1	# =====================================================================
     2	# mwGetCategories.awk: MetaWeblog API.
     3	#
     4	# Copyright (c) 2007,2008 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	BEGIN {
    22	
    23	  delete a; delete b; delete c
    24	
    25	  # I use the unixified group name as a URI here, so that
    26	  # blogger.getRecentPosts or anyone else using the output
    27	  # from this program will not need to read the actual group
    28	  # record into memory. Fortunately the TW design provides
    29	  # enough flexibility :-)
    30	
    31	  g_name = _rcget("cgi.group")
    32	
    33	  url = ENVIRON["CSA_RPC_URI"] "/" ENVIRON["CSA_LANG"] "/" g_name
    34	
    35	  printf("<array>\n<data>")
    36	}
    37	
    38	/^\001/ { next }			# skip table header, if any.
    39	
    40	{
    41	  # k_page, p_name, p_descr
    42	
    43	  split($0,a,"\t")			# split each record into fields.
    44	
    45	  split(a[2],b,".")			# page category name, if any.
    46	
    47	  split(a[1],c,".")			# page category URI, if any.
    48	
    49	  # Note that we do not need to test for redirected/hidden/restricted
    50	  # pages here, and possibly skip them, because categories exist regardless
    51	  # of what the pages belonging into them may contain. Also note that
    52	  # the MetaWeblog API specs are debatable regarding the getCategories
    53	  # method, as reported in many places, among which:
    54	  #
    55	  # http://www.truerwords.net/articles/web-tech/metaweblog.getrecentposts.html
    56	  # http://roy.tabulas.com/2008/04/02/xml-rpc-interfaces-and-standards-oh-yeah/
    57	  #
    58	  # I am currently sticking to the widely adopted interpretation of
    59	  # returning an array of structs as the result, but the original specs
    60	  # (which nobody seems to implement except maybe Userland's Radio), say
    61	  # that a struct of structs should be returned. See the specs at
    62	  # http://www.xmlrpc.com/metaWeblogApi .
    63	  #
    64	  # OTOH, even if one wanted to stick to the specs and return a struct of
    65	  # structs, it is not at all clear how this could possibly be accomplished,
    66	  # since a struct is an unordered list of name/value pairs, and the specs
    67	  # do not tell what names should be used in the outer struct.
    68	
    69	  print	"\n<value><struct>\n" \
    70		"<member>\n" \
    71		"<name>description</name>\n" \
    72		"<value><string>" _xmlencode(b[1]) "</string></value>\n" \
    73		"</member>\n" \
    74		"<member>\n" \
    75		"<name>htmlUrl</name>\n" \
    76		"<value><string>" url "/" c[1] "-recent-headlines</string></value>\n" \
    77		"</member>\n" \
    78		"<member>\n" \
    79		"<name>rssUrl</name>\n" \
    80		"<value><string>\n" \
    81		url "/tw-" c[1] "-recent-headlines/style/rss</string></value>\n" \
    82		"</member>"
    83	
    84	  printf("</struct></value>")
    85	
    86	} 
    87	
    88	END {
    89	
    90	  print "\n</data>\n</array>"
    91	}
    92	
    93	# EOF