source: collections/documented-examples/trunk/marc-e/etc/collect.cfg@ 19357

creator     [email protected]
maintainer  [email protected]
public      true

buildtype   mgpp

indexes     text dc.Title
defaultindex    text

levels  document

plugin      GreenstoneXMLPlugin
plugin      MARCPlugin -OIDtype incremental
plugin      MetadataXMLPlugin
plugin      ArchivesInfPlugin
plugin      DirectoryPlugin

classify    AZList -metadata dc.Title -removesuffix \\s*(\\/|;|,|\\.).* 
classify    AZCompactList -metadata dc.Creator -removesuffix (b\\.\\s+)?(\\d+(\\-?))(\\d+(\\.)?)? 
classify    AZCompactList -metadata dc.Subject 

format VList "<td>[link][icon][/link]</td>
<td>{If}{[numleafdocs],[Title],<b>[dc.Title]</b>{If}{[dc.Creator], [sibling:dc.Creator]}{If}{[dc.Publisher], <i>[dc.Publisher]</i>}}</td>{If}{[numleafdocs],<td><i>([numleafdocs])</i></td>}"

#format CL2VList "<td>[link][icon][/link]</td><td>{If}{[numleafdocs],[Title],[dc.Creator]; <i>[dc.Title]</i>{If}{[dc.Publisher], <i>[dc.Publisher]</i>}}</td><td>{If}{[numleafdocs],<i>([numleafdocs])</i>}</td>"
#format CL3VList "<td>[link][icon][/link]</td><td>{If}{[numleafdocs]{[Title],[dc.Title]{If}{[dc.Creator], [dc.Creator]}{If}{[dc.Publisher], [dc.Publisher]}}</td><td>{If}{[numleafdocs],<i>([numleafdocs])</i>}</td>"

format HList "[link][highlight][ex.Title][/highlight][/link]"

format DocumentHeading "[dc.Title]<br>"

format DocumentText "[Text]"

format DocumentButtons ""

format SearchTypes "plain,form"

collectionmeta  .text [l=en] "_labeltext_"
collectionmeta  .Title [l=en] "_labelTitle_"
collectionmeta  .Source [l=en] "_labelSource_"

collectionmeta sampleoid "D0s156"

# -- English strings ----------------
collectionmeta  collectionname [l=en] "MARC example"

# -- French strings ----------------
collectionmeta  collectionname [l=fr] "Exemple MARC"

# -- Spanish strings ----------------
collectionmeta  collectionname [l=es] "Colección de muestra MARC"

# -- Russian strings ----------------
collectionmeta  collectionname [l=ru] "ПрОЌер MARC"

# -- English text ----------------
collectionmeta  collectionextra [l=en] "This collection, which contains _about:numdocs_ MARC entries, is based on the MARC records of working papers published by
<a href=\"http://www.cs.waikato.ac.nz\">Computer Science Department</a> at <a href=\"http://www.waikato.ac.nz\">the University of Waikato</a>.
<a href=\"_gwcgi_?l=_cgiargl_&a=d&c=_cgiargc_&d=_sampleoid_\">Here</a> is a sample document in the collection.

<h3>How the collection works</h3>\n

<p>
The <a href=\"_httpcollection_/etc/collect.cfg\" target=collect.cfg>configuration file</a> uses <i>MARCPlugin</i> to process the MARC records, as well as the
standard plugins. There are three classifiers, based on <i>dc.Title</i>,
<i>dc.Creator</i>, and <i>dc.Subject</i> metadata. The <i>Title</i> classifier uses AZList, while the other two use AZCompactList, which groups items with the same metadata into a bookshelf. The <i>-removesuffix</i> argument for the <i>Title</i> and <i>Creator</i>
classifiers removes suffixes from the metadata string (<i>dc.Title</i> and
<i>dc.Creator</i> respectively). This is specified as a PERL regular
expression, and trims characters (such as trailing punctuation)
from the strings for display. 
<p>
The <i>VList</i> format statement controls the display of search results and all classifiers. For bookshelves, the number of leaf documents is displayed on the right-hand side. For documents, <i>dc.Title</i> is displayed, along with <i>dc.Creator</i> and <i>dc.Publisher</i>. <i>[sibling:dc.Creator]</i> is used as dc.Creator has multiple values, and specifies that all values be output, not just the first one.
<p>

The MARC plugin uses a special file to map MARC field numbers to
Greenstone-style metadata. This file resides in the
<i>greenstone/etc</i> directory, and is called
<a href=\"_httpprefix_/etc/marc2dc.txt\" target=marc2dc>marc2dc.txt</a>.
It lists the correspondences between MARC field numbers and Greenstone
metadata. Any MARC fields that are not listed simply do not
appear as metadata, though they are still present in the
Greenstone document. Each line in the file has the format
<blockquote>
&lt;MARC field number&gt; -&gt; GreenstoneMetadataName
</blockquote>
Lines in the file that begin with \"\#\" are comments. \n
<p>
The standard version of this file is loosely based on
the MARC to Dublin Core mapping found at <a
href=\"http://www.loc.gov/marc/marc2dc.html\">http://www.loc.gov/marc/marc2dc.html</a>
(which assumes USMARC/MARC21).
<p>
Multiple MARC fields may map to a single Dublin Core field. 
For example, fields 720 (\"Uncontrolled name\"), 100 (\"Personal name\"), 
110 (\"Corporate name\") and  111 (\"Meeting name\") all map to 
<i>dc.Creator</i>. Actual MARC records normally
define only one of these fields, and anyway Greenstone allows
multi-valued metadata.\n
<p>
Some mappings are dependent on subfields. For example, MARC field 260 contains
information about publication and distribution. Subfields \"c\" (Date of Publication) and \"g\" (Date of manufacture) are mapped to <i>dc.Date</i>, using the following mapping line:
<blockquote>
260$c$g     -&gt; dc.Date
</blockquote>

Greenstone also provides a file for mapping MARC to <b>qualified</b> dublin core: <a href=\"_httpprefix_/etc/marc2qdc.txt\" target=marc2qdc>greenstone/etc/marc2qdc.txt</a>. This can be used by the MARC plugin by setting the <i>-metadata_mapping_file</i> option to \"marc2qdc.txt\". 
"

# -- French text ----------------
collectionmeta  collectionextra [l=fr] "Cette collection, which contains _about:numdocs_ MARC entries, is based on the MARC records of working papers published by
<a href=\"http://www.cs.waikato.ac.nz\">Computer Science Department</a> at <a href=\"http://www.waikato.ac.nz\">the University of Waikato</a>.
<a href=\"_gwcgi_?l=_cgiargl_&a=d&c=_cgiargc_&d=_sampleoid_\">Voici</a> un document échantillon dans la collection.

<h3>Comment marche cette collection ?</h3>

<p>
Le <a href=\"_httpcollection_/etc/collect.cfg\" target=collect.cfg>fichier de configuration</a> utilise <i>ZipPlug</i> et <i>MarcPlug</i> à coté des trois qui sont utilisés en standard.
Il y a trois classificateurs basés sur les méta-données <i>dc.Title</i>, <i>dc.Creator</i> et <i>dc.Subject</i>. _text1_
 Ceci est spécifié comme une expression
réguliÚre de PERL et ajuste pour l\'affichage des caractÚres (comme une ponctuation finale). 
<p>
_text2_

<p>
Le module Marc utilise un fichier spécial pour la mise en correspondance des numéros de champ MARC avec les méta-donnée de type Greenstone. Ce fichier se trouve dans le répertoire <i>gsdl/etc</i>,
et est appelé <a href=\"_httpprefix_/etc/marc2dc.txt\" target=marc2dc>marc2dc.txt</a>. Il liste les correspondences entre les numéros de champ MARC et les méta-données Greenstone. Tous les champs MARC qui ne sont pas listés ne vont pas apparaître comme méta-données, bien qu\'ils spient toujours présents dans le document Greenstone. Chaque ligne dans le fichier à le format:

<blockquote>
&lt;numéro de champ MARC&gt; -&gt; NonMetadonnéeGreenstone
</blockquote>

Les lignes dans le fichier qui commence par \"\#\" sont des commentaires.

<p>
La version standard de ce fichier est approximativement basée sur la mise en correspondance MARC - Dublin Core trouvé à <a href=\"http://www.loc.gov/marc/marc2dc.html\">http://www.loc.gov/marc/marc2dc.html</a>
(qui suppose USMARC/MARC21).
_text3_
"

# -- Spanish text ----------------
collectionmeta  collectionextra [l=es] "Esta colección, which contains _about:numdocs_ MARC entries, is based on the MARC records of working papers published by
<a href=\"http://www.cs.waikato.ac.nz\">Computer Science Department</a> at <a href=\"http://www.waikato.ac.nz\">the University of Waikato</a>. He <a href=\"_gwcgi_?l=_cgiargl_&a=d&c=_cgiargc_&d=_sampleoid_\">aquí</a> un documento muestra de la colección.
<p>

<h3>Cómo trabaja esta colección</h3>
<p>

El <a href=\"_httpcollection_/etc/collect.cfg\" target=collect.cfg>archivo de configuración</a> utiliza <i>MARCPlugin</i> además de los tres plugins estándar. Existen tres clasificadores basados en los metadatos <i>dc.Título</i>, <i>dc.Creador</i> y <i>dc.Asunto</i>. _text1_  Esto se especifica como una expresión regular PERL y ordena los caracteres (como la puntuación que se encuentra al final) a partir de las cadenas para su presentación en pantalla. 
<p>
_text2_

<p>

El plugin de MARC utiliza un archivo especial para mapear y convertir los números de campo MARC a metadatos estilo Greenstone. Este archivo reside en el directorio <i>gsdl/etc</i> y se llama <a href=\"_httpprefix_/etc/marc2dc.txt\" target=marc2dc>marc2dc.txt</a>. Incluye una lista de las correspondencias entre los números de campo MARC y los metadatos Greenstone. Cualquier campo MARC que no esté incluido en la lista simplemente no aparece como metadato, aunque siga estando presente en el documento Greenstone. Cada línea del archivo tiene el siguiente formato:
<p>

<blockquote>
&lt;MARC field number&gt; -&gt; GreenstoneMetadataName
</blockquote>
<p>

Las líneas en el archivo que empiezan con \"\#\" son comentarios.
<p>

La versión estándar de este archivo se basa libremente en el mapeo de MARC a Dublin Core que se encuentra en <a href=\"http://www.loc.gov/marc/marc2dc.html\">http://www.loc.gov/marc/marc2dc.html</a> (el cual asume USMARC/MARC21).

_text3_
"

# -- Russian text ----------------
collectionmeta  collectionextra [l=ru] "This collection, which contains _about:numdocs_ MARC entries, is based on the MARC records of working papers published by
<a href=\"http://www.cs.waikato.ac.nz\">Computer Science Department</a> at <a href=\"http://www.waikato.ac.nz\">the University of Waikato</a>. <a href=\"_gwcgi_?l=_cgiargl_&a=d&c=_cgiargc_&d=_sampleoid_\">ЗЎесь</a> преЎставлеМ тОпПвПй ЎПкуЌеМт ЎаММПй кПллекцОО.

<h3>Как рабПтает кПллекцОя</h3>
<p>

<a href=\"_httpcollection_/etc/collect.cfg\" target=collect.cfg>КПМфОгурацОПММый файл</a> ОспПльзует плагОМы <i>ZIPPlug</i> О <i>MARCPlug</i>, пПЌОЌП третьегП стаМЎарта. ИЌеются трО классОфОкатПра, ПсМПваММые Ма ЌетаЎаММых
 <i>НазваМОя (dc.Title)</i>, <i>СПзЎателя (dc.Creator)</i> О <i>ПреЎЌета (dc.Subject)</i>. _text1_  ЭтП требует устаМПвкО PERL Ўля правОльМПгП выражеМОя, О урезает зМакО (тОпа кПМечМых
 зМакПв препОМаМОя) Оз стрПкО Ўля ПтПбражеМОя. 
<p>
_text2_
<p>

ПлагОМ MARC ОспПльзует спецОальМый файл Ўля сПпПставлеМОя МПЌера пПля в MARC О ЌетаЎаММых
 Greenstone. ЭтПт файл Мах
ПЎОтся в ЎОректПрОО <i>gsdl/etc</i> О Мазывается <a href=\"_httpprefix_/etc/marc2dc.txt\" target=marc2dc>marc2dc.txt</a>. ОМ преЎставляет спОсПк сППтветствОя ЌежЎу МПЌераЌО пПлей сОстеЌы MARC О ЌетаЎаММыЌО Greenstone. ￜюбые пПля MARC, кПтПрые Ме вМесеМы в спОсПк, прПстП Ме пПявляются как ЌетаЎаММые, х
Птя ПМО прОсутствуют в ЎПкуЌеМте Greenstone. КажЎая стрПка в этПЌ файле ОЌеет слеЎующОй фПрЌат.

<blockquote>
&lt;MARC field number&gt; -&gt; GreenstoneMetadataName
</blockquote>
СтрПкО в ЎаММПЌ файле, кПтПрые МачОМаются сП зМака \"\#\", являются кПЌЌеМтарОяЌО. 
<p>

СтаМЎартМая версОя этПгП файла свПбПЎМП базОруется Ма MARC в ПпОсаМОО Dublin Core, кПтПрПе вПспрОМОЌает USMARC/MARC21 О кПтПрПе ЌПжМП МайтО Ма <a href=\"http://www.loc.gov/marc/marc2dc.html\">http://www.loc.gov/marc/marc2dc.html</a>. 

_text3_
"