--- Webpacus/config.yml 2005/12/06 16:35:11 232 +++ Webpacus/config.yml 2006/04/30 23:20:12 440 @@ -1,15 +1,28 @@ --- #YAML:1.0 # DO NOT USE TABS FOR INDENTATION OR label/value SEPARATION!!! -# configuration for hyper estraier full text search engine +# 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 + defaultnode: 'webpac2' +# defaultnode: 'ps' + defaultdepth: 2 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 @@ -21,10 +34,123 @@ # which tag type to use for search engine (used while indexing) type: 'search' # - # options used for Catalyst only - # - # FIXME encoding comming from Catalyst. - catalyst_encoding: 'UTF-8' + +# 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 @@ -42,10 +168,40 @@ 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 @@ -54,7 +210,7 @@ # define input source input: - # this will create unique name with name of database and mfn + # this will create unique name with name of database and mfn - name: libri # isis type: isis @@ -69,7 +225,7 @@ lookup: 'conf/lookup/isis.pm' # limit number of records to read from database - limit: 100 + #limit: 100 # define normalisation for that source normalize: @@ -77,6 +233,7 @@ tag: 'isis' # path to normalization xml path: 'conf/normalize/isis_ffzg.xml' + #path: 'conf/normalize/isis_ffzg.yml' # another input database - name: peri @@ -89,9 +246,9 @@ tag: 'isis' path: 'conf/normalize/isis_ffzg.xml' - # Kooo... k? + # Komparativna kk: - name: 'Tko zna?' + name: 'Komparativna' input: name: libri @@ -99,7 +256,35 @@ path: '/data/isis_data/ffkk/LIBRI' encoding: '852' lookup: 'conf/lookup/isis.pm' - limit: 100 + #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'