def run_gzip_process(cluster_name, dataset_type, log, function=None):
'''
Run a gzip process.
'''
# initialize the control variable
OK = True
# get the gzip code and name
gzip_code = xlib.get_gzip_code()
gzip_name = xlib.get_gzip_name()
# get the gzip option dictionary
gzip_option_dict = xlib.get_option_dict(get_gzip_config_file(dataset_type))
# get the experiment identification
experiment_id = gzip_option_dict['identification']['experiment_id']
# get the gzip process script path in the local computer
gzip_process_script = get_gzip_process_script(dataset_type)
# get the gzip process starter path in the local computer
gzip_process_starter = get_gzip_process_starter(dataset_type)
# warn that the log window does not have to be closed
if not isinstance(log, xlib.DevStdOut):
log.write('This process might take several minutes. Do not close this window, please wait!\n')
# check the gzip config file
log.write(f'{xlib.get_separator()}\n')
log.write('Checking the {0} config file ...\n'.format(gzip_name))
(OK, error_list) = check_gzip_config_file(dataset_type, strict=True)
if OK:
log.write('The file is OK.\n')
else:
log.write('*** ERROR: The config file is not valid.\n')
log.write('Please correct this file or recreate the config files.\n')
# create the SSH client connection
if OK:
log.write(f'{xlib.get_separator()}\n')
log.write('Connecting the SSH client ...\n')
(OK, error_list, ssh_client) = xssh.create_ssh_client_connection(cluster_name)
if OK:
log.write('The SSH client is connected.\n')
else:
for error in error_list:
log.write(f'{error}\n')
# create the SSH transport connection
if OK:
log.write(f'{xlib.get_separator()}\n')
log.write('Connecting the SSH transport ...\n')
(OK, error_list, ssh_transport) = xssh.create_ssh_transport_connection(cluster_name)
if OK:
log.write('The SSH transport is connected.\n')
else:
for error in error_list:
log.write(f'{error}\n')
# create the SFTP client
if OK:
log.write(f'{xlib.get_separator()}\n')
log.write('Connecting the SFTP client ...\n')
sftp_client = xssh.create_sftp_client(ssh_transport)
log.write('The SFTP client is connected.\n')
# warn that the requirements are being verified
if OK:
log.write(f'{xlib.get_separator()}\n')
log.write('Checking process requirements ...\n')
# check the master is running
if OK:
(master_state_code, master_state_name) = xec2.get_node_state(cluster_name)
if master_state_code != 16:
log.write(f'*** ERROR: The cluster {cluster_name} is not running. Its state is {master_state_code} ({master_state_name}).\n')
OK = False
# warn that the requirements are OK
if OK:
log.write('Process requirements are OK.\n')
# determine the run directory in the cluster
if OK:
log.write(f'{xlib.get_separator()}\n')
log.write('Determining the run directory in the cluster ...\n')
if dataset_type == 'reference':
current_run_dir = xlib.get_cluster_current_run_dir('reference', gzip_code)
elif dataset_type == 'database':
current_run_dir = xlib.get_cluster_current_run_dir('database', gzip_code)
else:
current_run_dir = xlib.get_cluster_current_run_dir(experiment_id, gzip_code)
command = f'mkdir --parents {current_run_dir}'
(OK, stdout, stderr) = xssh.execute_cluster_command(ssh_client, command)
if OK:
log.write(f'The directory path is {current_run_dir}.\n')
else:
log.write(f'*** ERROR: Wrong command ---> {command}\n')
# build the gzip process script
if OK:
log.write(f'{xlib.get_separator()}\n')
log.write('Building the process script {0} ...\n'.format(gzip_process_script))
(OK, error_list) = build_gzip_process_script(cluster_name, dataset_type, current_run_dir)
if OK:
log.write('The file is built.\n')
else:
log.write('*** ERROR: The file could not be built.\n')
# upload the gzip process script to the cluster
if OK:
log.write(f'{xlib.get_separator()}\n')
log.write('Uploading the process script {0} to the directory {1} ...\n'.format(gzip_process_script, current_run_dir))
cluster_path = '{0}/{1}'.format(current_run_dir, os.path.basename(gzip_process_script))
(OK, error_list) = xssh.put_file(sftp_client, gzip_process_script, cluster_path)
if OK:
log.write('The file is uploaded.\n')
else:
for error in error_list:
log.write(f'{error}\n')
# set run permision to the gzip process script in the cluster
if OK:
log.write(f'{xlib.get_separator()}\n')
log.write('Setting on the run permision of {0}/{1} ...\n'.format(current_run_dir, os.path.basename(gzip_process_script)))
command = 'chmod u+x {0}/{1}'.format(current_run_dir, os.path.basename(gzip_process_script))
(OK, stdout, stderr) = xssh.execute_cluster_command(ssh_client, command)
if OK:
log.write('The run permision is set.\n')
else:
log.write(f'*** ERROR: Wrong command ---> {command}\n')
# build the gzip process starter
if OK:
log.write(f'{xlib.get_separator()}\n')
log.write('Building the process starter {0} ...\n'.format(gzip_process_starter))
(OK, error_list) = build_gzip_process_starter(dataset_type, current_run_dir)
if OK:
log.write('The file is built.\n')
else:
log.write('***ERROR: The file could not be built.\n')
# upload the gzip process starter to the cluster
if OK:
log.write(f'{xlib.get_separator()}\n')
log.write('Uploading the process starter {0} to the directory {1} ...\n'.format(gzip_process_starter, current_run_dir))
cluster_path = '{0}/{1}'.format(current_run_dir, os.path.basename(gzip_process_starter))
(OK, error_list) = xssh.put_file(sftp_client, gzip_process_starter, cluster_path)
if OK:
log.write('The file is uploaded.\n')
else:
for error in error_list:
log.write(f'{error}\n')
# set run permision to the gzip process starter in the cluster
if OK:
log.write(f'{xlib.get_separator()}\n')
log.write('Setting on the run permision of {0}/{1} ...\n'.format(current_run_dir, os.path.basename(gzip_process_starter)))
command = 'chmod u+x {0}/{1}'.format(current_run_dir, os.path.basename(gzip_process_starter))
(OK, stdout, stderr) = xssh.execute_cluster_command(ssh_client, command)
if OK:
log.write('The run permision is set.\n')
else:
log.write(f'*** ERROR: Wrong command ---> {command}\n')
# submit the gzip process
if OK:
log.write(f'{xlib.get_separator()}\n')
log.write('Submitting the process script {0}/{1} ...\n'.format(current_run_dir, os.path.basename(gzip_process_starter)))
OK = xssh.submit_script(cluster_name, ssh_client, current_run_dir, os.path.basename(gzip_process_starter), log)
# close the SSH transport connection
if OK:
log.write(f'{xlib.get_separator()}\n')
log.write('Closing the SSH transport connection ...\n')
xssh.close_ssh_transport_connection(ssh_transport)
log.write('The connection is closed.\n')
# close the SSH client connection
if OK:
log.write(f'{xlib.get_separator()}\n')
log.write('Closing the SSH client connection ...\n')
xssh.close_ssh_client_connection(ssh_client)
log.write('The connection is closed.\n')
# warn that the log window can be closed
if not isinstance(log, xlib.DevStdOut):
log.write(f'{xlib.get_separator()}\n')
log.write('You can close this window now.\n')
# execute final function
if function is not None:
function()
# return the control variable
return OK
def check_gzip_config_file(dataset_type, strict):
'''
Check the gzip config file of a run.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# intitialize variable used when value is not found
not_found = '***NOTFOUND***'.upper()
# get the option dictionary
try:
gzip_option_dict = xlib.get_option_dict(get_gzip_config_file(dataset_type))
except Exception as e:
error_list.append(f'*** EXCEPTION: "{e}".')
error_list.append('*** ERROR: The option dictionary could not be built from the config file')
OK = False
else:
# get the sections list
sections_list = []
for section in gzip_option_dict.keys():
sections_list.append(section)
sections_list.sort()
# check section "identification"
if 'identification' not in sections_list:
error_list.append('*** ERROR: the section "identification" is not found.')
OK = False
else:
# check section "identification" - key "experiment_id"
experiment_id = gzip_option_dict.get('identification', {}).get('experiment_id', not_found)
if experiment_id == not_found:
error_list.append('*** ERROR: the key "experiment_id" is not found in the section "identification".')
OK = False
elif dataset_type == 'reference' and experiment_id.upper() != 'NONE':
error_list.append('*** ERROR: the key "experiment_id" has to be always NONE')
OK = False
# check section "identification" - key "dataset_type"
dataset_type_2 = gzip_option_dict.get('identification', {}).get('dataset_type', not_found)
if dataset_type_2 == not_found:
error_list.append('*** ERROR: the key "dataset_type" is not found in the section "identification".')
OK = False
else:
if dataset_type in ['reference', 'read']:
if dataset_type_2.lower() != dataset_type:
error_list.append('*** ERROR: the key "dataset_type" has to be {0}.'.format(dataset_type))
OK = False
elif dataset_type == 'result':
if dataset_type_2.lower() not in ['result', 'whole-result']:
error_list.append('*** ERROR: the key "dataset_type" has to be result or whole-result.')
OK = False
# check section "identification" - key "dataset_id"
dataset_id = gzip_option_dict.get('identification', {}).get('dataset_id', not_found)
if dataset_id == not_found:
error_list.append('*** ERROR: the key "dataset_id" is not found in the section "identification".')
OK = False
# check section "gzip parameters"
if 'gzip parameters' not in sections_list:
error_list.append('*** ERROR: the section "gzip parameters" is not found.')
OK = False
else:
# check section "gzip parameters" - key "action"
action = gzip_option_dict.get('gzip parameters', {}).get('action', not_found)
if action == not_found:
error_list.append('*** ERROR: the key "action" is not found in the section "gzip parameters".')
OK = False
else:
if action.lower() not in ['compress', 'decompress']:
error_list.append('*** ERROR: the key "action" has to be compress or decompress.')
OK = False
# check section "file-1"
if dataset_type_2.lower() in ['reference', 'database', 'read', 'result']:
if 'file-1' not in sections_list:
error_list.append('*** ERROR: the section "file-1" is not found.')
OK = False
# check all sections "file-n"
if dataset_type_2.lower() in ['reference', 'database', 'read', 'result']:
for section in sections_list:
if section not in ['identification', 'gzip parameters']:
# check than the section identification is like file-n
if not re.match('^file-[0-9]+$', section):
error_list.append(f'*** ERROR: the section "{section}" has a wrong identification.')
OK = False
else:
# check section "file-n" - key "dataset_subdirectory"
dataset_subdirectory = gzip_option_dict.get(section, {}).get('dataset_subdirectory', not_found)
if dataset_subdirectory == not_found:
error_list.append('*** ERROR: the key "dataset_subdirectory" is not found in the section "{0}".'.format(section))
OK = False
elif not xlib.is_valid_path(dataset_subdirectory, 'linux'):
error_list.append('*** ERROR: the file {0} in the key "dataset_subdirectory" of the section "{1}" has a non valid file name.'.format(dataset_subdirectory, section))
OK = False
# check section "file-n" - key "file_name"
file_name = gzip_option_dict.get(section, {}).get('file_name', not_found)
if file_name == not_found:
error_list.append('*** ERROR: the key "file_name" is not found in the section "{0}".'.format(section))
OK = False
elif not xlib.is_valid_path(file_name, 'linux'):
error_list.append('*** ERROR: the file {0} in the key "file_name" of the section "{1}" has a non valid file name.'.format(file_name, section))
OK = False
# warn that the results config file is not valid if there are any errors
if not OK:
error_list.append('\nThe {0} config file is not valid. Please, correct this file or recreate it.'.format(xlib.get_gzip_name()))
# return the control variable and the error list
return (OK, error_list)
def get_result_dataset_dict(cluster_name, experiment_id, status, passed_connection, ssh_client):
'''
Get a dictionary with the result datasets of an experiment in the cluster.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# get the result directory in the cluster
cluster_result_dir = xlib.get_cluster_result_dir()
# initialize the dictionary of the result datasets
result_dataset_dict = {}
# create the SSH client connection
if not passed_connection:
(OK, error_list, ssh_client) = xssh.create_ssh_client_connection(cluster_name, 'master')
# verify the result directory is created
if OK:
command = '[ -d {0} ] && echo RC=0 || echo RC=1'.format(cluster_result_dir)
(OK, stdout, stderr) = xssh.execute_cluster_command(ssh_client, command)
if stdout[len(stdout) - 1] != 'RC=0':
error_list.append('*** ERROR: There is not any volume mounted in the result directory.\n')
error_list.append('You must link a volume in the mounting point {0} for the template {1}.\n'.format(cluster_result_dir, cluster_name))
OK = False
# get the dictionary of the result datasets
if OK:
if status == 'uncompressed':
command = 'cd {0}/{1}; for list in `ls`; do ls -ld $list | grep -v ^- > /dev/null && echo $list; done;'.format(cluster_result_dir, experiment_id)
elif status == 'compressed':
command = 'cd {0}/{1}; for list in `ls`; do ls -ld $list | grep -v ^d > /dev/null && echo $list; done;'.format(cluster_result_dir, experiment_id)
(OK, stdout, stderr) = xssh.execute_cluster_command(ssh_client, command)
if OK:
if status == 'uncompressed':
input_pattern = '{0}-(.+)-(.+)'
output_pattern = '{0} ({1} {2})'
elif status == 'compressed':
input_pattern = '{0}-(.+)-(.+).tar.gz'
output_pattern = '{0} ({1} {2}) [compressed]'
for line in stdout:
line = line.rstrip('\n')
if line != 'lost+found':
result_dataset_id = line
if result_dataset_id.startswith(xlib.get_cd_hit_est_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_cd_hit_est_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_cd_hit_est_name(), date, time)
elif result_dataset_id.startswith(xlib.get_fastqc_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_fastqc_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_fastqc_name(), date, time)
elif result_dataset_id.startswith(xlib.get_gzip_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_gzip_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_gzip_name(), date, time)
elif result_dataset_id.startswith(xlib.get_insilico_read_normalization_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_insilico_read_normalization_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_insilico_read_normalization_name(), date, time)
elif result_dataset_id.startswith(xlib.get_quast_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_quast_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_quast_name(), date, time)
elif result_dataset_id.startswith(xlib.get_ref_eval_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_ref_eval_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_ref_eval_name(), date, time)
elif result_dataset_id.startswith(xlib.get_rnaquast_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_rnaquast_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_rnaquast_name(), date, time)
elif result_dataset_id.startswith(xlib.get_rsem_eval_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_rsem_eval_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_rsem_eval_name(), date, time)
elif result_dataset_id.startswith(xlib.get_soapdenovotrans_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_soapdenovotrans_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_soapdenovotrans_name(), date, time)
elif result_dataset_id.startswith(xlib.get_star_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_star_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_star_name(), date, time)
elif result_dataset_id.startswith(xlib.get_transabyss_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_transabyss_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_transabyss_name(), date, time)
elif result_dataset_id.startswith(xlib.get_transcript_filter_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_transcript_filter_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_transcript_filter_name(), date, time)
elif result_dataset_id.startswith(xlib.get_transcriptome_blastx_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_transcriptome_blastx_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_transcriptome_blastx_name(), date, time)
elif result_dataset_id.startswith(xlib.get_transrate_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_transrate_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_transrate_name(), date, time)
elif result_dataset_id.startswith(xlib.get_trimmomatic_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_trimmomatic_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_trimmomatic_name(), date, time)
elif result_dataset_id.startswith(xlib.get_trinity_code()+'-'):
mo = re.match(input_pattern.format(xlib.get_trinity_code()), result_dataset_id)
date = mo.group(1)
time = mo.group(2)
result_dataset_name = output_pattern.format(xlib.get_trinity_name(), date, time)
else:
result_dataset_name = result_dataset_id
result_dataset_dict[result_dataset_id] = {'result_dataset_id': result_dataset_id, 'result_dataset_name': result_dataset_name}
# close the SSH client connection
if OK and not passed_connection:
xssh.close_ssh_client_connection(ssh_client)
# return the control variable, error list and dictionary of the result datasets
return (OK, error_list, result_dataset_dict)
def form_list_cluster_experiment_processes():
'''
List the processes of an experiment in the cluster.
'''
# initialize the control variable
OK = True
# print the header
clib.clear_screen()
clib.print_headers_with_environment('Logs - List experiment processes in the cluster')
# get the cluster name
print(xlib.get_separator())
if xec2.get_running_cluster_list(volume_creator_included=False) != []:
cluster_name = cinputs.input_cluster_name(volume_creator_included=False, help=True)
else:
print('WARNING: There is not any running cluster.')
OK = False
# create the SSH client connection
if OK:
(OK, error_list, ssh_client) = xssh.create_ssh_client_connection(cluster_name, 'master')
for error in error_list:
log.write('{0}\n'.format(error))
# get experiment identification
if OK:
experiment_id = cinputs.input_experiment_id(ssh_client, help=True)
if experiment_id == '':
print('WARNING: The cluster {0} has not experiment data.'.format(cluster_name))
OK = False
# get the result dataset list of the experiment
if OK:
command = 'cd {0}/{1}; for list in `ls`; do ls -ld $list | grep -v ^- > /dev/null && echo $list; done;'.format(xlib.get_cluster_result_dir(), experiment_id)
(OK, stdout, stderr) = xssh.execute_cluster_command(ssh_client, command)
if OK:
result_dataset_id_list = []
for line in stdout:
line = line.rstrip('\n')
if line != 'lost+found':
result_dataset_id_list.append(line)
# print the result dataset identification list of the experiment
if OK:
print(xlib.get_separator())
if result_dataset_id_list == []:
print('*** WARNING: There is not any result dataset of the experiment {0}.'.format(experiment_id))
else:
result_dataset_id_list.sort()
# set data width
result_dataset_width = 25
bioinfo_app_width = 25
# set line template
line_template = '{0:' + str(result_dataset_width) + '} {1:' + str(bioinfo_app_width) + '}'
# print header
print(line_template.format('Result dataset', 'Bioinfo app / Utility'))
print(line_template.format('=' * result_dataset_width, '=' * bioinfo_app_width))
# print detail lines
for result_dataset_id in result_dataset_id_list:
if result_dataset_id.startswith(xlib.get_bedtools_code()+'-'):
bioinfo_app_name = xlib.get_bedtools_name()
elif result_dataset_id.startswith(xlib.get_blastplus_code()+'-'):
bioinfo_app_name = xlib.get_blastplus_name()
elif result_dataset_id.startswith(xlib.get_bowtie2_code()+'-'):
bioinfo_app_name = xlib.get_bowtie2_name()
elif result_dataset_id.startswith(xlib.get_busco_code()+'-'):
bioinfo_app_name = xlib.get_busco_name()
elif result_dataset_id.startswith(xlib.get_cd_hit_code()+'-'):
bioinfo_app_name = xlib.get_cd_hit_est_name()
elif result_dataset_id.startswith(xlib.get_cd_hit_code()+'-'):
bioinfo_app_name = xlib.get_cd_hit_est_name()
elif result_dataset_id.startswith(xlib.get_detonate_code()+'-'):
bioinfo_app_name = xlib.get_detonate_name()
elif result_dataset_id.startswith(xlib.get_emboss_code()+'-'):
bioinfo_app_name = xlib.get_emboss_name()
elif result_dataset_id.startswith(xlib.get_fastqc_code()+'-'):
bioinfo_app_name = xlib.get_fastqc_name()
elif result_dataset_id.startswith(xlib.get_gmap_code()+'-'):
bioinfo_app_name = xlib.get_gmap_name()
elif result_dataset_id.startswith(xlib.get_gmap_gsnap_code()+'-'):
bioinfo_app_name = xlib.get_gmap_gsnap_name()
elif result_dataset_id.startswith(xlib.get_gzip_code()+'-'):
bioinfo_app_name = xlib.get_gzip_name()
elif result_dataset_id.startswith(xlib.get_insilico_read_normalization_code()+'-'):
bioinfo_app_name = xlib.get_insilico_read_normalization_name()
elif result_dataset_id.startswith(xlib.get_miniconda3_code()+'-'):
bioinfo_app_name = xlib.get_miniconda3_name()
elif result_dataset_id.startswith(xlib.get_ngshelper_code()+'-'):
bioinfo_app_name = xlib.get_ngshelper_name()
elif result_dataset_id.startswith(xlib.get_quast_code()+'-'):
bioinfo_app_name = xlib.get_quast_name()
elif result_dataset_id.startswith(xlib.get_r_code()+'-'):
bioinfo_app_name = xlib.get_r_name()
elif result_dataset_id.startswith(xlib.get_ref_eval_code()+'-'):
bioinfo_app_name = xlib.get_ref_eval_name()
elif result_dataset_id.startswith(xlib.get_rnaquast_code()+'-'):
bioinfo_app_name = xlib.get_rnaquast_name()
elif result_dataset_id.startswith(xlib.get_rsem_code()+'-'):
bioinfo_app_name = xlib.get_rsem_name()
elif result_dataset_id.startswith(xlib.get_rsem_eval_code()+'-'):
bioinfo_app_name = xlib.get_rsem_eval_name()
elif result_dataset_id.startswith(xlib.get_samtools_code()+'-'):
bioinfo_app_name = xlib.get_samtools_name()
elif result_dataset_id.startswith(xlib.get_soapdenovotrans_code()+'-'):
bioinfo_app_name = xlib.get_soapdenovotrans_name()
elif result_dataset_id.startswith(xlib.get_star_code()+'-'):
bioinfo_app_name = xlib.get_star_name()
elif result_dataset_id.startswith(xlib.get_transabyss_code()+'-'):
bioinfo_app_name = xlib.get_transabyss_name()
elif result_dataset_id.startswith(xlib.get_transcript_filter_code()+'-'):
bioinfo_app_name = xlib.get_transcript_filter_name()
elif result_dataset_id.startswith(xlib.get_transcriptome_blastx_code()+'-'):
bioinfo_app_name = xlib.get_transcriptome_blastx_name()
elif result_dataset_id.startswith(xlib.get_transrate_code()+'-'):
bioinfo_app_name = xlib.get_transrate_name()
elif result_dataset_id.startswith(xlib.get_trimmomatic_code()+'-'):
bioinfo_app_name = xlib.get_trimmomatic_name()
elif result_dataset_id.startswith(xlib.get_trinity_code()+'-'):
bioinfo_app_name = xlib.get_trinity_name()
else:
bioinfo_app_name = 'xxx'
print(line_template.format(result_dataset_id, bioinfo_app_name))
# close the SSH client connection
if OK:
xssh.close_ssh_client_connection(ssh_client)
# show continuation message
print(xlib.get_separator())
input('Press [Intro] to continue ...')
def execute(self, event=None):
'''
Execute the list the result logs in the cluster.
'''
# validate inputs
OK = self.validate_inputs()
if not OK:
message = 'Some input values are not OK.'
tkinter.messagebox.showerror('{0} - {1}'.format(xlib.get_project_name(), self.head), message)
# get the run dictionary of the experiment
if OK:
# -- command = 'ls {0}/{1}'.format(xlib.get_cluster_result_dir(), self.wrapper_experiment_id.get())
command = 'cd {0}/{1}; for list in `ls`; do ls -ld $list | grep -v ^- > /dev/null && echo $list; done;'.format(xlib.get_cluster_result_dir(), self.wrapper_experiment_id.get())
(OK, stdout, stderr) = xssh.execute_cluster_command(self.ssh_client, command)
if OK:
result_dataset_dict = {}
for line in stdout:
line = line.rstrip('\n')
if line != 'lost+found':
result_dataset_id = line
try:
pattern = r'^(.+)\-(.+)\-(.+)$'
mo = re.search(pattern, result_dataset_id)
bioinfo_app_code = mo.group(1).strip()
yymmdd = mo.group(2)
hhmmss = mo.group(3)
date = '20{0}-{1}-{2}'.format(yymmdd[:2], yymmdd[2:4], yymmdd[4:])
time = '{0}:{1}:{2}'.format(hhmmss[:2], hhmmss[2:4], hhmmss[4:])
except:
bioinfo_app_code = 'xxx'
date = '0000-00-00'
time = '00:00:00'
if result_dataset_id.startswith(xlib.get_bedtools_code()+'-'):
bioinfo_app_name = xlib.get_bedtools_name()
elif result_dataset_id.startswith(xlib.get_blastplus_code()+'-'):
bioinfo_app_name = xlib.get_blastplus_name()
elif result_dataset_id.startswith(xlib.get_bowtie2_code()+'-'):
bioinfo_app_name = xlib.get_bowtie2_name()
elif result_dataset_id.startswith(xlib.get_busco_code()+'-'):
bioinfo_app_name = xlib.get_busco_name()
elif result_dataset_id.startswith(xlib.get_cd_hit_code()+'-'):
bioinfo_app_name = xlib.get_cd_hit_name()
elif result_dataset_id.startswith(xlib.get_cd_hit_est_code()+'-'):
bioinfo_app_name = xlib.get_cd_hit_est_name()
elif result_dataset_id.startswith(xlib.get_detonate_code()+'-'):
bioinfo_app_name = xlib.get_detonate_name()
elif result_dataset_id.startswith(xlib.get_emboss_code()+'-'):
bioinfo_app_name = xlib.get_emboss_name()
elif result_dataset_id.startswith(xlib.get_fastqc_code()+'-'):
bioinfo_app_name = xlib.get_fastqc_name()
elif result_dataset_id.startswith(xlib.get_gmap_code()+'-'):
bioinfo_app_name = xlib.get_gmap_name()
elif result_dataset_id.startswith(xlib.get_gmap_gsnap_code()+'-'):
bioinfo_app_name = xlib.get_gmap_gsnap_name()
elif result_dataset_id.startswith(xlib.get_gzip_code()+'-'):
bioinfo_app_name = xlib.get_gzip_name()
elif result_dataset_id.startswith(xlib.get_insilico_read_normalization_code()+'-'):
bioinfo_app_name = xlib.get_insilico_read_normalization_name()
elif result_dataset_id.startswith(xlib.get_miniconda3_code()+'-'):
bioinfo_app_name = xlib.get_miniconda3_name()
elif result_dataset_id.startswith(xlib.get_ngshelper_code()+'-'):
bioinfo_app_name = xlib.get_ngshelper_name()
elif result_dataset_id.startswith(xlib.get_quast_code()+'-'):
bioinfo_app_name = xlib.get_quast_name()
elif result_dataset_id.startswith(xlib.get_r_code()+'-'):
bioinfo_app_name = xlib.get_r_name()
elif result_dataset_id.startswith(xlib.get_ref_eval_code()+'-'):
bioinfo_app_name = xlib.get_ref_eval_name()
elif result_dataset_id.startswith(xlib.get_rnaquast_code()+'-'):
bioinfo_app_name = xlib.get_rnaquast_name()
elif result_dataset_id.startswith(xlib.get_rsem_code()+'-'):
bioinfo_app_name = xlib.get_rsem_name()
elif result_dataset_id.startswith(xlib.get_rsem_eval_code()+'-'):
bioinfo_app_name = xlib.get_rsem_eval_name()
elif result_dataset_id.startswith(xlib.get_samtools_code()+'-'):
bioinfo_app_name = xlib.get_samtools_name()
elif result_dataset_id.startswith(xlib.get_soapdenovotrans_code()+'-'):
bioinfo_app_name = xlib.get_soapdenovotrans_name()
elif result_dataset_id.startswith(xlib.get_star_code()+'-'):
bioinfo_app_name = xlib.get_star_name()
elif result_dataset_id.startswith(xlib.get_transabyss_code()+'-'):
bioinfo_app_name = xlib.get_transabyss_name()
elif result_dataset_id.startswith(xlib.get_transcript_filter_code()+'-'):
bioinfo_app_name = xlib.get_transcript_filter_name()
elif result_dataset_id.startswith(xlib.get_transcriptome_blastx_code()+'-'):
bioinfo_app_name = xlib.get_transcriptome_blastx_name()
elif result_dataset_id.startswith(xlib.get_transrate_code()+'-'):
bioinfo_app_name = xlib.get_transrate_name()
elif result_dataset_id.startswith(xlib.get_trimmomatic_code()+'-'):
bioinfo_app_name = xlib.get_trimmomatic_name()
elif result_dataset_id.startswith(xlib.get_trinity_code()+'-'):
bioinfo_app_name = xlib.get_trinity_name()
else:
bioinfo_app_name = 'xxx'
result_dataset_dict[result_dataset_id] = {'experiment_id': self.wrapper_experiment_id.get(), 'result_dataset_id': result_dataset_id, 'bioinfo_app': bioinfo_app_name, 'date': date, 'time': time}
# verify if there are any nodes running
if OK:
if result_dataset_dict == {}:
message = 'There is not any run.'
tkinter.messagebox.showwarning('{0} - {1}'.format(xlib.get_project_name(), self.head), message)
# build the data list
if OK:
data_list = ['experiment_id', 'result_dataset_id', 'bioinfo_app', 'date', 'time']
# build the data dictionary
if OK:
data_dict = {}
data_dict['experiment_id']= {'text': 'Experiment id. / Process', 'width': 200, 'aligment': 'left'}
data_dict['result_dataset_id'] = {'text': 'Result dataset', 'width': 200, 'aligment': 'left'}
data_dict['bioinfo_app'] = {'text': 'Bioinfo app / Utility', 'width': 200, 'aligment': 'left'}
data_dict['date'] = {'text': 'Date', 'width': 80, 'aligment': 'right'}
data_dict['time'] = {'text': 'Time', 'width': 80, 'aligment': 'right'}
# create the dialog Table to show the nodes running
if OK:
dialog_table = gdialogs.DialogTable(self, 'Experiment runs in {0}/{1}'.format(xlib.get_cluster_result_dir(), self.wrapper_experiment_id.get()), 400, 900, data_list, data_dict, result_dataset_dict, 'view_result_logs', [self.wrapper_cluster_name.get()])
self.wait_window(dialog_table)
# close the form
if OK:
self.close()
def form_list_cluster_experiment_processes():
'''
List the processes of an experiment in the cluster.
'''
# initialize the control variable
OK = True
# print the header
clib.clear_screen()
clib.print_headers_with_environment(
'Logs - List experiment processes in the cluster')
# get the cluster name
print(xlib.get_separator())
if xec2.get_running_cluster_list(only_environment_cluster=True,
volume_creator_included=False) != []:
cluster_name = cinputs.input_cluster_name(
volume_creator_included=False, help=True)
else:
print('WARNING: There is not any running cluster.')
OK = False
# create the SSH client connection
if OK:
(OK, error_list,
ssh_client) = xssh.create_ssh_client_connection(cluster_name)
for error in error_list:
print(error)
# get experiment identification
if OK:
experiment_id = cinputs.input_experiment_id(ssh_client, help=True)
if experiment_id == '':
print(
f'WARNING: The cluster {cluster_name} does not have experiment data.'
)
OK = False
# get the result dataset list of the experiment
if OK:
command = f'cd {xlib.get_cluster_result_dir()}/{experiment_id}; for list in `ls`; do ls -ld $list | grep -v ^- > /dev/null && echo $list; done;'
(OK, stdout, _) = xssh.execute_cluster_command(ssh_client, command)
if OK:
result_dataset_id_list = []
for line in stdout:
line = line.rstrip('\n')
if line != 'lost+found':
result_dataset_id_list.append(line)
# print the result dataset identification list of the experiment
if OK:
print(xlib.get_separator())
if result_dataset_id_list == []:
print(
f'*** WARNING: There is not any result dataset of the experiment {experiment_id}.'
)
else:
result_dataset_id_list.sort()
# set data width
result_dataset_width = 30
bioinfo_app_width = 25
# set line
line = '{0:' + str(result_dataset_width) + '} {1:' + str(
bioinfo_app_width) + '}'
# print header
print(line.format('Result dataset', 'Bioinfo app / Utility'))
print(
line.format('=' * result_dataset_width,
'=' * bioinfo_app_width))
# print detail lines
for result_dataset_id in result_dataset_id_list:
if result_dataset_id.startswith(xlib.get_bedtools_code() +
'-'):
bioinfo_app_name = xlib.get_bedtools_name()
elif result_dataset_id.startswith(xlib.get_blastplus_code() +
'-'):
bioinfo_app_name = xlib.get_blastplus_name()
elif result_dataset_id.startswith(xlib.get_bcftools_code() +
'-'):
bioinfo_app_name = xlib.get_bcftools_name()
elif result_dataset_id.startswith(xlib.get_bowtie2_code() +
'-'):
bioinfo_app_name = xlib.get_bowtie2_name()
elif result_dataset_id.startswith(xlib.get_busco_code() + '-'):
bioinfo_app_name = xlib.get_busco_name()
elif result_dataset_id.startswith(xlib.get_cd_hit_code() +
'-'):
bioinfo_app_name = xlib.get_cd_hit_name()
elif result_dataset_id.startswith(xlib.get_cd_hit_est_code() +
'-'):
bioinfo_app_name = xlib.get_cd_hit_est_name()
elif result_dataset_id.startswith(xlib.get_cuffdiff_code() +
'-'):
bioinfo_app_name = xlib.get_cuffdiff_name()
elif result_dataset_id.startswith(xlib.get_cufflinks_code() +
'-'):
bioinfo_app_name = xlib.get_cufflinks_name()
elif result_dataset_id.startswith(
xlib.get_cufflinks_cuffmerge_code() + '-'):
bioinfo_app_name = xlib.get_cufflinks_cuffmerge_name()
elif result_dataset_id.startswith(xlib.get_cuffnorm_code() +
'-'):
bioinfo_app_name = xlib.get_cuffnorm_name()
elif result_dataset_id.startswith(xlib.get_cuffquant_code() +
'-'):
bioinfo_app_name = xlib.get_cuffquant_name()
elif result_dataset_id.startswith(xlib.get_cutadapt_code() +
'-'):
bioinfo_app_name = xlib.get_cutadapt_name()
elif result_dataset_id.startswith(
xlib.get_ddradseq_simulation_code() + '-'):
bioinfo_app_name = xlib.get_ddradseq_simulation_name()
elif result_dataset_id.startswith(
xlib.get_ddradseqtools_code() + '-'):
bioinfo_app_name = xlib.get_ddradseqtools_name()
elif result_dataset_id.startswith(xlib.get_detonate_code() +
'-'):
bioinfo_app_name = xlib.get_detonate_name()
elif result_dataset_id.startswith(xlib.get_diamond_code() +
'-'):
bioinfo_app_name = xlib.get_diamond_name()
elif result_dataset_id.startswith(xlib.get_emboss_code() +
'-'):
bioinfo_app_name = xlib.get_emboss_name()
elif result_dataset_id.startswith(
xlib.get_entrez_direct_code() + '-'):
bioinfo_app_name = xlib.get_entrez_direct_name()
elif result_dataset_id.startswith(xlib.get_express_code() +
'-'):
bioinfo_app_name = xlib.get_express_name()
elif result_dataset_id.startswith(xlib.get_fastqc_code() +
'-'):
bioinfo_app_name = xlib.get_fastqc_name()
elif result_dataset_id.startswith(xlib.get_ggtrinity_code() +
'-'):
bioinfo_app_name = xlib.get_ggtrinity_name()
elif result_dataset_id.startswith(xlib.get_gmap_gsnap_code() +
'-'):
bioinfo_app_name = xlib.get_gmap_gsnap_name()
elif result_dataset_id.startswith(xlib.get_gmap_code() + '-'):
bioinfo_app_name = xlib.get_gmap_name()
elif result_dataset_id.startswith(xlib.get_gsnap_code() + '-'):
bioinfo_app_name = xlib.get_gsnap_name()
elif result_dataset_id.startswith(xlib.get_gzip_code() + '-'):
bioinfo_app_name = xlib.get_gzip_name()
elif result_dataset_id.startswith(xlib.get_hisat2_code() +
'-'):
bioinfo_app_name = xlib.get_hisat2_name()
elif result_dataset_id.startswith(xlib.get_htseq_code() + '-'):
bioinfo_app_name = xlib.get_htseq_name()
elif result_dataset_id.startswith(xlib.get_htseq_count_code() +
'-'):
bioinfo_app_name = xlib.get_htseq_count_name()
elif result_dataset_id.startswith(
xlib.get_insilico_read_normalization_code() + '-'):
bioinfo_app_name = xlib.get_insilico_read_normalization_name(
)
elif result_dataset_id.startswith(xlib.get_ipyrad_code() +
'-'):
bioinfo_app_name = xlib.get_ipyrad_name()
elif result_dataset_id.startswith(xlib.get_kallisto_code() +
'-'):
bioinfo_app_name = xlib.get_kallisto_name()
elif result_dataset_id.startswith(xlib.get_miniconda3_code() +
'-'):
bioinfo_app_name = xlib.get_miniconda3_name()
elif result_dataset_id.startswith(xlib.get_ngshelper_code() +
'-'):
bioinfo_app_name = xlib.get_ngshelper_name()
elif result_dataset_id.startswith(xlib.get_quast_code() + '-'):
bioinfo_app_name = xlib.get_quast_name()
elif result_dataset_id.startswith(xlib.get_r_code() + '-'):
bioinfo_app_name = xlib.get_r_name()
elif result_dataset_id.startswith(xlib.get_raddesigner_code() +
'-'):
bioinfo_app_name = xlib.get_raddesigner_name()
elif result_dataset_id.startswith(xlib.get_ref_eval_code() +
'-'):
bioinfo_app_name = xlib.get_ref_eval_name()
elif result_dataset_id.startswith(xlib.get_rnaquast_code() +
'-'):
bioinfo_app_name = xlib.get_rnaquast_name()
elif result_dataset_id.startswith(xlib.get_rsem_code() + '-'):
bioinfo_app_name = xlib.get_rsem_name()
elif result_dataset_id.startswith(xlib.get_rsem_eval_code() +
'-'):
bioinfo_app_name = xlib.get_rsem_eval_name()
elif result_dataset_id.startswith(xlib.get_rsitesearch_code() +
'-'):
bioinfo_app_name = xlib.get_rsitesearch_name()
elif result_dataset_id.startswith(xlib.get_samtools_code() +
'-'):
bioinfo_app_name = xlib.get_samtools_name()
elif result_dataset_id.startswith(xlib.get_soapdenovo2_code() +
'-'):
bioinfo_app_name = xlib.get_soapdenovo2_name()
elif result_dataset_id.startswith(
xlib.get_soapdenovotrans_code() + '-'):
bioinfo_app_name = xlib.get_soapdenovotrans_name()
elif result_dataset_id.startswith(xlib.get_star_code() + '-'):
bioinfo_app_name = xlib.get_star_name()
elif result_dataset_id.startswith(xlib.get_starcode_code() +
'-'):
bioinfo_app_name = xlib.get_starcode_name()
elif result_dataset_id.startswith(xlib.get_toa_code() + '-'):
bioinfo_app_name = xlib.get_toa_name()
elif result_dataset_id.startswith(
xlib.get_toa_process_download_basic_data_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_basic_data_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_download_dicots_04_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_dicots_04_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_download_gene_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_gene_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_download_go_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_go_name()
elif result_dataset_id.startswith(
xlib.get_toa_process_download_gymno_01_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_gymno_01_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_download_interpro_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_interpro_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_download_monocots_04_code() +
'-'):
bioinfo_app_name = xlib.get_toa_process_download_monocots_04_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_download_taxonomy_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_download_taxonomy_name(
)
elif result_dataset_id.startswith(
xlib.
get_toa_process_gilist_viridiplantae_nucleotide_gi_code(
) + '-'):
bioinfo_app_name = xlib.get_toa_process_gilist_viridiplantae_nucleotide_gi_name(
)
elif result_dataset_id.startswith(
xlib.
get_toa_process_gilist_viridiplantae_protein_gi_code()
+ '-'):
bioinfo_app_name = xlib.get_toa_process_gilist_viridiplantae_protein_gi_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_load_basic_data_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_basic_data_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_load_dicots_04_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_dicots_04_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_load_gene_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_gene_name()
elif result_dataset_id.startswith(
xlib.get_toa_process_load_go_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_go_name()
elif result_dataset_id.startswith(
xlib.get_toa_process_load_gymno_01_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_gymno_01_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_load_interpro_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_interpro_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_load_monocots_04_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_load_monocots_04_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_merge_annotations_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_merge_annotations_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_nr_blastplus_db_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_nr_blastplus_db_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_nr_diamond_db_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_nr_diamond_db_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_nt_blastplus_db_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_nt_blastplus_db_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_pipeline_aminoacid_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_pipeline_aminoacid_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_pipeline_nucleotide_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_pipeline_nucleotide_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_proteome_dicots_04_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_proteome_dicots_04_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_proteome_gymno_01_code() + '-'):
bioinfo_app_name = xlib.get_toa_process_proteome_gymno_01_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_proteome_monocots_04_code() +
'-'):
bioinfo_app_name = xlib.get_toa_process_proteome_monocots_04_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_proteome_refseq_plant_code() +
'-'):
bioinfo_app_name = xlib.get_toa_process_proteome_refseq_plant_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_rebuild_toa_database_code() +
'-'):
bioinfo_app_name = xlib.get_get_toa_process_rebuild_toa_database_name(
)
elif result_dataset_id.startswith(
xlib.get_toa_process_recreate_toa_database_code() +
'-'):
bioinfo_app_name = xlib.get_get_toa_process_recreate_toa_database_name(
)
elif result_dataset_id.startswith(xlib.get_tophat_code() +
'-'):
bioinfo_app_name = xlib.get_tophat_name()
elif result_dataset_id.startswith(xlib.get_transabyss_code() +
'-'):
bioinfo_app_name = xlib.get_transabyss_name()
elif result_dataset_id.startswith(
xlib.get_transcript_filter_code() + '-'):
bioinfo_app_name = xlib.get_transcript_filter_name()
elif result_dataset_id.startswith(
xlib.get_transcriptome_blastx_code() + '-'):
bioinfo_app_name = xlib.get_transcriptome_blastx_name()
elif result_dataset_id.startswith(
xlib.get_transdecoder_code() + '-'):
bioinfo_app_name = xlib.get_transdecoder_name()
elif result_dataset_id.startswith(xlib.get_transrate_code() +
'-'):
bioinfo_app_name = xlib.get_transrate_name()
elif result_dataset_id.startswith(xlib.get_trimmomatic_code() +
'-'):
bioinfo_app_name = xlib.get_trimmomatic_name()
elif result_dataset_id.startswith(xlib.get_trinity_code() +
'-'):
bioinfo_app_name = xlib.get_trinity_name()
elif result_dataset_id.startswith(
xlib.get_variant_calling_code() + '-'):
bioinfo_app_name = xlib.get_variant_calling_name()
elif result_dataset_id.startswith(xlib.get_vcftools_code() +
'-'):
bioinfo_app_name = xlib.get_vcftools_name()
elif result_dataset_id.startswith(
xlib.get_vcftools_perl_libraries_code() + '-'):
bioinfo_app_name = xlib.get_vcftools_perl_libraries_name()
elif result_dataset_id.startswith(xlib.get_vsearch_code() +
'-'):
bioinfo_app_name = xlib.get_vsearch_name()
else:
bioinfo_app_name = 'xxx'
print(line.format(result_dataset_id, bioinfo_app_name))
# close the SSH client connection
if OK:
xssh.close_ssh_client_connection(ssh_client)
# show continuation message
print(xlib.get_separator())
input('Press [Intro] to continue ...')
def build_gzip_process_script(cluster_name, dataset_type, current_run_dir):
'''
Build the current gzip process script.
'''
# initialize the control variable and the error list
OK = True
error_list = []
# get the gzip option dictionary
gzip_option_dict = xlib.get_option_dict(get_gzip_config_file(dataset_type))
# get the options
experiment_id = gzip_option_dict['identification']['experiment_id']
dataset_type_2 = gzip_option_dict['identification']['dataset_type']
dataset_id = gzip_option_dict['identification']['dataset_id']
action = gzip_option_dict['gzip parameters']['action']
# get the sections list
sections_list = []
for section in gzip_option_dict.keys():
sections_list.append(section)
sections_list.sort()
# build the dataset subdirectory and file name lists
dataset_subdirectory_list = []
file_name_list = []
for section in sections_list:
# if the section identification is like library-n
if re.match('^file-[0-9]+$', section):
dataset_subdirectory = gzip_option_dict[section][
'dataset_subdirectory']
dataset_subdirectory_list.append(dataset_subdirectory)
file_name = gzip_option_dict[section]['file_name']
file_name_list.append(file_name)
# get the dataset directory
if dataset_type_2 == 'reference':
dataset_dir = xlib.get_cluster_reference_dataset_dir(dataset_id)
elif dataset_type_2 == 'database':
dataset_dir = xlib.get_cluster_database_dataset_dir(dataset_id)
elif dataset_type_2 == 'read':
dataset_dir = xlib.get_cluster_experiment_read_dataset_dir(
experiment_id, dataset_id)
elif dataset_type_2 == 'result':
dataset_dir = xlib.get_cluster_experiment_result_dataset_dir(
experiment_id, dataset_id)
elif dataset_type_2 == 'whole-result':
dataset_dir = xlib.get_cluster_experiment_result_dataset_dir(
experiment_id, dataset_id)
# write the gzip process script
try:
if not os.path.exists(
os.path.dirname(get_gzip_process_script(dataset_type_2))):
os.makedirs(
os.path.dirname(get_gzip_process_script(dataset_type_2)))
with open(get_gzip_process_script(dataset_type_2),
mode='w',
encoding='utf8',
newline='\n') as file_id:
file_id.write('{0}\n'.format('#!/bin/bash'))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format(
'SEP="#########################################"'))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format('function init'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' INIT_DATETIME=`date --utc +%s`'))
file_id.write('{0}\n'.format(
' FORMATTED_INIT_DATETIME=`date --date="@$INIT_DATETIME" "+%Y-%m-%d %H:%M:%S"`'
))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(
' echo "Script started in node $HOSTNAME of cluster {0} at $FORMATTED_INIT_DATETIME UTC."'
.format(cluster_name)))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format('function run_gzip_process'))
file_id.write('{0}\n'.format('{'))
if dataset_type_2 in ['reference', 'database', 'read', 'result']:
file_id.write('{0}\n'.format(
' cd {0}'.format(current_run_dir)))
for i in range(len(dataset_subdirectory_list)):
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(
' echo "Compressing/decompressing {0}/{1}/{2} ..."'.
format(dataset_dir, dataset_subdirectory_list[i],
file_name_list[i])))
file_id.write('{0}\n'.format(' /usr/bin/time \\'))
file_id.write('{0}\n'.format(
' --format="Elapsed real time (s): %e\\nCPU time in kernel mode (s): %S\\nCPU time in user mode (s): %U\\nPercentage of CPU: %P\\nMaximum resident set size(Kb): %M\\nAverage total memory use (Kb):%K" \\'
))
if action == 'compress':
file_id.write('{0}\n'.format(
' gzip {0}/{1}/{2}'.format(
dataset_dir, dataset_subdirectory_list[i],
file_name_list[i])))
elif action == 'decompress':
file_id.write('{0}\n'.format(
' gzip --decompress {0}/{1}/{2}'.format(
dataset_dir, dataset_subdirectory_list[i],
file_name_list[i])))
file_id.write('{0}\n'.format(' RC=$?'))
file_id.write('{0}\n'.format(
' if [ $RC -ne 0 ]; then manage_error gzip $RC; fi')
)
elif dataset_type_2 == 'whole-result':
file_id.write('{0}\n'.format(
' cd {0}'.format(current_run_dir)))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(
' echo "Compressing/decompressing {0} ..."'.format(
dataset_dir)))
file_id.write('{0}\n'.format(' /usr/bin/time \\'))
file_id.write('{0}\n'.format(
' --format="Elapsed real time (s): %e\\nCPU time in kernel mode (s): %S\\nCPU time in user mode (s): %U\\nPercentage of CPU: %P\\nMaximum resident set size(Kb): %M\\nAverage total memory use (Kb):%K" \\'
))
if action == 'compress':
file_id.write('{0}\n'.format(
' tar --create --gzip --verbose --file={0}.tar.gz {0}'
.format(dataset_dir)))
elif action == 'decompress':
file_id.write('{0}\n'.format(
' tar --extract --gzip --verbose --file={0} --directory=/'
.format(dataset_dir)))
file_id.write('{0}\n'.format(' RC=$?'))
file_id.write('{0}\n'.format(
' if [ $RC -ne 0 ]; then manage_error tar $RC; fi'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(
' echo "Removing {0} ..."'.format(dataset_dir)))
file_id.write('{0}\n'.format(' /usr/bin/time \\'))
file_id.write('{0}\n'.format(
' --format="Elapsed real time (s): %e\\nCPU time in kernel mode (s): %S\\nCPU time in user mode (s): %U\\nPercentage of CPU: %P\\nMaximum resident set size(Kb): %M\\nAverage total memory use (Kb):%K" \\'
))
file_id.write('{0}\n'.format(
' rm -rf {0}'.format(dataset_dir)))
file_id.write('{0}\n'.format(' RC=$?'))
file_id.write('{0}\n'.format(
' if [ $RC -ne 0 ]; then manage_error rm $RC; fi'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format('function end'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' END_DATETIME=`date --utc +%s`'))
file_id.write('{0}\n'.format(
' FORMATTED_END_DATETIME=`date --date="@$END_DATETIME" "+%Y-%m-%d %H:%M:%S"`'
))
file_id.write('{0}\n'.format(' calculate_duration'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(
' echo "Script ended OK at $FORMATTED_END_DATETIME UTC with a run duration of $DURATION s ($FORMATTED_DURATION)."'
))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' RECIPIENT={0}'.format(
xconfiguration.get_contact_data())))
file_id.write('{0}\n'.format(
' SUBJECT="{0}: {1} process"'.format(
xlib.get_project_name(), xlib.get_gzip_name())))
file_id.write('{0}\n'.format(
' MESSAGE="The {0} process in node $HOSTNAME of cluster {0} ended OK at $FORMATTED_END_DATETIME with a run duration of $DURATION s ($FORMATTED_DURATION). Please review its log.<br/><br/>Regards,<br/>GI Genetica, Fisiologia e Historia Forestal<br/>Dpto. Sistemas y Recursos Naturales<br/>ETSI Montes, Forestal y del Medio Natural<br/>Universidad Politecnica de Madrid<br/>https://github.com/ggfhf/"'
.format(xlib.get_gzip_name(), cluster_name)))
file_id.write('{0}\n'.format(
' mail --append "Content-type: text/html;" --subject "$SUBJECT" "$RECIPIENT" <<< "$MESSAGE"'
))
file_id.write('{0}\n'.format(' exit 0'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format('function manage_error'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(' END_DATETIME=`date --utc +%s`'))
file_id.write('{0}\n'.format(
' FORMATTED_END_DATETIME=`date --date="@$END_DATETIME" "+%Y-%m-%d %H:%M:%S"`'
))
file_id.write('{0}\n'.format(' calculate_duration'))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write(
'{0}\n'.format(' echo "ERROR: $1 returned error $2"'))
file_id.write('{0}\n'.format(
' echo "Script ended WRONG at $FORMATTED_END_DATETIME UTC with a run duration of $DURATION s ($FORMATTED_DURATION)."'
))
file_id.write('{0}\n'.format(' echo "$SEP"'))
file_id.write('{0}\n'.format(' RECIPIENT={0}'.format(
xconfiguration.get_contact_data())))
file_id.write('{0}\n'.format(
' SUBJECT="{0}: {1} process"'.format(
xlib.get_project_name(), xlib.get_gzip_name())))
file_id.write('{0}\n'.format(
' MESSAGE="The {0} process in node $HOSTNAME of cluster {0} ended WRONG at $FORMATTED_END_DATETIME with a run duration of $DURATION s ($FORMATTED_DURATION). Please review its log.<br/><br/>Regards,<br/>GI Genetica, Fisiologia e Historia Forestal<br/>Dpto. Sistemas y Recursos Naturales<br/>ETSI Montes, Forestal y del Medio Natural<br/>Universidad Politecnica de Madrid<br/>https://github.com/ggfhf/"'
.format(xlib.get_gzip_name(), cluster_name)))
file_id.write('{0}\n'.format(
' mail --append "Content-type: text/html;" --subject "$SUBJECT" "$RECIPIENT" <<< "$MESSAGE"'
))
file_id.write('{0}\n'.format(' exit 3'))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format('function calculate_duration'))
file_id.write('{0}\n'.format('{'))
file_id.write('{0}\n'.format(
' DURATION=`expr $END_DATETIME - $INIT_DATETIME`'))
file_id.write('{0}\n'.format(' HH=`expr $DURATION / 3600`'))
file_id.write(
'{0}\n'.format(' MM=`expr $DURATION % 3600 / 60`'))
file_id.write('{0}\n'.format(' SS=`expr $DURATION % 60`'))
file_id.write('{0}\n'.format(
' FORMATTED_DURATION=`printf "%03d:%02d:%02d\\n" $HH $MM $SS`'
))
file_id.write('{0}\n'.format('}'))
file_id.write('{0}\n'.format(
'#-------------------------------------------------------------------------------'
))
file_id.write('{0}\n'.format('init'))
file_id.write('{0}\n'.format('run_gzip_process'))
file_id.write('{0}\n'.format('end'))
except:
error_list.append('*** ERROR: The file {0} can not be created'.format(
get_gzip_process_script(dataset_type_2)))
OK = False
# return the control variable and the error list
return (OK, error_list)
