-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathfileread.py
561 lines (535 loc) · 26.4 KB
/
fileread.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from read import *
from cluster import *
from samfunction import *
from maxlike import *
path = "C:/Users/Administrator/Desktop/inpostxt/MSI_4/RealData/"
class fileRead:
def __init__(self):
self.counter = 0
self.doubleset = dict()
self.oneset = dict()
self.twoset = dict()
self.bklist = dict()
self.unitdic = None
self.bk = None
self.repetelist = dict()
self.lenhooklist = dict()
self.snplist= dict()
def classifyMSI(self, filename):
filename.seek(0)
unit = []
while True:
line1 = filename.readline()
if not line1: break
line2 = filename.readline().strip() #strip
line1_list = line1.split('\t')
line2_list = line2.split('\t')
readseq1 = line1_list[9].upper()
readseq2 = line2_list[9].upper()
pairedread = pairedRead(line1_list[0], line1_list[1], line1_list[2], line1_list[3], line1_list[4],
line1_list[5], line1_list[6], line1_list[7], line1_list[8], readseq1, \
line2_list[0], line2_list[1], line2_list[2], line2_list[3], line2_list[4],
line2_list[5], line2_list[6], line2_list[7], line2_list[8], readseq2)
if pairedread.read1.isRepete() and pairedread.read2.isRepete():
r = pairedread.read1.isRepete()
unit.append(r[1])
msilist = [unit[0]]
for i in range(1, len(unit)):
if unitindex(unit[i], msilist) is False:
msilist.append(unit[i])
return msilist
def countMSI(self, filename):
filename.seek(0)
counter1 = 0
while True:
line = filename.readline()
if not line: break
line_list = line.split('\t')
readseq = line_list[9].upper()
read = Read(line_list[0], line_list[1], line_list[2], line_list[3], line_list[4], line_list[5],
line_list[6], line_list[7], line_list[8], readseq)
if read.isRepete():
self.counter += 1
continue
else:
counter1 += 1
continue
return self.counter, counter1
def countdoubleMSI(self, filename):
filename.seek(0)
counter0 = counter1 = counter2 = counter3 = 0
while True:
line1 = filename.readline()
if not line1: break
line2 = filename.readline().strip()
line1_list = line1.split('\t')
line2_list = line2.split('\t')
readseq1 = line1_list[9].upper()
readseq2 = line2_list[9].upper()
pairedread = pairedRead(line1_list[0], line1_list[1], line1_list[2], line1_list[3], line1_list[4],
line1_list[5], line1_list[6], line1_list[7], line1_list[8], readseq1, \
line2_list[0], line2_list[1], line2_list[2], line2_list[3], line2_list[4],
line2_list[5], line2_list[6], line2_list[7], line2_list[8], readseq2)
if int(pairedread.classify()) == 3:
counter3 += 1
continue
if int(pairedread.classify()) == 2:
counter2 += 1
continue
if int(pairedread.classify()) == 1:
counter1 += 1
continue
if int(pairedread.classify()) == 0:
counter0 += 1
continue
return counter3, counter2, counter1, counter0
def countrpt(self, filename):
num1, num2, num3, num4 = self.countdoubleMSI(filename)
return num1 * 2 + num2 + num3
def countsum(self, filename):
filename.seek(0)
num1, num2, num3, num4 = self.countdoubleMSI(filename)
return (num1 + num2 + num3 + num4) * 2
def getset(self):
return self.doubleset, self.oneset, self.twoset
def getalnone(self, file_in, file_out, file_out1):
file_in.seek(0)
counter1 = counter2 = 0
while True:
line1 = file_in.readline()
if not line1: break
line2 = file_in.readline().strip()
line1_list = line1.split('\t')
line2_list = line2.split('\t')
readseq1 = line1_list[9].upper()
readseq2 = line2_list[9].upper()
pairedread = pairedRead(line1_list[0], line1_list[1], line1_list[2], line1_list[3], line1_list[4],
line1_list[5], line1_list[6], line1_list[7], line1_list[8], readseq1, \
line2_list[0], line2_list[1], line2_list[2], line2_list[3], line2_list[4],
line2_list[5], line2_list[6], line2_list[7], line2_list[8], readseq2)
if (str(pairedread.read1.CIGAR) == '100M' and str(pairedread.read2.CIGAR) != '100M' and str(
pairedread.read2.CIGAR) != '*') \
or (str(pairedread.read1.CIGAR) != '100M' and str(pairedread.read1.CIGAR) != '*' and str(
pairedread.read2.CIGAR) == '100M'):
print >> file_out, pairedread.printinf()
counter1 += 1
if (str(pairedread.read1.CIGAR) == '100M' and str(pairedread.read2.CIGAR) == '*') or \
(str(pairedread.read1.CIGAR) == '*' and str(pairedread.read2.CIGAR) == '100M'):
print >> file_out1, '*', pairedread.printinf()
counter2 += 1
return counter1, counter2
def getdoublealn(self, file_in, file_out):
file_in.seek(0)
counter = 0
while True:
line1 = file_in.readline()
if not line1: break
line2 = file_in.readline().strip()
line1_list = line1.split('\t')
line2_list = line2.split('\t')
readseq1 = line1_list[9].upper()
readseq2 = line2_list[9].upper()
pairedread = pairedRead(line1_list[0], line1_list[1], line1_list[2], line1_list[3], line1_list[4],
line1_list[5], line1_list[6], line1_list[7], line1_list[8], readseq1, \
line2_list[0], line2_list[1], line2_list[2], line2_list[3], line2_list[4],
line2_list[5], line2_list[6], line2_list[7], line2_list[8], readseq2)
if (str(pairedread.read1.CIGAR) == str(pairedread.read2.CIGAR) == '100M'):
print >> file_out, pairedread.printinf()
counter += 1
return counter
def searchBK(self, file_in, lmsi):
file_in.seek(0)
candidate = []
while True:
line1 = file_in.readline()
if not line1: break
line2 = file_in.readline().strip()
line1_list = line1.split('\t')
line2_list = line2.split('\t')
readseq1 = line1_list[9].upper()
readseq2 = line2_list[9].upper()
pairedread = pairedRead(line1_list[0], line1_list[1], line1_list[2], line1_list[3], line1_list[4],
line1_list[5], line1_list[6], line1_list[7], line1_list[8], readseq1, \
line2_list[0], line2_list[1], line2_list[2], line2_list[3], line2_list[4],
line2_list[5], line2_list[6], line2_list[7], line2_list[8], readseq2)
if (pairedread.read1.CIGAR == '100M' and pairedread.read2.CIGAR != '100M' and pairedread.read2.isRepete() is False
and (int(pairedread.read1.POS) < int(pairedread.read2.POS))):
bkun = pairedread.read2.getbkunit()
if bkun[0] and bkun[1]:
candidate.append(bkun)
cpos = cluster(candidate, 100, 0)
print len(cpos)
pos = []
for i in range(len(cpos)):
pos.append(cpos[i][0])
return pos
def searchHook(self, file_in):
file_in.seek(0)
len_hook = 0
while True:
line1 = file_in.readline()
if not line1: break
line2 = file_in.readline().strip()
line1_list = line1.split('\t')
line2_list = line2.split('\t')
if len(line1_list) > 10 and len(line2_list) > 10:
readseq1 = line1_list[9].upper()
readseq2 = line2_list[9].upper()
pairedread = pairedRead(line1_list[0], line1_list[1], line1_list[2], line1_list[3], line1_list[4],
line1_list[5], line1_list[6], line1_list[7], line1_list[8], readseq1, \
line2_list[0], line2_list[1], line2_list[2], line2_list[3], line2_list[4],
line2_list[5], line2_list[6], line2_list[7], line2_list[8], readseq2)
if (pairedread.read1.CIGAR == '100M' and pairedread.read2.CIGAR != '100M' and not pairedread.read2.isRepete()):
len_hook += pairedread.read2.getlefthook()
continue
if (pairedread.read1.CIGAR != '100M' and not pairedread.read1.isRepete() and pairedread.read2.CIGAR == '100M'):
len_hook += pairedread.read1.getlefthook()
continue
return len_hook
def searchHook1(self, file_in):
file_in.seek(0)
len_hook1 = 0
while True:
line1 = file_in.readline()
if not line1: break
line2 = file_in.readline().strip()
line1_list = line1.split('\t')
line2_list = line2.split('\t')
readseq1 = line1_list[9].upper()
readseq2 = line2_list[9].upper()
pairedread = pairedRead(line1_list[0], line1_list[1], line1_list[2], line1_list[3], line1_list[4],
line1_list[5], line1_list[6], line1_list[7], line1_list[8], readseq1, \
line2_list[0], line2_list[1], line2_list[2], line2_list[3], line2_list[4],
line2_list[5], line2_list[6], line2_list[7], line2_list[8], readseq2)
if (pairedread.read1.isRepete() and pairedread.read2.CIGAR != '100M' and not pairedread.read2.isRepete()):
len_hook1 += pairedread.read2.getlefthook()
continue
elif (pairedread.read1.CIGAR != '100M' and not pairedread.read1.isRepete() and pairedread.read2.isRepete()):
len_hook1 += pairedread.read1.getlefthook()
continue
return len_hook1
def searchHook2(self, file_in):
file_in.seek(0)
len_hook2 = 0
while True:
line1 = file_in.readline()
if not line1: break
line2 = file_in.readline().strip()
line1_list = line1.split('\t')
line2_list = line2.split('\t')
readseq1 = line1_list[9].upper()
readseq2 = line2_list[9].upper()
pairedread = pairedRead(line1_list[0], line1_list[1], line1_list[2], line1_list[3], line1_list[4],
line1_list[5], line1_list[6], line1_list[7], line1_list[8], readseq1, \
line2_list[0], line2_list[1], line2_list[2], line2_list[3], line2_list[4],
line2_list[5], line2_list[6], line2_list[7], line2_list[8], readseq2)
if (pairedread.read1.CIGAR != '100M' and pairedread.read2.CIGAR != '100M'):
len_hook2 += pairedread.read1.getlefthook()
len_hook2 += pairedread.read2.getlefthook()
continue
return len_hook2
def getlenhook(self, file_in):
le1 = self.searchHook(file_in)
le2 = self.searchHook1(file_in)
le3 = self.searchHook2(file_in)
return le1 + le2 + le3
def countreads(self, file_in):
file_in.seek(0)
counter = 0
for line in file_in:
counter += 1
return counter
def searchHook3(self, file_in):
file_in.seek(0)
len_hook = 0
while True:
line1 = file_in.readline()
if not line1: break
line2 = file_in.readline().strip()
line1_list = line1.split('\t')
line2_list = line2.split('\t')
readseq1 = line1_list[9].upper()
readseq2 = line2_list[9].upper()
pairedread = pairedRead(line1_list[0], line1_list[1], line1_list[2], line1_list[3], line1_list[4],
line1_list[5], line1_list[6], line1_list[7], line1_list[8], readseq1, \
line2_list[0], line2_list[1], line2_list[2], line2_list[3], line2_list[4],
line2_list[5], line2_list[6], line2_list[7], line2_list[8], readseq2)
if (pairedread.read1.CIGAR == '100M' and pairedread.read2.CIGAR != '100M' and not pairedread.read2.isRepete()):
len_hook = pairedread.read2.getlefthook()
break
if (pairedread.read1.CIGAR != '100M' and not pairedread.read1.isRepete() and pairedread.read2.CIGAR == '100M'):
len_hook = pairedread.read1.getlefthook()
break
return len_hook
def searchHook4(self, file_in):
file_in.seek(0)
len_hook1 = 0
while True:
line1 = file_in.readline()
if not line1: break
line2 = file_in.readline().strip()
line1_list = line1.split('\t')
line2_list = line2.split('\t')
readseq1 = line1_list[9].upper()
readseq2 = line2_list[9].upper()
pairedread = pairedRead(line1_list[0], line1_list[1], line1_list[2], line1_list[3], line1_list[4],
line1_list[5], line1_list[6], line1_list[7], line1_list[8], readseq1, \
line2_list[0], line2_list[1], line2_list[2], line2_list[3], line2_list[4],
line2_list[5], line2_list[6], line2_list[7], line2_list[8], readseq2)
if (pairedread.read1.isRepete() and pairedread.read2.CIGAR != '100M' and not pairedread.read2.isRepete()):
len_hook1 = pairedread.read2.getlefthook()
break
if (pairedread.read1.CIGAR != '100M' and not pairedread.read1.isRepete() and pairedread.read2.isRepete()):
len_hook1 = pairedread.read1.getlefthook()
break
return len_hook1
def getlenhook1(self, file_in):
le1 = self.searchHook3(file_in)
le2 = self.searchHook4(file_in)
return le1 + le2
def countCS(self, filename, msi_list):
# c = self.classifyMSI(filename)
filename.seek(0)
msl = [[] for i in range(len(msi_list))]
for i in range(len(msi_list)):
msl[i].append(msi_list[i])
msl[i].append(0)
while True:
line1 = filename.readline()
if not line1: break
line2 = filename.readline().strip()
line1_list = line1.split('\t')
line2_list = line2.split('\t')
readseq1 = line1_list[9].upper()
readseq2 = line2_list[9].upper()
pairedread = pairedRead(line1_list[0], line1_list[1], line1_list[2], line1_list[3], line1_list[4],
line1_list[5], line1_list[6], line1_list[7], line1_list[8], readseq1, \
line2_list[0], line2_list[1], line2_list[2], line2_list[3], line2_list[4],
line2_list[5], line2_list[6], line2_list[7], line2_list[8], readseq2)
if pairedread.read1.isRepete() and pairedread.read2.isRepete():
ms = pairedread.read1.isRepete()[1]
id = unitindex(ms, msi_list)
if type(id) is int:
msl[id][1] += 2
elif pairedread.read1.isRepete():
ms = pairedread.read1.isRepete()[1]
id = unitindex(ms, msi_list)
if type(id) is int:
msl[id][1] += 1
elif pairedread.read2.isRepete():
ms = pairedread.read2.isRepete()[1]
id = unitindex(ms, msi_list)
if type(id) is int:
msl[id][1] += 1
else:
continue
return msl
def ratioMS(self, filename, msi_list):
l = self.countCS(filename, msi_list)
print l
nl = []
for i in range(len(l)):
nl.append(l[i][1])
s = float(min(nl))
sl = []
for i in range(len(nl)):
sl.append(nl[i] / s)
rl = []
for i in range(len(l)):
rl.append((l[i][0], sl[i]))
return rl
def printrpt_read(self,file_in):
file_in.seek(0)
f_out = open("C:\\Users\\Administrator\\Desktop\\rpt1.txt",'w')
while True:
line1 = file_in.readline()
if not line1: break
line2 = file_in.readline().strip()
line1_list = line1.split('\t')
line2_list = line2.split('\t')
readseq1 = line1_list[9].upper()
readseq2 = line2_list[9].upper()
pairedread = pairedRead(line1_list[0], line1_list[1], line1_list[2], line1_list[3], line1_list[4],
line1_list[5], line1_list[6], line1_list[7], line1_list[8], readseq1, \
line2_list[0], line2_list[1], line2_list[2], line2_list[3], line2_list[4],
line2_list[5], line2_list[6], line2_list[7], line2_list[8], readseq2)
if int(pairedread.classify()) == 2:
print >>f_out,pairedread.read1.FLAG,':',pairedread.read1.SEQ,'\n',pairedread.read2.FLAG,':',pairedread.read2.SEQ,'\n','!!!!!!!!'
f_out.close()
def bk_unit(self,file_in):
print "Geting_breakpoint&unit>>>>>>>>>>>>>>>>>>>>>>>"
file_in.seek(0)
bklist = []
while True:
line1 = file_in.readline()
if not line1: break
line2 = file_in.readline().strip()
line1_list = line1.split('\t')
line2_list = line2.split('\t')
readseq1 = line1_list[9].upper()
readseq2 = line2_list[9].upper()
pairedread = pairedRead(line1_list[0], line1_list[1], line1_list[2], line1_list[3], line1_list[4],
line1_list[5], line1_list[6], line1_list[7], line1_list[8], readseq1, \
line2_list[0], line2_list[1], line2_list[2], line2_list[3], line2_list[4],
line2_list[5], line2_list[6], line2_list[7], line2_list[8], readseq2)
'''readlen1 = len(pairedread.read1.SEQ)
readlen2 = len(pairedread.read2.SEQ)
if pairedread.read1.CIGAR == str(readlen1) + "M" and pairedread.read2.CIGAR != str(readlen2) + "M" and \
pairedread.read2.CIGAR != "*" and int(pairedread.read1.POS) < int(pairedread.read2.POS):
# if pairedread.read1.verify(ref) and pairedread.read2.getmsiunit():
if pairedread.read2.getmsiunit()[0]:
bkun = pairedread.read2.getbkunit()
bklist.append(bkun)
elif pairedread.read2.CIGAR == str(readlen2) + "M" and pairedread.read1.CIGAR != str(readlen1) + "M" and \
pairedread.read1.CIGAR != "*" and int(pairedread.read2.POS) < int(pairedread.read1.POS):
# if pairedread.read2.verify(ref) and pairedread.read1.getmsiunit():
if pairedread.read1.getmsiunit()[0]:
bkun = pairedread.read1.getbkunit()
bklist.append(bkun)
else:
continue'''
if pairedread.read1.isMap() and not pairedread.read2.isMap() and pairedread.read2.CIGAR != "*" and \
int(pairedread.read1.POS) < int(pairedread.read2.POS) and pairedread.read2.getmsiunit()[0]:
bkun = pairedread.read2.getbkunit()
bklist.append(bkun)
elif not pairedread.read1.isMap() and pairedread.read1.CIGAR != "*"and pairedread.read2.isMap() and \
int(pairedread.read2.POS) < int(pairedread.read1.POS) and pairedread.read1.getmsiunit()[0]:
bkun = pairedread.read1.getbkunit()
bklist.append(bkun)
else:
continue
rebu = cluster(bklist,30,1,alpha=0.1)
keys = []
bklist =[]
for r in rebu:
bklist.append(r[0])
self.bklist = dict(bklist)
self.unitdic = list(self.bklist.keys())
return self.bklist,self.unitdic
def get_hook(self,file_in):
file_in.seek(0)
lenhooklist = {}
repetelist = {}
SNPlist = {}
unitlist = []
if self.unitdic is None:
unitlist = self.bk_unit(file_in)[1]
elif self.unitdic == []:
return
else:
unitlist = self.unitdic
#print unitlist
lenhooklist = lenhooklist.fromkeys(unitlist,0)
repetelist = repetelist.fromkeys(unitlist,0)
SNPlist = SNPlist.fromkeys(unitlist,'')
while True:
line1 = file_in.readline()
if not line1: break
line2 = file_in.readline().strip()
line1_list = line1.split('\t')
line2_list = line2.split('\t')
readseq1 = line1_list[9].upper()
readseq2 = line2_list[9].upper()
pairedread = pairedRead(line1_list[0], line1_list[1], line1_list[2], line1_list[3], line1_list[4],
line1_list[5], line1_list[6], line1_list[7], line1_list[8], readseq1, \
line2_list[0], line2_list[1], line2_list[2], line2_list[3], line2_list[4],
line2_list[5], line2_list[6], line2_list[7], line2_list[8], readseq2)
if not pairedread.read1.isMap():
unit , flag = pairedread.read1.getmsiunit()
if unit and flag != 0 and pairedread.read1.isRepete(unit,flag):
key = unitfromlist(unit,unitlist)
if key:
repetelist[key] += 1
SNP=findSNP(unit,readseq1)
if SNP and not SNPlist[key]:
SNPlist[key]=SNP
if unit and flag != 0 and not pairedread.read1.isRepete(unit,flag):
key = unitfromlist(unit, unitlist)
if key:
lenhook = pairedread.read1.getlefthook(unit, flag)
lenhooklist[key] += lenhook
SNP=findSNP(unit,readseq1[len(readseq1)-lenhook+len(unit):len(readseq1)])
if SNP and not SNPlist[key]:
SNPlist[key]=SNP
if not pairedread.read2.isMap():
unit , flag = pairedread.read2.getmsiunit()
if unit and flag != 0 and pairedread.read2.isRepete(unit,flag):
key = unitfromlist(unit,unitlist)
if key:
repetelist[key] += 1
SNP=findSNP(unit,readseq2)
if SNP and not SNPlist[key]:
SNPlist[key]=SNP
if unit and flag != 0 and not pairedread.read2.isRepete(unit,flag):
key = unitfromlist(unit, unitlist)
if key:
lenhook = pairedread.read2.getlefthook(unit, flag)
lenhooklist[key] += lenhook
SNP=findSNP(unit,readseq2[len(readseq2)-lenhook+len(unit):len(readseq2)])
if SNP and not SNPlist[key]:
SNPlist[key]=SNP
assert (len(lenhooklist) == len(repetelist))
delkey = []
for key in lenhooklist:
if lenhooklist[key] == 0 and repetelist[key] == 0:
delkey.append(key)
for key in delkey:
del lenhooklist[key]
del repetelist[key]
del SNPlist[key]
del self.bklist[key]
self.lenhooklist = lenhooklist
self.repetelist = repetelist
self.SNPlist=SNPlist
self.bk = self.bklist.values()
return self.lenhooklist,self.repetelist,self.bk,self.SNPlist
def read_count(self,file_in, poslist):
posdic = dict()
for key in poslist:
posdic[key] = [0]*ITIE_TIME
length = REF_INIT
for i in range(ITIE_TIME):
file_in.seek(0)
while True:
line = file_in.readline()
if not line: break
line_list = line.split('\t')
readseq = line_list[9].upper()
read = Read(line_list[0], line_list[1], line_list[2], line_list[3], line_list[4], line_list[5],line_list[6],
line_list[7], line_list[8], readseq)
readlen = len(readseq)
pos = int(read.getpos())
for p in poslist:
if (p- length / 2 - readlen) < pos < (p + length / 2 - readlen):
posdic[p][i] +=1
length = length + REF_PLUS
return posdic
if __name__ == "__main__":
file1 = sys.argv[1]
file2 = sys.argv[2]
#f = open(path +raw_input("Enter the filename:") , 'rU')
f = open(path+file1,'rU')
f_out = open(path+file2,'w')
fr = fileRead()
#fr.printrpt_read(f)
bklist,unitlist=fr.bk_unit(f)
lenhooklist,repetelist,bk=fr.get_hook(f)
#f_out = open(path +raw_input("Enter the out filename:"), 'w')
print len(bklist)
print >>f_out,'bklist:',bklist
print len(unitlist)
print >>f_out,'unitlist:',unitlist
print >>f_out,"lenhooklist:",lenhooklist
print len(lenhooklist)
print >>f_out,"repetelist:",repetelist
print len(repetelist)
print len(bk)
f_out.close()
posdic = fr.read_count(f,bk)
rdic = cal_nor(bklist,posdic,lenhooklist,repetelist)
print >> f_out, "rdic", rdic
f_out.close()
f.close()
print "OK"