Add bank statement analyzer with automatic work storage
This commit is contained in:
A R R R Associates
@@ -0,0 +1 @@
|
||||
"""Bank statement analyzer ERP module."""
|
||||
@@ -0,0 +1,107 @@
|
||||
from __future__ import annotations
|
||||
from pathlib import Path
|
||||
import re
|
||||
import pandas as pd
|
||||
from .parsers import parse_pdf
|
||||
from parsers.common import infer_mode
|
||||
|
||||
|
||||
def clean_key(s):
|
||||
s=re.sub(r'\s+',' ',str(s or '').upper()).strip()
|
||||
return re.sub(r'\b\d{8,}\b','<REF>',s)
|
||||
|
||||
def enrich(df):
|
||||
if df.empty:return df
|
||||
x=df.copy()
|
||||
x['mode']=x['narration'].map(infer_mode)
|
||||
x['amount']=x['debit'].fillna(0)+x['credit'].fillna(0)
|
||||
x['direction']=x['debit'].notna().map({True:'Debit',False:'Credit'})
|
||||
x['narration_key']=x['narration'].map(clean_key)
|
||||
x['exact_key']=x.apply(lambda r:f"{r.transaction_date}|{r.value_date}|{r.debit}|{r.credit}|{r.balance}|{clean_key(r.narration)}",axis=1)
|
||||
x['exact_duplicate']=x.duplicated('exact_key',keep=False)
|
||||
# possible duplicate: same date, direction, amount and normalized narration across different source files
|
||||
x['possible_key']=x.apply(lambda r:f"{r.transaction_date}|{r.direction}|{r.amount:.2f}|{r.narration_key}",axis=1)
|
||||
x['possible_duplicate']=x.duplicated('possible_key',keep=False) & ~x['exact_duplicate']
|
||||
return x
|
||||
|
||||
def analyze_files(paths, customer_override='', account_override=''):
|
||||
metas=[]; dfs=[]
|
||||
for p in paths:
|
||||
meta,df=parse_pdf(p)
|
||||
if customer_override: meta.customer_name=customer_override; df['customer_name']=customer_override
|
||||
if account_override: meta.account_number=account_override; df['account_number']=account_override
|
||||
metas.append(meta); dfs.append(df)
|
||||
all_df=enrich(pd.concat(dfs,ignore_index=True) if dfs else pd.DataFrame())
|
||||
# remove exact overlap duplicates, retaining first source occurrence
|
||||
unique_df=all_df.drop_duplicates('exact_key',keep='first').copy() if not all_df.empty else all_df.copy()
|
||||
return metas,all_df,unique_df
|
||||
|
||||
def reconcile(metas,all_df):
|
||||
rows=[]
|
||||
for m in metas:
|
||||
d=all_df[all_df.source_file.eq(m.source_file)] if not all_df.empty else pd.DataFrame()
|
||||
ed=float(d.debit.sum()) if not d.empty else 0
|
||||
ec=float(d.credit.sum()) if not d.empty else 0
|
||||
last=float(d.balance.dropna().iloc[-1]) if not d.empty and d.balance.notna().any() else None
|
||||
rows.append({**m.to_dict(),'extracted_transactions':len(d),'extracted_debit':ed,'extracted_credit':ec,'extracted_closing_balance':last,
|
||||
'debit_difference':None if m.total_debit is None else round(ed-m.total_debit,2),
|
||||
'credit_difference':None if m.total_credit is None else round(ec-m.total_credit,2),
|
||||
'closing_difference':None if m.closing_balance is None or last is None else round(last-m.closing_balance,2)})
|
||||
return pd.DataFrame(rows)
|
||||
|
||||
def monthly_summary(df):
|
||||
if df.empty:return pd.DataFrame()
|
||||
x=df.copy(); x['month']=x.transaction_date.dt.to_period('M').astype(str)
|
||||
return x.groupby('month',dropna=False).agg(transaction_count=('amount','size'),total_debit=('debit','sum'),total_credit=('credit','sum'),net_movement=('credit','sum')).reset_index().assign(net_movement=lambda z:z.total_credit-z.total_debit)
|
||||
|
||||
def mode_summary(df):
|
||||
if df.empty:return pd.DataFrame()
|
||||
return df.groupby(['mode','direction']).agg(transaction_count=('amount','size'),amount=('amount','sum')).reset_index()
|
||||
|
||||
def duplicate_summary(all_df):
|
||||
return pd.DataFrame([
|
||||
{'check':'All extracted rows','count':len(all_df)},
|
||||
{'check':'Exact duplicate rows','count':int(all_df.exact_duplicate.sum()) if not all_df.empty else 0},
|
||||
{'check':'Possible duplicate rows','count':int(all_df.possible_duplicate.sum()) if not all_df.empty else 0},
|
||||
{'check':'Unique rows after exact deduplication','count':int(all_df.exact_key.nunique()) if not all_df.empty else 0},
|
||||
])
|
||||
|
||||
def export_excel(output,metas,all_df,unique_df):
|
||||
recon=reconcile(metas,all_df)
|
||||
cust=next((m.customer_name for m in metas if m.customer_name),'')
|
||||
acct=next((m.account_number for m in metas if m.account_number),'')
|
||||
banks=', '.join(sorted({m.bank_name for m in metas}))
|
||||
dashboard=pd.DataFrame([
|
||||
['Customer / Account Holder',cust],['Account Number',acct],['Bank(s)',banks],
|
||||
['Statements Uploaded',len(metas)],['Rows Extracted',len(all_df)],['Unique Transactions',len(unique_df)],
|
||||
['Exact Duplicate Rows',int(all_df.exact_duplicate.sum()) if not all_df.empty else 0],
|
||||
['Possible Duplicate Rows',int(all_df.possible_duplicate.sum()) if not all_df.empty else 0],
|
||||
['Total Debit (Unique)',float(unique_df.debit.sum()) if not unique_df.empty else 0],
|
||||
['Total Credit (Unique)',float(unique_df.credit.sum()) if not unique_df.empty else 0],
|
||||
],columns=['Metric','Value'])
|
||||
with pd.ExcelWriter(output,engine='xlsxwriter',datetime_format='dd-mmm-yyyy') as w:
|
||||
dashboard.to_excel(w,'Dashboard',index=False)
|
||||
recon.to_excel(w,'Statement Reconciliation',index=False)
|
||||
all_df.to_excel(w,'All Extracted Rows',index=False)
|
||||
unique_df.to_excel(w,'Unique Transactions',index=False)
|
||||
all_df[all_df.exact_duplicate].to_excel(w,'Exact Duplicates',index=False)
|
||||
all_df[all_df.possible_duplicate].to_excel(w,'Possible Duplicates',index=False)
|
||||
monthly_summary(unique_df).to_excel(w,'Monthly Summary',index=False)
|
||||
mode_summary(unique_df).to_excel(w,'Mode Summary',index=False)
|
||||
duplicate_summary(all_df).to_excel(w,'Duplicate Summary',index=False)
|
||||
notes=pd.DataFrame({'Notes':[
|
||||
'Exact duplicates use transaction date, value date, debit, credit, balance and normalized narration.',
|
||||
'Possible duplicates use same date, direction, amount and normalized narration; review before deletion.',
|
||||
'Bank-specific parsers are selected automatically. Customer name/account number can be manually overridden in the app.',
|
||||
'The workbook is a bank-statement analysis aid, not a substitute for ledger, GST, inventory, receivable/payable and cash-book records.'
|
||||
]})
|
||||
notes.to_excel(w,'Notes',index=False)
|
||||
wb=w.book
|
||||
head=wb.add_format({'bold':True,'bg_color':'#1F4E78','font_color':'white','border':1})
|
||||
money=wb.add_format({'num_format':'#,##0.00'})
|
||||
for name,ws in w.sheets.items():
|
||||
ws.freeze_panes(1,0); ws.autofilter(0,0,0,max(0,ws.dim_colmax))
|
||||
ws.set_row(0,22,head)
|
||||
ws.set_column(0,max(0,ws.dim_colmax),18)
|
||||
w.sheets['Dashboard'].set_column('A:A',32); w.sheets['Dashboard'].set_column('B:B',28)
|
||||
return output
|
||||
@@ -0,0 +1,2 @@
|
||||
from .registry import parse_pdf, detect_parser, PARSERS
|
||||
from .base import StatementMeta, STANDARD_COLUMNS
|
||||
@@ -0,0 +1,37 @@
|
||||
from __future__ import annotations
|
||||
import re, pandas as pd
|
||||
from pathlib import Path
|
||||
from .base import *
|
||||
from .common import find
|
||||
|
||||
class AxisParser(BaseParser):
|
||||
bank_name='Axis Bank'; parser_name='AxisParser'
|
||||
@classmethod
|
||||
def detect(cls,text): return 0.98 if 'SMART STATEMENT REPORT' in text.upper() and 'UTIB' in text.upper() else 0
|
||||
def parse(self,path,text=None):
|
||||
text=text or extract_text(path); meta=StatementMeta(bank_name=self.bank_name,source_file=Path(path).name,parser_name=self.parser_name,confidence='High')
|
||||
# name is first meaningful line after report title
|
||||
m=re.search(r'Smart Statement Report\s*\n\s*([^\n]+)',text,re.I); meta.customer_name=norm(m.group(1)) if m else ''
|
||||
meta.account_number=find(r'Statement of Account No\s*-\s*([^\s]*)',text)
|
||||
meta.ifsc=find(r'IFSC:\s*([A-Z0-9]+)',text)
|
||||
m=re.search(r'for period\s*\((\d{2}/\d{2}/\d{4})\s+to\s+(\d{2}/\d{2}/\d{4})\)',text,re.I)
|
||||
if m: meta.period_from=pd.to_datetime(m.group(1),dayfirst=True).strftime('%Y-%m-%d'); meta.period_to=pd.to_datetime(m.group(2),dayfirst=True).strftime('%Y-%m-%d')
|
||||
meta.opening_balance=amount(find(r'Opening Balance:\s*INR\s*([\d,]+\.\d{2})',text))
|
||||
pat=re.compile(r'^\s*(\d+)\s+(\d{2}/\d{2}/\d{4})\s+(\d{2}/\d{2}/\d{4})\s+(.*)$')
|
||||
rows=[]; cur=None; page=1
|
||||
for line in text.splitlines():
|
||||
if '\f' in line: page+=line.count('\f')
|
||||
m=pat.match(line)
|
||||
if m:
|
||||
if cur: rows.append(cur)
|
||||
cur={'transaction_date':m.group(2),'value_date':m.group(3),'body':m.group(4),'source_page':page}
|
||||
elif cur and line.strip() and not re.match(r'^(S\. No\.|Smart Statement|Page )',line.strip(),re.I): cur['body']+=' '+line.strip()
|
||||
if cur: rows.append(cur)
|
||||
out=[]
|
||||
for r in rows:
|
||||
b=norm(r['body']); ma=re.search(r'INR\s*([\d,]+\.\d{2})\s+(CR|DR)\s+INR\s*([\d,]+\.\d{2})',b,re.I)
|
||||
if not ma: continue
|
||||
txn=amount(ma.group(1)); typ=ma.group(2).upper(); bal=amount(ma.group(3)); narr=b[:ma.start()].strip(); ref=''
|
||||
z=re.search(r'([A-Z0-9/-]{8,})',narr); ref=z.group(1) if z else ''
|
||||
out.append({**r,'narration':narr,'reference_no':ref,'debit':txn if typ=='DR' else None,'credit':txn if typ=='CR' else None,'balance':bal})
|
||||
return meta,finalize(pd.DataFrame(out),meta)
|
||||
@@ -0,0 +1,91 @@
|
||||
from __future__ import annotations
|
||||
from dataclasses import dataclass, asdict
|
||||
from pathlib import Path
|
||||
from typing import Optional
|
||||
import re, subprocess, tempfile
|
||||
import pandas as pd
|
||||
import pdfplumber
|
||||
|
||||
@dataclass
|
||||
class StatementMeta:
|
||||
bank_name: str = ""
|
||||
customer_name: str = ""
|
||||
account_number: str = ""
|
||||
customer_id: str = ""
|
||||
ifsc: str = ""
|
||||
period_from: str = ""
|
||||
period_to: str = ""
|
||||
opening_balance: Optional[float] = None
|
||||
total_debit: Optional[float] = None
|
||||
total_credit: Optional[float] = None
|
||||
closing_balance: Optional[float] = None
|
||||
source_file: str = ""
|
||||
parser_name: str = ""
|
||||
confidence: str = "Medium"
|
||||
|
||||
def to_dict(self):
|
||||
return asdict(self)
|
||||
|
||||
STANDARD_COLUMNS = [
|
||||
"transaction_date", "value_date", "narration", "reference_no",
|
||||
"debit", "credit", "balance", "bank_name", "customer_name",
|
||||
"account_number", "source_file", "source_page", "parser_name"
|
||||
]
|
||||
|
||||
def amount(v):
|
||||
if v is None: return None
|
||||
s=str(v).strip().replace('INR','').replace('Rs.','').replace('₹','').replace(',','').replace('+','')
|
||||
s=s.replace('CR','').replace('DR','').strip()
|
||||
if s in ('','-'): return None
|
||||
neg=s.startswith('-')
|
||||
s=s.lstrip('-')
|
||||
try:
|
||||
x=float(s)
|
||||
return -x if neg else x
|
||||
except: return None
|
||||
|
||||
def norm(s): return re.sub(r'\s+',' ',str(s or '')).strip()
|
||||
|
||||
def extract_text(path: str|Path) -> str:
|
||||
"""Prefer pdftotext layout output; fall back to pdfplumber."""
|
||||
path=str(path)
|
||||
try:
|
||||
p=subprocess.run(['pdftotext','-layout',path,'-'], capture_output=True, text=True, timeout=120)
|
||||
if p.returncode==0 and len(p.stdout.strip())>50:
|
||||
return p.stdout
|
||||
except Exception:
|
||||
pass
|
||||
parts=[]
|
||||
with pdfplumber.open(path) as pdf:
|
||||
for page in pdf.pages:
|
||||
parts.append(page.extract_text(x_tolerance=1,y_tolerance=3,layout=True) or '')
|
||||
return '\n\f\n'.join(parts)
|
||||
|
||||
def page_of_line(text: str, position: int) -> int:
|
||||
return text[:position].count('\f')+1
|
||||
|
||||
def finalize(df: pd.DataFrame, meta: StatementMeta) -> pd.DataFrame:
|
||||
if df is None or df.empty:
|
||||
return pd.DataFrame(columns=STANDARD_COLUMNS)
|
||||
for c in ['debit','credit','balance']:
|
||||
df[c]=pd.to_numeric(df.get(c),errors='coerce')
|
||||
for c in ['transaction_date','value_date']:
|
||||
df[c]=pd.to_datetime(df.get(c),errors='coerce',dayfirst=True)
|
||||
df['narration']=df.get('narration','').fillna('').map(norm)
|
||||
df['reference_no']=df.get('reference_no','').fillna('').map(norm)
|
||||
df['bank_name']=meta.bank_name
|
||||
df['customer_name']=meta.customer_name
|
||||
df['account_number']=meta.account_number
|
||||
df['source_file']=meta.source_file
|
||||
df['parser_name']=meta.parser_name
|
||||
if 'source_page' not in df: df['source_page']=None
|
||||
for c in STANDARD_COLUMNS:
|
||||
if c not in df: df[c]=None
|
||||
return df[STANDARD_COLUMNS]
|
||||
|
||||
class BaseParser:
|
||||
bank_name='Unknown'
|
||||
parser_name='BaseParser'
|
||||
@classmethod
|
||||
def detect(cls,text:str)->float: return 0.0
|
||||
def parse(self,path:str|Path,text:str|None=None): raise NotImplementedError
|
||||
@@ -0,0 +1,20 @@
|
||||
from __future__ import annotations
|
||||
import re
|
||||
from .base import amount, norm
|
||||
|
||||
def find(pattern,text,group=1,flags=re.I|re.M):
|
||||
m=re.search(pattern,text,flags)
|
||||
return norm(m.group(group)) if m else ''
|
||||
|
||||
def date_iso(s):
|
||||
import pandas as pd
|
||||
x=pd.to_datetime(s,errors='coerce',dayfirst=True)
|
||||
return '' if pd.isna(x) else x.strftime('%Y-%m-%d')
|
||||
|
||||
def split_pages(text): return text.split('\f')
|
||||
|
||||
def infer_mode(n):
|
||||
u=(n or '').upper()
|
||||
for k,v in [('UPI','UPI'),('NEFT','NEFT'),('IMPS','IMPS'),('RTGS','RTGS'),('CASH DEPOSIT','Cash Deposit'),('CASH WITHDRAWAL','Cash Withdrawal'),('ATM','ATM'),('CHEQUE','Cheque'),('CHQ','Cheque'),('POS','POS'),('EDC','Card Settlement'),('ACH','ACH')]:
|
||||
if k in u:return v
|
||||
return 'Other'
|
||||
@@ -0,0 +1,58 @@
|
||||
from __future__ import annotations
|
||||
import re, pandas as pd
|
||||
from pathlib import Path
|
||||
from .base import *
|
||||
from .common import find
|
||||
|
||||
class HDFCParser(BaseParser):
|
||||
bank_name='HDFC Bank'; parser_name='HDFCParser'
|
||||
@classmethod
|
||||
def detect(cls,text):
|
||||
u=text.upper(); return 0.97 if 'HDFC' in u and 'WITHDRAWAL AMT.' in u and 'DEPOSIT AMT.' in u else 0
|
||||
def parse(self,path,text=None):
|
||||
text=text or extract_text(path); meta=StatementMeta(bank_name=self.bank_name,source_file=Path(path).name,parser_name=self.parser_name,confidence='High')
|
||||
meta.account_number=find(r'Account No\s*:?\s*([0-9X*]+)',text)
|
||||
meta.customer_id=find(r'Cust ID\s*:?\s*([0-9X*]+)',text)
|
||||
meta.ifsc=find(r'(?:RTGS/\s*NEFT IFSC|IFSC)\s*:?\s*([A-Z0-9]+)',text)
|
||||
m=re.search(r'From\s*:\s*(\d{2}/\d{2}/\d{4})\s+To\s*:\s*(\d{2}/\d{2}/\d{4})',text,re.I)
|
||||
if m:
|
||||
meta.period_from=pd.to_datetime(m.group(1),dayfirst=True).strftime('%Y-%m-%d'); meta.period_to=pd.to_datetime(m.group(2),dayfirst=True).strftime('%Y-%m-%d')
|
||||
# first non-empty line before address usually contains customer name; allow manual override in UI
|
||||
m=re.search(r'\n\s{2,}([^\n:]{3,60})\s*\n.*?Address\s*:',text,re.S|re.I)
|
||||
if m: meta.customer_name=norm(m.group(1).splitlines()[-1])
|
||||
lines=text.splitlines(); rows=[]; cur=None; page=1
|
||||
wd_pos,dep_pos,bal_pos=130,165,190
|
||||
date_re=re.compile(r'^\s*(\d{2}/\d{2}/\d{2})\s+(.*)$')
|
||||
for line in lines:
|
||||
if '\f' in line: page += line.count('\f')
|
||||
if 'Withdrawal Amt.' in line and 'Deposit Amt.' in line:
|
||||
wd_pos=line.find('Withdrawal Amt.'); dep_pos=line.find('Deposit Amt.'); bal_pos=line.find('Closing Balance'); continue
|
||||
m=date_re.match(line)
|
||||
if m:
|
||||
if cur: rows.append(cur)
|
||||
cur={'transaction_date':m.group(1),'value_date':'','raw_lines':[line],'source_page':page,'wd_pos':wd_pos,'dep_pos':dep_pos,'bal_pos':bal_pos}
|
||||
elif cur and line.strip() and not re.match(r'^(Page No|Statement of account|Date\s+Narration|This is a computer)',line.strip(),re.I): cur['raw_lines'].append(line)
|
||||
if cur: rows.append(cur)
|
||||
out=[]
|
||||
for r in rows:
|
||||
first=r['raw_lines'][0]; body=' '.join(x.strip() for x in r['raw_lines'])
|
||||
# identify value date and ref on first line
|
||||
dts=list(re.finditer(r'\d{2}/\d{2}/\d{2}',first))
|
||||
if len(dts)>1: r['value_date']=dts[-1].group()
|
||||
else: r['value_date']=r['transaction_date']
|
||||
nums=list(re.finditer(r'(?<!\d)(?:\d{1,3}(?:,\d{3})+|\d+)\.\d{2}(?!\d)',first))
|
||||
debit=credit=bal=None
|
||||
for n in nums:
|
||||
x=amount(n.group()); p=n.start()
|
||||
if p>=r['bal_pos']-5: bal=x
|
||||
elif p>=r['dep_pos']-5: credit=x
|
||||
elif p>=r['wd_pos']-5: debit=x
|
||||
if bal is None and nums: bal=amount(nums[-1].group())
|
||||
# narration is text between date and likely ref/value-date region, plus continuation lines
|
||||
narr=first[dts[0].end():]
|
||||
if len(dts)>1: narr=narr[:dts[-1].start()-dts[0].end()]
|
||||
narr=norm(narr+' '+' '.join(x.strip() for x in r['raw_lines'][1:]))
|
||||
ref=''; z=re.search(r'\b([A-Z0-9]{10,})\b',body); ref=z.group(1) if z else ''
|
||||
if debit is None and credit is None: continue
|
||||
out.append({**r,'narration':narr,'reference_no':ref,'debit':debit,'credit':credit,'balance':bal})
|
||||
return meta,finalize(pd.DataFrame(out),meta)
|
||||
@@ -0,0 +1,56 @@
|
||||
from __future__ import annotations
|
||||
import re
|
||||
import pandas as pd
|
||||
from pathlib import Path
|
||||
from .base import BaseParser, StatementMeta, extract_text, amount, norm, finalize, page_of_line
|
||||
from .common import find, date_iso
|
||||
|
||||
class IDFCFirstParser(BaseParser):
|
||||
bank_name='IDFC FIRST Bank'; parser_name='IDFCFirstParser'
|
||||
@classmethod
|
||||
def detect(cls,text):
|
||||
u=text.upper(); return 0.99 if 'IDFC FIRST BANK' in u and 'STATEMENT PERIOD' in u else 0
|
||||
def parse(self,path,text=None):
|
||||
text=text or extract_text(path)
|
||||
meta=StatementMeta(bank_name=self.bank_name,source_file=Path(path).name,parser_name=self.parser_name,confidence='High')
|
||||
meta.customer_name=find(r'CUSTOMER NAME\s*:\s*([^\n]+)',text)
|
||||
meta.account_number=find(r'ACCOUNT NO\s*:\s*([0-9X*]+)',text)
|
||||
meta.customer_id=find(r'CUSTOMER ID\s*:\s*([0-9X*]+)',text)
|
||||
meta.ifsc=find(r'IFSC\s*:\s*([A-Z0-9]+)',text)
|
||||
m=re.search(r'STATEMENT PERIOD\s*:\s*(\d{4}-\d{2}-\d{2})\s+TO\s+(\d{4}-\d{2}-\d{2})',text,re.I)
|
||||
if m: meta.period_from,meta.period_to=m.groups()
|
||||
m=re.search(r'Opening Balance\s+Total Debit\s+Total Credit\s+Closing Balance\s*\n\s*([\d,.]+)\s+([\d,.]+)\s+([\d,.]+)\s+([\d,.]+)',text,re.I)
|
||||
if m: meta.opening_balance,meta.total_debit,meta.total_credit,meta.closing_balance=map(amount,m.groups())
|
||||
lines=text.splitlines(); rows=[]; current=None; pos=0
|
||||
pat=re.compile(r'^\s*(\d{2}-[A-Za-z]{3}-\d{4})\s+(\d{2}-[A-Za-z]{3}-\d{4})\s+(.*)$')
|
||||
for line in lines:
|
||||
mm=pat.match(line)
|
||||
if mm:
|
||||
if current: rows.append(current)
|
||||
current={'transaction_date':mm.group(1),'value_date':mm.group(2),'body':mm.group(3),'source_page':page_of_line(text,pos)}
|
||||
elif current and line.strip() and not re.match(r'^(STATEMENT|Opening Balance|REGISTERED OFFICE|Page \d+)',line.strip(),re.I):
|
||||
current['body']+=' '+line.strip()
|
||||
pos+=len(line)+1
|
||||
if current: rows.append(current)
|
||||
out=[]; prev=meta.opening_balance
|
||||
for r in rows:
|
||||
body=norm(r['body']); nums=list(re.finditer(r'(?<!\d)(?:\d{1,3}(?:,\d{2,3})+|\d+)\.\d{2}(?!\d)',body))
|
||||
if not nums: continue
|
||||
bal=amount(nums[-1].group()); rem=body[:nums[-1].start()].strip(); vals=[amount(x.group()) for x in nums[:-1]]
|
||||
debit=credit=None
|
||||
if vals:
|
||||
txn=vals[-1]
|
||||
if prev is not None and bal is not None:
|
||||
d1=round(prev-txn,2); c1=round(prev+txn,2)
|
||||
if abs(d1-bal)<0.02: debit=txn
|
||||
elif abs(c1-bal)<0.02: credit=txn
|
||||
else:
|
||||
# explicit columns often leave one amount only; infer from change
|
||||
credit=txn if bal>=prev else None; debit=txn if bal<prev else None
|
||||
else: credit=txn
|
||||
ref=''
|
||||
z=re.search(r'(?:UPI|NEFT|IMPS|RTGS)[/-](?:MOB/|OPM/|INET/|DR/|CR/)?([A-Z0-9]{8,})',rem,re.I)
|
||||
if z: ref=z.group(1)
|
||||
out.append({**r,'narration':rem,'reference_no':ref,'debit':debit,'credit':credit,'balance':bal})
|
||||
if bal is not None: prev=bal
|
||||
return meta,finalize(pd.DataFrame(out),meta)
|
||||
@@ -0,0 +1,102 @@
|
||||
from __future__ import annotations
|
||||
import re, pandas as pd
|
||||
from pathlib import Path
|
||||
from .base import *
|
||||
from .common import find
|
||||
|
||||
class IndianBankModernParser(BaseParser):
|
||||
bank_name='Indian Bank'; parser_name='IndianBankModernParser'
|
||||
@classmethod
|
||||
def detect(cls,text):
|
||||
u=text.upper(); return 0.98 if 'ACCOUNT STATEMENT' in u and 'TRANSACTION DETAILS' in u and 'TOTAL CREDITS' in u else 0
|
||||
def parse(self,path,text=None):
|
||||
text=text or extract_text(path); meta=StatementMeta(bank_name=self.bank_name,source_file=Path(path).name,parser_name=self.parser_name,confidence='High')
|
||||
meta.customer_name=find(r'Account Holder Name\s*\n\s*([^\n]+)',text)
|
||||
meta.account_number=find(r'Account Number\s*\n?\s*([0-9X*]+)',text)
|
||||
m=re.search(r'For period:\s*(\d{2}\s+[A-Za-z]{3}\s+\d{4})\s*-\s*(\d{2}\s+[A-Za-z]{3}\s+\d{4})',text,re.I)
|
||||
if m:
|
||||
meta.period_from=pd.to_datetime(m.group(1),dayfirst=True).strftime('%Y-%m-%d'); meta.period_to=pd.to_datetime(m.group(2),dayfirst=True).strftime('%Y-%m-%d')
|
||||
meta.opening_balance=amount(find(r'Opening Balance\s+INR\s*([\d,]+\.\d{2})',text))
|
||||
meta.total_credit=amount(find(r'Total Credits\s+\+\s*INR\s*([\d,]+\.\d{2})',text))
|
||||
meta.total_debit=amount(find(r'Total Debits\s+-\s*INR\s*([\d,]+\.\d{2})',text))
|
||||
meta.closing_balance=amount(find(r'Ending Balance\s+INR\s*([\d,]+\.\d{2})',text))
|
||||
date_re=re.compile(r'^\s*([A-Za-z]{3}\s+\d{2}\s+\d{4})\s+(.*)$')
|
||||
rows=[]; cur=None; page=1
|
||||
for line in text.splitlines():
|
||||
if '\f' in line: page+=line.count('\f')
|
||||
m=date_re.match(line)
|
||||
if m:
|
||||
if cur: rows.append(cur)
|
||||
cur={'transaction_date':m.group(1),'value_date':m.group(1),'lines':[m.group(2)],'source_page':page}
|
||||
elif cur and line.strip() and not re.match(r'^(Date\s+Transaction|ACCOUNT STATEMENT|Page)',line.strip(),re.I): cur['lines'].append(line)
|
||||
if cur: rows.append(cur)
|
||||
out=[]; prev=meta.opening_balance
|
||||
for r in rows:
|
||||
first=r['lines'][0]; alltxt=norm(' '.join(r['lines']))
|
||||
vals=[(m.start(),amount(m.group(1))) for m in re.finditer(r'INR\s*([\d,]+\.\d{2})',first,re.I)]
|
||||
# columns in sample: debit ~45, credit ~65, balance ~85. Use signs/placeholders and running balance.
|
||||
bal=vals[-1][1] if vals else None; debit=credit=None
|
||||
if len(vals)>=2:
|
||||
txn=vals[-2][1]
|
||||
before=first[:re.search(r'INR\s*[\d,]+\.\d{2}',first,re.I).start()] if re.search(r'INR\s*[\d,]+\.\d{2}',first,re.I) else first
|
||||
# presence of '-' before first amount often means no debit; inspect spacing/position
|
||||
p=vals[-2][0]
|
||||
if prev is not None and bal is not None:
|
||||
if abs((prev-txn)-bal)<0.05: debit=txn
|
||||
elif abs((prev+txn)-bal)<0.05: credit=txn
|
||||
if debit is None and credit is None:
|
||||
if p<52: debit=txn
|
||||
else: credit=txn
|
||||
narr=re.split(r'\s+INR\s*[\d,]+\.\d{2}',alltxt,1,flags=re.I)[0]
|
||||
ref=''; z=re.search(r'(?:NEFT|IMPS|UPI|RTGS)[/A-Z0-9-]{6,}',alltxt,re.I); ref=z.group(0) if z else ''
|
||||
if debit is None and credit is None: continue
|
||||
out.append({**r,'narration':narr,'reference_no':ref,'debit':debit,'credit':credit,'balance':bal})
|
||||
if bal is not None: prev=bal
|
||||
return meta,finalize(pd.DataFrame(out),meta)
|
||||
|
||||
class IndianBankLegacyParser(BaseParser):
|
||||
bank_name='Indian Bank'; parser_name='IndianBankLegacyParser'
|
||||
@classmethod
|
||||
def detect(cls,text):
|
||||
u=text.upper(); return 0.97 if 'STATEMENT OF ACCOUNT FROM' in u and 'REMITTER' in u and 'CHEQUE NO' in u else 0
|
||||
def parse(self,path,text=None):
|
||||
text=text or extract_text(path); meta=StatementMeta(bank_name=self.bank_name,source_file=Path(path).name,parser_name=self.parser_name,confidence='Medium')
|
||||
meta.account_number=find(r'for Account Number\s*\.?\s*([0-9X*]+)',text)
|
||||
m=re.search(r'STATEMENT OF ACCOUNT from\s*(\d{2}/\d{2}/\d{4})\s*to\s*(\d{2}/\d{2}/\d{4})',text,re.I)
|
||||
if m:
|
||||
meta.period_from=pd.to_datetime(m.group(1),dayfirst=True).strftime('%Y-%m-%d'); meta.period_to=pd.to_datetime(m.group(2),dayfirst=True).strftime('%Y-%m-%d')
|
||||
date_re=re.compile(r'^\s*(\d{2}/\d{2})(?:/\d{4})?\s+(\d{2}/\d{2})(?:/\d{4})?\s+(.*)$')
|
||||
rows=[]; cur=None; page=1
|
||||
for line in text.splitlines():
|
||||
if '\f' in line: page+=line.count('\f')
|
||||
m=date_re.match(line)
|
||||
if m:
|
||||
if cur: rows.append(cur)
|
||||
year=(meta.period_from[:4] if meta.period_from else '2024')
|
||||
td=m.group(1).replace(' ','')+'/'+year; vd=m.group(2).replace(' ','')+'/'+year
|
||||
cur={'transaction_date':td,'value_date':vd,'lines':[m.group(3)],'source_page':page}
|
||||
elif cur and line.strip() and not re.match(r'^(Value Post|Date Date|STATEMENT OF ACCOUNT|Page No)',line.strip(),re.I): cur['lines'].append(line)
|
||||
if cur: rows.append(cur)
|
||||
out=[]; prev=None
|
||||
for r in rows:
|
||||
first=r['lines'][0]; alltxt=norm(' '.join(r['lines']))
|
||||
# balance is amount followed by CR/DR at far right
|
||||
mb=re.search(r'([\d,]+\.\d{2})(CR|DR)\s*$',first,re.I)
|
||||
if not mb: continue
|
||||
bal=amount(mb.group(1)); prefix=first[:mb.start()]
|
||||
nums=list(re.finditer(r'(?<!\d)([\d,]+\.\d{2})(?!\d)',prefix))
|
||||
txn=amount(nums[-1].group(1)) if nums else None
|
||||
debit=credit=None
|
||||
if txn is not None and prev is not None:
|
||||
if abs((prev-txn)-bal)<0.05: debit=txn
|
||||
elif abs((prev+txn)-bal)<0.05: credit=txn
|
||||
if txn is not None and debit is None and credit is None:
|
||||
# column location: DR before CR in legacy format
|
||||
credit=txn if nums[-1].start()>70 else None; debit=txn if nums[-1].start()<=70 else None
|
||||
narr=alltxt
|
||||
ref=''; z=re.search(r'(?:UPI|NEFT|IMPS|RTGS)[/A-Z0-9-]{6,}',alltxt,re.I); ref=z.group(0) if z else ''
|
||||
out.append({**r,'narration':narr,'reference_no':ref,'debit':debit,'credit':credit,'balance':bal})
|
||||
prev=bal
|
||||
if out and meta.opening_balance is None:
|
||||
first=out[0]; txn=(first.get('debit') or 0)-(first.get('credit') or 0); meta.opening_balance=round((first['balance'] or 0)+txn,2)
|
||||
return meta,finalize(pd.DataFrame(out),meta)
|
||||
@@ -0,0 +1,53 @@
|
||||
from __future__ import annotations
|
||||
import re, pandas as pd
|
||||
from pathlib import Path
|
||||
from .base import *
|
||||
from .common import find
|
||||
|
||||
class IndusIndParser(BaseParser):
|
||||
bank_name='IndusInd Bank'; parser_name='IndusIndParser'
|
||||
@classmethod
|
||||
def detect(cls,text): return 0.98 if 'INDUSIND' in text.upper() and 'STATEMENT OF ACCOUNT' in text.upper() else 0
|
||||
def parse(self,path,text=None):
|
||||
text=text or extract_text(path); meta=StatementMeta(bank_name=self.bank_name,source_file=Path(path).name,parser_name=self.parser_name,confidence='Medium')
|
||||
meta.account_number=find(r'Account Number\s*:\s*([0-9X*]+)',text)
|
||||
meta.customer_id=find(r'Cust\.Reln\.No\s*:\s*([0-9X*]+)',text)
|
||||
meta.ifsc=find(r'IFSC Code\s*:\s*([A-Z0-9]+)',text)
|
||||
m=re.search(r'Period\s*:\s*(\d{2}[/-][A-Za-z0-9]{2,3}[/-]\d{2,4})\s*(?:to|TO|-)\s*(\d{2}[/-][A-Za-z0-9]{2,3}[/-]\d{2,4})',text,re.I)
|
||||
if m:
|
||||
meta.period_from=pd.to_datetime(m.group(1),dayfirst=True).strftime('%Y-%m-%d'); meta.period_to=pd.to_datetime(m.group(2),dayfirst=True).strftime('%Y-%m-%d')
|
||||
meta.total_debit=amount(find(r'Total Withdrawal Amount\s*:\s*([\d,]+\.\d{2})',text))
|
||||
meta.total_credit=amount(find(r'Total Deposit Amount\s*:\s*([\d,]+\.\d{2})',text))
|
||||
# rows start with date and often end with amount Dr/Cr and balance Cr
|
||||
date_re=re.compile(r'^\s*(\d{2}[-/]?[A-Za-z]{3}[-/]?\d{2,4}|\d{2}-\d{2}-\d{4})\s+(.*)$')
|
||||
rows=[]; cur=None; page=1
|
||||
for line in text.splitlines():
|
||||
if '\f' in line: page+=line.count('\f')
|
||||
m=date_re.match(line)
|
||||
if m:
|
||||
if cur: rows.append(cur)
|
||||
cur={'transaction_date':m.group(1),'value_date':m.group(1),'lines':[m.group(2)],'source_page':page}
|
||||
elif cur and line.strip() and not re.match(r'^(Statement Summary|Opening Balance|Total Withdrawal|Branch Address|The limits)',line.strip(),re.I): cur['lines'].append(line)
|
||||
if cur: rows.append(cur)
|
||||
out=[]; prev=None
|
||||
for r in rows:
|
||||
first=r['lines'][0]; alltxt=norm(' '.join(r['lines']))
|
||||
# Typical: narration ref debit Dr credit Cr balance Cr
|
||||
tokens=list(re.finditer(r'([\d,]+\.\d{2})\s*(Dr|Cr)',first,re.I))
|
||||
if not tokens: continue
|
||||
debit=credit=bal=None
|
||||
if len(tokens)>=2:
|
||||
bal=amount(tokens[-1].group(1))
|
||||
txn=amount(tokens[-2].group(1)); typ=tokens[-2].group(2).upper()
|
||||
if typ=='DR': debit=txn
|
||||
else: credit=txn
|
||||
elif len(tokens)==1:
|
||||
# carried forward / balance-only line; skip
|
||||
continue
|
||||
narr=first[:tokens[-2].start()].strip()+' '+' '.join(x.strip() for x in r['lines'][1:])
|
||||
ref=''; z=re.search(r'\b([A-Z0-9]{8,})\b',narr); ref=z.group(1) if z else ''
|
||||
out.append({**r,'narration':norm(narr),'reference_no':ref,'debit':debit,'credit':credit,'balance':bal})
|
||||
if out:
|
||||
f=out[0]; meta.opening_balance=round((f['balance'] or 0)+(f.get('debit') or 0)-(f.get('credit') or 0),2)
|
||||
meta.closing_balance=out[-1]['balance']
|
||||
return meta,finalize(pd.DataFrame(out),meta)
|
||||
@@ -0,0 +1,54 @@
|
||||
from __future__ import annotations
|
||||
import re, pandas as pd
|
||||
from pathlib import Path
|
||||
from .base import *
|
||||
from .common import find
|
||||
|
||||
class KotakParser(BaseParser):
|
||||
bank_name='Kotak Mahindra Bank'; parser_name='KotakParser'
|
||||
@classmethod
|
||||
def detect(cls,text):
|
||||
u=text.upper(); return 0.98 if 'KOTAK' in u and 'CHEQUE/REFERENCE#' in u and 'TRANSACTION DETAILS' in u else 0
|
||||
def parse(self,path,text=None):
|
||||
text=text or extract_text(path); meta=StatementMeta(bank_name=self.bank_name,source_file=Path(path).name,parser_name=self.parser_name,confidence='High')
|
||||
meta.account_number=find(r'Account\s*#\s*Variant\s*KOTAK\s*\n.*?([0-9X*]{6,})',text,flags=re.I|re.S)
|
||||
meta.ifsc=find(r'IFSC\s+([A-Z0-9]+)',text)
|
||||
m=re.search(r'(\d{2}\s+[A-Za-z]{3},\s*\d{4})\s*-\s*(\d{2}\s+[A-Za-z]{3},\s*\d{4})',text)
|
||||
if m:
|
||||
meta.period_from=pd.to_datetime(m.group(1),dayfirst=True).strftime('%Y-%m-%d'); meta.period_to=pd.to_datetime(m.group(2),dayfirst=True).strftime('%Y-%m-%d')
|
||||
date_re=re.compile(r'^\s*(\d{2}\s+[A-Za-z]{3},\s*\d{4})\s+(.*)$')
|
||||
rows=[]; cur=None; page=1
|
||||
for line in text.splitlines():
|
||||
if '\f' in line: page+=line.count('\f')
|
||||
m=date_re.match(line)
|
||||
if m:
|
||||
if ' - ' in m.group(2) and re.match(r'\d{2}\s+[A-Za-z]{3},',m.group(2).strip()): continue
|
||||
if cur: rows.append(cur)
|
||||
cur={'transaction_date':m.group(1),'value_date':m.group(1),'lines':[m.group(2)],'source_page':page}
|
||||
elif cur and line.strip() and not re.match(r'^(DATE\s+TRANSACTION|Need help|Page \d+)',line.strip(),re.I): cur['lines'].append(line)
|
||||
if cur: rows.append(cur)
|
||||
out=[]
|
||||
for r in rows:
|
||||
first=r['lines'][0]; alltxt=norm(' '.join(r['lines']))
|
||||
# amounts are signed in debit/credit columns, final unsigned balance
|
||||
nums=list(re.finditer(r'([+-]?\d{1,3}(?:,\d{3})*\.\d{2})',first))
|
||||
if not nums: continue
|
||||
bal=amount(nums[-1].group(1)); debit=credit=None
|
||||
if len(nums)>=2:
|
||||
raw=nums[-2].group(1); txn=abs(amount(raw) or 0)
|
||||
if raw.strip().startswith('-'): debit=txn
|
||||
elif raw.strip().startswith('+'): credit=txn
|
||||
else:
|
||||
# position fallback: debit column before credit
|
||||
credit=txn if nums[-2].start()>95 else None; debit=txn if nums[-2].start()<=95 else None
|
||||
elif 'OPENING BALANCE' in first.upper():
|
||||
meta.opening_balance=bal; continue
|
||||
narr=first[:nums[-2].start() if len(nums)>=2 else nums[-1].start()].strip()+' '+' '.join(x.strip() for x in r['lines'][1:])
|
||||
ref=''; z=re.search(r'\b(?:UPI|NEFT|IMPS|RTGS)-[A-Z0-9]+\b',alltxt,re.I); ref=z.group(0) if z else ''
|
||||
if debit is None and credit is None: continue
|
||||
out.append({**r,'narration':norm(narr),'reference_no':ref,'debit':debit,'credit':credit,'balance':bal})
|
||||
if out:
|
||||
if meta.opening_balance is None:
|
||||
f=out[0]; meta.opening_balance=round((f['balance'] or 0)+(f.get('debit') or 0)-(f.get('credit') or 0),2)
|
||||
meta.closing_balance=out[-1]['balance']
|
||||
return meta,finalize(pd.DataFrame(out),meta)
|
||||
@@ -0,0 +1,25 @@
|
||||
from .idfc import IDFCFirstParser
|
||||
from .axis import AxisParser
|
||||
from .hdfc import HDFCParser
|
||||
from .indian_bank import IndianBankModernParser, IndianBankLegacyParser
|
||||
from .indusind import IndusIndParser
|
||||
from .kotak import KotakParser
|
||||
from .sbi import SBIModernParser, SBIOtherParser
|
||||
from .base import extract_text
|
||||
|
||||
PARSERS=[IDFCFirstParser,AxisParser,HDFCParser,IndianBankModernParser,IndianBankLegacyParser,IndusIndParser,KotakParser,SBIOtherParser,SBIModernParser]
|
||||
|
||||
def detect_parser(text):
|
||||
scored=sorted(((p.detect(text),p) for p in PARSERS),key=lambda x:x[0],reverse=True)
|
||||
if not scored or scored[0][0] <= 0: return None,0
|
||||
return scored[0][1](),scored[0][0]
|
||||
|
||||
def parse_pdf(path, bank_hint=None):
|
||||
text=extract_text(path)
|
||||
if bank_hint:
|
||||
for p in PARSERS:
|
||||
if bank_hint.lower() in p.bank_name.lower() or bank_hint.lower() in p.__name__.lower():
|
||||
return p().parse(path,text)
|
||||
parser,score=detect_parser(text)
|
||||
if parser is None: raise ValueError('Unsupported statement format. Add a bank-specific parser or use a supported sample format.')
|
||||
return parser.parse(path,text)
|
||||
@@ -0,0 +1,100 @@
|
||||
from __future__ import annotations
|
||||
import re, pandas as pd
|
||||
from pathlib import Path
|
||||
from .base import *
|
||||
from .common import find
|
||||
|
||||
class SBIModernParser(BaseParser):
|
||||
bank_name='State Bank of India'; parser_name='SBIModernParser'
|
||||
@classmethod
|
||||
def detect(cls,text):
|
||||
u=text.upper(); return 0.98 if 'STATE BANK OF INDIA' in u and 'REF NO./CHEQUE' in u and 'DETAILS' in u else 0
|
||||
def parse(self,path,text=None):
|
||||
text=text or extract_text(path); meta=StatementMeta(bank_name=self.bank_name,source_file=Path(path).name,parser_name=self.parser_name,confidence='High')
|
||||
meta.customer_name=find(r'Account Name\s*:?\s*([^\n]+)',text)
|
||||
meta.account_number=find(r'Account Number\s*:?\s*([0-9X*]+)',text)
|
||||
meta.ifsc=find(r'IFS Code\s*:?\s*([A-Z0-9]+)',text)
|
||||
m=re.search(r'Account Statement from\s*(\d{1,2}\s+[A-Za-z]{3}\s+\d{4})\s+to\s+(\d{1,2}\s+[A-Za-z]{3}\s+\d{4})',text,re.I)
|
||||
if m:
|
||||
meta.period_from=pd.to_datetime(m.group(1),dayfirst=True).strftime('%Y-%m-%d'); meta.period_to=pd.to_datetime(m.group(2),dayfirst=True).strftime('%Y-%m-%d')
|
||||
meta.opening_balance=amount(find(r'Balance as on[^\n]*\n\s*([\d,]+\.\d{2})',text))
|
||||
# Format A: date details ref debit credit balance
|
||||
date_re=re.compile(r'^\s*(\d{1,2}\s+[A-Za-z]{3}\s+\d{4})\s+(.*)$')
|
||||
rows=[]; cur=None; page=1
|
||||
for line in text.splitlines():
|
||||
if '\f' in line: page += line.count('\f')
|
||||
m=date_re.match(line)
|
||||
if m:
|
||||
if cur: rows.append(cur)
|
||||
cur={'transaction_date':m.group(1),'value_date':m.group(1),'lines':[m.group(2)],'source_page':page}
|
||||
elif cur and line.strip() and not re.match(r'^(Date\s+Details|Txn Date|Account Statement|State Bank)',line.strip(),re.I):
|
||||
cur['lines'].append(line)
|
||||
if cur: rows.append(cur)
|
||||
out=[]; prev=meta.opening_balance
|
||||
for r in rows:
|
||||
first=r['lines'][0]; alltxt=norm(' '.join(r['lines']))
|
||||
nums=list(re.finditer(r'(?<!\d)([\d,]+\.\d{2})(?!\d)',first))
|
||||
if not nums: continue
|
||||
bal=amount(nums[-1].group(1)); debit=credit=None
|
||||
# use dashes and positions from SBI layout: debit then credit then balance
|
||||
if len(nums)>=2:
|
||||
txn=amount(nums[-2].group(1)); p=nums[-2].start()
|
||||
if prev is not None and bal is not None:
|
||||
if abs((prev-txn)-bal)<0.05: debit=txn
|
||||
elif abs((prev+txn)-bal)<0.05: credit=txn
|
||||
if debit is None and credit is None:
|
||||
if p >= 78: credit=txn
|
||||
else: debit=txn
|
||||
narr=first[:nums[-2].start() if len(nums)>=2 else nums[-1].start()].strip()+' '+' '.join(x.strip() for x in r['lines'][1:])
|
||||
ref=''; z=re.search(r'(?:UPI|NEFT|IMPS|RTGS)[/A-Z0-9-]{6,}',alltxt,re.I); ref=z.group(0) if z else ''
|
||||
if debit is None and credit is None: continue
|
||||
out.append({**r,'narration':norm(narr),'reference_no':ref,'debit':debit,'credit':credit,'balance':bal})
|
||||
if bal is not None: prev=bal
|
||||
if out:
|
||||
if meta.opening_balance is None:
|
||||
f=out[0]; meta.opening_balance=round((f['balance'] or 0)+(f.get('debit') or 0)-(f.get('credit') or 0),2)
|
||||
meta.closing_balance=out[-1]['balance']
|
||||
return meta,finalize(pd.DataFrame(out),meta)
|
||||
|
||||
class SBIOtherParser(BaseParser):
|
||||
bank_name='State Bank of India'; parser_name='SBIOtherParser'
|
||||
@classmethod
|
||||
def detect(cls,text):
|
||||
u=text.upper(); return 0.97 if 'TXN DATE' in u and 'VALUE' in u and 'REF NO./CHEQUE' in u and 'BY TRANSFER' in u else 0
|
||||
def parse(self,path,text=None):
|
||||
text=text or extract_text(path); meta=StatementMeta(bank_name=self.bank_name,source_file=Path(path).name,parser_name=self.parser_name,confidence='High')
|
||||
meta.customer_name=find(r'Account Name\s*:\s*([^\n]+)',text)
|
||||
meta.account_number=find(r'Account Number\s*:?\s*([0-9X*]+)',text)
|
||||
meta.ifsc=find(r'IFS Code\s*:?\s*([A-Z0-9]+)',text)
|
||||
m=re.search(r'Account Statement from\s*(\d{1,2}\s+[A-Za-z]{3}\s+\d{4})\s+to\s+(\d{1,2}\s+[A-Za-z]{3}\s+\d{4})',text,re.I)
|
||||
if m:
|
||||
meta.period_from=pd.to_datetime(m.group(1),dayfirst=True).strftime('%Y-%m-%d'); meta.period_to=pd.to_datetime(m.group(2),dayfirst=True).strftime('%Y-%m-%d')
|
||||
m=re.search(r'Balance as on\s+[^\n]+\n',text,re.I)
|
||||
date_re=re.compile(r'^\s*(\d{1,2}\s+[A-Za-z]{3}\s+\d{4})\s+(\d{1,2}\s+[A-Za-z]{3}\s+\d{4})\s+(.*)$')
|
||||
rows=[]; cur=None; page=1
|
||||
for line in text.splitlines():
|
||||
if '\f' in line: page += line.count('\f')
|
||||
mm=date_re.match(line)
|
||||
if mm:
|
||||
if cur: rows.append(cur)
|
||||
cur={'transaction_date':mm.group(1),'value_date':mm.group(2),'lines':[mm.group(3)],'source_page':page}
|
||||
elif cur and line.strip() and not re.match(r'^(Txn Date|Account Statement|Account Name)',line.strip(),re.I): cur['lines'].append(line)
|
||||
if cur: rows.append(cur)
|
||||
out=[]
|
||||
for r in rows:
|
||||
first=r['lines'][0]; alltxt=norm(' '.join(r['lines']))
|
||||
nums=list(re.finditer(r'(?<!\d)([\d,]+\.\d{2})(?!\d)',first))
|
||||
if not nums: continue
|
||||
bal=amount(nums[-1].group(1)); debit=credit=None
|
||||
if len(nums)>=2:
|
||||
txn=amount(nums[-2].group(1)); p=nums[-2].start()
|
||||
# Based on header layout: Debit starts before Credit
|
||||
if p < 55: debit=txn
|
||||
else: credit=txn
|
||||
narr=first[:nums[-2].start() if len(nums)>=2 else nums[-1].start()].strip()+' '+' '.join(x.strip() for x in r['lines'][1:])
|
||||
ref=''; z=re.search(r'(?:UPI|NEFT|IMPS|RTGS)[/A-Z0-9-]{6,}',alltxt,re.I); ref=z.group(0) if z else ''
|
||||
if debit is None and credit is None: continue
|
||||
out.append({**r,'narration':norm(narr),'reference_no':ref,'debit':debit,'credit':credit,'balance':bal})
|
||||
if out:
|
||||
f=out[0]; meta.opening_balance=round((f['balance'] or 0)+(f.get('debit') or 0)-(f.get('credit') or 0),2); meta.closing_balance=out[-1]['balance']
|
||||
return meta,finalize(pd.DataFrame(out),meta)
|
||||
@@ -0,0 +1,161 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import shutil
|
||||
import uuid
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from pathlib import Path
|
||||
from typing import Iterable
|
||||
|
||||
from fastapi import UploadFile
|
||||
|
||||
from app.modules.documents.services import DEFAULT_STORAGE_ROOT
|
||||
|
||||
from .analyzer import analyze_files, export_excel
|
||||
|
||||
ALLOWED_ROLES = {"Partner", "Manager", "Branch Manager", "Staff", "Employee", "Consultant"}
|
||||
MAX_FILES = int(os.getenv("BANK_ANALYZER_MAX_FILES", "24"))
|
||||
MAX_FILE_BYTES = int(os.getenv("BANK_ANALYZER_MAX_FILE_MB", "50")) * 1024 * 1024
|
||||
RETENTION_HOURS = int(os.getenv("BANK_ANALYZER_FAILED_RETENTION_HOURS", "24"))
|
||||
_SAFE = re.compile(r"[^A-Za-z0-9._-]+")
|
||||
|
||||
|
||||
def _now() -> datetime:
|
||||
return datetime.now(timezone.utc)
|
||||
|
||||
|
||||
def _root() -> Path:
|
||||
"""Return the automatic ERP work-storage root.
|
||||
|
||||
The document module already resolves its storage location for the current
|
||||
deployment. Bank-statement jobs use a sibling ``Work`` folder so no new
|
||||
environment variable or separate path configuration is required.
|
||||
"""
|
||||
return DEFAULT_STORAGE_ROOT.parent / "Work"
|
||||
|
||||
|
||||
def _segment(value: object, default: str = "NA") -> str:
|
||||
text = _SAFE.sub("_", str(value or default).strip()).strip("._-")
|
||||
return text[:80] or default
|
||||
|
||||
|
||||
def role_bucket(roles: Iterable[str]) -> str | None:
|
||||
role_set = set(roles)
|
||||
for role, bucket in (("Partner", "Partner"), ("Manager", "Manager"), ("Branch Manager", "Manager"), ("Staff", "Staff"), ("Employee", "Staff"), ("Consultant", "Consultant")):
|
||||
if role in role_set:
|
||||
return bucket
|
||||
return None
|
||||
|
||||
|
||||
def can_use(roles: Iterable[str]) -> bool:
|
||||
return bool(set(roles) & ALLOWED_ROLES)
|
||||
|
||||
|
||||
def _user_root(user, roles: Iterable[str]) -> Path:
|
||||
bucket = role_bucket(roles)
|
||||
if not bucket:
|
||||
raise PermissionError("Bank Statement Analyzer is available only to Partner, Manager, Staff and Consultant roles.")
|
||||
label = _segment(getattr(user, "full_name", None) or getattr(user, "email", None) or f"user_{user.id}")
|
||||
return _root() / bucket / f"{int(user.id)}_{label}" / "Bank_Statement_Analyzer"
|
||||
|
||||
|
||||
def cleanup_expired(user, roles: Iterable[str]) -> None:
|
||||
base = _user_root(user, roles)
|
||||
if not base.exists():
|
||||
return
|
||||
cutoff = _now() - timedelta(hours=RETENTION_HOURS)
|
||||
for child in base.iterdir():
|
||||
try:
|
||||
modified = datetime.fromtimestamp(child.stat().st_mtime, tz=timezone.utc)
|
||||
if child.is_dir() and modified < cutoff:
|
||||
shutil.rmtree(child, ignore_errors=True)
|
||||
except OSError:
|
||||
continue
|
||||
|
||||
|
||||
def create_job(user, roles: Iterable[str]) -> tuple[str, Path, Path]:
|
||||
cleanup_expired(user, roles)
|
||||
job_id = uuid.uuid4().hex
|
||||
job = _user_root(user, roles) / job_id
|
||||
input_dir = job / "Input"
|
||||
output_dir = job / "Output"
|
||||
input_dir.mkdir(parents=True, exist_ok=False)
|
||||
output_dir.mkdir(parents=True, exist_ok=False)
|
||||
return job_id, input_dir, output_dir
|
||||
|
||||
|
||||
def _validate_pdf_header(data: bytes) -> None:
|
||||
if not data.startswith(b"%PDF-"):
|
||||
raise ValueError("Only genuine PDF files are allowed.")
|
||||
|
||||
|
||||
async def save_uploads(files: list[UploadFile], input_dir: Path) -> list[Path]:
|
||||
usable = [f for f in files if f and (f.filename or "").strip()]
|
||||
if not usable:
|
||||
raise ValueError("Please select at least one PDF bank statement.")
|
||||
if len(usable) > MAX_FILES:
|
||||
raise ValueError(f"A maximum of {MAX_FILES} PDF files can be analyzed in one job.")
|
||||
saved: list[Path] = []
|
||||
for index, upload in enumerate(usable, start=1):
|
||||
name = Path(upload.filename or f"statement_{index}.pdf").name
|
||||
if Path(name).suffix.lower() != ".pdf":
|
||||
raise ValueError(f"{name}: only PDF files are allowed.")
|
||||
safe_name = f"{index:02d}_{_segment(Path(name).stem, f'statement_{index}')}.pdf"
|
||||
target = input_dir / safe_name
|
||||
size = 0
|
||||
first = b""
|
||||
with target.open("wb") as handle:
|
||||
while True:
|
||||
chunk = await upload.read(1024 * 1024)
|
||||
if not chunk:
|
||||
break
|
||||
if not first:
|
||||
first = chunk[:8]
|
||||
size += len(chunk)
|
||||
if size > MAX_FILE_BYTES:
|
||||
raise ValueError(f"{name}: file exceeds the {MAX_FILE_BYTES // (1024 * 1024)} MB limit.")
|
||||
handle.write(chunk)
|
||||
_validate_pdf_header(first)
|
||||
saved.append(target)
|
||||
return saved
|
||||
|
||||
|
||||
def analyze_job(*, user, roles: Iterable[str], job_id: str, paths: list[Path], output_dir: Path, customer_override: str = "", account_override: str = "") -> dict:
|
||||
metas, all_df, unique_df = analyze_files(paths, customer_override.strip(), account_override.strip())
|
||||
output = output_dir / "Bank_Statement_Analysis.xlsx"
|
||||
export_excel(output, metas, all_df, unique_df)
|
||||
summary = {
|
||||
"job_id": job_id,
|
||||
"owner_user_id": int(user.id),
|
||||
"created_at": _now().isoformat(),
|
||||
"statement_count": len(metas),
|
||||
"rows_extracted": int(len(all_df)),
|
||||
"unique_transactions": int(len(unique_df)),
|
||||
"exact_duplicate_rows": int(all_df.exact_duplicate.sum()) if not all_df.empty else 0,
|
||||
"possible_duplicate_rows": int(all_df.possible_duplicate.sum()) if not all_df.empty else 0,
|
||||
"banks": sorted({m.bank_name for m in metas}),
|
||||
"customer_name": next((m.customer_name for m in metas if m.customer_name), ""),
|
||||
"account_number": next((m.account_number for m in metas if m.account_number), ""),
|
||||
"output_file": output.name,
|
||||
}
|
||||
(output_dir.parent / "job.json").write_text(json.dumps(summary, indent=2), encoding="utf-8")
|
||||
return summary
|
||||
|
||||
|
||||
def resolve_owned_job(user, roles: Iterable[str], job_id: str) -> tuple[Path, dict]:
|
||||
if not re.fullmatch(r"[a-f0-9]{32}", job_id or ""):
|
||||
raise FileNotFoundError("Analysis job not found.")
|
||||
job = _user_root(user, roles) / job_id
|
||||
meta_path = job / "job.json"
|
||||
if not meta_path.is_file():
|
||||
raise FileNotFoundError("Analysis job not found.")
|
||||
meta = json.loads(meta_path.read_text(encoding="utf-8"))
|
||||
if int(meta.get("owner_user_id", 0)) != int(user.id):
|
||||
raise PermissionError("You cannot access another user's analysis job.")
|
||||
return job, meta
|
||||
|
||||
|
||||
def delete_job(job: Path) -> None:
|
||||
shutil.rmtree(job, ignore_errors=True)
|
||||
@@ -0,0 +1,20 @@
|
||||
{% extends "ui/templates/base/layout.html" %}
|
||||
{% block content %}
|
||||
<div class="mx-auto max-w-5xl space-y-6">
|
||||
<div class="rounded-2xl border border-slate-200 bg-white p-6 shadow-soft">
|
||||
<h1 class="text-2xl font-bold text-slate-900">Bank Statement Analyzer</h1>
|
||||
<p class="mt-2 text-sm text-slate-600">Upload one or more supported PDF bank statements. The analyzer prepares a reconciled Excel workbook with transaction summaries and duplicate checks.</p>
|
||||
</div>
|
||||
{% if error %}<div class="rounded-2xl border border-red-200 bg-red-50 p-4 text-sm text-red-800"><strong>Analysis could not be completed.</strong><div class="mt-1">{{ error }}</div></div>{% endif %}
|
||||
<form action="/tools/bank-statement-analyzer/analyze" method="post" enctype="multipart/form-data" class="rounded-2xl border border-slate-200 bg-white p-6 shadow-soft">
|
||||
<input type="hidden" name="csrf_token" value="{{ csrf_token }}">
|
||||
<div class="grid gap-5 md:grid-cols-2">
|
||||
<div><label class="mb-1 block text-sm font-semibold text-slate-700">Account holder override <span class="font-normal text-slate-400">(optional)</span></label><input name="customer_name" class="w-full rounded-xl border border-slate-300 px-3 py-2 text-sm" placeholder="Use only when statement extraction needs correction"></div>
|
||||
<div><label class="mb-1 block text-sm font-semibold text-slate-700">Account number override <span class="font-normal text-slate-400">(optional)</span></label><input name="account_number" class="w-full rounded-xl border border-slate-300 px-3 py-2 text-sm" placeholder="Use only when statement extraction needs correction"></div>
|
||||
</div>
|
||||
<div class="mt-5"><label class="mb-1 block text-sm font-semibold text-slate-700">PDF bank statements</label><input type="file" name="statements" accept="application/pdf,.pdf" multiple required class="block w-full rounded-xl border border-slate-300 bg-white px-3 py-3 text-sm"></div>
|
||||
<div class="mt-5 rounded-xl bg-slate-50 p-4 text-sm text-slate-600"><div class="font-semibold text-slate-800">Supported parsers</div><div class="mt-1">Axis Bank, HDFC Bank, IDFC FIRST Bank, Indian Bank, IndusInd Bank, Kotak Mahindra Bank and State Bank of India.</div><div class="mt-2 text-xs">Successful jobs are deleted automatically after the Excel response is sent. Failed or abandoned jobs are cleaned after the configured retention period.</div></div>
|
||||
<div class="mt-6 flex flex-wrap gap-3"><button class="rounded-xl bg-brand-600 px-5 py-2.5 text-sm font-semibold text-white hover:bg-brand-700">Analyze Statements</button></div>
|
||||
</form>
|
||||
</div>
|
||||
{% endblock %}
|
||||
@@ -0,0 +1,15 @@
|
||||
{% extends "ui/templates/base/layout.html" %}
|
||||
{% block content %}
|
||||
<div class="mx-auto max-w-5xl space-y-6">
|
||||
<div class="rounded-2xl border border-emerald-200 bg-emerald-50 p-6 shadow-soft"><h1 class="text-2xl font-bold text-emerald-900">Analysis completed</h1><p class="mt-2 text-sm text-emerald-800">Review the summary below and download the Excel workbook. The uploaded PDFs and temporary workbook are removed automatically after the download response completes.</p></div>
|
||||
<div class="grid gap-4 sm:grid-cols-2 lg:grid-cols-4">
|
||||
{% for label, value in [('Statements', summary.statement_count), ('Rows extracted', summary.rows_extracted), ('Unique transactions', summary.unique_transactions), ('Exact duplicate rows', summary.exact_duplicate_rows), ('Possible duplicate rows', summary.possible_duplicate_rows)] %}
|
||||
<div class="rounded-2xl border border-slate-200 bg-white p-5 shadow-soft"><div class="text-xs font-semibold uppercase tracking-wide text-slate-500">{{ label }}</div><div class="mt-2 text-2xl font-bold text-slate-900">{{ value }}</div></div>
|
||||
{% endfor %}
|
||||
</div>
|
||||
<div class="rounded-2xl border border-slate-200 bg-white p-6 shadow-soft">
|
||||
<dl class="grid gap-4 md:grid-cols-2"><div><dt class="text-xs font-semibold uppercase text-slate-500">Bank(s)</dt><dd class="mt-1 text-sm font-medium text-slate-900">{{ summary.banks|join(', ') }}</dd></div><div><dt class="text-xs font-semibold uppercase text-slate-500">Account holder</dt><dd class="mt-1 text-sm font-medium text-slate-900">{{ summary.customer_name or '-' }}</dd></div></dl>
|
||||
<div class="mt-6 flex flex-wrap gap-3"><a href="/tools/bank-statement-analyzer/{{ summary.job_id }}/download" class="rounded-xl bg-brand-600 px-5 py-2.5 text-sm font-semibold text-white hover:bg-brand-700">Download Analysis Excel</a><form action="/tools/bank-statement-analyzer/{{ summary.job_id }}/delete" method="post"><input type="hidden" name="csrf_token" value="{{ csrf_token }}"><button class="rounded-xl border border-slate-300 px-5 py-2.5 text-sm font-semibold text-slate-700 hover:bg-slate-50">Delete Without Download</button></form></div>
|
||||
</div>
|
||||
</div>
|
||||
{% endblock %}
|
||||
@@ -0,0 +1,116 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import shutil
|
||||
from pathlib import Path
|
||||
|
||||
from fastapi import APIRouter, File, Form, Request, UploadFile
|
||||
from fastapi.responses import FileResponse, RedirectResponse
|
||||
from starlette.background import BackgroundTask
|
||||
|
||||
from app.core.db.common import CommonSessionLocal
|
||||
from app.core.http_responses import ui_access_denied, not_found_response
|
||||
from app.core.security.csrf import get_or_create_csrf_token, validate_csrf
|
||||
from app.core.security.session_auth import get_current_user
|
||||
from app.core.templating import templates
|
||||
from app.modules.core.rbac.deps import get_user_permissions, get_user_roles
|
||||
from .service import can_use, create_job, save_uploads, analyze_job, resolve_owned_job, delete_job
|
||||
|
||||
router = APIRouter(prefix="/tools/bank-statement-analyzer", tags=["bank-statement-analyzer-ui"])
|
||||
|
||||
|
||||
def _ctx(request, db, user, **extra):
|
||||
data = {
|
||||
"request": request,
|
||||
"current_user": user,
|
||||
"current_user_roles": get_user_roles(db, user.id),
|
||||
"current_user_permissions": get_user_permissions(db, user.id),
|
||||
"csrf_token": get_or_create_csrf_token(request),
|
||||
"title": "Bank Statement Analyzer",
|
||||
}
|
||||
data.update(extra)
|
||||
return data
|
||||
|
||||
|
||||
def _auth(request, db):
|
||||
user = get_current_user(request, db=db)
|
||||
if not user:
|
||||
return None, None, RedirectResponse("/login", status_code=303)
|
||||
roles = get_user_roles(db, user.id)
|
||||
if not can_use(roles):
|
||||
return user, roles, ui_access_denied("Bank Statement Analyzer is available only to Partner, Manager, Staff and Consultant roles.")
|
||||
return user, roles, None
|
||||
|
||||
|
||||
@router.get("")
|
||||
def index(request: Request):
|
||||
db = CommonSessionLocal()
|
||||
try:
|
||||
user, roles, denied = _auth(request, db)
|
||||
if denied:
|
||||
return denied
|
||||
return templates.TemplateResponse("modules/bank_statement_analyzer/templates/bank_statement_analyzer/index.html", _ctx(request, db, user, error=""))
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
|
||||
@router.post("/analyze")
|
||||
async def analyze(request: Request, csrf_token: str = Form(...), customer_name: str = Form(""), account_number: str = Form(""), statements: list[UploadFile] = File(...)):
|
||||
db = CommonSessionLocal()
|
||||
job_dir: Path | None = None
|
||||
try:
|
||||
user, roles, denied = _auth(request, db)
|
||||
if denied:
|
||||
return denied
|
||||
validate_csrf(request, csrf_token)
|
||||
job_id, input_dir, output_dir = create_job(user, roles)
|
||||
job_dir = input_dir.parent
|
||||
paths = await save_uploads(statements, input_dir)
|
||||
summary = analyze_job(user=user, roles=roles, job_id=job_id, paths=paths, output_dir=output_dir, customer_override=customer_name, account_override=account_number)
|
||||
return templates.TemplateResponse("modules/bank_statement_analyzer/templates/bank_statement_analyzer/result.html", _ctx(request, db, user, summary=summary))
|
||||
except Exception as exc:
|
||||
if job_dir and job_dir.exists():
|
||||
# Failed jobs are retained for the configured short retention period for troubleshooting/retry.
|
||||
pass
|
||||
user = get_current_user(request, db=db)
|
||||
if not user:
|
||||
return RedirectResponse("/login", status_code=303)
|
||||
return templates.TemplateResponse("modules/bank_statement_analyzer/templates/bank_statement_analyzer/index.html", _ctx(request, db, user, error=str(exc)), status_code=400)
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
|
||||
@router.get("/{job_id}/download")
|
||||
def download(job_id: str, request: Request):
|
||||
db = CommonSessionLocal()
|
||||
try:
|
||||
user, roles, denied = _auth(request, db)
|
||||
if denied:
|
||||
return denied
|
||||
try:
|
||||
job, meta = resolve_owned_job(user, roles, job_id)
|
||||
except FileNotFoundError:
|
||||
return not_found_response(request, "Analysis job not found or already cleaned up.")
|
||||
output = job / "Output" / meta["output_file"]
|
||||
if not output.is_file():
|
||||
return not_found_response(request, "Analysis workbook not found.")
|
||||
return FileResponse(path=output, filename="Bank_Statement_Analysis.xlsx", media_type="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", background=BackgroundTask(delete_job, job))
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
|
||||
@router.post("/{job_id}/delete")
|
||||
def delete(job_id: str, request: Request, csrf_token: str = Form(...)):
|
||||
db = CommonSessionLocal()
|
||||
try:
|
||||
user, roles, denied = _auth(request, db)
|
||||
if denied:
|
||||
return denied
|
||||
validate_csrf(request, csrf_token)
|
||||
try:
|
||||
job, _ = resolve_owned_job(user, roles, job_id)
|
||||
delete_job(job)
|
||||
except FileNotFoundError:
|
||||
pass
|
||||
return RedirectResponse("/tools/bank-statement-analyzer", status_code=303)
|
||||
finally:
|
||||
db.close()
|
||||
@@ -32,6 +32,7 @@ from app.modules.workspace_navigation.ui import router as workspace_navigation_r
|
||||
from app.modules.firm_admin_dashboard.ui import router as firm_admin_dashboard_router
|
||||
from app.modules.aqmm_dashboard.ui import router as aqmm_dashboard_router
|
||||
from app.modules.peer_review_export.ui import router as peer_review_export_router
|
||||
from app.modules.bank_statement_analyzer.ui import router as bank_statement_analyzer_router
|
||||
|
||||
|
||||
def mount_ui(app: FastAPI) -> None:
|
||||
@@ -50,6 +51,7 @@ def mount_ui(app: FastAPI) -> None:
|
||||
app.include_router(services_ui_router)
|
||||
app.include_router(aqmm_dashboard_router)
|
||||
app.include_router(peer_review_export_router)
|
||||
app.include_router(bank_statement_analyzer_router)
|
||||
app.include_router(work_tracker_ui_router)
|
||||
app.include_router(billing_ui_router)
|
||||
app.include_router(platform_billing_ui_router)
|
||||
|
||||
@@ -61,6 +61,12 @@
|
||||
'visible': true,
|
||||
'active': _consultant_path.startswith('/consultant/profile')
|
||||
},
|
||||
{
|
||||
'label': 'Bank Analyzer',
|
||||
'url': '/tools/bank-statement-analyzer',
|
||||
'visible': true,
|
||||
'active': _consultant_path.startswith('/tools/bank-statement-analyzer')
|
||||
},
|
||||
{
|
||||
'label': 'Alerts',
|
||||
'url': '/alerts',
|
||||
|
||||
@@ -53,6 +53,12 @@
|
||||
'visible': true,
|
||||
'active': _manager_path.startswith('/employees/leave')
|
||||
},
|
||||
{
|
||||
'label': 'Bank Analyzer',
|
||||
'url': '/tools/bank-statement-analyzer',
|
||||
'visible': true,
|
||||
'active': _manager_path.startswith('/tools/bank-statement-analyzer')
|
||||
},
|
||||
{
|
||||
'label': 'Alerts',
|
||||
'url': '/alerts',
|
||||
|
||||
@@ -58,6 +58,12 @@
|
||||
'visible': true,
|
||||
'active': _partner_path.startswith('/billing')
|
||||
},
|
||||
{
|
||||
'label': 'Bank Analyzer',
|
||||
'url': '/tools/bank-statement-analyzer',
|
||||
'visible': true,
|
||||
'active': _partner_path.startswith('/tools/bank-statement-analyzer')
|
||||
},
|
||||
{
|
||||
'label': 'Alerts',
|
||||
'url': '/alerts',
|
||||
|
||||
@@ -62,6 +62,12 @@
|
||||
'visible': can_view_employee_portal(current_user, current_user_permissions, current_user_roles),
|
||||
'active': _staff_path.startswith('/employee/profile')
|
||||
},
|
||||
{
|
||||
'label': 'Bank Analyzer',
|
||||
'url': '/tools/bank-statement-analyzer',
|
||||
'visible': true,
|
||||
'active': _staff_path.startswith('/tools/bank-statement-analyzer')
|
||||
},
|
||||
{
|
||||
'label': 'Alerts',
|
||||
'url': '/alerts',
|
||||
|
||||
@@ -15,3 +15,6 @@ email-validator
|
||||
dnspython==2.7.0
|
||||
openpyxl
|
||||
itsdangerous
|
||||
pandas
|
||||
xlsxwriter
|
||||
pdfplumber
|
||||
|
||||
Reference in New Issue
Block a user