1	# =====================================================================
     2	# extLink.awk: spot external links and label the as such.
     3	#
     4	# Copyright (c) 2009 Carlo Strozzi
     5	#
     6	# This program is free software; you can redistribute it and/or modify
     7	# it under the terms of the GNU General Public License as published by
     8	# the Free Software Foundation; version 2 dated June, 1991.
     9	#
    10	# This program is distributed in the hope that it will be useful,
    11	# but WITHOUT ANY WARRANTY; without even the implied warranty of
    12	# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    13	# GNU General Public License for more details.
    14	#
    15	# You should have received a copy of the GNU General Public License
    16	# along with this program; if not, write to the Free Software
    17	# Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
    18	#
    19	# =====================================================================
    20	
    21	# =====================================================================
    22	# string extLink(string link, string groupdir)
    23	# =====================================================================
    24	
    25	function extLink(html,					      tmp,re) {
    26	
    27	  re = ENVIRON["CSA_FQDN"]
    28	
    29	  # Match on 2nd level domain as opposed of the host name,
    30	  # which seems reasonable. That is, links to different hosts
    31	  # in the same domain are NOT considered external links.
    32	
    33	  if (re ~ /^[^.]+\.[^.]+\.[^.]+$/) sub (/^[^.]+\./,_NULL,re)
    34	
    35	  re = "https?://((.*\\.)?" \
    36		_escreg(re) "|" _escreg("(:localhost:)") ")(/.*)?"
    37	
    38	  tmp = html
    39	
    40	  sub(/>.*/,_NULL,tmp); sub(/[^>]+/,_NULL,html)
    41	
    42	  if (tmp ~ /https?:\/\// && tmp !~ re) {
    43	
    44	     # Add to current "class" attribute if defined, or append one anew.
    45	     if (!sub(/[^a-z]*class=["']/, "&tw-extlink ",tmp))
    46				sub(/$/," class='tw-extlink'",tmp)
    47	
    48	     if (_bool(ENVIRON["TNS_EXT_NOFOLLOW"]) == _TRUE) {
    49	
    50		# Add to current "rel" attribute if defined, or append one anew.
    51		# note that adding to an existing one may break XFN relations,
    52		# but Google's nofollow hack is notoriously badly conceived.
    53	
    54		if (tmp !~ /[^a-z]*rel=["'][^'"]*nofollow/ && \
    55			!sub(/[^a-z]*rel=["']/, "&nofollow ",tmp))
    56					sub(/$/," rel='nofollow'",tmp)
    57	     }
    58	
    59	     # Always set the rel="external" attribute, mainly for validators.
    60	     if (tmp !~ /[^a-z]*rel=["'][^'"]*external/ && \
    61			!sub(/[^a-z]*rel=["']/, "&external ",tmp))
    62					sub(/$/," rel='external'",tmp)
    63	  }
    64	
    65	  return tmp html
    66	}
    67	
    68	# EOF