highlight.py
75 lines
| 2.6 KiB
| text/x-python
|
PythonLexer
|
r8251 | # 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 | ||||
|
r10263 | # GNU General Public License version 2 or any later version. | ||
|
r6938 | # | ||
# The original module was split in an interface and an implementation | ||||
# file to defer pygments loading and speedup extension setup. | ||||
from mercurial import demandimport | ||||
|
r10394 | demandimport.ignore.extend(['pkgutil', 'pkg_resources', '__main__']) | ||
|
r7948 | from mercurial import util, encoding | ||
|
r6938 | |||
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" />') | ||||
|
r26680 | def pygmentize(field, fctx, style, tmpl, guessfilenameonly=False): | ||
|
r6938 | |||
# append a <link ...> to the syntax highlighting css | ||||
|
r10959 | old_header = tmpl.load('header') | ||
|
r6938 | if SYNTAX_CSS not in old_header: | ||
|
r27637 | new_header = old_header + SYNTAX_CSS | ||
|
r6938 | tmpl.cache['header'] = new_header | ||
text = fctx.data() | ||||
if util.binary(text): | ||||
return | ||||
|
r23613 | # str.splitlines() != unicode.splitlines() because "reasons" | ||
for c in "\x0c\x1c\x1d\x1e": | ||||
if c in text: | ||||
text = text.replace(c, '') | ||||
|
r9424 | # Pygments is best used with Unicode strings: | ||
# <http://pygments.org/docs/unicode/> | ||||
text = text.decode(encoding.encoding, 'replace') | ||||
|
r7120 | |||
|
r6938 | # To get multi-line strings right, we can't format line-by-line | ||
try: | ||||
|
r19169 | lexer = guess_lexer_for_filename(fctx.path(), text[:1024], | ||
stripnl=False) | ||||
|
r6938 | except (ClassNotFound, ValueError): | ||
|
r26680 | # 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 | ||||
|
r6938 | try: | ||
|
r19169 | lexer = guess_lexer(text[:1024], stripnl=False) | ||
|
r6938 | except (ClassNotFound, ValueError): | ||
r25899 | # Don't highlight unknown files | |||
return | ||||
# Don't highlight text files | ||||
if isinstance(lexer, TextLexer): | ||||
return | ||||
|
r6938 | |||
r25867 | formatter = HtmlFormatter(nowrap=True, style=style) | |||
|
r6938 | |||
colorized = highlight(text, lexer, formatter) | ||||
|
r9424 | coloriter = (s.encode(encoding.encoding, 'replace') | ||
for s in colorized.splitlines()) | ||||
|
r6938 | |||
|
r8360 | tmpl.filters['colorize'] = lambda x: coloriter.next() | ||
|
r6938 | |||
oldl = tmpl.cache[field] | ||||
newl = oldl.replace('line|escape', 'line|colorize') | ||||
tmpl.cache[field] = newl | ||||