##// END OF EJS Templates
highlight: exit early on textual and unknown files (issue3005)...
highlight: exit early on textual and unknown files (issue3005) When highlight extension encountered files that pygments didn't recognize, it used to fall back to text lexer. Also, pygments uses TextLexer for .txt files. This lexer is noop by design. On bigger files, however, doing the noop highlighting resulted in noticeable extra CPU work and memory usage: to show a 1 MB text file, hgweb required about 0.7s more (on top of ~3.8s, Q8400) and consumed about 100 MB of RAM more (on top of ~150 MB). Let's just exit the function when it's clear that nothing will be highlighted. Due to how this pygmentize function works (it modifies the template in-place), we can just return from it and everything else will work as if highlight extension wasn't enabled.

File last commit:

r25899:c35ee1bb default
r25899:c35ee1bb default
Show More
highlight.py
69 lines | 2.3 KiB | text/x-python | PythonLexer
# 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):
# 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