#!/usr/bin/env bash
# Prints the Bewerbungs-Tracker BLACKLIST in a matchable, tab-separated form, so
# a job-search run can discard candidates that are blocked BEFORE listing or
# importing them (server also rejects blocked offers with 409 on POST /joboffers,
# but we don't want to even present them).
#
# Output: one blacklist entry per line, tab-separated:
#   id <TAB> typ <TAB> firma <TAB> stelle <TAB> ort <TAB> domain <TAB> url_norm <TAB> firma_norm <TAB> firma_slug <TAB> stelle_norm <TAB> ort_norm <TAB> grund
#
#   typ = url | domain | firma | firma_stelle | auto
#
#   firma_slug = robuster Firmen-Schlüssel (Umlaut-Translit, End-Rechtsform raus,
#                mit "-" verbunden) — identisch zu applied-set.sh und firmaSlug()
#                in lib/blacklist.js. Damit greift die Firmen-Sperre auch bei
#                abweichender Schreibweise/Rechtsform.
#
# A candidate is BLOCKED when one entry matches:
#   typ=url          -> candidate URL (normalized) == url_norm
#   typ=domain       -> candidate URL host == domain (also matches subdomains)
#   typ=firma        -> SAME company: candidate firma_slug == firma_slug, OR one
#                       firma_slug is a leading hyphen-prefix of the other (>=2
#                       tokens); firma_norm only as fallback for legacy rows.
#   typ=firma_stelle -> same company (firma_slug, wie oben) AND stelle_norm equal
#                       (ort_norm only narrows further when set)
#   typ=auto         -> treat like the concrete fields it carries (url/firma_stelle)
#
# The server already provides the *_norm fields (lowercased, tracking params
# stripped, gender/legal-form removed), so compare against those.
#
# Reuses the bewerbungs-tracker skill's helper for auth/base-URL.
set -euo pipefail

BT="${BT_SCRIPT:-$HOME/.claude/skills/bewerbungs-tracker/scripts/bt.sh}"
if [[ ! -x "$BT" ]]; then
  echo "blacklist-set.sh: bewerbungs-tracker helper not found at $BT" >&2
  exit 2
fi

bl="$("$BT" GET '/joboffers/blacklist')"

BL_JSON="$bl" python3 <<'PY'
import os, json, html, sys

def load(name):
    raw = os.environ[name].split('<http')[0]
    try:
        return json.loads(raw)
    except Exception:
        return []

def clean(v):
    return html.unescape(str(v if v is not None else '')).replace('\t', ' ').strip()

rows = load('BL_JSON')
for e in rows:
    print('\t'.join(clean(e.get(k)) for k in (
        'id', 'typ', 'firma', 'stelle', 'ort', 'domain',
        'url_norm', 'firma_norm', 'firma_slug', 'stelle_norm', 'ort_norm', 'grund')))

print(f'# {len(rows)} Blacklist-Eintraege', file=sys.stderr)
PY