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
|
"""
pygments.lexers.ezhil
~~~~~~~~~~~~~~~~~~~~~
Pygments lexers for Ezhil language.
:copyright: Copyright 2006-2024 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 Keyword, Comment, Name, String, Number, \
Punctuation, Operator, Whitespace
__all__ = ['EzhilLexer']
class EzhilLexer(RegexLexer):
"""
Lexer for Ezhil, a Tamil script-based programming language.
"""
name = 'Ezhil'
url = 'http://ezhillang.org'
aliases = ['ezhil']
filenames = ['*.n']
mimetypes = ['text/x-ezhil']
version_added = '2.1'
# Refer to tamil.utf8.tamil_letters from open-tamil for a stricter version of this.
# This much simpler version is close enough, and includes combining marks.
_TALETTERS = '[a-zA-Z_]|[\u0b80-\u0bff]'
tokens = {
'root': [
include('keywords'),
(r'#.*$', Comment.Single),
(r'[@+/*,^\-%]|[!<>=]=?|&&?|\|\|?', Operator),
('இல்', Operator.Word),
(words(('assert', 'max', 'min',
'நீளம்', 'சரம்_இடமாற்று', 'சரம்_கண்டுபிடி',
'பட்டியல்', 'பின்இணை', 'வரிசைப்படுத்து',
'எடு', 'தலைகீழ்', 'நீட்டிக்க', 'நுழைக்க', 'வை',
'கோப்பை_திற', 'கோப்பை_எழுது', 'கோப்பை_மூடு',
'pi', 'sin', 'cos', 'tan', 'sqrt', 'hypot', 'pow',
'exp', 'log', 'log10', 'exit',
), suffix=r'\b'), Name.Builtin),
(r'(True|False)\b', Keyword.Constant),
(r'[^\S\n]+', Whitespace),
include('identifier'),
include('literal'),
(r'[(){}\[\]:;.]', Punctuation),
],
'keywords': [
('பதிப்பி|தேர்ந்தெடு|தேர்வு|ஏதேனில்|ஆனால்|இல்லைஆனால்|இல்லை|ஆக|ஒவ்வொன்றாக|இல்|வரை|செய்|முடியேனில்|பின்கொடு|முடி|நிரல்பாகம்|தொடர்|நிறுத்து|நிரல்பாகம்', Keyword),
],
'identifier': [
('(?:'+_TALETTERS+')(?:[0-9]|'+_TALETTERS+')*', Name),
],
'literal': [
(r'".*?"', String),
(r'\d+((\.\d*)?[eE][+-]?\d+|\.\d*)', Number.Float),
(r'\d+', Number.Integer),
]
}
def analyse_text(text):
"""This language uses Tamil-script. We'll assume that if there's a
decent amount of Tamil-characters, it's this language. This assumption
is obviously horribly off if someone uses string literals in tamil
in another language."""
if len(re.findall(r'[\u0b80-\u0bff]', text)) > 10:
return 0.25
def __init__(self, **options):
super().__init__(**options)
self.encoding = options.get('encoding', 'utf-8')
|
