#!/usr/bin/env python3
"""
Diagnose fuzzy matching between Egyptian institutions and Wikidata.
Shows top 3 Wikidata matches for each institution with similarity scores.
"""

import sys
from pathlib import Path
import yaml
import re
from difflib import SequenceMatcher

sys.path.insert(0, str(Path(__file__).parent.parent / "src"))
from SPARQLWrapper import SPARQLWrapper, JSON as SPARQL_JSON

def normalize_name(name: str) -> str:
    """Improved normalization that preserves type words."""
    name = name.lower()
    name = re.sub(r'^(the|a|an)\s+', '', name)
    name = re.sub(r'\b(national|regional|central|public|state|royal|great)\b', '', name)
    name = re.sub(r'\b(dar|dār)\b', 'dar', name)
    name = re.sub(r'\b(mathaf|mat?haf)\b', 'mathaf', name)
    name = re.sub(r'\b(maktabat)\b', 'library', name)
    name = re.sub(r'\b(al-|el-)\b', '', name)
    name = re.sub(r'[^\w\s]', ' ', name)
    name = ' '.join(name.split())
    return name

def similarity_score(name1: str, name2: str) -> float:
    """Calculate similarity between two names."""
    norm1 = normalize_name(name1)
    norm2 = normalize_name(name2)
    return SequenceMatcher(None, norm1, norm2).ratio()

# Load local institutions
with open('data/instances/egypt_institutions.yaml', 'r', encoding='utf-8') as f:
    institutions = yaml.safe_load(f)

# Query Wikidata
sparql = SPARQLWrapper("https://query.wikidata.org/sparql")
sparql.setReturnFormat(SPARQL_JSON)

query = """
SELECT DISTINCT ?item ?itemLabel ?type WHERE {
  VALUES ?type { wd:Q33506 wd:Q7075 wd:Q166118 wd:Q1007870 wd:Q31855 }
  ?item wdt:P31 ?type .
  ?item wdt:P17 wd:Q79 .
  SERVICE wikibase:label { bd:serviceParam wikibase:language "en,ar" }
}
"""

sparql.setQuery(query)
results = sparql.query().convert()

# Build Wikidata institutions dict
wd_institutions = {}
for result in results["results"]["bindings"]:
    qid = result["item"]["value"].split("/")[-1]
    name = result.get("itemLabel", {}).get("value", "")
    if name and qid:
        wd_institutions[qid] = name

print(f"Found {len(wd_institutions)} Wikidata institutions\n")
print("="*100)
print("DIAGNOSTIC: Top 3 Wikidata matches for each institution")
print("="*100)

for i, inst in enumerate(institutions, 1):
    inst_name = inst.get("name", "NO NAME")
    print(f"\n{i:2d}. {inst_name}")
    print(f"    Normalized: '{normalize_name(inst_name)}'")
    
    # Calculate scores for all Wikidata institutions
    scores = []
    for qid, wd_name in wd_institutions.items():
        score = similarity_score(inst_name, wd_name)
        if score > 0.5:  # Only show promising matches
            scores.append((score, qid, wd_name))
    
    # Sort by score and show top 3
    scores.sort(reverse=True)
    for rank, (score, qid, wd_name) in enumerate(scores[:3], 1):
        print(f"    {rank}. {score:.3f} - {wd_name} ({qid})")
        print(f"       Normalized: '{normalize_name(wd_name)}'")
    
    if not scores:
        print("    ❌ No matches above 0.5 threshold")