| 1 |
dhidas |
1.1 |
#!/usr/bin/python
|
| 2 |
|
|
'''
|
| 3 |
|
|
Created on 1 Jun 2010
|
| 4 |
|
|
|
| 5 |
|
|
@author: kreczko
|
| 6 |
|
|
|
| 7 |
|
|
Email: kreczko@cern.ch
|
| 8 |
|
|
'''
|
| 9 |
|
|
|
| 10 |
|
|
from optparse import OptionParser
|
| 11 |
|
|
import os
|
| 12 |
|
|
import copy
|
| 13 |
|
|
import glob
|
| 14 |
|
|
|
| 15 |
|
|
duplicates = []
|
| 16 |
|
|
duplicateFiles = {}
|
| 17 |
|
|
|
| 18 |
|
|
def getROOTFiles(path):
|
| 19 |
|
|
path += "/*.root"
|
| 20 |
|
|
files = glob.glob(path)
|
| 21 |
|
|
return files
|
| 22 |
|
|
|
| 23 |
|
|
def getUniqueFiles(files):
|
| 24 |
|
|
if listContainsDuplicates(files):
|
| 25 |
|
|
findDuplicates(files)
|
| 26 |
|
|
else:
|
| 27 |
|
|
return files
|
| 28 |
|
|
uniqueFiles = copy.copy(files)
|
| 29 |
|
|
for values in duplicateFiles.itervalues():
|
| 30 |
|
|
for value in values:
|
| 31 |
|
|
uniqueFiles.remove(value)
|
| 32 |
|
|
values.sort()
|
| 33 |
|
|
uniqueFiles.append(values[-1])
|
| 34 |
|
|
return uniqueFiles
|
| 35 |
|
|
|
| 36 |
|
|
def listContainsDuplicates(list):
|
| 37 |
|
|
seen = []
|
| 38 |
|
|
for item in list:
|
| 39 |
|
|
jobnumber = extractJobnumber(item)
|
| 40 |
|
|
if jobnumber in seen:
|
| 41 |
|
|
duplicates.append(jobnumber)
|
| 42 |
|
|
else:
|
| 43 |
|
|
seen.append(jobnumber)
|
| 44 |
|
|
return len(duplicates) >0
|
| 45 |
|
|
|
| 46 |
|
|
def findDuplicates(files):
|
| 47 |
|
|
for file in files:
|
| 48 |
|
|
for job in duplicates:
|
| 49 |
|
|
if job == extractJobnumber(file):
|
| 50 |
|
|
addDuplicate(job, file)
|
| 51 |
|
|
|
| 52 |
|
|
def extractJobnumber(file):
|
| 53 |
|
|
jobnumber = file.split('_')[-3]
|
| 54 |
|
|
return int(jobnumber)
|
| 55 |
|
|
|
| 56 |
|
|
def addDuplicate(jobnumber, file):
|
| 57 |
|
|
if not duplicateFiles.has_key(jobnumber):
|
| 58 |
|
|
duplicateFiles[jobnumber] = []
|
| 59 |
|
|
duplicateFiles[jobnumber].append(file)
|
| 60 |
|
|
|
| 61 |
|
|
def getDuplicateFiles(allFiles, uniqueFiles):
|
| 62 |
|
|
# print 'Number of file in path:', len(files)
|
| 63 |
|
|
# files.sort()
|
| 64 |
|
|
# uniqueFiles = getUniqueFiles(files)
|
| 65 |
|
|
# uniqueFiles.sort()
|
| 66 |
|
|
# print 'Number of unique files', len(uniqueFiles)
|
| 67 |
|
|
filesToRemove = [file for file in allFiles if not file in uniqueFiles]
|
| 68 |
|
|
return filesToRemove
|
| 69 |
|
|
|
| 70 |
|
|
if __name__ == "__main__":
|
| 71 |
|
|
parser = OptionParser()
|
| 72 |
|
|
(options, args) = parser.parse_args()
|
| 73 |
|
|
if len(args) >0:
|
| 74 |
|
|
path = args[0]
|
| 75 |
|
|
files = os.listdir(path)
|
| 76 |
|
|
files.sort()
|
| 77 |
|
|
uniqueFiles = getUniqueFiles(files)
|
| 78 |
|
|
uniqueFiles.sort()
|
| 79 |
|
|
duplicateFiles = getDuplicateFiles(files, uniqueFiles)
|
| 80 |
|
|
print 'Number of file in path:', len(files)
|
| 81 |
|
|
print 'Number of unique files', len(uniqueFiles)
|
| 82 |
|
|
print 'Number of duplicate files:', len(duplicateFiles)
|
| 83 |
|
|
if len(duplicateFiles) > 0:
|
| 84 |
|
|
print 'Files to remove:'
|
| 85 |
|
|
for file in duplicateFiles:
|
| 86 |
|
|
print path + file
|
| 87 |
|
|
else:
|
| 88 |
|
|
print 'File path was not specified. Use script "./remove_duplicates path"' |
