ecr.ui.helper.BashLexer

src/ecr/ui/helper/BashLexer.py
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
# pylint: disable=W0611,E0213,E1101,R1710
import re

from pygments.lexer import Lexer, RegexLexer, do_insertions, bygroups, \
    include, default, this, using, words
from pygments.token import Punctuation, \
    Text, Comment, Operator, Keyword, Name, String, Number, Generic
from pygments.util import shebang_matches


class BashLexer(RegexLexer):
    """
    Lexer for (ba|k|z|)sh shell scripts.

    .. versionadded:: 0.6
    """

    name = 'Bash'
    aliases = ['bash', 'sh', 'ksh', 'zsh', 'shell']
    filenames = ['*.sh', '*.ksh', '*.bash', '*.ebuild', '*.eclass',
                 '*.exheres-0', '*.exlib', '*.zsh',
                 '.bashrc', 'bashrc', '.bash_*', 'bash_*', 'zshrc', '.zshrc',
                 'PKGBUILD']
    mimetypes = ['application/x-sh', 'application/x-shellscript']

    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|do|done|for|then|return|function|case|'
            #  r'select|continue|until|esac|elif)(\s*)\b',
            #  bygroups(Keyword, Text)),
            (r'\b(init|clear|new|now|edit|run|test|clean|pwd|cd|'
             r'version|cls|exit|debug|status|template|reload|show)', # (?=[\s)`])
             Name.Builtin),
            (r'\A#!.+\n', Comment.Hashbang),
            (r'#.*\n', Comment.Single),
            (r'\\[\w\W]', String.Escape),
            (r'(\b\w+)(\s*)(\+?=)', bygroups(Name.Variable, Text, Operator)),
            (r'[\[\]{}()=]', Operator),
            (r'<<<', Operator),  # here-string
            (r'<<-?\s*(\'?)\\?(\w+)[\w\W]+?\2', String),
            (r'&&|\|\|', Operator),
        ],
        'data': [
            (r'(?s)\$?"(\\\\|\\[0-7]+|\\.|[^"\\$])*"', String.Double),
            (r'"', String.Double, 'string'),
            (r"(?s)\$'(\\\\|\\[0-7]+|\\.|[^'\\])*'", String.Single),
            (r"(?s)'.*?'", String.Single),
            (r';', Punctuation),
            (r'&', Punctuation),
            (r'\|', Punctuation),
            (r'\s+', Text),
            (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+#\d+', Number),
            (r'\d+#(?! )', Number),
            (r'\d+', Number),
            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