--- /dev/null
+(
+
+sqlite3 -header -column -echo var/webpac2.sqlite 'select * from authors'
+
+2>&1 ) | vi -R -
--- /dev/null
+drop table if exists utca;
+
+create table utca (
+ id serial,
+ ut text,
+ ca text,
+);
+
+drop table if exists cited;
+
+create table cited (
+ id serial,
+ cited_au text,
+ from_au text,
+ ut text,
+ cited_full text
+);
+
+drop table if exists authors;
+
+create table authors (
+ id serial,
+ au text not null
+);
+
+
+drop table if exists citing;
+
+create table citing (
+ id serial,
+ ut text,
+ ca text,
+ pt text,
+ au text,
+ af text,
+ ti text,
+ so text,
+ la text,
+ dt text,
+ c1 text,
+ rp text,
+ cr text,
+ nr integer,
+ pi text,
+ py integer,
+ sc text
+);
+
+
+-- create index cited_au on cited(au);
+-- create index cited_cited on cited(cited);
+
--- /dev/null
+# warn dump(rec('AU'));
+# warn dump(rec_array('AU'));
+
+row( 'citirani',
+ ca => rec('A'),
+ cr_auth => rec('B'),
+ cr_ref => rec('C'),
+ cr_year => rec('D'),
+ cr_vol => rec('E'),
+ cr_page => rec('F'),
+ ttc => rec('H'),
+ cr =>
+ join_with(', ',
+ join_with(', P',
+ join_with(', V',
+ join_with(', ',
+ rec('B'),
+ rec('D'),
+ rec('C'),
+ ),
+ rec('E'),
+ ),
+ rec('F')
+ ),
+ rec('G')
+ ),
+ can => rec('J')
+);
--- /dev/null
+--- #YAML:1.0
+# DO NOT USE TABS FOR INDENTATION OR label/value SEPARATION!!!
+
+# encoding of this configuration file
+config_encoding: 'ISO-8859-2'
+# encoding in Catalyst.
+catalyst_encoding: 'UTF-8'
+# relative path to sites templates under Catalyst root
+sites_root: 'sites'
+
+# which indexing engine to use? (hyperestraier is default)
+#use_indexer: 'hyperestraier'
+#use_indexer: 'hyperestraier-native'
+#use_indexer: 'kinosearch'
+
+# configuration for Hyper Estraier full text search engine
+hyperestraier:
+ #url: 'http://localhost:1978/node/webpac2'
+ masterurl: 'http://localhost:1978'
+ defaultnode: 'webpac2'
+# defaultnode: 'ps'
+ defaultdepth: 1
+ user: 'admin'
+ passwd: 'admin'
+ # don't turn this on! it will spit huge amounts of output
+ #debug: 1
+ #
+ #
+ path: 'casket/'
+ # number of results on each page
+ hits_on_page: 10
+ # number of results to fetch for suggestion (it will fold multiple sameones)
+ hits_for_suggest: 20
+ #
+ # options used while indexing
+ #
+ # which tag type to use for search engine (used while indexing)
+ type: 'search'
+ #
+
+# options for pager
+pager:
+ # how many pages to show for navigation?
+ max_pages: 20
+
+# configuration for KinoSearch search engine library
+kinosearch:
+ index_path: './kinosearch/'
+ database: 'unconfigured database name'
+ label: 'unconfigured database label'
+ encoding: 'iso-8859-2'
+ # clean database before opening? (WARNING: this erases existing database)
+ clean: 1
+ # which field type to index?
+ type: 'search'
+
+webpac:
+ # default template to use
+ template: 'html_ffzg_results_short.tt'
+ # path to database files
+ db_path: '/data/webpac2/db'
+ # path to templates used by WebPAC::Output
+ template_path: '/data/webpac2/conf/output/tt'
+ # default template for results
+ default_template: 'html_ffzg.tt'
+ # default user editable css file
+ default_css: 'user.css'
+ css_path: 'root/css'
+ # encoding comming from webpac
+ webpac_encoding: 'iso-8859-2'
+ # encoding expected by Catalyst
+ out_encoding: 'utf-8'
+ # define different input formats (types) and perl modules to handle them
+ inputs:
+ isis: 'WebPAC::Input::ISIS'
+ marc: 'WebPAC::Input::MARC'
+ excel: 'WebPAC::Input::Excel'
+ dbf: 'WebPAC::Input::DBF'
+ isi: 'WebPAC::Input::ISI'
+ # define delimiters for validation
+ delimiters:
+ - ' ; '
+ - ' : '
+ - ' / '
+ - ' = '
+editor:
+ # open this record when opening editor
+ # (it will also be used to deduce default database and input)
+ default_record_uri: 'ps/peri/1'
+
+# directives after this are used when indexing using core WebPAC modules
+
+databases:
+ # This is empty database created only in Hyper Estraier to merge
+ # all three databases
+ 'webpac2':
+ name: 'Search all'
+ links:
+ - to: isi
+ credit: 10000
+
+# citirani:
+# name: 'CITIRANI'
+# input:
+# - name: radovi
+# type: excel
+# path: '/data/FF/citati/proba.xls'
+# encoding: 'windows-1250'
+# normalize:
+# path: 'conf/isi/isi2xls-citirani.pl'
+# output:
+# - module: 'Excel'
+# path: '/data/FF/citiari/citirani.xls'
+
+ isi:
+ name: 'ISI'
+ input:
+ - name: ajdukovicd
+ type: isi
+ path: '/data/FF/citati/citing/ajdukovicd.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ - name: arambasicl
+ type: isi
+ path: '/data/FF/citati/citing/arambasicl.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ - name: bratkod
+ type: isi
+ path: '/data/FF/citati/citing/bratkod.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ - name: buskov
+ type: isi
+ path: '/data/FF/citati/citing/buskov.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ skip: 1
+ - name: butkovica.txt
+ type: isi
+ path: '/data/FF/citati/citing/butkovica.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ skip: 1
+ - name: corkalobiruskid.txt
+ type: isi
+ path: '/data/FF/citati/citing/corkalobiruskid.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ skip: 1
+ - name: hrend
+ type: isi
+ path: '/data/FF/citati/citing/hrend.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ - name: hromatkoi
+ type: isi
+ path: '/data/FF/citati/citing/hromatkoi.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ skip: 1
+ - name: hudekknezevicj
+ type: isi
+ path: '/data/FF/citati/citing/hudekknezevicj.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ - name: kaliternalipovcanlj
+ type: isi
+ path: '/data/FF/citati/citing/kaliternalipovcanlj.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ - name: kardumi
+ type: isi
+ path: '/data/FF/citati/citing/kardumi.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ - name: kerestesg
+ type: isi
+ path: '/data/FF/citati/citing/kerestesg.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ skip: 1
+ - name: knezovicz
+ type: isi
+ path: '/data/FF/citati/citing/knezovicz.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ skip: 1
+ - name: kolesaricv
+ type: isi
+ path: '/data/FF/citati/citing/kolesaricv.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ skip: 1
+ - name: kuterovacjagodicg
+ type: isi
+ path: '/data/FF/citati/citing/kuterovacjagodicg.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ - name: lackovicgrgink
+ type: isi
+ path: '/data/FF/citati/citing/lackovicgrgink.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ - name: lamzaposavecv
+ type: isi
+ path: '/data/FF/citati/citing/lamzaposavecv.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ - name: manenicai
+ type: isi
+ path: '/data/FF/citati/citing/manenicai.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ - name: maslicsersicd
+ type: isi
+ path: '/data/FF/citati/citing/maslicsersicd.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ skip: 1
+ - name: radosevicvidacekb
+ type: isi
+ path: '/data/FF/citati/citing/radosevicvidacekb.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ - name: sverkob
+ type: isi
+ path: '/data/FF/citati/citing/sverkob.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ - name: galicz
+ type: isi
+ path: '/data/FF/citati/citing/galicz.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ skip: 1
+ - name: tadinacm
+ type: isi
+ path: '/data/FF/citati/citing/tadinacm.txt'
+ encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/tables.pl'
+ - name: radovi
+ type: excel
+ path: '/data/FF/citati/citirani_radovi.xls'
+ worksheet: 'Sheet1'
+ # encoding: 'ISO-8859-1'
+ normalize:
+ # - path: 'conf/normalize/isi/isi2xls.pl'
+ # - path: 'conf/isi/isi2sorted.pl'
+ - path: 'conf/isi/citirani-radovi.pl'
+ - name: cropsy
+ type: isi
+ path: '/data/FF/citati/croatia-psychol.txt'
+ normalize:
+ - path: 'conf/isi/tables-cropsy.pl'
+ skip: 0
+ output:
+# - module: 'Excel'
+# path: '/data/FF/citati/data.xls'
+# - module: 'Sorted'
+# path: '/data/FF/citati/sorted/'
+# - module: 'CouchDB'
+# url: 'http://193.198.212.57:5984'
+ - module: 'DBI'
+ dsn: 'dbi:Pg:dbname=dipl'
+ schema: 'conf/isi/schema.sql'
+# table: 'citirani'
--- /dev/null
+
+foreach my $au ( rec_array 'AU' ) {
+ row( 'authors', au => $au );
+ foreach my $cr ( rec_array 'CR' ) {
+ if ( ! $cr->{author} ) {
+# warn "# cr ",dump( $cr );
+ next;
+ }
+ row( 'cited',
+ cited_au => $cr->{author},
+ from_au => $au,
+ );
+ }
+}
+
--- /dev/null
+(
+
+sqlite3 -header -column -echo var/webpac2.sqlite 'select count(*),au from authors group by au order by count(*) desc'
+sqlite3 -header -column -echo var/webpac2.sqlite 'select count(*),cited_au,from_au from cited group by cited_au,from_au order by count(*) desc,cited_au,from_au'
+
+2>&1 ) | vi -R -
--- /dev/null
+sqlite3 -column var/webpac2.sqlite 'select * from cited' | vi -R -
--- /dev/null
+select cited_au,cited_full,count(*) from cited where cited_au = 'SVERKO B' group by cited_full, cited_au order by cited_full
--- /dev/null
+sorted('au',
+ prefix( rec('UT') . ' | ',
+ rec('AU')
+ )
+);
+
+
+
+sorted('cr',
+ suffix(
+ ' | ' . rec('UT') . ' | ' . join_with(' ; ', rec('AU')) . ' | ' . join_with(' ; ', rec('SO')) . ' | ' . rec('PY'),
+ rec('CR','full')
+ )
+);
+
--- /dev/null
+sub csv { to('csv',@_) }
+
+#warn( dump(
+# rec('CR','author')
+#)
+#);
+
+my $cr = join_with(' ; ',
+ rec('CR','author')
+ );
+
+if ( $cr =~ m/SVERKO B/ ) {
+
+
+csv('A',
+ rec('PT'),
+);
+
+csv('B',
+ join_with(', ',
+ rec('AU')
+ )
+);
+
+csv('C',
+ rec('TI'),
+);
+
+csv('D',
+ rec('DE'),
+);
+
+csv('E',
+ rec('ID'),
+);
+
+csv('F',
+ rec('TC'),
+);
+
+csv('G',
+ rec('NR'),
+);
+
+csv('H',
+ join_with(' | ',
+ rec('CR','full')
+ )
+);
+
+#csv('H',
+# rec('CR','author')
+#);
+#
+#csv('I',
+# rec('CR','institution')
+#);
+#
+#csv('J',
+# rec('CR','page')
+#);
+#
+#csv('K',
+# rec('CR','reference')
+#);
+#
+#csv('L',
+# rec('CR','volume')
+#);
+#
+#csv('M',
+# rec('CR','year')
+#);
+
+
+csv('I',
+ rec('BP'),
+);
+
+csv('J',
+ rec('EP'),
+);
+
+csv('K',
+ rec('DT'),
+);
+
+csv('L',
+ rec('LA'),
+);
+
+csv('M',
+ rec('SN'),
+);
+
+csv('N',
+ rec('SO'),
+);
+
+
+
+}
--- /dev/null
+select distinct citirani_radovi.cr,
+ cited.cr_full,
+ cited.ut
+from citirani_radovi
+left join cited on (citirani_radovi.cr=cited.cr_full)
+order by citirani_radovi.cr
+;
+
--- /dev/null
+drop view if exists parovi;
+drop view if exists rpcou;
+drop view if exists citingu;
+drop view if exists citiraniu;
+
+drop table if exists utca;
+create table utca (
+ id serial,
+ ut text,
+ ca text
+);
+
+drop table if exists cited;
+create table cited (
+ id serial,
+ ca text,
+ cr_auth text,
+ au text,
+ ut text,
+ cr_full text,
+ cr_year text,
+ cr_ref text,
+ cr_doi text
+);
+
+drop table if exists authors;
+create table authors (
+ id serial,
+ ut text,
+ au text,
+ af text,
+ ca text
+);
+
+
+drop table if exists citing;
+create table citing (
+ id serial,
+ ut text,
+ pt text,
+ au text,
+ af text,
+ ti text,
+ so text,
+ la text,
+ dt text,
+ c1 text,
+ rp text,
+ nr integer,
+ tc integer,
+ pi text,
+ py integer,
+ di text,
+ sc text
+);
+
+drop table if exists rpco;
+create table rpco (
+ ut text,
+ rp text,
+ rpco text
+);
+
+
+drop table if exists citirani;
+create table citirani (
+ id serial,
+ ca text,
+ cr_auth text,
+ cr_ref text,
+ cr_year text,
+ cr_vol text,
+ cr_page text,
+ ttc integer,
+ cr text,
+ can text
+);
+
+create view citingu as select distinct ut,pt,au,so,la,dt,nr,tc,pi,py,di,sc,rp from citing ;
+
+create view rpcou as select distinct * from rpco ;
+
+create view parovi as select distinct citirani.ca,
+ citirani.cr,
+ cited.cr_full,
+ cited.ut,
+ citingu.pt,
+ citingu.au,
+ citingu.so,
+ citingu.la,
+ citingu.dt,
+ citingu.nr,
+ citingu.tc,
+ citingu.pi,
+ citingu.py,
+ citingu.sc,
+ citingu.rp
+from citirani
+left join cited on citirani.cr = cited.cr_full
+left join citingu on cited.ut = citingu.ut
+left join rpcou on cited.ut = rpcou.ut
+;
+
+create view citiraniu as select distinct cr_auth,cr_ref,cr_year,cr_vol,cr_page,ttc,cr from citirani ;
+
+
+drop table if exists cropsy;
+create table cropsy (
+ id serial,
+ ut text,
+ au text,
+ c1 text,
+ rp text,
+ tc integer,
+ py integer
+);
+
+
+-- CREATE AGGREGATE array_accum (anyelement)
+-- (
+-- sfunc = array_append,
+-- stype = anyarray,
+-- initcond = '{}'
+-- );
+
+-- select d, count(*),
+-- array_to_string(array_accum('+'::text),'') as graph
+-- from hits group by 1 order by 1 asc;
+
+
+-- create index cited_au on cited(au);
+-- create index cited_cited on cited(cited);
+
--- /dev/null
+
+my @c1 = rec_array ('C1');
+my @rp = rec_array ('RP');
+foreach my $au ( rec_array('AU') ) {
+ row( 'cropsy',
+ ut => rec('UT'),
+ au => $au,
+ c1 => shift @c1,
+ rp => shift @rp,
+ tc => rec('TC'),
+ py => rec('PY')
+ )
+}
+
--- /dev/null
+# warn dump(rec('AU'));
+# warn dump(rec_array('AU'));
+
+#di => split( /;/, rec(
+
+row( 'citing',
+ ut => rec('UT'),
+ pt => rec('PT'),
+ au => regex('s/,//',
+ uc ( frec('AU') )
+ ),
+ ti => rec('TI'),
+ so => rec('SO'),
+ la => rec('LA'),
+ dt => rec('DT'),
+ c1 => frec('C1'),
+ rp => uc ( rec('RP') ),
+ nr => rec('NR'),
+ tc => rec('TC'),
+ pi => rec('PI'),
+ py => rec('PY'),
+ di => rec('DI'),
+ sc => rec('SC')
+);
+
+if ( rec('RP') ) {
+ row( 'rpco',
+ ut => rec('UT'),
+ rp => rec('RP'),
+ rpco =>
+ regex('s/.*,(.*)/$1/',
+ regex('s/\.$//',
+ rec('RP')
+ )
+ ),
+ );
+}
+
+my @af = rec_array ('AF');
+foreach my $au ( rec_array ('AU') ) {
+ foreach my $cr ( rec_array('CR') ) {
+ row( 'cited',
+ ut => rec('UT'),
+ ca => config('input name'),
+ cr_auth => $cr->{author},
+ au => regex('s/,//',
+ uc ( $au )
+ ),
+ cr_full => $cr->{full},
+ cr_year => $cr->{year},
+ cr_ref => $cr->{reference}
+ );
+ }
+ row( 'authors',
+ ut => rec('UT'),
+ ca => config('input name'),
+ au => regex('s/,//',
+ uc ( $au )
+ ),
+ af => shift @af,
+ )
+}
+
+row( 'utca',
+ ut => rec('UT'),
+ ca => config('input name')
+);
+
+
+++ /dev/null
-(
-
-sqlite3 -header -column -echo var/webpac2.sqlite 'select * from authors'
-
-2>&1 ) | vi -R -
+++ /dev/null
-drop table if exists utca;
-
-create table utca (
- id serial,
- ut text,
- ca text,
-);
-
-drop table if exists cited;
-
-create table cited (
- id serial,
- cited_au text,
- from_au text,
- ut text,
- cited_full text
-);
-
-drop table if exists authors;
-
-create table authors (
- id serial,
- au text not null
-);
-
-
-drop table if exists citing;
-
-create table citing (
- id serial,
- ut text,
- ca text,
- pt text,
- au text,
- af text,
- ti text,
- so text,
- la text,
- dt text,
- c1 text,
- rp text,
- cr text,
- nr integer,
- pi text,
- py integer,
- sc text
-);
-
-
--- create index cited_au on cited(au);
--- create index cited_cited on cited(cited);
-
+++ /dev/null
-# warn dump(rec('AU'));
-# warn dump(rec_array('AU'));
-
-row( 'citirani',
- ca => rec('A'),
- cr_auth => rec('B'),
- cr_ref => rec('C'),
- cr_year => rec('D'),
- cr_vol => rec('E'),
- cr_page => rec('F'),
- ttc => rec('H'),
- cr =>
- join_with(', ',
- join_with(', P',
- join_with(', V',
- join_with(', ',
- rec('B'),
- rec('D'),
- rec('C'),
- ),
- rec('E'),
- ),
- rec('F')
- ),
- rec('G')
- ),
- can => rec('J')
-);
+++ /dev/null
-
-foreach my $au ( rec_array 'AU' ) {
- row( 'authors', au => $au );
- foreach my $cr ( rec_array 'CR' ) {
- if ( ! $cr->{author} ) {
-# warn "# cr ",dump( $cr );
- next;
- }
- row( 'cited',
- cited_au => $cr->{author},
- from_au => $au,
- );
- }
-}
-
+++ /dev/null
-(
-
-sqlite3 -header -column -echo var/webpac2.sqlite 'select count(*),au from authors group by au order by count(*) desc'
-sqlite3 -header -column -echo var/webpac2.sqlite 'select count(*),cited_au,from_au from cited group by cited_au,from_au order by count(*) desc,cited_au,from_au'
-
-2>&1 ) | vi -R -
+++ /dev/null
-sqlite3 -column var/webpac2.sqlite 'select * from cited' | vi -R -
+++ /dev/null
-select cited_au,cited_full,count(*) from cited where cited_au = 'SVERKO B' group by cited_full, cited_au order by cited_full
+++ /dev/null
---- #YAML:1.0
-# DO NOT USE TABS FOR INDENTATION OR label/value SEPARATION!!!
-
-# encoding of this configuration file
-config_encoding: 'ISO-8859-2'
-# encoding in Catalyst.
-catalyst_encoding: 'UTF-8'
-# relative path to sites templates under Catalyst root
-sites_root: 'sites'
-
-# which indexing engine to use? (hyperestraier is default)
-#use_indexer: 'hyperestraier'
-#use_indexer: 'hyperestraier-native'
-#use_indexer: 'kinosearch'
-
-# configuration for Hyper Estraier full text search engine
-hyperestraier:
- #url: 'http://localhost:1978/node/webpac2'
- masterurl: 'http://localhost:1978'
- defaultnode: 'webpac2'
-# defaultnode: 'ps'
- defaultdepth: 1
- user: 'admin'
- passwd: 'admin'
- # don't turn this on! it will spit huge amounts of output
- #debug: 1
- #
- #
- path: 'casket/'
- # number of results on each page
- hits_on_page: 10
- # number of results to fetch for suggestion (it will fold multiple sameones)
- hits_for_suggest: 20
- #
- # options used while indexing
- #
- # which tag type to use for search engine (used while indexing)
- type: 'search'
- #
-
-# options for pager
-pager:
- # how many pages to show for navigation?
- max_pages: 20
-
-# configuration for KinoSearch search engine library
-kinosearch:
- index_path: './kinosearch/'
- database: 'unconfigured database name'
- label: 'unconfigured database label'
- encoding: 'iso-8859-2'
- # clean database before opening? (WARNING: this erases existing database)
- clean: 1
- # which field type to index?
- type: 'search'
-
-webpac:
- # default template to use
- template: 'html_ffzg_results_short.tt'
- # path to database files
- db_path: '/data/webpac2/db'
- # path to templates used by WebPAC::Output
- template_path: '/data/webpac2/conf/output/tt'
- # default template for results
- default_template: 'html_ffzg.tt'
- # default user editable css file
- default_css: 'user.css'
- css_path: 'root/css'
- # encoding comming from webpac
- webpac_encoding: 'iso-8859-2'
- # encoding expected by Catalyst
- out_encoding: 'utf-8'
- # define different input formats (types) and perl modules to handle them
- inputs:
- isis: 'WebPAC::Input::ISIS'
- marc: 'WebPAC::Input::MARC'
- excel: 'WebPAC::Input::Excel'
- dbf: 'WebPAC::Input::DBF'
- isi: 'WebPAC::Input::ISI'
- # define delimiters for validation
- delimiters:
- - ' ; '
- - ' : '
- - ' / '
- - ' = '
-editor:
- # open this record when opening editor
- # (it will also be used to deduce default database and input)
- default_record_uri: 'ps/peri/1'
-
-# directives after this are used when indexing using core WebPAC modules
-
-databases:
- # This is empty database created only in Hyper Estraier to merge
- # all three databases
- 'webpac2':
- name: 'Search all'
- links:
- - to: isi
- credit: 10000
-
-# citirani:
-# name: 'CITIRANI'
-# input:
-# - name: radovi
-# type: excel
-# path: '/data/FF/citati/proba.xls'
-# encoding: 'windows-1250'
-# normalize:
-# path: 'conf/isi/isi2xls-citirani.pl'
-# output:
-# - module: 'Excel'
-# path: '/data/FF/citiari/citirani.xls'
-
- isi:
- name: 'ISI'
- input:
- - name: ajdukovicd
- type: isi
- path: '/data/FF/citati/citing/ajdukovicd.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- - name: arambasicl
- type: isi
- path: '/data/FF/citati/citing/arambasicl.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- - name: bratkod
- type: isi
- path: '/data/FF/citati/citing/bratkod.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- - name: buskov
- type: isi
- path: '/data/FF/citati/citing/buskov.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- skip: 1
- - name: butkovica.txt
- type: isi
- path: '/data/FF/citati/citing/butkovica.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- skip: 1
- - name: corkalobiruskid.txt
- type: isi
- path: '/data/FF/citati/citing/corkalobiruskid.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- skip: 1
- - name: hrend
- type: isi
- path: '/data/FF/citati/citing/hrend.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- - name: hromatkoi
- type: isi
- path: '/data/FF/citati/citing/hromatkoi.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- skip: 1
- - name: hudekknezevicj
- type: isi
- path: '/data/FF/citati/citing/hudekknezevicj.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- - name: kaliternalipovcanlj
- type: isi
- path: '/data/FF/citati/citing/kaliternalipovcanlj.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- - name: kardumi
- type: isi
- path: '/data/FF/citati/citing/kardumi.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- - name: kerestesg
- type: isi
- path: '/data/FF/citati/citing/kerestesg.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- skip: 1
- - name: knezovicz
- type: isi
- path: '/data/FF/citati/citing/knezovicz.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- skip: 1
- - name: kolesaricv
- type: isi
- path: '/data/FF/citati/citing/kolesaricv.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- skip: 1
- - name: kuterovacjagodicg
- type: isi
- path: '/data/FF/citati/citing/kuterovacjagodicg.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- - name: lackovicgrgink
- type: isi
- path: '/data/FF/citati/citing/lackovicgrgink.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- - name: lamzaposavecv
- type: isi
- path: '/data/FF/citati/citing/lamzaposavecv.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- - name: manenicai
- type: isi
- path: '/data/FF/citati/citing/manenicai.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- - name: maslicsersicd
- type: isi
- path: '/data/FF/citati/citing/maslicsersicd.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- skip: 1
- - name: radosevicvidacekb
- type: isi
- path: '/data/FF/citati/citing/radosevicvidacekb.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- - name: sverkob
- type: isi
- path: '/data/FF/citati/citing/sverkob.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- - name: galicz
- type: isi
- path: '/data/FF/citati/citing/galicz.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- skip: 1
- - name: tadinacm
- type: isi
- path: '/data/FF/citati/citing/tadinacm.txt'
- encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/tables.pl'
- - name: radovi
- type: excel
- path: '/data/FF/citati/citirani_radovi.xls'
- worksheet: 'Sheet1'
- # encoding: 'ISO-8859-1'
- normalize:
- # - path: 'conf/normalize/isi/isi2xls.pl'
- # - path: 'conf/isi/isi2sorted.pl'
- - path: 'conf/isi/citirani-radovi.pl'
- - name: cropsy
- type: isi
- path: '/data/FF/citati/croatia-psychol.txt'
- normalize:
- - path: 'conf/isi/tables-cropsy.pl'
- skip: 0
- output:
-# - module: 'Excel'
-# path: '/data/FF/citati/data.xls'
-# - module: 'Sorted'
-# path: '/data/FF/citati/sorted/'
-# - module: 'CouchDB'
-# url: 'http://193.198.212.57:5984'
- - module: 'DBI'
- dsn: 'dbi:Pg:dbname=dipl'
- schema: 'conf/isi/schema.sql'
-# table: 'citirani'
+++ /dev/null
-sorted('au',
- prefix( rec('UT') . ' | ',
- rec('AU')
- )
-);
-
-
-
-sorted('cr',
- suffix(
- ' | ' . rec('UT') . ' | ' . join_with(' ; ', rec('AU')) . ' | ' . join_with(' ; ', rec('SO')) . ' | ' . rec('PY'),
- rec('CR','full')
- )
-);
-
+++ /dev/null
-sub csv { to('csv',@_) }
-
-#warn( dump(
-# rec('CR','author')
-#)
-#);
-
-my $cr = join_with(' ; ',
- rec('CR','author')
- );
-
-if ( $cr =~ m/SVERKO B/ ) {
-
-
-csv('A',
- rec('PT'),
-);
-
-csv('B',
- join_with(', ',
- rec('AU')
- )
-);
-
-csv('C',
- rec('TI'),
-);
-
-csv('D',
- rec('DE'),
-);
-
-csv('E',
- rec('ID'),
-);
-
-csv('F',
- rec('TC'),
-);
-
-csv('G',
- rec('NR'),
-);
-
-csv('H',
- join_with(' | ',
- rec('CR','full')
- )
-);
-
-#csv('H',
-# rec('CR','author')
-#);
-#
-#csv('I',
-# rec('CR','institution')
-#);
-#
-#csv('J',
-# rec('CR','page')
-#);
-#
-#csv('K',
-# rec('CR','reference')
-#);
-#
-#csv('L',
-# rec('CR','volume')
-#);
-#
-#csv('M',
-# rec('CR','year')
-#);
-
-
-csv('I',
- rec('BP'),
-);
-
-csv('J',
- rec('EP'),
-);
-
-csv('K',
- rec('DT'),
-);
-
-csv('L',
- rec('LA'),
-);
-
-csv('M',
- rec('SN'),
-);
-
-csv('N',
- rec('SO'),
-);
-
-
-
-}
+++ /dev/null
-select distinct citirani_radovi.cr,
- cited.cr_full,
- cited.ut
-from citirani_radovi
-left join cited on (citirani_radovi.cr=cited.cr_full)
-order by citirani_radovi.cr
-;
-
+++ /dev/null
-drop view if exists parovi;
-drop view if exists rpcou;
-drop view if exists citingu;
-drop view if exists citiraniu;
-
-drop table if exists utca;
-create table utca (
- id serial,
- ut text,
- ca text
-);
-
-drop table if exists cited;
-create table cited (
- id serial,
- ca text,
- cr_auth text,
- au text,
- ut text,
- cr_full text,
- cr_year text,
- cr_ref text,
- cr_doi text
-);
-
-drop table if exists authors;
-create table authors (
- id serial,
- ut text,
- au text,
- af text,
- ca text
-);
-
-
-drop table if exists citing;
-create table citing (
- id serial,
- ut text,
- pt text,
- au text,
- af text,
- ti text,
- so text,
- la text,
- dt text,
- c1 text,
- rp text,
- nr integer,
- tc integer,
- pi text,
- py integer,
- di text,
- sc text
-);
-
-drop table if exists rpco;
-create table rpco (
- ut text,
- rp text,
- rpco text
-);
-
-
-drop table if exists citirani;
-create table citirani (
- id serial,
- ca text,
- cr_auth text,
- cr_ref text,
- cr_year text,
- cr_vol text,
- cr_page text,
- ttc integer,
- cr text,
- can text
-);
-
-create view citingu as select distinct ut,pt,au,so,la,dt,nr,tc,pi,py,di,sc,rp from citing ;
-
-create view rpcou as select distinct * from rpco ;
-
-create view parovi as select distinct citirani.ca,
- citirani.cr,
- cited.cr_full,
- cited.ut,
- citingu.pt,
- citingu.au,
- citingu.so,
- citingu.la,
- citingu.dt,
- citingu.nr,
- citingu.tc,
- citingu.pi,
- citingu.py,
- citingu.sc,
- citingu.rp
-from citirani
-left join cited on citirani.cr = cited.cr_full
-left join citingu on cited.ut = citingu.ut
-left join rpcou on cited.ut = rpcou.ut
-;
-
-create view citiraniu as select distinct cr_auth,cr_ref,cr_year,cr_vol,cr_page,ttc,cr from citirani ;
-
-
-drop table if exists cropsy;
-create table cropsy (
- id serial,
- ut text,
- au text,
- c1 text,
- rp text,
- tc integer,
- py integer
-);
-
-
--- CREATE AGGREGATE array_accum (anyelement)
--- (
--- sfunc = array_append,
--- stype = anyarray,
--- initcond = '{}'
--- );
-
--- select d, count(*),
--- array_to_string(array_accum('+'::text),'') as graph
--- from hits group by 1 order by 1 asc;
-
-
--- create index cited_au on cited(au);
--- create index cited_cited on cited(cited);
-
+++ /dev/null
-
-my @c1 = rec_array ('C1');
-my @rp = rec_array ('RP');
-foreach my $au ( rec_array('AU') ) {
- row( 'cropsy',
- ut => rec('UT'),
- au => $au,
- c1 => shift @c1,
- rp => shift @rp,
- tc => rec('TC'),
- py => rec('PY')
- )
-}
-
+++ /dev/null
-# warn dump(rec('AU'));
-# warn dump(rec_array('AU'));
-
-#di => split( /;/, rec(
-
-row( 'citing',
- ut => rec('UT'),
- pt => rec('PT'),
- au => regex('s/,//',
- uc ( frec('AU') )
- ),
- ti => rec('TI'),
- so => rec('SO'),
- la => rec('LA'),
- dt => rec('DT'),
- c1 => frec('C1'),
- rp => uc ( rec('RP') ),
- nr => rec('NR'),
- tc => rec('TC'),
- pi => rec('PI'),
- py => rec('PY'),
- di => rec('DI'),
- sc => rec('SC')
-);
-
-if ( rec('RP') ) {
- row( 'rpco',
- ut => rec('UT'),
- rp => rec('RP'),
- rpco =>
- regex('s/.*,(.*)/$1/',
- regex('s/\.$//',
- rec('RP')
- )
- ),
- );
-}
-
-my @af = rec_array ('AF');
-foreach my $au ( rec_array ('AU') ) {
- foreach my $cr ( rec_array('CR') ) {
- row( 'cited',
- ut => rec('UT'),
- ca => config('input name'),
- cr_auth => $cr->{author},
- au => regex('s/,//',
- uc ( $au )
- ),
- cr_full => $cr->{full},
- cr_year => $cr->{year},
- cr_ref => $cr->{reference}
- );
- }
- row( 'authors',
- ut => rec('UT'),
- ca => config('input name'),
- au => regex('s/,//',
- uc ( $au )
- ),
- af => shift @af,
- )
-}
-
-row( 'utca',
- ut => rec('UT'),
- ca => config('input name')
-);
-
-
projects / webpac2 / commitdiff