import json, collections, re
p='.scratch/cockpit-real-data-wayfinding/verify/artifacts/t67/geom-none.json'
with open(p,encoding='utf-8') as f: d=json.load(f)
feats=d['data']['features']
print('features:', len(feats))
# 1) 是否存在 location / 位置描述类字段
keys=collections.Counter()
for ft in feats: keys.update((ft.get('properties') or {}).keys())
print('property keys:', dict(keys))
# 2) code 前缀分布
pref=collections.Counter()
for ft in feats:
    code=str((ft.get('properties') or {}).get('code') or '')
    m=re.match(r'^([A-Za-z]{2})', code)
    pref[m.group(1) if m else '(none)']+=1
print('code 2-letter prefix:', dict(pref))
# 3) 按 source 分组看前缀
bysrc=collections.defaultdict(collections.Counter)
for ft in feats:
    pr=ft.get('properties') or {}
    code=str(pr.get('code') or '')
    m=re.match(r'^([A-Za-z]{2})', code)
    bysrc[pr.get('source')][m.group(1) if m else '(none)']+=1
for k,v in bysrc.items(): print('source', k, dict(v))
# 4) 样例
for ft in feats[:3]:
    print('SAMPLE', json.dumps(ft.get('properties'), ensure_ascii=False)[:400])
# 5) 看 name/remark 里是否含 城南/城北/太常
for word in ['城南','城北','太常']:
    hits=[ (ft.get('properties') or {}).get('code') for ft in feats if word in json.dumps(ft.get('properties') or {}, ensure_ascii=False)]
    print(word, 'appears in', len(hits), 'features; sample codes:', hits[:3])