annotate hgext/highlight/highlight.py @ 51863:f4733654f144

typing: add `from __future__ import annotations` to most files

Now that py36 is no longer supported, we can postpone annotation evaluation.
This means that the quoting is usually optional (for things imported under the
guard of `if typing.TYPE_CHECKING:` to avoid circular imports), and there's less
overhead on startup[1].

There may be some missing here.  I backed out 6000f5b25c9b (which removed the
`from __future__ import ...` that was supporting py2), reverted the changes in
`contrib/`, `doc/`, and `tests/`, and then ran:

    $ hg status -n --change . | \
        xargs sed -i -e 's/from __future__ import .*$/from __future__ import annotations/'

There were some minor tweaks needed when reviewing (mostly making the spacing
around the import consistent, and `mercurial/testing/__init__.py` had a
multiline import that wasn't fully rewritten.

[1] https://docs.python.org/3/whatsnew/3.7.html#pep-563-postponed-evaluation-of-annotations

# highlight.py - highlight extension implementation file
#
#  Copyright 2007-2009 Adam Hupp <[e-mail]> and others
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
#
# The original module was split in an interface and an implementation
# file to defer pygments loading and speedup extension setup.

from __future__ import annotations

from mercurial import demandimport

demandimport.IGNORES.update(['pkgutil', 'pkg_resources', '__main__'])

from mercurial import (
    encoding,
    pycompat,
)

from mercurial.utils import stringutil

with demandimport.deactivated():
    import pygments
    import pygments.formatters
    import pygments.lexers
    import pygments.plugin
    import pygments.util

    for unused in pygments.plugin.find_plugin_lexers():
        pass

highlight = pygments.highlight
ClassNotFound = pygments.util.ClassNotFound
guess_lexer = pygments.lexers.guess_lexer
guess_lexer_for_filename = pygments.lexers.guess_lexer_for_filename
TextLexer = pygments.lexers.TextLexer
HtmlFormatter = pygments.formatters.HtmlFormatter

SYNTAX_CSS = (
    b'\n<link rel="stylesheet" href="{url}highlightcss" type="text/css" />'
)


def pygmentize(field, fctx, style, tmpl, guessfilenameonly=False):
    # append a <link ...> to the syntax highlighting css
    tmpl.load(b'header')
    old_header = tmpl.cache[b'header']
    if SYNTAX_CSS not in old_header:
        new_header = old_header + SYNTAX_CSS
        tmpl.cache[b'header'] = new_header

    text = fctx.data()
    if stringutil.binary(text):
        return

    # str.splitlines() != unicode.splitlines() because "reasons"
    for c in b"\x0c", b"\x1c", b"\x1d", b"\x1e":
        if c in text:
            text = text.replace(c, b'')

    # Pygments is best used with Unicode strings:
    # <http://pygments.org/docs/unicode/>
    text = text.decode(pycompat.sysstr(encoding.encoding), 'replace')

    # To get multi-line strings right, we can't format line-by-line
    try:
        path = pycompat.sysstr(fctx.path())
        lexer = guess_lexer_for_filename(path, text[:1024], stripnl=False)
    except (ClassNotFound, ValueError):
        # guess_lexer will return a lexer if *any* lexer matches. There is
        # no way to specify a minimum match score. This can give a high rate of
        # false positives on files with an unknown filename pattern.
        if guessfilenameonly:
            return

        try:
            lexer = guess_lexer(text[:1024], stripnl=False)
        except (ClassNotFound, ValueError):
            # Don't highlight unknown files
            return

    # Don't highlight text files
    if isinstance(lexer, TextLexer):
        return

    formatter = HtmlFormatter(nowrap=True, style=pycompat.sysstr(style))

    colorized = highlight(text, lexer, formatter)
    coloriter = (
        s.encode(pycompat.sysstr(encoding.encoding), 'replace')
        for s in colorized.splitlines()
    )

    tmpl._filters[b'colorize'] = lambda x: next(coloriter)

    oldl = tmpl.cache[field]
    newl = oldl.replace(b'line|escape', b'line|colorize')
    tmpl.cache[field] = newl