server-scripts/qhtcp-workflow/apps/python/concatGTFResults.py

#!/usr/bin/env python
# This code is to concatenate the batch GO Term Finder results (.tsv) generated from batch GTF perl code(Chris Johnson, U of Tulsa) into a list table

import os
import glob

def list_files(directory):
    """Return a list of all files in the given directory."""
    return glob.glob(os.path.join(directory, '*.txt.tsv'))

def concatenate_gtf_results(data_dir, output_file):
    """Concatenate the GTF results into a single file."""
    output = open(output_file, 'w')

    files = list_files(data_dir)
    files.sort()

    for file_path in files:
        file_name = os.path.basename(file_path).rstrip('.txt.tsv')
        with open(file_path, 'r') as f:
            labels = f.readline().strip().split('\t')
            output.write('\t'.join(labels) + '\n')

            for line in f:
                line = line.strip().strip('\t')
                if line:
                    output.write(line + '\n')

    output.close()

if __name__ == '__main__':
    if len(sys.argv) != 3:
        print('Usage: python Concatenate_GTF_results.py data_dir output_file')
        sys.exit(1)

    data_dir = sys.argv[1]
    output_file = sys.argv[2]

    concatenate_gtf_results(data_dir, output_file)





# Old version
# def list_files(directory):
#     """Return a list of all files in the given directory."""
#     return glob.glob(os.path.join(directory, '*.txt.tsv'))

# try:
#    data_file_Path = sys.argv[1]
#    output_file_Path = sys.argv[2]
# except: 
#    print ('Usage: python Concatenate_GTF_results.py /datasetPath /outputFilePath_and_Name')
#    print ('Data file not found, error in given directory')
#    sys.exit(1)

# try:
#     output = open(output_file_Path, 'w')
# except OSError:
#     print ('output file error')

# # get all the GTF result files in given directory
# File_list = []
# File_list = list_files(data_file_Path)
# File_list.sort()

# i = 0
# for file in File_list:
#     #parse the file names given in absolute path
#     file_name = file.strip().split('/')[-1]
#     file_name = file_name.rstrip('.txt.tsv')
#     # function to read tsv files from a given directory
#     #open the file
#     data = open(file,'r')
#     #reading the label line
#     labelLine = data.readline()
#     label = labelLine.strip().split('\t')
#     #write the label
#     #updates2010July26: update following label writing code	
#     if i == 0:
#     #    output.write('cluster origin')
#         for element in label:
#             output.write(element)
#             output.write('\t')
#     i = i + 1
#     #updates2010July26 End
#     #switch to the next line
#     output.write('\n')

#     #read the GO terms
#     GOTermLines = data.readlines()
#     for GOTerm in GOTermLines:
#         GOTerm = GOTerm.strip().strip('\t')
#         if GOTerm != '':
# 	    #updates2010July26: remove the code to write the first column 'REMc cluster ID'
#             #output.write(file_name)
#             #output.write('\t')
# 	    ##updates2010July26 update end
#             output.write(GOTerm + '\n')
#             #output.write('\n')
# output.close()