--- #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)
# disable indexer
use_indexer: ''
#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
  #
  # if using hyperestraier-native use following:
  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'
    gutenberg: 'WebPAC::Input::Gutenberg'
    dbf: 'WebPAC::Input::DBF'
  # 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/libri/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: ps
        credit: 10000
      - to: kk
        credit: 10000
      - to: jzav
        credit: 10000

  # site with alternative databases
  'hr':
    name: 'Primjer za hrvatsko suèelje'
    links:
      - to: ffps
        credit: 10000
      - to: ffkk
        credit: 5000
      - to: fffo
        credit: 10000

  # Psihologija
  'ffps':
    # all variables here will be available as config variables in template
    name: 'Knji¾nica psihologije'
    code: 'ps'
  
    # define input source
    input:
      # this will create unique name with name of database and mfn
      - name: libri
        # isis
        type: isis
    
        # full path to database
        path: '/data/FF/ps/LIBRI'
    
        # encoding of character set in isis data
        encoding: 'cp852'
    
        # limit number of records to read from database
        #limit: 100
    
        # define normalisation for that source
        modify_file: 'conf/modify/common.pl' 
        normalize:
          # which tag to use in normalize xml for data?
            # path to normalization xml
          path: 'conf/normalize/ff-libri.pl'
  
      # another input database
      - name: peri
        type: isis
        path: '/data/isis_data/ffps-peri/PERI'
        encoding: 'cp852'
        #limit: 100
        normalize:
          tag: 'isis'
          path: 'conf/normalize/common.pl'

  # Komparativna
  ffkk:
    name: 'Komparativna knji¾evnost, Filozofski fakultet u Zagrebu'
  
    input:
      - name: libri
        type: isis
        path: '/data/isis_data/ffkk-libri/LIBRI'
        encoding: 'cp852'
        modify_file: 'conf/modify/common.pl'
        normalize:
#          path: 'conf/normalize/common.pl'
          path: 'conf/normalize/mapping.pl'
      - name: peri
        type: isis
        path: '/data/isis_data/ffkk-peri/PERI'
        encoding: 'cp852'
        modify_file: 'conf/modify/common.pl'
        normalize:
#          path: 'conf/normalize/common.pl'
          path: 'conf/normalize/mapping.pl'
      - name: arti
        type: isis
        path: '/data/isis_data/ffkk-arti/ARTI'
        encoding: 'cp852'
        modify_file: 'conf/modify/ffkk-arti.pl'
        normalize:
#          - path: 'conf/normalize/common.pl'
          - path: 'conf/normalize/mapping.pl'
          - path: 'conf/lookup/ffkk-arti.pl'
  
  fffo:
    name: 'Filozofski Fakultet - Fonetika'
  
    input:
      name: libri
      type: isis
      path: '/data/isis_data/fffo-libri/LIBRI'
      encoding: 'cp852'
      #limit: 100
      normalize:
        tag: 'isis'
        path: 'conf/normalize/common.pl'

  jzav:
    name: 'Jadranski zavod'
    input:
      name: knjige
      type: isis
      path: '/data/isis_data/jzav/BIB'
      encoding: 'cp852'
      #limit: 100
      normalize:
        tag: 'isis'
        path: 'conf/normalize/common.pl'
  
  efzg:
    name: 'Ekonomski fakutet u Zagrebu'
    input:
      name: knjige
      type: marc
      path: '/data/isis_data/efzg/unimarc.iso'
      encoding: 'cp852'
      # CroList recoding pairs to fix encoding problems
      recode: 'ÏC È Ïc è ÂC Æ Âc æ ò ð ÏS © Ïs ¹ ÏZ ® Ïz ¾'
      #limit: 100
      normalize:
        tag: 'isis'
        path: 'conf/normalize/common.pl'
  
  ffsfb:
    name: 'Slavenska filologija (B), Filozofski fakulteti u Zagrebu'
    input:
      name: libri
      type: isis
      path: '/data/isis_data/ffsfb-libri/'
      encoding: 'cp852'
      #limit: 10
      modify_records:
        200:
          '^a':
            ' ; ': '^k'
          '^d':
            '^e': ' : '
          '^e':
            '^d': ' = '
          '*':
            '^g': ' ; '
        210:
          '*':
            '^c': '^b'
            '^d': '^c'
            '. (': '. (^e'
            ' : ': ' :^f' 
        700:
          '^a':
            '^b': ', '
        701:
          '^a':
            '^b': ', '
        702:
          '^a':
            '^b': ', '
      normalize:
        path: 'conf/normalize/common.pl'
  fflo:
    name: 'Lingvistika, Filozofski fakultet u Zagrebu'
    input:
      name: libri
      type: isis
      path: '/data/isis_data/fflo-libri/LIBRI'
      encoding: 'cp852'
      #limit: 10
      modify_records:
        200:
          '^d':
            '^e': ' : '
          '^e':
            '^d': ' = '
          '*':
            '^g': ' ; '
            '^c': '. '
        210:
          '*':
            '^c': '^b'
            '^d': '^c'
        700:
          '^a':
            '^b': ', '
        701:
          '^a':
            '^b': ', '
        702:
          '^a':
            '^b': ', '
      normalize:
        path: 'conf/normalize/common.pl'

  gutenberg:
    name: 'Project Gutenberg archive'
    input:
      name: archive
      type: gutenberg
      path: 't/data/gutenberg-small.rdf'
      normalize:
        path: 'conf/normalize/common.pl'

  sand:
    name: 'SAND'
    input:
      name: casopisi
      type: dbf
      path: 't/data/cas2000.dbf'
      normalize:
        path: 'conf/normalize/common.pl'
#      mapping_path: 'conf/input/dbf/cas2000.yml'

  exhibit:
    name: 'SMILE Exhibit based ouptput for WebPAC'
    input:
      name: 'FFZG - Psihologija'
      type: marc
      path: 'out/marc/ffsf-peri.marc'
      encoding: 'cp852'
      normalize:
        path: 'conf/normalize/json.pl'
    output:
      module: 'JSON'
      path: 'out/exhibit/ps.js'

  hidra:
    name: 'HIDRA'
    input:
      - name: bib
        type: isis
        path: '/data/hidra/BIB'
        encoding: 'cp852'
        #modify_file: 'conf/modify/common.pl'
        normalize:
          path: 'conf/normalize/minimal.pl' 

  webpacus:
    name: 'Webpacus'
    input:
      name: 'foobar'
      type: marc 
#      path: 'out/marc/ffsf-peri.marc'
#      path: 'out/marc/ffkk-libri.marc'
#      path: '/data/hidra/BIB'
#      path: '/data/FF/ps/LIBRI'
      path: '/data/FF/iz/ffiz-libri.marc'
      encoding: 'UTF-8'
      normalize:
        path: 'conf/normalize/webpacus.pl'
    output:
      - module: 'KinoSearch'
        path: 'var/kinosearch'
      - module: 'Sorted'
        path: 'var/sorted'
      - module: 'Webpacus'
        path: '/data/Webpacus2'