# some simple testing stuff

SET emboss_qadata $emboss_basedirectory/test
SET emboss_tempdata  $emboss_standard/test

# Standard date for test runs - set to the date of the release
# Used to make the output consistent where an application reports
# today's date

SET emboss_timetoday "2011-07-15 12:00:00"

#######################################
# Standard test databases
#######################################

# Should be uncommented in the installed copy of emboss.default

##################################################################
# Test Databases
# Used by the qatest.pl script to test an EMBOSS installation.
# Comment them out if you do not want your users to use them.
# Examples in the EMBOSS documentation should all run by using
# TEMBL: in place of EMBL:, TSW: in place of SW:, and so on.
##################################################################


# swissprot
# =========

DB tsw [
   type: "Protein"
   directory: "$emboss_tempdata/swiss"
   method: "emblcd"
   format: "swiss"
   release: "36"
   field: "id"
   field: "acc"
   field: "sv"
   field: "des"
   field: "org"
   field: "key"
   comment: "Swissprot native format with EMBL CD-ROM index"
   taxon: "1 all"
   edamdat: "0001230 UniProt protein sequence record"
]

# trembl
# ======

DB tswnew [ type: P dir: $emboss_tempdata/swnew
   method: emblcd format: swiss release: 37 
   fields: "sv des org key"
   comment: "SpTrEmbl as 3 files in native format with EMBL CD-ROM index"
   taxon: "1 all"
   edamdat: "0001230 UniProt protein sequence record"
]

# embl
# ====

DB tembl [ type: N dir: $emboss_tempdata/embl
   method: emblcd format: embl release: 57 
   fields: "sv des org key"
   comment: "EMBL in native format with EMBL CD-ROM index"
   taxon: "1 all"
   edamdat: "0001226 EMBL nucleotide sequence record"
]

# pir
# ===

DB tpir [ type: P dir: $emboss_tempdata/pir
   method: gcg
   file: pir*.seq
   format: nbrf
   fields: "des org key"
   comment: "PIR using NBRF access for 4 files"
   taxon: "1 all"
   edamdat: "0001232 PIR protein sequence record"
]

# Genbank (DKFZ - we are not using the GCG formatted files in test/gb)
# =======

DB tgb [ type: N method: srswww format: genbank
   url: "http://genius.embnet.dkfz-heidelberg.de/menu/cgi-bin/srs7.1.3.1/wgetz"
   dbalias: genbank
   fields: "sv des org key"
   comment: "Genbank IDs"
   taxon: "1 all"
]

# Genbank
# =======

DB tgenbank [ type: N dir: $emboss_tempdata/genbank
   method: emblcd format: genbank release: 01 
   fields: "sv des org key"
   comment: "GenBank in native format with EMBL CD-ROM index"
   taxon: "1 all"
]

# TestDB
# =======

DB testdb [ type: N dir: $emboss_tempdata/testdb
   method: emblcd format: fasta release: 01
   fields: "des"
   comment: "test sequence data" ]

#######################################
### Access method EMBLCD, flatfile data
#######################################

# Nucleotide data (1 file)
# ===============

DB qanflat  [ type: N format: embl method: emblcd
  dir: $emboss_qadata/embl
  indexdir: $emboss_qadata/qa/dbiflat-ex-keep
  comment: "EMBL flatfiles"
  taxon: "1 all"
  edamdat: "0001226 EMBL nucleotide sequence record"
]

DB qanflatall  [ type: N format: embl method: emblcd
  dir: $emboss_qadata/embl
  indexdir: $emboss_qadata/qa/dbiflat-embl-allsys-keep
  comment: "EMBL flatfiles"
  taxon: "1 all"
  edamdat: "0001226 EMBL nucleotide sequence record"
]

DB qanflatexc  [ type: N format: embl method: emblcd
  dir: $emboss_qadata/embl
  exclude: rod.dat
  indexdir: $emboss_qadata/qa/dbiflat-embl-allsys-keep
  comment: "EMBL flatfiles, no rodent file"
  taxon: "1 all"
  edamdat: "0001226 EMBL nucleotide sequence record"
]

DB qanflatinc  [ type: N format: embl method: emblcd
  dir: $emboss_qadata/embl
  file: rod.dat
  exclude: *.dat
  indexdir: $emboss_qadata/qa/dbiflat-embl-allsys-keep
  comment: "EMBL flatfiles, only rodent file"
  edamdat: "0001226 EMBL nucleotide sequence record"
]

DB qanxflat  [ type: N format: embl method: emboss
  dir: $emboss_qadata/embl
  indexdir: $emboss_qadata/qa/dbxflat-ex-keep
  dbalias: embl
  comment: "EMBL flatfiles"
  taxon: "1 all"
  edamdat: "0001226 EMBL nucleotide sequence record"
]

DB qanxflatall  [ type: N format: embl method: emboss
  dir: $emboss_qadata/embl
  indexdir: $emboss_qadata/qa/dbxflat-all-keep
  dbalias: embl
  comment: "EMBL flatfiles"
  taxon: "1 all"
  edamdat: "0001226 EMBL nucleotide sequence record"
]

DB qanxflatexc  [ type: N format: embl method: emboss
  dir: $emboss_qadata/embl
  exclude: rod.dat
  indexdir: $emboss_qadata/qa/dbxflat-all-keep
  dbalias: embl
  comment: "EMBL flatfiles, no rodent file"
  taxon: "1 all"
  edamdat: "0001226 EMBL nucleotide sequence record"
]

DB qanxflatinc  [ type: N format: embl method: emboss
  dir: $emboss_qadata/embl
  file: rod.dat
  exclude: *.dat
  indexdir: $emboss_qadata/qa/dbxflat-all-keep
  dbalias: embl
  comment: "EMBL flatfiles, only rodent file"
  taxon: "1 all"
  edamdat: "0001226 EMBL nucleotide sequence record"
]

# Protein data (3 files)
# ============

DB qapflat  [ type: P format: swiss method: emblcd
  dir: $emboss_qadata/swnew
  indexdir: $emboss_qadata/qa/dbiflat-swiss-keep
  comment: "SpTrEmbl flatfile"
  taxon: "1 all"
  edamdat: "0001230 UniProt protein sequence record"
]

DB qapflatall  [ type: P format: swiss method: emblcd
  dir: $emboss_qadata/swnew
  indexdir: $emboss_qadata/qa/dbiflat-swiss-keep
  comment: "SpTrEmbl flatfiles, all fields indexed"
  fields: "sv des org key"
  taxon: "1 all"
  edamdat: "0001230 UniProt protein sequence record"
]

DB qapxflat  [ type: P format: swiss method: emboss
  dir: $emboss_qadata/swnew
  indexdir: $emboss_qadata/qa/dbxflat-swiss-keep
  dbalias: swnew
  comment: "Swissnew flatfiles"
  taxon: "1 all"
  edamdat: "0001230 UniProt protein sequence record"
]

DB qanxflatall  [ type: N format: embl method: emboss
  dir: $emboss_qadata/embl
  indexdir: $emboss_qadata/qa/dbxflat-all-keep
  fields: "des org key"
  dbalias: embl
  comment: "EMBL flatfiles, all fields indexed"
  taxon: "1 all"
  edamdat: "0001226 EMBL nucleotide sequence record"
]

###########################################
### Access method EMBLCD, FASTA format data
###########################################

DB qanfasta  [ type: N format: fasta method: emblcd
  dir: $emboss_qadata/data
  indexdir: $emboss_qadata/qa/dbifasta-ex-keep
  comment: "FASTA file EMBL rodents"
  taxon: "9989 rodentia"
]

DB qapfasta  [ type: P format: fasta method: emblcd
  dir: $emboss_qadata/data
  indexdir: $emboss_qadata/qa/dbifasta-swiss-keep
  comment: "FASTA file swissnew entries"
  taxon: "1 all"
]

DB qawfasta  [ type: N format: fasta method: emblcd
  dir: $emboss_qadata/data
  indexdir: $emboss_qadata/qa/dbifasta-worm-keep
  comment: "FASTA file wormpep entries"
  taxon: "6239 caenorhabditis elegans"
]

DB qanfastaall  [ type: N format: fasta method: emblcd
  dir: $emboss_qadata/data
  indexdir: $emboss_qadata/qa/dbifasta-allsys-keep
  comment: "FASTA file EMBL rodents, all fields indexed"
  fields: "sv des"
  taxon: "9989 rodentia"
]

###########################################
### Access method EMBOSS, FASTA format data
###########################################

DB qanxfasta  [ type: N format: fasta method: emboss
  dir: $emboss_qadata/data
  indexdir: $emboss_qadata/qa/dbxfasta-ex-keep
  dbalias: emrod
  comment: "FASTA file EMBL rodents"
  taxon: "9989 rodentia"
]

DB qapxfasta  [ type: P format: fasta method: emboss
  dir: $emboss_qadata/data
  indexdir: $emboss_qadata/qa/dbxfasta-swiss-keep
  dbalias: swnew
  comment: "FASTA file swissnew entries"
  taxon: "1 all"
]

DB qawxfasta  [ type: N format: fasta method: emboss
  dir: $emboss_qadata/data
  indexdir: $emboss_qadata/qa/dbxfasta-worm-keep
  dbalias: worm
  comment: "FASTA file wormpep entries"
  taxon: "6239 caenorhabditis elegans"
]

DB qanxfastaall  [ type: N format: fasta method: emboss
  dir: $emboss_qadata/data
  indexdir: $emboss_qadata/qa/dbxfasta-allsys-keep
  fields: "sv des"
  comment: "FASTA file EMBL rodents, all fields indexed"
  dbalias: emrod
  taxon: "9989 rodentia"
]

#######################
### Access method BLAST
#######################

DB qapblast  [ type: P format: ncbi method: blast
  dir: $emboss_qadata/data
  indexdir: $emboss_qadata/qa/dbiblast-ex-keep
  comment: "BLAST swissnew"
  taxon: "1 all"
]

DB qapblastsplit  [ type: P format: ncbi method: blast
  dir: $emboss_qadata/data
  indexdir: $emboss_qadata/qa/dbiblast-split-keep
  comment: "BLAST swissnew split in 5 files"
  taxon: "1 all"
]

DB qapblastsplitexc  [ type: P format: ncbi method: blast
  dir: $emboss_qadata/data
  exclude: swsplit.02.*
  indexdir: $emboss_qadata/qa/dbiblast-split-keep
  comment: "BLAST swissnew split in 5 files, not file 02"
  taxon: "1 all"
]

DB qapblastsplitinc  [ type: P format: ncbi method: blast
  dir: $emboss_qadata/data
  file: swsplit.02.*
  exclude: *
  indexdir: $emboss_qadata/qa/dbiblast-split-keep
  comment: "BLAST swissnew split in 5 files, only file 02"
  taxon: "1 all"
]

DB qapblastall  [ type: P format: ncbi method: blast
  dir: $emboss_qadata/data
  indexdir: $emboss_qadata/qa/dbiblast-allsys-keep
  comment: "BLAST swissnew, all fields indexed"
  fields: "sv des"
  taxon: "1 all"
]

#####################
### access method GCG
#####################

DB qangcg  [ type: N format: embl method: gcg
  dir: $emboss_qadata/embl
  indexdir: $emboss_qadata/qa/dbigcg-ex-keep
  comment: "GCG format EMBL"
  taxon: "1 all"
  edamdat: "0001226 EMBL nucleotide sequence record"
]

DB qangcgexc  [ type: N format: embl method: gcg
  dir: $emboss_qadata/embl
  exclude: eem_ba1.*
  indexdir: $emboss_qadata/qa/dbigcg-ex-keep
  comment: "GCG format EMBL without prokaryotes"
  taxon: "1 all"
  edamdat: "0001226 EMBL nucleotide sequence record"
]

DB qangcginc  [ type: N format: embl method: gcg
  dir: $emboss_qadata/embl
  file: eem_ba1.*
  exclude: *
  indexdir: $emboss_qadata/qa/dbigcg-ex-keep
  comment: "GCG format EMBL only prokaryotes"
  taxon: "1 all"
# need multiple taxon attributes as bacteria and archaea are in embl PRO
  edamdat: "0001226 EMBL nucleotide sequence record"
]

DB qangcgall  [ type: N format: embl method: gcg
  dir: $emboss_qadata/embl
  indexdir: $emboss_qadata/qa/dbigcg-allsys-keep
  comment: "GCG format EMBL"
  fields: "sv des org key"
  taxon: "1 all"
  edamdat: "0001226 EMBL nucleotide sequence record"
]

DB qapir  [ type: P format: nbrf method: gcg
  dir: $emboss_qadata/pir
  indexdir: $emboss_qadata/qa/dbigcg-pir-keep
  comment: "PIR"
  taxon: "1 all"
  edamdat: "0001232 PIR protein sequence record"
]

DB qapirexc  [ type: N format: nbrf method: gcg
  dir: $emboss_qadata/pir
  exclude: pir1.*
  indexdir: $emboss_qadata/qa/dbigcg-pir-keep
  comment: "PIR"
  taxon: "1 all"
  edamdat: "0001232 PIR protein sequence record"
]

DB qapirinc  [ type: P format: nbrf method: gcg
  dir: $emboss_qadata/pir
  file: pir1.*
  exclude: *
  indexdir: $emboss_qadata/qa/dbigcg-pir-keep
  comment: "PIR"
  taxon: "1 all"
  edamdat: "0001232 PIR protein sequence record"
]

DB qapirall  [ type: P format: nbrf method: gcg
  dir: $emboss_qadata/pir
  indexdir: $emboss_qadata/qa/dbigcg-pirall-keep
  comment: "PIR"
  fields: "des org key"
  taxon: "1 all"
]

###########################
### access method EMBOSSGCG
###########################

DB qanxgcg  [ type: N format: embl method: embossgcg
  dir: $emboss_qadata/embl
  indexdir: $emboss_qadata/qa/dbxgcg-ex-keep
  dbalias: embl
  comment: "GCG format EMBL"
  taxon: "1 all"
  edamdat: "0001226 EMBL nucleotide sequence record"
]

DB qanxgcgexc  [ type: N format: embl method: embossgcg
  dir: $emboss_qadata/embl
  exclude: eem_ba1.*
  indexdir: $emboss_qadata/qa/dbxgcg-ex-keep
  dbalias: embl
  comment: "GCG format EMBL without prokaryotes"
  taxon: "1 all"
  edamdat: "0001226 EMBL nucleotide sequence record"
]

DB qanxgcginc  [ type: N format: embl method: embossgcg
  dir: $emboss_qadata/embl
  file: eem_ba1.*
  exclude: *
  indexdir: $emboss_qadata/qa/dbxgcg-ex-keep
  dbalias: embl
  comment: "GCG format EMBL only prokaryotes"
  taxon: "1 all"
  edamdat: "0001226 EMBL nucleotide sequence record"
]

DB qanxgcgall  [ type: N format: embl method: embossgcg
  dir: $emboss_qadata/embl
  indexdir: $emboss_qadata/qa/dbxgcg-allsys-keep
  fields: "sv des org key"
  dbalias: embl
  comment: "GCG format EMBL"
  taxon: "1 all"
  edamdat: "0001226 EMBL nucleotide sequence record"
]

DB qaxpir  [ type: P format: nbrf method: embossgcg
  dir: $emboss_qadata/pir
  indexdir: $emboss_qadata/qa/dbxgcg-pir-keep
  dbalias: pir
  comment: "PIR"
  taxon: "1 all"
  edamdat: "0001232 PIR protein sequence record"
]

DB qaxpirexc  [ type: N format: nbrf method: embossgcg
  dir: $emboss_qadata/pir
  exclude: pir1.*
  indexdir: $emboss_qadata/qa/dbxgcg-pir-keep
  dbalias: pir
  comment: "PIR"
  taxon: "1 all"
  edamdat: "0001232 PIR protein sequence record"
]

DB qaxpirinc  [ type: P format: nbrf method: embossgcg
  dir: $emboss_qadata/pir
  file: pir1.*
  exclude: *
  indexdir: $emboss_qadata/qa/dbxgcg-pir-keep
  dbalias: pir
  comment: "PIR"
  taxon: "1 all"
  edamdat: "0001232 PIR protein sequence record"
]

DB qaxpirall  [ type: P format: nbrf method: embossgcg
  dir: $emboss_qadata/pir
  indexdir: $emboss_qadata/qa/dbxgcg-pirall-keep
  fields: "des org key"
  dbalias: pir
  comment: "PIR"
  taxon: "1 all"
  edamdat: "0001232 PIR protein sequence record"
]

#####################
### access method SRS
#####################

#DB qasrs [ type: N format: embl method: srs
#  dbalias: embl
#  fields: "sv des org"     # key omitted to test error messages
#  comment: "EMBL in local srs installation"
#  taxon: "1 all"
#  edamdat: "0001226 EMBL nucleotide sequence record"
#]

##########################
### access method SRSFASTA
##########################

#DB qasrsfasta [ type: N format: fasta method: srsfasta
#  dbalias: embl
#  fields: "sv des org key"
#  comment: "EMBL in local srs installation, fasta format"
#  taxon: "1 all"
#]

########################
### access method SRSWWW
########################

DB qasrswww [ type: N format: embl method: srswww
  dbalias: embl
  fields: "sv des org key"
  url: http://srs.ebi.ac.uk/srs6bin/cgi-bin/wgetz
  comment: "Remote SRS web server"
  taxon: "1 all"
  edamdat: "0001226 EMBL nucleotide sequence record"
]

IFDEF EMBOSS_POSTGRESQL

########################
### access method chado
########################

DB tgenedb [
    methodentry: "chado"
    type:   "features"
    url:    "postgresql://genedb_ro:@db.genedb.org:5432/snapshot"
    format: "chado"
    field:  "uniquename ! identifier"
    hasacc: "N"
    identifier: "uniquename"
    taxon: "1 all"
]

DB tflybase [
    methodentry: "chado"
    type:   "features"
    url:    "postgresql://flybase:@flybase.org:5432/flybase"
    format: "chado"
    field:  "uniquename ! identifier"
    hasacc: "N"
    identifier: "uniquename"
    taxon: "1 all"
]

ENDIF

########################
### access method DAS
########################

SERVER tdas [
    method:    "das"
    type:      "sequence, features"
    url:       "http://www.dasregistry.org/das/"
    comment:   "sequence/feature sources listed on dasregistry.org"
    cachefile: "qatests.server.dasregistry"
    taxon:     "1 all"
]

SERVER tensembldasserver [
    method:   "das"
    type:     "sequence, features"
    url:      "http://www.ensembl.org/das/"
    comment:  "sequence/feature sources on ensembl das server"
    cachefile: qatests.server.ensembldasserver
    taxon:    "1 all"
]

DB tensembldasgrch37 [
    method:  "das"
    type:    "N"
    url:     "http://www.ensembl.org:80/das/Homo_sapiens.GRCh37.reference/"
    comment: "Homo_sapiens Reference server based on GRCh37 assembly"
    format: "das"
    taxon: "9606 homo sapiens"
]

DB tgenedashuman [
    method:  "das"
    type:    "N"
    url:     "http://www.ebi.ac.uk/das-srv/genedas/das/Homo_sapiens.Gene_ID.reference/"
    comment: "The Ensembl human Gene_ID reference source"
    format: "das"
    taxon: "9606 homo sapiens"
]

########################
### EBI webservices
########################

SERVER twsdbfetch [
  methodentry:   "wsdbfetch"
  type:          "sequence, features, text, obo"
  url:           "http://www.ebi.ac.uk/ws/services/WSDbfetchDoclit"
  comment:       "EBI dbfetch webservices(SOAP)"
  cachefile:     "qatests.server.twsdbfetch"
  taxon: "1 all"
]

SERVER tdbfetch [
  methodentry:   "dbfetch"
  type:          "sequence, features, text, obo"
  url:           "http://www.ebi.ac.uk/Tools/dbfetch/"
  comment:       "EBI dbfetch webservices(REST)"
  cachefile:     "qatests.server.tdbfetch"
]

SERVER tebeye [
   method:    "ebeye"
   type:      "text"
   url:       "http://www.ebi.ac.uk/ebisearch/service.ebi"
   comment:   "EBI ebeye webservices"
   cachefile: "qatests.server.ebeye"
   taxon: "1 all"
]


############################
### access method direct ###
############################

# embl
# ====

DB temblall [ type: N dir: "$emboss_tempdata/embl"
   method: direct format: embl release: 57 
   fields: "sv des org key"
   comment: "EMBL in native format with EMBL CD-ROM index"
   filename: "*.dat"
   taxon: "1 all"
   edamdat: "0001226 EMBL nucleotide sequence record"
]

# embl (vertebrates)
# ====

DB temblvrt [ type: N dir: "$emboss_tempdata/embl"
   method: direct format: embl release: 57 
   fields: "sv des org key"
   comment: "EMBL in native format with EMBL CD-ROM index"
   filename: "hum*.dat rod*.dat vrt*.dat"
   taxon: "9711 chordata"
   edamdat: "0001226 EMBL nucleotide sequence record"
]

# embl (non-vertebrates)
# ====

DB temblrest [ type: N dir: "$emboss_tempdata/embl"
   method: direct format: embl release: 57 
   fields: "sv des org key"
   comment: "EMBL in native format with EMBL CD-ROM index"
   filename: "*.dat"
   exclude: "hum*.dat rod*.dat vrt*.dat"
   taxon: "1 all"
   edamdat: "0001226 EMBL nucleotide sequence record"
]

# cache and page sizes for dbx indexing ... matching the default values

SET emboss_pagesize 2048
SET emboss_cachesize 100

# dummy resource names for dbx indexing to use the default values
# no longer needed - use system-wide definitions in emboss.standard

# edam
# ====

DB tedam [
  dbalias: "edam"
  type: "obo"
  indexdirectory: "$emboss_qadata/qa/dbxedam-keep"
  dir: "$emboss_qadata/data"
  method: "emboss"
  format: "obo"
  release: "beta11"
  fields: "id acc nam isa des ns hasattr hasin hasout
           isid isfmt issrc"
  comment: "EDAM using dbxedam test indexes"
]


# edam with dbxobo
# ================

DB tobo [
  dbalias: "edam"
  type: "obo"
  indexdirectory: "$emboss_qadata/qa/dbxobo-keep"
  dir: "$emboss_qadata/data"
  method: "emboss"
  format: "obo"
  release: "beta11"
  fields: "id acc nam isa des ns hasattr hasin hasout
           isid isfmt issrc"
  comment: "EDAM using dbxobo test indexes"
]


DB ttax [
  type:   "taxonomy"
  format: "ncbi"
  method: "embosstax"
  dbalias: "taxon"
  indexdirectory: "$emboss_qadata/qa/dbxtax-keep"
  directory:      "$emboss_qadata/data/taxonomy"
  fields: "id acc nam rnk up gc mgc"
]

