'),
+            include('_parenth_helper'),
+        ],
+        'whitespaces': [
+            # skip whitespace and comments
+            (r'\s+', Text),
+            (r'"(""|[^"])*"', Comment),
+        ],
+        'objects': [
+            (r'\[', Text, 'blockvariables'),
+            (r'\]', Text, 'afterobject'),
+            (r'\b(self|super|true|false|nil|thisContext)\b',
+             Name.Builtin.Pseudo, 'afterobject'),
+            (r'\b[A-Z]\w*(?!:)\b', Name.Class, 'afterobject'),
+            (r'\b[a-z]\w*(?!:)\b', Name.Variable, 'afterobject'),
+            (r'#("(""|[^"])*"|[-+*/\\~<>=|&!?,@%]+|[\w:]+)',
+             String.Symbol, 'afterobject'),
+            include('literals'),
+        ],
+        'afterobject': [
+            (r'! !$', Keyword, '#pop'),  # squeak chunk delimiter
+            include('whitespaces'),
+            (r'\b(ifTrue:|ifFalse:|whileTrue:|whileFalse:|timesRepeat:)',
+             Name.Builtin, '#pop'),
+            (r'\b(new\b(?!:))', Name.Builtin),
+            (r'\:=|\_', Operator, '#pop'),
+            (r'\b[a-zA-Z]+\w*:', Name.Function, '#pop'),
+            (r'\b[a-zA-Z]+\w*', Name.Function),
+            (r'\w+:?|[-+*/\\~<>=|&!?,@%]+', Name.Function, '#pop'),
+            (r'\.', Punctuation, '#pop'),
+            (r';', Punctuation),
+            (r'[\])}]', Text),
+            (r'[\[({]', Text, '#pop'),
+        ],
+        'squeak fileout': [
+            # Squeak fileout format (optional)
+            (r'^"(""|[^"])*"!', Keyword),
+            (r"^'(''|[^'])*'!", Keyword),
+            (r'^(!)(\w+)( commentStamp: )(.*?)( prior: .*?!\n)(.*?)(!)',
+                bygroups(Keyword, Name.Class, Keyword, String, Keyword, Text, Keyword)),
+            (r"^(!)(\w+(?: class)?)( methodsFor: )('(?:''|[^'])*')(.*?!)",
+                bygroups(Keyword, Name.Class, Keyword, String, Keyword)),
+            (r'^(\w+)( subclass: )(#\w+)'
+             r'(\s+instanceVariableNames: )(.*?)'
+             r'(\s+classVariableNames: )(.*?)'
+             r'(\s+poolDictionaries: )(.*?)'
+             r'(\s+category: )(.*?)(!)',
+                bygroups(Name.Class, Keyword, String.Symbol, Keyword, String, Keyword,
+                         String, Keyword, String, Keyword, String, Keyword)),
+            (r'^(\w+(?: class)?)(\s+instanceVariableNames: )(.*?)(!)',
+                bygroups(Name.Class, Keyword, String, Keyword)),
+            (r'(!\n)(\].*)(! !)$', bygroups(Keyword, Text, Keyword)),
+            (r'! !$', Keyword),
+        ],
+    }
+
+
+class NewspeakLexer(RegexLexer):
+    """
+    For Newspeak syntax.
+    """
+    name = 'Newspeak'
+    url = 'http://newspeaklanguage.org/'
+    filenames = ['*.ns2']
+    aliases = ['newspeak', ]
+    mimetypes = ['text/x-newspeak']
+    version_added = '1.1'
+
+    tokens = {
+        'root': [
+            (r'\b(Newsqueak2)\b', Keyword.Declaration),
+            (r"'[^']*'", String),
+            (r'\b(class)(\s+)(\w+)(\s*)',
+             bygroups(Keyword.Declaration, Text, Name.Class, Text)),
+            (r'\b(mixin|self|super|private|public|protected|nil|true|false)\b',
+             Keyword),
+            (r'(\w+\:)(\s*)([a-zA-Z_]\w+)',
+             bygroups(Name.Function, Text, Name.Variable)),
+            (r'(\w+)(\s*)(=)',
+             bygroups(Name.Attribute, Text, Operator)),
+            (r'<\w+>', Comment.Special),
+            include('expressionstat'),
+            include('whitespace')
+        ],
+
+        'expressionstat': [
+            (r'(\d+\.\d*|\.\d+|\d+[fF])[fF]?', Number.Float),
+            (r'\d+', Number.Integer),
+            (r':\w+', Name.Variable),
+            (r'(\w+)(::)', bygroups(Name.Variable, Operator)),
+            (r'\w+:', Name.Function),
+            (r'\w+', Name.Variable),
+            (r'\(|\)', Punctuation),
+            (r'\[|\]', Punctuation),
+            (r'\{|\}', Punctuation),
+
+            (r'(\^|\+|\/|~|\*|<|>|=|@|%|\||&|\?|!|,|-|:)', Operator),
+            (r'\.|;', Punctuation),
+            include('whitespace'),
+            include('literals'),
+        ],
+        'literals': [
+            (r'\$.', String),
+            (r"'[^']*'", String),
+            (r"#'[^']*'", String.Symbol),
+            (r"#\w+:?", String.Symbol),
+            (r"#(\+|\/|~|\*|<|>|=|@|%|\||&|\?|!|,|-)+", String.Symbol)
+        ],
+        'whitespace': [
+            (r'\s+', Text),
+            (r'"[^"]*"', Comment)
+        ],
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/sql.py

@@ -0,0 +1,1111 @@
+"""
+    pygments.lexers.sql
+    ~~~~~~~~~~~~~~~~~~~
+
+    Lexers for various SQL dialects and related interactive sessions.
+
+    Postgres specific lexers:
+
+    `PostgresLexer`
+        A SQL lexer for the PostgreSQL dialect. Differences w.r.t. the SQL
+        lexer are:
+
+        - keywords and data types list parsed from the PG docs (run the
+          `_postgres_builtins` module to update them);
+        - Content of $-strings parsed using a specific lexer, e.g. the content
+          of a PL/Python function is parsed using the Python lexer;
+        - parse PG specific constructs: E-strings, $-strings, U&-strings,
+          different operators and punctuation.
+
+    `PlPgsqlLexer`
+        A lexer for the PL/pgSQL language. Adds a few specific construct on
+        top of the PG SQL lexer (such as <<label>>).
+
+    `PostgresConsoleLexer`
+        A lexer to highlight an interactive psql session:
+
+        - identifies the prompt and does its best to detect the end of command
+          in multiline statement where not all the lines are prefixed by a
+          prompt, telling them apart from the output;
+        - highlights errors in the output and notification levels;
+        - handles psql backslash commands.
+
+    `PostgresExplainLexer`
+        A lexer to highlight Postgres execution plan.
+
+    The ``tests/examplefiles`` contains a few test files with data to be
+    parsed by these lexers.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import collections
+import re
+
+from pygments.lexer import Lexer, RegexLexer, do_insertions, bygroups, words
+from pygments.lexers import _googlesql_builtins
+from pygments.lexers import _mysql_builtins
+from pygments.lexers import _postgres_builtins
+from pygments.lexers import _sql_builtins
+from pygments.lexers import _tsql_builtins
+from pygments.lexers import get_lexer_by_name, ClassNotFound
+from pygments.token import Punctuation, Whitespace, Text, Comment, Operator, \
+    Keyword, Name, String, Number, Generic, Literal
+
+
+__all__ = ['GoogleSqlLexer', 'PostgresLexer', 'PlPgsqlLexer',
+           'PostgresConsoleLexer', 'PostgresExplainLexer', 'SqlLexer',
+           'TransactSqlLexer', 'MySqlLexer', 'SqliteConsoleLexer', 'RqlLexer']
+
+line_re  = re.compile('.*?\n')
+sqlite_prompt_re = re.compile(r'^(?:sqlite|   ...)>(?= )')
+
+language_re = re.compile(r"\s+LANGUAGE\s+'?(\w+)'?", re.IGNORECASE)
+
+do_re = re.compile(r'\bDO\b', re.IGNORECASE)
+
+# Regular expressions for analyse_text()
+name_between_bracket_re = re.compile(r'\[[a-zA-Z_]\w*\]')
+name_between_backtick_re = re.compile(r'`[a-zA-Z_]\w*`')
+tsql_go_re = re.compile(r'\bgo\b', re.IGNORECASE)
+tsql_declare_re = re.compile(r'\bdeclare\s+@', re.IGNORECASE)
+tsql_variable_re = re.compile(r'@[a-zA-Z_]\w*\b')
+
+# Identifiers for analyse_text()
+googlesql_identifiers = (
+    _googlesql_builtins.functionnames
+    + _googlesql_builtins.keywords
+    + _googlesql_builtins.types)
+
+
+def language_callback(lexer, match):
+    """Parse the content of a $-string using a lexer
+
+    The lexer is chosen looking for a nearby LANGUAGE or assumed as
+    plpgsql if inside a DO statement and no LANGUAGE has been found.
+    """
+    lx = None
+    m = language_re.match(lexer.text[match.end():match.end()+100])
+    if m is not None:
+        lx = lexer._get_lexer(m.group(1))
+    else:
+        m = list(language_re.finditer(
+            lexer.text[max(0, match.start()-100):match.start()]))
+        if m:
+            lx = lexer._get_lexer(m[-1].group(1))
+        else:
+            m = list(do_re.finditer(
+                lexer.text[max(0, match.start()-25):match.start()]))
+            if m:
+                lx = lexer._get_lexer('plpgsql')
+
+    # 1 = $, 2 = delimiter, 3 = $
+    yield (match.start(1), String, match.group(1))
+    yield (match.start(2), String.Delimiter, match.group(2))
+    yield (match.start(3), String, match.group(3))
+    # 4 = string contents
+    if lx:
+        yield from lx.get_tokens_unprocessed(match.group(4))
+    else:
+        yield (match.start(4), String, match.group(4))
+    # 5 = $, 6 = delimiter, 7 = $
+    yield (match.start(5), String, match.group(5))
+    yield (match.start(6), String.Delimiter, match.group(6))
+    yield (match.start(7), String, match.group(7))
+
+
+class PostgresBase:
+    """Base class for Postgres-related lexers.
+
+    This is implemented as a mixin to avoid the Lexer metaclass kicking in.
+    this way the different lexer don't have a common Lexer ancestor. If they
+    had, _tokens could be created on this ancestor and not updated for the
+    other classes, resulting e.g. in PL/pgSQL parsed as SQL. This shortcoming
+    seem to suggest that regexp lexers are not really subclassable.
+    """
+    def get_tokens_unprocessed(self, text, *args):
+        # Have a copy of the entire text to be used by `language_callback`.
+        self.text = text
+        yield from super().get_tokens_unprocessed(text, *args)
+
+    def _get_lexer(self, lang):
+        if lang.lower() == 'sql':
+            return get_lexer_by_name('postgresql', **self.options)
+
+        tries = [lang]
+        if lang.startswith('pl'):
+            tries.append(lang[2:])
+        if lang.endswith('u'):
+            tries.append(lang[:-1])
+        if lang.startswith('pl') and lang.endswith('u'):
+            tries.append(lang[2:-1])
+
+        for lx in tries:
+            try:
+                return get_lexer_by_name(lx, **self.options)
+            except ClassNotFound:
+                pass
+        else:
+            # TODO: better logging
+            # print >>sys.stderr, "language not found:", lang
+            return None
+
+
+class PostgresLexer(PostgresBase, RegexLexer):
+    """
+    Lexer for the PostgreSQL dialect of SQL.
+    """
+
+    name = 'PostgreSQL SQL dialect'
+    aliases = ['postgresql', 'postgres']
+    mimetypes = ['text/x-postgresql']
+    url = 'https://www.postgresql.org'
+    version_added = '1.5'
+
+    flags = re.IGNORECASE
+    tokens = {
+        'root': [
+            (r'\s+', Whitespace),
+            (r'--.*\n?', Comment.Single),
+            (r'/\*', Comment.Multiline, 'multiline-comments'),
+            (r'(' + '|'.join(s.replace(" ", r"\s+")
+                             for s in _postgres_builtins.DATATYPES +
+                             _postgres_builtins.PSEUDO_TYPES) + r')\b',
+             Name.Builtin),
+            (words(_postgres_builtins.KEYWORDS, suffix=r'\b'), Keyword),
+            (r'[+*/<>=~!@#%^&|`?-]+', Operator),
+            (r'::', Operator),  # cast
+            (r'\$\d+', Name.Variable),
+            (r'([0-9]*\.[0-9]*|[0-9]+)(e[+-]?[0-9]+)?', Number.Float),
+            (r'[0-9]+', Number.Integer),
+            (r"((?:E|U&)?)(')", bygroups(String.Affix, String.Single), 'string'),
+            # quoted identifier
+            (r'((?:U&)?)(")', bygroups(String.Affix, String.Name), 'quoted-ident'),
+            (r'(?s)(\$)([^$]*)(\$)(.*?)(\$)(\2)(\$)', language_callback),
+            (r'[a-z_]\w*', Name),
+
+            # psql variable in SQL
+            (r""":(['"]?)[a-z]\w*\b\1""", Name.Variable),
+
+            (r'[;:()\[\]{},.]', Punctuation),
+        ],
+        'multiline-comments': [
+            (r'/\*', Comment.Multiline, 'multiline-comments'),
+            (r'\*/', Comment.Multiline, '#pop'),
+            (r'[^/*]+', Comment.Multiline),
+            (r'[/*]', Comment.Multiline)
+        ],
+        'string': [
+            (r"[^']+", String.Single),
+            (r"''", String.Single),
+            (r"'", String.Single, '#pop'),
+        ],
+        'quoted-ident': [
+            (r'[^"]+', String.Name),
+            (r'""', String.Name),
+            (r'"', String.Name, '#pop'),
+        ],
+    }
+
+
+class PlPgsqlLexer(PostgresBase, RegexLexer):
+    """
+    Handle the extra syntax in Pl/pgSQL language.
+    """
+    name = 'PL/pgSQL'
+    aliases = ['plpgsql']
+    mimetypes = ['text/x-plpgsql']
+    url = 'https://www.postgresql.org/docs/current/plpgsql.html'
+    version_added = '1.5'
+
+    flags = re.IGNORECASE
+    # FIXME: use inheritance
+    tokens = {name: state[:] for (name, state) in PostgresLexer.tokens.items()}
+
+    # extend the keywords list
+    for i, pattern in enumerate(tokens['root']):
+        if pattern[1] == Keyword:
+            tokens['root'][i] = (
+                words(_postgres_builtins.KEYWORDS +
+                      _postgres_builtins.PLPGSQL_KEYWORDS, suffix=r'\b'),
+                Keyword)
+            del i
+            break
+    else:
+        assert 0, "SQL keywords not found"
+
+    # Add specific PL/pgSQL rules (before the SQL ones)
+    tokens['root'][:0] = [
+        (r'\%[a-z]\w*\b', Name.Builtin),     # actually, a datatype
+        (r':=', Operator),
+        (r'\<\<[a-z]\w*\>\>', Name.Label),
+        (r'\#[a-z]\w*\b', Keyword.Pseudo),   # #variable_conflict
+    ]
+
+
+class PsqlRegexLexer(PostgresBase, RegexLexer):
+    """
+    Extend the PostgresLexer adding support specific for psql commands.
+
+    This is not a complete psql lexer yet as it lacks prompt support
+    and output rendering.
+    """
+
+    name = 'PostgreSQL console - regexp based lexer'
+    aliases = []    # not public
+
+    flags = re.IGNORECASE
+    tokens = {name: state[:] for (name, state) in PostgresLexer.tokens.items()}
+
+    tokens['root'].append(
+        (r'\\[^\s]+', Keyword.Pseudo, 'psql-command'))
+    tokens['psql-command'] = [
+        (r'\n', Text, 'root'),
+        (r'\s+', Whitespace),
+        (r'\\[^\s]+', Keyword.Pseudo),
+        (r""":(['"]?)[a-z]\w*\b\1""", Name.Variable),
+        (r"'(''|[^'])*'", String.Single),
+        (r"`([^`])*`", String.Backtick),
+        (r"[^\s]+", String.Symbol),
+    ]
+
+
+re_prompt = re.compile(r'^(\S.*?)??[=\-\(\$\'\"][#>]')
+re_psql_command = re.compile(r'\s*\\')
+re_end_command = re.compile(r';\s*(--.*?)?$')
+re_psql_command = re.compile(r'(\s*)(\\.+?)(\s+)$')
+re_error = re.compile(r'(ERROR|FATAL):')
+re_message = re.compile(
+    r'((?:DEBUG|INFO|NOTICE|WARNING|ERROR|'
+    r'FATAL|HINT|DETAIL|CONTEXT|LINE [0-9]+):)(.*?\n)')
+
+
+class lookahead:
+    """Wrap an iterator and allow pushing back an item."""
+    def __init__(self, x):
+        self.iter = iter(x)
+        self._nextitem = None
+
+    def __iter__(self):
+        return self
+
+    def send(self, i):
+        self._nextitem = i
+        return i
+
+    def __next__(self):
+        if self._nextitem is not None:
+            ni = self._nextitem
+            self._nextitem = None
+            return ni
+        return next(self.iter)
+    next = __next__
+
+
+class PostgresConsoleLexer(Lexer):
+    """
+    Lexer for psql sessions.
+    """
+
+    name = 'PostgreSQL console (psql)'
+    aliases = ['psql', 'postgresql-console', 'postgres-console']
+    mimetypes = ['text/x-postgresql-psql']
+    url = 'https://www.postgresql.org'
+    version_added = '1.5'
+    _example = "psql/psql_session.txt"
+
+    def get_tokens_unprocessed(self, data):
+        sql = PsqlRegexLexer(**self.options)
+
+        lines = lookahead(line_re.findall(data))
+
+        # prompt-output cycle
+        while 1:
+
+            # consume the lines of the command: start with an optional prompt
+            # and continue until the end of command is detected
+            curcode = ''
+            insertions = []
+            for line in lines:
+                # Identify a shell prompt in case of psql commandline example
+                if line.startswith('$') and not curcode:
+                    lexer = get_lexer_by_name('console', **self.options)
+                    yield from lexer.get_tokens_unprocessed(line)
+                    break
+
+                # Identify a psql prompt
+                mprompt = re_prompt.match(line)
+                if mprompt is not None:
+                    insertions.append((len(curcode),
+                                       [(0, Generic.Prompt, mprompt.group())]))
+                    curcode += line[len(mprompt.group()):]
+                else:
+                    curcode += line
+
+                # Check if this is the end of the command
+                # TODO: better handle multiline comments at the end with
+                # a lexer with an external state?
+                if re_psql_command.match(curcode) \
+                   or re_end_command.search(curcode):
+                    break
+
+            # Emit the combined stream of command and prompt(s)
+            yield from do_insertions(insertions,
+                                     sql.get_tokens_unprocessed(curcode))
+
+            # Emit the output lines
+            out_token = Generic.Output
+            for line in lines:
+                mprompt = re_prompt.match(line)
+                if mprompt is not None:
+                    # push the line back to have it processed by the prompt
+                    lines.send(line)
+                    break
+
+                mmsg = re_message.match(line)
+                if mmsg is not None:
+                    if mmsg.group(1).startswith("ERROR") \
+                       or mmsg.group(1).startswith("FATAL"):
+                        out_token = Generic.Error
+                    yield (mmsg.start(1), Generic.Strong, mmsg.group(1))
+                    yield (mmsg.start(2), out_token, mmsg.group(2))
+                else:
+                    yield (0, out_token, line)
+            else:
+                return
+
+
+class PostgresExplainLexer(RegexLexer):
+    """
+    Handle PostgreSQL EXPLAIN output
+    """
+
+    name = 'PostgreSQL EXPLAIN dialect'
+    aliases = ['postgres-explain']
+    filenames = ['*.explain']
+    mimetypes = ['text/x-postgresql-explain']
+    url = 'https://www.postgresql.org/docs/current/using-explain.html'
+    version_added = '2.15'
+
+    tokens = {
+        'root': [
+            (r'(:|\(|\)|ms|kB|->|\.\.|\,|\/|=|%)', Punctuation),
+            (r'(\s+)', Whitespace),
+
+            # This match estimated cost and effectively measured counters with ANALYZE
+            # Then, we move to instrumentation state
+            (r'(cost)(=?)', bygroups(Name.Class, Punctuation), 'instrumentation'),
+            (r'(actual)( )(=?)', bygroups(Name.Class, Whitespace, Punctuation), 'instrumentation'),
+
+            # Misc keywords
+            (words(('actual', 'Memory Usage', 'Disk Usage', 'Memory', 'Buckets',
+                    'Batches', 'originally', 'row', 'rows', 'Hits', 'Misses',
+                    'Evictions', 'Overflows', 'Planned Partitions', 'Estimates',
+                    'capacity', 'distinct keys', 'lookups', 'hit percent',
+                    'Index Searches', 'Storage', 'Disk Maximum Storage'), suffix=r'\b'),
+             Comment.Single),
+
+            (r'(hit|read|dirtied|written|write|time|calls)(=)', bygroups(Comment.Single, Operator)),
+            (r'(shared|temp|local)', Keyword.Pseudo),
+
+            # We move to sort state in order to emphasize specific keywords (especially disk access)
+            (r'(Sort Method)(: )', bygroups(Comment.Preproc, Punctuation), 'sort'),
+
+            # These keywords can be followed by an object, like a table
+            (r'(Sort Key|Group Key|Presorted Key|Hash Key)(:)( )',
+             bygroups(Comment.Preproc, Punctuation, Whitespace), 'object_name'),
+            (r'(Cache Key|Cache Mode)(:)( )', bygroups(Comment, Punctuation, Whitespace), 'object_name'),
+
+            # These keywords can be followed by a predicate
+            (words(('Join Filter', 'Subplans Removed', 'Filter', 'Merge Cond',
+                    'Hash Cond', 'Index Cond', 'Recheck Cond', 'Heap Blocks',
+                    'TID Cond', 'Run Condition', 'Order By', 'Function Call',
+                    'Table Function Call', 'Inner Unique', 'Params Evaluated',
+                    'Single Copy', 'Sampling', 'One-Time Filter', 'Output',
+                    'Relations', 'Remote SQL', 'Disabled'), suffix=r'\b'),
+             Comment.Preproc, 'predicate'),
+
+            # Special keyword to handle ON CONFLICT
+            (r'Conflict ', Comment.Preproc, 'conflict'),
+
+            # Special keyword for InitPlan or SubPlan
+            (r'(InitPlan|SubPlan)( )(\d+)( )',
+             bygroups(Keyword, Whitespace, Number.Integer, Whitespace),
+             'init_plan'),
+
+            (words(('Sort Method', 'Join Filter', 'Planning time',
+                    'Planning Time', 'Execution time', 'Execution Time',
+                    'Workers Planned', 'Workers Launched', 'Buffers',
+                    'Planning', 'Worker', 'Query Identifier', 'Time',
+                    'Full-sort Groups', 'Pre-sorted Groups'), suffix=r'\b'), Comment.Preproc),
+
+            # Emphasize these keywords
+
+            (words(('Rows Removed by Join Filter', 'Rows Removed by Filter',
+                    'Rows Removed by Index Recheck',
+                    'Heap Fetches', 'never executed'),
+                   suffix=r'\b'), Name.Exception),
+            (r'(I/O Timings)(:)( )', bygroups(Name.Exception, Punctuation, Whitespace)),
+
+            (words(_postgres_builtins.EXPLAIN_KEYWORDS, suffix=r'\b'), Keyword),
+
+            # join keywords
+            (r'((Right|Left|Full|Semi|Anti) Join)', Keyword.Type),
+            (r'(Parallel |Async |Finalize |Partial )', Comment.Preproc),
+            (r'Backward', Comment.Preproc),
+            (r'(Intersect|Except|Hash)', Comment.Preproc),
+
+            (r'(CTE)( )(\w*)?', bygroups(Comment, Whitespace, Name.Variable)),
+
+
+            # Treat "on" and "using" as a punctuation
+            (r'(on|using)', Punctuation, 'object_name'),
+
+
+            # strings
+            (r"'(''|[^'])*'", String.Single),
+            # numbers
+            (r'-?\d+\.\d+', Number.Float),
+            (r'(-?\d+)', Number.Integer),
+
+            # boolean
+            (r'(true|false)', Name.Constant),
+            # explain header
+            (r'\s*QUERY PLAN\s*\n\s*-+', Comment.Single),
+            # Settings
+            (r'(Settings)(:)( )', bygroups(Comment.Preproc, Punctuation, Whitespace), 'setting'),
+
+            # Handle JIT counters
+            (r'(JIT|Functions|Options|Timing)(:)', bygroups(Comment.Preproc, Punctuation)),
+            (r'(Inlining|Optimization|Expressions|Deforming|Generation|Emission|Total)', Keyword.Pseudo),
+
+            # Handle Triggers counters
+            (r'(Trigger)( )(\S*)(:)( )',
+             bygroups(Comment.Preproc, Whitespace, Name.Variable, Punctuation, Whitespace)),
+
+        ],
+        'expression': [
+            # matches any kind of parenthesized expression
+            # the first opening paren is matched by the 'caller'
+            (r'\(', Punctuation, '#push'),
+            (r'\)', Punctuation, '#pop'),
+            (r'(never executed)', Name.Exception),
+            (r'[^)(]+', Comment),
+        ],
+        'object_name': [
+
+            # This is a cost or analyze measure
+            (r'(\(cost)(=?)', bygroups(Name.Class, Punctuation), 'instrumentation'),
+            (r'(\(actual)( )(=?)', bygroups(Name.Class, Whitespace, Punctuation), 'instrumentation'),
+
+            # if object_name is parenthesized, mark opening paren as
+            # punctuation, call 'expression', and exit state
+            (r'\(', Punctuation, 'expression'),
+            (r'(on)', Punctuation),
+            # matches possibly schema-qualified table and column names
+            (r'\w+(\.\w+)*( USING \S+| \w+ USING \S+)', Name.Variable),
+            (r'\"?\w+\"?(?:\.\"?\w+\"?)?', Name.Variable),
+            (r'\'\S*\'', Name.Variable),
+
+            # if we encounter a comma, another object is listed
+            (r',\n', Punctuation, 'object_name'),
+            (r',', Punctuation, 'object_name'),
+
+            # special case: "*SELECT*"
+            (r'"\*SELECT\*( \d+)?"(.\w+)?', Name.Variable),
+            (r'"\*VALUES\*(_\d+)?"(.\w+)?', Name.Variable),
+            (r'"ANY_subquery"', Name.Variable),
+
+            # Variable $1 ...
+            (r'\$\d+', Name.Variable),
+            # cast
+            (r'::\w+', Name.Variable),
+            (r' +', Whitespace),
+            (r'"', Punctuation),
+            (r'\[\.\.\.\]', Punctuation),
+            (r'\)', Punctuation, '#pop'),
+        ],
+        'predicate': [
+            # if predicate is parenthesized, mark paren as punctuation
+            (r'(\()([^\n]*)(\))', bygroups(Punctuation, Name.Variable, Punctuation), '#pop'),
+            # otherwise color until newline
+            (r'[^\n]*', Name.Variable, '#pop'),
+        ],
+        'instrumentation': [
+            (r'=|\.\.', Punctuation),
+            (r' +', Whitespace),
+            (r'(rows|width|time|loops)', Name.Class),
+            (r'\d+\.\d+', Number.Float),
+            (r'(\d+)', Number.Integer),
+            (r'\)', Punctuation, '#pop'),
+        ],
+        'conflict': [
+            (r'(Resolution: )(\w+)', bygroups(Comment.Preproc, Name.Variable)),
+            (r'(Arbiter \w+:)', Comment.Preproc, 'object_name'),
+            (r'(Filter: )', Comment.Preproc, 'predicate'),
+        ],
+        'setting': [
+            (r'([a-z_]*?)(\s*)(=)(\s*)(\'.*?\')', bygroups(Name.Attribute, Whitespace, Operator, Whitespace, String)),
+            (r'\, ', Punctuation),
+        ],
+        'init_plan': [
+            (r'\(', Punctuation),
+            (r'returns \$\d+(,\$\d+)?', Name.Variable),
+            (r'\)', Punctuation, '#pop'),
+        ],
+        'sort': [
+            (r':|kB', Punctuation),
+            (r'(quicksort|top-N|heapsort|Average|Memory|Peak)', Comment.Prepoc),
+            (r'(external|merge|Disk|sort)', Name.Exception),
+            (r'(\d+)', Number.Integer),
+            (r' +', Whitespace),
+        ],
+    }
+
+
+class SqlLexer(RegexLexer):
+    """
+    Lexer for Structured Query Language. Currently, this lexer does
+    not recognize any special syntax except ANSI SQL.
+    """
+
+    name = 'SQL'
+    aliases = ['sql']
+    filenames = ['*.sql']
+    mimetypes = ['text/x-sql']
+    url = 'https://en.wikipedia.org/wiki/SQL'
+    version_added = ''
+
+    flags = re.IGNORECASE
+    tokens = {
+        'root': [
+            (r'\s+', Whitespace),
+            (r'--.*\n?', Comment.Single),
+            (r'/\*', Comment.Multiline, 'multiline-comments'),
+            (words(_sql_builtins.KEYWORDS, suffix=r'\b'), Keyword),
+            (words(_sql_builtins.DATATYPES, suffix=r'\b'), Name.Builtin),
+            (r'[+*/<>=~!@#%^&|`?-]', Operator),
+            (r'[0-9]+', Number.Integer),
+            # TODO: Backslash escapes?
+            (r"'(''|[^'])*'", String.Single),
+            (r'"(""|[^"])*"', String.Symbol),  # not a real string literal in ANSI SQL
+            (r'[a-z_][\w$]*', Name),  # allow $s in strings for Oracle
+            (r'[;:()\[\],.]', Punctuation)
+        ],
+        'multiline-comments': [
+            (r'/\*', Comment.Multiline, 'multiline-comments'),
+            (r'\*/', Comment.Multiline, '#pop'),
+            (r'[^/*]+', Comment.Multiline),
+            (r'[/*]', Comment.Multiline)
+        ]
+    }
+
+    def analyse_text(self, text):
+        return
+
+
+class TransactSqlLexer(RegexLexer):
+    """
+    Transact-SQL (T-SQL) is Microsoft's and Sybase's proprietary extension to
+    SQL.
+
+    The list of keywords includes ODBC and keywords reserved for future use.
+    """
+
+    name = 'Transact-SQL'
+    aliases = ['tsql', 't-sql']
+    filenames = ['*.sql']
+    mimetypes = ['text/x-tsql']
+    url = 'https://www.tsql.info'
+    version_added = ''
+
+    flags = re.IGNORECASE
+
+    tokens = {
+        'root': [
+            (r'\s+', Whitespace),
+            (r'--.*[$|\n]?', Comment.Single),
+            (r'/\*', Comment.Multiline, 'multiline-comments'),
+            (words(_tsql_builtins.OPERATORS), Operator),
+            (words(_tsql_builtins.OPERATOR_WORDS, suffix=r'\b'), Operator.Word),
+            (words(_tsql_builtins.TYPES, suffix=r'\b'), Name.Class),
+            (words(_tsql_builtins.FUNCTIONS, suffix=r'\b'), Name.Function),
+            (r'(goto)(\s+)(\w+\b)', bygroups(Keyword, Whitespace, Name.Label)),
+            (words(_tsql_builtins.KEYWORDS, suffix=r'\b'), Keyword),
+            (r'(\[)([^]]+)(\])', bygroups(Operator, Name, Operator)),
+            (r'0x[0-9a-f]+', Number.Hex),
+            # Float variant 1, for example: 1., 1.e2, 1.2e3
+            (r'[0-9]+\.[0-9]*(e[+-]?[0-9]+)?', Number.Float),
+            # Float variant 2, for example: .1, .1e2
+            (r'\.[0-9]+(e[+-]?[0-9]+)?', Number.Float),
+            # Float variant 3, for example: 123e45
+            (r'[0-9]+e[+-]?[0-9]+', Number.Float),
+            (r'[0-9]+', Number.Integer),
+            (r"'(''|[^'])*'", String.Single),
+            (r'"(""|[^"])*"', String.Symbol),
+            (r'[;(),.]', Punctuation),
+            # Below we use \w even for the first "real" character because
+            # tokens starting with a digit have already been recognized
+            # as Number above.
+            (r'@@\w+', Name.Builtin),
+            (r'@\w+', Name.Variable),
+            (r'(\w+)(:)', bygroups(Name.Label, Punctuation)),
+            (r'#?#?\w+', Name),  # names for temp tables and anything else
+            (r'\?', Name.Variable.Magic),  # parameter for prepared statements
+        ],
+        'multiline-comments': [
+            (r'/\*', Comment.Multiline, 'multiline-comments'),
+            (r'\*/', Comment.Multiline, '#pop'),
+            (r'[^/*]+', Comment.Multiline),
+            (r'[/*]', Comment.Multiline)
+        ]
+    }
+
+    def analyse_text(text):
+        rating = 0
+        if tsql_declare_re.search(text):
+            # Found T-SQL variable declaration.
+            rating = 1.0
+        else:
+            name_between_backtick_count = len(
+                name_between_backtick_re.findall(text))
+            name_between_bracket_count = len(
+                name_between_bracket_re.findall(text))
+            # We need to check if there are any names using
+            # backticks or brackets, as otherwise both are 0
+            # and 0 >= 2 * 0, so we would always assume it's true
+            dialect_name_count = name_between_backtick_count + name_between_bracket_count
+            if dialect_name_count >= 1 and \
+               name_between_bracket_count >= 2 * name_between_backtick_count:
+                # Found at least twice as many [name] as `name`.
+                rating += 0.5
+            elif name_between_bracket_count > name_between_backtick_count:
+                rating += 0.2
+            elif name_between_bracket_count > 0:
+                rating += 0.1
+            if tsql_variable_re.search(text) is not None:
+                rating += 0.1
+            if tsql_go_re.search(text) is not None:
+                rating += 0.1
+        return rating
+
+
+class MySqlLexer(RegexLexer):
+    """The Oracle MySQL lexer.
+
+    This lexer does not attempt to maintain strict compatibility with
+    MariaDB syntax or keywords. Although MySQL and MariaDB's common code
+    history suggests there may be significant overlap between the two,
+    compatibility between the two is not a target for this lexer.
+    """
+
+    name = 'MySQL'
+    aliases = ['mysql']
+    mimetypes = ['text/x-mysql']
+    url = 'https://www.mysql.com'
+    version_added = ''
+
+    flags = re.IGNORECASE
+    tokens = {
+        'root': [
+            (r'\s+', Whitespace),
+
+            # Comments
+            (r'(?:#|--\s+).*', Comment.Single),
+            (r'/\*\+', Comment.Special, 'optimizer-hints'),
+            (r'/\*', Comment.Multiline, 'multiline-comment'),
+
+            # Hexadecimal literals
+            (r"x'([0-9a-f]{2})+'", Number.Hex),  # MySQL requires paired hex characters in this form.
+            (r'0x[0-9a-f]+', Number.Hex),
+
+            # Binary literals
+            (r"b'[01]+'", Number.Bin),
+            (r'0b[01]+', Number.Bin),
+
+            # Numeric literals
+            (r'[0-9]+\.[0-9]*(e[+-]?[0-9]+)?', Number.Float),  # Mandatory integer, optional fraction and exponent
+            (r'[0-9]*\.[0-9]+(e[+-]?[0-9]+)?', Number.Float),  # Mandatory fraction, optional integer and exponent
+            (r'[0-9]+e[+-]?[0-9]+', Number.Float),  # Exponents with integer significands are still floats
+            (r'[0-9]+(?=[^0-9a-z$_\u0080-\uffff])', Number.Integer),  # Integers that are not in a schema object name
+
+            # Date literals
+            (r"\{\s*d\s*(?P<quote>['\"])\s*\d{2}(\d{2})?.?\d{2}.?\d{2}\s*(?P=quote)\s*\}",
+             Literal.Date),
+
+            # Time literals
+            (r"\{\s*t\s*(?P<quote>['\"])\s*(?:\d+\s+)?\d{1,2}.?\d{1,2}.?\d{1,2}(\.\d*)?\s*(?P=quote)\s*\}",
+             Literal.Date),
+
+            # Timestamp literals
+            (
+                r"\{\s*ts\s*(?P<quote>['\"])\s*"
+                r"\d{2}(?:\d{2})?.?\d{2}.?\d{2}"  # Date part
+                r"\s+"  # Whitespace between date and time
+                r"\d{1,2}.?\d{1,2}.?\d{1,2}(\.\d*)?"  # Time part
+                r"\s*(?P=quote)\s*\}",
+                Literal.Date
+            ),
+
+            # String literals
+            (r"'", String.Single, 'single-quoted-string'),
+            (r'"', String.Double, 'double-quoted-string'),
+
+            # Variables
+            (r'@@(?:global\.|persist\.|persist_only\.|session\.)?[a-z_]+', Name.Variable),
+            (r'@[a-z0-9_$.]+', Name.Variable),
+            (r"@'", Name.Variable, 'single-quoted-variable'),
+            (r'@"', Name.Variable, 'double-quoted-variable'),
+            (r"@`", Name.Variable, 'backtick-quoted-variable'),
+            (r'\?', Name.Variable),  # For demonstrating prepared statements
+
+            # Operators
+            (r'[!%&*+/:<=>^|~-]+', Operator),
+
+            # Exceptions; these words tokenize differently in different contexts.
+            (r'\b(set)(?!\s*\()', Keyword),
+            (r'\b(character)(\s+)(set)\b', bygroups(Keyword, Whitespace, Keyword)),
+            # In all other known cases, "SET" is tokenized by MYSQL_DATATYPES.
+
+            (words(_mysql_builtins.MYSQL_CONSTANTS, prefix=r'\b', suffix=r'\b'),
+             Name.Constant),
+            (words(_mysql_builtins.MYSQL_DATATYPES, prefix=r'\b', suffix=r'\b'),
+             Keyword.Type),
+            (words(_mysql_builtins.MYSQL_KEYWORDS, prefix=r'\b', suffix=r'\b'),
+             Keyword),
+            (words(_mysql_builtins.MYSQL_FUNCTIONS, prefix=r'\b', suffix=r'\b(\s*)(\()'),
+             bygroups(Name.Function, Whitespace, Punctuation)),
+
+            # Schema object names
+            #
+            # Note: Although the first regex supports unquoted all-numeric
+            # identifiers, this will not be a problem in practice because
+            # numeric literals have already been handled above.
+            #
+            ('[0-9a-z$_\u0080-\uffff]+', Name),
+            (r'`', Name.Quoted, 'schema-object-name'),
+
+            # Punctuation
+            (r'[(),.;]', Punctuation),
+        ],
+
+        # Multiline comment substates
+        # ---------------------------
+
+        'optimizer-hints': [
+            (r'[^*a-z]+', Comment.Special),
+            (r'\*/', Comment.Special, '#pop'),
+            (words(_mysql_builtins.MYSQL_OPTIMIZER_HINTS, suffix=r'\b'),
+             Comment.Preproc),
+            ('[a-z]+', Comment.Special),
+            (r'\*', Comment.Special),
+        ],
+
+        'multiline-comment': [
+            (r'[^*]+', Comment.Multiline),
+            (r'\*/', Comment.Multiline, '#pop'),
+            (r'\*', Comment.Multiline),
+        ],
+
+        # String substates
+        # ----------------
+
+        'single-quoted-string': [
+            (r"[^'\\]+", String.Single),
+            (r"''", String.Escape),
+            (r"""\\[0'"bnrtZ\\%_]""", String.Escape),
+            (r"'", String.Single, '#pop'),
+        ],
+
+        'double-quoted-string': [
+            (r'[^"\\]+', String.Double),
+            (r'""', String.Escape),
+            (r"""\\[0'"bnrtZ\\%_]""", String.Escape),
+            (r'"', String.Double, '#pop'),
+        ],
+
+        # Variable substates
+        # ------------------
+
+        'single-quoted-variable': [
+            (r"[^']+", Name.Variable),
+            (r"''", Name.Variable),
+            (r"'", Name.Variable, '#pop'),
+        ],
+
+        'double-quoted-variable': [
+            (r'[^"]+', Name.Variable),
+            (r'""', Name.Variable),
+            (r'"', Name.Variable, '#pop'),
+        ],
+
+        'backtick-quoted-variable': [
+            (r'[^`]+', Name.Variable),
+            (r'``', Name.Variable),
+            (r'`', Name.Variable, '#pop'),
+        ],
+
+        # Schema object name substates
+        # ----------------------------
+        #
+        # "Name.Quoted" and "Name.Quoted.Escape" are non-standard but
+        # formatters will style them as "Name" by default but add
+        # additional styles based on the token name. This gives users
+        # flexibility to add custom styles as desired.
+        #
+        'schema-object-name': [
+            (r'[^`]+', Name.Quoted),
+            (r'``', Name.Quoted.Escape),
+            (r'`', Name.Quoted, '#pop'),
+        ],
+    }
+
+    def analyse_text(text):
+        rating = 0
+        name_between_backtick_count = len(
+            name_between_backtick_re.findall(text))
+        name_between_bracket_count = len(
+            name_between_bracket_re.findall(text))
+        # Same logic as above in the TSQL analysis
+        dialect_name_count = name_between_backtick_count + name_between_bracket_count
+        if dialect_name_count >= 1 and \
+           name_between_backtick_count >= 2 * name_between_bracket_count:
+            # Found at least twice as many `name` as [name].
+            rating += 0.5
+        elif name_between_backtick_count > name_between_bracket_count:
+            rating += 0.2
+        elif name_between_backtick_count > 0:
+            rating += 0.1
+        return rating
+
+
+class GoogleSqlLexer(RegexLexer):
+    """
+    GoogleSQL is Google's standard SQL dialect, formerly known as ZetaSQL.
+
+    The list of keywords includes reserved words for future use.
+    """
+
+    name = 'GoogleSQL'
+    aliases = ['googlesql', 'zetasql']
+    filenames = ['*.googlesql', '*.googlesql.sql']
+    mimetypes = ['text/x-google-sql', 'text/x-google-sql-aux']
+    url = 'https://cloud.google.com/bigquery/googlesql'
+    version_added = '2.19'
+
+    flags = re.IGNORECASE
+    tokens = {
+        'root': [
+            (r'\s+', Whitespace),
+
+            # Comments
+            (r'(?:#|--\s+).*', Comment.Single),
+            (r'/\*', Comment.Multiline, 'multiline-comment'),
+
+            # Hexadecimal literals
+            (r"x'([0-9a-f]{2})+'", Number.Hex),
+            (r'0x[0-9a-f]+', Number.Hex),
+
+            # Binary literals
+            (r"b'[01]+'", Number.Bin),
+            (r'0b[01]+', Number.Bin),
+
+            # Numeric literals
+            (r'[0-9]+\.[0-9]*(e[+-]?[0-9]+)?', Number.Float),  # Mandatory integer, optional fraction and exponent
+            (r'[0-9]*\.[0-9]+(e[+-]?[0-9]+)?', Number.Float),  # Mandatory fraction, optional integer and exponent
+            (r'[0-9]+e[+-]?[0-9]+', Number.Float),  # Exponents with integer significands are still floats
+            (r'[0-9]+(?=[^0-9a-z$_\u0080-\uffff])', Number.Integer),  # Integers that are not in a schema object name
+
+            # Date literals
+            (r"\{\s*d\s*(?P<quote>['\"])\s*\d{2}(\d{2})?.?\d{2}.?\d{2}\s*(?P=quote)\s*\}",
+             Literal.Date),
+
+            # Time literals
+            (r"\{\s*t\s*(?P<quote>['\"])\s*(?:\d+\s+)?\d{1,2}.?\d{1,2}.?\d{1,2}(\.\d*)?\s*(?P=quote)\s*\}",
+             Literal.Date),
+
+            # Timestamp literals
+            (
+                r"\{\s*ts\s*(?P<quote>['\"])\s*"
+                r"\d{2}(?:\d{2})?.?\d{2}.?\d{2}"  # Date part
+                r"\s+"  # Whitespace between date and time
+                r"\d{1,2}.?\d{1,2}.?\d{1,2}(\.\d*)?"  # Time part
+                r"\s*(?P=quote)\s*\}",
+                Literal.Date
+            ),
+
+            # String literals
+            (r"'", String.Single, 'single-quoted-string'),
+            (r'"', String.Double, 'double-quoted-string'),
+
+            # Variables
+            (r'@@(?:global\.|persist\.|persist_only\.|session\.)?[a-z_]+', Name.Variable),
+            (r'@[a-z0-9_$.]+', Name.Variable),
+            (r"@'", Name.Variable, 'single-quoted-variable'),
+            (r'@"', Name.Variable, 'double-quoted-variable'),
+            (r"@`", Name.Variable, 'backtick-quoted-variable'),
+            (r'\?', Name.Variable),  # For demonstrating prepared statements
+
+            # Exceptions; these words tokenize differently in different contexts.
+            (r'\b(set)(?!\s*\()', Keyword),
+            (r'\b(character)(\s+)(set)\b', bygroups(Keyword, Whitespace, Keyword)),
+
+            # Constants, types, keywords, functions, operators
+            (words(_googlesql_builtins.constants, prefix=r'\b', suffix=r'\b'), Name.Constant),
+            (words(_googlesql_builtins.types, prefix=r'\b', suffix=r'\b'), Keyword.Type),
+            (words(_googlesql_builtins.keywords, prefix=r'\b', suffix=r'\b'), Keyword),
+            (words(_googlesql_builtins.functionnames, prefix=r'\b', suffix=r'\b(\s*)(\()'),
+             bygroups(Name.Function, Whitespace, Punctuation)),
+            (words(_googlesql_builtins.operators, prefix=r'\b', suffix=r'\b'), Operator),
+
+            # Schema object names
+            #
+            # Note: Although the first regex supports unquoted all-numeric
+            # identifiers, this will not be a problem in practice because
+            # numeric literals have already been handled above.
+            #
+            ('[0-9a-z$_\u0080-\uffff]+', Name),
+            (r'`', Name.Quoted, 'schema-object-name'),
+
+            # Punctuation
+            (r'[(),.;]', Punctuation),
+        ],
+
+        # Multiline comment substates
+        # ---------------------------
+
+        'multiline-comment': [
+            (r'[^*]+', Comment.Multiline),
+            (r'\*/', Comment.Multiline, '#pop'),
+            (r'\*', Comment.Multiline),
+        ],
+
+        # String substates
+        # ----------------
+
+        'single-quoted-string': [
+            (r"[^'\\]+", String.Single),
+            (r"''", String.Escape),
+            (r"""\\[0'"bnrtZ\\%_]""", String.Escape),
+            (r"'", String.Single, '#pop'),
+        ],
+
+        'double-quoted-string': [
+            (r'[^"\\]+', String.Double),
+            (r'""', String.Escape),
+            (r"""\\[0'"bnrtZ\\%_]""", String.Escape),
+            (r'"', String.Double, '#pop'),
+        ],
+
+        # Variable substates
+        # ------------------
+
+        'single-quoted-variable': [
+            (r"[^']+", Name.Variable),
+            (r"''", Name.Variable),
+            (r"'", Name.Variable, '#pop'),
+        ],
+
+        'double-quoted-variable': [
+            (r'[^"]+', Name.Variable),
+            (r'""', Name.Variable),
+            (r'"', Name.Variable, '#pop'),
+        ],
+
+        'backtick-quoted-variable': [
+            (r'[^`]+', Name.Variable),
+            (r'``', Name.Variable),
+            (r'`', Name.Variable, '#pop'),
+        ],
+
+        # Schema object name substates
+        # ----------------------------
+        #
+        # "Name.Quoted" and "Name.Quoted.Escape" are non-standard but
+        # formatters will style them as "Name" by default but add
+        # additional styles based on the token name. This gives users
+        # flexibility to add custom styles as desired.
+        #
+        'schema-object-name': [
+            (r'[^`]+', Name.Quoted),
+            (r'``', Name.Quoted.Escape),
+            (r'`', Name.Quoted, '#pop'),
+        ],
+    }
+
+    def analyse_text(text):
+        tokens = collections.Counter(text.split())
+        return 0.001 * sum(count for t, count in tokens.items()
+                           if t in googlesql_identifiers)
+
+
+class SqliteConsoleLexer(Lexer):
+    """
+    Lexer for example sessions using sqlite3.
+    """
+
+    name = 'sqlite3con'
+    aliases = ['sqlite3']
+    filenames = ['*.sqlite3-console']
+    mimetypes = ['text/x-sqlite3-console']
+    url = 'https://www.sqlite.org'
+    version_added = '0.11'
+    _example = "sqlite3/sqlite3.sqlite3-console"
+
+    def get_tokens_unprocessed(self, data):
+        sql = SqlLexer(**self.options)
+
+        curcode = ''
+        insertions = []
+        for match in line_re.finditer(data):
+            line = match.group()
+            prompt_match = sqlite_prompt_re.match(line)
+            if prompt_match is not None:
+                insertions.append((len(curcode),
+                                   [(0, Generic.Prompt, line[:7])]))
+                insertions.append((len(curcode),
+                                   [(7, Whitespace, ' ')]))
+                curcode += line[8:]
+            else:
+                if curcode:
+                    yield from do_insertions(insertions,
+                                             sql.get_tokens_unprocessed(curcode))
+                    curcode = ''
+                    insertions = []
+                if line.startswith('SQL error: '):
+                    yield (match.start(), Generic.Traceback, line)
+                else:
+                    yield (match.start(), Generic.Output, line)
+        if curcode:
+            yield from do_insertions(insertions,
+                                     sql.get_tokens_unprocessed(curcode))
+
+
+class RqlLexer(RegexLexer):
+    """
+    Lexer for Relation Query Language.
+    """
+    name = 'RQL'
+    url = 'http://www.logilab.org/project/rql'
+    aliases = ['rql']
+    filenames = ['*.rql']
+    mimetypes = ['text/x-rql']
+    version_added = '2.0'
+
+    flags = re.IGNORECASE
+    tokens = {
+        'root': [
+            (r'\s+', Whitespace),
+            (r'(DELETE|SET|INSERT|UNION|DISTINCT|WITH|WHERE|BEING|OR'
+             r'|AND|NOT|GROUPBY|HAVING|ORDERBY|ASC|DESC|LIMIT|OFFSET'
+             r'|TODAY|NOW|TRUE|FALSE|NULL|EXISTS)\b', Keyword),
+            (r'[+*/<>=%-]', Operator),
+            (r'(Any|is|instance_of|CWEType|CWRelation)\b', Name.Builtin),
+            (r'[0-9]+', Number.Integer),
+            (r'[A-Z_]\w*\??', Name),
+            (r"'(''|[^'])*'", String.Single),
+            (r'"(""|[^"])*"', String.Single),
+            (r'[;:()\[\],.]', Punctuation)
+        ],
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/typoscript.py

@@ -0,0 +1,216 @@
+"""
+    pygments.lexers.typoscript
+    ~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexers for TypoScript
+
+    `TypoScriptLexer`
+        A TypoScript lexer.
+
+    `TypoScriptCssDataLexer`
+        Lexer that highlights markers, constants and registers within css.
+
+    `TypoScriptHtmlDataLexer`
+        Lexer that highlights markers, constants and registers within html tags.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import RegexLexer, include, bygroups, using
+from pygments.token import Text, Comment, Name, String, Number, \
+    Operator, Punctuation
+
+__all__ = ['TypoScriptLexer', 'TypoScriptCssDataLexer', 'TypoScriptHtmlDataLexer']
+
+
+class TypoScriptCssDataLexer(RegexLexer):
+    """
+    Lexer that highlights markers, constants and registers within css blocks.
+    """
+
+    name = 'TypoScriptCssData'
+    aliases = ['typoscriptcssdata']
+    url = 'http://docs.typo3.org/typo3cms/TyposcriptReference/'
+    version_added = '2.2'
+
+    tokens = {
+        'root': [
+            # marker: ###MARK###
+            (r'(.*)(###\w+###)(.*)', bygroups(String, Name.Constant, String)),
+            # constant: {$some.constant}
+            (r'(\{)(\$)((?:[\w\-]+\.)*)([\w\-]+)(\})',
+             bygroups(String.Symbol, Operator, Name.Constant,
+                      Name.Constant, String.Symbol)),  # constant
+            # constant: {register:somevalue}
+            (r'(.*)(\{)([\w\-]+)(\s*:\s*)([\w\-]+)(\})(.*)',
+             bygroups(String, String.Symbol, Name.Constant, Operator,
+                      Name.Constant, String.Symbol, String)),  # constant
+            # whitespace
+            (r'\s+', Text),
+            # comments
+            (r'/\*(?:(?!\*/).)*\*/', Comment),
+            (r'(?<!(#|\'|"))(?:#(?!(?:[a-fA-F0-9]{6}|[a-fA-F0-9]{3}))[^\n#]+|//[^\n]*)',
+             Comment),
+            # other
+            (r'[<>,:=.*%+|]', String),
+            (r'[\w"\-!/&;(){}]+', String),
+        ]
+    }
+
+
+class TypoScriptHtmlDataLexer(RegexLexer):
+    """
+    Lexer that highlights markers, constants and registers within html tags.
+    """
+
+    name = 'TypoScriptHtmlData'
+    aliases = ['typoscripthtmldata']
+    url = 'http://docs.typo3.org/typo3cms/TyposcriptReference/'
+    version_added = '2.2'
+
+    tokens = {
+        'root': [
+            # INCLUDE_TYPOSCRIPT
+            (r'(INCLUDE_TYPOSCRIPT)', Name.Class),
+            # Language label or extension resource FILE:... or LLL:... or EXT:...
+            (r'(EXT|FILE|LLL):[^}\n"]*', String),
+            # marker: ###MARK###
+            (r'(.*)(###\w+###)(.*)', bygroups(String, Name.Constant, String)),
+            # constant: {$some.constant}
+            (r'(\{)(\$)((?:[\w\-]+\.)*)([\w\-]+)(\})',
+             bygroups(String.Symbol, Operator, Name.Constant,
+                      Name.Constant, String.Symbol)),  # constant
+            # constant: {register:somevalue}
+            (r'(.*)(\{)([\w\-]+)(\s*:\s*)([\w\-]+)(\})(.*)',
+             bygroups(String, String.Symbol, Name.Constant, Operator,
+                      Name.Constant, String.Symbol, String)),  # constant
+            # whitespace
+            (r'\s+', Text),
+            # other
+            (r'[<>,:=.*%+|]', String),
+            (r'[\w"\-!/&;(){}#]+', String),
+        ]
+    }
+
+
+class TypoScriptLexer(RegexLexer):
+    """
+    Lexer for TypoScript code.
+    """
+
+    name = 'TypoScript'
+    url = 'http://docs.typo3.org/typo3cms/TyposcriptReference/'
+    aliases = ['typoscript']
+    filenames = ['*.typoscript']
+    mimetypes = ['text/x-typoscript']
+    version_added = '2.2'
+
+    flags = re.DOTALL | re.MULTILINE
+
+    tokens = {
+        'root': [
+            include('comment'),
+            include('constant'),
+            include('html'),
+            include('label'),
+            include('whitespace'),
+            include('keywords'),
+            include('punctuation'),
+            include('operator'),
+            include('structure'),
+            include('literal'),
+            include('other'),
+        ],
+        'keywords': [
+            # Conditions
+            (r'(?i)(\[)(browser|compatVersion|dayofmonth|dayofweek|dayofyear|'
+             r'device|ELSE|END|GLOBAL|globalString|globalVar|hostname|hour|IP|'
+             r'language|loginUser|loginuser|minute|month|page|PIDinRootline|'
+             r'PIDupinRootline|system|treeLevel|useragent|userFunc|usergroup|'
+             r'version)([^\]]*)(\])',
+             bygroups(String.Symbol, Name.Constant, Text, String.Symbol)),
+            # Functions
+            (r'(?=[\w\-])(HTMLparser|HTMLparser_tags|addParams|cache|encapsLines|'
+             r'filelink|if|imageLinkWrap|imgResource|makelinks|numRows|numberFormat|'
+             r'parseFunc|replacement|round|select|split|stdWrap|strPad|tableStyle|'
+             r'tags|textStyle|typolink)(?![\w\-])', Name.Function),
+            # Toplevel objects and _*
+            (r'(?:(=?\s*<?\s+|^\s*))(cObj|field|config|content|constants|FEData|'
+             r'file|frameset|includeLibs|lib|page|plugin|register|resources|sitemap|'
+             r'sitetitle|styles|temp|tt_[^:.\s]*|types|xmlnews|INCLUDE_TYPOSCRIPT|'
+             r'_CSS_DEFAULT_STYLE|_DEFAULT_PI_VARS|_LOCAL_LANG)(?![\w\-])',
+             bygroups(Operator, Name.Builtin)),
+            # Content objects
+            (r'(?=[\w\-])(CASE|CLEARGIF|COA|COA_INT|COBJ_ARRAY|COLUMNS|CONTENT|'
+             r'CTABLE|EDITPANEL|FILE|FILES|FLUIDTEMPLATE|FORM|HMENU|HRULER|HTML|'
+             r'IMAGE|IMGTEXT|IMG_RESOURCE|LOAD_REGISTER|MEDIA|MULTIMEDIA|OTABLE|'
+             r'PAGE|QTOBJECT|RECORDS|RESTORE_REGISTER|SEARCHRESULT|SVG|SWFOBJECT|'
+             r'TEMPLATE|TEXT|USER|USER_INT)(?![\w\-])', Name.Class),
+            # Menu states
+            (r'(?=[\w\-])(ACTIFSUBRO|ACTIFSUB|ACTRO|ACT|CURIFSUBRO|CURIFSUB|CURRO|'
+             r'CUR|IFSUBRO|IFSUB|NO|SPC|USERDEF1RO|USERDEF1|USERDEF2RO|USERDEF2|'
+             r'USRRO|USR)', Name.Class),
+            # Menu objects
+            (r'(?=[\w\-])(GMENU_FOLDOUT|GMENU_LAYERS|GMENU|IMGMENUITEM|IMGMENU|'
+             r'JSMENUITEM|JSMENU|TMENUITEM|TMENU_LAYERS|TMENU)', Name.Class),
+            # PHP objects
+            (r'(?=[\w\-])(PHP_SCRIPT(_EXT|_INT)?)', Name.Class),
+            (r'(?=[\w\-])(userFunc)(?![\w\-])', Name.Function),
+        ],
+        'whitespace': [
+            (r'\s+', Text),
+        ],
+        'html': [
+            (r'<\S[^\n>]*>', using(TypoScriptHtmlDataLexer)),
+            (r'&[^;\n]*;', String),
+            (r'(?s)(_CSS_DEFAULT_STYLE)(\s*)(\()(.*(?=\n\)))',
+             bygroups(Name.Class, Text, String.Symbol, using(TypoScriptCssDataLexer))),
+        ],
+        'literal': [
+            (r'0x[0-9A-Fa-f]+t?', Number.Hex),
+            # (r'[0-9]*\.[0-9]+([eE][0-9]+)?[fd]?\s*(?:[^=])', Number.Float),
+            (r'[0-9]+', Number.Integer),
+            (r'(###\w+###)', Name.Constant),
+        ],
+        'label': [
+            # Language label or extension resource FILE:... or LLL:... or EXT:...
+            (r'(EXT|FILE|LLL):[^}\n"]*', String),
+            # Path to a resource
+            (r'(?![^\w\-])([\w\-]+(?:/[\w\-]+)+/?)(\S*\n)',
+             bygroups(String, String)),
+        ],
+        'punctuation': [
+            (r'[,.]', Punctuation),
+        ],
+        'operator': [
+            (r'[<>,:=.*%+|]', Operator),
+        ],
+        'structure': [
+            # Brackets and braces
+            (r'[{}()\[\]\\]', String.Symbol),
+        ],
+        'constant': [
+            # Constant: {$some.constant}
+            (r'(\{)(\$)((?:[\w\-]+\.)*)([\w\-]+)(\})',
+                bygroups(String.Symbol, Operator, Name.Constant,
+                         Name.Constant, String.Symbol)),  # constant
+            # Constant: {register:somevalue}
+            (r'(\{)([\w\-]+)(\s*:\s*)([\w\-]+)(\})',
+                bygroups(String.Symbol, Name.Constant, Operator,
+                         Name.Constant, String.Symbol)),  # constant
+            # Hex color: #ff0077
+            (r'(#[a-fA-F0-9]{6}\b|#[a-fA-F0-9]{3}\b)', String.Char)
+        ],
+        'comment': [
+            (r'(?<!(#|\'|"))(?:#(?!(?:[a-fA-F0-9]{6}|[a-fA-F0-9]{3}))[^\n#]+|//[^\n]*)',
+             Comment),
+            (r'/\*(?:(?!\*/).)*\*/', Comment),
+            (r'(\s*#\s*\n)', Comment),
+        ],
+        'other': [
+            (r'[\w"\-!/&;]+', Text),
+        ],
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/vyper.py

@@ -0,0 +1,140 @@
+"""
+    pygments.lexers.vyper
+    ~~~~~~~~~~~~~~~~~~~~~
+
+    Lexer for the Vyper Smart Contract language.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import RegexLexer, bygroups, words
+from pygments.token import (Comment, String, Name, Keyword, Number,
+                            Operator, Punctuation, Text, Whitespace)
+
+__all__ = ['VyperLexer']
+
+
+class VyperLexer(RegexLexer):
+    """For the Vyper smart contract language.
+    """
+    name = 'Vyper'
+    aliases = ['vyper']
+    filenames = ['*.vy']
+    url = "https://vyper.readthedocs.io"
+    version_added = '2.17'
+
+    tokens = {
+        'root': [
+            # Whitespace
+            (r'\s+', Whitespace),
+
+            # Line continuations
+            (r'(\\)(\n|\r\n|\r)', bygroups(Text, Whitespace)),
+
+            # Comments - inline and multiline
+            (r'#.*$', Comment.Single),
+            (r'\"\"\"', Comment.Multiline, 'multiline-comment'),
+
+            # Strings - single and double
+            (r"'", String.Single, 'single-string'),
+            (r'"', String.Double, 'double-string'),
+
+            # Functions (working)
+            (r'(def)(\s+)([a-zA-Z_][a-zA-Z0-9_]*)',
+             bygroups(Keyword, Whitespace, Name.Function)),
+
+            # Event and Struct
+            (r'(event|struct|interface|log)(\s+)([a-zA-Z_][a-zA-Z0-9_]*)',
+             bygroups(Keyword, Whitespace, Name.Class)),
+
+            # Imports
+            (r'(from)(\s+)(vyper\.\w+)(\s+)(import)(\s+)(\w+)',
+             bygroups(Keyword, Whitespace, Name.Namespace, Whitespace,
+                      Keyword, Whitespace, Name.Class)),
+
+            # Numeric Literals
+            (r'\b0x[0-9a-fA-F]+\b', Number.Hex),
+            (r'\b(\d{1,3}(?:_\d{3})*|\d+)\b', Number.Integer),
+            (r'\b\d+\.\d*\b', Number.Float),
+
+            # Keywords
+            (words(('def', 'event', 'pass', 'return', 'for', 'while', 'if', 'elif',
+                    'else', 'assert', 'raise', 'import', 'in', 'struct', 'implements',
+                    'interface', 'from', 'indexed', 'log', 'extcall', 'staticcall'),
+                   prefix=r'\b', suffix=r'\b'), Keyword),
+
+            # Visibility and State Mutability
+            (words(('public', 'private', 'view', 'pure', 'constant',
+                    'immutable', 'nonpayable'), prefix=r'\b', suffix=r'\b'),
+             Keyword.Declaration),
+
+            # Built-in Functions
+            (words(('bitwise_and', 'bitwise_not', 'bitwise_or', 'bitwise_xor', 'shift',
+                    'create_minimal_proxy_to', 'create_copy_of', 'create_from_blueprint',
+                    'ecadd', 'ecmul', 'ecrecover', 'keccak256', 'sha256', 'concat', 'convert',
+                    'uint2str', 'extract32', 'slice', 'abs', 'ceil', 'floor', 'max', 'max_value',
+                    'min', 'min_value', 'pow_mod256', 'sqrt', 'isqrt', 'uint256_addmod',
+                    'uint256_mulmod', 'unsafe_add', 'unsafe_sub', 'unsafe_mul', 'unsafe_div',
+                    'as_wei_value', 'blockhash', 'empty', 'len', 'method_id', '_abi_encode',
+                    '_abi_decode', 'print', 'range'), prefix=r'\b', suffix=r'\b'),
+             Name.Builtin),
+
+            # Built-in Variables and Attributes
+            (words(('msg.sender', 'msg.value', 'block.timestamp', 'block.number', 'msg.gas'),
+                   prefix=r'\b', suffix=r'\b'),
+             Name.Builtin.Pseudo),
+
+            (words(('uint', 'uint8', 'uint16', 'uint32', 'uint64', 'uint128', 'uint256',
+                    'int', 'int8', 'int16', 'int32', 'int64', 'int128', 'int256', 'bool',
+                    'decimal', 'bytes', 'bytes1', 'bytes2', 'bytes3', 'bytes4', 'bytes5',
+                    'bytes6', 'bytes7', 'bytes8', 'bytes9', 'bytes10', 'bytes11',
+                    'bytes12', 'bytes13', 'bytes14', 'bytes15', 'bytes16', 'bytes17',
+                    'bytes18', 'bytes19', 'bytes20', 'bytes21', 'bytes22', 'bytes23',
+                    'bytes24', 'bytes25', 'bytes26', 'bytes27', 'bytes28', 'bytes29',
+                    'bytes30', 'bytes31', 'bytes32', 'string', 'String', 'address',
+                    'enum', 'struct'), prefix=r'\b', suffix=r'\b'),
+             Keyword.Type),
+
+            # indexed keywords
+            (r'\b(indexed)\b(\s*)(\()(\s*)(\w+)(\s*)(\))',
+             bygroups(Keyword, Whitespace, Punctuation, Whitespace,
+                      Keyword.Type, Punctuation)),
+
+            # Operators and Punctuation
+            (r'(\+|\-|\*|\/|<=?|>=?|==|!=|=|\||&|%)', Operator),
+            (r'[.,:;()\[\]{}]', Punctuation),
+
+            # Other variable names and types
+            (r'@[\w.]+', Name.Decorator),
+            (r'__\w+__', Name.Magic),  # Matches double underscores followed by word characters
+            (r'EMPTY_BYTES32', Name.Constant),
+            (r'\bERC20\b', Name.Class),
+            (r'\bself\b', Name.Attribute),
+
+            (r'Bytes\[\d+\]', Keyword.Type),
+
+            # Generic names and variables
+            (r'\b[a-zA-Z_]\w*\b:', Name.Variable),
+            (r'\b[a-zA-Z_]\w*\b', Name),
+
+        ],
+
+        'multiline-comment': [
+            (r'\"\"\"', Comment.Multiline, '#pop'),
+            (r'[^"]+', Comment.Multiline),
+            (r'\"', Comment.Multiline)
+        ],
+
+        'single-string': [
+            (r"[^\\']+", String.Single),
+            (r"'", String.Single, '#pop'),
+            (r'\\.', String.Escape),
+        ],
+
+        'double-string': [
+            (r'[^\\"]+', String.Double),
+            (r'"', String.Double, '#pop'),
+            (r'\\.', String.Escape),
+        ]
+    }

LTA_openwebtext_dualt/runs_transfer/lta_owt_distilbert_len1024_init_lm1b1m_posemb_repeat_fully_c1024_adamw_gbs512_4gpu_20k_20260514_120045/args.json

@@ -0,0 +1,158 @@
+{
+  "data_path": "/e2e-data/evad-tech-vla/wanghan58/data/small_benchmarks/langflow_2604_11748/openwebtext",
+  "text_column": "text",
+  "txt_record_mode": "auto",
+  "detokenizer": "auto",
+  "openwebtext_split": "train_minus_100k",
+  "tokenizer_path": "/e2e-data/evad-tech-vla/wanghan58/workspace/imagenet_handoff_20260327/nlp_dts_light/assets/distilbert-base-uncased/tokenizer.json",
+  "save_dir": "runs_transfer/lta_owt_distilbert_len1024_init_lm1b1m_posemb_repeat_fully_c1024_adamw_gbs512_4gpu_20k_20260514_120045",
+  "max_records": 0,
+  "elf_conditional_hf": false,
+  "eval_data_path": "",
+  "dataset_cache_dir": "",
+  "max_input_len": 64,
+  "conditional_pad_token": "eos",
+  "label_drop_prob": 0.0,
+  "streaming": false,
+  "record_pad_truncate": false,
+  "record_add_eos": false,
+  "record_add_special_tokens": false,
+  "record_pad_token": "pad",
+  "record_shuffle_buffer": 10000,
+  "wrap": true,
+  "wrap_mode": "stream",
+  "wrap_record_buffer_size": 200,
+  "owt_cached_chunks": false,
+  "owt_chunk_cache_dir": "",
+  "owt_chunk_cache_rebuild": false,
+  "owt_chunk_cache_write_batch": 4096,
+  "owt_exact_repeat_per_chunk": 0,
+  "online_chunk_shuffle": false,
+  "online_chunk_shuffle_buffer": 10000,
+  "max_len": 1024,
+  "stride": 0,
+  "batch_size": 16,
+  "num_workers": 4,
+  "dataloader_prefetch_factor": 4,
+  "blocking_data_transfer": false,
+  "global_batch_size": 512,
+  "grad_accum": 8,
+  "total_steps": 20000,
+  "lr": 0.0003,
+  "weight_decay": 0.0,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_eps": 1e-08,
+  "optimizer": "adamw",
+  "muon_momentum": 0.95,
+  "muon_ns_steps": 5,
+  "muon_update_scale": 1.0,
+  "ema_decay": 0.0,
+  "ema_start_step": 0,
+  "warmup_steps": 2500,
+  "lr_schedule": "constant_warmup",
+  "min_lr": 6e-05,
+  "adamw_param_groups": "nanogpt",
+  "grad_clip": 1.0,
+  "seed": 42,
+  "d_model": 768,
+  "cond_dim": 128,
+  "n_layers": 12,
+  "n_heads": 12,
+  "dim_ff": 3072,
+  "dropout": 0.1,
+  "vocab_size_override": 0,
+  "model_type": "ddit",
+  "state_format": "prob",
+  "bridge": "dirichlet",
+  "target_loss": "hard_ce",
+  "meanflow_weight": 0.0,
+  "loss_t_weight_mode": "none",
+  "loss_t_min_weight": 0.0,
+  "loss_t_drop_below": 0.2,
+  "prior_center_loss_beta": 0.0,
+  "prior_center_state": "uniform",
+  "rollout_train_prob": 0.0,
+  "rollout_train_steps": 1,
+  "rollout_train_infer_steps": 64,
+  "rollout_train_temp": 1.45,
+  "rollout_train_max_gamma": 1.0,
+  "rollout_train_corrupt_only": true,
+  "rollout_train_samplewise": false,
+  "rollout_train_compute_always": false,
+  "rollout_train_debug_return_base": false,
+  "target_prob": 1.0,
+  "min_t": 0.0,
+  "max_t": 1.0,
+  "dual_t": true,
+  "corrupt_t_mode": "same",
+  "corrupt_t_value": 0.0,
+  "corrupt_min_t": null,
+  "corrupt_max_t": null,
+  "prefix_block_prob": 0.0,
+  "prefix_block_len": 128,
+  "min_mask_ratio": 0.1,
+  "max_mask_ratio": 1.0,
+  "mask_ratio_floor_schedule": "none",
+  "mask_mixture_original_prob": 0.0,
+  "mask_mixture_lowk_prob": 0.0,
+  "mask_mixture_lowcorrupt_prob": 0.0,
+  "mask_mixture_block_prob": 0.0,
+  "mask_mixture_all_prob": 0.0,
+  "mask_mixture_lowk_clean_tokens": "1,2,4,8,16,32,64",
+  "mask_mixture_lowcorrupt_tokens": "1,2,4,8,16,32,64",
+  "mask_mixture_block_tokens": "64,128",
+  "clean_state_mode": "onehot",
+  "wrong_token_replace_prob": "1.0",
+  "wrong_token_schedule": "linear_t",
+  "wrong_token_exp_k": 1.0,
+  "dirichlet_concentration_min": 1.0,
+  "dirichlet_concentration_max": 1024.0,
+  "dirichlet_endpoint_mode": "categorical_dual_t",
+  "dirichlet_semantic_t_mode": "same",
+  "dirichlet_semantic_t_value": 0.0,
+  "dirichlet_semantic_t_curve": "linear",
+  "dirichlet_semantic_t_power": 1.0,
+  "endpoint_sequence_random_prob_alpha": 0.0,
+  "categorical_wrong_from_full_vocab": true,
+  "categorical_wrong_from_batch_valid_tokens": false,
+  "simplex_bridge_sampler": "dirichlet",
+  "logistic_normal_sigma_min": 0.18,
+  "logistic_normal_sigma_max": 2.2,
+  "logistic_normal_tau_min": 0.65,
+  "logistic_normal_tau_max": 1.15,
+  "dirichlet_scale": 128.0,
+  "dirichlet_floor": 0.001,
+  "eps": 1e-08,
+  "log_every": 50,
+  "eval_every": 0,
+  "save_every": 1000,
+  "latest_every": 500,
+  "resume_path": "",
+  "init_model_path": "runs/lta_lm1b_dirichlet_categorical_fullvocab_c1024_fullycoupled_flmpack_onehot_hardce_ddit_small_len128_gbs512_8gpu_1m_nw0/step_1000000.pt",
+  "init_pos_embed_mode": "repeat",
+  "infer_steps": 128,
+  "decode_damping": 1.0,
+  "max_gamma": 1.0,
+  "decode_solver": "flowmap",
+  "noise_init": "logistic_normal",
+  "bridge_noise_init": "logistic_normal",
+  "noise_sigma": -1.0,
+  "demo_mask_ratios": "0.1,0.5,1.0",
+  "demo_fill_t": 0.0,
+  "bf16": true,
+  "allow_tf32": true,
+  "activation_checkpointing": false,
+  "activation_checkpoint_interval": 1,
+  "activation_checkpoint_scope": "block",
+  "ddp_static_graph": false,
+  "ddp_gradient_as_bucket_view": true,
+  "full_train_stats": false,
+  "log_train_stats_each_step": true,
+  "log_t_bin_stats": true,
+  "log_t_bin_edges": "0,0.2,0.4,0.6,0.8,1.0",
+  "torch_compile": false,
+  "compile_mode": "max-autotune",
+  "resolved_detokenizer": null,
+  "effective_vocab_size": 30522
+}