| 1 |
nino.borges |
914 |
"""
|
| 2 |
|
|
|
| 3 |
|
|
PrivilegeLogFieldCompare
|
| 4 |
|
|
|
| 5 |
|
|
Created by:
|
| 6 |
|
|
Emanuel Borges
|
| 7 |
|
|
07.23.2025
|
| 8 |
|
|
|
| 9 |
|
|
This program will take a DAT export from Relativity and will compare the values in the fields.
|
| 10 |
|
|
|
| 11 |
|
|
"""
|
| 12 |
|
|
|
| 13 |
|
|
|
| 14 |
|
|
import csv
|
| 15 |
|
|
|
| 16 |
|
|
|
| 17 |
|
|
class ConcordanceLoader:
|
| 18 |
|
|
def __init__(self, filePath):
|
| 19 |
|
|
self.filePath = filePath
|
| 20 |
|
|
self.delimiter = '\x14' # ASCII 20
|
| 21 |
|
|
self.quotechar = '\xfe' # ASCII 254
|
| 22 |
|
|
self.records = []
|
| 23 |
|
|
|
| 24 |
|
|
|
| 25 |
|
|
def load(self):
|
| 26 |
|
|
with open(self.filePath, 'r', encoding='utf-8', newline='') as file:
|
| 27 |
|
|
reader = csv.reader(file, delimiter = self.delimiter, quotechar = self.quotechar)
|
| 28 |
|
|
self.records = [row for row in reader]
|
| 29 |
|
|
|
| 30 |
|
|
|
| 31 |
|
|
def get_headers(self):
|
| 32 |
|
|
return self.records[0] if self.records else []
|
| 33 |
|
|
|
| 34 |
|
|
def get_data(self):
|
| 35 |
|
|
return self.records[1:] if len(self.records) >1 else []
|
| 36 |
|
|
|
| 37 |
|
|
def get_all(self):
|
| 38 |
|
|
return self.records
|
| 39 |
|
|
|
| 40 |
|
|
|
| 41 |
|
|
def compare_fields(self, report_on_field: str, field_name_a: str, field_name_b: str):
|
| 42 |
|
|
"""Will compare the values in two different fields. report on should be the REVIEWID field"""
|
| 43 |
|
|
if not self.records:
|
| 44 |
|
|
raise ValueError("No data loaded. Run .load() first.")
|
| 45 |
|
|
|
| 46 |
|
|
headers = self.get_headers()
|
| 47 |
|
|
try:
|
| 48 |
|
|
report_idx = headers.index(report_on_field)
|
| 49 |
|
|
first_field_idx = headers.index(field_name_a)
|
| 50 |
|
|
second_field_idx = headers.index(field_name_b)
|
| 51 |
|
|
except ValueError as e:
|
| 52 |
|
|
raise ValueError(f"Column not found: {e}")
|
| 53 |
|
|
|
| 54 |
|
|
for row_num, row in enumerate(self.get_data(), start=2): # Use Excel-style row numbers
|
| 55 |
|
|
report_val = row[report_idx] if report_idx < len(row) else ''
|
| 56 |
|
|
first_field_val = row[first_field_idx] if first_field_idx < len(row) else ''
|
| 57 |
|
|
second_field_val = row[second_field_idx] if second_field_idx < len(row) else ''
|
| 58 |
|
|
## For now I only care if the PLOG field has data.
|
| 59 |
|
|
if second_field_val:
|
| 60 |
|
|
sVals = second_field_val.split(";")
|
| 61 |
|
|
sVals.sort()
|
| 62 |
|
|
if first_field_val:
|
| 63 |
|
|
fVals = first_field_val.split(";")
|
| 64 |
|
|
fVals.sort()
|
| 65 |
|
|
sTest = [s.upper().strip() for s in sVals]
|
| 66 |
|
|
fTest = [f.upper().strip() for f in fVals]
|
| 67 |
|
|
if sTest != fTest:
|
| 68 |
|
|
print(f"{report_val}: Values in {field_name_b} are different from those in {field_name_a}.")
|
| 69 |
|
|
else:
|
| 70 |
|
|
print(f"{report_val}: Value in {field_name_b} but {field_name_a} is empty.")
|
| 71 |
|
|
|
| 72 |
|
|
if __name__ == '__main__':
|
| 73 |
|
|
## Full path to the DAT input file
|
| 74 |
|
|
inputFilePath = r"C:\Test_Dir\ATT\20250723_PLOG_FieldCompare\20250723 - PrivLog001_fieldAnalysis(w_PLOG).dat"
|
| 75 |
|
|
|
| 76 |
|
|
loader = ConcordanceLoader(inputFilePath)
|
| 77 |
|
|
loader.load()
|
| 78 |
|
|
|
| 79 |
|
|
#loader.compare_fields("REVIEWID", "MA Normalized To::Full Name", "PLOG Recipients")
|
| 80 |
|
|
#loader.compare_fields("REVIEWID", "MA Normalized Cc::Full Name", "PLOG CC")
|
| 81 |
|
|
loader.compare_fields("REVIEWID", "MA Normalized To::Full Name", "To")
|
| 82 |
|
|
|
| 83 |
|
|
|
