| 1 |
#!/usr/bin/env python
|
| 2 |
#===================================================================================================
|
| 3 |
import sys, getopt, os, fnmatch, commands
|
| 4 |
import string
|
| 5 |
|
| 6 |
# declare
|
| 7 |
setupCmsswCommand = \
|
| 8 |
'cd /home/$USER/cms/cmssw/017/CMSSW_3_9_5_patch1/src;eval `scram runtime -sh`;cd - >& /dev/null;'
|
| 9 |
|
| 10 |
#===================================================================================================
|
| 11 |
def usage():
|
| 12 |
print "possible options are: --help, --InputPath=<myInputPath>, --OutputPath=<myOutputPath>," \
|
| 13 |
+ " --FilenameHeader=<myFileHeader>, --DatasetListFile=<datasetListFile>"
|
| 14 |
|
| 15 |
#===================================================================================================
|
| 16 |
def filesExist(path,filenameExpression):
|
| 17 |
exists = False
|
| 18 |
|
| 19 |
if not os.path.exists(path):
|
| 20 |
return exists;
|
| 21 |
|
| 22 |
for fileName in os.listdir(path):
|
| 23 |
if fnmatch.fnmatch (fileName,filenameExpression):
|
| 24 |
exists = True
|
| 25 |
return exists
|
| 26 |
|
| 27 |
#===================================================================================================
|
| 28 |
# Merge Filesets
|
| 29 |
#===================================================================================================
|
| 30 |
def MergeFilesets(versionList,datasetNameList,skimNameList,inputPath,outputPath,filenameHeader):
|
| 31 |
n = 0
|
| 32 |
for dataset in datasetNameList:
|
| 33 |
#print "================================================================"
|
| 34 |
print " Merging files for dataset: " + dataset
|
| 35 |
|
| 36 |
# create the output directory in case it is not yet there
|
| 37 |
command = 'mkdir -p ' + outputPath
|
| 38 |
os.system(command)
|
| 39 |
|
| 40 |
outputMergedFilename = filenameHeader + '_' + dataset + '_' + skimNameList[n] + '.root'
|
| 41 |
inputFilenameRegExp = filenameHeader + '_' + dataset + '_' + skimNameList[n] + '_????.root'
|
| 42 |
# command = setupCmsswCommand + 'hadd -f ' + outputPath + outputMergedFilename \
|
| 43 |
command = 'hadd -f7 ' + outputPath + outputMergedFilename \
|
| 44 |
+ ' ' + inputPath + '/' + versionList[n] + '/' + dataset + '/' \
|
| 45 |
+ inputFilenameRegExp + ' >& ./merging.tmp'
|
| 46 |
# command = 'hadd -f ' + outputPath + \
|
| 47 |
# outputMergedFilename + ' ' + inputPath + inputFilenameRegExp + \
|
| 48 |
# ' >& ./merging.tmp'
|
| 49 |
|
| 50 |
if (filesExist(inputPath+'/'+versionList[n]+'/'+dataset,inputFilenameRegExp) == True):
|
| 51 |
if (os.path.exists(outputPath+outputMergedFilename)):
|
| 52 |
print " Warning: merged file already exists. It will be deleted.\n " + \
|
| 53 |
outputPath+outputMergedFilename
|
| 54 |
os.system('rm ' + outputPath+outputMergedFilename)
|
| 55 |
#print ' merging: ' + command
|
| 56 |
os.system(command)
|
| 57 |
#print ''
|
| 58 |
else:
|
| 59 |
print " Warning: No files for dataset " + dataset + "\n at the location: " + inputPath \
|
| 60 |
+ '/' + versionList[n] + '/' + dataset + '/' + inputFilenameRegExp
|
| 61 |
#print ''
|
| 62 |
n += 1
|
| 63 |
|
| 64 |
#===================================================================================================
|
| 65 |
# Main Program
|
| 66 |
#===================================================================================================
|
| 67 |
datasetListFile = ''
|
| 68 |
inputPath = ''
|
| 69 |
outputPath = ''
|
| 70 |
filenameHeader = ''
|
| 71 |
versionList = list()
|
| 72 |
datasetNameList = list()
|
| 73 |
skimNameList = list()
|
| 74 |
|
| 75 |
if len(sys.argv[1:]) < 1:
|
| 76 |
print "Error: not enough parameters specified"
|
| 77 |
usage()
|
| 78 |
sys.exit()
|
| 79 |
|
| 80 |
try:
|
| 81 |
opts, args = getopt.getopt(sys.argv[1:], "hi:o:f:d:",
|
| 82 |
["help","InputPath=","OutputPath=",
|
| 83 |
"FilenameHeader=","DatasetListFile="])
|
| 84 |
for o, a in opts:
|
| 85 |
if o in ("-h", "--help"):
|
| 86 |
usage()
|
| 87 |
sys.exit()
|
| 88 |
elif o in ("-i", "--InputPath"):
|
| 89 |
inputPath = a + "/"
|
| 90 |
elif o in ("-o", "--OutputPath"):
|
| 91 |
outputPath = a + "/"
|
| 92 |
elif o in ("-f", "--FilenameHeader"):
|
| 93 |
filenameHeader = a
|
| 94 |
elif o in ("-d", "--DatasetListFile"):
|
| 95 |
datasetListFile = a
|
| 96 |
else:
|
| 97 |
usage()
|
| 98 |
sys.exit()
|
| 99 |
except getopt.GetoptError:
|
| 100 |
usage()
|
| 101 |
sys.exit(2)
|
| 102 |
|
| 103 |
if (inputPath == ''):
|
| 104 |
print "Error: No InputPath specified."
|
| 105 |
sys.exit()
|
| 106 |
|
| 107 |
if (outputPath == ''):
|
| 108 |
print "Error: No OutputPath specified."
|
| 109 |
sys.exit()
|
| 110 |
|
| 111 |
if (filenameHeader == ''):
|
| 112 |
print "Error: No FilenameHeader specified."
|
| 113 |
sys.exit()
|
| 114 |
|
| 115 |
if (datasetListFile == ''):
|
| 116 |
print "Error: No dataset list file specified."
|
| 117 |
sys.exit()
|
| 118 |
|
| 119 |
try:
|
| 120 |
inputFile = open(datasetListFile,"r")
|
| 121 |
except IOError:
|
| 122 |
print "Error: The specified dataset list file " + datasetListFile + " could not be opened."
|
| 123 |
sys.exit()
|
| 124 |
|
| 125 |
print datasetListFile
|
| 126 |
#===================================================================================================
|
| 127 |
# Read in list of datasets and skim names
|
| 128 |
#===================================================================================================
|
| 129 |
lineNumber = 1
|
| 130 |
templine = inputFile.readline()
|
| 131 |
while len(templine.split()) > 0:
|
| 132 |
|
| 133 |
# print "reading line"
|
| 134 |
# print templine
|
| 135 |
|
| 136 |
# ignore commented lines
|
| 137 |
if (templine[0] == '#'):
|
| 138 |
templine = inputFile.readline()
|
| 139 |
lineNumber += 1
|
| 140 |
continue;
|
| 141 |
|
| 142 |
|
| 143 |
# print "processing line"
|
| 144 |
# check what type of list was provided and assume 'noskim' as default
|
| 145 |
if (len(templine.split()) == 7) :
|
| 146 |
tempInputList = templine.split()
|
| 147 |
versionList .append(tempInputList[0])
|
| 148 |
datasetNameList.append(tempInputList[1])
|
| 149 |
skimNameList .append('noskim')
|
| 150 |
lineNumber += 1
|
| 151 |
else:
|
| 152 |
print " ERROR: incorrect format for cross section file. Check line %s" % lineNumber
|
| 153 |
sys.exit()
|
| 154 |
|
| 155 |
# read the next line
|
| 156 |
templine = inputFile.readline()
|
| 157 |
|
| 158 |
inputFile.close()
|
| 159 |
|
| 160 |
# Check the list of variables
|
| 161 |
count = 0
|
| 162 |
for l in datasetNameList:
|
| 163 |
count += 1
|
| 164 |
|
| 165 |
MergeFilesets(versionList,datasetNameList,skimNameList,inputPath,outputPath,filenameHeader)
|
