1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
"""
    pygments.lexers.urbi
    ~~~~~~~~~~~~~~~~~~~~

    Lexers for UrbiScript language.

    :copyright: Copyright 2006-2022 by the Pygments team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

import re

from pygments.lexer import ExtendedRegexLexer, words
from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
    Number, Punctuation

__all__ = ['UrbiscriptLexer']


class UrbiscriptLexer(ExtendedRegexLexer):
    """
    For UrbiScript source code.

    .. versionadded:: 1.5
    """

    name = 'UrbiScript'
    aliases = ['urbiscript']
    filenames = ['*.u']
    mimetypes = ['application/x-urbiscript']

    flags = re.DOTALL

    # TODO
    # - handle Experimental and deprecated tags with specific tokens
    # - handle Angles and Durations with specific tokens

    def blob_callback(lexer, match, ctx):
        text_before_blob = match.group(1)
        blob_start = match.group(2)
        blob_size_str = match.group(3)
        blob_size = int(blob_size_str)
        yield match.start(), String, text_before_blob
        ctx.pos += len(text_before_blob)

        # if blob size doesn't match blob format (example : "\B(2)(aaa)")
        # yield blob as a string
        if ctx.text[match.end() + blob_size] != ")":
            result = "\\B(" + blob_size_str + ")("
            yield match.start(), String, result
            ctx.pos += len(result)
            return

        # if blob is well formatted, yield as Escape
        blob_text = blob_start + ctx.text[match.end():match.end()+blob_size] + ")"
        yield match.start(), String.Escape, blob_text
        ctx.pos = match.end() + blob_size + 1  # +1 is the ending ")"

    tokens = {
        'root': [
            (r'\s+', Text),
            # comments
            (r'//.*?\n', Comment),
            (r'/\*', Comment.Multiline, 'comment'),
            (r'(every|for|loop|while)(?:;|&|\||,)', Keyword),
            (words((
                'assert', 'at', 'break', 'case', 'catch', 'closure', 'compl',
                'continue', 'default', 'else', 'enum', 'every', 'external',
                'finally', 'for', 'freezeif', 'if', 'new', 'onleave', 'return',
                'stopif', 'switch', 'this', 'throw', 'timeout', 'try',
                'waituntil', 'whenever', 'while'), suffix=r'\b'),
             Keyword),
            (words((
                'asm', 'auto', 'bool', 'char', 'const_cast', 'delete', 'double',
                'dynamic_cast', 'explicit', 'export', 'extern', 'float', 'friend',
                'goto', 'inline', 'int', 'long', 'mutable', 'namespace', 'register',
                'reinterpret_cast', 'short', 'signed', 'sizeof', 'static_cast',
                'struct', 'template', 'typedef', 'typeid', 'typename', 'union',
                'unsigned', 'using', 'virtual', 'volatile', 'wchar_t'), suffix=r'\b'),
             Keyword.Reserved),
            # deprecated keywords, use a meaningful token when available
            (r'(emit|foreach|internal|loopn|static)\b', Keyword),
            # ignored keywords, use a meaningful token when available
            (r'(private|protected|public)\b', Keyword),
            (r'(var|do|const|function|class)\b', Keyword.Declaration),
            (r'(true|false|nil|void)\b', Keyword.Constant),
            (words((
                'Barrier', 'Binary', 'Boolean', 'CallMessage', 'Channel', 'Code',
                'Comparable', 'Container', 'Control', 'Date', 'Dictionary', 'Directory',
                'Duration', 'Enumeration', 'Event', 'Exception', 'Executable', 'File',
                'Finalizable', 'Float', 'FormatInfo', 'Formatter', 'Global', 'Group',
                'Hash', 'InputStream', 'IoService', 'Job', 'Kernel', 'Lazy', 'List',
                'Loadable', 'Lobby', 'Location', 'Logger', 'Math', 'Mutex', 'nil',
                'Object', 'Orderable', 'OutputStream', 'Pair', 'Path', 'Pattern',
                'Position', 'Primitive', 'Process', 'Profile', 'PseudoLazy', 'PubSub',
                'RangeIterable', 'Regexp', 'Semaphore', 'Server', 'Singleton', 'Socket',
                'StackFrame', 'Stream', 'String', 'System', 'Tag', 'Timeout',
                'Traceable', 'TrajectoryGenerator', 'Triplet', 'Tuple', 'UObject',
                'UValue', 'UVar'), suffix=r'\b'),
             Name.Builtin),
            (r'(?:this)\b', Name.Builtin.Pseudo),
            # don't match single | and &
            (r'(?:[-=+*%/<>~^:]+|\.&?|\|\||&&)', Operator),
            (r'(?:and_eq|and|bitand|bitor|in|not|not_eq|or_eq|or|xor_eq|xor)\b',
             Operator.Word),
            (r'[{}\[\]()]+', Punctuation),
            (r'(?:;|\||,|&|\?|!)+', Punctuation),
            (r'[$a-zA-Z_]\w*', Name.Other),
            (r'0x[0-9a-fA-F]+', Number.Hex),
            # Float, Integer, Angle and Duration
            (r'(?:[0-9]+(?:(?:\.[0-9]+)?(?:[eE][+-]?[0-9]+)?)?'
             r'((?:rad|deg|grad)|(?:ms|s|min|h|d))?)\b', Number.Float),
            # handle binary blob in strings
            (r'"', String.Double, "string.double"),
            (r"'", String.Single, "string.single"),
        ],
        'string.double': [
            (r'((?:\\\\|\\"|[^"])*?)(\\B\((\d+)\)\()', blob_callback),
            (r'(\\\\|\\[^\\]|[^"\\])*?"', String.Double, '#pop'),
        ],
        'string.single': [
            (r"((?:\\\\|\\'|[^'])*?)(\\B\((\d+)\)\()", blob_callback),
            (r"(\\\\|\\[^\\]|[^'\\])*?'", String.Single, '#pop'),
        ],
        # from http://pygments.org/docs/lexerdevelopment/#changing-states
        'comment': [
            (r'[^*/]', Comment.Multiline),
            (r'/\*', Comment.Multiline, '#push'),
            (r'\*/', Comment.Multiline, '#pop'),
            (r'[*/]', Comment.Multiline),
        ]
    }

    def analyse_text(text):
        """This is fairly similar to C and others, but freezeif and
        waituntil are unique keywords."""
        result = 0

        if 'freezeif' in text:
            result += 0.05

        if 'waituntil' in text:
            result += 0.05

        return result