| 1 |
=== Here I was asked to make a report of the relates to but using priority tags ===
|
| 2 |
== First I take the priority scale that they gave me into a dict ==
|
| 3 |
contents = open(r"C:\Users\eborges\Box Sync\Client\Honeywell\Perligo\Project_RelatesTo_Priority\Group A\GroupA_pri.txt").readlines()
|
| 4 |
>>> priMatrix = {}
|
| 5 |
>>> for line in contents:
|
| 6 |
... line = line.replace("\n","")
|
| 7 |
... line = line.split("*")
|
| 8 |
... pri = line[0]
|
| 9 |
... tag = line[2]
|
| 10 |
... tag = tag.replace(" ","")
|
| 11 |
... tag = tag.upper()
|
| 12 |
... if pri in priMatrix.keys():
|
| 13 |
... priMatrix[pri].append(tag)
|
| 14 |
... else:
|
| 15 |
... priMatrix[pri] = [tag,]
|
| 16 |
...
|
| 17 |
== Then I parse the export from the db ==
|
| 18 |
>>> contents = open(r"C:\Users\eborges\Box Sync\Client\Honeywell\Perligo\Project_RelatesTo_Priority\Group A\export_20140926_163727.dat").readlines()
|
| 19 |
>>> head = contents[0]
|
| 20 |
>>> head = head.replace("\n","")
|
| 21 |
>>> contents = contents[1:]
|
| 22 |
>>> head = head.split("|")
|
| 23 |
>>> head = head[1:]
|
| 24 |
>>> dbMatrix = {}
|
| 25 |
>>> for line in contents:
|
| 26 |
... line = line.replace("\n","")
|
| 27 |
... line = line.split("|")
|
| 28 |
... entries = line[1:]
|
| 29 |
... count = 0
|
| 30 |
... finalList = []
|
| 31 |
... for i in entries:
|
| 32 |
... if i:
|
| 33 |
... if ";" in i:
|
| 34 |
... i = i.split(";")
|
| 35 |
... else:
|
| 36 |
... i = [i,]
|
| 37 |
... for x in i:
|
| 38 |
... x = head[count] + "|" + x
|
| 39 |
... x = x.replace(" ","")
|
| 40 |
... x = x.upper()
|
| 41 |
... finalList.append(x)
|
| 42 |
... count = count +1
|
| 43 |
... dbMatrix[line[0]] = list(finalList)
|
| 44 |
...
|
| 45 |
== Now unpack ==
|
| 46 |
>>> tallyMatrix = {}
|
| 47 |
>>> for i in priMatrix.keys():
|
| 48 |
... tallyMatrix[i] = []
|
| 49 |
|
| 50 |
for bates in dbMatrix.keys():
|
| 51 |
... for entry in dbMatrix[bates]:
|
| 52 |
... if entry in priMatrix['A1']:
|
| 53 |
... if entry in tallyMatrix['A1']:
|
| 54 |
... pass
|
| 55 |
... else:
|
| 56 |
... tallyMatrix['A1'].append(bates)
|
| 57 |
... elif entry in priMatrix['A2']:
|
| 58 |
... if entry in tallyMatrix['A2']:
|
| 59 |
... pass
|
| 60 |
... else:
|
| 61 |
... tallyMatrix['A2'].append(bates)
|
| 62 |
... elif entry in priMatrix['A3']:
|
| 63 |
... if entry in tallyMatrix['A3']:
|
| 64 |
... pass
|
| 65 |
... else:
|
| 66 |
... tallyMatrix['A3'].append(bates)
|
| 67 |
... elif entry in priMatrix['A4']:
|
| 68 |
... if entry in tallyMatrix['A4']:
|
| 69 |
... pass
|
| 70 |
... else:
|
| 71 |
... tallyMatrix['A4'].append(bates)
|
| 72 |
... elif entry in priMatrix['A5']:
|
| 73 |
... if entry in tallyMatrix['A5']:
|
| 74 |
... pass
|
| 75 |
... else:
|
| 76 |
... tallyMatrix['A5'].append(bates)
|
| 77 |
... elif entry in priMatrix['A6']:
|
| 78 |
... if entry in tallyMatrix['A6']:
|
| 79 |
... pass
|
| 80 |
... else:
|
| 81 |
... tallyMatrix['A6'].append(bates)
|
| 82 |
... elif entry in priMatrix['A7']:
|
| 83 |
... if entry in tallyMatrix['A7']:
|
| 84 |
... pass
|
| 85 |
... else:
|
| 86 |
... tallyMatrix['A7'].append(bates)
|
| 87 |
... elif entry in priMatrix['A8']:
|
| 88 |
... if entry in tallyMatrix['A8']:
|
| 89 |
... pass
|
| 90 |
... else:
|
| 91 |
... tallyMatrix['A8'].append(bates)
|
| 92 |
... elif entry in priMatrix['A9']:
|
| 93 |
... if entry in tallyMatrix['A9']:
|
| 94 |
... pass
|
| 95 |
... else:
|
| 96 |
... tallyMatrix['A9'].append(bates)
|
| 97 |
|
| 98 |
## But remember there will be dups. 1 document will exist in multiple A's
|
| 99 |
|
| 100 |
>>> len(tallyMatrix['A1'])
|
| 101 |
103
|
| 102 |
>>> len(tallyMatrix['A2'])
|
| 103 |
51
|
| 104 |
>>> len(tallyMatrix['A3'])
|
| 105 |
126
|
| 106 |
>>> len(tallyMatrix['A4'])
|
| 107 |
230
|
| 108 |
>>> len(tallyMatrix['A5'])
|
| 109 |
6020
|
| 110 |
>>> len(tallyMatrix['A6'])
|
| 111 |
9458
|
| 112 |
>>> len(tallyMatrix['A7'])
|
| 113 |
3555
|
| 114 |
>>>
|
| 115 |
|
| 116 |
== So now we write to file but removing dups ==
|
| 117 |
>>> outputFile = open(r"C:\Users\eborges\Box Sync\Client\Honeywell\Perligo\Project_RelatesTo_Priority\Group A\overlay.dat",'w')
|
| 118 |
>>> outputFile.write("Bates|Level 1 Review Coding Consolidated\n")
|
| 119 |
>>> a1List = []
|
| 120 |
>>> a2List = []
|
| 121 |
>>> a3List = []
|
| 122 |
>>> a4List = []
|
| 123 |
>>> a5List = []
|
| 124 |
>>> a6List = []
|
| 125 |
>>> a7List = []
|
| 126 |
>>> a8List = []
|
| 127 |
>>> a9List = []
|
| 128 |
>>> totList = []
|
| 129 |
>>> sets = priMatrix.keys()
|
| 130 |
>>> sets.sort()
|
| 131 |
>>> aLists = [a1List,a2List,a3List,a4List,a5List,a6List,a7List,a8List,a9List]
|
| 132 |
>>> count = 0
|
| 133 |
## This only works because I go in order.
|
| 134 |
>>> for a in sets:
|
| 135 |
... for bates in tallyMatrix[a]:
|
| 136 |
... if bates in totList:
|
| 137 |
... pass
|
| 138 |
... else:
|
| 139 |
... outputFile.write("%s|%s\n"%(bates,a))
|
| 140 |
... totList.append(bates)
|
| 141 |
... aLists[count].append(bates)
|
| 142 |
... count = count +1
|
| 143 |
...
|
| 144 |
>>> outputFile.close()
|
| 145 |
>>> len(a1List)
|
| 146 |
103
|
| 147 |
>>> len(a2List)
|
| 148 |
51
|
| 149 |
>>> len(a3List)
|
| 150 |
126
|
| 151 |
>>> len(a4List)
|
| 152 |
230
|
| 153 |
>>> len(a5List)
|
| 154 |
6020
|
| 155 |
>>> len(a6List)
|
| 156 |
8863
|
| 157 |
>>> len(a7List)
|
| 158 |
3115
|
| 159 |
>>> len(totList)
|
| 160 |
18508
|
| 161 |
>>>
|
| 162 |
|
| 163 |
|
| 164 |
=== END ===
|
| 165 |
=== Here I was asked to get a report of documents that contain X tags ===
|
| 166 |
>>> contents = open(r"\\BSTDD967DTW1\Users\eborges\Box Sync\Client\Honeywell\Perligo\Project_RelatesTo\export_2.dat").readlines()
|
| 167 |
>>> contents = contents[1:]
|
| 168 |
>>> contents[0]
|
| 169 |
'HWHC000000001||||Livonia, MI|Invoice/Purchase order|||||Document retention (policies/compliance)|\n'
|
| 170 |
>>> matrix = {}
|
| 171 |
>>> for line in contents:
|
| 172 |
... line = line.replace("\n","")
|
| 173 |
... line = line.split("|")
|
| 174 |
... bates = line[0]
|
| 175 |
... parts = line[1:]
|
| 176 |
... countList = []
|
| 177 |
... for i in parts:
|
| 178 |
... if i:
|
| 179 |
... i = i.split(";")
|
| 180 |
... for x in i:
|
| 181 |
... countList.append(x)
|
| 182 |
... if len(countList) in matrix.keys():
|
| 183 |
... matrix[len(countList)].append(bates)
|
| 184 |
... else:
|
| 185 |
... matrix[len(countList)] = [bates,]
|
| 186 |
...
|
| 187 |
>>> outputFile = open(r"\\BSTDD967DTW1\Users\eborges\Box Sync\Client\Honeywell\Perligo\Project_RelatesTo\relatesToReport.txt",'w')
|
| 188 |
>>> for i in matrix.keys():
|
| 189 |
... outputFile.write("%s documents have %s tags.\n"% (len(matrix[i]),i))
|
| 190 |
...
|
| 191 |
>>> outputFile.close()
|
| 192 |
=== END ===
|
| 193 |
|
| 194 |
=== Here I was asked to do a 5 before and 5 after field and at first only for docs without famiies ===
|
| 195 |
== first I removed documents with families from the entire uni ==
|
| 196 |
>>> contents = open(r"w:\manny\client\honeywell\perligo\5Before_5After_Proj\export.csv").readlines()
|
| 197 |
>>> outputFile = open(r"w:\manny\client\honeywell\perligo\5Before_5After_Proj\StandAloneOnly.dat",'w')
|
| 198 |
>>> for line in contents:
|
| 199 |
... newline = line.replace("\n","")
|
| 200 |
... newline = newline.split(",")
|
| 201 |
... err = False
|
| 202 |
... if newline[0] == newline [2]:
|
| 203 |
... err = True
|
| 204 |
... if newline[1] == newline[3]:
|
| 205 |
... err = True
|
| 206 |
... if newline[2] == "":
|
| 207 |
... err = True
|
| 208 |
... if err == True:
|
| 209 |
... outputFile.write(line)
|
| 210 |
|
| 211 |
== then to make a packed matrix ==
|
| 212 |
=first back buffer=
|
| 213 |
>>> contents = open(r"w:\manny\client\honeywell\perligo\5Before_5After_Proj\StandAloneOnly.dat").readlines()
|
| 214 |
>>> outputFile = open(r"w:\manny\client\honeywell\perligo\5Before_5After_Proj\ShiftedOverlay.dat",'w')
|
| 215 |
>>> befBuffer = []
|
| 216 |
>>> befMatrix = {}
|
| 217 |
>>> for line in contents:
|
| 218 |
... line = line.replace("\n","")
|
| 219 |
... begNo = line.split(",")[0]
|
| 220 |
... befBuffer.append(begNo)
|
| 221 |
... if len(befBuffer) > 6:
|
| 222 |
... nul = befBuffer.pop(0)
|
| 223 |
... befMatrix[begNo] = list(befBuffer)
|
| 224 |
|
| 225 |
= then reversing for the after buffer=
|
| 226 |
>>> contents.reverse()
|
| 227 |
>>> aftMatrix = {}
|
| 228 |
>>> aftBuffer = []
|
| 229 |
>>> for line in contents:
|
| 230 |
... line = line.replace("\n","")
|
| 231 |
... begNo = line.split(",")[0]
|
| 232 |
... aftBuffer.append(begNo)
|
| 233 |
... if len(aftBuffer) > 6:
|
| 234 |
... nul = aftBuffer.pop(0)
|
| 235 |
... aftMatrix[begNo] = list(aftBuffer)
|
| 236 |
|
| 237 |
== now to unpack and make the final load file ==
|
| 238 |
>>> outputFile = open(r"w:\manny\client\honeywell\perligo\5Before_5After_Proj\ShiftedOverlay.dat",'w')
|
| 239 |
>>> for line in contents:
|
| 240 |
... begno = line.split(",")[0]
|
| 241 |
... outputFile.write("%s|"%begno)
|
| 242 |
... for i in befMatrix[begno]:
|
| 243 |
... outputFile.write("%s;"%i)
|
| 244 |
... count = 1
|
| 245 |
... aftList = aftMatrix[begno]
|
| 246 |
... aftList.remove(begno)
|
| 247 |
... aftList.sort()
|
| 248 |
... for i in aftList:
|
| 249 |
... outputFile.write("%s"%i)
|
| 250 |
... if count < len(aftList):
|
| 251 |
... outputFile.write(";")
|
| 252 |
... count = count +1
|
| 253 |
... outputFile.write("\n")
|
| 254 |
...
|
| 255 |
>>> outputFile.close()
|
| 256 |
=== END ===
|
| 257 |
=== Here I was asked, in prok 199, to compare the page counts of prod vs review and report ===
|
| 258 |
for f in os.listdir(startDir):
|
| 259 |
... outputFile = open(os.path.join(outputDir,os.path.splitext(f)[0]+".txt"),'w')
|
| 260 |
... outputErrFile = open(os.path.join(outputDir,os.path.splitext(f)[0]+".err"),'w')
|
| 261 |
... contents = open(os.path.join(startDir,f)).readlines()
|
| 262 |
... headder = contents[0]
|
| 263 |
... outputFile.write(headder)
|
| 264 |
... outputErrFile.write(headder)
|
| 265 |
... contents = contents[1:]
|
| 266 |
... for line in contents:
|
| 267 |
... line = line.replace("\n","")
|
| 268 |
... prodBeg,prodEnd,beg,end,concordBeg = line.split(",")
|
| 269 |
... if prodBeg:
|
| 270 |
... pass
|
| 271 |
... else:
|
| 272 |
... prodBeg = beg
|
| 273 |
... err = False
|
| 274 |
... if ";" in prodBeg:
|
| 275 |
... err = True
|
| 276 |
... if ";" in prodEnd:
|
| 277 |
... testList = prodEnd.split(";")
|
| 278 |
... if len(testList) == 2:
|
| 279 |
... test1,test2 = prodEnd.split(";")
|
| 280 |
... test1 = test1.strip()
|
| 281 |
... test2 = test2.strip()
|
| 282 |
... if test1:
|
| 283 |
... if test2:
|
| 284 |
... err = True
|
| 285 |
... else:
|
| 286 |
... prodEnd = test1
|
| 287 |
... elif test2:
|
| 288 |
... prodEnd = test2
|
| 289 |
... else:
|
| 290 |
... err = True
|
| 291 |
... else:
|
| 292 |
... err = True
|
| 293 |
... if ";" in concordBeg:
|
| 294 |
... err = True
|
| 295 |
... if ";" in end:
|
| 296 |
... err = True
|
| 297 |
... if prodBeg[-5:] == "LOKEY":
|
| 298 |
... err = True
|
| 299 |
... if concordBeg == "":
|
| 300 |
... err = True
|
| 301 |
... if err == False:
|
| 302 |
... try:
|
| 303 |
... prodList = FixBatesRange_func.EnumerateBates(prodBeg,prodEnd)
|
| 304 |
... revList = FixBatesRange_func.EnumerateBates(concordBeg,end)
|
| 305 |
... if len(prodList) == len(revList):
|
| 306 |
... outputFile.write(line+"\n")
|
| 307 |
... else:
|
| 308 |
... outputErrFile.write(line+"\n")
|
| 309 |
... except:
|
| 310 |
... outputErrFile.write(line+"\n")
|
| 311 |
... else:
|
| 312 |
... outputErrFile.write(line+"\n")
|
| 313 |
... outputFile.close()
|
| 314 |
... outputErrFile.close()
|
| 315 |
|
| 316 |
== Then make a dat file for KPMG ==
|
| 317 |
for f in os.listdir(startDir):
|
| 318 |
... outputFile = open(os.path.join(outputDir,os.path.splitext(f)[0]+".DAT"),'w')
|
| 319 |
... outputFile.write("BegImage|%s BatesBeg|%s BatesEnd|Prod Production History Multi Choice\n"%(os.path.splitext(f)[0],os.path.splitext(f)[0]))
|
| 320 |
... contents = open(os.path.join(startDir,f)).readlines()
|
| 321 |
... contents = contents[1:]
|
| 322 |
... for line in contents:
|
| 323 |
... line = line.replace("\n","")
|
| 324 |
... prodBeg,prodEnd,beg,end,concordBeg = line.split(",")
|
| 325 |
... if prodBeg:
|
| 326 |
... pass
|
| 327 |
... else:
|
| 328 |
... prodBeg = beg
|
| 329 |
... err = False
|
| 330 |
... if ";" in prodBeg:
|
| 331 |
... err = True
|
| 332 |
... if ";" in prodEnd:
|
| 333 |
... testList = prodEnd.split(";")
|
| 334 |
... if len(testList) == 2:
|
| 335 |
... test1,test2 = prodEnd.split(";")
|
| 336 |
... test1 = test1.strip()
|
| 337 |
... test2 = test2.strip()
|
| 338 |
... if test1:
|
| 339 |
... if test2:
|
| 340 |
... err = True
|
| 341 |
... else:
|
| 342 |
... prodEnd = test1
|
| 343 |
... elif test2:
|
| 344 |
... prodEnd = test2
|
| 345 |
... else:
|
| 346 |
... err = True
|
| 347 |
... else:
|
| 348 |
... err = True
|
| 349 |
... if ";" in concordBeg:
|
| 350 |
... err = True
|
| 351 |
... if ";" in end:
|
| 352 |
... err = True
|
| 353 |
... if prodBeg[-5:] == "LOKEY":
|
| 354 |
... err = True
|
| 355 |
... if concordBeg == "":
|
| 356 |
... err = True
|
| 357 |
... if err == False:
|
| 358 |
... outputFile.write("%s|%s|%s|%s\n"%(concordBeg,prodBeg,prodEnd,os.path.splitext(f)[0]))
|
| 359 |
... outputFile.close()
|
| 360 |
=== End ===
|
| 361 |
|
| 362 |
=== Here I was asked to group and code documents by doc title ===
|
| 363 |
## first take her huge xls file and make a smaller pipe delim file with only fields that have stuff in the key fields
|
| 364 |
>>> contents = open(r"W:\Manny\Client\honeywell\DocTitleBatchCode_Proj\Document Title Tally.csv").readlines()
|
| 365 |
>>> outputFile = open(r"W:\Manny\Client\honeywell\DocTitleBatchCode_Proj\Document Title Tally_small.csv",'w')
|
| 366 |
>>> contents = contents[1:]
|
| 367 |
>>> for line in contents:
|
| 368 |
... wr = False
|
| 369 |
... line = line.split("|")
|
| 370 |
... if line[2]:
|
| 371 |
... wr = True
|
| 372 |
... if line[4]:
|
| 373 |
... wr = True
|
| 374 |
... if line[5]:
|
| 375 |
... wr = True
|
| 376 |
... if line[6]:
|
| 377 |
... wr = True
|
| 378 |
... if line[7]:
|
| 379 |
... wr = True
|
| 380 |
... if line[8]:
|
| 381 |
... wr = True
|
| 382 |
... if line[9]:
|
| 383 |
... wr = True
|
| 384 |
... if wr:
|
| 385 |
... outputFile.write("%s|%s|%s|%s|%s|%s|%s|%s\n"% (line[0],line[2],line[4],line[5],line[6],line[7],line[8],line[9]))
|
| 386 |
...
|
| 387 |
>>> outputFile.close()
|
| 388 |
|
| 389 |
## Create the matrix, if you dont have a pickle. Here I write to a pickel, which can be reused, since the doctitle shouldnt change
|
| 390 |
>>> contents = open(r"W:\Manny\Client\honeywell\DocTitleTally.dat").readlines()
|
| 391 |
>>> matrix = {}
|
| 392 |
>>> for line in contents:
|
| 393 |
... line = line.replace("\n","")
|
| 394 |
... line = line.split("|")
|
| 395 |
... bates = line[0]
|
| 396 |
... title = line[2]
|
| 397 |
... if title in matrix.keys():
|
| 398 |
... matrix[title].append(bates)
|
| 399 |
... else:
|
| 400 |
... matrix[title] = [bates,]
|
| 401 |
...
|
| 402 |
>>> len(matrix.keys())
|
| 403 |
239844
|
| 404 |
## saving to a pickel
|
| 405 |
import pickle
|
| 406 |
>>> with open(r"C:\McDermott-Discovery\Client\docTitle_proj.pkl",'wb') as f:
|
| 407 |
... pickle.dump(matrix,f,pickle.HIGHEST_PROTOCOL)
|
| 408 |
...
|
| 409 |
##
|
| 410 |
>>> outputFile = open(r"C:\McDermott-Discovery\Client\docTitle_proj.dat",'w')
|
| 411 |
>>> contents = open(r"\\nykads01\data\CLI\Honeywell-17th Floor\Manny\20140630_DocTitleTally_MannyCopy_small.dat").readlines()
|
| 412 |
>>> headder = contents[0]
|
| 413 |
>>> headder = "Bates|" + headder
|
| 414 |
>>> outputFile.write(headder)
|
| 415 |
>>> for line in contents[1:]:
|
| 416 |
... line = line.replace("\n","")
|
| 417 |
... line = line.split("|")
|
| 418 |
... for b in matrix[line[0]]:
|
| 419 |
... outputFile.write("%s|%s|%s|%s|%s|%s|%s\n"%(b,line[1],line[2],line[3],line[4],line[5],line[6]))
|
| 420 |
...
|
| 421 |
>>> outputFile.close()
|
| 422 |
|
| 423 |
|
| 424 |
## family groups
|
| 425 |
>>> contents = open(r"C:\McDermott-Discovery\Client\RL_BegImage_BegAttach.csv").readlines()
|
| 426 |
>>> contents = contents[1:]
|
| 427 |
>>> familyLookupMatrix = {}
|
| 428 |
>>> familyMatrix = {}
|
| 429 |
>>> for line in contents:
|
| 430 |
... line = line.replace('"','')
|
| 431 |
... line = line.replace("\n","")
|
| 432 |
... bates,begAttach = line.split(",")
|
| 433 |
... familyLookupMatrix[bates] = begAttach
|
| 434 |
... if begAttach in familyMatrix.keys():
|
| 435 |
... familyMatrix[begAttach].append(bates)
|
| 436 |
... else:
|
| 437 |
... familyMatrix[begAttach] = [bates,]
|
| 438 |
...
|
| 439 |
## Now the meat of the proj
|
| 440 |
>>> contents = open(r"C:\McDermott-Discovery\Client\docTitle_proj.dat").readlines()
|
| 441 |
>>> contents = contents[1:]
|
| 442 |
>>> fbc = {}
|
| 443 |
>>> rbg1 = {}
|
| 444 |
>>> rbg2 = {}
|
| 445 |
>>> rbg3 = {}
|
| 446 |
>>> rbg4 = {}
|
| 447 |
>>> rbg5 = {}
|
| 448 |
>>> for line in contents:
|
| 449 |
... line = line.replace("\n","")
|
| 450 |
... line = line.split("|")
|
| 451 |
... parent = familyLookupMatrix[line[0]]
|
| 452 |
... fullFam = familyMatrix[parent]
|
| 453 |
... for x in fullFam:
|
| 454 |
... if line[1]:
|
| 455 |
... if x in fbc.keys():
|
| 456 |
... if line[1] in fbc[x]:
|
| 457 |
... pass
|
| 458 |
... else:
|
| 459 |
... fbc[x].append(line[1])
|
| 460 |
... else:
|
| 461 |
... fbc[x] = [line[1],]
|
| 462 |
... if line[2]:
|
| 463 |
... if x in rbg1.keys():
|
| 464 |
... if line[2] in rbg1[x]:
|
| 465 |
... pass
|
| 466 |
... else:
|
| 467 |
... rbg1[x].append(line[2])
|
| 468 |
... else:
|
| 469 |
... rbg1[x] = [line[2],]
|
| 470 |
... if line[3]:
|
| 471 |
... if x in rbg2.keys():
|
| 472 |
... if line[3] in rbg2[x]:
|
| 473 |
... pass
|
| 474 |
... else:
|
| 475 |
... rbg2[x].append(line[3])
|
| 476 |
... else:
|
| 477 |
... rbg2[x] = [line[3],]
|
| 478 |
... if line[4]:
|
| 479 |
... if x in rbg3.keys():
|
| 480 |
... if line[4] in rbg3[x]:
|
| 481 |
... pass
|
| 482 |
... else:
|
| 483 |
... rbg3[x].append(line[4])
|
| 484 |
... else:
|
| 485 |
... rbg3[x] = [line[4],]
|
| 486 |
... if line[5]:
|
| 487 |
... if x in rbg4.keys():
|
| 488 |
... if line[5] in rbg4[x]:
|
| 489 |
... pass
|
| 490 |
... else:
|
| 491 |
... rbg4[x].append(line[5])
|
| 492 |
... else:
|
| 493 |
... rbg4[x] = [line[5],]
|
| 494 |
... if line[6]:
|
| 495 |
... if x in rbg5.keys():
|
| 496 |
... if line[6] in rbg5[x]:
|
| 497 |
... pass
|
| 498 |
... else:
|
| 499 |
... rbg5[x].append(line[6])
|
| 500 |
... else:
|
| 501 |
... rbg5[x] = [line[6],]
|
| 502 |
...
|
| 503 |
>>> mainList = []
|
| 504 |
>>> for i in fbc.keys():
|
| 505 |
... if i in mainList:
|
| 506 |
... pass
|
| 507 |
... else:
|
| 508 |
... mainList.append(i)
|
| 509 |
...
|
| 510 |
>>> len(mainList)
|
| 511 |
80490
|
| 512 |
>>> for i in rbg1.keys():
|
| 513 |
... if i in mainList:
|
| 514 |
... pass
|
| 515 |
... else:
|
| 516 |
... mainList.append(i)
|
| 517 |
...
|
| 518 |
>>> len(mainList)
|
| 519 |
80490
|
| 520 |
>>> for i in rbg2.keys():
|
| 521 |
... if i in mainList:
|
| 522 |
... pass
|
| 523 |
... else:
|
| 524 |
... mainList.append(i)
|
| 525 |
...
|
| 526 |
>>> for i in rbg3.keys():
|
| 527 |
... if i in mainList:
|
| 528 |
... pass
|
| 529 |
... else:
|
| 530 |
... mainList.append(i)
|
| 531 |
...
|
| 532 |
>>> for i in rbg4.keys():
|
| 533 |
... if i in mainList:
|
| 534 |
... pass
|
| 535 |
... else:
|
| 536 |
... mainList.append(i)
|
| 537 |
...
|
| 538 |
>>> for i in rbg5.keys():
|
| 539 |
... if i in mainList:
|
| 540 |
... pass
|
| 541 |
... else:
|
| 542 |
... mainList.append(i)
|
| 543 |
>>> mainList.sort()
|
| 544 |
>>> outputFile = open(r"C:\McDermott-Discovery\Client\output.txt",'w')
|
| 545 |
>>> for bates in mainList:
|
| 546 |
... if bates in fbc.keys():
|
| 547 |
... if fbc[bates]:
|
| 548 |
... fbcVal = str(fbc[bates])
|
| 549 |
... else:
|
| 550 |
... fbcVal = ""
|
| 551 |
... else:
|
| 552 |
... fbcVal = ""
|
| 553 |
... if bates in rbg1.keys():
|
| 554 |
... if rbg1[bates]:
|
| 555 |
... rbg1Val = str(rbg1[bates])
|
| 556 |
... else:
|
| 557 |
... rbg1Val = ""
|
| 558 |
... else:
|
| 559 |
... rbg1Val = ""
|
| 560 |
... if bates in rbg2.keys():
|
| 561 |
... if rbg2[bates]:
|
| 562 |
... rbg2Val = str(rbg2[bates])
|
| 563 |
... else:
|
| 564 |
... rbg2Val = ""
|
| 565 |
... else:
|
| 566 |
... rbg2Val = ""
|
| 567 |
... if bates in rbg3.keys():
|
| 568 |
... if rbg3[bates]:
|
| 569 |
... rbg3Val = str(rbg3[bates])
|
| 570 |
... else:
|
| 571 |
... rbg3Val = ""
|
| 572 |
... else:
|
| 573 |
... rbg3Val = ""
|
| 574 |
... if bates in rbg4.keys():
|
| 575 |
... if rbg4[bates]:
|
| 576 |
... rbg4Val = str(rbg4[bates])
|
| 577 |
... else:
|
| 578 |
... rbg4Val = ""
|
| 579 |
... else:
|
| 580 |
... rbg4Val = ""
|
| 581 |
... if bates in rbg5.keys():
|
| 582 |
... if rbg5[bates]:
|
| 583 |
... rbg5Val = str(rbg5[bates])
|
| 584 |
... else:
|
| 585 |
... rbg5Val = ""
|
| 586 |
... else:
|
| 587 |
... rbg5Val = ""
|
| 588 |
... outputFile.write("%s|%s|%s|%s|%s|%s|%s\n"%(bates,fbcVal,rbg1Val,rbg2Val,rbg3Val,rbg4Val,rbg5Val))
|
| 589 |
...
|
| 590 |
>>> outputFile.close()
|
| 591 |
|
| 592 |
## Cleanup the output and make the final overlay
|
| 593 |
>>> contents = open(r"C:\McDermott-Discovery\Client\output.txt").readlines()
|
| 594 |
>>> outputFile = open(r"C:\McDermott-Discovery\Client\overlay.dat",'w')
|
| 595 |
>>> for line in contents:
|
| 596 |
... line = line.split("|")
|
| 597 |
... for i in line:
|
| 598 |
... i = i.replace("'","")
|
| 599 |
... i = i.replace("[","")
|
| 600 |
... i = i.replace("]","")
|
| 601 |
... i = i.replace(",",";")
|
| 602 |
... if "\n" in i:
|
| 603 |
... outputFile.write(i)
|
| 604 |
... else:
|
| 605 |
... outputFile.write(i + "|")
|
| 606 |
...
|
| 607 |
>>> outputFile.close()
|
| 608 |
|
| 609 |
|
| 610 |
=== Here I was asked to copy frm long text date to real date field but there were errors because some of the dates were missing info ie. 00/00/1991. I fixed the entries based on their criteria.===
|
| 611 |
>>> contents = open(r"C:\Users\eborges\Box Sync\Client\Honeywell\Perligo\Document_Delivery\Vol003\GroupA\export_20140929_192612.csv").readlines()
|
| 612 |
>>> contents = contents[1:]
|
| 613 |
>>> outputFile = open(r"C:\Users\eborges\Box Sync\Client\Honeywell\Perligo\Document_Delivery\Vol003\GroupA\FIXED.dat",'w')
|
| 614 |
>>> outputFile.write("BegDoc|DocDate_New\n")
|
| 615 |
>>> for line in contents:
|
| 616 |
... line = line.replace("\n","")
|
| 617 |
... bates,date,nul = line.split("|")
|
| 618 |
... if date:
|
| 619 |
... mm,dd,yy = date.split("/")
|
| 620 |
... if mm == '00':
|
| 621 |
... mm = '01'
|
| 622 |
... if dd == '00':
|
| 623 |
... dd = '01'
|
| 624 |
... if yy == '0000':
|
| 625 |
... yy = '1800'
|
| 626 |
... date = '%s/%s/%s'%(mm,dd,yy)
|
| 627 |
... outputFile.write("%s|%s\n"%(bates,date))
|
| 628 |
>>> outputFile.close()
|
| 629 |
=== END ===
|
| 630 |
=== Here I was asked to make a tally report frm the prefixes in HOBX ===
|
| 631 |
>>> contents = open(r"W:\Manny\Client\honeywell\PrefixTallyProj\20140717 search for manny_export\20140717 search for manny_export.csv").readlines()
|
| 632 |
>>> contents = contents[1:]
|
| 633 |
>>> import FixBatesRange_func
|
| 634 |
>>> outputFile = open(r"W:\Manny\Client\honeywell\PrefixTallyProj\20140717 search for manny_export\output.txt",'w')
|
| 635 |
>>> errorFile = open(r"W:\Manny\Client\honeywell\PrefixTallyProj\20140717 search for manny_export\errFile.txt",'w')
|
| 636 |
>>> matrix = {}
|
| 637 |
>>> cnt = NinoGenTools.Counter()
|
| 638 |
>>> for line in contents:
|
| 639 |
... line = line.replace("\n","")
|
| 640 |
... line = line.replace('"',"")
|
| 641 |
... try:
|
| 642 |
... alph = FixBatesRange_func.SeperateAlpha3(line)[0]
|
| 643 |
... except:
|
| 644 |
... alph = "00"
|
| 645 |
... errorFile.write("%s\n"%line)
|
| 646 |
... if alph[:2] == "00":
|
| 647 |
... alph = ""
|
| 648 |
... elif alph[-1] == "0":
|
| 649 |
... while alph[-1] == "0":
|
| 650 |
... alph = alph[:-1]
|
| 651 |
... if alph in matrix.keys():
|
| 652 |
... matrix[alph] = matrix[alph] + 1
|
| 653 |
... else:
|
| 654 |
... matrix[alph] = 1
|
| 655 |
... cnt.inc()
|
| 656 |
...
|
| 657 |
>>> outputFile.close()
|
| 658 |
>>> errorFile.close()
|
| 659 |
=== End ===
|
| 660 |
|
| 661 |
==== Here I was asked to find documents with family problems. Note that the values have to be enumerated first.
|
| 662 |
import FixBatesRange_func
|
| 663 |
>>> content = open(r"W:\Manny\Client\Perligo\Family_probs_export.csv").readlines()
|
| 664 |
>>> batesValues = []
|
| 665 |
>>> attachValues = {}
|
| 666 |
>>> for line in content:
|
| 667 |
... line = line.replace("\n","")
|
| 668 |
... batesEnum = line.split("|")[6]
|
| 669 |
... batesEnum = batesEnum.split(';')
|
| 670 |
... if batesEnum >1:
|
| 671 |
... for i in batesEnum:
|
| 672 |
... batesValues.append(i)
|
| 673 |
... else:
|
| 674 |
... batesValues.append(batesEnum)
|
| 675 |
...
|
| 676 |
>>> content = content[1:]
|
| 677 |
>>> for line in content:
|
| 678 |
... line = line.replace("\n","")
|
| 679 |
... batesBeg = line.split("|")[4]
|
| 680 |
... batesEnd = line.split("|")[5]
|
| 681 |
... batesEnum = FixBatesRange_func.EnumerateBates(batesBeg,batesEnd)
|
| 682 |
... clump = "%s,%s"%(batesBeg,batesEnd)
|
| 683 |
... attachValues[clump] = batesEnum
|
| 684 |
...
|
| 685 |
>>> outputFile = open(r"W:\Manny\Client\Perligo\export_output.txt",'w')
|
| 686 |
>>> for clump in attachValues.keys():
|
| 687 |
... errList = []
|
| 688 |
... for i in attachValues[clump]:
|
| 689 |
... if i in batesValues:
|
| 690 |
... pass
|
| 691 |
... else:
|
| 692 |
... errList.append(i)
|
| 693 |
... if errList:
|
| 694 |
... outputFile.write("%s family is an issue because it's missing pages: "%clump)
|
| 695 |
... for x in errList:
|
| 696 |
... outputFile.write("%s;"%x)
|
| 697 |
... outputFile.write("\n")
|
| 698 |
...
|
| 699 |
>>> outputFile.close()
|
| 700 |
>>> begAttachList = []
|
| 701 |
>>> contents = open(r"W:\Manny\Client\Perligo\export_output.txt").readlines()
|
| 702 |
>>> for i in contents:
|
| 703 |
... i = i.split(",")
|
| 704 |
... begAttachList.append(i[0])
|
| 705 |
...
|
| 706 |
>>> contents = open(r"W:\Manny\Client\Perligo\Family_probs_export.csv").readlines()
|
| 707 |
>>> outputFile = open(r"W:\Manny\Client\Perligo\overlay.dat",'w')
|
| 708 |
>>> for line in contents:
|
| 709 |
... line = line.split("|")
|
| 710 |
... if line[4] in begAttachList:
|
| 711 |
... outputFile.write("%s|x\n"%line[0])
|
| 712 |
...
|
| 713 |
>>> outputFile.close()
|
| 714 |
>>>
|
| 715 |
|
| 716 |
==== END =======
|
| 717 |
|
| 718 |
|
| 719 |
==== Here I was asked to both test the kpmg enumerated values field and to also verify that
|
| 720 |
all of the bendix ranges in rl were in my LFP.
|
| 721 |
-------------------------------
|
| 722 |
>>> contents = open(r"\\bstads01\app\Manny\Client\honeywell\LFP Export\LFP Export\Non_microfiche\373540873_REVIEW_JUSTBENDIX.lfp").readlines()
|
| 723 |
>>> MasterList = []
|
| 724 |
>>> for line in contents:
|
| 725 |
... bates = line.split(",")[1]
|
| 726 |
... MasterList.append(bates)
|
| 727 |
...
|
| 728 |
>>> len(MasterList)
|
| 729 |
357525
|
| 730 |
|
| 731 |
-------------------------------
|
| 732 |
>>> outputFile2 = open(r"C:\Client\honeywell\BENDIX-Beg_End_Enum_enumErr.csv",'w')
|
| 733 |
>>> outputFile = open(r"C:\Client\honeywell\BENDIX-Beg_End_Enum_output.csv",'w')
|
| 734 |
>>> for line in contents:
|
| 735 |
... line = line.replace("\n","")
|
| 736 |
... begNo,endNo,enumValues = line.split(",")
|
| 737 |
... begTest = begNo.split(" ")[-1]
|
| 738 |
... endTest = endNo.split(" ")[-1]
|
| 739 |
... rangeTest = FixBatesRange_func.EnumerateBates(begTest,endTest)
|
| 740 |
... enumCount = len(rangeTest)
|
| 741 |
... if ";" in enumValues:
|
| 742 |
... kpmgEnumCount = len(enumValues.split(";"))
|
| 743 |
... else:
|
| 744 |
... kpmgEnumCount = 1
|
| 745 |
... if enumCount == kpmgEnumCount:
|
| 746 |
... pass
|
| 747 |
... else:
|
| 748 |
... outputFile2.write(line+"\n")
|
| 749 |
... if begNo in MasterList:
|
| 750 |
... pass
|
| 751 |
... elif begNo.replace(" "," ") in MasterList:
|
| 752 |
... pass
|
| 753 |
... elif begNo.replace(" "," ") in MasterList:
|
| 754 |
... pass
|
| 755 |
... elif begNo.replace(" "," ") in MasterList:
|
| 756 |
... pass
|
| 757 |
... elif begNo.replace(" ","") in MasterList:
|
| 758 |
... pass
|
| 759 |
... elif begNo.replace(" ","") in MasterList:
|
| 760 |
... pass
|
| 761 |
... else:
|
| 762 |
... outputFile.write(line+"\n")
|
| 763 |
...
|
| 764 |
>>> outputFile.close()
|
| 765 |
>>> outputFile2.close()
|
| 766 |
|
| 767 |
==== END ==== |
