hgext/highlight/highlight.py

lfs: only hardlink between the usercache and local store if the blob verifies

This fixes the issue where verify (and other read commands) would propagate
corrupt blobs.  I originalled coded this to only hardlink if 'verify=True' for
store.read(), but then good blobs weren't being linked, and this broke a bunch
of tests.  (The blob in repo5 that is being corrupted seems to be linked into
repo5 in the loop running dumpflog.py prior to it being corrupted, but only if
verify=False is handled too.)  It's probably better to do a one time extra
verification in order to create these files, so that the repo can be copied to a
removable drive.

Adding the same check to store.write() was only for completeness, but also needs
to do a one time extra verification to avoid breaking tests.

# 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.ignore.extend(['pkgutil', 'pkg_resources', '__main__'])

from mercurial import (
    encoding,
    util,
)

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
    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