Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Commit 42a5f4a

Browse files
rhettingerrhettinger
committed
Minor algorithmic tweaks, better factoring, improved docstrings and variable names
1 parent dd445e8 commit 42a5f4a

1 file changed

Lines changed: 62 additions & 55 deletions

File tree

‎Tools/scripts/highlight.py‎

Lines changed: 62 additions & 55 deletions
Original file line numberDiff line numberDiff line change
@@ -1,24 +1,9 @@
11
#!/usr/bin/env python3
2-
'''Add syntax highlighting to Python source code
2+
'''Add syntax highlighting to Python source code'''
33

4-
Example command-line calls:
4+
__all__ = ['analyze_python', 'ansi_highlight', 'default_ansi',
5+
'html_highlight', 'build_html_page', 'default_css', 'default_html']
56

6-
# Show syntax highlighted code in the terminal window
7-
$ ./highlight.py myfile.py
8-
9-
# Colorize myfile.py and display in a browser
10-
$ ./highlight.py -b myfile.py
11-
12-
# Create an HTML section that can be embedded in an existing webpage
13-
./highlight.py -s myfile.py
14-
15-
# Create a complete HTML file
16-
$ ./highlight.py -c myfile.py > myfile.html
17-
18-
'''
19-
20-
__all__ = ['colorize_html', 'build_page', 'default_css', 'default_html',
21-
'colorize_ansi', 'default_ansi']
227
__author__ = 'Raymond Hettinger'
238

249
import keyword, tokenize, cgi, functools
@@ -31,13 +16,16 @@ def combine_range(lines, start, end):
3116
'Join content from a range of lines between start and end'
3217
(srow, scol), (erow, ecol) = start, end
3318
if srow == erow:
34-
rows = [lines[srow-1][scol:ecol]]
35-
else:
36-
rows = [lines[srow-1][scol:]] + lines[srow: erow-1] + [lines[erow-1][:ecol]]
19+
return lines[srow-1][scol:ecol], end
20+
rows = [lines[srow-1][scol:]] + lines[srow: erow-1] + [lines[erow-1][:ecol]]
3721
return ''.join(rows), end
3822

39-
def isolate_tokens(source):
40-
'Generate chunks of source and identify chunks to be highlighted'
23+
def analyze_python(source):
24+
'''Generate and classify chunks of Python for syntax highlighting.
25+
Yields tuples in the form: (leadin_text, category, categorized_text).
26+
The final tuple has empty strings for the category and categorized text.
27+
28+
'''
4129
lines = source.splitlines(True)
4230
lines.append('')
4331
readline = functools.partial(next, iter(lines), '')
@@ -65,36 +53,37 @@ def isolate_tokens(source):
6553
kind = 'keyword'
6654
elif is_builtin(tok_str) and prev_tok_str != '.':
6755
kind = 'builtin'
68-
line_upto_token, written = combine_range(lines, written, (srow, scol))
69-
line_thru_token, written = combine_range(lines, written, (erow, ecol))
70-
yield kind, line_upto_token, line_thru_token
56+
if kind:
57+
line_upto_token, written = combine_range(lines, written, (srow, scol))
58+
line_thru_token, written = combine_range(lines, written, (erow, ecol))
59+
yield line_upto_token, kind, line_thru_token
60+
line_upto_token, written = combine_range(lines, written, (erow, ecol))
61+
yield line_upto_token, '', ''
7162

7263
default_ansi = {
73-
'comment': '\033[0;31m',
74-
'string': '\033[0;32m',
75-
'docstring': '\033[0;32m',
76-
'keyword': '\033[0;33m',
77-
'builtin': '\033[0;35m',
78-
'definition': '\033[0;33m',
79-
'defname': '\033[0;34m',
80-
'operator': '\033[0;33m',
64+
'comment': ('\033[0;31m', '\033[0m'),
65+
'string': ('\033[0;32m', '\033[0m'),
66+
'docstring': ('\033[0;32m', '\033[0m'),
67+
'keyword': ('\033[0;33m', '\033[0m'),
68+
'builtin': ('\033[0;35m', '\033[0m'),
69+
'definition': ('\033[0;33m', '\033[0m'),
70+
'defname': ('\033[0;34m', '\033[0m'),
71+
'operator': ('\033[0;33m', '\033[0m'),
8172
}
8273

83-
def colorize_ansi(source, colors=default_ansi):
84-
'Add syntax highlighting to Python source code using ANSI escape sequences'
74+
def ansi_highlight(classified_text, colors=default_ansi):
75+
'Add syntax highlighting to source code using ANSI escape sequences'
8576
# http://en.wikipedia.org/wiki/ANSI_escape_code
8677
result = []
87-
for kind, line_upto_token, line_thru_token in isolate_tokens(source):
88-
if kind:
89-
result += [line_upto_token, colors[kind], line_thru_token, '\033[0m']
90-
else:
91-
result += [line_upto_token, line_thru_token]
78+
for line_upto_token, kind, line_thru_token in classified_text:
79+
opener, closer = colors.get(kind, ('', ''))
80+
result += [line_upto_token, opener, line_thru_token, closer]
9281
return ''.join(result)
9382

94-
def colorize_html(source):
95-
'Convert Python source code to an HTML fragment with colorized markup'
96-
result = ['<pre class="python">\n']
97-
for kind, line_upto_token, line_thru_token in isolate_tokens(source):
83+
def html_highlight(classified_text,opener='<pre class="python">\n', closer='</pre>\n'):
84+
'Convert classified text to an HTML fragment'
85+
result = [opener]
86+
for line_upto_token, kind, line_thru_token in classified_text:
9887
if kind:
9988
result += [cgi.escape(line_upto_token),
10089
'<span class="%s">' % kind,
@@ -103,7 +92,7 @@ def colorize_html(source):
10392
else:
10493
result += [cgi.escape(line_upto_token),
10594
cgi.escape(line_thru_token)]
106-
result += ['</pre>\n']
95+
result += [closer]
10796
return ''.join(result)
10897

10998
default_css = {
@@ -134,21 +123,38 @@ def colorize_html(source):
134123
</html>
135124
'''
136125

137-
def build_page(source, title='python', css=default_css, html=default_html):
138-
'Create a complete HTML page with colorized Python source code'
126+
def build_html_page(classified_text, title='python',
127+
css=default_css, html=default_html):
128+
'Create a complete HTML page with colorized source code'
139129
css_str = '\n'.join(['%s %s' % item for item in css.items()])
140-
result = colorize_html(source)
130+
result = html_highlight(classified_text)
141131
title = cgi.escape(title)
142132
return html.format(title=title, css=css_str, body=result)
143133

144134

145135
if __name__ == '__main__':
146-
import sys, argparse, webbrowser, os
136+
import sys, argparse, webbrowser, os, textwrap
147137

148138
parser = argparse.ArgumentParser(
149-
description = 'Add syntax highlighting to Python source')
139+
description = 'Add syntax highlighting to Python source code',
140+
formatter_class=argparse.RawDescriptionHelpFormatter,
141+
epilog = textwrap.dedent('''
142+
examples:
143+
144+
# Show syntax highlighted code in the terminal window
145+
$ ./highlight.py myfile.py
146+
147+
# Colorize myfile.py and display in a browser
148+
$ ./highlight.py -b myfile.py
149+
150+
# Create an HTML section to embed in an existing webpage
151+
./highlight.py -s myfile.py
152+
153+
# Create a complete HTML file
154+
$ ./highlight.py -c myfile.py > myfile.html
155+
'''))
150156
parser.add_argument('sourcefile', metavar = 'SOURCEFILE',
151-
help = 'File containing Python sourcecode')
157+
help = 'file containing Python sourcecode')
152158
parser.add_argument('-b', '--browser', action = 'store_true',
153159
help = 'launch a browser to show results')
154160
parser.add_argument('-c', '--complete', action = 'store_true',
@@ -164,13 +170,14 @@ def build_page(source, title='python', css=default_css, html=default_html):
164170
sourcefile = args.sourcefile
165171
with open(sourcefile) as f:
166172
source = f.read()
173+
classified_text = analyze_python(source)
167174

168175
if args.complete or args.browser:
169-
encoded = build_page(source, title=sourcefile)
176+
encoded = build_html_page(classified_text, title=sourcefile)
170177
elif args.section:
171-
encoded = colorize_html(source)
178+
encoded = html_highlight(classified_text)
172179
else:
173-
encoded = colorize_ansi(source)
180+
encoded = ansi_highlight(classified_text)
174181

175182
if args.browser:
176183
htmlfile = os.path.splitext(os.path.basename(sourcefile))[0] + '.html'

0 commit comments

Comments
 (0)