|
6
|
1 #! /usr/bin/env python
|
|
|
2 #
|
|
|
3 # Copyright INRA-URGI 2009-2012
|
|
|
4 #
|
|
|
5 # This software is governed by the CeCILL license under French law and
|
|
|
6 # abiding by the rules of distribution of free software. You can use,
|
|
|
7 # modify and/ or redistribute the software under the terms of the CeCILL
|
|
|
8 # license as circulated by CEA, CNRS and INRIA at the following URL
|
|
|
9 # "http://www.cecill.info".
|
|
|
10 #
|
|
|
11 # As a counterpart to the access to the source code and rights to copy,
|
|
|
12 # modify and redistribute granted by the license, users are provided only
|
|
|
13 # with a limited warranty and the software's author, the holder of the
|
|
|
14 # economic rights, and the successive licensors have only limited
|
|
|
15 # liability.
|
|
|
16 #
|
|
|
17 # In this respect, the user's attention is drawn to the risks associated
|
|
|
18 # with loading, using, modifying and/or developing or reproducing the
|
|
|
19 # software by the user in light of its specific status of free software,
|
|
|
20 # that may mean that it is complicated to manipulate, and that also
|
|
|
21 # therefore means that it is reserved for developers and experienced
|
|
|
22 # professionals having in-depth computer knowledge. Users are therefore
|
|
|
23 # encouraged to load and test the software's suitability as regards their
|
|
|
24 # requirements in conditions enabling the security of their systems and/or
|
|
|
25 # data to be ensured and, more generally, to use and operate it in the
|
|
|
26 # same conditions as regards security.
|
|
|
27 #
|
|
|
28 # The fact that you are presently reading this means that you have had
|
|
|
29 # knowledge of the CeCILL license and that you accept its terms.
|
|
|
30 #
|
|
|
31
|
|
|
32 import random, os, time, shutil
|
|
|
33 from optparse import OptionParser
|
|
|
34 from commons.core.parsing.ParserChooser import ParserChooser
|
|
|
35 from SMART.Java.Python.structure.Transcript import Transcript
|
|
|
36 from SMART.Java.Python.structure.Interval import Interval
|
|
|
37 from SMART.Java.Python.ncList.NCList import NCList
|
|
|
38 from SMART.Java.Python.ncList.NCListCursor import NCListCursor
|
|
|
39 from SMART.Java.Python.ncList.NCListFilePickle import NCListFilePickle, NCListFileUnpickle
|
|
|
40 from SMART.Java.Python.ncList.FileSorter import FileSorter
|
|
|
41 from SMART.Java.Python.ncList.NCListMerger import NCListMerger
|
|
|
42 from SMART.Java.Python.misc.Progress import Progress
|
|
|
43 from SMART.Java.Python.misc.UnlimitedProgress import UnlimitedProgress
|
|
|
44 try:
|
|
|
45 import cPickle as pickle
|
|
|
46 except:
|
|
|
47 import pickle
|
|
|
48
|
|
|
49 class ConvertToNCList(object):
|
|
|
50
|
|
|
51 def __init__(self, verbosity = 1):
|
|
|
52 self._parsers = {}
|
|
|
53 self._sortedFileNames = {}
|
|
|
54 self._inputFileName = None
|
|
|
55 self._outputFileName = None
|
|
|
56 self._index = False
|
|
|
57 self._ncLists = {}
|
|
|
58 self._splittedFileNames = {}
|
|
|
59 self._nbElements = 0
|
|
|
60 self._nbElementsPerChromosome = {}
|
|
|
61 self._randomNumber = random.randint(0, 10000)
|
|
|
62 self._sorted = False
|
|
|
63 self._verbosity = verbosity
|
|
|
64
|
|
|
65 def setInputFileName(self, fileName, format):
|
|
|
66 self._inputFileName = fileName
|
|
|
67 chooser = ParserChooser(self._verbosity)
|
|
|
68 chooser.findFormat(format)
|
|
|
69 self._parser = chooser.getParser(fileName)
|
|
|
70
|
|
|
71 def setOutputFileName(self, fileName):
|
|
|
72 self._outputFileName = fileName
|
|
|
73 fileNameNoExtension = os.path.splitext(fileName)[0]
|
|
|
74 baseName = "%s_%d" % (fileNameNoExtension, self._randomNumber)
|
|
|
75 self._directory = "%s_files" % (baseName)
|
|
|
76 if not os.path.exists(self._directory):
|
|
|
77 os.makedirs(self._directory)
|
|
|
78 self._sortedFileNames = os.path.join(self._directory, baseName)
|
|
|
79
|
|
|
80 def setIndex(self, boolean):
|
|
|
81 self._index = boolean
|
|
|
82
|
|
|
83 def setSorted(self, boolean):
|
|
|
84 self._sorted = boolean
|
|
|
85
|
|
|
86 def sortFile(self):
|
|
|
87 if self._verbosity > 2:
|
|
|
88 print "%s file %s..." % ("Rewriting" if self._sorted else "Sorting", self._inputFileName)
|
|
|
89 startTime = time.time()
|
|
|
90 fs = FileSorter(self._parser, self._verbosity-4)
|
|
|
91 fs.setPresorted(self._sorted)
|
|
|
92 fs.perChromosome(True)
|
|
|
93 fs.setOutputFileName(self._sortedFileNames)
|
|
|
94 fs.sort()
|
|
|
95 self._splittedFileNames = fs.getOutputFileNames()
|
|
|
96 self._nbElementsPerChromosome = fs.getNbElementsPerChromosome()
|
|
|
97 self._nbElements = fs.getNbElements()
|
|
|
98 endTime = time.time()
|
|
|
99 if self._verbosity > 2:
|
|
|
100 print " ...done (%ds)" % (endTime - startTime)
|
|
|
101
|
|
|
102 def createNCLists(self):
|
|
|
103 self._ncLists = {}
|
|
|
104 if self._verbosity > 2:
|
|
|
105 print "Creating NC-list for %s..." % (self._inputFileName)
|
|
|
106 startTime = time.time()
|
|
|
107 for chromosome, fileName in self._splittedFileNames.iteritems():
|
|
|
108 if self._verbosity > 3:
|
|
|
109 print " chromosome %s" % (chromosome)
|
|
|
110 ncList = NCList(self._verbosity)
|
|
|
111 if self._index:
|
|
|
112 ncList.createIndex(True)
|
|
|
113 ncList.setChromosome(chromosome)
|
|
|
114 ncList.setFileName(fileName)
|
|
|
115 ncList.setNbElements(self._nbElementsPerChromosome[chromosome])
|
|
|
116 ncList.buildLists()
|
|
|
117 self._ncLists[chromosome] = ncList
|
|
|
118 endTime = time.time()
|
|
|
119 if self._verbosity > 2:
|
|
|
120 print " ...done (%ds)" % (endTime - startTime)
|
|
|
121
|
|
|
122 def writeOutputFile(self):
|
|
|
123 merger = NCListMerger(self._verbosity)
|
|
|
124 merger.setFileName(self._outputFileName)
|
|
|
125 merger.addIndex(self._index)
|
|
|
126 merger.setNCLists(self._ncLists)
|
|
|
127 merger.merge()
|
|
|
128
|
|
|
129 def cleanFiles(self):
|
|
|
130 shutil.rmtree(self._directory)
|
|
|
131
|
|
|
132 def run(self):
|
|
|
133 self.sortFile()
|
|
|
134 self.createNCLists()
|
|
|
135 self.writeOutputFile()
|
|
|
136 self.cleanFiles()
|
|
|
137
|
|
|
138 def getSortedFileNames(self):
|
|
|
139 return self._splittedFileNames
|
|
|
140
|
|
|
141 def getNbElements(self):
|
|
|
142 return self._nbElements
|
|
|
143
|
|
|
144 def getNbElementsPerChromosome(self):
|
|
|
145 return self._nbElementsPerChromosome
|
|
|
146
|
|
|
147 def getNCLists(self):
|
|
|
148 return self._ncLists
|
|
|
149
|
|
|
150 def getTmpDirectory(self):
|
|
|
151 return self._directory
|
|
|
152
|
|
|
153
|
|
|
154 if __name__ == "__main__":
|
|
|
155 description = "Convert To NC-List v1.0.0: Convert a mapping or transcript file into a NC-List. [Category: NC-List]"
|
|
|
156
|
|
|
157 parser = OptionParser(description = description)
|
|
|
158 parser.add_option("-i", "--input", dest="inputFileName", action="store", type="string", help="Query input file [compulsory] [format: file in transcript format given by -f]")
|
|
|
159 parser.add_option("-f", "--format", dest="format", action="store", type="string", help="format of previous file [compulsory] [format: transcript file format]")
|
|
|
160 parser.add_option("-d", "--index", dest="index", action="store_true", default=False, help="create an index [default: false] [format: boolean]")
|
|
|
161 parser.add_option("-o", "--output", dest="outputFileName", action="store", type="string", help="Output file [compulsory] [format: output file in NCList format]")
|
|
|
162 parser.add_option("-s", "--sorted", dest="sorted", action="store_true", default=False, help="input file is already sorted [format: boolean] [default: False]")
|
|
|
163 parser.add_option("-v", "--verbosity", dest="verbosity", action="store", default=1, type="int", help="Trace level [format: int] [default: 1]")
|
|
|
164 (options, args) = parser.parse_args()
|
|
|
165
|
|
|
166 ctncl = ConvertToNCList(options.verbosity)
|
|
|
167 ctncl.setInputFileName(options.inputFileName, options.format)
|
|
|
168 ctncl.setOutputFileName(options.outputFileName)
|
|
|
169 ctncl.setIndex(options.index)
|
|
|
170 ctncl.setSorted(options.sorted)
|
|
|
171 ctncl.run()
|
|
|
172
|
