t5_translator/sigs_parser.py

import csv
import os


class SIGSParser:
    def __init__(self, csv_path):
        self.lexicon = {}
        self.load_lexicon(csv_path)


    def load_lexicon(self, csv_path):
        """Loads the SIGS CSV into a fast lookup dictionary."""
        if not os.path.exists(csv_path):
            raise FileNotFoundError(f"❌ Could not find lexicon file at: {csv_path}")
            
        with open(csv_path, mode='r', encoding='utf-8') as f:
            reader = csv.DictReader(f)
            for row in reader:
                # Key = wire_token (e.g., 'agr001')
                # Value = Definition + Category
                token = row.get('wire_token', '').strip()
                if token:
                    self.lexicon[token] = {
                        "title": row.get('title', 'N/A'),
                        "definition": row.get('definition', 'N/A'),
                        "category": row.get('category_name', 'N/A')
                    }
        print(f"✅ SIGS Parser loaded {len(self.lexicon)} tokens.")


    def parse(self, sigs_message):
        """
        Takes a SIGS string (e.g., 'agr001 tim030') and returns details.
        """
        tokens = sigs_message.split()
        results = []
        
        for t in tokens:
            data = self.lexicon.get(t)
            if data:
                results.append(f"[{t.upper()}] {data['title']}: {data['definition']}")
            else:
                results.append(f"[{t.upper()}] ⚠️ Unknown Token")
        
        return "\n".join(results)


# --- Example Usage ---
if __name__ == "__main__":
    # Point this to your actual CSV file
    parser = SIGSParser("The_SIGS_Lexicon_v1-STATIC_COPY-Master_Lexicon.csv")
    
    # Test it
    print("\n--- Decoding Message: 'agr001 mot004' ---")
    print(parser.parse("agr001 mot004"))