| 1 |
nino.borges |
913 |
"""
|
| 2 |
|
|
|
| 3 |
|
|
ATT_MasterAttorneyList
|
| 4 |
|
|
|
| 5 |
|
|
Created by:
|
| 6 |
|
|
Emanuel Borges
|
| 7 |
|
|
07.14.2025
|
| 8 |
|
|
|
| 9 |
|
|
A library for the creation and management of the ATT MAL.
|
| 10 |
|
|
|
| 11 |
|
|
"""
|
| 12 |
|
|
|
| 13 |
|
|
import os, uuid, pickle, re
|
| 14 |
nino.borges |
951 |
#import dill as pickle
|
| 15 |
nino.borges |
913 |
from dataclasses import dataclass, field, fields
|
| 16 |
|
|
from typing import List, Tuple, Optional
|
| 17 |
|
|
from collections import namedtuple
|
| 18 |
|
|
from win32com.client import Dispatch
|
| 19 |
|
|
|
| 20 |
|
|
|
| 21 |
nino.borges |
973 |
version = "1.3"
|
| 22 |
nino.borges |
913 |
|
| 23 |
|
|
@dataclass
|
| 24 |
|
|
class Person:
|
| 25 |
|
|
first_name: Optional[str] = None
|
| 26 |
|
|
last_name: Optional[str] = None
|
| 27 |
|
|
alt_first_name: Optional[str] = None
|
| 28 |
|
|
## TODO: Make these email addresses lists instead of strings
|
| 29 |
|
|
work_email_addresses: Optional[str] = None
|
| 30 |
|
|
#alt_work_email_addresses: Optional[str] = None
|
| 31 |
|
|
raw_email_addresses: Optional[str] = None
|
| 32 |
|
|
_id: uuid.UUID = field(default_factory=uuid.uuid4)
|
| 33 |
|
|
is_attorney: Optional[str] = None
|
| 34 |
|
|
split_role_date_range: Optional[str] = None
|
| 35 |
|
|
middle_initial: Optional[str] = None
|
| 36 |
|
|
company: Optional[str] = None
|
| 37 |
|
|
category: Optional[str] = None
|
| 38 |
|
|
job_title: Optional[str] = None
|
| 39 |
|
|
full_name_preferred: Optional[str] = None
|
| 40 |
nino.borges |
916 |
lh_normalized_name: Optional[str] = None
|
| 41 |
nino.borges |
913 |
user_id: Optional[str] = None
|
| 42 |
|
|
full_name_overide: Optional[str] = None
|
| 43 |
|
|
## Only gather unique_attorney_row_number from the attorney and split role attorney tabs. NEVER from Non-Attorneys.
|
| 44 |
|
|
unique_attorney_row_number:Optional[str] = None
|
| 45 |
|
|
## Will be saving this as a list of tuple pairs (startdate,enddate). Allowing None for now but may update this to forcing an empty list, to avoid mutable default issues.
|
| 46 |
|
|
dates_as_counsel:Optional[List[Tuple[str,str]]] = None
|
| 47 |
|
|
|
| 48 |
|
|
def __post_init__(self):
|
| 49 |
|
|
"""Convert all string fields to uppercase."""
|
| 50 |
|
|
if self.first_name:
|
| 51 |
|
|
self.first_name = self.first_name.strip().upper()
|
| 52 |
|
|
if self.alt_first_name:
|
| 53 |
|
|
self.alt_first_name = self.alt_first_name.strip().upper()
|
| 54 |
|
|
if self.last_name:
|
| 55 |
|
|
self.last_name = self.last_name.strip().upper()
|
| 56 |
|
|
if self.work_email_addresses:
|
| 57 |
|
|
self.work_email_addresses = self.work_email_addresses.strip().upper()
|
| 58 |
|
|
## if self.alt_work_email_addresses:
|
| 59 |
|
|
## self.alt_work_email_addresses = self.alt_work_email_addresses.strip().upper()
|
| 60 |
|
|
if self.raw_email_addresses:
|
| 61 |
|
|
self.raw_email_addresses = self.raw_email_addresses.strip().upper()
|
| 62 |
|
|
if self.is_attorney:
|
| 63 |
|
|
self.is_attorney = self.is_attorney.strip().upper()
|
| 64 |
|
|
if self.split_role_date_range:
|
| 65 |
|
|
self.split_role_date_range = self.split_role_date_range.strip().upper()
|
| 66 |
|
|
if self.middle_initial:
|
| 67 |
|
|
self.middle_initial = self.middle_initial.strip().upper()
|
| 68 |
|
|
if self.company:
|
| 69 |
|
|
self.company = self.company.strip().upper()
|
| 70 |
|
|
if self.category:
|
| 71 |
|
|
self.category = self.category.strip().upper()
|
| 72 |
|
|
if self.job_title:
|
| 73 |
|
|
self.job_title = self.job_title.strip().upper()
|
| 74 |
|
|
if self.full_name_preferred:
|
| 75 |
|
|
self.full_name_preferred = self.full_name_preferred.strip().upper()
|
| 76 |
nino.borges |
916 |
if self.lh_normalized_name:
|
| 77 |
|
|
self.lh_normalized_name = self.lh_normalized_name.strip().upper()
|
| 78 |
nino.borges |
913 |
if self.user_id:
|
| 79 |
|
|
self.user_id = self.user_id.strip().upper()
|
| 80 |
|
|
|
| 81 |
|
|
|
| 82 |
|
|
@dataclass
|
| 83 |
|
|
class PeopleList:
|
| 84 |
|
|
people: List[Person] = field(default_factory=list)
|
| 85 |
|
|
|
| 86 |
|
|
def add_person(self, person: Person):
|
| 87 |
|
|
self.people.append(person)
|
| 88 |
|
|
#print(f"Added person: {person}")
|
| 89 |
|
|
|
| 90 |
|
|
|
| 91 |
|
|
def search_by_email(self, emailAddress:str) -> Optional[Person]:
|
| 92 |
|
|
"""Returns the first matching emailAddress value. Assumes emailAddresses are unique"""
|
| 93 |
|
|
for person in self.people:
|
| 94 |
nino.borges |
951 |
if person.work_email_addresses:
|
| 95 |
|
|
#print(person.work_email_addresses)
|
| 96 |
|
|
personEmailAddresses = person.work_email_addresses.split(";\n")
|
| 97 |
|
|
personEmailAddresses = [x.strip() for x in personEmailAddresses]
|
| 98 |
|
|
if emailAddress in personEmailAddresses:
|
| 99 |
|
|
#if person.work_email_addresses == emailAddress:
|
| 100 |
|
|
return person
|
| 101 |
|
|
## elif person.alt_work_email_addresses == emailAddress:
|
| 102 |
|
|
## return person
|
| 103 |
nino.borges |
913 |
return None
|
| 104 |
|
|
|
| 105 |
nino.borges |
951 |
def search_by_login_id(self, loginID:str) -> Optional[Person]:
|
| 106 |
|
|
"""Returns the first matching login user id value. Assumes login user ids are unique"""
|
| 107 |
|
|
for person in self.people:
|
| 108 |
|
|
if person.user_id:
|
| 109 |
|
|
personLoginIds = person.user_id.split(";\n")
|
| 110 |
|
|
personLoginIds = [x.strip() for x in personLoginIds]
|
| 111 |
|
|
if loginID in personLoginIds:
|
| 112 |
|
|
return person
|
| 113 |
|
|
return None
|
| 114 |
nino.borges |
913 |
|
| 115 |
|
|
def search_by_unique_attorney_row_number(self,uniqueAttorneyRowNumber:str) -> Optional[Person]:
|
| 116 |
|
|
"""Returns the first matching uniqueAttorneyRowNumber value. Assumes uniqueAttorneyRowNumbers are unique"""
|
| 117 |
|
|
for person in self.people:
|
| 118 |
|
|
if person.unique_attorney_row_number == uniqueAttorneyRowNumber:
|
| 119 |
|
|
return person
|
| 120 |
|
|
return None
|
| 121 |
|
|
|
| 122 |
|
|
def search_by_id(self, idNumber):
|
| 123 |
|
|
"""Returns the first matching idNumber value. Must be in format UUID('7414f78c-8289-4c9f-bd49-a5aaac35545f')."""
|
| 124 |
|
|
for person in self.people:
|
| 125 |
|
|
if person._id == idNumber:
|
| 126 |
|
|
return person
|
| 127 |
|
|
return None
|
| 128 |
|
|
|
| 129 |
|
|
def return_list_of_matching_values(self,fieldName, value:str):
|
| 130 |
|
|
"""Returns a full list of items where value is found in fieldName"""
|
| 131 |
|
|
matchingPeopleList = []
|
| 132 |
|
|
for person in self.people:
|
| 133 |
nino.borges |
916 |
personVals = getattr(person,fieldName)
|
| 134 |
|
|
if personVals:
|
| 135 |
|
|
personVals = personVals.split(";\n")
|
| 136 |
|
|
personVals = [x.strip() for x in personVals]
|
| 137 |
|
|
if value in personVals:
|
| 138 |
|
|
matchingPeopleList.append(person)
|
| 139 |
nino.borges |
913 |
return matchingPeopleList
|
| 140 |
|
|
|
| 141 |
|
|
def list_people(self):
|
| 142 |
|
|
for person in self.people:
|
| 143 |
|
|
print(person)
|
| 144 |
|
|
|
| 145 |
|
|
def update_full_Name_overide(self, emailAddress:str, fullNameOverideValue) -> Optional[Person]:
|
| 146 |
|
|
valueUpdated = False
|
| 147 |
|
|
for person in self.people:
|
| 148 |
|
|
if person.work_email_addresses == emailAddress.upper():
|
| 149 |
|
|
person.full_name_overide = fullNameOverideValue.upper()
|
| 150 |
|
|
valueUpdated = True
|
| 151 |
|
|
## Give a quik warning as you add the override value into the database if the last name differs.
|
| 152 |
|
|
if "," in fullNameOverideValue:
|
| 153 |
|
|
lastName = fullNameOverideValue.split(",")[0]
|
| 154 |
|
|
else:
|
| 155 |
|
|
lastName = fullNameOverideValue.split(" ")[-1]
|
| 156 |
|
|
if lastName.upper() == person.last_name:
|
| 157 |
|
|
pass
|
| 158 |
|
|
else:
|
| 159 |
|
|
print(f"WARNING: Overide last name value {lastName.upper()} does not match {person.last_name}.")
|
| 160 |
|
|
if valueUpdated == False:
|
| 161 |
|
|
print(f"WARNING: No email address match for {emailAddress} found.")
|
| 162 |
|
|
|
| 163 |
nino.borges |
916 |
def return_person_all_name_variations(self, person):
|
| 164 |
|
|
"""This will take a matched person and return a large list of all of the possible full name variations"""
|
| 165 |
nino.borges |
951 |
last = person.last_name.strip() if person.last_name else None
|
| 166 |
|
|
firsts = [person.first_name.strip() if person.first_name else None]
|
| 167 |
nino.borges |
916 |
if person.alt_first_name:
|
| 168 |
|
|
firsts.append(person.alt_first_name.strip())
|
| 169 |
|
|
|
| 170 |
|
|
middle = person.middle_initial.replace(".","").strip() if person.middle_initial else None
|
| 171 |
|
|
|
| 172 |
|
|
combos = set() ## Using a set here to avoid dupes.
|
| 173 |
|
|
|
| 174 |
|
|
for first in firsts:
|
| 175 |
|
|
## Some basic combinations
|
| 176 |
|
|
combos.add(f"{first} {last}")
|
| 177 |
|
|
combos.add(f"{last} {first}")
|
| 178 |
|
|
combos.add(f"{last}, {first}")
|
| 179 |
|
|
|
| 180 |
|
|
## Include middle initial variations if it exists
|
| 181 |
|
|
if middle:
|
| 182 |
|
|
combos.add(f"{first} {middle} {last}")
|
| 183 |
|
|
combos.add(f"{last} {first} {middle}")
|
| 184 |
|
|
combos.add(f"{last}, {first} {middle}")
|
| 185 |
|
|
combos.add(f"{first} {middle}. {last}")
|
| 186 |
|
|
combos.add(f"{last} {first} {middle}.")
|
| 187 |
|
|
combos.add(f"{last}, {first} {middle}.")
|
| 188 |
|
|
|
| 189 |
nino.borges |
951 |
fNamePrefered = person.full_name_preferred
|
| 190 |
|
|
if fNamePrefered:
|
| 191 |
|
|
fNamePrefered = fNamePrefered.split(";\n")
|
| 192 |
|
|
fNamePrefered = [x.strip() for x in fNamePrefered]
|
| 193 |
|
|
combos.update(fNamePrefered)
|
| 194 |
|
|
if person.lh_normalized_name:
|
| 195 |
|
|
combos.add(person.lh_normalized_name.strip())
|
| 196 |
|
|
## Want to add the LH version of the name without the ESQ here.
|
| 197 |
|
|
combos.add(person.lh_normalized_name.upper().replace("(ESQ.)","").strip())
|
| 198 |
nino.borges |
916 |
return list(combos)
|
| 199 |
|
|
|
| 200 |
nino.borges |
973 |
|
| 201 |
|
|
def return_str_string(self, person):## TODO: add similar names support soon includeSimilarNamesExclusion = True):
|
| 202 |
|
|
"""returns the STR search string for a given person."""
|
| 203 |
|
|
namesList = []
|
| 204 |
|
|
#emailAddrList = []
|
| 205 |
|
|
emailAddrSet = set()
|
| 206 |
|
|
firstNamesSet = set()
|
| 207 |
|
|
lastNamesSet = set()
|
| 208 |
|
|
|
| 209 |
|
|
if person.last_name:
|
| 210 |
|
|
lastNamesSet.add(person.last_name)
|
| 211 |
|
|
## if person.alt_surnames:
|
| 212 |
|
|
## for lastName in person.alt_surnames.split(";\n"):
|
| 213 |
|
|
## lastNamesSet.add(lastName)
|
| 214 |
|
|
if person.first_name:
|
| 215 |
|
|
firstNamesSet.add(person.first_name)
|
| 216 |
|
|
if person.alt_first_name:
|
| 217 |
|
|
firstNamesSet.add(person.alt_first_name)
|
| 218 |
|
|
if person.full_name_preferred:
|
| 219 |
|
|
person.full_name_preferred = person.full_name_preferred.replace('(SHE, HER)',"(SHE HER)")
|
| 220 |
|
|
person.full_name_preferred = person.full_name_preferred.replace(",(LEGAL),"," (LEGAL),")
|
| 221 |
|
|
if "," in person.full_name_preferred:
|
| 222 |
|
|
parsedLast, parsedFirst = person.full_name_preferred.split(",", 1)
|
| 223 |
|
|
else:
|
| 224 |
|
|
parsedLast = person.full_name_preferred.split(" ")[-1]
|
| 225 |
|
|
parsedFirst = person.full_name_preferred.split(" ")[:-1]
|
| 226 |
|
|
parsedFirst = " ".join(parsedFirst)
|
| 227 |
|
|
lastNamesSet.add(parsedLast.strip())
|
| 228 |
|
|
firstNamesSet.add(parsedFirst.strip())
|
| 229 |
|
|
|
| 230 |
|
|
## within all values in both the first name and last name sets, replace any open or close parenthesis with a space.
|
| 231 |
|
|
firstNamesSet = {fn.replace("("," ").replace(")"," ") for fn in firstNamesSet}
|
| 232 |
|
|
lastNamesSet = {ln.replace("("," ").replace(")"," ") for ln in lastNamesSet}
|
| 233 |
|
|
|
| 234 |
|
|
if len(lastNamesSet) >1:
|
| 235 |
|
|
namesList.append(f'({" OR ".join((lastNamesSet))})')
|
| 236 |
|
|
elif len(lastNamesSet) == 1:
|
| 237 |
|
|
namesList.append(list(lastNamesSet)[0])
|
| 238 |
|
|
if len(firstNamesSet) >1:
|
| 239 |
|
|
namesList.append(f'({" OR ".join((firstNamesSet))})')
|
| 240 |
|
|
elif len(firstNamesSet) == 1:
|
| 241 |
|
|
namesList.append(list(firstNamesSet)[0])
|
| 242 |
|
|
|
| 243 |
|
|
|
| 244 |
|
|
withinWordCount = len(str(firstNamesSet).split(" ")) + len(str(lastNamesSet).split(" "))
|
| 245 |
|
|
withinPhrase = f' W/{str(withinWordCount)} '
|
| 246 |
|
|
|
| 247 |
|
|
|
| 248 |
|
|
## Assembling the list of email addresses and possibly adding the international domain parts.
|
| 249 |
|
|
if person.work_email_addresses:
|
| 250 |
|
|
emailAddrSet.add(person.work_email_addresses)
|
| 251 |
|
|
## if includeInternationalDomains:
|
| 252 |
|
|
## ## They elected to add the additional international domain parts.
|
| 253 |
|
|
## for addr in list(emailAddrSet):
|
| 254 |
|
|
## addrDomain = addr.split("@")[-1]
|
| 255 |
|
|
## if addrDomain in self.internationalEmailDomainsSet:
|
| 256 |
|
|
## for intDomain in self.internationalEmailDomainsSet:
|
| 257 |
|
|
## emailAddrSet.add(addr.replace(addrDomain, intDomain))
|
| 258 |
|
|
|
| 259 |
|
|
|
| 260 |
|
|
emailAddrList = list(emailAddrSet)
|
| 261 |
|
|
|
| 262 |
|
|
if namesList:
|
| 263 |
|
|
if emailAddrList:
|
| 264 |
|
|
if len(emailAddrList) >1:
|
| 265 |
|
|
strText = f"({withinPhrase.join(namesList)}) OR ({' OR '.join(emailAddrList)})"
|
| 266 |
|
|
else:
|
| 267 |
|
|
strText = f"({withinPhrase.join(namesList)}) OR {' OR '.join(emailAddrList)}"
|
| 268 |
|
|
else:
|
| 269 |
|
|
strText = f"{withinPhrase.join(namesList)}"
|
| 270 |
|
|
else:
|
| 271 |
|
|
if emailAddrList:
|
| 272 |
|
|
strText = f"{' OR '.join(emailAddrList)}"
|
| 273 |
|
|
else:
|
| 274 |
|
|
strText = "NONE"
|
| 275 |
|
|
|
| 276 |
|
|
if person.user_id:
|
| 277 |
|
|
## Only consider the login if it's longer than 4 characters. We may adjust this cutoff to more than 5 in the future.
|
| 278 |
|
|
if len(person.user_id) > 4:
|
| 279 |
|
|
if person.user_id in str(namesList):
|
| 280 |
|
|
pass
|
| 281 |
|
|
else:
|
| 282 |
|
|
strText = strText + f" OR {person.user_id.lower()}"
|
| 283 |
|
|
|
| 284 |
|
|
|
| 285 |
|
|
## if includeSimilarNamesExclusion:
|
| 286 |
|
|
## ## This will check the similar_names value for the person and will add the NOT clause at the end.
|
| 287 |
|
|
## if person.similar_names:
|
| 288 |
|
|
## #print("Similar names for this person exists")
|
| 289 |
|
|
## similarNamesEmailList = []
|
| 290 |
|
|
## similarNamesIDList = person.similar_names
|
| 291 |
|
|
## for sID in similarNamesIDList:
|
| 292 |
|
|
## sPerson = self.search_by_id(sID)
|
| 293 |
|
|
## if sPerson.work_email_address:
|
| 294 |
|
|
## similarNamesEmailList.append(sPerson.work_email_address)
|
| 295 |
|
|
## if sPerson.alt_work_email_address:
|
| 296 |
|
|
## similarNamesEmailList.append(sPerson.alt_work_email_address)
|
| 297 |
|
|
## strText = f"({strText}) NOT W/2 ({' OR '.join(similarNamesEmailList)})"
|
| 298 |
|
|
|
| 299 |
|
|
return strText
|
| 300 |
|
|
|
| 301 |
nino.borges |
913 |
class ATT_MasterAttorneyList(object):
|
| 302 |
|
|
"""A class for building and performing functions against the ATT Master Attorney List."""
|
| 303 |
|
|
version = '0.01.0'
|
| 304 |
|
|
|
| 305 |
|
|
|
| 306 |
|
|
def __init__(self, masterAttorneyListFileName,fullNameOveridesFileName = False, forceNewPklFile = False, Encoding = 'UTF8'):
|
| 307 |
|
|
"""Assumes the MAL is a spreadsheet (for now).MAL gets saved to a pkl file for performance reasons. pkl will be used unless forceNewPklFile is set to true"""
|
| 308 |
|
|
pklFileName = os.path.splitext(masterAttorneyListFileName)[0] + ".pkl"
|
| 309 |
|
|
|
| 310 |
|
|
print("Initializing data structures...")
|
| 311 |
|
|
if forceNewPklFile:
|
| 312 |
|
|
print("Creating MAL structure...")
|
| 313 |
|
|
self.malPeopleList = PeopleList()
|
| 314 |
|
|
self.__IngestMALSpreadsheet(masterAttorneyListFileName)
|
| 315 |
|
|
print("MAL structure created.")
|
| 316 |
|
|
if fullNameOveridesFileName:
|
| 317 |
|
|
print("Loading full name overide values...")
|
| 318 |
|
|
self.__LoadFullNameOverideValues(fullNameOveridesFileName)
|
| 319 |
|
|
print("Full name overide values loaded.")
|
| 320 |
|
|
print("Creating pickle backup...")
|
| 321 |
|
|
self.__SaveMalToPkl(pklFileName)
|
| 322 |
|
|
print("Pickle backup created.")
|
| 323 |
|
|
else:
|
| 324 |
|
|
if os.path.exists(pklFileName):
|
| 325 |
|
|
print("Loading MAL structure from pickle file...")
|
| 326 |
|
|
self.malPeopleList = self.__LoadMalFromPkl(pklFileName)
|
| 327 |
|
|
print("MAL structure loaded.")
|
| 328 |
|
|
else:
|
| 329 |
|
|
print("Pickle file doesnt exist.")
|
| 330 |
|
|
print("Creating MAL structure...")
|
| 331 |
|
|
self.malPeopleList = PeopleList()
|
| 332 |
|
|
self.__IngestMALSpreadsheet(masterAttorneyListFileName)
|
| 333 |
|
|
print("MAL structure created.")
|
| 334 |
|
|
if fullNameOveridesFileName:
|
| 335 |
|
|
print("Loading full name overide values...")
|
| 336 |
|
|
self.__LoadFullNameOverideValues(fullNameOveridesFileName)
|
| 337 |
|
|
print("Full name overide values loaded.")
|
| 338 |
|
|
print("Creating pickle backup...")
|
| 339 |
|
|
self.__SaveMalToPkl(pklFileName)
|
| 340 |
|
|
print("Pickle backup created.")
|
| 341 |
|
|
|
| 342 |
|
|
|
| 343 |
|
|
def __IngestMALSpreadsheet(self, masterAttorneyListFileName):
|
| 344 |
|
|
"""Pseudo-private method which will open an Excel spreadsheet and ingest the values into the peoplelist dataclass."""
|
| 345 |
|
|
## There doenst seem to be a consistent value in the "row" column in the MAL, so setting these parameters here to avoid gap issues.
|
| 346 |
|
|
|
| 347 |
|
|
## excelTabParametersList should always be an ordered list because now order matters.
|
| 348 |
nino.borges |
973 |
excelTabParametersList = [{"tabName":"Attorneys", "beginRowNumber":2, "endRowNumber":2534, "beginColNumber":1, "endColNumber":19},
|
| 349 |
|
|
{"tabName":"Non-Attorneys", "beginRowNumber":2, "endRowNumber":3435, "beginColNumber":1, "endColNumber":19},
|
| 350 |
nino.borges |
913 |
{"tabName":"Split Role Attorneys", "beginRowNumber":2, "endRowNumber":21, "beginColNumber":1, "endColNumber":10}]
|
| 351 |
|
|
|
| 352 |
|
|
|
| 353 |
|
|
# 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",
|
| 354 |
|
|
# "Split Role - Attorney Capacity Date Range":"split_role_date_range", " Validated by OC??":"sidley_validated", "Category": "category", "Organization":"organization", "Job Title":"job_title",
|
| 355 |
|
|
# "Business Title":"business_title", "Full Name (Preferred)":"full_name_preferred", "Login":"login", "Department (Fine)":"department_fine", "Addressed during CAAG":"addressed_during_caag",
|
| 356 |
|
|
# "Last Updated":"last_updated"}
|
| 357 |
|
|
|
| 358 |
|
|
xlApp = Dispatch('Excel.Application')
|
| 359 |
|
|
xlBook = xlApp.Workbooks.Open(masterAttorneyListFileName)
|
| 360 |
|
|
|
| 361 |
|
|
for excelTab in excelTabParametersList:
|
| 362 |
|
|
sht = xlBook.Worksheets(excelTab['tabName'])
|
| 363 |
|
|
print(f"Ingesting sheet {excelTab['tabName']}.")
|
| 364 |
|
|
excelFieldPositionMatrix = {}
|
| 365 |
|
|
for col in range (excelTab['beginColNumber'], excelTab['endColNumber'] +1):
|
| 366 |
|
|
excelFieldPositionMatrix[sht.Cells(1,col).Value] = col
|
| 367 |
|
|
for row in range(excelTab['beginRowNumber'], excelTab['endRowNumber'] +1):
|
| 368 |
|
|
#print(row)
|
| 369 |
|
|
## TODO: Refactor the excelTabParametersList later. Didnt realize columns were not consistent.
|
| 370 |
|
|
if excelTab['tabName'] == 'Attorneys':
|
| 371 |
|
|
self.malPeopleList.add_person(Person(is_attorney = sht.Cells(row,excelFieldPositionMatrix['Is Attorney']).Value,
|
| 372 |
|
|
#split_role_date_range = sht.Cells(row,excelFieldPositionMatrix['Split Role - Dates as Counsel']).Value,
|
| 373 |
|
|
company = sht.Cells(row,excelFieldPositionMatrix['Company']).Value,
|
| 374 |
|
|
category = sht.Cells(row,excelFieldPositionMatrix['Category']).Value,
|
| 375 |
|
|
last_name = sht.Cells(row,excelFieldPositionMatrix['Last Name']).Value,
|
| 376 |
|
|
first_name = sht.Cells(row,excelFieldPositionMatrix['First Name']).Value,
|
| 377 |
|
|
alt_first_name = sht.Cells(row,excelFieldPositionMatrix['Alt First Name']).Value,
|
| 378 |
|
|
middle_initial = sht.Cells(row,excelFieldPositionMatrix['Middle Initial']).Value,
|
| 379 |
|
|
work_email_addresses = sht.Cells(row,excelFieldPositionMatrix['Email Addresses']).Value,
|
| 380 |
|
|
#alt_work_email_address = sht.Cells(row,excelFieldPositionMatrix['Alt Work Email']).Value,
|
| 381 |
|
|
raw_email_addresses = sht.Cells(row,excelFieldPositionMatrix['EmailAddress RAW']).Value,
|
| 382 |
|
|
job_title = sht.Cells(row,excelFieldPositionMatrix['Title']).Value,
|
| 383 |
|
|
full_name_preferred = sht.Cells(row,excelFieldPositionMatrix['Full Name (Preferred)']).Value,
|
| 384 |
nino.borges |
916 |
lh_normalized_name = sht.Cells(row,excelFieldPositionMatrix['Lighthouse Normalized Name']).Value,
|
| 385 |
nino.borges |
913 |
user_id = sht.Cells(row,excelFieldPositionMatrix['UserID']).Value,
|
| 386 |
nino.borges |
916 |
unique_attorney_row_number = sht.Cells(row,excelFieldPositionMatrix['MAL ID']).Value))
|
| 387 |
nino.borges |
913 |
|
| 388 |
|
|
elif excelTab['tabName'] == 'Non-Attorneys':
|
| 389 |
|
|
## Make sure to NOT grab the unique attorney row number from here
|
| 390 |
|
|
self.malPeopleList.add_person(Person(is_attorney = sht.Cells(row,excelFieldPositionMatrix['Is Attorney']).Value,
|
| 391 |
|
|
#split_role_date_range = sht.Cells(row,excelFieldPositionMatrix['Split Role - Dates as Counsel']).Value,
|
| 392 |
|
|
company = sht.Cells(row,excelFieldPositionMatrix['Company']).Value,
|
| 393 |
|
|
category = sht.Cells(row,excelFieldPositionMatrix['Category']).Value,
|
| 394 |
|
|
last_name = sht.Cells(row,excelFieldPositionMatrix['Last Name']).Value,
|
| 395 |
|
|
first_name = sht.Cells(row,excelFieldPositionMatrix['First Name']).Value,
|
| 396 |
|
|
alt_first_name = sht.Cells(row,excelFieldPositionMatrix['Alt First Name']).Value,
|
| 397 |
|
|
middle_initial = sht.Cells(row,excelFieldPositionMatrix['Middle Initial']).Value,
|
| 398 |
|
|
work_email_addresses = sht.Cells(row,excelFieldPositionMatrix['Email Addresses']).Value,
|
| 399 |
|
|
#alt_work_email_address = sht.Cells(row,excelFieldPositionMatrix['Alt Work Email']).Value,
|
| 400 |
|
|
raw_email_addresses = sht.Cells(row,excelFieldPositionMatrix['EmailAddress RAW']).Value,
|
| 401 |
|
|
job_title = sht.Cells(row,excelFieldPositionMatrix['Title']).Value,
|
| 402 |
|
|
full_name_preferred = sht.Cells(row,excelFieldPositionMatrix['Full Name (Preferred)']).Value,
|
| 403 |
nino.borges |
916 |
lh_normalized_name = sht.Cells(row,excelFieldPositionMatrix['Lighthouse Normalized Name']).Value,
|
| 404 |
nino.borges |
913 |
user_id = sht.Cells(row,excelFieldPositionMatrix['UserID']).Value,
|
| 405 |
nino.borges |
916 |
unique_attorney_row_number = sht.Cells(row,excelFieldPositionMatrix['MAL ID']).Value))
|
| 406 |
nino.borges |
913 |
elif excelTab['tabName'] == 'Split Role Attorneys':
|
| 407 |
|
|
## Skip this tab for now.
|
| 408 |
|
|
pass
|
| 409 |
|
|
## unique_attorney_row_number = sht.Cells(row,excelFieldPositionMatrix['Attorney Row']).Value
|
| 410 |
|
|
## matchedPerson = self.malPeopleList.search_by_unique_attorney_row_number(unique_attorney_row_number)
|
| 411 |
|
|
## if matchedPerson:
|
| 412 |
|
|
##
|
| 413 |
|
|
## ## dates_as_counsel should always be a two string value tuple (startdate,enddate).
|
| 414 |
|
|
## datesAsCounselValue = sht.Cells(row,excelFieldPositionMatrix['Dates as Counsel']).Value
|
| 415 |
|
|
## datesAsCounselList = []
|
| 416 |
|
|
## ## First get rid of any extra data that is on a new line. Note that they shouldnt be seperating the date ranges by newline.
|
| 417 |
|
|
## datesAsCounselValue = datesAsCounselValue.split("\n")[0]
|
| 418 |
|
|
## ## Next split the ranges correctly by semicolon
|
| 419 |
|
|
## dateRanges = datesAsCounselValue.split(";")
|
| 420 |
|
|
## for dateRange in dateRanges:
|
| 421 |
|
|
## ## Split out the start and end, allowing non-date words. (current, present, etc) however force these to be uppercase.
|
| 422 |
|
|
## counselStartDate, counselEndDate = dateRange.split("-")
|
| 423 |
|
|
## counselStartDate = counselStartDate.upper().strip()
|
| 424 |
|
|
## counselEndDate = counselEndDate.upper().strip()
|
| 425 |
|
|
## datesAsCounselList.append((counselStartDate,counselEndDate))
|
| 426 |
|
|
## matchedPerson.dates_as_counsel = datesAsCounselList
|
| 427 |
|
|
|
| 428 |
|
|
else:
|
| 429 |
|
|
print(f"ERROR UNKNOWN TAB! {excelTab['tabName']} HAVE NEEDED TAB NAMES CHANGED?")
|
| 430 |
|
|
|
| 431 |
|
|
|
| 432 |
|
|
xlBook.Close()
|
| 433 |
|
|
|
| 434 |
|
|
|
| 435 |
|
|
|
| 436 |
|
|
def __SaveMalToPkl(self, pklFileName):
|
| 437 |
|
|
"""Pseudo-private method which will save the current MAL people list object to a pkl file, for performance reasons."""
|
| 438 |
|
|
outputFile = open(pklFileName,'wb')
|
| 439 |
|
|
pickle.dump(self.malPeopleList,outputFile)
|
| 440 |
|
|
outputFile.close()
|
| 441 |
|
|
|
| 442 |
|
|
def __LoadMalFromPkl(self, pklFileName):
|
| 443 |
|
|
"""Pseudo-private method which will load a MAL people list object from a pkl file, for performance reasons."""
|
| 444 |
|
|
contents = open(pklFileName, 'rb')
|
| 445 |
|
|
obj = pickle.load(contents)
|
| 446 |
|
|
contents.close()
|
| 447 |
|
|
return obj
|
| 448 |
|
|
|
| 449 |
|
|
def __LoadFullNameOverideValues(self, fullNameOveridesFileName):
|
| 450 |
|
|
"""Pseudo-private method which will update the MAL people list object with the full name overide values."""
|
| 451 |
|
|
contents = open(fullNameOveridesFileName).readlines()
|
| 452 |
|
|
for line in contents:
|
| 453 |
|
|
line = line.replace("\n","")
|
| 454 |
|
|
emailAddress,fullNameOverideValue = line.split("|")
|
| 455 |
|
|
|
| 456 |
|
|
self.malPeopleList.update_full_Name_overide(emailAddress, fullNameOverideValue)
|
| 457 |
|
|
|
| 458 |
|
|
def SmartDedupeSet(self, currentSet):
|
| 459 |
|
|
"""A method that attempts to do some additional deduplication of the values in a set by lowering all values and deduplicating. Returns a lowered deduplicated set."""
|
| 460 |
|
|
newSet = set()
|
| 461 |
|
|
for val in currentSet:
|
| 462 |
|
|
newSet.add(val.lower())
|
| 463 |
|
|
return newSet
|
| 464 |
|
|
|
| 465 |
|
|
|
| 466 |
|
|
|
| 467 |
|
|
def RunMalEmailAddressIntegrityCheck(self):
|
| 468 |
|
|
"""This method performs an integrity check on the MAL by analyzing and looking for duplicate email addresses."""
|
| 469 |
|
|
emailTestMatrix = {}
|
| 470 |
|
|
altTestMatrix = {}
|
| 471 |
|
|
print("Performing MAL email address integrity check...")
|
| 472 |
|
|
for i in range(0,len(self.malPeopleList.people)):
|
| 473 |
|
|
#altAddr = self.malPeopleList.people[i].alt_work_email_address
|
| 474 |
|
|
altAddr = None
|
| 475 |
nino.borges |
916 |
## Right now workaddrs are stored as a string that you need to parse to use.
|
| 476 |
|
|
workAddrs = self.malPeopleList.people[i].work_email_addresses
|
| 477 |
nino.borges |
913 |
if altAddr != None:
|
| 478 |
|
|
altAddr = altAddr.strip()
|
| 479 |
|
|
if altAddr in list(emailTestMatrix.keys()):
|
| 480 |
|
|
print(f"ISSUE:{altAddr} is a dupe of an workAddr.")
|
| 481 |
|
|
if altAddr in list(altTestMatrix.keys()):
|
| 482 |
|
|
print(f"ISSUE:{altAddr} is a dupe!")
|
| 483 |
|
|
else:
|
| 484 |
|
|
altTestMatrix[altAddr] = 1
|
| 485 |
nino.borges |
916 |
if workAddrs != None:
|
| 486 |
|
|
workAddrs = [w.upper().strip() for w in workAddrs.split(";\n")]
|
| 487 |
|
|
for workAddr in workAddrs:
|
| 488 |
|
|
workAddr = workAddr.strip()
|
| 489 |
|
|
if workAddr in list(altTestMatrix.keys()):
|
| 490 |
|
|
print(f"ISSUE:{workAddr} is a dupe of an altAddr.")
|
| 491 |
|
|
if workAddr in list(emailTestMatrix.keys()):
|
| 492 |
|
|
print(f"ISSUE:{workAddr} is a dupe!")
|
| 493 |
|
|
else:
|
| 494 |
|
|
emailTestMatrix[workAddr] = 1
|
| 495 |
nino.borges |
913 |
print("\nEmail address integrity check complete.\n\n")
|
| 496 |
|
|
|
| 497 |
|
|
|
| 498 |
nino.borges |
951 |
def RunMalLoginIdIntegrityCheck(self):
|
| 499 |
|
|
"""This method performs an integrity check on the MAL by analyzing and looking for duplicate User Login ID values."""
|
| 500 |
|
|
loginIdTestMatrix = {}
|
| 501 |
|
|
print("Performing MAL user login ID integrity check...")
|
| 502 |
|
|
for i in range(0,len(self.malPeopleList.people)):
|
| 503 |
|
|
loginIds = self.malPeopleList.people[i].user_id
|
| 504 |
|
|
if loginIds != None:
|
| 505 |
|
|
loginIds = [w.upper().strip() for w in loginIds.split(";\n")]
|
| 506 |
|
|
for loginId in loginIds:
|
| 507 |
|
|
loginId = loginId.strip()
|
| 508 |
|
|
if loginId in list(loginIdTestMatrix.keys()):
|
| 509 |
|
|
print(f"ISSUE:{loginId} is a dupe!")
|
| 510 |
|
|
else:
|
| 511 |
|
|
loginIdTestMatrix[loginId] = 1
|
| 512 |
|
|
print("\nUser Login ID integrity check complete.\n\n")
|
| 513 |
|
|
|
| 514 |
nino.borges |
913 |
if __name__ == '__main__':
|
| 515 |
nino.borges |
973 |
masterAttorneyListFileName = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\AT&T\Cybersecurity FCA Case\_ATT_Current_MAL\RG - ATT Cross-Matter Master Attorney List (20260116)(20260116-0530).xlsx"
|
| 516 |
nino.borges |
913 |
attMal = ATT_MasterAttorneyList(masterAttorneyListFileName)
|
| 517 |
nino.borges |
951 |
test = attMal.malPeopleList.search_by_email('ahickey@mayerbrown.com'.upper())
|
| 518 |
nino.borges |
916 |
#test = attMal.malPeopleList.search_by_email('LMENRIQUEZ@DIRECTV.COM')
|
| 519 |
nino.borges |
951 |
#test = attMal.malPeopleList.return_list_of_matching_values('work_email_addresses','LMENRIQUEZ@DIRECTV.COM')
|
| 520 |
|
|
#test = attMal.malPeopleList.search_by_login_id('JS6637')
|
| 521 |
nino.borges |
916 |
print(test)
|
| 522 |
nino.borges |
951 |
print(attMal.malPeopleList.return_person_all_name_variations(test))
|
| 523 |
nino.borges |
973 |
attMal.RunMalEmailAddressIntegrityCheck()
|
| 524 |
|
|
attMal.RunMalLoginIdIntegrityCheck()
|
| 525 |
nino.borges |
913 |
## emailCheckList = []
|
| 526 |
|
|
## contents = open(r"C:\Test_Dir\ATT\JoshVerifyPrivResponse\Not_Verified_by_ATT.txt").readlines()
|
| 527 |
|
|
## for line in contents:
|
| 528 |
|
|
## line = line.replace("\n","")
|
| 529 |
|
|
## emailCheckList.append(line)
|
| 530 |
|
|
## print(f"There are {len(emailCheckList)} email addresses to check.")
|
| 531 |
|
|
## notFoundList = []
|
| 532 |
|
|
## for i in emailCheckList:
|
| 533 |
|
|
## test = attMal.malPeopleList.search_by_email(i)
|
| 534 |
|
|
## if test:
|
| 535 |
|
|
## print(f"{test.first_name} {test.last_name} | {i}")
|
| 536 |
|
|
## else:
|
| 537 |
|
|
## notFoundList.append(i)
|
| 538 |
|
|
## print("\n\n")
|
| 539 |
|
|
## print(f"There are {len(notFoundList)} email addresses not found:")
|
| 540 |
|
|
## notFoundList.sort()
|
| 541 |
|
|
## for x in notFoundList:
|
| 542 |
|
|
## print(x)
|
| 543 |
|
|
|
| 544 |
|
|
|
| 545 |
|
|
|
| 546 |
|
|
## lastNameCheckList = []
|
| 547 |
|
|
## notFoundList = []
|
| 548 |
|
|
## contents = open(r"C:\Test_Dir\ATT\JoshVerifyPrivResponse\Josh-ATT_No_title.txt").readlines()
|
| 549 |
|
|
## for line in contents:
|
| 550 |
|
|
## line = line.replace("\n","")
|
| 551 |
|
|
## lName = line.split(",")[0]
|
| 552 |
|
|
## lName = lName.strip()
|
| 553 |
|
|
## lName = lName.upper()
|
| 554 |
|
|
## test = attMal.malPeopleList.return_list_of_matching_values('last_name',lName)
|
| 555 |
|
|
## if test:
|
| 556 |
|
|
## #print(f"Possible match for {line}:")
|
| 557 |
|
|
## for x in test:
|
| 558 |
|
|
## print(f"{line}|{x.last_name},{x.first_name}|{x.company}|{x.job_title}|{x.is_attorney}")
|
| 559 |
|
|
## else:
|
| 560 |
|
|
## notFoundList.append(line)
|
| 561 |
|
|
##
|
| 562 |
|
|
## print("\n\n")
|
| 563 |
|
|
## print(f"There are {len(notFoundList)} email addresses not found:")
|
| 564 |
|
|
## notFoundList.sort()
|
| 565 |
|
|
## for x in notFoundList:
|
| 566 |
|
|
## print(x)
|
| 567 |
|
|
|
| 568 |
|
|
|
| 569 |
|
|
|
| 570 |
|
|
|
| 571 |
|
|
## findList = ["JON.GREER@DIRECTV.COM","AJJOHNSON@GIBSONDUNN.COM","RLANG@GIBSONDUNN.COM","MATT.MILLER@CROWDSTRIKE.COM","ADAM.MONTGOMERY@FLEISHMAN.COM","ALPESHP@AMDOCS.COM",
|
| 572 |
|
|
## "ERIC.PRATT@CROWDSTRIKE.COM","MROBERTS@GIBSONDUNN.COM","VVARGAS@KTSLAW.COM","TIM.WILLIAMS@FLEISHMAN.COM"]
|
| 573 |
|
|
## for s in findList:
|
| 574 |
|
|
## test = attMal.malPeopleList.search_by_email(s)
|
| 575 |
|
|
## print(f"{s}|{test.last_name},{test.first_name}|{test.company}")
|
| 576 |
|
|
|
| 577 |
|
|
|
| 578 |
nino.borges |
916 |
## foundList = []
|
| 579 |
|
|
## outputFile = open(r"C:\Test_Dir\ATT\20250716_ESQLogTest\NormalizedFromDOJLog(DB MATCH REPORT)2.txt",'w',encoding='UTF-8')
|
| 580 |
|
|
## contents = open(r"C:\Test_Dir\ATT\20250716_ESQLogTest\NormalizedFromDOJLog(all-deduplicated-cleaned)2.txt").readlines()
|
| 581 |
|
|
## for line in contents:
|
| 582 |
|
|
## line = line.replace("\n","")
|
| 583 |
|
|
## line = line.upper()
|
| 584 |
|
|
## line = line.strip()
|
| 585 |
|
|
## if "@" in line:
|
| 586 |
|
|
## result = attMal.malPeopleList.search_by_email(line)
|
| 587 |
|
|
## if result:
|
| 588 |
|
|
## outputFile.write(f"{line}|{result.last_name},{result.first_name}|{result.is_attorney}\n")
|
| 589 |
|
|
## results = attMal.malPeopleList.return_list_of_matching_values('full_name_preferred',line)
|
| 590 |
|
|
## if results:
|
| 591 |
|
|
## for result in results:
|
| 592 |
|
|
## outputFile.write(f"{line}|{result.last_name},{result.first_name}|{result.is_attorney}\n")
|
| 593 |
|
|
## elif "," in line:
|
| 594 |
|
|
## lName = line.split(",")[0]
|
| 595 |
|
|
## results = attMal.malPeopleList.return_list_of_matching_values('last_name',lName)
|
| 596 |
|
|
## if results:
|
| 597 |
|
|
## for result in results:
|
| 598 |
|
|
## outputFile.write(f"{line}|{result.last_name},{result.first_name}|{result.is_attorney}\n")
|
| 599 |
|
|
## else:
|
| 600 |
|
|
## lName = line.split(" ")[-1]
|
| 601 |
|
|
## results = attMal.malPeopleList.return_list_of_matching_values('last_name',lName)
|
| 602 |
|
|
## if results:
|
| 603 |
|
|
## for result in results:
|
| 604 |
|
|
## outputFile.write(f"{line}|{result.last_name},{result.first_name}|{result.is_attorney}\n")
|
| 605 |
|
|
## outputFile.close() |
