#modnlp.idx.IndexManager's properties (tailored to ECPC indexing)
#Wed May 16 15:29:14 IST 2007
tokeniser.ignore.elements=(omit|ignore|header|chair|heading|post|name)
## index header files?
index.headers=true
## which element should be indexed (i.e. text within elements
## specified here will be indexed and can form subcorpora if xquery
## restrictions are applied. Format: a regexp grouping 
subcorpusindexer.element=(speech|writing)
## which attribute from the element above will we use to uniquely
## identify the text segments. Attribute mus be of xml type ID
subcorpusindexer.attribute=ref
## specify 'root' xml element, relative to which the xqueries will be
## formulated
xquery.root.element.path=//intervention
## the element to be returned by xquery to select which indexed texts
## should be included in the inverted-index query
xquery.return.attribute.path=(speech|writing)/@ref
## specs and paths all relative to xquery.root.element.path
## form: description_1;path_1;description_2;path_2,...
xquery.attribute.chooser.specs=File name;../../header/@filename;Spoken language;speech/@language;Written language;writing/@language;Affiliation;(speaker|writer)/affiliation/@EPparty
header.extension=hed
## the maximum number of subcorpus constraint query results to be stored (by HeaderDBManager)
xquery.max.cache.size=23
file.encoding=UTF8
xquery.root.filedescription.path=/header
## xquery expression that returns a (human-readable) file description 
xquery.file.description.return={data($s/@filename)}<sep/>{data($s/@language)}<sep/>{data($s/index/label)}, {data($s/index/place)}, {data($s/index/date)}, {data($s/index/edition)}