changeset 2:54d549210759

correction

--- a/preprocess.py	Tue Apr 28 11:23:47 2015 +0200
+++ b/preprocess.py	Tue Apr 28 11:26:30 2015 +0200
@@ -4,43 +4,41 @@
 import sys
 import subprocess
 import zipfile
-
+import optparse
 
 def main():
     
-    extra_files_directory = sys.argv[1]
-    report = sys.argv[4]
-    new_files_directory = sys.argv[6]
-    dataset=sys.argv[7]
-    cdffull_name=sys.argv[9]
-    ufl_name=sys.argv[10]
-    ugp_name=sys.argv[11]
-    acs_name=sys.argv[12]
-    cdffull=sys.argv[14]
-    ufl=sys.argv[15]
-    ugp=sys.argv[16]
-    acs=sys.argv[17]
-    tumor=sys.argv[18]
-    settingType=sys.argv[19]
-    outputgraph=sys.argv[20]
-    zipfigures=sys.argv[21]
-    outputlog=sys.argv[22]
-    log=sys.argv[23]
-    user=sys.argv[24]
+    parser = optparse.OptionParser()
+    parser.add_option('-s', action="store", dest='summary')
+    parser.add_option('-e', action="store", dest='dataSetName')
+    parser.add_option('-p', action="store", dest='new_file_path')
+    parser.add_option('-c', action="store", dest='inputcdffull_name')
+    parser.add_option('-f', action="store", dest='inputufl_name')
+    parser.add_option('-g', action="store", dest='inputugp_name')
+    parser.add_option('-a', action="store", dest='inputacs_name')
+    parser.add_option('-d', action="store", dest='inputcdffull')
+    parser.add_option('-v', action="store", dest='inputufl')
+    parser.add_option('-w', action="store", dest='inputugp')
+    parser.add_option('-b', action="store", dest='inputacs')
+    parser.add_option('-t', action="store", dest='tumorcsv')
+    parser.add_option('-y', action="store", dest='settingsType')
+    parser.add_option('-o', action="store", dest='outputgraph')
+    parser.add_option('-z', action="store", dest='zipfigures')
+    parser.add_option('-k', action="store", dest='outputlog')
+    parser.add_option('-l', action="store", dest='log')
+    parser.add_option('-u', action="store", dest='user_id')
+
+    parser.add_option('-i', action="append", dest='inputFile', default=[])
+    parser.add_option('-n', action='append', dest='inputFileName', default=[])
+        
+    options, args = parser.parse_args()
+        
+    dataSetName=options.dataSetName
+    destinationPath=os.path.join(options.new_file_path, options.user_id, dataSetName)
     
-    extra_file_names = sorted(os.listdir(extra_files_directory))
-        
-    if (cdffull_name.count(",") != 0):    
-        chipType=cdffull_name.split(",",1)[0]
-        tagExt=cdffull_name.split(",",1)[1]
-        tag=tagExt.split(".",1)[0]
-    else:
-        chipType=cdffull_name.split(".",1)[0]
-        tag=""
-                
-    data_dir = os.path.join(new_files_directory, user, dataset)
-    mpagenomics_dir = os.path.join(new_files_directory, "mpagenomics",user)
-        
+    mpagenomics_dir = os.path.join(options.new_file_path,"mpagenomics",options.user_id)
+    data_dir = os.path.join(options.new_file_path, options.user_id)
+    
     try:
         os.makedirs(data_dir)
     except:
@@ -49,61 +47,61 @@
     
     if (not os.path.isdir(mpagenomics_dir)):
         os.makedirs(mpagenomics_dir)
-            
-    for name in extra_file_names:
-        source = os.path.join(extra_files_directory, name)
-        # Strip _task_XXX from end of name
-        name_match = re.match(r"^\d+_task_(.*).dat$", name)
-        if name_match:
-            name = name_match.group(1)
-        else:
-            # Skip indices, composite extra_files_paths, etc...
-            continue
-        #escaped_name = name.replace("_", "-")
-        #dataset_name = "%s" % (name, 'visible', ext, db_key)
-        destination = os.path.join(data_dir, name)
-        _copy(source, destination)
-#       datasets_created.append(name)
+    
+    for inputFile, inputFileName in zip(options.inputFile,options.inputFileName):
+        source = inputFile
+        destination=os.path.join(data_dir,inputFileName)
+        _copy(source,destination)
+    
     
-    _copy(cdffull,os.path.join(data_dir, cdffull_name))
-    _copy(ugp,os.path.join(data_dir, ugp_name))
-    _copy(ufl,os.path.join(data_dir, ufl_name))
-    _copy(acs,os.path.join(data_dir, acs_name))
+    cdffull_name=options.inputcdffull_name
+    if (cdffull_name.count(",") != 0):    
+        chipType=cdffull_name.split(",",1)[0]
+        tagExt=cdffull_name.split(",",1)[1]
+        tag=tagExt.split(".",1)[0]
+    else:
+        chipType=cdffull_name.split(".",1)[0]
+        tag=""
+         
+    _copy(options.inputcdffull,os.path.join(data_dir, options.inputcdffull_name))
+    _copy(options.inputugp,os.path.join(data_dir, options.inputugp_name))
+    _copy(options.inputufl,os.path.join(data_dir, options.inputufl_name))
+    _copy(options.inputacs,os.path.join(data_dir, options.inputacs_name))
+     
     
-   
-    fig_dir = os.path.join("mpagenomics", user, "figures", dataset, "signal")
-    abs_fig_dir = os.path.join(new_files_directory, fig_dir)
-       
-    
-    retcode = _preprocess(chipType, dataset, mpagenomics_dir, data_dir, new_files_directory, tumor, settingType, outputgraph, outputlog, log, tag)
+    fig_dir = os.path.join("mpagenomics", options.user_id, "figures", dataSetName, "signal")
+    abs_fig_dir = os.path.join(options.new_file_path, fig_dir)
         
+     
+    retcode = _preprocess(chipType, dataSetName, mpagenomics_dir, data_dir, options.new_file_path, options.tumorcsv, options.settingsType, options.outputgraph, options.outputlog, options.log, tag)
+         
     if (retcode == 0):
-        if (os.path.isdir(abs_fig_dir)) and (outputgraph == "TRUE"):
-        
+        if (os.path.isdir(abs_fig_dir)) and (options.outputgraph == "TRUE"):
+         
             new_files = os.listdir(abs_fig_dir)
-            zipbuf = zipfile.ZipFile(os.path.join(abs_fig_dir, zipfigures), 'w', zipfile.ZIP_DEFLATED)
+            zipbuf = zipfile.ZipFile(os.path.join(abs_fig_dir, options.zipfigures), 'w', zipfile.ZIP_DEFLATED)
             for current_file in new_files:
                 fn = os.path.join(abs_fig_dir, current_file)
                 relfn = fn[len(abs_fig_dir) + len(os.sep):]
                 zipbuf.write(fn, relfn)
-        
-        f = open(report, "w")   
+         
+        f = open(options.summary, "w")   
         # Create report
         try:
-            for name in extra_file_names:
-                f.write("%s\t%s\t%s\n" %(re.match(r"^\d+_task_(.*).dat$", name).group(1),dataset,chipType))
+            for inputFileName in options.inputFileName:
+                f.write("%s\t%s\t%s\n" %(inputFileName,dataSetName,chipType))
         finally:
             shutil.rmtree(data_dir)
             f.close()
-        
+         
         sys.exit(retcode)
-        
+         
     sys.exit(retcode)
-    
+     
     
 def _copy(source, destination):
     try:
-        os.link(source, destination)
+        os.symlink(source, destination)
     except:
         shutil.copy(source, destination)
 

--- a/preprocess.xml	Tue Apr 28 11:23:47 2015 +0200
+++ b/preprocess.xml	Tue Apr 28 11:26:30 2015 +0200
@@ -1,7 +1,7 @@
 <tool id="preprocess2" name="Data Normalization" force_history_refresh="True" version="0.1.0">
   
 	<command interpreter="python">
-    preprocess2.py 
+    preprocess.py 
 		-s '$summary' 
 		-p '$__new_file_path__'  
 		-c '$inputcdffull.name'