"""Find (and delete) objects that harness runs left in A4H: names with a run prefix at the start (Z4CGT1HJ_X) or inside (ZCL_Z4CGT1HJ_X).

  python3 -m harness.sweep                 dry run: list them by prefix
  python3 -m harness.sweep --delete        delete them (ADT deletion API, dependency order); a locked object is reported, not forced
  python3 -m harness.sweep --keep-recent 60   do not touch prefixes of runs whose directory changed in the last 60 minutes (default 60)

Never run it while a controller or a series is writing: it can only judge by directory age.
"""
import argparse
import glob
import json
import os
import re
import time

from .adt_client import load_env
from .mcp_client import McpClient
from .runner import DELETE_ORDER, delete_uris
from .task import prefix_for

ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
START = re.compile(r"^(Z\d[0-9A-Z]{6}_)", re.I)
MID = re.compile(r"^[A-Z]{1,5}_(Z\d[0-9A-Z]{6}_)", re.I)


def recent_prefixes(minutes):
    keep = set()
    for d in glob.glob(os.path.join(ROOT, "runs", "**", "*_G*_*"), recursive=True) + glob.glob(os.path.join(ROOT, "runs", "**", "*_T*_*"), recursive=True):
        b = os.path.basename(d)
        m = re.match(r"^(\d+)_([GT]\d+)_", b)
        if m and time.time() - os.path.getmtime(d) < minutes * 60:
            keep.add(prefix_for(int(m.group(1)), m.group(2)).upper())
    return keep


def main():
    load_env(os.path.join(ROOT, ".env"))
    ap = argparse.ArgumentParser()
    ap.add_argument("--delete", action="store_true")
    ap.add_argument("--keep-recent", type=int, default=60)
    a = ap.parse_args()
    found = {}
    with McpClient() as m:
        # run prefixes are Z + a digit + 6 characters: one query per digit (a single "Z*" query is cut at 1000 results), at the start and after the type part
        for q in [f"Z{d}*" for d in "0123456789"] + [f"*_Z{d}*" for d in "0123456789"] + ["ZPROBE*", "ZTEST*"]:
            try:
                for o in json.loads(m.call("sap_search_object", {"query": q, "maxResults": 1000})[1]):
                    if o.get("objectType"):      # a STOB entry of a CDS view has the same name and no objectType: skip it
                        found[(o["name"], o["objectType"])] = o
            except ValueError:
                pass
    keep = recent_prefixes(a.keep_recent)
    by_prefix = {}
    for (n, _t), o in found.items():
        mm = START.match(n.upper()) or MID.match(n.upper())
        if not mm or not o.get("objectType"):
            continue
        pre = mm.group(1).upper()
        if len(pre) != 9 or not pre[1].isdigit():
            continue
        if pre in keep:
            continue
        by_prefix.setdefault(pre, []).append(o)
    total = sum(len(v) for v in by_prefix.values())
    print(f"{total} objects of {len(by_prefix)} run prefixes ({len(keep)} recent prefixes kept)")
    for pre, objs in sorted(by_prefix.items()):
        print(" ", pre, [o["name"] for o in objs][:6])
    json.dump({p: [o["name"] for o in v] for p, v in by_prefix.items()}, open(os.path.join(ROOT, "runs", "sweep.json"), "w"), indent=1)
    if not a.delete:
        return
    objs = sorted([o for v in by_prefix.values() for o in v],
                  key=lambda o: DELETE_ORDER.index(o["objectType"]) if o["objectType"] in DELETE_ORDER else 99)
    done = failed = 0
    for i in range(0, len(objs), 10):
        uris = []
        for o in objs[i:i + 10]:
            uris.append(o["uri"])
        res = delete_uris(uris)
        for u, v in res.items():
            if v["deleted"]:
                done += 1
            else:
                failed += 1
                print("not deleted:", u.split("/")[-1], v["msg"])
    print(f"deleted {done}, not deleted {failed}")


if __name__ == "__main__":
    main()