Configuration.default

# Name: Configuration.default
# Assumes: This will be imported into a Bourne shell (/bin/sh) script.
# Product: femover

#
#  If the MGICONFIG environment variable does not have a local override,
#  use the default "live" settings.
#
if [ "${MGICONFIG}" = "" ]
then
    MGICONFIG=/usr/local/mgi/live/mgiconfig
    export MGICONFIG
fi

. ${MGICONFIG}/master.config.sh

#
# Directory and file settings.
#
FILE_DIR=${DATALOADSOUTPUT}/femover
LOG_DIR=${FILE_DIR}/logs
DATA_DIR=${FILE_DIR}/data
CACHE_DIR=${FILE_DIR}/cache

export FILE_DIR LOG_DIR DATA_DIR CACHE_DIR

#
# Numbers of concurrent processes by stage.
#
CONCURRENT_CREATE=3           # create statements
CONCURRENT_DROP=1             # drop statements for target tables (should
                              #   now be 1 to prevent deadlocks with FK)
CONCURRENT_GATHER=4	      # number of gatherers (extracting data from mgd)
CONCURRENT_BCPIN=2            # bcp in statements
CONCURRENT_CLUSTERED_INDEX=1  # create clustered index statements
CONCURRENT_CLUSTER=1          # cluster data statements
CONCURRENT_OPTIMIZE=1         # table optimization statements
CONCURRENT_COMMENT=3          # create comment statements
CONCURRENT_INDEX=2            # create index statements
CONCURRENT_FOREIGN_KEY=1      # create foreign key statements

export CONCURRENT_DROP CONCURRENT_CREATE
export CONCURRENT_BCPIN CONCURRENT_INDEX
export CONCURRENT_GATHER
export CONCURRENT_FOREIGN_KEY CONCURRENT_OPTIMIZE CONCURRENT_COMMENT
export CONCURRENT_CLUSTERED_INDEX CONCURRENT_CLUSTER

#
# Logging levels.
#
LOG_DEBUG=True
LOG_INFO=True

export LOG_DEBUG LOG_INFO

#
# settings for retrieving IMSR counts of strains and cell lines
#
IMSR_COUNT_FILE="/data/downloads/www.findmice.org/report/mgiCounts.txt"

export IMSR_COUNT_URL

#
# setting for retrieving IMSR strain data
#
IMSR_STRAIN_FILE="/data/downloads/www.findmice.org/strains.txt"
export IMSR_STRAIN_URL

#
# setting for retrieving allele IDs that have data in MMHCdb
#
MMHCDB_ALLELE_URL="https://tumor.informatics.jax.org/mtbwi/alleleIDReport.do"
export MMHCDB_ALLELE_URL

#
# setting for retrieving MPD strain data
#
MPD_STRAIN_FILE="/data/downloads/phenome.jax.org/phenomedoc?name=MPD_downloads/straininfo.csv"
export MPD_STRAIN_FILE
 
#
# Miscellaneous settings
#
CHUNK_SIZE=100000	# for large tables, how many rows to do at once
BUILDS_IN_SYNC=1	# are dbSNP and MGI coords in sync?  (0/1)
SOURCE_TYPE=postgres	# build from postgres
TARGET_TYPE=postgres	# build into postgres
REMOVE_DATA_FILES=1	# remove data fles from prior run?  (0/1)
RUN_CONTAINS_PRIVATE=1  # determine if the source database still has private data 

export CHUNK_SIZE BUILDS_IN_SYNC SOURCE_TYPE TARGET_TYPE REMOVE_DATA_FILES RUN_CONTAINS_PRIVATE

# path to data file for short papers' Full Text links
FULL_TEXT_LINKS_PATH=../data/fullTextLinks.txt
export FULL_TEXT_LINKS_PATH

# path to incidental mutations master file
INCIDENTAL_MUTS_FILE=../data/curator_INC.txt
export INCIDENTAL_MUTS_FILE

GLOSSARY_PATH=../data/glossary.rcd
export GLOSSARY_PATH

PYTHONPATH=../lib/python:.:../gather:../schema:../testdata:${PYTHONPATH}
export PYTHONPATH

#
# list of high priority gatherers, in order of precedence
# (these will be moved up in the queue of to-do items, as they are the
# critical path)
#
HIGH_PRIORITY_TABLES="accession sequence sequence_sequence_num sequence_id"
export HIGH_PRIORITY_TABLES

#
# single-priority tables
#
# list of tables that require single-sequential processing
# these tables will be skippped by the "shuffle" routine
# the wrapper (buildDB.sh) will iterate thru each single-priority-table
# and call "buildDB.sh -G" for each table in the list
#
SINGLE_PRIORITY_TABLES=""
export SINGLE_PRIORITY_TABLES