pygments.rb 1.2.1 → 2.0.0.rc2

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

@@ -0,0 +1,152 @@
+# -*- coding: utf-8 -*-
+"""
+    pygments.lexers.qvt
+    ~~~~~~~~~~~~~~~~~~~
+
+    Lexer for QVT Operational language.
+
+    :copyright: Copyright 2006-2020 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import RegexLexer, bygroups, include, combined, default, \
+    words
+from pygments.token import Text, Comment, Operator, Keyword, Punctuation, \
+    Name, String, Number
+
+__all__ = ['QVToLexer']
+
+
+class QVToLexer(RegexLexer):
+    """
+    For the `QVT Operational Mapping language <http://www.omg.org/spec/QVT/1.1/>`_.
+
+    Reference for implementing this: «Meta Object Facility (MOF) 2.0
+    Query/View/Transformation Specification», Version 1.1 - January 2011
+    (http://www.omg.org/spec/QVT/1.1/), see §8.4, «Concrete Syntax» in
+    particular.
+
+    Notable tokens assignments:
+
+    - Name.Class is assigned to the identifier following any of the following
+      keywords: metamodel, class, exception, primitive, enum, transformation
+      or library
+
+    - Name.Function is assigned to the names of mappings and queries
+
+    - Name.Builtin.Pseudo is assigned to the pre-defined variables 'this',
+      'self' and 'result'.
+    """
+    # With obvious borrowings & inspiration from the Java, Python and C lexers
+
+    name = 'QVTO'
+    aliases = ['qvto', 'qvt']
+    filenames = ['*.qvto']
+
+    tokens = {
+        'root': [
+            (r'\n', Text),
+            (r'[^\S\n]+', Text),
+            (r'(--|//)(\s*)(directive:)?(.*)$',
+             bygroups(Comment, Comment, Comment.Preproc, Comment)),
+            # Uncomment the following if you want to distinguish between
+            # '/*' and '/**', à la javadoc
+            # (r'/[*]{2}(.|\n)*?[*]/', Comment.Multiline),
+            (r'/[*](.|\n)*?[*]/', Comment.Multiline),
+            (r'\\\n', Text),
+            (r'(and|not|or|xor|##?)\b', Operator.Word),
+            (r'(:{1,2}=|[-+]=)\b', Operator.Word),
+            (r'(@|<<|>>)\b', Keyword),  # stereotypes
+            (r'!=|<>|==|=|!->|->|>=|<=|[.]{3}|[+/*%=<>&|.~]', Operator),
+            (r'[]{}:(),;[]', Punctuation),
+            (r'(true|false|unlimited|null)\b', Keyword.Constant),
+            (r'(this|self|result)\b', Name.Builtin.Pseudo),
+            (r'(var)\b', Keyword.Declaration),
+            (r'(from|import)\b', Keyword.Namespace, 'fromimport'),
+            (r'(metamodel|class|exception|primitive|enum|transformation|'
+             r'library)(\s+)(\w+)',
+             bygroups(Keyword.Word, Text, Name.Class)),
+            (r'(exception)(\s+)(\w+)',
+             bygroups(Keyword.Word, Text, Name.Exception)),
+            (r'(main)\b', Name.Function),
+            (r'(mapping|helper|query)(\s+)',
+             bygroups(Keyword.Declaration, Text), 'operation'),
+            (r'(assert)(\s+)\b', bygroups(Keyword, Text), 'assert'),
+            (r'(Bag|Collection|Dict|OrderedSet|Sequence|Set|Tuple|List)\b',
+             Keyword.Type),
+            include('keywords'),
+            ('"', String, combined('stringescape', 'dqs')),
+            ("'", String, combined('stringescape', 'sqs')),
+            include('name'),
+            include('numbers'),
+            # (r'([a-zA-Z_]\w*)(::)([a-zA-Z_]\w*)',
+            # bygroups(Text, Text, Text)),
+        ],
+
+        'fromimport': [
+            (r'(?:[ \t]|\\\n)+', Text),
+            (r'[a-zA-Z_][\w.]*', Name.Namespace),
+            default('#pop'),
+        ],
+
+        'operation': [
+            (r'::', Text),
+            (r'(.*::)([a-zA-Z_]\w*)([ \t]*)(\()',
+             bygroups(Text, Name.Function, Text, Punctuation), '#pop')
+        ],
+
+        'assert': [
+            (r'(warning|error|fatal)\b', Keyword, '#pop'),
+            default('#pop'),  # all else: go back
+        ],
+
+        'keywords': [
+            (words((
+                'abstract', 'access', 'any', 'assert', 'blackbox', 'break',
+                'case', 'collect', 'collectNested', 'collectOne', 'collectselect',
+                'collectselectOne', 'composes', 'compute', 'configuration',
+                'constructor', 'continue', 'datatype', 'default', 'derived',
+                'disjuncts', 'do', 'elif', 'else', 'end', 'endif', 'except',
+                'exists', 'extends', 'forAll', 'forEach', 'forOne', 'from', 'if',
+                'implies', 'in', 'inherits', 'init', 'inout', 'intermediate',
+                'invresolve', 'invresolveIn', 'invresolveone', 'invresolveoneIn',
+                'isUnique', 'iterate', 'late', 'let', 'literal', 'log', 'map',
+                'merges', 'modeltype', 'new', 'object', 'one', 'ordered', 'out',
+                'package', 'population', 'property', 'raise', 'readonly',
+                'references', 'refines', 'reject', 'resolve', 'resolveIn',
+                'resolveone', 'resolveoneIn', 'return', 'select', 'selectOne',
+                'sortedBy', 'static', 'switch', 'tag', 'then', 'try', 'typedef',
+                'unlimited', 'uses', 'when', 'where', 'while', 'with', 'xcollect',
+                'xmap', 'xselect'), suffix=r'\b'), Keyword),
+        ],
+
+        # There is no need to distinguish between String.Single and
+        # String.Double: 'strings' is factorised for 'dqs' and 'sqs'
+        'strings': [
+            (r'[^\\\'"\n]+', String),
+            # quotes, percents and backslashes must be parsed one at a time
+            (r'[\'"\\]', String),
+        ],
+        'stringescape': [
+            (r'\\([\\btnfr"\']|u[0-3][0-7]{2}|u[0-7]{1,2})', String.Escape)
+        ],
+        'dqs': [  # double-quoted string
+            (r'"', String, '#pop'),
+            (r'\\\\|\\"', String.Escape),
+            include('strings')
+        ],
+        'sqs': [  # single-quoted string
+            (r"'", String, '#pop'),
+            (r"\\\\|\\'", String.Escape),
+            include('strings')
+        ],
+        'name': [
+            (r'[a-zA-Z_]\w*', Name),
+        ],
+        # numbers: excerpt taken from the python lexer
+        'numbers': [
+            (r'(\d+\.\d*|\d*\.\d+)([eE][+-]?[0-9]+)?', Number.Float),
+            (r'\d+[eE][+-]?[0-9]+', Number.Float),
+            (r'\d+', Number.Integer)
+        ],
+    }

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

@@ -0,0 +1,191 @@
+# -*- coding: utf-8 -*-
+"""
+    pygments.lexers.r
+    ~~~~~~~~~~~~~~~~~
+
+    Lexers for the R/S languages.
+
+    :copyright: Copyright 2006-2020 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import Lexer, RegexLexer, include, do_insertions, bygroups
+from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation, Generic
+
+__all__ = ['RConsoleLexer', 'SLexer', 'RdLexer']
+
+
+line_re  = re.compile('.*?\n')
+
+
+class RConsoleLexer(Lexer):
+    """
+    For R console transcripts or R CMD BATCH output files.
+    """
+
+    name = 'RConsole'
+    aliases = ['rconsole', 'rout']
+    filenames = ['*.Rout']
+
+    def get_tokens_unprocessed(self, text):
+        slexer = SLexer(**self.options)
+
+        current_code_block = ''
+        insertions = []
+
+        for match in line_re.finditer(text):
+            line = match.group()
+            if line.startswith('>') or line.startswith('+'):
+                # Colorize the prompt as such,
+                # then put rest of line into current_code_block
+                insertions.append((len(current_code_block),
+                                   [(0, Generic.Prompt, line[:2])]))
+                current_code_block += line[2:]
+            else:
+                # We have reached a non-prompt line!
+                # If we have stored prompt lines, need to process them first.
+                if current_code_block:
+                    # Weave together the prompts and highlight code.
+                    yield from do_insertions(
+                        insertions, slexer.get_tokens_unprocessed(current_code_block))
+                    # Reset vars for next code block.
+                    current_code_block = ''
+                    insertions = []
+                # Now process the actual line itself, this is output from R.
+                yield match.start(), Generic.Output, line
+
+        # If we happen to end on a code block with nothing after it, need to
+        # process the last code block. This is neither elegant nor DRY so
+        # should be changed.
+        if current_code_block:
+            yield from do_insertions(
+                insertions, slexer.get_tokens_unprocessed(current_code_block))
+
+
+class SLexer(RegexLexer):
+    """
+    For S, S-plus, and R source code.
+
+    .. versionadded:: 0.10
+    """
+
+    name = 'S'
+    aliases = ['splus', 's', 'r']
+    filenames = ['*.S', '*.R', '.Rhistory', '.Rprofile', '.Renviron']
+    mimetypes = ['text/S-plus', 'text/S', 'text/x-r-source', 'text/x-r',
+                 'text/x-R', 'text/x-r-history', 'text/x-r-profile']
+
+    valid_name = r'`[^`\\]*(?:\\.[^`\\]*)*`|(?:[a-zA-Z]|\.[A-Za-z_.])[\w.]*|\.'
+    tokens = {
+        'comments': [
+            (r'#.*$', Comment.Single),
+        ],
+        'valid_name': [
+            (valid_name, Name),
+        ],
+        'punctuation': [
+            (r'\[{1,2}|\]{1,2}|\(|\)|;|,', Punctuation),
+        ],
+        'keywords': [
+            (r'(if|else|for|while|repeat|in|next|break|return|switch|function)'
+             r'(?![\w.])',
+             Keyword.Reserved),
+        ],
+        'operators': [
+            (r'<<?-|->>?|-|==|<=|>=|<|>|&&?|!=|\|\|?|\?', Operator),
+            (r'\*|\+|\^|/|!|%[^%]*%|=|~|\$|@|:{1,3}', Operator),
+        ],
+        'builtin_symbols': [
+            (r'(NULL|NA(_(integer|real|complex|character)_)?|'
+             r'letters|LETTERS|Inf|TRUE|FALSE|NaN|pi|\.\.(\.|[0-9]+))'
+             r'(?![\w.])',
+             Keyword.Constant),
+            (r'(T|F)\b', Name.Builtin.Pseudo),
+        ],
+        'numbers': [
+            # hex number
+            (r'0[xX][a-fA-F0-9]+([pP][0-9]+)?[Li]?', Number.Hex),
+            # decimal number
+            (r'[+-]?([0-9]+(\.[0-9]+)?|\.[0-9]+|\.)([eE][+-]?[0-9]+)?[Li]?',
+             Number),
+        ],
+        'statements': [
+            include('comments'),
+            # whitespaces
+            (r'\s+', Text),
+            (r'\'', String, 'string_squote'),
+            (r'\"', String, 'string_dquote'),
+            include('builtin_symbols'),
+            include('valid_name'),
+            include('numbers'),
+            include('keywords'),
+            include('punctuation'),
+            include('operators'),
+        ],
+        'root': [
+            # calls:
+            (r'(%s)\s*(?=\()' % valid_name, Name.Function),
+            include('statements'),
+            # blocks:
+            (r'\{|\}', Punctuation),
+            # (r'\{', Punctuation, 'block'),
+            (r'.', Text),
+        ],
+        # 'block': [
+        #    include('statements'),
+        #    ('\{', Punctuation, '#push'),
+        #    ('\}', Punctuation, '#pop')
+        # ],
+        'string_squote': [
+            (r'([^\'\\]|\\.)*\'', String, '#pop'),
+        ],
+        'string_dquote': [
+            (r'([^"\\]|\\.)*"', String, '#pop'),
+        ],
+    }
+
+    def analyse_text(text):
+        if re.search(r'[a-z0-9_\])\s]<-(?!-)', text):
+            return 0.11
+
+
+class RdLexer(RegexLexer):
+    """
+    Pygments Lexer for R documentation (Rd) files
+
+    This is a very minimal implementation, highlighting little more
+    than the macros. A description of Rd syntax is found in `Writing R
+    Extensions <http://cran.r-project.org/doc/manuals/R-exts.html>`_
+    and `Parsing Rd files <http://developer.r-project.org/parseRd.pdf>`_.
+
+    .. versionadded:: 1.6
+    """
+    name = 'Rd'
+    aliases = ['rd']
+    filenames = ['*.Rd']
+    mimetypes = ['text/x-r-doc']
+
+    # To account for verbatim / LaTeX-like / and R-like areas
+    # would require parsing.
+    tokens = {
+        'root': [
+            # catch escaped brackets and percent sign
+            (r'\\[\\{}%]', String.Escape),
+            # comments
+            (r'%.*$', Comment),
+            # special macros with no arguments
+            (r'\\(?:cr|l?dots|R|tab)\b', Keyword.Constant),
+            # macros
+            (r'\\[a-zA-Z]+\b', Keyword),
+            # special preprocessor macros
+            (r'^\s*#(?:ifn?def|endif).*\b', Comment.Preproc),
+            # non-escaped brackets
+            (r'[{}]', Name.Builtin),
+            # everything else
+            (r'[^\\%\n{}]+', Text),
+            (r'.', Text),
+        ]
+    }

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

@@ -0,0 +1,463 @@
+# -*- coding: utf-8 -*-
+"""
+    pygments.lexers.rdf
+    ~~~~~~~~~~~~~~~~~~~
+
+    Lexers for semantic web and RDF query languages and markup.
+
+    :copyright: Copyright 2006-2020 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import RegexLexer, bygroups, default
+from pygments.token import Keyword, Punctuation, String, Number, Operator, Generic, \
+    Whitespace, Name, Literal, Comment, Text
+
+__all__ = ['SparqlLexer', 'TurtleLexer', 'ShExCLexer']
+
+
+class SparqlLexer(RegexLexer):
+    """
+    Lexer for `SPARQL <https://www.w3.org/TR/sparql11-query/>`_ query language.
+
+    .. versionadded:: 2.0
+    """
+    name = 'SPARQL'
+    aliases = ['sparql']
+    filenames = ['*.rq', '*.sparql']
+    mimetypes = ['application/sparql-query']
+
+    # character group definitions ::
+
+    PN_CHARS_BASE_GRP = ('a-zA-Z'
+                         '\u00c0-\u00d6'
+                         '\u00d8-\u00f6'
+                         '\u00f8-\u02ff'
+                         '\u0370-\u037d'
+                         '\u037f-\u1fff'
+                         '\u200c-\u200d'
+                         '\u2070-\u218f'
+                         '\u2c00-\u2fef'
+                         '\u3001-\ud7ff'
+                         '\uf900-\ufdcf'
+                         '\ufdf0-\ufffd')
+
+    PN_CHARS_U_GRP = (PN_CHARS_BASE_GRP + '_')
+
+    PN_CHARS_GRP = (PN_CHARS_U_GRP +
+                    r'\-' +
+                    r'0-9' +
+                    '\u00b7' +
+                    '\u0300-\u036f' +
+                    '\u203f-\u2040')
+
+    HEX_GRP = '0-9A-Fa-f'
+
+    PN_LOCAL_ESC_CHARS_GRP = r' _~.\-!$&"()*+,;=/?#@%'
+
+    # terminal productions ::
+
+    PN_CHARS_BASE = '[' + PN_CHARS_BASE_GRP + ']'
+
+    PN_CHARS_U = '[' + PN_CHARS_U_GRP + ']'
+
+    PN_CHARS = '[' + PN_CHARS_GRP + ']'
+
+    HEX = '[' + HEX_GRP + ']'
+
+    PN_LOCAL_ESC_CHARS = '[' + PN_LOCAL_ESC_CHARS_GRP + ']'
+
+    IRIREF = r'<(?:[^<>"{}|^`\\\x00-\x20])*>'
+
+    BLANK_NODE_LABEL = '_:[0-9' + PN_CHARS_U_GRP + '](?:[' + PN_CHARS_GRP + \
+                       '.]*' + PN_CHARS + ')?'
+
+    PN_PREFIX = PN_CHARS_BASE + '(?:[' + PN_CHARS_GRP + '.]*' + PN_CHARS + ')?'
+
+    VARNAME = '[0-9' + PN_CHARS_U_GRP + '][' + PN_CHARS_U_GRP + \
+              '0-9\u00b7\u0300-\u036f\u203f-\u2040]*'
+
+    PERCENT = '%' + HEX + HEX
+
+    PN_LOCAL_ESC = r'\\' + PN_LOCAL_ESC_CHARS
+
+    PLX = '(?:' + PERCENT + ')|(?:' + PN_LOCAL_ESC + ')'
+
+    PN_LOCAL = ('(?:[' + PN_CHARS_U_GRP + ':0-9' + ']|' + PLX + ')' +
+                '(?:(?:[' + PN_CHARS_GRP + '.:]|' + PLX + ')*(?:[' +
+                PN_CHARS_GRP + ':]|' + PLX + '))?')
+
+    EXPONENT = r'[eE][+-]?\d+'
+
+    # Lexer token definitions ::
+
+    tokens = {
+        'root': [
+            (r'\s+', Text),
+            # keywords ::
+            (r'(?i)(select|construct|describe|ask|where|filter|group\s+by|minus|'
+             r'distinct|reduced|from\s+named|from|order\s+by|desc|asc|limit|'
+             r'offset|values|bindings|load|into|clear|drop|create|add|move|copy|'
+             r'insert\s+data|delete\s+data|delete\s+where|with|delete|insert|'
+             r'using\s+named|using|graph|default|named|all|optional|service|'
+             r'silent|bind|undef|union|not\s+in|in|as|having|to|prefix|base)\b', Keyword),
+            (r'(a)\b', Keyword),
+            # IRIs ::
+            ('(' + IRIREF + ')', Name.Label),
+            # blank nodes ::
+            ('(' + BLANK_NODE_LABEL + ')', Name.Label),
+            #  # variables ::
+            ('[?$]' + VARNAME, Name.Variable),
+            # prefixed names ::
+            (r'(' + PN_PREFIX + r')?(\:)(' + PN_LOCAL + r')?',
+             bygroups(Name.Namespace, Punctuation, Name.Tag)),
+            # function names ::
+            (r'(?i)(str|lang|langmatches|datatype|bound|iri|uri|bnode|rand|abs|'
+             r'ceil|floor|round|concat|strlen|ucase|lcase|encode_for_uri|'
+             r'contains|strstarts|strends|strbefore|strafter|year|month|day|'
+             r'hours|minutes|seconds|timezone|tz|now|uuid|struuid|md5|sha1|sha256|sha384|'
+             r'sha512|coalesce|if|strlang|strdt|sameterm|isiri|isuri|isblank|'
+             r'isliteral|isnumeric|regex|substr|replace|exists|not\s+exists|'
+             r'count|sum|min|max|avg|sample|group_concat|separator)\b',
+             Name.Function),
+            # boolean literals ::
+            (r'(true|false)', Keyword.Constant),
+            # double literals ::
+            (r'[+\-]?(\d+\.\d*' + EXPONENT + r'|\.?\d+' + EXPONENT + ')', Number.Float),
+            # decimal literals ::
+            (r'[+\-]?(\d+\.\d*|\.\d+)', Number.Float),
+            # integer literals ::
+            (r'[+\-]?\d+', Number.Integer),
+            # operators ::
+            (r'(\|\||&&|=|\*|\-|\+|/|!=|<=|>=|!|<|>)', Operator),
+            # punctuation characters ::
+            (r'[(){}.;,:^\[\]]', Punctuation),
+            # line comments ::
+            (r'#[^\n]*', Comment),
+            # strings ::
+            (r'"""', String, 'triple-double-quoted-string'),
+            (r'"', String, 'single-double-quoted-string'),
+            (r"'''", String, 'triple-single-quoted-string'),
+            (r"'", String, 'single-single-quoted-string'),
+        ],
+        'triple-double-quoted-string': [
+            (r'"""', String, 'end-of-string'),
+            (r'[^\\]+', String),
+            (r'\\', String, 'string-escape'),
+        ],
+        'single-double-quoted-string': [
+            (r'"', String, 'end-of-string'),
+            (r'[^"\\\n]+', String),
+            (r'\\', String, 'string-escape'),
+        ],
+        'triple-single-quoted-string': [
+            (r"'''", String, 'end-of-string'),
+            (r'[^\\]+', String),
+            (r'\\', String.Escape, 'string-escape'),
+        ],
+        'single-single-quoted-string': [
+            (r"'", String, 'end-of-string'),
+            (r"[^'\\\n]+", String),
+            (r'\\', String, 'string-escape'),
+        ],
+        'string-escape': [
+            (r'u' + HEX + '{4}', String.Escape, '#pop'),
+            (r'U' + HEX + '{8}', String.Escape, '#pop'),
+            (r'.', String.Escape, '#pop'),
+        ],
+        'end-of-string': [
+            (r'(@)([a-zA-Z]+(?:-[a-zA-Z0-9]+)*)',
+             bygroups(Operator, Name.Function), '#pop:2'),
+            (r'\^\^', Operator, '#pop:2'),
+            default('#pop:2'),
+        ],
+    }
+
+
+class TurtleLexer(RegexLexer):
+    """
+    Lexer for `Turtle <http://www.w3.org/TR/turtle/>`_ data language.
+
+    .. versionadded:: 2.1
+    """
+    name = 'Turtle'
+    aliases = ['turtle']
+    filenames = ['*.ttl']
+    mimetypes = ['text/turtle', 'application/x-turtle']
+
+    # character group definitions ::
+    PN_CHARS_BASE_GRP = ('a-zA-Z'
+                         '\u00c0-\u00d6'
+                         '\u00d8-\u00f6'
+                         '\u00f8-\u02ff'
+                         '\u0370-\u037d'
+                         '\u037f-\u1fff'
+                         '\u200c-\u200d'
+                         '\u2070-\u218f'
+                         '\u2c00-\u2fef'
+                         '\u3001-\ud7ff'
+                         '\uf900-\ufdcf'
+                         '\ufdf0-\ufffd')
+
+    PN_CHARS_U_GRP = (PN_CHARS_BASE_GRP + '_')
+
+    PN_CHARS_GRP = (PN_CHARS_U_GRP +
+                    r'\-' +
+                    r'0-9' +
+                    '\u00b7' +
+                    '\u0300-\u036f' +
+                    '\u203f-\u2040')
+
+    PN_CHARS = '[' + PN_CHARS_GRP + ']'
+
+    PN_CHARS_BASE = '[' + PN_CHARS_BASE_GRP + ']'
+
+    PN_PREFIX = PN_CHARS_BASE + '(?:[' + PN_CHARS_GRP + '.]*' + PN_CHARS + ')?'
+
+    HEX_GRP = '0-9A-Fa-f'
+
+    HEX = '[' + HEX_GRP + ']'
+
+    PERCENT = '%' + HEX + HEX
+
+    PN_LOCAL_ESC_CHARS_GRP = r' _~.\-!$&"()*+,;=/?#@%'
+
+    PN_LOCAL_ESC_CHARS = '[' + PN_LOCAL_ESC_CHARS_GRP + ']'
+
+    PN_LOCAL_ESC = r'\\' + PN_LOCAL_ESC_CHARS
+
+    PLX = '(?:' + PERCENT + ')|(?:' + PN_LOCAL_ESC + ')'
+
+    PN_LOCAL = ('(?:[' + PN_CHARS_U_GRP + ':0-9' + ']|' + PLX + ')' +
+                '(?:(?:[' + PN_CHARS_GRP + '.:]|' + PLX + ')*(?:[' +
+                PN_CHARS_GRP + ':]|' + PLX + '))?')
+
+    patterns = {
+        'PNAME_NS': r'((?:[a-zA-Z][\w-]*)?\:)',  # Simplified character range
+        'IRIREF': r'(<[^<>"{}|^`\\\x00-\x20]*>)'
+    }
+
+    tokens = {
+        'root': [
+            (r'\s+', Text),
+
+            # Base / prefix
+            (r'(@base|BASE)(\s+)%(IRIREF)s(\s*)(\.?)' % patterns,
+             bygroups(Keyword, Whitespace, Name.Variable, Whitespace,
+                      Punctuation)),
+            (r'(@prefix|PREFIX)(\s+)%(PNAME_NS)s(\s+)%(IRIREF)s(\s*)(\.?)' % patterns,
+             bygroups(Keyword, Whitespace, Name.Namespace, Whitespace,
+                      Name.Variable, Whitespace, Punctuation)),
+
+            # The shorthand predicate 'a'
+            (r'(?<=\s)a(?=\s)', Keyword.Type),
+
+            # IRIREF
+            (r'%(IRIREF)s' % patterns, Name.Variable),
+
+            # PrefixedName
+            (r'(' + PN_PREFIX + r')?(\:)(' + PN_LOCAL + r')?',
+             bygroups(Name.Namespace, Punctuation, Name.Tag)),
+
+            # Comment
+            (r'#[^\n]+', Comment),
+
+            (r'\b(true|false)\b', Literal),
+            (r'[+\-]?\d*\.\d+', Number.Float),
+            (r'[+\-]?\d*(:?\.\d+)?E[+\-]?\d+', Number.Float),
+            (r'[+\-]?\d+', Number.Integer),
+            (r'[\[\](){}.;,:^]', Punctuation),
+
+            (r'"""', String, 'triple-double-quoted-string'),
+            (r'"', String, 'single-double-quoted-string'),
+            (r"'''", String, 'triple-single-quoted-string'),
+            (r"'", String, 'single-single-quoted-string'),
+        ],
+        'triple-double-quoted-string': [
+            (r'"""', String, 'end-of-string'),
+            (r'[^\\]+', String),
+            (r'\\', String, 'string-escape'),
+        ],
+        'single-double-quoted-string': [
+            (r'"', String, 'end-of-string'),
+            (r'[^"\\\n]+', String),
+            (r'\\', String, 'string-escape'),
+        ],
+        'triple-single-quoted-string': [
+            (r"'''", String, 'end-of-string'),
+            (r'[^\\]+', String),
+            (r'\\', String, 'string-escape'),
+        ],
+        'single-single-quoted-string': [
+            (r"'", String, 'end-of-string'),
+            (r"[^'\\\n]+", String),
+            (r'\\', String, 'string-escape'),
+        ],
+        'string-escape': [
+            (r'.', String, '#pop'),
+        ],
+        'end-of-string': [
+            (r'(@)([a-zA-Z]+(?:-[a-zA-Z0-9]+)*)',
+             bygroups(Operator, Generic.Emph), '#pop:2'),
+
+            (r'(\^\^)%(IRIREF)s' % patterns, bygroups(Operator, Generic.Emph), '#pop:2'),
+
+            default('#pop:2'),
+
+        ],
+    }
+
+    # Turtle and Tera Term macro files share the same file extension
+    # but each has a recognizable and distinct syntax.
+    def analyse_text(text):
+        for t in ('@base ', 'BASE ', '@prefix ', 'PREFIX '):
+            if re.search(r'^\s*%s' % t, text):
+                return 0.80
+
+
+class ShExCLexer(RegexLexer):
+    """
+    Lexer for `ShExC <https://shex.io/shex-semantics/#shexc>`_ shape expressions language syntax.
+    """
+    name = 'ShExC'
+    aliases = ['shexc', 'shex']
+    filenames = ['*.shex']
+    mimetypes = ['text/shex']
+
+    # character group definitions ::
+
+    PN_CHARS_BASE_GRP = ('a-zA-Z'
+                         '\u00c0-\u00d6'
+                         '\u00d8-\u00f6'
+                         '\u00f8-\u02ff'
+                         '\u0370-\u037d'
+                         '\u037f-\u1fff'
+                         '\u200c-\u200d'
+                         '\u2070-\u218f'
+                         '\u2c00-\u2fef'
+                         '\u3001-\ud7ff'
+                         '\uf900-\ufdcf'
+                         '\ufdf0-\ufffd')
+
+    PN_CHARS_U_GRP = (PN_CHARS_BASE_GRP + '_')
+
+    PN_CHARS_GRP = (PN_CHARS_U_GRP +
+                    r'\-' +
+                    r'0-9' +
+                    '\u00b7' +
+                    '\u0300-\u036f' +
+                    '\u203f-\u2040')
+
+    HEX_GRP = '0-9A-Fa-f'
+
+    PN_LOCAL_ESC_CHARS_GRP = r"_~.\-!$&'()*+,;=/?#@%"
+
+    # terminal productions ::
+
+    PN_CHARS_BASE = '[' + PN_CHARS_BASE_GRP + ']'
+
+    PN_CHARS_U = '[' + PN_CHARS_U_GRP + ']'
+
+    PN_CHARS = '[' + PN_CHARS_GRP + ']'
+
+    HEX = '[' + HEX_GRP + ']'
+
+    PN_LOCAL_ESC_CHARS = '[' + PN_LOCAL_ESC_CHARS_GRP + ']'
+
+    UCHAR_NO_BACKSLASH = '(?:u' + HEX + '{4}|U' + HEX + '{8})'
+
+    UCHAR = r'\\' + UCHAR_NO_BACKSLASH
+
+    IRIREF = r'<(?:[^\x00-\x20<>"{}|^`\\]|' + UCHAR + ')*>'
+
+    BLANK_NODE_LABEL = '_:[0-9' + PN_CHARS_U_GRP + '](?:[' + PN_CHARS_GRP + \
+                       '.]*' + PN_CHARS + ')?'
+
+    PN_PREFIX = PN_CHARS_BASE + '(?:[' + PN_CHARS_GRP + '.]*' + PN_CHARS + ')?'
+
+    PERCENT = '%' + HEX + HEX
+
+    PN_LOCAL_ESC = r'\\' + PN_LOCAL_ESC_CHARS
+
+    PLX = '(?:' + PERCENT + ')|(?:' + PN_LOCAL_ESC + ')'
+
+    PN_LOCAL = ('(?:[' + PN_CHARS_U_GRP + ':0-9' + ']|' + PLX + ')' +
+                '(?:(?:[' + PN_CHARS_GRP + '.:]|' + PLX + ')*(?:[' +
+                PN_CHARS_GRP + ':]|' + PLX + '))?')
+
+    EXPONENT = r'[eE][+-]?\d+'
+
+    # Lexer token definitions ::
+
+    tokens = {
+        'root': [
+            (r'\s+', Text),
+            # keywords ::
+            (r'(?i)(base|prefix|start|external|'
+             r'literal|iri|bnode|nonliteral|length|minlength|maxlength|'
+             r'mininclusive|minexclusive|maxinclusive|maxexclusive|'
+             r'totaldigits|fractiondigits|'
+             r'closed|extra)\b', Keyword),
+            (r'(a)\b', Keyword),
+            # IRIs ::
+            ('(' + IRIREF + ')', Name.Label),
+            # blank nodes ::
+            ('(' + BLANK_NODE_LABEL + ')', Name.Label),
+            # prefixed names ::
+            (r'(' + PN_PREFIX + r')?(\:)(' + PN_LOCAL + ')?',
+             bygroups(Name.Namespace, Punctuation, Name.Tag)),
+            # boolean literals ::
+            (r'(true|false)', Keyword.Constant),
+            # double literals ::
+            (r'[+\-]?(\d+\.\d*' + EXPONENT + r'|\.?\d+' + EXPONENT + ')', Number.Float),
+            # decimal literals ::
+            (r'[+\-]?(\d+\.\d*|\.\d+)', Number.Float),
+            # integer literals ::
+            (r'[+\-]?\d+', Number.Integer),
+            # operators ::
+            (r'[@|$&=*+?^\-~]', Operator),
+            # operator keywords ::
+            (r'(?i)(and|or|not)\b', Operator.Word),
+            # punctuation characters ::
+            (r'[(){}.;,:^\[\]]', Punctuation),
+            # line comments ::
+            (r'#[^\n]*', Comment),
+            # strings ::
+            (r'"""', String, 'triple-double-quoted-string'),
+            (r'"', String, 'single-double-quoted-string'),
+            (r"'''", String, 'triple-single-quoted-string'),
+            (r"'", String, 'single-single-quoted-string'),
+        ],
+        'triple-double-quoted-string': [
+            (r'"""', String, 'end-of-string'),
+            (r'[^\\]+', String),
+            (r'\\', String, 'string-escape'),
+        ],
+        'single-double-quoted-string': [
+            (r'"', String, 'end-of-string'),
+            (r'[^"\\\n]+', String),
+            (r'\\', String, 'string-escape'),
+        ],
+        'triple-single-quoted-string': [
+            (r"'''", String, 'end-of-string'),
+            (r'[^\\]+', String),
+            (r'\\', String.Escape, 'string-escape'),
+        ],
+        'single-single-quoted-string': [
+            (r"'", String, 'end-of-string'),
+            (r"[^'\\\n]+", String),
+            (r'\\', String, 'string-escape'),
+        ],
+        'string-escape': [
+            (UCHAR_NO_BACKSLASH, String.Escape, '#pop'),
+            (r'.', String.Escape, '#pop'),
+        ],
+        'end-of-string': [
+            (r'(@)([a-zA-Z]+(?:-[a-zA-Z0-9]+)*)',
+             bygroups(Operator, Name.Function), '#pop:2'),
+            (r'\^\^', Operator, '#pop:2'),
+            default('#pop:2'),
+        ],
+    }