first commit

This commit is contained in:
Yura 2024-09-15 15:12:16 +03:00
commit 417e54da96
5696 changed files with 900003 additions and 0 deletions

View file

@ -0,0 +1,157 @@
"""
pygments.formatters
~~~~~~~~~~~~~~~~~~~
Pygments formatters.
:copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
import sys
import types
import fnmatch
from os.path import basename
from pygments.formatters._mapping import FORMATTERS
from pygments.plugin import find_plugin_formatters
from pygments.util import ClassNotFound
__all__ = ['get_formatter_by_name', 'get_formatter_for_filename',
'get_all_formatters', 'load_formatter_from_file'] + list(FORMATTERS)
_formatter_cache = {} # classes by name
_pattern_cache = {}
def _fn_matches(fn, glob):
"""Return whether the supplied file name fn matches pattern filename."""
if glob not in _pattern_cache:
pattern = _pattern_cache[glob] = re.compile(fnmatch.translate(glob))
return pattern.match(fn)
return _pattern_cache[glob].match(fn)
def _load_formatters(module_name):
"""Load a formatter (and all others in the module too)."""
mod = __import__(module_name, None, None, ['__all__'])
for formatter_name in mod.__all__:
cls = getattr(mod, formatter_name)
_formatter_cache[cls.name] = cls
def get_all_formatters():
"""Return a generator for all formatter classes."""
# NB: this returns formatter classes, not info like get_all_lexers().
for info in FORMATTERS.values():
if info[1] not in _formatter_cache:
_load_formatters(info[0])
yield _formatter_cache[info[1]]
for _, formatter in find_plugin_formatters():
yield formatter
def find_formatter_class(alias):
"""Lookup a formatter by alias.
Returns None if not found.
"""
for module_name, name, aliases, _, _ in FORMATTERS.values():
if alias in aliases:
if name not in _formatter_cache:
_load_formatters(module_name)
return _formatter_cache[name]
for _, cls in find_plugin_formatters():
if alias in cls.aliases:
return cls
def get_formatter_by_name(_alias, **options):
"""
Return an instance of a :class:`.Formatter` subclass that has `alias` in its
aliases list. The formatter is given the `options` at its instantiation.
Will raise :exc:`pygments.util.ClassNotFound` if no formatter with that
alias is found.
"""
cls = find_formatter_class(_alias)
if cls is None:
raise ClassNotFound(f"no formatter found for name {_alias!r}")
return cls(**options)
def load_formatter_from_file(filename, formattername="CustomFormatter", **options):
"""
Return a `Formatter` subclass instance loaded from the provided file, relative
to the current directory.
The file is expected to contain a Formatter class named ``formattername``
(by default, CustomFormatter). Users should be very careful with the input, because
this method is equivalent to running ``eval()`` on the input file. The formatter is
given the `options` at its instantiation.
:exc:`pygments.util.ClassNotFound` is raised if there are any errors loading
the formatter.
.. versionadded:: 2.2
"""
try:
# This empty dict will contain the namespace for the exec'd file
custom_namespace = {}
with open(filename, 'rb') as f:
exec(f.read(), custom_namespace)
# Retrieve the class `formattername` from that namespace
if formattername not in custom_namespace:
raise ClassNotFound(f'no valid {formattername} class found in {filename}')
formatter_class = custom_namespace[formattername]
# And finally instantiate it with the options
return formatter_class(**options)
except OSError as err:
raise ClassNotFound(f'cannot read {filename}: {err}')
except ClassNotFound:
raise
except Exception as err:
raise ClassNotFound(f'error when loading custom formatter: {err}')
def get_formatter_for_filename(fn, **options):
"""
Return a :class:`.Formatter` subclass instance that has a filename pattern
matching `fn`. The formatter is given the `options` at its instantiation.
Will raise :exc:`pygments.util.ClassNotFound` if no formatter for that filename
is found.
"""
fn = basename(fn)
for modname, name, _, filenames, _ in FORMATTERS.values():
for filename in filenames:
if _fn_matches(fn, filename):
if name not in _formatter_cache:
_load_formatters(modname)
return _formatter_cache[name](**options)
for _name, cls in find_plugin_formatters():
for filename in cls.filenames:
if _fn_matches(fn, filename):
return cls(**options)
raise ClassNotFound(f"no formatter found for file name {fn!r}")
class _automodule(types.ModuleType):
"""Automatically import formatters."""
def __getattr__(self, name):
info = FORMATTERS.get(name)
if info:
_load_formatters(info[0])
cls = _formatter_cache[info[1]]
setattr(self, name, cls)
return cls
raise AttributeError(name)
oldmod = sys.modules[__name__]
newmod = _automodule(__name__)
newmod.__dict__.update(oldmod.__dict__)
sys.modules[__name__] = newmod
del newmod.newmod, newmod.oldmod, newmod.sys, newmod.types

View file

@ -0,0 +1,23 @@
# Automatically generated by scripts/gen_mapfiles.py.
# DO NOT EDIT BY HAND; run `tox -e mapfiles` instead.
FORMATTERS = {
'BBCodeFormatter': ('pygments.formatters.bbcode', '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': ('pygments.formatters.img', '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': ('pygments.formatters.img', '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.'),
'GroffFormatter': ('pygments.formatters.groff', 'groff', ('groff', 'troff', 'roff'), (), 'Format tokens with groff escapes to change their color and font style.'),
'HtmlFormatter': ('pygments.formatters.html', 'HTML', ('html',), ('*.html', '*.htm'), "Format tokens as HTML 4 ``<span>`` tags. By default, the content is enclosed in a ``<pre>`` tag, itself wrapped in a ``<div>`` tag (but see the `nowrap` option). The ``<div>``'s CSS class can be set by the `cssclass` option."),
'IRCFormatter': ('pygments.formatters.irc', 'IRC', ('irc', 'IRC'), (), 'Format tokens with IRC color sequences'),
'ImageFormatter': ('pygments.formatters.img', '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': ('pygments.formatters.img', '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': ('pygments.formatters.latex', 'LaTeX', ('latex', 'tex'), ('*.tex',), 'Format tokens as LaTeX code. This needs the `fancyvrb` and `color` standard packages.'),
'NullFormatter': ('pygments.formatters.other', 'Text only', ('text', 'null'), ('*.txt',), 'Output the text unchanged without any formatting.'),
'PangoMarkupFormatter': ('pygments.formatters.pangomarkup', 'Pango Markup', ('pango', 'pangomarkup'), (), 'Format tokens as Pango Markup code. It can then be rendered to an SVG.'),
'RawTokenFormatter': ('pygments.formatters.other', 'Raw tokens', ('raw', 'tokens'), ('*.raw',), 'Format tokens as a raw representation for storing token streams.'),
'RtfFormatter': ('pygments.formatters.rtf', '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(R) Word(R) documents.'),
'SvgFormatter': ('pygments.formatters.svg', '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': ('pygments.formatters.terminal256', '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': ('pygments.formatters.terminal', '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.'),
'TerminalTrueColorFormatter': ('pygments.formatters.terminal256', 'TerminalTrueColor', ('terminal16m', 'console16m', '16m'), (), 'Format tokens with ANSI color sequences, for output in a true-color terminal or console. Like in `TerminalFormatter` color sequences are terminated at newlines, so that paging the output works correctly.'),
'TestcaseFormatter': ('pygments.formatters.other', 'Testcase', ('testcase',), (), 'Format tokens as appropriate for a new testcase.'),
}

View file

@ -0,0 +1,108 @@
"""
pygments.formatters.bbcode
~~~~~~~~~~~~~~~~~~~~~~~~~~
BBcode formatter.
:copyright: Copyright 2006-2024 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=#{}]'.format(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 +1,170 @@
"""
pygments.formatters.groff
~~~~~~~~~~~~~~~~~~~~~~~~~
Formatter for groff output.
:copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import math
from pygments.formatter import Formatter
from pygments.util import get_bool_opt, get_int_opt
__all__ = ['GroffFormatter']
class GroffFormatter(Formatter):
"""
Format tokens with groff escapes to change their color and font style.
.. versionadded:: 2.11
Additional options accepted:
`style`
The style to use, can be a string or a Style subclass (default:
``'default'``).
`monospaced`
If set to true, monospace font will be used (default: ``true``).
`linenos`
If set to true, print the line numbers (default: ``false``).
`wrap`
Wrap lines to the specified number of characters. Disabled if set to 0
(default: ``0``).
"""
name = 'groff'
aliases = ['groff','troff','roff']
filenames = []
def __init__(self, **options):
Formatter.__init__(self, **options)
self.monospaced = get_bool_opt(options, 'monospaced', True)
self.linenos = get_bool_opt(options, 'linenos', False)
self._lineno = 0
self.wrap = get_int_opt(options, 'wrap', 0)
self._linelen = 0
self.styles = {}
self._make_styles()
def _make_styles(self):
regular = '\\f[CR]' if self.monospaced else '\\f[R]'
bold = '\\f[CB]' if self.monospaced else '\\f[B]'
italic = '\\f[CI]' if self.monospaced else '\\f[I]'
for ttype, ndef in self.style:
start = end = ''
if ndef['color']:
start += '\\m[{}]'.format(ndef['color'])
end = '\\m[]' + end
if ndef['bold']:
start += bold
end = regular + end
if ndef['italic']:
start += italic
end = regular + end
if ndef['bgcolor']:
start += '\\M[{}]'.format(ndef['bgcolor'])
end = '\\M[]' + end
self.styles[ttype] = start, end
def _define_colors(self, outfile):
colors = set()
for _, ndef in self.style:
if ndef['color'] is not None:
colors.add(ndef['color'])
for color in sorted(colors):
outfile.write('.defcolor ' + color + ' rgb #' + color + '\n')
def _write_lineno(self, outfile):
self._lineno += 1
outfile.write("%s% 4d " % (self._lineno != 1 and '\n' or '', self._lineno))
def _wrap_line(self, line):
length = len(line.rstrip('\n'))
space = ' ' if self.linenos else ''
newline = ''
if length > self.wrap:
for i in range(0, math.floor(length / self.wrap)):
chunk = line[i*self.wrap:i*self.wrap+self.wrap]
newline += (chunk + '\n' + space)
remainder = length % self.wrap
if remainder > 0:
newline += line[-remainder-1:]
self._linelen = remainder
elif self._linelen + length > self.wrap:
newline = ('\n' + space) + line
self._linelen = length
else:
newline = line
self._linelen += length
return newline
def _escape_chars(self, text):
text = text.replace('\\', '\\[u005C]'). \
replace('.', '\\[char46]'). \
replace('\'', '\\[u0027]'). \
replace('`', '\\[u0060]'). \
replace('~', '\\[u007E]')
copy = text
for char in copy:
if len(char) != len(char.encode()):
uni = char.encode('unicode_escape') \
.decode()[1:] \
.replace('x', 'u00') \
.upper()
text = text.replace(char, '\\[u' + uni[1:] + ']')
return text
def format_unencoded(self, tokensource, outfile):
self._define_colors(outfile)
outfile.write('.nf\n\\f[CR]\n')
if self.linenos:
self._write_lineno(outfile)
for ttype, value in tokensource:
while ttype not in self.styles:
ttype = ttype.parent
start, end = self.styles[ttype]
for line in value.splitlines(True):
if self.wrap > 0:
line = self._wrap_line(line)
if start and end:
text = self._escape_chars(line.rstrip('\n'))
if text != '':
outfile.write(''.join((start, text, end)))
else:
outfile.write(self._escape_chars(line.rstrip('\n')))
if line.endswith('\n'):
if self.linenos:
self._write_lineno(outfile)
self._linelen = 0
else:
outfile.write('\n')
self._linelen = 0
outfile.write('\n.fi')

View file

@ -0,0 +1,987 @@
"""
pygments.formatters.html
~~~~~~~~~~~~~~~~~~~~~~~~
Formatter for HTML output.
:copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import functools
import os
import sys
import os.path
from io 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
try:
import ctags
except ImportError:
ctags = None
__all__ = ['HtmlFormatter']
_escape_html_table = {
ord('&'): '&amp;',
ord('<'): '&lt;',
ord('>'): '&gt;',
ord('"'): '&quot;',
ord("'"): '&#39;',
}
def escape_html(text, table=_escape_html_table):
"""Escape &, <, > as well as single and double quotes for HTML."""
return text.translate(table)
def webify(color):
if color.startswith('calc') or color.startswith('var'):
return color
else:
return '#' + color
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 = '''\
/*
generated by Pygments <https://pygments.org/>
Copyright 2006-2024 by the Pygments team.
Licensed under the BSD license, see LICENSE for details.
*/
%(styledefs)s
'''
DOC_HEADER = '''\
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN"
"http://www.w3.org/TR/html4/strict.dtd">
<!--
generated by Pygments <https://pygments.org/>
Copyright 2006-2024 by the Pygments team.
Licensed under the BSD license, see LICENSE for details.
-->
<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. By default, the content is enclosed
in a ``<pre>`` tag, itself wrapped in a ``<div>`` tag (but see the `nowrap` option).
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).
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
`lineanchors` 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 add a ``<pre>`` and a ``<div>`` tag
around the tokens. 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 (as well as line number elements)
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.
.. versionadded:: 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: ``''``).
.. versionadded:: 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.
.. versionadded:: 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``.
.. versionadded:: 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. The line numbers are always
relative to the input (i.e. the first line is line 1) and are
independent of `linenostart`.
.. versionadded:: 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``).
.. versionadded:: 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.
.. versionadded:: 0.7
`lineanchors`
If set to a nonempty string, e.g. ``foo``, the formatter will wrap each
output line in an anchor tag with an ``id`` (and `name`) of ``foo-linenumber``.
This allows easy linking to certain lines.
.. versionadded:: 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.
.. versionadded:: 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).
The tags file is assumed to be encoded in UTF-8.
.. versionadded:: 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.
.. versionadded:: 1.6
`filename`
A string used to generate a filename when rendering ``<pre>`` blocks,
for example if displaying source code. If `linenos` is set to
``'table'`` then the filename will be rendered in an initial row
containing a single `<th>` which spans both columns.
.. versionadded:: 2.1
`wrapcode`
Wrap the code inside ``<pre>`` blocks using ``<code>``, as recommended
by the HTML5 specification.
.. versionadded:: 2.4
`debug_token_types`
Add ``title`` attributes to all token ``<span>`` tags that show the
name of the token.
.. versionadded:: 2.10
**Subclassing the HTML formatter**
.. versionadded:: 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, *, include_div):
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', ''))
self.filename = self._decodeifneeded(options.get('filename', ''))
self.wrapcode = get_bool_opt(options, 'wrapcode', False)
self.span_element_openers = {}
self.debug_token_types = get_bool_opt(options, 'debug_token_types', False)
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 = get_bool_opt(options, '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 _get_css_classes(self, ttype):
"""Return the CSS classes of this token type prefixed with the classprefix option."""
cls = self._get_css_class(ttype)
while ttype not in STANDARD_TYPES:
ttype = ttype.parent
cls = self._get_css_class(ttype) + ' ' + cls
return cls or ''
def _get_css_inline_styles(self, ttype):
"""Return the inline CSS styles for this token type."""
cclass = self.ttype2class.get(ttype)
while cclass is None:
ttype = ttype.parent
cclass = self.ttype2class.get(ttype)
return cclass or ''
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: {}; '.format(webify(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: {}; '.format(webify(ndef['bgcolor']))
if ndef['border']:
style += 'border: 1px solid {}; '.format(webify(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.
"""
style_lines = []
style_lines.extend(self.get_linenos_style_defs())
style_lines.extend(self.get_background_style_defs(arg))
style_lines.extend(self.get_token_style_defs(arg))
return '\n'.join(style_lines)
def get_token_style_defs(self, arg=None):
prefix = self.get_css_prefix(arg)
styles = [
(level, ttype, cls, style)
for cls, (style, ttype, level) in self.class2style.items()
if cls and style
]
styles.sort()
lines = [
f'{prefix(cls)} {{ {style} }} /* {repr(ttype)[6:]} */'
for (level, ttype, cls, style) in styles
]
return lines
def get_background_style_defs(self, arg=None):
prefix = self.get_css_prefix(arg)
bg_color = self.style.background_color
hl_color = self.style.highlight_color
lines = []
if arg and not self.nobackground and bg_color is not None:
text_style = ''
if Text in self.ttype2class:
text_style = ' ' + self.class2style[self.ttype2class[Text]][0]
lines.insert(
0, '{}{{ background: {};{} }}'.format(
prefix(''), bg_color, text_style
)
)
if hl_color is not None:
lines.insert(
0, '{} {{ background-color: {} }}'.format(prefix('hll'), hl_color)
)
return lines
def get_linenos_style_defs(self):
lines = [
f'pre {{ {self._pre_style} }}',
f'td.linenos .normal {{ {self._linenos_style} }}',
f'span.linenos {{ {self._linenos_style} }}',
f'td.linenos .special {{ {self._linenos_special_style} }}',
f'span.linenos.special {{ {self._linenos_special_style} }}',
]
return lines
def get_css_prefix(self, arg):
if arg is None:
arg = ('cssclass' in self.options and '.'+self.cssclass or '')
if isinstance(arg, str):
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)
return prefix
@property
def _pre_style(self):
return 'line-height: 125%;'
@property
def _linenos_style(self):
color = self.style.line_number_color
background_color = self.style.line_number_background_color
return f'color: {color}; background-color: {background_color}; padding-left: 5px; padding-right: 5px;'
@property
def _linenos_special_style(self):
color = self.style.line_number_special_color
background_color = self.style.line_number_special_background_color
return f'color: {color}; background-color: {background_color}; padding-left: 5px; padding-right: 5px;'
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('Note: Cannot determine output file name, '
'using current directory as base for the CSS file name',
file=sys.stderr)
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:
with open(cssfilename, "w", encoding="utf-8") as cf:
cf.write(CSSFILE_TEMPLATE %
{'styledefs': self.get_style_defs('body')})
except OSError as 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))
yield from inner
yield 0, DOC_FOOTER
def _wrap_tablelinenos(self, inner):
dummyoutfile = 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
anchor_name = self.lineanchors or self.linespans
aln = self.anchorlinenos
nocls = self.noclasses
lines = []
for i in range(fl, fl+lncount):
print_line = i % st == 0
special_line = sp and i % sp == 0
if print_line:
line = '%*d' % (mw, i)
if aln:
line = '<a href="#%s-%d">%s</a>' % (anchor_name, i, line)
else:
line = ' ' * mw
if nocls:
if special_line:
style = f' style="{self._linenos_special_style}"'
else:
style = f' style="{self._linenos_style}"'
else:
if special_line:
style = ' class="special"'
else:
style = ' class="normal"'
if style:
line = f'<span{style}>{line}</span>'
lines.append(line)
ls = '\n'.join(lines)
# If a filename was specified, we can't put it into the code table as it
# would misalign the line numbers. Hence we emit a separate row for it.
filename_tr = ""
if self.filename:
filename_tr = (
'<tr><th colspan="2" class="filename">'
'<span class="filename">' + self.filename + '</span>'
'</th></tr>')
# 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...
yield 0, (f'<table class="{self.cssclass}table">' + filename_tr +
'<tr><td class="linenos"><div class="linenodiv"><pre>' +
ls + '</pre></div></td><td class="code">')
yield 0, '<div>'
yield 0, dummyoutfile.getvalue()
yield 0, '</div>'
yield 0, '</td></tr></table>'
def _wrap_inlinelinenos(self, inner):
# need a list of lines since we need the width of a single number :(
inner_lines = list(inner)
sp = self.linenospecial
st = self.linenostep
num = self.linenostart
mw = len(str(len(inner_lines) + num - 1))
anchor_name = self.lineanchors or self.linespans
aln = self.anchorlinenos
nocls = self.noclasses
for _, inner_line in inner_lines:
print_line = num % st == 0
special_line = sp and num % sp == 0
if print_line:
line = '%*d' % (mw, num)
else:
line = ' ' * mw
if nocls:
if special_line:
style = f' style="{self._linenos_special_style}"'
else:
style = f' style="{self._linenos_style}"'
else:
if special_line:
style = ' class="linenos special"'
else:
style = ' class="linenos"'
if style:
linenos = f'<span{style}>{line}</span>'
else:
linenos = line
if aln:
yield 1, ('<a href="#%s-%d">%s</a>' % (anchor_name, num, linenos) +
inner_line)
else:
yield 1, linenos + inner_line
num += 1
def _wrap_lineanchors(self, inner):
s = self.lineanchors
# subtract 1 since we have to increment i *before* yielding
i = self.linenostart - 1
for t, line in inner:
if t:
i += 1
href = "" if self.linenos else ' href="#%s-%d"' % (s, i)
yield 1, '<a id="%s-%d" name="%s-%d"%s></a>' % (s, i, s, i, href) + 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(f'background: {self.style.background_color}')
if self.cssstyles:
style.append(self.cssstyles)
style = '; '.join(style)
yield 0, ('<div' + (self.cssclass and f' class="{self.cssclass}"') +
(style and (f' style="{style}"')) + '>')
yield from inner
yield 0, '</div>\n'
def _wrap_pre(self, inner):
style = []
if self.prestyles:
style.append(self.prestyles)
if self.noclasses:
style.append(self._pre_style)
style = '; '.join(style)
if self.filename and self.linenos != 1:
yield 0, ('<span class="filename">' + self.filename + '</span>')
# the empty span here is to keep leading empty lines from being
# ignored by HTML parsers
yield 0, ('<pre' + (style and f' style="{style}"') + '><span></span>')
yield from inner
yield 0, '</pre>'
def _wrap_code(self, inner):
yield 0, '<code>'
yield from inner
yield 0, '</code>'
@functools.lru_cache(maxsize=100)
def _translate_parts(self, value):
"""HTML-escape a value and split it by newlines."""
return value.translate(_escape_html_table).split('\n')
def _format_lines(self, tokensource):
"""
Just format the tokens, without any wrapping tags.
Yield individual lines.
"""
nocls = self.noclasses
lsep = self.lineseparator
tagsfile = self.tagsfile
lspan = ''
line = []
for ttype, value in tokensource:
try:
cspan = self.span_element_openers[ttype]
except KeyError:
title = ' title="{}"'.format('.'.join(ttype)) if self.debug_token_types else ''
if nocls:
css_style = self._get_css_inline_styles(ttype)
if css_style:
css_style = self.class2style[css_style][0]
cspan = f'<span style="{css_style}"{title}>'
else:
cspan = ''
else:
css_class = self._get_css_classes(ttype)
if css_class:
cspan = f'<span class="{css_class}"{title}>'
else:
cspan = ''
self.span_element_openers[ttype] = cspan
parts = self._translate_parts(value)
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:
# Also check for part being non-empty, so we avoid creating
# empty <span> tags
if lspan != cspan and part:
line.extend(((lspan and '</span>'), cspan, part,
(cspan and '</span>'), lsep))
else: # both are the same, or the current part was empty
line.extend((part, (lspan and '</span>'), lsep))
yield 1, ''.join(line)
line = []
elif part:
yield 1, ''.join((cspan, part, (cspan and '</span>'), lsep))
else:
yield 1, lsep
# for the last line
if line and parts[-1]:
if lspan != cspan:
line.extend(((lspan and '</span>'), cspan, parts[-1]))
lspan = cspan
else:
line.append(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:
line.extend(((lspan and '</span>'), lsep))
yield 1, ''.join(line)
def _lookup_ctag(self, token):
entry = ctags.TagEntry()
if self._ctags.find(entry, token.encode(), 0):
return entry['file'].decode(), 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 = (f' style="background-color: {self.style.highlight_color}"')
yield 1, f'<span{style}>{value}</span>'
else:
yield 1, f'<span class="hll">{value}</span>'
else:
yield 1, value
def wrap(self, source):
"""
Wrap the ``source``, which is a generator yielding
individual lines, in custom generators. See docstring
for `format`. Can be overridden.
"""
output = source
if self.wrapcode:
output = self._wrap_code(output)
output = self._wrap_pre(output)
return output
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)
# As a special case, we wrap line numbers before line highlighting
# so the line numbers get wrapped in the highlighting tag.
if not self.nowrap and self.linenos == 2:
source = self._wrap_inlinelinenos(source)
if self.hl_lines:
source = self._highlight_lines(source)
if not self.nowrap:
if self.lineanchors:
source = self._wrap_lineanchors(source)
if self.linespans:
source = self._wrap_linespans(source)
source = self.wrap(source)
if self.linenos == 1:
source = self._wrap_tablelinenos(source)
source = self._wrap_div(source)
if self.full:
source = self._wrap_full(source, outfile)
for t, piece in source:
outfile.write(piece)

View file

@ -0,0 +1,685 @@
"""
pygments.formatters.img
~~~~~~~~~~~~~~~~~~~~~~~
Formatter for Pixmap output.
:copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import os
import sys
from pygments.formatter import Formatter
from pygments.util import get_bool_opt, get_int_opt, get_list_opt, \
get_choice_opt
import subprocess
# Import this carefully
try:
from PIL import Image, ImageDraw, ImageFont
pil_available = True
except ImportError:
pil_available = False
try:
import _winreg
except ImportError:
try:
import winreg as _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 = 'DejaVu Sans Mono'
DEFAULT_FONT_NAME_WIN = 'Courier New'
DEFAULT_FONT_NAME_MAC = 'Menlo'
class PilNotAvailable(ImportError):
"""When Python imaging library is not available"""
class FontNotFound(Exception):
"""When there are no usable fonts specified"""
class FontManager:
"""
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
self.variable = False
if hasattr(font_name, 'read') or os.path.isfile(font_name):
font = ImageFont.truetype(font_name, self.font_size)
self.variable = True
for style in STYLES:
self.fonts[style] = font
return
if sys.platform.startswith('win'):
if not font_name:
self.font_name = DEFAULT_FONT_NAME_WIN
self._create_win()
elif sys.platform.startswith('darwin'):
if not font_name:
self.font_name = DEFAULT_FONT_NAME_MAC
self._create_mac()
else:
if not font_name:
self.font_name = DEFAULT_FONT_NAME_NIX
self._create_nix()
def _get_nix_font_path(self, name, style):
proc = subprocess.Popen(['fc-list', f"{name}:style={style}", 'file'],
stdout=subprocess.PIPE, stderr=None)
stdout, _ = proc.communicate()
if proc.returncode == 0:
lines = stdout.splitlines()
for line in lines:
if line.startswith(b'Fontconfig warning:'):
continue
path = line.decode().strip().strip(':')
if path:
return path
return None
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(f'No usable fonts named: "{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 _get_mac_font_path(self, font_map, name, style):
return font_map.get((name + ' ' + style).strip().lower())
def _create_mac(self):
font_map = {}
for font_dir in (os.path.join(os.getenv("HOME"), 'Library/Fonts/'),
'/Library/Fonts/', '/System/Library/Fonts/'):
font_map.update(
(os.path.splitext(f)[0].lower(), os.path.join(font_dir, f))
for f in os.listdir(font_dir)
if f.lower().endswith(('ttf', 'ttc')))
for name in STYLES['NORMAL']:
path = self._get_mac_font_path(font_map, self.font_name, name)
if path is not None:
self.fonts['NORMAL'] = ImageFont.truetype(path, self.font_size)
break
else:
raise FontNotFound(f'No usable fonts named: "{self.font_name}"')
for style in ('ITALIC', 'BOLD', 'BOLDITALIC'):
for stylename in STYLES[style]:
path = self._get_mac_font_path(font_map, 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 = '{}{}{}'.format(basename, style and ' '+style, suffix)
val, _ = _winreg.QueryValueEx(key, valname)
return val
except OSError:
continue
else:
if fail:
raise FontNotFound(f'Font {basename} ({styles[0]}) not found in registry')
return None
def _create_win(self):
lookuperror = None
keynames = [ (_winreg.HKEY_CURRENT_USER, r'Software\Microsoft\Windows NT\CurrentVersion\Fonts'),
(_winreg.HKEY_CURRENT_USER, r'Software\Microsoft\Windows\CurrentVersion\Fonts'),
(_winreg.HKEY_LOCAL_MACHINE, r'Software\Microsoft\Windows NT\CurrentVersion\Fonts'),
(_winreg.HKEY_LOCAL_MACHINE, r'Software\Microsoft\Windows\CurrentVersion\Fonts') ]
for keyname in keynames:
try:
key = _winreg.OpenKey(*keyname)
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']
return
except FontNotFound as err:
lookuperror = err
finally:
_winreg.CloseKey(key)
except OSError:
pass
else:
# If we get here, we checked all registry keys and had no luck
# We can be in one of two situations now:
# * All key lookups failed. In this case lookuperror is None and we
# will raise a generic error
# * At least one lookup failed with a FontNotFound error. In this
# case, we will raise that as a more specific error
if lookuperror:
raise lookuperror
raise FontNotFound('Can\'t open Windows font registry key')
def get_char_size(self):
"""
Get the character size.
"""
return self.get_text_size('M')
def get_text_size(self, text):
"""
Get the text size (width, height).
"""
font = self.fonts['NORMAL']
if hasattr(font, 'getbbox'): # Pillow >= 9.2.0
return font.getbbox(text)[2:4]
else:
return font.getsize(text)
def get_font(self, bold, oblique):
"""
Get the font based on bold and italic flags.
"""
if bold and oblique:
if self.variable:
return self.get_style('BOLDITALIC')
return self.fonts['BOLDITALIC']
elif bold:
if self.variable:
return self.get_style('BOLD')
return self.fonts['BOLD']
elif oblique:
if self.variable:
return self.get_style('ITALIC')
return self.fonts['ITALIC']
else:
if self.variable:
return self.get_style('NORMAL')
return self.fonts['NORMAL']
def get_style(self, style):
"""
Get the specified style of the font if it is a variable font.
If not found, return the normal font.
"""
font = self.fonts[style]
for style_name in STYLES[style]:
try:
font.set_variation_by_name(style_name)
return font
except ValueError:
pass
except OSError:
return font
return font
class ImageFormatter(Formatter):
"""
Create a PNG image from source code. This uses the Python Imaging Library to
generate a pixmap from the source code.
.. versionadded:: 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.
If a filename or a file-like object is specified, the user must
provide different styles of the font.
Default: "Courier New" on Windows, "Menlo" on Mac OS, and
"DejaVu Sans Mono" on \\*nix
`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.
.. versionadded:: 1.2
Default: empty list
`hl_color`
Specify the color for highlighting lines.
.. versionadded:: 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)
self.encoding = 'latin1' # let pygments.format() do the right thing
# 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, linelength):
"""
Get the X coordinate of a character position.
"""
return linelength + self.image_pad + self.line_number_width
def _get_text_pos(self, linelength, lineno):
"""
Get the actual position for a character and line position.
"""
return self._get_char_x(linelength), 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_text_bg_color(self, style):
"""
Get the correct background color for the token from the style.
"""
if style['bgcolor'] is not None:
bg_color = '#' + style['bgcolor']
else:
bg_color = None
return bg_color
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, maxlinelength, maxlineno):
"""
Get the required image size.
"""
return (self._get_char_x(maxlinelength) + 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),
text_fg=self.line_number_fg,
text_bg=None,
)
def _draw_text(self, pos, text, font, text_fg, text_bg):
"""
Remember a single drawable tuple to paint later.
"""
self.drawables.append((pos, text, font, text_fg, text_bg))
def _create_drawables(self, tokensource):
"""
Create drawables for the token content.
"""
lineno = charno = maxcharno = 0
maxlinelength = linelength = 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(linelength, lineno),
temp,
font = self._get_style_font(style),
text_fg = self._get_text_color(style),
text_bg = self._get_text_bg_color(style),
)
temp_width, _ = self.fonts.get_text_size(temp)
linelength += temp_width
maxlinelength = max(maxlinelength, linelength)
charno += len(temp)
maxcharno = max(maxcharno, charno)
if line.endswith('\n'):
# add a line for each extra line in the value
linelength = 0
charno = 0
lineno += 1
self.maxlinelength = maxlinelength
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 range(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)
if self.line_number_separator:
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.maxlinelength, 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, text_fg, text_bg in self.drawables:
if text_bg:
# see deprecations https://pillow.readthedocs.io/en/stable/releasenotes/9.2.0.html#font-size-and-offset-methods
if hasattr(draw, 'textsize'):
text_size = draw.textsize(text=value, font=font)
else:
text_size = font.getbbox(value)[2:]
draw.rectangle([pos[0], pos[1], pos[0] + text_size[0], pos[1] + text_size[1]], fill=text_bg)
draw.text(pos, value, font=font, fill=text_fg)
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.
.. versionadded:: 1.0
"""
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.
.. versionadded:: 1.0
"""
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.
.. versionadded:: 1.0
"""
name = 'img_bmp'
aliases = ['bmp', 'bitmap']
filenames = ['*.bmp']
default_image_format = 'bmp'

View file

@ -0,0 +1,154 @@
"""
pygments.formatters.irc
~~~~~~~~~~~~~~~~~~~~~~~
Formatter for IRC output
:copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pygments.formatter import Formatter
from pygments.token import Keyword, Name, Comment, String, Error, \
Number, Operator, Generic, Token, Whitespace
from pygments.util import get_choice_opt
__all__ = ['IRCFormatter']
#: Map token types to a tuple of color values for light and dark
#: backgrounds.
IRC_COLORS = {
Token: ('', ''),
Whitespace: ('gray', 'brightblack'),
Comment: ('gray', 'brightblack'),
Comment.Preproc: ('cyan', 'brightcyan'),
Keyword: ('blue', 'brightblue'),
Keyword.Type: ('cyan', 'brightcyan'),
Operator.Word: ('magenta', 'brightcyan'),
Name.Builtin: ('cyan', 'brightcyan'),
Name.Function: ('green', 'brightgreen'),
Name.Namespace: ('_cyan_', '_brightcyan_'),
Name.Class: ('_green_', '_brightgreen_'),
Name.Exception: ('cyan', 'brightcyan'),
Name.Decorator: ('brightblack', 'gray'),
Name.Variable: ('red', 'brightred'),
Name.Constant: ('red', 'brightred'),
Name.Attribute: ('cyan', 'brightcyan'),
Name.Tag: ('brightblue', 'brightblue'),
String: ('yellow', 'yellow'),
Number: ('blue', 'brightblue'),
Generic.Deleted: ('brightred', 'brightred'),
Generic.Inserted: ('green', 'brightgreen'),
Generic.Heading: ('**', '**'),
Generic.Subheading: ('*magenta*', '*brightmagenta*'),
Generic.Error: ('brightred', 'brightred'),
Error: ('_brightred_', '_brightred_'),
}
IRC_COLOR_MAP = {
'white': 0,
'black': 1,
'blue': 2,
'brightgreen': 3,
'brightred': 4,
'yellow': 5,
'magenta': 6,
'orange': 7,
'green': 7, #compat w/ ansi
'brightyellow': 8,
'lightgreen': 9,
'brightcyan': 9, # compat w/ ansi
'cyan': 10,
'lightblue': 11,
'red': 11, # compat w/ ansi
'brightblue': 12,
'brightmagenta': 13,
'brightblack': 14,
'gray': 15,
}
def ircformat(color, text):
if len(color) < 1:
return text
add = sub = ''
if '_' in color: # italic
add += '\x1D'
sub = '\x1D' + sub
color = color.strip('_')
if '*' in color: # bold
add += '\x02'
sub = '\x02' + sub
color = color.strip('*')
# underline (\x1F) not supported
# backgrounds (\x03FF,BB) not supported
if len(color) > 0: # actual color - may have issues with ircformat("red", "blah")+"10" type stuff
add += '\x03' + str(IRC_COLOR_MAP[color]).zfill(2)
sub = '\x03' + sub
return add + text + sub
return '<'+add+'>'+text+'</'+sub+'>'
class IRCFormatter(Formatter):
r"""
Format tokens with IRC color sequences
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).
`linenos`
Set to ``True`` to have line numbers in the output as well
(default: ``False`` = no line numbers).
"""
name = 'IRC'
aliases = ['irc', 'IRC']
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 IRC_COLORS
self.linenos = options.get('linenos', False)
self._lineno = 0
def _write_lineno(self, outfile):
if self.linenos:
self._lineno += 1
outfile.write("%04d: " % self._lineno)
def format_unencoded(self, tokensource, outfile):
self._write_lineno(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(ircformat(color, line))
outfile.write('\n')
self._write_lineno(outfile)
if spl[-1]:
outfile.write(ircformat(color, spl[-1]))
else:
outfile.write(value)

View file

@ -0,0 +1,518 @@
"""
pygments.formatters.latex
~~~~~~~~~~~~~~~~~~~~~~~~~
Formatter for LaTeX fancyvrb output.
:copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from io import StringIO
from pygments.formatter import Formatter
from pygments.lexer import Lexer, do_insertions
from pygments.token import Token, STANDARD_TYPES
from pygments.util import get_bool_opt, get_int_opt
__all__ = ['LatexFormatter']
def escape_tex(text, commandprefix):
return text.replace('\\', '\x00'). \
replace('{', '\x01'). \
replace('}', '\x02'). \
replace('\x00', rf'\{commandprefix}Zbs{{}}'). \
replace('\x01', rf'\{commandprefix}Zob{{}}'). \
replace('\x02', rf'\{commandprefix}Zcb{{}}'). \
replace('^', rf'\{commandprefix}Zca{{}}'). \
replace('_', rf'\{commandprefix}Zus{{}}'). \
replace('&', rf'\{commandprefix}Zam{{}}'). \
replace('<', rf'\{commandprefix}Zlt{{}}'). \
replace('>', rf'\{commandprefix}Zgt{{}}'). \
replace('#', rf'\{commandprefix}Zsh{{}}'). \
replace('%', rf'\{commandprefix}Zpc{{}}'). \
replace('$', rf'\{commandprefix}Zdl{{}}'). \
replace('-', rf'\{commandprefix}Zhy{{}}'). \
replace("'", rf'\{commandprefix}Zsq{{}}'). \
replace('"', rf'\{commandprefix}Zdq{{}}'). \
replace('~', rf'\{commandprefix}Zti{{}}')
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}
Wrapping can be disabled using the `nowrap` option.
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:
`nowrap`
If set to ``True``, don't wrap the tokens at all, not even inside a
``\begin{Verbatim}`` environment. This disables most other options
(default: ``False``).
`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'``).
.. versionadded:: 0.7
.. versionchanged:: 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``).
.. versionadded:: 1.2
`mathescape`
If set to ``True``, enables LaTeX math mode escape in comments. That
is, ``'$...$'`` inside a comment will trigger math mode (default:
``False``).
.. versionadded:: 1.2
`escapeinside`
If set to a string of length 2, enables escaping to LaTeX. Text
delimited by these 2 characters is read as LaTeX code and
typeset accordingly. It has no effect in string literals. It has
no effect in comments if `texcomments` or `mathescape` is
set. (default: ``''``).
.. versionadded:: 2.0
`envname`
Allows you to pick an alternative environment name replacing Verbatim.
The alternate environment still has to support Verbatim's option syntax.
(default: ``'Verbatim'``).
.. versionadded:: 2.0
"""
name = 'LaTeX'
aliases = ['latex', 'tex']
filenames = ['*.tex']
def __init__(self, **options):
Formatter.__init__(self, **options)
self.nowrap = get_bool_opt(options, 'nowrap', False)
self.docclass = options.get('docclass', 'article')
self.preamble = options.get('preamble', '')
self.linenos = get_bool_opt(options, 'linenos', False)
self.linenostart = abs(get_int_opt(options, 'linenostart', 1))
self.linenostep = abs(get_int_opt(options, 'linenostep', 1))
self.verboptions = options.get('verboptions', '')
self.nobackground = get_bool_opt(options, 'nobackground', False)
self.commandprefix = options.get('commandprefix', 'PY')
self.texcomments = get_bool_opt(options, 'texcomments', False)
self.mathescape = get_bool_opt(options, 'mathescape', False)
self.escapeinside = options.get('escapeinside', '')
if len(self.escapeinside) == 2:
self.left = self.escapeinside[0]
self.right = self.escapeinside[1]
else:
self.escapeinside = ''
self.envname = options.get('envname', 'Verbatim')
self._create_stylesheet()
def _create_stylesheet(self):
t2n = self.ttype2name = {Token: ''}
c2d = self.cmd2def = {}
cp = self.commandprefix
def rgbcolor(col):
if col:
return ','.join(['%.2f' % (int(col[i] + col[i + 1], 16) / 255.0)
for i in (0, 2, 4)])
else:
return '1,1,1'
for ttype, ndef in self.style:
name = _get_ttype_name(ttype)
cmndef = ''
if ndef['bold']:
cmndef += r'\let\$$@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]{{{}}}{{##1}}}}'.format(rgbcolor(ndef['color'])))
if ndef['border']:
cmndef += (r'\def\$$@bc##1{{{{\setlength{{\fboxsep}}{{\string -\fboxrule}}'
r'\fcolorbox[rgb]{{{}}}{{{}}}{{\strut ##1}}}}}}'.format(rgbcolor(ndef['border']),
rgbcolor(ndef['bgcolor'])))
elif ndef['bgcolor']:
cmndef += (r'\def\$$@bc##1{{{{\setlength{{\fboxsep}}{{0pt}}'
r'\colorbox[rgb]{{{}}}{{\strut ##1}}}}}}'.format(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.items():
styles.append(rf'\@namedef{{{cp}@tok@{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()
if not self.nowrap:
outfile.write('\\begin{' + self.envname + '}[commandchars=\\\\\\{\\}')
if self.linenos:
start, step = self.linenostart, self.linenostep
outfile.write(',numbers=left' +
(start and ',firstnumber=%d' % start or '') +
(step and ',stepnumber=%d' % step or ''))
if self.mathescape or self.texcomments or self.escapeinside:
outfile.write(',codes={\\catcode`\\$=3\\catcode`\\^=7'
'\\catcode`\\_=8\\relax}')
if self.verboptions:
outfile.write(',' + self.verboptions)
outfile.write(']\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 range(1, len(value)):
if start[0] != value[i]:
break
start += value[i]
value = value[len(start):]
start = escape_tex(start, cp)
# ... but do not escape inside comment.
value = start + value
elif self.mathescape:
# Only escape parts not inside a math environment.
parts = value.split('$')
in_math = False
for i, part in enumerate(parts):
if not in_math:
parts[i] = escape_tex(part, cp)
in_math = not in_math
value = '$'.join(parts)
elif self.escapeinside:
text = value
value = ''
while text:
a, sep1, text = text.partition(self.left)
if sep1:
b, sep2, text = text.partition(self.right)
if sep2:
value += escape_tex(a, cp) + b
else:
value += escape_tex(a + sep1 + b, cp)
else:
value += escape_tex(a, cp)
else:
value = escape_tex(value, cp)
elif ttype not in Token.Escape:
value = escape_tex(value, cp)
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(f"\\{cp}{{{styleval}}}{{{line}}}")
outfile.write('\n')
if spl[-1]:
outfile.write(f"\\{cp}{{{styleval}}}{{{spl[-1]}}}")
else:
outfile.write(value)
if not self.nowrap:
outfile.write('\\end{' + self.envname + '}\n')
if self.full:
encoding = self.encoding or 'utf8'
# map known existings encodings from LaTeX distribution
encoding = {
'utf_8': 'utf8',
'latin_1': 'latin1',
'iso_8859_1': 'latin1',
}.get(encoding.replace('-', '_'), encoding)
realoutfile.write(DOC_TEMPLATE %
dict(docclass = self.docclass,
preamble = self.preamble,
title = self.title,
encoding = encoding,
styledefs = self.get_style_defs(),
code = outfile.getvalue()))
class LatexEmbeddedLexer(Lexer):
"""
This lexer takes one lexer as argument, the lexer for the language
being formatted, and the left and right delimiters for escaped text.
First everything is scanned using the language lexer to obtain
strings and comments. All other consecutive tokens are merged and
the resulting text is scanned for escaped segments, which are given
the Token.Escape type. Finally text that is not escaped is scanned
again with the language lexer.
"""
def __init__(self, left, right, lang, **options):
self.left = left
self.right = right
self.lang = lang
Lexer.__init__(self, **options)
def get_tokens_unprocessed(self, text):
# find and remove all the escape tokens (replace with an empty string)
# this is very similar to DelegatingLexer.get_tokens_unprocessed.
buffered = ''
insertions = []
insertion_buf = []
for i, t, v in self._find_safe_escape_tokens(text):
if t is None:
if insertion_buf:
insertions.append((len(buffered), insertion_buf))
insertion_buf = []
buffered += v
else:
insertion_buf.append((i, t, v))
if insertion_buf:
insertions.append((len(buffered), insertion_buf))
return do_insertions(insertions,
self.lang.get_tokens_unprocessed(buffered))
def _find_safe_escape_tokens(self, text):
""" find escape tokens that are not in strings or comments """
for i, t, v in self._filter_to(
self.lang.get_tokens_unprocessed(text),
lambda t: t in Token.Comment or t in Token.String
):
if t is None:
for i2, t2, v2 in self._find_escape_tokens(v):
yield i + i2, t2, v2
else:
yield i, None, v
def _filter_to(self, it, pred):
""" Keep only the tokens that match `pred`, merge the others together """
buf = ''
idx = 0
for i, t, v in it:
if pred(t):
if buf:
yield idx, None, buf
buf = ''
yield i, t, v
else:
if not buf:
idx = i
buf += v
if buf:
yield idx, None, buf
def _find_escape_tokens(self, text):
""" Find escape tokens within text, give token=None otherwise """
index = 0
while text:
a, sep1, text = text.partition(self.left)
if a:
yield index, None, a
index += len(a)
if sep1:
b, sep2, text = text.partition(self.right)
if sep2:
yield index + len(sep1), Token.Escape, b
index += len(sep1) + len(b) + len(sep2)
else:
yield index, Token.Error, sep1
index += len(sep1)
text = b

View file

@ -0,0 +1,160 @@
"""
pygments.formatters.other
~~~~~~~~~~~~~~~~~~~~~~~~~
Other formatters: NullFormatter, RawTokenFormatter.
:copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pygments.formatter import Formatter
from pygments.util import get_choice_opt
from pygments.token import Token
from pygments.console import colorize
__all__ = ['NullFormatter', 'RawTokenFormatter', 'TestcaseFormatter']
class NullFormatter(Formatter):
"""
Output the text unchanged without any formatting.
"""
name = 'Text only'
aliases = ['text', 'null']
filenames = ['*.txt']
def format(self, tokensource, outfile):
enc = self.encoding
for ttype, value in tokensource:
if enc:
outfile.write(value.encode(enc))
else:
outfile.write(value)
class RawTokenFormatter(Formatter):
r"""
Format tokens as a raw representation for storing token streams.
The format is ``tokentype<TAB>repr(tokenstring)\n``. The output can later
be converted to a token stream with the `RawTokenLexer`, described in the
:doc:`lexer list <lexers>`.
Only two options are accepted:
`compress`
If set to ``'gz'`` or ``'bz2'``, compress the output with the given
compression algorithm after encoding (default: ``''``).
`error_color`
If set to a color name, highlight error tokens using that color. If
set but with no value, defaults to ``'red'``.
.. versionadded:: 0.11
"""
name = 'Raw tokens'
aliases = ['raw', 'tokens']
filenames = ['*.raw']
unicodeoutput = False
def __init__(self, **options):
Formatter.__init__(self, **options)
# We ignore self.encoding if it is set, since it gets set for lexer
# and formatter if given with -Oencoding on the command line.
# The RawTokenFormatter outputs only ASCII. Override here.
self.encoding = 'ascii' # let pygments.format() do the right thing
self.compress = get_choice_opt(options, 'compress',
['', 'none', 'gz', 'bz2'], '')
self.error_color = options.get('error_color', None)
if self.error_color is True:
self.error_color = 'red'
if self.error_color is not None:
try:
colorize(self.error_color, '')
except KeyError:
raise ValueError(f"Invalid color {self.error_color!r} specified")
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)
write = outfile.write
flush = outfile.close
elif self.compress == 'bz2':
import bz2
compressor = bz2.BZ2Compressor(9)
def write(text):
outfile.write(compressor.compress(text))
def flush():
outfile.write(compressor.flush())
outfile.flush()
else:
write = outfile.write
flush = outfile.flush
if self.error_color:
for ttype, value in tokensource:
line = b"%r\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(b"%r\t%r\n" % (ttype, value))
flush()
TESTCASE_BEFORE = '''\
def testNeedsName(lexer):
fragment = %r
tokens = [
'''
TESTCASE_AFTER = '''\
]
assert list(lexer.get_tokens(fragment)) == tokens
'''
class TestcaseFormatter(Formatter):
"""
Format tokens as appropriate for a new testcase.
.. versionadded:: 2.0
"""
name = 'Testcase'
aliases = ['testcase']
def __init__(self, **options):
Formatter.__init__(self, **options)
if self.encoding is not None and self.encoding != 'utf-8':
raise ValueError("Only None and utf-8 are allowed encodings.")
def format(self, tokensource, outfile):
indentation = ' ' * 12
rawbuf = []
outbuf = []
for ttype, value in tokensource:
rawbuf.append(value)
outbuf.append(f'{indentation}({ttype}, {value!r}),\n')
before = TESTCASE_BEFORE % (''.join(rawbuf),)
during = ''.join(outbuf)
after = TESTCASE_AFTER
if self.encoding is None:
outfile.write(before + during + after)
else:
outfile.write(before.encode('utf-8'))
outfile.write(during.encode('utf-8'))
outfile.write(after.encode('utf-8'))
outfile.flush()

View file

@ -0,0 +1,83 @@
"""
pygments.formatters.pangomarkup
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Formatter for Pango markup output.
:copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pygments.formatter import Formatter
__all__ = ['PangoMarkupFormatter']
_escape_table = {
ord('&'): '&amp;',
ord('<'): '&lt;',
}
def escape_special_chars(text, table=_escape_table):
"""Escape & and < for Pango Markup."""
return text.translate(table)
class PangoMarkupFormatter(Formatter):
"""
Format tokens as Pango Markup code. It can then be rendered to an SVG.
.. versionadded:: 2.9
"""
name = 'Pango Markup'
aliases = ['pango', 'pangomarkup']
filenames = []
def __init__(self, **options):
Formatter.__init__(self, **options)
self.styles = {}
for token, style in self.style:
start = ''
end = ''
if style['color']:
start += '<span fgcolor="#{}">'.format(style['color'])
end = '</span>' + end
if style['bold']:
start += '<b>'
end = '</b>' + end
if style['italic']:
start += '<i>'
end = '</i>' + end
if style['underline']:
start += '<u>'
end = '</u>' + end
self.styles[token] = (start, end)
def format_unencoded(self, tokensource, outfile):
lastval = ''
lasttype = None
outfile.write('<tt>')
for ttype, value in tokensource:
while ttype not in self.styles:
ttype = ttype.parent
if ttype == lasttype:
lastval += escape_special_chars(value)
else:
if lastval:
stylebegin, styleend = self.styles[lasttype]
outfile.write(stylebegin + lastval + styleend)
lastval = escape_special_chars(value)
lasttype = ttype
if lastval:
stylebegin, styleend = self.styles[lasttype]
outfile.write(stylebegin + lastval + styleend)
outfile.write('</tt>')

View file

@ -0,0 +1,349 @@
"""
pygments.formatters.rtf
~~~~~~~~~~~~~~~~~~~~~~~
A formatter that generates RTF files.
:copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from collections import OrderedDict
from pygments.formatter import Formatter
from pygments.style import _ansimap
from pygments.util import get_bool_opt, get_int_opt, get_list_opt, surrogatepair
__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(R) Word(R) documents.
Please note that ``encoding`` and ``outencoding`` options are ignored.
The RTF format is ASCII natively, but handles unicode characters correctly
thanks to escape sequences.
.. versionadded:: 0.6
Additional options accepted:
`style`
The style to use, can be a string or a Style subclass (default:
``'default'``).
`fontface`
The used font family, for example ``Bitstream Vera Sans``. Defaults to
some generic font which is supposed to have fixed width.
`fontsize`
Size of the font used. Size is specified in half points. The
default is 24 half-points, giving a size 12 font.
.. versionadded:: 2.0
`linenos`
Turn on line numbering (default: ``False``).
.. versionadded:: 2.18
`lineno_fontsize`
Font size for line numbers. Size is specified in half points
(default: `fontsize`).
.. versionadded:: 2.18
`lineno_padding`
Number of spaces between the (inline) line numbers and the
source code (default: ``2``).
.. versionadded:: 2.18
`linenostart`
The line number for the first line (default: ``1``).
.. versionadded:: 2.18
`linenostep`
If set to a number n > 1, only every nth line number is printed.
.. versionadded:: 2.18
`lineno_color`
Color for line numbers specified as a hex triplet, e.g. ``'5e5e5e'``.
Defaults to the style's line number color if it is a hex triplet,
otherwise ansi bright black.
.. versionadded:: 2.18
`hl_lines`
Specify a list of lines to be highlighted, as line numbers separated by
spaces, e.g. ``'3 7 8'``. The line numbers are relative to the input
(i.e. the first line is line 1) unless `hl_linenostart` is set.
.. versionadded:: 2.18
`hl_color`
Color for highlighting the lines specified in `hl_lines`, specified as
a hex triplet (default: style's `highlight_color`).
.. versionadded:: 2.18
`hl_linenostart`
If set to ``True`` line numbers in `hl_lines` are specified
relative to `linenostart` (default ``False``).
.. versionadded:: 2.18
"""
name = 'RTF'
aliases = ['rtf']
filenames = ['*.rtf']
def __init__(self, **options):
r"""
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 ''
self.fontsize = get_int_opt(options, 'fontsize', 0)
self.linenos = get_bool_opt(options, 'linenos', False)
self.lineno_fontsize = get_int_opt(options, 'lineno_fontsize',
self.fontsize)
self.lineno_padding = get_int_opt(options, 'lineno_padding', 2)
self.linenostart = abs(get_int_opt(options, 'linenostart', 1))
self.linenostep = abs(get_int_opt(options, 'linenostep', 1))
self.hl_linenostart = get_bool_opt(options, 'hl_linenostart', False)
self.hl_color = options.get('hl_color', '')
if not self.hl_color:
self.hl_color = self.style.highlight_color
self.hl_lines = []
for lineno in get_list_opt(options, 'hl_lines', []):
try:
lineno = int(lineno)
if self.hl_linenostart:
lineno = lineno - self.linenostart + 1
self.hl_lines.append(lineno)
except ValueError:
pass
self.lineno_color = options.get('lineno_color', '')
if not self.lineno_color:
if self.style.line_number_color == 'inherit':
# style color is the css value 'inherit'
# default to ansi bright-black
self.lineno_color = _ansimap['ansibrightblack']
else:
# style color is assumed to be a hex triplet as other
# colors in pygments/style.py
self.lineno_color = self.style.line_number_color
self.color_mapping = self._create_color_mapping()
def _escape(self, text):
return text.replace('\\', '\\\\') \
.replace('{', '\\{') \
.replace('}', '\\}')
def _escape_text(self, text):
# empty strings, should give a small performance improvement
if not text:
return ''
# escape text
text = self._escape(text)
buf = []
for c in text:
cn = ord(c)
if cn < (2**7):
# ASCII character
buf.append(str(c))
elif (2**7) <= cn < (2**16):
# single unicode escape sequence
buf.append('{\\u%d}' % cn)
elif (2**16) <= cn:
# RTF limits unicode to 16 bits.
# Force surrogate pairs
buf.append('{\\u%d}{\\u%d}' % surrogatepair(cn))
return ''.join(buf).replace('\n', '\\par')
@staticmethod
def hex_to_rtf_color(hex_color):
if hex_color[0] == "#":
hex_color = hex_color[1:]
return '\\red%d\\green%d\\blue%d;' % (
int(hex_color[0:2], 16),
int(hex_color[2:4], 16),
int(hex_color[4:6], 16)
)
def _split_tokens_on_newlines(self, tokensource):
"""
Split tokens containing newline characters into multiple token
each representing a line of the input file. Needed for numbering
lines of e.g. multiline comments.
"""
for ttype, value in tokensource:
if value == '\n':
yield (ttype, value)
elif "\n" in value:
lines = value.split("\n")
for line in lines[:-1]:
yield (ttype, line+"\n")
if lines[-1]:
yield (ttype, lines[-1])
else:
yield (ttype, value)
def _create_color_mapping(self):
"""
Create a mapping of style hex colors to index/offset in
the RTF color table.
"""
color_mapping = OrderedDict()
offset = 1
if self.linenos:
color_mapping[self.lineno_color] = offset
offset += 1
if self.hl_lines:
color_mapping[self.hl_color] = offset
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
offset += 1
return color_mapping
@property
def _lineno_template(self):
if self.lineno_fontsize != self.fontsize:
return '{{\\fs{} \\cf{} %s{}}}'.format(self.lineno_fontsize,
self.color_mapping[self.lineno_color],
" " * self.lineno_padding)
return '{{\\cf{} %s{}}}'.format(self.color_mapping[self.lineno_color],
" " * self.lineno_padding)
@property
def _hl_open_str(self):
return rf'{{\highlight{self.color_mapping[self.hl_color]} '
@property
def _rtf_header(self):
lines = []
# rtf 1.8 header
lines.append('{\\rtf1\\ansi\\uc0\\deff0'
'{\\fonttbl{\\f0\\fmodern\\fprq1\\fcharset0%s;}}'
% (self.fontface and ' '
+ self._escape(self.fontface) or ''))
# color table
lines.append('{\\colortbl;')
for color, _ in self.color_mapping.items():
lines.append(self.hex_to_rtf_color(color))
lines.append('}')
# font and fontsize
lines.append('\\f0\\sa0')
if self.fontsize:
lines.append('\\fs%d' % self.fontsize)
# ensure Libre Office Writer imports and renders consecutive
# space characters the same width, needed for line numbering.
# https://bugs.documentfoundation.org/show_bug.cgi?id=144050
lines.append('\\dntblnsbdb')
return lines
def format_unencoded(self, tokensource, outfile):
for line in self._rtf_header:
outfile.write(line + "\n")
tokensource = self._split_tokens_on_newlines(tokensource)
# first pass of tokens to count lines, needed for line numbering
if self.linenos:
line_count = 0
tokens = [] # for copying the token source generator
for ttype, value in tokensource:
tokens.append((ttype, value))
if value.endswith("\n"):
line_count += 1
# width of line number strings (for padding with spaces)
linenos_width = len(str(line_count+self.linenostart-1))
tokensource = tokens
# highlight stream
lineno = 1
start_new_line = True
for ttype, value in tokensource:
if start_new_line and lineno in self.hl_lines:
outfile.write(self._hl_open_str)
if start_new_line and self.linenos:
if (lineno-self.linenostart+1)%self.linenostep == 0:
current_lineno = lineno + self.linenostart - 1
lineno_str = str(current_lineno).rjust(linenos_width)
else:
lineno_str = "".rjust(linenos_width)
outfile.write(self._lineno_template % lineno_str)
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('\\cb%d' % self.color_mapping[style['bgcolor']])
if style['color']:
buf.append('\\cf%d' % self.color_mapping[style['color']])
if style['bold']:
buf.append('\\b')
if style['italic']:
buf.append('\\i')
if style['underline']:
buf.append('\\ul')
if style['border']:
buf.append('\\chbrdr\\chcfpat%d' %
self.color_mapping[style['border']])
start = ''.join(buf)
if start:
outfile.write(f'{{{start} ')
outfile.write(self._escape_text(value))
if start:
outfile.write('}')
start_new_line = False
# complete line of input
if value.endswith("\n"):
# close line highlighting
if lineno in self.hl_lines:
outfile.write('}')
# newline in RTF file after closing }
outfile.write("\n")
start_new_line = True
lineno += 1
outfile.write('}\n')

View file

@ -0,0 +1,185 @@
"""
pygments.formatters.svg
~~~~~~~~~~~~~~~~~~~~~~~
Formatter for SVG output.
:copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
from pygments.formatter import Formatter
from pygments.token import Comment
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.
.. versionadded:: 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"``.
`linenos`
If ``True``, add 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.
`linenowidth`
Maximum width devoted to line numbers (default: ``3*ystep``, sufficient
for up to 4-digit line numbers. Increase width for longer code blocks).
`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):
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 ValueError:
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.linenos = get_bool_opt(options,'linenos',False)
self.linenostart = get_int_opt(options,'linenostart',1)
self.linenostep = get_int_opt(options,'linenostep',1)
self.linenowidth = get_int_opt(options,'linenowidth', 3*self.ystep)
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(f'<?xml version="1.0" encoding="{self.encoding}"?>\n')
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(f'<g font-family="{self.fontfamily}" font-size="{self.fontsize}">\n')
counter = self.linenostart
counter_step = self.linenostep
counter_style = self._get_style(Comment)
line_x = x
if self.linenos:
if counter % counter_step == 0:
outfile.write(f'<text x="{x+self.linenowidth}" y="{y}" {counter_style} text-anchor="end">{counter}</text>')
line_x += self.linenowidth + self.ystep
counter += 1
outfile.write(f'<text x="{line_x}" y="{y}" xml:space="preserve">')
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')
if self.linenos and counter % counter_step == 0:
outfile.write(f'<text x="{x+self.linenowidth}" y="{y}" text-anchor="end" {counter_style}>{counter}</text>')
counter += 1
outfile.write(f'<text x="{line_x}" y="{y}" ' 'xml:space="preserve">')
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 +1,127 @@
"""
pygments.formatters.terminal
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Formatter for terminal output with ANSI sequences.
:copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
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: ('gray', 'brightblack'),
Comment: ('gray', 'brightblack'),
Comment.Preproc: ('cyan', 'brightcyan'),
Keyword: ('blue', 'brightblue'),
Keyword.Type: ('cyan', 'brightcyan'),
Operator.Word: ('magenta', 'brightmagenta'),
Name.Builtin: ('cyan', 'brightcyan'),
Name.Function: ('green', 'brightgreen'),
Name.Namespace: ('_cyan_', '_brightcyan_'),
Name.Class: ('_green_', '_brightgreen_'),
Name.Exception: ('cyan', 'brightcyan'),
Name.Decorator: ('brightblack', 'gray'),
Name.Variable: ('red', 'brightred'),
Name.Constant: ('red', 'brightred'),
Name.Attribute: ('cyan', 'brightcyan'),
Name.Tag: ('brightblue', 'brightblue'),
String: ('yellow', 'yellow'),
Number: ('blue', 'brightblue'),
Generic.Deleted: ('brightred', 'brightred'),
Generic.Inserted: ('green', 'brightgreen'),
Generic.Heading: ('**', '**'),
Generic.Subheading: ('*magenta*', '*brightmagenta*'),
Generic.Prompt: ('**', '**'),
Generic.Error: ('brightred', 'brightred'),
Error: ('_brightred_', '_brightred_'),
}
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).
`linenos`
Set to ``True`` to have line numbers on the terminal output as well
(default: ``False`` = no line numbers).
"""
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
self.linenos = options.get('linenos', False)
self._lineno = 0
def format(self, tokensource, outfile):
return Formatter.format(self, tokensource, outfile)
def _write_lineno(self, outfile):
self._lineno += 1
outfile.write("%s%04d: " % (self._lineno != 1 and '\n' or '', self._lineno))
def _get_color(self, ttype):
# self.colorscheme is a dict containing usually generic types, so we
# have to walk the tree of dots. The base Token type must be a key,
# even if it's empty string, as in the default above.
colors = self.colorscheme.get(ttype)
while colors is None:
ttype = ttype.parent
colors = self.colorscheme.get(ttype)
return colors[self.darkbg]
def format_unencoded(self, tokensource, outfile):
if self.linenos:
self._write_lineno(outfile)
for ttype, value in tokensource:
color = self._get_color(ttype)
for line in value.splitlines(True):
if color:
outfile.write(ansiformat(color, line.rstrip('\n')))
else:
outfile.write(line.rstrip('\n'))
if line.endswith('\n'):
if self.linenos:
self._write_lineno(outfile)
else:
outfile.write('\n')
if self.linenos:
outfile.write("\n")

View file

@ -0,0 +1,338 @@
"""
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 2006-2024 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...
from pygments.formatter import Formatter
from pygments.console import codes
from pygments.style import ansicolors
__all__ = ['Terminal256Formatter', 'TerminalTrueColorFormatter']
class EscapeSequence:
def __init__(self, fg=None, bg=None, bold=False, underline=False, italic=False):
self.fg = fg
self.bg = bg
self.bold = bold
self.underline = underline
self.italic = italic
def escape(self, attrs):
if len(attrs):
return "\x1b[" + ";".join(attrs) + "m"
return ""
def color_string(self):
attrs = []
if self.fg is not None:
if self.fg in ansicolors:
esc = codes[self.fg.replace('ansi','')]
if ';01m' in esc:
self.bold = True
# extract fg color code.
attrs.append(esc[2:4])
else:
attrs.extend(("38", "5", "%i" % self.fg))
if self.bg is not None:
if self.bg in ansicolors:
esc = codes[self.bg.replace('ansi','')]
# extract fg color code, add 10 for bg.
attrs.append(str(int(esc[2:4])+10))
else:
attrs.extend(("48", "5", "%i" % self.bg))
if self.bold:
attrs.append("01")
if self.underline:
attrs.append("04")
if self.italic:
attrs.append("03")
return self.escape(attrs)
def true_color_string(self):
attrs = []
if self.fg:
attrs.extend(("38", "2", str(self.fg[0]), str(self.fg[1]), str(self.fg[2])))
if self.bg:
attrs.extend(("48", "2", str(self.bg[0]), str(self.bg[1]), str(self.bg[2])))
if self.bold:
attrs.append("01")
if self.underline:
attrs.append("04")
if self.italic:
attrs.append("03")
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 or self.italic:
attrs.append("00")
return self.escape(attrs)
class Terminal256Formatter(Formatter):
"""
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).
.. versionadded:: 0.9
.. versionchanged:: 2.2
If the used style defines foreground colors in the form ``#ansi*``, then
`Terminal256Formatter` will map these to non extended foreground color.
See :ref:`AnsiTerminalStyle` for more information.
.. versionchanged:: 2.4
The ANSI color names have been updated with names that are easier to
understand and align with colornames of other projects and terminals.
See :ref:`this table <new-ansi-color-names>` for more information.
Options accepted:
`style`
The style to use, can be a string or a Style subclass (default:
``'default'``).
`linenos`
Set to ``True`` to have line numbers on the terminal output as well
(default: ``False`` = no line numbers).
"""
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.useitalic = 'noitalic' 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
self.linenos = options.get('linenos', False)
self._lineno = 0
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 color in ansicolors:
# strip the `ansi/#ansi` part and look up code
index = color
self.best_match[color] = index
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()
# get foreground from ansicolor if set
if ndef['ansicolor']:
escape.fg = self._color_index(ndef['ansicolor'])
elif ndef['color']:
escape.fg = self._color_index(ndef['color'])
if ndef['bgansicolor']:
escape.bg = self._color_index(ndef['bgansicolor'])
elif 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
if self.useitalic and ndef['italic']:
escape.italic = True
self.style_string[str(ttype)] = (escape.color_string(),
escape.reset_string())
def _write_lineno(self, outfile):
self._lineno += 1
outfile.write("%s%04d: " % (self._lineno != 1 and '\n' or '', self._lineno))
def format(self, tokensource, outfile):
return Formatter.format(self, tokensource, outfile)
def format_unencoded(self, tokensource, outfile):
if self.linenos:
self._write_lineno(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)
if self.linenos:
self._write_lineno(outfile)
else:
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.parent
# outfile.write( '!' + str(ottype) + '->' + str(ttype) + '!' )
if not_found:
outfile.write(value)
if self.linenos:
outfile.write("\n")
class TerminalTrueColorFormatter(Terminal256Formatter):
r"""
Format tokens with ANSI color sequences, for output in a true-color
terminal or console. Like in `TerminalFormatter` color sequences
are terminated at newlines, so that paging the output works correctly.
.. versionadded:: 2.1
Options accepted:
`style`
The style to use, can be a string or a Style subclass (default:
``'default'``).
"""
name = 'TerminalTrueColor'
aliases = ['terminal16m', 'console16m', '16m']
filenames = []
def _build_color_table(self):
pass
def _color_tuple(self, color):
try:
rgb = int(str(color), 16)
except ValueError:
return None
r = (rgb >> 16) & 0xff
g = (rgb >> 8) & 0xff
b = rgb & 0xff
return (r, g, b)
def _setup_styles(self):
for ttype, ndef in self.style:
escape = EscapeSequence()
if ndef['color']:
escape.fg = self._color_tuple(ndef['color'])
if ndef['bgcolor']:
escape.bg = self._color_tuple(ndef['bgcolor'])
if self.usebold and ndef['bold']:
escape.bold = True
if self.useunderline and ndef['underline']:
escape.underline = True
if self.useitalic and ndef['italic']:
escape.italic = True
self.style_string[str(ttype)] = (escape.true_color_string(),
escape.reset_string())