view hgext/highlight/__init__.py @ 33649:377e8ddaebef stable

pathauditor: disable cache of audited paths by default (issue5628)

The initial attempt was to discard cache when appropriate, but it appears
to be error prone. We had to carefully inspect all places where audit() is
called e.g. without actually updating filesystem, before removing files and
directories, etc.

So, this patch disables the cache of audited paths by default, and enables
it only for the following cases:

 - short-lived auditor objects
 - repo.vfs, repo.svfs, and repo.cachevfs, which are managed directories
   and considered sort of append-only (a file/directory would never be
   replaced with a symlink)

There would be more cacheable vfs objects (e.g. mq.queue.opener), but I
decided not to inspect all of them in this patch. We can make them cached
later.

Benchmark result:

- using old clone of http://selenic.com/repo/linux-2.6/ (38319 files)
- on tmpfs
- run HGRCPATH=/dev/null hg up -q --time tip && hg up -q null
- try 4 times and take the last three results

original:
real 7.480 secs (user 1.140+22.760 sys 0.150+1.690)
real 8.010 secs (user 1.070+22.280 sys 0.170+2.120)
real 7.470 secs (user 1.120+22.390 sys 0.120+1.910)

clearcache (the other series):
real 7.680 secs (user 1.120+23.420 sys 0.140+1.970)
real 7.670 secs (user 1.110+23.620 sys 0.130+1.810)
real 7.740 secs (user 1.090+23.510 sys 0.160+1.940)

enable cache only for vfs and svfs (this series):
real 8.730 secs (user 1.500+25.190 sys 0.260+2.260)
real 8.750 secs (user 1.490+25.170 sys 0.250+2.340)
real 9.010 secs (user 1.680+25.340 sys 0.280+2.540)

remove cache function at all (for reference):
real 9.620 secs (user 1.440+27.120 sys 0.250+2.980)
real 9.420 secs (user 1.400+26.940 sys 0.320+3.130)
real 9.760 secs (user 1.530+27.270 sys 0.250+2.970)

# highlight - syntax highlighting in hgweb, based on Pygments
#
#  Copyright 2008, 2009 Patrick Mezard <[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.

"""syntax highlighting for hgweb (requires Pygments)

It depends on the Pygments syntax highlighting library:
http://pygments.org/

There are the following configuration options::

  [web]
  pygments_style = <style> (default: colorful)
  highlightfiles = <fileset> (default: size('<5M'))
  highlightonlymatchfilename = <bool> (default False)

``highlightonlymatchfilename`` will only highlight files if their type could
be identified by their filename. When this is not enabled (the default),
Pygments will try very hard to identify the file type from content and any
match (even matches with a low confidence score) will be used.
"""

from __future__ import absolute_import

from . import highlight
from mercurial.hgweb import (
    common,
    webcommands,
    webutil,
)

from mercurial import (
    encoding,
    extensions,
    fileset,
)

# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = 'ships-with-hg-core'

def pygmentize(web, field, fctx, tmpl):
    style = web.config('web', 'pygments_style', 'colorful')
    expr = web.config('web', 'highlightfiles', "size('<5M')")
    filenameonly = web.configbool('web', 'highlightonlymatchfilename', False)

    ctx = fctx.changectx()
    tree = fileset.parse(expr)
    mctx = fileset.matchctx(ctx, subset=[fctx.path()], status=None)
    if fctx.path() in fileset.getset(mctx, tree):
        highlight.pygmentize(field, fctx, style, tmpl,
                guessfilenameonly=filenameonly)

def filerevision_highlight(orig, web, req, tmpl, fctx):
    mt = ''.join(tmpl('mimetype', encoding=encoding.encoding))
    # only pygmentize for mimetype containing 'html' so we both match
    # 'text/html' and possibly 'application/xhtml+xml' in the future
    # so that we don't have to touch the extension when the mimetype
    # for a template changes; also hgweb optimizes the case that a
    # raw file is sent using rawfile() and doesn't call us, so we
    # can't clash with the file's content-type here in case we
    # pygmentize a html file
    if 'html' in mt:
        pygmentize(web, 'fileline', fctx, tmpl)

    return orig(web, req, tmpl, fctx)

def annotate_highlight(orig, web, req, tmpl):
    mt = ''.join(tmpl('mimetype', encoding=encoding.encoding))
    if 'html' in mt:
        fctx = webutil.filectx(web.repo, req)
        pygmentize(web, 'annotateline', fctx, tmpl)

    return orig(web, req, tmpl)

def generate_css(web, req, tmpl):
    pg_style = web.config('web', 'pygments_style', 'colorful')
    fmter = highlight.HtmlFormatter(style=pg_style)
    req.respond(common.HTTP_OK, 'text/css')
    return ['/* pygments_style = %s */\n\n' % pg_style,
            fmter.get_style_defs('')]

def extsetup():
    # monkeypatch in the new version
    extensions.wrapfunction(webcommands, '_filerevision',
                            filerevision_highlight)
    extensions.wrapfunction(webcommands, 'annotate', annotate_highlight)
    webcommands.highlightcss = generate_css
    webcommands.__all__.append('highlightcss')