hgext/highlight/highlight.py

narrow: don't send the changelog information when widening without ellipses

When we widen anon-ellipses narrow copy, the server sends the changelog
information of all the changesets. The code was copied from ellipses case and in
ellipses cases, it's required to send the new changelog data.

But in non-ellipses cases, we don't need to send the changelog data as we will
have all the changesets locally.

Before this patch, there was a overhead of ~8-10 mins on each widening call
because of all the changelog information being pulled and being applied. After
this patch, we no more pull the changelog information. So this patch can save ~5
mins on Mozilla repo on each widening and more on repos which have more
changesets.

When we apply an empty changelog from changegroup, there is a devel-warn. This
patch kind of hacks to silence that devel-warn.

Differential Revision: https://phab.mercurial-scm.org/D4639

# 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

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

from mercurial import (
    encoding,
)

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

    text = fctx.data()
    if stringutil.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