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
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
|
# -*- coding: utf-8 -*-
"""
pygments.lexers.r
~~~~~~~~~~~~~~~~~
Lexers for the R/S languages.
:copyright: Copyright 2006-2019 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.
for item in do_insertions(
insertions, slexer.get_tokens_unprocessed(current_code_block)):
yield item
# 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:
for item in do_insertions(
insertions, slexer.get_tokens_unprocessed(current_code_block)):
yield item
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]|[_.][^0-9])[\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),
]
}
|
