trunk/conf/mjesec.yml

--- #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/'
  fields:
    - 'uri'
    - 'AccompanyingMaterial'
    - 'APA'
    - 'CallNo'
    - 'ContentsNote'
    - 'CorporateName'
    - 'CorporateName2'
    - 'DatePublication'
    - 'EditionNote'
    - 'EditionStatement'
    - 'ExpandedTitle'
    - 'fond'
    - 'Form'
    - 'Frequency'
    - 'GeneralNote'
    - 'ID'
    - 'IdentificationNumbers'
    - 'IntellectResponsNote'
    - 'InternalBibliographies'
    - 'InvNo'
    - 'ISBN'
    - 'ISSN'
    - 'ISN'
    - 'IssuedWith'
    - 'Language'
    - 'level'
    - 'MaterialDesignation'
    - 'MFN'
    - 'NamePublisher'
    - 'Names'
    - 'OriginatingSource'
    - 'ParallelTitle'
    - 'Parts'
    - 'PartsEF'
    - 'PartsID'
    - 'PersonalName'
    - 'PersonalName2'
    - 'PersonalNameOther'
    - 'PhysicalDescription'
    - 'PhysicalDescriptionNote'
    - 'PhysicalDetails'
    - 'Piece'
    - 'PieceAnalitic'
    - 'PieceNum'
    - 'PieceSubtitle'
    - 'PlacePublication'
    - 'Responsibility'
    - 'ResponsibilityFirst'
    - 'ResponsibilitySecond'
    - 'SerialNo'
    - 'Series'
    - 'SeriesTitle'
    - 'Set'
    - 'Set2'
    - 'Subtitle'
    - 'Summary'
    - 'SystemRequirements'
    - 'titleNo'
    - 'TitleProper'
    - 'TitleProper2'
    - 'UDC'
    - 'UDC_All'
    - 'UDCb'
    - 'UncontrolledTerms'
    - 'UniformHeading'
    - 'URL'
    - 'VolumeDesignation'
    - 'AllThes'
    - 'BroaderTerm'
    - 'ClassCode'
    - 'DescriptorEN'
    - 'DescriptorFR'
    - 'DescriptorGE'
    - 'DescriptorHR'
    - 'filename'
    - 'format'
    - 'headline'
    - 'IDths'
    - 'line'
    - 'line2'
    - 'line3'
    - 'line4'
    - 'MicrothesaurusEN'
    - 'MicrothesaurusFR'
    - 'MicrothesaurusGE'
    - 'MicrothesaurusHR'
    - 'NarrowerTerm'
    - 'NonDescriptorEN'
    - 'NonDescriptorFR'
    - 'NonDescriptorGE'
    - 'NonDescriptorHR'
    - 'RelatedTerm'
    - 'ScopeNoteEN'
    - 'ScopeNoteHR'
    - 'SeeBefore'
    - 'SeeNext'
    - 'Source'
    - 'SubjectAreaHR'
    - 'SubjectIndex'
    - 'URL'
  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'

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: ffps 
        credit: 10000
      - to: nsk 
        credit: 10000


  ffps:
    # all variables here will be available as config variables in template
    name: 'Psihologija, Filozofski fakultet u Zagrebu'
    code: 'ps'
    url: 'http://www.knjiznice.ffzg.hr/psihologija'

    # 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: '/backup/isis_backup/sunce2/isisdata/latest/LIBRI/'
        # path: '/data/isis_data/PS/LIBRI/'

        # encoding of character set in isis data
        encoding: 'cp852'

        # lookup
        # lookup: 'conf/lookup/isis_ffzg.yml'

        # limit number of records to read from database
        #limit: 10

        modify_file: 'conf/modify/common.pl'
        
        # define normalisation for that source
        normalize:
          # which tag to use in normalize xml for data?
          # tag: 'isis'
          # path to normalization xml
          #- path: 'conf/normalize/ff-nakladnicka.pl'
          path: 'conf/normalize/ff-libri.pl'
          #- path: 'conf/normalize/minimal.pl'
          #- path: 'conf/normalize/ff-dupli.pl'
          #- path: 'conf/normalize/ffps-spec.pl'

      # another input database
      - name: peri
        type: isis
        path: '/backup/isis_backup/sunce2/isisdata/latest/PERI/PERI'
        encoding: 'cp852'
        #limit: 10
        # modify_file: 'conf/modify/common.pl'
        normalize:
          path: 'conf/normalize/ff-peri.pl'

  nsk:
    name: 'Nacionalna i sveucilisna knjiznica'
    input:
      name: baza
      type: marc
      path: '/backup/data/NSK/BBaza.ISO'
      encoding: 'ISO-8859-2'
      normalize:
        path: 'conf/normalize/ps-casopisi.pl'

1	dpavlin	612	--- #YAML:1.0
2			# DO NOT USE TABS FOR INDENTATION OR label/value SEPARATION!!!
3
4			# encoding of this configuration file
5			config_encoding: 'ISO-8859-2'
6			# encoding in Catalyst.
7			catalyst_encoding: 'UTF-8'
8			# relative path to sites templates under Catalyst root
9			sites_root: 'sites'
10
11			# which indexing engine to use? (hyperestraier is default)
12	dpavlin	635	#use_indexer: 'hyperestraier'
13			use_indexer: 'hyperestraier-native'
14	dpavlin	612	#use_indexer: 'kinosearch'
15
16			# configuration for Hyper Estraier full text search engine
17			hyperestraier:
18			#url: 'http://localhost:1978/node/webpac2'
19			masterurl: 'http://localhost:1978'
20			defaultnode: 'webpac2'
21			# defaultnode: 'ps'
22			defaultdepth: 1
23			user: 'admin'
24			passwd: 'admin'
25			# don't turn this on! it will spit huge amounts of output
26			#debug: 1
27			#
28	dpavlin	635	#
29			path: 'casket/'
30	dpavlin	612	# number of results on each page
31			hits_on_page: 10
32			# number of results to fetch for suggestion (it will fold multiple sameones)
33			hits_for_suggest: 20
34			#
35			# options used while indexing
36			#
37			# which tag type to use for search engine (used while indexing)
38			type: 'search'
39			#
40
41			# options for pager
42			pager:
43			# how many pages to show for navigation?
44			max_pages: 20
45
46			# configuration for KinoSearch search engine library
47			kinosearch:
48			index_path: './kinosearch/'
49			fields:
50			- 'uri'
51			- 'AccompanyingMaterial'
52			- 'APA'
53			- 'CallNo'
54			- 'ContentsNote'
55			- 'CorporateName'
56			- 'CorporateName2'
57			- 'DatePublication'
58			- 'EditionNote'
59			- 'EditionStatement'
60			- 'ExpandedTitle'
61			- 'fond'
62			- 'Form'
63			- 'Frequency'
64			- 'GeneralNote'
65			- 'ID'
66			- 'IdentificationNumbers'
67			- 'IntellectResponsNote'
68			- 'InternalBibliographies'
69			- 'InvNo'
70			- 'ISBN'
71			- 'ISSN'
72			- 'ISN'
73			- 'IssuedWith'
74			- 'Language'
75			- 'level'
76			- 'MaterialDesignation'
77			- 'MFN'
78			- 'NamePublisher'
79			- 'Names'
80			- 'OriginatingSource'
81			- 'ParallelTitle'
82			- 'Parts'
83			- 'PartsEF'
84			- 'PartsID'
85			- 'PersonalName'
86			- 'PersonalName2'
87			- 'PersonalNameOther'
88			- 'PhysicalDescription'
89			- 'PhysicalDescriptionNote'
90			- 'PhysicalDetails'
91			- 'Piece'
92			- 'PieceAnalitic'
93			- 'PieceNum'
94			- 'PieceSubtitle'
95			- 'PlacePublication'
96			- 'Responsibility'
97			- 'ResponsibilityFirst'
98			- 'ResponsibilitySecond'
99			- 'SerialNo'
100			- 'Series'
101			- 'SeriesTitle'
102			- 'Set'
103			- 'Set2'
104			- 'Subtitle'
105			- 'Summary'
106			- 'SystemRequirements'
107			- 'titleNo'
108			- 'TitleProper'
109			- 'TitleProper2'
110			- 'UDC'
111			- 'UDC_All'
112			- 'UDCb'
113			- 'UncontrolledTerms'
114			- 'UniformHeading'
115			- 'URL'
116			- 'VolumeDesignation'
117			- 'AllThes'
118			- 'BroaderTerm'
119			- 'ClassCode'
120			- 'DescriptorEN'
121			- 'DescriptorFR'
122			- 'DescriptorGE'
123			- 'DescriptorHR'
124			- 'filename'
125			- 'format'
126			- 'headline'
127			- 'IDths'
128			- 'line'
129			- 'line2'
130			- 'line3'
131			- 'line4'
132			- 'MicrothesaurusEN'
133			- 'MicrothesaurusFR'
134			- 'MicrothesaurusGE'
135			- 'MicrothesaurusHR'
136			- 'NarrowerTerm'
137			- 'NonDescriptorEN'
138			- 'NonDescriptorFR'
139			- 'NonDescriptorGE'
140			- 'NonDescriptorHR'
141			- 'RelatedTerm'
142			- 'ScopeNoteEN'
143			- 'ScopeNoteHR'
144			- 'SeeBefore'
145			- 'SeeNext'
146			- 'Source'
147			- 'SubjectAreaHR'
148			- 'SubjectIndex'
149			- 'URL'
150			database: 'unconfigured database name'
151			label: 'unconfigured database label'
152			encoding: 'iso-8859-2'
153			# clean database before opening? (WARNING: this erases existing database)
154			clean: 1
155			# which field type to index?
156			type: 'search'
157
158			webpac:
159			# default template to use
160			template: 'html_ffzg_results_short.tt'
161			# path to database files
162			db_path: '/data/webpac2/db'
163			# path to templates used by WebPAC::Output
164			template_path: '/data/webpac2/conf/output/tt'
165			# default template for results
166			default_template: 'html_ffzg.tt'
167			# default user editable css file
168			default_css: 'user.css'
169			css_path: 'root/css'
170			# encoding comming from webpac
171			webpac_encoding: 'iso-8859-2'
172			# encoding expected by Catalyst
173			out_encoding: 'utf-8'
174			# define different input formats (types) and perl modules to handle them
175			inputs:
176			isis: 'WebPAC::Input::ISIS'
177			marc: 'WebPAC::Input::MARC'
178			excel: 'WebPAC::Input::Excel'
179
180			editor:
181			# open this record when opening editor
182			# (it will also be used to deduce default database and input)
183			default_record_uri: 'ps/libri/1'
184
185			# directives after this are used when indexing using core WebPAC modules
186
187			databases:
188			# This is empty database created only in Hyper Estraier to merge
189			# all three databases
190			'webpac2':
191			name: 'Search all'
192			links:
193			- to: ffps
194			credit: 10000
195	dpavlin	802	- to: nsk
196	dpavlin	612	credit: 10000
197
198
199			ffps:
200			# all variables here will be available as config variables in template
201			name: 'Psihologija, Filozofski fakultet u Zagrebu'
202			code: 'ps'
203			url: 'http://www.knjiznice.ffzg.hr/psihologija'
204
205			# define input source
206			input:
207			# this will create unique name with name of database and mfn
208			- name: libri
209			# isis
210			type: isis
211
212			# full path to database
213			path: '/backup/isis_backup/sunce2/isisdata/latest/LIBRI/'
214			# path: '/data/isis_data/PS/LIBRI/'
215
216			# encoding of character set in isis data
217	dpavlin	629	encoding: 'cp852'
218	dpavlin	612
219			# lookup
220	dpavlin	754	# lookup: 'conf/lookup/isis_ffzg.yml'
221	dpavlin	612
222			# limit number of records to read from database
223			#limit: 10
224
225	dpavlin	802	modify_file: 'conf/modify/common.pl'
226	dpavlin	660
227	dpavlin	612	# define normalisation for that source
228			normalize:
229			# which tag to use in normalize xml for data?
230			# tag: 'isis'
231			# path to normalization xml
232	dpavlin	795	#- path: 'conf/normalize/ff-nakladnicka.pl'
233	dpavlin	802	path: 'conf/normalize/ff-libri.pl'
234	dpavlin	795	#- path: 'conf/normalize/minimal.pl'
235	dpavlin	792	#- path: 'conf/normalize/ff-dupli.pl'
236	dpavlin	802	#- path: 'conf/normalize/ffps-spec.pl'
237	dpavlin	612
238			# another input database
239			- name: peri
240			type: isis
241			path: '/backup/isis_backup/sunce2/isisdata/latest/PERI/PERI'
242	dpavlin	629	encoding: 'cp852'
243	dpavlin	612	#limit: 10
244	dpavlin	758	# modify_file: 'conf/modify/common.pl'
245	dpavlin	612	normalize:
246	dpavlin	758	path: 'conf/normalize/ff-peri.pl'
247	dpavlin	612
248	dpavlin	795	nsk:
249			name: 'Nacionalna i sveucilisna knjiznica'
250			input:
251			name: baza
252			type: marc
253			path: '/backup/data/NSK/BBaza.ISO'
254			encoding: 'ISO-8859-2'
255			normalize:
256	dpavlin	802	path: 'conf/normalize/ps-casopisi.pl'
257	dpavlin	758