File size: 34,112 Bytes
f501431 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 | """
Merchant Classifier — LLM-powered UPI merchant identification with caching.
Flow:
1. Extract UPI handle from transaction description
2. Look up in SQLite merchant DB → return if found
3. If not found, call LLM to classify → store in DB → return
4. DB acts as persistent cache — LLM called only once per new merchant
DB tables:
- merchants: upi_handle → display_name, category, is_income, confidence
- merchant_aliases: canonical_name → upi_handle (for dedup)
"""
import sqlite3
import re
import json
from pathlib import Path
from typing import Optional, Tuple
DB_PATH = Path(__file__).parent.parent.parent / "data" / "merchants.db"
# Persist outside of rsync path so deploys don't wipe it
def get_merchant(upi_handle: str) -> Optional[dict]:
"""Look up a UPI handle in the merchant database."""
conn = None
try:
conn = sqlite3.connect(str(DB_PATH))
conn.row_factory = sqlite3.Row
row = conn.execute(
"SELECT * FROM merchants WHERE upi_handle = ?", (upi_handle,)
).fetchone()
return dict(row) if row else None
except sqlite3.OperationalError:
return None
finally:
if conn is not None:
conn.close()
def normalize_description_key(desc: str) -> str:
"""Normalize description for rule matching: uppercase, strip digits, collapse whitespace."""
if not desc:
return ""
text = str(desc).upper().strip()
text = re.sub(r'\d+', '', text)
text = re.sub(r'\s+', ' ', text).strip()
# Guard against very short keys that could match unrelated transactions
if len(text) < 5:
return ""
return text[:200]
def _ensure_description_rules_table(conn):
conn.execute(
"""
CREATE TABLE IF NOT EXISTS description_rules (
description_key TEXT PRIMARY KEY,
category TEXT NOT NULL,
is_income INTEGER DEFAULT 0,
confidence REAL DEFAULT 0.90,
sample_desc TEXT,
created_at TEXT
)
"""
)
def store_description_rule(desc: str, category: str, is_income: bool, confidence: float = 0.90) -> bool:
key = normalize_description_key(desc)
if not key:
return False
conn = sqlite3.connect(str(DB_PATH))
try:
_ensure_description_rules_table(conn)
import datetime
now_str = datetime.datetime.now(datetime.timezone.utc).isoformat()
conn.execute(
"""INSERT OR REPLACE INTO description_rules
(description_key, category, is_income, confidence, sample_desc, created_at)
VALUES (?, ?, ?, ?, ?, ?)""",
(key, category, 1 if is_income else 0, confidence, desc[:200], now_str)
)
conn.commit()
return True
except Exception as e:
print(f"Error storing description rule {key}: {e}")
return False
finally:
conn.close()
def get_description_rule(desc: str) -> Optional[dict]:
key = normalize_description_key(desc)
if not key:
return None
conn = None
try:
conn = sqlite3.connect(str(DB_PATH))
_ensure_description_rules_table(conn)
conn.row_factory = sqlite3.Row
row = conn.execute(
"SELECT * FROM description_rules WHERE description_key = ?", (key,)
).fetchone()
return dict(row) if row else None
except Exception:
return None
finally:
if conn is not None:
conn.close()
def extract_upi_handle(description: str) -> Optional[str]:
"""Extract the merchant/counterparty handle from an Indian bank transaction narration.
Supports all major Indian bank narration formats:
- UPI: UPI/merchant_handle/purpose/BANK/ref/txn_id (ICICI, HDFC, Axis)
- IMPS: IMPS/merchant_handle/... or IMPS-merchant_handle-...
- NEFT: NEFT/merchant_handle/... or NEFT CR/merchant_name/...
- RTGS: RTGS/merchant_handle/... or RTGS-merchant_handle-...
- NACH: NACH/merchant_handle/... or NACH-merchant_handle-...
- Generic: any string containing @vpa_handle pattern
"""
if not description:
return None
desc = description.strip()
# Format: UPI/handle/... (ICICI, HDFC, Axis, etc.)
if desc.upper().startswith('UPI/'):
parts = desc.split('/')
if len(parts) >= 2 and parts[1].strip():
return parts[1].strip().lower()[:100]
# Format: GENERIC-UPI/handle/... (SBI)
if 'UPI/' in desc.upper():
idx = desc.upper().index('UPI/')
parts = desc[idx:].split('/')
if len(parts) >= 2 and parts[1].strip():
return parts[1].strip().lower()[:100]
# Generic stop-words that indicate the narration segment is NOT a merchant handle
_NARRATION_STOP_WORDS = frozenset({
"transfer", "to", "from", "cr", "dr", "credit", "debit",
"payment", "refund", "reversal", "charges", "fee",
"salary", "interest", "dividend", "rent", "emi", "loan",
"tax", "tds", "cash", "deposit", "withdrawal",
})
# Format: IMPS/handle/... or IMPS-handle-...
if desc.upper().startswith('IMPS'):
parts = desc.split('/')
if len(parts) >= 2 and parts[1].strip():
candidate = parts[1].strip().lower()[:100]
if candidate not in _NARRATION_STOP_WORDS:
return candidate
# IMPS-merchant-bank format
dash_parts = desc.split('-')
if len(dash_parts) >= 2 and dash_parts[1].strip():
candidate = dash_parts[1].strip().lower()[:100]
if candidate not in _NARRATION_STOP_WORDS:
return candidate
# Format: NEFT/handle/... or NEFT CR/handle/... or NEFT DR/handle/...
if desc.upper().startswith('NEFT'):
parts = desc.split('/')
# Skip CR/DR suffix in first segment
start_idx = 1
if len(parts) >= 2 and parts[0].strip().upper() in ('NEFT CR', 'NEFT DR'):
start_idx = 1
if len(parts) > start_idx and parts[start_idx].strip():
candidate = parts[start_idx].strip().lower()[:100]
if candidate not in _NARRATION_STOP_WORDS:
return candidate
# NEFT-merchant-bank format
dash_parts = desc.split('-')
if len(dash_parts) >= 2 and dash_parts[1].strip():
candidate = dash_parts[1].strip().lower()[:100]
if candidate not in _NARRATION_STOP_WORDS:
return candidate
# Format: RTGS/handle/... or RTGS-handle-...
if desc.upper().startswith('RTGS'):
parts = desc.split('/')
if len(parts) >= 2 and parts[1].strip():
candidate = parts[1].strip().lower()[:100]
if candidate not in _NARRATION_STOP_WORDS:
return candidate
dash_parts = desc.split('-')
if len(dash_parts) >= 2 and dash_parts[1].strip():
candidate = dash_parts[1].strip().lower()[:100]
if candidate not in _NARRATION_STOP_WORDS:
return candidate
# Format: NACH/handle/... or NACH-handle-...
if desc.upper().startswith('NACH'):
parts = desc.split('/')
if len(parts) >= 2 and parts[1].strip():
candidate = parts[1].strip().lower()[:100]
if candidate not in _NARRATION_STOP_WORDS:
return candidate
dash_parts = desc.split('-')
if len(dash_parts) >= 2 and dash_parts[1].strip():
candidate = dash_parts[1].strip().lower()[:100]
if candidate not in _NARRATION_STOP_WORDS:
return candidate
# Format: handle@vpa (direct UPI ID in description)
m = re.search(r'([a-zA-Z0-9_.\-]{2,40}@[a-zA-Z]{2,20})', desc)
if m:
handle = m.group(1).lower()
# Skip personal-looking handles (common names)
personal_patterns = ['ybl', 'oksbi', 'okhdfc', 'okaxis', 'okicici', 'paytm', 'ibh',
'ybl', 'apl', 'axl', 'sbi', 'hdfcbank', 'icici', 'kotak']
vpa = handle.split('@')[1] if '@' in handle else ''
if vpa in personal_patterns:
return handle # Still return it — merchant DB can classify it as personal_transfer
return handle
# Format: UPI-DEBIT/handle/... or DEBIT-UPI/handle/...
if 'UPI' in desc.upper():
parts = desc.split('/')
for i, part in enumerate(parts):
if part.strip().upper().startswith('UPI') and i + 1 < len(parts):
handle = parts[i + 1].strip()
if handle:
return handle.lower()[:100]
return None
# Heuristic merchant name extraction from UPI handle
def extract_display_name(upi_handle: str) -> str:
"""Extract a human-readable display name from a UPI handle."""
# Take the part before @
name = upi_handle.split('@')[0] if '@' in upi_handle else upi_handle
# Remove common prefixes/suffixes
name = re.sub(r'^(pay|p2p|p2m|merchant|txn|trn|order|bill)', '', name, flags=re.IGNORECASE)
# Split on dots, hyphens, underscores and take meaningful parts
parts = re.split(r'[.\-_\s]+', name)
# Filter out short/empty parts and common noise
meaningful = [p for p in parts if len(p) >= 2 and p.lower() not in ('upi', 'com', 'in', 'ltd')]
if not meaningful:
return name[:40].title()
return ' '.join(meaningful[:3]).title()[:40]
# Heuristic category classification based on UPI handle keywords
MERCHANT_ALIASES = {
# Handle pattern → (display_name, category, is_income, confidence)
'apple': ('Apple', 'entertainment', False, 0.85),
'appleservices': ('Apple Services', 'entertainment', False, 0.85),
'amznlpa': ('Amazon', 'shopping', False, 0.85),
'amazon': ('Amazon', 'shopping', False, 0.85),
'discovery': ('Discovery+', 'entertainment', False, 0.85),
'simpl': ('Simpl', 'credit_card', False, 0.85),
'setu.simpl': ('Simpl', 'credit_card', False, 0.85),
'dlf': ('DLF', 'bills', False, 0.75),
'ambience': ('Ambience Mall', 'shopping', False, 0.75),
'bistro': ('Bistro', 'food', False, 0.80),
'bundl': ('Swiggy', 'food', False, 0.90),
'eternal': ('Zomato', 'food', False, 0.90),
'zepto': ('Zepto', 'grocery', False, 0.90),
'blinkit': ('Blinkit', 'grocery', False, 0.90),
'groww': ('Groww', 'investment', False, 0.85),
'indmoney': ('IndMoney', 'investment', False, 0.85),
'zerodha': ('Zerodha', 'trading_deposit', False, 0.85),
'paytmqr': ('PayTM QR', 'bills', False, 0.70),
'qutab': ('Qutab Plaza', 'bills', False, 0.70),
'hsquare': ('H Square', 'bills', False, 0.70),
'rumaani': ('Rumaani', 'food', False, 0.70),
'laxman': ('Laxman Cafe', 'food', False, 0.70),
'vinod': ('Vinod Mandi', 'grocery', False, 0.70),
'idealprepa': ('Ideal Prep', 'education', False, 0.70),
}
CURATED_TRANSACTION_MARKERS = {
'gpaytoll@icici': ('Google Pay FASTag', 'travel', False, 0.98),
'blusmartmobilit': ('BluSmart', 'travel', False, 0.98),
'1mg.payu@axisba': ('Tata 1mg', 'medical', False, 0.98),
'artemis ho': ('Artemis Hospital', 'medical', False, 0.98),
'artemishospita': ('Artemis Hospital', 'medical', False, 0.98),
'the chemis': ('The Chemist', 'medical', False, 0.95),
'the chemist': ('The Chemist', 'medical', False, 0.95),
'zomatoindia@ic': ('Zomato', 'food', False, 0.98),
'mgf mall m': ('MGF Mall Parking', 'bills', False, 0.95),
'med point': ('Med Point', 'medical', False, 0.95),
}
HANDLE_CATEGORY_MAP = {
# Food delivery
'zomato': ('Zomato', 'food', False, 0.95),
'swiggy': ('Swiggy', 'food', False, 0.95),
'blinkit': ('Blinkit', 'grocery', False, 0.95),
'zepto': ('Zepto', 'grocery', False, 0.95),
'bigbasket': ('BigBasket', 'grocery', False, 0.95),
'dominos': ('Dominos', 'food', False, 0.92),
'pizzahut': ('Pizza Hut', 'food', False, 0.92),
'kfc': ('KFC', 'food', False, 0.90),
'mcdonald': ("McDonald's", 'food', False, 0.92),
'eatfit': ('EatFit', 'food', False, 0.85),
'box8': ('Box8', 'food', False, 0.85),
# Shopping
'amazon': ('Amazon', 'shopping', False, 0.90),
'flipkart': ('Flipkart', 'shopping', False, 0.90),
'myntra': ('Myntra', 'shopping', False, 0.90),
'ajio': ('AJIO', 'shopping', False, 0.88),
'meesho': ('Meesho', 'shopping', False, 0.85),
'nykaa': ('Nykaa', 'shopping', False, 0.88),
'tatacliq': ('Tata CLiQ', 'shopping', False, 0.85),
'jiomart': ('JioMart', 'grocery', False, 0.88),
'bigbazaar': ('Big Bazaar', 'grocery', False, 0.82),
# Travel
'uber': ('Uber', 'travel', False, 0.95),
'ola': ('Ola', 'travel', False, 0.95),
'blusmart': ('BluSmart', 'travel', False, 0.92),
'rapido': ('Rapido', 'travel', False, 0.92),
'irctc': ('IRCTC', 'travel', False, 0.95),
'makemytrip': ('MakeMyTrip', 'travel', False, 0.90),
'redbus': ('RedBus', 'travel', False, 0.90),
'goibibo': ('Goibibo', 'travel', False, 0.88),
'indigo': ('Indigo Airlines', 'travel', False, 0.92),
'airindia': ('Air India', 'travel', False, 0.90),
# Entertainment
'netflix': ('Netflix', 'entertainment', False, 0.95),
'spotify': ('Spotify', 'entertainment', False, 0.95),
'hotstar': ('Disney+ Hotstar', 'entertainment', False, 0.92),
'prime': ('Amazon Prime', 'entertainment', False, 0.90),
'youtube': ('YouTube', 'entertainment', False, 0.95),
'playstore': ('Google Play Store', 'entertainment', False, 0.92),
'sonyliv': ('SonyLIV', 'entertainment', False, 0.88),
'jiosaavn': ('JioSaavn', 'entertainment', False, 0.85),
# Bills & utilities
'gpay-utility': ('Google Pay Utility', 'bills', False, 0.80),
'mygate': ('MyGate', 'bills', False, 0.90),
'paytm-mygate': ('MyGate Society', 'bills', False, 0.90),
'electricity': ('Electricity Bill', 'bills', False, 0.82),
'water': ('Water Bill', 'bills', False, 0.80),
'gas': ('Gas Bill', 'bills', False, 0.80),
'broadband': ('Broadband Bill', 'bills', False, 0.82),
'airtel': ('Airtel', 'bills', False, 0.85),
'jio': ('Jio', 'bills', False, 0.82),
'vodafone': ('Vodafone Idea', 'bills', False, 0.80),
'bsnl': ('BSNL', 'bills', False, 0.80),
# Insurance
'nivabupa': ('Niva Bupa Insurance', 'insurance', False, 0.92),
'hdfclife': ('HDFC Life', 'insurance', False, 0.90),
'iciciprulife': ('ICICI Prudential Life', 'insurance', False, 0.90),
'lic': ('LIC', 'insurance', False, 0.88),
'starhealth': ('Star Health', 'insurance', False, 0.88),
# Trading / investments
'zerodha': ('Zerodha', 'trading_deposit', False, 0.98),
'groww': ('Groww', 'trading_deposit', False, 0.92),
'indmoney': ('INDmoney', 'investment', False, 0.90),
'upstox': ('Upstox', 'trading_deposit', False, 0.90),
'angelone': ('Angel One', 'trading_deposit', False, 0.90),
'5paisa': ('5paisa', 'trading_deposit', False, 0.85),
# Credit card payments via CRED — check before food/shopping (CRED intermediates for many merchants)
'cred.club': ('CRED', 'credit_card', False, 0.95),
'cred': ('CRED', 'credit_card', False, 0.95),
'paytm-jiomobili': ('CRED Bill Pay', 'bills', False, 0.82),
'payzomato@hdfcb': ('CRED Bill Pay', 'bills', False, 0.75),
'paytm-credit': ('Paytm Credit Card', 'credit_card', False, 0.88),
# Medical
'pharmeasy': ('PharmEasy', 'medical', False, 0.90),
'tata1mg': ('Tata 1mg', 'medical', False, 0.90),
'1mg': ('Tata 1mg', 'medical', False, 0.90),
'apollo': ('Apollo Pharmacy', 'medical', False, 0.82),
'netmeds': ('Netmeds', 'medical', False, 0.85),
'artemis': ('Artemis Hospital', 'medical', False, 0.88),
# Education
'udemy': ('Udemy', 'education', False, 0.92),
'coursera': ('Coursera', 'education', False, 0.92),
'unacademy': ('Unacademy', 'education', False, 0.90),
'byjus': ("Byju's", 'education', False, 0.88),
# Personal transfers (VPA patterns indicating P2P)
'ybl': ('UPI Transfer', 'personal_transfer', False, 0.40),
'oksbi': ('UPI Transfer', 'personal_transfer', False, 0.40),
'okhdfc': ('UPI Transfer', 'personal_transfer', False, 0.40),
'okaxis': ('UPI Transfer', 'personal_transfer', False, 0.40),
'okicici': ('UPI Transfer', 'personal_transfer', False, 0.40),
'apl': ('UPI Transfer', 'personal_transfer', False, 0.40),
# --- GitHub-augmented: high-signal UPI handles from training data ---
'cred.club': ('CRED', 'credit_card', False, 0.95),
'payzomato': ('Zomato Pay (via CRED)', 'bills', False, 0.85),
'setu.simpl': ('Simpl', 'credit_card', False, 0.90),
'airindia.bdpg': ('Air India', 'travel', False, 0.90),
'paytmqr': ('Paytm Merchant', 'bills', False, 0.70),
# --- Training-data misclassification fixes ---
'grofersindia': ('Blinkit (Grofers)', 'grocery', False, 0.85),
'flightsmojoin': ('Flight Booking', 'travel', False, 0.80),
'khargymkhana': ('Khar Gymkhana', 'health_fitness', False, 0.85),
'getsimpl': ('Simpl', 'credit_card', False, 0.90),
# --- Cash withdrawal ---
'atm': ('ATM Withdrawal', 'cash_withdrawal', False, 0.85),
}
PERSONAL_TRANSFER_MARKERS = (
'p2p',
'personal transfer',
'send money',
)
# Generic category words belong to transaction-purpose inference, not merchant identity.
GENERIC_NARRATION_KEYWORDS = {
'electricity', 'water', 'gas', 'broadband', 'jio', 'lic', 'atm', 'prime',
}
# Conservative purpose/category evidence from the complete bank narration.
# These rules intentionally exclude generic words such as "payment" and "purchase".
NARRATION_CATEGORY_RULES = (
('credit_card', 'Credit Card Payment', 0.86, (
'credit card bill', 'card bill payment', 'credit card payment',
)),
('tax_payment', 'Tax Payment', 0.86, (
'income tax', 'advance tax', 'tax challan', 'tax payment',
)),
('insurance', 'Insurance Premium', 0.84, (
'insurance premium', 'policy premium',
)),
('medical', 'Medical', 0.80, (
'pharmacy', 'hospital', 'medical store', 'clinic payment',
)),
('education', 'Education', 0.80, (
'school fee', 'college fee', 'tuition fee', 'course fee',
)),
('trading_deposit', 'Trading Deposit', 0.82, (
'trading account', 'broker deposit',
)),
('investment', 'Investment', 0.82, (
'mutual fund', 'sip investment', 'investment contribution',
)),
('grocery', 'Grocery', 0.78, (
'grocery', 'supermarket', 'kirana', 'provision store',
)),
('food', 'Food', 0.76, (
'restaurant', 'food order', 'cafe payment', 'meal payment',
)),
('travel', 'Travel', 0.78, (
'flight booking', 'hotel booking', 'cab ride', 'railway ticket',
'travel booking',
)),
('entertainment', 'Entertainment', 0.76, (
'movie ticket', 'cinema', 'streaming subscription',
)),
('bills', 'Utility Bill', 0.78, (
'electricity bill', 'water bill', 'gas bill', 'mobile recharge',
'broadband bill', 'utility bill',
)),
('shopping', 'Shopping', 0.72, (
'retail purchase', 'shopping order', 'apparel', 'electronics purchase',
)),
('staff_salary', 'Staff Salary', 0.82, (
'staff salary', 'maid salary', 'driver salary',
)),
('donation', 'Donation', 0.78, ('donation', 'charity contribution')),
('cash_withdrawal', 'Cash Withdrawal', 0.85, (
'cash withdrawal', 'upi atm withdrawal',
)),
)
def _normalize_evidence(value: str) -> str:
"""Normalize narration text for conservative token/phrase matching."""
return ' '.join(re.sub(r'[^a-z0-9]+', ' ', value.lower()).split())
def _contains_evidence(value: str, phrase: str) -> bool:
"""Match a normalized token or phrase without accidental substrings."""
normalized_value = f" {_normalize_evidence(value)} "
normalized_phrase = _normalize_evidence(phrase)
return bool(normalized_phrase) and f" {normalized_phrase} " in normalized_value
def _handle_contains_keyword(handle: str, keyword: str) -> bool:
"""Match exact token phrases or brand-prefixed handle tokens without infixes."""
if _contains_evidence(handle, keyword):
return True
compact_keyword = _normalize_evidence(keyword).replace(" ", "")
if len(compact_keyword) <= 4:
return False
handle_tokens = re.findall(r"[a-z0-9]+", handle.lower())
return any(token.startswith(compact_keyword) for token in handle_tokens)
def get_curated_transaction_override(
upi_handle: str,
sample_description: str = "",
) -> Optional[dict]:
"""Return only exact transaction markers that may outrank learned cache rows."""
handle_lower = (upi_handle or "").lower().strip()
description_lower = (sample_description or "").lower()
for marker, (display, category, is_income, confidence) in CURATED_TRANSACTION_MARKERS.items():
marker_pattern = rf"(?<![a-z0-9._@-]){re.escape(marker)}(?![a-z0-9._@-])"
if handle_lower == marker or re.search(marker_pattern, description_lower):
return {
"display_name": display,
"category": category,
"is_income": is_income,
"confidence": confidence,
"rationale": f"Curated transaction marker: {display}",
}
return None
def get_curated_merchant_override(
upi_handle: str,
sample_description: str = "",
) -> Optional[dict]:
"""Return curated markers and handle aliases for heuristic classification."""
curated = get_curated_transaction_override(upi_handle, sample_description)
if curated:
return curated
handle_lower = (upi_handle or "").lower().strip()
for alias_key, (display, category, is_income, confidence) in MERCHANT_ALIASES.items():
if _handle_contains_keyword(handle_lower, alias_key):
return {
"display_name": display,
"category": category,
"is_income": is_income,
"confidence": confidence,
"rationale": f"Merchant alias: {display}",
}
return None
def classify_upi_merchant(
upi_handle: str,
sample_description: str,
*,
learn: bool = True,
) -> dict:
"""Infer a UPI category, optionally learning stable handle evidence."""
handle_lower = (upi_handle or '').lower().strip()
description = sample_description or ''
curated = get_curated_merchant_override(upi_handle, description)
if curated:
return curated
# Exact handle identity always outranks incidental merchant text in narration.
sorted_map = sorted(HANDLE_CATEGORY_MAP.items(), key=lambda item: len(item[0]), reverse=True)
merchant_match = next(
(
(keyword, merchant)
for keyword, merchant in sorted_map
if merchant[1] != 'personal_transfer'
and _handle_contains_keyword(handle_lower, keyword)
),
None,
)
# Only high-confidence, sufficiently specific merchant names may match narration.
if merchant_match is None:
merchant_match = next(
(
(keyword, merchant)
for keyword, merchant in sorted_map
if merchant[1] != 'personal_transfer'
and merchant[3] >= 0.80
and keyword not in GENERIC_NARRATION_KEYWORDS
and len(_normalize_evidence(keyword).replace(' ', '')) >= 4
and _contains_evidence(description, keyword)
),
None,
)
if merchant_match is not None:
keyword, (display, category, is_income, confidence) = merchant_match
if category == 'credit_card' and 'cred' in keyword:
for part in description.split('/'):
part = part.strip()
if any(bank in part.upper() for bank in [
'AXIS BANK', 'HDFC BANK', 'ICICI BANK', 'SBI', 'YES BANK',
'KOTAK', 'IDFC', 'INDUSIND', 'AMERICAN EXPRESS',
'STANDARD CHARTED', 'STANDARD CHARTERED', 'RBL', 'FEDERAL',
'BANDHAN', 'YES BANK LIMITE',
]):
display = f'CRED — {part.title()}'
break
# Specific known-merchant evidence is stable enough to learn for this handle.
if handle_lower and learn:
try:
store_merchant(
upi_handle,
display,
category,
is_income=is_income,
confidence=confidence,
sample_desc=description[:200],
)
except Exception:
pass
return {
'display_name': display,
'category': category,
'is_income': is_income,
'confidence': confidence,
'rationale': f'Known UPI merchant evidence: {display}',
}
display = extract_display_name(handle_lower) or 'Unknown UPI counterparty'
# Purpose/category evidence is transaction-specific, so do not cache it by handle.
for category, generic_display, confidence, phrases in NARRATION_CATEGORY_RULES:
matched_phrase = next(
(phrase for phrase in phrases if _contains_evidence(description, phrase)),
None,
)
if matched_phrase:
return {
'display_name': display if display != 'Unknown UPI counterparty' else generic_display,
'category': category,
'is_income': False,
'confidence': confidence,
'rationale': f'UPI narration evidence: {matched_phrase}',
}
local_part = handle_lower.split('@', 1)[0]
compact_local = re.sub(r'[^a-z0-9]', '', local_part)
mostly_numeric = bool(compact_local) and (
compact_local.isdigit()
or sum(character.isdigit() for character in compact_local) / len(compact_local) >= 0.8
)
explicit_personal = any(
_contains_evidence(description, marker) for marker in PERSONAL_TRANSFER_MARKERS
)
# Indian person-name P2P detection
local_part_fallback = handle_lower.split('@', 1)[0] if handle_lower else ''
# Remove non-alpha chars to evaluate the name
alpha_only = re.sub(r'[^a-z]', '', local_part_fallback)
# Skip masked handles (xxxxxxxxxx), repeated-char handles, and handles
# where the local part is mostly one repeated character — these are
# privacy-masked VPAs, not person names
unique_chars = set(alpha_only)
is_masked = len(unique_chars) <= 2 # e.g. "xxxxxxxxxx" → {'x'} → masked
# If handle local part is 5+ alphabetic chars, has no merchant keywords,
# no digits, no known brand indicators, and doesn't match any narration
# category → classify as personal_transfer at 0.40 confidence
if (len(alpha_only) >= 5
and not is_masked # exclude masked/repeated-char handles
and not any(kw in alpha_only for kw in (
'paytm', 'phonepe', 'gpay', 'amazon', 'flipkart', 'zomato',
'swiggy', 'blinkit', 'zepto', 'cred', 'bill', 'pay', 'tax',
'loan', 'emi', 'insur', 'med', 'hospital', 'pharma', 'food',
'mart', 'store', 'shop', 'bazar', 'mall', 'petrol', 'gas',
'electric', 'water', 'broadband', 'recharge', 'netflix',
'spotify', 'prime', 'hotstar', 'disney', 'apple', 'google',
'flight', 'air', 'irctc', 'mmt', 'makemy', 'yatra', 'goibibo', 'cleartrip',
'uber', 'ola', 'rapido', 'rent', 'pg', 'hostel',
))
and not mostly_numeric # already handled above
and not explicit_personal # already handled above
and not merchant_match # no merchant evidence found
and not any(_contains_evidence(description, phrase)
for category, _, _, phrases in NARRATION_CATEGORY_RULES
for phrase in phrases)
):
return {
'display_name': 'UPI Transfer',
'category': 'personal_transfer',
'is_income': False,
'confidence': 0.40,
'rationale': 'Personal UPI transfer — no merchant evidence in handle or narration',
}
if mostly_numeric or explicit_personal:
return {
'display_name': 'UPI Transfer',
'category': 'personal_transfer',
'is_income': False,
'confidence': 0.55 if mostly_numeric else 0.60,
'rationale': 'Strong personal-transfer evidence in UPI transaction',
}
return {
'display_name': display,
'category': 'unclassified',
'is_income': False,
'confidence': 0.35,
'rationale': 'No reliable merchant or purpose evidence in UPI transaction',
}
def store_merchant(upi_handle: str, display_name: str, category: str,
is_income: bool = False, confidence: float = 0.85,
sample_desc: str = '') -> bool:
"""Store a classified merchant in the database."""
conn = sqlite3.connect(str(DB_PATH))
try:
conn.execute(
"""INSERT OR REPLACE INTO merchants
(upi_handle, display_name, category, is_income, confidence, sample_desc)
VALUES (?, ?, ?, ?, ?, ?)""",
(upi_handle.lower(), display_name, category,
1 if is_income else 0, confidence, sample_desc[:200])
)
conn.commit()
return True
except Exception as e:
print(f"Error storing merchant {upi_handle}: {e}")
return False
finally:
conn.close()
def batch_store(merchants: list[dict]) -> int:
"""Store multiple merchants at once. Each dict: {upi_handle, display_name, category, is_income, confidence, sample_desc}"""
conn = sqlite3.connect(str(DB_PATH))
count = 0
for m in merchants:
try:
conn.execute(
"""INSERT OR REPLACE INTO merchants
(upi_handle, display_name, category, is_income, confidence, sample_desc)
VALUES (?, ?, ?, ?, ?, ?)""",
(m['upi_handle'].lower(), m['display_name'], m['category'],
1 if m.get('is_income') else 0, m.get('confidence', 0.85),
m.get('sample_desc', '')[:200])
)
count += 1
except Exception:
pass
conn.commit()
conn.close()
return count
def get_db_stats() -> dict:
"""Get statistics about the merchant database."""
conn = sqlite3.connect(str(DB_PATH))
total = conn.execute("SELECT COUNT(*) FROM merchants").fetchone()[0]
by_cat = conn.execute(
"SELECT category, COUNT(*) as cnt FROM merchants GROUP BY category ORDER BY cnt DESC"
).fetchall()
conn.close()
return {
'total_merchants': total,
'categories': {cat: cnt for cat, cnt in by_cat}
}
# ─── Seed Data: Known merchants from regex patterns ───
SEED_MERCHANTS = [
# Trading / investments
{'upi_handle': 'zerodhabroking@', 'display_name': 'Zerodha', 'category': 'trading_deposit', 'is_income': False, 'confidence': 0.98},
{'upi_handle': 'indmoney@', 'display_name': 'INDmoney', 'category': 'investment', 'is_income': False, 'confidence': 0.90},
# Food delivery
{'upi_handle': 'zomato-order@pt', 'display_name': 'Zomato', 'category': 'food', 'is_income': False, 'confidence': 0.95},
{'upi_handle': 'swiggy@', 'display_name': 'Swiggy', 'category': 'food', 'is_income': False, 'confidence': 0.95},
# Shopping
{'upi_handle': 'amazon-pod@rap', 'display_name': 'Amazon', 'category': 'shopping', 'is_income': False, 'confidence': 0.90},
{'upi_handle': 'amazonsellerser', 'display_name': 'Amazon Seller Services', 'category': 'shopping', 'is_income': False, 'confidence': 0.85},
{'upi_handle': 'flipkart@', 'display_name': 'Flipkart', 'category': 'shopping', 'is_income': False, 'confidence': 0.90},
# Bills & utilities
{'upi_handle': 'gpay-utility@ok', 'display_name': 'Google Pay Utility', 'category': 'bills', 'is_income': False, 'confidence': 0.80},
{'upi_handle': 'youtube@axisba', 'display_name': 'YouTube Premium', 'category': 'entertainment', 'is_income': False, 'confidence': 0.95},
{'upi_handle': 'playstore@axis', 'display_name': 'Google Play Store', 'category': 'entertainment', 'is_income': False, 'confidence': 0.95},
{'upi_handle': 'netflix@', 'display_name': 'Netflix', 'category': 'entertainment', 'is_income': False, 'confidence': 0.95},
# Insurance (known providers)
{'upi_handle': 'nivabupa@', 'display_name': 'Niva Bupa Insurance', 'category': 'insurance', 'is_income': False, 'confidence': 0.92},
# Society / maintenance
{'upi_handle': 'paytm-mygate@pt', 'display_name': 'MyGate Society', 'category': 'bills', 'is_income': False, 'confidence': 0.90},
{'upi_handle': 'mygate.razorpa', 'display_name': 'MyGate', 'category': 'bills', 'is_income': False, 'confidence': 0.90},
# Travel
{'upi_handle': 'uber@', 'display_name': 'Uber', 'category': 'travel', 'is_income': False, 'confidence': 0.95},
{'upi_handle': 'ola@', 'display_name': 'Ola', 'category': 'travel', 'is_income': False, 'confidence': 0.95},
{'upi_handle': 'irctc@', 'display_name': 'IRCTC', 'category': 'travel', 'is_income': False, 'confidence': 0.95},
{'upi_handle': 'airindiaexpress', 'display_name': 'Air India Express', 'category': 'travel', 'is_income': False, 'confidence': 0.90},
# Credit card payments
{'upi_handle': 'cred@', 'display_name': 'CRED', 'category': 'credit_card', 'is_income': False, 'confidence': 0.95},
# Grocery
{'upi_handle': 'blinkit@', 'display_name': 'Blinkit', 'category': 'grocery', 'is_income': False, 'confidence': 0.95},
{'upi_handle': 'zepto@', 'display_name': 'Zepto', 'category': 'grocery', 'is_income': False, 'confidence': 0.95},
{'upi_handle': 'bigbasket@', 'display_name': 'BigBasket', 'category': 'grocery', 'is_income': False, 'confidence': 0.95},
]
def seed_database():
"""Initialize the merchant database with known merchants."""
count = batch_store(SEED_MERCHANTS)
print(f"Seeded {count} known merchants")
return count
|