def load_data(col_map, data):
"""Loads the data into the database.
Parameters
----------
col_map : [str,]
The columns to load the data into
data : bytes, bytearray, str
The data to load
"""
if data is not None:
values = f.raw_input_to_list(data)
if values:
# If the data has more values than the header provided, ignore the end (green data set has that)
while len(values) > len(col_map):
f.debug(
"Removing extra row value entry not present in the header."
)
values.pop()
cfg.input_data.append(values)
if (len(cfg.input_data) == cfg.batch_size) or (data is None):
f.debug("Executing statement:")
stmt = generate_statement(col_map)
f.debug(stmt)
cur = cfg.conn.cursor()
cur.executemany(stmt, cfg.input_data)
f.debug("Commit")
cfg.conn.commit()
cur.close()
f.verbose("{0} rows loaded".format(len(cfg.input_data)))
cfg.input_data.clear()
def load_data(col_map, data):
"""Loads the data into the database.
Parameters
----------
col_map : [str,]
The columns to load the data into
data : [str,]
The data to load. If data is None the array will be loaded and flushed.
"""
if data is not None and len(data) > 0:
# If the data has more values than the header provided, ignore the end (green data set has that)
while len(data) > len(col_map):
f.debug(
"Removing extra row value entry not present in the header.")
data.pop()
# tuple or dictionary only for SQL Server
cfg.input_data.append(tuple(data))
# If batch size has been reached or input array should be flushed
if (len(cfg.input_data)
== cfg.batch_size) or (data is None and len(cfg.input_data) > 0):
f.debug("Executing statement:")
stmt = generate_statement(col_map)
f.debug(stmt)
cur = cfg.conn.cursor()
try:
f.executemany(cur, stmt)
except Exception as err:
# Rollback old batch (needed for at least Postgres to finish transaction)
cfg.conn.rollback()
# If debug output is enabled, find failing record
if cfg.debug:
for record in cfg.input_data:
try:
cur.execute(stmt, record)
except Exception as err1:
f.debug("Error with record: {0}".format(record))
# Rollback old batch (needed for at least Postgres to finish transaction)
cfg.conn.rollback()
cur.close()
cfg.input_data.clear()
raise
# Debug output is not enabled, clear current batch and raise error
else:
cur.close()
cfg.input_data.clear()
raise
f.debug("Commit")
cfg.conn.commit()
cur.close()
f.verbose("{0} rows loaded.".format(len(cfg.input_data)))
cfg.input_data.clear()
def run(cmd):
"""Runs csv2db.
This function is the main entry point for csv2db.
Parameters
----------
cmd : str array
The arguments passed
Returns
-------
int
The exit code.
"""
args = parse_arguments(cmd)
# Set verbose and debug output flags
cfg.verbose = args.verbose
if args.debug:
cfg.verbose = True
cfg.debug = True
# Set table name
cfg.table_name = args.table
# Find all files
f.verbose("Finding file(s).")
file_names = f.find_all_files(args.file)
f.debug("Found {0} files.".format(len(file_names)))
f.debug(file_names)
if args.command.startswith("gen"):
f.verbose("Generating CREATE TABLE statement.")
generate_table_sql(file_names, args.column_type)
else:
# Set DB type
f.debug("DB type: {0}".format(args.dbtype))
cfg.db_type = args.dbtype
# Set DB default port, if needed
if args.port is None:
args.port = f.get_default_db_port(args.dbtype)
f.debug("Using default port {0}".format(args.port))
# Set batch size
f.debug("Batch size: {0}".format(args.batch))
cfg.batch_size = int(args.batch)
f.verbose("Establishing database connection.")
f.debug("Database details:")
f.debug({
"dbtype": args.dbtype,
"user": args.user,
"host": args.host,
"port": args.port,
"dbname": args.dbname
})
try:
cfg.conn = f.get_db_connection(cfg.db_type, args.user,
args.password, args.host, args.port,
args.dbname)
load_files(file_names)
f.verbose("Closing database connection.")
cfg.conn.close()
except Exception as err:
print("Error connecting to the database: {0}".format(err))
except KeyboardInterrupt:
print("Exiting program")
cfg.conn.close()
def run(cmd):
"""Runs csv2db.
This function is the main entry point for csv2db.
Parameters
----------
cmd : str array
The arguments passed
Returns
-------
int
The exit code.
"""
args = parse_arguments(cmd)
# Set verbose and debug output flags
cfg.verbose = args.verbose
if args.debug:
cfg.verbose = True
cfg.debug = True
# Set table name
cfg.table_name = args.table
f.debug("Table name: {0}".format(cfg.table_name))
# Set column separator characters(s)
cfg.column_separator = args.separator
f.debug("Column separator: {0}".format(cfg.column_separator))
# Set quote character(s)
cfg.quote_char = args.quote
f.debug("Column escape character: {0}".format(cfg.quote_char))
# Find all files
f.verbose("Finding file(s).")
file_names = f.find_all_files(args.file)
f.verbose("Found {0} file(s).".format(len(file_names)))
# Exit program if no files found.
if len(file_names) == 0:
return f.ExitCodes.SUCCESS.value
f.debug(file_names)
# Generate CREATE TABLE SQL
if args.command.startswith("gen"):
f.verbose("Generating CREATE TABLE statement.")
try:
generate_table_sql(file_names, args.column_type)
return f.ExitCodes.SUCCESS.value
except Exception as err:
f.error("Error generating statement: {0}".format(err))
return f.ExitCodes.GENERIC_ERROR.value
# Load data
else:
# Set DB type
f.debug("DB type: {0}".format(args.dbtype))
cfg.db_type = args.dbtype
cfg.direct_path = args.directpath
# Set DB default port, if needed
if args.port is None:
args.port = f.get_default_db_port(args.dbtype)
f.debug("Using default port {0}".format(args.port))
# Set batch size
f.debug("Batch size: {0}".format(args.batch))
cfg.batch_size = int(args.batch)
# If batch size is lower than 10k and direct path has been specified, overwrite batch size to 10k.
if cfg.direct_path and cfg.batch_size < 10000:
f.debug(
"Direct path was specified but batch size is less than 10000.")
f.debug(
"Overwriting the batch size to 10000 for direct-path load to make sense."
)
cfg.batch_size = 10000
f.verbose("Establishing database connection.")
f.debug("Database details:")
f.debug({
"dbtype": args.dbtype,
"user": args.user,
"host": args.host,
"port": args.port,
"dbname": args.dbname
})
if args.password is None:
args.password = getpass.getpass()
try:
cfg.conn = f.get_db_connection(cfg.db_type, args.user,
args.password, args.host, args.port,
args.dbname)
except Exception as err:
f.error("Error connecting to the database: {0}".format(err))
return f.ExitCodes.DATABASE_ERROR.value
try:
load_files(file_names)
f.verbose("Closing database connection.")
cfg.conn.close()
return f.ExitCodes.SUCCESS.value if not cfg.data_loading_error else f.ExitCodes.DATA_LOADING_ERROR.value
except KeyboardInterrupt:
print("Exiting program")
cfg.conn.close()
return f.ExitCodes.GENERIC_ERROR.value
except Exception as err:
f.error("Error loading file(s): {0}".format(err))
cfg.conn.close()
return f.ExitCodes.GENERIC_ERROR.value
"name", "ignore_error", "verbose", "input"
]:
settings[key] = user[key]
"Loads config file"
if settings["config"]:
settings = functions.load_config(settings)
"Checks speed, time and FPS if they are set all three."
if settings["speed"] and settings["time"] and settings[
"fps"] and not float(settings["speed"]) * float(
settings["fps"]) == float(settings["time"]):
functions.soft_error(
"WARNING: Mutually exclusive arguments defined. (-S speed, -T time, -F fps)",
settings["verbose"], 1, settings["ignore_error"])
functions.verbose(" - Using default values.", settings["verbose"], 1)
settings["speed"] = constants["speed"]
settings["time"] = None
settings["fps"] = constants["fps"]
"If only one of the values time, speed and FPS set we have to compute the rest."
if settings["time"] and not settings["fps"] and not settings["speed"]:
settings["fps"] = constants["fps"]
elif not settings["time"] and settings["fps"] and not settings["speed"]:
settings["speed"] = constants["speed"]
elif not settings["time"] and not settings["fps"] and settings["speed"]:
settings["fps"] = constants["fps"]
elif not settings["time"] and not settings["fps"] and not settings["speed"]:
settings["fps"] = constants["fps"]
settings["speed"] = constants["speed"]
args = parser.parse_args()
user = vars(args)
"Copy arguments the the dict settings"
for key in ["time_format", "max_val", "min_val", "max_time", "min_time", "speed", "time", "fps", "legend", "gnuplot", "effect", "config", "name", "ignore_error", "verbose", "input"]:
settings[key] = user[key]
"Loads config file"
if settings["config"]:
settings = functions.load_config(settings)
"Checks speed, time and FPS if they are set all three."
if settings["speed"] and settings["time"] and settings["fps"] and not float(settings["speed"]) * float(settings["fps"]) == float(settings["time"]):
functions.soft_error("WARNING: Mutually exclusive arguments defined. (-S speed, -T time, -F fps)", settings["verbose"], 1, settings["ignore_error"])
functions.verbose(" - Using default values.", settings["verbose"], 1)
settings["speed"] = constants["speed"]
settings["time"] = None
settings["fps"] = constants["fps"]
"If only one of the values time, speed and FPS set we have to compute the rest."
if settings["time"] and not settings["fps"] and not settings["speed"]:
settings["fps"] = constants["fps"]
elif not settings["time"] and settings["fps"] and not settings["speed"]:
settings["speed"] = constants["speed"]
elif not settings["time"] and not settings["fps"] and settings["speed"]:
settings["fps"] = constants["fps"]
elif not settings["time"] and not settings["fps"] and not settings["speed"]:
settings["fps"] = constants["fps"]
settings["speed"] = constants["speed"]
