def main():
try:
settings = startup.read_settings(filename="file2db_settings.json")
Log.start(settings.debug)
with DB(settings.db) as db:
db.execute("""
DROP TABLE IF EXISTS b2g_tests
""")
db.execute("""
CREATE TABLE b2g_tests (
id INTEGER PRIMARY KEY NOT NULL,
branch VARCHAR(100),
name VARCHAR(100),
version VARCHAR(100),
suite varchar(200),
revision varchar(100),
`date` LONG
)
""")
file2db(db, "b2g_tests", settings.source_file)
except Exception, e:
Log.error("can not seem to startup", e)
def main():
try:
settings = startup.read_settings(defs=[{
"name": ["--no_restart", "--no_reset", "--no_redo", "--norestart", "--noreset", "--noredo"],
"help": "do not allow creation of new index (for debugging rouge resets)",
"action": "store_true",
"dest": "no_restart"
}, {
"name": ["--restart", "--reset", "--redo"],
"help": "force a reprocessing of all data",
"action": "store_true",
"dest": "restart"
}, {
"name": ["--file", "--scan_file", "--scanfile", "--use_file", "--usefile"],
"help": "scan file for missing ids",
"action": "store_true",
"dest": "scan_file"
}, {
"name": ["--nofile", "--no_file", "--no-file"],
"help": "do not scan file for missing ids",
"action": "store_false",
"dest": "scan_file"
}])
Log.start(settings.debug)
with startup.SingleInstance(flavor_id=settings.args.filename):
settings.production.threads = nvl(settings.production.threads, 1)
settings.param.output_file = nvl(settings.param.output_file, "./results/raw_json_blobs.tab")
transformer = DZ_to_ES(settings.pushlog)
#RESET ONLY IF NEW Transform IS USED
if settings.args.restart:
es = Cluster(settings.elasticsearch).create_index(settings.elasticsearch)
es.add_alias()
es.delete_all_but_self()
extract_from_datazilla_using_id(es, settings, transformer)
else:
es = Cluster(settings.elasticsearch).get_or_create_index(settings.elasticsearch)
extract_from_datazilla_using_id(es, settings, transformer)
except Exception, e:
Log.error("Problem with etl", e)
