view hgext/highlight/highlight.py @ 26362:3bfc473f4d33

gitweb, monoblue: fix vertical align of spans in .sourcelines

Empty lines in file view could produce an inexplicable margin before the next
line (most noticeable in browsers on webkit/blink engine). That was making
empty lines seem taller than the rest.

Instead of using default vertical align, let's set it to 'top'.

This issue is actually present in paper, and only recently got into gitweb
(2239626369f5) and monoblue (119202d4d7a4). There's a bit more to it in paper,
so that will be dealt with in a future patch.

Recipe to see live: preferably using a webkit/blink browser, such as chromium,
browse a file with empty lines, e.g. https://selenic.com/hg/file/3.5/README#l8
Selecting a block of text that includes empty lines will reveal white "breaks"
in the selection. Highlighted line (#l8) also shows such a break below itself.

# 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):
            # 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