#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ 对 Patient_FrontPages 做字段级体检。 输出： - 数据处理结果区/05_质量体检/患者首页_数据库体检报告.txt - 数据处理结果区/05_质量体检/患者首页_字段空值统计.csv - 数据处理结果区/05_质量体检/患者首页_疑似异常记录.csv """ from __future__ import annotations import argparse import os import re import shutil import subprocess import sys import tempfile from pathlib import Path PROJECT_ROOT = Path(__file__).resolve().parents[2] DEFAULT_OUTPUT_DIR = PROJECT_ROOT / "数据处理结果区" / "05_质量体检" DEFAULT_TABLE = "Patient_FrontPages" def quote_pg_identifier(identifier: str) -> str: if not re.fullmatch(r"[A-Za-z_][A-Za-z0-9_]*", identifier): raise ValueError(f"非法 PostgreSQL 表名：{identifier}") return '"' + identifier.replace('"', '""') + '"' def connection_env(args: argparse.Namespace) -> dict[str, str]: env = os.environ.copy() env.update( { "PGHOST": args.pg_host or os.environ.get("PGHOST", ""), "PGPORT": str(args.pg_port or os.environ.get("PGPORT", "")), "PGDATABASE": args.pg_database or os.environ.get("PGDATABASE", ""), "PGUSER": args.pg_user or os.environ.get("PGUSER", ""), "PGPASSWORD": args.pg_password or os.environ.get("PGPASSWORD", ""), } ) missing = [name for name in ["PGHOST", "PGPORT", "PGDATABASE", "PGUSER", "PGPASSWORD"] if not env.get(name)] if missing: raise RuntimeError("缺少 PostgreSQL 连接配置：" + "、".join(missing)) return env def run_psql(sql: str, args: argparse.Namespace) -> str: if shutil.which("psql") is None: raise RuntimeError("未找到 psql。请先安装 PostgreSQL 客户端。") with tempfile.TemporaryDirectory(prefix="patient_front_audit_") as tmpdir: sql_path = Path(tmpdir) / "audit.sql" sql_path.write_text(sql, encoding="utf-8") completed = subprocess.run( ["psql", "--no-password", "--file", str(sql_path)], check=False, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, encoding="utf-8", errors="replace", env=connection_env(args), ) if completed.returncode != 0: raise RuntimeError(completed.stderr.strip() or completed.stdout.strip() or "psql 执行失败") return completed.stdout def build_empty_stat_sql(table: str) -> str: monitored_columns = [ "inpatient_no", "medical_record_no", "patient_name", "gender", "birth_date", "id_card_no", "contact_address", "admission_time", "discharge_time", "major_department", "primary_diagnosis", "primary_diagnosis_code", "discharge_diagnoses", "operations", "quality_status", "review_status", ] selects = [] for column in monitored_columns: identifier = quote_pg_identifier(column) if column in {"discharge_diagnoses", "operations"}: empty_expr = f"{identifier} IS NULL OR jsonb_array_length({identifier}) = 0" else: empty_expr = f"{identifier} IS NULL OR {identifier}::text = ''" selects.append(f"SELECT '{column}' AS column_name, count(*) FILTER (WHERE {empty_expr}) AS empty_count, count(*) AS total_count FROM {table}") return " UNION ALL ".join(selects) def audit(args: argparse.Namespace) -> None: output_dir = args.output_dir.resolve() output_dir.mkdir(parents=True, exist_ok=True) table = quote_pg_identifier(args.pg_table) empty_csv = output_dir / "患者首页_字段空值统计.csv" suspicious_csv = output_dir / "患者首页_疑似异常记录.csv" report_path = output_dir / "患者首页_数据库体检报告.txt" empty_stat_sql = build_empty_stat_sql(table) suspicious_sql = ( "SELECT source_file, inpatient_no, medical_record_no, patient_name, review_status, " "review_notes::text AS review_notes, contact_address, primary_diagnosis, primary_diagnosis_code " f"FROM {table} " "WHERE review_status <> 'auto_pass' " "OR inpatient_no !~ '^ZY\\d{12}$' " "OR medical_record_no !~ '^\\d{10}$' " "OR contact_address ~ '急诊|门诊|其他医疗机构转入|医嘱离院' " "OR primary_diagnosis_code IS NULL " "OR primary_diagnosis_code = '' " "ORDER BY source_file" ) sql = f""" \\set ON_ERROR_STOP on \\pset pager off \\o {str(report_path).replace("'", "''")} SELECT '总记录数' AS item, count(*)::text AS value FROM {table} UNION ALL SELECT '需复核记录数', count(*)::text FROM {table} WHERE review_status <> 'auto_pass' UNION ALL SELECT '缺字段注释数', count(*)::text FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace JOIN pg_attribute a ON a.attrelid = c.oid WHERE n.nspname = 'public' AND c.relname = {args.pg_table!r} AND a.attnum > 0 AND NOT a.attisdropped AND col_description(c.oid, a.attnum) IS NULL; \\o \\copy ({empty_stat_sql}) TO '{str(empty_csv).replace("'", "''")}' WITH (FORMAT csv, HEADER true, ENCODING 'UTF8') \\copy ({suspicious_sql}) TO '{str(suspicious_csv).replace("'", "''")}' WITH (FORMAT csv, HEADER true, ENCODING 'UTF8') """.strip() stdout = run_psql(sql, args) if stdout.strip(): print(stdout.strip()) print(f"体检报告：{report_path}") print(f"字段空值统计：{empty_csv}") print(f"疑似异常记录：{suspicious_csv}") def build_parser() -> argparse.ArgumentParser: parser = argparse.ArgumentParser(description="核验 Patient_FrontPages 字段注释、空值和疑似错位记录。") parser.add_argument("--pg-host", default=os.environ.get("PGHOST", ""), help="PostgreSQL 主机；也可用 PGHOST") parser.add_argument("--pg-port", default=os.environ.get("PGPORT", "5432"), help="PostgreSQL 端口；也可用 PGPORT") parser.add_argument("--pg-database", default=os.environ.get("PGDATABASE", ""), help="PostgreSQL 数据库；也可用 PGDATABASE") parser.add_argument("--pg-user", default=os.environ.get("PGUSER", ""), help="PostgreSQL 用户名；也可用 PGUSER") parser.add_argument("--pg-password", default=os.environ.get("PGPASSWORD", ""), help="PostgreSQL 密码；也可用 PGPASSWORD") parser.add_argument("--pg-table", default=os.environ.get("PG_PATIENT_TABLE", DEFAULT_TABLE), help="PostgreSQL 表名") parser.add_argument("-o", "--output-dir", type=Path, default=DEFAULT_OUTPUT_DIR, help="体检结果输出目录") return parser def main() -> int: audit(build_parser().parse_args()) return 0 if __name__ == "__main__": try: raise SystemExit(main()) except Exception as exc: # noqa: BLE001 print(f"错误：{exc}", file=sys.stderr) raise SystemExit(1)