view hgext/highlight/__init__.py @ 30817:2b279126b8f5

revlog: use compression engine APIs for decompression

Now that compression engines declare their header in revlog chunks
and can decompress revlog chunks, we refactor revlog.decompress()
to use them.

Making full use of the property that revlog compressor objects are
reusable, revlog instances now maintain a dict mapping an engine's
revlog header to a compressor object. This is not only a performance
optimization for engines where compressor object reuse can result in
better performance, but it also serves as a cache of header values
so we don't need to perform redundant lookups against the compression
engine manager. (Yes, I measured and the overhead of a function call
versus a dict lookup was observed.)

Replacing the previous inline lookup table with a dict lookup was
measured to make chunk reading ~2.5% slower on changelogs and ~4.5%
slower on manifests. So, the inline lookup table has been mostly
preserved so we don't lose performance. This is unfortunate. But
many decompression operations complete in microseconds, so Python
attribute lookup, dict lookup, and function calls do matter.

The impact of this change on mozilla-unified is as follows:

$ hg perfrevlogchunks -c
! chunk
! wall 1.953663 comb 1.950000 user 1.920000 sys 0.030000 (best of 6)
! wall 1.946000 comb 1.940000 user 1.910000 sys 0.030000 (best of 6)
! chunk batch
! wall 1.791075 comb 1.800000 user 1.760000 sys 0.040000 (best of 6)
! wall 1.785690 comb 1.770000 user 1.750000 sys 0.020000 (best of 6)

$ hg perfrevlogchunks -m
! chunk
! wall 2.587262 comb 2.580000 user 2.550000 sys 0.030000 (best of 4)
! wall 2.616330 comb 2.610000 user 2.560000 sys 0.050000 (best of 4)
! chunk batch
! wall 2.427092 comb 2.420000 user 2.400000 sys 0.020000 (best of 5)
! wall 2.462061 comb 2.460000 user 2.400000 sys 0.060000 (best of 4)

Changelog chunk reading is slightly faster but manifest reading is
slower. What gives?

On this repo, 99.85% of changelog entries are zlib compressed (the 'x'
header). On the manifest, 67.5% are zlib and 32.4% are '\0'. This patch
swapped the test order of 'x' and '\0' so now 'x' is tested first. This
makes changelogs faster since they almost always hit the first branch.
This makes a significant percentage of manifest '\0' chunks slower
because that code path now performs an extra test. Yes, I too can't
believe we're able to measure the impact of an if..elif with simple
string compares. I reckon this code would benefit from being written
in C...

# 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')