hgext/highlight/highlight.py

localrepo: make invalidate avoid invalidating store inside transaction (API)

Before this patch, invalidate() discards in-memory fncache changes,
even inside transaction scope.

Such changes should be written out at closing transaction. Otherwise,
fncache might overlook newly added files. A file overlooked by
fncache isn't accessible via store vfs, even if it actually exists in
store.

On the other hand, a non-existing file in fncache is less harmful,
because fncachestore always examines whether a file actually exists or
not before access. Therefore, discarding in-memory changes can be
safely omitted.

It is typical case that repo.invalidate() in streamclone is executed
inside nested transaction.

This patch makes invalidate() avoid invalidating store inside
transaction.

This patch focuses on describing only how invalidate() changes own
behavior according to activity of transaction. Describing other detail
of invalidate() in docstr will be done in another series, which
refactors invalidate*() functions.

# 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 absolute_import

import pygments
import pygments.formatters
import pygments.lexers
import pygments.util

from mercurial import demandimport
demandimport.ignore.extend(['pkgutil', 'pkg_resources', '__main__'])

from mercurial import (
    encoding,
    util,
)

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 = ('\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
    old_header = tmpl.load('header')
    if SYNTAX_CSS not in old_header:
        new_header = old_header + SYNTAX_CSS
        tmpl.cache['header'] = new_header

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

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

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

    # To get multi-line strings right, we can't format line-by-line
    try:
        lexer = guess_lexer_for_filename(fctx.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=style)

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

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

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