webpac2/Webpacus/config.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: '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
  #
  # number of results on each page
  hits_on_page: 30
  # 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'

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: ps
        credit: 10000
      - to: kk
        credit: 5000

  # Psihologija
  'ps':
    # 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/isis_data/ffps-libri/LIBRI'
    
        # encoding of character set in isis data
        encoding: '852'
    
        # lookup
        lookup: 'conf/lookup/isis.pm'
    
        # limit number of records to read from database
        #limit: 100
    
        # define normalisation for that source
        normalize:
          # which tag to use in normalize xml for data?
          tag: 'isis'
          # path to normalization xml
          path: 'conf/normalize/isis_ffzg.xml'
          #path: 'conf/normalize/isis_ffzg.yml'
  
      # another input database
      - name: peri
        type: isis
        path: '/data/isis_data/ffps-peri/PERI'
        encoding: '852'
        lookup: 'conf/lookup/isis.pm'
        #limit: 100
        normalize:
          tag: 'isis'
          path: 'conf/normalize/isis_ffzg.xml'

  # Komparativna
  kk:
    name: 'Komparativna'
  
    input:
      name: libri
      type: isis
      path: '/data/isis_data/ffkk/LIBRI'
      encoding: '852'
      lookup: 'conf/lookup/isis.pm'
      #limit: 100
      normalize:
        tag: 'isis'
        path: 'conf/normalize/isis_ffzg.xml'
  
  jzav:
    name: 'Jadranski zavod'
    input:
      name: knjige
      type: isis
      path: '/data/isis_data/jzav/BIB'
      encoding: '852'
      lookup: 'conf/lookup/jzav.yml'
      #limit: 100
      normalize:
        tag: 'isis'
        path: 'conf/normalize/isis_ffzg.xml'
  
  efzg:
    name: 'Ekonomski fakutet u Zagrebu'
    input:
      name: knjige
      type: marc
      path: '/data/isis_data/efzg/unimarc.iso'
      encoding: '852'
      # CroList recoding pairs to fix encoding problems
      recode: 'ÏC È Ïc è ÂC Æ Âc æ ò ð ÏS © Ïs ¹ ÏZ ® Ïz ¾'
      lookup: 'conf/lookup/isis.pm'
      #limit: 100
      normalize:
        tag: 'isis'
        path: 'conf/normalize/isis_ffzg.xml'
  
1	--- #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	use_indexer: 'hyperestraier'
13	#use_indexer: 'kinosearch'
14
15	# configuration for Hyper Estraier full text search engine
16	hyperestraier:
17	#url: 'http://localhost:1978/node/webpac2'
18	masterurl: 'http://localhost:1978'
19	defaultnode: 'webpac2'
20	# defaultnode: 'ps'
21	defaultdepth: 1
22	user: 'admin'
23	passwd: 'admin'
24	# don't turn this on! it will spit huge amounts of output
25	#debug: 1
26	#
27	# number of results on each page
28	hits_on_page: 30
29	# number of results to fetch for suggestion (it will fold multiple sameones)
30	hits_for_suggest: 20
31	#
32	# options used while indexing
33	#
34	# which tag type to use for search engine (used while indexing)
35	type: 'search'
36	#
37
38	# options for pager
39	pager:
40	# how many pages to show for navigation?
41	max_pages: 20
42
43	# configuration for KinoSearch search engine library
44	kinosearch:
45	index_path: './kinosearch/'
46	fields:
47	- 'uri'
48	- 'AccompanyingMaterial'
49	- 'APA'
50	- 'CallNo'
51	- 'ContentsNote'
52	- 'CorporateName'
53	- 'CorporateName2'
54	- 'DatePublication'
55	- 'EditionNote'
56	- 'EditionStatement'
57	- 'ExpandedTitle'
58	- 'fond'
59	- 'Form'
60	- 'Frequency'
61	- 'GeneralNote'
62	- 'ID'
63	- 'IdentificationNumbers'
64	- 'IntellectResponsNote'
65	- 'InternalBibliographies'
66	- 'InvNo'
67	- 'ISBN'
68	- 'ISSN'
69	- 'ISN'
70	- 'IssuedWith'
71	- 'Language'
72	- 'level'
73	- 'MaterialDesignation'
74	- 'MFN'
75	- 'NamePublisher'
76	- 'Names'
77	- 'OriginatingSource'
78	- 'ParallelTitle'
79	- 'Parts'
80	- 'PartsEF'
81	- 'PartsID'
82	- 'PersonalName'
83	- 'PersonalName2'
84	- 'PersonalNameOther'
85	- 'PhysicalDescription'
86	- 'PhysicalDescriptionNote'
87	- 'PhysicalDetails'
88	- 'Piece'
89	- 'PieceAnalitic'
90	- 'PieceNum'
91	- 'PieceSubtitle'
92	- 'PlacePublication'
93	- 'Responsibility'
94	- 'ResponsibilityFirst'
95	- 'ResponsibilitySecond'
96	- 'SerialNo'
97	- 'Series'
98	- 'SeriesTitle'
99	- 'Set'
100	- 'Set2'
101	- 'Subtitle'
102	- 'Summary'
103	- 'SystemRequirements'
104	- 'titleNo'
105	- 'TitleProper'
106	- 'TitleProper2'
107	- 'UDC'
108	- 'UDC_All'
109	- 'UDCb'
110	- 'UncontrolledTerms'
111	- 'UniformHeading'
112	- 'URL'
113	- 'VolumeDesignation'
114	- 'AllThes'
115	- 'BroaderTerm'
116	- 'ClassCode'
117	- 'DescriptorEN'
118	- 'DescriptorFR'
119	- 'DescriptorGE'
120	- 'DescriptorHR'
121	- 'filename'
122	- 'format'
123	- 'headline'
124	- 'IDths'
125	- 'line'
126	- 'line2'
127	- 'line3'
128	- 'line4'
129	- 'MicrothesaurusEN'
130	- 'MicrothesaurusFR'
131	- 'MicrothesaurusGE'
132	- 'MicrothesaurusHR'
133	- 'NarrowerTerm'
134	- 'NonDescriptorEN'
135	- 'NonDescriptorFR'
136	- 'NonDescriptorGE'
137	- 'NonDescriptorHR'
138	- 'RelatedTerm'
139	- 'ScopeNoteEN'
140	- 'ScopeNoteHR'
141	- 'SeeBefore'
142	- 'SeeNext'
143	- 'Source'
144	- 'SubjectAreaHR'
145	- 'SubjectIndex'
146	- 'URL'
147	database: 'unconfigured database name'
148	label: 'unconfigured database label'
149	encoding: 'iso-8859-2'
150	# clean database before opening? (WARNING: this erases existing database)
151	clean: 1
152	# which field type to index?
153	type: 'search'
154
155	webpac:
156	# default template to use
157	template: 'html_ffzg_results_short.tt'
158	# path to database files
159	db_path: '/data/webpac2/db'
160	# path to templates used by WebPAC::Output
161	template_path: '/data/webpac2/conf/output/tt'
162	# default template for results
163	default_template: 'html_ffzg.tt'
164	# default user editable css file
165	default_css: 'user.css'
166	css_path: 'root/css'
167	# encoding comming from webpac
168	webpac_encoding: 'iso-8859-2'
169	# encoding expected by Catalyst
170	out_encoding: 'utf-8'
171	# define different input formats (types) and perl modules to handle them
172	inputs:
173	isis: 'WebPAC::Input::ISIS'
174	marc: 'WebPAC::Input::MARC'
175
176	editor:
177	# open this record when opening editor
178	# (it will also be used to deduce default database and input)
179	default_record_uri: 'ps/libri/1'
180
181	# directives after this are used when indexing using core WebPAC modules
182
183	databases:
184	# This is empty database created only in Hyper Estraier to merge
185	# all three databases
186	'webpac2':
187	name: 'Search all'
188	links:
189	- to: ps
190	credit: 10000
191	- to: kk
192	credit: 10000
193	- to: jzav
194	credit: 10000
195
196	# site with alternative databases
197	'hr':
198	name: 'Primjer za hrvatsko suèelje'
199	links:
200	- to: ps
201	credit: 10000
202	- to: kk
203	credit: 5000
204
205	# Psihologija
206	'ps':
207	# all variables here will be available as config variables in template
208	name: 'Knji¾nica psihologije'
209	code: 'ps'
210
211	# define input source
212	input:
213	# this will create unique name with name of database and mfn
214	- name: libri
215	# isis
216	type: isis
217
218	# full path to database
219	path: '/data/isis_data/ffps-libri/LIBRI'
220
221	# encoding of character set in isis data
222	encoding: '852'
223
224	# lookup
225	lookup: 'conf/lookup/isis.pm'
226
227	# limit number of records to read from database
228	#limit: 100
229
230	# define normalisation for that source
231	normalize:
232	# which tag to use in normalize xml for data?
233	tag: 'isis'
234	# path to normalization xml
235	path: 'conf/normalize/isis_ffzg.xml'
236	#path: 'conf/normalize/isis_ffzg.yml'
237
238	# another input database
239	- name: peri
240	type: isis
241	path: '/data/isis_data/ffps-peri/PERI'
242	encoding: '852'
243	lookup: 'conf/lookup/isis.pm'
244	#limit: 100
245	normalize:
246	tag: 'isis'
247	path: 'conf/normalize/isis_ffzg.xml'
248
249	# Komparativna
250	kk:
251	name: 'Komparativna'
252
253	input:
254	name: libri
255	type: isis
256	path: '/data/isis_data/ffkk/LIBRI'
257	encoding: '852'
258	lookup: 'conf/lookup/isis.pm'
259	#limit: 100
260	normalize:
261	tag: 'isis'
262	path: 'conf/normalize/isis_ffzg.xml'
263
264	jzav:
265	name: 'Jadranski zavod'
266	input:
267	name: knjige
268	type: isis
269	path: '/data/isis_data/jzav/BIB'
270	encoding: '852'
271	lookup: 'conf/lookup/jzav.yml'
272	#limit: 100
273	normalize:
274	tag: 'isis'
275	path: 'conf/normalize/isis_ffzg.xml'
276
277	efzg:
278	name: 'Ekonomski fakutet u Zagrebu'
279	input:
280	name: knjige
281	type: marc
282	path: '/data/isis_data/efzg/unimarc.iso'
283	encoding: '852'
284	# CroList recoding pairs to fix encoding problems
285	recode: 'ÏC È Ïc è ÂC Æ Âc æ ò ð ÏS © Ïs ¹ ÏZ ® Ïz ¾'
286	lookup: 'conf/lookup/isis.pm'
287	#limit: 100
288	normalize:
289	tag: 'isis'
290	path: 'conf/normalize/isis_ffzg.xml'
291