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
|
#!/usr/bin/env python3
'''Add syntax highlighting to Python source code
Example command-line calls:
# Show syntax highlighted code in the terminal window
$ ./highlight.py myfile.py
# Colorize myfile.py and display in a browser
$ ./highlight.py -b myfile.py
# Create an HTML section that can be embedded in an existing webpage
./highlight.py -s myfile.py
# Create a complete HTML file
$ ./highlight.py -c myfile.py > myfile.html
'''
__all__ = ['colorize_html', 'build_page', 'default_css', 'default_html',
'colorize_ansi', 'default_ansi']
__author__ = 'Raymond Hettinger'
import keyword, tokenize, cgi, functools
def is_builtin(s):
'Return True if s is the name of a builtin'
return s in vars(__builtins__)
def combine_range(lines, start, end):
'Join content from a range of lines between start and end'
(srow, scol), (erow, ecol) = start, end
if srow == erow:
rows = [lines[srow-1][scol:ecol]]
else:
rows = [lines[srow-1][scol:]] + lines[srow: erow-1] + [lines[erow-1][:ecol]]
return ''.join(rows), end
def isolate_tokens(source):
'Generate chunks of source and identify chunks to be highlighted'
lines = source.splitlines(True)
lines.append('')
readline = functools.partial(next, iter(lines), '')
kind = tok_str = ''
tok_type = tokenize.COMMENT
written = (1, 0)
for tok in tokenize.generate_tokens(readline):
prev_tok_type, prev_tok_str = tok_type, tok_str
tok_type, tok_str, (srow, scol), (erow, ecol), logical_lineno = tok
kind = ''
if tok_type == tokenize.COMMENT:
kind = 'comment'
elif tok_type == tokenize.OP and tok_str[:1] not in '{}[](),.:;':
kind = 'operator'
elif tok_type == tokenize.STRING:
kind = 'string'
if prev_tok_type == tokenize.INDENT or scol==0:
kind = 'docstring'
elif tok_type == tokenize.NAME:
if tok_str in ('def', 'class', 'import', 'from'):
kind = 'definition'
elif prev_tok_str in ('def', 'class'):
kind = 'defname'
elif keyword.iskeyword(tok_str):
kind = 'keyword'
elif is_builtin(tok_str) and prev_tok_str != '.':
kind = 'builtin'
line_upto_token, written = combine_range(lines, written, (srow, scol))
line_thru_token, written = combine_range(lines, written, (erow, ecol))
yield kind, line_upto_token, line_thru_token
default_ansi = {
'comment': '\033[0;31m',
'string': '\033[0;32m',
'docstring': '\033[0;32m',
'keyword': '\033[0;33m',
'builtin': '\033[0;35m',
'definition': '\033[0;33m',
'defname': '\033[0;34m',
'operator': '\033[0;33m',
}
def colorize_ansi(source, colors=default_ansi):
'Add syntax highlighting to Python source code using ANSI escape sequences'
# http://en.wikipedia.org/wiki/ANSI_escape_code
result = []
for kind, line_upto_token, line_thru_token in isolate_tokens(source):
if kind:
result += [line_upto_token, colors[kind], line_thru_token, '\033[0m']
else:
result += [line_upto_token, line_thru_token]
return ''.join(result)
def colorize_html(source):
'Convert Python source code to an HTML fragment with colorized markup'
result = ['<pre class="python">\n']
for kind, line_upto_token, line_thru_token in isolate_tokens(source):
if kind:
result += [cgi.escape(line_upto_token),
'<span class="%s">' % kind,
cgi.escape(line_thru_token),
'</span>']
else:
result += [cgi.escape(line_upto_token),
cgi.escape(line_thru_token)]
result += ['</pre>\n']
return ''.join(result)
default_css = {
'.comment': '{color: crimson;}',
'.string': '{color: forestgreen;}',
'.docstring': '{color: forestgreen; font-style:italic;}',
'.keyword': '{color: darkorange;}',
'.builtin': '{color: purple;}',
'.definition': '{color: darkorange; font-weight:bold;}',
'.defname': '{color: blue;}',
'.operator': '{color: brown;}',
}
default_html = '''\
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
"http://www.w3.org/TR/html4/strict.dtd">
<html>
<head>
<meta http-equiv="Content-type" content="text/html;charset=UTF-8">
<title> {title} </title>
<style type="text/css">
{css}
</style>
</head>
<body>
{body}
</body>
</html>
'''
def build_page(source, title='python', css=default_css, html=default_html):
'Create a complete HTML page with colorized Python source code'
css_str = '\n'.join(['%s %s' % item for item in css.items()])
result = colorize_html(source)
title = cgi.escape(title)
return html.format(title=title, css=css_str, body=result)
if __name__ == '__main__':
import sys, argparse, webbrowser, os
parser = argparse.ArgumentParser(
description = 'Add syntax highlighting to Python source')
parser.add_argument('sourcefile', metavar = 'SOURCEFILE',
help = 'File containing Python sourcecode')
parser.add_argument('-b', '--browser', action = 'store_true',
help = 'launch a browser to show results')
parser.add_argument('-c', '--complete', action = 'store_true',
help = 'build a complete html webpage')
parser.add_argument('-s', '--section', action = 'store_true',
help = 'show an HTML section rather than a complete webpage')
args = parser.parse_args()
if args.section and (args.browser or args.complete):
parser.error('The -s/--section option is incompatible with '
'the -b/--browser or -c/--complete options')
sourcefile = args.sourcefile
with open(sourcefile) as f:
source = f.read()
if args.complete or args.browser:
encoded = build_page(source, title=sourcefile)
elif args.section:
encoded = colorize_html(source)
else:
encoded = colorize_ansi(source)
if args.browser:
htmlfile = os.path.splitext(os.path.basename(sourcefile))[0] + '.html'
with open(htmlfile, 'w') as f:
f.write(encoded)
webbrowser.open('file://' + os.path.abspath(htmlfile))
else:
sys.stdout.write(encoded)
|
