pygments.rb 1.1.0 → 2.0.0.rc2

data/vendor/pygments-main/Pygments-2.7.3.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: bdist_wheel (0.35.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

data/vendor/pygments-main/Pygments-2.7.3.dist-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+pygmentize = pygments.cmdline:main
+

data/vendor/pygments-main/Pygments-2.7.3.dist-info/top_level.txt

@@ -0,0 +1 @@
+pygments

data/vendor/pygments-main/bin/pygmentize

@@ -0,0 +1,8 @@
+#!/usr/bin/python3.8
+# -*- coding: utf-8 -*-
+import re
+import sys
+from pygments.cmdline import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

data/vendor/pygments-main/pygments/__init__.py

@@ -17,19 +17,18 @@
     * it is usable as a command-line tool and as a library
     * ... and it highlights even Brainfuck!
 
-    The `Pygments tip`_ is installable with ``easy_install Pygments==dev``.
+    The `Pygments master branch`_ is installable with ``easy_install Pygments==dev``.
 
-    .. _Pygments tip:
-       http://bitbucket.org/birkenfeld/pygments-main/get/tip.zip#egg=Pygments-dev
+    .. _Pygments master branch:
+       https://github.com/pygments/pygments/archive/master.zip#egg=Pygments-dev
 
-    :copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2020 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 import sys
+from io import StringIO, BytesIO
 
-from pygments.util import StringIO, BytesIO
-
-__version__ = '2.2a0'
+__version__ = '2.7.3'
 __docformat__ = 'restructuredtext'
 
 __all__ = ['lex', 'format', 'highlight']
@@ -84,7 +83,3 @@ def highlight(code, lexer, formatter, outfile=None):
     """
     return format(lex(code, lexer), formatter, outfile)
 
-
-if __name__ == '__main__':  # pragma: no cover
-    from pygments.cmdline import main
-    sys.exit(main(sys.argv))

data/vendor/pygments-main/pygments/__main__.py

@@ -0,0 +1,18 @@
+# -*- coding: utf-8 -*-
+"""
+    pygments.__main__
+    ~~~~~~~~~~~~~~~~~
+
+    Main entry point for ``python -m pygments``.
+
+    :copyright: Copyright 2006-2020 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import sys
+import pygments.cmdline
+
+try:
+    sys.exit(pygments.cmdline.main(sys.argv))
+except KeyboardInterrupt:
+    sys.exit(1)

data/vendor/pygments-main/pygments/cmdline.py

@@ -5,33 +5,34 @@
 
     Command line interface.
 
-    :copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2020 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
-from __future__ import print_function
-
+import os
 import sys
 import getopt
 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
+    guess_decode, guess_decode_from_terminal, terminal_encoding, \
+    UnclosingTextIOWrapper
 from pygments.lexers import get_all_lexers, get_lexer_by_name, guess_lexer, \
-    get_lexer_for_filename, find_lexer_class_for_filename
+    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, \
-    get_formatter_for_filename, find_formatter_class
+    load_formatter_from_file, get_formatter_for_filename, find_formatter_class
 from pygments.formatters.terminal import TerminalFormatter
+from pygments.formatters.terminal256 import Terminal256Formatter
 from pygments.filters import get_all_filters, find_filter_class
 from pygments.styles import get_all_styles, get_style_by_name
 
 
 USAGE = """\
 Usage: %s [-l <lexer> | -g] [-F <filter>[:<options>]] [-f <formatter>]
-          [-O <options>] [-P <option=value>] [-s] [-v] [-o <outfile>] [<infile>]
+          [-O <options>] [-P <option=value>] [-s] [-v] [-x] [-o <outfile>] [<infile>]
 
        %s -S <style> -f <formatter> [-a <arg>] [-O <options>] [-P <option=value>]
        %s -L [<which> ...]
@@ -57,6 +58,14 @@ Likewise, <formatter> is a formatter name, and will be guessed from
 the extension of the output file name. If no output file is given,
 the terminal formatter will be used by default.
 
+The additional option -x allows 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.
+
 With the -O option, you can give the lexer and formatter a comma-
 separated list of options, e.g. ``-O bg=light,python=cool``.
 
@@ -223,7 +232,7 @@ def main_inner(popts, args, usage):
         return 0
 
     if opts.pop('-V', None) is not None:
-        print('Pygments version %s, (c) 2006-2015 by Georg Brandl.' % __version__)
+        print('Pygments version %s, (c) 2006-2020 by Georg Brandl.' % __version__)
         return 0
 
     # handle ``pygmentize -L``
@@ -314,17 +323,44 @@ def main_inner(popts, args, usage):
     F_opts = _parse_filters(F_opts)
     opts.pop('-F', None)
 
+    allow_custom_lexer_formatter = False
+    # -x: allow custom (eXternal) lexers and formatters
+    if opts.pop('-x', None) is not None:
+        allow_custom_lexer_formatter = True
+
     # select lexer
     lexer = None
 
     # given by name?
     lexername = opts.pop('-l', None)
     if lexername:
-        try:
-            lexer = get_lexer_by_name(lexername, **parsed_opts)
-        except (OptionError, ClassNotFound) as err:
-            print('Error:', err, file=sys.stderr)
-            return 1
+        # 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
@@ -369,11 +405,7 @@ def main_inner(popts, args, usage):
     elif '-s' not in opts:  # 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
-        if sys.version_info > (3,):
-            # Python 3: we have to use .buffer to get a binary stream
-            code = sys.stdin.buffer.read()
-        else:
-            code = sys.stdin.read()
+        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
@@ -401,11 +433,32 @@ def main_inner(popts, args, usage):
     outfn = opts.pop('-o', None)
     fmter = opts.pop('-f', None)
     if fmter:
-        try:
-            fmter = get_formatter_by_name(fmter, **parsed_opts)
-        except (OptionError, ClassNotFound) as err:
-            print('Error:', err, file=sys.stderr)
-            return 1
+        # 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:
@@ -421,12 +474,11 @@ def main_inner(popts, args, usage):
             return 1
     else:
         if not fmter:
-            fmter = TerminalFormatter(**parsed_opts)
-        if sys.version_info > (3,):
-            # Python 3: we have to use .buffer to get a binary stream
-            outfile = sys.stdout.buffer
-        else:
-            outfile = sys.stdout
+            if '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:
@@ -441,10 +493,8 @@ def main_inner(popts, args, usage):
     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
-        if sys.version_info > (3,):
-            from pygments.util import UnclosingTextIOWrapper
-            outfile = UnclosingTextIOWrapper(outfile, encoding=fmter.encoding)
-            fmter.encoding = None
+        outfile = UnclosingTextIOWrapper(outfile, encoding=fmter.encoding)
+        fmter.encoding = None
         try:
             import colorama.initialise
         except ImportError:
@@ -465,17 +515,17 @@ def main_inner(popts, args, usage):
     # ... and do it!
     if '-s' not in opts:
         # process whole input as per normal...
-        highlight(code, lexer, fmter, outfile)
+        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:
-                if sys.version_info > (3,):
-                    # Python 3: we have to use .buffer to get a binary stream
-                    line = sys.stdin.buffer.readline()
-                else:
-                    line = sys.stdin.readline()
+                line = sys.stdin.buffer.readline()
                 if not line:
                     break
                 if not inencoding:
@@ -486,6 +536,9 @@ def main_inner(popts, args, usage):
             return 0
         except KeyboardInterrupt:  # pragma: no cover
             return 0
+        finally:
+            if outfn:
+                outfile.close()
 
 
 def main(args=sys.argv):
@@ -495,7 +548,7 @@ def main(args=sys.argv):
     usage = USAGE % ((args[0],) * 6)
 
     try:
-        popts, args = getopt.getopt(args[1:], "l:f:F:o:O:P:LS:a:N:vhVHgs")
+        popts, args = getopt.getopt(args[1:], "l:f:F:o:O:P:LS:a:N:vhVHgsx")
     except getopt.GetoptError:
         print(usage, file=sys.stderr)
         return 2
@@ -510,7 +563,7 @@ def main(args=sys.argv):
                   file=sys.stderr)
             print('Please report the whole traceback to the issue tracker at',
                   file=sys.stderr)
-            print('<https://bitbucket.org/birkenfeld/pygments-main/issues>.',
+            print('<https://github.com/pygments/pygments/issues>.',
                   file=sys.stderr)
             print('*' * 65, file=sys.stderr)
             print(file=sys.stderr)

data/vendor/pygments-main/pygments/console.py

@@ -5,7 +5,7 @@
 
     Format colored console output.
 
-    :copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2020 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -22,22 +22,19 @@ codes["underline"] = esc + "04m"
 codes["blink"] = esc + "05m"
 codes["overline"] = esc + "06m"
 
-dark_colors = ["black", "darkred", "darkgreen", "brown", "darkblue",
-               "purple", "teal", "lightgray"]
-light_colors = ["darkgray", "red", "green", "yellow", "blue",
-                "fuchsia", "turquoise", "white"]
+dark_colors = ["black", "red", "green", "yellow", "blue",
+               "magenta", "cyan", "gray"]
+light_colors = ["brightblack", "brightred", "brightgreen", "brightyellow", "brightblue",
+                "brightmagenta", "brightcyan", "white"]
 
 x = 30
 for d, l in zip(dark_colors, light_colors):
     codes[d] = esc + "%im" % x
-    codes[l] = esc + "%i;01m" % x
+    codes[l] = esc + "%im" % (60 + x)
     x += 1
 
 del d, l, x
 
-codes["darkteal"] = codes["turquoise"]
-codes["darkyellow"] = codes["brown"]
-codes["fuscia"] = codes["fuchsia"]
 codes["white"] = codes["bold"]
 
 

data/vendor/pygments-main/pygments/filter.py

@@ -5,7 +5,7 @@
 
     Module that implements the default filter.
 
-    :copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2020 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -17,8 +17,7 @@ def apply_filters(stream, filters, lexer=None):
     filter, otherwise the filter receives `None`.
     """
     def _apply(filter_, stream):
-        for token in filter_.filter(lexer, stream):
-            yield token
+        yield from filter_.filter(lexer, stream)
     for filter_ in filters:
         stream = _apply(filter_, stream)
     return stream
@@ -40,7 +39,7 @@ def simplefilter(f):
     })
 
 
-class Filter(object):
+class Filter:
     """
     Default filter. Subclass this class or use the `simplefilter`
     decorator to create own filters.
@@ -70,5 +69,4 @@ class FunctionFilter(Filter):
 
     def filter(self, lexer, stream):
         # pylint: disable=not-callable
-        for ttype, value in self.function(lexer, stream, self.options):
-            yield ttype, value
+        yield from self.function(lexer, stream, self.options)

data/vendor/pygments-main/pygments/filters/__init__.py

@@ -6,7 +6,7 @@
     Module containing filter lookup functions and default
     filters.
 
-    :copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2020 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -16,7 +16,7 @@ from pygments.token import String, Comment, Keyword, Name, Error, Whitespace, \
     string_to_tokentype
 from pygments.filter import Filter
 from pygments.util import get_list_opt, get_int_opt, get_bool_opt, \
-     get_choice_opt, ClassNotFound, OptionError, text_type, string_types
+    get_choice_opt, ClassNotFound, OptionError
 from pygments.plugin import find_plugin_filters
 
 
@@ -45,8 +45,7 @@ def get_filter_by_name(filtername, **options):
 
 def get_all_filters():
     """Return a generator of all filter names."""
-    for name in FILTERS:
-        yield name
+    yield from FILTERS
     for name, _ in find_plugin_filters():
         yield name
 
@@ -88,9 +87,597 @@ class CodeTagFilter(Filter):
             if ttype in String.Doc or \
                ttype in Comment and \
                ttype not in Comment.Preproc:
-                for sttype, svalue in _replace_special(ttype, value, regex,
-                                                       Comment.Special):
-                    yield sttype, svalue
+                yield from _replace_special(ttype, value, regex, Comment.Special)
+            else:
+                yield ttype, value
+
+
+class SymbolFilter(Filter):
+    """Convert mathematical symbols such as \\<longrightarrow> in Isabelle
+    or \\longrightarrow in LaTeX into Unicode characters.
+
+    This is mostly useful for HTML or console output when you want to
+    approximate the source rendering you'd see in an IDE.
+
+    Options accepted:
+
+    `lang` : string
+       The symbol language. Must be one of ``'isabelle'`` or
+       ``'latex'``.  The default is ``'isabelle'``.
+    """
+
+    latex_symbols = {
+        '\\alpha'                : '\U000003b1',
+        '\\beta'                 : '\U000003b2',
+        '\\gamma'                : '\U000003b3',
+        '\\delta'                : '\U000003b4',
+        '\\varepsilon'           : '\U000003b5',
+        '\\zeta'                 : '\U000003b6',
+        '\\eta'                  : '\U000003b7',
+        '\\vartheta'             : '\U000003b8',
+        '\\iota'                 : '\U000003b9',
+        '\\kappa'                : '\U000003ba',
+        '\\lambda'               : '\U000003bb',
+        '\\mu'                   : '\U000003bc',
+        '\\nu'                   : '\U000003bd',
+        '\\xi'                   : '\U000003be',
+        '\\pi'                   : '\U000003c0',
+        '\\varrho'               : '\U000003c1',
+        '\\sigma'                : '\U000003c3',
+        '\\tau'                  : '\U000003c4',
+        '\\upsilon'              : '\U000003c5',
+        '\\varphi'               : '\U000003c6',
+        '\\chi'                  : '\U000003c7',
+        '\\psi'                  : '\U000003c8',
+        '\\omega'                : '\U000003c9',
+        '\\Gamma'                : '\U00000393',
+        '\\Delta'                : '\U00000394',
+        '\\Theta'                : '\U00000398',
+        '\\Lambda'               : '\U0000039b',
+        '\\Xi'                   : '\U0000039e',
+        '\\Pi'                   : '\U000003a0',
+        '\\Sigma'                : '\U000003a3',
+        '\\Upsilon'              : '\U000003a5',
+        '\\Phi'                  : '\U000003a6',
+        '\\Psi'                  : '\U000003a8',
+        '\\Omega'                : '\U000003a9',
+        '\\leftarrow'            : '\U00002190',
+        '\\longleftarrow'        : '\U000027f5',
+        '\\rightarrow'           : '\U00002192',
+        '\\longrightarrow'       : '\U000027f6',
+        '\\Leftarrow'            : '\U000021d0',
+        '\\Longleftarrow'        : '\U000027f8',
+        '\\Rightarrow'           : '\U000021d2',
+        '\\Longrightarrow'       : '\U000027f9',
+        '\\leftrightarrow'       : '\U00002194',
+        '\\longleftrightarrow'   : '\U000027f7',
+        '\\Leftrightarrow'       : '\U000021d4',
+        '\\Longleftrightarrow'   : '\U000027fa',
+        '\\mapsto'               : '\U000021a6',
+        '\\longmapsto'           : '\U000027fc',
+        '\\relbar'               : '\U00002500',
+        '\\Relbar'               : '\U00002550',
+        '\\hookleftarrow'        : '\U000021a9',
+        '\\hookrightarrow'       : '\U000021aa',
+        '\\leftharpoondown'      : '\U000021bd',
+        '\\rightharpoondown'     : '\U000021c1',
+        '\\leftharpoonup'        : '\U000021bc',
+        '\\rightharpoonup'       : '\U000021c0',
+        '\\rightleftharpoons'    : '\U000021cc',
+        '\\leadsto'              : '\U0000219d',
+        '\\downharpoonleft'      : '\U000021c3',
+        '\\downharpoonright'     : '\U000021c2',
+        '\\upharpoonleft'        : '\U000021bf',
+        '\\upharpoonright'       : '\U000021be',
+        '\\restriction'          : '\U000021be',
+        '\\uparrow'              : '\U00002191',
+        '\\Uparrow'              : '\U000021d1',
+        '\\downarrow'            : '\U00002193',
+        '\\Downarrow'            : '\U000021d3',
+        '\\updownarrow'          : '\U00002195',
+        '\\Updownarrow'          : '\U000021d5',
+        '\\langle'               : '\U000027e8',
+        '\\rangle'               : '\U000027e9',
+        '\\lceil'                : '\U00002308',
+        '\\rceil'                : '\U00002309',
+        '\\lfloor'               : '\U0000230a',
+        '\\rfloor'               : '\U0000230b',
+        '\\flqq'                 : '\U000000ab',
+        '\\frqq'                 : '\U000000bb',
+        '\\bot'                  : '\U000022a5',
+        '\\top'                  : '\U000022a4',
+        '\\wedge'                : '\U00002227',
+        '\\bigwedge'             : '\U000022c0',
+        '\\vee'                  : '\U00002228',
+        '\\bigvee'               : '\U000022c1',
+        '\\forall'               : '\U00002200',
+        '\\exists'               : '\U00002203',
+        '\\nexists'              : '\U00002204',
+        '\\neg'                  : '\U000000ac',
+        '\\Box'                  : '\U000025a1',
+        '\\Diamond'              : '\U000025c7',
+        '\\vdash'                : '\U000022a2',
+        '\\models'               : '\U000022a8',
+        '\\dashv'                : '\U000022a3',
+        '\\surd'                 : '\U0000221a',
+        '\\le'                   : '\U00002264',
+        '\\ge'                   : '\U00002265',
+        '\\ll'                   : '\U0000226a',
+        '\\gg'                   : '\U0000226b',
+        '\\lesssim'              : '\U00002272',
+        '\\gtrsim'               : '\U00002273',
+        '\\lessapprox'           : '\U00002a85',
+        '\\gtrapprox'            : '\U00002a86',
+        '\\in'                   : '\U00002208',
+        '\\notin'                : '\U00002209',
+        '\\subset'               : '\U00002282',
+        '\\supset'               : '\U00002283',
+        '\\subseteq'             : '\U00002286',
+        '\\supseteq'             : '\U00002287',
+        '\\sqsubset'             : '\U0000228f',
+        '\\sqsupset'             : '\U00002290',
+        '\\sqsubseteq'           : '\U00002291',
+        '\\sqsupseteq'           : '\U00002292',
+        '\\cap'                  : '\U00002229',
+        '\\bigcap'               : '\U000022c2',
+        '\\cup'                  : '\U0000222a',
+        '\\bigcup'               : '\U000022c3',
+        '\\sqcup'                : '\U00002294',
+        '\\bigsqcup'             : '\U00002a06',
+        '\\sqcap'                : '\U00002293',
+        '\\Bigsqcap'             : '\U00002a05',
+        '\\setminus'             : '\U00002216',
+        '\\propto'               : '\U0000221d',
+        '\\uplus'                : '\U0000228e',
+        '\\bigplus'              : '\U00002a04',
+        '\\sim'                  : '\U0000223c',
+        '\\doteq'                : '\U00002250',
+        '\\simeq'                : '\U00002243',
+        '\\approx'               : '\U00002248',
+        '\\asymp'                : '\U0000224d',
+        '\\cong'                 : '\U00002245',
+        '\\equiv'                : '\U00002261',
+        '\\Join'                 : '\U000022c8',
+        '\\bowtie'               : '\U00002a1d',
+        '\\prec'                 : '\U0000227a',
+        '\\succ'                 : '\U0000227b',
+        '\\preceq'               : '\U0000227c',
+        '\\succeq'               : '\U0000227d',
+        '\\parallel'             : '\U00002225',
+        '\\mid'                  : '\U000000a6',
+        '\\pm'                   : '\U000000b1',
+        '\\mp'                   : '\U00002213',
+        '\\times'                : '\U000000d7',
+        '\\div'                  : '\U000000f7',
+        '\\cdot'                 : '\U000022c5',
+        '\\star'                 : '\U000022c6',
+        '\\circ'                 : '\U00002218',
+        '\\dagger'               : '\U00002020',
+        '\\ddagger'              : '\U00002021',
+        '\\lhd'                  : '\U000022b2',
+        '\\rhd'                  : '\U000022b3',
+        '\\unlhd'                : '\U000022b4',
+        '\\unrhd'                : '\U000022b5',
+        '\\triangleleft'         : '\U000025c3',
+        '\\triangleright'        : '\U000025b9',
+        '\\triangle'             : '\U000025b3',
+        '\\triangleq'            : '\U0000225c',
+        '\\oplus'                : '\U00002295',
+        '\\bigoplus'             : '\U00002a01',
+        '\\otimes'               : '\U00002297',
+        '\\bigotimes'            : '\U00002a02',
+        '\\odot'                 : '\U00002299',
+        '\\bigodot'              : '\U00002a00',
+        '\\ominus'               : '\U00002296',
+        '\\oslash'               : '\U00002298',
+        '\\dots'                 : '\U00002026',
+        '\\cdots'                : '\U000022ef',
+        '\\sum'                  : '\U00002211',
+        '\\prod'                 : '\U0000220f',
+        '\\coprod'               : '\U00002210',
+        '\\infty'                : '\U0000221e',
+        '\\int'                  : '\U0000222b',
+        '\\oint'                 : '\U0000222e',
+        '\\clubsuit'             : '\U00002663',
+        '\\diamondsuit'          : '\U00002662',
+        '\\heartsuit'            : '\U00002661',
+        '\\spadesuit'            : '\U00002660',
+        '\\aleph'                : '\U00002135',
+        '\\emptyset'             : '\U00002205',
+        '\\nabla'                : '\U00002207',
+        '\\partial'              : '\U00002202',
+        '\\flat'                 : '\U0000266d',
+        '\\natural'              : '\U0000266e',
+        '\\sharp'                : '\U0000266f',
+        '\\angle'                : '\U00002220',
+        '\\copyright'            : '\U000000a9',
+        '\\textregistered'       : '\U000000ae',
+        '\\textonequarter'       : '\U000000bc',
+        '\\textonehalf'          : '\U000000bd',
+        '\\textthreequarters'    : '\U000000be',
+        '\\textordfeminine'      : '\U000000aa',
+        '\\textordmasculine'     : '\U000000ba',
+        '\\euro'                 : '\U000020ac',
+        '\\pounds'               : '\U000000a3',
+        '\\yen'                  : '\U000000a5',
+        '\\textcent'             : '\U000000a2',
+        '\\textcurrency'         : '\U000000a4',
+        '\\textdegree'           : '\U000000b0',
+    }
+
+    isabelle_symbols = {
+        '\\<zero>'                 : '\U0001d7ec',
+        '\\<one>'                  : '\U0001d7ed',
+        '\\<two>'                  : '\U0001d7ee',
+        '\\<three>'                : '\U0001d7ef',
+        '\\<four>'                 : '\U0001d7f0',
+        '\\<five>'                 : '\U0001d7f1',
+        '\\<six>'                  : '\U0001d7f2',
+        '\\<seven>'                : '\U0001d7f3',
+        '\\<eight>'                : '\U0001d7f4',
+        '\\<nine>'                 : '\U0001d7f5',
+        '\\<A>'                    : '\U0001d49c',
+        '\\<B>'                    : '\U0000212c',
+        '\\<C>'                    : '\U0001d49e',
+        '\\<D>'                    : '\U0001d49f',
+        '\\<E>'                    : '\U00002130',
+        '\\<F>'                    : '\U00002131',
+        '\\<G>'                    : '\U0001d4a2',
+        '\\<H>'                    : '\U0000210b',
+        '\\<I>'                    : '\U00002110',
+        '\\<J>'                    : '\U0001d4a5',
+        '\\<K>'                    : '\U0001d4a6',
+        '\\<L>'                    : '\U00002112',
+        '\\<M>'                    : '\U00002133',
+        '\\<N>'                    : '\U0001d4a9',
+        '\\<O>'                    : '\U0001d4aa',
+        '\\<P>'                    : '\U0001d4ab',
+        '\\<Q>'                    : '\U0001d4ac',
+        '\\<R>'                    : '\U0000211b',
+        '\\<S>'                    : '\U0001d4ae',
+        '\\<T>'                    : '\U0001d4af',
+        '\\<U>'                    : '\U0001d4b0',
+        '\\<V>'                    : '\U0001d4b1',
+        '\\<W>'                    : '\U0001d4b2',
+        '\\<X>'                    : '\U0001d4b3',
+        '\\<Y>'                    : '\U0001d4b4',
+        '\\<Z>'                    : '\U0001d4b5',
+        '\\<a>'                    : '\U0001d5ba',
+        '\\<b>'                    : '\U0001d5bb',
+        '\\<c>'                    : '\U0001d5bc',
+        '\\<d>'                    : '\U0001d5bd',
+        '\\<e>'                    : '\U0001d5be',
+        '\\<f>'                    : '\U0001d5bf',
+        '\\<g>'                    : '\U0001d5c0',
+        '\\<h>'                    : '\U0001d5c1',
+        '\\<i>'                    : '\U0001d5c2',
+        '\\<j>'                    : '\U0001d5c3',
+        '\\<k>'                    : '\U0001d5c4',
+        '\\<l>'                    : '\U0001d5c5',
+        '\\<m>'                    : '\U0001d5c6',
+        '\\<n>'                    : '\U0001d5c7',
+        '\\<o>'                    : '\U0001d5c8',
+        '\\<p>'                    : '\U0001d5c9',
+        '\\<q>'                    : '\U0001d5ca',
+        '\\<r>'                    : '\U0001d5cb',
+        '\\<s>'                    : '\U0001d5cc',
+        '\\<t>'                    : '\U0001d5cd',
+        '\\<u>'                    : '\U0001d5ce',
+        '\\<v>'                    : '\U0001d5cf',
+        '\\<w>'                    : '\U0001d5d0',
+        '\\<x>'                    : '\U0001d5d1',
+        '\\<y>'                    : '\U0001d5d2',
+        '\\<z>'                    : '\U0001d5d3',
+        '\\<AA>'                   : '\U0001d504',
+        '\\<BB>'                   : '\U0001d505',
+        '\\<CC>'                   : '\U0000212d',
+        '\\<DD>'                   : '\U0001d507',
+        '\\<EE>'                   : '\U0001d508',
+        '\\<FF>'                   : '\U0001d509',
+        '\\<GG>'                   : '\U0001d50a',
+        '\\<HH>'                   : '\U0000210c',
+        '\\<II>'                   : '\U00002111',
+        '\\<JJ>'                   : '\U0001d50d',
+        '\\<KK>'                   : '\U0001d50e',
+        '\\<LL>'                   : '\U0001d50f',
+        '\\<MM>'                   : '\U0001d510',
+        '\\<NN>'                   : '\U0001d511',
+        '\\<OO>'                   : '\U0001d512',
+        '\\<PP>'                   : '\U0001d513',
+        '\\<QQ>'                   : '\U0001d514',
+        '\\<RR>'                   : '\U0000211c',
+        '\\<SS>'                   : '\U0001d516',
+        '\\<TT>'                   : '\U0001d517',
+        '\\<UU>'                   : '\U0001d518',
+        '\\<VV>'                   : '\U0001d519',
+        '\\<WW>'                   : '\U0001d51a',
+        '\\<XX>'                   : '\U0001d51b',
+        '\\<YY>'                   : '\U0001d51c',
+        '\\<ZZ>'                   : '\U00002128',
+        '\\<aa>'                   : '\U0001d51e',
+        '\\<bb>'                   : '\U0001d51f',
+        '\\<cc>'                   : '\U0001d520',
+        '\\<dd>'                   : '\U0001d521',
+        '\\<ee>'                   : '\U0001d522',
+        '\\<ff>'                   : '\U0001d523',
+        '\\<gg>'                   : '\U0001d524',
+        '\\<hh>'                   : '\U0001d525',
+        '\\<ii>'                   : '\U0001d526',
+        '\\<jj>'                   : '\U0001d527',
+        '\\<kk>'                   : '\U0001d528',
+        '\\<ll>'                   : '\U0001d529',
+        '\\<mm>'                   : '\U0001d52a',
+        '\\<nn>'                   : '\U0001d52b',
+        '\\<oo>'                   : '\U0001d52c',
+        '\\<pp>'                   : '\U0001d52d',
+        '\\<qq>'                   : '\U0001d52e',
+        '\\<rr>'                   : '\U0001d52f',
+        '\\<ss>'                   : '\U0001d530',
+        '\\<tt>'                   : '\U0001d531',
+        '\\<uu>'                   : '\U0001d532',
+        '\\<vv>'                   : '\U0001d533',
+        '\\<ww>'                   : '\U0001d534',
+        '\\<xx>'                   : '\U0001d535',
+        '\\<yy>'                   : '\U0001d536',
+        '\\<zz>'                   : '\U0001d537',
+        '\\<alpha>'                : '\U000003b1',
+        '\\<beta>'                 : '\U000003b2',
+        '\\<gamma>'                : '\U000003b3',
+        '\\<delta>'                : '\U000003b4',
+        '\\<epsilon>'              : '\U000003b5',
+        '\\<zeta>'                 : '\U000003b6',
+        '\\<eta>'                  : '\U000003b7',
+        '\\<theta>'                : '\U000003b8',
+        '\\<iota>'                 : '\U000003b9',
+        '\\<kappa>'                : '\U000003ba',
+        '\\<lambda>'               : '\U000003bb',
+        '\\<mu>'                   : '\U000003bc',
+        '\\<nu>'                   : '\U000003bd',
+        '\\<xi>'                   : '\U000003be',
+        '\\<pi>'                   : '\U000003c0',
+        '\\<rho>'                  : '\U000003c1',
+        '\\<sigma>'                : '\U000003c3',
+        '\\<tau>'                  : '\U000003c4',
+        '\\<upsilon>'              : '\U000003c5',
+        '\\<phi>'                  : '\U000003c6',
+        '\\<chi>'                  : '\U000003c7',
+        '\\<psi>'                  : '\U000003c8',
+        '\\<omega>'                : '\U000003c9',
+        '\\<Gamma>'                : '\U00000393',
+        '\\<Delta>'                : '\U00000394',
+        '\\<Theta>'                : '\U00000398',
+        '\\<Lambda>'               : '\U0000039b',
+        '\\<Xi>'                   : '\U0000039e',
+        '\\<Pi>'                   : '\U000003a0',
+        '\\<Sigma>'                : '\U000003a3',
+        '\\<Upsilon>'              : '\U000003a5',
+        '\\<Phi>'                  : '\U000003a6',
+        '\\<Psi>'                  : '\U000003a8',
+        '\\<Omega>'                : '\U000003a9',
+        '\\<bool>'                 : '\U0001d539',
+        '\\<complex>'              : '\U00002102',
+        '\\<nat>'                  : '\U00002115',
+        '\\<rat>'                  : '\U0000211a',
+        '\\<real>'                 : '\U0000211d',
+        '\\<int>'                  : '\U00002124',
+        '\\<leftarrow>'            : '\U00002190',
+        '\\<longleftarrow>'        : '\U000027f5',
+        '\\<rightarrow>'           : '\U00002192',
+        '\\<longrightarrow>'       : '\U000027f6',
+        '\\<Leftarrow>'            : '\U000021d0',
+        '\\<Longleftarrow>'        : '\U000027f8',
+        '\\<Rightarrow>'           : '\U000021d2',
+        '\\<Longrightarrow>'       : '\U000027f9',
+        '\\<leftrightarrow>'       : '\U00002194',
+        '\\<longleftrightarrow>'   : '\U000027f7',
+        '\\<Leftrightarrow>'       : '\U000021d4',
+        '\\<Longleftrightarrow>'   : '\U000027fa',
+        '\\<mapsto>'               : '\U000021a6',
+        '\\<longmapsto>'           : '\U000027fc',
+        '\\<midarrow>'             : '\U00002500',
+        '\\<Midarrow>'             : '\U00002550',
+        '\\<hookleftarrow>'        : '\U000021a9',
+        '\\<hookrightarrow>'       : '\U000021aa',
+        '\\<leftharpoondown>'      : '\U000021bd',
+        '\\<rightharpoondown>'     : '\U000021c1',
+        '\\<leftharpoonup>'        : '\U000021bc',
+        '\\<rightharpoonup>'       : '\U000021c0',
+        '\\<rightleftharpoons>'    : '\U000021cc',
+        '\\<leadsto>'              : '\U0000219d',
+        '\\<downharpoonleft>'      : '\U000021c3',
+        '\\<downharpoonright>'     : '\U000021c2',
+        '\\<upharpoonleft>'        : '\U000021bf',
+        '\\<upharpoonright>'       : '\U000021be',
+        '\\<restriction>'          : '\U000021be',
+        '\\<Colon>'                : '\U00002237',
+        '\\<up>'                   : '\U00002191',
+        '\\<Up>'                   : '\U000021d1',
+        '\\<down>'                 : '\U00002193',
+        '\\<Down>'                 : '\U000021d3',
+        '\\<updown>'               : '\U00002195',
+        '\\<Updown>'               : '\U000021d5',
+        '\\<langle>'               : '\U000027e8',
+        '\\<rangle>'               : '\U000027e9',
+        '\\<lceil>'                : '\U00002308',
+        '\\<rceil>'                : '\U00002309',
+        '\\<lfloor>'               : '\U0000230a',
+        '\\<rfloor>'               : '\U0000230b',
+        '\\<lparr>'                : '\U00002987',
+        '\\<rparr>'                : '\U00002988',
+        '\\<lbrakk>'               : '\U000027e6',
+        '\\<rbrakk>'               : '\U000027e7',
+        '\\<lbrace>'               : '\U00002983',
+        '\\<rbrace>'               : '\U00002984',
+        '\\<guillemotleft>'        : '\U000000ab',
+        '\\<guillemotright>'       : '\U000000bb',
+        '\\<bottom>'               : '\U000022a5',
+        '\\<top>'                  : '\U000022a4',
+        '\\<and>'                  : '\U00002227',
+        '\\<And>'                  : '\U000022c0',
+        '\\<or>'                   : '\U00002228',
+        '\\<Or>'                   : '\U000022c1',
+        '\\<forall>'               : '\U00002200',
+        '\\<exists>'               : '\U00002203',
+        '\\<nexists>'              : '\U00002204',
+        '\\<not>'                  : '\U000000ac',
+        '\\<box>'                  : '\U000025a1',
+        '\\<diamond>'              : '\U000025c7',
+        '\\<turnstile>'            : '\U000022a2',
+        '\\<Turnstile>'            : '\U000022a8',
+        '\\<tturnstile>'           : '\U000022a9',
+        '\\<TTurnstile>'           : '\U000022ab',
+        '\\<stileturn>'            : '\U000022a3',
+        '\\<surd>'                 : '\U0000221a',
+        '\\<le>'                   : '\U00002264',
+        '\\<ge>'                   : '\U00002265',
+        '\\<lless>'                : '\U0000226a',
+        '\\<ggreater>'             : '\U0000226b',
+        '\\<lesssim>'              : '\U00002272',
+        '\\<greatersim>'           : '\U00002273',
+        '\\<lessapprox>'           : '\U00002a85',
+        '\\<greaterapprox>'        : '\U00002a86',
+        '\\<in>'                   : '\U00002208',
+        '\\<notin>'                : '\U00002209',
+        '\\<subset>'               : '\U00002282',
+        '\\<supset>'               : '\U00002283',
+        '\\<subseteq>'             : '\U00002286',
+        '\\<supseteq>'             : '\U00002287',
+        '\\<sqsubset>'             : '\U0000228f',
+        '\\<sqsupset>'             : '\U00002290',
+        '\\<sqsubseteq>'           : '\U00002291',
+        '\\<sqsupseteq>'           : '\U00002292',
+        '\\<inter>'                : '\U00002229',
+        '\\<Inter>'                : '\U000022c2',
+        '\\<union>'                : '\U0000222a',
+        '\\<Union>'                : '\U000022c3',
+        '\\<squnion>'              : '\U00002294',
+        '\\<Squnion>'              : '\U00002a06',
+        '\\<sqinter>'              : '\U00002293',
+        '\\<Sqinter>'              : '\U00002a05',
+        '\\<setminus>'             : '\U00002216',
+        '\\<propto>'               : '\U0000221d',
+        '\\<uplus>'                : '\U0000228e',
+        '\\<Uplus>'                : '\U00002a04',
+        '\\<noteq>'                : '\U00002260',
+        '\\<sim>'                  : '\U0000223c',
+        '\\<doteq>'                : '\U00002250',
+        '\\<simeq>'                : '\U00002243',
+        '\\<approx>'               : '\U00002248',
+        '\\<asymp>'                : '\U0000224d',
+        '\\<cong>'                 : '\U00002245',
+        '\\<smile>'                : '\U00002323',
+        '\\<equiv>'                : '\U00002261',
+        '\\<frown>'                : '\U00002322',
+        '\\<Join>'                 : '\U000022c8',
+        '\\<bowtie>'               : '\U00002a1d',
+        '\\<prec>'                 : '\U0000227a',
+        '\\<succ>'                 : '\U0000227b',
+        '\\<preceq>'               : '\U0000227c',
+        '\\<succeq>'               : '\U0000227d',
+        '\\<parallel>'             : '\U00002225',
+        '\\<bar>'                  : '\U000000a6',
+        '\\<plusminus>'            : '\U000000b1',
+        '\\<minusplus>'            : '\U00002213',
+        '\\<times>'                : '\U000000d7',
+        '\\<div>'                  : '\U000000f7',
+        '\\<cdot>'                 : '\U000022c5',
+        '\\<star>'                 : '\U000022c6',
+        '\\<bullet>'               : '\U00002219',
+        '\\<circ>'                 : '\U00002218',
+        '\\<dagger>'               : '\U00002020',
+        '\\<ddagger>'              : '\U00002021',
+        '\\<lhd>'                  : '\U000022b2',
+        '\\<rhd>'                  : '\U000022b3',
+        '\\<unlhd>'                : '\U000022b4',
+        '\\<unrhd>'                : '\U000022b5',
+        '\\<triangleleft>'         : '\U000025c3',
+        '\\<triangleright>'        : '\U000025b9',
+        '\\<triangle>'             : '\U000025b3',
+        '\\<triangleq>'            : '\U0000225c',
+        '\\<oplus>'                : '\U00002295',
+        '\\<Oplus>'                : '\U00002a01',
+        '\\<otimes>'               : '\U00002297',
+        '\\<Otimes>'               : '\U00002a02',
+        '\\<odot>'                 : '\U00002299',
+        '\\<Odot>'                 : '\U00002a00',
+        '\\<ominus>'               : '\U00002296',
+        '\\<oslash>'               : '\U00002298',
+        '\\<dots>'                 : '\U00002026',
+        '\\<cdots>'                : '\U000022ef',
+        '\\<Sum>'                  : '\U00002211',
+        '\\<Prod>'                 : '\U0000220f',
+        '\\<Coprod>'               : '\U00002210',
+        '\\<infinity>'             : '\U0000221e',
+        '\\<integral>'             : '\U0000222b',
+        '\\<ointegral>'            : '\U0000222e',
+        '\\<clubsuit>'             : '\U00002663',
+        '\\<diamondsuit>'          : '\U00002662',
+        '\\<heartsuit>'            : '\U00002661',
+        '\\<spadesuit>'            : '\U00002660',
+        '\\<aleph>'                : '\U00002135',
+        '\\<emptyset>'             : '\U00002205',
+        '\\<nabla>'                : '\U00002207',
+        '\\<partial>'              : '\U00002202',
+        '\\<flat>'                 : '\U0000266d',
+        '\\<natural>'              : '\U0000266e',
+        '\\<sharp>'                : '\U0000266f',
+        '\\<angle>'                : '\U00002220',
+        '\\<copyright>'            : '\U000000a9',
+        '\\<registered>'           : '\U000000ae',
+        '\\<hyphen>'               : '\U000000ad',
+        '\\<inverse>'              : '\U000000af',
+        '\\<onequarter>'           : '\U000000bc',
+        '\\<onehalf>'              : '\U000000bd',
+        '\\<threequarters>'        : '\U000000be',
+        '\\<ordfeminine>'          : '\U000000aa',
+        '\\<ordmasculine>'         : '\U000000ba',
+        '\\<section>'              : '\U000000a7',
+        '\\<paragraph>'            : '\U000000b6',
+        '\\<exclamdown>'           : '\U000000a1',
+        '\\<questiondown>'         : '\U000000bf',
+        '\\<euro>'                 : '\U000020ac',
+        '\\<pounds>'               : '\U000000a3',
+        '\\<yen>'                  : '\U000000a5',
+        '\\<cent>'                 : '\U000000a2',
+        '\\<currency>'             : '\U000000a4',
+        '\\<degree>'               : '\U000000b0',
+        '\\<amalg>'                : '\U00002a3f',
+        '\\<mho>'                  : '\U00002127',
+        '\\<lozenge>'              : '\U000025ca',
+        '\\<wp>'                   : '\U00002118',
+        '\\<wrong>'                : '\U00002240',
+        '\\<struct>'               : '\U000022c4',
+        '\\<acute>'                : '\U000000b4',
+        '\\<index>'                : '\U00000131',
+        '\\<dieresis>'             : '\U000000a8',
+        '\\<cedilla>'              : '\U000000b8',
+        '\\<hungarumlaut>'         : '\U000002dd',
+        '\\<some>'                 : '\U000003f5',
+        '\\<newline>'              : '\U000023ce',
+        '\\<open>'                 : '\U00002039',
+        '\\<close>'                : '\U0000203a',
+        '\\<here>'                 : '\U00002302',
+        '\\<^sub>'                 : '\U000021e9',
+        '\\<^sup>'                 : '\U000021e7',
+        '\\<^bold>'                : '\U00002759',
+        '\\<^bsub>'                : '\U000021d8',
+        '\\<^esub>'                : '\U000021d9',
+        '\\<^bsup>'                : '\U000021d7',
+        '\\<^esup>'                : '\U000021d6',
+    }
+
+    lang_map = {'isabelle' : isabelle_symbols, 'latex' : latex_symbols}
+
+    def __init__(self, **options):
+        Filter.__init__(self, **options)
+        lang = get_choice_opt(options, 'lang',
+                              ['isabelle', 'latex'], 'isabelle')
+        self.symbols = self.lang_map[lang]
+
+    def filter(self, lexer, stream):
+        for ttype, value in stream:
+            if value in self.symbols:
+                yield ttype, self.symbols[value]
             else:
                 yield ttype, value
 
@@ -113,7 +700,7 @@ class KeywordCaseFilter(Filter):
         Filter.__init__(self, **options)
         case = get_choice_opt(options, 'case',
                               ['lower', 'upper', 'capitalize'], 'lower')
-        self.convert = getattr(text_type, case)
+        self.convert = getattr(str, case)
 
     def filter(self, lexer, stream):
         for ttype, value in stream:
@@ -229,11 +816,11 @@ class VisibleWhitespaceFilter(Filter):
 
     def __init__(self, **options):
         Filter.__init__(self, **options)
-        for name, default in [('spaces',   u'·'),
-                              ('tabs',     u'»'),
-                              ('newlines', u'¶')]:
+        for name, default in [('spaces',   '·'),
+                              ('tabs',     '»'),
+                              ('newlines', '¶')]:
             opt = options.get(name, False)
-            if isinstance(opt, string_types) and len(opt) == 1:
+            if isinstance(opt, str) and len(opt) == 1:
                 setattr(self, name, opt)
             else:
                 setattr(self, name, (opt and default or ''))
@@ -246,10 +833,11 @@ class VisibleWhitespaceFilter(Filter):
 
     def filter(self, lexer, stream):
         if self.wstt:
-            spaces = self.spaces or u' '
-            tabs = self.tabs or u'\t'
-            newlines = self.newlines or u'\n'
+            spaces = self.spaces or ' '
+            tabs = self.tabs or '\t'
+            newlines = self.newlines or '\n'
             regex = re.compile(r'\s')
+
             def replacefunc(wschar):
                 if wschar == ' ':
                     return spaces
@@ -260,9 +848,8 @@ class VisibleWhitespaceFilter(Filter):
                 return wschar
 
             for ttype, value in stream:
-                for sttype, svalue in _replace_special(ttype, value, regex,
-                                                       Whitespace, replacefunc):
-                    yield sttype, svalue
+                yield from _replace_special(ttype, value, regex, Whitespace,
+                                            replacefunc)
         else:
             spaces, tabs, newlines = self.spaces, self.tabs, self.newlines
             # simpler processing
@@ -298,18 +885,18 @@ class GobbleFilter(Filter):
         if left < len(value):
             return value[left:], 0
         else:
-            return u'', left - len(value)
+            return '', left - len(value)
 
     def filter(self, lexer, stream):
         n = self.n
-        left = n # How many characters left to gobble.
+        left = n  # How many characters left to gobble.
         for ttype, value in stream:
             # Remove ``left`` tokens from first line, ``n`` from all others.
             parts = value.split('\n')
             (parts[0], left) = self.gobble(parts[0], left)
             for i in range(1, len(parts)):
                 (parts[i], left) = self.gobble(parts[i], n)
-            value = u'\n'.join(parts)
+            value = '\n'.join(parts)
 
             if value != '':
                 yield ttype, value
@@ -347,4 +934,5 @@ FILTERS = {
     'whitespace':     VisibleWhitespaceFilter,
     'gobble':         GobbleFilter,
     'tokenmerge':     TokenMergeFilter,
+    'symbols':        SymbolFilter,
 }