# gnomap.properties
# for dmel het fff/gnomap feature data

LIB_NAME=gnomap
title = FlyBase Genome Feaures

#  leave these to command line args?
DATA_ROOT=web/data/genomes/Drosophila_melanogaster/current/fff/
# INDEX_PATH=web/genomes/Drosophila_melanogaster/current/indices/fff/

MIME_TYPE=text/tsv

## ---- search/report ---------------------
## default search field
searchfield=all
format=native
# outfields=chr,start,feature,gene,range.stop,id

resultspage = results.jsp
## for xslt to produce the result page tables
# resultxsl = conf/fbab_result.xsl
# resultspage = resultxsl.jsp

header.native=# Chr	Start	Feature	gene    map     range   id      db_xref         notes
footer.native=
header.xml=<?xml version="1.0" encoding="ISO-8859-1"?>\n<LuceGene>
footer.xml=</LuceGene>
xsl = gnomap.xsl
# xsl = fban.xsl


docurl=/cgi-bin/gbrowse_fb/dmel?id=

outfields= gene,feature,chr,start,range.stop,url
storefields= gene,chr,start,feature,range.stop,db_xref
# displayFields = gene,chr,start,feature,range,db_xref
#        chr     db_xref docclass        docid   feature gene    id      map     modified        notes   
# range   range.start     range.stop      range.strand    start   uid     url

searchskip.range=1
searchskip.start=1
title.range.strand=strand
title.range.stop=stop
title.range.start=start
 
## --- field indexing -------------------
# locate data with regex file, folder patterns

regex_folder=^\\w.+$
regex_file=^.*\\.fff$
regex_skipfile=.*\\.old
regex_skipfolder=tmp|old.*|.*\\.old

INDEX_CLASS=org.eugenes.index.LuceneTableIndexer
analyzer=org.eugenes.index.BiodataAnalyzer

fieldnames_lastcomment=false
fieldnames_firstline=false
fieldnames=chr start feature gene map range id db_xref notes

regex_comment=^\\s*[!#]

## table field separator regex

## any whitespace
# regex_keyval=\\s*(\\S+)
## tabs only
regex_keyval=\\t*([^\\t]+)
## commas
# regex_keyval=,*([^,]+)
## commas, optional quotes
# regex_keyval=,*([^,]+)|,*"([^"]+)"


## append existing index or create new
INDEX_APPEND=false
## index <tag> names as values (as well as field names)?
INDEX_TAGS=false
## index <tag attr="val"> values ?
INDEX_ATTRIBUTES=false
## use fieldname xpath; full top.middle.last field name?
INDEX_XPATH=false
## INDEX_LEVEL=0 means index main records one level below xml <top> tag 
INDEX_LEVEL=2
INDEX_BLANKS=false


merge_factor=10
max_field_length=1000000
## memory crash cure:
MAX_FIELDS=10000

# to create "contents" field of all text
indexall=false

## field indexing parameters

# special summary fields -- replace w/ fieldalias.TAG=newtag
sumfields=docid,docclass
field.docid=id
field.docclass=feature

## fieldalias.OLDTAG=NEWTAG
## fieldalias precedes fieldtype.tag processing
# fieldalias.GID=ID


## default - UnStored = index but dont store text
fieldtype=Text
# fieldtype.contents=UnStored
# fieldtype.summary=UnIndexed
fieldtype.ancestors=ignore

## these must always be stored; Text or UnIndexed
fieldtype.docid=Text
fieldtype.docclass=Text
fieldtype.url=Text
fieldtype.modified=Keyword


analyzer=org.eugenes.index.BiodataAnalyzer

## field filters
tokenfilter=org.eugenes.index.BiodataAnalyzer$DataFilter
#tokenfilter.SYM=org.eugenes.index.BiodataAnalyzer$DataFilter
#tokenfilter.ID=org.eugenes.index.BiodataAnalyzer$LowerDataFilter
#tokenfilter.contents=org.eugenes.index.BiodataAnalyzer$LowerWordFilter

# tokenfilter.len=org.eugenes.index.BiodataAnalyzer$NumberFilter
tokenfilter.range.start=org.eugenes.index.BiodataAnalyzer$NumberFilter
tokenfilter.range.stop=org.eugenes.index.BiodataAnalyzer$NumberFilter

## field tokenizers -- replace with filters
tokenizer=org.eugenes.index.BiodataAnalyzer$LowerDataTokenizer
#tokenizer.contents=org.eugenes.index.BiodataAnalyzer$LowerWordTokenizer
tokenizer.db_xref=org.eugenes.index.BiodataAnalyzer$LowerWordTokenizer

fieldrecoder.range=LucegeneIndexers$Location_FieldRecoder

## parse chr field from top source line
#source  fly     2L      1..22217931     -       -       -
##fieldrecoder.feature=LucegeneIndexers$FeatureSourceChr_FieldRecoder
##fieldrecoder.map=LucegeneIndexers$FeatureSourceChr_FieldRecoder