Intermediate changes

1 files changed, 363 insertions, 65 deletions

diff --git a/contrib/python/Pygments/py3/pygments/lexers/lisp.py b/contrib/python/Pygments/py3/pygments/lexers/lisp.py
index 966b6063ab..e6cc5875fa 100644
--- a/contrib/python/Pygments/py3/pygments/lexers/lisp.py
+++ b/contrib/python/Pygments/py3/pygments/lexers/lisp.py
@@ -4,7 +4,7 @@
 
     Lexers for Lispy languages.
 
-    :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -20,7 +20,7 @@ from pygments.lexers._scheme_builtins import scheme_keywords, scheme_builtins
 
 __all__ = ['SchemeLexer', 'CommonLispLexer', 'HyLexer', 'RacketLexer',
            'NewLispLexer', 'EmacsLispLexer', 'ShenLexer', 'CPSALexer',
-           'XtlangLexer', 'FennelLexer']
+           'XtlangLexer', 'FennelLexer', 'JanetLexer']
 
 
 class SchemeLexer(RegexLexer):
@@ -31,14 +31,13 @@ class SchemeLexer(RegexLexer):
     at http://paste.lisp.org/ to cover as much syntax as possible.
 
     It supports the full Scheme syntax as defined in R5RS.
-
-    .. versionadded:: 0.6
     """
     name = 'Scheme'
     url = 'http://www.scheme-reports.org/'
     aliases = ['scheme', 'scm']
     filenames = ['*.scm', '*.ss']
     mimetypes = ['text/x-scheme', 'application/x-scheme']
+    version_added = '0.6'
 
     flags = re.DOTALL | re.MULTILINE
 
@@ -296,14 +295,13 @@ class SchemeLexer(RegexLexer):
 class CommonLispLexer(RegexLexer):
     """
     A Common Lisp lexer.
-
-    .. versionadded:: 0.9
     """
     name = 'Common Lisp'
     url = 'https://lisp-lang.org/'
     aliases = ['common-lisp', 'cl', 'lisp']
     filenames = ['*.cl', '*.lisp']
     mimetypes = ['text/x-common-lisp']
+    version_added = '0.9'
 
     flags = re.IGNORECASE | re.MULTILINE
 
@@ -316,7 +314,7 @@ class CommonLispLexer(RegexLexer):
 
     # symbol token, reverse-engineered from hyperspec
     # Take a deep breath...
-    symbol = r'(\|[^|]+\||(?:%s)(?:%s)*)' % (nonmacro, constituent)
+    symbol = rf'(\|[^|]+\||(?:{nonmacro})(?:{constituent})*)'
 
     def __init__(self, **options):
         from pygments.lexers._cl_builtins import BUILTIN_FUNCTIONS, \
@@ -485,14 +483,13 @@ class CommonLispLexer(RegexLexer):
 class HyLexer(RegexLexer):
     """
     Lexer for Hy source code.
-
-    .. versionadded:: 2.0
     """
     name = 'Hy'
     url = 'http://hylang.org/'
-    aliases = ['hylang']
+    aliases = ['hylang', 'hy']
     filenames = ['*.hy']
     mimetypes = ['text/x-hy', 'application/x-hy']
+    version_added = '2.0'
 
     special_forms = (
         'cond', 'for', '->', '->>', 'car',
@@ -522,7 +519,7 @@ class HyLexer(RegexLexer):
     # valid names for identifiers
     # well, names can only not consist fully of numbers
     # but this should be good enough for now
-    valid_name = r'(?!#)[\w!$%*+<=>?/.#:-]+'
+    valid_name = r"[^ \t\n\r\f\v()[\]{};\"'`~]+"
 
     def _multi_escape(entries):
         return words(entries, suffix=' ')
@@ -534,8 +531,7 @@ class HyLexer(RegexLexer):
             (r';.*$', Comment.Single),
 
             # whitespaces - usually not relevant
-            (r',+', Text),
-            (r'\s+', Whitespace),
+            (r'[ \t\n\r\f\v]+', Whitespace),
 
             # numbers
             (r'-?\d+\.\d+', Number.Float),
@@ -601,8 +597,6 @@ class RacketLexer(RegexLexer):
     """
     Lexer for Racket source code (formerly
     known as PLT Scheme).
-
-    .. versionadded:: 1.6
     """
 
     name = 'Racket'
@@ -610,6 +604,7 @@ class RacketLexer(RegexLexer):
     aliases = ['racket', 'rkt']
     filenames = ['*.rkt', '*.rktd', '*.rktl']
     mimetypes = ['text/x-racket', 'application/x-racket']
+    version_added = '1.6'
 
     # Generated by example.rkt
     _keywords = (
@@ -1391,19 +1386,17 @@ class RacketLexer(RegexLexer):
     _opening_parenthesis = r'[([{]'
     _closing_parenthesis = r'[)\]}]'
     _delimiters = r'()[\]{}",\'`;\s'
-    _symbol = r'(?:\|[^|]*\||\\[\w\W]|[^|\\%s]+)+' % _delimiters
+    _symbol = rf'(?:\|[^|]*\||\\[\w\W]|[^|\\{_delimiters}]+)+'
     _exact_decimal_prefix = r'(?:#e)?(?:#d)?(?:#e)?'
     _exponent = r'(?:[defls][-+]?\d+)'
     _inexact_simple_no_hashes = r'(?:\d+(?:/\d+|\.\d*)?|\.\d+)'
-    _inexact_simple = (r'(?:%s|(?:\d+#+(?:\.#*|/\d+#*)?|\.\d+#+|'
-                       r'\d+(?:\.\d*#+|/\d+#+)))' % _inexact_simple_no_hashes)
-    _inexact_normal_no_hashes = r'(?:%s%s?)' % (_inexact_simple_no_hashes,
-                                                _exponent)
-    _inexact_normal = r'(?:%s%s?)' % (_inexact_simple, _exponent)
+    _inexact_simple = (rf'(?:{_inexact_simple_no_hashes}|(?:\d+#+(?:\.#*|/\d+#*)?|\.\d+#+|'
+                       r'\d+(?:\.\d*#+|/\d+#+)))')
+    _inexact_normal_no_hashes = rf'(?:{_inexact_simple_no_hashes}{_exponent}?)'
+    _inexact_normal = rf'(?:{_inexact_simple}{_exponent}?)'
     _inexact_special = r'(?:(?:inf|nan)\.[0f])'
-    _inexact_real = r'(?:[-+]?%s|[-+]%s)' % (_inexact_normal,
-                                             _inexact_special)
-    _inexact_unsigned = r'(?:%s|%s)' % (_inexact_normal, _inexact_special)
+    _inexact_real = rf'(?:[-+]?{_inexact_normal}|[-+]{_inexact_special})'
+    _inexact_unsigned = rf'(?:{_inexact_normal}|{_inexact_special})'
 
     tokens = {
         'root': [
@@ -1423,36 +1416,29 @@ class RacketLexer(RegexLexer):
             # onto Pygments token types; some judgment calls here.
 
             # #d or no prefix
-            (r'(?i)%s[-+]?\d+(?=[%s])' % (_exact_decimal_prefix, _delimiters),
+            (rf'(?i){_exact_decimal_prefix}[-+]?\d+(?=[{_delimiters}])',
              Number.Integer, '#pop'),
-            (r'(?i)%s[-+]?(\d+(\.\d*)?|\.\d+)([deflst][-+]?\d+)?(?=[%s])' %
-             (_exact_decimal_prefix, _delimiters), Number.Float, '#pop'),
-            (r'(?i)%s[-+]?(%s([-+]%s?i)?|[-+]%s?i)(?=[%s])' %
-             (_exact_decimal_prefix, _inexact_normal_no_hashes,
-              _inexact_normal_no_hashes, _inexact_normal_no_hashes,
-              _delimiters), Number, '#pop'),
+            (rf'(?i){_exact_decimal_prefix}[-+]?(\d+(\.\d*)?|\.\d+)([deflst][-+]?\d+)?(?=[{_delimiters}])', Number.Float, '#pop'),
+            (rf'(?i){_exact_decimal_prefix}[-+]?({_inexact_normal_no_hashes}([-+]{_inexact_normal_no_hashes}?i)?|[-+]{_inexact_normal_no_hashes}?i)(?=[{_delimiters}])', Number, '#pop'),
 
             # Inexact without explicit #i
-            (r'(?i)(#d)?(%s([-+]%s?i)?|[-+]%s?i|%s@%s)(?=[%s])' %
-             (_inexact_real, _inexact_unsigned, _inexact_unsigned,
-              _inexact_real, _inexact_real, _delimiters), Number.Float,
+            (rf'(?i)(#d)?({_inexact_real}([-+]{_inexact_unsigned}?i)?|[-+]{_inexact_unsigned}?i|{_inexact_real}@{_inexact_real})(?=[{_delimiters}])', Number.Float,
              '#pop'),
 
             # The remaining extflonums
-            (r'(?i)(([-+]?%st[-+]?\d+)|[-+](inf|nan)\.t)(?=[%s])' %
-             (_inexact_simple, _delimiters), Number.Float, '#pop'),
+            (rf'(?i)(([-+]?{_inexact_simple}t[-+]?\d+)|[-+](inf|nan)\.t)(?=[{_delimiters}])', Number.Float, '#pop'),
 
             # #b
-            (r'(?iu)(#[ei])?#b%s' % _symbol, Number.Bin, '#pop'),
+            (rf'(?iu)(#[ei])?#b{_symbol}', Number.Bin, '#pop'),
 
             # #o
-            (r'(?iu)(#[ei])?#o%s' % _symbol, Number.Oct, '#pop'),
+            (rf'(?iu)(#[ei])?#o{_symbol}', Number.Oct, '#pop'),
 
             # #x
-            (r'(?iu)(#[ei])?#x%s' % _symbol, Number.Hex, '#pop'),
+            (rf'(?iu)(#[ei])?#x{_symbol}', Number.Hex, '#pop'),
 
             # #i is always inexact, i.e. float
-            (r'(?iu)(#d)?#i%s' % _symbol, Number.Float, '#pop'),
+            (rf'(?iu)(#d)?#i{_symbol}', Number.Float, '#pop'),
 
             # Strings and characters
             (r'#?"', String.Double, ('#pop', 'string')),
@@ -1465,7 +1451,7 @@ class RacketLexer(RegexLexer):
             (r'#(true|false|[tTfF])', Name.Constant, '#pop'),
 
             # Keyword argument names (e.g. #:keyword)
-            (r'#:%s' % _symbol, Keyword.Declaration, '#pop'),
+            (rf'#:{_symbol}', Keyword.Declaration, '#pop'),
 
             # Reader extensions
             (r'(#lang |#!)(\S+)',
@@ -1473,8 +1459,8 @@ class RacketLexer(RegexLexer):
             (r'#reader', Keyword.Namespace, 'quoted-datum'),
 
             # Other syntax
-            (r"(?i)\.(?=[%s])|#c[is]|#['`]|#,@?" % _delimiters, Operator),
-            (r"'|#[s&]|#hash(eqv?)?|#\d*(?=%s)" % _opening_parenthesis,
+            (rf"(?i)\.(?=[{_delimiters}])|#c[is]|#['`]|#,@?", Operator),
+            (rf"'|#[s&]|#hash(eqv?)?|#\d*(?={_opening_parenthesis})",
              Operator, ('#pop', 'quoted-datum'))
         ],
         'datum*': [
@@ -1488,15 +1474,15 @@ class RacketLexer(RegexLexer):
         ],
         'unquoted-datum': [
             include('datum'),
-            (r'quote(?=[%s])' % _delimiters, Keyword,
+            (rf'quote(?=[{_delimiters}])', Keyword,
              ('#pop', 'quoted-datum')),
             (r'`', Operator, ('#pop', 'quasiquoted-datum')),
-            (r'quasiquote(?=[%s])' % _delimiters, Keyword,
+            (rf'quasiquote(?=[{_delimiters}])', Keyword,
              ('#pop', 'quasiquoted-datum')),
             (_opening_parenthesis, Punctuation, ('#pop', 'unquoted-list')),
-            (words(_keywords, suffix='(?=[%s])' % _delimiters),
+            (words(_keywords, suffix=f'(?=[{_delimiters}])'),
              Keyword, '#pop'),
-            (words(_builtins, suffix='(?=[%s])' % _delimiters),
+            (words(_builtins, suffix=f'(?=[{_delimiters}])'),
              Name.Builtin, '#pop'),
             (_symbol, Name, '#pop'),
             include('datum*')
@@ -1508,7 +1494,7 @@ class RacketLexer(RegexLexer):
         'quasiquoted-datum': [
             include('datum'),
             (r',@?', Operator, ('#pop', 'unquoted-datum')),
-            (r'unquote(-splicing)?(?=[%s])' % _delimiters, Keyword,
+            (rf'unquote(-splicing)?(?=[{_delimiters}])', Keyword,
              ('#pop', 'unquoted-datum')),
             (_opening_parenthesis, Punctuation, ('#pop', 'quasiquoted-list')),
             include('datum*')
@@ -1543,8 +1529,6 @@ class RacketLexer(RegexLexer):
 class NewLispLexer(RegexLexer):
     """
     For newLISP source code (version 10.3.0).
-
-    .. versionadded:: 1.5
     """
 
     name = 'NewLisp'
@@ -1552,6 +1536,7 @@ class NewLispLexer(RegexLexer):
     aliases = ['newlisp']
     filenames = ['*.lsp', '*.nl', '*.kif']
     mimetypes = ['text/x-newlisp', 'application/x-newlisp']
+    version_added = '1.5'
 
     flags = re.IGNORECASE | re.MULTILINE
 
@@ -1676,13 +1661,13 @@ class EmacsLispLexer(RegexLexer):
     """
     An ELisp lexer, parsing a stream and outputting the tokens
     needed to highlight elisp code.
-
-    .. versionadded:: 2.1
     """
     name = 'EmacsLisp'
     aliases = ['emacs-lisp', 'elisp', 'emacs']
     filenames = ['*.el']
     mimetypes = ['text/x-elisp', 'application/x-elisp']
+    url = 'https://www.gnu.org/software/emacs'
+    version_added = '2.1'
 
     flags = re.MULTILINE
 
@@ -1695,7 +1680,7 @@ class EmacsLispLexer(RegexLexer):
 
     # symbol token, reverse-engineered from hyperspec
     # Take a deep breath...
-    symbol = r'((?:%s)(?:%s)*)' % (nonmacro, constituent)
+    symbol = rf'((?:{nonmacro})(?:{constituent})*)'
 
     macros = {
         'atomic-change-group', 'case', 'block', 'cl-block', 'cl-callf', 'cl-callf2',
@@ -2308,7 +2293,7 @@ class EmacsLispLexer(RegexLexer):
         ],
         'string': [
             (r'[^"\\`]+', String),
-            (r'`%s\'' % symbol, String.Symbol),
+            (rf'`{symbol}\'', String.Symbol),
             (r'`', String),
             (r'\\.', String),
             (r'\\\n', String),
@@ -2320,14 +2305,13 @@ class EmacsLispLexer(RegexLexer):
 class ShenLexer(RegexLexer):
     """
     Lexer for Shen source code.
-
-    .. versionadded:: 2.1
     """
     name = 'Shen'
     url = 'http://shenlanguage.org/'
     aliases = ['shen']
     filenames = ['*.shen']
     mimetypes = ['text/x-shen', 'application/x-shen']
+    version_added = '2.1'
 
     DECLARATIONS = (
         'datatype', 'define', 'defmacro', 'defprolog', 'defcc',
@@ -2375,9 +2359,9 @@ class ShenLexer(RegexLexer):
     MAPPINGS.update((s, Keyword) for s in SPECIAL_FORMS)
 
     valid_symbol_chars = r'[\w!$%*+,<=>?/.\'@&#:-]'
-    valid_name = '%s+' % valid_symbol_chars
-    symbol_name = r'[a-z!$%%*+,<=>?/.\'@&#_-]%s*' % valid_symbol_chars
-    variable = r'[A-Z]%s*' % valid_symbol_chars
+    valid_name = f'{valid_symbol_chars}+'
+    symbol_name = rf'[a-z!$%*+,<=>?/.\'@&#_-]{valid_symbol_chars}*'
+    variable = rf'[A-Z]{valid_symbol_chars}*'
 
     tokens = {
         'string': [
@@ -2485,13 +2469,13 @@ class ShenLexer(RegexLexer):
 class CPSALexer(RegexLexer):
     """
     A CPSA lexer based on the CPSA language as of version 2.2.12
-
-    .. versionadded:: 2.1
     """
     name = 'CPSA'
     aliases = ['cpsa']
     filenames = ['*.cpsa']
     mimetypes = []
+    url = 'https://web.cs.wpi.edu/~guttman/cs564/cpsauser.html'
+    version_added = '2.1'
 
     # list of known keywords and builtins taken form vim 6.4 scheme.vim
     # syntax file.
@@ -2566,14 +2550,13 @@ class XtlangLexer(RegexLexer):
     This is a mixture of Scheme and xtlang, really. Keyword lists are
     taken from the Extempore Emacs mode
     (https://github.com/extemporelang/extempore-emacs-mode)
-
-    .. versionadded:: 2.2
     """
     name = 'xtlang'
     url = 'http://extempore.moso.com.au'
     aliases = ['extempore']
     filenames = ['*.xtm']
     mimetypes = []
+    version_added = '2.2'
 
     common_keywords = (
         'lambda', 'define', 'if', 'else', 'cond', 'and',
@@ -2769,13 +2752,12 @@ class FennelLexer(RegexLexer):
 
     Fennel compiles to Lua, so all the Lua builtins are recognized as well
     as the special forms that are particular to the Fennel compiler.
-
-    .. versionadded:: 2.3
     """
     name = 'Fennel'
     url = 'https://fennel-lang.org'
     aliases = ['fennel', 'fnl']
     filenames = ['*.fnl']
+    version_added = '2.3'
 
     # this list is current as of Fennel version 0.10.0.
     special_forms = (
@@ -2846,3 +2828,319 @@ class FennelLexer(RegexLexer):
             (r'#', Punctuation),
         ]
     }
+
+
+class JanetLexer(RegexLexer):
+    """A lexer for the Janet programming language.
+    """
+    name = 'Janet'
+    url =  'https://janet-lang.org/'
+    aliases = ['janet']
+    filenames = ['*.janet', '*.jdn']
+    mimetypes = ['text/x-janet', 'application/x-janet']
+    version_added = '2.18'
+
+    # XXX: gets too slow
+    #flags = re.MULTILINE | re.VERBOSE
+
+    special_forms = (
+        'break', 'def', 'do', 'fn', 'if', 'quote', 'quasiquote', 'splice',
+        'set', 'unquote', 'upscope', 'var', 'while'
+    )
+
+    builtin_macros = (
+        '%=', '*=', '++', '+=', '--', '-=', '->', '->>', '-?>',
+        '-?>>', '/=', 'and', 'as->', 'as-macro', 'as?->',
+        'assert', 'case', 'catseq', 'chr', 'comment', 'compif',
+        'comptime', 'compwhen', 'cond', 'coro', 'def-',
+        'default', 'defdyn', 'defer', 'defmacro', 'defmacro-',
+        'defn', 'defn-', 'delay', 'doc', 'each', 'eachk',
+        'eachp', 'edefer', 'ev/do-thread', 'ev/gather',
+        'ev/spawn', 'ev/spawn-thread', 'ev/with-deadline',
+        'ffi/defbind', 'fiber-fn', 'for', 'forever', 'forv',
+        'generate', 'if-let', 'if-not', 'if-with', 'import',
+        'juxt', 'label', 'let', 'loop', 'match', 'or', 'prompt',
+        'protect', 'repeat', 'seq', 'short-fn', 'tabseq',
+        'toggle', 'tracev', 'try', 'unless', 'use', 'var-',
+        'varfn', 'when', 'when-let', 'when-with', 'with',
+        'with-dyns', 'with-syms', 'with-vars',
+        # obsolete builtin macros
+        'eachy'
+    )
+
+    builtin_functions = (
+        '%', '*', '+', '-', '/', '<', '<=', '=', '>', '>=',
+        'abstract?', 'accumulate', 'accumulate2', 'all',
+        'all-bindings', 'all-dynamics', 'any?', 'apply',
+        'array', 'array/clear', 'array/concat', 'array/ensure',
+        'array/fill', 'array/insert', 'array/new',
+        'array/new-filled', 'array/peek', 'array/pop',
+        'array/push', 'array/remove', 'array/slice',
+        'array/trim', 'array/weak', 'array?', 'asm',
+        'bad-compile', 'bad-parse', 'band', 'blshift', 'bnot',
+        'boolean?', 'bor', 'brshift', 'brushift', 'buffer',
+        'buffer/bit', 'buffer/bit-clear', 'buffer/bit-set',
+        'buffer/bit-toggle', 'buffer/blit', 'buffer/clear',
+        'buffer/fill', 'buffer/format', 'buffer/from-bytes',
+        'buffer/new', 'buffer/new-filled', 'buffer/popn',
+        'buffer/push', 'buffer/push-at', 'buffer/push-byte',
+        'buffer/push-string', 'buffer/push-word',
+        'buffer/slice', 'buffer/trim', 'buffer?', 'bxor',
+        'bytes?', 'cancel', 'cfunction?', 'cli-main', 'cmp',
+        'comp', 'compare', 'compare<', 'compare<=', 'compare=',
+        'compare>', 'compare>=', 'compile', 'complement',
+        'count', 'curenv', 'debug', 'debug/arg-stack',
+        'debug/break', 'debug/fbreak', 'debug/lineage',
+        'debug/stack', 'debug/stacktrace', 'debug/step',
+        'debug/unbreak', 'debug/unfbreak', 'debugger',
+        'debugger-on-status', 'dec', 'deep-not=', 'deep=',
+        'defglobal', 'describe', 'dictionary?', 'disasm',
+        'distinct', 'div', 'doc*', 'doc-format', 'doc-of',
+        'dofile', 'drop', 'drop-until', 'drop-while', 'dyn',
+        'eflush', 'empty?', 'env-lookup', 'eprin', 'eprinf',
+        'eprint', 'eprintf', 'error', 'errorf',
+        'ev/acquire-lock', 'ev/acquire-rlock',
+        'ev/acquire-wlock', 'ev/all-tasks', 'ev/call',
+        'ev/cancel', 'ev/capacity', 'ev/chan', 'ev/chan-close',
+        'ev/chunk', 'ev/close', 'ev/count', 'ev/deadline',
+        'ev/full', 'ev/give', 'ev/give-supervisor', 'ev/go',
+        'ev/lock', 'ev/read', 'ev/release-lock',
+        'ev/release-rlock', 'ev/release-wlock', 'ev/rselect',
+        'ev/rwlock', 'ev/select', 'ev/sleep', 'ev/take',
+        'ev/thread', 'ev/thread-chan', 'ev/write', 'eval',
+        'eval-string', 'even?', 'every?', 'extreme', 'false?',
+        'ffi/align', 'ffi/call', 'ffi/calling-conventions',
+        'ffi/close', 'ffi/context', 'ffi/free', 'ffi/jitfn',
+        'ffi/lookup', 'ffi/malloc', 'ffi/native',
+        'ffi/pointer-buffer', 'ffi/pointer-cfunction',
+        'ffi/read', 'ffi/signature', 'ffi/size', 'ffi/struct',
+        'ffi/trampoline', 'ffi/write', 'fiber/can-resume?',
+        'fiber/current', 'fiber/getenv', 'fiber/last-value',
+        'fiber/maxstack', 'fiber/new', 'fiber/root',
+        'fiber/setenv', 'fiber/setmaxstack', 'fiber/status',
+        'fiber?', 'file/close', 'file/flush', 'file/lines',
+        'file/open', 'file/read', 'file/seek', 'file/tell',
+        'file/temp', 'file/write', 'filter', 'find',
+        'find-index', 'first', 'flatten', 'flatten-into',
+        'flush', 'flycheck', 'freeze', 'frequencies',
+        'from-pairs', 'function?', 'gccollect', 'gcinterval',
+        'gcsetinterval', 'gensym', 'get', 'get-in', 'getline',
+        'getproto', 'group-by', 'has-key?', 'has-value?',
+        'hash', 'idempotent?', 'identity', 'import*', 'in',
+        'inc', 'index-of', 'indexed?', 'int/s64',
+        'int/to-bytes', 'int/to-number', 'int/u64', 'int?',
+        'interleave', 'interpose', 'invert', 'juxt*', 'keep',
+        'keep-syntax', 'keep-syntax!', 'keys', 'keyword',
+        'keyword/slice', 'keyword?', 'kvs', 'last', 'length',
+        'lengthable?', 'load-image', 'macex', 'macex1',
+        'maclintf', 'make-env', 'make-image', 'map', 'mapcat',
+        'marshal', 'math/abs', 'math/acos', 'math/acosh',
+        'math/asin', 'math/asinh', 'math/atan', 'math/atan2',
+        'math/atanh', 'math/cbrt', 'math/ceil', 'math/cos',
+        'math/cosh', 'math/erf', 'math/erfc', 'math/exp',
+        'math/exp2', 'math/expm1', 'math/floor', 'math/gamma',
+        'math/gcd', 'math/hypot', 'math/lcm', 'math/log',
+        'math/log-gamma', 'math/log10', 'math/log1p',
+        'math/log2', 'math/next', 'math/pow', 'math/random',
+        'math/rng', 'math/rng-buffer', 'math/rng-int',
+        'math/rng-uniform', 'math/round', 'math/seedrandom',
+        'math/sin', 'math/sinh', 'math/sqrt', 'math/tan',
+        'math/tanh', 'math/trunc', 'max', 'max-of', 'mean',
+        'memcmp', 'merge', 'merge-into', 'merge-module', 'min',
+        'min-of', 'mod', 'module/add-paths',
+        'module/expand-path', 'module/find', 'module/value',
+        'nan?', 'nat?', 'native', 'neg?', 'net/accept',
+        'net/accept-loop', 'net/address', 'net/address-unpack',
+        'net/chunk', 'net/close', 'net/connect', 'net/flush',
+        'net/listen', 'net/localname', 'net/peername',
+        'net/read', 'net/recv-from', 'net/send-to',
+        'net/server', 'net/setsockopt', 'net/shutdown',
+        'net/write', 'next', 'nil?', 'not', 'not=', 'number?',
+        'odd?', 'one?', 'os/arch', 'os/cd', 'os/chmod',
+        'os/clock', 'os/compiler', 'os/cpu-count',
+        'os/cryptorand', 'os/cwd', 'os/date', 'os/dir',
+        'os/environ', 'os/execute', 'os/exit', 'os/getenv',
+        'os/isatty', 'os/link', 'os/lstat', 'os/mkdir',
+        'os/mktime', 'os/open', 'os/perm-int', 'os/perm-string',
+        'os/pipe', 'os/posix-exec', 'os/posix-fork',
+        'os/proc-close', 'os/proc-kill', 'os/proc-wait',
+        'os/readlink', 'os/realpath', 'os/rename', 'os/rm',
+        'os/rmdir', 'os/setenv', 'os/shell', 'os/sigaction',
+        'os/sleep', 'os/spawn', 'os/stat', 'os/strftime',
+        'os/symlink', 'os/time', 'os/touch', 'os/umask',
+        'os/which', 'pairs', 'parse', 'parse-all',
+        'parser/byte', 'parser/clone', 'parser/consume',
+        'parser/eof', 'parser/error', 'parser/flush',
+        'parser/has-more', 'parser/insert', 'parser/new',
+        'parser/produce', 'parser/state', 'parser/status',
+        'parser/where', 'partial', 'partition', 'partition-by',
+        'peg/compile', 'peg/find', 'peg/find-all', 'peg/match',
+        'peg/replace', 'peg/replace-all', 'pos?', 'postwalk',
+        'pp', 'prewalk', 'prin', 'prinf', 'print', 'printf',
+        'product', 'propagate', 'put', 'put-in', 'quit',
+        'range', 'reduce', 'reduce2', 'repl', 'require',
+        'resume', 'return', 'reverse', 'reverse!',
+        'run-context', 'sandbox', 'scan-number', 'setdyn',
+        'signal', 'slice', 'slurp', 'some', 'sort', 'sort-by',
+        'sorted', 'sorted-by', 'spit', 'string',
+        'string/ascii-lower', 'string/ascii-upper',
+        'string/bytes', 'string/check-set', 'string/find',
+        'string/find-all', 'string/format', 'string/from-bytes',
+        'string/has-prefix?', 'string/has-suffix?',
+        'string/join', 'string/repeat', 'string/replace',
+        'string/replace-all', 'string/reverse', 'string/slice',
+        'string/split', 'string/trim', 'string/triml',
+        'string/trimr', 'string?', 'struct', 'struct/getproto',
+        'struct/proto-flatten', 'struct/to-table',
+        'struct/with-proto', 'struct?', 'sum', 'symbol',
+        'symbol/slice', 'symbol?', 'table', 'table/clear',
+        'table/clone', 'table/getproto', 'table/new',
+        'table/proto-flatten', 'table/rawget', 'table/setproto',
+        'table/to-struct', 'table/weak', 'table/weak-keys',
+        'table/weak-values', 'table?', 'take', 'take-until',
+        'take-while', 'thaw', 'trace', 'true?', 'truthy?',
+        'tuple', 'tuple/brackets', 'tuple/setmap',
+        'tuple/slice', 'tuple/sourcemap', 'tuple/type',
+        'tuple?', 'type', 'unmarshal', 'untrace', 'update',
+        'update-in', 'values', 'varglobal', 'walk',
+        'warn-compile', 'xprin', 'xprinf', 'xprint', 'xprintf',
+        'yield', 'zero?', 'zipcoll',
+        # obsolete builtin functions
+        'tarray/buffer', 'tarray/copy-bytes', 'tarray/length',
+        'tarray/new', 'tarray/properties', 'tarray/slice',
+        'tarray/swap-bytes', 'thread/close', 'thread/current',
+        'thread/exit', 'thread/new', 'thread/receive',
+        'thread/send'
+    )
+
+    builtin_variables = (
+        'debugger-env', 'default-peg-grammar', 'janet/build',
+        'janet/config-bits', 'janet/version', 'load-image-dict',
+        'make-image-dict', 'math/-inf', 'math/e', 'math/inf',
+        'math/int-max', 'math/int-min', 'math/int32-max',
+        'math/int32-min', 'math/nan', 'math/pi', 'module/cache',
+        'module/loaders', 'module/loading', 'module/paths',
+        'root-env', 'stderr', 'stdin', 'stdout'
+    )
+
+    constants = (
+        'false', 'nil', 'true'
+    )
+
+    # XXX: this form not usable to pass to `suffix=`
+    #_token_end = r'''
+    #  (?=            # followed by one of:
+    #      \s           # whitespace
+    #    | \#           # comment
+    #    | [)\]]        # end delimiters
+    #    | $            # end of file
+    #  )
+    #'''
+
+    # ...so, express it like this
+    _token_end = r'(?=\s|#|[)\]]|$)'
+
+    _first_char = r'[a-zA-Z!$%&*+\-./<=>?@^_]'
+    _rest_char = rf'([0-9:]|{_first_char})'
+
+    valid_name = rf'{_first_char}({_rest_char})*'
+
+    _radix_unit = r'[0-9a-zA-Z][0-9a-zA-Z_]*'
+
+    # exponent marker, optional sign, one or more alphanumeric
+    _radix_exp = r'&[+-]?[0-9a-zA-Z]+'
+
+    # 2af3__bee_
+    _hex_unit = r'[0-9a-fA-F][0-9a-fA-F_]*'
+
+    # 12_000__
+    _dec_unit = r'[0-9][0-9_]*'
+
+    # E-23
+    # lower or uppercase e, optional sign, one or more digits
+    _dec_exp = r'[eE][+-]?[0-9]+'
+
+    tokens = {
+        'root': [
+            (r'#.*$', Comment.Single),
+
+            (r'\s+', Whitespace),
+
+            # radix number
+            (rf'''(?x)
+                  [+-]? [0-9]{{1,2}} r {_radix_unit} \. ({_radix_unit})?
+                  ({_radix_exp})?
+               ''',
+             Number),
+
+            (rf'''(?x)
+                  [+-]? [0-9]{{1,2}} r (\.)? {_radix_unit}
+                  ({_radix_exp})?
+               ''',
+             Number),
+
+            # hex number
+            (rf'(?x) [+-]? 0x {_hex_unit} \. ({_hex_unit})?',
+             Number.Hex),
+
+            (rf'(?x) [+-]? 0x (\.)? {_hex_unit}',
+             Number.Hex),
+
+            # decimal number
+            (rf'(?x) [+-]? {_dec_unit} \. ({_dec_unit})? ({_dec_exp})?',
+             Number.Float),
+
+            (rf'(?x) [+-]? (\.)? {_dec_unit} ({_dec_exp})?',
+             Number.Float),
+
+            # strings and buffers
+            (r'@?"', String, 'string'),
+
+            # long-strings and long-buffers
+            #
+            #   non-empty content enclosed by a pair of n-backticks
+            #   with optional leading @
+            (r'@?(`+)(.|\n)+?\1', String),
+
+            # things that hang out on front
+            #
+            #   ' ~ , ; |
+            (r"['~,;|]", Operator),
+
+            # collection delimiters
+            #
+            #   @( ( )
+            #   @[ [ ]
+            #   @{ { }
+            (r'@?[(\[{]|[)\]}]', Punctuation),
+
+            # constants
+            (words(constants, suffix=_token_end), Keyword.Constants),
+
+            # keywords
+            (rf'(:({_rest_char})+|:)', Name.Constant),
+
+            # symbols
+            (words(builtin_variables, suffix=_token_end),
+             Name.Variable.Global),
+
+            (words(special_forms, prefix=r'(?<=\()', suffix=_token_end),
+             Keyword.Reserved),
+
+            (words(builtin_macros, prefix=r'(?<=\()', suffix=_token_end),
+             Name.Builtin),
+
+            (words(builtin_functions, prefix=r'(?<=\()', suffix=_token_end),
+             Name.Function),
+
+            # other symbols
+            (valid_name, Name.Variable),
+        ],
+        'string': [
+            (r'\\(u[0-9a-fA-F]{4}|U[0-9a-fA-F]{6})', String.Escape),
+            (r'\\x[0-9a-fA-F]{2}', String.Escape),
+            (r'\\.', String.Escape),
+            (r'"', String, '#pop'),
+            (r'[^\\"]+', String),
+        ]
+    }