pygments.rb 1.2.1 → 2.2.0

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

@@ -0,0 +1,158 @@
+"""
+    pygments.lexers.nimrod
+    ~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexer for the Nim language (formerly known as Nimrod).
+
+    :copyright: Copyright 2006-2021 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import RegexLexer, include, default
+from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation, Error
+
+__all__ = ['NimrodLexer']
+
+
+class NimrodLexer(RegexLexer):
+    """
+    For `Nim <http://nim-lang.org/>`_ source code.
+
+    .. versionadded:: 1.5
+    """
+
+    name = 'Nimrod'
+    aliases = ['nim', 'nimrod']
+    filenames = ['*.nim', '*.nimrod']
+    mimetypes = ['text/x-nim']
+
+    flags = re.MULTILINE | re.IGNORECASE | re.UNICODE
+
+    def underscorize(words):
+        newWords = []
+        new = ""
+        for word in words:
+            for ch in word:
+                new += (ch + "_?")
+            newWords.append(new)
+            new = ""
+        return "|".join(newWords)
+
+    keywords = [
+        'addr', 'and', 'as', 'asm', 'bind', 'block', 'break', 'case',
+        'cast', 'concept', 'const', 'continue', 'converter', 'defer', 'discard',
+        'distinct', 'div', 'do', 'elif', 'else', 'end', 'enum', 'except',
+        'export', 'finally', 'for', 'func', 'if', 'in', 'yield', 'interface',
+        'is', 'isnot', 'iterator', 'let', 'macro', 'method', 'mixin', 'mod',
+        'not', 'notin', 'object', 'of', 'or', 'out', 'proc', 'ptr', 'raise',
+        'ref', 'return', 'shl', 'shr', 'static', 'template', 'try',
+        'tuple', 'type', 'using', 'when', 'while', 'xor'
+    ]
+
+    keywordsPseudo = [
+        'nil', 'true', 'false'
+    ]
+
+    opWords = [
+        'and', 'or', 'not', 'xor', 'shl', 'shr', 'div', 'mod', 'in',
+        'notin', 'is', 'isnot'
+    ]
+
+    types = [
+        'int', 'int8', 'int16', 'int32', 'int64', 'float', 'float32', 'float64',
+        'bool', 'char', 'range', 'array', 'seq', 'set', 'string'
+    ]
+
+    tokens = {
+        'root': [
+            (r'##.*$', String.Doc),
+            (r'#.*$', Comment),
+            (r'[*=><+\-/@$~&%!?|\\\[\]]', Operator),
+            (r'\.\.|\.|,|\[\.|\.\]|\{\.|\.\}|\(\.|\.\)|\{|\}|\(|\)|:|\^|`|;',
+             Punctuation),
+
+            # Strings
+            (r'(?:[\w]+)"', String, 'rdqs'),
+            (r'"""', String, 'tdqs'),
+            ('"', String, 'dqs'),
+
+            # Char
+            ("'", String.Char, 'chars'),
+
+            # Keywords
+            (r'(%s)\b' % underscorize(opWords), Operator.Word),
+            (r'(p_?r_?o_?c_?\s)(?![(\[\]])', Keyword, 'funcname'),
+            (r'(%s)\b' % underscorize(keywords), Keyword),
+            (r'(%s)\b' % underscorize(['from', 'import', 'include']),
+             Keyword.Namespace),
+            (r'(v_?a_?r)\b', Keyword.Declaration),
+            (r'(%s)\b' % underscorize(types), Keyword.Type),
+            (r'(%s)\b' % underscorize(keywordsPseudo), Keyword.Pseudo),
+            # Identifiers
+            (r'\b((?![_\d])\w)(((?!_)\w)|(_(?!_)\w))*', Name),
+            # Numbers
+            (r'[0-9][0-9_]*(?=([e.]|\'f(32|64)))',
+             Number.Float, ('float-suffix', 'float-number')),
+            (r'0x[a-f0-9][a-f0-9_]*', Number.Hex, 'int-suffix'),
+            (r'0b[01][01_]*', Number.Bin, 'int-suffix'),
+            (r'0o[0-7][0-7_]*', Number.Oct, 'int-suffix'),
+            (r'[0-9][0-9_]*', Number.Integer, 'int-suffix'),
+            # Whitespace
+            (r'\s+', Text),
+            (r'.+$', Error),
+        ],
+        'chars': [
+            (r'\\([\\abcefnrtvl"\']|x[a-f0-9]{2}|[0-9]{1,3})', String.Escape),
+            (r"'", String.Char, '#pop'),
+            (r".", String.Char)
+        ],
+        'strings': [
+            (r'(?<!\$)\$(\d+|#|\w+)+', String.Interpol),
+            (r'[^\\\'"$\n]+', String),
+            # quotes, dollars and backslashes must be parsed one at a time
+            (r'[\'"\\]', String),
+            # unhandled string formatting sign
+            (r'\$', String)
+            # newlines are an error (use "nl" state)
+        ],
+        'dqs': [
+            (r'\\([\\abcefnrtvl"\']|\n|x[a-f0-9]{2}|[0-9]{1,3})',
+             String.Escape),
+            (r'"', String, '#pop'),
+            include('strings')
+        ],
+        'rdqs': [
+            (r'"(?!")', String, '#pop'),
+            (r'""', String.Escape),
+            include('strings')
+        ],
+        'tdqs': [
+            (r'"""(?!")', String, '#pop'),
+            include('strings'),
+            include('nl')
+        ],
+        'funcname': [
+            (r'((?![\d_])\w)(((?!_)\w)|(_(?!_)\w))*', Name.Function, '#pop'),
+            (r'`.+`', Name.Function, '#pop')
+        ],
+        'nl': [
+            (r'\n', String)
+        ],
+        'float-number': [
+            (r'\.(?!\.)[0-9_]*', Number.Float),
+            (r'e[+-]?[0-9][0-9_]*', Number.Float),
+            default('#pop')
+        ],
+        'float-suffix': [
+            (r'\'f(32|64)', Number.Float),
+            default('#pop')
+        ],
+        'int-suffix': [
+            (r'\'i(32|64)', Number.Integer.Long),
+            (r'\'i(8|16)', Number.Integer),
+            default('#pop')
+        ],
+    }

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

@@ -0,0 +1,63 @@
+"""
+    pygments.lexers.nit
+    ~~~~~~~~~~~~~~~~~~~
+
+    Lexer for the Nit language.
+
+    :copyright: Copyright 2006-2021 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 <http://nitlanguage.org>`_ source.
+
+    .. versionadded:: 2.0
+    """
+
+    name = 'Nit'
+    aliases = ['nit']
+    filenames = ['*.nit']
+    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),
+        ],
+    }

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

@@ -0,0 +1,135 @@
+"""
+    pygments.lexers.nix
+    ~~~~~~~~~~~~~~~~~~~
+
+    Lexers for the NixOS Nix language.
+
+    :copyright: Copyright 2006-2021 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import RegexLexer, include
+from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation, Literal
+
+__all__ = ['NixLexer']
+
+
+class NixLexer(RegexLexer):
+    """
+    For the `Nix language <http://nixos.org/nix/>`_.
+
+    .. versionadded:: 2.0
+    """
+
+    name = 'Nix'
+    aliases = ['nixos', 'nix']
+    filenames = ['*.nix']
+    mimetypes = ['text/x-nix']
+
+    flags = re.MULTILINE | re.UNICODE
+
+    keywords = ['rec', 'with', 'let', 'in', 'inherit', 'assert', 'if',
+                'else', 'then', '...']
+    builtins = ['import', 'abort', 'baseNameOf', 'dirOf', 'isNull', 'builtins',
+                'map', 'removeAttrs', 'throw', 'toString', 'derivation']
+    operators = ['++', '+', '?', '.', '!', '//', '==',
+                 '!=', '&&', '||', '->', '=']
+
+    punctuations = ["(", ")", "[", "]", ";", "{", "}", ":", ",", "@"]
+
+    tokens = {
+        'root': [
+            # comments starting with #
+            (r'#.*$', Comment.Single),
+
+            # multiline comments
+            (r'/\*', Comment.Multiline, 'comment'),
+
+            # whitespace
+            (r'\s+', Text),
+
+            # keywords
+            ('(%s)' % '|'.join(re.escape(entry) + '\\b' for entry in keywords), Keyword),
+
+            # highlight the builtins
+            ('(%s)' % '|'.join(re.escape(entry) + '\\b' for entry in builtins),
+             Name.Builtin),
+
+            (r'\b(true|false|null)\b', Name.Constant),
+
+            # operators
+            ('(%s)' % '|'.join(re.escape(entry) for entry in operators),
+             Operator),
+
+            # word operators
+            (r'\b(or|and)\b', Operator.Word),
+
+            # punctuations
+            ('(%s)' % '|'.join(re.escape(entry) for entry in punctuations), Punctuation),
+
+            # integers
+            (r'[0-9]+', Number.Integer),
+
+            # strings
+            (r'"', String.Double, 'doublequote'),
+            (r"''", String.Single, 'singlequote'),
+
+            # paths
+            (r'[\w.+-]*(\/[\w.+-]+)+', Literal),
+            (r'\<[\w.+-]+(\/[\w.+-]+)*\>', Literal),
+
+            # urls
+            (r'[a-zA-Z][a-zA-Z0-9\+\-\.]*\:[\w%/?:@&=+$,\\.!~*\'-]+', Literal),
+
+            # names of variables
+            (r'[\w-]+\s*=', String.Symbol),
+            (r'[a-zA-Z_][\w\'-]*', Text),
+
+        ],
+        'comment': [
+            (r'[^/*]+', Comment.Multiline),
+            (r'/\*', Comment.Multiline, '#push'),
+            (r'\*/', Comment.Multiline, '#pop'),
+            (r'[*/]', Comment.Multiline),
+        ],
+        'singlequote': [
+            (r"'''", String.Escape),
+            (r"''\$\{", String.Escape),
+            (r"''\n", String.Escape),
+            (r"''\r", String.Escape),
+            (r"''\t", String.Escape),
+            (r"''", String.Single, '#pop'),
+            (r'\$\{', String.Interpol, 'antiquote'),
+            (r"[^']", String.Single),
+        ],
+        'doublequote': [
+            (r'\\', String.Escape),
+            (r'\\"', String.Escape),
+            (r'\\$\{', String.Escape),
+            (r'"', String.Double, '#pop'),
+            (r'\$\{', String.Interpol, 'antiquote'),
+            (r'[^"]', String.Double),
+        ],
+        'antiquote': [
+            (r"\}", String.Interpol, '#pop'),
+            # TODO: we should probably escape also here ''${ \${
+            (r"\$\{", String.Interpol, '#push'),
+            include('root'),
+        ],
+    }
+
+    def analyse_text(text):
+        rv = 0.0
+        # TODO: let/in
+        if re.search(r'import.+?<[^>]+>', text):
+            rv += 0.4
+        if re.search(r'mkDerivation\s+(\(|\{|rec)', text):
+            rv += 0.4
+        if re.search(r'=\s+mkIf\s+', text):
+            rv += 0.4
+        if re.search(r'\{[a-zA-Z,\s]+\}:', text):
+            rv += 0.1
+        return rv

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

@@ -0,0 +1,120 @@
+"""
+    pygments.lexers.oberon
+    ~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexers for Oberon family languages.
+
+    :copyright: Copyright 2006-2021 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import RegexLexer, include, words
+from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation
+
+__all__ = ['ComponentPascalLexer']
+
+
+class ComponentPascalLexer(RegexLexer):
+    """
+    For `Component Pascal <http://www.oberon.ch/pdf/CP-Lang.pdf>`_ source code.
+
+    .. versionadded:: 2.1
+    """
+    name = 'Component Pascal'
+    aliases = ['componentpascal', 'cp']
+    filenames = ['*.cp', '*.cps']
+    mimetypes = ['text/x-component-pascal']
+
+    flags = re.MULTILINE | re.DOTALL
+
+    tokens = {
+        'root': [
+            include('whitespace'),
+            include('comments'),
+            include('punctuation'),
+            include('numliterals'),
+            include('strings'),
+            include('operators'),
+            include('builtins'),
+            include('identifiers'),
+        ],
+        'whitespace': [
+            (r'\n+', Text),  # blank lines
+            (r'\s+', Text),  # whitespace
+        ],
+        'comments': [
+            (r'\(\*([^$].*?)\*\)', Comment.Multiline),
+            # TODO: nested comments (* (* ... *) ... (* ... *) *) not supported!
+        ],
+        'punctuation': [
+            (r'[()\[\]{},.:;|]', Punctuation),
+        ],
+        'numliterals': [
+            (r'[0-9A-F]+X\b', Number.Hex),                 # char code
+            (r'[0-9A-F]+[HL]\b', Number.Hex),              # hexadecimal number
+            (r'[0-9]+\.[0-9]+E[+-][0-9]+', Number.Float),  # real number
+            (r'[0-9]+\.[0-9]+', Number.Float),             # real number
+            (r'[0-9]+', Number.Integer),                   # decimal whole number
+        ],
+        'strings': [
+            (r"'[^\n']*'", String),  # single quoted string
+            (r'"[^\n"]*"', String),  # double quoted string
+        ],
+        'operators': [
+            # Arithmetic Operators
+            (r'[+-]', Operator),
+            (r'[*/]', Operator),
+            # Relational Operators
+            (r'[=#<>]', Operator),
+            # Dereferencing Operator
+            (r'\^', Operator),
+            # Logical AND Operator
+            (r'&', Operator),
+            # Logical NOT Operator
+            (r'~', Operator),
+            # Assignment Symbol
+            (r':=', Operator),
+            # Range Constructor
+            (r'\.\.', Operator),
+            (r'\$', Operator),
+        ],
+        'identifiers': [
+            (r'([a-zA-Z_$][\w$]*)', Name),
+        ],
+        'builtins': [
+            (words((
+                'ANYPTR', 'ANYREC', 'BOOLEAN', 'BYTE', 'CHAR', 'INTEGER', 'LONGINT',
+                'REAL', 'SET', 'SHORTCHAR', 'SHORTINT', 'SHORTREAL'
+                ), suffix=r'\b'), Keyword.Type),
+            (words((
+                'ABS', 'ABSTRACT', 'ARRAY', 'ASH', 'ASSERT', 'BEGIN', 'BITS', 'BY',
+                'CAP', 'CASE', 'CHR', 'CLOSE', 'CONST', 'DEC', 'DIV', 'DO', 'ELSE',
+                'ELSIF', 'EMPTY', 'END', 'ENTIER', 'EXCL', 'EXIT', 'EXTENSIBLE', 'FOR',
+                'HALT', 'IF', 'IMPORT', 'IN', 'INC', 'INCL', 'IS', 'LEN', 'LIMITED',
+                'LONG', 'LOOP', 'MAX', 'MIN', 'MOD', 'MODULE', 'NEW', 'ODD', 'OF',
+                'OR', 'ORD', 'OUT', 'POINTER', 'PROCEDURE', 'RECORD', 'REPEAT', 'RETURN',
+                'SHORT', 'SHORTCHAR', 'SHORTINT', 'SIZE', 'THEN', 'TYPE', 'TO', 'UNTIL',
+                'VAR', 'WHILE', 'WITH'
+                ), suffix=r'\b'), Keyword.Reserved),
+            (r'(TRUE|FALSE|NIL|INF)\b', Keyword.Constant),
+        ]
+    }
+
+    def analyse_text(text):
+        """The only other lexer using .cp is the C++ one, so we check if for
+        a few common Pascal keywords here. Those are unfortunately quite
+        common across various business languages as well."""
+        result = 0
+        if 'BEGIN' in text:
+            result += 0.01
+        if 'END' in text:
+            result += 0.01
+        if 'PROCEDURE' in text:
+            result += 0.01
+        if 'END' in text:
+            result += 0.01
+
+        return result