sorting of bed file implemented

.gitignore

 .idea/
+bin
 venv/
 *.bed
 *.txt.gz

generate.py

 import gzip
 import ntpath
+import os
 import sys
+import subprocess
+import urllib.request
+from pathlib import Path
 
 
 def transform(input_line):
@@ -22,15 +26,18 @@ def transform(input_line):
     for i in range(0, int(block_count)):
         block_starts.append(block_starts_tmp[i])
         block_sizes.append(str(int(block_ends_tmp[i]) - int(block_starts_tmp[i])))
-    output = [chromosome, chromosome_start, chromosome_end, name, score, strand, thick_start, thick_end, item_rgb,
+    output_line = [chromosome, chromosome_start, chromosome_end, name, score, strand, thick_start, thick_end, item_rgb,
                    block_count, ",".join(block_sizes), ",".join(block_starts)]
-    return output
+    return output_line
 
 
 inputFile = sys.argv[1]
-outputFile = ntpath.basename(inputFile).replace(".txt.gz", "") + ".bed"
+basename = ntpath.basename(inputFile).replace(".txt.gz", "")
+output_file_unsorted = basename + ".bed"
 
-output = open(outputFile, "w")
+output = open(output_file_unsorted, "w")
+
+print('Generating bed file: ' + output_file_unsorted)
 
 with gzip.open(inputFile, 'rt') as hIN:
     for line in hIN:
@@ -38,3 +45,25 @@ with gzip.open(inputFile, 'rt') as hIN:
         output_line = transform(F)
         print("\t".join(output_line), file=output)
 output.close()
+
+if not Path('bin').is_dir():
+    os.mkdir('bin')
+
+
+def downloadUcscFile(filename):
+    if not Path('bin/' + filename).is_file():
+        print('Beginning file download ' + filename + '...')
+
+        url = 'http://hgdownload.soe.ucsc.edu/admin/exe/linux.x86_64/' + filename
+        urllib.request.urlretrieve(url, 'bin/' + filename)
+        os.chmod('bin/' + filename, 0o755)
+
+
+downloadUcscFile("sortBed")
+
+output_file_sorted = basename + "-sorted.bed"
+print('Sorting bed file: ')
+subprocess.call(["bin/sortBed", output_file_unsorted, output_file_sorted])
+
+downloadUcscFile("bedToBigBed")
+downloadUcscFile("fetchChromSizes")