#!/usr/bin/env python3
import json
import random
import pathlib

def generate():
    out_dir = pathlib.Path("data")
    out_dir.mkdir(exist_ok=True)
    
    titles = [
        "Apple releases new MLX framework for Apple Silicon",
        "How to use Rust in your backend",
        "An introduction to QLoRA fine-tuning",
        "Why we migrated from React to Vue",
        "The future of AI is smaller models",
        "Python 3.13 released with new features",
        "Understanding Generalized Knowledge Distillation",
        "Building a podcast generator with Edge-TTS"
    ]
    
    with open("data/rank_log_filter.jsonl", "w") as f1, open("data/rank_log_score.jsonl", "w") as f2:
        for i in range(100):
            title = random.choice(titles) + f" - Part {i}"
            source = random.choice(["hn", "arxiv", "github", "rss"])
            summary = "This is a synthetic summary about " + title
            
            is_relevant = any(k in title for k in ["MLX", "QLoRA", "AI", "models", "podcast"])
            verdict = "KEEP" if is_relevant else "DROP"
            
            if is_relevant:
                score = random.randint(7, 10)
                reason = "Highly relevant to our technical podcast about AI and ML on macOS."
                reasoning = "This article explicitly mentions MLX and Apple Silicon. Since our audience is senior engineers interested in local AI, this is a strong KEEP."
            else:
                score = random.randint(1, 4)
                reason = "Not relevant enough for the podcast theme."
                reasoning = "This article is about a general topic that doesn't fit our core focus on AI, local models, or macOS development. It lacks deep technical signal."
                
            f1.write(json.dumps({
                "title": title,
                "source": source,
                "summary": summary,
                "reasoning": reasoning,
                "verdict": verdict
            }) + "\n")
            
            f2.write(json.dumps({
                "title": title,
                "source": source,
                "summary": summary,
                "reasoning": reasoning,
                "score": score,
                "reason": reason
            }) + "\n")
            
    print("Generated synthetic data in data/rank_log_filter.jsonl and data/rank_log_score.jsonl")

if __name__ == "__main__":
    generate()