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
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
|
"""
pygments.cmdline
~~~~~~~~~~~~~~~~
Command line interface.
:copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import os
import sys
import shutil
import argparse
from textwrap import dedent
from pygments import __version__, highlight
from pygments.util import ClassNotFound, OptionError, docstring_headline, \
guess_decode, guess_decode_from_terminal, terminal_encoding, \
UnclosingTextIOWrapper
from pygments.lexers import get_all_lexers, get_lexer_by_name, guess_lexer, \
load_lexer_from_file, get_lexer_for_filename, find_lexer_class_for_filename
from pygments.lexers.special import TextLexer
from pygments.formatters.latex import LatexEmbeddedLexer, LatexFormatter
from pygments.formatters import get_all_formatters, get_formatter_by_name, \
load_formatter_from_file, get_formatter_for_filename, find_formatter_class
from pygments.formatters.terminal import TerminalFormatter
from pygments.formatters.terminal256 import Terminal256Formatter, TerminalTrueColorFormatter
from pygments.filters import get_all_filters, find_filter_class
from pygments.styles import get_all_styles, get_style_by_name
def _parse_options(o_strs):
opts = {}
if not o_strs:
return opts
for o_str in o_strs:
if not o_str.strip():
continue
o_args = o_str.split(',')
for o_arg in o_args:
o_arg = o_arg.strip()
try:
o_key, o_val = o_arg.split('=', 1)
o_key = o_key.strip()
o_val = o_val.strip()
except ValueError:
opts[o_arg] = True
else:
opts[o_key] = o_val
return opts
def _parse_filters(f_strs):
filters = []
if not f_strs:
return filters
for f_str in f_strs:
if ':' in f_str:
fname, fopts = f_str.split(':', 1)
filters.append((fname, _parse_options([fopts])))
else:
filters.append((f_str, {}))
return filters
def _print_help(what, name):
try:
if what == 'lexer':
cls = get_lexer_by_name(name)
print(f"Help on the {cls.name} lexer:")
print(dedent(cls.__doc__))
elif what == 'formatter':
cls = find_formatter_class(name)
print(f"Help on the {cls.name} formatter:")
print(dedent(cls.__doc__))
elif what == 'filter':
cls = find_filter_class(name)
print(f"Help on the {name} filter:")
print(dedent(cls.__doc__))
return 0
except (AttributeError, ValueError):
print(f"{what} not found!", file=sys.stderr)
return 1
def _print_list(what):
if what == 'lexer':
print()
print("Lexers:")
print("~~~~~~~")
info = []
for fullname, names, exts, _ in get_all_lexers():
tup = (', '.join(names)+':', fullname,
exts and '(filenames ' + ', '.join(exts) + ')' or '')
info.append(tup)
info.sort()
for i in info:
print(('* {}\n {} {}').format(*i))
elif what == 'formatter':
print()
print("Formatters:")
print("~~~~~~~~~~~")
info = []
for cls in get_all_formatters():
doc = docstring_headline(cls)
tup = (', '.join(cls.aliases) + ':', doc, cls.filenames and
'(filenames ' + ', '.join(cls.filenames) + ')' or '')
info.append(tup)
info.sort()
for i in info:
print(('* {}\n {} {}').format(*i))
elif what == 'filter':
print()
print("Filters:")
print("~~~~~~~~")
for name in get_all_filters():
cls = find_filter_class(name)
print("* " + name + ':')
print(f" {docstring_headline(cls)}")
elif what == 'style':
print()
print("Styles:")
print("~~~~~~~")
for name in get_all_styles():
cls = get_style_by_name(name)
print("* " + name + ':')
print(f" {docstring_headline(cls)}")
def _print_list_as_json(requested_items):
import json
result = {}
if 'lexer' in requested_items:
info = {}
for fullname, names, filenames, mimetypes in get_all_lexers():
info[fullname] = {
'aliases': names,
'filenames': filenames,
'mimetypes': mimetypes
}
result['lexers'] = info
if 'formatter' in requested_items:
info = {}
for cls in get_all_formatters():
doc = docstring_headline(cls)
info[cls.name] = {
'aliases': cls.aliases,
'filenames': cls.filenames,
'doc': doc
}
result['formatters'] = info
if 'filter' in requested_items:
info = {}
for name in get_all_filters():
cls = find_filter_class(name)
info[name] = {
'doc': docstring_headline(cls)
}
result['filters'] = info
if 'style' in requested_items:
info = {}
for name in get_all_styles():
cls = get_style_by_name(name)
info[name] = {
'doc': docstring_headline(cls)
}
result['styles'] = info
json.dump(result, sys.stdout)
def main_inner(parser, argns):
if argns.help:
parser.print_help()
return 0
if argns.V:
print(f'Pygments version {__version__}, (c) 2006-2024 by Georg Brandl, Matthäus '
'Chajdas and contributors.')
return 0
def is_only_option(opt):
return not any(v for (k, v) in vars(argns).items() if k != opt)
# handle ``pygmentize -L``
if argns.L is not None:
arg_set = set()
for k, v in vars(argns).items():
if v:
arg_set.add(k)
arg_set.discard('L')
arg_set.discard('json')
if arg_set:
parser.print_help(sys.stderr)
return 2
# print version
if not argns.json:
main(['', '-V'])
allowed_types = {'lexer', 'formatter', 'filter', 'style'}
largs = [arg.rstrip('s') for arg in argns.L]
if any(arg not in allowed_types for arg in largs):
parser.print_help(sys.stderr)
return 0
if not largs:
largs = allowed_types
if not argns.json:
for arg in largs:
_print_list(arg)
else:
_print_list_as_json(largs)
return 0
# handle ``pygmentize -H``
if argns.H:
if not is_only_option('H'):
parser.print_help(sys.stderr)
return 2
what, name = argns.H
if what not in ('lexer', 'formatter', 'filter'):
parser.print_help(sys.stderr)
return 2
return _print_help(what, name)
# parse -O options
parsed_opts = _parse_options(argns.O or [])
# parse -P options
for p_opt in argns.P or []:
try:
name, value = p_opt.split('=', 1)
except ValueError:
parsed_opts[p_opt] = True
else:
parsed_opts[name] = value
# encodings
inencoding = parsed_opts.get('inencoding', parsed_opts.get('encoding'))
outencoding = parsed_opts.get('outencoding', parsed_opts.get('encoding'))
# handle ``pygmentize -N``
if argns.N:
lexer = find_lexer_class_for_filename(argns.N)
if lexer is None:
lexer = TextLexer
print(lexer.aliases[0])
return 0
# handle ``pygmentize -C``
if argns.C:
inp = sys.stdin.buffer.read()
try:
lexer = guess_lexer(inp, inencoding=inencoding)
except ClassNotFound:
lexer = TextLexer
print(lexer.aliases[0])
return 0
# handle ``pygmentize -S``
S_opt = argns.S
a_opt = argns.a
if S_opt is not None:
f_opt = argns.f
if not f_opt:
parser.print_help(sys.stderr)
return 2
if argns.l or argns.INPUTFILE:
parser.print_help(sys.stderr)
return 2
try:
parsed_opts['style'] = S_opt
fmter = get_formatter_by_name(f_opt, **parsed_opts)
except ClassNotFound as err:
print(err, file=sys.stderr)
return 1
print(fmter.get_style_defs(a_opt or ''))
return 0
# if no -S is given, -a is not allowed
if argns.a is not None:
parser.print_help(sys.stderr)
return 2
# parse -F options
F_opts = _parse_filters(argns.F or [])
# -x: allow custom (eXternal) lexers and formatters
allow_custom_lexer_formatter = bool(argns.x)
# select lexer
lexer = None
# given by name?
lexername = argns.l
if lexername:
# custom lexer, located relative to user's cwd
if allow_custom_lexer_formatter and '.py' in lexername:
try:
filename = None
name = None
if ':' in lexername:
filename, name = lexername.rsplit(':', 1)
if '.py' in name:
# This can happen on Windows: If the lexername is
# C:\lexer.py -- return to normal load path in that case
name = None
if filename and name:
lexer = load_lexer_from_file(filename, name,
**parsed_opts)
else:
lexer = load_lexer_from_file(lexername, **parsed_opts)
except ClassNotFound as err:
print('Error:', err, file=sys.stderr)
return 1
else:
try:
lexer = get_lexer_by_name(lexername, **parsed_opts)
except (OptionError, ClassNotFound) as err:
print('Error:', err, file=sys.stderr)
return 1
# read input code
code = None
if argns.INPUTFILE:
if argns.s:
print('Error: -s option not usable when input file specified',
file=sys.stderr)
return 2
infn = argns.INPUTFILE
try:
with open(infn, 'rb') as infp:
code = infp.read()
except Exception as err:
print('Error: cannot read infile:', err, file=sys.stderr)
return 1
if not inencoding:
code, inencoding = guess_decode(code)
# do we have to guess the lexer?
if not lexer:
try:
lexer = get_lexer_for_filename(infn, code, **parsed_opts)
except ClassNotFound as err:
if argns.g:
try:
lexer = guess_lexer(code, **parsed_opts)
except ClassNotFound:
lexer = TextLexer(**parsed_opts)
else:
print('Error:', err, file=sys.stderr)
return 1
except OptionError as err:
print('Error:', err, file=sys.stderr)
return 1
elif not argns.s: # treat stdin as full file (-s support is later)
# read code from terminal, always in binary mode since we want to
# decode ourselves and be tolerant with it
code = sys.stdin.buffer.read() # use .buffer to get a binary stream
if not inencoding:
code, inencoding = guess_decode_from_terminal(code, sys.stdin)
# else the lexer will do the decoding
if not lexer:
try:
lexer = guess_lexer(code, **parsed_opts)
except ClassNotFound:
lexer = TextLexer(**parsed_opts)
else: # -s option needs a lexer with -l
if not lexer:
print('Error: when using -s a lexer has to be selected with -l',
file=sys.stderr)
return 2
# process filters
for fname, fopts in F_opts:
try:
lexer.add_filter(fname, **fopts)
except ClassNotFound as err:
print('Error:', err, file=sys.stderr)
return 1
# select formatter
outfn = argns.o
fmter = argns.f
if fmter:
# custom formatter, located relative to user's cwd
if allow_custom_lexer_formatter and '.py' in fmter:
try:
filename = None
name = None
if ':' in fmter:
# Same logic as above for custom lexer
filename, name = fmter.rsplit(':', 1)
if '.py' in name:
name = None
if filename and name:
fmter = load_formatter_from_file(filename, name,
**parsed_opts)
else:
fmter = load_formatter_from_file(fmter, **parsed_opts)
except ClassNotFound as err:
print('Error:', err, file=sys.stderr)
return 1
else:
try:
fmter = get_formatter_by_name(fmter, **parsed_opts)
except (OptionError, ClassNotFound) as err:
print('Error:', err, file=sys.stderr)
return 1
if outfn:
if not fmter:
try:
fmter = get_formatter_for_filename(outfn, **parsed_opts)
except (OptionError, ClassNotFound) as err:
print('Error:', err, file=sys.stderr)
return 1
try:
outfile = open(outfn, 'wb')
except Exception as err:
print('Error: cannot open outfile:', err, file=sys.stderr)
return 1
else:
if not fmter:
if os.environ.get('COLORTERM','') in ('truecolor', '24bit'):
fmter = TerminalTrueColorFormatter(**parsed_opts)
elif '256' in os.environ.get('TERM', ''):
fmter = Terminal256Formatter(**parsed_opts)
else:
fmter = TerminalFormatter(**parsed_opts)
outfile = sys.stdout.buffer
# determine output encoding if not explicitly selected
if not outencoding:
if outfn:
# output file? use lexer encoding for now (can still be None)
fmter.encoding = inencoding
else:
# else use terminal encoding
fmter.encoding = terminal_encoding(sys.stdout)
# provide coloring under Windows, if possible
if not outfn and sys.platform in ('win32', 'cygwin') and \
fmter.name in ('Terminal', 'Terminal256'): # pragma: no cover
# unfortunately colorama doesn't support binary streams on Py3
outfile = UnclosingTextIOWrapper(outfile, encoding=fmter.encoding)
fmter.encoding = None
try:
import colorama.initialise
except ImportError:
pass
else:
outfile = colorama.initialise.wrap_stream(
outfile, convert=None, strip=None, autoreset=False, wrap=True)
# When using the LaTeX formatter and the option `escapeinside` is
# specified, we need a special lexer which collects escaped text
# before running the chosen language lexer.
escapeinside = parsed_opts.get('escapeinside', '')
if len(escapeinside) == 2 and isinstance(fmter, LatexFormatter):
left = escapeinside[0]
right = escapeinside[1]
lexer = LatexEmbeddedLexer(left, right, lexer)
# ... and do it!
if not argns.s:
# process whole input as per normal...
try:
highlight(code, lexer, fmter, outfile)
finally:
if outfn:
outfile.close()
return 0
else:
# line by line processing of stdin (eg: for 'tail -f')...
try:
while 1:
line = sys.stdin.buffer.readline()
if not line:
break
if not inencoding:
line = guess_decode_from_terminal(line, sys.stdin)[0]
highlight(line, lexer, fmter, outfile)
if hasattr(outfile, 'flush'):
outfile.flush()
return 0
except KeyboardInterrupt: # pragma: no cover
return 0
finally:
if outfn:
outfile.close()
class HelpFormatter(argparse.HelpFormatter):
def __init__(self, prog, indent_increment=2, max_help_position=16, width=None):
if width is None:
try:
width = shutil.get_terminal_size().columns - 2
except Exception:
pass
argparse.HelpFormatter.__init__(self, prog, indent_increment,
max_help_position, width)
def main(args=sys.argv):
"""
Main command line entry point.
"""
desc = "Highlight an input file and write the result to an output file."
parser = argparse.ArgumentParser(description=desc, add_help=False,
formatter_class=HelpFormatter)
operation = parser.add_argument_group('Main operation')
lexersel = operation.add_mutually_exclusive_group()
lexersel.add_argument(
'-l', metavar='LEXER',
help='Specify the lexer to use. (Query names with -L.) If not '
'given and -g is not present, the lexer is guessed from the filename.')
lexersel.add_argument(
'-g', action='store_true',
help='Guess the lexer from the file contents, or pass through '
'as plain text if nothing can be guessed.')
operation.add_argument(
'-F', metavar='FILTER[:options]', action='append',
help='Add a filter to the token stream. (Query names with -L.) '
'Filter options are given after a colon if necessary.')
operation.add_argument(
'-f', metavar='FORMATTER',
help='Specify the formatter to use. (Query names with -L.) '
'If not given, the formatter is guessed from the output filename, '
'and defaults to the terminal formatter if the output is to the '
'terminal or an unknown file extension.')
operation.add_argument(
'-O', metavar='OPTION=value[,OPTION=value,...]', action='append',
help='Give options to the lexer and formatter as a comma-separated '
'list of key-value pairs. '
'Example: `-O bg=light,python=cool`.')
operation.add_argument(
'-P', metavar='OPTION=value', action='append',
help='Give a single option to the lexer and formatter - with this '
'you can pass options whose value contains commas and equal signs. '
'Example: `-P "heading=Pygments, the Python highlighter"`.')
operation.add_argument(
'-o', metavar='OUTPUTFILE',
help='Where to write the output. Defaults to standard output.')
operation.add_argument(
'INPUTFILE', nargs='?',
help='Where to read the input. Defaults to standard input.')
flags = parser.add_argument_group('Operation flags')
flags.add_argument(
'-v', action='store_true',
help='Print a detailed traceback on unhandled exceptions, which '
'is useful for debugging and bug reports.')
flags.add_argument(
'-s', action='store_true',
help='Process lines one at a time until EOF, rather than waiting to '
'process the entire file. This only works for stdin, only for lexers '
'with no line-spanning constructs, and is intended for streaming '
'input such as you get from `tail -f`. '
'Example usage: `tail -f sql.log | pygmentize -s -l sql`.')
flags.add_argument(
'-x', action='store_true',
help='Allow custom lexers and formatters to be loaded from a .py file '
'relative to the current working directory. For example, '
'`-l ./customlexer.py -x`. By default, this option expects a file '
'with a class named CustomLexer or CustomFormatter; you can also '
'specify your own class name with a colon (`-l ./lexer.py:MyLexer`). '
'Users should be very careful not to use this option with untrusted '
'files, because it will import and run them.')
flags.add_argument('--json', help='Output as JSON. This can '
'be only used in conjunction with -L.',
default=False,
action='store_true')
special_modes_group = parser.add_argument_group(
'Special modes - do not do any highlighting')
special_modes = special_modes_group.add_mutually_exclusive_group()
special_modes.add_argument(
'-S', metavar='STYLE -f formatter',
help='Print style definitions for STYLE for a formatter '
'given with -f. The argument given by -a is formatter '
'dependent.')
special_modes.add_argument(
'-L', nargs='*', metavar='WHAT',
help='List lexers, formatters, styles or filters -- '
'give additional arguments for the thing(s) you want to list '
'(e.g. "styles"), or omit them to list everything.')
special_modes.add_argument(
'-N', metavar='FILENAME',
help='Guess and print out a lexer name based solely on the given '
'filename. Does not take input or highlight anything. If no specific '
'lexer can be determined, "text" is printed.')
special_modes.add_argument(
'-C', action='store_true',
help='Like -N, but print out a lexer name based solely on '
'a given content from standard input.')
special_modes.add_argument(
'-H', action='store', nargs=2, metavar=('NAME', 'TYPE'),
help='Print detailed help for the object <name> of type <type>, '
'where <type> is one of "lexer", "formatter" or "filter".')
special_modes.add_argument(
'-V', action='store_true',
help='Print the package version.')
special_modes.add_argument(
'-h', '--help', action='store_true',
help='Print this help.')
special_modes_group.add_argument(
'-a', metavar='ARG',
help='Formatter-specific additional argument for the -S (print '
'style sheet) mode.')
argns = parser.parse_args(args[1:])
try:
return main_inner(parser, argns)
except BrokenPipeError:
# someone closed our stdout, e.g. by quitting a pager.
return 0
except Exception:
if argns.v:
print(file=sys.stderr)
print('*' * 65, file=sys.stderr)
print('An unhandled exception occurred while highlighting.',
file=sys.stderr)
print('Please report the whole traceback to the issue tracker at',
file=sys.stderr)
print('<https://github.com/pygments/pygments/issues>.',
file=sys.stderr)
print('*' * 65, file=sys.stderr)
print(file=sys.stderr)
raise
import traceback
info = traceback.format_exception(*sys.exc_info())
msg = info[-1].strip()
if len(info) >= 3:
# extract relevant file and position info
msg += '\n (f{})'.format(info[-2].split('\n')[0].strip()[1:])
print(file=sys.stderr)
print('*** Error while highlighting:', file=sys.stderr)
print(msg, file=sys.stderr)
print('*** If this is a bug you want to report, please rerun with -v.',
file=sys.stderr)
return 1
|