Import sanitized HIS processing tools

2026-05-26 08:51:10 +08:00
commit 7e329f1d85
46 changed files with 19175 additions and 0 deletions
--- a/患者首页处理/数据处理工作区/03_人工复核/03_人工复核导出与回写.py
+++ b/患者首页处理/数据处理工作区/03_人工复核/03_人工复核导出与回写.py
@@ -0,0 +1,224 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+从 PostgreSQL 导出患者首页复核表，并把人工复核结果回写到 Patient_FrontPages。
+
+依赖系统命令 psql；数据库密码通过 PGPASSWORD 环境变量或 --pg-password 传入。
+"""
+
+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 = PROJECT_ROOT / "数据处理结果区" / "04_复核与人工校正" / "患者首页_人工复核表.csv"
+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) -> None:
+    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_review_") as tmpdir:
+        sql_path = Path(tmpdir) / "review.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")
+    if completed.stdout.strip():
+        print(completed.stdout.strip())
+
+
+def export_review(args: argparse.Namespace) -> None:
+    output = args.output.resolve()
+    output.parent.mkdir(parents=True, exist_ok=True)
+    escaped_output = str(output).replace("'", "''")
+    table = quote_pg_identifier(args.pg_table)
+    where_sql = "" if args.all else "WHERE review_status <> 'auto_pass' OR manual_corrected IS TRUE"
+    select_sql = (
+        "SELECT inpatient_no, source_file, medical_record_no, front_page_medical_record_no, patient_name, "
+        "gender, birth_date, discharge_dept, major_department, primary_diagnosis, "
+        "primary_diagnosis_code, total_cost, self_pay_amount, review_status, "
+        "review_notes::text AS review_notes, auto_corrections::text AS auto_corrections, "
+        "manual_corrected, contact_address, contact_phone, discharge_diagnoses::text AS discharge_diagnoses, "
+        "operations::text AS operations, pathology_diagnosis, pathology_diagnosis_code, pathology_no, "
+        "discharge_disposition_code, readmission_plan_code, quality_status, quality_notes::text AS quality_notes, "
+        "'' AS manual_review_notes, '' AS corrected_medical_record_no, "
+        "'' AS corrected_patient_name, '' AS corrected_major_department, "
+        "'' AS corrected_primary_diagnosis, '' AS corrected_primary_diagnosis_code, "
+        "'' AS corrected_total_cost, '' AS corrected_self_pay_amount, '' AS mark_review_status "
+        f"FROM {table} {where_sql} ORDER BY source_file"
+    )
+    sql = f"\\set ON_ERROR_STOP on\n\\copy ({select_sql}) TO '{escaped_output}' WITH (FORMAT csv, HEADER true, ENCODING 'UTF8')\n"
+    run_psql(sql, args)
+    print(f"已导出复核表：{output}")
+
+
+def import_review(args: argparse.Namespace) -> None:
+    input_path = args.input.resolve()
+    if not input_path.exists():
+        raise RuntimeError(f"复核表不存在：{input_path}")
+    escaped_input = str(input_path).replace("'", "''")
+    table = quote_pg_identifier(args.pg_table)
+    sql = f"""
+\\set ON_ERROR_STOP on
+CREATE TEMP TABLE patient_front_review_import (
+    inpatient_no TEXT,
+    source_file TEXT,
+    medical_record_no TEXT,
+    front_page_medical_record_no TEXT,
+    patient_name TEXT,
+    gender TEXT,
+    birth_date TEXT,
+    discharge_dept TEXT,
+    major_department TEXT,
+    primary_diagnosis TEXT,
+    primary_diagnosis_code TEXT,
+    total_cost TEXT,
+    self_pay_amount TEXT,
+    review_status TEXT,
+    review_notes TEXT,
+    auto_corrections TEXT,
+    manual_corrected TEXT,
+    contact_address TEXT,
+    contact_phone TEXT,
+    discharge_diagnoses TEXT,
+    operations TEXT,
+    pathology_diagnosis TEXT,
+    pathology_diagnosis_code TEXT,
+    pathology_no TEXT,
+    discharge_disposition_code TEXT,
+    readmission_plan_code TEXT,
+    quality_status TEXT,
+    quality_notes TEXT,
+    manual_review_notes TEXT,
+    corrected_medical_record_no TEXT,
+    corrected_patient_name TEXT,
+    corrected_major_department TEXT,
+    corrected_primary_diagnosis TEXT,
+    corrected_primary_diagnosis_code TEXT,
+    corrected_total_cost TEXT,
+    corrected_self_pay_amount TEXT,
+    mark_review_status TEXT
+);
+
+\\copy patient_front_review_import FROM '{escaped_input}' WITH (FORMAT csv, HEADER true, ENCODING 'UTF8')
+
+UPDATE {table} AS t
+SET
+    medical_record_no = COALESCE(NULLIF(i.corrected_medical_record_no, ''), t.medical_record_no),
+    patient_name = COALESCE(NULLIF(i.corrected_patient_name, ''), t.patient_name),
+    major_department = COALESCE(NULLIF(i.corrected_major_department, ''), t.major_department),
+    primary_diagnosis = COALESCE(NULLIF(i.corrected_primary_diagnosis, ''), t.primary_diagnosis),
+    primary_diagnosis_code = COALESCE(NULLIF(i.corrected_primary_diagnosis_code, ''), t.primary_diagnosis_code),
+    total_cost = COALESCE(NULLIF(i.corrected_total_cost, '')::numeric, t.total_cost),
+    self_pay_amount = COALESCE(NULLIF(i.corrected_self_pay_amount, '')::numeric, t.self_pay_amount),
+    review_status = COALESCE(NULLIF(i.mark_review_status, ''), 'reviewed'),
+    review_notes = CASE
+        WHEN NULLIF(i.manual_review_notes, '') IS NULL THEN t.review_notes
+        ELSE t.review_notes || jsonb_build_array(i.manual_review_notes)
+    END,
+    manual_corrected = CASE
+        WHEN NULLIF(i.corrected_medical_record_no, '') IS NOT NULL
+          OR NULLIF(i.corrected_patient_name, '') IS NOT NULL
+          OR NULLIF(i.corrected_major_department, '') IS NOT NULL
+          OR NULLIF(i.corrected_primary_diagnosis, '') IS NOT NULL
+          OR NULLIF(i.corrected_primary_diagnosis_code, '') IS NOT NULL
+          OR NULLIF(i.corrected_total_cost, '') IS NOT NULL
+          OR NULLIF(i.corrected_self_pay_amount, '') IS NOT NULL
+          OR lower(COALESCE(i.manual_corrected, '')) IN ('true', 't', '1', 'yes', 'y')
+        THEN true
+        ELSE t.manual_corrected
+    END
+FROM patient_front_review_import AS i
+WHERE (
+    NULLIF(i.inpatient_no, '') IS NOT NULL
+    AND t.inpatient_no = i.inpatient_no
+) OR (
+    NULLIF(i.inpatient_no, '') IS NULL
+    AND t.source_file = i.source_file
+);
+""".strip()
+    run_psql(sql, args)
+    print(f"已回写人工复核表：{input_path}")
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(description="导出/回写患者首页 PostgreSQL 人工复核表。")
+    subparsers = parser.add_subparsers(dest="command", required=True)
+
+    def add_pg_options(subparser: argparse.ArgumentParser) -> None:
+        subparser.add_argument("--pg-host", default=os.environ.get("PGHOST", ""), help="PostgreSQL 主机；也可用 PGHOST")
+        subparser.add_argument("--pg-port", default=os.environ.get("PGPORT", "5432"), help="PostgreSQL 端口；也可用 PGPORT")
+        subparser.add_argument("--pg-database", default=os.environ.get("PGDATABASE", ""), help="PostgreSQL 数据库；也可用 PGDATABASE")
+        subparser.add_argument("--pg-user", default=os.environ.get("PGUSER", ""), help="PostgreSQL 用户名；也可用 PGUSER")
+        subparser.add_argument("--pg-password", default=os.environ.get("PGPASSWORD", ""), help="PostgreSQL 密码；也可用 PGPASSWORD")
+        subparser.add_argument("--pg-table", default=os.environ.get("PG_PATIENT_TABLE", DEFAULT_TABLE), help="PostgreSQL 表名")
+
+    export_parser = subparsers.add_parser("export", help="从 PostgreSQL 导出待复核 CSV")
+    add_pg_options(export_parser)
+    export_parser.add_argument("-o", "--output", type=Path, default=DEFAULT_OUTPUT, help="复核 CSV 输出路径")
+    export_parser.add_argument("--all", action="store_true", help="导出全部记录，而不仅是需复核/已人工修正记录")
+
+    import_parser = subparsers.add_parser("import", help="把人工复核 CSV 回写 PostgreSQL")
+    add_pg_options(import_parser)
+    import_parser.add_argument("-i", "--input", type=Path, default=DEFAULT_OUTPUT, help="人工复核 CSV 路径")
+    return parser
+
+
+def main() -> int:
+    args = build_parser().parse_args()
+    if args.command == "export":
+        export_review(args)
+    elif args.command == "import":
+        import_review(args)
+    else:
+        raise RuntimeError(f"未知命令：{args.command}")
+    return 0
+
+
+if __name__ == "__main__":
+    try:
+        raise SystemExit(main())
+    except Exception as exc:  # noqa: BLE001 - 命令行工具需要清楚输出错误
+        print(f"错误：{exc}", file=sys.stderr)
+        raise SystemExit(1)