#!/usr/bin/env python3
"""Wrapper for ak-rss-digest: add state-based deduplication on top of the real fetch script."""

import json
import subprocess
import sys
import os

SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
REAL_SCRIPT = os.path.join(SCRIPT_DIR, "fetch_today_feed_items.py")
STATE_FILE = os.path.join(os.path.dirname(SCRIPT_DIR), "references", "last_seen.json")

# Run the real script
result = subprocess.run(
    [sys.executable, REAL_SCRIPT] + sys.argv[1:],
    capture_output=True, text=True
)
if result.returncode != 0:
    print(result.stderr, file=sys.stderr)
    sys.exit(result.returncode)

data = json.loads(result.stdout)
entries = data.get("entries", [])

# Load last seen
last_seen = {}
if os.path.exists(STATE_FILE):
    with open(STATE_FILE) as f:
        last_seen = json.load(f)

# Filter: keep only entries not seen before (by URL)
new_entries = []
new_seen = {}
for e in entries:
    url = e.get("url", "")
    source = e.get("source", "")
    if url:
        key = f"{source}|{url}"
        new_seen[key] = True
        if key not in last_seen:
            new_entries.append(e)

# Group new entries by source
new_by_source = {}
for e in new_entries:
    src = e.get("source", "unknown")
    new_by_source[src] = new_by_source.get(src, 0) + 1

# Output filtered results
output = {
    **data,
    "entries": new_entries,
    "has_new": len(new_entries) > 0,
    "new_by_source": new_by_source,
    "total_fetched": len(entries),
}

# Save state
os.makedirs(os.path.dirname(STATE_FILE), exist_ok=True)
with open(STATE_FILE, "w") as f:
    json.dump(new_seen, f, ensure_ascii=False, indent=2)

print(json.dumps(output, ensure_ascii=False, indent=2))