This is the repository for the online module Bots as Digital Infrapuncture, commissioned by the Utrecht University
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 

164 lines
5.0 KiB

# -*- coding: utf-8 -*-
"""
pygments.formatters.other
~~~~~~~~~~~~~~~~~~~~~~~~~
Other formatters: NullFormatter, RawTokenFormatter.
:copyright: Copyright 2006-2019 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pygments.formatter import Formatter
from pygments.util import get_choice_opt
from pygments.token import Token
from pygments.console import colorize
__all__ = ['NullFormatter', 'RawTokenFormatter', 'TestcaseFormatter']
class NullFormatter(Formatter):
"""
Output the text unchanged without any formatting.
"""
name = 'Text only'
aliases = ['text', 'null']
filenames = ['*.txt']
def format(self, tokensource, outfile):
enc = self.encoding
for ttype, value in tokensource:
if enc:
outfile.write(value.encode(enc))
else:
outfile.write(value)
class RawTokenFormatter(Formatter):
r"""
Format tokens as a raw representation for storing token streams.
The format is ``tokentype<TAB>repr(tokenstring)\n``. The output can later
be converted to a token stream with the `RawTokenLexer`, described in the
:doc:`lexer list <lexers>`.
Only two options are accepted:
`compress`
If set to ``'gz'`` or ``'bz2'``, compress the output with the given
compression algorithm after encoding (default: ``''``).
`error_color`
If set to a color name, highlight error tokens using that color. If
set but with no value, defaults to ``'red'``.
.. versionadded:: 0.11
"""
name = 'Raw tokens'
aliases = ['raw', 'tokens']
filenames = ['*.raw']
unicodeoutput = False
def __init__(self, **options):
Formatter.__init__(self, **options)
# We ignore self.encoding if it is set, since it gets set for lexer
# and formatter if given with -Oencoding on the command line.
# The RawTokenFormatter outputs only ASCII. Override here.
self.encoding = 'ascii' # let pygments.format() do the right thing
self.compress = get_choice_opt(options, 'compress',
['', 'none', 'gz', 'bz2'], '')
self.error_color = options.get('error_color', None)
if self.error_color is True:
self.error_color = 'red'
if self.error_color is not None:
try:
colorize(self.error_color, '')
except KeyError:
raise ValueError("Invalid color %r specified" %
self.error_color)
def format(self, tokensource, outfile):
try:
outfile.write(b'')
except TypeError:
raise TypeError('The raw tokens formatter needs a binary '
'output file')
if self.compress == 'gz':
import gzip
outfile = gzip.GzipFile('', 'wb', 9, outfile)
def write(text):
outfile.write(text.encode())
flush = outfile.flush
elif self.compress == 'bz2':
import bz2
compressor = bz2.BZ2Compressor(9)
def write(text):
outfile.write(compressor.compress(text.encode()))
def flush():
outfile.write(compressor.flush())
outfile.flush()
else:
def write(text):
outfile.write(text.encode())
flush = outfile.flush
if self.error_color:
for ttype, value in tokensource:
line = "%s\t%r\n" % (ttype, value)
if ttype is Token.Error:
write(colorize(self.error_color, line))
else:
write(line)
else:
for ttype, value in tokensource:
write("%s\t%r\n" % (ttype, value))
flush()
TESTCASE_BEFORE = u'''\
def testNeedsName(lexer):
fragment = %r
tokens = [
'''
TESTCASE_AFTER = u'''\
]
assert list(lexer.get_tokens(fragment)) == tokens
'''
class TestcaseFormatter(Formatter):
"""
Format tokens as appropriate for a new testcase.
.. versionadded:: 2.0
"""
name = 'Testcase'
aliases = ['testcase']
def __init__(self, **options):
Formatter.__init__(self, **options)
if self.encoding is not None and self.encoding != 'utf-8':
raise ValueError("Only None and utf-8 are allowed encodings.")
def format(self, tokensource, outfile):
indentation = ' ' * 12
rawbuf = []
outbuf = []
for ttype, value in tokensource:
rawbuf.append(value)
outbuf.append('%s(%s, %r),\n' % (indentation, ttype, value))
before = TESTCASE_BEFORE % (u''.join(rawbuf),)
during = u''.join(outbuf)
after = TESTCASE_AFTER
if self.encoding is None:
outfile.write(before + during + after)
else:
outfile.write(before.encode('utf-8'))
outfile.write(during.encode('utf-8'))
outfile.write(after.encode('utf-8'))
outfile.flush()