summaryrefslogtreecommitdiff
path: root/pygments/lexers/special.py
diff options
context:
space:
mode:
authorGeorg Brandl <georg@python.org>2014-03-04 14:17:10 +0100
committerGeorg Brandl <georg@python.org>2014-03-04 14:17:10 +0100
commit18348a61d7e90b03a624fdc78fafdcb46b92307d (patch)
treee4fe1541ad9e2ada2de394eb2e020e2a0916ce94 /pygments/lexers/special.py
parentcd9c0b70635f2a6c65ea97d042537478a0a95b7a (diff)
parent27895fe85076d2f1b44e7d30387b3f459fc60281 (diff)
downloadpygments-18348a61d7e90b03a624fdc78fafdcb46b92307d.tar.gz
merge with raichoo/pygments-main (pull request #210)
Diffstat (limited to 'pygments/lexers/special.py')
-rw-r--r--pygments/lexers/special.py15
1 files changed, 7 insertions, 8 deletions
diff --git a/pygments/lexers/special.py b/pygments/lexers/special.py
index 9b3cd508..9ea2e22c 100644
--- a/pygments/lexers/special.py
+++ b/pygments/lexers/special.py
@@ -5,16 +5,15 @@
Special lexers.
- :copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
+ :copyright: Copyright 2006-2014 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
-import cStringIO
from pygments.lexer import Lexer
from pygments.token import Token, Error, Text
-from pygments.util import get_choice_opt, b
+from pygments.util import get_choice_opt, text_type, BytesIO
__all__ = ['TextLexer', 'RawTokenLexer']
@@ -35,7 +34,7 @@ class TextLexer(Lexer):
_ttype_cache = {}
-line_re = re.compile(b('.*?\n'))
+line_re = re.compile(b'.*?\n')
class RawTokenLexer(Lexer):
"""
@@ -60,12 +59,12 @@ class RawTokenLexer(Lexer):
Lexer.__init__(self, **options)
def get_tokens(self, text):
- if isinstance(text, unicode):
+ if isinstance(text, text_type):
# raw token stream never has any non-ASCII characters
text = text.encode('ascii')
if self.compress == 'gz':
import gzip
- gzipfile = gzip.GzipFile('', 'rb', 9, cStringIO.StringIO(text))
+ gzipfile = gzip.GzipFile('', 'rb', 9, BytesIO(text))
text = gzipfile.read()
elif self.compress == 'bz2':
import bz2
@@ -73,7 +72,7 @@ class RawTokenLexer(Lexer):
# do not call Lexer.get_tokens() because we do not want Unicode
# decoding to occur, and stripping is not optional.
- text = text.strip(b('\n')) + b('\n')
+ text = text.strip(b'\n') + b'\n'
for i, t, v in self.get_tokens_unprocessed(text):
yield t, v
@@ -81,7 +80,7 @@ class RawTokenLexer(Lexer):
length = 0
for match in line_re.finditer(text):
try:
- ttypestr, val = match.group().split(b('\t'), 1)
+ ttypestr, val = match.group().split(b'\t', 1)
except ValueError:
val = match.group().decode(self.encoding)
ttype = Error