upgraded wakatime package

This commit is contained in:
Alan Hamlett 2013-09-22 15:24:50 -07:00
parent c3e08623c1
commit b836f26226
155 changed files with 48554 additions and 2 deletions

View file

@ -0,0 +1,91 @@
# -*- coding: utf-8 -*-
"""
Pygments
~~~~~~~~
Pygments is a syntax highlighting package written in Python.
It is a generic syntax highlighter for general use in all kinds of software
such as forum systems, wikis or other applications that need to prettify
source code. Highlights are:
* a wide range of common languages and markup formats is supported
* special attention is paid to details, increasing quality by a fair amount
* support for new languages and formats are added easily
* a number of output formats, presently HTML, LaTeX, RTF, SVG, all image
formats that PIL supports, and ANSI sequences
* 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``.
.. _Pygments tip:
http://bitbucket.org/birkenfeld/pygments-main/get/tip.zip#egg=Pygments-dev
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
__version__ = '1.6'
__docformat__ = 'restructuredtext'
__all__ = ['lex', 'format', 'highlight']
import sys
from pygments.util import StringIO, BytesIO
def lex(code, lexer):
"""
Lex ``code`` with ``lexer`` and return an iterable of tokens.
"""
try:
return lexer.get_tokens(code)
except TypeError, err:
if isinstance(err.args[0], str) and \
'unbound method get_tokens' in err.args[0]:
raise TypeError('lex() argument must be a lexer instance, '
'not a class')
raise
def format(tokens, formatter, outfile=None):
"""
Format a tokenlist ``tokens`` with the formatter ``formatter``.
If ``outfile`` is given and a valid file object (an object
with a ``write`` method), the result will be written to it, otherwise
it is returned as a string.
"""
try:
if not outfile:
#print formatter, 'using', formatter.encoding
realoutfile = formatter.encoding and BytesIO() or StringIO()
formatter.format(tokens, realoutfile)
return realoutfile.getvalue()
else:
formatter.format(tokens, outfile)
except TypeError, err:
if isinstance(err.args[0], str) and \
'unbound method format' in err.args[0]:
raise TypeError('format() argument must be a formatter instance, '
'not a class')
raise
def highlight(code, lexer, formatter, outfile=None):
"""
Lex ``code`` with ``lexer`` and format it with the formatter ``formatter``.
If ``outfile`` is given and a valid file object (an object
with a ``write`` method), the result will be written to it, otherwise
it is returned as a string.
"""
return format(lex(code, lexer), formatter, outfile)
if __name__ == '__main__':
from pygments.cmdline import main
sys.exit(main(sys.argv))

View file

@ -0,0 +1,441 @@
# -*- coding: utf-8 -*-
"""
pygments.cmdline
~~~~~~~~~~~~~~~~
Command line interface.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import sys
import getopt
from textwrap import dedent
from pygments import __version__, highlight
from pygments.util import ClassNotFound, OptionError, docstring_headline
from pygments.lexers import get_all_lexers, get_lexer_by_name, get_lexer_for_filename, \
find_lexer_class, guess_lexer, TextLexer
from pygments.formatters import get_all_formatters, get_formatter_by_name, \
get_formatter_for_filename, find_formatter_class, \
TerminalFormatter # pylint:disable-msg=E0611
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>] [-o <outfile>] [<infile>]
%s -S <style> -f <formatter> [-a <arg>] [-O <options>] [-P <option=value>]
%s -L [<which> ...]
%s -N <filename>
%s -H <type> <name>
%s -h | -V
Highlight the input file and write the result to <outfile>.
If no input file is given, use stdin, if -o is not given, use stdout.
<lexer> is a lexer name (query all lexer names with -L). If -l is not
given, the lexer is guessed from the extension of the input file name
(this obviously doesn't work if the input is stdin). If -g is passed,
attempt to guess the lexer from the file contents, or pass through as
plain text if this fails (this can work for stdin).
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.
With the -O option, you can give the lexer and formatter a comma-
separated list of options, e.g. ``-O bg=light,python=cool``.
The -P option adds lexer and formatter options like the -O option, but
you can only give one option per -P. That way, the option value may
contain commas and equals signs, which it can't with -O, e.g.
``-P "heading=Pygments, the Python highlighter".
With the -F option, you can add filters to the token stream, you can
give options in the same way as for -O after a colon (note: there must
not be spaces around the colon).
The -O, -P and -F options can be given multiple times.
With the -S option, print out style definitions for style <style>
for formatter <formatter>. The argument given by -a is formatter
dependent.
The -L option lists lexers, formatters, styles or filters -- set
`which` to the thing you want to list (e.g. "styles"), or omit it to
list everything.
The -N option guesses and prints out a lexer name based solely on
the given filename. It does not take input or highlight anything.
If no specific lexer can be determined "text" is returned.
The -H option prints detailed help for the object <name> of type <type>,
where <type> is one of "lexer", "formatter" or "filter".
The -h option prints this help.
The -V option prints the package version.
"""
def _parse_options(o_strs):
opts = {}
if not o_strs:
return opts
for o_str in o_strs:
if not o_str:
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('=')
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 = find_lexer_class(name)
print "Help on the %s lexer:" % cls.name
print dedent(cls.__doc__)
elif what == 'formatter':
cls = find_formatter_class(name)
print "Help on the %s formatter:" % cls.name
print dedent(cls.__doc__)
elif what == 'filter':
cls = find_filter_class(name)
print "Help on the %s filter:" % name
print dedent(cls.__doc__)
except AttributeError:
print >>sys.stderr, "%s not found!" % what
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 ('* %s\n %s %s') % 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 ('* %s\n %s %s') % i
elif what == 'filter':
print
print "Filters:"
print "~~~~~~~~"
for name in get_all_filters():
cls = find_filter_class(name)
print "* " + name + ':'
print " %s" % 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 " %s" % docstring_headline(cls)
def main(args=sys.argv):
"""
Main command line entry point.
"""
# pylint: disable-msg=R0911,R0912,R0915
usage = USAGE % ((args[0],) * 6)
if sys.platform in ['win32', 'cygwin']:
try:
# Provide coloring under Windows, if possible
import colorama
colorama.init()
except ImportError:
pass
try:
popts, args = getopt.getopt(args[1:], "l:f:F:o:O:P:LS:a:N:hVHg")
except getopt.GetoptError, err:
print >>sys.stderr, usage
return 2
opts = {}
O_opts = []
P_opts = []
F_opts = []
for opt, arg in popts:
if opt == '-O':
O_opts.append(arg)
elif opt == '-P':
P_opts.append(arg)
elif opt == '-F':
F_opts.append(arg)
opts[opt] = arg
if not opts and not args:
print usage
return 0
if opts.pop('-h', None) is not None:
print usage
return 0
if opts.pop('-V', None) is not None:
print 'Pygments version %s, (c) 2006-2013 by Georg Brandl.' % __version__
return 0
# handle ``pygmentize -L``
L_opt = opts.pop('-L', None)
if L_opt is not None:
if opts:
print >>sys.stderr, usage
return 2
# print version
main(['', '-V'])
if not args:
args = ['lexer', 'formatter', 'filter', 'style']
for arg in args:
_print_list(arg.rstrip('s'))
return 0
# handle ``pygmentize -H``
H_opt = opts.pop('-H', None)
if H_opt is not None:
if opts or len(args) != 2:
print >>sys.stderr, usage
return 2
what, name = args
if what not in ('lexer', 'formatter', 'filter'):
print >>sys.stderr, usage
return 2
_print_help(what, name)
return 0
# parse -O options
parsed_opts = _parse_options(O_opts)
opts.pop('-O', None)
# parse -P options
for p_opt in P_opts:
try:
name, value = p_opt.split('=', 1)
except ValueError:
parsed_opts[p_opt] = True
else:
parsed_opts[name] = value
opts.pop('-P', None)
# handle ``pygmentize -N``
infn = opts.pop('-N', None)
if infn is not None:
try:
lexer = get_lexer_for_filename(infn, **parsed_opts)
except ClassNotFound, err:
lexer = TextLexer()
except OptionError, err:
print >>sys.stderr, 'Error:', err
return 1
print lexer.aliases[0]
return 0
# handle ``pygmentize -S``
S_opt = opts.pop('-S', None)
a_opt = opts.pop('-a', None)
if S_opt is not None:
f_opt = opts.pop('-f', None)
if not f_opt:
print >>sys.stderr, usage
return 2
if opts or args:
print >>sys.stderr, usage
return 2
try:
parsed_opts['style'] = S_opt
fmter = get_formatter_by_name(f_opt, **parsed_opts)
except ClassNotFound, err:
print >>sys.stderr, err
return 1
arg = a_opt or ''
try:
print fmter.get_style_defs(arg)
except Exception, err:
print >>sys.stderr, 'Error:', err
return 1
return 0
# if no -S is given, -a is not allowed
if a_opt is not None:
print >>sys.stderr, usage
return 2
# parse -F options
F_opts = _parse_filters(F_opts)
opts.pop('-F', None)
# select formatter
outfn = opts.pop('-o', None)
fmter = opts.pop('-f', None)
if fmter:
try:
fmter = get_formatter_by_name(fmter, **parsed_opts)
except (OptionError, ClassNotFound), err:
print >>sys.stderr, 'Error:', err
return 1
if outfn:
if not fmter:
try:
fmter = get_formatter_for_filename(outfn, **parsed_opts)
except (OptionError, ClassNotFound), err:
print >>sys.stderr, 'Error:', err
return 1
try:
outfile = open(outfn, 'wb')
except Exception, err:
print >>sys.stderr, 'Error: cannot open outfile:', err
return 1
else:
if not fmter:
fmter = TerminalFormatter(**parsed_opts)
outfile = sys.stdout
# select lexer
lexer = opts.pop('-l', None)
if lexer:
try:
lexer = get_lexer_by_name(lexer, **parsed_opts)
except (OptionError, ClassNotFound), err:
print >>sys.stderr, 'Error:', err
return 1
if args:
if len(args) > 1:
print >>sys.stderr, usage
return 2
infn = args[0]
try:
code = open(infn, 'rb').read()
except Exception, err:
print >>sys.stderr, 'Error: cannot read infile:', err
return 1
if not lexer:
try:
lexer = get_lexer_for_filename(infn, code, **parsed_opts)
except ClassNotFound, err:
if '-g' in opts:
try:
lexer = guess_lexer(code, **parsed_opts)
except ClassNotFound:
lexer = TextLexer(**parsed_opts)
else:
print >>sys.stderr, 'Error:', err
return 1
except OptionError, err:
print >>sys.stderr, 'Error:', err
return 1
else:
if '-g' in opts:
code = sys.stdin.read()
try:
lexer = guess_lexer(code, **parsed_opts)
except ClassNotFound:
lexer = TextLexer(**parsed_opts)
elif not lexer:
print >>sys.stderr, 'Error: no lexer name given and reading ' + \
'from stdin (try using -g or -l <lexer>)'
return 2
else:
code = sys.stdin.read()
# No encoding given? Use latin1 if output file given,
# stdin/stdout encoding otherwise.
# (This is a compromise, I'm not too happy with it...)
if 'encoding' not in parsed_opts and 'outencoding' not in parsed_opts:
if outfn:
# encoding pass-through
fmter.encoding = 'latin1'
else:
if sys.version_info < (3,):
# use terminal encoding; Python 3's terminals already do that
lexer.encoding = getattr(sys.stdin, 'encoding',
None) or 'ascii'
fmter.encoding = getattr(sys.stdout, 'encoding',
None) or 'ascii'
elif not outfn and sys.version_info > (3,):
# output to terminal with encoding -> use .buffer
outfile = sys.stdout.buffer
# ... and do it!
try:
# process filters
for fname, fopts in F_opts:
lexer.add_filter(fname, **fopts)
highlight(code, lexer, fmter, outfile)
except Exception, err:
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%s)' % info[-2].split('\n')[0].strip()[1:]
print >>sys.stderr
print >>sys.stderr, '*** Error while highlighting:'
print >>sys.stderr, msg
return 1
return 0

View file

@ -0,0 +1,356 @@
# -*- coding: utf-8 -*-
"""
pygments.filters
~~~~~~~~~~~~~~~~
Module containing filter lookup functions and default
filters.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
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
from pygments.plugin import find_plugin_filters
def find_filter_class(filtername):
"""
Lookup a filter by name. Return None if not found.
"""
if filtername in FILTERS:
return FILTERS[filtername]
for name, cls in find_plugin_filters():
if name == filtername:
return cls
return None
def get_filter_by_name(filtername, **options):
"""
Return an instantiated filter. Options are passed to the filter
initializer if wanted. Raise a ClassNotFound if not found.
"""
cls = find_filter_class(filtername)
if cls:
return cls(**options)
else:
raise ClassNotFound('filter %r not found' % filtername)
def get_all_filters():
"""
Return a generator of all filter names.
"""
for name in FILTERS:
yield name
for name, _ in find_plugin_filters():
yield name
def _replace_special(ttype, value, regex, specialttype,
replacefunc=lambda x: x):
last = 0
for match in regex.finditer(value):
start, end = match.start(), match.end()
if start != last:
yield ttype, value[last:start]
yield specialttype, replacefunc(value[start:end])
last = end
if last != len(value):
yield ttype, value[last:]
class CodeTagFilter(Filter):
"""
Highlight special code tags in comments and docstrings.
Options accepted:
`codetags` : list of strings
A list of strings that are flagged as code tags. The default is to
highlight ``XXX``, ``TODO``, ``BUG`` and ``NOTE``.
"""
def __init__(self, **options):
Filter.__init__(self, **options)
tags = get_list_opt(options, 'codetags',
['XXX', 'TODO', 'BUG', 'NOTE'])
self.tag_re = re.compile(r'\b(%s)\b' % '|'.join([
re.escape(tag) for tag in tags if tag
]))
def filter(self, lexer, stream):
regex = self.tag_re
for ttype, value in stream:
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
else:
yield ttype, value
class KeywordCaseFilter(Filter):
"""
Convert keywords to lowercase or uppercase or capitalize them, which
means first letter uppercase, rest lowercase.
This can be useful e.g. if you highlight Pascal code and want to adapt the
code to your styleguide.
Options accepted:
`case` : string
The casing to convert keywords to. Must be one of ``'lower'``,
``'upper'`` or ``'capitalize'``. The default is ``'lower'``.
"""
def __init__(self, **options):
Filter.__init__(self, **options)
case = get_choice_opt(options, 'case', ['lower', 'upper', 'capitalize'], 'lower')
self.convert = getattr(unicode, case)
def filter(self, lexer, stream):
for ttype, value in stream:
if ttype in Keyword:
yield ttype, self.convert(value)
else:
yield ttype, value
class NameHighlightFilter(Filter):
"""
Highlight a normal Name (and Name.*) token with a different token type.
Example::
filter = NameHighlightFilter(
names=['foo', 'bar', 'baz'],
tokentype=Name.Function,
)
This would highlight the names "foo", "bar" and "baz"
as functions. `Name.Function` is the default token type.
Options accepted:
`names` : list of strings
A list of names that should be given the different token type.
There is no default.
`tokentype` : TokenType or string
A token type or a string containing a token type name that is
used for highlighting the strings in `names`. The default is
`Name.Function`.
"""
def __init__(self, **options):
Filter.__init__(self, **options)
self.names = set(get_list_opt(options, 'names', []))
tokentype = options.get('tokentype')
if tokentype:
self.tokentype = string_to_tokentype(tokentype)
else:
self.tokentype = Name.Function
def filter(self, lexer, stream):
for ttype, value in stream:
if ttype in Name and value in self.names:
yield self.tokentype, value
else:
yield ttype, value
class ErrorToken(Exception):
pass
class RaiseOnErrorTokenFilter(Filter):
"""
Raise an exception when the lexer generates an error token.
Options accepted:
`excclass` : Exception class
The exception class to raise.
The default is `pygments.filters.ErrorToken`.
*New in Pygments 0.8.*
"""
def __init__(self, **options):
Filter.__init__(self, **options)
self.exception = options.get('excclass', ErrorToken)
try:
# issubclass() will raise TypeError if first argument is not a class
if not issubclass(self.exception, Exception):
raise TypeError
except TypeError:
raise OptionError('excclass option is not an exception class')
def filter(self, lexer, stream):
for ttype, value in stream:
if ttype is Error:
raise self.exception(value)
yield ttype, value
class VisibleWhitespaceFilter(Filter):
"""
Convert tabs, newlines and/or spaces to visible characters.
Options accepted:
`spaces` : string or bool
If this is a one-character string, spaces will be replaces by this string.
If it is another true value, spaces will be replaced by ``·`` (unicode
MIDDLE DOT). If it is a false value, spaces will not be replaced. The
default is ``False``.
`tabs` : string or bool
The same as for `spaces`, but the default replacement character is ``»``
(unicode RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK). The default value
is ``False``. Note: this will not work if the `tabsize` option for the
lexer is nonzero, as tabs will already have been expanded then.
`tabsize` : int
If tabs are to be replaced by this filter (see the `tabs` option), this
is the total number of characters that a tab should be expanded to.
The default is ``8``.
`newlines` : string or bool
The same as for `spaces`, but the default replacement character is ````
(unicode PILCROW SIGN). The default value is ``False``.
`wstokentype` : bool
If true, give whitespace the special `Whitespace` token type. This allows
styling the visible whitespace differently (e.g. greyed out), but it can
disrupt background colors. The default is ``True``.
*New in Pygments 0.8.*
"""
def __init__(self, **options):
Filter.__init__(self, **options)
for name, default in {'spaces': u'·', 'tabs': u'»', 'newlines': u''}.items():
opt = options.get(name, False)
if isinstance(opt, basestring) and len(opt) == 1:
setattr(self, name, opt)
else:
setattr(self, name, (opt and default or ''))
tabsize = get_int_opt(options, 'tabsize', 8)
if self.tabs:
self.tabs += ' '*(tabsize-1)
if self.newlines:
self.newlines += '\n'
self.wstt = get_bool_opt(options, 'wstokentype', True)
def filter(self, lexer, stream):
if self.wstt:
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
elif wschar == '\t':
return tabs
elif wschar == '\n':
return newlines
return wschar
for ttype, value in stream:
for sttype, svalue in _replace_special(ttype, value, regex,
Whitespace, replacefunc):
yield sttype, svalue
else:
spaces, tabs, newlines = self.spaces, self.tabs, self.newlines
# simpler processing
for ttype, value in stream:
if spaces:
value = value.replace(' ', spaces)
if tabs:
value = value.replace('\t', tabs)
if newlines:
value = value.replace('\n', newlines)
yield ttype, value
class GobbleFilter(Filter):
"""
Gobbles source code lines (eats initial characters).
This filter drops the first ``n`` characters off every line of code. This
may be useful when the source code fed to the lexer is indented by a fixed
amount of space that isn't desired in the output.
Options accepted:
`n` : int
The number of characters to gobble.
*New in Pygments 1.2.*
"""
def __init__(self, **options):
Filter.__init__(self, **options)
self.n = get_int_opt(options, 'n', 0)
def gobble(self, value, left):
if left < len(value):
return value[left:], 0
else:
return '', left - len(value)
def filter(self, lexer, stream):
n = self.n
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 = '\n'.join(parts)
if value != '':
yield ttype, value
class TokenMergeFilter(Filter):
"""
Merges consecutive tokens with the same token type in the output stream of a
lexer.
*New in Pygments 1.2.*
"""
def __init__(self, **options):
Filter.__init__(self, **options)
def filter(self, lexer, stream):
current_type = None
current_value = None
for ttype, value in stream:
if ttype is current_type:
current_value += value
else:
if current_type is not None:
yield current_type, current_value
current_type = ttype
current_value = value
if current_type is not None:
yield current_type, current_value
FILTERS = {
'codetagify': CodeTagFilter,
'keywordcase': KeywordCaseFilter,
'highlight': NameHighlightFilter,
'raiseonerror': RaiseOnErrorTokenFilter,
'whitespace': VisibleWhitespaceFilter,
'gobble': GobbleFilter,
'tokenmerge': TokenMergeFilter,
}

View file

@ -0,0 +1,95 @@
# -*- coding: utf-8 -*-
"""
pygments.formatter
~~~~~~~~~~~~~~~~~~
Base formatter class.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import codecs
from pygments.util import get_bool_opt
from pygments.styles import get_style_by_name
__all__ = ['Formatter']
def _lookup_style(style):
if isinstance(style, basestring):
return get_style_by_name(style)
return style
class Formatter(object):
"""
Converts a token stream to text.
Options accepted:
``style``
The style to use, can be a string or a Style subclass
(default: "default"). Not used by e.g. the
TerminalFormatter.
``full``
Tells the formatter to output a "full" document, i.e.
a complete self-contained document. This doesn't have
any effect for some formatters (default: false).
``title``
If ``full`` is true, the title that should be used to
caption the document (default: '').
``encoding``
If given, must be an encoding name. This will be used to
convert the Unicode token strings to byte strings in the
output. If it is "" or None, Unicode strings will be written
to the output file, which most file-like objects do not
support (default: None).
``outencoding``
Overrides ``encoding`` if given.
"""
#: Name of the formatter
name = None
#: Shortcuts for the formatter
aliases = []
#: fn match rules
filenames = []
#: If True, this formatter outputs Unicode strings when no encoding
#: option is given.
unicodeoutput = True
def __init__(self, **options):
self.style = _lookup_style(options.get('style', 'default'))
self.full = get_bool_opt(options, 'full', False)
self.title = options.get('title', '')
self.encoding = options.get('encoding', None) or None
if self.encoding == 'guess':
# can happen for pygmentize -O encoding=guess
self.encoding = 'utf-8'
self.encoding = options.get('outencoding', None) or self.encoding
self.options = options
def get_style_defs(self, arg=''):
"""
Return the style definitions for the current style as a string.
``arg`` is an additional argument whose meaning depends on the
formatter used. Note that ``arg`` can also be a list or tuple
for some formatters like the html formatter.
"""
return ''
def format(self, tokensource, outfile):
"""
Format ``tokensource``, an iterable of ``(tokentype, tokenstring)``
tuples and write it into ``outfile``.
"""
if self.encoding:
# wrap the outfile in a StreamWriter
outfile = codecs.lookup(self.encoding)[3](outfile)
return self.format_unencoded(tokensource, outfile)

View file

@ -0,0 +1,92 @@
# -*- coding: utf-8 -*-
"""
pygments.formatters._mapping
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Formatter mapping defintions. This file is generated by itself. Everytime
you change something on a builtin formatter defintion, run this script from
the formatters folder to update it.
Do not alter the FORMATTERS dictionary by hand.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
# start
from pygments.formatters.bbcode import BBCodeFormatter
from pygments.formatters.html import HtmlFormatter
from pygments.formatters.img import BmpImageFormatter
from pygments.formatters.img import GifImageFormatter
from pygments.formatters.img import ImageFormatter
from pygments.formatters.img import JpgImageFormatter
from pygments.formatters.latex import LatexFormatter
from pygments.formatters.other import NullFormatter
from pygments.formatters.other import RawTokenFormatter
from pygments.formatters.rtf import RtfFormatter
from pygments.formatters.svg import SvgFormatter
from pygments.formatters.terminal import TerminalFormatter
from pygments.formatters.terminal256 import Terminal256Formatter
FORMATTERS = {
BBCodeFormatter: ('BBCode', ('bbcode', 'bb'), (), 'Format tokens with BBcodes. These formatting codes are used by many bulletin boards, so you can highlight your sourcecode with pygments before posting it there.'),
BmpImageFormatter: ('img_bmp', ('bmp', 'bitmap'), ('*.bmp',), 'Create a bitmap image from source code. This uses the Python Imaging Library to generate a pixmap from the source code.'),
GifImageFormatter: ('img_gif', ('gif',), ('*.gif',), 'Create a GIF image from source code. This uses the Python Imaging Library to generate a pixmap from the source code.'),
HtmlFormatter: ('HTML', ('html',), ('*.html', '*.htm'), "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."),
ImageFormatter: ('img', ('img', 'IMG', 'png'), ('*.png',), 'Create a PNG image from source code. This uses the Python Imaging Library to generate a pixmap from the source code.'),
JpgImageFormatter: ('img_jpg', ('jpg', 'jpeg'), ('*.jpg',), 'Create a JPEG image from source code. This uses the Python Imaging Library to generate a pixmap from the source code.'),
LatexFormatter: ('LaTeX', ('latex', 'tex'), ('*.tex',), 'Format tokens as LaTeX code. This needs the `fancyvrb` and `color` standard packages.'),
NullFormatter: ('Text only', ('text', 'null'), ('*.txt',), 'Output the text unchanged without any formatting.'),
RawTokenFormatter: ('Raw tokens', ('raw', 'tokens'), ('*.raw',), 'Format tokens as a raw representation for storing token streams.'),
RtfFormatter: ('RTF', ('rtf',), ('*.rtf',), 'Format tokens as RTF markup. This formatter automatically outputs full RTF documents with color information and other useful stuff. Perfect for Copy and Paste into Microsoft\xc2\xae Word\xc2\xae documents.'),
SvgFormatter: ('SVG', ('svg',), ('*.svg',), 'Format tokens as an SVG graphics file. This formatter is still experimental. Each line of code is a ``<text>`` element with explicit ``x`` and ``y`` coordinates containing ``<tspan>`` elements with the individual token styles.'),
Terminal256Formatter: ('Terminal256', ('terminal256', 'console256', '256'), (), 'Format tokens with ANSI color sequences, for output in a 256-color terminal or console. Like in `TerminalFormatter` color sequences are terminated at newlines, so that paging the output works correctly.'),
TerminalFormatter: ('Terminal', ('terminal', 'console'), (), 'Format tokens with ANSI color sequences, for output in a text console. Color sequences are terminated at newlines, so that paging the output works correctly.')
}
if __name__ == '__main__':
import sys
import os
# lookup formatters
found_formatters = []
imports = []
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', '..'))
from pygments.util import docstring_headline
for filename in os.listdir('.'):
if filename.endswith('.py') and not filename.startswith('_'):
module_name = 'pygments.formatters.%s' % filename[:-3]
print module_name
module = __import__(module_name, None, None, [''])
for formatter_name in module.__all__:
imports.append((module_name, formatter_name))
formatter = getattr(module, formatter_name)
found_formatters.append(
'%s: %r' % (formatter_name,
(formatter.name,
tuple(formatter.aliases),
tuple(formatter.filenames),
docstring_headline(formatter))))
# sort them, that should make the diff files for svn smaller
found_formatters.sort()
imports.sort()
# extract useful sourcecode from this file
f = open(__file__)
try:
content = f.read()
finally:
f.close()
header = content[:content.find('# start')]
footer = content[content.find("if __name__ == '__main__':"):]
# write new file
f = open(__file__, 'w')
f.write(header)
f.write('# start\n')
f.write('\n'.join(['from %s import %s' % imp for imp in imports]))
f.write('\n\n')
f.write('FORMATTERS = {\n %s\n}\n\n' % ',\n '.join(found_formatters))
f.write(footer)
f.close()

View file

@ -0,0 +1,821 @@
# -*- coding: utf-8 -*-
"""
pygments.formatters.html
~~~~~~~~~~~~~~~~~~~~~~~~
Formatter for HTML output.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import os
import sys
import os.path
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, get_list_opt, bytes
try:
import ctags
except ImportError:
ctags = None
__all__ = ['HtmlFormatter']
_escape_html_table = {
ord('&'): u'&amp;',
ord('<'): u'&lt;',
ord('>'): u'&gt;',
ord('"'): u'&quot;',
ord("'"): u'&#39;',
}
def escape_html(text, table=_escape_html_table):
"""Escape &, <, > as well as single and double quotes for HTML."""
return text.translate(table)
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
CSSFILE_TEMPLATE = '''\
td.linenos { background-color: #f0f0f0; padding-right: 10px; }
span.lineno { background-color: #f0f0f0; padding: 0 5px 0 5px; }
pre { line-height: 125%%; }
%(styledefs)s
'''
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">
''' + CSSFILE_TEMPLATE + '''
</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" type="text/css">
</head>
<body>
<h2>%(title)s</h2>
'''
DOC_FOOTER = '''\
</body>
</html>
'''
class HtmlFormatter(Formatter):
r"""
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 set to ``"table"``, 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.
A list of lines can be specified using the `hl_lines` option to make these
lines highlighted (as of Pygments 0.11).
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.
When `tagsfile` is set to the path of a ctags index file, it is used to
generate hyperlinks from names to their definition. You must enable
`anchorlines` and run ctags with the `-n` option for this to work. The
`python-ctags` module from PyPI must be installed to use this feature;
otherwise a `RuntimeError` will be raised.
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 or 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 most other options (default: ``False``).
`full`
Tells the formatter to output a "full" document, i.e. a complete
self-contained document (default: ``False``).
`title`
If `full` is true, the title that should be used to caption the
document (default: ``''``).
`style`
The style to use, can be a string or a Style subclass (default:
``'default'``). This option has no effect if the `cssfile`
and `noclobber_cssfile` option are given and the file specified in
`cssfile` exists.
`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'``).
If you set this option, the default selector for `get_style_defs()`
will be this class.
*New in Pygments 0.9:* If you select the ``'table'`` line numbers, the
wrapping table will have a CSS class of this string plus ``'table'``,
the default is accordingly ``'highlighttable'``.
`cssstyles`
Inline CSS styles for the wrapping ``<div>`` tag (default: ``''``).
`prestyles`
Inline CSS styles for the ``<pre>`` tag (default: ``''``). *New in
Pygments 0.11.*
`cssfile`
If the `full` option is true and this option is given, it must be the
name of an external file. If the filename does not include an absolute
path, the file's path will be assumed to be relative to the main output
file's path, if the latter can be found. The stylesheet is then written
to this file instead of the HTML file. *New in Pygments 0.6.*
`noclobber_cssfile`
If `cssfile` is given and the specified file exists, the css file will
not be overwritten. This allows the use of the `full` option in
combination with a user specified css file. Default is ``False``.
*New in Pygments 1.1.*
`linenos`
If set to ``'table'``, output line numbers as a table with two cells,
one containing the line numbers, the other the whole code. This is
copy-and-paste-friendly, but may cause alignment problems with some
browsers or fonts. If set to ``'inline'``, the line numbers will be
integrated in the ``<pre>`` tag that contains the code (that setting
is *new in Pygments 0.8*).
For compatibility with Pygments 0.7 and earlier, every true value
except ``'inline'`` means the same as ``'table'`` (in particular, that
means also ``True``).
The default value is ``False``, which means no line numbers at all.
**Note:** with the default ("table") line number mechanism, the line
numbers and code can have different line heights in Internet Explorer
unless you give the enclosing ``<pre>`` tags an explicit ``line-height``
CSS property (you get the default line spacing with ``line-height:
125%``).
`hl_lines`
Specify a list of lines to be highlighted. *New in Pygments 0.11.*
`linenostart`
The line number for the first line (default: ``1``).
`linenostep`
If set to a number n > 1, only every nth line number is printed.
`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.*
`lineanchors`
If set to a nonempty string, e.g. ``foo``, the formatter will wrap each
output line in an anchor tag with a ``name`` of ``foo-linenumber``.
This allows easy linking to certain lines. *New in Pygments 0.9.*
`linespans`
If set to a nonempty string, e.g. ``foo``, the formatter will wrap each
output line in a span tag with an ``id`` of ``foo-linenumber``.
This allows easy access to lines via javascript. *New in Pygments 1.6.*
`anchorlinenos`
If set to `True`, will wrap line numbers in <a> tags. Used in
combination with `linenos` and `lineanchors`.
`tagsfile`
If set to the path of a ctags file, wrap names in anchor tags that
link to their definitions. `lineanchors` should be used, and the
tags file should specify line numbers (see the `-n` option to ctags).
*New in Pygments 1.6.*
`tagurlformat`
A string formatting pattern used to generate links to ctags definitions.
Available variables are `%(path)s`, `%(fname)s` and `%(fext)s`.
Defaults to an empty string, resulting in just `#prefix-number` links.
*New in Pygments 1.6.*
**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 calls
`self._format_lines()` which returns a generator that yields tuples of ``(1,
line)``, where the ``1`` indicates that the ``line`` 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 may 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 HTML
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:
# it's a line of formatted code
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. Then, all
HTML yielded by the wrapped generator is output.
"""
name = 'HTML'
aliases = ['html']
filenames = ['*.html', '*.htm']
def __init__(self, **options):
Formatter.__init__(self, **options)
self.title = self._decodeifneeded(self.title)
self.nowrap = get_bool_opt(options, 'nowrap', False)
self.noclasses = get_bool_opt(options, 'noclasses', False)
self.classprefix = options.get('classprefix', '')
self.cssclass = self._decodeifneeded(options.get('cssclass', 'highlight'))
self.cssstyles = self._decodeifneeded(options.get('cssstyles', ''))
self.prestyles = self._decodeifneeded(options.get('prestyles', ''))
self.cssfile = self._decodeifneeded(options.get('cssfile', ''))
self.noclobber_cssfile = get_bool_opt(options, 'noclobber_cssfile', False)
self.tagsfile = self._decodeifneeded(options.get('tagsfile', ''))
self.tagurlformat = self._decodeifneeded(options.get('tagurlformat', ''))
if self.tagsfile:
if not ctags:
raise RuntimeError('The "ctags" package must to be installed '
'to be able to use the "tagsfile" feature.')
self._ctags = ctags.CTags(self.tagsfile)
linenos = options.get('linenos', False)
if linenos == 'inline':
self.linenos = 2
elif linenos:
# compatibility with <= 0.7
self.linenos = 1
else:
self.linenos = 0
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.lineanchors = options.get('lineanchors', '')
self.linespans = options.get('linespans', '')
self.anchorlinenos = options.get('anchorlinenos', False)
self.hl_lines = set()
for lineno in get_list_opt(options, 'hl_lines', []):
try:
self.hl_lines.add(int(lineno))
except ValueError:
pass
self._create_stylesheet()
def _get_css_class(self, ttype):
"""Return the css class of this token type prefixed with
the classprefix option."""
ttypeclass = _get_ttype_class(ttype)
if ttypeclass:
return self.classprefix + ttypeclass
return ''
def _create_stylesheet(self):
t2c = self.ttype2class = {Token: ''}
c2s = self.class2style = {}
for ttype, ndef in self.style:
name = self._get_css_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=None):
"""
Return CSS style definitions for the classes produced by the current
highlighting style. ``arg`` can be a string or list of selectors to
insert before the token type classes.
"""
if arg is None:
arg = ('cssclass' in self.options and '.'+self.cssclass or '')
if isinstance(arg, basestring):
args = [arg]
else:
args = list(arg)
def prefix(cls):
if cls:
cls = '.' + 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 }' %
(prefix(''), self.style.background_color, text_style))
if self.style.highlight_color is not None:
lines.insert(0, '%s.hll { background-color: %s }' %
(prefix(''), self.style.highlight_color))
return '\n'.join(lines)
def _decodeifneeded(self, value):
if isinstance(value, bytes):
if self.encoding:
return value.decode(self.encoding)
return value.decode()
return value
def _wrap_full(self, inner, outfile):
if self.cssfile:
if os.path.isabs(self.cssfile):
# it's an absolute filename
cssfilename = self.cssfile
else:
try:
filename = outfile.name
if not filename or filename[0] == '<':
# pseudo files, e.g. name == '<fdopen>'
raise AttributeError
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 only if noclobber_cssfile isn't given as an option.
try:
if not os.path.exists(cssfilename) or not self.noclobber_cssfile:
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_tablelinenos(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
la = self.lineanchors
aln = self.anchorlinenos
nocls = self.noclasses
if sp:
lines = []
for i in range(fl, fl+lncount):
if i % st == 0:
if i % sp == 0:
if aln:
lines.append('<a href="#%s-%d" class="special">%*d</a>' %
(la, i, mw, i))
else:
lines.append('<span class="special">%*d</span>' % (mw, i))
else:
if aln:
lines.append('<a href="#%s-%d">%*d</a>' % (la, i, mw, i))
else:
lines.append('%*d' % (mw, i))
else:
lines.append('')
ls = '\n'.join(lines)
else:
lines = []
for i in range(fl, fl+lncount):
if i % st == 0:
if aln:
lines.append('<a href="#%s-%d">%*d</a>' % (la, i, mw, i))
else:
lines.append('%*d' % (mw, i))
else:
lines.append('')
ls = '\n'.join(lines)
# in case you wonder about the seemingly redundant <div> here: since the
# content in the other cell also is wrapped in a div, some browsers in
# some configurations seem to mess up the formatting...
if nocls:
yield 0, ('<table class="%stable">' % self.cssclass +
'<tr><td><div class="linenodiv" '
'style="background-color: #f0f0f0; padding-right: 10px">'
'<pre style="line-height: 125%">' +
ls + '</pre></div></td><td class="code">')
else:
yield 0, ('<table class="%stable">' % self.cssclass +
'<tr><td class="linenos"><div class="linenodiv"><pre>' +
ls + '</pre></div></td><td class="code">')
yield 0, dummyoutfile.getvalue()
yield 0, '</td></tr></table>'
def _wrap_inlinelinenos(self, inner):
# need a list of lines since we need the width of a single number :(
lines = list(inner)
sp = self.linenospecial
st = self.linenostep
num = self.linenostart
mw = len(str(len(lines) + num - 1))
if self.noclasses:
if sp:
for t, line in lines:
if num%sp == 0:
style = 'background-color: #ffffc0; padding: 0 5px 0 5px'
else:
style = 'background-color: #f0f0f0; padding: 0 5px 0 5px'
yield 1, '<span style="%s">%*s</span> ' % (
style, mw, (num%st and ' ' or num)) + line
num += 1
else:
for t, line in lines:
yield 1, ('<span style="background-color: #f0f0f0; '
'padding: 0 5px 0 5px">%*s</span> ' % (
mw, (num%st and ' ' or num)) + line)
num += 1
elif sp:
for t, line in lines:
yield 1, '<span class="lineno%s">%*s</span> ' % (
num%sp == 0 and ' special' or '', mw,
(num%st and ' ' or num)) + line
num += 1
else:
for t, line in lines:
yield 1, '<span class="lineno">%*s</span> ' % (
mw, (num%st and ' ' or num)) + line
num += 1
def _wrap_lineanchors(self, inner):
s = self.lineanchors
i = self.linenostart - 1 # subtract 1 since we have to increment i
# *before* yielding
for t, line in inner:
if t:
i += 1
yield 1, '<a name="%s-%d"></a>' % (s, i) + line
else:
yield 0, line
def _wrap_linespans(self, inner):
s = self.linespans
i = self.linenostart - 1
for t, line in inner:
if t:
i += 1
yield 1, '<span id="%s-%d">%s</span>' % (s, i, line)
else:
yield 0, line
def _wrap_div(self, inner):
style = []
if (self.noclasses and not self.nobackground and
self.style.background_color is not None):
style.append('background: %s' % (self.style.background_color,))
if self.cssstyles:
style.append(self.cssstyles)
style = '; '.join(style)
yield 0, ('<div' + (self.cssclass and ' class="%s"' % self.cssclass)
+ (style and (' style="%s"' % style)) + '>')
for tup in inner:
yield tup
yield 0, '</div>\n'
def _wrap_pre(self, inner):
style = []
if self.prestyles:
style.append(self.prestyles)
if self.noclasses:
style.append('line-height: 125%')
style = '; '.join(style)
yield 0, ('<pre' + (style and ' style="%s"' % style) + '>')
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
lsep = self.lineseparator
# for <span style=""> lookup only
getcls = self.ttype2class.get
c2s = self.class2style
escape_table = _escape_html_table
tagsfile = self.tagsfile
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] or ''
else:
cls = self._get_css_class(ttype)
cspan = cls and '<span class="%s">' % cls or ''
parts = value.translate(escape_table).split('\n')
if tagsfile and ttype in Token.Name:
filename, linenumber = self._lookup_ctag(value)
if linenumber:
base, filename = os.path.split(filename)
if base:
base += '/'
filename, extension = os.path.splitext(filename)
url = self.tagurlformat % {'path': base, 'fname': filename,
'fext': extension}
parts[0] = "<a href=\"%s#%s-%d\">%s" % \
(url, self.lineanchors, linenumber, parts[0])
parts[-1] = parts[-1] + "</a>"
# 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 = ''
elif part:
yield 1, cspan + part + (cspan and '</span>') + lsep
else:
yield 1, lsep
# for the last line
if line and parts[-1]:
if lspan != cspan:
line += (lspan and '</span>') + cspan + parts[-1]
lspan = cspan
else:
line += parts[-1]
elif parts[-1]:
line = cspan + parts[-1]
lspan = cspan
# else we neither have to open a new span nor set lspan
if line:
yield 1, line + (lspan and '</span>') + lsep
def _lookup_ctag(self, token):
entry = ctags.TagEntry()
if self._ctags.find(entry, token, 0):
return entry['file'], entry['lineNumber']
else:
return None, None
def _highlight_lines(self, tokensource):
"""
Highlighted the lines specified in the `hl_lines` option by
post-processing the token stream coming from `_format_lines`.
"""
hls = self.hl_lines
for i, (t, value) in enumerate(tokensource):
if t != 1:
yield t, value
if i + 1 in hls: # i + 1 because Python indexes start at 0
if self.noclasses:
style = ''
if self.style.highlight_color is not None:
style = (' style="background-color: %s"' %
(self.style.highlight_color,))
yield 1, '<span%s>%s</span>' % (style, value)
else:
yield 1, '<span class="hll">%s</span>' % value
else:
yield 1, value
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_unencoded(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 self.hl_lines:
source = self._highlight_lines(source)
if not self.nowrap:
if self.linenos == 2:
source = self._wrap_inlinelinenos(source)
if self.lineanchors:
source = self._wrap_lineanchors(source)
if self.linespans:
source = self._wrap_linespans(source)
source = self.wrap(source, outfile)
if self.linenos == 1:
source = self._wrap_tablelinenos(source)
if self.full:
source = self._wrap_full(source, outfile)
for t, piece in source:
outfile.write(piece)

View file

@ -0,0 +1,553 @@
# -*- coding: utf-8 -*-
"""
pygments.formatters.img
~~~~~~~~~~~~~~~~~~~~~~~
Formatter for Pixmap output.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import sys
from pygments.formatter import Formatter
from pygments.util import get_bool_opt, get_int_opt, \
get_list_opt, get_choice_opt
# Import this carefully
try:
from PIL import Image, ImageDraw, ImageFont
pil_available = True
except ImportError:
pil_available = False
try:
import _winreg
except ImportError:
_winreg = None
__all__ = ['ImageFormatter', 'GifImageFormatter', 'JpgImageFormatter',
'BmpImageFormatter']
# For some unknown reason every font calls it something different
STYLES = {
'NORMAL': ['', 'Roman', 'Book', 'Normal', 'Regular', 'Medium'],
'ITALIC': ['Oblique', 'Italic'],
'BOLD': ['Bold'],
'BOLDITALIC': ['Bold Oblique', 'Bold Italic'],
}
# A sane default for modern systems
DEFAULT_FONT_NAME_NIX = 'Bitstream Vera Sans Mono'
DEFAULT_FONT_NAME_WIN = 'Courier New'
class PilNotAvailable(ImportError):
"""When Python imaging library is not available"""
class FontNotFound(Exception):
"""When there are no usable fonts specified"""
class FontManager(object):
"""
Manages a set of fonts: normal, italic, bold, etc...
"""
def __init__(self, font_name, font_size=14):
self.font_name = font_name
self.font_size = font_size
self.fonts = {}
self.encoding = None
if sys.platform.startswith('win'):
if not font_name:
self.font_name = DEFAULT_FONT_NAME_WIN
self._create_win()
else:
if not font_name:
self.font_name = DEFAULT_FONT_NAME_NIX
self._create_nix()
def _get_nix_font_path(self, name, style):
from commands import getstatusoutput
exit, out = getstatusoutput('fc-list "%s:style=%s" file' %
(name, style))
if not exit:
lines = out.splitlines()
if lines:
path = lines[0].strip().strip(':')
return path
def _create_nix(self):
for name in STYLES['NORMAL']:
path = self._get_nix_font_path(self.font_name, name)
if path is not None:
self.fonts['NORMAL'] = ImageFont.truetype(path, self.font_size)
break
else:
raise FontNotFound('No usable fonts named: "%s"' %
self.font_name)
for style in ('ITALIC', 'BOLD', 'BOLDITALIC'):
for stylename in STYLES[style]:
path = self._get_nix_font_path(self.font_name, stylename)
if path is not None:
self.fonts[style] = ImageFont.truetype(path, self.font_size)
break
else:
if style == 'BOLDITALIC':
self.fonts[style] = self.fonts['BOLD']
else:
self.fonts[style] = self.fonts['NORMAL']
def _lookup_win(self, key, basename, styles, fail=False):
for suffix in ('', ' (TrueType)'):
for style in styles:
try:
valname = '%s%s%s' % (basename, style and ' '+style, suffix)
val, _ = _winreg.QueryValueEx(key, valname)
return val
except EnvironmentError:
continue
else:
if fail:
raise FontNotFound('Font %s (%s) not found in registry' %
(basename, styles[0]))
return None
def _create_win(self):
try:
key = _winreg.OpenKey(
_winreg.HKEY_LOCAL_MACHINE,
r'Software\Microsoft\Windows NT\CurrentVersion\Fonts')
except EnvironmentError:
try:
key = _winreg.OpenKey(
_winreg.HKEY_LOCAL_MACHINE,
r'Software\Microsoft\Windows\CurrentVersion\Fonts')
except EnvironmentError:
raise FontNotFound('Can\'t open Windows font registry key')
try:
path = self._lookup_win(key, self.font_name, STYLES['NORMAL'], True)
self.fonts['NORMAL'] = ImageFont.truetype(path, self.font_size)
for style in ('ITALIC', 'BOLD', 'BOLDITALIC'):
path = self._lookup_win(key, self.font_name, STYLES[style])
if path:
self.fonts[style] = ImageFont.truetype(path, self.font_size)
else:
if style == 'BOLDITALIC':
self.fonts[style] = self.fonts['BOLD']
else:
self.fonts[style] = self.fonts['NORMAL']
finally:
_winreg.CloseKey(key)
def get_char_size(self):
"""
Get the character size.
"""
return self.fonts['NORMAL'].getsize('M')
def get_font(self, bold, oblique):
"""
Get the font based on bold and italic flags.
"""
if bold and oblique:
return self.fonts['BOLDITALIC']
elif bold:
return self.fonts['BOLD']
elif oblique:
return self.fonts['ITALIC']
else:
return self.fonts['NORMAL']
class ImageFormatter(Formatter):
"""
Create a PNG image from source code. This uses the Python Imaging Library to
generate a pixmap from the source code.
*New in Pygments 0.10.*
Additional options accepted:
`image_format`
An image format to output to that is recognised by PIL, these include:
* "PNG" (default)
* "JPEG"
* "BMP"
* "GIF"
`line_pad`
The extra spacing (in pixels) between each line of text.
Default: 2
`font_name`
The font name to be used as the base font from which others, such as
bold and italic fonts will be generated. This really should be a
monospace font to look sane.
Default: "Bitstream Vera Sans Mono"
`font_size`
The font size in points to be used.
Default: 14
`image_pad`
The padding, in pixels to be used at each edge of the resulting image.
Default: 10
`line_numbers`
Whether line numbers should be shown: True/False
Default: True
`line_number_start`
The line number of the first line.
Default: 1
`line_number_step`
The step used when printing line numbers.
Default: 1
`line_number_bg`
The background colour (in "#123456" format) of the line number bar, or
None to use the style background color.
Default: "#eed"
`line_number_fg`
The text color of the line numbers (in "#123456"-like format).
Default: "#886"
`line_number_chars`
The number of columns of line numbers allowable in the line number
margin.
Default: 2
`line_number_bold`
Whether line numbers will be bold: True/False
Default: False
`line_number_italic`
Whether line numbers will be italicized: True/False
Default: False
`line_number_separator`
Whether a line will be drawn between the line number area and the
source code area: True/False
Default: True
`line_number_pad`
The horizontal padding (in pixels) between the line number margin, and
the source code area.
Default: 6
`hl_lines`
Specify a list of lines to be highlighted. *New in Pygments 1.2.*
Default: empty list
`hl_color`
Specify the color for highlighting lines. *New in Pygments 1.2.*
Default: highlight color of the selected style
"""
# Required by the pygments mapper
name = 'img'
aliases = ['img', 'IMG', 'png']
filenames = ['*.png']
unicodeoutput = False
default_image_format = 'png'
def __init__(self, **options):
"""
See the class docstring for explanation of options.
"""
if not pil_available:
raise PilNotAvailable(
'Python Imaging Library is required for this formatter')
Formatter.__init__(self, **options)
# Read the style
self.styles = dict(self.style)
if self.style.background_color is None:
self.background_color = '#fff'
else:
self.background_color = self.style.background_color
# Image options
self.image_format = get_choice_opt(
options, 'image_format', ['png', 'jpeg', 'gif', 'bmp'],
self.default_image_format, normcase=True)
self.image_pad = get_int_opt(options, 'image_pad', 10)
self.line_pad = get_int_opt(options, 'line_pad', 2)
# The fonts
fontsize = get_int_opt(options, 'font_size', 14)
self.fonts = FontManager(options.get('font_name', ''), fontsize)
self.fontw, self.fonth = self.fonts.get_char_size()
# Line number options
self.line_number_fg = options.get('line_number_fg', '#886')
self.line_number_bg = options.get('line_number_bg', '#eed')
self.line_number_chars = get_int_opt(options,
'line_number_chars', 2)
self.line_number_bold = get_bool_opt(options,
'line_number_bold', False)
self.line_number_italic = get_bool_opt(options,
'line_number_italic', False)
self.line_number_pad = get_int_opt(options, 'line_number_pad', 6)
self.line_numbers = get_bool_opt(options, 'line_numbers', True)
self.line_number_separator = get_bool_opt(options,
'line_number_separator', True)
self.line_number_step = get_int_opt(options, 'line_number_step', 1)
self.line_number_start = get_int_opt(options, 'line_number_start', 1)
if self.line_numbers:
self.line_number_width = (self.fontw * self.line_number_chars +
self.line_number_pad * 2)
else:
self.line_number_width = 0
self.hl_lines = []
hl_lines_str = get_list_opt(options, 'hl_lines', [])
for line in hl_lines_str:
try:
self.hl_lines.append(int(line))
except ValueError:
pass
self.hl_color = options.get('hl_color',
self.style.highlight_color) or '#f90'
self.drawables = []
def get_style_defs(self, arg=''):
raise NotImplementedError('The -S option is meaningless for the image '
'formatter. Use -O style=<stylename> instead.')
def _get_line_height(self):
"""
Get the height of a line.
"""
return self.fonth + self.line_pad
def _get_line_y(self, lineno):
"""
Get the Y coordinate of a line number.
"""
return lineno * self._get_line_height() + self.image_pad
def _get_char_width(self):
"""
Get the width of a character.
"""
return self.fontw
def _get_char_x(self, charno):
"""
Get the X coordinate of a character position.
"""
return charno * self.fontw + self.image_pad + self.line_number_width
def _get_text_pos(self, charno, lineno):
"""
Get the actual position for a character and line position.
"""
return self._get_char_x(charno), self._get_line_y(lineno)
def _get_linenumber_pos(self, lineno):
"""
Get the actual position for the start of a line number.
"""
return (self.image_pad, self._get_line_y(lineno))
def _get_text_color(self, style):
"""
Get the correct color for the token from the style.
"""
if style['color'] is not None:
fill = '#' + style['color']
else:
fill = '#000'
return fill
def _get_style_font(self, style):
"""
Get the correct font for the style.
"""
return self.fonts.get_font(style['bold'], style['italic'])
def _get_image_size(self, maxcharno, maxlineno):
"""
Get the required image size.
"""
return (self._get_char_x(maxcharno) + self.image_pad,
self._get_line_y(maxlineno + 0) + self.image_pad)
def _draw_linenumber(self, posno, lineno):
"""
Remember a line number drawable to paint later.
"""
self._draw_text(
self._get_linenumber_pos(posno),
str(lineno).rjust(self.line_number_chars),
font=self.fonts.get_font(self.line_number_bold,
self.line_number_italic),
fill=self.line_number_fg,
)
def _draw_text(self, pos, text, font, **kw):
"""
Remember a single drawable tuple to paint later.
"""
self.drawables.append((pos, text, font, kw))
def _create_drawables(self, tokensource):
"""
Create drawables for the token content.
"""
lineno = charno = maxcharno = 0
for ttype, value in tokensource:
while ttype not in self.styles:
ttype = ttype.parent
style = self.styles[ttype]
# TODO: make sure tab expansion happens earlier in the chain. It
# really ought to be done on the input, as to do it right here is
# quite complex.
value = value.expandtabs(4)
lines = value.splitlines(True)
#print lines
for i, line in enumerate(lines):
temp = line.rstrip('\n')
if temp:
self._draw_text(
self._get_text_pos(charno, lineno),
temp,
font = self._get_style_font(style),
fill = self._get_text_color(style)
)
charno += len(temp)
maxcharno = max(maxcharno, charno)
if line.endswith('\n'):
# add a line for each extra line in the value
charno = 0
lineno += 1
self.maxcharno = maxcharno
self.maxlineno = lineno
def _draw_line_numbers(self):
"""
Create drawables for the line numbers.
"""
if not self.line_numbers:
return
for p in xrange(self.maxlineno):
n = p + self.line_number_start
if (n % self.line_number_step) == 0:
self._draw_linenumber(p, n)
def _paint_line_number_bg(self, im):
"""
Paint the line number background on the image.
"""
if not self.line_numbers:
return
if self.line_number_fg is None:
return
draw = ImageDraw.Draw(im)
recth = im.size[-1]
rectw = self.image_pad + self.line_number_width - self.line_number_pad
draw.rectangle([(0, 0),
(rectw, recth)],
fill=self.line_number_bg)
draw.line([(rectw, 0), (rectw, recth)], fill=self.line_number_fg)
del draw
def format(self, tokensource, outfile):
"""
Format ``tokensource``, an iterable of ``(tokentype, tokenstring)``
tuples and write it into ``outfile``.
This implementation calculates where it should draw each token on the
pixmap, then calculates the required pixmap size and draws the items.
"""
self._create_drawables(tokensource)
self._draw_line_numbers()
im = Image.new(
'RGB',
self._get_image_size(self.maxcharno, self.maxlineno),
self.background_color
)
self._paint_line_number_bg(im)
draw = ImageDraw.Draw(im)
# Highlight
if self.hl_lines:
x = self.image_pad + self.line_number_width - self.line_number_pad + 1
recth = self._get_line_height()
rectw = im.size[0] - x
for linenumber in self.hl_lines:
y = self._get_line_y(linenumber - 1)
draw.rectangle([(x, y), (x + rectw, y + recth)],
fill=self.hl_color)
for pos, value, font, kw in self.drawables:
draw.text(pos, value, font=font, **kw)
im.save(outfile, self.image_format.upper())
# Add one formatter per format, so that the "-f gif" option gives the correct result
# when used in pygmentize.
class GifImageFormatter(ImageFormatter):
"""
Create a GIF image from source code. This uses the Python Imaging Library to
generate a pixmap from the source code.
*New in Pygments 1.0.* (You could create GIF images before by passing a
suitable `image_format` option to the `ImageFormatter`.)
"""
name = 'img_gif'
aliases = ['gif']
filenames = ['*.gif']
default_image_format = 'gif'
class JpgImageFormatter(ImageFormatter):
"""
Create a JPEG image from source code. This uses the Python Imaging Library to
generate a pixmap from the source code.
*New in Pygments 1.0.* (You could create JPEG images before by passing a
suitable `image_format` option to the `ImageFormatter`.)
"""
name = 'img_jpg'
aliases = ['jpg', 'jpeg']
filenames = ['*.jpg']
default_image_format = 'jpeg'
class BmpImageFormatter(ImageFormatter):
"""
Create a bitmap image from source code. This uses the Python Imaging Library to
generate a pixmap from the source code.
*New in Pygments 1.0.* (You could create bitmap images before by passing a
suitable `image_format` option to the `ImageFormatter`.)
"""
name = 'img_bmp'
aliases = ['bmp', 'bitmap']
filenames = ['*.bmp']
default_image_format = 'bmp'

View file

@ -0,0 +1,378 @@
# -*- coding: utf-8 -*-
"""
pygments.formatters.latex
~~~~~~~~~~~~~~~~~~~~~~~~~
Formatter for LaTeX fancyvrb output.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pygments.formatter import Formatter
from pygments.token import Token, STANDARD_TYPES
from pygments.util import get_bool_opt, get_int_opt, StringIO
__all__ = ['LatexFormatter']
def escape_tex(text, commandprefix):
return text.replace('\\', '\x00'). \
replace('{', '\x01'). \
replace('}', '\x02'). \
replace('\x00', r'\%sZbs{}' % commandprefix). \
replace('\x01', r'\%sZob{}' % commandprefix). \
replace('\x02', r'\%sZcb{}' % commandprefix). \
replace('^', r'\%sZca{}' % commandprefix). \
replace('_', r'\%sZus{}' % commandprefix). \
replace('&', r'\%sZam{}' % commandprefix). \
replace('<', r'\%sZlt{}' % commandprefix). \
replace('>', r'\%sZgt{}' % commandprefix). \
replace('#', r'\%sZsh{}' % commandprefix). \
replace('%', r'\%sZpc{}' % commandprefix). \
replace('$', r'\%sZdl{}' % commandprefix). \
replace('-', r'\%sZhy{}' % commandprefix). \
replace("'", r'\%sZsq{}' % commandprefix). \
replace('"', r'\%sZdq{}' % commandprefix). \
replace('~', r'\%sZti{}' % commandprefix)
DOC_TEMPLATE = r'''
\documentclass{%(docclass)s}
\usepackage{fancyvrb}
\usepackage{color}
\usepackage[%(encoding)s]{inputenc}
%(preamble)s
%(styledefs)s
\begin{document}
\section*{%(title)s}
%(code)s
\end{document}
'''
## Small explanation of the mess below :)
#
# The previous version of the LaTeX formatter just assigned a command to
# each token type defined in the current style. That obviously is
# problematic if the highlighted code is produced for a different style
# than the style commands themselves.
#
# This version works much like the HTML formatter which assigns multiple
# CSS classes to each <span> tag, from the most specific to the least
# specific token type, thus falling back to the parent token type if one
# is not defined. Here, the classes are there too and use the same short
# forms given in token.STANDARD_TYPES.
#
# Highlighted code now only uses one custom command, which by default is
# \PY and selectable by the commandprefix option (and in addition the
# escapes \PYZat, \PYZlb and \PYZrb which haven't been renamed for
# backwards compatibility purposes).
#
# \PY has two arguments: the classes, separated by +, and the text to
# render in that style. The classes are resolved into the respective
# style commands by magic, which serves to ignore unknown classes.
#
# The magic macros are:
# * \PY@it, \PY@bf, etc. are unconditionally wrapped around the text
# to render in \PY@do. Their definition determines the style.
# * \PY@reset resets \PY@it etc. to do nothing.
# * \PY@toks parses the list of classes, using magic inspired by the
# keyval package (but modified to use plusses instead of commas
# because fancyvrb redefines commas inside its environments).
# * \PY@tok processes one class, calling the \PY@tok@classname command
# if it exists.
# * \PY@tok@classname sets the \PY@it etc. to reflect the chosen style
# for its class.
# * \PY resets the style, parses the classnames and then calls \PY@do.
#
# Tip: to read this code, print it out in substituted form using e.g.
# >>> print STYLE_TEMPLATE % {'cp': 'PY'}
STYLE_TEMPLATE = r'''
\makeatletter
\def\%(cp)s@reset{\let\%(cp)s@it=\relax \let\%(cp)s@bf=\relax%%
\let\%(cp)s@ul=\relax \let\%(cp)s@tc=\relax%%
\let\%(cp)s@bc=\relax \let\%(cp)s@ff=\relax}
\def\%(cp)s@tok#1{\csname %(cp)s@tok@#1\endcsname}
\def\%(cp)s@toks#1+{\ifx\relax#1\empty\else%%
\%(cp)s@tok{#1}\expandafter\%(cp)s@toks\fi}
\def\%(cp)s@do#1{\%(cp)s@bc{\%(cp)s@tc{\%(cp)s@ul{%%
\%(cp)s@it{\%(cp)s@bf{\%(cp)s@ff{#1}}}}}}}
\def\%(cp)s#1#2{\%(cp)s@reset\%(cp)s@toks#1+\relax+\%(cp)s@do{#2}}
%(styles)s
\def\%(cp)sZbs{\char`\\}
\def\%(cp)sZus{\char`\_}
\def\%(cp)sZob{\char`\{}
\def\%(cp)sZcb{\char`\}}
\def\%(cp)sZca{\char`\^}
\def\%(cp)sZam{\char`\&}
\def\%(cp)sZlt{\char`\<}
\def\%(cp)sZgt{\char`\>}
\def\%(cp)sZsh{\char`\#}
\def\%(cp)sZpc{\char`\%%}
\def\%(cp)sZdl{\char`\$}
\def\%(cp)sZhy{\char`\-}
\def\%(cp)sZsq{\char`\'}
\def\%(cp)sZdq{\char`\"}
\def\%(cp)sZti{\char`\~}
%% for compatibility with earlier versions
\def\%(cp)sZat{@}
\def\%(cp)sZlb{[}
\def\%(cp)sZrb{]}
\makeatother
'''
def _get_ttype_name(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
class LatexFormatter(Formatter):
r"""
Format tokens as LaTeX code. This needs the `fancyvrb` and `color`
standard packages.
Without the `full` option, code is formatted as one ``Verbatim``
environment, like this:
.. sourcecode:: latex
\begin{Verbatim}[commandchars=\\{\}]
\PY{k}{def }\PY{n+nf}{foo}(\PY{n}{bar}):
\PY{k}{pass}
\end{Verbatim}
The special command used here (``\PY``) and all the other macros it needs
are output by the `get_style_defs` method.
With the `full` option, a complete LaTeX document is output, including
the command definitions in the preamble.
The `get_style_defs()` method of a `LatexFormatter` returns a string
containing ``\def`` commands defining the macros needed inside the
``Verbatim`` environments.
Additional options accepted:
`style`
The style to use, can be a string or a Style subclass (default:
``'default'``).
`full`
Tells the formatter to output a "full" document, i.e. a complete
self-contained document (default: ``False``).
`title`
If `full` is true, the title that should be used to caption the
document (default: ``''``).
`docclass`
If the `full` option is enabled, this is the document class to use
(default: ``'article'``).
`preamble`
If the `full` option is enabled, this can be further preamble commands,
e.g. ``\usepackage`` (default: ``''``).
`linenos`
If set to ``True``, output line numbers (default: ``False``).
`linenostart`
The line number for the first line (default: ``1``).
`linenostep`
If set to a number n > 1, only every nth line number is printed.
`verboptions`
Additional options given to the Verbatim environment (see the *fancyvrb*
docs for possible values) (default: ``''``).
`commandprefix`
The LaTeX commands used to produce colored output are constructed
using this prefix and some letters (default: ``'PY'``).
*New in Pygments 0.7.*
*New in Pygments 0.10:* the default is now ``'PY'`` instead of ``'C'``.
`texcomments`
If set to ``True``, enables LaTeX comment lines. That is, LaTex markup
in comment tokens is not escaped so that LaTeX can render it (default:
``False``). *New in Pygments 1.2.*
`mathescape`
If set to ``True``, enables LaTeX math mode escape in comments. That
is, ``'$...$'`` inside a comment will trigger math mode (default:
``False``). *New in Pygments 1.2.*
"""
name = 'LaTeX'
aliases = ['latex', 'tex']
filenames = ['*.tex']
def __init__(self, **options):
Formatter.__init__(self, **options)
self.docclass = options.get('docclass', 'article')
self.preamble = options.get('preamble', '')
self.linenos = get_bool_opt(options, 'linenos', False)
self.linenostart = abs(get_int_opt(options, 'linenostart', 1))
self.linenostep = abs(get_int_opt(options, 'linenostep', 1))
self.verboptions = options.get('verboptions', '')
self.nobackground = get_bool_opt(options, 'nobackground', False)
self.commandprefix = options.get('commandprefix', 'PY')
self.texcomments = get_bool_opt(options, 'texcomments', False)
self.mathescape = get_bool_opt(options, 'mathescape', False)
self._create_stylesheet()
def _create_stylesheet(self):
t2n = self.ttype2name = {Token: ''}
c2d = self.cmd2def = {}
cp = self.commandprefix
def rgbcolor(col):
if col:
return ','.join(['%.2f' %(int(col[i] + col[i + 1], 16) / 255.0)
for i in (0, 2, 4)])
else:
return '1,1,1'
for ttype, ndef in self.style:
name = _get_ttype_name(ttype)
cmndef = ''
if ndef['bold']:
cmndef += r'\let\$$@bf=\textbf'
if ndef['italic']:
cmndef += r'\let\$$@it=\textit'
if ndef['underline']:
cmndef += r'\let\$$@ul=\underline'
if ndef['roman']:
cmndef += r'\let\$$@ff=\textrm'
if ndef['sans']:
cmndef += r'\let\$$@ff=\textsf'
if ndef['mono']:
cmndef += r'\let\$$@ff=\textsf'
if ndef['color']:
cmndef += (r'\def\$$@tc##1{\textcolor[rgb]{%s}{##1}}' %
rgbcolor(ndef['color']))
if ndef['border']:
cmndef += (r'\def\$$@bc##1{\setlength{\fboxsep}{0pt}'
r'\fcolorbox[rgb]{%s}{%s}{\strut ##1}}' %
(rgbcolor(ndef['border']),
rgbcolor(ndef['bgcolor'])))
elif ndef['bgcolor']:
cmndef += (r'\def\$$@bc##1{\setlength{\fboxsep}{0pt}'
r'\colorbox[rgb]{%s}{\strut ##1}}' %
rgbcolor(ndef['bgcolor']))
if cmndef == '':
continue
cmndef = cmndef.replace('$$', cp)
t2n[ttype] = name
c2d[name] = cmndef
def get_style_defs(self, arg=''):
"""
Return the command sequences needed to define the commands
used to format text in the verbatim environment. ``arg`` is ignored.
"""
cp = self.commandprefix
styles = []
for name, definition in self.cmd2def.iteritems():
styles.append(r'\expandafter\def\csname %s@tok@%s\endcsname{%s}' %
(cp, name, definition))
return STYLE_TEMPLATE % {'cp': self.commandprefix,
'styles': '\n'.join(styles)}
def format_unencoded(self, tokensource, outfile):
# TODO: add support for background colors
t2n = self.ttype2name
cp = self.commandprefix
if self.full:
realoutfile = outfile
outfile = StringIO()
outfile.write(ur'\begin{Verbatim}[commandchars=\\\{\}')
if self.linenos:
start, step = self.linenostart, self.linenostep
outfile.write(u',numbers=left' +
(start and u',firstnumber=%d' % start or u'') +
(step and u',stepnumber=%d' % step or u''))
if self.mathescape or self.texcomments:
outfile.write(ur',codes={\catcode`\$=3\catcode`\^=7\catcode`\_=8}')
if self.verboptions:
outfile.write(u',' + self.verboptions)
outfile.write(u']\n')
for ttype, value in tokensource:
if ttype in Token.Comment:
if self.texcomments:
# Try to guess comment starting lexeme and escape it ...
start = value[0:1]
for i in xrange(1, len(value)):
if start[0] != value[i]:
break
start += value[i]
value = value[len(start):]
start = escape_tex(start, self.commandprefix)
# ... but do not escape inside comment.
value = start + value
elif self.mathescape:
# Only escape parts not inside a math environment.
parts = value.split('$')
in_math = False
for i, part in enumerate(parts):
if not in_math:
parts[i] = escape_tex(part, self.commandprefix)
in_math = not in_math
value = '$'.join(parts)
else:
value = escape_tex(value, self.commandprefix)
else:
value = escape_tex(value, self.commandprefix)
styles = []
while ttype is not Token:
try:
styles.append(t2n[ttype])
except KeyError:
# not in current style
styles.append(_get_ttype_name(ttype))
ttype = ttype.parent
styleval = '+'.join(reversed(styles))
if styleval:
spl = value.split('\n')
for line in spl[:-1]:
if line:
outfile.write("\\%s{%s}{%s}" % (cp, styleval, line))
outfile.write('\n')
if spl[-1]:
outfile.write("\\%s{%s}{%s}" % (cp, styleval, spl[-1]))
else:
outfile.write(value)
outfile.write(u'\\end{Verbatim}\n')
if self.full:
realoutfile.write(DOC_TEMPLATE %
dict(docclass = self.docclass,
preamble = self.preamble,
title = self.title,
encoding = self.encoding or 'latin1',
styledefs = self.get_style_defs(),
code = outfile.getvalue()))

View file

@ -0,0 +1,765 @@
# -*- coding: utf-8 -*-
"""
pygments.lexer
~~~~~~~~~~~~~~
Base lexer classes.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re, itertools
from pygments.filter import apply_filters, Filter
from pygments.filters import get_filter_by_name
from pygments.token import Error, Text, Other, _TokenType
from pygments.util import get_bool_opt, get_int_opt, get_list_opt, \
make_analysator
__all__ = ['Lexer', 'RegexLexer', 'ExtendedRegexLexer', 'DelegatingLexer',
'LexerContext', 'include', 'inherit', 'bygroups', 'using', 'this']
_encoding_map = [('\xef\xbb\xbf', 'utf-8'),
('\xff\xfe\0\0', 'utf-32'),
('\0\0\xfe\xff', 'utf-32be'),
('\xff\xfe', 'utf-16'),
('\xfe\xff', 'utf-16be')]
_default_analyse = staticmethod(lambda x: 0.0)
class LexerMeta(type):
"""
This metaclass automagically converts ``analyse_text`` methods into
static methods which always return float values.
"""
def __new__(cls, name, bases, d):
if 'analyse_text' in d:
d['analyse_text'] = make_analysator(d['analyse_text'])
return type.__new__(cls, name, bases, d)
class Lexer(object):
"""
Lexer for a specific language.
Basic options recognized:
``stripnl``
Strip leading and trailing newlines from the input (default: True).
``stripall``
Strip all leading and trailing whitespace from the input
(default: False).
``ensurenl``
Make sure that the input ends with a newline (default: True). This
is required for some lexers that consume input linewise.
*New in Pygments 1.3.*
``tabsize``
If given and greater than 0, expand tabs in the input (default: 0).
``encoding``
If given, must be an encoding name. This encoding will be used to
convert the input string to Unicode, if it is not already a Unicode
string (default: ``'latin1'``).
Can also be ``'guess'`` to use a simple UTF-8 / Latin1 detection, or
``'chardet'`` to use the chardet library, if it is installed.
"""
#: Name of the lexer
name = None
#: Shortcuts for the lexer
aliases = []
#: File name globs
filenames = []
#: Secondary file name globs
alias_filenames = []
#: MIME types
mimetypes = []
#: Priority, should multiple lexers match and no content is provided
priority = 0
__metaclass__ = LexerMeta
def __init__(self, **options):
self.options = options
self.stripnl = get_bool_opt(options, 'stripnl', True)
self.stripall = get_bool_opt(options, 'stripall', False)
self.ensurenl = get_bool_opt(options, 'ensurenl', True)
self.tabsize = get_int_opt(options, 'tabsize', 0)
self.encoding = options.get('encoding', 'latin1')
# self.encoding = options.get('inencoding', None) or self.encoding
self.filters = []
for filter_ in get_list_opt(options, 'filters', ()):
self.add_filter(filter_)
def __repr__(self):
if self.options:
return '<pygments.lexers.%s with %r>' % (self.__class__.__name__,
self.options)
else:
return '<pygments.lexers.%s>' % self.__class__.__name__
def add_filter(self, filter_, **options):
"""
Add a new stream filter to this lexer.
"""
if not isinstance(filter_, Filter):
filter_ = get_filter_by_name(filter_, **options)
self.filters.append(filter_)
def analyse_text(text):
"""
Has to return a float between ``0`` and ``1`` that indicates
if a lexer wants to highlight this text. Used by ``guess_lexer``.
If this method returns ``0`` it won't highlight it in any case, if
it returns ``1`` highlighting with this lexer is guaranteed.
The `LexerMeta` metaclass automatically wraps this function so
that it works like a static method (no ``self`` or ``cls``
parameter) and the return value is automatically converted to
`float`. If the return value is an object that is boolean `False`
it's the same as if the return values was ``0.0``.
"""
def get_tokens(self, text, unfiltered=False):
"""
Return an iterable of (tokentype, value) pairs generated from
`text`. If `unfiltered` is set to `True`, the filtering mechanism
is bypassed even if filters are defined.
Also preprocess the text, i.e. expand tabs and strip it if
wanted and applies registered filters.
"""
if not isinstance(text, unicode):
if self.encoding == 'guess':
try:
text = text.decode('utf-8')
if text.startswith(u'\ufeff'):
text = text[len(u'\ufeff'):]
except UnicodeDecodeError:
text = text.decode('latin1')
elif self.encoding == 'chardet':
try:
import chardet
except ImportError:
raise ImportError('To enable chardet encoding guessing, '
'please install the chardet library '
'from http://chardet.feedparser.org/')
# check for BOM first
decoded = None
for bom, encoding in _encoding_map:
if text.startswith(bom):
decoded = unicode(text[len(bom):], encoding,
errors='replace')
break
# no BOM found, so use chardet
if decoded is None:
enc = chardet.detect(text[:1024]) # Guess using first 1KB
decoded = unicode(text, enc.get('encoding') or 'utf-8',
errors='replace')
text = decoded
else:
text = text.decode(self.encoding)
else:
if text.startswith(u'\ufeff'):
text = text[len(u'\ufeff'):]
# text now *is* a unicode string
text = text.replace('\r\n', '\n')
text = text.replace('\r', '\n')
if self.stripall:
text = text.strip()
elif self.stripnl:
text = text.strip('\n')
if self.tabsize > 0:
text = text.expandtabs(self.tabsize)
if self.ensurenl and not text.endswith('\n'):
text += '\n'
def streamer():
for i, t, v in self.get_tokens_unprocessed(text):
yield t, v
stream = streamer()
if not unfiltered:
stream = apply_filters(stream, self.filters, self)
return stream
def get_tokens_unprocessed(self, text):
"""
Return an iterable of (tokentype, value) pairs.
In subclasses, implement this method as a generator to
maximize effectiveness.
"""
raise NotImplementedError
class DelegatingLexer(Lexer):
"""
This lexer takes two lexer as arguments. A root lexer and
a language lexer. First everything is scanned using the language
lexer, afterwards all ``Other`` tokens are lexed using the root
lexer.
The lexers from the ``template`` lexer package use this base lexer.
"""
def __init__(self, _root_lexer, _language_lexer, _needle=Other, **options):
self.root_lexer = _root_lexer(**options)
self.language_lexer = _language_lexer(**options)
self.needle = _needle
Lexer.__init__(self, **options)
def get_tokens_unprocessed(self, text):
buffered = ''
insertions = []
lng_buffer = []
for i, t, v in self.language_lexer.get_tokens_unprocessed(text):
if t is self.needle:
if lng_buffer:
insertions.append((len(buffered), lng_buffer))
lng_buffer = []
buffered += v
else:
lng_buffer.append((i, t, v))
if lng_buffer:
insertions.append((len(buffered), lng_buffer))
return do_insertions(insertions,
self.root_lexer.get_tokens_unprocessed(buffered))
#-------------------------------------------------------------------------------
# RegexLexer and ExtendedRegexLexer
#
class include(str):
"""
Indicates that a state should include rules from another state.
"""
pass
class _inherit(object):
"""
Indicates the a state should inherit from its superclass.
"""
def __repr__(self):
return 'inherit'
inherit = _inherit()
class combined(tuple):
"""
Indicates a state combined from multiple states.
"""
def __new__(cls, *args):
return tuple.__new__(cls, args)
def __init__(self, *args):
# tuple.__init__ doesn't do anything
pass
class _PseudoMatch(object):
"""
A pseudo match object constructed from a string.
"""
def __init__(self, start, text):
self._text = text
self._start = start
def start(self, arg=None):
return self._start
def end(self, arg=None):
return self._start + len(self._text)
def group(self, arg=None):
if arg:
raise IndexError('No such group')
return self._text
def groups(self):
return (self._text,)
def groupdict(self):
return {}
def bygroups(*args):
"""
Callback that yields multiple actions for each group in the match.
"""
def callback(lexer, match, ctx=None):
for i, action in enumerate(args):
if action is None:
continue
elif type(action) is _TokenType:
data = match.group(i + 1)
if data:
yield match.start(i + 1), action, data
else:
data = match.group(i + 1)
if data is not None:
if ctx:
ctx.pos = match.start(i + 1)
for item in action(lexer, _PseudoMatch(match.start(i + 1),
data), ctx):
if item:
yield item
if ctx:
ctx.pos = match.end()
return callback
class _This(object):
"""
Special singleton used for indicating the caller class.
Used by ``using``.
"""
this = _This()
def using(_other, **kwargs):
"""
Callback that processes the match with a different lexer.
The keyword arguments are forwarded to the lexer, except `state` which
is handled separately.
`state` specifies the state that the new lexer will start in, and can
be an enumerable such as ('root', 'inline', 'string') or a simple
string which is assumed to be on top of the root state.
Note: For that to work, `_other` must not be an `ExtendedRegexLexer`.
"""
gt_kwargs = {}
if 'state' in kwargs:
s = kwargs.pop('state')
if isinstance(s, (list, tuple)):
gt_kwargs['stack'] = s
else:
gt_kwargs['stack'] = ('root', s)
if _other is this:
def callback(lexer, match, ctx=None):
# if keyword arguments are given the callback
# function has to create a new lexer instance
if kwargs:
# XXX: cache that somehow
kwargs.update(lexer.options)
lx = lexer.__class__(**kwargs)
else:
lx = lexer
s = match.start()
for i, t, v in lx.get_tokens_unprocessed(match.group(), **gt_kwargs):
yield i + s, t, v
if ctx:
ctx.pos = match.end()
else:
def callback(lexer, match, ctx=None):
# XXX: cache that somehow
kwargs.update(lexer.options)
lx = _other(**kwargs)
s = match.start()
for i, t, v in lx.get_tokens_unprocessed(match.group(), **gt_kwargs):
yield i + s, t, v
if ctx:
ctx.pos = match.end()
return callback
class RegexLexerMeta(LexerMeta):
"""
Metaclass for RegexLexer, creates the self._tokens attribute from
self.tokens on the first instantiation.
"""
def _process_regex(cls, regex, rflags):
"""Preprocess the regular expression component of a token definition."""
return re.compile(regex, rflags).match
def _process_token(cls, token):
"""Preprocess the token component of a token definition."""
assert type(token) is _TokenType or callable(token), \
'token type must be simple type or callable, not %r' % (token,)
return token
def _process_new_state(cls, new_state, unprocessed, processed):
"""Preprocess the state transition action of a token definition."""
if isinstance(new_state, str):
# an existing state
if new_state == '#pop':
return -1
elif new_state in unprocessed:
return (new_state,)
elif new_state == '#push':
return new_state
elif new_state[:5] == '#pop:':
return -int(new_state[5:])
else:
assert False, 'unknown new state %r' % new_state
elif isinstance(new_state, combined):
# combine a new state from existing ones
tmp_state = '_tmp_%d' % cls._tmpname
cls._tmpname += 1
itokens = []
for istate in new_state:
assert istate != new_state, 'circular state ref %r' % istate
itokens.extend(cls._process_state(unprocessed,
processed, istate))
processed[tmp_state] = itokens
return (tmp_state,)
elif isinstance(new_state, tuple):
# push more than one state
for istate in new_state:
assert (istate in unprocessed or
istate in ('#pop', '#push')), \
'unknown new state ' + istate
return new_state
else:
assert False, 'unknown new state def %r' % new_state
def _process_state(cls, unprocessed, processed, state):
"""Preprocess a single state definition."""
assert type(state) is str, "wrong state name %r" % state
assert state[0] != '#', "invalid state name %r" % state
if state in processed:
return processed[state]
tokens = processed[state] = []
rflags = cls.flags
for tdef in unprocessed[state]:
if isinstance(tdef, include):
# it's a state reference
assert tdef != state, "circular state reference %r" % state
tokens.extend(cls._process_state(unprocessed, processed,
str(tdef)))
continue
if isinstance(tdef, _inherit):
# processed already
continue
assert type(tdef) is tuple, "wrong rule def %r" % tdef
try:
rex = cls._process_regex(tdef[0], rflags)
except Exception, err:
raise ValueError("uncompilable regex %r in state %r of %r: %s" %
(tdef[0], state, cls, err))
token = cls._process_token(tdef[1])
if len(tdef) == 2:
new_state = None
else:
new_state = cls._process_new_state(tdef[2],
unprocessed, processed)
tokens.append((rex, token, new_state))
return tokens
def process_tokendef(cls, name, tokendefs=None):
"""Preprocess a dictionary of token definitions."""
processed = cls._all_tokens[name] = {}
tokendefs = tokendefs or cls.tokens[name]
for state in tokendefs.keys():
cls._process_state(tokendefs, processed, state)
return processed
def get_tokendefs(cls):
"""
Merge tokens from superclasses in MRO order, returning a single tokendef
dictionary.
Any state that is not defined by a subclass will be inherited
automatically. States that *are* defined by subclasses will, by
default, override that state in the superclass. If a subclass wishes to
inherit definitions from a superclass, it can use the special value
"inherit", which will cause the superclass' state definition to be
included at that point in the state.
"""
tokens = {}
inheritable = {}
for c in itertools.chain((cls,), cls.__mro__):
toks = c.__dict__.get('tokens', {})
for state, items in toks.iteritems():
curitems = tokens.get(state)
if curitems is None:
tokens[state] = items
try:
inherit_ndx = items.index(inherit)
except ValueError:
continue
inheritable[state] = inherit_ndx
continue
inherit_ndx = inheritable.pop(state, None)
if inherit_ndx is None:
continue
# Replace the "inherit" value with the items
curitems[inherit_ndx:inherit_ndx+1] = items
try:
new_inh_ndx = items.index(inherit)
except ValueError:
pass
else:
inheritable[state] = inherit_ndx + new_inh_ndx
return tokens
def __call__(cls, *args, **kwds):
"""Instantiate cls after preprocessing its token definitions."""
if '_tokens' not in cls.__dict__:
cls._all_tokens = {}
cls._tmpname = 0
if hasattr(cls, 'token_variants') and cls.token_variants:
# don't process yet
pass
else:
cls._tokens = cls.process_tokendef('', cls.get_tokendefs())
return type.__call__(cls, *args, **kwds)
class RegexLexer(Lexer):
"""
Base for simple stateful regular expression-based lexers.
Simplifies the lexing process so that you need only
provide a list of states and regular expressions.
"""
__metaclass__ = RegexLexerMeta
#: Flags for compiling the regular expressions.
#: Defaults to MULTILINE.
flags = re.MULTILINE
#: Dict of ``{'state': [(regex, tokentype, new_state), ...], ...}``
#:
#: The initial state is 'root'.
#: ``new_state`` can be omitted to signify no state transition.
#: If it is a string, the state is pushed on the stack and changed.
#: If it is a tuple of strings, all states are pushed on the stack and
#: the current state will be the topmost.
#: It can also be ``combined('state1', 'state2', ...)``
#: to signify a new, anonymous state combined from the rules of two
#: or more existing ones.
#: Furthermore, it can be '#pop' to signify going back one step in
#: the state stack, or '#push' to push the current state on the stack
#: again.
#:
#: The tuple can also be replaced with ``include('state')``, in which
#: case the rules from the state named by the string are included in the
#: current one.
tokens = {}
def get_tokens_unprocessed(self, text, stack=('root',)):
"""
Split ``text`` into (tokentype, text) pairs.
``stack`` is the inital stack (default: ``['root']``)
"""
pos = 0
tokendefs = self._tokens
statestack = list(stack)
statetokens = tokendefs[statestack[-1]]
while 1:
for rexmatch, action, new_state in statetokens:
m = rexmatch(text, pos)
if m:
if type(action) is _TokenType:
yield pos, action, m.group()
else:
for item in action(self, m):
yield item
pos = m.end()
if new_state is not None:
# state transition
if isinstance(new_state, tuple):
for state in new_state:
if state == '#pop':
statestack.pop()
elif state == '#push':
statestack.append(statestack[-1])
else:
statestack.append(state)
elif isinstance(new_state, int):
# pop
del statestack[new_state:]
elif new_state == '#push':
statestack.append(statestack[-1])
else:
assert False, "wrong state def: %r" % new_state
statetokens = tokendefs[statestack[-1]]
break
else:
try:
if text[pos] == '\n':
# at EOL, reset state to "root"
statestack = ['root']
statetokens = tokendefs['root']
yield pos, Text, u'\n'
pos += 1
continue
yield pos, Error, text[pos]
pos += 1
except IndexError:
break
class LexerContext(object):
"""
A helper object that holds lexer position data.
"""
def __init__(self, text, pos, stack=None, end=None):
self.text = text
self.pos = pos
self.end = end or len(text) # end=0 not supported ;-)
self.stack = stack or ['root']
def __repr__(self):
return 'LexerContext(%r, %r, %r)' % (
self.text, self.pos, self.stack)
class ExtendedRegexLexer(RegexLexer):
"""
A RegexLexer that uses a context object to store its state.
"""
def get_tokens_unprocessed(self, text=None, context=None):
"""
Split ``text`` into (tokentype, text) pairs.
If ``context`` is given, use this lexer context instead.
"""
tokendefs = self._tokens
if not context:
ctx = LexerContext(text, 0)
statetokens = tokendefs['root']
else:
ctx = context
statetokens = tokendefs[ctx.stack[-1]]
text = ctx.text
while 1:
for rexmatch, action, new_state in statetokens:
m = rexmatch(text, ctx.pos, ctx.end)
if m:
if type(action) is _TokenType:
yield ctx.pos, action, m.group()
ctx.pos = m.end()
else:
for item in action(self, m, ctx):
yield item
if not new_state:
# altered the state stack?
statetokens = tokendefs[ctx.stack[-1]]
# CAUTION: callback must set ctx.pos!
if new_state is not None:
# state transition
if isinstance(new_state, tuple):
for state in new_state:
if state == '#pop':
ctx.stack.pop()
elif state == '#push':
ctx.stack.append(statestack[-1])
else:
ctx.stack.append(state)
elif isinstance(new_state, int):
# pop
del ctx.stack[new_state:]
elif new_state == '#push':
ctx.stack.append(ctx.stack[-1])
else:
assert False, "wrong state def: %r" % new_state
statetokens = tokendefs[ctx.stack[-1]]
break
else:
try:
if ctx.pos >= ctx.end:
break
if text[ctx.pos] == '\n':
# at EOL, reset state to "root"
ctx.stack = ['root']
statetokens = tokendefs['root']
yield ctx.pos, Text, u'\n'
ctx.pos += 1
continue
yield ctx.pos, Error, text[ctx.pos]
ctx.pos += 1
except IndexError:
break
def do_insertions(insertions, tokens):
"""
Helper for lexers which must combine the results of several
sublexers.
``insertions`` is a list of ``(index, itokens)`` pairs.
Each ``itokens`` iterable should be inserted at position
``index`` into the token stream given by the ``tokens``
argument.
The result is a combined token stream.
TODO: clean up the code here.
"""
insertions = iter(insertions)
try:
index, itokens = insertions.next()
except StopIteration:
# no insertions
for item in tokens:
yield item
return
realpos = None
insleft = True
# iterate over the token stream where we want to insert
# the tokens from the insertion list.
for i, t, v in tokens:
# first iteration. store the postition of first item
if realpos is None:
realpos = i
oldi = 0
while insleft and i + len(v) >= index:
tmpval = v[oldi:index - i]
yield realpos, t, tmpval
realpos += len(tmpval)
for it_index, it_token, it_value in itokens:
yield realpos, it_token, it_value
realpos += len(it_value)
oldi = index - i
try:
index, itokens = insertions.next()
except StopIteration:
insleft = False
break # not strictly necessary
yield realpos, t, v[oldi:]
realpos += len(v) - oldi
# leftover tokens
while insleft:
# no normal tokens, set realpos to zero
realpos = realpos or 0
for p, t, v in itokens:
yield realpos, t, v
realpos += len(v)
try:
index, itokens = insertions.next()
except StopIteration:
insleft = False
break # not strictly necessary

View file

@ -0,0 +1,240 @@
# -*- coding: utf-8 -*-
"""
pygments.lexers
~~~~~~~~~~~~~~~
Pygments lexers.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import sys
import types
import fnmatch
from os.path import basename
from pygments.lexers._mapping import LEXERS
from pygments.modeline import get_filetype_from_buffer
from pygments.plugin import find_plugin_lexers
from pygments.util import ClassNotFound, bytes
__all__ = ['get_lexer_by_name', 'get_lexer_for_filename', 'find_lexer_class',
'guess_lexer'] + LEXERS.keys()
_lexer_cache = {}
def _load_lexers(module_name):
"""
Load a lexer (and all others in the module too).
"""
mod = __import__(module_name, None, None, ['__all__'])
for lexer_name in mod.__all__:
cls = getattr(mod, lexer_name)
_lexer_cache[cls.name] = cls
def get_all_lexers():
"""
Return a generator of tuples in the form ``(name, aliases,
filenames, mimetypes)`` of all know lexers.
"""
for item in LEXERS.itervalues():
yield item[1:]
for lexer in find_plugin_lexers():
yield lexer.name, lexer.aliases, lexer.filenames, lexer.mimetypes
def find_lexer_class(name):
"""
Lookup a lexer class by name. Return None if not found.
"""
if name in _lexer_cache:
return _lexer_cache[name]
# lookup builtin lexers
for module_name, lname, aliases, _, _ in LEXERS.itervalues():
if name == lname:
_load_lexers(module_name)
return _lexer_cache[name]
# continue with lexers from setuptools entrypoints
for cls in find_plugin_lexers():
if cls.name == name:
return cls
def get_lexer_by_name(_alias, **options):
"""
Get a lexer by an alias.
"""
# lookup builtin lexers
for module_name, name, aliases, _, _ in LEXERS.itervalues():
if _alias in aliases:
if name not in _lexer_cache:
_load_lexers(module_name)
return _lexer_cache[name](**options)
# continue with lexers from setuptools entrypoints
for cls in find_plugin_lexers():
if _alias in cls.aliases:
return cls(**options)
raise ClassNotFound('no lexer for alias %r found' % _alias)
def get_lexer_for_filename(_fn, code=None, **options):
"""
Get a lexer for a filename. If multiple lexers match the filename
pattern, use ``analyze_text()`` to figure out which one is more
appropriate.
"""
matches = []
fn = basename(_fn)
for modname, name, _, filenames, _ in LEXERS.itervalues():
for filename in filenames:
if fnmatch.fnmatch(fn, filename):
if name not in _lexer_cache:
_load_lexers(modname)
matches.append((_lexer_cache[name], filename))
for cls in find_plugin_lexers():
for filename in cls.filenames:
if fnmatch.fnmatch(fn, filename):
matches.append((cls, filename))
if sys.version_info > (3,) and isinstance(code, bytes):
# decode it, since all analyse_text functions expect unicode
code = code.decode('latin1')
def get_rating(info):
cls, filename = info
# explicit patterns get a bonus
bonus = '*' not in filename and 0.5 or 0
# The class _always_ defines analyse_text because it's included in
# the Lexer class. The default implementation returns None which
# gets turned into 0.0. Run scripts/detect_missing_analyse_text.py
# to find lexers which need it overridden.
if code:
return cls.analyse_text(code) + bonus
return cls.priority + bonus
if matches:
matches.sort(key=get_rating)
#print "Possible lexers, after sort:", matches
return matches[-1][0](**options)
raise ClassNotFound('no lexer for filename %r found' % _fn)
def get_lexer_for_mimetype(_mime, **options):
"""
Get a lexer for a mimetype.
"""
for modname, name, _, _, mimetypes in LEXERS.itervalues():
if _mime in mimetypes:
if name not in _lexer_cache:
_load_lexers(modname)
return _lexer_cache[name](**options)
for cls in find_plugin_lexers():
if _mime in cls.mimetypes:
return cls(**options)
raise ClassNotFound('no lexer for mimetype %r found' % _mime)
def _iter_lexerclasses():
"""
Return an iterator over all lexer classes.
"""
for key in sorted(LEXERS):
module_name, name = LEXERS[key][:2]
if name not in _lexer_cache:
_load_lexers(module_name)
yield _lexer_cache[name]
for lexer in find_plugin_lexers():
yield lexer
def guess_lexer_for_filename(_fn, _text, **options):
"""
Lookup all lexers that handle those filenames primary (``filenames``)
or secondary (``alias_filenames``). Then run a text analysis for those
lexers and choose the best result.
usage::
>>> from pygments.lexers import guess_lexer_for_filename
>>> guess_lexer_for_filename('hello.html', '<%= @foo %>')
<pygments.lexers.templates.RhtmlLexer object at 0xb7d2f32c>
>>> guess_lexer_for_filename('hello.html', '<h1>{{ title|e }}</h1>')
<pygments.lexers.templates.HtmlDjangoLexer object at 0xb7d2f2ac>
>>> guess_lexer_for_filename('style.css', 'a { color: <?= $link ?> }')
<pygments.lexers.templates.CssPhpLexer object at 0xb7ba518c>
"""
fn = basename(_fn)
primary = None
matching_lexers = set()
for lexer in _iter_lexerclasses():
for filename in lexer.filenames:
if fnmatch.fnmatch(fn, filename):
matching_lexers.add(lexer)
primary = lexer
for filename in lexer.alias_filenames:
if fnmatch.fnmatch(fn, filename):
matching_lexers.add(lexer)
if not matching_lexers:
raise ClassNotFound('no lexer for filename %r found' % fn)
if len(matching_lexers) == 1:
return matching_lexers.pop()(**options)
result = []
for lexer in matching_lexers:
rv = lexer.analyse_text(_text)
if rv == 1.0:
return lexer(**options)
result.append((rv, lexer))
result.sort()
if not result[-1][0] and primary is not None:
return primary(**options)
return result[-1][1](**options)
def guess_lexer(_text, **options):
"""
Guess a lexer by strong distinctions in the text (eg, shebang).
"""
# try to get a vim modeline first
ft = get_filetype_from_buffer(_text)
if ft is not None:
try:
return get_lexer_by_name(ft, **options)
except ClassNotFound:
pass
best_lexer = [0.0, None]
for lexer in _iter_lexerclasses():
rv = lexer.analyse_text(_text)
if rv == 1.0:
return lexer(**options)
if rv > best_lexer[0]:
best_lexer[:] = (rv, lexer)
if not best_lexer[0] or best_lexer[1] is None:
raise ClassNotFound('no lexer matching the text found')
return best_lexer[1](**options)
class _automodule(types.ModuleType):
"""Automatically import lexers."""
def __getattr__(self, name):
info = LEXERS.get(name)
if info:
_load_lexers(info[0])
cls = _lexer_cache[info[1]]
setattr(self, name, cls)
return cls
raise AttributeError(name)
oldmod = sys.modules['pygments.lexers']
newmod = _automodule('pygments.lexers')
newmod.__dict__.update(oldmod.__dict__)
sys.modules['pygments.lexers'] = newmod
del newmod.newmod, newmod.oldmod, newmod.sys, newmod.types

View file

@ -0,0 +1,249 @@
# -*- coding: utf-8 -*-
"""
pygments.lexers._luabuiltins
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
This file contains the names and modules of lua functions
It is able to re-generate itself, but for adding new functions you
probably have to add some callbacks (see function module_callbacks).
Do not edit the MODULES dict by hand.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
MODULES = {'basic': ['_G',
'_VERSION',
'assert',
'collectgarbage',
'dofile',
'error',
'getfenv',
'getmetatable',
'ipairs',
'load',
'loadfile',
'loadstring',
'next',
'pairs',
'pcall',
'print',
'rawequal',
'rawget',
'rawset',
'select',
'setfenv',
'setmetatable',
'tonumber',
'tostring',
'type',
'unpack',
'xpcall'],
'coroutine': ['coroutine.create',
'coroutine.resume',
'coroutine.running',
'coroutine.status',
'coroutine.wrap',
'coroutine.yield'],
'debug': ['debug.debug',
'debug.getfenv',
'debug.gethook',
'debug.getinfo',
'debug.getlocal',
'debug.getmetatable',
'debug.getregistry',
'debug.getupvalue',
'debug.setfenv',
'debug.sethook',
'debug.setlocal',
'debug.setmetatable',
'debug.setupvalue',
'debug.traceback'],
'io': ['io.close',
'io.flush',
'io.input',
'io.lines',
'io.open',
'io.output',
'io.popen',
'io.read',
'io.tmpfile',
'io.type',
'io.write'],
'math': ['math.abs',
'math.acos',
'math.asin',
'math.atan2',
'math.atan',
'math.ceil',
'math.cosh',
'math.cos',
'math.deg',
'math.exp',
'math.floor',
'math.fmod',
'math.frexp',
'math.huge',
'math.ldexp',
'math.log10',
'math.log',
'math.max',
'math.min',
'math.modf',
'math.pi',
'math.pow',
'math.rad',
'math.random',
'math.randomseed',
'math.sinh',
'math.sin',
'math.sqrt',
'math.tanh',
'math.tan'],
'modules': ['module',
'require',
'package.cpath',
'package.loaded',
'package.loadlib',
'package.path',
'package.preload',
'package.seeall'],
'os': ['os.clock',
'os.date',
'os.difftime',
'os.execute',
'os.exit',
'os.getenv',
'os.remove',
'os.rename',
'os.setlocale',
'os.time',
'os.tmpname'],
'string': ['string.byte',
'string.char',
'string.dump',
'string.find',
'string.format',
'string.gmatch',
'string.gsub',
'string.len',
'string.lower',
'string.match',
'string.rep',
'string.reverse',
'string.sub',
'string.upper'],
'table': ['table.concat',
'table.insert',
'table.maxn',
'table.remove',
'table.sort']}
if __name__ == '__main__':
import re
import urllib
import pprint
# you can't generally find out what module a function belongs to if you
# have only its name. Because of this, here are some callback functions
# that recognize if a gioven function belongs to a specific module
def module_callbacks():
def is_in_coroutine_module(name):
return name.startswith('coroutine.')
def is_in_modules_module(name):
if name in ['require', 'module'] or name.startswith('package'):
return True
else:
return False
def is_in_string_module(name):
return name.startswith('string.')
def is_in_table_module(name):
return name.startswith('table.')
def is_in_math_module(name):
return name.startswith('math')
def is_in_io_module(name):
return name.startswith('io.')
def is_in_os_module(name):
return name.startswith('os.')
def is_in_debug_module(name):
return name.startswith('debug.')
return {'coroutine': is_in_coroutine_module,
'modules': is_in_modules_module,
'string': is_in_string_module,
'table': is_in_table_module,
'math': is_in_math_module,
'io': is_in_io_module,
'os': is_in_os_module,
'debug': is_in_debug_module}
def get_newest_version():
f = urllib.urlopen('http://www.lua.org/manual/')
r = re.compile(r'^<A HREF="(\d\.\d)/">Lua \1</A>')
for line in f:
m = r.match(line)
if m is not None:
return m.groups()[0]
def get_lua_functions(version):
f = urllib.urlopen('http://www.lua.org/manual/%s/' % version)
r = re.compile(r'^<A HREF="manual.html#pdf-(.+)">\1</A>')
functions = []
for line in f:
m = r.match(line)
if m is not None:
functions.append(m.groups()[0])
return functions
def get_function_module(name):
for mod, cb in module_callbacks().iteritems():
if cb(name):
return mod
if '.' in name:
return name.split('.')[0]
else:
return 'basic'
def regenerate(filename, modules):
f = open(filename)
try:
content = f.read()
finally:
f.close()
header = content[:content.find('MODULES = {')]
footer = content[content.find("if __name__ == '__main__':"):]
f = open(filename, 'w')
f.write(header)
f.write('MODULES = %s\n\n' % pprint.pformat(modules))
f.write(footer)
f.close()
def run():
version = get_newest_version()
print '> Downloading function index for Lua %s' % version
functions = get_lua_functions(version)
print '> %d functions found:' % len(functions)
modules = {}
for full_function_name in functions:
print '>> %s' % full_function_name
m = get_function_module(full_function_name)
modules.setdefault(m, []).append(full_function_name)
regenerate(__file__, modules)
run()

View file

@ -0,0 +1,350 @@
# -*- coding: utf-8 -*-
"""
pygments.lexers._mapping
~~~~~~~~~~~~~~~~~~~~~~~~
Lexer mapping defintions. This file is generated by itself. Everytime
you change something on a builtin lexer defintion, run this script from
the lexers folder to update it.
Do not alter the LEXERS dictionary by hand.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
LEXERS = {
'ABAPLexer': ('pygments.lexers.other', 'ABAP', ('abap',), ('*.abap',), ('text/x-abap',)),
'ActionScript3Lexer': ('pygments.lexers.web', 'ActionScript 3', ('as3', 'actionscript3'), ('*.as',), ('application/x-actionscript', 'text/x-actionscript', 'text/actionscript')),
'ActionScriptLexer': ('pygments.lexers.web', 'ActionScript', ('as', 'actionscript'), ('*.as',), ('application/x-actionscript3', 'text/x-actionscript3', 'text/actionscript3')),
'AdaLexer': ('pygments.lexers.compiled', 'Ada', ('ada', 'ada95ada2005'), ('*.adb', '*.ads', '*.ada'), ('text/x-ada',)),
'AgdaLexer': ('pygments.lexers.functional', 'Agda', ('agda',), ('*.agda',), ('text/x-agda',)),
'AntlrActionScriptLexer': ('pygments.lexers.parsers', 'ANTLR With ActionScript Target', ('antlr-as', 'antlr-actionscript'), ('*.G', '*.g'), ()),
'AntlrCSharpLexer': ('pygments.lexers.parsers', 'ANTLR With C# Target', ('antlr-csharp', 'antlr-c#'), ('*.G', '*.g'), ()),
'AntlrCppLexer': ('pygments.lexers.parsers', 'ANTLR With CPP Target', ('antlr-cpp',), ('*.G', '*.g'), ()),
'AntlrJavaLexer': ('pygments.lexers.parsers', 'ANTLR With Java Target', ('antlr-java',), ('*.G', '*.g'), ()),
'AntlrLexer': ('pygments.lexers.parsers', 'ANTLR', ('antlr',), (), ()),
'AntlrObjectiveCLexer': ('pygments.lexers.parsers', 'ANTLR With ObjectiveC Target', ('antlr-objc',), ('*.G', '*.g'), ()),
'AntlrPerlLexer': ('pygments.lexers.parsers', 'ANTLR With Perl Target', ('antlr-perl',), ('*.G', '*.g'), ()),
'AntlrPythonLexer': ('pygments.lexers.parsers', 'ANTLR With Python Target', ('antlr-python',), ('*.G', '*.g'), ()),
'AntlrRubyLexer': ('pygments.lexers.parsers', 'ANTLR With Ruby Target', ('antlr-ruby', 'antlr-rb'), ('*.G', '*.g'), ()),
'ApacheConfLexer': ('pygments.lexers.text', 'ApacheConf', ('apacheconf', 'aconf', 'apache'), ('.htaccess', 'apache.conf', 'apache2.conf'), ('text/x-apacheconf',)),
'AppleScriptLexer': ('pygments.lexers.other', 'AppleScript', ('applescript',), ('*.applescript',), ()),
'AspectJLexer': ('pygments.lexers.jvm', 'AspectJ', ('aspectj',), ('*.aj',), ('text/x-aspectj',)),
'AsymptoteLexer': ('pygments.lexers.other', 'Asymptote', ('asy', 'asymptote'), ('*.asy',), ('text/x-asymptote',)),
'AutoItLexer': ('pygments.lexers.other', 'AutoIt', ('autoit', 'Autoit'), ('*.au3',), ('text/x-autoit',)),
'AutohotkeyLexer': ('pygments.lexers.other', 'autohotkey', ('ahk', 'autohotkey'), ('*.ahk', '*.ahkl'), ('text/x-autohotkey',)),
'AwkLexer': ('pygments.lexers.other', 'Awk', ('awk', 'gawk', 'mawk', 'nawk'), ('*.awk',), ('application/x-awk',)),
'BBCodeLexer': ('pygments.lexers.text', 'BBCode', ('bbcode',), (), ('text/x-bbcode',)),
'BaseMakefileLexer': ('pygments.lexers.text', 'Base Makefile', ('basemake',), (), ()),
'BashLexer': ('pygments.lexers.shell', 'Bash', ('bash', 'sh', 'ksh'), ('*.sh', '*.ksh', '*.bash', '*.ebuild', '*.eclass', '.bashrc', 'bashrc', '.bash_*', 'bash_*'), ('application/x-sh', 'application/x-shellscript')),
'BashSessionLexer': ('pygments.lexers.shell', 'Bash Session', ('console',), ('*.sh-session',), ('application/x-shell-session',)),
'BatchLexer': ('pygments.lexers.shell', 'Batchfile', ('bat', 'dosbatch', 'winbatch'), ('*.bat', '*.cmd'), ('application/x-dos-batch',)),
'BefungeLexer': ('pygments.lexers.other', 'Befunge', ('befunge',), ('*.befunge',), ('application/x-befunge',)),
'BlitzBasicLexer': ('pygments.lexers.compiled', 'BlitzBasic', ('blitzbasic', 'b3d', 'bplus'), ('*.bb', '*.decls'), ('text/x-bb',)),
'BlitzMaxLexer': ('pygments.lexers.compiled', 'BlitzMax', ('blitzmax', 'bmax'), ('*.bmx',), ('text/x-bmx',)),
'BooLexer': ('pygments.lexers.dotnet', 'Boo', ('boo',), ('*.boo',), ('text/x-boo',)),
'BrainfuckLexer': ('pygments.lexers.other', 'Brainfuck', ('brainfuck', 'bf'), ('*.bf', '*.b'), ('application/x-brainfuck',)),
'BroLexer': ('pygments.lexers.other', 'Bro', ('bro',), ('*.bro',), ()),
'BugsLexer': ('pygments.lexers.math', 'BUGS', ('bugs', 'winbugs', 'openbugs'), ('*.bug',), ()),
'CLexer': ('pygments.lexers.compiled', 'C', ('c',), ('*.c', '*.h', '*.idc'), ('text/x-chdr', 'text/x-csrc')),
'CMakeLexer': ('pygments.lexers.text', 'CMake', ('cmake',), ('*.cmake', 'CMakeLists.txt'), ('text/x-cmake',)),
'CObjdumpLexer': ('pygments.lexers.asm', 'c-objdump', ('c-objdump',), ('*.c-objdump',), ('text/x-c-objdump',)),
'CSharpAspxLexer': ('pygments.lexers.dotnet', 'aspx-cs', ('aspx-cs',), ('*.aspx', '*.asax', '*.ascx', '*.ashx', '*.asmx', '*.axd'), ()),
'CSharpLexer': ('pygments.lexers.dotnet', 'C#', ('csharp', 'c#'), ('*.cs',), ('text/x-csharp',)),
'Ca65Lexer': ('pygments.lexers.asm', 'ca65', ('ca65',), ('*.s',), ()),
'CbmBasicV2Lexer': ('pygments.lexers.other', 'CBM BASIC V2', ('cbmbas',), ('*.bas',), ()),
'CeylonLexer': ('pygments.lexers.jvm', 'Ceylon', ('ceylon',), ('*.ceylon',), ('text/x-ceylon',)),
'Cfengine3Lexer': ('pygments.lexers.other', 'CFEngine3', ('cfengine3', 'cf3'), ('*.cf',), ()),
'CheetahHtmlLexer': ('pygments.lexers.templates', 'HTML+Cheetah', ('html+cheetah', 'html+spitfire', 'htmlcheetah'), (), ('text/html+cheetah', 'text/html+spitfire')),
'CheetahJavascriptLexer': ('pygments.lexers.templates', 'JavaScript+Cheetah', ('js+cheetah', 'javascript+cheetah', 'js+spitfire', 'javascript+spitfire'), (), ('application/x-javascript+cheetah', 'text/x-javascript+cheetah', 'text/javascript+cheetah', 'application/x-javascript+spitfire', 'text/x-javascript+spitfire', 'text/javascript+spitfire')),
'CheetahLexer': ('pygments.lexers.templates', 'Cheetah', ('cheetah', 'spitfire'), ('*.tmpl', '*.spt'), ('application/x-cheetah', 'application/x-spitfire')),
'CheetahXmlLexer': ('pygments.lexers.templates', 'XML+Cheetah', ('xml+cheetah', 'xml+spitfire'), (), ('application/xml+cheetah', 'application/xml+spitfire')),
'ClayLexer': ('pygments.lexers.compiled', 'Clay', ('clay',), ('*.clay',), ('text/x-clay',)),
'ClojureLexer': ('pygments.lexers.jvm', 'Clojure', ('clojure', 'clj'), ('*.clj',), ('text/x-clojure', 'application/x-clojure')),
'CobolFreeformatLexer': ('pygments.lexers.compiled', 'COBOLFree', ('cobolfree',), ('*.cbl', '*.CBL'), ()),
'CobolLexer': ('pygments.lexers.compiled', 'COBOL', ('cobol',), ('*.cob', '*.COB', '*.cpy', '*.CPY'), ('text/x-cobol',)),
'CoffeeScriptLexer': ('pygments.lexers.web', 'CoffeeScript', ('coffee-script', 'coffeescript', 'coffee'), ('*.coffee',), ('text/coffeescript',)),
'ColdfusionHtmlLexer': ('pygments.lexers.templates', 'Coldfusion HTML', ('cfm',), ('*.cfm', '*.cfml', '*.cfc'), ('application/x-coldfusion',)),
'ColdfusionLexer': ('pygments.lexers.templates', 'cfstatement', ('cfs',), (), ()),
'CommonLispLexer': ('pygments.lexers.functional', 'Common Lisp', ('common-lisp', 'cl', 'lisp'), ('*.cl', '*.lisp', '*.el'), ('text/x-common-lisp',)),
'CoqLexer': ('pygments.lexers.functional', 'Coq', ('coq',), ('*.v',), ('text/x-coq',)),
'CppLexer': ('pygments.lexers.compiled', 'C++', ('cpp', 'c++'), ('*.cpp', '*.hpp', '*.c++', '*.h++', '*.cc', '*.hh', '*.cxx', '*.hxx', '*.C', '*.H', '*.cp', '*.CPP'), ('text/x-c++hdr', 'text/x-c++src')),
'CppObjdumpLexer': ('pygments.lexers.asm', 'cpp-objdump', ('cpp-objdump', 'c++-objdumb', 'cxx-objdump'), ('*.cpp-objdump', '*.c++-objdump', '*.cxx-objdump'), ('text/x-cpp-objdump',)),
'CrocLexer': ('pygments.lexers.agile', 'Croc', ('croc',), ('*.croc',), ('text/x-crocsrc',)),
'CssDjangoLexer': ('pygments.lexers.templates', 'CSS+Django/Jinja', ('css+django', 'css+jinja'), (), ('text/css+django', 'text/css+jinja')),
'CssErbLexer': ('pygments.lexers.templates', 'CSS+Ruby', ('css+erb', 'css+ruby'), (), ('text/css+ruby',)),
'CssGenshiLexer': ('pygments.lexers.templates', 'CSS+Genshi Text', ('css+genshitext', 'css+genshi'), (), ('text/css+genshi',)),
'CssLexer': ('pygments.lexers.web', 'CSS', ('css',), ('*.css',), ('text/css',)),
'CssPhpLexer': ('pygments.lexers.templates', 'CSS+PHP', ('css+php',), (), ('text/css+php',)),
'CssSmartyLexer': ('pygments.lexers.templates', 'CSS+Smarty', ('css+smarty',), (), ('text/css+smarty',)),
'CudaLexer': ('pygments.lexers.compiled', 'CUDA', ('cuda', 'cu'), ('*.cu', '*.cuh'), ('text/x-cuda',)),
'CythonLexer': ('pygments.lexers.compiled', 'Cython', ('cython', 'pyx', 'pyrex'), ('*.pyx', '*.pxd', '*.pxi'), ('text/x-cython', 'application/x-cython')),
'DLexer': ('pygments.lexers.compiled', 'D', ('d',), ('*.d', '*.di'), ('text/x-dsrc',)),
'DObjdumpLexer': ('pygments.lexers.asm', 'd-objdump', ('d-objdump',), ('*.d-objdump',), ('text/x-d-objdump',)),
'DarcsPatchLexer': ('pygments.lexers.text', 'Darcs Patch', ('dpatch',), ('*.dpatch', '*.darcspatch'), ()),
'DartLexer': ('pygments.lexers.web', 'Dart', ('dart',), ('*.dart',), ('text/x-dart',)),
'DebianControlLexer': ('pygments.lexers.text', 'Debian Control file', ('control', 'debcontrol'), ('control',), ()),
'DelphiLexer': ('pygments.lexers.compiled', 'Delphi', ('delphi', 'pas', 'pascal', 'objectpascal'), ('*.pas',), ('text/x-pascal',)),
'DgLexer': ('pygments.lexers.agile', 'dg', ('dg',), ('*.dg',), ('text/x-dg',)),
'DiffLexer': ('pygments.lexers.text', 'Diff', ('diff', 'udiff'), ('*.diff', '*.patch'), ('text/x-diff', 'text/x-patch')),
'DjangoLexer': ('pygments.lexers.templates', 'Django/Jinja', ('django', 'jinja'), (), ('application/x-django-templating', 'application/x-jinja')),
'DtdLexer': ('pygments.lexers.web', 'DTD', ('dtd',), ('*.dtd',), ('application/xml-dtd',)),
'DuelLexer': ('pygments.lexers.web', 'Duel', ('duel', 'Duel Engine', 'Duel View', 'JBST', 'jbst', 'JsonML+BST'), ('*.duel', '*.jbst'), ('text/x-duel', 'text/x-jbst')),
'DylanConsoleLexer': ('pygments.lexers.compiled', 'Dylan session', ('dylan-console', 'dylan-repl'), ('*.dylan-console',), ('text/x-dylan-console',)),
'DylanLexer': ('pygments.lexers.compiled', 'Dylan', ('dylan',), ('*.dylan', '*.dyl', '*.intr'), ('text/x-dylan',)),
'DylanLidLexer': ('pygments.lexers.compiled', 'DylanLID', ('dylan-lid', 'lid'), ('*.lid', '*.hdp'), ('text/x-dylan-lid',)),
'ECLLexer': ('pygments.lexers.other', 'ECL', ('ecl',), ('*.ecl',), ('application/x-ecl',)),
'ECLexer': ('pygments.lexers.compiled', 'eC', ('ec',), ('*.ec', '*.eh'), ('text/x-echdr', 'text/x-ecsrc')),
'EbnfLexer': ('pygments.lexers.text', 'EBNF', ('ebnf',), ('*.ebnf',), ('text/x-ebnf',)),
'ElixirConsoleLexer': ('pygments.lexers.functional', 'Elixir iex session', ('iex',), (), ('text/x-elixir-shellsession',)),
'ElixirLexer': ('pygments.lexers.functional', 'Elixir', ('elixir', 'ex', 'exs'), ('*.ex', '*.exs'), ('text/x-elixir',)),
'ErbLexer': ('pygments.lexers.templates', 'ERB', ('erb',), (), ('application/x-ruby-templating',)),
'ErlangLexer': ('pygments.lexers.functional', 'Erlang', ('erlang',), ('*.erl', '*.hrl', '*.es', '*.escript'), ('text/x-erlang',)),
'ErlangShellLexer': ('pygments.lexers.functional', 'Erlang erl session', ('erl',), ('*.erl-sh',), ('text/x-erl-shellsession',)),
'EvoqueHtmlLexer': ('pygments.lexers.templates', 'HTML+Evoque', ('html+evoque',), ('*.html',), ('text/html+evoque',)),
'EvoqueLexer': ('pygments.lexers.templates', 'Evoque', ('evoque',), ('*.evoque',), ('application/x-evoque',)),
'EvoqueXmlLexer': ('pygments.lexers.templates', 'XML+Evoque', ('xml+evoque',), ('*.xml',), ('application/xml+evoque',)),
'FSharpLexer': ('pygments.lexers.dotnet', 'FSharp', ('fsharp',), ('*.fs', '*.fsi'), ('text/x-fsharp',)),
'FactorLexer': ('pygments.lexers.agile', 'Factor', ('factor',), ('*.factor',), ('text/x-factor',)),
'FancyLexer': ('pygments.lexers.agile', 'Fancy', ('fancy', 'fy'), ('*.fy', '*.fancypack'), ('text/x-fancysrc',)),
'FantomLexer': ('pygments.lexers.compiled', 'Fantom', ('fan',), ('*.fan',), ('application/x-fantom',)),
'FelixLexer': ('pygments.lexers.compiled', 'Felix', ('felix', 'flx'), ('*.flx', '*.flxh'), ('text/x-felix',)),
'FortranLexer': ('pygments.lexers.compiled', 'Fortran', ('fortran',), ('*.f', '*.f90', '*.F', '*.F90'), ('text/x-fortran',)),
'FoxProLexer': ('pygments.lexers.foxpro', 'FoxPro', ('Clipper', 'XBase'), ('*.PRG', '*.prg'), ()),
'GLShaderLexer': ('pygments.lexers.compiled', 'GLSL', ('glsl',), ('*.vert', '*.frag', '*.geo'), ('text/x-glslsrc',)),
'GasLexer': ('pygments.lexers.asm', 'GAS', ('gas', 'asm'), ('*.s', '*.S'), ('text/x-gas',)),
'GenshiLexer': ('pygments.lexers.templates', 'Genshi', ('genshi', 'kid', 'xml+genshi', 'xml+kid'), ('*.kid',), ('application/x-genshi', 'application/x-kid')),
'GenshiTextLexer': ('pygments.lexers.templates', 'Genshi Text', ('genshitext',), (), ('application/x-genshi-text', 'text/x-genshi')),
'GettextLexer': ('pygments.lexers.text', 'Gettext Catalog', ('pot', 'po'), ('*.pot', '*.po'), ('application/x-gettext', 'text/x-gettext', 'text/gettext')),
'GherkinLexer': ('pygments.lexers.other', 'Gherkin', ('Cucumber', 'cucumber', 'Gherkin', 'gherkin'), ('*.feature',), ('text/x-gherkin',)),
'GnuplotLexer': ('pygments.lexers.other', 'Gnuplot', ('gnuplot',), ('*.plot', '*.plt'), ('text/x-gnuplot',)),
'GoLexer': ('pygments.lexers.compiled', 'Go', ('go',), ('*.go',), ('text/x-gosrc',)),
'GoodDataCLLexer': ('pygments.lexers.other', 'GoodData-CL', ('gooddata-cl',), ('*.gdc',), ('text/x-gooddata-cl',)),
'GosuLexer': ('pygments.lexers.jvm', 'Gosu', ('gosu',), ('*.gs', '*.gsx', '*.gsp', '*.vark'), ('text/x-gosu',)),
'GosuTemplateLexer': ('pygments.lexers.jvm', 'Gosu Template', ('gst',), ('*.gst',), ('text/x-gosu-template',)),
'GroffLexer': ('pygments.lexers.text', 'Groff', ('groff', 'nroff', 'man'), ('*.[1234567]', '*.man'), ('application/x-troff', 'text/troff')),
'GroovyLexer': ('pygments.lexers.jvm', 'Groovy', ('groovy',), ('*.groovy',), ('text/x-groovy',)),
'HamlLexer': ('pygments.lexers.web', 'Haml', ('haml', 'HAML'), ('*.haml',), ('text/x-haml',)),
'HaskellLexer': ('pygments.lexers.functional', 'Haskell', ('haskell', 'hs'), ('*.hs',), ('text/x-haskell',)),
'HaxeLexer': ('pygments.lexers.web', 'Haxe', ('hx', 'Haxe', 'haxe', 'haXe', 'hxsl'), ('*.hx', '*.hxsl'), ('text/haxe', 'text/x-haxe', 'text/x-hx')),
'HtmlDjangoLexer': ('pygments.lexers.templates', 'HTML+Django/Jinja', ('html+django', 'html+jinja', 'htmldjango'), (), ('text/html+django', 'text/html+jinja')),
'HtmlGenshiLexer': ('pygments.lexers.templates', 'HTML+Genshi', ('html+genshi', 'html+kid'), (), ('text/html+genshi',)),
'HtmlLexer': ('pygments.lexers.web', 'HTML', ('html',), ('*.html', '*.htm', '*.xhtml', '*.xslt'), ('text/html', 'application/xhtml+xml')),
'HtmlPhpLexer': ('pygments.lexers.templates', 'HTML+PHP', ('html+php',), ('*.phtml',), ('application/x-php', 'application/x-httpd-php', 'application/x-httpd-php3', 'application/x-httpd-php4', 'application/x-httpd-php5')),
'HtmlSmartyLexer': ('pygments.lexers.templates', 'HTML+Smarty', ('html+smarty',), (), ('text/html+smarty',)),
'HttpLexer': ('pygments.lexers.text', 'HTTP', ('http',), (), ()),
'HxmlLexer': ('pygments.lexers.text', 'Hxml', ('haxeml', 'hxml'), ('*.hxml',), ()),
'HybrisLexer': ('pygments.lexers.other', 'Hybris', ('hybris', 'hy'), ('*.hy', '*.hyb'), ('text/x-hybris', 'application/x-hybris')),
'IDLLexer': ('pygments.lexers.math', 'IDL', ('idl',), ('*.pro',), ('text/idl',)),
'IgorLexer': ('pygments.lexers.math', 'Igor', ('igor', 'igorpro'), ('*.ipf',), ('text/ipf',)),
'IniLexer': ('pygments.lexers.text', 'INI', ('ini', 'cfg', 'dosini'), ('*.ini', '*.cfg'), ('text/x-ini',)),
'IoLexer': ('pygments.lexers.agile', 'Io', ('io',), ('*.io',), ('text/x-iosrc',)),
'IokeLexer': ('pygments.lexers.jvm', 'Ioke', ('ioke', 'ik'), ('*.ik',), ('text/x-iokesrc',)),
'IrcLogsLexer': ('pygments.lexers.text', 'IRC logs', ('irc',), ('*.weechatlog',), ('text/x-irclog',)),
'JadeLexer': ('pygments.lexers.web', 'Jade', ('jade', 'JADE'), ('*.jade',), ('text/x-jade',)),
'JagsLexer': ('pygments.lexers.math', 'JAGS', ('jags',), ('*.jag', '*.bug'), ()),
'JavaLexer': ('pygments.lexers.jvm', 'Java', ('java',), ('*.java',), ('text/x-java',)),
'JavascriptDjangoLexer': ('pygments.lexers.templates', 'JavaScript+Django/Jinja', ('js+django', 'javascript+django', 'js+jinja', 'javascript+jinja'), (), ('application/x-javascript+django', 'application/x-javascript+jinja', 'text/x-javascript+django', 'text/x-javascript+jinja', 'text/javascript+django', 'text/javascript+jinja')),
'JavascriptErbLexer': ('pygments.lexers.templates', 'JavaScript+Ruby', ('js+erb', 'javascript+erb', 'js+ruby', 'javascript+ruby'), (), ('application/x-javascript+ruby', 'text/x-javascript+ruby', 'text/javascript+ruby')),
'JavascriptGenshiLexer': ('pygments.lexers.templates', 'JavaScript+Genshi Text', ('js+genshitext', 'js+genshi', 'javascript+genshitext', 'javascript+genshi'), (), ('application/x-javascript+genshi', 'text/x-javascript+genshi', 'text/javascript+genshi')),
'JavascriptLexer': ('pygments.lexers.web', 'JavaScript', ('js', 'javascript'), ('*.js',), ('application/javascript', 'application/x-javascript', 'text/x-javascript', 'text/javascript')),
'JavascriptPhpLexer': ('pygments.lexers.templates', 'JavaScript+PHP', ('js+php', 'javascript+php'), (), ('application/x-javascript+php', 'text/x-javascript+php', 'text/javascript+php')),
'JavascriptSmartyLexer': ('pygments.lexers.templates', 'JavaScript+Smarty', ('js+smarty', 'javascript+smarty'), (), ('application/x-javascript+smarty', 'text/x-javascript+smarty', 'text/javascript+smarty')),
'JsonLexer': ('pygments.lexers.web', 'JSON', ('json',), ('*.json',), ('application/json',)),
'JspLexer': ('pygments.lexers.templates', 'Java Server Page', ('jsp',), ('*.jsp',), ('application/x-jsp',)),
'JuliaConsoleLexer': ('pygments.lexers.math', 'Julia console', ('jlcon',), (), ()),
'JuliaLexer': ('pygments.lexers.math', 'Julia', ('julia', 'jl'), ('*.jl',), ('text/x-julia', 'application/x-julia')),
'KconfigLexer': ('pygments.lexers.other', 'Kconfig', ('kconfig', 'menuconfig', 'linux-config', 'kernel-config'), ('Kconfig', '*Config.in*', 'external.in*', 'standard-modules.in'), ('text/x-kconfig',)),
'KokaLexer': ('pygments.lexers.functional', 'Koka', ('koka',), ('*.kk', '*.kki'), ('text/x-koka',)),
'KotlinLexer': ('pygments.lexers.jvm', 'Kotlin', ('kotlin',), ('*.kt',), ('text/x-kotlin',)),
'LassoCssLexer': ('pygments.lexers.templates', 'CSS+Lasso', ('css+lasso',), (), ('text/css+lasso',)),
'LassoHtmlLexer': ('pygments.lexers.templates', 'HTML+Lasso', ('html+lasso',), (), ('text/html+lasso', 'application/x-httpd-lasso', 'application/x-httpd-lasso[89]')),
'LassoJavascriptLexer': ('pygments.lexers.templates', 'JavaScript+Lasso', ('js+lasso', 'javascript+lasso'), (), ('application/x-javascript+lasso', 'text/x-javascript+lasso', 'text/javascript+lasso')),
'LassoLexer': ('pygments.lexers.web', 'Lasso', ('lasso', 'lassoscript'), ('*.lasso', '*.lasso[89]'), ('text/x-lasso',)),
'LassoXmlLexer': ('pygments.lexers.templates', 'XML+Lasso', ('xml+lasso',), (), ('application/xml+lasso',)),
'LighttpdConfLexer': ('pygments.lexers.text', 'Lighttpd configuration file', ('lighty', 'lighttpd'), (), ('text/x-lighttpd-conf',)),
'LiterateAgdaLexer': ('pygments.lexers.functional', 'Literate Agda', ('lagda', 'literate-agda'), ('*.lagda',), ('text/x-literate-agda',)),
'LiterateHaskellLexer': ('pygments.lexers.functional', 'Literate Haskell', ('lhs', 'literate-haskell', 'lhaskell'), ('*.lhs',), ('text/x-literate-haskell',)),
'LiveScriptLexer': ('pygments.lexers.web', 'LiveScript', ('live-script', 'livescript'), ('*.ls',), ('text/livescript',)),
'LlvmLexer': ('pygments.lexers.asm', 'LLVM', ('llvm',), ('*.ll',), ('text/x-llvm',)),
'LogosLexer': ('pygments.lexers.compiled', 'Logos', ('logos',), ('*.x', '*.xi', '*.xm', '*.xmi'), ('text/x-logos',)),
'LogtalkLexer': ('pygments.lexers.other', 'Logtalk', ('logtalk',), ('*.lgt',), ('text/x-logtalk',)),
'LuaLexer': ('pygments.lexers.agile', 'Lua', ('lua',), ('*.lua', '*.wlua'), ('text/x-lua', 'application/x-lua')),
'MOOCodeLexer': ('pygments.lexers.other', 'MOOCode', ('moocode', 'moo'), ('*.moo',), ('text/x-moocode',)),
'MakefileLexer': ('pygments.lexers.text', 'Makefile', ('make', 'makefile', 'mf', 'bsdmake'), ('*.mak', 'Makefile', 'makefile', 'Makefile.*', 'GNUmakefile'), ('text/x-makefile',)),
'MakoCssLexer': ('pygments.lexers.templates', 'CSS+Mako', ('css+mako',), (), ('text/css+mako',)),
'MakoHtmlLexer': ('pygments.lexers.templates', 'HTML+Mako', ('html+mako',), (), ('text/html+mako',)),
'MakoJavascriptLexer': ('pygments.lexers.templates', 'JavaScript+Mako', ('js+mako', 'javascript+mako'), (), ('application/x-javascript+mako', 'text/x-javascript+mako', 'text/javascript+mako')),
'MakoLexer': ('pygments.lexers.templates', 'Mako', ('mako',), ('*.mao',), ('application/x-mako',)),
'MakoXmlLexer': ('pygments.lexers.templates', 'XML+Mako', ('xml+mako',), (), ('application/xml+mako',)),
'MaqlLexer': ('pygments.lexers.other', 'MAQL', ('maql',), ('*.maql',), ('text/x-gooddata-maql', 'application/x-gooddata-maql')),
'MasonLexer': ('pygments.lexers.templates', 'Mason', ('mason',), ('*.m', '*.mhtml', '*.mc', '*.mi', 'autohandler', 'dhandler'), ('application/x-mason',)),
'MatlabLexer': ('pygments.lexers.math', 'Matlab', ('matlab',), ('*.m',), ('text/matlab',)),
'MatlabSessionLexer': ('pygments.lexers.math', 'Matlab session', ('matlabsession',), (), ()),
'MiniDLexer': ('pygments.lexers.agile', 'MiniD', ('minid',), ('*.md',), ('text/x-minidsrc',)),
'ModelicaLexer': ('pygments.lexers.other', 'Modelica', ('modelica',), ('*.mo',), ('text/x-modelica',)),
'Modula2Lexer': ('pygments.lexers.compiled', 'Modula-2', ('modula2', 'm2'), ('*.def', '*.mod'), ('text/x-modula2',)),
'MoinWikiLexer': ('pygments.lexers.text', 'MoinMoin/Trac Wiki markup', ('trac-wiki', 'moin'), (), ('text/x-trac-wiki',)),
'MonkeyLexer': ('pygments.lexers.compiled', 'Monkey', ('monkey',), ('*.monkey',), ('text/x-monkey',)),
'MoonScriptLexer': ('pygments.lexers.agile', 'MoonScript', ('moon', 'moonscript'), ('*.moon',), ('text/x-moonscript', 'application/x-moonscript')),
'MscgenLexer': ('pygments.lexers.other', 'Mscgen', ('mscgen', 'msc'), ('*.msc',), ()),
'MuPADLexer': ('pygments.lexers.math', 'MuPAD', ('mupad',), ('*.mu',), ()),
'MxmlLexer': ('pygments.lexers.web', 'MXML', ('mxml',), ('*.mxml',), ()),
'MySqlLexer': ('pygments.lexers.sql', 'MySQL', ('mysql',), (), ('text/x-mysql',)),
'MyghtyCssLexer': ('pygments.lexers.templates', 'CSS+Myghty', ('css+myghty',), (), ('text/css+myghty',)),
'MyghtyHtmlLexer': ('pygments.lexers.templates', 'HTML+Myghty', ('html+myghty',), (), ('text/html+myghty',)),
'MyghtyJavascriptLexer': ('pygments.lexers.templates', 'JavaScript+Myghty', ('js+myghty', 'javascript+myghty'), (), ('application/x-javascript+myghty', 'text/x-javascript+myghty', 'text/javascript+mygthy')),
'MyghtyLexer': ('pygments.lexers.templates', 'Myghty', ('myghty',), ('*.myt', 'autodelegate'), ('application/x-myghty',)),
'MyghtyXmlLexer': ('pygments.lexers.templates', 'XML+Myghty', ('xml+myghty',), (), ('application/xml+myghty',)),
'NSISLexer': ('pygments.lexers.other', 'NSIS', ('nsis', 'nsi', 'nsh'), ('*.nsi', '*.nsh'), ('text/x-nsis',)),
'NasmLexer': ('pygments.lexers.asm', 'NASM', ('nasm',), ('*.asm', '*.ASM'), ('text/x-nasm',)),
'NemerleLexer': ('pygments.lexers.dotnet', 'Nemerle', ('nemerle',), ('*.n',), ('text/x-nemerle',)),
'NesCLexer': ('pygments.lexers.compiled', 'nesC', ('nesc',), ('*.nc',), ('text/x-nescsrc',)),
'NewLispLexer': ('pygments.lexers.functional', 'NewLisp', ('newlisp',), ('*.lsp', '*.nl'), ('text/x-newlisp', 'application/x-newlisp')),
'NewspeakLexer': ('pygments.lexers.other', 'Newspeak', ('newspeak',), ('*.ns2',), ('text/x-newspeak',)),
'NginxConfLexer': ('pygments.lexers.text', 'Nginx configuration file', ('nginx',), (), ('text/x-nginx-conf',)),
'NimrodLexer': ('pygments.lexers.compiled', 'Nimrod', ('nimrod', 'nim'), ('*.nim', '*.nimrod'), ('text/x-nimrod',)),
'NumPyLexer': ('pygments.lexers.math', 'NumPy', ('numpy',), (), ()),
'ObjdumpLexer': ('pygments.lexers.asm', 'objdump', ('objdump',), ('*.objdump',), ('text/x-objdump',)),
'ObjectiveCLexer': ('pygments.lexers.compiled', 'Objective-C', ('objective-c', 'objectivec', 'obj-c', 'objc'), ('*.m', '*.h'), ('text/x-objective-c',)),
'ObjectiveCppLexer': ('pygments.lexers.compiled', 'Objective-C++', ('objective-c++', 'objectivec++', 'obj-c++', 'objc++'), ('*.mm', '*.hh'), ('text/x-objective-c++',)),
'ObjectiveJLexer': ('pygments.lexers.web', 'Objective-J', ('objective-j', 'objectivej', 'obj-j', 'objj'), ('*.j',), ('text/x-objective-j',)),
'OcamlLexer': ('pygments.lexers.functional', 'OCaml', ('ocaml',), ('*.ml', '*.mli', '*.mll', '*.mly'), ('text/x-ocaml',)),
'OctaveLexer': ('pygments.lexers.math', 'Octave', ('octave',), ('*.m',), ('text/octave',)),
'OocLexer': ('pygments.lexers.compiled', 'Ooc', ('ooc',), ('*.ooc',), ('text/x-ooc',)),
'OpaLexer': ('pygments.lexers.functional', 'Opa', ('opa',), ('*.opa',), ('text/x-opa',)),
'OpenEdgeLexer': ('pygments.lexers.other', 'OpenEdge ABL', ('openedge', 'abl', 'progress'), ('*.p', '*.cls'), ('text/x-openedge', 'application/x-openedge')),
'Perl6Lexer': ('pygments.lexers.agile', 'Perl6', ('perl6', 'pl6'), ('*.pl', '*.pm', '*.nqp', '*.p6', '*.6pl', '*.p6l', '*.pl6', '*.6pm', '*.p6m', '*.pm6'), ('text/x-perl6', 'application/x-perl6')),
'PerlLexer': ('pygments.lexers.agile', 'Perl', ('perl', 'pl'), ('*.pl', '*.pm'), ('text/x-perl', 'application/x-perl')),
'PhpLexer': ('pygments.lexers.web', 'PHP', ('php', 'php3', 'php4', 'php5'), ('*.php', '*.php[345]', '*.inc'), ('text/x-php',)),
'PlPgsqlLexer': ('pygments.lexers.sql', 'PL/pgSQL', ('plpgsql',), (), ('text/x-plpgsql',)),
'PostScriptLexer': ('pygments.lexers.other', 'PostScript', ('postscript', 'postscr'), ('*.ps', '*.eps'), ('application/postscript',)),
'PostgresConsoleLexer': ('pygments.lexers.sql', 'PostgreSQL console (psql)', ('psql', 'postgresql-console', 'postgres-console'), (), ('text/x-postgresql-psql',)),
'PostgresLexer': ('pygments.lexers.sql', 'PostgreSQL SQL dialect', ('postgresql', 'postgres'), (), ('text/x-postgresql',)),
'PovrayLexer': ('pygments.lexers.other', 'POVRay', ('pov',), ('*.pov', '*.inc'), ('text/x-povray',)),
'PowerShellLexer': ('pygments.lexers.shell', 'PowerShell', ('powershell', 'posh', 'ps1', 'psm1'), ('*.ps1', '*.psm1'), ('text/x-powershell',)),
'PrologLexer': ('pygments.lexers.compiled', 'Prolog', ('prolog',), ('*.prolog', '*.pro', '*.pl'), ('text/x-prolog',)),
'PropertiesLexer': ('pygments.lexers.text', 'Properties', ('properties', 'jproperties'), ('*.properties',), ('text/x-java-properties',)),
'ProtoBufLexer': ('pygments.lexers.other', 'Protocol Buffer', ('protobuf', 'proto'), ('*.proto',), ()),
'PuppetLexer': ('pygments.lexers.other', 'Puppet', ('puppet',), ('*.pp',), ()),
'PyPyLogLexer': ('pygments.lexers.text', 'PyPy Log', ('pypylog', 'pypy'), ('*.pypylog',), ('application/x-pypylog',)),
'Python3Lexer': ('pygments.lexers.agile', 'Python 3', ('python3', 'py3'), (), ('text/x-python3', 'application/x-python3')),
'Python3TracebackLexer': ('pygments.lexers.agile', 'Python 3.0 Traceback', ('py3tb',), ('*.py3tb',), ('text/x-python3-traceback',)),
'PythonConsoleLexer': ('pygments.lexers.agile', 'Python console session', ('pycon',), (), ('text/x-python-doctest',)),
'PythonLexer': ('pygments.lexers.agile', 'Python', ('python', 'py', 'sage'), ('*.py', '*.pyw', '*.sc', 'SConstruct', 'SConscript', '*.tac', '*.sage'), ('text/x-python', 'application/x-python')),
'PythonTracebackLexer': ('pygments.lexers.agile', 'Python Traceback', ('pytb',), ('*.pytb',), ('text/x-python-traceback',)),
'QmlLexer': ('pygments.lexers.web', 'QML', ('qml', 'Qt Meta Language', 'Qt modeling Language'), ('*.qml',), ('application/x-qml',)),
'RConsoleLexer': ('pygments.lexers.math', 'RConsole', ('rconsole', 'rout'), ('*.Rout',), ()),
'RPMSpecLexer': ('pygments.lexers.other', 'RPMSpec', ('spec',), ('*.spec',), ('text/x-rpm-spec',)),
'RacketLexer': ('pygments.lexers.functional', 'Racket', ('racket', 'rkt'), ('*.rkt', '*.rktl'), ('text/x-racket', 'application/x-racket')),
'RagelCLexer': ('pygments.lexers.parsers', 'Ragel in C Host', ('ragel-c',), ('*.rl',), ()),
'RagelCppLexer': ('pygments.lexers.parsers', 'Ragel in CPP Host', ('ragel-cpp',), ('*.rl',), ()),
'RagelDLexer': ('pygments.lexers.parsers', 'Ragel in D Host', ('ragel-d',), ('*.rl',), ()),
'RagelEmbeddedLexer': ('pygments.lexers.parsers', 'Embedded Ragel', ('ragel-em',), ('*.rl',), ()),
'RagelJavaLexer': ('pygments.lexers.parsers', 'Ragel in Java Host', ('ragel-java',), ('*.rl',), ()),
'RagelLexer': ('pygments.lexers.parsers', 'Ragel', ('ragel',), (), ()),
'RagelObjectiveCLexer': ('pygments.lexers.parsers', 'Ragel in Objective C Host', ('ragel-objc',), ('*.rl',), ()),
'RagelRubyLexer': ('pygments.lexers.parsers', 'Ragel in Ruby Host', ('ragel-ruby', 'ragel-rb'), ('*.rl',), ()),
'RawTokenLexer': ('pygments.lexers.special', 'Raw token data', ('raw',), (), ('application/x-pygments-tokens',)),
'RdLexer': ('pygments.lexers.math', 'Rd', ('rd',), ('*.Rd',), ('text/x-r-doc',)),
'RebolLexer': ('pygments.lexers.other', 'REBOL', ('rebol',), ('*.r', '*.r3'), ('text/x-rebol',)),
'RedcodeLexer': ('pygments.lexers.other', 'Redcode', ('redcode',), ('*.cw',), ()),
'RegeditLexer': ('pygments.lexers.text', 'reg', ('registry',), ('*.reg',), ('text/x-windows-registry',)),
'RexxLexer': ('pygments.lexers.other', 'Rexx', ('rexx', 'ARexx', 'arexx'), ('*.rexx', '*.rex', '*.rx', '*.arexx'), ('text/x-rexx',)),
'RhtmlLexer': ('pygments.lexers.templates', 'RHTML', ('rhtml', 'html+erb', 'html+ruby'), ('*.rhtml',), ('text/html+ruby',)),
'RobotFrameworkLexer': ('pygments.lexers.other', 'RobotFramework', ('RobotFramework', 'robotframework'), ('*.txt', '*.robot'), ('text/x-robotframework',)),
'RstLexer': ('pygments.lexers.text', 'reStructuredText', ('rst', 'rest', 'restructuredtext'), ('*.rst', '*.rest'), ('text/x-rst', 'text/prs.fallenstein.rst')),
'RubyConsoleLexer': ('pygments.lexers.agile', 'Ruby irb session', ('rbcon', 'irb'), (), ('text/x-ruby-shellsession',)),
'RubyLexer': ('pygments.lexers.agile', 'Ruby', ('rb', 'ruby', 'duby'), ('*.rb', '*.rbw', 'Rakefile', '*.rake', '*.gemspec', '*.rbx', '*.duby'), ('text/x-ruby', 'application/x-ruby')),
'RustLexer': ('pygments.lexers.compiled', 'Rust', ('rust',), ('*.rs', '*.rc'), ('text/x-rustsrc',)),
'SLexer': ('pygments.lexers.math', 'S', ('splus', 's', 'r'), ('*.S', '*.R', '.Rhistory', '.Rprofile'), ('text/S-plus', 'text/S', 'text/x-r-source', 'text/x-r', 'text/x-R', 'text/x-r-history', 'text/x-r-profile')),
'SMLLexer': ('pygments.lexers.functional', 'Standard ML', ('sml',), ('*.sml', '*.sig', '*.fun'), ('text/x-standardml', 'application/x-standardml')),
'SassLexer': ('pygments.lexers.web', 'Sass', ('sass', 'SASS'), ('*.sass',), ('text/x-sass',)),
'ScalaLexer': ('pygments.lexers.jvm', 'Scala', ('scala',), ('*.scala',), ('text/x-scala',)),
'ScamlLexer': ('pygments.lexers.web', 'Scaml', ('scaml', 'SCAML'), ('*.scaml',), ('text/x-scaml',)),
'SchemeLexer': ('pygments.lexers.functional', 'Scheme', ('scheme', 'scm'), ('*.scm', '*.ss'), ('text/x-scheme', 'application/x-scheme')),
'ScilabLexer': ('pygments.lexers.math', 'Scilab', ('scilab',), ('*.sci', '*.sce', '*.tst'), ('text/scilab',)),
'ScssLexer': ('pygments.lexers.web', 'SCSS', ('scss',), ('*.scss',), ('text/x-scss',)),
'ShellSessionLexer': ('pygments.lexers.shell', 'Shell Session', ('shell-session',), ('*.shell-session',), ('application/x-sh-session',)),
'SmaliLexer': ('pygments.lexers.dalvik', 'Smali', ('smali',), ('*.smali',), ('text/smali',)),
'SmalltalkLexer': ('pygments.lexers.other', 'Smalltalk', ('smalltalk', 'squeak', 'st'), ('*.st',), ('text/x-smalltalk',)),
'SmartyLexer': ('pygments.lexers.templates', 'Smarty', ('smarty',), ('*.tpl',), ('application/x-smarty',)),
'SnobolLexer': ('pygments.lexers.other', 'Snobol', ('snobol',), ('*.snobol',), ('text/x-snobol',)),
'SourcePawnLexer': ('pygments.lexers.other', 'SourcePawn', ('sp',), ('*.sp',), ('text/x-sourcepawn',)),
'SourcesListLexer': ('pygments.lexers.text', 'Debian Sourcelist', ('sourceslist', 'sources.list', 'debsources'), ('sources.list',), ()),
'SqlLexer': ('pygments.lexers.sql', 'SQL', ('sql',), ('*.sql',), ('text/x-sql',)),
'SqliteConsoleLexer': ('pygments.lexers.sql', 'sqlite3con', ('sqlite3',), ('*.sqlite3-console',), ('text/x-sqlite3-console',)),
'SquidConfLexer': ('pygments.lexers.text', 'SquidConf', ('squidconf', 'squid.conf', 'squid'), ('squid.conf',), ('text/x-squidconf',)),
'SspLexer': ('pygments.lexers.templates', 'Scalate Server Page', ('ssp',), ('*.ssp',), ('application/x-ssp',)),
'StanLexer': ('pygments.lexers.math', 'Stan', ('stan',), ('*.stan',), ()),
'SwigLexer': ('pygments.lexers.compiled', 'SWIG', ('Swig', 'swig'), ('*.swg', '*.i'), ('text/swig',)),
'SystemVerilogLexer': ('pygments.lexers.hdl', 'systemverilog', ('systemverilog', 'sv'), ('*.sv', '*.svh'), ('text/x-systemverilog',)),
'TclLexer': ('pygments.lexers.agile', 'Tcl', ('tcl',), ('*.tcl',), ('text/x-tcl', 'text/x-script.tcl', 'application/x-tcl')),
'TcshLexer': ('pygments.lexers.shell', 'Tcsh', ('tcsh', 'csh'), ('*.tcsh', '*.csh'), ('application/x-csh',)),
'TeaTemplateLexer': ('pygments.lexers.templates', 'Tea', ('tea',), ('*.tea',), ('text/x-tea',)),
'TexLexer': ('pygments.lexers.text', 'TeX', ('tex', 'latex'), ('*.tex', '*.aux', '*.toc'), ('text/x-tex', 'text/x-latex')),
'TextLexer': ('pygments.lexers.special', 'Text only', ('text',), ('*.txt',), ('text/plain',)),
'TreetopLexer': ('pygments.lexers.parsers', 'Treetop', ('treetop',), ('*.treetop', '*.tt'), ()),
'TypeScriptLexer': ('pygments.lexers.web', 'TypeScript', ('ts',), ('*.ts',), ('text/x-typescript',)),
'UrbiscriptLexer': ('pygments.lexers.other', 'UrbiScript', ('urbiscript',), ('*.u',), ('application/x-urbiscript',)),
'VGLLexer': ('pygments.lexers.other', 'VGL', ('vgl',), ('*.rpf',), ()),
'ValaLexer': ('pygments.lexers.compiled', 'Vala', ('vala', 'vapi'), ('*.vala', '*.vapi'), ('text/x-vala',)),
'VbNetAspxLexer': ('pygments.lexers.dotnet', 'aspx-vb', ('aspx-vb',), ('*.aspx', '*.asax', '*.ascx', '*.ashx', '*.asmx', '*.axd'), ()),
'VbNetLexer': ('pygments.lexers.dotnet', 'VB.net', ('vb.net', 'vbnet'), ('*.vb', '*.bas'), ('text/x-vbnet', 'text/x-vba')),
'VelocityHtmlLexer': ('pygments.lexers.templates', 'HTML+Velocity', ('html+velocity',), (), ('text/html+velocity',)),
'VelocityLexer': ('pygments.lexers.templates', 'Velocity', ('velocity',), ('*.vm', '*.fhtml'), ()),
'VelocityXmlLexer': ('pygments.lexers.templates', 'XML+Velocity', ('xml+velocity',), (), ('application/xml+velocity',)),
'VerilogLexer': ('pygments.lexers.hdl', 'verilog', ('verilog', 'v'), ('*.v',), ('text/x-verilog',)),
'VhdlLexer': ('pygments.lexers.hdl', 'vhdl', ('vhdl',), ('*.vhdl', '*.vhd'), ('text/x-vhdl',)),
'VimLexer': ('pygments.lexers.text', 'VimL', ('vim',), ('*.vim', '.vimrc', '.exrc', '.gvimrc', '_vimrc', '_exrc', '_gvimrc', 'vimrc', 'gvimrc'), ('text/x-vim',)),
'XQueryLexer': ('pygments.lexers.web', 'XQuery', ('xquery', 'xqy', 'xq', 'xql', 'xqm'), ('*.xqy', '*.xquery', '*.xq', '*.xql', '*.xqm'), ('text/xquery', 'application/xquery')),
'XmlDjangoLexer': ('pygments.lexers.templates', 'XML+Django/Jinja', ('xml+django', 'xml+jinja'), (), ('application/xml+django', 'application/xml+jinja')),
'XmlErbLexer': ('pygments.lexers.templates', 'XML+Ruby', ('xml+erb', 'xml+ruby'), (), ('application/xml+ruby',)),
'XmlLexer': ('pygments.lexers.web', 'XML', ('xml',), ('*.xml', '*.xsl', '*.rss', '*.xslt', '*.xsd', '*.wsdl', '*.wsf'), ('text/xml', 'application/xml', 'image/svg+xml', 'application/rss+xml', 'application/atom+xml')),
'XmlPhpLexer': ('pygments.lexers.templates', 'XML+PHP', ('xml+php',), (), ('application/xml+php',)),
'XmlSmartyLexer': ('pygments.lexers.templates', 'XML+Smarty', ('xml+smarty',), (), ('application/xml+smarty',)),
'XsltLexer': ('pygments.lexers.web', 'XSLT', ('xslt',), ('*.xsl', '*.xslt', '*.xpl'), ('application/xsl+xml', 'application/xslt+xml')),
'XtendLexer': ('pygments.lexers.jvm', 'Xtend', ('xtend',), ('*.xtend',), ('text/x-xtend',)),
'YamlLexer': ('pygments.lexers.text', 'YAML', ('yaml',), ('*.yaml', '*.yml'), ('text/x-yaml',)),
}
if __name__ == '__main__':
import sys
import os
# lookup lexers
found_lexers = []
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', '..'))
for filename in os.listdir('.'):
if filename.endswith('.py') and not filename.startswith('_'):
module_name = 'pygments.lexers.%s' % filename[:-3]
print module_name
module = __import__(module_name, None, None, [''])
for lexer_name in module.__all__:
lexer = getattr(module, lexer_name)
found_lexers.append(
'%r: %r' % (lexer_name,
(module_name,
lexer.name,
tuple(lexer.aliases),
tuple(lexer.filenames),
tuple(lexer.mimetypes))))
# sort them, that should make the diff files for svn smaller
found_lexers.sort()
# extract useful sourcecode from this file
f = open(__file__)
try:
content = f.read()
finally:
f.close()
header = content[:content.find('LEXERS = {')]
footer = content[content.find("if __name__ == '__main__':"):]
# write new file
f = open(__file__, 'wb')
f.write(header)
f.write('LEXERS = {\n %s,\n}\n\n' % ',\n '.join(found_lexers))
f.write(footer)
f.close()

File diff suppressed because it is too large Load diff

View file

@ -0,0 +1,233 @@
# -*- coding: utf-8 -*-
"""
pygments.lexers._postgres_builtins
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Self-updating data files for PostgreSQL lexer.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
import urllib
# One man's constant is another man's variable.
SOURCE_URL = 'https://github.com/postgres/postgres/raw/master'
KEYWORDS_URL = SOURCE_URL + '/doc/src/sgml/keywords.sgml'
DATATYPES_URL = SOURCE_URL + '/doc/src/sgml/datatype.sgml'
def update_myself():
data_file = list(fetch(DATATYPES_URL))
datatypes = parse_datatypes(data_file)
pseudos = parse_pseudos(data_file)
keywords = parse_keywords(fetch(KEYWORDS_URL))
update_consts(__file__, 'DATATYPES', datatypes)
update_consts(__file__, 'PSEUDO_TYPES', pseudos)
update_consts(__file__, 'KEYWORDS', keywords)
def parse_keywords(f):
kw = []
for m in re.finditer(
r'\s*<entry><token>([^<]+)</token></entry>\s*'
r'<entry>([^<]+)</entry>', f.read()):
kw.append(m.group(1))
if not kw:
raise ValueError('no keyword found')
kw.sort()
return kw
def parse_datatypes(f):
dt = set()
for line in f:
if '<sect1' in line:
break
if '<entry><type>' not in line:
continue
# Parse a string such as
# time [ (<replaceable>p</replaceable>) ] [ without time zone ]
# into types "time" and "without time zone"
# remove all the tags
line = re.sub("<replaceable>[^<]+</replaceable>", "", line)
line = re.sub("<[^>]+>", "", line)
# Drop the parts containing braces
for tmp in [t for tmp in line.split('[')
for t in tmp.split(']') if "(" not in t]:
for t in tmp.split(','):
t = t.strip()
if not t: continue
dt.add(" ".join(t.split()))
dt = list(dt)
dt.sort()
return dt
def parse_pseudos(f):
dt = []
re_start = re.compile(r'\s*<table id="datatype-pseudotypes-table">')
re_entry = re.compile(r'\s*<entry><type>([^<]+)</></entry>')
re_end = re.compile(r'\s*</table>')
f = iter(f)
for line in f:
if re_start.match(line) is not None:
break
else:
raise ValueError('pseudo datatypes table not found')
for line in f:
m = re_entry.match(line)
if m is not None:
dt.append(m.group(1))
if re_end.match(line) is not None:
break
else:
raise ValueError('end of pseudo datatypes table not found')
if not dt:
raise ValueError('pseudo datatypes not found')
return dt
def fetch(url):
return urllib.urlopen(url)
def update_consts(filename, constname, content):
f = open(filename)
lines = f.readlines()
f.close()
# Line to start/end inserting
re_start = re.compile(r'^%s\s*=\s*\[\s*$' % constname)
re_end = re.compile(r'^\s*\]\s*$')
start = [ n for n, l in enumerate(lines) if re_start.match(l) ]
if not start:
raise ValueError("couldn't find line containing '%s = ['" % constname)
if len(start) > 1:
raise ValueError("too many lines containing '%s = ['" % constname)
start = start[0] + 1
end = [ n for n, l in enumerate(lines) if n >= start and re_end.match(l) ]
if not end:
raise ValueError("couldn't find line containing ']' after %s " % constname)
end = end[0]
# Pack the new content in lines not too long
content = [repr(item) for item in content ]
new_lines = [[]]
for item in content:
if sum(map(len, new_lines[-1])) + 2 * len(new_lines[-1]) + len(item) + 4 > 75:
new_lines.append([])
new_lines[-1].append(item)
lines[start:end] = [ " %s,\n" % ", ".join(items) for items in new_lines ]
f = open(filename, 'w')
f.write(''.join(lines))
f.close()
# Autogenerated: please edit them if you like wasting your time.
KEYWORDS = [
'ABORT', 'ABSOLUTE', 'ACCESS', 'ACTION', 'ADD', 'ADMIN', 'AFTER',
'AGGREGATE', 'ALL', 'ALSO', 'ALTER', 'ALWAYS', 'ANALYSE', 'ANALYZE',
'AND', 'ANY', 'ARRAY', 'AS', 'ASC', 'ASSERTION', 'ASSIGNMENT',
'ASYMMETRIC', 'AT', 'ATTRIBUTE', 'AUTHORIZATION', 'BACKWARD', 'BEFORE',
'BEGIN', 'BETWEEN', 'BIGINT', 'BINARY', 'BIT', 'BOOLEAN', 'BOTH', 'BY',
'CACHE', 'CALLED', 'CASCADE', 'CASCADED', 'CASE', 'CAST', 'CATALOG',
'CHAIN', 'CHAR', 'CHARACTER', 'CHARACTERISTICS', 'CHECK', 'CHECKPOINT',
'CLASS', 'CLOSE', 'CLUSTER', 'COALESCE', 'COLLATE', 'COLLATION',
'COLUMN', 'COMMENT', 'COMMENTS', 'COMMIT', 'COMMITTED', 'CONCURRENTLY',
'CONFIGURATION', 'CONNECTION', 'CONSTRAINT', 'CONSTRAINTS', 'CONTENT',
'CONTINUE', 'CONVERSION', 'COPY', 'COST', 'CREATE', 'CROSS', 'CSV',
'CURRENT', 'CURRENT_CATALOG', 'CURRENT_DATE', 'CURRENT_ROLE',
'CURRENT_SCHEMA', 'CURRENT_TIME', 'CURRENT_TIMESTAMP', 'CURRENT_USER',
'CURSOR', 'CYCLE', 'DATA', 'DATABASE', 'DAY', 'DEALLOCATE', 'DEC',
'DECIMAL', 'DECLARE', 'DEFAULT', 'DEFAULTS', 'DEFERRABLE', 'DEFERRED',
'DEFINER', 'DELETE', 'DELIMITER', 'DELIMITERS', 'DESC', 'DICTIONARY',
'DISABLE', 'DISCARD', 'DISTINCT', 'DO', 'DOCUMENT', 'DOMAIN', 'DOUBLE',
'DROP', 'EACH', 'ELSE', 'ENABLE', 'ENCODING', 'ENCRYPTED', 'END',
'ENUM', 'ESCAPE', 'EXCEPT', 'EXCLUDE', 'EXCLUDING', 'EXCLUSIVE',
'EXECUTE', 'EXISTS', 'EXPLAIN', 'EXTENSION', 'EXTERNAL', 'EXTRACT',
'FALSE', 'FAMILY', 'FETCH', 'FIRST', 'FLOAT', 'FOLLOWING', 'FOR',
'FORCE', 'FOREIGN', 'FORWARD', 'FREEZE', 'FROM', 'FULL', 'FUNCTION',
'FUNCTIONS', 'GLOBAL', 'GRANT', 'GRANTED', 'GREATEST', 'GROUP',
'HANDLER', 'HAVING', 'HEADER', 'HOLD', 'HOUR', 'IDENTITY', 'IF',
'ILIKE', 'IMMEDIATE', 'IMMUTABLE', 'IMPLICIT', 'IN', 'INCLUDING',
'INCREMENT', 'INDEX', 'INDEXES', 'INHERIT', 'INHERITS', 'INITIALLY',
'INLINE', 'INNER', 'INOUT', 'INPUT', 'INSENSITIVE', 'INSERT', 'INSTEAD',
'INT', 'INTEGER', 'INTERSECT', 'INTERVAL', 'INTO', 'INVOKER', 'IS',
'ISNULL', 'ISOLATION', 'JOIN', 'KEY', 'LABEL', 'LANGUAGE', 'LARGE',
'LAST', 'LC_COLLATE', 'LC_CTYPE', 'LEADING', 'LEAST', 'LEFT', 'LEVEL',
'LIKE', 'LIMIT', 'LISTEN', 'LOAD', 'LOCAL', 'LOCALTIME',
'LOCALTIMESTAMP', 'LOCATION', 'LOCK', 'MAPPING', 'MATCH', 'MAXVALUE',
'MINUTE', 'MINVALUE', 'MODE', 'MONTH', 'MOVE', 'NAME', 'NAMES',
'NATIONAL', 'NATURAL', 'NCHAR', 'NEXT', 'NO', 'NONE', 'NOT', 'NOTHING',
'NOTIFY', 'NOTNULL', 'NOWAIT', 'NULL', 'NULLIF', 'NULLS', 'NUMERIC',
'OBJECT', 'OF', 'OFF', 'OFFSET', 'OIDS', 'ON', 'ONLY', 'OPERATOR',
'OPTION', 'OPTIONS', 'OR', 'ORDER', 'OUT', 'OUTER', 'OVER', 'OVERLAPS',
'OVERLAY', 'OWNED', 'OWNER', 'PARSER', 'PARTIAL', 'PARTITION',
'PASSING', 'PASSWORD', 'PLACING', 'PLANS', 'POSITION', 'PRECEDING',
'PRECISION', 'PREPARE', 'PREPARED', 'PRESERVE', 'PRIMARY', 'PRIOR',
'PRIVILEGES', 'PROCEDURAL', 'PROCEDURE', 'QUOTE', 'RANGE', 'READ',
'REAL', 'REASSIGN', 'RECHECK', 'RECURSIVE', 'REF', 'REFERENCES',
'REINDEX', 'RELATIVE', 'RELEASE', 'RENAME', 'REPEATABLE', 'REPLACE',
'REPLICA', 'RESET', 'RESTART', 'RESTRICT', 'RETURNING', 'RETURNS',
'REVOKE', 'RIGHT', 'ROLE', 'ROLLBACK', 'ROW', 'ROWS', 'RULE',
'SAVEPOINT', 'SCHEMA', 'SCROLL', 'SEARCH', 'SECOND', 'SECURITY',
'SELECT', 'SEQUENCE', 'SEQUENCES', 'SERIALIZABLE', 'SERVER', 'SESSION',
'SESSION_USER', 'SET', 'SETOF', 'SHARE', 'SHOW', 'SIMILAR', 'SIMPLE',
'SMALLINT', 'SOME', 'STABLE', 'STANDALONE', 'START', 'STATEMENT',
'STATISTICS', 'STDIN', 'STDOUT', 'STORAGE', 'STRICT', 'STRIP',
'SUBSTRING', 'SYMMETRIC', 'SYSID', 'SYSTEM', 'TABLE', 'TABLES',
'TABLESPACE', 'TEMP', 'TEMPLATE', 'TEMPORARY', 'TEXT', 'THEN', 'TIME',
'TIMESTAMP', 'TO', 'TRAILING', 'TRANSACTION', 'TREAT', 'TRIGGER',
'TRIM', 'TRUE', 'TRUNCATE', 'TRUSTED', 'TYPE', 'UNBOUNDED',
'UNCOMMITTED', 'UNENCRYPTED', 'UNION', 'UNIQUE', 'UNKNOWN', 'UNLISTEN',
'UNLOGGED', 'UNTIL', 'UPDATE', 'USER', 'USING', 'VACUUM', 'VALID',
'VALIDATE', 'VALIDATOR', 'VALUE', 'VALUES', 'VARCHAR', 'VARIADIC',
'VARYING', 'VERBOSE', 'VERSION', 'VIEW', 'VOLATILE', 'WHEN', 'WHERE',
'WHITESPACE', 'WINDOW', 'WITH', 'WITHOUT', 'WORK', 'WRAPPER', 'WRITE',
'XML', 'XMLATTRIBUTES', 'XMLCONCAT', 'XMLELEMENT', 'XMLEXISTS',
'XMLFOREST', 'XMLPARSE', 'XMLPI', 'XMLROOT', 'XMLSERIALIZE', 'YEAR',
'YES', 'ZONE',
]
DATATYPES = [
'bigint', 'bigserial', 'bit', 'bit varying', 'bool', 'boolean', 'box',
'bytea', 'char', 'character', 'character varying', 'cidr', 'circle',
'date', 'decimal', 'double precision', 'float4', 'float8', 'inet',
'int', 'int2', 'int4', 'int8', 'integer', 'interval', 'json', 'line',
'lseg', 'macaddr', 'money', 'numeric', 'path', 'point', 'polygon',
'real', 'serial', 'serial2', 'serial4', 'serial8', 'smallint',
'smallserial', 'text', 'time', 'timestamp', 'timestamptz', 'timetz',
'tsquery', 'tsvector', 'txid_snapshot', 'uuid', 'varbit', 'varchar',
'with time zone', 'without time zone', 'xml',
]
PSEUDO_TYPES = [
'any', 'anyelement', 'anyarray', 'anynonarray', 'anyenum', 'anyrange',
'cstring', 'internal', 'language_handler', 'fdw_handler', 'record',
'trigger', 'void', 'opaque',
]
# Remove 'trigger' from types
PSEUDO_TYPES = sorted(set(PSEUDO_TYPES) - set(map(str.lower, KEYWORDS)))
PLPGSQL_KEYWORDS = [
'ALIAS', 'CONSTANT', 'DIAGNOSTICS', 'ELSIF', 'EXCEPTION', 'EXIT',
'FOREACH', 'GET', 'LOOP', 'NOTICE', 'OPEN', 'PERFORM', 'QUERY', 'RAISE',
'RETURN', 'REVERSE', 'SQLSTATE', 'WHILE',
]
if __name__ == '__main__':
update_myself()

View file

@ -0,0 +1,557 @@
# -*- coding: utf-8 -*-
"""
pygments.lexers._robotframeworklexer
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Lexer for Robot Framework.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
# Copyright 2012 Nokia Siemens Networks Oyj
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import re
from pygments.lexer import Lexer
from pygments.token import Token
HEADING = Token.Generic.Heading
SETTING = Token.Keyword.Namespace
IMPORT = Token.Name.Namespace
TC_KW_NAME = Token.Generic.Subheading
KEYWORD = Token.Name.Function
ARGUMENT = Token.String
VARIABLE = Token.Name.Variable
COMMENT = Token.Comment
SEPARATOR = Token.Punctuation
SYNTAX = Token.Punctuation
GHERKIN = Token.Generic.Emph
ERROR = Token.Error
def normalize(string, remove=''):
string = string.lower()
for char in remove + ' ':
if char in string:
string = string.replace(char, '')
return string
class RobotFrameworkLexer(Lexer):
"""
For `Robot Framework <http://robotframework.org>`_ test data.
Supports both space and pipe separated plain text formats.
*New in Pygments 1.6.*
"""
name = 'RobotFramework'
aliases = ['RobotFramework', 'robotframework']
filenames = ['*.txt', '*.robot']
mimetypes = ['text/x-robotframework']
def __init__(self, **options):
options['tabsize'] = 2
options['encoding'] = 'UTF-8'
Lexer.__init__(self, **options)
def get_tokens_unprocessed(self, text):
row_tokenizer = RowTokenizer()
var_tokenizer = VariableTokenizer()
index = 0
for row in text.splitlines():
for value, token in row_tokenizer.tokenize(row):
for value, token in var_tokenizer.tokenize(value, token):
if value:
yield index, token, unicode(value)
index += len(value)
class VariableTokenizer(object):
def tokenize(self, string, token):
var = VariableSplitter(string, identifiers='$@%')
if var.start < 0 or token in (COMMENT, ERROR):
yield string, token
return
for value, token in self._tokenize(var, string, token):
if value:
yield value, token
def _tokenize(self, var, string, orig_token):
before = string[:var.start]
yield before, orig_token
yield var.identifier + '{', SYNTAX
for value, token in self.tokenize(var.base, VARIABLE):
yield value, token
yield '}', SYNTAX
if var.index:
yield '[', SYNTAX
for value, token in self.tokenize(var.index, VARIABLE):
yield value, token
yield ']', SYNTAX
for value, token in self.tokenize(string[var.end:], orig_token):
yield value, token
class RowTokenizer(object):
def __init__(self):
self._table = UnknownTable()
self._splitter = RowSplitter()
testcases = TestCaseTable()
settings = SettingTable(testcases.set_default_template)
variables = VariableTable()
keywords = KeywordTable()
self._tables = {'settings': settings, 'setting': settings,
'metadata': settings,
'variables': variables, 'variable': variables,
'testcases': testcases, 'testcase': testcases,
'keywords': keywords, 'keyword': keywords,
'userkeywords': keywords, 'userkeyword': keywords}
def tokenize(self, row):
commented = False
heading = False
for index, value in enumerate(self._splitter.split(row)):
# First value, and every second after that, is a separator.
index, separator = divmod(index-1, 2)
if value.startswith('#'):
commented = True
elif index == 0 and value.startswith('*'):
self._table = self._start_table(value)
heading = True
for value, token in self._tokenize(value, index, commented,
separator, heading):
yield value, token
self._table.end_row()
def _start_table(self, header):
name = normalize(header, remove='*')
return self._tables.get(name, UnknownTable())
def _tokenize(self, value, index, commented, separator, heading):
if commented:
yield value, COMMENT
elif separator:
yield value, SEPARATOR
elif heading:
yield value, HEADING
else:
for value, token in self._table.tokenize(value, index):
yield value, token
class RowSplitter(object):
_space_splitter = re.compile('( {2,})')
_pipe_splitter = re.compile('((?:^| +)\|(?: +|$))')
def split(self, row):
splitter = (row.startswith('| ') and self._split_from_pipes
or self._split_from_spaces)
for value in splitter(row):
yield value
yield '\n'
def _split_from_spaces(self, row):
yield '' # Start with (pseudo)separator similarly as with pipes
for value in self._space_splitter.split(row):
yield value
def _split_from_pipes(self, row):
_, separator, rest = self._pipe_splitter.split(row, 1)
yield separator
while self._pipe_splitter.search(rest):
cell, separator, rest = self._pipe_splitter.split(rest, 1)
yield cell
yield separator
yield rest
class Tokenizer(object):
_tokens = None
def __init__(self):
self._index = 0
def tokenize(self, value):
values_and_tokens = self._tokenize(value, self._index)
self._index += 1
if isinstance(values_and_tokens, type(Token)):
values_and_tokens = [(value, values_and_tokens)]
return values_and_tokens
def _tokenize(self, value, index):
index = min(index, len(self._tokens) - 1)
return self._tokens[index]
def _is_assign(self, value):
if value.endswith('='):
value = value[:-1].strip()
var = VariableSplitter(value, identifiers='$@')
return var.start == 0 and var.end == len(value)
class Comment(Tokenizer):
_tokens = (COMMENT,)
class Setting(Tokenizer):
_tokens = (SETTING, ARGUMENT)
_keyword_settings = ('suitesetup', 'suiteprecondition', 'suiteteardown',
'suitepostcondition', 'testsetup', 'testprecondition',
'testteardown', 'testpostcondition', 'testtemplate')
_import_settings = ('library', 'resource', 'variables')
_other_settings = ('documentation', 'metadata', 'forcetags', 'defaulttags',
'testtimeout')
_custom_tokenizer = None
def __init__(self, template_setter=None):
Tokenizer.__init__(self)
self._template_setter = template_setter
def _tokenize(self, value, index):
if index == 1 and self._template_setter:
self._template_setter(value)
if index == 0:
normalized = normalize(value)
if normalized in self._keyword_settings:
self._custom_tokenizer = KeywordCall(support_assign=False)
elif normalized in self._import_settings:
self._custom_tokenizer = ImportSetting()
elif normalized not in self._other_settings:
return ERROR
elif self._custom_tokenizer:
return self._custom_tokenizer.tokenize(value)
return Tokenizer._tokenize(self, value, index)
class ImportSetting(Tokenizer):
_tokens = (IMPORT, ARGUMENT)
class TestCaseSetting(Setting):
_keyword_settings = ('setup', 'precondition', 'teardown', 'postcondition',
'template')
_import_settings = ()
_other_settings = ('documentation', 'tags', 'timeout')
def _tokenize(self, value, index):
if index == 0:
type = Setting._tokenize(self, value[1:-1], index)
return [('[', SYNTAX), (value[1:-1], type), (']', SYNTAX)]
return Setting._tokenize(self, value, index)
class KeywordSetting(TestCaseSetting):
_keyword_settings = ('teardown',)
_other_settings = ('documentation', 'arguments', 'return', 'timeout')
class Variable(Tokenizer):
_tokens = (SYNTAX, ARGUMENT)
def _tokenize(self, value, index):
if index == 0 and not self._is_assign(value):
return ERROR
return Tokenizer._tokenize(self, value, index)
class KeywordCall(Tokenizer):
_tokens = (KEYWORD, ARGUMENT)
def __init__(self, support_assign=True):
Tokenizer.__init__(self)
self._keyword_found = not support_assign
self._assigns = 0
def _tokenize(self, value, index):
if not self._keyword_found and self._is_assign(value):
self._assigns += 1
return SYNTAX # VariableTokenizer tokenizes this later.
if self._keyword_found:
return Tokenizer._tokenize(self, value, index - self._assigns)
self._keyword_found = True
return GherkinTokenizer().tokenize(value, KEYWORD)
class GherkinTokenizer(object):
_gherkin_prefix = re.compile('^(Given|When|Then|And) ', re.IGNORECASE)
def tokenize(self, value, token):
match = self._gherkin_prefix.match(value)
if not match:
return [(value, token)]
end = match.end()
return [(value[:end], GHERKIN), (value[end:], token)]
class TemplatedKeywordCall(Tokenizer):
_tokens = (ARGUMENT,)
class ForLoop(Tokenizer):
def __init__(self):
Tokenizer.__init__(self)
self._in_arguments = False
def _tokenize(self, value, index):
token = self._in_arguments and ARGUMENT or SYNTAX
if value.upper() in ('IN', 'IN RANGE'):
self._in_arguments = True
return token
class _Table(object):
_tokenizer_class = None
def __init__(self, prev_tokenizer=None):
self._tokenizer = self._tokenizer_class()
self._prev_tokenizer = prev_tokenizer
self._prev_values_on_row = []
def tokenize(self, value, index):
if self._continues(value, index):
self._tokenizer = self._prev_tokenizer
yield value, SYNTAX
else:
for value_and_token in self._tokenize(value, index):
yield value_and_token
self._prev_values_on_row.append(value)
def _continues(self, value, index):
return value == '...' and all(self._is_empty(t)
for t in self._prev_values_on_row)
def _is_empty(self, value):
return value in ('', '\\')
def _tokenize(self, value, index):
return self._tokenizer.tokenize(value)
def end_row(self):
self.__init__(prev_tokenizer=self._tokenizer)
class UnknownTable(_Table):
_tokenizer_class = Comment
def _continues(self, value, index):
return False
class VariableTable(_Table):
_tokenizer_class = Variable
class SettingTable(_Table):
_tokenizer_class = Setting
def __init__(self, template_setter, prev_tokenizer=None):
_Table.__init__(self, prev_tokenizer)
self._template_setter = template_setter
def _tokenize(self, value, index):
if index == 0 and normalize(value) == 'testtemplate':
self._tokenizer = Setting(self._template_setter)
return _Table._tokenize(self, value, index)
def end_row(self):
self.__init__(self._template_setter, prev_tokenizer=self._tokenizer)
class TestCaseTable(_Table):
_setting_class = TestCaseSetting
_test_template = None
_default_template = None
@property
def _tokenizer_class(self):
if self._test_template or (self._default_template and
self._test_template is not False):
return TemplatedKeywordCall
return KeywordCall
def _continues(self, value, index):
return index > 0 and _Table._continues(self, value, index)
def _tokenize(self, value, index):
if index == 0:
if value:
self._test_template = None
return GherkinTokenizer().tokenize(value, TC_KW_NAME)
if index == 1 and self._is_setting(value):
if self._is_template(value):
self._test_template = False
self._tokenizer = self._setting_class(self.set_test_template)
else:
self._tokenizer = self._setting_class()
if index == 1 and self._is_for_loop(value):
self._tokenizer = ForLoop()
if index == 1 and self._is_empty(value):
return [(value, SYNTAX)]
return _Table._tokenize(self, value, index)
def _is_setting(self, value):
return value.startswith('[') and value.endswith(']')
def _is_template(self, value):
return normalize(value) == '[template]'
def _is_for_loop(self, value):
return value.startswith(':') and normalize(value, remove=':') == 'for'
def set_test_template(self, template):
self._test_template = self._is_template_set(template)
def set_default_template(self, template):
self._default_template = self._is_template_set(template)
def _is_template_set(self, template):
return normalize(template) not in ('', '\\', 'none', '${empty}')
class KeywordTable(TestCaseTable):
_tokenizer_class = KeywordCall
_setting_class = KeywordSetting
def _is_template(self, value):
return False
# Following code copied directly from Robot Framework 2.7.5.
class VariableSplitter:
def __init__(self, string, identifiers):
self.identifier = None
self.base = None
self.index = None
self.start = -1
self.end = -1
self._identifiers = identifiers
self._may_have_internal_variables = False
try:
self._split(string)
except ValueError:
pass
else:
self._finalize()
def get_replaced_base(self, variables):
if self._may_have_internal_variables:
return variables.replace_string(self.base)
return self.base
def _finalize(self):
self.identifier = self._variable_chars[0]
self.base = ''.join(self._variable_chars[2:-1])
self.end = self.start + len(self._variable_chars)
if self._has_list_variable_index():
self.index = ''.join(self._list_variable_index_chars[1:-1])
self.end += len(self._list_variable_index_chars)
def _has_list_variable_index(self):
return self._list_variable_index_chars\
and self._list_variable_index_chars[-1] == ']'
def _split(self, string):
start_index, max_index = self._find_variable(string)
self.start = start_index
self._open_curly = 1
self._state = self._variable_state
self._variable_chars = [string[start_index], '{']
self._list_variable_index_chars = []
self._string = string
start_index += 2
for index, char in enumerate(string[start_index:]):
index += start_index # Giving start to enumerate only in Py 2.6+
try:
self._state(char, index)
except StopIteration:
return
if index == max_index and not self._scanning_list_variable_index():
return
def _scanning_list_variable_index(self):
return self._state in [self._waiting_list_variable_index_state,
self._list_variable_index_state]
def _find_variable(self, string):
max_end_index = string.rfind('}')
if max_end_index == -1:
raise ValueError('No variable end found')
if self._is_escaped(string, max_end_index):
return self._find_variable(string[:max_end_index])
start_index = self._find_start_index(string, 1, max_end_index)
if start_index == -1:
raise ValueError('No variable start found')
return start_index, max_end_index
def _find_start_index(self, string, start, end):
index = string.find('{', start, end) - 1
if index < 0:
return -1
if self._start_index_is_ok(string, index):
return index
return self._find_start_index(string, index+2, end)
def _start_index_is_ok(self, string, index):
return string[index] in self._identifiers\
and not self._is_escaped(string, index)
def _is_escaped(self, string, index):
escaped = False
while index > 0 and string[index-1] == '\\':
index -= 1
escaped = not escaped
return escaped
def _variable_state(self, char, index):
self._variable_chars.append(char)
if char == '}' and not self._is_escaped(self._string, index):
self._open_curly -= 1
if self._open_curly == 0:
if not self._is_list_variable():
raise StopIteration
self._state = self._waiting_list_variable_index_state
elif char in self._identifiers:
self._state = self._internal_variable_start_state
def _is_list_variable(self):
return self._variable_chars[0] == '@'
def _internal_variable_start_state(self, char, index):
self._state = self._variable_state
if char == '{':
self._variable_chars.append(char)
self._open_curly += 1
self._may_have_internal_variables = True
else:
self._variable_state(char, index)
def _waiting_list_variable_index_state(self, char, index):
if char != '[':
raise StopIteration
self._list_variable_index_chars.append(char)
self._state = self._list_variable_index_state
def _list_variable_index_state(self, char, index):
self._list_variable_index_chars.append(char)
if char == ']':
raise StopIteration

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff

View file

@ -0,0 +1,671 @@
# -*- coding: utf-8 -*-
"""
pygments.lexers.dotnet
~~~~~~~~~~~~~~~~~~~~~~
Lexers for .net languages.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
from pygments.lexer import RegexLexer, DelegatingLexer, bygroups, include, \
using, this
from pygments.token import Punctuation, \
Text, Comment, Operator, Keyword, Name, String, Number, Literal, Other
from pygments.util import get_choice_opt
from pygments import unistring as uni
from pygments.lexers.web import XmlLexer
__all__ = ['CSharpLexer', 'NemerleLexer', 'BooLexer', 'VbNetLexer',
'CSharpAspxLexer', 'VbNetAspxLexer', 'FSharpLexer']
class CSharpLexer(RegexLexer):
"""
For `C# <http://msdn2.microsoft.com/en-us/vcsharp/default.aspx>`_
source code.
Additional options accepted:
`unicodelevel`
Determines which Unicode characters this lexer allows for identifiers.
The possible values are:
* ``none`` -- only the ASCII letters and numbers are allowed. This
is the fastest selection.
* ``basic`` -- all Unicode characters from the specification except
category ``Lo`` are allowed.
* ``full`` -- all Unicode characters as specified in the C# specs
are allowed. Note that this means a considerable slowdown since the
``Lo`` category has more than 40,000 characters in it!
The default value is ``basic``.
*New in Pygments 0.8.*
"""
name = 'C#'
aliases = ['csharp', 'c#']
filenames = ['*.cs']
mimetypes = ['text/x-csharp'] # inferred
flags = re.MULTILINE | re.DOTALL | re.UNICODE
# for the range of allowed unicode characters in identifiers,
# see http://www.ecma-international.org/publications/files/ECMA-ST/Ecma-334.pdf
levels = {
'none': '@?[_a-zA-Z][a-zA-Z0-9_]*',
'basic': ('@?[_' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl + ']' +
'[' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl +
uni.Nd + uni.Pc + uni.Cf + uni.Mn + uni.Mc + ']*'),
'full': ('@?(?:_|[^' +
uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl') + '])'
+ '[^' + uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl',
'Nd', 'Pc', 'Cf', 'Mn', 'Mc') + ']*'),
}
tokens = {}
token_variants = True
for levelname, cs_ident in levels.items():
tokens[levelname] = {
'root': [
# method names
(r'^([ \t]*(?:' + cs_ident + r'(?:\[\])?\s+)+?)' # return type
r'(' + cs_ident + ')' # method name
r'(\s*)(\()', # signature start
bygroups(using(this), Name.Function, Text, Punctuation)),
(r'^\s*\[.*?\]', Name.Attribute),
(r'[^\S\n]+', Text),
(r'\\\n', Text), # line continuation
(r'//.*?\n', Comment.Single),
(r'/[*].*?[*]/', Comment.Multiline),
(r'\n', Text),
(r'[~!%^&*()+=|\[\]:;,.<>/?-]', Punctuation),
(r'[{}]', Punctuation),
(r'@"(""|[^"])*"', String),
(r'"(\\\\|\\"|[^"\n])*["\n]', String),
(r"'\\.'|'[^\\]'", String.Char),
(r"[0-9](\.[0-9]*)?([eE][+-][0-9]+)?"
r"[flFLdD]?|0[xX][0-9a-fA-F]+[Ll]?", Number),
(r'#[ \t]*(if|endif|else|elif|define|undef|'
r'line|error|warning|region|endregion|pragma)\b.*?\n',
Comment.Preproc),
(r'\b(extern)(\s+)(alias)\b', bygroups(Keyword, Text,
Keyword)),
(r'(abstract|as|async|await|base|break|case|catch|'
r'checked|const|continue|default|delegate|'
r'do|else|enum|event|explicit|extern|false|finally|'
r'fixed|for|foreach|goto|if|implicit|in|interface|'
r'internal|is|lock|new|null|operator|'
r'out|override|params|private|protected|public|readonly|'
r'ref|return|sealed|sizeof|stackalloc|static|'
r'switch|this|throw|true|try|typeof|'
r'unchecked|unsafe|virtual|void|while|'
r'get|set|new|partial|yield|add|remove|value|alias|ascending|'
r'descending|from|group|into|orderby|select|where|'
r'join|equals)\b', Keyword),
(r'(global)(::)', bygroups(Keyword, Punctuation)),
(r'(bool|byte|char|decimal|double|dynamic|float|int|long|object|'
r'sbyte|short|string|uint|ulong|ushort|var)\b\??', Keyword.Type),
(r'(class|struct)(\s+)', bygroups(Keyword, Text), 'class'),
(r'(namespace|using)(\s+)', bygroups(Keyword, Text), 'namespace'),
(cs_ident, Name),
],
'class': [
(cs_ident, Name.Class, '#pop')
],
'namespace': [
(r'(?=\()', Text, '#pop'), # using (resource)
('(' + cs_ident + r'|\.)+', Name.Namespace, '#pop')
]
}
def __init__(self, **options):
level = get_choice_opt(options, 'unicodelevel', self.tokens.keys(), 'basic')
if level not in self._all_tokens:
# compile the regexes now
self._tokens = self.__class__.process_tokendef(level)
else:
self._tokens = self._all_tokens[level]
RegexLexer.__init__(self, **options)
class NemerleLexer(RegexLexer):
"""
For `Nemerle <http://nemerle.org>`_ source code.
Additional options accepted:
`unicodelevel`
Determines which Unicode characters this lexer allows for identifiers.
The possible values are:
* ``none`` -- only the ASCII letters and numbers are allowed. This
is the fastest selection.
* ``basic`` -- all Unicode characters from the specification except
category ``Lo`` are allowed.
* ``full`` -- all Unicode characters as specified in the C# specs
are allowed. Note that this means a considerable slowdown since the
``Lo`` category has more than 40,000 characters in it!
The default value is ``basic``.
*New in Pygments 1.5.*
"""
name = 'Nemerle'
aliases = ['nemerle']
filenames = ['*.n']
mimetypes = ['text/x-nemerle'] # inferred
flags = re.MULTILINE | re.DOTALL | re.UNICODE
# for the range of allowed unicode characters in identifiers, see
# http://www.ecma-international.org/publications/files/ECMA-ST/Ecma-334.pdf
levels = dict(
none = '@?[_a-zA-Z][a-zA-Z0-9_]*',
basic = ('@?[_' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl + ']' +
'[' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl +
uni.Nd + uni.Pc + uni.Cf + uni.Mn + uni.Mc + ']*'),
full = ('@?(?:_|[^' + uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo',
'Nl') + '])'
+ '[^' + uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl',
'Nd', 'Pc', 'Cf', 'Mn', 'Mc') + ']*'),
)
tokens = {}
token_variants = True
for levelname, cs_ident in levels.items():
tokens[levelname] = {
'root': [
# method names
(r'^([ \t]*(?:' + cs_ident + r'(?:\[\])?\s+)+?)' # return type
r'(' + cs_ident + ')' # method name
r'(\s*)(\()', # signature start
bygroups(using(this), Name.Function, Text, Punctuation)),
(r'^\s*\[.*?\]', Name.Attribute),
(r'[^\S\n]+', Text),
(r'\\\n', Text), # line continuation
(r'//.*?\n', Comment.Single),
(r'/[*].*?[*]/', Comment.Multiline),
(r'\n', Text),
(r'\$\s*"', String, 'splice-string'),
(r'\$\s*<#', String, 'splice-string2'),
(r'<#', String, 'recursive-string'),
(r'(<\[)\s*(' + cs_ident + ':)?', Keyword),
(r'\]\>', Keyword),
# quasiquotation only
(r'\$' + cs_ident, Name),
(r'(\$)(\()', bygroups(Name, Punctuation),
'splice-string-content'),
(r'[~!%^&*()+=|\[\]:;,.<>/?-]', Punctuation),
(r'[{}]', Punctuation),
(r'@"(""|[^"])*"', String),
(r'"(\\\\|\\"|[^"\n])*["\n]', String),
(r"'\\.'|'[^\\]'", String.Char),
(r"0[xX][0-9a-fA-F]+[Ll]?", Number),
(r"[0-9](\.[0-9]*)?([eE][+-][0-9]+)?[flFLdD]?", Number),
(r'#[ \t]*(if|endif|else|elif|define|undef|'
r'line|error|warning|region|endregion|pragma)\b.*?\n',
Comment.Preproc),
(r'\b(extern)(\s+)(alias)\b', bygroups(Keyword, Text,
Keyword)),
(r'(abstract|and|as|base|catch|def|delegate|'
r'enum|event|extern|false|finally|'
r'fun|implements|interface|internal|'
r'is|macro|match|matches|module|mutable|new|'
r'null|out|override|params|partial|private|'
r'protected|public|ref|sealed|static|'
r'syntax|this|throw|true|try|type|typeof|'
r'virtual|volatile|when|where|with|'
r'assert|assert2|async|break|checked|continue|do|else|'
r'ensures|for|foreach|if|late|lock|new|nolate|'
r'otherwise|regexp|repeat|requires|return|surroundwith|'
r'unchecked|unless|using|while|yield)\b', Keyword),
(r'(global)(::)', bygroups(Keyword, Punctuation)),
(r'(bool|byte|char|decimal|double|float|int|long|object|sbyte|'
r'short|string|uint|ulong|ushort|void|array|list)\b\??',
Keyword.Type),
(r'(:>?)\s*(' + cs_ident + r'\??)',
bygroups(Punctuation, Keyword.Type)),
(r'(class|struct|variant|module)(\s+)',
bygroups(Keyword, Text), 'class'),
(r'(namespace|using)(\s+)', bygroups(Keyword, Text),
'namespace'),
(cs_ident, Name),
],
'class': [
(cs_ident, Name.Class, '#pop')
],
'namespace': [
(r'(?=\()', Text, '#pop'), # using (resource)
('(' + cs_ident + r'|\.)+', Name.Namespace, '#pop')
],
'splice-string': [
(r'[^"$]', String),
(r'\$' + cs_ident, Name),
(r'(\$)(\()', bygroups(Name, Punctuation),
'splice-string-content'),
(r'\\"', String),
(r'"', String, '#pop')
],
'splice-string2': [
(r'[^#<>$]', String),
(r'\$' + cs_ident, Name),
(r'(\$)(\()', bygroups(Name, Punctuation),
'splice-string-content'),
(r'<#', String, '#push'),
(r'#>', String, '#pop')
],
'recursive-string': [
(r'[^#<>]', String),
(r'<#', String, '#push'),
(r'#>', String, '#pop')
],
'splice-string-content': [
(r'if|match', Keyword),
(r'[~!%^&*+=|\[\]:;,.<>/?-\\"$ ]', Punctuation),
(cs_ident, Name),
(r'\d+', Number),
(r'\(', Punctuation, '#push'),
(r'\)', Punctuation, '#pop')
]
}
def __init__(self, **options):
level = get_choice_opt(options, 'unicodelevel', self.tokens.keys(),
'basic')
if level not in self._all_tokens:
# compile the regexes now
self._tokens = self.__class__.process_tokendef(level)
else:
self._tokens = self._all_tokens[level]
RegexLexer.__init__(self, **options)
class BooLexer(RegexLexer):
"""
For `Boo <http://boo.codehaus.org/>`_ source code.
"""
name = 'Boo'
aliases = ['boo']
filenames = ['*.boo']
mimetypes = ['text/x-boo']
tokens = {
'root': [
(r'\s+', Text),
(r'(#|//).*$', Comment.Single),
(r'/[*]', Comment.Multiline, 'comment'),
(r'[]{}:(),.;[]', Punctuation),
(r'\\\n', Text),
(r'\\', Text),
(r'(in|is|and|or|not)\b', Operator.Word),
(r'/(\\\\|\\/|[^/\s])/', String.Regex),
(r'@/(\\\\|\\/|[^/])*/', String.Regex),
(r'=~|!=|==|<<|>>|[-+/*%=<>&^|]', Operator),
(r'(as|abstract|callable|constructor|destructor|do|import|'
r'enum|event|final|get|interface|internal|of|override|'
r'partial|private|protected|public|return|set|static|'
r'struct|transient|virtual|yield|super|and|break|cast|'
r'continue|elif|else|ensure|except|for|given|goto|if|in|'
r'is|isa|not|or|otherwise|pass|raise|ref|try|unless|when|'
r'while|from|as)\b', Keyword),
(r'def(?=\s+\(.*?\))', Keyword),
(r'(def)(\s+)', bygroups(Keyword, Text), 'funcname'),
(r'(class)(\s+)', bygroups(Keyword, Text), 'classname'),
(r'(namespace)(\s+)', bygroups(Keyword, Text), 'namespace'),
(r'(?<!\.)(true|false|null|self|__eval__|__switch__|array|'
r'assert|checked|enumerate|filter|getter|len|lock|map|'
r'matrix|max|min|normalArrayIndexing|print|property|range|'
r'rawArrayIndexing|required|typeof|unchecked|using|'
r'yieldAll|zip)\b', Name.Builtin),
(r'"""(\\\\|\\"|.*?)"""', String.Double),
(r'"(\\\\|\\"|[^"]*?)"', String.Double),
(r"'(\\\\|\\'|[^']*?)'", String.Single),
(r'[a-zA-Z_][a-zA-Z0-9_]*', Name),
(r'(\d+\.\d*|\d*\.\d+)([fF][+-]?[0-9]+)?', Number.Float),
(r'[0-9][0-9\.]*(ms?|d|h|s)', Number),
(r'0\d+', Number.Oct),
(r'0x[a-fA-F0-9]+', Number.Hex),
(r'\d+L', Number.Integer.Long),
(r'\d+', Number.Integer),
],
'comment': [
('/[*]', Comment.Multiline, '#push'),
('[*]/', Comment.Multiline, '#pop'),
('[^/*]', Comment.Multiline),
('[*/]', Comment.Multiline)
],
'funcname': [
('[a-zA-Z_][a-zA-Z0-9_]*', Name.Function, '#pop')
],
'classname': [
('[a-zA-Z_][a-zA-Z0-9_]*', Name.Class, '#pop')
],
'namespace': [
('[a-zA-Z_][a-zA-Z0-9_.]*', Name.Namespace, '#pop')
]
}
class VbNetLexer(RegexLexer):
"""
For
`Visual Basic.NET <http://msdn2.microsoft.com/en-us/vbasic/default.aspx>`_
source code.
"""
name = 'VB.net'
aliases = ['vb.net', 'vbnet']
filenames = ['*.vb', '*.bas']
mimetypes = ['text/x-vbnet', 'text/x-vba'] # (?)
flags = re.MULTILINE | re.IGNORECASE
tokens = {
'root': [
(r'^\s*<.*?>', Name.Attribute),
(r'\s+', Text),
(r'\n', Text),
(r'rem\b.*?\n', Comment),
(r"'.*?\n", Comment),
(r'#If\s.*?\sThen|#ElseIf\s.*?\sThen|#End\s+If|#Const|'
r'#ExternalSource.*?\n|#End\s+ExternalSource|'
r'#Region.*?\n|#End\s+Region|#ExternalChecksum',
Comment.Preproc),
(r'[\(\){}!#,.:]', Punctuation),
(r'Option\s+(Strict|Explicit|Compare)\s+'
r'(On|Off|Binary|Text)', Keyword.Declaration),
(r'(?<!\.)(AddHandler|Alias|'
r'ByRef|ByVal|Call|Case|Catch|CBool|CByte|CChar|CDate|'
r'CDec|CDbl|CInt|CLng|CObj|Continue|CSByte|CShort|'
r'CSng|CStr|CType|CUInt|CULng|CUShort|Declare|'
r'Default|Delegate|DirectCast|Do|Each|Else|ElseIf|'
r'EndIf|Erase|Error|Event|Exit|False|Finally|For|'
r'Friend|Get|Global|GoSub|GoTo|Handles|If|'
r'Implements|Inherits|Interface|'
r'Let|Lib|Loop|Me|MustInherit|'
r'MustOverride|MyBase|MyClass|Narrowing|New|Next|'
r'Not|Nothing|NotInheritable|NotOverridable|Of|On|'
r'Operator|Option|Optional|Overloads|Overridable|'
r'Overrides|ParamArray|Partial|Private|Protected|'
r'Public|RaiseEvent|ReadOnly|ReDim|RemoveHandler|Resume|'
r'Return|Select|Set|Shadows|Shared|Single|'
r'Static|Step|Stop|SyncLock|Then|'
r'Throw|To|True|Try|TryCast|Wend|'
r'Using|When|While|Widening|With|WithEvents|'
r'WriteOnly)\b', Keyword),
(r'(?<!\.)End\b', Keyword, 'end'),
(r'(?<!\.)(Dim|Const)\b', Keyword, 'dim'),
(r'(?<!\.)(Function|Sub|Property)(\s+)',
bygroups(Keyword, Text), 'funcname'),
(r'(?<!\.)(Class|Structure|Enum)(\s+)',
bygroups(Keyword, Text), 'classname'),
(r'(?<!\.)(Module|Namespace|Imports)(\s+)',
bygroups(Keyword, Text), 'namespace'),
(r'(?<!\.)(Boolean|Byte|Char|Date|Decimal|Double|Integer|Long|'
r'Object|SByte|Short|Single|String|Variant|UInteger|ULong|'
r'UShort)\b', Keyword.Type),
(r'(?<!\.)(AddressOf|And|AndAlso|As|GetType|In|Is|IsNot|Like|Mod|'
r'Or|OrElse|TypeOf|Xor)\b', Operator.Word),
(r'&=|[*]=|/=|\\=|\^=|\+=|-=|<<=|>>=|<<|>>|:=|'
r'<=|>=|<>|[-&*/\\^+=<>]',
Operator),
('"', String, 'string'),
('[a-zA-Z_][a-zA-Z0-9_]*[%&@!#$]?', Name),
('#.*?#', Literal.Date),
(r'(\d+\.\d*|\d*\.\d+)([fF][+-]?[0-9]+)?', Number.Float),
(r'\d+([SILDFR]|US|UI|UL)?', Number.Integer),
(r'&H[0-9a-f]+([SILDFR]|US|UI|UL)?', Number.Integer),
(r'&O[0-7]+([SILDFR]|US|UI|UL)?', Number.Integer),
(r'_\n', Text), # Line continuation
],
'string': [
(r'""', String),
(r'"C?', String, '#pop'),
(r'[^"]+', String),
],
'dim': [
(r'[a-z_][a-z0-9_]*', Name.Variable, '#pop'),
(r'', Text, '#pop'), # any other syntax
],
'funcname': [
(r'[a-z_][a-z0-9_]*', Name.Function, '#pop'),
],
'classname': [
(r'[a-z_][a-z0-9_]*', Name.Class, '#pop'),
],
'namespace': [
(r'[a-z_][a-z0-9_.]*', Name.Namespace, '#pop'),
],
'end': [
(r'\s+', Text),
(r'(Function|Sub|Property|Class|Structure|Enum|Module|Namespace)\b',
Keyword, '#pop'),
(r'', Text, '#pop'),
]
}
class GenericAspxLexer(RegexLexer):
"""
Lexer for ASP.NET pages.
"""
name = 'aspx-gen'
filenames = []
mimetypes = []
flags = re.DOTALL
tokens = {
'root': [
(r'(<%[@=#]?)(.*?)(%>)', bygroups(Name.Tag, Other, Name.Tag)),
(r'(<script.*?>)(.*?)(</script>)', bygroups(using(XmlLexer),
Other,
using(XmlLexer))),
(r'(.+?)(?=<)', using(XmlLexer)),
(r'.+', using(XmlLexer)),
],
}
#TODO support multiple languages within the same source file
class CSharpAspxLexer(DelegatingLexer):
"""
Lexer for highligting C# within ASP.NET pages.
"""
name = 'aspx-cs'
aliases = ['aspx-cs']
filenames = ['*.aspx', '*.asax', '*.ascx', '*.ashx', '*.asmx', '*.axd']
mimetypes = []
def __init__(self, **options):
super(CSharpAspxLexer, self).__init__(CSharpLexer,GenericAspxLexer,
**options)
def analyse_text(text):
if re.search(r'Page\s*Language="C#"', text, re.I) is not None:
return 0.2
elif re.search(r'script[^>]+language=["\']C#', text, re.I) is not None:
return 0.15
class VbNetAspxLexer(DelegatingLexer):
"""
Lexer for highligting Visual Basic.net within ASP.NET pages.
"""
name = 'aspx-vb'
aliases = ['aspx-vb']
filenames = ['*.aspx', '*.asax', '*.ascx', '*.ashx', '*.asmx', '*.axd']
mimetypes = []
def __init__(self, **options):
super(VbNetAspxLexer, self).__init__(VbNetLexer,GenericAspxLexer,
**options)
def analyse_text(text):
if re.search(r'Page\s*Language="Vb"', text, re.I) is not None:
return 0.2
elif re.search(r'script[^>]+language=["\']vb', text, re.I) is not None:
return 0.15
# Very close to functional.OcamlLexer
class FSharpLexer(RegexLexer):
"""
For the F# language (version 3.0).
*New in Pygments 1.5.*
"""
name = 'FSharp'
aliases = ['fsharp']
filenames = ['*.fs', '*.fsi']
mimetypes = ['text/x-fsharp']
keywords = [
'abstract', 'as', 'assert', 'base', 'begin', 'class', 'default',
'delegate', 'do!', 'do', 'done', 'downcast', 'downto', 'elif', 'else',
'end', 'exception', 'extern', 'false', 'finally', 'for', 'function',
'fun', 'global', 'if', 'inherit', 'inline', 'interface', 'internal',
'in', 'lazy', 'let!', 'let', 'match', 'member', 'module', 'mutable',
'namespace', 'new', 'null', 'of', 'open', 'override', 'private', 'public',
'rec', 'return!', 'return', 'select', 'static', 'struct', 'then', 'to',
'true', 'try', 'type', 'upcast', 'use!', 'use', 'val', 'void', 'when',
'while', 'with', 'yield!', 'yield',
]
# Reserved words; cannot hurt to color them as keywords too.
keywords += [
'atomic', 'break', 'checked', 'component', 'const', 'constraint',
'constructor', 'continue', 'eager', 'event', 'external', 'fixed',
'functor', 'include', 'method', 'mixin', 'object', 'parallel',
'process', 'protected', 'pure', 'sealed', 'tailcall', 'trait',
'virtual', 'volatile',
]
keyopts = [
'!=', '#', '&&', '&', '\(', '\)', '\*', '\+', ',', '-\.',
'->', '-', '\.\.', '\.', '::', ':=', ':>', ':', ';;', ';', '<-',
'<\]', '<', '>\]', '>', '\?\?', '\?', '\[<', '\[\|', '\[', '\]',
'_', '`', '{', '\|\]', '\|', '}', '~', '<@@', '<@', '=', '@>', '@@>',
]
operators = r'[!$%&*+\./:<=>?@^|~-]'
word_operators = ['and', 'or', 'not']
prefix_syms = r'[!?~]'
infix_syms = r'[=<>@^|&+\*/$%-]'
primitives = [
'sbyte', 'byte', 'char', 'nativeint', 'unativeint', 'float32', 'single',
'float', 'double', 'int8', 'uint8', 'int16', 'uint16', 'int32',
'uint32', 'int64', 'uint64', 'decimal', 'unit', 'bool', 'string',
'list', 'exn', 'obj', 'enum',
]
# See http://msdn.microsoft.com/en-us/library/dd233181.aspx and/or
# http://fsharp.org/about/files/spec.pdf for reference. Good luck.
tokens = {
'escape-sequence': [
(r'\\[\\\"\'ntbrafv]', String.Escape),
(r'\\[0-9]{3}', String.Escape),
(r'\\u[0-9a-fA-F]{4}', String.Escape),
(r'\\U[0-9a-fA-F]{8}', String.Escape),
],
'root': [
(r'\s+', Text),
(r'\(\)|\[\]', Name.Builtin.Pseudo),
(r'\b(?<!\.)([A-Z][A-Za-z0-9_\']*)(?=\s*\.)',
Name.Namespace, 'dotted'),
(r'\b([A-Z][A-Za-z0-9_\']*)', Name),
(r'///.*?\n', String.Doc),
(r'//.*?\n', Comment.Single),
(r'\(\*(?!\))', Comment, 'comment'),
(r'@"', String, 'lstring'),
(r'"""', String, 'tqs'),
(r'"', String, 'string'),
(r'\b(open|module)(\s+)([a-zA-Z0-9_.]+)',
bygroups(Keyword, Text, Name.Namespace)),
(r'\b(let!?)(\s+)([a-zA-Z0-9_]+)',
bygroups(Keyword, Text, Name.Variable)),
(r'\b(type)(\s+)([a-zA-Z0-9_]+)',
bygroups(Keyword, Text, Name.Class)),
(r'\b(member|override)(\s+)([a-zA-Z0-9_]+)(\.)([a-zA-Z0-9_]+)',
bygroups(Keyword, Text, Name, Punctuation, Name.Function)),
(r'\b(%s)\b' % '|'.join(keywords), Keyword),
(r'(%s)' % '|'.join(keyopts), Operator),
(r'(%s|%s)?%s' % (infix_syms, prefix_syms, operators), Operator),
(r'\b(%s)\b' % '|'.join(word_operators), Operator.Word),
(r'\b(%s)\b' % '|'.join(primitives), Keyword.Type),
(r'#[ \t]*(if|endif|else|line|nowarn|light|\d+)\b.*?\n',
Comment.Preproc),
(r"[^\W\d][\w']*", Name),
(r'\d[\d_]*[uU]?[yslLnQRZINGmM]?', Number.Integer),
(r'0[xX][\da-fA-F][\da-fA-F_]*[uU]?[yslLn]?[fF]?', Number.Hex),
(r'0[oO][0-7][0-7_]*[uU]?[yslLn]?', Number.Oct),
(r'0[bB][01][01_]*[uU]?[yslLn]?', Number.Binary),
(r'-?\d[\d_]*(.[\d_]*)?([eE][+\-]?\d[\d_]*)[fFmM]?',
Number.Float),
(r"'(?:(\\[\\\"'ntbr ])|(\\[0-9]{3})|(\\x[0-9a-fA-F]{2}))'B?",
String.Char),
(r"'.'", String.Char),
(r"'", Keyword), # a stray quote is another syntax element
(r'[~?][a-z][\w\']*:', Name.Variable),
],
'dotted': [
(r'\s+', Text),
(r'\.', Punctuation),
(r'[A-Z][A-Za-z0-9_\']*(?=\s*\.)', Name.Namespace),
(r'[A-Z][A-Za-z0-9_\']*', Name, '#pop'),
(r'[a-z_][A-Za-z0-9_\']*', Name, '#pop'),
],
'comment': [
(r'[^(*)@"]+', Comment),
(r'\(\*', Comment, '#push'),
(r'\*\)', Comment, '#pop'),
# comments cannot be closed within strings in comments
(r'@"', String, 'lstring'),
(r'"""', String, 'tqs'),
(r'"', String, 'string'),
(r'[(*)@]', Comment),
],
'string': [
(r'[^\\"]+', String),
include('escape-sequence'),
(r'\\\n', String),
(r'\n', String), # newlines are allowed in any string
(r'"B?', String, '#pop'),
],
'lstring': [
(r'[^"]+', String),
(r'\n', String),
(r'""', String),
(r'"B?', String, '#pop'),
],
'tqs': [
(r'[^"]+', String),
(r'\n', String),
(r'"""B?', String, '#pop'),
(r'"', String),
],
}

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff

View file

@ -0,0 +1,100 @@
# -*- coding: utf-8 -*-
"""
pygments.lexers.special
~~~~~~~~~~~~~~~~~~~~~~~
Special lexers.
:copyright: Copyright 2006-2013 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
__all__ = ['TextLexer', 'RawTokenLexer']
class TextLexer(Lexer):
"""
"Null" lexer, doesn't highlight anything.
"""
name = 'Text only'
aliases = ['text']
filenames = ['*.txt']
mimetypes = ['text/plain']
def get_tokens_unprocessed(self, text):
yield 0, Text, text
_ttype_cache = {}
line_re = re.compile(b('.*?\n'))
class RawTokenLexer(Lexer):
"""
Recreate a token stream formatted with the `RawTokenFormatter`. This
lexer raises exceptions during parsing if the token stream in the
file is malformed.
Additional options accepted:
`compress`
If set to ``"gz"`` or ``"bz2"``, decompress the token stream with
the given compression algorithm before lexing (default: ``""``).
"""
name = 'Raw token data'
aliases = ['raw']
filenames = []
mimetypes = ['application/x-pygments-tokens']
def __init__(self, **options):
self.compress = get_choice_opt(options, 'compress',
['', 'none', 'gz', 'bz2'], '')
Lexer.__init__(self, **options)
def get_tokens(self, text):
if isinstance(text, unicode):
# 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))
text = gzipfile.read()
elif self.compress == 'bz2':
import bz2
text = bz2.decompress(text)
# 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')
for i, t, v in self.get_tokens_unprocessed(text):
yield t, v
def get_tokens_unprocessed(self, text):
length = 0
for match in line_re.finditer(text):
try:
ttypestr, val = match.group().split(b('\t'), 1)
except ValueError:
val = match.group().decode(self.encoding)
ttype = Error
else:
ttype = _ttype_cache.get(ttypestr)
if not ttype:
ttype = Token
ttypes = ttypestr.split('.')[1:]
for ttype_ in ttypes:
if not ttype_ or not ttype_[0].isupper():
raise ValueError('malformed token name')
ttype = getattr(ttype, ttype_)
_ttype_cache[ttypestr] = ttype
val = val[2:-2].decode('unicode-escape')
yield length, ttype, val
length += len(val)

View file

@ -0,0 +1,559 @@
# -*- coding: utf-8 -*-
"""
pygments.lexers.sql
~~~~~~~~~~~~~~~~~~~
Lexers for various SQL dialects and related interactive sessions.
Postgres specific lexers:
`PostgresLexer`
A SQL lexer for the PostgreSQL dialect. Differences w.r.t. the SQL
lexer are:
- keywords and data types list parsed from the PG docs (run the
`_postgres_builtins` module to update them);
- Content of $-strings parsed using a specific lexer, e.g. the content
of a PL/Python function is parsed using the Python lexer;
- parse PG specific constructs: E-strings, $-strings, U&-strings,
different operators and punctuation.
`PlPgsqlLexer`
A lexer for the PL/pgSQL language. Adds a few specific construct on
top of the PG SQL lexer (such as <<label>>).
`PostgresConsoleLexer`
A lexer to highlight an interactive psql session:
- identifies the prompt and does its best to detect the end of command
in multiline statement where not all the lines are prefixed by a
prompt, telling them apart from the output;
- highlights errors in the output and notification levels;
- handles psql backslash commands.
The ``tests/examplefiles`` contains a few test files with data to be
parsed by these lexers.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
from pygments.lexer import Lexer, RegexLexer, do_insertions, bygroups
from pygments.token import Punctuation, \
Text, Comment, Operator, Keyword, Name, String, Number, Generic
from pygments.lexers import get_lexer_by_name, ClassNotFound
from pygments.lexers._postgres_builtins import KEYWORDS, DATATYPES, \
PSEUDO_TYPES, PLPGSQL_KEYWORDS
__all__ = ['PostgresLexer', 'PlPgsqlLexer', 'PostgresConsoleLexer',
'SqlLexer', 'MySqlLexer', 'SqliteConsoleLexer']
line_re = re.compile('.*?\n')
language_re = re.compile(r"\s+LANGUAGE\s+'?(\w+)'?", re.IGNORECASE)
def language_callback(lexer, match):
"""Parse the content of a $-string using a lexer
The lexer is chosen looking for a nearby LANGUAGE.
"""
l = None
m = language_re.match(lexer.text[match.end():match.end()+100])
if m is not None:
l = lexer._get_lexer(m.group(1))
else:
m = list(language_re.finditer(
lexer.text[max(0, match.start()-100):match.start()]))
if m:
l = lexer._get_lexer(m[-1].group(1))
if l:
yield (match.start(1), String, match.group(1))
for x in l.get_tokens_unprocessed(match.group(2)):
yield x
yield (match.start(3), String, match.group(3))
else:
yield (match.start(), String, match.group())
class PostgresBase(object):
"""Base class for Postgres-related lexers.
This is implemented as a mixin to avoid the Lexer metaclass kicking in.
this way the different lexer don't have a common Lexer ancestor. If they
had, _tokens could be created on this ancestor and not updated for the
other classes, resulting e.g. in PL/pgSQL parsed as SQL. This shortcoming
seem to suggest that regexp lexers are not really subclassable.
"""
def get_tokens_unprocessed(self, text, *args):
# Have a copy of the entire text to be used by `language_callback`.
self.text = text
for x in super(PostgresBase, self).get_tokens_unprocessed(
text, *args):
yield x
def _get_lexer(self, lang):
if lang.lower() == 'sql':
return get_lexer_by_name('postgresql', **self.options)
tries = [ lang ]
if lang.startswith('pl'):
tries.append(lang[2:])
if lang.endswith('u'):
tries.append(lang[:-1])
if lang.startswith('pl') and lang.endswith('u'):
tries.append(lang[2:-1])
for l in tries:
try:
return get_lexer_by_name(l, **self.options)
except ClassNotFound:
pass
else:
# TODO: better logging
# print >>sys.stderr, "language not found:", lang
return None
class PostgresLexer(PostgresBase, RegexLexer):
"""
Lexer for the PostgreSQL dialect of SQL.
*New in Pygments 1.5.*
"""
name = 'PostgreSQL SQL dialect'
aliases = ['postgresql', 'postgres']
mimetypes = ['text/x-postgresql']
flags = re.IGNORECASE
tokens = {
'root': [
(r'\s+', Text),
(r'--.*?\n', Comment.Single),
(r'/\*', Comment.Multiline, 'multiline-comments'),
(r'(' + '|'.join([s.replace(" ", "\s+")
for s in DATATYPES + PSEUDO_TYPES])
+ r')\b', Name.Builtin),
(r'(' + '|'.join(KEYWORDS) + r')\b', Keyword),
(r'[+*/<>=~!@#%^&|`?-]+', Operator),
(r'::', Operator), # cast
(r'\$\d+', Name.Variable),
(r'([0-9]*\.[0-9]*|[0-9]+)(e[+-]?[0-9]+)?', Number.Float),
(r'[0-9]+', Number.Integer),
(r"(E|U&)?'(''|[^'])*'", String.Single),
(r'(U&)?"(""|[^"])*"', String.Name), # quoted identifier
(r'(?s)(\$[^\$]*\$)(.*?)(\1)', language_callback),
(r'[a-zA-Z_][a-zA-Z0-9_]*', Name),
# psql variable in SQL
(r""":(['"]?)[a-z][a-z0-9_]*\b\1""", Name.Variable),
(r'[;:()\[\]\{\},\.]', Punctuation),
],
'multiline-comments': [
(r'/\*', Comment.Multiline, 'multiline-comments'),
(r'\*/', Comment.Multiline, '#pop'),
(r'[^/\*]+', Comment.Multiline),
(r'[/*]', Comment.Multiline)
],
}
class PlPgsqlLexer(PostgresBase, RegexLexer):
"""
Handle the extra syntax in Pl/pgSQL language.
*New in Pygments 1.5.*
"""
name = 'PL/pgSQL'
aliases = ['plpgsql']
mimetypes = ['text/x-plpgsql']
flags = re.IGNORECASE
tokens = dict((k, l[:]) for (k, l) in PostgresLexer.tokens.iteritems())
# extend the keywords list
for i, pattern in enumerate(tokens['root']):
if pattern[1] == Keyword:
tokens['root'][i] = (
r'(' + '|'.join(KEYWORDS + PLPGSQL_KEYWORDS) + r')\b',
Keyword)
del i
break
else:
assert 0, "SQL keywords not found"
# Add specific PL/pgSQL rules (before the SQL ones)
tokens['root'][:0] = [
(r'\%[a-z][a-z0-9_]*\b', Name.Builtin), # actually, a datatype
(r':=', Operator),
(r'\<\<[a-z][a-z0-9_]*\>\>', Name.Label),
(r'\#[a-z][a-z0-9_]*\b', Keyword.Pseudo), # #variable_conflict
]
class PsqlRegexLexer(PostgresBase, RegexLexer):
"""
Extend the PostgresLexer adding support specific for psql commands.
This is not a complete psql lexer yet as it lacks prompt support
and output rendering.
"""
name = 'PostgreSQL console - regexp based lexer'
aliases = [] # not public
flags = re.IGNORECASE
tokens = dict((k, l[:]) for (k, l) in PostgresLexer.tokens.iteritems())
tokens['root'].append(
(r'\\[^\s]+', Keyword.Pseudo, 'psql-command'))
tokens['psql-command'] = [
(r'\n', Text, 'root'),
(r'\s+', Text),
(r'\\[^\s]+', Keyword.Pseudo),
(r""":(['"]?)[a-z][a-z0-9_]*\b\1""", Name.Variable),
(r"'(''|[^'])*'", String.Single),
(r"`([^`])*`", String.Backtick),
(r"[^\s]+", String.Symbol),
]
re_prompt = re.compile(r'^(\S.*?)??[=\-\(\$\'\"][#>]')
re_psql_command = re.compile(r'\s*\\')
re_end_command = re.compile(r';\s*(--.*?)?$')
re_psql_command = re.compile(r'(\s*)(\\.+?)(\s+)$')
re_error = re.compile(r'(ERROR|FATAL):')
re_message = re.compile(
r'((?:DEBUG|INFO|NOTICE|WARNING|ERROR|'
r'FATAL|HINT|DETAIL|CONTEXT|LINE [0-9]+):)(.*?\n)')
class lookahead(object):
"""Wrap an iterator and allow pushing back an item."""
def __init__(self, x):
self.iter = iter(x)
self._nextitem = None
def __iter__(self):
return self
def send(self, i):
self._nextitem = i
return i
def next(self):
if self._nextitem is not None:
ni = self._nextitem
self._nextitem = None
return ni
return self.iter.next()
class PostgresConsoleLexer(Lexer):
"""
Lexer for psql sessions.
*New in Pygments 1.5.*
"""
name = 'PostgreSQL console (psql)'
aliases = ['psql', 'postgresql-console', 'postgres-console']
mimetypes = ['text/x-postgresql-psql']
def get_tokens_unprocessed(self, data):
sql = PsqlRegexLexer(**self.options)
lines = lookahead(line_re.findall(data))
# prompt-output cycle
while 1:
# consume the lines of the command: start with an optional prompt
# and continue until the end of command is detected
curcode = ''
insertions = []
while 1:
try:
line = lines.next()
except StopIteration:
# allow the emission of partially collected items
# the repl loop will be broken below
break
# Identify a shell prompt in case of psql commandline example
if line.startswith('$') and not curcode:
lexer = get_lexer_by_name('console', **self.options)
for x in lexer.get_tokens_unprocessed(line):
yield x
break
# Identify a psql prompt
mprompt = re_prompt.match(line)
if mprompt is not None:
insertions.append((len(curcode),
[(0, Generic.Prompt, mprompt.group())]))
curcode += line[len(mprompt.group()):]
else:
curcode += line
# Check if this is the end of the command
# TODO: better handle multiline comments at the end with
# a lexer with an external state?
if re_psql_command.match(curcode) \
or re_end_command.search(curcode):
break
# Emit the combined stream of command and prompt(s)
for item in do_insertions(insertions,
sql.get_tokens_unprocessed(curcode)):
yield item
# Emit the output lines
out_token = Generic.Output
while 1:
line = lines.next()
mprompt = re_prompt.match(line)
if mprompt is not None:
# push the line back to have it processed by the prompt
lines.send(line)
break
mmsg = re_message.match(line)
if mmsg is not None:
if mmsg.group(1).startswith("ERROR") \
or mmsg.group(1).startswith("FATAL"):
out_token = Generic.Error
yield (mmsg.start(1), Generic.Strong, mmsg.group(1))
yield (mmsg.start(2), out_token, mmsg.group(2))
else:
yield (0, out_token, line)
class SqlLexer(RegexLexer):
"""
Lexer for Structured Query Language. Currently, this lexer does
not recognize any special syntax except ANSI SQL.
"""
name = 'SQL'
aliases = ['sql']
filenames = ['*.sql']
mimetypes = ['text/x-sql']
flags = re.IGNORECASE
tokens = {
'root': [
(r'\s+', Text),
(r'--.*?\n', Comment.Single),
(r'/\*', Comment.Multiline, 'multiline-comments'),
(r'(ABORT|ABS|ABSOLUTE|ACCESS|ADA|ADD|ADMIN|AFTER|AGGREGATE|'
r'ALIAS|ALL|ALLOCATE|ALTER|ANALYSE|ANALYZE|AND|ANY|ARE|AS|'
r'ASC|ASENSITIVE|ASSERTION|ASSIGNMENT|ASYMMETRIC|AT|ATOMIC|'
r'AUTHORIZATION|AVG|BACKWARD|BEFORE|BEGIN|BETWEEN|BITVAR|'
r'BIT_LENGTH|BOTH|BREADTH|BY|C|CACHE|CALL|CALLED|CARDINALITY|'
r'CASCADE|CASCADED|CASE|CAST|CATALOG|CATALOG_NAME|CHAIN|'
r'CHARACTERISTICS|CHARACTER_LENGTH|CHARACTER_SET_CATALOG|'
r'CHARACTER_SET_NAME|CHARACTER_SET_SCHEMA|CHAR_LENGTH|CHECK|'
r'CHECKED|CHECKPOINT|CLASS|CLASS_ORIGIN|CLOB|CLOSE|CLUSTER|'
r'COALSECE|COBOL|COLLATE|COLLATION|COLLATION_CATALOG|'
r'COLLATION_NAME|COLLATION_SCHEMA|COLUMN|COLUMN_NAME|'
r'COMMAND_FUNCTION|COMMAND_FUNCTION_CODE|COMMENT|COMMIT|'
r'COMMITTED|COMPLETION|CONDITION_NUMBER|CONNECT|CONNECTION|'
r'CONNECTION_NAME|CONSTRAINT|CONSTRAINTS|CONSTRAINT_CATALOG|'
r'CONSTRAINT_NAME|CONSTRAINT_SCHEMA|CONSTRUCTOR|CONTAINS|'
r'CONTINUE|CONVERSION|CONVERT|COPY|CORRESPONTING|COUNT|'
r'CREATE|CREATEDB|CREATEUSER|CROSS|CUBE|CURRENT|CURRENT_DATE|'
r'CURRENT_PATH|CURRENT_ROLE|CURRENT_TIME|CURRENT_TIMESTAMP|'
r'CURRENT_USER|CURSOR|CURSOR_NAME|CYCLE|DATA|DATABASE|'
r'DATETIME_INTERVAL_CODE|DATETIME_INTERVAL_PRECISION|DAY|'
r'DEALLOCATE|DECLARE|DEFAULT|DEFAULTS|DEFERRABLE|DEFERRED|'
r'DEFINED|DEFINER|DELETE|DELIMITER|DELIMITERS|DEREF|DESC|'
r'DESCRIBE|DESCRIPTOR|DESTROY|DESTRUCTOR|DETERMINISTIC|'
r'DIAGNOSTICS|DICTIONARY|DISCONNECT|DISPATCH|DISTINCT|DO|'
r'DOMAIN|DROP|DYNAMIC|DYNAMIC_FUNCTION|DYNAMIC_FUNCTION_CODE|'
r'EACH|ELSE|ENCODING|ENCRYPTED|END|END-EXEC|EQUALS|ESCAPE|EVERY|'
r'EXCEPTION|EXCEPT|EXCLUDING|EXCLUSIVE|EXEC|EXECUTE|EXISTING|'
r'EXISTS|EXPLAIN|EXTERNAL|EXTRACT|FALSE|FETCH|FINAL|FIRST|FOR|'
r'FORCE|FOREIGN|FORTRAN|FORWARD|FOUND|FREE|FREEZE|FROM|FULL|'
r'FUNCTION|G|GENERAL|GENERATED|GET|GLOBAL|GO|GOTO|GRANT|GRANTED|'
r'GROUP|GROUPING|HANDLER|HAVING|HIERARCHY|HOLD|HOST|IDENTITY|'
r'IGNORE|ILIKE|IMMEDIATE|IMMUTABLE|IMPLEMENTATION|IMPLICIT|IN|'
r'INCLUDING|INCREMENT|INDEX|INDITCATOR|INFIX|INHERITS|INITIALIZE|'
r'INITIALLY|INNER|INOUT|INPUT|INSENSITIVE|INSERT|INSTANTIABLE|'
r'INSTEAD|INTERSECT|INTO|INVOKER|IS|ISNULL|ISOLATION|ITERATE|JOIN|'
r'KEY|KEY_MEMBER|KEY_TYPE|LANCOMPILER|LANGUAGE|LARGE|LAST|'
r'LATERAL|LEADING|LEFT|LENGTH|LESS|LEVEL|LIKE|LIMIT|LISTEN|LOAD|'
r'LOCAL|LOCALTIME|LOCALTIMESTAMP|LOCATION|LOCATOR|LOCK|LOWER|'
r'MAP|MATCH|MAX|MAXVALUE|MESSAGE_LENGTH|MESSAGE_OCTET_LENGTH|'
r'MESSAGE_TEXT|METHOD|MIN|MINUTE|MINVALUE|MOD|MODE|MODIFIES|'
r'MODIFY|MONTH|MORE|MOVE|MUMPS|NAMES|NATIONAL|NATURAL|NCHAR|'
r'NCLOB|NEW|NEXT|NO|NOCREATEDB|NOCREATEUSER|NONE|NOT|NOTHING|'
r'NOTIFY|NOTNULL|NULL|NULLABLE|NULLIF|OBJECT|OCTET_LENGTH|OF|OFF|'
r'OFFSET|OIDS|OLD|ON|ONLY|OPEN|OPERATION|OPERATOR|OPTION|OPTIONS|'
r'OR|ORDER|ORDINALITY|OUT|OUTER|OUTPUT|OVERLAPS|OVERLAY|OVERRIDING|'
r'OWNER|PAD|PARAMETER|PARAMETERS|PARAMETER_MODE|PARAMATER_NAME|'
r'PARAMATER_ORDINAL_POSITION|PARAMETER_SPECIFIC_CATALOG|'
r'PARAMETER_SPECIFIC_NAME|PARAMATER_SPECIFIC_SCHEMA|PARTIAL|'
r'PASCAL|PENDANT|PLACING|PLI|POSITION|POSTFIX|PRECISION|PREFIX|'
r'PREORDER|PREPARE|PRESERVE|PRIMARY|PRIOR|PRIVILEGES|PROCEDURAL|'
r'PROCEDURE|PUBLIC|READ|READS|RECHECK|RECURSIVE|REF|REFERENCES|'
r'REFERENCING|REINDEX|RELATIVE|RENAME|REPEATABLE|REPLACE|RESET|'
r'RESTART|RESTRICT|RESULT|RETURN|RETURNED_LENGTH|'
r'RETURNED_OCTET_LENGTH|RETURNED_SQLSTATE|RETURNS|REVOKE|RIGHT|'
r'ROLE|ROLLBACK|ROLLUP|ROUTINE|ROUTINE_CATALOG|ROUTINE_NAME|'
r'ROUTINE_SCHEMA|ROW|ROWS|ROW_COUNT|RULE|SAVE_POINT|SCALE|SCHEMA|'
r'SCHEMA_NAME|SCOPE|SCROLL|SEARCH|SECOND|SECURITY|SELECT|SELF|'
r'SENSITIVE|SERIALIZABLE|SERVER_NAME|SESSION|SESSION_USER|SET|'
r'SETOF|SETS|SHARE|SHOW|SIMILAR|SIMPLE|SIZE|SOME|SOURCE|SPACE|'
r'SPECIFIC|SPECIFICTYPE|SPECIFIC_NAME|SQL|SQLCODE|SQLERROR|'
r'SQLEXCEPTION|SQLSTATE|SQLWARNINIG|STABLE|START|STATE|STATEMENT|'
r'STATIC|STATISTICS|STDIN|STDOUT|STORAGE|STRICT|STRUCTURE|STYPE|'
r'SUBCLASS_ORIGIN|SUBLIST|SUBSTRING|SUM|SYMMETRIC|SYSID|SYSTEM|'
r'SYSTEM_USER|TABLE|TABLE_NAME| TEMP|TEMPLATE|TEMPORARY|TERMINATE|'
r'THAN|THEN|TIMESTAMP|TIMEZONE_HOUR|TIMEZONE_MINUTE|TO|TOAST|'
r'TRAILING|TRANSATION|TRANSACTIONS_COMMITTED|'
r'TRANSACTIONS_ROLLED_BACK|TRANSATION_ACTIVE|TRANSFORM|'
r'TRANSFORMS|TRANSLATE|TRANSLATION|TREAT|TRIGGER|TRIGGER_CATALOG|'
r'TRIGGER_NAME|TRIGGER_SCHEMA|TRIM|TRUE|TRUNCATE|TRUSTED|TYPE|'
r'UNCOMMITTED|UNDER|UNENCRYPTED|UNION|UNIQUE|UNKNOWN|UNLISTEN|'
r'UNNAMED|UNNEST|UNTIL|UPDATE|UPPER|USAGE|USER|'
r'USER_DEFINED_TYPE_CATALOG|USER_DEFINED_TYPE_NAME|'
r'USER_DEFINED_TYPE_SCHEMA|USING|VACUUM|VALID|VALIDATOR|VALUES|'
r'VARIABLE|VERBOSE|VERSION|VIEW|VOLATILE|WHEN|WHENEVER|WHERE|'
r'WITH|WITHOUT|WORK|WRITE|YEAR|ZONE)\b', Keyword),
(r'(ARRAY|BIGINT|BINARY|BIT|BLOB|BOOLEAN|CHAR|CHARACTER|DATE|'
r'DEC|DECIMAL|FLOAT|INT|INTEGER|INTERVAL|NUMBER|NUMERIC|REAL|'
r'SERIAL|SMALLINT|VARCHAR|VARYING|INT8|SERIAL8|TEXT)\b',
Name.Builtin),
(r'[+*/<>=~!@#%^&|`?-]', Operator),
(r'[0-9]+', Number.Integer),
# TODO: Backslash escapes?
(r"'(''|[^'])*'", String.Single),
(r'"(""|[^"])*"', String.Symbol), # not a real string literal in ANSI SQL
(r'[a-zA-Z_][a-zA-Z0-9_]*', Name),
(r'[;:()\[\],\.]', Punctuation)
],
'multiline-comments': [
(r'/\*', Comment.Multiline, 'multiline-comments'),
(r'\*/', Comment.Multiline, '#pop'),
(r'[^/\*]+', Comment.Multiline),
(r'[/*]', Comment.Multiline)
]
}
class MySqlLexer(RegexLexer):
"""
Special lexer for MySQL.
"""
name = 'MySQL'
aliases = ['mysql']
mimetypes = ['text/x-mysql']
flags = re.IGNORECASE
tokens = {
'root': [
(r'\s+', Text),
(r'(#|--\s+).*?\n', Comment.Single),
(r'/\*', Comment.Multiline, 'multiline-comments'),
(r'[0-9]+', Number.Integer),
(r'[0-9]*\.[0-9]+(e[+-][0-9]+)', Number.Float),
# TODO: add backslash escapes
(r"'(''|[^'])*'", String.Single),
(r'"(""|[^"])*"', String.Double),
(r"`(``|[^`])*`", String.Symbol),
(r'[+*/<>=~!@#%^&|`?-]', Operator),
(r'\b(tinyint|smallint|mediumint|int|integer|bigint|date|'
r'datetime|time|bit|bool|tinytext|mediumtext|longtext|text|'
r'tinyblob|mediumblob|longblob|blob|float|double|double\s+'
r'precision|real|numeric|dec|decimal|timestamp|year|char|'
r'varchar|varbinary|varcharacter|enum|set)(\b\s*)(\()?',
bygroups(Keyword.Type, Text, Punctuation)),
(r'\b(add|all|alter|analyze|and|as|asc|asensitive|before|between|'
r'bigint|binary|blob|both|by|call|cascade|case|change|char|'
r'character|check|collate|column|condition|constraint|continue|'
r'convert|create|cross|current_date|current_time|'
r'current_timestamp|current_user|cursor|database|databases|'
r'day_hour|day_microsecond|day_minute|day_second|dec|decimal|'
r'declare|default|delayed|delete|desc|describe|deterministic|'
r'distinct|distinctrow|div|double|drop|dual|each|else|elseif|'
r'enclosed|escaped|exists|exit|explain|fetch|float|float4|float8'
r'|for|force|foreign|from|fulltext|grant|group|having|'
r'high_priority|hour_microsecond|hour_minute|hour_second|if|'
r'ignore|in|index|infile|inner|inout|insensitive|insert|int|'
r'int1|int2|int3|int4|int8|integer|interval|into|is|iterate|'
r'join|key|keys|kill|leading|leave|left|like|limit|lines|load|'
r'localtime|localtimestamp|lock|long|loop|low_priority|match|'
r'minute_microsecond|minute_second|mod|modifies|natural|'
r'no_write_to_binlog|not|numeric|on|optimize|option|optionally|'
r'or|order|out|outer|outfile|precision|primary|procedure|purge|'
r'raid0|read|reads|real|references|regexp|release|rename|repeat|'
r'replace|require|restrict|return|revoke|right|rlike|schema|'
r'schemas|second_microsecond|select|sensitive|separator|set|'
r'show|smallint|soname|spatial|specific|sql|sql_big_result|'
r'sql_calc_found_rows|sql_small_result|sqlexception|sqlstate|'
r'sqlwarning|ssl|starting|straight_join|table|terminated|then|'
r'to|trailing|trigger|undo|union|unique|unlock|unsigned|update|'
r'usage|use|using|utc_date|utc_time|utc_timestamp|values|'
r'varying|when|where|while|with|write|x509|xor|year_month|'
r'zerofill)\b', Keyword),
# TODO: this list is not complete
(r'\b(auto_increment|engine|charset|tables)\b', Keyword.Pseudo),
(r'(true|false|null)', Name.Constant),
(r'([a-zA-Z_][a-zA-Z0-9_]*)(\s*)(\()',
bygroups(Name.Function, Text, Punctuation)),
(r'[a-zA-Z_][a-zA-Z0-9_]*', Name),
(r'@[A-Za-z0-9]*[._]*[A-Za-z0-9]*', Name.Variable),
(r'[;:()\[\],\.]', Punctuation)
],
'multiline-comments': [
(r'/\*', Comment.Multiline, 'multiline-comments'),
(r'\*/', Comment.Multiline, '#pop'),
(r'[^/\*]+', Comment.Multiline),
(r'[/*]', Comment.Multiline)
]
}
class SqliteConsoleLexer(Lexer):
"""
Lexer for example sessions using sqlite3.
*New in Pygments 0.11.*
"""
name = 'sqlite3con'
aliases = ['sqlite3']
filenames = ['*.sqlite3-console']
mimetypes = ['text/x-sqlite3-console']
def get_tokens_unprocessed(self, data):
sql = SqlLexer(**self.options)
curcode = ''
insertions = []
for match in line_re.finditer(data):
line = match.group()
if line.startswith('sqlite> ') or line.startswith(' ...> '):
insertions.append((len(curcode),
[(0, Generic.Prompt, line[:8])]))
curcode += line[8:]
else:
if curcode:
for item in do_insertions(insertions,
sql.get_tokens_unprocessed(curcode)):
yield item
curcode = ''
insertions = []
if line.startswith('SQL error: '):
yield (match.start(), Generic.Traceback, line)
else:
yield (match.start(), Generic.Output, line)
if curcode:
for item in do_insertions(insertions,
sql.get_tokens_unprocessed(curcode)):
yield item

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff

View file

@ -0,0 +1,117 @@
# -*- coding: utf-8 -*-
"""
pygments.style
~~~~~~~~~~~~~~
Basic style object.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pygments.token import Token, STANDARD_TYPES
class StyleMeta(type):
def __new__(mcs, name, bases, dct):
obj = type.__new__(mcs, name, bases, dct)
for token in STANDARD_TYPES:
if token not in obj.styles:
obj.styles[token] = ''
def colorformat(text):
if text[0:1] == '#':
col = text[1:]
if len(col) == 6:
return col
elif len(col) == 3:
return col[0]*2 + col[1]*2 + col[2]*2
elif text == '':
return ''
assert False, "wrong color format %r" % text
_styles = obj._styles = {}
for ttype in obj.styles:
for token in ttype.split():
if token in _styles:
continue
ndef = _styles.get(token.parent, None)
styledefs = obj.styles.get(token, '').split()
if not ndef or token is None:
ndef = ['', 0, 0, 0, '', '', 0, 0, 0]
elif 'noinherit' in styledefs and token is not Token:
ndef = _styles[Token][:]
else:
ndef = ndef[:]
_styles[token] = ndef
for styledef in obj.styles.get(token, '').split():
if styledef == 'noinherit':
pass
elif styledef == 'bold':
ndef[1] = 1
elif styledef == 'nobold':
ndef[1] = 0
elif styledef == 'italic':
ndef[2] = 1
elif styledef == 'noitalic':
ndef[2] = 0
elif styledef == 'underline':
ndef[3] = 1
elif styledef == 'nounderline':
ndef[3] = 0
elif styledef[:3] == 'bg:':
ndef[4] = colorformat(styledef[3:])
elif styledef[:7] == 'border:':
ndef[5] = colorformat(styledef[7:])
elif styledef == 'roman':
ndef[6] = 1
elif styledef == 'sans':
ndef[7] = 1
elif styledef == 'mono':
ndef[8] = 1
else:
ndef[0] = colorformat(styledef)
return obj
def style_for_token(cls, token):
t = cls._styles[token]
return {
'color': t[0] or None,
'bold': bool(t[1]),
'italic': bool(t[2]),
'underline': bool(t[3]),
'bgcolor': t[4] or None,
'border': t[5] or None,
'roman': bool(t[6]) or None,
'sans': bool(t[7]) or None,
'mono': bool(t[8]) or None,
}
def list_styles(cls):
return list(cls)
def styles_token(cls, ttype):
return ttype in cls._styles
def __iter__(cls):
for token in cls._styles:
yield token, cls.style_for_token(token)
def __len__(cls):
return len(cls._styles)
class Style(object):
__metaclass__ = StyleMeta
#: overall background color (``None`` means transparent)
background_color = '#ffffff'
#: highlight background color
highlight_color = '#ffffcc'
#: Style definitions for individual token types.
styles = {}

File diff suppressed because one or more lines are too long

View file

@ -0,0 +1,277 @@
# -*- coding: utf-8 -*-
"""
pygments.util
~~~~~~~~~~~~~
Utility functions.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
import sys
import codecs
split_path_re = re.compile(r'[/\\ ]')
doctype_lookup_re = re.compile(r'''(?smx)
(<\?.*?\?>)?\s*
<!DOCTYPE\s+(
[a-zA-Z_][a-zA-Z0-9]*\s+
[a-zA-Z_][a-zA-Z0-9]*\s+
"[^"]*")
[^>]*>
''')
tag_re = re.compile(r'<(.+?)(\s.*?)?>.*?</.+?>(?uism)')
class ClassNotFound(ValueError):
"""
If one of the get_*_by_* functions didn't find a matching class.
"""
class OptionError(Exception):
pass
def get_choice_opt(options, optname, allowed, default=None, normcase=False):
string = options.get(optname, default)
if normcase:
string = string.lower()
if string not in allowed:
raise OptionError('Value for option %s must be one of %s' %
(optname, ', '.join(map(str, allowed))))
return string
def get_bool_opt(options, optname, default=None):
string = options.get(optname, default)
if isinstance(string, bool):
return string
elif isinstance(string, int):
return bool(string)
elif not isinstance(string, basestring):
raise OptionError('Invalid type %r for option %s; use '
'1/0, yes/no, true/false, on/off' % (
string, optname))
elif string.lower() in ('1', 'yes', 'true', 'on'):
return True
elif string.lower() in ('0', 'no', 'false', 'off'):
return False
else:
raise OptionError('Invalid value %r for option %s; use '
'1/0, yes/no, true/false, on/off' % (
string, optname))
def get_int_opt(options, optname, default=None):
string = options.get(optname, default)
try:
return int(string)
except TypeError:
raise OptionError('Invalid type %r for option %s; you '
'must give an integer value' % (
string, optname))
except ValueError:
raise OptionError('Invalid value %r for option %s; you '
'must give an integer value' % (
string, optname))
def get_list_opt(options, optname, default=None):
val = options.get(optname, default)
if isinstance(val, basestring):
return val.split()
elif isinstance(val, (list, tuple)):
return list(val)
else:
raise OptionError('Invalid type %r for option %s; you '
'must give a list value' % (
val, optname))
def docstring_headline(obj):
if not obj.__doc__:
return ''
res = []
for line in obj.__doc__.strip().splitlines():
if line.strip():
res.append(" " + line.strip())
else:
break
return ''.join(res).lstrip()
def make_analysator(f):
"""
Return a static text analysation function that
returns float values.
"""
def text_analyse(text):
try:
rv = f(text)
except Exception:
return 0.0
if not rv:
return 0.0
try:
return min(1.0, max(0.0, float(rv)))
except (ValueError, TypeError):
return 0.0
text_analyse.__doc__ = f.__doc__
return staticmethod(text_analyse)
def shebang_matches(text, regex):
"""
Check if the given regular expression matches the last part of the
shebang if one exists.
>>> from pygments.util import shebang_matches
>>> shebang_matches('#!/usr/bin/env python', r'python(2\.\d)?')
True
>>> shebang_matches('#!/usr/bin/python2.4', r'python(2\.\d)?')
True
>>> shebang_matches('#!/usr/bin/python-ruby', r'python(2\.\d)?')
False
>>> shebang_matches('#!/usr/bin/python/ruby', r'python(2\.\d)?')
False
>>> shebang_matches('#!/usr/bin/startsomethingwith python',
... r'python(2\.\d)?')
True
It also checks for common windows executable file extensions::
>>> shebang_matches('#!C:\\Python2.4\\Python.exe', r'python(2\.\d)?')
True
Parameters (``'-f'`` or ``'--foo'`` are ignored so ``'perl'`` does
the same as ``'perl -e'``)
Note that this method automatically searches the whole string (eg:
the regular expression is wrapped in ``'^$'``)
"""
index = text.find('\n')
if index >= 0:
first_line = text[:index].lower()
else:
first_line = text.lower()
if first_line.startswith('#!'):
try:
found = [x for x in split_path_re.split(first_line[2:].strip())
if x and not x.startswith('-')][-1]
except IndexError:
return False
regex = re.compile('^%s(\.(exe|cmd|bat|bin))?$' % regex, re.IGNORECASE)
if regex.search(found) is not None:
return True
return False
def doctype_matches(text, regex):
"""
Check if the doctype matches a regular expression (if present).
Note that this method only checks the first part of a DOCTYPE.
eg: 'html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"'
"""
m = doctype_lookup_re.match(text)
if m is None:
return False
doctype = m.group(2)
return re.compile(regex).match(doctype.strip()) is not None
def html_doctype_matches(text):
"""
Check if the file looks like it has a html doctype.
"""
return doctype_matches(text, r'html\s+PUBLIC\s+"-//W3C//DTD X?HTML.*')
_looks_like_xml_cache = {}
def looks_like_xml(text):
"""
Check if a doctype exists or if we have some tags.
"""
key = hash(text)
try:
return _looks_like_xml_cache[key]
except KeyError:
m = doctype_lookup_re.match(text)
if m is not None:
return True
rv = tag_re.search(text[:1000]) is not None
_looks_like_xml_cache[key] = rv
return rv
# Python narrow build compatibility
def _surrogatepair(c):
return (0xd7c0 + (c >> 10), (0xdc00 + (c & 0x3ff)))
def unirange(a, b):
"""
Returns a regular expression string to match the given non-BMP range.
"""
if b < a:
raise ValueError("Bad character range")
if a < 0x10000 or b < 0x10000:
raise ValueError("unirange is only defined for non-BMP ranges")
if sys.maxunicode > 0xffff:
# wide build
return u'[%s-%s]' % (unichr(a), unichr(b))
else:
# narrow build stores surrogates, and the 're' module handles them
# (incorrectly) as characters. Since there is still ordering among
# these characters, expand the range to one that it understands. Some
# background in http://bugs.python.org/issue3665 and
# http://bugs.python.org/issue12749
#
# Additionally, the lower constants are using unichr rather than
# literals because jython [which uses the wide path] can't load this
# file if they are literals.
ah, al = _surrogatepair(a)
bh, bl = _surrogatepair(b)
if ah == bh:
return u'(?:%s[%s-%s])' % (unichr(ah), unichr(al), unichr(bl))
else:
buf = []
buf.append(u'%s[%s-%s]' %
(unichr(ah), unichr(al),
ah == bh and unichr(bl) or unichr(0xdfff)))
if ah - bh > 1:
buf.append(u'[%s-%s][%s-%s]' %
unichr(ah+1), unichr(bh-1), unichr(0xdc00), unichr(0xdfff))
if ah != bh:
buf.append(u'%s[%s-%s]' %
(unichr(bh), unichr(0xdc00), unichr(bl)))
return u'(?:' + u'|'.join(buf) + u')'
# Python 2/3 compatibility
if sys.version_info < (3,0):
b = bytes = str
u_prefix = 'u'
import StringIO, cStringIO
BytesIO = cStringIO.StringIO
StringIO = StringIO.StringIO
uni_open = codecs.open
else:
import builtins
bytes = builtins.bytes
u_prefix = ''
def b(s):
if isinstance(s, str):
return bytes(map(ord, s))
elif isinstance(s, bytes):
return s
else:
raise TypeError("Invalid argument %r for b()" % (s,))
import io
BytesIO = io.BytesIO
StringIO = io.StringIO
uni_open = builtins.open

View file

@ -0,0 +1,74 @@
# -*- coding: utf-8 -*-
"""
pygments.console
~~~~~~~~~~~~~~~~
Format colored console output.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
esc = "\x1b["
codes = {}
codes[""] = ""
codes["reset"] = esc + "39;49;00m"
codes["bold"] = esc + "01m"
codes["faint"] = esc + "02m"
codes["standout"] = esc + "03m"
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"]
x = 30
for d, l in zip(dark_colors, light_colors):
codes[d] = esc + "%im" % x
codes[l] = esc + "%i;01m" % x
x += 1
del d, l, x
codes["darkteal"] = codes["turquoise"]
codes["darkyellow"] = codes["brown"]
codes["fuscia"] = codes["fuchsia"]
codes["white"] = codes["bold"]
def reset_color():
return codes["reset"]
def colorize(color_key, text):
return codes[color_key] + text + codes["reset"]
def ansiformat(attr, text):
"""
Format ``text`` with a color and/or some attributes::
color normal color
*color* bold color
_color_ underlined color
+color+ blinking color
"""
result = []
if attr[:1] == attr[-1:] == '+':
result.append(codes['blink'])
attr = attr[1:-1]
if attr[:1] == attr[-1:] == '*':
result.append(codes['bold'])
attr = attr[1:-1]
if attr[:1] == attr[-1:] == '_':
result.append(codes['underline'])
attr = attr[1:-1]
result.append(codes[attr])
result.append(text)
result.append(codes['reset'])
return ''.join(result)

View file

@ -0,0 +1,74 @@
# -*- coding: utf-8 -*-
"""
pygments.filter
~~~~~~~~~~~~~~~
Module that implements the default filter.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
def apply_filters(stream, filters, lexer=None):
"""
Use this method to apply an iterable of filters to
a stream. If lexer is given it's forwarded to the
filter, otherwise the filter receives `None`.
"""
def _apply(filter_, stream):
for token in filter_.filter(lexer, stream):
yield token
for filter_ in filters:
stream = _apply(filter_, stream)
return stream
def simplefilter(f):
"""
Decorator that converts a function into a filter::
@simplefilter
def lowercase(lexer, stream, options):
for ttype, value in stream:
yield ttype, value.lower()
"""
return type(f.__name__, (FunctionFilter,), {
'function': f,
'__module__': getattr(f, '__module__'),
'__doc__': f.__doc__
})
class Filter(object):
"""
Default filter. Subclass this class or use the `simplefilter`
decorator to create own filters.
"""
def __init__(self, **options):
self.options = options
def filter(self, lexer, stream):
raise NotImplementedError()
class FunctionFilter(Filter):
"""
Abstract class used by `simplefilter` to create simple
function filters on the fly. The `simplefilter` decorator
automatically creates subclasses of this class for
functions passed to it.
"""
function = None
def __init__(self, **options):
if not hasattr(self, 'function'):
raise TypeError('%r used without bound function' %
self.__class__.__name__)
Filter.__init__(self, **options)
def filter(self, lexer, stream):
# pylint: disable-msg=E1102
for ttype, value in self.function(lexer, stream, self.options):
yield ttype, value

View file

@ -0,0 +1,68 @@
# -*- coding: utf-8 -*-
"""
pygments.formatters
~~~~~~~~~~~~~~~~~~~
Pygments formatters.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import os.path
import fnmatch
from pygments.formatters._mapping import FORMATTERS
from pygments.plugin import find_plugin_formatters
from pygments.util import ClassNotFound
ns = globals()
for fcls in FORMATTERS:
ns[fcls.__name__] = fcls
del fcls
__all__ = ['get_formatter_by_name', 'get_formatter_for_filename',
'get_all_formatters'] + [cls.__name__ for cls in FORMATTERS]
_formatter_alias_cache = {}
_formatter_filename_cache = []
def _init_formatter_cache():
if _formatter_alias_cache:
return
for cls in get_all_formatters():
for alias in cls.aliases:
_formatter_alias_cache[alias] = cls
for fn in cls.filenames:
_formatter_filename_cache.append((fn, cls))
def find_formatter_class(name):
_init_formatter_cache()
cls = _formatter_alias_cache.get(name, None)
return cls
def get_formatter_by_name(name, **options):
_init_formatter_cache()
cls = _formatter_alias_cache.get(name, None)
if not cls:
raise ClassNotFound("No formatter found for name %r" % name)
return cls(**options)
def get_formatter_for_filename(fn, **options):
_init_formatter_cache()
fn = os.path.basename(fn)
for pattern, cls in _formatter_filename_cache:
if fnmatch.fnmatch(fn, pattern):
return cls(**options)
raise ClassNotFound("No formatter found for file name %r" % fn)
def get_all_formatters():
"""Return a generator for all formatters."""
for formatter in FORMATTERS:
yield formatter
for _, formatter in find_plugin_formatters():
yield formatter

View file

@ -0,0 +1,109 @@
# -*- coding: utf-8 -*-
"""
pygments.formatters.bbcode
~~~~~~~~~~~~~~~~~~~~~~~~~~
BBcode formatter.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pygments.formatter import Formatter
from pygments.util import get_bool_opt
__all__ = ['BBCodeFormatter']
class BBCodeFormatter(Formatter):
"""
Format tokens with BBcodes. These formatting codes are used by many
bulletin boards, so you can highlight your sourcecode with pygments before
posting it there.
This formatter has no support for background colors and borders, as there
are no common BBcode tags for that.
Some board systems (e.g. phpBB) don't support colors in their [code] tag,
so you can't use the highlighting together with that tag.
Text in a [code] tag usually is shown with a monospace font (which this
formatter can do with the ``monofont`` option) and no spaces (which you
need for indentation) are removed.
Additional options accepted:
`style`
The style to use, can be a string or a Style subclass (default:
``'default'``).
`codetag`
If set to true, put the output into ``[code]`` tags (default:
``false``)
`monofont`
If set to true, add a tag to show the code with a monospace font
(default: ``false``).
"""
name = 'BBCode'
aliases = ['bbcode', 'bb']
filenames = []
def __init__(self, **options):
Formatter.__init__(self, **options)
self._code = get_bool_opt(options, 'codetag', False)
self._mono = get_bool_opt(options, 'monofont', False)
self.styles = {}
self._make_styles()
def _make_styles(self):
for ttype, ndef in self.style:
start = end = ''
if ndef['color']:
start += '[color=#%s]' % ndef['color']
end = '[/color]' + end
if ndef['bold']:
start += '[b]'
end = '[/b]' + end
if ndef['italic']:
start += '[i]'
end = '[/i]' + end
if ndef['underline']:
start += '[u]'
end = '[/u]' + end
# there are no common BBcodes for background-color and border
self.styles[ttype] = start, end
def format_unencoded(self, tokensource, outfile):
if self._code:
outfile.write('[code]')
if self._mono:
outfile.write('[font=monospace]')
lastval = ''
lasttype = None
for ttype, value in tokensource:
while ttype not in self.styles:
ttype = ttype.parent
if ttype == lasttype:
lastval += value
else:
if lastval:
start, end = self.styles[lasttype]
outfile.write(''.join((start, lastval, end)))
lastval = value
lasttype = ttype
if lastval:
start, end = self.styles[lasttype]
outfile.write(''.join((start, lastval, end)))
if self._mono:
outfile.write('[/font]')
if self._code:
outfile.write('[/code]')
if self._code or self._mono:
outfile.write('\n')

View file

@ -0,0 +1,115 @@
# -*- coding: utf-8 -*-
"""
pygments.formatters.other
~~~~~~~~~~~~~~~~~~~~~~~~~
Other formatters: NullFormatter, RawTokenFormatter.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pygments.formatter import Formatter
from pygments.util import OptionError, get_choice_opt, b
from pygments.token import Token
from pygments.console import colorize
__all__ = ['NullFormatter', 'RawTokenFormatter']
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
`lexer list <lexers.txt>`_.
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'``.
*New in Pygments 0.11.*
"""
name = 'Raw tokens'
aliases = ['raw', 'tokens']
filenames = ['*.raw']
unicodeoutput = False
def __init__(self, **options):
Formatter.__init__(self, **options)
if self.encoding:
raise OptionError('the raw formatter does not support the '
'encoding option')
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()

View file

@ -0,0 +1,136 @@
# -*- coding: utf-8 -*-
"""
pygments.formatters.rtf
~~~~~~~~~~~~~~~~~~~~~~~
A formatter that generates RTF files.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pygments.formatter import Formatter
__all__ = ['RtfFormatter']
class RtfFormatter(Formatter):
"""
Format tokens as RTF markup. This formatter automatically outputs full RTF
documents with color information and other useful stuff. Perfect for Copy and
Paste into Microsoft® Word® documents.
*New in Pygments 0.6.*
Additional options accepted:
`style`
The style to use, can be a string or a Style subclass (default:
``'default'``).
`fontface`
The used font famliy, for example ``Bitstream Vera Sans``. Defaults to
some generic font which is supposed to have fixed width.
"""
name = 'RTF'
aliases = ['rtf']
filenames = ['*.rtf']
unicodeoutput = False
def __init__(self, **options):
"""
Additional options accepted:
``fontface``
Name of the font used. Could for example be ``'Courier New'``
to further specify the default which is ``'\fmodern'``. The RTF
specification claims that ``\fmodern`` are "Fixed-pitch serif
and sans serif fonts". Hope every RTF implementation thinks
the same about modern...
"""
Formatter.__init__(self, **options)
self.fontface = options.get('fontface') or ''
def _escape(self, text):
return text.replace('\\', '\\\\') \
.replace('{', '\\{') \
.replace('}', '\\}')
def _escape_text(self, text):
# empty strings, should give a small performance improvment
if not text:
return ''
# escape text
text = self._escape(text)
if self.encoding in ('utf-8', 'utf-16', 'utf-32'):
encoding = 'iso-8859-15'
else:
encoding = self.encoding or 'iso-8859-15'
buf = []
for c in text:
if ord(c) > 128:
ansic = c.encode(encoding, 'ignore') or '?'
if ord(ansic) > 128:
ansic = '\\\'%x' % ord(ansic)
else:
ansic = c
buf.append(r'\ud{\u%d%s}' % (ord(c), ansic))
else:
buf.append(str(c))
return ''.join(buf).replace('\n', '\\par\n')
def format_unencoded(self, tokensource, outfile):
# rtf 1.8 header
outfile.write(r'{\rtf1\ansi\deff0'
r'{\fonttbl{\f0\fmodern\fprq1\fcharset0%s;}}'
r'{\colortbl;' % (self.fontface and
' ' + self._escape(self.fontface) or
''))
# convert colors and save them in a mapping to access them later.
color_mapping = {}
offset = 1
for _, style in self.style:
for color in style['color'], style['bgcolor'], style['border']:
if color and color not in color_mapping:
color_mapping[color] = offset
outfile.write(r'\red%d\green%d\blue%d;' % (
int(color[0:2], 16),
int(color[2:4], 16),
int(color[4:6], 16)
))
offset += 1
outfile.write(r'}\f0')
# highlight stream
for ttype, value in tokensource:
while not self.style.styles_token(ttype) and ttype.parent:
ttype = ttype.parent
style = self.style.style_for_token(ttype)
buf = []
if style['bgcolor']:
buf.append(r'\cb%d' % color_mapping[style['bgcolor']])
if style['color']:
buf.append(r'\cf%d' % color_mapping[style['color']])
if style['bold']:
buf.append(r'\b')
if style['italic']:
buf.append(r'\i')
if style['underline']:
buf.append(r'\ul')
if style['border']:
buf.append(r'\chbrdr\chcfpat%d' %
color_mapping[style['border']])
start = ''.join(buf)
if start:
outfile.write('{%s ' % start)
outfile.write(self._escape_text(value))
if start:
outfile.write('}')
outfile.write('}')

View file

@ -0,0 +1,154 @@
# -*- coding: utf-8 -*-
"""
pygments.formatters.svg
~~~~~~~~~~~~~~~~~~~~~~~
Formatter for SVG output.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pygments.formatter import Formatter
from pygments.util import get_bool_opt, get_int_opt
__all__ = ['SvgFormatter']
def escape_html(text):
"""Escape &, <, > as well as single and double quotes for HTML."""
return text.replace('&', '&amp;'). \
replace('<', '&lt;'). \
replace('>', '&gt;'). \
replace('"', '&quot;'). \
replace("'", '&#39;')
class2style = {}
class SvgFormatter(Formatter):
"""
Format tokens as an SVG graphics file. This formatter is still experimental.
Each line of code is a ``<text>`` element with explicit ``x`` and ``y``
coordinates containing ``<tspan>`` elements with the individual token styles.
By default, this formatter outputs a full SVG document including doctype
declaration and the ``<svg>`` root element.
*New in Pygments 0.9.*
Additional options accepted:
`nowrap`
Don't wrap the SVG ``<text>`` elements in ``<svg><g>`` elements and
don't add a XML declaration and a doctype. If true, the `fontfamily`
and `fontsize` options are ignored. Defaults to ``False``.
`fontfamily`
The value to give the wrapping ``<g>`` element's ``font-family``
attribute, defaults to ``"monospace"``.
`fontsize`
The value to give the wrapping ``<g>`` element's ``font-size``
attribute, defaults to ``"14px"``.
`xoffset`
Starting offset in X direction, defaults to ``0``.
`yoffset`
Starting offset in Y direction, defaults to the font size if it is given
in pixels, or ``20`` else. (This is necessary since text coordinates
refer to the text baseline, not the top edge.)
`ystep`
Offset to add to the Y coordinate for each subsequent line. This should
roughly be the text size plus 5. It defaults to that value if the text
size is given in pixels, or ``25`` else.
`spacehack`
Convert spaces in the source to ``&#160;``, which are non-breaking
spaces. SVG provides the ``xml:space`` attribute to control how
whitespace inside tags is handled, in theory, the ``preserve`` value
could be used to keep all whitespace as-is. However, many current SVG
viewers don't obey that rule, so this option is provided as a workaround
and defaults to ``True``.
"""
name = 'SVG'
aliases = ['svg']
filenames = ['*.svg']
def __init__(self, **options):
# XXX outencoding
Formatter.__init__(self, **options)
self.nowrap = get_bool_opt(options, 'nowrap', False)
self.fontfamily = options.get('fontfamily', 'monospace')
self.fontsize = options.get('fontsize', '14px')
self.xoffset = get_int_opt(options, 'xoffset', 0)
fs = self.fontsize.strip()
if fs.endswith('px'): fs = fs[:-2].strip()
try:
int_fs = int(fs)
except:
int_fs = 20
self.yoffset = get_int_opt(options, 'yoffset', int_fs)
self.ystep = get_int_opt(options, 'ystep', int_fs + 5)
self.spacehack = get_bool_opt(options, 'spacehack', True)
self._stylecache = {}
def format_unencoded(self, tokensource, outfile):
"""
Format ``tokensource``, an iterable of ``(tokentype, tokenstring)``
tuples and write it into ``outfile``.
For our implementation we put all lines in their own 'line group'.
"""
x = self.xoffset
y = self.yoffset
if not self.nowrap:
if self.encoding:
outfile.write('<?xml version="1.0" encoding="%s"?>\n' %
self.encoding)
else:
outfile.write('<?xml version="1.0"?>\n')
outfile.write('<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.0//EN" '
'"http://www.w3.org/TR/2001/REC-SVG-20010904/DTD/'
'svg10.dtd">\n')
outfile.write('<svg xmlns="http://www.w3.org/2000/svg">\n')
outfile.write('<g font-family="%s" font-size="%s">\n' %
(self.fontfamily, self.fontsize))
outfile.write('<text x="%s" y="%s" xml:space="preserve">' % (x, y))
for ttype, value in tokensource:
style = self._get_style(ttype)
tspan = style and '<tspan' + style + '>' or ''
tspanend = tspan and '</tspan>' or ''
value = escape_html(value)
if self.spacehack:
value = value.expandtabs().replace(' ', '&#160;')
parts = value.split('\n')
for part in parts[:-1]:
outfile.write(tspan + part + tspanend)
y += self.ystep
outfile.write('</text>\n<text x="%s" y="%s" '
'xml:space="preserve">' % (x, y))
outfile.write(tspan + parts[-1] + tspanend)
outfile.write('</text>')
if not self.nowrap:
outfile.write('</g></svg>\n')
def _get_style(self, tokentype):
if tokentype in self._stylecache:
return self._stylecache[tokentype]
otokentype = tokentype
while not self.style.styles_token(tokentype):
tokentype = tokentype.parent
value = self.style.style_for_token(tokentype)
result = ''
if value['color']:
result = ' fill="#' + value['color'] + '"'
if value['bold']:
result += ' font-weight="bold"'
if value['italic']:
result += ' font-style="italic"'
self._stylecache[otokentype] = result
return result

View file

@ -0,0 +1,112 @@
# -*- coding: utf-8 -*-
"""
pygments.formatters.terminal
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Formatter for terminal output with ANSI sequences.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import sys
from pygments.formatter import Formatter
from pygments.token import Keyword, Name, Comment, String, Error, \
Number, Operator, Generic, Token, Whitespace
from pygments.console import ansiformat
from pygments.util import get_choice_opt
__all__ = ['TerminalFormatter']
#: Map token types to a tuple of color values for light and dark
#: backgrounds.
TERMINAL_COLORS = {
Token: ('', ''),
Whitespace: ('lightgray', 'darkgray'),
Comment: ('lightgray', 'darkgray'),
Comment.Preproc: ('teal', 'turquoise'),
Keyword: ('darkblue', 'blue'),
Keyword.Type: ('teal', 'turquoise'),
Operator.Word: ('purple', 'fuchsia'),
Name.Builtin: ('teal', 'turquoise'),
Name.Function: ('darkgreen', 'green'),
Name.Namespace: ('_teal_', '_turquoise_'),
Name.Class: ('_darkgreen_', '_green_'),
Name.Exception: ('teal', 'turquoise'),
Name.Decorator: ('darkgray', 'lightgray'),
Name.Variable: ('darkred', 'red'),
Name.Constant: ('darkred', 'red'),
Name.Attribute: ('teal', 'turquoise'),
Name.Tag: ('blue', 'blue'),
String: ('brown', 'brown'),
Number: ('darkblue', 'blue'),
Generic.Deleted: ('red', 'red'),
Generic.Inserted: ('darkgreen', 'green'),
Generic.Heading: ('**', '**'),
Generic.Subheading: ('*purple*', '*fuchsia*'),
Generic.Error: ('red', 'red'),
Error: ('_red_', '_red_'),
}
class TerminalFormatter(Formatter):
r"""
Format tokens with ANSI color sequences, for output in a text console.
Color sequences are terminated at newlines, so that paging the output
works correctly.
The `get_style_defs()` method doesn't do anything special since there is
no support for common styles.
Options accepted:
`bg`
Set to ``"light"`` or ``"dark"`` depending on the terminal's background
(default: ``"light"``).
`colorscheme`
A dictionary mapping token types to (lightbg, darkbg) color names or
``None`` (default: ``None`` = use builtin colorscheme).
"""
name = 'Terminal'
aliases = ['terminal', 'console']
filenames = []
def __init__(self, **options):
Formatter.__init__(self, **options)
self.darkbg = get_choice_opt(options, 'bg',
['light', 'dark'], 'light') == 'dark'
self.colorscheme = options.get('colorscheme', None) or TERMINAL_COLORS
def format(self, tokensource, outfile):
# hack: if the output is a terminal and has an encoding set,
# use that to avoid unicode encode problems
if not self.encoding and hasattr(outfile, "encoding") and \
hasattr(outfile, "isatty") and outfile.isatty() and \
sys.version_info < (3,):
self.encoding = outfile.encoding
return Formatter.format(self, tokensource, outfile)
def format_unencoded(self, tokensource, outfile):
for ttype, value in tokensource:
color = self.colorscheme.get(ttype)
while color is None:
ttype = ttype[:-1]
color = self.colorscheme.get(ttype)
if color:
color = color[self.darkbg]
spl = value.split('\n')
for line in spl[:-1]:
if line:
outfile.write(ansiformat(color, line))
outfile.write('\n')
if spl[-1]:
outfile.write(ansiformat(color, spl[-1]))
else:
outfile.write(value)

View file

@ -0,0 +1,222 @@
# -*- coding: utf-8 -*-
"""
pygments.formatters.terminal256
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Formatter for 256-color terminal output with ANSI sequences.
RGB-to-XTERM color conversion routines adapted from xterm256-conv
tool (http://frexx.de/xterm-256-notes/data/xterm256-conv2.tar.bz2)
by Wolfgang Frisch.
Formatter version 1.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
# TODO:
# - Options to map style's bold/underline/italic/border attributes
# to some ANSI attrbutes (something like 'italic=underline')
# - An option to output "style RGB to xterm RGB/index" conversion table
# - An option to indicate that we are running in "reverse background"
# xterm. This means that default colors are white-on-black, not
# black-on-while, so colors like "white background" need to be converted
# to "white background, black foreground", etc...
import sys
from pygments.formatter import Formatter
__all__ = ['Terminal256Formatter']
class EscapeSequence:
def __init__(self, fg=None, bg=None, bold=False, underline=False):
self.fg = fg
self.bg = bg
self.bold = bold
self.underline = underline
def escape(self, attrs):
if len(attrs):
return "\x1b[" + ";".join(attrs) + "m"
return ""
def color_string(self):
attrs = []
if self.fg is not None:
attrs.extend(("38", "5", "%i" % self.fg))
if self.bg is not None:
attrs.extend(("48", "5", "%i" % self.bg))
if self.bold:
attrs.append("01")
if self.underline:
attrs.append("04")
return self.escape(attrs)
def reset_string(self):
attrs = []
if self.fg is not None:
attrs.append("39")
if self.bg is not None:
attrs.append("49")
if self.bold or self.underline:
attrs.append("00")
return self.escape(attrs)
class Terminal256Formatter(Formatter):
r"""
Format tokens with ANSI color sequences, for output in a 256-color
terminal or console. Like in `TerminalFormatter` color sequences
are terminated at newlines, so that paging the output works correctly.
The formatter takes colors from a style defined by the `style` option
and converts them to nearest ANSI 256-color escape sequences. Bold and
underline attributes from the style are preserved (and displayed).
*New in Pygments 0.9.*
Options accepted:
`style`
The style to use, can be a string or a Style subclass (default:
``'default'``).
"""
name = 'Terminal256'
aliases = ['terminal256', 'console256', '256']
filenames = []
def __init__(self, **options):
Formatter.__init__(self, **options)
self.xterm_colors = []
self.best_match = {}
self.style_string = {}
self.usebold = 'nobold' not in options
self.useunderline = 'nounderline' not in options
self._build_color_table() # build an RGB-to-256 color conversion table
self._setup_styles() # convert selected style's colors to term. colors
def _build_color_table(self):
# colors 0..15: 16 basic colors
self.xterm_colors.append((0x00, 0x00, 0x00)) # 0
self.xterm_colors.append((0xcd, 0x00, 0x00)) # 1
self.xterm_colors.append((0x00, 0xcd, 0x00)) # 2
self.xterm_colors.append((0xcd, 0xcd, 0x00)) # 3
self.xterm_colors.append((0x00, 0x00, 0xee)) # 4
self.xterm_colors.append((0xcd, 0x00, 0xcd)) # 5
self.xterm_colors.append((0x00, 0xcd, 0xcd)) # 6
self.xterm_colors.append((0xe5, 0xe5, 0xe5)) # 7
self.xterm_colors.append((0x7f, 0x7f, 0x7f)) # 8
self.xterm_colors.append((0xff, 0x00, 0x00)) # 9
self.xterm_colors.append((0x00, 0xff, 0x00)) # 10
self.xterm_colors.append((0xff, 0xff, 0x00)) # 11
self.xterm_colors.append((0x5c, 0x5c, 0xff)) # 12
self.xterm_colors.append((0xff, 0x00, 0xff)) # 13
self.xterm_colors.append((0x00, 0xff, 0xff)) # 14
self.xterm_colors.append((0xff, 0xff, 0xff)) # 15
# colors 16..232: the 6x6x6 color cube
valuerange = (0x00, 0x5f, 0x87, 0xaf, 0xd7, 0xff)
for i in range(217):
r = valuerange[(i // 36) % 6]
g = valuerange[(i // 6) % 6]
b = valuerange[i % 6]
self.xterm_colors.append((r, g, b))
# colors 233..253: grayscale
for i in range(1, 22):
v = 8 + i * 10
self.xterm_colors.append((v, v, v))
def _closest_color(self, r, g, b):
distance = 257*257*3 # "infinity" (>distance from #000000 to #ffffff)
match = 0
for i in range(0, 254):
values = self.xterm_colors[i]
rd = r - values[0]
gd = g - values[1]
bd = b - values[2]
d = rd*rd + gd*gd + bd*bd
if d < distance:
match = i
distance = d
return match
def _color_index(self, color):
index = self.best_match.get(color, None)
if index is None:
try:
rgb = int(str(color), 16)
except ValueError:
rgb = 0
r = (rgb >> 16) & 0xff
g = (rgb >> 8) & 0xff
b = rgb & 0xff
index = self._closest_color(r, g, b)
self.best_match[color] = index
return index
def _setup_styles(self):
for ttype, ndef in self.style:
escape = EscapeSequence()
if ndef['color']:
escape.fg = self._color_index(ndef['color'])
if ndef['bgcolor']:
escape.bg = self._color_index(ndef['bgcolor'])
if self.usebold and ndef['bold']:
escape.bold = True
if self.useunderline and ndef['underline']:
escape.underline = True
self.style_string[str(ttype)] = (escape.color_string(),
escape.reset_string())
def format(self, tokensource, outfile):
# hack: if the output is a terminal and has an encoding set,
# use that to avoid unicode encode problems
if not self.encoding and hasattr(outfile, "encoding") and \
hasattr(outfile, "isatty") and outfile.isatty() and \
sys.version_info < (3,):
self.encoding = outfile.encoding
return Formatter.format(self, tokensource, outfile)
def format_unencoded(self, tokensource, outfile):
for ttype, value in tokensource:
not_found = True
while ttype and not_found:
try:
#outfile.write( "<" + str(ttype) + ">" )
on, off = self.style_string[str(ttype)]
# Like TerminalFormatter, add "reset colors" escape sequence
# on newline.
spl = value.split('\n')
for line in spl[:-1]:
if line:
outfile.write(on + line + off)
outfile.write('\n')
if spl[-1]:
outfile.write(on + spl[-1] + off)
not_found = False
#outfile.write( '#' + str(ttype) + '#' )
except KeyError:
#ottype = ttype
ttype = ttype[:-1]
#outfile.write( '!' + str(ottype) + '->' + str(ttype) + '!' )
if not_found:
outfile.write(value)

File diff suppressed because it is too large Load diff

View file

@ -0,0 +1,232 @@
# -*- coding: utf-8 -*-
"""
pygments.lexers._clbuiltins
~~~~~~~~~~~~~~~~~~~~~~~~~~~
ANSI Common Lisp builtins.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
BUILTIN_FUNCTIONS = [ # 638 functions
'<', '<=', '=', '>', '>=', '-', '/', '/=', '*', '+', '1-', '1+',
'abort', 'abs', 'acons', 'acos', 'acosh', 'add-method', 'adjoin',
'adjustable-array-p', 'adjust-array', 'allocate-instance',
'alpha-char-p', 'alphanumericp', 'append', 'apply', 'apropos',
'apropos-list', 'aref', 'arithmetic-error-operands',
'arithmetic-error-operation', 'array-dimension', 'array-dimensions',
'array-displacement', 'array-element-type', 'array-has-fill-pointer-p',
'array-in-bounds-p', 'arrayp', 'array-rank', 'array-row-major-index',
'array-total-size', 'ash', 'asin', 'asinh', 'assoc', 'assoc-if',
'assoc-if-not', 'atan', 'atanh', 'atom', 'bit', 'bit-and', 'bit-andc1',
'bit-andc2', 'bit-eqv', 'bit-ior', 'bit-nand', 'bit-nor', 'bit-not',
'bit-orc1', 'bit-orc2', 'bit-vector-p', 'bit-xor', 'boole',
'both-case-p', 'boundp', 'break', 'broadcast-stream-streams',
'butlast', 'byte', 'byte-position', 'byte-size', 'caaaar', 'caaadr',
'caaar', 'caadar', 'caaddr', 'caadr', 'caar', 'cadaar', 'cadadr',
'cadar', 'caddar', 'cadddr', 'caddr', 'cadr', 'call-next-method', 'car',
'cdaaar', 'cdaadr', 'cdaar', 'cdadar', 'cdaddr', 'cdadr', 'cdar',
'cddaar', 'cddadr', 'cddar', 'cdddar', 'cddddr', 'cdddr', 'cddr', 'cdr',
'ceiling', 'cell-error-name', 'cerror', 'change-class', 'char', 'char<',
'char<=', 'char=', 'char>', 'char>=', 'char/=', 'character',
'characterp', 'char-code', 'char-downcase', 'char-equal',
'char-greaterp', 'char-int', 'char-lessp', 'char-name',
'char-not-equal', 'char-not-greaterp', 'char-not-lessp', 'char-upcase',
'cis', 'class-name', 'class-of', 'clear-input', 'clear-output',
'close', 'clrhash', 'code-char', 'coerce', 'compile',
'compiled-function-p', 'compile-file', 'compile-file-pathname',
'compiler-macro-function', 'complement', 'complex', 'complexp',
'compute-applicable-methods', 'compute-restarts', 'concatenate',
'concatenated-stream-streams', 'conjugate', 'cons', 'consp',
'constantly', 'constantp', 'continue', 'copy-alist', 'copy-list',
'copy-pprint-dispatch', 'copy-readtable', 'copy-seq', 'copy-structure',
'copy-symbol', 'copy-tree', 'cos', 'cosh', 'count', 'count-if',
'count-if-not', 'decode-float', 'decode-universal-time', 'delete',
'delete-duplicates', 'delete-file', 'delete-if', 'delete-if-not',
'delete-package', 'denominator', 'deposit-field', 'describe',
'describe-object', 'digit-char', 'digit-char-p', 'directory',
'directory-namestring', 'disassemble', 'documentation', 'dpb',
'dribble', 'echo-stream-input-stream', 'echo-stream-output-stream',
'ed', 'eighth', 'elt', 'encode-universal-time', 'endp',
'enough-namestring', 'ensure-directories-exist',
'ensure-generic-function', 'eq', 'eql', 'equal', 'equalp', 'error',
'eval', 'evenp', 'every', 'exp', 'export', 'expt', 'fboundp',
'fceiling', 'fdefinition', 'ffloor', 'fifth', 'file-author',
'file-error-pathname', 'file-length', 'file-namestring',
'file-position', 'file-string-length', 'file-write-date',
'fill', 'fill-pointer', 'find', 'find-all-symbols', 'find-class',
'find-if', 'find-if-not', 'find-method', 'find-package', 'find-restart',
'find-symbol', 'finish-output', 'first', 'float', 'float-digits',
'floatp', 'float-precision', 'float-radix', 'float-sign', 'floor',
'fmakunbound', 'force-output', 'format', 'fourth', 'fresh-line',
'fround', 'ftruncate', 'funcall', 'function-keywords',
'function-lambda-expression', 'functionp', 'gcd', 'gensym', 'gentemp',
'get', 'get-decoded-time', 'get-dispatch-macro-character', 'getf',
'gethash', 'get-internal-real-time', 'get-internal-run-time',
'get-macro-character', 'get-output-stream-string', 'get-properties',
'get-setf-expansion', 'get-universal-time', 'graphic-char-p',
'hash-table-count', 'hash-table-p', 'hash-table-rehash-size',
'hash-table-rehash-threshold', 'hash-table-size', 'hash-table-test',
'host-namestring', 'identity', 'imagpart', 'import',
'initialize-instance', 'input-stream-p', 'inspect',
'integer-decode-float', 'integer-length', 'integerp',
'interactive-stream-p', 'intern', 'intersection',
'invalid-method-error', 'invoke-debugger', 'invoke-restart',
'invoke-restart-interactively', 'isqrt', 'keywordp', 'last', 'lcm',
'ldb', 'ldb-test', 'ldiff', 'length', 'lisp-implementation-type',
'lisp-implementation-version', 'list', 'list*', 'list-all-packages',
'listen', 'list-length', 'listp', 'load',
'load-logical-pathname-translations', 'log', 'logand', 'logandc1',
'logandc2', 'logbitp', 'logcount', 'logeqv', 'logical-pathname',
'logical-pathname-translations', 'logior', 'lognand', 'lognor',
'lognot', 'logorc1', 'logorc2', 'logtest', 'logxor', 'long-site-name',
'lower-case-p', 'machine-instance', 'machine-type', 'machine-version',
'macroexpand', 'macroexpand-1', 'macro-function', 'make-array',
'make-broadcast-stream', 'make-concatenated-stream', 'make-condition',
'make-dispatch-macro-character', 'make-echo-stream', 'make-hash-table',
'make-instance', 'make-instances-obsolete', 'make-list',
'make-load-form', 'make-load-form-saving-slots', 'make-package',
'make-pathname', 'make-random-state', 'make-sequence', 'make-string',
'make-string-input-stream', 'make-string-output-stream', 'make-symbol',
'make-synonym-stream', 'make-two-way-stream', 'makunbound', 'map',
'mapc', 'mapcan', 'mapcar', 'mapcon', 'maphash', 'map-into', 'mapl',
'maplist', 'mask-field', 'max', 'member', 'member-if', 'member-if-not',
'merge', 'merge-pathnames', 'method-combination-error',
'method-qualifiers', 'min', 'minusp', 'mismatch', 'mod',
'muffle-warning', 'name-char', 'namestring', 'nbutlast', 'nconc',
'next-method-p', 'nintersection', 'ninth', 'no-applicable-method',
'no-next-method', 'not', 'notany', 'notevery', 'nreconc', 'nreverse',
'nset-difference', 'nset-exclusive-or', 'nstring-capitalize',
'nstring-downcase', 'nstring-upcase', 'nsublis', 'nsubst', 'nsubst-if',
'nsubst-if-not', 'nsubstitute', 'nsubstitute-if', 'nsubstitute-if-not',
'nth', 'nthcdr', 'null', 'numberp', 'numerator', 'nunion', 'oddp',
'open', 'open-stream-p', 'output-stream-p', 'package-error-package',
'package-name', 'package-nicknames', 'packagep',
'package-shadowing-symbols', 'package-used-by-list', 'package-use-list',
'pairlis', 'parse-integer', 'parse-namestring', 'pathname',
'pathname-device', 'pathname-directory', 'pathname-host',
'pathname-match-p', 'pathname-name', 'pathnamep', 'pathname-type',
'pathname-version', 'peek-char', 'phase', 'plusp', 'position',
'position-if', 'position-if-not', 'pprint', 'pprint-dispatch',
'pprint-fill', 'pprint-indent', 'pprint-linear', 'pprint-newline',
'pprint-tab', 'pprint-tabular', 'prin1', 'prin1-to-string', 'princ',
'princ-to-string', 'print', 'print-object', 'probe-file', 'proclaim',
'provide', 'random', 'random-state-p', 'rassoc', 'rassoc-if',
'rassoc-if-not', 'rational', 'rationalize', 'rationalp', 'read',
'read-byte', 'read-char', 'read-char-no-hang', 'read-delimited-list',
'read-from-string', 'read-line', 'read-preserving-whitespace',
'read-sequence', 'readtable-case', 'readtablep', 'realp', 'realpart',
'reduce', 'reinitialize-instance', 'rem', 'remhash', 'remove',
'remove-duplicates', 'remove-if', 'remove-if-not', 'remove-method',
'remprop', 'rename-file', 'rename-package', 'replace', 'require',
'rest', 'restart-name', 'revappend', 'reverse', 'room', 'round',
'row-major-aref', 'rplaca', 'rplacd', 'sbit', 'scale-float', 'schar',
'search', 'second', 'set', 'set-difference',
'set-dispatch-macro-character', 'set-exclusive-or',
'set-macro-character', 'set-pprint-dispatch', 'set-syntax-from-char',
'seventh', 'shadow', 'shadowing-import', 'shared-initialize',
'short-site-name', 'signal', 'signum', 'simple-bit-vector-p',
'simple-condition-format-arguments', 'simple-condition-format-control',
'simple-string-p', 'simple-vector-p', 'sin', 'sinh', 'sixth', 'sleep',
'slot-boundp', 'slot-exists-p', 'slot-makunbound', 'slot-missing',
'slot-unbound', 'slot-value', 'software-type', 'software-version',
'some', 'sort', 'special-operator-p', 'sqrt', 'stable-sort',
'standard-char-p', 'store-value', 'stream-element-type',
'stream-error-stream', 'stream-external-format', 'streamp', 'string',
'string<', 'string<=', 'string=', 'string>', 'string>=', 'string/=',
'string-capitalize', 'string-downcase', 'string-equal',
'string-greaterp', 'string-left-trim', 'string-lessp',
'string-not-equal', 'string-not-greaterp', 'string-not-lessp',
'stringp', 'string-right-trim', 'string-trim', 'string-upcase',
'sublis', 'subseq', 'subsetp', 'subst', 'subst-if', 'subst-if-not',
'substitute', 'substitute-if', 'substitute-if-not', 'subtypep','svref',
'sxhash', 'symbol-function', 'symbol-name', 'symbolp', 'symbol-package',
'symbol-plist', 'symbol-value', 'synonym-stream-symbol', 'syntax:',
'tailp', 'tan', 'tanh', 'tenth', 'terpri', 'third',
'translate-logical-pathname', 'translate-pathname', 'tree-equal',
'truename', 'truncate', 'two-way-stream-input-stream',
'two-way-stream-output-stream', 'type-error-datum',
'type-error-expected-type', 'type-of', 'typep', 'unbound-slot-instance',
'unexport', 'unintern', 'union', 'unread-char', 'unuse-package',
'update-instance-for-different-class',
'update-instance-for-redefined-class', 'upgraded-array-element-type',
'upgraded-complex-part-type', 'upper-case-p', 'use-package',
'user-homedir-pathname', 'use-value', 'values', 'values-list', 'vector',
'vectorp', 'vector-pop', 'vector-push', 'vector-push-extend', 'warn',
'wild-pathname-p', 'write', 'write-byte', 'write-char', 'write-line',
'write-sequence', 'write-string', 'write-to-string', 'yes-or-no-p',
'y-or-n-p', 'zerop',
]
SPECIAL_FORMS = [
'block', 'catch', 'declare', 'eval-when', 'flet', 'function', 'go', 'if',
'labels', 'lambda', 'let', 'let*', 'load-time-value', 'locally', 'macrolet',
'multiple-value-call', 'multiple-value-prog1', 'progn', 'progv', 'quote',
'return-from', 'setq', 'symbol-macrolet', 'tagbody', 'the', 'throw',
'unwind-protect',
]
MACROS = [
'and', 'assert', 'call-method', 'case', 'ccase', 'check-type', 'cond',
'ctypecase', 'decf', 'declaim', 'defclass', 'defconstant', 'defgeneric',
'define-compiler-macro', 'define-condition', 'define-method-combination',
'define-modify-macro', 'define-setf-expander', 'define-symbol-macro',
'defmacro', 'defmethod', 'defpackage', 'defparameter', 'defsetf',
'defstruct', 'deftype', 'defun', 'defvar', 'destructuring-bind', 'do',
'do*', 'do-all-symbols', 'do-external-symbols', 'dolist', 'do-symbols',
'dotimes', 'ecase', 'etypecase', 'formatter', 'handler-bind',
'handler-case', 'ignore-errors', 'incf', 'in-package', 'lambda', 'loop',
'loop-finish', 'make-method', 'multiple-value-bind', 'multiple-value-list',
'multiple-value-setq', 'nth-value', 'or', 'pop',
'pprint-exit-if-list-exhausted', 'pprint-logical-block', 'pprint-pop',
'print-unreadable-object', 'prog', 'prog*', 'prog1', 'prog2', 'psetf',
'psetq', 'push', 'pushnew', 'remf', 'restart-bind', 'restart-case',
'return', 'rotatef', 'setf', 'shiftf', 'step', 'time', 'trace', 'typecase',
'unless', 'untrace', 'when', 'with-accessors', 'with-compilation-unit',
'with-condition-restarts', 'with-hash-table-iterator',
'with-input-from-string', 'with-open-file', 'with-open-stream',
'with-output-to-string', 'with-package-iterator', 'with-simple-restart',
'with-slots', 'with-standard-io-syntax',
]
LAMBDA_LIST_KEYWORDS = [
'&allow-other-keys', '&aux', '&body', '&environment', '&key', '&optional',
'&rest', '&whole',
]
DECLARATIONS = [
'dynamic-extent', 'ignore', 'optimize', 'ftype', 'inline', 'special',
'ignorable', 'notinline', 'type',
]
BUILTIN_TYPES = [
'atom', 'boolean', 'base-char', 'base-string', 'bignum', 'bit',
'compiled-function', 'extended-char', 'fixnum', 'keyword', 'nil',
'signed-byte', 'short-float', 'single-float', 'double-float', 'long-float',
'simple-array', 'simple-base-string', 'simple-bit-vector', 'simple-string',
'simple-vector', 'standard-char', 'unsigned-byte',
# Condition Types
'arithmetic-error', 'cell-error', 'condition', 'control-error',
'division-by-zero', 'end-of-file', 'error', 'file-error',
'floating-point-inexact', 'floating-point-overflow',
'floating-point-underflow', 'floating-point-invalid-operation',
'parse-error', 'package-error', 'print-not-readable', 'program-error',
'reader-error', 'serious-condition', 'simple-condition', 'simple-error',
'simple-type-error', 'simple-warning', 'stream-error', 'storage-condition',
'style-warning', 'type-error', 'unbound-variable', 'unbound-slot',
'undefined-function', 'warning',
]
BUILTIN_CLASSES = [
'array', 'broadcast-stream', 'bit-vector', 'built-in-class', 'character',
'class', 'complex', 'concatenated-stream', 'cons', 'echo-stream',
'file-stream', 'float', 'function', 'generic-function', 'hash-table',
'integer', 'list', 'logical-pathname', 'method-combination', 'method',
'null', 'number', 'package', 'pathname', 'ratio', 'rational', 'readtable',
'real', 'random-state', 'restart', 'sequence', 'standard-class',
'standard-generic-function', 'standard-method', 'standard-object',
'string-stream', 'stream', 'string', 'structure-class', 'structure-object',
'symbol', 'synonym-stream', 't', 'two-way-stream', 'vector',
]

File diff suppressed because it is too large Load diff

Some files were not shown because too many files have changed in this diff Show more