LEAF
/
PortfolioParser
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fully working app. Interface needs work. Could use config to remember last opened location. Debug option not configured

Browse Source
master
Griffiths Lott 3 years ago
commit 6b375ecb72
3 changed files with 167 additions and 0 deletions
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Show Stats Download Patch File Download Diff File
  1. 6
      .gitignore
  2. 20
      getcol.py
  3. 141
      main.py

6
.gitignore vendored
Unescape View File

@ -0,0 +1,6 @@
venv/
Inputs/
Outputs/
__pycache__/
*.csv
*.log

20
getcol.py
Unescape View File

@ -0,0 +1,20 @@
import re
import pandas as pd
for input in ["ASSET", "CUST", "DOB"]:
with open(f"Inputs/{input}", errors="replace") as reportFile:
report: str = reportFile.read()
# Removes characters that cause errors
report: str = report.replace("^"," ")
colDict = {"ColName": [], "start": [], "end": []}
for line in report.splitlines():
print(line.strip())
if len(line.strip()) > 50:
matches = re.finditer('(\w|\.)+\s', line)
for match in matches:
print(match)
colDict["ColName"].append(match.group())
colDict["start"].append(match.start())
colDict["end"].append(match.end())
break
pd.DataFrame(colDict).to_csv(f"Outputs/{input}.csv")

141
main.py
Unescape View File

@ -0,0 +1,141 @@
from pandas import DataFrame
import re
from logging import debug, DEBUG, basicConfig, warn
from typing import Optional, Union
logConfig = basicConfig(filename='ILFormatter.log', encoding='utf-8', level=DEBUG)
TEST_FIN_LOCATION = r"Inputs/FIN"
TEST_ASSET_LOCATION = R"Inputs\ASSET"
CONTRACT_NO_REGEX = "\d{3}-\d{7}-\d{3}"
class Column:
def __init__(self, columnName: str, startIndex: int,
length: Optional[int] = None, endIndex: Optional[int] = None, valueRegex: Optional[str] = None) -> None:
assert length != None or endIndex != None, "You must specify either the length or endIndex of this column"
self.name = columnName
self.start = startIndex
self.end = endIndex if endIndex != None else startIndex + length
self.valueRegex = valueRegex
def __regex_check(self, value: str) -> bool:
if self.valueRegex == None: return True
return False if re.search(self.valueRegex, value) == None else True
def extract_column(self, line: str) -> tuple[str, Union[str, float]]:
debug(line)
if self.end == -1:
end = len(line)
else:
assert len(line) >= self.end, f"Line is to short to extract value: len: {len(line)} > end : {self.end}"
end = self.end
dataValue: str = line[self.start : end].replace(',', '').strip()
if not self.__regex_check(dataValue):
warn(f"Invalid column value: Column: {self.name} value: {dataValue} regex: {self.valueRegex}")
try:
dataValue = float(dataValue)
except: pass
return self.name, dataValue
FIN_COLUMNS: list[Column] = [
Column("CUST.ID", startIndex= 0 ,endIndex = 21, valueRegex = "\d{8}"),
Column("CONTRACT.NO", startIndex= 21 ,endIndex = 37, valueRegex = "CONTRACT_NO_REGEX"),
Column("BUSINESS.TYPE", startIndex= 37 ,endIndex = 51, valueRegex = "\d{2}"),
Column("FED.ID", startIndex= 51 ,endIndex = 72, valueRegex = "\d{9}"),
Column("CUST.CREDIT.ACCT", startIndex= 72 ,endIndex = 89, valueRegex = "\d+"),
Column("CUSTOMER", startIndex= 89 ,endIndex = 120, valueRegex = None),
Column("LEASE.TYPE", startIndex= 120 ,endIndex = 131, valueRegex = None),
Column("EQUIPMENT.COST", startIndex= 131 ,endIndex = 146, valueRegex = None),
Column("CBR.", startIndex= 146 ,endIndex = 161, valueRegex = None),
Column("NET.INVESTMENT", startIndex= 161 ,endIndex = 176, valueRegex = None),
Column("ANNUAL.COMBINED.IRR", startIndex= 176 ,endIndex = 185, valueRegex = None),
Column("CONTRACT.TERM", startIndex= 185 ,endIndex = 199, valueRegex = None),
Column("INCOME.START.DATE", startIndex= 199 ,endIndex = 217, valueRegex = None),
Column("FIRST.PYMT.DATE", startIndex= 217 ,endIndex = 233, valueRegex = None),
Column("FIRST.PYMT.AMT", startIndex= 233 ,endIndex = 248, valueRegex = None),
Column("CONTRACT.PYMT.", startIndex= 248 ,endIndex = 263, valueRegex = None),
Column("INVOICE.CODE", startIndex= 263 ,endIndex = 276, valueRegex = None),
Column("INV.DAYS", startIndex= 276 ,endIndex = 285, valueRegex = None),
Column("INV.DUE.DAY", startIndex= 285 ,endIndex = 297, valueRegex = None),
Column("SEC.DEPOSIT.", startIndex= 297 ,endIndex = 312, valueRegex = None),
Column("IDC.AMOUNTS.", startIndex= 312 ,endIndex = 327, valueRegex = None),
Column("IDC.DATES.", startIndex= 327 ,endIndex = 338, valueRegex = None),
Column("RESIDUAL", startIndex= 338 ,endIndex = 353, valueRegex = None),
Column("MANAGERS.RESIDUAL", startIndex= 353 ,endIndex = 371, valueRegex = None),
Column("PROMOTION", startIndex= 371 ,endIndex = 381, valueRegex = None),
Column("PRODUCT.LINE", startIndex= 381 ,endIndex = 394, valueRegex = None),
Column("REGION", startIndex= 394 ,endIndex = 401, valueRegex = None),
Column("REGION.DESC.", startIndex= 401 ,endIndex = 432, valueRegex = None),
Column("BRANCH", startIndex= 432 ,endIndex = 439, valueRegex = None),
Column("BUSINESS.SEGMENT", startIndex= 439 ,endIndex = 456, valueRegex = None),
Column("LEAD.BANK", startIndex= 456 ,endIndex = 466, valueRegex = None),
Column("MRKTNG.REP", startIndex= 466 ,endIndex = 477, valueRegex = None),
Column("MRKTNG.REGION", startIndex= 477 ,endIndex = 491, valueRegex = None),
Column("REMIT.TO", startIndex= 491 ,endIndex = 500, valueRegex = None),
Column("PYMT.OPTION", startIndex= 500 ,endIndex = 512, valueRegex = None),
Column("BANK.CODE", startIndex= 512 ,endIndex = 522, valueRegex = None),
Column("TAPE.BANK.NUM", startIndex= 522 ,endIndex = 536, valueRegex = None),
Column("TAPE.ACCOUNT.NUM", startIndex= 536 ,endIndex = 557, valueRegex = None),
Column("TAPE.ACCT.TYPE", startIndex= 557 ,endIndex = 572, valueRegex = None),
Column("DEALER", startIndex= 572 ,endIndex = 583, valueRegex = None),
Column("PRIVATE.LABEL", startIndex= 583 ,endIndex = 597, valueRegex = None),
Column("RESID.METHOD", startIndex= 597 ,endIndex = 610, valueRegex = None),
Column("LATE.CHRG.EXMPT", startIndex= 610 ,endIndex = 626, valueRegex = None),
Column("INSURANCE.CODE", startIndex= 626 ,endIndex = 641, valueRegex = None),
Column("VARIABLE.DATE", startIndex= 641 ,endIndex = 655, valueRegex = None),
Column("VARIABLE.RATE", startIndex= 655 ,endIndex = 671, valueRegex = None),
Column("BILLING.CYCLE", startIndex= 671 ,endIndex = 685, valueRegex = None),
Column("UM.USER.DATE2", startIndex= 685 ,endIndex = 699, valueRegex = None),
Column("CR.ATTG.PHONE", startIndex= 699 ,endIndex = 715, valueRegex = None),
Column("GROSS.CONTRACT", startIndex= 715 ,endIndex = 730, valueRegex = None),
Column("ADV", startIndex= 730 ,endIndex = 734, valueRegex = None),
Column("PD.AMT.FINANCED ", startIndex= 735 ,endIndex = 751, valueRegex = None),
Column("PD.INCOME.START.DATE ", startIndex= 751 ,endIndex = 772, valueRegex = None),
Column("INVOICE.DESC", startIndex= 772 ,endIndex = 792, valueRegex = None),
Column("VARIABLE.PYMT.CODE ", startIndex= 792 ,endIndex = 811, valueRegex = None),
Column("PD.PAYMENT.AMT ", startIndex= 811 ,endIndex = 826, valueRegex = None),
Column("QUOTE.BUYOUT ", startIndex= 826 ,endIndex = 839, valueRegex = None),
Column("LATE.CHARGE.CODE ", startIndex= 839 ,endIndex = 856, valueRegex = None),
Column("LATE.CHRG.RATE ", startIndex= 856 ,endIndex = 871, valueRegex = None),
Column("M.DEF.COLLECTOR ", startIndex= 871 ,endIndex = 887, valueRegex = None),
Column("AM.ACH.LEAD.DAYS ", startIndex= 887 ,endIndex = 904, valueRegex = None),
Column("UNL POOL", startIndex= 904 ,endIndex = 915, valueRegex = None),
Column("PD RISK", startIndex= 915 ,endIndex = 926, valueRegex = None),
Column("PD RISK DATE.", startIndex= 926 ,endIndex = 940, valueRegex = None),
Column("LGD RISK", startIndex= 940 ,endIndex = 949, valueRegex = None),
Column("LGD DATE", startIndex= 949 ,endIndex = 960, valueRegex = None),
Column("Service By Others", startIndex= 960 ,endIndex = -1, valueRegex = None)
]
def parse(ILOutput: str, columns: list[Column], dataColumnRegex: str = CONTRACT_NO_REGEX) -> DataFrame :
debug(ILOutput)
lines = ILOutput.splitlines()
dataDict = {}
for index, line in enumerate(lines):
debug(f"Index: {index} | {line}")
debug(re.search(dataColumnRegex, line))
if re.search(dataColumnRegex, line) == None: continue
for col in columns:
name, value = col.extract_column(line)
try:
dataDict[name].append(value)
except:
dataDict[name] = [value]
dataframe = DataFrame(dataDict)
return dataframe
with open(TEST_FIN_LOCATION, errors="replace") as reportFile:
report: str = reportFile.read()
# Removes characters that cause errors
report: str = report.replace("^"," ")
finDataframe: DataFrame = parse(ILOutput=report, columns=FIN_COLUMNS)
print(f"FIN dataframe: {finDataframe}")
Write Preview
Loading…
Cancel
Save