1	# =====================================================================
     2	# xmlbreak.sed:
     3	# break long [x]html input into lines, for better RCS versioning.
     4	#
     5	# Copyright (c) 2007,2008,2009 Carlo Strozzi
     6	#
     7	# This program is free software; you can redistribute it and/or modify
     8	# it under the terms of the GNU General Public License as published by
     9	# the Free Software Foundation; version 2 dated June, 1991.
    10	#
    11	# This program is distributed in the hope that it will be useful,
    12	# but WITHOUT ANY WARRANTY; without even the implied warranty of
    13	# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    14	# GNU General Public License for more details.
    15	#
    16	# You should have received a copy of the GNU General Public License
    17	# along with this program; if not, write to the Free Software
    18	# Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
    19	#
    20	# =====================================================================
    21	
    22	# =====================================================================
    23	# This program is meant to be used instead of tidy(1) on data produced
    24	# by some buggy GUI editors, such as TinyMCE, that produce broken
    25	# markup which will not pass through tidy. The resulting data may still
    26	# be rendered correctly by browsers, so this may still be acceptable
    27	# HTML but broken XHTML. So, if the latter mode is used, we need to
    28	# tweak the input data which is not going to be scanned by tidy(1).
    29	# This filter also helps not to bloat RCS versioning files because of
    30	# those HTML editors that send all the data in one single line.
    31	# =====================================================================
    32	
    33	# Turn CR+LF line-end convention into NL.
    34	s/
$//
    35	
    36	# Same as above, but for Macintosh clients.
    37	s/
/\
    38	/g
    39	
    40	# This looks a bit elaborated at a first glance, but we need to avoid
    41	# the insertion of an additional newline at every repeated page editing.
    42	
    43	s/\(.\)<\([^\/]\)/\1\
    44	<\2/g
    45	
    46	# The TinyMCE WYSIWYG AJAX editor insists on turning hard line breaks
    47	# into <br/> sequences, which will result in duplicated line breaks in
    48	# <pre> element contents that end with real newlines. Although it is
    49	# not up to TypeWriter to try and fix bugs of other programs, in this
    50	# case it may be worth doing it since the solution is general enough.
    51	# It sounds logical to me that if a <br/> follows a newline, then the
    52	# newline can be safely removed as the task of breaking the line is
    53	# the rendered page is left to the <br/> itself.
    54	
    55	s/\n<br *\/>/<br \/>/g
    56	
    57	# Make sure a blank is inserted before each newline, or XHTML 1.1 will
    58	# swallow the spacing between the two words that are across the break.
    59	
    60	s/ *$/ /
    61	
    62	# EOF