| 1 |
"""
|
| 2 |
|
| 3 |
Amazon-NamesNormQC
|
| 4 |
|
| 5 |
Created by:
|
| 6 |
Emanuel Borges
|
| 7 |
11.21.2024
|
| 8 |
|
| 9 |
This program will assist with the process of performing Names Normalization QC on the Amazon privilege logs.
|
| 10 |
|
| 11 |
"""
|
| 12 |
|
| 13 |
import os, uuid, pickle, re
|
| 14 |
import MyCode.Active_prgs.Redgrave.Amazon_PrivLogQC
|
| 15 |
from dataclasses import dataclass, field
|
| 16 |
from typing import List, Optional
|
| 17 |
from collections import namedtuple
|
| 18 |
from win32com.client import Dispatch
|
| 19 |
|
| 20 |
|
| 21 |
@dataclass
|
| 22 |
class Person:
|
| 23 |
first_name: Optional[str] = None
|
| 24 |
last_name: Optional[str] = None
|
| 25 |
work_email_address: Optional[str] = None
|
| 26 |
alt_work_email_address: Optional[str] = None
|
| 27 |
_id: uuid.UUID = field(default_factory=uuid.uuid4)
|
| 28 |
is_attorney: Optional[str] = None
|
| 29 |
split_role_date_range: Optional[str] = None
|
| 30 |
sidley_validated: Optional[str] = None
|
| 31 |
category: Optional[str] = None
|
| 32 |
organization: Optional[str] = None
|
| 33 |
job_title: Optional[str] = None
|
| 34 |
business_title: Optional[str] = None
|
| 35 |
full_name_preferred: Optional[str] = None
|
| 36 |
login: Optional[str] = None
|
| 37 |
department_fine: Optional[str] = None
|
| 38 |
addressed_during_caag: Optional[str] = None
|
| 39 |
|
| 40 |
def __post_init__(self):
|
| 41 |
"""Convert all string fields to uppercase."""
|
| 42 |
if self.first_name:
|
| 43 |
self.first_name = self.first_name.upper()
|
| 44 |
if self.last_name:
|
| 45 |
self.last_name = self.last_name.upper()
|
| 46 |
if self.work_email_address:
|
| 47 |
self.work_email_address = self.work_email_address.upper()
|
| 48 |
if self.alt_work_email_address:
|
| 49 |
self.alt_work_email_address = self.alt_work_email_address.upper()
|
| 50 |
if self.is_attorney:
|
| 51 |
self.is_attorney = self.is_attorney.upper()
|
| 52 |
if self.split_role_date_range:
|
| 53 |
self.split_role_date_range = self.split_role_date_range.upper()
|
| 54 |
if self.sidley_validated:
|
| 55 |
self.sidley_validated = self.sidley_validated.upper()
|
| 56 |
if self.category:
|
| 57 |
self.category = self.category.upper()
|
| 58 |
if self.organization:
|
| 59 |
self.organization = self.organization.upper()
|
| 60 |
if self.job_title:
|
| 61 |
self.job_title = self.job_title.upper()
|
| 62 |
if self.business_title:
|
| 63 |
self.business_title = self.business_title.upper()
|
| 64 |
if self.full_name_preferred:
|
| 65 |
self.full_name_preferred = self.full_name_preferred.upper()
|
| 66 |
if self.login:
|
| 67 |
self.login = self.login.upper()
|
| 68 |
if self.department_fine:
|
| 69 |
self.department_fine = self.department_fine.upper()
|
| 70 |
if self.addressed_during_caag:
|
| 71 |
self.addressed_during_caag = self.addressed_during_caag.upper()
|
| 72 |
|
| 73 |
@dataclass
|
| 74 |
class PeopleList:
|
| 75 |
people: List[Person] = field(default_factory=list)
|
| 76 |
|
| 77 |
def add_person(self, person: Person):
|
| 78 |
self.people.append(person)
|
| 79 |
#print(f"Added person: {person}")
|
| 80 |
|
| 81 |
|
| 82 |
def search_by_email(self, emailAddress:str) -> Optional[Person]:
|
| 83 |
for person in self.people:
|
| 84 |
if person.work_email_address == emailAddress:
|
| 85 |
return person
|
| 86 |
return None
|
| 87 |
|
| 88 |
def list_people(self):
|
| 89 |
for person in self.people:
|
| 90 |
print(person)
|
| 91 |
|
| 92 |
|
| 93 |
class NamesVerification(object):
|
| 94 |
"""A class for automating the process of performing QC on the names within the Amazon privilege logs."""
|
| 95 |
version = '0.2.0'
|
| 96 |
|
| 97 |
|
| 98 |
def __init__(self, cleanedDatExportFileName, masterAttorneyListFileName, forceNewPklFile = False, Encoding = 'UTF8'):
|
| 99 |
"""Initializes the data structures. cleanedDatExportFileName should be the full path to the file.
|
| 100 |
Assumes the first row of the data file is the header and first column is DocID.
|
| 101 |
Assumes the MAL is a spreadsheet (for now).
|
| 102 |
MAL gets saved to a pkl file for performance reasons. pkl will be used unless forceNewPklFile is set to true"""
|
| 103 |
pklFileName = os.path.splitext(masterAttorneyListFileName)[0] + ".pkl"
|
| 104 |
|
| 105 |
print("Initializing data structures...")
|
| 106 |
if forceNewPklFile:
|
| 107 |
print("Creating MAL structure...")
|
| 108 |
self.malPeopleList = PeopleList()
|
| 109 |
self.__IngestMALSpreadsheet(masterAttorneyListFileName)
|
| 110 |
print("MAL structure created.")
|
| 111 |
print("Creating pickle backup...")
|
| 112 |
self.__SaveMalToPkl(pklFileName)
|
| 113 |
print("Pickle backup created.")
|
| 114 |
else:
|
| 115 |
if os.path.exists(pklFileName):
|
| 116 |
print("Loading MAL structure from pickle file...")
|
| 117 |
self.malPeopleList = self.__LoadMalFromPkl(pklFileName)
|
| 118 |
print("MAL structure loaded.")
|
| 119 |
else:
|
| 120 |
print("Pickle file doesnt exist.")
|
| 121 |
print("Creating MAL structure...")
|
| 122 |
self.malPeopleList = PeopleList()
|
| 123 |
self.__IngestMALSpreadsheet(masterAttorneyListFileName)
|
| 124 |
print("MAL structure created.")
|
| 125 |
print("Creating pickle backup...")
|
| 126 |
self.__SaveMalToPkl(pklFileName)
|
| 127 |
print("Pickle backup created.")
|
| 128 |
|
| 129 |
## self.malPeopleList = PeopleList()
|
| 130 |
##
|
| 131 |
## print("Creating MAL structure...")
|
| 132 |
## self.__IngestMALSpreadsheet(masterAttorneyListFileName)
|
| 133 |
## print("MAL structure created.")
|
| 134 |
## print("Creating pickle backup...")
|
| 135 |
|
| 136 |
|
| 137 |
|
| 138 |
|
| 139 |
|
| 140 |
def __IngestMALSpreadsheet(self, masterAttorneyListFileName):
|
| 141 |
"""Pseudo-private method which will open an Excel spreadsheet and ingest the values into the peoplelist dataclass."""
|
| 142 |
## There doenst seem to be a consistent value in the "row" column in the MAL, so setting these parameters here to avoid gap issues.
|
| 143 |
|
| 144 |
excelTabParametersList = [{"tabName":"Attorneys", "beginRowNumber":2, "endRowNumber":10909, "beginColNumber":2, "endColNumber":16},
|
| 145 |
{"tabName":"Downgrades", "beginRowNumber":2, "endRowNumber":565, "beginColNumber":2, "endColNumber":15}]
|
| 146 |
|
| 147 |
# excelTabParametersList = [{"tabName":"Attorneys", "beginRowNumber":2, "endRowNumber":30, "beginColNumber":2, "endColNumber":16},
|
| 148 |
# {"tabName":"Downgrades", "beginRowNumber":2, "endRowNumber":30, "beginColNumber":2, "endColNumber":15}]
|
| 149 |
|
| 150 |
spreadsheetFileMappingMatrix = {"First Name":"first_name", "Last Name":"last_name", "Work Email":"work_email_address", "Alt Work Email":"alt_work_email_address", "Is Attorney": "is_attorney",
|
| 151 |
"Split Role - Attorney Capacity Date Range":"split_role_date_range", "Sidley Validated?":"sidley_validated", "Category": "category", "Organization":"organization", "Job Title":"job_title",
|
| 152 |
"Business Title":"business_title", "Full Name (Preferred)":"full_name_preferred", "Login":"login", "Department (Fine)":"department_fine", "Addressed during CAAG":"addressed_during_caag"}
|
| 153 |
|
| 154 |
xlApp = Dispatch('Excel.Application')
|
| 155 |
xlBook = xlApp.Workbooks.Open(masterAttorneyListFileName)
|
| 156 |
|
| 157 |
for excelTab in excelTabParametersList:
|
| 158 |
sht = xlBook.Worksheets(excelTab['tabName'])
|
| 159 |
print(f"Ingesting sheet {excelTab['tabName']}.")
|
| 160 |
excelFieldPositionMatrix = {}
|
| 161 |
for col in range (excelTab['beginColNumber'], excelTab['endColNumber'] +1):
|
| 162 |
excelFieldPositionMatrix[sht.Cells(1,col).Value] = col
|
| 163 |
for row in range(excelTab['beginRowNumber'], excelTab['endRowNumber'] +1):
|
| 164 |
#print(row)
|
| 165 |
## TODO: Refactor the excelTabParametersList later. Didnt realize columns were not consistent.
|
| 166 |
if excelTab['tabName'] == 'Attorneys':
|
| 167 |
self.malPeopleList.add_person(Person(is_attorney = sht.Cells(row,excelFieldPositionMatrix['Is Attorney']).Value,
|
| 168 |
split_role_date_range = sht.Cells(row,excelFieldPositionMatrix['Split Role - Attorney Capacity Date Range']).Value,
|
| 169 |
sidley_validated = sht.Cells(row,excelFieldPositionMatrix['Sidley Validated?']).Value,
|
| 170 |
category = sht.Cells(row,excelFieldPositionMatrix['Category']).Value,
|
| 171 |
organization = sht.Cells(row,excelFieldPositionMatrix['Organization']).Value,
|
| 172 |
last_name = sht.Cells(row,excelFieldPositionMatrix['Last Name']).Value,
|
| 173 |
first_name = sht.Cells(row,excelFieldPositionMatrix['First Name']).Value,
|
| 174 |
work_email_address = sht.Cells(row,excelFieldPositionMatrix['Work Email']).Value,
|
| 175 |
alt_work_email_address = sht.Cells(row,excelFieldPositionMatrix['Alt Work Email']).Value,
|
| 176 |
job_title = sht.Cells(row,excelFieldPositionMatrix['Job Title']).Value,
|
| 177 |
business_title = sht.Cells(row,excelFieldPositionMatrix['Business Title']).Value,
|
| 178 |
full_name_preferred = sht.Cells(row,excelFieldPositionMatrix['Full Name (Preferred)']).Value,
|
| 179 |
login = sht.Cells(row,excelFieldPositionMatrix['Login']).Value,
|
| 180 |
department_fine = sht.Cells(row,excelFieldPositionMatrix['Department (Fine)']).Value,
|
| 181 |
addressed_during_caag = sht.Cells(row,excelFieldPositionMatrix['Addressed during CAAG']).Value))
|
| 182 |
|
| 183 |
|
| 184 |
xlBook.Close()
|
| 185 |
|
| 186 |
def __SaveMalToPkl(self, pklFileName):
|
| 187 |
"""Pseudo-private method which will save the current MAL people list object to a pkl file, for performance reasons."""
|
| 188 |
outputFile = open(pklFileName,'wb')
|
| 189 |
pickle.dump(self.malPeopleList,outputFile)
|
| 190 |
outputFile.close()
|
| 191 |
|
| 192 |
def __LoadMalFromPkl(self, pklFileName):
|
| 193 |
"""Pseudo-private method which will load a MAL people list object from a pkl file, for performance reasons."""
|
| 194 |
contents = open(pklFileName, 'rb')
|
| 195 |
obj = pickle.load(contents)
|
| 196 |
contents.close()
|
| 197 |
return obj
|
| 198 |
|
| 199 |
|
| 200 |
if __name__ == '__main__':
|
| 201 |
#cleanedDatExportFileName = r"C:\Users\eborges\AppData\Local\Programs\Python\Python312\MyCode\JN\_Temp2\20241115_PrivLogWorking_CAAG\PrivLogExport_20241113_CAAG_Converted.txt"
|
| 202 |
cleanedDatExportFileName = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\_PrivLogQCProcess\20241122 - VEAS CAAG 20241206\export_20241122_160117_Converted.txt"
|
| 203 |
#cleanedDatExportFileName = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\_PrivLogQCProcess\20241122 - VEAS CAAG 20241206\TEST.txt"
|
| 204 |
masterAttorneyListFileName = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\_PrivLogQCProcess\Amazon_ Master Attorney List 2024.11.06(7045550.3).xlsx"
|
| 205 |
#masterAttorneyListFileName = r"C:\Test_Dir\Amazon\TEST-MAL.xlsx"
|
| 206 |
|
| 207 |
|
| 208 |
|
| 209 |
nv = NamesVerification(cleanedDatExportFileName, masterAttorneyListFileName)
|
| 210 |
#nv.malPeopleList.list_people()
|
| 211 |
|
| 212 |
qcP = MyCode.Active_prgs.Redgrave.Amazon_PrivLogQC.QcPrivLog(cleanedDatExportFileName)
|
| 213 |
#print(nv.malPeopleList.search_by_email('joyshine@amazon.com'.upper()))
|
| 214 |
workList = qcP.metadataValuesDict.keys()
|
| 215 |
outputFile = open(r"C:\Test_Dir\Amazon\NameNormOutputText.txt",'w')
|
| 216 |
for docID in workList:
|
| 217 |
metadataFieldValues = qcP.metadataValuesDict[docID]._asdict()['toValues']
|
| 218 |
formattedFieldValues = qcP.formattedValuesDict[docID]._asdict()['toValues']
|
| 219 |
formattedAttorneyValues = set()
|
| 220 |
for formattedValue in formattedFieldValues:
|
| 221 |
if "*" in formattedValue:
|
| 222 |
formattedAttorneyValues.add(formattedValue.upper())
|
| 223 |
|
| 224 |
if metadataFieldValues:
|
| 225 |
matchedMetadataValues = set()
|
| 226 |
for nameItem in metadataFieldValues:
|
| 227 |
## First test to see if there is a valid email address.
|
| 228 |
resultSet = set()
|
| 229 |
results = re.findall(qcP.allPossibleEmailAddressesRegExPattern, nameItem)
|
| 230 |
if results:
|
| 231 |
for result in results:
|
| 232 |
resultSet.add(result)
|
| 233 |
if len(resultSet) >1:
|
| 234 |
print("ERROR multiple email unique email addresses in one item.")
|
| 235 |
else:
|
| 236 |
personMatch = nv.malPeopleList.search_by_email(resultSet.pop().upper())
|
| 237 |
if personMatch:
|
| 238 |
if personMatch.full_name_preferred:
|
| 239 |
## Going to need to do a bit of replacing to remove some information that is just never in the formatted.
|
| 240 |
fullPreferredName = personMatch.full_name_preferred
|
| 241 |
fullPreferredName = fullPreferredName.replace('(LEGAL)','')
|
| 242 |
fullPreferredName = fullPreferredName.replace('(SHE, HER)','')
|
| 243 |
fullPreferredName = fullPreferredName.replace('(SHE HER)','')
|
| 244 |
preferedLastName, preferedFirstName = fullPreferredName.split(',')
|
| 245 |
preferedLastName = preferedLastName.strip()
|
| 246 |
preferedFirstName = preferedFirstName.strip()
|
| 247 |
preferedFirstName = preferedFirstName.split(" ")[0]
|
| 248 |
fullName = f"{preferedFirstName} {preferedLastName}"
|
| 249 |
else:
|
| 250 |
fullName = f"{personMatch.first_name} {personMatch.last_name}"
|
| 251 |
if personMatch.is_attorney == 'YES':
|
| 252 |
#outputFile.write(f"{docID} has match {personMatch.first_name} {personMatch.last_name}* ({personMatch.work_email_address.split('@')[-1]})\n")
|
| 253 |
matchedMetadataValues.add(f"{fullName}* ({personMatch.work_email_address.split('@')[-1]})")
|
| 254 |
else:
|
| 255 |
#outputFile.write(f"{docID} has match {personMatch.first_name} {personMatch.last_name} ({personMatch.work_email_address.split('@')[-1]})\n")
|
| 256 |
matchedMetadataValues.add(f"{fullName} ({personMatch.work_email_address.split('@')[-1]})")
|
| 257 |
else:
|
| 258 |
outputFile.write(f"{docID} contains a non-email item {nameItem}\n")
|
| 259 |
missingFromFormatted = matchedMetadataValues - formattedAttorneyValues
|
| 260 |
missingFromMeta = formattedAttorneyValues - matchedMetadataValues
|
| 261 |
if missingFromFormatted:
|
| 262 |
for missingItem in missingFromFormatted:
|
| 263 |
outputFile.write(f"{docID} has {missingItem} missing from the formatted field\n")
|
| 264 |
if missingFromMeta:
|
| 265 |
for missingItem in missingFromMeta:
|
| 266 |
outputFile.write(f"{docID} has {missingItem} missing from the metadata field\n")
|
| 267 |
if missingFromFormatted:
|
| 268 |
outputFile.write("\n")
|
| 269 |
elif missingFromMeta:
|
| 270 |
outputFile.write("\n")
|
| 271 |
outputFile.close()
|
| 272 |
|
| 273 |
|
| 274 |
|
| 275 |
|
| 276 |
## people_list = PeopleList()
|
| 277 |
## people_list.add_person(Person(firstName = "Sally", lastName = "Smith", workEmailAddress = "fooBar@gmail.com", altWorkEmailAddress = ""))
|
| 278 |
## people_list.add_person(Person(firstName = "Gary", lastName = "Cooper", workEmailAddress = "", altWorkEmailAddress = "spam.eggs@hotmail.com"))
|
| 279 |
## people_list.add_person(Person(firstName = "", lastName = "", workEmailAddress = "noname@gmail.com", altWorkEmailAddress = ""))
|
| 280 |
## people_list.add_person(Person(firstName = "Sally", lastName = "Smith", workEmailAddress = "eggs@outlook.com", altWorkEmailAddress = ""))
|
| 281 |
## print("\nAll People:")
|
| 282 |
## people_list.list_people()
|
| 283 |
## print("\nSearching...")
|
| 284 |
## result = people_list.search_by_email('fooBar@gmail.com')
|
| 285 |
## print(result if result else "email not found.") |
