1	# =====================================================================
     2	# unixify.awk: turn a free-form string into a safer form.
     3	#
     4	# Copyright (c) 2007,2008,2009,2010 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	# string unixify(string s [,boolean mode])
    21	#
    22	# If mode is "1" then "s" will be considered a page name, otherwise
    23	# "s" will be considered to be a group name (default).
    24	# =====================================================================
    25	
    26	function unixify(s,mode) {
    27	
    28	   s = tolower(s)
    29	
    30	   # Some editors my intentionally use en-dash and em-dash characters
    31	   # in place of true hyphens in page names, which should be avoided
    32	   # by all means, as that is usually done by mistake. These characters
    33	   # are still allowed in page contents, even if they may not be
    34	   # palatable to some XML clients.
    35	
    36	   # http://www.fileformat.info/info/unicode/char/2013/index.htm
    37	   gsub(/\xe2\x80\x93/,"-",s)
    38	
    39	   # See http://www.fileformat.info/info/unicode/char/2014/index.htm
    40	   gsub(/\xe2\x80\x94/,"-",s)
    41	
    42	   # For backward-compatibility, if this variable is set
    43	   # to true then sequences of multiple blanks and/or dashes
    44	   # in page and attachment names will be turned into as many
    45	   # dashes, i.e. a page name like "My page - how nice" becomes
    46	   # "my-page---how-nice". By default they are squeezed to one
    47	   # single dash, that is "my-page-how-nice" .
    48	   #
    49	   # This hack was necessary to retain backward-compatibility
    50	   # with older pre-existing TW databases.
    51	
    52	   if (_bool(ENVIRON["TNS_LOCAL_HACK_1"]) == _TRUE) {
    53	      s = _strip(s)
    54	       gsub(/\t+/,"-",s)
    55	     gsub(/[- ]/,"-",s)
    56	   }
    57	   else {
    58	     s = _strip(s,_O_MIDDLE)
    59	     gsub(/[- \t]+/,"-",s)
    60	   }
    61	
    62	   if (mode) return _userencode(2,s,ENVIRON["TNS_PAGE_MAXLEN"])
    63	   else return _userencode(1,s,ENVIRON["TNS_GROUP_MAXLEN"])
    64	}
    65