diff --git a/modules/bibrank/etc/template_word_similarity.cfg.wml b/modules/bibrank/etc/template_word_similarity.cfg.wml index 39dcaf590..ba0a4aaa7 100644 --- a/modules/bibrank/etc/template_word_similarity.cfg.wml +++ b/modules/bibrank/etc/template_word_similarity.cfg.wml @@ -1,80 +1,78 @@ ## This file is part of the CERN Document Server Software (CDSware). ## Copyright (C) 2002 CERN. ## ## The CDSware is free software; you can redistribute it and/or ## modify it under the terms of the GNU General Public License as ## published by the Free Software Foundation; either version 2 of the ## License, or (at your option) any later version. ## ## The CDSware is distributed in the hope that it will be useful, but ## WITHOUT ANY WARRANTY; without even the implied warranty of ## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU ## General Public License for more details. ## ## You should have received a copy of the GNU General Public License ## along with CDSware; if not, write to the Free Software Foundation, Inc., ## 59 Temple Place, Suite 330, Boston, MA 02111-1307, USA. #include "configbis.wml" #include "config.wml" [rank_method] function = word_similarity [word_similarity] #None = no stemming stemming = table = rnkWORD01F #using stopwordlist from /bibindex/bibindex_engine_config stopword = True relevance_number_output_prologue = ( relevance_number_output_epilogue = ) #MARC tag,tag points, tag language #keyword tag1 = 6531_a, 1, #keyword tag2 = 695__a, 1, #keyword tag3 = 6532_a, 1, #title tag4 = 245__%, 10, #title tag5 = 246_%, 1, fr #title tag6 = 250__a, 1, #title tag7 = 711__a, 1, #abbreviated tag8 = 210__a, 1, #key title tag9 = 222__a, 1, #abstract tag10 = 520__%, 1, #abstract tag11 = 590__%, 1, fr #conference tag12 = 111__a, 1, #author tag13 = 100__%, 1, none #author tag14 = 700__%, 1, none #author tag15 = 721__a, 1, none [find_similar] #term should exist in maximum X/100% of documents max_word_occurence = 0.05 #term should exist in minimum X/100% of documents min_word_occurence = 0.00 #term should be atleast 3 characters long min_word_length = 3 #term should be in atleast 3 documents or more min_nr_words_docs = 3 #do not use more than 20 terms for "find similar" max_nr_words_upper = 20 #if a document contains less than 10 terms, use much used terms too, if not ignore them max_nr_words_lower = 10 -#override minimum relevance value and use the one from search_engine? -override_default_min_relevance = no #default minimum relevance value to use for find similar default_min_relevance = 75 diff --git a/modules/bibrank/etc/wrd.cfg.wml b/modules/bibrank/etc/wrd.cfg.wml index 5dbca6aba..c3229d1bf 100644 --- a/modules/bibrank/etc/wrd.cfg.wml +++ b/modules/bibrank/etc/wrd.cfg.wml @@ -1,70 +1,68 @@ ## This file is part of the CERN Document Server Software (CDSware). ## Copyright (C) 2002 CERN. ## ## The CDSware is free software; you can redistribute it and/or ## modify it under the terms of the GNU General Public License as ## published by the Free Software Foundation; either version 2 of the ## License, or (at your option) any later version. ## ## The CDSware is distributed in the hope that it will be useful, but ## WITHOUT ANY WARRANTY; without even the implied warranty of ## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU ## General Public License for more details. ## ## You should have received a copy of the GNU General Public License ## along with CDSware; if not, write to the Free Software Foundation, Inc., ## 59 Temple Place, Suite 330, Boston, MA 02111-1307, USA. #include "configbis.wml" #include "config.wml" [rank_method] function = word_similarity [word_similarity] #None = no stemming stemming = table = rnkWORD01F #using stopword list from /bibindex/bibindex_engine_config #False = no stopword removal stopword = True relevance_number_output_prologue = ( relevance_number_output_epilogue = ) #relevance_number_output_prologue = #MARC tag,tag points, tag language -tag1 = 6531_a, 1, +tag1 = 6531_a, 2, tag2 = 695__a, 1, tag3 = 6532_a, 1, tag4 = 245__%, 10, tag5 = 246_%, 1, fr tag6 = 250__a, 1, tag7 = 711__a, 1, tag8 = 210__a, 1, tag9 = 222__a, 1, tag10 = 520__%, 1, tag11 = 590__%, 1, fr tag12 = 111__a, 1, -tag13 = 100__%, 1, none +tag13 = 100__%, 2, none tag14 = 700__%, 1, none tag15 = 721__a, 1, none [find_similar] #term should exist in maximum X/100% of documents max_word_occurence = 0.05 #term should exist in minimum X/100% of documents min_word_occurence = 0.00 #term should be atleast 3 characters long min_word_length = 3 #term should be in atleast 3 documents or more min_nr_words_docs = 3 #do not use more than 20 terms for "find similar" max_nr_words_upper = 20 #if a document contains less than 10 terms, use much used terms too, if not ignore them max_nr_words_lower = 10 -#override minimum relevance value and use the one from search_engine? -override_default_min_relevance = no #default minimum relevance value to use for find similar default_min_relevance = 75