139 lines
5.7 KiB
Python
139 lines
5.7 KiB
Python
"""
|
|
Fix remaining records: P5 ability tag, P6 ability tags, JSON fixes for 5 broken records
|
|
"""
|
|
import json, urllib.request, re
|
|
|
|
APP_TOKEN = "CMHSbUUjka3TrUsaxxEc297ongf"
|
|
CRED_FILE = "/root/.openclaw/credentials/xiaoyan/config.json"
|
|
|
|
STD_HEARING_TAGS = {
|
|
"显性事实理解｜关键词识别", "显性事实理解｜单句信息点抓取",
|
|
"基础语境理解｜场景/物品/动作识别", "显性细节理解｜数字/时间/地点",
|
|
"同义替换识别｜词/短语级", "目的/偏好识别｜显性 to/for/like",
|
|
"干扰抑制｜多信息筛选", "语用推断｜否定与纠错",
|
|
"多句保持｜信息整合", "情绪/态度理解", "长对话理解｜主旨+细节",
|
|
}
|
|
|
|
# Tag mapping for section-level ability (P5 style)
|
|
SECTION_TAG_MAP = {
|
|
"听觉抓取关键信息": "显性事实理解｜关键词识别",
|
|
}
|
|
|
|
def get_token():
|
|
with open(CRED_FILE) as f:
|
|
cfg = json.load(f)
|
|
app_id = cfg['apps'][0]['appId']
|
|
app_secret = cfg['apps'][0]['appSecret']
|
|
req = urllib.request.Request(
|
|
"https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal",
|
|
data=json.dumps({"app_id": app_id, "app_secret": app_secret}).encode(),
|
|
headers={"Content-Type": "application/json"})
|
|
return json.loads(urllib.request.urlopen(req).read())['tenant_access_token']
|
|
|
|
def api_call(url, method='GET', body=None):
|
|
token = get_token()
|
|
headers = {"Authorization": f"Bearer {token}"}
|
|
data = json.dumps(body).encode() if body else None
|
|
if data:
|
|
headers["Content-Type"] = "application/json"
|
|
req = urllib.request.Request(url, data=data, method=method, headers=headers)
|
|
return json.loads(urllib.request.urlopen(req).read())
|
|
|
|
def update_record(table_id, record_id, fields):
|
|
url = f"https://open.feishu.cn/open-apis/bitable/v1/apps/{APP_TOKEN}/tables/{table_id}/records/{record_id}"
|
|
return api_call(url, 'PUT', {"fields": fields})
|
|
|
|
# 1. Fix P5 032801 - update section-level ability
|
|
print("=== P5 032801 ===")
|
|
url = f"https://open.feishu.cn/open-apis/bitable/v1/apps/{APP_TOKEN}/tables/tblDssVmhGzc3UKd/records?page_size=50"
|
|
resp = api_call(url)
|
|
for item in resp['data']['items']:
|
|
sid = item['fields'].get('题目集合 ID', '')
|
|
if sid == '032801':
|
|
rid = item['record_id']
|
|
jd = json.loads(item['fields']['jsonData'])
|
|
old_ability = jd.get('first', {}).get('ability', [])
|
|
new_ability = [SECTION_TAG_MAP.get(a, a) for a in old_ability]
|
|
if new_ability != old_ability:
|
|
jd['first']['ability'] = new_ability
|
|
# Also fix per-question ability if it exists
|
|
qs = jd.get('first', {}).get('questionSet', [])
|
|
for q in qs:
|
|
if 'ability' in q:
|
|
old = q['ability']
|
|
if isinstance(old, list):
|
|
q['ability'] = [SECTION_TAG_MAP.get(a, a) for a in old]
|
|
new_jd = json.dumps(jd, ensure_ascii=False)
|
|
result = update_record("tblDssVmhGzc3UKd", rid, {"jsonData": new_jd})
|
|
print(f" Updated: {result.get('code')}")
|
|
else:
|
|
print(f" No change needed")
|
|
break
|
|
|
|
# 2. Fix P6 records - add ability tags based on question content
|
|
print("\n=== P6 ===")
|
|
url = f"https://open.feishu.cn/open-apis/bitable/v1/apps/{APP_TOKEN}/tables/tbloiMcD0sBtGSTq/records?page_size=50"
|
|
resp = api_call(url)
|
|
for item in resp['data']['items']:
|
|
sid = item['fields'].get('题目集合 ID', '')
|
|
if '010199' in str(sid):
|
|
continue
|
|
jd_str = item['fields'].get('jsonData', '{}')
|
|
if not jd_str or jd_str == 'None':
|
|
continue
|
|
jd = json.loads(jd_str)
|
|
qs = jd.get('questionSet', [])
|
|
changed = False
|
|
for q in qs:
|
|
if not q.get('ability'):
|
|
q['ability'] = ["显性事实理解｜关键词识别"] # Default for P6 listening_choosePic
|
|
changed = True
|
|
if changed:
|
|
new_jd = json.dumps(jd, ensure_ascii=False)
|
|
result = update_record("tbloiMcD0sBtGSTq", item['record_id'], {"jsonData": new_jd})
|
|
print(f" ID={sid}: {'✅' if result.get('code')==0 else '❌'} ability filled")
|
|
|
|
# 3. Fix 5 broken JSON records
|
|
print("\n=== Fixing broken JSONs ===")
|
|
broken_mapping = {
|
|
"P2_021901": {"table_id": "tblzTLNH7f13uWQN", "sid": "021901"},
|
|
"P2_022301": {"table_id": "tblzTLNH7f13uWQN", "sid": "022301"},
|
|
"P4_021301": {"table_id": "tblVmeDtBDKsAEfz", "sid": "021301"},
|
|
"P4_021601": {"table_id": "tblVmeDtBDKsAEfz", "sid": "021601"},
|
|
"P4_021801": {"table_id": "tblVmeDtBDKsAEfz", "sid": "021801"},
|
|
}
|
|
|
|
for key, info in broken_mapping.items():
|
|
with open(f'/tmp/fixed_{key}.txt') as f:
|
|
fixed_jd = f.read()
|
|
|
|
# Update ability tags in fixed JSON too
|
|
jd = json.loads(fixed_jd)
|
|
changed = False
|
|
for section in ['first', 'second']:
|
|
sect = jd.get(section, {})
|
|
if not sect:
|
|
continue
|
|
qs = sect.get('questionSet', [])
|
|
for q in qs:
|
|
old = q.get('ability', [])
|
|
if isinstance(old, list):
|
|
new = [SECTION_TAG_MAP.get(a, a) for a in old]
|
|
if new != old:
|
|
q['ability'] = new
|
|
changed = True
|
|
if changed:
|
|
fixed_jd = json.dumps(jd, ensure_ascii=False)
|
|
|
|
# Find record_id
|
|
url = f"https://open.feishu.cn/open-apis/bitable/v1/apps/{APP_TOKEN}/tables/{info['table_id']}/records?page_size=50"
|
|
resp = api_call(url)
|
|
for item in resp['data']['items']:
|
|
if item['fields'].get('题目集合 ID', '') == info['sid']:
|
|
rid = item['record_id']
|
|
result = update_record(info['table_id'], rid, {"jsonData": fixed_jd})
|
|
print(f" {key}: {'✅' if result.get('code')==0 else '❌'} fixed+tags")
|
|
break
|
|
|
|
print("\nDone!")
|