bazarr/libs/pygments/formatter.py

"""
    pygments.formatter
    ~~~~~~~~~~~~~~~~~~

    Base formatter class.

    :copyright: Copyright 2006-2023 by the Pygments team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

import codecs

from pygments.util import get_bool_opt
from pygments.styles import get_style_by_name

__all__ = ['Formatter']


def _lookup_style(style):
    if isinstance(style, str):
        return get_style_by_name(style)
    return style


class Formatter:
    """
    Converts a token stream to text.

    Formatters should have attributes to help selecting them. These
    are similar to the corresponding :class:`~pygments.lexer.Lexer`
    attributes.

    .. autoattribute:: name
       :no-value:

    .. autoattribute:: aliases
       :no-value:

    .. autoattribute:: filenames
       :no-value:

    You can pass options as keyword arguments to the constructor.
    All formatters accept these basic options:

    ``style``
        The style to use, can be a string or a Style subclass
        (default: "default"). Not used by e.g. the
        TerminalFormatter.
    ``full``
        Tells the formatter to output a "full" document, i.e.
        a complete self-contained document. This doesn't have
        any effect for some formatters (default: false).
    ``title``
        If ``full`` is true, the title that should be used to
        caption the document (default: '').
    ``encoding``
        If given, must be an encoding name. This will be used to
        convert the Unicode token strings to byte strings in the
        output. If it is "" or None, Unicode strings will be written
        to the output file, which most file-like objects do not
        support (default: None).
    ``outencoding``
        Overrides ``encoding`` if given.

    """

    #: Full name for the formatter, in human-readable form.
    name = None

    #: A list of short, unique identifiers that can be used to lookup
    #: the formatter from a list, e.g. using :func:`.get_formatter_by_name()`.
    aliases = []

    #: A list of fnmatch patterns that match filenames for which this
    #: formatter can produce output. The patterns in this list should be unique
    #: among all formatters.
    filenames = []

    #: If True, this formatter outputs Unicode strings when no encoding
    #: option is given.
    unicodeoutput = True

    def __init__(self, **options):
        """
        As with lexers, this constructor takes arbitrary optional arguments,
        and if you override it, you should first process your own options, then
        call the base class implementation.
        """
        self.style = _lookup_style(options.get('style', 'default'))
        self.full = get_bool_opt(options, 'full', False)
        self.title = options.get('title', '')
        self.encoding = options.get('encoding', None) or None
        if self.encoding in ('guess', 'chardet'):
            # can happen for e.g. pygmentize -O encoding=guess
            self.encoding = 'utf-8'
        self.encoding = options.get('outencoding') or self.encoding
        self.options = options

    def get_style_defs(self, arg=''):
        """
        This method must return statements or declarations suitable to define
        the current style for subsequent highlighted text (e.g. CSS classes
        in the `HTMLFormatter`).

        The optional argument `arg` can be used to modify the generation and
        is formatter dependent (it is standardized because it can be given on
        the command line).

        This method is called by the ``-S`` :doc:`command-line option <cmdline>`,
        the `arg` is then given by the ``-a`` option.
        """
        return ''

    def format(self, tokensource, outfile):
        """
        This method must format the tokens from the `tokensource` iterable and
        write the formatted version to the file object `outfile`.

        Formatter options can control how exactly the tokens are converted.
        """
        if self.encoding:
            # wrap the outfile in a StreamWriter
            outfile = codecs.lookup(self.encoding)[3](outfile)
        return self.format_unencoded(tokensource, outfile)