rules.py

import re
from datetime import datetime
from typing import List, Dict

# =========================================================
# NORMALIZATION & PREPROCESSING
# =========================================================
def preprocess_text(text):
    """Remove extra trailing/leading spaces and normalize whitespace"""
    if not text:
        return ""
    return re.sub(r"\s+", " ", text.strip())

def normalize_text(text):
    """Normalize text to lowercase and remove extra spaces"""
    return re.sub(r"\s+", " ", text.lower().strip()) if text else ""

# =========================================================
# VALIDATION FUNCTIONS
# =========================================================
def validate_and_normalize_pincode(pincode):
    """
    Validate and normalize pincode to exactly 6 digits
    Returns normalized pincode or None if invalid
    """
    if not pincode:
        return None
    
    digits = re.sub(r'\D', '', str(pincode).strip())
    
    if len(digits) == 6:
        return digits
    
    return None

def validate_and_normalize_phone(phone):
    """
    Validate and normalize phone to exactly 10 digits
    Handles formats: +91, 91-, 91, or plain 10 digits
    Returns normalized 10-digit phone or None if invalid
    """
    if not phone:
        return None
    
    phone_str = str(phone).strip()
    
    # Remove common prefixes and separators
    phone_str = re.sub(r'^\+91[-\s]?', '', phone_str)
    phone_str = re.sub(r'^91[-\s]?', '', phone_str)
    phone_str = re.sub(r'^0[-\s]?', '', phone_str)
    
    digits = re.sub(r'\D', '', phone_str)
    
    if len(digits) == 10:
        return digits
    
    return None

def validate_and_normalize_email(email):
    """
    Validate and normalize email using regex
    Returns normalized email or None if invalid
    """
    if not email:
        return None
    
    email_str = str(email).strip().lower()
    
    email_pattern = r'^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$'
    
    if re.match(email_pattern, email_str):
        return email_str
    
    return None

def normalize_dob(dob_str):
    """Normalize DOB to YYYY-MM-DD format"""
    if not dob_str:
        return None
    
    formats = [
        "%Y-%m-%d", "%Y/%m/%d",
        "%d-%m-%Y", "%d/%m/%Y",
    ]
    
    for fmt in formats:
        try:
            dt = datetime.strptime(dob_str, fmt)
            return dt.strftime("%Y-%m-%d")
        except ValueError:
            continue
    
    return None

# =========================================================
# STATE & CITY MAPPINGS
# =========================================================
STATE_MAPPING = {
    "andhra pradesh": ["andhra pradesh", "ap", "a.p", "a.p.", "andhra", "andhrapradesh"],
    "arunachal pradesh": ["arunachal pradesh", "arunachal", "ar", "a.r"],
    "assam": ["assam", "as", "a.s"],
    "bihar": ["bihar", "br", "b.r"],
    "chhattisgarh": ["chhattisgarh", "chattisgarh", "chhatisgarh", "cg", "c.g"],
    "goa": ["goa", "ga", "g.a"],
    "gujarat": ["gujarat", "gujrat", "gj", "g.j"],
    "haryana": ["haryana", "hr", "h.r"],
    "himachal pradesh": ["himachal pradesh", "himachal", "hp", "h.p", "h.p."],
    "jharkhand": ["jharkhand", "jh", "j.h"],
    "karnataka": ["karnataka", "ka", "k.a", "karn", "karnatak"],
    "kerala": ["kerala", "kl", "k.l"],
    "madhya pradesh": ["madhya pradesh", "mp", "m.p", "m.p.", "madhya", "madhyapradesh"],
    "maharashtra": ["maharashtra", "mh", "m.h", "maha", "maharastra"],
    "manipur": ["manipur", "mn", "m.n"],
    "meghalaya": ["meghalaya", "ml", "m.l"],
    "mizoram": ["mizoram", "mz", "m.z"],
    "nagaland": ["nagaland", "nl", "n.l"],
    "odisha": ["odisha", "orissa", "od", "o.d", "or", "o.r"],
    "punjab": ["punjab", "pb", "p.b"],
    "rajasthan": ["rajasthan", "rj", "r.j", "raj"],
    "sikkim": ["sikkim", "sk", "s.k"],
    "tamil nadu": ["tamil nadu", "tamilnadu", "tn", "t.n", "t.n.", "tamil"],
    "telangana": ["telangana", "tg", "t.g", "telengana", "ts", "t.s"],
    "tripura": ["tripura", "tr", "t.r"],
    "uttar pradesh": ["uttar pradesh", "up", "u.p", "u.p.", "uttar", "uttarpradesh"],
    "uttarakhand": ["uttarakhand", "uttaranchal", "uk", "u.k", "ua"],
    "west bengal": ["west bengal", "westbengal", "wb", "w.b", "w.b.", "bengal"],
    "andaman and nicobar islands": ["andaman and nicobar islands", "andaman", "nicobar", "an", "a.n"],
    "chandigarh": ["chandigarh", "ch", "c.h"],
    "dadra and nagar haveli and daman and diu": ["dadra and nagar haveli and daman and diu", "dadra", "daman", "diu", "dn", "d.n", "dnh"],
    "lakshadweep": ["lakshadweep", "ld", "l.d"],
    "delhi": ["delhi", "new delhi", "dl", "d.l"],
    "puducherry": ["puducherry", "pondicherry", "py", "p.y"],
    "ladakh": ["ladakh", "la", "l.a"],
    "jammu and kashmir": ["jammu and kashmir", "jammu", "kashmir", "jk", "j.k", "j&k"]
}

CITY_MAPPING = {
    "mumbai": ["mumbai", "bombay", "bom"],
    "delhi": ["delhi", "dl", "new delhi", "newdelhi"],
    "bengaluru": ["bengaluru", "bangalore", "blr"],
    "hyderabad": ["hyderabad", "hyd", "secunderabad"],
    "ahmedabad": ["ahmedabad", "amdavad", "amd"],
    "chennai": ["chennai", "madras", "maa"],
    "kolkata": ["kolkata", "calcutta", "cal"],
    "pune": ["pune", "poona"],
    "jaipur": ["jaipur", "jai"],
    "surat": ["surat", "sur"],
    "lucknow": ["lucknow", "lko"],
    "kanpur": ["kanpur", "cawnpore"],
    "nagpur": ["nagpur", "nag"],
    "indore": ["indore", "ind"],
    "thane": ["thane", "tha"],
    "bhopal": ["bhopal", "bho"],
    "visakhapatnam": ["visakhapatnam", "vizag", "vishakhapatnam", "vsp"],
    "pimpri-chinchwad": ["pimpri-chinchwad", "pimpri", "chinchwad"],
    "patna": ["patna", "pat"],
    "vadodara": ["vadodara", "baroda", "vad"],
    "ghaziabad": ["ghaziabad", "ghz"],
    "ludhiana": ["ludhiana", "ldh"],
    "agra": ["agra", "agr"],
    "nashik": ["nashik", "nasik"],
    "faridabad": ["faridabad", "fbd"],
    "meerut": ["meerut", "mer"],
    "rajkot": ["rajkot", "raj"],
    "kalyan-dombivli": ["kalyan-dombivli", "kalyan", "dombivli"],
    "vasai-virar": ["vasai-virar", "vasai", "virar"],
    "varanasi": ["varanasi", "banaras", "kashi"],
    "srinagar": ["srinagar", "sri"],
    "aurangabad": ["aurangabad", "aur"],
    "dhanbad": ["dhanbad", "dhn"],
    "amritsar": ["amritsar", "asr"],
    "navi mumbai": ["navi mumbai", "navimumbai", "new mumbai"],
    "allahabad": ["allahabad", "prayagraj", "pra"],
    "ranchi": ["ranchi", "ran"],
    "howrah": ["howrah", "how"],
    "coimbatore": ["coimbatore", "coi"],
    "jabalpur": ["jabalpur", "jab"],
    "gwalior": ["gwalior", "gwa"],
    "vijayawada": ["vijayawada", "vij"],
    "jodhpur": ["jodhpur", "jod"],
    "madurai": ["madurai", "mad"],
    "raipur": ["raipur", "rai"],
    "kota": ["kota", "kot"],
    "chandigarh": ["chandigarh", "chd"],
    "guwahati": ["guwahati", "gauhati", "guw"],
    "thiruvananthapuram": ["thiruvananthapuram", "trivandrum", "trv"],
    "mysore": ["mysore", "mysuru", "mys"],
    "dehradun": ["dehradun", "ddn"],
    "bhubaneswar": ["bhubaneswar", "bhubaneshwar", "bbs"],
    "kochi": ["kochi", "cochin", "cok"],
    "shimla": ["shimla", "simla"],
    "tiruchirappalli": ["tiruchirappalli", "trichy", "trc"],
    "tirupati": ["tirupati", "tpt"],
    "mangalore": ["mangalore", "mangaluru", "man"],
    "hubli": ["hubli", "hubli-dharwad", "dharwad"]
}

def standardize_state(text):
    """Standardize state names to canonical form"""
    if not text:
        return None
    tokens = re.split(r"[,\s]+", normalize_text(text))
    for token in tokens:
        for standard, variants in STATE_MAPPING.items():
            if token in variants:
                return standard
    return normalize_text(text)

def standardize_city(text):
    """Standardize city names to canonical form"""
    if not text:
        return None
    tokens = re.split(r"[,\s]+", normalize_text(text))
    for token in tokens:
        for standard, variants in CITY_MAPPING.items():
            if token in variants:
                return standard
    return normalize_text(text)

# =========================================================
# 1:N MATCHING LOGIC
# =========================================================
# def compare_any_match(list1: List, list2: List, field_type="text") -> Dict:
#     """
#     Check if any value in list1 matches any value in list2
#     Returns: {"Result": "Match"/"No Match"/"missing value", "Confidence Score": 100, "Overall Similarity": 100/0}
#     """
#     if not list1 or not list2:
#         return {"Result": "missing value", "Confidence Score": 100, "Overall Similarity": 0}
    
#     # Apply appropriate normalization based on field type
#     if field_type == "pincode":
#         vals1 = [validate_and_normalize_pincode(v) for v in list1 if v]
#         vals2 = [validate_and_normalize_pincode(v) for v in list2 if v]
#     elif field_type == "state":
#         vals1 = [standardize_state(v) for v in list1 if v]
#         vals2 = [standardize_state(v) for v in list2 if v]
#     elif field_type == "city":
#         vals1 = [standardize_city(v) for v in list1 if v]
#         vals2 = [standardize_city(v) for v in list2 if v]
#     else:
#         vals1 = [normalize_text(v) for v in list1 if v]
#         vals2 = [normalize_text(v) for v in list2 if v]
    
#     # Filter out None values
#     vals1 = [v for v in vals1 if v]
#     vals2 = [v for v in vals2 if v]
    
#     if not vals1 or not vals2:
#         return {"Result": "missing value", "Confidence Score": 100, "Overall Similarity": 0}
    
#     # Check if any value matches
#     for v1 in vals1:
#         for v2 in vals2:
#             if v1 == v2:
#                 return {"Result": "Match", "Confidence Score": 100, "Overall Similarity": 100}
    
#     return {"Result": "No Match", "Confidence Score": 100, "Overall Similarity": 0}

# def compare_phone_any_match(list1: List, list2: List) -> Dict:
#     """
#     Check if any phone in list1 matches any phone in list2
#     Returns: {"Result": "Match"/"No Match"/"missing value", "Confidence Score": 100, "Overall Similarity": 100/0}
#     """
#     if not list1 or not list2:
#         return {"Result": "missing value", "Confidence Score": 100, "Overall Similarity": 0}
    
#     phones1 = [validate_and_normalize_phone(p) for p in list1 if p]
#     phones2 = [validate_and_normalize_phone(p) for p in list2 if p]
    
#     phones1 = [p for p in phones1 if p]
#     phones2 = [p for p in phones2 if p]
    
#     if not phones1 or not phones2:
#         return {"Result": "missing value", "Confidence Score": 100, "Overall Similarity": 0}
    
#     for p1 in phones1:
#         for p2 in phones2:
#             if p1 == p2:
#                 return {"Result": "Match", "Confidence Score": 100, "Overall Similarity": 100}
    
#     return {"Result": "No Match", "Confidence Score": 100, "Overall Similarity": 0}

# def compare_email_any_match(list1: List, list2: List) -> Dict:
#     """
#     Check if any email in list1 matches any email in list2
#     Returns: {"Result": "Match"/"No Match"/"missing value", "Confidence Score": 100, "Overall Similarity": 100/0}
#     """
#     if not list1 or not list2:
#         return {"Result": "missing value", "Confidence Score": 100, "Overall Similarity": 0}
    
#     emails1 = [validate_and_normalize_email(e) for e in list1 if e]
#     emails2 = [validate_and_normalize_email(e) for e in list2 if e]
    
#     emails1 = [e for e in emails1 if e]
#     emails2 = [e for e in emails2 if e]
    
#     if not emails1 or not emails2:
#         return {"Result": "missing value", "Confidence Score": 100, "Overall Similarity": 0}
    
#     for e1 in emails1:
#         for e2 in emails2:
#             if e1 == e2:
#                 return {"Result": "Match", "Confidence Score": 100, "Overall Similarity": 100}
    
#     return {"Result": "No Match", "Confidence Score": 100, "Overall Similarity": 0}

# # =========================================================
# # DIRECT COMPARISON (Exact Match Fields)
# # =========================================================
# def compare_exact(v1, v2) -> Dict:
#     """
#     Direct exact comparison for fields like GENDER, TAXID, LICENSEID, PASSPORTID, BIRTHDATE
#     Returns: {"Result": "Match"/"No Match"/"missing value", "Confidence Score": 100, "Overall Similarity": 100/0}
#     """
#     if not v1 or not v2:
#         return {"Result": "missing value", "Confidence Score": 100, "Overall Similarity": 0}
    
#     v1_norm = normalize_text(v1)
#     v2_norm = normalize_text(v2)
    
#     if v1_norm == v2_norm:
#         return {"Result": "Match", "Confidence Score": 100, "Overall Similarity": 100}
#     else:
#         return {"Result": "No Match", "Confidence Score": 100, "Overall Similarity": 0}

# # =========================================================
# # MATCHING RULES EVALUATION
# # =========================================================
# def evaluate_matching_rules(field_results: Dict) -> tuple:
#     """Evaluate matching rules based on field results"""
    
#     def rule_matched(*fields):
#         return all(field_results.get(f, {}).get("Result") == "Match" for f in fields)

#     RULES = [
#         (("NAME", "PHONE", "EMAIL", "BIRTHDATE"),
#          "Matched on Name, Phone Number, Email ID and DOB"),

#         (("NAME", "CITY", "PHONE", "EMAIL", "ZIPCODE"),
#          "Matched on Name, City, Phone Number, Email ID and Pincode"),

#         (("NAME", "STATE", "PHONE", "EMAIL", "BIRTHDATE"),
#          "Matched on Name, State, Phone Number, Email ID and DOB"),

#         (("NAME", "PHONE", "ZIPCODE", "BIRTHDATE", "ADDRESSLINE"),
#          "Matched on Name, Phone Number, Pincode, DOB and Address"),

#         (("NAME", "CITY", "BIRTHDATE", "STATE", "ZIPCODE"),
#          "Matched on Name, City, DOB, State and Pincode"),

#         (("NAME", "CITY", "ZIPCODE", "BIRTHDATE"),
#          "Matched on Name, City, Pincode and DOB"),

#         (("NAME", "ADDRESSLINE", "EMAIL"),
#          "Matched on Name, Address and Email ID"),

#         (("NAME", "PHONE", "ZIPCODE", "BIRTHDATE"),
#          "Matched on Name, Phone Number, Pincode and DOB"),

#         (("NAME", "EMAIL", "BIRTHDATE"),
#          "Matched on Name, Email ID and DOB"),

#         (("NAME", "BIRTHDATE", "ADDRESSLINE", "PHONE"),
#          "Matched on Name, DOB, Address and Phone Number"),

#         (("NAME", "CITY", "ZIPCODE", "EMAIL"),
#          "Matched on Name, City, Pincode and Email ID"),

#         (("NAME", "ADDRESSLINE", "PHONE", "ZIPCODE"),
#          "Matched on Name, Address, Phone Number and Pincode"),
#     ]

#     for fields, reason in RULES:
#         if rule_matched(*fields):
#             return "Match", reason

#     return "No Match", "None of the defined matching rules were satisfied"

# =========================================================
# 1:N MATCHING LOGIC - Modified to return similarity scores
# =========================================================
def compare_any_match(list1: List, list2: List, field_type="text") -> float:
    """
    Check if any value in list1 matches any value in list2
    Returns: similarity score (0 or 100) or "missing value"
    """
    if not list1 or not list2:
        return 0
    
    # Apply appropriate normalization based on field type
    if field_type == "pincode":
        vals1 = [validate_and_normalize_pincode(v) for v in list1 if v]
        vals2 = [validate_and_normalize_pincode(v) for v in list2 if v]
    elif field_type == "state":
        vals1 = [standardize_state(v) for v in list1 if v]
        vals2 = [standardize_state(v) for v in list2 if v]
    elif field_type == "city":
        vals1 = [standardize_city(v) for v in list1 if v]
        vals2 = [standardize_city(v) for v in list2 if v]
    else:
        vals1 = [normalize_text(v) for v in list1 if v]
        vals2 = [normalize_text(v) for v in list2 if v]
    
    # Filter out None values
    vals1 = [v for v in vals1 if v]
    vals2 = [v for v in vals2 if v]
    
    if not vals1 or not vals2:
        return 0
    
    # Check if any value matches
    for v1 in vals1:
        for v2 in vals2:
            if v1 == v2:
                return 100
    
    return 0

def compare_phone_any_match(list1: List, list2: List) -> float:
    """
    Check if any phone in list1 matches any phone in list2
    Returns: similarity score (0 or 100) or "missing value"
    """
    if not list1 or not list2:
        return 0
    
    phones1 = [validate_and_normalize_phone(p) for p in list1 if p]
    phones2 = [validate_and_normalize_phone(p) for p in list2 if p]
    
    phones1 = [p for p in phones1 if p]
    phones2 = [p for p in phones2 if p]
    
    if not phones1 or not phones2:
        return 0
    
    for p1 in phones1:
        for p2 in phones2:
            if p1 == p2:
                return 100
    
    return 0

def compare_email_any_match(list1: List, list2: List) -> float:
    """
    Check if any email in list1 matches any email in list2
    Returns: similarity score (0 or 100) or "missing value"
    """
    if not list1 or not list2:
        return 0
    
    emails1 = [validate_and_normalize_email(e) for e in list1 if e]
    emails2 = [validate_and_normalize_email(e) for e in list2 if e]
    
    emails1 = [e for e in emails1 if e]
    emails2 = [e for e in emails2 if e]
    
    if not emails1 or not emails2:
        return 0
    
    for e1 in emails1:
        for e2 in emails2:
            if e1 == e2:
                return 100
    
    return 0

# =========================================================
# DIRECT COMPARISON - Modified to return similarity scores
# =========================================================
def compare_exact(v1, v2) -> float:
    """
    Direct exact comparison for fields like GENDER, TAXID, LICENSEID, PASSPORTID, BIRTHDATE
    Returns: similarity score (0 or 100) or "missing value"
    """
    if not v1 or not v2:
        return 0
    
    v1_norm = normalize_text(v1)
    v2_norm = normalize_text(v2)
    
    if v1_norm == v2_norm:
        return 100
    else:
        return 0

# =========================================================
# MATCHING RULES EVALUATION - Modified for new rule logic
# =========================================================
def evaluate_matching_rules(field_results: Dict) -> tuple:
    """Evaluate matching rules based on field results with similarity scores"""
    
    def get_score(field_name):
        """Get numeric score from field result, handle missing values"""
        result = field_results.get(field_name)
        if result == "missing value" or result is None:
            return 0
        return round(float(result),2)
    
    def rule_satisfied(conditions):
        """Check if all conditions in a rule are satisfied"""
        for field, threshold in conditions:
            if get_score(field) < threshold:
                return False
        return True
    
    # Define all matching rules
    RULES = [
        ([("CITY", 100), ("ADDRESSLINE", 85), ("NAME", 60), ("BIRTHDATE", 100)],
         "CITY >= 100 and ADDRESS >= 85 and NAME >= 60 and BIRTHDATE >= 100"),
        
        ([("CITY", 100), ("ADDRESSLINE", 75), ("NAME", 60), ("BIRTHDATE", 100)],
         "CITY >= 100 and ADDRESS >= 75 and NAME >= 60 and BIRTHDATE >= 100"),
        
        ([("ADDRESSLINE", 85), ("CITY", 100), ("NAME", 85), ("BIRTHDATE", 100)],
         "ADDRESS >= 85 and CITY >= 100 and NAME >= 85 and BIRTHDATE >= 100"),
        
        ([("ADDRESSLINE", 85), ("NAME", 85), ("BIRTHDATE", 100), ("ZIPCODE", 100)],
         "ADDRESS >= 85 and NAME >= 85 and BIRTHDATE >= 100 and ZIPCODE >= 100"),
        
        ([("ADDRESSLINE", 65), ("NAME", 60), ("BIRTHDATE", 100), ("ZIPCODE", 100)],
         "ADDRESS >= 65 and NAME >= 60 and BIRTHDATE >= 100 and ZIPCODE >= 100"),
        
        ([("CITY", 100), ("ADDRESSLINE", 65), ("NAME", 60), ("BIRTHDATE", 100)],
         "CITY >= 100 and ADDRESS >= 65 and NAME >= 60 and BIRTHDATE >= 100"),
        
        ([("ADDRESSLINE", 70), ("NAME", 60), ("BIRTHDATE", 100), ("COMPANYNAME", 60)],
         "ADDRESS >= 70 and NAME >= 60 and BIRTHDATE >= 100 and EMPLOYERNAME >= 60"),
        
        ([("ADDRESSLINE", 75), ("CITY", 95), ("NAME", 50), ("ZIPCODE", 100)],
         "ADDRESS >= 75 and CITY >= 95 and NAME >= 50 and ZIPCODE >= 100"),
        
        ([("ADDRESSLINE", 70), ("NAME", 60), ("PHONE", 100), ("ZIPCODE", 100)],
         "ADDRESS >= 70 and NAME >= 60 and PHONE >= 100 and ZIPCODE >= 100"),
        
        ([("NAME", 85), ("ZIPCODE", 100), ("ADDRESSLINE", 60), ("CITY", 100)],
         "NAME >= 85 AND ZIPCODE >=100 AND ADDRESS >=60 AND CITY >= 100"),
        
        ([("NAME", 85), ("CITY", 100), ("ADDRESSLINE", 60)],
         "NAME >= 85 AND CITY >= 100 AND ADDRESS >= 60"),
        
        ([("NAME", 60), ("BIRTHDATE", 100), ("ZIPCODE", 100)],
         "NAME >= 60 and BIRTHDATE >= 100 and ZIPCODE >= 100"),
        
        ([("CITY", 100), ("ADDRESSLINE", 75), ("NAME", 85)],
         "CITY >= 100 and ADDRESS >= 75 and NAME >= 85"),
        
        ([("ADDRESSLINE", 75), ("NAME", 85), ("ZIPCODE", 100)],
         "ADDRESS >= 75 and NAME >= 85 and ZIPCODE >= 100"),
        
        ([("CITY", 100), ("NAME", 60), ("BIRTHDATE", 100)],
         "CITY >= 100 and NAME >= 60 and BIRTHDATE >= 100"),
        
        ([("CITY", 100), ("ADDRESSLINE", 70), ("LASTNAME", 85)],
         "CITY >= 100 and ADDRESS >= 70 and LASTNAME >= 85"),
        
        ([("CITY", 100), ("ADDRESSLINE", 80), ("LASTNAME", 85)],
         "CITY >= 100 and ADDRESS >= 80 and LASTNAME >= 85"),
        
        ([("CITY", 100), ("ADDRESSLINE", 90), ("LASTNAME", 85)],
         "CITY >= 100 and ADDRESS >= 90 and LASTNAME >= 85"),
        
        ([("ADDRESSLINE", 80), ("LASTNAME", 85), ("ZIPCODE", 100)],
         "ADDRESS >= 80 and LASTNAME >= 85 and ZIPCODE >= 100"),
        
        ([("ADDRESSLINE", 70), ("LASTNAME", 85), ("ZIPCODE", 100)],
         "ADDRESS >= 70 and LASTNAME >= 85 and ZIPCODE >= 100"),
        
        ([("ADDRESSLINE", 90), ("LASTNAME", 85), ("ZIPCODE", 100)],
         "ADDRESS >= 90 and LASTNAME >= 85 and ZIPCODE >= 100"),
        
        ([("NAME", 80), ("BIRTHDATE", 100), ("ZIPCODE", 100)],
         "NAME >= 80 and BIRTHDATE >= 100 and ZIPCODE >= 100"),
        
        ([("NAME", 100), ("COMPANYNAME", 75), ("PHONE", 100)],
         "NAME >= 100 and EMPLOYERNAME >= 75 and PHONE >= 100"),
        
        ([("NAME", 80), ("BIRTHDATE", 100), ("CITY", 100)],
         "NAME >= 80 AND BIRTHDATE >= 100 AND CITY >= 100"),
        
        ([("NAME", 85), ("ZIPCODE", 100), ("ADDRESSLINE", 60)],
         "NAME >= 85 AND ZIPCODE >=100 AND ADDRESS >=60"),
        
        ([("LASTNAME", 85), ("CITY", 100), ("ADDRESSLINE", 60)],
         "LASTNAME >= 85 AND CITY >=100 AND ADDRESS >= 60"),
        
        ([("BIRTHDATE", 100), ("ZIPCODE", 100), ("ADDRESSLINE", 65)],
         "BIRTHDATE >= 100 AND ZIPCODE >= 100 AND ADDRESS >= 65"),
        
        ([("BIRTHDATE", 100), ("CITY", 100), ("ADDRESSLINE", 65)],
         "BIRTHDATE >= 100 AND CITY >= 100 AND ADDRESS >= 65"),
        
        ([("LASTNAME", 85), ("ZIPCODE", 100), ("ADDRESSLINE", 60)],
         "LASTNAME >= 85 AND ZIPCODE >= 100 AND ADDRESS >= 60"),
        
        ([("NAME", 85), ("PHONE", 100)],
         "NAME >= 85 AND PHONE >= 100"),
        
        ([("BIRTHDATE", 100), ("PHONE", 100)],
         "BIRTHDATE >= 100 AND PHONE >= 100"),
        
        ([("BIRTHDATE", 100), ("NAME", 85)],
         "BIRTHDATE >=100 AND NAME>=85"),
        
        ([("ADDRESSLINE", 60), ("TAXID", 100)],
         "ADDRESS >= 60 and PAN >= 100"),
        
        ([("ADDRESSLINE", 60), ("LICENSEID", 100)],
         "ADDRESS >= 60 and DRIVING_LICN_NO >= 100"),
        
        ([("BIRTHDATE", 75), ("PHONE", 100)],
         "BIRTHDATE >= 75 and PHONE >= 100"),
        
        ([("BIRTHDATE", 75), ("TAXID", 100)],
         "BIRTHDATE >= 75 and PAN >= 100"),
        
        ([("BIRTHDATE", 75), ("LICENSEID", 100)],
         "BIRTHDATE >= 75 and DRIVING_LICN_NO >= 100"),
        
        ([("BIRTHDATE", 75), ("PASSPORTID", 100)],
         "BIRTHDATE >= 75 and PASSPORT_NO >= 100"),
        
        ([("NAME", 60), ("PASSPORTID", 100)],
         "NAME >= 60 and PASSPORT_NO >= 100"),
        
        ([("NAME", 60), ("LICENSEID", 100)],
         "NAME >= 60 and DRIVING_LICN_NO >= 100"),
        
        ([("NAME", 60), ("TAXID", 100)],
         "NAME >= 60 and PAN >= 100"),
        
        ([("PHONE", 100)], "PHONE >= 100"),
        ([("LICENSEID", 100)], "DRIVING_LICN_NO >= 100"),
        ([("PASSPORTID", 100)], "PASSPORT_NO >= 100"),
        ([("TAXID", 100)], "PAN >= 100"),
        ([("EMAIL", 100)], "EMAIL >= 100"),
    ]
    
    # Check each rule in order
    for conditions, reason in RULES:
        if rule_satisfied(conditions):
            return "Match", reason
    
    return "No Match", "None of the defined matching rules were satisfied"

# =========================================================
# PATTERN-BASED FIELD MATCHING (0 or 100 logic)
# =========================================================
def apply_pattern_matching_logic(field_name: str, score) -> float:
    """
    Apply 0 or 100 logic for pattern-based fields
    For DOB, PHONE, EMAIL, ZIPCODE, etc.: if match -> 100, else -> 0
    For other fields: return the actual similarity score
    """
    # Pattern fields that should be 0 or 100
    PATTERN_FIELDS = {
        "BIRTHDATE", "PHONE", "EMAIL", "ZIPCODE", 
        "TAXID", "LICENSEID", "PASSPORTID", "GENDER"
    }
    
    # If it's a missing value, keep it as is
    if score == "missing value":
        return 0
    
    # If it's a pattern field, apply 0 or 100 logic
    if field_name in PATTERN_FIELDS:
        return 100 if score >= 100 else 0
    
    # For non-pattern fields, return the actual score
    return score