highlight: add option to prevent content-only based fallback
When Mozilla enabled Pygments on hg.mozilla.org, we got a lot of weirdly
colorized files. Upon further investigation, the hightlight extension
is first attempting a filename+content based match then falling back to a
purely content-driven detection mode in Pygments. Sounds good in theory.
Unfortunately, Pygments' content-driven detection establishes no minimum
threshold for returning a lexer. Furthermore, the detection code for
a number of languages is very liberal. For example, ActionScript 3 will
return a confidence of 0.3 (out of 1.0) if the first 1k of the file
we pass in matches the regex "\w+\s*:\s*\w"! Python matches on
"import ". It's no coincidence that a number of our extension-less files
were getting highlighted improperly.
This patch adds an option to have the highlighter not fall back to
purely content-based detection when filename+content detection failed.
This can be enabled to render unlighted text instead of taking the risk
that unknown file types are highlighted incorrectly. The old behavior is
still the default.
# 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, 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: coloriter.next()
oldl = tmpl.cache[field]
newl = oldl.replace('line|escape', 'line|colorize')
tmpl.cache[field] = newl