def copy_gpad(nex_session):
dstDir = "curation/literature/"
gpad_file = "gp_association.559292_sgd.gpad.gz"
for x in nex_session.query(Filedbentity).filter(
Filedbentity.previous_file_name.like(
'gp_association.559292_sgd_%.gz')).filter(
Filedbentity.dbentity_status == 'Active').all():
if x.s3_url is None:
continue
urlParam = x.s3_url.split('/')
filename = urlParam[4].split('?')[0]
srcFile = urlParam[3] + '/' + filename
## copy to archive
dstFile = dstDir + "archive/" + filename
print(x.dbentity_status, srcFile, dstFile)
boto3_copy_file(S3_BUCKET, srcFile, S3_BUCKET2, dstFile)
## copy to current directory
dstFile = dstDir + gpad_file
print(x.dbentity_status, srcFile, dstFile)
boto3_copy_file(S3_BUCKET, srcFile, S3_BUCKET2, dstFile)
def copy_gff(nex_session):
dstDir = "curation/chromosomal_feature/archive/"
for x in nex_session.query(Filedbentity).filter(
Filedbentity.previous_file_name.like(
'saccharomyces_cerevisiae.%.gff.gz')).all():
if '.2019' in x.s3_url or '.2020' in x.s3_url:
urlParam = x.s3_url.split('/')
srcFile = urlParam[3] + '/' + urlParam[4].split('?')[0]
dstFile = dstDir + urlParam[4].split('?')[0]
print(x.dbentity_status, srcFile, dstFile)
boto3_copy_file(S3_BUCKET, srcFile, S3_BUCKET2, dstFile)
def copy_gaf(nex_session):
dstDir = "curation/literature/archive/"
for x in nex_session.query(Filedbentity).filter(
Filedbentity.previous_file_name.like(
'gene_association.sgd.%.gz')).all():
if x.s3_url is not None:
urlParam = x.s3_url.split('/')
srcFile = urlParam[3] + '/' + urlParam[4].split('?')[0]
dstFile = dstDir + urlParam[4].split('?')[0]
print(x.dbentity_status, srcFile, dstFile)
boto3_copy_file(S3_BUCKET, srcFile, S3_BUCKET2, dstFile)
def copy_gff(nex_session):
## current directory
dstDir = "curation/chromosomal_feature/"
gff_file = "saccharomyces_cerevisiae.gff.gz"
for x in nex_session.query(Filedbentity).filter(
Filedbentity.previous_file_name.like(
'saccharomyces_cerevisiae.%.gff.gz')).filter(
Filedbentity.dbentity_status == 'Active').all():
if x.s3_url is None:
continue
urlParam = x.s3_url.split('/')
filename = urlParam[4].split('?')[0]
srcFile = urlParam[3] + '/' + filename
## copy to archive
dstFile = dstDir + "archive/" + filename
print(x.dbentity_status, srcFile, dstFile)
boto3_copy_file(S3_BUCKET, srcFile, S3_BUCKET2, dstFile)
## copy to current directory
dstFile = dstDir + gff_file
print(x.dbentity_status, srcFile, dstFile)
boto3_copy_file(S3_BUCKET, srcFile, S3_BUCKET2, dstFile)
## copy to latest directory
dstFile = "latest/" + gff_file
print(x.dbentity_status, srcFile, dstFile)
boto3_copy_file(S3_BUCKET, srcFile, S3_BUCKET, dstFile)
