| 1 |
"""
|
| 2 |
|
| 3 |
IncomingProdAnalyzer
|
| 4 |
|
| 5 |
Created by
|
| 6 |
Emanuel Borges
|
| 7 |
2020.02.07
|
| 8 |
|
| 9 |
A simple program that I can point to a DAT and it will analyze it for issues like columns not lining up,
|
| 10 |
what fields they gave in the headder and which ones have stuff and which are totally empty, etc.
|
| 11 |
Support for UTF quotechars and delims plus removing that little BOM at the beging added.
|
| 12 |
|
| 13 |
"""
|
| 14 |
|
| 15 |
import chardet
|
| 16 |
|
| 17 |
def AnalyzeDAT(datFilePath):
|
| 18 |
"""Returns totalRecordCount, fullFieldList, populatedFieldsList, emptyFieldsList, parsingErrorCount"""
|
| 19 |
matrix = {}
|
| 20 |
headderMatrix = {}
|
| 21 |
populatedFieldsList = []
|
| 22 |
emptyFieldsList = []
|
| 23 |
|
| 24 |
|
| 25 |
contents = open(datFilePath).readlines()
|
| 26 |
|
| 27 |
charEncoding = None
|
| 28 |
charEncodingCount = 0
|
| 29 |
while charEncoding == None:
|
| 30 |
charEncoding = chardet.detect(contents[charEncodingCount])['encoding']
|
| 31 |
charEncodingCount = charEncodingCount +1
|
| 32 |
|
| 33 |
charEncoding = charEncoding.upper()
|
| 34 |
#print charEncoding
|
| 35 |
if "UTF" in charEncoding:
|
| 36 |
print "UTF found"
|
| 37 |
quoteChar = "\xc3\xbe"
|
| 38 |
headder = contents[0].replace("\xef\xbb\xbf","")
|
| 39 |
else:
|
| 40 |
print "Standard load file found"
|
| 41 |
quoteChar = "\xfe"
|
| 42 |
headder = contents[0]
|
| 43 |
delim = "\x14"
|
| 44 |
|
| 45 |
|
| 46 |
headder = headder.replace(quoteChar,"")
|
| 47 |
headder = headder.split(delim)
|
| 48 |
## This headder Matrix is really to look up at the end. I dont use it for the main matrix below.
|
| 49 |
for hSpot, hFieldName in enumerate(headder):
|
| 50 |
headderMatrix[hSpot] = hFieldName
|
| 51 |
numberOfFields = len(headder)
|
| 52 |
contents = contents[1:]
|
| 53 |
|
| 54 |
|
| 55 |
|
| 56 |
totalRecordCount = len(contents)
|
| 57 |
parsingErrorCount = 0
|
| 58 |
for line in contents:
|
| 59 |
line = line.replace("\n","")
|
| 60 |
line = line.replace(quoteChar,"")
|
| 61 |
line = line.split(delim)
|
| 62 |
if len(line) == numberOfFields:
|
| 63 |
pass
|
| 64 |
else:
|
| 65 |
print "Warning: number of fields for this line doenst match."
|
| 66 |
parsingErrorCount = parsingErrorCount +1
|
| 67 |
for itemSpot, value in enumerate(line):
|
| 68 |
if value:
|
| 69 |
matrix[itemSpot] = 1
|
| 70 |
|
| 71 |
|
| 72 |
for spot in matrix.keys():
|
| 73 |
#print headder[spot]
|
| 74 |
populatedFieldsList.append(headder[spot])
|
| 75 |
|
| 76 |
|
| 77 |
for hSpot in headderMatrix.keys():
|
| 78 |
if hSpot in matrix.keys():
|
| 79 |
pass
|
| 80 |
else:
|
| 81 |
#print headderMatrix[hSpot]
|
| 82 |
emptyFieldsList.append(headderMatrix[hSpot])
|
| 83 |
|
| 84 |
fullFieldList = headder
|
| 85 |
|
| 86 |
return totalRecordCount, fullFieldList, populatedFieldsList, emptyFieldsList, parsingErrorCount
|
| 87 |
|
| 88 |
if __name__ == '__main__':
|
| 89 |
|
| 90 |
datFilePath = r"\\sas12\sas12\30393\Inbound\11\099878\All American Title Final Distribution Ledger REport\data\All American Title Final Distribution Ledger REport.DAT"
|
| 91 |
|
| 92 |
print "Analyzing file..."
|
| 93 |
totalRecordCount, fullFieldList, populatedFieldsList, emptyFieldsList, parsingErroCount = AnalyzeDAT(datFilePath)
|
| 94 |
print ""
|
| 95 |
print "There are %s records in this load."%totalRecordCount
|
| 96 |
|
| 97 |
print "\nAnalysis completed."
|
| 98 |
print ""
|
| 99 |
print "-"*10
|
| 100 |
print "The following fields exist in this DAT:"
|
| 101 |
for i in fullFieldList:
|
| 102 |
print i
|
| 103 |
|
| 104 |
print "-"*10
|
| 105 |
print ""
|
| 106 |
print "The following fields actually contains *some* data:"
|
| 107 |
for x in populatedFieldsList:
|
| 108 |
print x
|
| 109 |
|
| 110 |
print "-"*10
|
| 111 |
print ""
|
| 112 |
print "The following fields are totally empty:"
|
| 113 |
for y in emptyFieldsList:
|
| 114 |
print y
|
| 115 |
|
| 116 |
|
| 117 |
|
| 118 |
|
