akg-factor-bridge/user_research.py

274 lines
12 KiB
Python
Raw Normal View History

"""人工关注的独立评析状态:先持久化受理凭据,再投基座;查询绝不派任务。
计划的 evaluated 只表示已收录,不能代替买方评议完成。网络结果不明时不重复
投递,后续只读核验真实报告,并由原评析目标名单/批任务继续补齐。
"""
from __future__ import annotations
import contextlib
import datetime as dt
import fcntl
import json
import logging
from pathlib import Path
import re
import urllib.error
import urllib.parse
import urllib.request
import uuid
from zoneinfo import ZoneInfo
import plan_versions as pv
BJ = ZoneInfo('Asia/Shanghai')
UTC = dt.timezone.utc
_FILE = 'user_research.json'
log = logging.getLogger(__name__)
def _time(value):
try:
value = value if isinstance(value, dt.datetime) else dt.datetime.fromisoformat(str(value).replace('Z', '+00:00'))
return value.replace(tzinfo=UTC) if value.tzinfo is None else value
except (TypeError, ValueError):
return None
def _now(now=None):
return _time(now) or dt.datetime.now(UTC)
@contextlib.contextmanager
def _writer(root):
Path(root).mkdir(parents=True, exist_ok=True)
with open(Path(root) / '.user-research.lock', 'a') as lock:
fcntl.flock(lock, fcntl.LOCK_EX)
yield
def read(root):
path = Path(root) / _FILE
if not path.exists():
return {'version': 1, 'rows': {}}
value = json.loads(path.read_text())
if value.get('version') != 1 or not isinstance(value.get('rows'), dict):
raise ValueError('人工关注评析状态暂不可用')
return value
def _save(root, state):
pv.atomic(Path(root) / _FILE, state)
def _active(root, now):
import user_candidates as uc
rows = []
for row in uc.active(root, now):
try:
rows.append(dict(row, code=uc.normalize(row['code'])))
except (ValueError, KeyError):
# 持久化来源也在入口守沪深范围,不能因旧文件或外部写入越界。
continue
return rows
def report_state(report, now=None, fresh_days=7):
"""只判报告完成事实;财报期是否落后仍由基座原有批任务判断。"""
now = _now(now)
report = report if isinstance(report, dict) else {}
generated = _time(report.get('report_ran_at'))
checked = _time(report.get('checked_at'))
if not report:
return False, '尚无买方评析报告', None
if generated is None or generated > now:
return False, '评析生成时间缺失或晚于当前时刻,待核实', None
# 旧报告命中指纹时只更新 checked_at;不能把复核当新报告,也不能永远判旧。
verified = max(t for t in (generated, checked) if t is not None and t <= now)
if not report.get('brain_used') or report.get('brain_status') != 'ok':
return False, '买方评议尚未完整完成', verified
if not re.fullmatch(r'[0-9a-f]{64}', str(report.get('review_ref') or '')):
return False, '报告缺少可核验的固定版本,等待重新归档', verified
if not str(report.get('thesis') or '').strip():
return False, '报告尚缺买方论点', verified
if now - verified > dt.timedelta(days=fresh_days):
return False, '评析需要重新核对资料', verified
return True, None, verified
def load_reports(codes, now=None):
import sources
now = _now(now)
if not codes:
return {}
return sources.company_reviews(codes, now.astimezone(BJ).date().isoformat(),
cutoff_at=now.isoformat(), strict=True, include_check=True)
def _public(report, record, now, fresh_days):
import card
report = report if isinstance(report, dict) else None
complete, reason, verified = report_state(report, now, fresh_days)
status = (record or {}).get('status', 'missing')
if status == 'completed' and not complete: # 上次完成不能掩盖这次缺报或陈旧。
status = 'missing'
if complete:
status = 'completed'
generated = _time((report or {}).get('report_ran_at'))
error = None if complete else (record or {}).get('error') or reason
return {'review_status': status, 'review_updated_at': (verified.isoformat() if complete and verified else (record or {}).get('updated_at')),
'review_error': error,
'review_data_date': generated.astimezone(BJ).date().isoformat() if generated and generated <= now else None,
'company_review': report, 'company_review_text': card.company_review_view(report),
'review_ref': (report or {}).get('review_ref')}
def views(root, codes, *, now=None, reader=None):
"""实时只读视图;既不落状态文件,也不触发请求或写研究目标表。"""
import config
import user_candidates as uc
now = _now(now)
safe = []
for code in codes:
try:
safe.append(uc.normalize(code))
except ValueError:
continue
safe = sorted(set(safe))
state = read(root)
try:
reports = (reader or load_reports)(safe, now)
except Exception:
log.exception('人工关注评析读取失败')
return {code: {'review_status': 'failed', 'review_updated_at': None,
'review_error': '评析资料暂不可读取,请稍后核实', 'review_data_date': None,
'company_review': None, 'company_review_text': '', 'review_ref': None}
for code in safe}
return {code: _public(reports.get(code), state['rows'].get(code), now,
config.USER_RESEARCH_FRESH_DAYS) for code in safe}
class _NoRedirect(urllib.request.HTTPRedirectHandler):
def redirect_request(self, req, fp, code, msg, headers, newurl):
raise urllib.error.HTTPError(req.full_url, code, '评析提交不接受跳转', headers, fp)
def submit_review(code):
"""唯一请求地址来自受管配置,代码参数无法改变域名、路径或强制重跑。"""
import config
import user_candidates as uc
code = uc.normalize(code)
base = urllib.parse.urlsplit(config.AKG_API_BASE)
if (base.scheme not in ('http', 'https') or not base.hostname or base.username
or base.password or base.query or base.fragment):
raise ValueError('评析服务地址配置无效')
endpoint = config.AKG_API_BASE.rstrip('/') + '/admin/company_review'
query = urllib.parse.urlencode({'ts_code': code[2:] + '.' + code[:2],
'force': 'false', 'sync': 'false',
'with_brain': 'true', 'with_qual': 'true'})
request = urllib.request.Request(endpoint + '?' + query, data=b'', method='POST')
timeout = max(1.0, min(float(config.USER_RESEARCH_REQUEST_TIMEOUT), 10.0))
opener = urllib.request.build_opener(_NoRedirect())
with opener.open(request, timeout=timeout) as response:
return json.loads(response.read(1024 * 1024).decode('utf-8'))
def _targets(root, active, state, write=None):
"""给原自然批任务补齐全部有效人工关注,不改变已发布计划内容。"""
import review_targets
if not active and not state.get('targets_key'):
return
day = pv.latest_date(root)
if not day:
return
published = pv.load(root, day)
key = pv.digest({'day': day, 'decision': published.get('decision'), 'active': active})
if state.get('targets_key') == key:
return
review_targets.persist(day, published, write=write, user_rows=active)
state['targets_key'] = key
state.pop('targets_error', None)
def sync(root=None, *, now=None, reader=None, submit=None, target_write=None):
"""后台/自然调度入口。锁只护本地状态;网络前 claim 已经原子落盘。"""
import config
root = root or config.PLAN_SNAPSHOT_DIR
now = _now(now)
active = _active(root, now)
codes = sorted({r['code'] for r in active})
with _writer(root):
state = read(root)
try:
_targets(root, active, state, target_write)
except Exception:
state['targets_error'] = '研究目标名单同步失败,后台会继续核对'
log.exception('人工关注研究目标名单同步失败')
_save(root, state)
try:
reports = (reader or load_reports)(codes, now)
except Exception:
log.exception('人工关注评析同步读取失败,本轮不投递')
return {'status': 'failed', 'error': '评析资料暂不可读取,本轮未重复提交', 'submitted': 0}
submitted = 0
for code in codes:
report = reports.get(code)
complete, reason, verified = report_state(report, now, config.USER_RESEARCH_FRESH_DAYS)
with _writer(root):
state = read(root)
previous = state['rows'].get(code, {})
# 提交前再核对删除/到期,避免旧后台任务给已移除关注派新任务。
if code not in {r['code'] for r in _active(root, now)}:
continue
if complete:
state['rows'][code] = dict(previous, status='completed', error=None,
updated_at=verified.isoformat(), observed_at=now.isoformat(),
report_ref=report['review_ref'])
_save(root, state)
continue
if previous.get('status') == 'completed' and (_time(previous.get('observed_at')) or dt.datetime.min.replace(tzinfo=UTC)) >= now:
continue # 较早开始的并发读取不能把刚核实的完成状态反向改成待投递。
claimed = _time(previous.get('claimed_at'))
if previous.get('status') in ('pending', 'queued', 'failed') and claimed:
# 已投过的旧无 ref/不完整报告,核对更新后仍不合格,明确留待补齐;不假造完成。
if verified and verified > claimed and previous.get('status') != 'failed':
state['rows'][code] = dict(previous, status='failed', error=reason,
updated_at=now.isoformat())
_save(root, state)
continue
if submitted >= max(1, config.USER_RESEARCH_SUBMIT_LIMIT):
continue
claim = uuid.uuid4().hex
state['rows'][code] = dict(previous, status='pending', claim_id=claim,
claimed_at=now.isoformat(), updated_at=now.isoformat(),
error='评析请求正在受理,结果待核实')
_save(root, state)
submitted += 1
status, error, task_id = 'pending', '评析请求的受理结果待核实,暂不重复提交', None
try:
result = (submit or submit_review)(code)
if (isinstance(result, dict) and result.get('status') == 'queued'
and isinstance(result.get('task_id'), str) and result['task_id'].strip()):
status, error, task_id = 'queued', None, str(result['task_id'])
elif isinstance(result, dict) and result.get('status') == 'done':
result_status = (result.get('result') or {}).get('status')
if result_status not in ('ok', 'skipped_fresh'):
status, error = 'failed', '评析尚未生成完整报告,等待资料补齐'
else:
error = '评析已返回,等待核验固定报告'
except urllib.error.HTTPError as exc:
if 400 <= exc.code < 500:
status, error = 'failed', '评析请求未被接受,请核对服务后重试'
log.warning('人工关注评析请求失败 code=%s http=%s', code, exc.code)
except ValueError:
log.exception('人工关注评析响应或配置不可核验 code=%s', code)
except Exception:
log.exception('人工关注评析受理结果不明 code=%s', code)
with _writer(root):
state = read(root)
previous = state['rows'].get(code, {})
if previous.get('claim_id') == claim and previous.get('status') != 'completed':
state['rows'][code] = dict(previous, status=status, error=error,
task_id=task_id, updated_at=now.isoformat())
_save(root, state)
return {'status': 'checked', 'active': len(codes), 'submitted': submitted}