Spaces:
Sleeping
Sleeping
File size: 2,010 Bytes
4385db3 8cf23c5 4385db3 8cf23c5 4385db3 8cf23c5 4385db3 8cf23c5 4385db3 8cf23c5 4385db3 8cf23c5 4385db3 8cf23c5 4385db3 8cf23c5 4385db3 8cf23c5 4385db3 8cf23c5 4385db3 8cf23c5 4385db3 8cf23c5 | 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 | import re
# -----------------------------
# INTEREST RATE EXTRACTION
# -----------------------------
def extract_interest_rate(text):
"""
Extract interest rate using semantic priority.
The document can contain multiple rates.
We select the most authoritative one.
"""
priority_patterns = [
# 1. Comparison rate (most stable & always present)
r"砖讬注讜专\s+讛专讬讘讬转\s+诇爪专讻讬\s+讛砖讜讜讗讛\s*[:\-]?\s*(\d+\.\d+)\s*%",
# 2. Forecast total interest rate
r"讛专讬讘讬转\s+讛讻讜诇诇转\s+讛讞讝讜讬讛\s*[:\-]?\s*(\d+\.\d+)\s*%",
# 3. Adjusted interest rate
r"砖讬注讜专\s+讛专讬讘讬转\s+讛诪转讜讗诪转\s*[:\-]?\s*(\d+\.\d+)\s*%",
# 4. Base interest rate
r"砖讬注讜专\s+讛专讬讘讬转\s*[:\-]?\s*(\d+\.\d+)\s*%"
]
for pattern in priority_patterns:
match = re.search(pattern, text)
if match:
try:
return float(match.group(1))
except ValueError:
continue
# Special case: Bank of Israel 0% loans
if "诪转讜讜讛 讘谞拽 讬砖专讗诇" in text or "专讬讘讬转 0" in text:
return 0.0
return None
# -----------------------------
# LOAN AMOUNT EXTRACTION
# -----------------------------
def extract_loan_amount(text):
"""
Extract loan amount ONLY from execution amount.
Never guess from balances, totals, or monthly values.
"""
priority_patterns = [
# Canonical execution amount
r"住讻讜诐\s+讞诇拽\s+讝讛\s+讘注转\s+讛讘讬爪讜注\s*[:\-]?\s*([\d,]+(?:\.\d{2})?)",
# Variant formatting sometimes seen
r"住讻讜诐\s+讛讛诇讜讜讗讛\s+讘注转\s+讛讘讬爪讜注\s*[:\-]?\s*([\d,]+(?:\.\d{2})?)"
]
for pattern in priority_patterns:
match = re.search(pattern, text)
if match:
value = match.group(1).replace(",", "")
try:
return float(value)
except ValueError:
continue
return None
|