import json, os
from collections import Counter

base = r'.scratch/opportunity-e2e/env-raw'
out_path = r'.scratch/opportunity-e2e/env-analysis2.txt'
_buf = []
def out(s=''):
    _buf.append(str(s))

def load(name):
    with open(os.path.join(base, name + '.json'), encoding='utf-8-sig') as f:
        return json.load(f)

def fix(s):
    if not isinstance(s, str):
        return s
    try:
        return s.encode('latin-1').decode('utf-8')
    except (UnicodeEncodeError, UnicodeDecodeError):
        return s

def deepfix(x):
    if isinstance(x, str):
        return fix(x)
    if isinstance(x, list):
        return [deepfix(i) for i in x]
    if isinstance(x, dict):
        return {k: deepfix(v) for k, v in x.items()}
    return x

# 1. 各部门用户样例：挑普通用户（无管理员角色）
out('=== USER CANDIDATES ===')
for tag in ['yinxiao', 'tezhan', 'yunying', 'huannan-seed']:
    u = load('users-' + tag)
    ul = (u.get('data') or {}).get('content') or []
    out('--- %s total=%s ---' % (tag, (u.get('data') or {}).get('total')))
    for x in ul[:12]:
        roles = ','.join((r.get('name') or '') for r in (x.get('roles') or []))
        out('id=%s name=%s dept=%s status=%s roles=[%s]' % (
            x.get('id'), fix(x.get('username')), fix(x.get('primaryDeptName')) or fix(x.get('primaryDeptId')) or 'null',
            x.get('employmentStatus'), roles))

# 2. 商机全量明细
opp = load('opp-all')
ol = (opp.get('data') or {}).get('content') or []
out('=== OPP ALL total=%s n=%s ===' % ((opp.get('data') or {}).get('total'), len(ol)))
out('owner dist: %s' % Counter(fix(o.get('ownerNameSnapshot')) or o.get('ownerUserId') for o in ol).most_common())
out('ownerDept dist: %s' % Counter(fix(o.get('ownerDeptName')) or 'null' for o in ol).most_common())
out('source dist: %s' % Counter(fix(o.get('oppSourceName')) or o.get('oppSource') for o in ol).most_common())
out('--- all rows ---')
for o in ol:
    out('id=%s name=%s status=%s owner=%s/%s poolReason=%s stage=%s created=%s' % (
        o.get('id'), fix(o.get('oppName')), o.get('oppStatus'), fix(o.get('ownerNameSnapshot')),
        fix(o.get('ownerDeptName')) or '-', fix(o.get('poolReason')) or '-', fix(o.get('currentStageName')),
        o.get('createTime')))

# 3. dict industry 层级
di = load('dict-items')
items = di.get('data') or {}
out('=== DICT ITEMS industry / opp_stage / pool_reason ===')
for grp in ['industry', 'opp_stage', 'pool_reason', 'pause_reason', 'close_reason']:
    lst = items.get(grp) or []
    out('--- %s (%s items) ---' % (grp, len(lst)))
    for it in lst[:20]:
        out('code=%s name=%s parent=%s level=%s enabled=%s' % (
            it.get('code'), fix(it.get('name')), it.get('parentId'), it.get('level'), it.get('status')))

with open(out_path, 'w', encoding='utf-8') as f:
    f.write('\n'.join(_buf))
print('written', out_path, len(_buf), 'lines')