import json
import re
import os
from pathlib import Path
from datetime import datetime

BASE = Path(r"C:\Users\Lenovo\Documents")
DIRS = {
    "NG1": BASE / "- Dolphin NG",
    "NG2": BASE / "- Dolphin NG2",
    "NG4": BASE / "- DOLPHIN NG4" / "- Results",
    "NG5": BASE / "- Dolphin NG5",
    "NG3": BASE / "- Dolphin NG HD (NG3)" / "correlation_arb512" / "eigenvalues"
}

def parse_ts(s):
    for fmt in ("%Y-%m-%dT%H:%M:%S.%f", "%Y-%m-%dT%H:%M:%S",
                "%Y-%m-%d %H:%M:%S.%f", "%Y-%m-%d %H:%M:%S",
                "%Y-%m-%dT%H:%M:%SZ"):
        try:
            return datetime.strptime(str(s)[:26].replace('Z', ''), fmt)
        except ValueError:
            continue
    return None

def scan_dir_json(d, pattern):
    ts_list = []
    if not d.exists(): return ts_list
    for f in d.glob(pattern):
        try:
            with open(f, 'r', encoding='utf-8', errors='replace') as fb:
                data = json.load(fb)
                ts_str = data.get('timestamp')
                if ts_str:
                    ts = parse_ts(ts_str)
                    if ts: ts_list.append(ts)
        except: continue
    return ts_list

def scan_ng4(d):
    ts_list = []
    if not d.exists(): return ts_list
    log_re = re.compile(r'(\d{4}-\d{2}-\d{2}T[\d:.]+Z)')
    for f in d.glob('*.txt'):
        try:
            with open(f, 'r', encoding='utf-8', errors='replace') as fb:
                for line in fb:
                    m = log_re.search(line)
                    if m:
                        ts = parse_ts(m.group(1))
                        if ts: ts_list.append(ts)
        except: continue
    return ts_list

def scan_ng3(d):
    ts_list = []
    if not d.exists(): return ts_list
    # Just check the first and last date directories to save time
    subdirs = sorted([s for s in d.iterdir() if s.is_dir() and not s.name.endswith('_SKIP')])
    if not subdirs: return ts_list
    
    for subdir in [subdirs[0], subdirs[-1]]:
        for f in subdir.glob('scan_*.json'):
            if '__Indicators' in f.name: continue
            try:
                with open(f, 'r', encoding='utf-8', errors='replace') as fb:
                    data = json.load(fb)
                    ts_str = data.get('timestamp')
                    if ts_str:
                        ts = parse_ts(ts_str)
                        if ts: ts_list.append(ts)
            except: continue
    return ts_list

print("--- Data Archaeology Result ---")
for name, d in DIRS.items():
    print(f"Checking {name} in {d}...")
    if name in ["NG1", "NG2", "NG5"]:
        times = scan_dir_json(d, 'regime_result_*.json')
    elif name == "NG4":
        times = scan_ng4(d)
    elif name == "NG3":
        times = scan_ng3(d)
    
    if times:
        print(f"  {name}: {min(times)} to {max(times)} ({len(times)} samples found in scan)")
    else:
        print(f"  {name}: No data found.")