view hgext/highlight/highlight.py @ 25867:a74e9806d17d stable

highlight: produce correct markup when there's a blank line just before EOF

Due to how the colorized output from pygments was stripped of <pre> elements,
when there was an empty line at the end of a file, highlight extension produced
an incorrect markup (no closing tags from the fileline/annotateline template).
It wasn't usually noticeable, because browsers were smart enough to see where
the missing tags should've been, but in monoblue style it resulted in the last
line having twice the normal height.

Instead of awkwardly trying to strip outer <pre></pre> tags, let's make the
formatter with nowrap=True, which should do what we need in pygments since at
least 0.5 (2006-10-30).

Example from monoblue style:

Before:

    <div class="source">

<div style="font-family:monospace" class="parity0">
<pre><a class="linenr" href="#l1" id="l1">     1</a> </pre>
</div>
<div style="font-family:monospace" class="parity1">
<pre><a class="linenr" href="#l2" id="l2">     2</a>
    </div>

Now:

    <div class="source">

<div style="font-family:monospace" class="parity0">
<pre><a class="linenr" href="#l1" id="l1">     1</a> </pre>
</div>
<div style="font-family:monospace" class="parity1">
<pre><a class="linenr" href="#l2" id="l2">     2</a> </pre>
</div>
    </div>

(Notice the missing </pre></div> now in place)

# 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 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):
            lexer = TextLexer(stripnl=False)

    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