view hgext/highlight/highlight.py @ 11010:18e81d42ee5c stable

util: fix default termwidth() under Windows sys.stdout.write('-'*80 + '\n') or sys.stdout.write('-'*80 + '\r') do not work on Windows as they do on unix. On a 80 columns Windows console, the extra CR or LF are interpreted as if belonging to the next line, so the first command displays 2 lines (only one on unix) and the second one leave the line visible and move back to the following line. To avoid this, we sacrifice one column under Windows.
author Patrick Mezard <pmezard@gmail.com>
date Mon, 26 Apr 2010 22:30:40 +0200
parents 4612cded5176
children d1f4657f55e4
line wrap: on
line source

# 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 = ''.join(tmpl('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

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

    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