akg-factor-bridge/user_candidates.py

221 lines
9.1 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

"""用户补充的候选来源。与计划共用文件锁,先保存,再由修订任务发布。"""
from __future__ import annotations
import datetime as dt
import json
import re
import uuid
from pathlib import Path
from zoneinfo import ZoneInfo
import plan_versions as pv
BJ = ZoneInfo('Asia/Shanghai')
def consumer_view(published, include_user_candidates=False):
"""旧调用方只取系统来源;显式声明支持新来源后才返回人工候选。"""
if include_user_candidates or not published.get('user_candidates'):
return published
out = dict(published)
out.pop('user_candidates', None)
for bucket in ('main', 'observe', 'main_shown', 'observe_shown', 'candidates', 'watch'):
if bucket in out:
out[bucket] = [{k: v for k, v in r.items() if k not in ('user_candidate', 'user_required')}
for r in out[bucket] if not r.get('user_required')]
if 'counts' in out:
out['counts'] = dict(out['counts'], main=len(out.get('main', [])), observe=len(out.get('observe', [])))
if 'card_counts' in out:
rows = out.get('main', []) + out.get('observe', [])
out['card_counts'] = {v: sum(r.get('verdict') == v for r in rows) for v in out['card_counts']}
return out
def normalize(value):
value = str(value or '').strip().upper()
if re.fullmatch(r'\d{6}\.(SH|SZ)', value):
value = value[-2:] + value[:6]
elif re.fullmatch(r'\d{6}', value):
value = ('SH' if value.startswith(('60', '68')) else 'SZ') + value
if not re.fullmatch(r'(SH(?:60|68)\d{4}|SZ(?:00|30)\d{4})', value):
raise ValueError('仅支持沪深 A 股,请检查股票代码')
return value
def catalog():
"""使用上市证券基础表,不能把部分行业池当作完整可搜索名单。"""
import db
frame = db.read_mysql('heat',
"SELECT gp_code_two,gp_name FROM gp_code_all WHERE list_status='L' "
"AND (gp_code_two LIKE '%.SH' OR gp_code_two LIKE '%.SZ')")
out = {}
for row in frame.to_dict('records'):
try:
code = normalize(row.get('gp_code_two'))
except ValueError:
continue
name = str(row.get('gp_name') or '').strip()
if name:
out[code] = name
if not out:
raise ValueError('证券名称资料暂不可用,请稍后重试')
return out
def resolve(raw, names=None):
"""批量名称只按完整简称精确匹配;全部解析成功后才允许保存。"""
if isinstance(raw, str):
raw = [raw]
if not isinstance(raw, list) or any(not isinstance(v, str) for v in raw):
raise ValueError('请输入股票名称或代码')
tokens = [v for item in raw for v in re.split(r'[\s,,;;、]+', item.strip()) if v]
if not 1 <= len(tokens) <= 30:
raise ValueError('每次可添加 1 至 30 只股票')
index = None
codes = []
for value in tokens:
try:
code = normalize(value)
except ValueError:
# 明确的证券代码继续走原交易所限制,不尝试按名称解释。
if re.fullmatch(r'(?:(?:SH|SZ|BJ)?\d+(?:\.(?:SH|SZ|BJ))?)', value.upper()):
raise
if index is None:
source = names() if callable(names) else names or {}
index = {}
for candidate, name in source.items():
try:
canonical = normalize(candidate)
except ValueError:
continue
index.setdefault(str(name).strip().upper(), set()).add(canonical)
matches = index.get(value.upper(), set())
if not matches:
raise ValueError(f'未找到沪深 A 股“{value[:40]}”,请检查完整名称或使用代码') from None
if len(matches) != 1:
raise ValueError(f'“{value[:40]}”对应多只股票,请使用代码') from None
code = next(iter(matches))
if code not in codes:
codes.append(code)
return codes
def read(root):
path = Path(root) / 'user_candidates.json'
if not path.exists():
return {'revision': 0, 'rows': []}
state = json.loads(path.read_text())
if not isinstance(state.get('rows'), list) or not isinstance(state.get('revision'), int):
raise ValueError('添加记录暂不可用')
return state
def active(root, now=None):
today = (now or dt.datetime.now(BJ)).astimezone(BJ).date().isoformat()
return [dict(r) for r in read(root)['rows']
if not r.get('removed_at') and r['expires_on'] >= today]
def save(root, payload, actor, now=None, *, names=None):
now = now or dt.datetime.now(BJ)
codes = resolve(payload.get('codes'), names)
reason = str(payload.get('reason') or '').strip()
if not reason or len(reason) > 300:
raise ValueError('请填写添加理由,最多 300 字')
try:
expires = dt.date.fromisoformat(str(payload.get('expires_on') or ''))
except ValueError as exc:
raise ValueError('请选择关注截止日期') from exc
if not now.astimezone(BJ).date() <= expires <= now.astimezone(BJ).date() + dt.timedelta(days=90):
raise ValueError('关注期限应在今天至未来 90 天内')
with pv.writer(root):
state = read(root)
current = {r['code'] for r in active(root, now)}
added = []
for code in codes:
if code in current:
continue
row = {'id': uuid.uuid4().hex, 'code': code, 'reason': reason,
'expires_on': expires.isoformat(), 'created_at': now.isoformat(),
'created_by': str(actor)[:100]}
if isinstance(names, dict) and names.get(code):
row['name'] = names[code]
state['rows'].append(row)
added.append(row)
if added:
state['revision'] += 1
pv.atomic(Path(root) / 'user_candidates.json', state)
mark_pending(root, [r['code'] for r in added])
return {'ok': True, 'added': len(added), 'existing': len(codes) - len(added),
'revision': state['revision']}
def remove(root, identity, actor, now=None):
now = now or dt.datetime.now(BJ)
with pv.writer(root):
state = read(root)
row = next((r for r in state['rows'] if r['id'] == identity), None)
if row is None:
raise ValueError('添加记录不存在,请刷新后重试')
if not row.get('removed_at'):
row.update(removed_at=now.isoformat(), removed_by=str(actor)[:100])
state['revision'] += 1
pv.atomic(Path(root) / 'user_candidates.json', state)
mark_pending(root, [row['code']])
return {'ok': True, 'revision': state['revision']}
def mark_pending(root, codes):
day = pv.latest_date(root)
if day:
state = pv.health(root, day)
pv.health(root, day, pending_codes=sorted(set(state.get('pending_codes') or []) | set(codes)))
def live_pending(root, published, now=None):
"""写后未发布、删除或到期时,即使后台失败也不能继续消费旧人工来源。"""
current = {r['code']: r['id'] for r in active(root, now)}
frozen = {r['code']: r['id'] for r in published.get('user_candidates', [])}
return sorted(c for c in current.keys() | frozen.keys() if current.get(c) != frozen.get(c))
def listing(root, now=None):
now = now or dt.datetime.now(BJ)
state = read(root)
try:
published = pv.load(root) if pv.latest_date(root) else {}
except FileNotFoundError:
published = {}
material = {r['code']: r for b in ('main', 'observe') for r in published.get(b, [])}
expected = {r['id'] for r in published.get('user_candidates', [])}
today = now.astimezone(BJ).date().isoformat()
import user_research
research = user_research.views(root, [r['code'] for r in state['rows'][-300:]], now=now)
rows = []
for source in reversed(state['rows']):
row = material.get(source['code']) or {}
status = ('removed' if source.get('removed_at') else
'expired' if source['expires_on'] < today else
'pending' if source['id'] not in expected else 'evaluated')
rows.append({**source, 'status': status, 'name': row.get('name') or source.get('name'),
'verdict': row.get('verdict'), 'basis': row.get('basis'),
'decision_id': (published.get('decision') or {}).get('id'),
**research.get(source['code'], {})})
return {'ok': True, 'rows': rows[:300], 'revision': state['revision']}
def refresh_saved():
"""请求结束后尝试发布;失败保留登记和待核验状态,定时修订会重试。"""
import logging
import plan_refresh
import user_research
try:
user_research.sync()
except Exception:
logging.getLogger(__name__).exception('人工关注评析状态同步失败,保留登记等待自然调度')
try:
return plan_refresh.refresh()
except Exception:
logging.getLogger(__name__).exception('用户候选已保存,计划修订待重试')
return {'status': 'pending'}