duyunzhoudyz/dyz-gongwen-skills / skills/gongwen-grassroots
gongwen-grassroots
Verified基层行业包:写乡镇(街道)、村(社区)的专用文书,含报上级的政务信息、迎检汇报与自查、居民通知、告知书、倡议书、防汛防火应急通知、工作台账、走访提纲、实事清单、村(居)务公开、一表通和准入清单报告,查面向群众的处罚和强制表述。用户说镇里报篇信息争取采用、县里来检查要准备自查报告和现场汇报、社区迎检自查、居民停水通知、暴雨预警通知各村、村务公开怎么贴时使用。基层总结计划交 gongwen-report,请示和会议通知交 gongwen-draft,讲话交 gongwen-speech,检查后的整改交 gongwen-rectify,新闻稿、县直部门本部门信息交 gongwen-brief。
scripts/notice_check.py
View on GitHub#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""面向群众文书体检(gongwen-grassroots)。
适用于居民(村民)通知、告知书、倡议书、防汛防火等应急通知、村(居)务公开和公示、群消息。
检查八件事:
1. 要素是否齐全:称呼、时间、联系方式、落款、日期(按文书类型取舍);
2. 日期与星期是否一致,日期是否存在(阿拉伯数字、中文数字日期,以及“星期二(1月12日)”的写法);
3. 对群众的文书是否通俗:长句、公文腔词语;
4. 倡议书有没有强制性措辞;
5. 村(居)务公开的公布期限(低保初审公示按 7 天另行核对;起止日期恰好卡在临界值时另行提示)、
公示中有没有与事项无关的个人信息;
6. 转发预警时有没有写明发布单位和发布时间;
7. 有没有引用已废止的法规(如《森林防火条例》);
8. 面向群众的文书中,村(社区)常见、gongwen_lint.py legal 类容易漏报的强制措施(NTC-018):
取消资格或分红、要求签责任书、“不得进山”、停发扣除福利。
罚款、拘留、断水断电等一般法律表述和个人信息(身份证号、手机号)由 gongwen_lint.py 的
legal、privacy 两类检查负责,本脚本不重复。
用法:python scripts/notice_check.py <文件> [--kind 类型] [--year 年份] [--json] [--strict]
不填 --kind 时从标题推断;文件名含“群消息”的按群消息处理。
退出码:0 正常;1 使用 --strict 且存在 P0;2 输入错误。
只用标准库;读取 .docx 时需要 python-docx。不联网,不写任何文件。
"""
from __future__ import annotations
import argparse
import datetime as _dt
import json
import re
import sys
from pathlib import Path
from typing import Any, Dict, List, Optional, Sequence, Tuple
VERSION = "1.2.0"
KINDS = ("通知", "告知书", "倡议书", "应急通知", "公示", "群消息")
LEVELS = ("P0", "P1", "P2")
# 工具约定:群众文书单句超过 60 字提示;群消息超过 300 字提示(约一屏)
LONG_SENTENCE = 60
MAX_LONG_REPORTS = 5
GROUP_MSG_LIMIT = 300
# 村(居)务公开的公布期限下限(《村民委员会组织法》第三十五条、《城市居民委员会组织法》第三十四条)
PUBLIC_DAYS_MIN = 15
# 低保初审公示期(《最低生活保障审核确认办法》第十九条)
DIBAO_DAYS = 7
DRAFT_NOTE_RE = re.compile(r"^\s*【起草说明】\s*$")
TODO_RE = re.compile(r"【待(?:补|核实):[^】]*】")
EMERGENCY_TITLE_RE = re.compile(
r"防汛|防台|台风|暴雨|降雨|强降水|洪水|汛期|汛情|山洪|大风|冰雹|雷电|森林防火|草原防火|防灭火|防火|火险|"
r"寒潮|暴雪|冰冻|高温|地质灾害|应急|预警|避险|转移|紧急通知"
)
PUBLIC_TITLE_RE = re.compile(r"公示|公开|公布")
PUBLIC_AUDIENCE_RE = re.compile(
r"居民|村民|群众|市民|业主|住户|商户|家长|乡亲|朋友|游客|租户|街坊|邻居|老年人|各位"
)
TIME_RE = re.compile(
r"\d{1,2}月\d{1,2}日|[一二三四五六七八九十]{1,2}月[一二三四五六七八九十]{1,3}日|"
r"\d{1,2}[::]\d{2}|\d{1,2}时|\d{1,2}点|星期[一二三四五六日天]|周[一二三四五六日天]|"
r"今天|明天|后天|今晚|今夜|即日起|本周|下周|【待(?:补|核实):[^】]*(?:时间|日期|期限)[^】]*】"
)
DEADLINE_RE = re.compile(r"前|之前|以前|以内|日内|天内|期限|截止|届满")
PHONE_RE = re.compile(
r"(?<![\d.])(?:0\d{2,3}-?)?\d{7,8}(?![\d.]|\s*(?:元|万|亿|人|户|个|名|次|件|套|台|辆|吨|斤|公斤|千克|亩|平方|立方|米|千瓦|度|%|%))|"
r"(?<!\d)1[3-9]\d{9}(?!\d)|"
r"(?<!\d)1[3-9]\d\*{4}\d{4}(?!\d)|(?<!\d)\d{3}-\d{3,4}-\d{4}(?!\d)|"
r"(?:拨打|电话|热线|报警|求助)[^。\n]{0,4}(?<!\d)(?:110|119|120|122|12345|12315|12319|12350)(?!\d)|"
r"【待(?:补|核实):[^】]*(?:电话|联系)[^】]*】"
)
ORG_TAIL_RE = re.compile(
r"(?:委员会|居委会|村委会|办事处|人民政府|党委|党工委|党支部|党总支|社区|街道|镇|乡|村|"
r"指挥部|办公室|服务中心|服务站|中心|物业|物业服务中心|工作站|小组|站|所)$"
)
SIGN_TODO_RE = re.compile(r"^【待(?:补|核实):[^】]*(?:落款|单位|署名)[^】]*】$")
CN_NUM = "〇零一二三四五六七八九"
# 成文日期行;紧急通知可写到“时”“分”,缺时的可写“2026年7月12日【待补:时】”
DATE_LINE_RE = re.compile(
r"^(?:\d{4}年\d{1,2}月(?:\d{1,2}|[ ]*)日(?:(?:\d{1,2}|[ ]*)时(?:\d{1,2}分)?|【待(?:补|核实):[^】]*】)?|"
r"[〇零一二三四五六七八九]{4}年[一二三四五六七八九十]{1,2}月[一二三四五六七八九十]{1,3}日|"
r"【待(?:补|核实):[^】]*(?:日期|时间)[^】]*】)$"
)
YEAR_RE = re.compile(r"(\d{4})年")
_MD = r"\d{1,2}|[一二三四五六七八九十]{1,3}"
_YEAR = r"\d{4}|[〇零一二三四五六七八九]{4}"
# 日期加星期:“10月20日(星期二)”“十月二十日(星期二)”“星期二(10月20日)”
WEEKDAY_PATTERNS: Tuple["re.Pattern[str]", ...] = (
re.compile(
rf"(?:(?P<year>{_YEAR})年)?(?P<month>{_MD})月(?P<day>{_MD})日\s*[((]?\s*"
r"(?:星期|周|礼拜)(?P<wd>[一二三四五六日天])\s*[))]?"
),
re.compile(
r"(?:星期|周|礼拜)(?P<wd>[一二三四五六日天])\s*[((]\s*"
rf"(?:(?P<year>{_YEAR})年)?(?P<month>{_MD})月(?P<day>{_MD})日\s*[))]"
),
)
# 没有和日期写在一起的“星期X”(“周X”常见于“每周一”,不计)
LONE_WEEKDAY_RE = re.compile(r"(?:星期|礼拜)[一二三四五六日天]")
CN_YEAR_DIGITS = {"〇": 0, "零": 0, "一": 1, "二": 2, "三": 3, "四": 4, "五": 5, "六": 6, "七": 7, "八": 8, "九": 9}
WEEKDAY_NAMES = "一二三四五六日"
SENTENCE_SPLIT_RE = re.compile(r"(?<=[。!?;!?;])")
# 面向群众时的公文腔词语:(正则, 说明, 建议)
JARGON: Tuple[Tuple[str, str, str], ...] = (
(r"兹定于", "“兹定于”是旧式公文用语", "改为“定于”或“将在”"),
(r"届时", "“届时”对居民不够直白", "改为“到时”或写明具体时间"),
(r"予以", "“予以”是书面公文用语", "删去,或改成具体动作,如“帮您办理”"),
(r"务必", "“务必”语气生硬", "改为“请”"),
(r"(?:相关|有关)事宜", "“相关事宜”没有说清是什么事", "写明具体事项"),
(r"高度重视", "“高度重视”是机关套话,居民不需要", "删去,直接写要做什么"),
(r"切实", "“切实”是机关套话", "删去"),
(r"落实落细|走深走实|压实责任|抓手|闭环|赋能|见行见效", "机关内部用语,居民看不懂", "改成具体做法或删去"),
(r"属地管理|履职|台账|网格化管理", "内部工作用语", "改成居民能懂的说法,如“由社区工作人员上门登记”"),
(r"广大居民群众|广大村民群众|广大人民群众", "称呼生硬", "改为“各位居民”“各位村民”"),
(r"配合做好", "“配合做好”把居民当成下级", "改为“请您……”,写清需要居民做的具体事"),
(r"即日起", "“即日起”对居民不够直白", "写明从几月几日起"),
)
COERCIVE_RE = re.compile(
r"必须|严禁|禁止|不得|一律|务必|责令|处罚|罚款|追究|问责|考核|通报批评|曝光|黑名单|后果自负"
)
PUBLICITY_PERIOD_RE = re.compile(r"公示期|公示时间|公示期限|公布期限|公开期限|公示至|公示日期|公开时间|公布时间|公示从")
# 村(居)务公开:标题含这些词,或正文出现“村务公开”等(“村务公开栏”“村务监督委员会”不算)
WUGONGKAI_TITLE_RE = re.compile(r"(?:村务|居务|财务)公开|(?:村|居)务(?!监督)")
WUGONGKAI_TEXT_RE = re.compile(r"(?:村务|居务|财务)公开(?!栏)")
# 村(居)务公开本身的公布期限行;公示子项(如低保初审公示)用“公示期”“公示时间”,不在此列
DOC_PERIOD_LABEL_RE = re.compile(r"(?:公开|公布)(?:时间|期限|日期)")
SUB_PERIOD_LABEL_RE = re.compile(r"^(?:公示期|公示时间|公示期限|公示日期|公示从|公示至)")
# 有自己公示期规定的事项:不按村(居)务公开的 15 日判断
EXEMPT_PERIOD_RE = re.compile(r"低保|最低生活保障|特困|救助|初审")
DIBAO_RE = re.compile(r"低保|最低生活保障")
HEADING_RE = re.compile(r"^[一二三四五六七八九十]+、")
PERIOD_DAYS_RE = re.compile(
r"(?:公示期|公布期限|公开期限|公示时间|公示期限|公布时间|公开时间)[^。\n]{0,10}?"
r"(?<![月\d一二三四五六七八九十])(\d+|[一二三四五六七八九十]+)\s*(?:个工作日|日|天)"
)
DATE_RANGE_RE = re.compile(r"(?:(\d{4})年)?(\d{1,2})月(\d{1,2})日[^。\n]{0,6}?(?:至|到|—|~|~|-)\s*(?:(\d{4})年)?(?:(\d{1,2})月)?(\d{1,2})日")
SENSITIVE_RE = re.compile(
r"病情|病史|诊断|疾病名称|精神疾病|精神病|艾滋|癌症|透析|服刑|吸毒|戒毒|残疾等级|离婚原因|"
r"家庭住址|门牌号|身份证号|银行卡号"
)
PREWARN_RE = re.compile(
r"(?:蓝色|黄色|橙色|红色)(?:预警信号|预警)|[ⅠⅡⅢⅣ]级(?:应急响应|响应|预警)|"
r"[一二三四1234]级(?:应急响应|响应|预警)"
)
PREWARN_SOURCE_RE = re.compile(
r"气象台|气象局|气象部门|防汛抗旱指挥部|防汛指挥部|防指|应急管理局|应急管理部门|水文|自然资源|"
r"指挥部|防灭火指挥部|人民政府|【待(?:补|核实):[^】]*(?:发布|来源|单位)[^】]*】"
)
RELEASE_TIME_RE = re.compile(r"\d{1,2}时|\d{1,2}[::]\d{2}|\d{1,2}点|【待(?:补|核实):[^】]*时间[^】]*】")
# 已废止的法规:(书名号内名称, 替代说明)
REPEALED_LAWS: Tuple[Tuple[str, str], ...] = (
("森林防火条例", "《森林草原防灭火条例》(2025年11月公布,2026年1月1日起施行)"),
("草原防火条例", "《森林草原防灭火条例》(2025年11月公布,2026年1月1日起施行)"),
)
BASIS_REPEALED = "《森林草原防灭火条例》第六十三条(《森林防火条例》《草原防火条例》同时废止)"
BASIS_ELEMENTS = "references/templates/jumin-wenshu.md;references/_shared/profiles/units/shequ.md 第八、九部分"
BASIS_PLAIN = "references/_shared/profiles/units/shequ.md 第九部分(对居民说大白话);60 字为工具约定"
BASIS_INITIATIVE = "references/templates/jumin-wenshu.md(倡议书邀请自愿参与,不带强制性)"
BASIS_GROUP = "references/_shared/profiles/units/shequ.md 第八部分第 3 条;300 字为工具约定"
BASIS_PERIOD = "《村民委员会组织法》第三十五条、《城市居民委员会组织法》第三十四条(2026年1月1日起施行)"
BASIS_DIBAO = "《最低生活保障审核确认办法》第十九条(初审公示期为 7 天)"
BASIS_SENSITIVE = "《最低生活保障审核确认办法》第二十四条;《个人信息保护法》第二十八条"
BASIS_PREWARN = "《气象灾害预警信号发布与传播办法》第七条、第十条;《突发事件应对法》第七条"
BASIS_COERCION = ("references/redlines.md 第一条;references/templates/jumin-wenshu.md 第七部分"
"(村(居)委会是基层群众性自治组织,没有行政执法权)")
BASIS_BOUNDARY = "《民法典》第二百零一条(按日计算期间的,开始的当日不计入);各地公示期算法不一,以本地惯例为准"
# 面向群众的文书中,村(社区)常见、gongwen_lint.py legal 类容易漏报的强制措施:(正则, 说明)
COERCION_EXTRA: Tuple[Tuple["re.Pattern[str]", str], ...] = (
(re.compile(r"取消[^,。;!?\n]{0,12}(?:资格|待遇|分红|福利|补贴|补助)"), "以取消资格、待遇、分红或补贴作为强制手段"),
(re.compile(r"(?:签订|签署)[^,。;!?\n]{0,8}(?:责任书|承诺书|保证书)"), "要求群众签责任书、承诺书或保证书"),
(re.compile(r"不得(?:进|入)(?:山|村|小区|楼)|禁止(?:进|入)(?:山|村|小区)"), "限制群众进山、进村、进小区"),
(re.compile(r"(?:停发|扣除|扣发)[^,。;!?\n]{0,6}(?:分红|福利|补贴|补助)"), "以停发、扣除分红或福利作为强制手段"),
)
# 句中写明了依据(转述上级命令、法规):只提示核对依据,不直接定为 P0
BASIS_CUE_RE = re.compile(r"根据|按照|依据|依照|《[^》]+》|人民政府[^。\n]{0,10}(?:令|命令|通告)")
# 落款是村(居)委会、社区或村党组织
GRASSROOTS_SIGN_RE = re.compile(
r"(?:村|居)民委员会|村委会|居委会|村(?:党支部|党总支|党委)|社区(?:党支部|党总支|党委)|(?:社区|村)$"
)
class InputError(Exception):
"""输入文件错误(退出码 2)。"""
# ---------------------------------------------------------------------------
# 读取
# ---------------------------------------------------------------------------
def read_lines(path: Path) -> Tuple[List[Tuple[int, str]], List[str]]:
"""读取文件,返回 [(行号, 文本)] 和提示信息。"""
notes: List[str] = []
if not path.is_file():
raise InputError(f"未找到文件:{path}")
suffix = path.suffix.lower()
if suffix in (".txt", ".md", ".markdown", ".text"):
raw = path.read_bytes()
try:
text = raw.decode("utf-8-sig")
except UnicodeDecodeError:
try:
text = raw.decode("gb18030")
notes.append("文件不是 UTF-8 编码,已按 GB18030 读取。")
except UnicodeDecodeError as exc:
raise InputError("无法识别文件编码,请另存为 UTF-8 后重试。") from exc
text = text.replace("\r\n", "\n").replace("\r", "\n")
return [(i, line) for i, line in enumerate(text.split("\n"), start=1)], notes
if suffix == ".docx":
try:
import docx # type: ignore
except ImportError as exc:
raise InputError("读取 .docx 需要 python-docx,请先运行:pip install python-docx") from exc
try:
document = docx.Document(str(path))
except Exception as exc: # 损坏或加密的 docx
raise InputError(f"无法打开 docx 文件:{exc}") from exc
return [(i, p.text) for i, p in enumerate(document.paragraphs, start=1)], notes
raise InputError(f"不支持的文件类型:{path.suffix or '无扩展名'}。只支持 .txt、.md、.docx。")
def body_lines(lines: Sequence[Tuple[int, str]]) -> Tuple[List[Tuple[int, str]], Optional[int]]:
"""取【起草说明】之前的非空行,返回 (行列表, 起草说明所在行号)。"""
kept: List[Tuple[int, str]] = []
for number, text in lines:
if DRAFT_NOTE_RE.match(text):
return kept, number
stripped = text.strip()
if stripped:
kept.append((number, stripped))
return kept, None
def nonspace_len(text: str) -> int:
return len(re.sub(r"\s", "", text))
# ---------------------------------------------------------------------------
# 判断类型与对象
# ---------------------------------------------------------------------------
def detect_kind(title: str, explicit: Optional[str], filename: str = "") -> Tuple[str, str]:
if explicit:
return explicit, "参数"
if "群消息" in filename:
return "群消息", "文件名推断"
if "倡议" in title:
return "倡议书", "标题推断"
if re.search(r"告知书|告知函|一封信|告居民书|告村民书", title):
return "告知书", "标题推断"
if PUBLIC_TITLE_RE.search(title):
return "公示", "标题推断"
if EMERGENCY_TITLE_RE.search(title):
return "应急通知", "标题推断"
return "通知", "默认"
def find_salutation(body: Sequence[Tuple[int, str]]) -> Optional[Tuple[int, str]]:
"""以冒号结尾的短行视为称呼或主送对象:没有标题时看第一行,有标题时看标题后 3 行。"""
for number, text in body[0:4]:
if text.endswith((":", ":")) and nonspace_len(text) <= 30:
return number, text
return None
def is_public(kind: str, title: str, salutation: Optional[Tuple[int, str]]) -> bool:
if kind in ("倡议书", "群消息", "公示", "告知书"):
return True
if salutation and PUBLIC_AUDIENCE_RE.search(salutation[1]):
return True
if salutation is None and PUBLIC_AUDIENCE_RE.search(title):
return True
return False
# ---------------------------------------------------------------------------
# 日期工具
# ---------------------------------------------------------------------------
def cn_to_int(text: str) -> Optional[int]:
"""把“十五”“二十”“三”之类的中文数字转为整数(1–99)。"""
if text.isdigit():
return int(text)
digits = {c: i for i, c in enumerate("零一二三四五六七八九")}
if text == "十":
return 10
if text.startswith("十"):
return 10 + digits.get(text[1:], 0) if len(text) == 2 else None
if "十" in text:
tens, _, ones = text.partition("十")
if tens not in digits:
return None
return digits[tens] * 10 + (digits.get(ones, 0) if ones else 0)
return digits.get(text)
def signoff_year(body: Sequence[Tuple[int, str]]) -> Tuple[Optional[int], Optional[int]]:
"""从落款日期取年份和月份。"""
for _number, text in reversed(body[-4:]):
match = re.match(r"^(\d{4})年(\d{1,2})月(?:\d{1,2}|[ ]*)日(?:(?:\d{1,2}|[ ]*)时(?:\d{1,2}分)?|【待(?:补|核实):[^】]*】)?$", text)
if match:
return int(match.group(1)), int(match.group(2))
return None, None
def parse_year(text: Optional[str]) -> Optional[int]:
"""“2026”或“二〇二六”转为整数。"""
if not text:
return None
if text.isdigit():
return int(text)
if all(c in CN_YEAR_DIGITS for c in text):
return int("".join(str(CN_YEAR_DIGITS[c]) for c in text))
return None
def resolve_year(explicit: Optional[int], month: int, arg_year: Optional[int],
sign_year: Optional[int], sign_month: Optional[int], first_year: Optional[int]) -> Optional[int]:
if explicit:
return explicit
if arg_year:
return arg_year
if sign_year:
# 12 月发文、写次年 1 月的事:月份比发文月份小 6 个月以上时按次年算
if sign_month and sign_month - month > 6:
return sign_year + 1
return sign_year
return first_year
# ---------------------------------------------------------------------------
# 检查
# ---------------------------------------------------------------------------
class Checker:
def __init__(self, body: List[Tuple[int, str]], kind: str, year: Optional[int]) -> None:
self.body = body
self.kind = kind
self.arg_year = year
self.issues: List[Dict[str, Any]] = []
self.notes: List[str] = []
self.title = body[0][1] if body else ""
self.salutation = find_salutation(body)
self.public = is_public(kind, self.title, self.salutation)
self.full_text = "\n".join(text for _n, text in body)
# 落款日期行不算正文中的时间要素
self.text_wo_date = "\n".join(text for _n, text in body if not DATE_LINE_RE.match(text))
def add(self, issue_id: str, level: str, category: str, line: Optional[int], excerpt: str,
message: str, suggestion: str, basis: str) -> None:
self.issues.append({
"id": issue_id,
"level": level,
"category": category,
"line": line,
"excerpt": excerpt[:60],
"message": message,
"suggestion": suggestion,
"basis": basis,
})
# 一、要素 -------------------------------------------------------------
def check_elements(self) -> None:
kind = self.kind
# 公示、村(居)务公开和群消息可以不写称呼
if kind not in ("群消息", "公示") and self.salutation is None:
self.add("NTC-001", "P1", "要素", self.body[0][0], self.title,
"缺少称呼或主送对象行(如“各位居民:”“各村(社区):”)",
"标题下一行写明对象,以全角冒号结尾", BASIS_ELEMENTS)
has_time = bool(TIME_RE.search(self.text_wo_date))
if kind in ("通知", "应急通知", "群消息") and not has_time:
self.add("NTC-002", "P1", "要素", None, self.title,
"正文没有具体时间(日期、几点、星期)",
"写明日期和时间;用户没提供的写【待补:时间】", BASIS_ELEMENTS)
if kind == "告知书" and not (has_time or DEADLINE_RE.search(self.text_wo_date)):
self.add("NTC-002", "P2", "要素", None, self.title,
"告知书没有写办理期限或时间",
"需要居民在期限内办理的,写明截止日期", BASIS_ELEMENTS)
if kind != "倡议书" and not PHONE_RE.search(self.full_text):
self.add("NTC-003", "P1", "要素", None, self.title,
"没有联系电话或咨询、监督电话",
"写明联系人和电话;用户没提供的写【待补:联系电话】", BASIS_ELEMENTS)
if kind == "群消息":
return
tail = self.body[-4:] if len(self.body) > 1 else []
has_date = any(DATE_LINE_RE.match(text) for _n, text in tail)
has_sign = any(
(ORG_TAIL_RE.search(text) and "。" not in text and nonspace_len(text) <= 40
and not DATE_LINE_RE.match(text) and not text.endswith((":", ":")))
or SIGN_TODO_RE.match(text)
for _n, text in tail[-3:]
)
last_line = self.body[-1][0] if self.body else None
if not has_sign:
self.add("NTC-004", "P1", "要素", last_line, self.body[-1][1] if self.body else "",
"末尾没有落款单位", "正文后另起一行写落款单位全称(张贴版须加盖公章)", BASIS_ELEMENTS)
if not has_date:
self.add("NTC-005", "P1", "要素", last_line, self.body[-1][1] if self.body else "",
"末尾没有成文日期", "落款下一行写成文日期,如“2026年10月16日”", BASIS_ELEMENTS)
# 二、日期与星期 ---------------------------------------------------------
def check_weekday(self) -> None:
sign_year, sign_month = signoff_year(self.body)
first = YEAR_RE.search(self.full_text)
first_year = int(first.group(1)) if first else None
skipped = 0
unparsed = 0
for number, text in self.body:
matches = self._weekday_matches(text)
for match in matches:
month, day = cn_to_int(match.group("month")), cn_to_int(match.group("day"))
if month is None or day is None or not 1 <= month <= 12:
unparsed += 1
continue
year = resolve_year(parse_year(match.group("year")), month, self.arg_year,
sign_year, sign_month, first_year)
if year is None:
skipped += 1
continue
try:
date = _dt.date(year, month, day)
except ValueError:
self.add("NTC-006", "P0", "日期", number, match.group(0),
f"{year}年没有{month}月{day}日", "核实日期", "核对事实:日期必须真实存在")
continue
actual = WEEKDAY_NAMES[date.weekday()]
written = "日" if match.group("wd") == "天" else match.group("wd")
if written != actual:
self.add("NTC-006", "P0", "日期", number, match.group(0),
f"日期与星期不一致:{year}年{month}月{day}日是星期{actual},稿中写的是星期{match.group('wd')}",
"向用户核实日期和星期哪个正确,不要自行改动",
"核对事实:居民会按错误的时间行动")
spans = [m.span() for m in matches]
unparsed += sum(
1 for m in LONE_WEEKDAY_RE.finditer(text)
if not any(start <= m.start() < end for start, end in spans)
)
if skipped:
self.notes.append(f"有 {skipped} 处“日期加星期”无法确定年份,未核对星期;可用 --year 指定年份。")
if unparsed:
self.notes.append(f"有 {unparsed} 处星期未核对(没有和日期写在一起,或日期写法无法识别);"
"用户只给了星期几的,已知当天日期则按今天推算并在起草说明注明;"
"用户给了日期的,请人工核对星期。")
@staticmethod
def _weekday_matches(text: str) -> List["re.Match[str]"]:
"""找出“日期加星期”和“星期加(日期)”,重叠的只取先找到的。"""
found: List["re.Match[str]"] = []
for pattern in WEEKDAY_PATTERNS:
for match in pattern.finditer(text):
start, end = match.span()
if any(start < m.end() and m.start() < end for m in found):
continue
found.append(match)
return found
# 三、通俗程度 -----------------------------------------------------------
def check_plain(self) -> None:
if not self.public:
return
skip = {self.body[0][0]}
if self.salutation:
skip.add(self.salutation[0])
long_hits: List[Tuple[int, str]] = []
for number, text in self.body:
if number in skip or DATE_LINE_RE.match(text):
continue
for sentence in SENTENCE_SPLIT_RE.split(text):
clean = TODO_RE.sub("", sentence)
if nonspace_len(clean) > LONG_SENTENCE:
long_hits.append((number, sentence))
for number, sentence in long_hits[:MAX_LONG_REPORTS]:
self.add("NTC-007", "P2", "通俗", number, sentence,
f"句子超过 {LONG_SENTENCE} 字,居民不容易一次看懂",
"拆成几句,一句话说一件事", BASIS_PLAIN)
if len(long_hits) > MAX_LONG_REPORTS:
self.notes.append(f"长句共 {len(long_hits)} 句,只列出前 {MAX_LONG_REPORTS} 句。")
for pattern, message, suggestion in JARGON:
regex = re.compile(pattern)
hits = [(n, m.group(0)) for n, t in self.body for m in regex.finditer(t)]
if not hits:
continue
number, word = hits[0]
extra = f"(全文共 {len(hits)} 处)" if len(hits) > 1 else ""
self.add("NTC-008", "P2", "通俗", number, word, message + extra, suggestion, BASIS_PLAIN)
# 四、倡议书 -------------------------------------------------------------
def check_initiative(self) -> None:
if self.kind != "倡议书":
return
seen = set()
for number, text in self.body:
for match in COERCIVE_RE.finditer(text):
word = match.group(0)
if word in seen:
continue
seen.add(word)
self.add("NTC-009", "P1", "语气", number, word,
f"倡议书出现强制性措辞“{word}”",
"倡议只邀请自愿参与:改为“请大家”“欢迎”;确需强制执行的,须由有权限的主体改用通知并写明依据和执法主体(村(社区)无此权限,转请乡镇(街道)或执法部门依法办理)",
BASIS_INITIATIVE)
# 五、群消息篇幅 ---------------------------------------------------------
def check_group_message(self) -> None:
if self.kind != "群消息":
return
count = nonspace_len(self.full_text)
if count > GROUP_MSG_LIMIT:
self.add("NTC-010", "P1", "篇幅", None, self.title,
f"群消息共 {count} 字,超过 {GROUP_MSG_LIMIT} 字,手机上一屏看不完",
"只留时间、地点、对象、要做的事和联系电话,其余放进张贴版", BASIS_GROUP)
# 六、公示与村(居)务公开 -------------------------------------------------
def check_publicity(self) -> None:
if self.kind != "公示":
return
periods = self._periods()
text_wo_title = "\n".join(text for _n, text in self.body[1:])
if not PUBLICITY_PERIOD_RE.search(text_wo_title) and not periods:
self.add("NTC-011", "P1", "要素", None, self.title,
"公示没有写明公示期(起止日期或天数)",
"写明公示起止日期,以及对公示内容有异议时的反映渠道", BASIS_ELEMENTS)
if self._is_wugongkai():
# 公布期限优先取“公开时间”“公布期限”行;没有的,逐个看不属于低保等专项公示的期限
doc_level = [p for p in periods if p["doc_label"] and not p["exempt"]]
targets = doc_level or [p for p in periods if not p["exempt"]]
if periods and not targets:
self.add("NTC-011", "P2", "要素", None, self.title,
"只写了低保等专项公示的期限,没有写这次村(居)务公开本身的公开时间",
f"另起一行写“公开时间:某月某日至某月某日”,不少于 {PUBLIC_DAYS_MIN} 日",
BASIS_PERIOD)
for period in targets:
if period["days"] < PUBLIC_DAYS_MIN:
self.add("NTC-012", "P1", "期限", period["line"], period["excerpt"],
f"村(居)务公开的公布期限为 {period['days']} 天,少于 {PUBLIC_DAYS_MIN} 日",
f"公布期限不少于 {PUBLIC_DAYS_MIN} 日;本地规定更长的按本地规定",
BASIS_PERIOD)
elif period["days"] == PUBLIC_DAYS_MIN and period["from_range"]:
self._boundary(period, "村(居)务公开的公布期限", "结束日期往后延一天,或按本地惯例核对起算日")
for period in periods:
if not period["dibao"]:
continue
days = period["days"]
if period["from_range"] and days == DIBAO_DAYS + 1:
continue # 开始当日不计入时正好 7 天
if days == DIBAO_DAYS:
if period["from_range"]:
self._boundary(period, "低保初审公示期", "按乡镇(街道)民政部门的算法核对起止日期")
continue
level = "P1" if days < DIBAO_DAYS else "P2"
self.add("NTC-017", level, "期限", period["line"], period["excerpt"],
f"低保初审公示期写的是 {period['days']} 天,规定为 {DIBAO_DAYS} 天",
f"低保初审公示期为 {DIBAO_DAYS} 天;本地另有规定的,请用户提供依据",
BASIS_DIBAO)
seen = set()
for number, text in self.body:
for match in SENSITIVE_RE.finditer(text):
word = match.group(0)
if word in seen:
continue
seen.add(word)
self.add("NTC-013", "P1", "个人信息", number, word,
f"公示中出现“{word}”,可能公开了与公示事项无关的个人信息",
"公示只列必要信息(如姓名、家庭人口、金额),删去病情、住址门牌、证件号等",
BASIS_SENSITIVE)
def _boundary(self, period: Dict[str, Any], what: str, suggestion: str) -> None:
days = period["days"]
self.add("NTC-019", "P2", "期限", period["line"], period["excerpt"],
f"{what}按首尾两天都算正好 {days} 天,按开始当日不计入的算法只有 {days - 1} 天",
suggestion, BASIS_BOUNDARY)
def _is_wugongkai(self) -> bool:
"""标题是村(居)务公开,或正文写明“村务公开”等;“村务监督委员会”“村务公开栏”不算。"""
return bool(WUGONGKAI_TITLE_RE.search(self.title) or WUGONGKAI_TEXT_RE.search(self.full_text))
def _adjacent(self, upper: int, lower: int) -> bool:
"""body 中相邻两行之间没有空行。"""
return self.body[lower][0] - self.body[upper][0] == 1
def _period_context(self, idx: int) -> str:
"""取判断期限性质用的上下文:本行;公示子项标签行加上一行;所在一级标题;独立公示的标题。
只在期限行与上文之间没有空行时才继承上一行和小节标题:空一行单独写在末尾的期限行,
是整份公开的期限(如低保小节之后、落款之前的“公示时间”)。
"""
text = self.body[idx][1]
parts = [text]
if DOC_PERIOD_LABEL_RE.search(text) and not EXEMPT_PERIOD_RE.search(text):
return text # “公开时间”“公布期限”行是整份公开的期限
if SUB_PERIOD_LABEL_RE.match(text) and idx > 1 and self._adjacent(idx - 1, idx):
parts.append(self.body[idx - 1][1])
for j in range(idx - 1, 0, -1):
if not self._adjacent(j, j + 1):
break
if HEADING_RE.match(self.body[j][1]):
parts.append(self.body[j][1])
break
if not self._is_wugongkai():
parts.append(self.title) # 单独一份公示:标题说明公示的是什么
return "\n".join(parts)
def _periods(self) -> List[Dict[str, Any]]:
"""逐行找公示、公开期限(起止日期或天数),跳过标题、成文日期行和一级标题行。"""
sign_year, _m = signoff_year(self.body)
default_year = self.arg_year or sign_year or _dt.date.today().year
found: List[Dict[str, Any]] = []
for idx in range(1, len(self.body)):
number, text = self.body[idx]
if DATE_LINE_RE.match(text) or HEADING_RE.match(text):
continue
if not re.search(r"公示|公布|公开", text):
continue
spans: List[Tuple[int, str, bool]] = []
for match in DATE_RANGE_RE.finditer(text):
days = self._range_days(match, default_year)
if days is not None:
spans.append((days, match.group(0), True))
for match in PERIOD_DAYS_RE.finditer(text):
days = cn_to_int(match.group(1))
if days is not None:
spans.append((days, match.group(0), False))
if not spans:
continue
context = self._period_context(idx)
exempt = bool(EXEMPT_PERIOD_RE.search(context))
for days, excerpt, from_range in spans:
found.append({
"line": number,
"days": days,
"excerpt": excerpt,
"from_range": from_range,
"doc_label": bool(DOC_PERIOD_LABEL_RE.search(text)),
"exempt": exempt,
"dibao": exempt and bool(DIBAO_RE.search(context)),
})
return found
@staticmethod
def _range_days(match: "re.Match[str]", default_year: int) -> Optional[int]:
year1 = int(match.group(1)) if match.group(1) else default_year
month1, day1 = int(match.group(2)), int(match.group(3))
year2 = int(match.group(4)) if match.group(4) else year1
month2 = int(match.group(5)) if match.group(5) else month1
day2 = int(match.group(6))
try:
start = _dt.date(year1, month1, day1)
end = _dt.date(year2, month2, day2)
except ValueError:
return None
if end < start:
try:
end = _dt.date(year2 + 1, month2, day2)
except ValueError:
return None
return (end - start).days + 1
# 七、转发预警 -----------------------------------------------------------
def check_prewarning(self) -> None:
for number, text in self.body:
match = PREWARN_RE.search(text)
if not match:
continue
if not PREWARN_SOURCE_RE.search(text):
self.add("NTC-014", "P1", "预警", number, match.group(0),
"提到预警或应急响应,但没有写明由哪个单位发布",
"照原文写明发布单位、发布时间和级别,如“县气象台10月16日8时发布暴雨橙色预警信号”;不改动预警内容",
BASIS_PREWARN)
elif not RELEASE_TIME_RE.search(text):
self.add("NTC-015", "P2", "预警", number, match.group(0),
"转发预警没有写发布时间", "补上发布时间,用户没提供的写【待补:预警发布时间】",
BASIS_PREWARN)
# 八、已废止的法规 ---------------------------------------------------------
def check_repealed(self) -> None:
for name, replacement in REPEALED_LAWS:
hits = [n for n, t in self.body if f"《{name}》" in t]
if hits:
extra = f"(全文共 {len(hits)} 处)" if len(hits) > 1 else ""
self.add("NTC-016", "P1", "依据", hits[0], f"《{name}》",
f"引用的《{name}》已废止{extra}",
f"改为引用{replacement},条号按新条例对应调整", BASIS_REPEALED)
# 九、村(社区)常见的强制措施 ----------------------------------------------
def _signed_by_grassroots(self) -> bool:
"""落款是村(居)委会、社区或村党组织。群消息看最后一句之后的署名。"""
if self.kind == "群消息" and self.body:
tail = re.split(r"[。!?!?]", self.body[-1][1].rstrip("。!?!? "))[-1].strip()
if tail and nonspace_len(tail) <= 40 and GRASSROOTS_SIGN_RE.search(tail):
return True
for _n, text in self.body[-3:]:
if DATE_LINE_RE.match(text) or "。" in text or text.endswith((":", ":")):
continue
if nonspace_len(text) <= 40 and any(
GRASSROOTS_SIGN_RE.search(part) for part in re.split(r"\s+", text) if part):
return True
return False
def check_coercion(self) -> None:
if not self.public:
return
grassroots = self._signed_by_grassroots()
for number, text in self.body:
for sentence in SENTENCE_SPLIT_RE.split(text):
for pattern, what in COERCION_EXTRA:
match = pattern.search(sentence)
if not match:
continue
has_basis = bool(BASIS_CUE_RE.search(sentence))
if grassroots and not has_basis:
level = "P0"
message = f"村(社区)发布的面向群众的文书{what}(“{match.group(0)}”),村(居)委会没有这项权力"
else:
level = "P1"
message = (f"面向群众的文书{what}(“{match.group(0)}”);发文主体是村(社区)的按 P0"
+ (";句中写了依据,请核对依据原文是否有这项措施、由谁执行" if has_basis else ""))
self.add("NTC-018", level, "强制", number, match.group(0), message,
"村(社区)发布的删去,改为提醒和服务(如“请不要进山”“有困难打村委会电话”);"
"乡镇(街道)发布的,有法律依据和本级职权才写,并写明依据和执法主体",
BASIS_COERCION)
def run(self) -> None:
self.check_elements()
self.check_weekday()
self.check_plain()
self.check_initiative()
self.check_group_message()
self.check_publicity()
self.check_prewarning()
self.check_repealed()
self.check_coercion()
order = {lv: i for i, lv in enumerate(LEVELS)}
self.issues.sort(key=lambda i: (order[i["level"]], i["line"] or 0, i["id"]))
def check_file(path: Path, kind: Optional[str] = None, year: Optional[int] = None) -> Dict[str, Any]:
lines, notes = read_lines(path)
body, note_line = body_lines(lines)
if not body:
raise InputError("正文为空(【起草说明】之前没有内容)")
detected, source = detect_kind(body[0][1], kind, path.stem)
checker = Checker(body, detected, year)
checker.run()
all_notes = list(notes)
if note_line is not None:
all_notes.append(f"第 {note_line} 行为【起草说明】,其后内容未检查。")
all_notes.extend(checker.notes)
all_notes.append("罚款、拘留等法律表述和个人信息请另行运行:python scripts/gongwen_lint.py <文件> --checks legal,privacy;"
"两个脚本都可能漏报,按 references/review-addon.md 第一部分第 1 项的检索词再人工搜一遍。")
summary = {lv: sum(1 for i in checker.issues if i["level"] == lv) for lv in LEVELS}
return {
"file": path.name,
"kind": detected,
"kind_source": source,
"audience": "群众" if checker.public else "工作对象",
"char_count": sum(nonspace_len(t) for _n, t in body),
"summary": summary,
"issues": checker.issues,
"notes": all_notes,
"version": VERSION,
}
def render_text(result: Dict[str, Any]) -> str:
out = [
f"文件:{result['file']} 类型:{result['kind']}({result['kind_source']}) 对象:{result['audience']} 字数:{result['char_count']}",
"结果:P0 {P0} 条,P1 {P1} 条,P2 {P2} 条".format(**result["summary"]),
]
for issue in result["issues"]:
where = f"第 {issue['line']} 行" if issue["line"] else "全文"
out.append(f"[{issue['level']}] {issue['id']} {where}|{issue['excerpt']}")
out.append(f" 问题:{issue['message']}")
out.append(f" 建议:{issue['suggestion']}")
out.append(f" 依据:{issue['basis']}")
for note in result["notes"]:
out.append(f"提示:{note}")
return "\n".join(out)
def build_parser() -> argparse.ArgumentParser:
parser = argparse.ArgumentParser(
prog="notice_check.py",
description="面向群众文书体检:要素、日期与星期、通俗程度、倡议书语气、公示期限、预警来源、已废止法规、"
"村(社区)常见的强制措施。",
epilog="退出码:0 正常;1 使用 --strict 且存在 P0;2 输入错误。罚款、拘留等法律表述和个人信息请用 gongwen_lint.py 检查。",
)
parser.add_argument("file", help="要检查的文件(.txt、.md、.docx),读到单独一行的【起草说明】为止")
parser.add_argument("--kind", choices=KINDS, help="文书类型;不填时从标题推断,文件名含“群消息”的按群消息处理")
parser.add_argument("--year", type=int, help="日期没写年份时,用这个年份核对星期")
parser.add_argument("--json", action="store_true", help="输出 JSON")
parser.add_argument("--strict", action="store_true", help="存在 P0 时返回 1")
return parser
def main(argv: Optional[Sequence[str]] = None) -> int:
for stream in (sys.stdout, sys.stderr):
try:
stream.reconfigure(encoding="utf-8") # type: ignore[attr-defined]
except Exception:
pass
args = build_parser().parse_args(argv)
if args.year is not None and not 1900 <= args.year <= 2100:
print("错误:--year 应为 1900 至 2100 之间的四位年份", file=sys.stderr)
return 2
try:
result = check_file(Path(args.file), args.kind, args.year)
except InputError as exc:
print(f"错误:{exc}", file=sys.stderr)
return 2
if args.json:
print(json.dumps(result, ensure_ascii=False, indent=2))
else:
print(render_text(result))
if args.strict and result["summary"]["P0"] > 0:
return 1
return 0
if __name__ == "__main__":
sys.exit(main())
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |