hubarchivecreator: hubArchiveCreator.py comparison

comparison hubArchiveCreator.py @ 20:40469b265ddb draft

planemo upload for repository https://github.com/goeckslab/hub-archive-creator commit 3af31e043f5b82636015c18e013d2f22ce6c9077-dirty

author	yating-l
date	Fri, 20 Jan 2017 17:12:03 -0500
parents	d786bca6a75d
children	884ee2a71680

comparison

equal deleted inserted replaced

-:0152500d9acd
+:40469b265ddb
 import sys
 # Internal dependencies
 from Bam import Bam
 from BedSimpleRepeats import BedSimpleRepeats
+from BedSpliceJunctions import BedSpliceJunctions
 from Bed import Bed
 from BigWig import BigWig
 from util.Fasta import Fasta
 from util.Filters import TraceBackFormatter
 from Gff3 import Gff3
 from Gtf import Gtf
 from Psl import Psl
 from TrackHub import TrackHub
+from bigPsl import bigPsl
 # TODO: Verify each subprocessed dependency is accessible [gff3ToGenePred, genePredToBed, twoBitInfo, faToTwoBit, bedToBigBed, sort
 def main(argv):
 parser.add_argument('--gtf', action='append', help='GTF format')
 # Bed4+12 (TrfBig)
 parser.add_argument('--bedSimpleRepeats', action='append', help='Bed4+12 format, using simpleRepeats.as')
+# Bed12+1 (regtools)
+parser.add_argument('--bedSpliceJunctions', action='append', help='Bed12+1 format, using spliceJunctions.as')
 # Generic Bed (Blastx transformed to bed)
 parser.add_argument('--bed', action='append', help='Bed generic format')
+# Bed12+12 (tblastn)
+parser.add_argument('--bigpsl', action='append', help='bigPsl format')
 # BigWig Management
 parser.add_argument('--bigwig', action='append', help='BigWig format')
 # Bam Management
 # ARRAY[DICT{FILE_PATH: DICT{NAME: NAME_VALUE, EXTRA_DATA: EXTRA_DATA_VALUE}}]
 # EXTRA_DATA could be anything, for example the index of a BAM => {"index", FILE_PATH}
 array_inputs_bam = args.bam
 array_inputs_bed_generic = args.bed
 array_inputs_bed_simple_repeats = args.bedSimpleRepeats
+array_inputs_bed_splice_junctions = args.bedSpliceJunctions
 array_inputs_bigwig = args.bigwig
 array_inputs_gff3 = args.gff3
 array_inputs_gtf = args.gtf
 array_inputs_psl = args.psl
+array_inputs_bigpsl = args.bigpsl
 outputFile = args.output
 json_inputs_data = args.data_json
+# TODO: Instead use a class to properly store the objects, with object_hook
 inputs_data = json.loads(json_inputs_data)
 # We remove the spaces in ["name"] of inputs_data
 sanitize_name_inputs(inputs_data)
 # TODO: Check here all the binaries / tools we need. Exception if missing
 for (inputs, datatype_class) in [
 (array_inputs_bam, Bam),
 (array_inputs_bed_generic, Bed),
 (array_inputs_bigwig, BigWig),
 (array_inputs_bed_simple_repeats, BedSimpleRepeats),
+(array_inputs_bed_splice_junctions, BedSpliceJunctions),
 (array_inputs_gff3, Gff3),
 (array_inputs_gtf, Gtf),
-(array_inputs_psl, Psl)]:
+(array_inputs_psl, Psl),
+(array_inputs_bigpsl, bigPsl)]:
 if inputs:
 all_datatype_dictionary.update(create_ordered_datatype_objects(datatype_class, inputs, inputs_data))
 # Create Ordered Dictionary to add the tracks in the tool form order
 all_datatype_ordered_dictionary = collections.OrderedDict(all_datatype_dictionary)
 sys.exit(0)
 def sanitize_name_input(string_to_sanitize):
-return string_to_sanitize \
+"""
+Sanitize the string passed in parameter by replacing '/' and ' ' by '_'
+:param string_to_sanitize:
+:return :
+:Example:
+>>> sanitize_name_input('this/is an//example')
+this_is_an__example
+"""
+return string_to_sanitize \
 .replace("/", "_") \
 .replace(" ", "_")
 def sanitize_name_inputs(inputs_data):
 """
-Sometimes output from Galaxy, or even just file name from user have spaces
+Sanitize value of the keys "name" of the dictionary passed in parameter.
-Also, it can contain '/' character and could break the use of os.path function
+Because sometimes output from Galaxy, or even just file name, from user inputs, have spaces.
+Also, it can contain '/' character and could break the use of os.path function.
 :param inputs_data: dict[string, dict[string, string]]
-:return:
 """
 for key in inputs_data:
 inputs_data[key]["name"] = sanitize_name_input(inputs_data[key]["name"])
 def create_ordered_datatype_objects(ExtensionClass, array_inputs, inputs_data):
 """
 Function which executes the creation all the necessary files / folders for a special Datatype, for TrackHub
 and update the dictionary of datatype
-:param ExtensionClass: T <= Datatype
-:param array_inputs: list[string]
+:param ExtensionClass:
+:param array_inputs:
 :param inputs_data:
+:type ExtensionClass: Datatype
+:type array_inputs: list[string]
+:type inputs_data: dict
+:rtype: dict
 """
 datatype_dictionary = {}
 # TODO: Optimize this double loop
 in STDOUT
 - Still access to full, brute and traceback for errors
 in STDERR
 - And further access to debug if needed
 in .log
-:return:
 """
 if not log_stdout:
 raise Exception("No log_stdout given. Stopping the application")
 # stdout for INFO / WARN / ERROR / CRITICAL
 log_stdout.setLevel(logging.INFO)
 """
 Dev Logger is defined as following:
 - Dev needs to have WARN, ERROR and CRITICAL but well formatted / without traceback, in stdout
 - Still access to full, brute and traceback in stderr for errors
 - And further access to debug if needed
-:return:
 """
 if not log_stdout:
 raise Exception("No log_stdout given. Stopping the application")
 log_format = '%(message)s'
 logging.getLogger().addHandler(log_stdout)
 def configure_logger_stderr():
 """
 Configure what should be logged in stderr
-:return:
 """
 log_error = logging.StreamHandler(sys.stderr)
 log_error.setLevel(logging.ERROR)
 log_error_format = '%(message)s'

Mercurial > repos > rmarenco > hubarchivecreator

comparison hubArchiveCreator.py @ 20:40469b265ddb draft