hgext/highlight/highlight.py
author Pierre-Yves David <pierre-yves.david@fb.com>
Wed, 10 Jun 2015 19:26:16 -0700
changeset 25527 262e6ad93885
parent 23613 7b8ff3fd11d3
child 25867 a74e9806d17d
permissions -rw-r--r--
phases: really fix native phase computation For some reason (probably rebase issue, leprechaun or badly resolved .rej) 1635579f9baf contains only half of the emailed patches and do not fix the bug. This patch adds the other half and enable the sweet native computation for real. As expected this provide massive speedup along the board. revset #0: not public() plain first 0) 0.011960 0.010523 1) 0.000465 3% 0.000492 4% revset #1: (tip~1000::) - public() plain first 0) 0.025700 0.025169 1) 0.002864 11% 0.001899 7% revset #2: not public() and branch("default") plain first 0) 0.022842 0.020863 1) 0.011418 49% 0.010948 52% However, it has a less impact (even bad) on first result time in simple situation. This comes from the overhead of building the set and filtering it. This is especially true on my Mercurial repository (used here) where about 1/3 of the changesets are non public and hidden. This could be mitigated by a caching of the set and a better usage of smartset in '_notpublic'. (But this won't happen in this patch because the win is massive everywhere else). revset #0: not public() last 0) 0.000081 1) 0.000493 x6.1 <-- bad impact revset #1: (tip~1000::) - public() last 0) 0.013966 1) 0.002737 19% revset #2: not public() and branch("default") last 0) 0.011021 1) 0.011038 The effect mostly disappear when the number of non-public changesets is small and/or the repo get bigger. Result for Mozilla central: Mozilla revset #0: not public() plain first last 0) 0.092787 0.084094 0.000080 1) 0.000054 0% 0.000083 0% 0.000083 revset #1: (tip~1000::) - public() plain first last 0) 0.215607 0.183996 0.124962 1) 0.031620 14% 0.006616 3% 0.031168 24% revset #2: not public() and branch("default") plain first last 0) 0.092626 0.082687 0.000162 1) 0.000139 0% 0.000165 0% 0.000167

# highlight.py - highlight extension implementation file
#
#  Copyright 2007-2009 Adam Hupp <adam@hupp.org> 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 mercurial import demandimport
demandimport.ignore.extend(['pkgutil', 'pkg_resources', '__main__'])
from mercurial import util, encoding

from pygments import highlight
from pygments.util import ClassNotFound
from pygments.lexers import guess_lexer, guess_lexer_for_filename, TextLexer
from pygments.formatters import HtmlFormatter

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

def pygmentize(field, fctx, style, tmpl):

    # 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):
        try:
            lexer = guess_lexer(text[:1024], stripnl=False)
        except (ClassNotFound, ValueError):
            lexer = TextLexer(stripnl=False)

    formatter = HtmlFormatter(style=style)

    colorized = highlight(text, lexer, formatter)
    # strip wrapping div
    colorized = colorized[:colorized.find('\n</pre>')]
    colorized = colorized[colorized.find('<pre>') + 5:]
    coloriter = (s.encode(encoding.encoding, 'replace')
                 for s in colorized.splitlines())

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

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