| 1 |
nino.borges |
802 |
"""
|
| 2 |
|
|
|
| 3 |
|
|
SF-SubjectLineDeconstructor
|
| 4 |
|
|
|
| 5 |
|
|
Created by:
|
| 6 |
|
|
Emanuel Borges
|
| 7 |
|
|
09.21.2023
|
| 8 |
|
|
|
| 9 |
|
|
Very simple program that will read a list of subject lines and deconstruct them to consilidate them into a list of something attorneys
|
| 10 |
|
|
can use to pull out responsive terms.
|
| 11 |
|
|
|
| 12 |
|
|
"""
|
| 13 |
|
|
|
| 14 |
|
|
def ProcessLine(line, removalList):
|
| 15 |
|
|
line = line.strip()
|
| 16 |
|
|
for begVal in removalList:
|
| 17 |
|
|
if line.startswith(begVal):
|
| 18 |
|
|
line = line.replace(begVal,"",1)
|
| 19 |
|
|
return line.strip()
|
| 20 |
|
|
|
| 21 |
|
|
|
| 22 |
|
|
if __name__ == '__main__':
|
| 23 |
|
|
removalList = ['[EXTERNAL] ', 'RE: ', 'FW: ','Accepted: ','Canceled: ','Tentative: ', 'Re: ', 'Fw: ', 'Fwd: ', 'Automatic reply: ', 'Declined: ', '[EXTERNAL EMAIL] ']
|
| 24 |
|
|
sfInputFileName = r"C:\Users\eborges\Documents\Cases\State Farm\subject_line_raw.txt"
|
| 25 |
|
|
|
| 26 |
|
|
outputFileName = r"C:\Users\eborges\Documents\Cases\State Farm\subject_line_EB.txt"
|
| 27 |
|
|
|
| 28 |
|
|
sfSubjectSet = set()
|
| 29 |
|
|
|
| 30 |
|
|
contents = open(sfInputFileName).readlines()
|
| 31 |
|
|
print(f"This file contains {len(contents)} lines.")
|
| 32 |
|
|
for line in contents:
|
| 33 |
|
|
line = line.replace("\n","")
|
| 34 |
|
|
begLineTest = True
|
| 35 |
|
|
while begLineTest == True:
|
| 36 |
|
|
begLineTest = False
|
| 37 |
|
|
for begVal in removalList:
|
| 38 |
|
|
if line.startswith(begVal):
|
| 39 |
|
|
begLineTest = True
|
| 40 |
|
|
line = ProcessLine(line, removalList)
|
| 41 |
|
|
|
| 42 |
|
|
sfSubjectSet.add(line)
|
| 43 |
|
|
|
| 44 |
|
|
outputFile = open(outputFileName,'w')
|
| 45 |
|
|
sfSubJectList = list(sfSubjectSet)
|
| 46 |
|
|
sfSubJectList.sort()
|
| 47 |
|
|
for i in sfSubJectList:
|
| 48 |
|
|
outputFile.write(f"{i}\n")
|
| 49 |
|
|
outputFile.close() |
