Mercurial > cpython-lru_cache-weakref

annotate Tools/scripts/highlight.py @ 80779:10d04bdb05ab 3.3

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Issue #16248: Disable code execution from the user's home directory by tkinter when the -E flag is passed to Python. Patch by Zachary Ware.
author Antoine Pitrou <solipsis@pitrou.net>
date Sun, 09 Dec 2012 14:46:46 +0100
parents b127046831e2
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
1 #!/usr/bin/env python3
78014
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
2 '''Add syntax highlighting to Python source code'''
77942
1401ff261ced Add examples to the module docstring
Raymond Hettinger <python@rcn.com>
parents: 77941
diff changeset
3
77903
21ca7f56e12c Set title to the source filename
Raymond Hettinger <python@rcn.com>
parents: 77902
diff changeset
4 __author__ = 'Raymond Hettinger'
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
5
78049
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
6 import keyword, tokenize, cgi, re, functools
78079
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
7 try:
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
8 import builtins
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
9 except ImportError:
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
10 import __builtin__ as builtins
78049
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
11
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
12 #### Analyze Python Source #################################
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
13
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
14 def is_builtin(s):
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
15 'Return True if s is the name of a builtin'
78079
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
16 return hasattr(builtins, s)
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
17
77938
1f06fe5cd4da Refactor to isolate HTML encoding step from the parsing step.
Raymond Hettinger <python@rcn.com>
parents: 77929
diff changeset
18 def combine_range(lines, start, end):
1f06fe5cd4da Refactor to isolate HTML encoding step from the parsing step.
Raymond Hettinger <python@rcn.com>
parents: 77929
diff changeset
19 'Join content from a range of lines between start and end'
77918
671894ae19a2 Do HTML escaping after the tokenization step.
Raymond Hettinger <python@rcn.com>
parents: 77904
diff changeset
20 (srow, scol), (erow, ecol) = start, end
671894ae19a2 Do HTML escaping after the tokenization step.
Raymond Hettinger <python@rcn.com>
parents: 77904
diff changeset
21 if srow == erow:
78014
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
22 return lines[srow-1][scol:ecol], end
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
23 rows = [lines[srow-1][scol:]] + lines[srow: erow-1] + [lines[erow-1][:ecol]]
77938
1f06fe5cd4da Refactor to isolate HTML encoding step from the parsing step.
Raymond Hettinger <python@rcn.com>
parents: 77929
diff changeset
24 return ''.join(rows), end
77918
671894ae19a2 Do HTML escaping after the tokenization step.
Raymond Hettinger <python@rcn.com>
parents: 77904
diff changeset
25
78014
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
26 def analyze_python(source):
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
27 '''Generate and classify chunks of Python for syntax highlighting.
78079
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
28 Yields tuples in the form: (category, categorized_text).
78014
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
29 '''
77929
d7bed032520b Fix keyword argument
Raymond Hettinger <python@rcn.com>
parents: 77928
diff changeset
30 lines = source.splitlines(True)
77918
671894ae19a2 Do HTML escaping after the tokenization step.
Raymond Hettinger <python@rcn.com>
parents: 77904
diff changeset
31 lines.append('')
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
32 readline = functools.partial(next, iter(lines), '')
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
33 kind = tok_str = ''
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
34 tok_type = tokenize.COMMENT
77918
671894ae19a2 Do HTML escaping after the tokenization step.
Raymond Hettinger <python@rcn.com>
parents: 77904
diff changeset
35 written = (1, 0)
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
36 for tok in tokenize.generate_tokens(readline):
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
37 prev_tok_type, prev_tok_str = tok_type, tok_str
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
38 tok_type, tok_str, (srow, scol), (erow, ecol), logical_lineno = tok
77928
4d320cd4c6fe Minor cleanups
Raymond Hettinger <python@rcn.com>
parents: 77920
diff changeset
39 kind = ''
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
40 if tok_type == tokenize.COMMENT:
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
41 kind = 'comment'
78079
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
42 elif tok_type == tokenize.OP and tok_str[:1] not in '{}[](),.:;@':
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
43 kind = 'operator'
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
44 elif tok_type == tokenize.STRING:
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
45 kind = 'string'
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
46 if prev_tok_type == tokenize.INDENT or scol==0:
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
47 kind = 'docstring'
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
48 elif tok_type == tokenize.NAME:
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
49 if tok_str in ('def', 'class', 'import', 'from'):
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
50 kind = 'definition'
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
51 elif prev_tok_str in ('def', 'class'):
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
52 kind = 'defname'
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
53 elif keyword.iskeyword(tok_str):
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
54 kind = 'keyword'
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
55 elif is_builtin(tok_str) and prev_tok_str != '.':
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
56 kind = 'builtin'
78014
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
57 if kind:
78079
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
58 text, written = combine_range(lines, written, (srow, scol))
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
59 yield '', text
78253
b127046831e2 Simplify the LaTeX section (only three escapes are needed for alltt)
Raymond Hettinger <python@rcn.com>
parents: 78103
diff changeset
60 text, written = tok_str, (erow, ecol)
78079
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
61 yield kind, text
78014
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
62 line_upto_token, written = combine_range(lines, written, (erow, ecol))
78079
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
63 yield '', line_upto_token
77938
1f06fe5cd4da Refactor to isolate HTML encoding step from the parsing step.
Raymond Hettinger <python@rcn.com>
parents: 77929
diff changeset
64
78049
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
65 #### Raw Output ###########################################
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
66
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
67 def raw_highlight(classified_text):
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
68 'Straight text display of text classifications'
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
69 result = []
78079
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
70 for kind, text in classified_text:
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
71 result.append('%15s: %r\n' % (kind or 'plain', text))
78049
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
72 return ''.join(result)
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
73
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
74 #### ANSI Output ###########################################
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
75
77940
980de5b47d0d Add support for ANSI escape sequences
Raymond Hettinger <python@rcn.com>
parents: 77938
diff changeset
76 default_ansi = {
78014
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
77 'comment': ('\033[0;31m', '\033[0m'),
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
78 'string': ('\033[0;32m', '\033[0m'),
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
79 'docstring': ('\033[0;32m', '\033[0m'),
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
80 'keyword': ('\033[0;33m', '\033[0m'),
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
81 'builtin': ('\033[0;35m', '\033[0m'),
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
82 'definition': ('\033[0;33m', '\033[0m'),
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
83 'defname': ('\033[0;34m', '\033[0m'),
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
84 'operator': ('\033[0;33m', '\033[0m'),
77940
980de5b47d0d Add support for ANSI escape sequences
Raymond Hettinger <python@rcn.com>
parents: 77938
diff changeset
85 }
980de5b47d0d Add support for ANSI escape sequences
Raymond Hettinger <python@rcn.com>
parents: 77938
diff changeset
86
78014
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
87 def ansi_highlight(classified_text, colors=default_ansi):
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
88 'Add syntax highlighting to source code using ANSI escape sequences'
77940
980de5b47d0d Add support for ANSI escape sequences
Raymond Hettinger <python@rcn.com>
parents: 77938
diff changeset
89 # http://en.wikipedia.org/wiki/ANSI_escape_code
980de5b47d0d Add support for ANSI escape sequences
Raymond Hettinger <python@rcn.com>
parents: 77938
diff changeset
90 result = []
78079
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
91 for kind, text in classified_text:
78014
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
92 opener, closer = colors.get(kind, ('', ''))
78079
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
93 result += [opener, text, closer]
77940
980de5b47d0d Add support for ANSI escape sequences
Raymond Hettinger <python@rcn.com>
parents: 77938
diff changeset
94 return ''.join(result)
980de5b47d0d Add support for ANSI escape sequences
Raymond Hettinger <python@rcn.com>
parents: 77938
diff changeset
95
78049
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
96 #### HTML Output ###########################################
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
97
78014
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
98 def html_highlight(classified_text,opener='<pre class="python">\n', closer='</pre>\n'):
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
99 'Convert classified text to an HTML fragment'
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
100 result = [opener]
78079
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
101 for kind, text in classified_text:
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
102 if kind:
78079
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
103 result.append('<span class="%s">' % kind)
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
104 result.append(cgi.escape(text))
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
105 if kind:
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
106 result.append('</span>')
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
107 result.append(closer)
77918
671894ae19a2 Do HTML escaping after the tokenization step.
Raymond Hettinger <python@rcn.com>
parents: 77904
diff changeset
108 return ''.join(result)
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
109
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
110 default_css = {
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
111 '.comment': '{color: crimson;}',
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
112 '.string': '{color: forestgreen;}',
77938
1f06fe5cd4da Refactor to isolate HTML encoding step from the parsing step.
Raymond Hettinger <python@rcn.com>
parents: 77929
diff changeset
113 '.docstring': '{color: forestgreen; font-style:italic;}',
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
114 '.keyword': '{color: darkorange;}',
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
115 '.builtin': '{color: purple;}',
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
116 '.definition': '{color: darkorange; font-weight:bold;}',
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
117 '.defname': '{color: blue;}',
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
118 '.operator': '{color: brown;}',
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
119 }
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
120
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
121 default_html = '''\
77902
d02588a26057 Small cleanups
Raymond Hettinger <python@rcn.com>
parents: 77901
diff changeset
122 <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
d02588a26057 Small cleanups
Raymond Hettinger <python@rcn.com>
parents: 77901
diff changeset
123 "http://www.w3.org/TR/html4/strict.dtd">
d02588a26057 Small cleanups
Raymond Hettinger <python@rcn.com>
parents: 77901
diff changeset
124 <html>
d02588a26057 Small cleanups
Raymond Hettinger <python@rcn.com>
parents: 77901
diff changeset
125 <head>
d02588a26057 Small cleanups
Raymond Hettinger <python@rcn.com>
parents: 77901
diff changeset
126 <meta http-equiv="Content-type" content="text/html;charset=UTF-8">
77920
2367ec12da2d Use new-style string formatting for the HTML template
Raymond Hettinger <python@rcn.com>
parents: 77919
diff changeset
127 <title> {title} </title>
77902
d02588a26057 Small cleanups
Raymond Hettinger <python@rcn.com>
parents: 77901
diff changeset
128 <style type="text/css">
77920
2367ec12da2d Use new-style string formatting for the HTML template
Raymond Hettinger <python@rcn.com>
parents: 77919
diff changeset
129 {css}
77902
d02588a26057 Small cleanups
Raymond Hettinger <python@rcn.com>
parents: 77901
diff changeset
130 </style>
d02588a26057 Small cleanups
Raymond Hettinger <python@rcn.com>
parents: 77901
diff changeset
131 </head>
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
132 <body>
77920
2367ec12da2d Use new-style string formatting for the HTML template
Raymond Hettinger <python@rcn.com>
parents: 77919
diff changeset
133 {body}
77902
d02588a26057 Small cleanups
Raymond Hettinger <python@rcn.com>
parents: 77901
diff changeset
134 </body>
d02588a26057 Small cleanups
Raymond Hettinger <python@rcn.com>
parents: 77901
diff changeset
135 </html>
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
136 '''
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
137
78014
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
138 def build_html_page(classified_text, title='python',
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
139 css=default_css, html=default_html):
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
140 'Create a complete HTML page with colorized source code'
77902
d02588a26057 Small cleanups
Raymond Hettinger <python@rcn.com>
parents: 77901
diff changeset
141 css_str = '\n'.join(['%s %s' % item for item in css.items()])
78014
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
142 result = html_highlight(classified_text)
77903
21ca7f56e12c Set title to the source filename
Raymond Hettinger <python@rcn.com>
parents: 77902
diff changeset
143 title = cgi.escape(title)
77920
2367ec12da2d Use new-style string formatting for the HTML template
Raymond Hettinger <python@rcn.com>
parents: 77919
diff changeset
144 return html.format(title=title, css=css_str, body=result)
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
145
78049
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
146 #### LaTeX Output ##########################################
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
147
78103
592307606f51 Fix-up latex styling
Raymond Hettinger <python@rcn.com>
parents: 78079
diff changeset
148 default_latex_commands = {
592307606f51 Fix-up latex styling
Raymond Hettinger <python@rcn.com>
parents: 78079
diff changeset
149 'comment': '{\color{red}#1}',
592307606f51 Fix-up latex styling
Raymond Hettinger <python@rcn.com>
parents: 78079
diff changeset
150 'string': '{\color{ForestGreen}#1}',
592307606f51 Fix-up latex styling
Raymond Hettinger <python@rcn.com>
parents: 78079
diff changeset
151 'docstring': '{\emph{\color{ForestGreen}#1}}',
592307606f51 Fix-up latex styling
Raymond Hettinger <python@rcn.com>
parents: 78079
diff changeset
152 'keyword': '{\color{orange}#1}',
592307606f51 Fix-up latex styling
Raymond Hettinger <python@rcn.com>
parents: 78079
diff changeset
153 'builtin': '{\color{purple}#1}',
592307606f51 Fix-up latex styling
Raymond Hettinger <python@rcn.com>
parents: 78079
diff changeset
154 'definition': '{\color{orange}#1}',
592307606f51 Fix-up latex styling
Raymond Hettinger <python@rcn.com>
parents: 78079
diff changeset
155 'defname': '{\color{blue}#1}',
592307606f51 Fix-up latex styling
Raymond Hettinger <python@rcn.com>
parents: 78079
diff changeset
156 'operator': '{\color{brown}#1}',
78049
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
157 }
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
158
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
159 default_latex_document = r'''
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
160 \documentclass{article}
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
161 \usepackage{alltt}
78103
592307606f51 Fix-up latex styling
Raymond Hettinger <python@rcn.com>
parents: 78079
diff changeset
162 \usepackage{upquote}
78049
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
163 \usepackage{color}
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
164 \usepackage[usenames,dvipsnames]{xcolor}
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
165 \usepackage[cm]{fullpage}
78103
592307606f51 Fix-up latex styling
Raymond Hettinger <python@rcn.com>
parents: 78079
diff changeset
166 %(macros)s
78049
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
167 \begin{document}
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
168 \center{\LARGE{%(title)s}}
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
169 \begin{alltt}
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
170 %(body)s
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
171 \end{alltt}
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
172 \end{document}
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
173 '''
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
174
78253
b127046831e2 Simplify the LaTeX section (only three escapes are needed for alltt)
Raymond Hettinger <python@rcn.com>
parents: 78103
diff changeset
175 def alltt_escape(s):
b127046831e2 Simplify the LaTeX section (only three escapes are needed for alltt)
Raymond Hettinger <python@rcn.com>
parents: 78103
diff changeset
176 'Replace backslash and braces with their escaped equivalents'
b127046831e2 Simplify the LaTeX section (only three escapes are needed for alltt)
Raymond Hettinger <python@rcn.com>
parents: 78103
diff changeset
177 xlat = {'{': r'\{', '}': r'\}', '\\': r'\textbackslash{}'}
b127046831e2 Simplify the LaTeX section (only three escapes are needed for alltt)
Raymond Hettinger <python@rcn.com>
parents: 78103
diff changeset
178 return re.sub(r'[\\{}]', lambda mo: xlat[mo.group()], s)
78049
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
179
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
180 def latex_highlight(classified_text, title = 'python',
78103
592307606f51 Fix-up latex styling
Raymond Hettinger <python@rcn.com>
parents: 78079
diff changeset
181 commands = default_latex_commands,
78049
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
182 document = default_latex_document):
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
183 'Create a complete LaTeX document with colorized source code'
78103
592307606f51 Fix-up latex styling
Raymond Hettinger <python@rcn.com>
parents: 78079
diff changeset
184 macros = '\n'.join(r'\newcommand{\py%s}[1]{%s}' % c for c in commands.items())
78049
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
185 result = []
78079
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
186 for kind, text in classified_text:
78049
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
187 if kind:
78103
592307606f51 Fix-up latex styling
Raymond Hettinger <python@rcn.com>
parents: 78079
diff changeset
188 result.append(r'\py%s{' % kind)
78253
b127046831e2 Simplify the LaTeX section (only three escapes are needed for alltt)
Raymond Hettinger <python@rcn.com>
parents: 78103
diff changeset
189 result.append(alltt_escape(text))
78079
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
190 if kind:
425d5e89fa25 Fix builtin test and simplify the classified text tuple.
Raymond Hettinger <python@rcn.com>
parents: 78049
diff changeset
191 result.append('}')
78103
592307606f51 Fix-up latex styling
Raymond Hettinger <python@rcn.com>
parents: 78079
diff changeset
192 return default_latex_document % dict(title=title, macros=macros, body=''.join(result))
78049
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
193
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
194
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
195 if __name__ == '__main__':
78014
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
196 import sys, argparse, webbrowser, os, textwrap
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
197
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
198 parser = argparse.ArgumentParser(
78014
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
199 description = 'Add syntax highlighting to Python source code',
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
200 formatter_class=argparse.RawDescriptionHelpFormatter,
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
201 epilog = textwrap.dedent('''
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
202 examples:
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
203
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
204 # Show syntax highlighted code in the terminal window
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
205 $ ./highlight.py myfile.py
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
206
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
207 # Colorize myfile.py and display in a browser
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
208 $ ./highlight.py -b myfile.py
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
209
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
210 # Create an HTML section to embed in an existing webpage
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
211 ./highlight.py -s myfile.py
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
212
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
213 # Create a complete HTML file
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
214 $ ./highlight.py -c myfile.py > myfile.html
78049
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
215
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
216 # Create a PDF using LaTeX
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
217 $ ./highlight.py -l myfile.py | pdflatex
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
218
78014
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
219 '''))
77928
4d320cd4c6fe Minor cleanups
Raymond Hettinger <python@rcn.com>
parents: 77920
diff changeset
220 parser.add_argument('sourcefile', metavar = 'SOURCEFILE',
78014
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
221 help = 'file containing Python sourcecode')
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
222 parser.add_argument('-b', '--browser', action = 'store_true',
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
223 help = 'launch a browser to show results')
77943
9fe720fe6057 Make ANSI the default output style
Raymond Hettinger <python@rcn.com>
parents: 77942
diff changeset
224 parser.add_argument('-c', '--complete', action = 'store_true',
9fe720fe6057 Make ANSI the default output style
Raymond Hettinger <python@rcn.com>
parents: 77942
diff changeset
225 help = 'build a complete html webpage')
78049
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
226 parser.add_argument('-l', '--latex', action = 'store_true',
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
227 help = 'build a LaTeX document')
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
228 parser.add_argument('-r', '--raw', action = 'store_true',
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
229 help = 'raw parse of categorized text')
77928
4d320cd4c6fe Minor cleanups
Raymond Hettinger <python@rcn.com>
parents: 77920
diff changeset
230 parser.add_argument('-s', '--section', action = 'store_true',
4d320cd4c6fe Minor cleanups
Raymond Hettinger <python@rcn.com>
parents: 77920
diff changeset
231 help = 'show an HTML section rather than a complete webpage')
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
232 args = parser.parse_args()
77940
980de5b47d0d Add support for ANSI escape sequences
Raymond Hettinger <python@rcn.com>
parents: 77938
diff changeset
233
77943
9fe720fe6057 Make ANSI the default output style
Raymond Hettinger <python@rcn.com>
parents: 77942
diff changeset
234 if args.section and (args.browser or args.complete):
77928
4d320cd4c6fe Minor cleanups
Raymond Hettinger <python@rcn.com>
parents: 77920
diff changeset
235 parser.error('The -s/--section option is incompatible with '
77943
9fe720fe6057 Make ANSI the default output style
Raymond Hettinger <python@rcn.com>
parents: 77942
diff changeset
236 'the -b/--browser or -c/--complete options')
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
237
77928
4d320cd4c6fe Minor cleanups
Raymond Hettinger <python@rcn.com>
parents: 77920
diff changeset
238 sourcefile = args.sourcefile
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
239 with open(sourcefile) as f:
77942
1401ff261ced Add examples to the module docstring
Raymond Hettinger <python@rcn.com>
parents: 77941
diff changeset
240 source = f.read()
78014
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
241 classified_text = analyze_python(source)
77940
980de5b47d0d Add support for ANSI escape sequences
Raymond Hettinger <python@rcn.com>
parents: 77938
diff changeset
242
78049
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
243 if args.raw:
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
244 encoded = raw_highlight(classified_text)
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
245 elif args.complete or args.browser:
78014
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
246 encoded = build_html_page(classified_text, title=sourcefile)
77940
980de5b47d0d Add support for ANSI escape sequences
Raymond Hettinger <python@rcn.com>
parents: 77938
diff changeset
247 elif args.section:
78014
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
248 encoded = html_highlight(classified_text)
78049
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
249 elif args.latex:
08bfd88027bb Add simple LaTeX markup
Raymond Hettinger <python@rcn.com>
parents: 78021
diff changeset
250 encoded = latex_highlight(classified_text, title=sourcefile)
77940
980de5b47d0d Add support for ANSI escape sequences
Raymond Hettinger <python@rcn.com>
parents: 77938
diff changeset
251 else:
78014
77ca62751877 Minor algorithmic tweaks, better factoring, improved docstrings and variable names
Raymond Hettinger <python@rcn.com>
parents: 77944
diff changeset
252 encoded = ansi_highlight(classified_text)
77940
980de5b47d0d Add support for ANSI escape sequences
Raymond Hettinger <python@rcn.com>
parents: 77938
diff changeset
253
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
254 if args.browser:
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
255 htmlfile = os.path.splitext(os.path.basename(sourcefile))[0] + '.html'
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
256 with open(htmlfile, 'w') as f:
77940
980de5b47d0d Add support for ANSI escape sequences
Raymond Hettinger <python@rcn.com>
parents: 77938
diff changeset
257 f.write(encoded)
77899
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
258 webbrowser.open('file://' + os.path.abspath(htmlfile))
da4dd603030b Add syntax highlighter tool
Raymond Hettinger <python@rcn.com>
parents:
diff changeset
259 else:
77940
980de5b47d0d Add support for ANSI escape sequences
Raymond Hettinger <python@rcn.com>
parents: 77938
diff changeset
260 sys.stdout.write(encoded)