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
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
|
# -*- coding: utf-8 -*-
"""
pygments.formatters.html
~~~~~~~~~~~~~~~~~~~~~~~~
Formatter for HTML output.
:copyright: 2006-2007 by Georg Brandl, Armin Ronacher.
:license: BSD, see LICENSE for more details.
"""
import sys, os
import StringIO
from pygments.formatter import Formatter
from pygments.token import Token, Text, STANDARD_TYPES
from pygments.util import get_bool_opt, get_int_opt
__all__ = ['HtmlFormatter']
def escape_html(text):
"""Escape &, <, > as well as single and double quotes for HTML."""
return text.replace('&', '&'). \
replace('<', '<'). \
replace('>', '>'). \
replace('"', '"'). \
replace("'", ''')
def get_random_id():
"""Return a random id for javascript fields."""
from random import random
from time import time
try:
from hashlib import sha1 as sha
except ImportError:
import sha
sha = sha.new
return sha('%s|%s' % (random(), time())).hexdigest()
def _get_ttype_class(ttype):
fname = STANDARD_TYPES.get(ttype)
if fname:
return fname
aname = ''
while fname is None:
aname = '-' + ttype[-1] + aname
ttype = ttype.parent
fname = STANDARD_TYPES.get(ttype, '')
return fname + aname
DOC_HEADER = '''\
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN"
"http://www.w3.org/TR/html4/strict.dtd">
<html>
<head>
<title>%(title)s</title>
<meta http-equiv="content-type" content="text/html; charset=%(encoding)s">
<style type="text/css">
td.linenos { background-color: #f0f0f0; padding-right: 10px; }
%(styledefs)s
</style>
</head>
<body>
<h2>%(title)s</h2>
'''
DOC_HEADER_EXTERNALCSS = '''\
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN"
"http://www.w3.org/TR/html4/strict.dtd">
<html>
<head>
<title>%(title)s</title>
<meta http-equiv="content-type" content="text/html; charset=%(encoding)s">
<link rel="stylesheet" href="%(cssfile)s">
</head>
<body>
<h2>%(title)s</h2>
'''
DOC_FOOTER = '''\
</body>
</html>
'''
CSSFILE_TEMPLATE = '''\
td.linenos { background-color: #f0f0f0; padding-right: 10px; }
%(styledefs)s
'''
class HtmlFormatter(Formatter):
"""
Format tokens as HTML 4 ``<span>`` tags within a ``<pre>`` tag, wrapped
in a ``<div>`` tag. The ``<div>``'s CSS class can be set by the `cssclass`
option.
If the `linenos` option is given and true, the ``<pre>`` is additionally
wrapped inside a ``<table>`` which has one row and two cells: one
containing the line numbers and one containing the code. Example:
.. sourcecode:: html
<div class="highlight" >
<table><tr>
<td class="linenos" title="click to toggle"
onclick="with (this.firstChild.style)
{ display = (display == '') ? 'none' : '' }">
<pre>1
2</pre>
</td>
<td class="code">
<pre><span class="Ke">def </span><span class="NaFu">foo</span>(bar):
<span class="Ke">pass</span>
</pre>
</td>
</tr></table></div>
(whitespace added to improve clarity). Wrapping can be disabled using the
`nowrap` option.
With the `full` option, a complete HTML 4 document is output, including
the style definitions inside a ``<style>`` tag, or in a separate file if
the `cssfile` option is given.
The `get_style_defs(arg='')` method of a `HtmlFormatter` returns a string
containing CSS rules for the CSS classes used by the formatter. The
argument `arg` can be used to specify additional CSS selectors that
are prepended to the classes. A call `fmter.get_style_defs('td .code')`
would result in the following CSS classes:
.. sourcecode:: css
td .code .kw { font-weight: bold; color: #00FF00 }
td .code .cm { color: #999999 }
...
If you have pygments 0.6 or higher you can also pass a list of tuple to the
`get_style_defs` method to request multiple prefixes for the tokens:
.. sourcecode:: python
formatter.get_style_defs(['div.syntax pre', 'pre.syntax'])
The output would then look like this:
.. sourcecode:: css
div.syntax pre .kw,
pre.syntax .kw { font-weight: bold; color: #00FF00 }
div.syntax pre .cm,
pre.syntax .cm { color: #999999 }
...
Additional options accepted:
`nowrap`
If set to ``True``, don't wrap the tokens at all, not even inside a ``<pre>``
tag. This disables all other options (default: ``False``).
`noclasses`
If set to true, token ``<span>`` tags will not use CSS classes, but
inline styles. This is not recommended for larger pieces of code since
it increases output size by quite a bit (default: ``False``).
`classprefix`
Since the token types use relatively short class names, they may clash
with some of your own class names. In this case you can use the
`classprefix` option to give a string to prepend to all Pygments-generated
CSS class names for token types.
Note that this option also affects the output of `get_style_defs()`.
`cssclass`
CSS class for the wrapping ``<div>`` tag (default: ``'highlight'``).
`cssstyles`
Inline CSS styles for the wrapping ``<div>`` tag (default: ``''``).
`cssfile`
If the `full` option is true and this option is given, it must be the
name of an external file. The stylesheet is then written to this file
instead of the HTML file. *New in Pygments 0.6.*
`linenospecial`
If set to a number n > 0, every nth line number is given the CSS
class ``"special"`` (default: ``0``).
`nobackground`
If set to ``True``, the formatter won't output the background color
for the wrapping element (this automatically defaults to ``False``
when there is no wrapping element [eg: no argument for the
`get_syntax_defs` method given]) (default: ``False``). *New in
Pygments 0.6.*
`lineseparator`
This string is output between lines of code. It defaults to ``"\n"``,
which is enough to break a line inside ``<pre>`` tags, but you can
e.g. set it to ``"<br>"`` to get HTML line breaks. *New in Pygments
0.7.*
Subclassing the HTML formatter
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
*New in Pygments 0.7.*
The HTML formatter is now built in a way that allows easy subclassing, thus
customizing the output HTML code. The `format()` method creates a basic
generator by calling `self._format_lines()`. The resulting iterator yields
tuples of ``(code, text)``, where ``code`` is always ``1`` and indicates that
the ``text`` is a line of the formatted source code.
If the `nowrap` option is set, the generator is the iterated over and the
resulting HTML is output.
Otherwise, `format()` calls `self.wrap()`, which wraps the generator with other
generators. These add some HTML code to the one generated by `_format_lines()`,
either by modifying the lines generated by the latter, then yielding them again
with ``(1, line)``, and/or by yielding other code before or after the lines,
with ``(0, html)``. The distinction between source lines and other code makes it
possible to wrap the generator multiple times.
The default `wrap()` implementation adds a ``<div>`` and a ``<pre>`` tag.
A custom `HtmlFormatter` subclass could look like this:
.. sourcecode:: python
class CodeHtmlFormatter(HtmlFormatter):
def wrap(self, source, outfile):
return self._wrap_code(source)
def _wrap_code(self, source):
yield 0, '<code>'
for i, t in source:
if i == 1:
t += '<br>'
yield i, t
yield 0, '</code>'
This results in wrapping the formatted lines with a ``<code>`` tag, where the
source lines are broken using ``<br>`` tags.
After calling `wrap()`, the `format()` method also adds the "line numbers"
and/or "full document" wrappers if the respective options are set.
"""
def __init__(self, **options):
Formatter.__init__(self, **options)
self.nowrap = get_bool_opt(options, 'nowrap', False)
self.noclasses = get_bool_opt(options, 'noclasses', False)
self.classprefix = options.get('classprefix', '')
self.cssclass = options.get('cssclass', 'highlight')
self.cssstyles = options.get('cssstyles', '')
self.cssfile = options.get('cssfile', '')
self.linenos = get_bool_opt(options, 'linenos', False)
self.linenostart = abs(get_int_opt(options, 'linenostart', 1))
self.linenostep = abs(get_int_opt(options, 'linenostep', 1))
self.linenospecial = abs(get_int_opt(options, 'linenospecial', 0))
self.nobackground = get_bool_opt(options, 'nobackground', False)
self.lineseparator = options.get('lineseparator', '\n')
self._class_cache = {}
self._create_stylesheet()
def _get_css_class(self, ttype):
"""Return the css class of this token type prefixed with
the classprefix option."""
if ttype in self._class_cache:
return self._class_cache[ttype]
return self.classprefix + _get_ttype_class(ttype)
def _create_stylesheet(self):
t2c = self.ttype2class = {Token: ''}
c2s = self.class2style = {}
cp = self.classprefix
for ttype, ndef in self.style:
name = cp + _get_ttype_class(ttype)
style = ''
if ndef['color']:
style += 'color: #%s; ' % ndef['color']
if ndef['bold']:
style += 'font-weight: bold; '
if ndef['italic']:
style += 'font-style: italic; '
if ndef['underline']:
style += 'text-decoration: underline; '
if ndef['bgcolor']:
style += 'background-color: #%s; ' % ndef['bgcolor']
if ndef['border']:
style += 'border: 1px solid #%s; ' % ndef['border']
if style:
t2c[ttype] = name
# save len(ttype) to enable ordering the styles by
# hierarchy (necessary for CSS cascading rules!)
c2s[name] = (style[:-2], ttype, len(ttype))
def get_style_defs(self, arg=''):
"""
Return CSS style definitions for the classes produced by the
current highlighting style. ``arg`` can be a string of selectors
to insert before the token type classes.
"""
if isinstance(arg, basestring):
args = [arg]
else:
args = list(arg)
def prefix(cls):
tmp = []
for arg in args:
tmp.append((arg and arg + ' ' or '') + '.' + cls)
return ', '.join(tmp)
styles = [(level, ttype, cls, style)
for cls, (style, ttype, level) in self.class2style.iteritems()
if cls and style]
styles.sort()
lines = ['%s { %s } /* %s */' % (prefix(cls), style, repr(ttype)[6:])
for level, ttype, cls, style in styles]
if arg and not self.nobackground and \
self.style.background_color is not None:
text_style = ''
if Text in self.ttype2class:
text_style = ' ' + self.class2style[self.ttype2class[Text]][0]
lines.insert(0, '%s{ background: %s;%s }' %
(arg, self.style.background_color, text_style))
return '\n'.join(lines)
def _wrap_full(self, inner, outfile):
if self.cssfile:
try:
filename = outfile.name
cssfilename = os.path.join(os.path.dirname(filename), self.cssfile)
except AttributeError:
print >>sys.stderr, 'Note: Cannot determine output file name, ' \
'using current directory as base for the CSS file name'
cssfilename = self.cssfile
# write CSS file
try:
cf = open(cssfilename, "w")
cf.write(CSSFILE_TEMPLATE %
{'styledefs': self.get_style_defs('body')})
cf.close()
except IOError, err:
err.strerror = 'Error writing CSS file: ' + err.strerror
raise
yield 0, (DOC_HEADER_EXTERNALCSS %
dict(title = self.title,
cssfile = self.cssfile,
encoding = self.encoding))
else:
yield 0, (DOC_HEADER %
dict(title = self.title,
styledefs = self.get_style_defs('body'),
encoding = self.encoding))
for t, line in inner:
yield t, line
yield 0, DOC_FOOTER
def _wrap_linenos(self, inner):
dummyoutfile = StringIO.StringIO()
lncount = 0
for t, line in inner:
if t:
lncount += 1
dummyoutfile.write(line)
fl = self.linenostart
mw = len(str(lncount + fl - 1))
sp = self.linenospecial
st = self.linenostep
if sp:
ls = '\n'.join([(i%st == 0 and
(i%sp == 0 and '<span class="special">%*d</span>'
or '%*d') % (mw, i)
or '')
for i in range(fl, fl + lncount)])
else:
ls = '\n'.join([(i%st == 0 and ('%*d' % (mw, i)) or '')
for i in range(fl, fl + lncount)])
yield 0, ('<table><tr><td class="linenos"><pre>' +
ls + '</pre></td><td class="code">')
yield 0, dummyoutfile.getvalue()
yield 0, '</td></tr></table>'
def _wrap_div(self, inner):
yield 0, ('<div' + (self.cssclass and ' class="%s" ' % self.cssclass)
+ (self.cssstyles and ' style="%s"' % self.cssstyles) + '>')
for tup in inner:
yield tup
yield 0, '</div>\n'
def _wrap_pre(self, inner):
yield 0, '<pre>'
for tup in inner:
yield tup
yield 0, '</pre>'
def _format_lines(self, tokensource):
"""
Just format the tokens, without any wrapping tags.
Yield individual lines.
"""
nocls = self.noclasses
enc = self.encoding
lsep = self.lineseparator
# for <span style=""> lookup only
getcls = self.ttype2class.get
c2s = self.class2style
lspan = ''
line = ''
for ttype, value in tokensource:
if nocls:
cclass = getcls(ttype)
while cclass is None:
ttype = ttype.parent
cclass = getcls(ttype)
cspan = cclass and '<span style="%s">' % c2s[cclass][0]
else:
cls = self._get_css_class(ttype)
cspan = cls and '<span class="%s">' % cls
if enc:
value = value.encode(enc)
parts = escape_html(value).split('\n')
# for all but the last line
for part in parts[:-1]:
if line:
if lspan != cspan:
line += (lspan and '</span>') + cspan + part + \
(cspan and '</span>') + lsep
else: # both are the same
line += part + (lspan and '</span>') + lsep
yield 1, line
line = ''
else:
yield 1, cspan + part + (cspan and '</span>') + lsep
# for the last line
if line:
if lspan != cspan:
line += (lspan and '</span>') + cspan + parts[-1]
lspan = cspan
else:
line += parts[-1]
else:
line = cspan + parts[-1]
lspan = cspan
if line:
yield 1, line + (lspan and '</span>') + lsep
def wrap(self, source, outfile):
"""
Wrap the ``source``, which is a generator yielding
individual lines, in custom generators. See docstring
for `format`. Can be overridden.
"""
return self._wrap_div(self._wrap_pre(source))
def format(self, tokensource, outfile):
"""
The formatting process uses several nested generators; which of
them are used is determined by the user's options.
Each generator should take at least one argument, ``inner``,
and wrap the pieces of text generated by this.
Always yield 2-tuples: (code, text). If "code" is 1, the text
is part of the original tokensource being highlighted, if it's
0, the text is some piece of wrapping. This makes it possible to
use several different wrappers that process the original source
linewise, e.g. line number generators.
"""
source = self._format_lines(tokensource)
if not self.nowrap:
source = self.wrap(source, outfile)
if self.linenos:
source = self._wrap_linenos(source)
if self.full:
source = self._wrap_full(source, outfile)
for t, piece in source:
outfile.write(piece)
|
