| 1 |
nino.borges |
828 |
"""
|
| 2 |
|
|
|
| 3 |
|
|
Amazon-PrivLogQC
|
| 4 |
|
|
|
| 5 |
|
|
Created by:
|
| 6 |
|
|
Emanuel Borges
|
| 7 |
|
|
11.19.2024
|
| 8 |
|
|
|
| 9 |
|
|
This program will assist with the process of performing QC on the Amazon privilege logs.
|
| 10 |
|
|
|
| 11 |
|
|
"""
|
| 12 |
|
|
|
| 13 |
|
|
import os, re
|
| 14 |
|
|
from collections import namedtuple
|
| 15 |
nino.borges |
851 |
from MyCode.Tool_Box import FileEncodingLib
|
| 16 |
nino.borges |
828 |
|
| 17 |
|
|
|
| 18 |
|
|
class QcPrivLog(object):
|
| 19 |
|
|
"""A class for automating the process of performing QC on the Amazon privilege logs, including names normalization analysis"""
|
| 20 |
nino.borges |
924 |
version = '0.8.0'
|
| 21 |
nino.borges |
828 |
|
| 22 |
|
|
|
| 23 |
|
|
def __init__(self, cleanedDatExportFileName, fileEncoding = 'UTF8'):
|
| 24 |
|
|
"""Initializes the data structures. cleanedDatExportFileName should be the full path to the file. Assumes the first row of the data file is the header and first column is DocID."""
|
| 25 |
|
|
print("Initializing data structures...")
|
| 26 |
|
|
self.metadataValuesDict = {}
|
| 27 |
|
|
self.formattedValuesDict = {}
|
| 28 |
nino.borges |
852 |
self.additionalValuesDict = {}
|
| 29 |
nino.borges |
830 |
self.allPossibleEmailAddressesRegExPattern = r"[\w.+-]+@[\w-]+\.[\w.-]+"
|
| 30 |
nino.borges |
828 |
|
| 31 |
|
|
contents = open(cleanedDatExportFileName,encoding = fileEncoding).readlines()
|
| 32 |
nino.borges |
924 |
self.cleanedInputDataFileHeader = contents[0].replace("\n","")
|
| 33 |
nino.borges |
832 |
self.cleanedInputDataFileHeaderList = self.cleanedInputDataFileHeader.split("|")
|
| 34 |
nino.borges |
828 |
contents = contents[1:]
|
| 35 |
nino.borges |
832 |
print (f"There are {len(contents)} rows of data in this input file.\n\n")
|
| 36 |
nino.borges |
828 |
|
| 37 |
nino.borges |
851 |
|
| 38 |
nino.borges |
881 |
## Floyd
|
| 39 |
|
|
## print (f"The data structure will be made of following field pairs:")
|
| 40 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[23]} | {self.cleanedInputDataFileHeaderList[24]}")
|
| 41 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[25]} | {self.cleanedInputDataFileHeaderList[26]}")
|
| 42 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[27]} | {self.cleanedInputDataFileHeaderList[28]}")
|
| 43 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[29]} | {self.cleanedInputDataFileHeaderList[20]}")
|
| 44 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[29]} | {self.cleanedInputDataFileHeaderList[32]}\n\n")
|
| 45 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[12]} will be used for the date qualifier.")
|
| 46 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[36]} will be used as the Legal Source field.")
|
| 47 |
|
|
|
| 48 |
|
|
|
| 49 |
|
|
## CAAG
|
| 50 |
|
|
## print (f"The data structure will be made of following field pairs:")
|
| 51 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[30]} | {self.cleanedInputDataFileHeaderList[31]}")
|
| 52 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[34]} | {self.cleanedInputDataFileHeaderList[35]}")
|
| 53 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[36]} | {self.cleanedInputDataFileHeaderList[37]}")
|
| 54 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[38]} | {self.cleanedInputDataFileHeaderList[39]}")
|
| 55 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[29]} | {self.cleanedInputDataFileHeaderList[32]}\n\n")
|
| 56 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[15]} will be used for the date qualifier.")
|
| 57 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[45]} will be used as the Legal Source field.")
|
| 58 |
|
|
|
| 59 |
|
|
## CAAG Custom 2
|
| 60 |
|
|
## print (f"The data structure will be made of following field pairs:")
|
| 61 |
nino.borges |
924 |
## print(f"{self.cleanedInputDataFileHeaderList[4]} | {self.cleanedInputDataFileHeaderList[14]}")
|
| 62 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[5]} | {self.cleanedInputDataFileHeaderList[10]}")
|
| 63 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[6]} | {self.cleanedInputDataFileHeaderList[11]}")
|
| 64 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[7]} | {self.cleanedInputDataFileHeaderList[12]}")
|
| 65 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[8]} | {self.cleanedInputDataFileHeaderList[9]}\n\n")
|
| 66 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[16]} will be used for the date qualifier.")
|
| 67 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[15]} will be used as the Legal Source field.")
|
| 68 |
nino.borges |
881 |
|
| 69 |
nino.borges |
851 |
## VEAS-CAAG
|
| 70 |
nino.borges |
881 |
## print (f"The data structure will be made of following field pairs:")
|
| 71 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[26]} | {self.cleanedInputDataFileHeaderList[27]}")
|
| 72 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[29]} | {self.cleanedInputDataFileHeaderList[30]}")
|
| 73 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[31]} | {self.cleanedInputDataFileHeaderList[32]}")
|
| 74 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[33]} | {self.cleanedInputDataFileHeaderList[34]}")
|
| 75 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[25]} | {self.cleanedInputDataFileHeaderList[28]}\n\n")
|
| 76 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[15]} will be used for the date qualifier.")
|
| 77 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[40]} will be used as the Legal Source field.")
|
| 78 |
nino.borges |
832 |
|
| 79 |
nino.borges |
881 |
## VEAS-CAAG 2
|
| 80 |
|
|
## print (f"The data structure will be made of following field pairs:")
|
| 81 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[11]} | {self.cleanedInputDataFileHeaderList[5]}")
|
| 82 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[12]} | {self.cleanedInputDataFileHeaderList[6]}")
|
| 83 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[13]} | {self.cleanedInputDataFileHeaderList[7]}")
|
| 84 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[14]} | {self.cleanedInputDataFileHeaderList[8]}")
|
| 85 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[15]} | {self.cleanedInputDataFileHeaderList[4]}\n\n")
|
| 86 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[1]} will be used for the date qualifier.")
|
| 87 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[9]} will be used as the Legal Source field.")
|
| 88 |
|
|
|
| 89 |
nino.borges |
851 |
## VEAS_custom
|
| 90 |
|
|
## print (f"The data structure will be made of following field pairs:")
|
| 91 |
nino.borges |
924 |
## print(f"{self.cleanedInputDataFileHeaderList[35]} | {self.cleanedInputDataFileHeaderList[36]}")
|
| 92 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[38]} | {self.cleanedInputDataFileHeaderList[61]}")
|
| 93 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[40]} | {self.cleanedInputDataFileHeaderList[62]}")
|
| 94 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[42]} | {self.cleanedInputDataFileHeaderList[63]}")
|
| 95 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[34]} | {self.cleanedInputDataFileHeaderList[37]}\n\n")
|
| 96 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[21]} will be used for the date qualifier.")
|
| 97 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[49]} will be used as the Legal Source field.")
|
| 98 |
nino.borges |
851 |
|
| 99 |
nino.borges |
881 |
## FTC-Retail
|
| 100 |
nino.borges |
924 |
## print (f"The data structure will be made of following field pairs:")
|
| 101 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[39]} | {self.cleanedInputDataFileHeaderList[40]}")
|
| 102 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[41]} | {self.cleanedInputDataFileHeaderList[42]}")
|
| 103 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[43]} | {self.cleanedInputDataFileHeaderList[44]}")
|
| 104 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[45]} | {self.cleanedInputDataFileHeaderList[46]}")
|
| 105 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[37]} | {self.cleanedInputDataFileHeaderList[38]}\n\n")
|
| 106 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[27]} will be used for the date qualifier.")
|
| 107 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[52]} will be used as the Legal Source field.")
|
| 108 |
|
|
|
| 109 |
|
|
## FTC-Retail PLOG
|
| 110 |
nino.borges |
881 |
print (f"The data structure will be made of following field pairs:")
|
| 111 |
nino.borges |
924 |
print(f"{self.cleanedInputDataFileHeaderList[29]} | {self.cleanedInputDataFileHeaderList[31]}")
|
| 112 |
|
|
print(f"{self.cleanedInputDataFileHeaderList[32]} | {self.cleanedInputDataFileHeaderList[34]}")
|
| 113 |
|
|
print(f"{self.cleanedInputDataFileHeaderList[35]} | {self.cleanedInputDataFileHeaderList[37]}")
|
| 114 |
|
|
print(f"{self.cleanedInputDataFileHeaderList[38]} | {self.cleanedInputDataFileHeaderList[40]}")
|
| 115 |
|
|
print(f"{self.cleanedInputDataFileHeaderList[27]} | {self.cleanedInputDataFileHeaderList[28]}\n\n")
|
| 116 |
|
|
print(f"{self.cleanedInputDataFileHeaderList[15]} will be used for the date qualifier.")
|
| 117 |
|
|
print(f"{self.cleanedInputDataFileHeaderList[47]} will be used as the Legal Source field.")
|
| 118 |
nino.borges |
881 |
|
| 119 |
nino.borges |
924 |
## FTC-CID 2
|
| 120 |
|
|
## print (f"The data structure will be made of following field pairs:")
|
| 121 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[22]} | {self.cleanedInputDataFileHeaderList[25]}")
|
| 122 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[26]} | {self.cleanedInputDataFileHeaderList[27]}")
|
| 123 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[28]} | {self.cleanedInputDataFileHeaderList[29]}")
|
| 124 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[30]} | {self.cleanedInputDataFileHeaderList[31]}")
|
| 125 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[21]} | {self.cleanedInputDataFileHeaderList[24]}\n\n")
|
| 126 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[8]} will be used for the date qualifier.")
|
| 127 |
|
|
## print(f"{self.cleanedInputDataFileHeaderList[20]} will be used as the Legal Source field.")
|
| 128 |
|
|
|
| 129 |
nino.borges |
831 |
RecordValues = namedtuple("RecordValues","fromValues toValues ccValues bccValues docAuthor")
|
| 130 |
nino.borges |
828 |
self.recordValuesFieldList = RecordValues._fields
|
| 131 |
|
|
|
| 132 |
nino.borges |
852 |
AdditionalValues = namedtuple("AdditionalValues","dateValue legalSourceValues")
|
| 133 |
|
|
self.additionalValuesFieldList = AdditionalValues._fields
|
| 134 |
|
|
|
| 135 |
nino.borges |
828 |
for line in contents:
|
| 136 |
|
|
line = line.replace("\n","")
|
| 137 |
|
|
line = line.split("|")
|
| 138 |
|
|
docID = line[0]
|
| 139 |
|
|
## TODO: These are hard coded for now but change to column header lookup asap.
|
| 140 |
nino.borges |
881 |
## CAAG_custom 2
|
| 141 |
nino.borges |
924 |
#self.metadataValuesDict[docID] = RecordValues(self.__SplitAndClean(line[4]),self.__SplitAndClean(line[5]),self.__SplitAndClean(line[6]),self.__SplitAndClean(line[7]) ,self.__SplitAndClean(line[8]))
|
| 142 |
|
|
#self.formattedValuesDict[docID] = RecordValues(self.__SplitAndClean(line[14]),self.__SplitAndClean(line[10]),self.__SplitAndClean(line[11]),self.__SplitAndClean(line[12]),self.__SplitAndClean(line[9]))
|
| 143 |
nino.borges |
881 |
## TODO: update code because they now have time values in the family date field.
|
| 144 |
nino.borges |
924 |
#self.additionalValuesDict[docID] = AdditionalValues(line[16].split(" ")[0],self.__SplitAndClean(line[15]))
|
| 145 |
nino.borges |
881 |
## Floyd
|
| 146 |
|
|
#self.metadataValuesDict[docID] = RecordValues(self.__SplitAndClean(line[30]),self.__SplitAndClean(line[34]),self.__SplitAndClean(line[36]),self.__SplitAndClean(line[38]) ,self.__SplitAndClean(line[29]))
|
| 147 |
|
|
#self.formattedValuesDict[docID] = RecordValues(self.__SplitAndClean(line[31]),self.__SplitAndClean(line[35]),self.__SplitAndClean(line[37]),self.__SplitAndClean(line[39]),self.__SplitAndClean(line[32]))
|
| 148 |
|
|
#self.additionalValuesDict[docID] = AdditionalValues(line[15],self.__SplitAndClean(line[45]))
|
| 149 |
nino.borges |
839 |
## CAAG
|
| 150 |
nino.borges |
833 |
#self.metadataValuesDict[docID] = RecordValues(self.__SplitAndClean(line[30]),self.__SplitAndClean(line[34]),self.__SplitAndClean(line[36]),self.__SplitAndClean(line[38]) ,self.__SplitAndClean(line[29]))
|
| 151 |
|
|
#self.formattedValuesDict[docID] = RecordValues(self.__SplitAndClean(line[31]),self.__SplitAndClean(line[35]),self.__SplitAndClean(line[37]),self.__SplitAndClean(line[39]),self.__SplitAndClean(line[32]))
|
| 152 |
nino.borges |
881 |
#self.additionalValuesDict[docID] = AdditionalValues(line[15],self.__SplitAndClean(line[45]))
|
| 153 |
nino.borges |
839 |
## VEAS-CAAG
|
| 154 |
nino.borges |
881 |
#self.metadataValuesDict[docID] = RecordValues(self.__SplitAndClean(line[26]),self.__SplitAndClean(line[29]),self.__SplitAndClean(line[31]),self.__SplitAndClean(line[33]) ,self.__SplitAndClean(line[25]))
|
| 155 |
|
|
#self.formattedValuesDict[docID] = RecordValues(self.__SplitAndClean(line[27]),self.__SplitAndClean(line[30]),self.__SplitAndClean(line[32]),self.__SplitAndClean(line[34]),self.__SplitAndClean(line[28]))
|
| 156 |
|
|
#self.additionalValuesDict[docID] = AdditionalValues(line[15],self.__SplitAndClean(line[40]))
|
| 157 |
|
|
## VEAS-CAAG 2
|
| 158 |
|
|
#self.metadataValuesDict[docID] = RecordValues(self.__SplitAndClean(line[11]),self.__SplitAndClean(line[12]),self.__SplitAndClean(line[13]),self.__SplitAndClean(line[14]) ,self.__SplitAndClean(line[15]))
|
| 159 |
|
|
#self.formattedValuesDict[docID] = RecordValues(self.__SplitAndClean(line[5]),self.__SplitAndClean(line[6]),self.__SplitAndClean(line[7]),self.__SplitAndClean(line[8]),self.__SplitAndClean(line[4]))
|
| 160 |
|
|
## TODO: update code because they now have time values in the family date field.
|
| 161 |
|
|
#self.additionalValuesDict[docID] = AdditionalValues(line[1].split(" ")[0],self.__SplitAndClean(line[9]))
|
| 162 |
nino.borges |
839 |
## FTC-CID
|
| 163 |
|
|
#self.metadataValuesDict[docID] = RecordValues(self.__SplitAndClean(line[6]),self.__SplitAndClean(line[7]),self.__SplitAndClean(line[8]),self.__SplitAndClean(line[9]) ,self.__SplitAndClean(line[10]))
|
| 164 |
|
|
#self.formattedValuesDict[docID] = RecordValues(self.__SplitAndClean(line[3]),self.__SplitAndClean(line[5]),self.__SplitAndClean(line[2]),self.__SplitAndClean(line[4]),self.__SplitAndClean(line[11]))
|
| 165 |
|
|
## VEAS_custom
|
| 166 |
nino.borges |
924 |
#self.metadataValuesDict[docID] = RecordValues(self.__SplitAndClean(line[35]),self.__SplitAndClean(line[38]),self.__SplitAndClean(line[40]),self.__SplitAndClean(line[42]) ,self.__SplitAndClean(line[34]))
|
| 167 |
|
|
#self.formattedValuesDict[docID] = RecordValues(self.__SplitAndClean(line[36]),self.__SplitAndClean(line[61]),self.__SplitAndClean(line[62]),self.__SplitAndClean(line[63]),self.__SplitAndClean(line[37]))
|
| 168 |
|
|
## TODO: update code because they now have time values in the family date field.
|
| 169 |
|
|
#self.additionalValuesDict[docID] = AdditionalValues(line[21].split(" ")[0],self.__SplitAndClean(line[49]))
|
| 170 |
nino.borges |
839 |
## CAAG_custom
|
| 171 |
|
|
#self.metadataValuesDict[docID] = RecordValues(self.__SplitAndClean(line[3]),self.__SplitAndClean(line[4]),self.__SplitAndClean(line[5]),self.__SplitAndClean(line[6]) ,self.__SplitAndClean(line[2]))
|
| 172 |
|
|
#self.formattedValuesDict[docID] = RecordValues(self.__SplitAndClean(line[7]),self.__SplitAndClean(line[8]),self.__SplitAndClean(line[9]),self.__SplitAndClean(line[10]),self.__SplitAndClean(line[7]))
|
| 173 |
nino.borges |
924 |
## TODO: update code because they now have time values in the family date field.
|
| 174 |
|
|
#self.additionalValuesDict[docID] = AdditionalValues(line[21].split(" ")[0],self.__SplitAndClean(line[49]))
|
| 175 |
nino.borges |
881 |
## FTC-Retail
|
| 176 |
nino.borges |
924 |
self.metadataValuesDict[docID] = RecordValues(self.__SplitAndClean(line[29]),self.__SplitAndClean(line[32]),self.__SplitAndClean(line[35]),self.__SplitAndClean(line[38]) ,self.__SplitAndClean(line[27]))
|
| 177 |
|
|
self.formattedValuesDict[docID] = RecordValues(self.__SplitAndClean(line[31]),self.__SplitAndClean(line[34]),self.__SplitAndClean(line[37]),self.__SplitAndClean(line[40]),self.__SplitAndClean(line[28]))
|
| 178 |
nino.borges |
881 |
## TODO: update code because they now have time values in the family date field.
|
| 179 |
nino.borges |
924 |
self.additionalValuesDict[docID] = AdditionalValues(line[15].split(" ")[0],self.__SplitAndClean(line[47]))
|
| 180 |
|
|
## FTC-CID 2
|
| 181 |
|
|
#self.metadataValuesDict[docID] = RecordValues(self.__SplitAndClean(line[22]),self.__SplitAndClean(line[26]),self.__SplitAndClean(line[28]),self.__SplitAndClean(line[30]) ,self.__SplitAndClean(line[21]))
|
| 182 |
|
|
#self.formattedValuesDict[docID] = RecordValues(self.__SplitAndClean(line[25]),self.__SplitAndClean(line[27]),self.__SplitAndClean(line[29]),self.__SplitAndClean(line[31]),self.__SplitAndClean(line[24]))
|
| 183 |
|
|
## TODO: update code because they now have time values in the family date field.
|
| 184 |
|
|
#self.additionalValuesDict[docID] = AdditionalValues(line[8].split(" ")[0],self.__SplitAndClean(line[20]))
|
| 185 |
nino.borges |
828 |
|
| 186 |
|
|
print("Data structures created.")
|
| 187 |
|
|
|
| 188 |
|
|
|
| 189 |
|
|
|
| 190 |
|
|
def __SplitAndClean(self, rawVal, delim = ";"):
|
| 191 |
|
|
"""Pseudo-private method which will take a raw string and split this into a list, removing any leading or trailing whitespace"""
|
| 192 |
nino.borges |
833 |
if rawVal:
|
| 193 |
|
|
newVal = [x.strip() for x in rawVal.split(delim)]
|
| 194 |
|
|
else: newVal = ""
|
| 195 |
|
|
return newVal
|
| 196 |
nino.borges |
828 |
|
| 197 |
|
|
|
| 198 |
|
|
def __FieldDedupeByEmailAddress(self, valuesList):
|
| 199 |
|
|
"""Pseudo-private method which will attempt to deduplicate a list of values from a specific field by pulling out email addresses as the deduplication criteria. Returns deduplicated count."""
|
| 200 |
nino.borges |
830 |
## This should ONLY be used for deduplication for counting and not for true deduplication because it removes a duplicate value at random and sometimes this will be the value with more information.
|
| 201 |
|
|
## TODO: update this to be case insensitive.
|
| 202 |
|
|
tempEmailList = []
|
| 203 |
|
|
newList = []
|
| 204 |
|
|
for item in valuesList:
|
| 205 |
|
|
result = re.findall(self.allPossibleEmailAddressesRegExPattern, item)
|
| 206 |
|
|
if result:
|
| 207 |
|
|
for r in result:
|
| 208 |
|
|
if r.upper() in tempEmailList:
|
| 209 |
|
|
pass
|
| 210 |
|
|
else:
|
| 211 |
|
|
newList.append(item)
|
| 212 |
|
|
tempEmailList.append(r.upper())
|
| 213 |
|
|
else:
|
| 214 |
|
|
newList.append(item)
|
| 215 |
|
|
return len(newList)
|
| 216 |
|
|
|
| 217 |
nino.borges |
828 |
|
| 218 |
nino.borges |
831 |
def __FieldFullValueDedupe(self, valuesList):
|
| 219 |
|
|
"""Pseudo-private method which will attempt to deduplicate a list of values from a specific field using the FULL VALUE. This was created because there appears to be duplicate values int he formatted fields"""
|
| 220 |
|
|
## Going to do this the long way because of possible uppercase-lowercase issues. These should all be uppercase but there shouldnt have been dups either...
|
| 221 |
|
|
newSet = set()
|
| 222 |
|
|
for item in valuesList:
|
| 223 |
|
|
newSet.add(item.upper())
|
| 224 |
|
|
return len(newSet)
|
| 225 |
nino.borges |
828 |
|
| 226 |
nino.borges |
830 |
|
| 227 |
nino.borges |
828 |
def PerformValueCountChecks(self, countsOnly = True):
|
| 228 |
|
|
"""Performs the inital value count checks between the metadata values and formatted values, looking for red flags and warnings. By default reports numbers. Set countsOnly to false to export reports."""
|
| 229 |
|
|
workList = self.metadataValuesDict.keys()
|
| 230 |
|
|
#misCount = 0
|
| 231 |
|
|
#redFlagDocList = []
|
| 232 |
|
|
#warningDocList = []
|
| 233 |
|
|
#misList = []
|
| 234 |
|
|
redFlagDocSet = set()
|
| 235 |
nino.borges |
833 |
redFlagDocMatrix = {}
|
| 236 |
nino.borges |
828 |
warningDocSet = set()
|
| 237 |
nino.borges |
833 |
warningDocMatrix = {}
|
| 238 |
nino.borges |
832 |
#duplicatesInFormattedSet = set()
|
| 239 |
|
|
duplicatesInFormattedMatrix = {}
|
| 240 |
nino.borges |
828 |
|
| 241 |
|
|
for docID in workList:
|
| 242 |
nino.borges |
829 |
for fieldName in self.recordValuesFieldList:
|
| 243 |
|
|
metadataFieldValues = self.metadataValuesDict[docID]._asdict()[fieldName]
|
| 244 |
|
|
formattedFieldValues = self.formattedValuesDict[docID]._asdict()[fieldName]
|
| 245 |
nino.borges |
833 |
|
| 246 |
nino.borges |
829 |
if len(metadataFieldValues) - len(formattedFieldValues) == 0:
|
| 247 |
|
|
pass
|
| 248 |
nino.borges |
828 |
else:
|
| 249 |
nino.borges |
829 |
if len(metadataFieldValues) == 0:
|
| 250 |
nino.borges |
833 |
## Have to account for instances where the meta docAuthor is blank because it's an email and the formatted just has the from value in it.
|
| 251 |
|
|
if fieldName == 'docAuthor':
|
| 252 |
|
|
if self.metadataValuesDict[docID].fromValues:
|
| 253 |
|
|
pass
|
| 254 |
|
|
else:
|
| 255 |
|
|
redFlagDocSet.add(docID)
|
| 256 |
|
|
#print(docID)
|
| 257 |
|
|
try:
|
| 258 |
nino.borges |
924 |
redFlagDocMatrix[docID].append(fieldName+"-No_Metadata_Entries-A")
|
| 259 |
nino.borges |
833 |
except KeyError:
|
| 260 |
nino.borges |
924 |
redFlagDocMatrix[docID] = [fieldName+"-No_Metadata_Entries-A",]
|
| 261 |
nino.borges |
833 |
else:
|
| 262 |
|
|
redFlagDocSet.add(docID)
|
| 263 |
|
|
try:
|
| 264 |
nino.borges |
924 |
redFlagDocMatrix[docID].append(fieldName+"-No_Metadata_Entries-B")
|
| 265 |
nino.borges |
833 |
except KeyError:
|
| 266 |
nino.borges |
924 |
redFlagDocMatrix[docID] = [fieldName+"-No_Metadata_Entries-B",]
|
| 267 |
nino.borges |
829 |
elif len(formattedFieldValues) == 0:
|
| 268 |
|
|
redFlagDocSet.add(docID)
|
| 269 |
nino.borges |
833 |
try:
|
| 270 |
nino.borges |
924 |
redFlagDocMatrix[docID].append(fieldName+"-No_Formatted_Entries")
|
| 271 |
nino.borges |
833 |
except KeyError:
|
| 272 |
nino.borges |
924 |
redFlagDocMatrix[docID] = [fieldName+"-No_Formatted_Entries",]
|
| 273 |
nino.borges |
829 |
else:
|
| 274 |
nino.borges |
830 |
## try the count again by deduplicating the metadata field values. Never on the formatted field values.
|
| 275 |
|
|
deduplicatedFieldCount = self.__FieldDedupeByEmailAddress(metadataFieldValues)
|
| 276 |
|
|
if deduplicatedFieldCount - len(formattedFieldValues) == 0:
|
| 277 |
|
|
pass
|
| 278 |
|
|
else:
|
| 279 |
nino.borges |
833 |
distanceBetween = abs(deduplicatedFieldCount - len(formattedFieldValues))
|
| 280 |
|
|
if deduplicatedFieldCount > 30:
|
| 281 |
|
|
if distanceBetween > (10 * deduplicatedFieldCount)/100:
|
| 282 |
nino.borges |
924 |
#print(docID,fieldName)
|
| 283 |
nino.borges |
833 |
redFlagDocSet.add(docID)
|
| 284 |
|
|
try:
|
| 285 |
|
|
redFlagDocMatrix[docID].append(fieldName)
|
| 286 |
|
|
except KeyError:
|
| 287 |
|
|
redFlagDocMatrix[docID] = [fieldName,]
|
| 288 |
|
|
else:
|
| 289 |
|
|
warningDocSet.add(docID)
|
| 290 |
|
|
try:
|
| 291 |
|
|
warningDocMatrix[docID].append(fieldName)
|
| 292 |
|
|
except KeyError:
|
| 293 |
|
|
warningDocMatrix[docID]= [fieldName,]
|
| 294 |
|
|
else:
|
| 295 |
|
|
if distanceBetween > 2:
|
| 296 |
nino.borges |
924 |
#print(docID,fieldName)
|
| 297 |
nino.borges |
833 |
redFlagDocSet.add(docID)
|
| 298 |
|
|
try:
|
| 299 |
|
|
redFlagDocMatrix[docID].append(fieldName)
|
| 300 |
|
|
except KeyError:
|
| 301 |
|
|
redFlagDocMatrix[docID] = [fieldName,]
|
| 302 |
|
|
else:
|
| 303 |
|
|
warningDocSet.add(docID)
|
| 304 |
|
|
try:
|
| 305 |
|
|
warningDocMatrix[docID].append(fieldName)
|
| 306 |
|
|
except KeyError:
|
| 307 |
|
|
warningDocMatrix[docID]= [fieldName,]
|
| 308 |
nino.borges |
831 |
|
| 309 |
|
|
## Perform a separate check for duplicates in the formatted field.
|
| 310 |
|
|
if len(formattedFieldValues) == self.__FieldFullValueDedupe(formattedFieldValues):
|
| 311 |
|
|
pass
|
| 312 |
|
|
else:
|
| 313 |
nino.borges |
832 |
try:
|
| 314 |
|
|
duplicatesInFormattedMatrix[docID].append(fieldName)
|
| 315 |
|
|
except KeyError:
|
| 316 |
|
|
duplicatesInFormattedMatrix[docID] = [fieldName,]
|
| 317 |
|
|
#duplicatesInFormattedSet.add(docID)
|
| 318 |
nino.borges |
829 |
## if len(self.metadataValuesDict[docID].toValues) - len(self.formattedValuesDict[docID].toValues) == 0:
|
| 319 |
|
|
## pass
|
| 320 |
|
|
## else:
|
| 321 |
|
|
## if len(self.metadataValuesDict[docID].toValues) == 0:
|
| 322 |
|
|
## #redFlagDocList.append(docID)
|
| 323 |
|
|
## redFlagDocSet.add(docID)
|
| 324 |
|
|
## elif len(self.formattedValuesDict[docID].toValues) == 0:
|
| 325 |
|
|
## #redFlagDocList.append(docID)
|
| 326 |
|
|
## redFlagDocSet.add(docID)
|
| 327 |
|
|
## else:
|
| 328 |
|
|
## #misCount +=1
|
| 329 |
|
|
## #misList.append(docID)
|
| 330 |
|
|
## #warningDocList.append(docID)
|
| 331 |
|
|
## warningDocSet.add(docID)
|
| 332 |
nino.borges |
828 |
|
| 333 |
nino.borges |
830 |
print(f"There are a total of {len(redFlagDocSet)} red flag documents and {len(warningDocSet)} warnings where the matching field value counts that do not match.")
|
| 334 |
nino.borges |
828 |
if countsOnly == False:
|
| 335 |
|
|
warningsOutputFile = open(r"C:\Test_Dir\Amazon\warnings.txt",'w')
|
| 336 |
|
|
redFladsOutputFile = open(r"C:\Test_Dir\Amazon\redFlags.txt",'w')
|
| 337 |
nino.borges |
831 |
duplicatesInFormattedOutputFile = open(r"C:\Test_Dir\Amazon\dupesInFormattedFields.txt",'w')
|
| 338 |
nino.borges |
833 |
for x in warningDocMatrix:
|
| 339 |
|
|
warningsOutputFile.write(f"{x} | {*warningDocMatrix[x],}\n")
|
| 340 |
nino.borges |
828 |
warningsOutputFile.close()
|
| 341 |
nino.borges |
833 |
for y in redFlagDocMatrix:
|
| 342 |
|
|
redFladsOutputFile.write(f"{y} | {*redFlagDocMatrix[y],}\n")
|
| 343 |
nino.borges |
828 |
redFladsOutputFile.close()
|
| 344 |
nino.borges |
832 |
for z in duplicatesInFormattedMatrix:
|
| 345 |
|
|
duplicatesInFormattedOutputFile.write(f"{z} | {*duplicatesInFormattedMatrix[z],}\n")
|
| 346 |
nino.borges |
831 |
duplicatesInFormattedOutputFile.close()
|
| 347 |
nino.borges |
828 |
|
| 348 |
|
|
|
| 349 |
|
|
if __name__ == '__main__':
|
| 350 |
nino.borges |
924 |
cleanedDatExportFileName = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\_PrivLogQCProcess\20250303-FTC-Retail\export_20250304_021504_Converted.txt"
|
| 351 |
nino.borges |
881 |
#cleanedDatExportFileName = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\_PrivLogQCProcess\20250129\VEAS\VEAS_20250130_020124_Converted.txt"
|
| 352 |
|
|
#cleanedDatExportFileName = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\_PrivLogQCProcess\20241215\PrivLogExports\PrivLogExport_20241211_CAAG_Converted.txt"
|
| 353 |
|
|
#cleanedDatExportFileName = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\_PrivLogQCProcess\Testing_3\PrivLogExport_20241204_VEAS_Converted.txt"
|
| 354 |
nino.borges |
851 |
#cleanedDatExportFileName = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\_PrivLogQCProcess\Data Exports\CAAG\CAAG_Log_Data_Export_Converted.txt"
|
| 355 |
nino.borges |
839 |
#cleanedDatExportFileName = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\_PrivLogQCProcess\20241202 - FTC-CID\PLOG All IDs (20241202)\PLOG All IDs (20241202)_Converted_SubSetOnly.txt"
|
| 356 |
|
|
#cleanedDatExportFileName = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\_PrivLogQCProcess\20241122 - VEAS CAAG 20241206\export_20241122_160117_Converted.txt"
|
| 357 |
nino.borges |
833 |
#cleanedDatExportFileName = r"C:\Users\eborges\AppData\Local\Programs\Python\Python312\MyCode\JN\_Temp2\20241115_PrivLogWorking_CAAG\PrivLogExport_20241113_CAAG_Converted.txt"
|
| 358 |
|
|
#cleanedDatExportFileName = r"C:\Users\eborges\AppData\Local\Programs\Python\Python312\MyCode\JN\_Temp2\20241115_PrivLogWorking_CAAG\TEST.txt"
|
| 359 |
nino.borges |
828 |
|
| 360 |
|
|
## Code Testing
|
| 361 |
|
|
qcP = QcPrivLog(cleanedDatExportFileName)
|
| 362 |
nino.borges |
833 |
## print(qcP.metadataValuesDict['H55278-0268-003517'].fromValues)
|
| 363 |
|
|
## print(qcP.metadataValuesDict['H55278-0268-003517'].toValues)
|
| 364 |
|
|
## print(qcP.metadataValuesDict['H55278-0268-003517'].ccValues)
|
| 365 |
|
|
## print(qcP.metadataValuesDict['H55278-0268-003517'].bccValues)
|
| 366 |
|
|
## print(qcP.formattedValuesDict['H55278-0268-003517'].fromValues)
|
| 367 |
|
|
## print(qcP.formattedValuesDict['H55278-0268-003517'].toValues)
|
| 368 |
|
|
## print(qcP.formattedValuesDict['H55278-0268-003517'].ccValues)
|
| 369 |
|
|
## print(qcP.formattedValuesDict['H55278-0268-003517'].bccValues)
|
| 370 |
nino.borges |
828 |
|
| 371 |
|
|
qcP.PerformValueCountChecks(countsOnly = False)
|
| 372 |
|
|
|
| 373 |
|
|
|
