from __future__ import annotations import json import re from dataclasses import dataclass from pathlib import Path from docx import Document from docx.enum.section import WD_SECTION_START from docx.enum.text import WD_LINE_SPACING from docx.oxml.ns import qn from docx.shared import Cm, Pt ROOT = Path("/Users/hedy/Desktop/zhct") WORK_DIR = ROOT / "zhctprompt/product_software_copyright/locker-pickup-source-20260520" DOCX_PATH = WORK_DIR / "locker-pickup-source-30-pages.docx" CLEAN_TEXT_PATH = WORK_DIR / "selected_source.clean.txt" MANIFEST_PATH = WORK_DIR / "source-selection-manifest.json" CHECK_PATH = WORK_DIR / "pre-submission-check.md" LINES_PER_PAGE = 42 PAGE_COUNT = 30 TOTAL_LINES = LINES_PER_PAGE * PAGE_COUNT @dataclass(frozen=True) class SourceSlice: path: str reason: str start: int | None = None end: int | None = None SOURCES: list[SourceSlice] = [ SourceSlice( "zhctproject/store/application/api/controller/LockerPickup.php", "取餐柜设备前置核验与存取回调入口", ), SourceSlice( "zhctproject/store/application/api/service/LockerPickup.php", "订单核验、设备匹配、柜格回调、存餐取餐撤销状态流转和异常记录", ), SourceSlice( "zhctproject/store/application/common/service/MealOrderPickup.php", "取餐号生成、取餐记录创建、Redis 计数与异常兜底", ), SourceSlice( "zhctproject/store/application/api/service/Consume.php", "备餐完成呼叫、取餐号预占、设备消费订单绑定取餐记录", 145, 250, ), SourceSlice( "zhctproject/store/application/api/service/Consume.php", "订单保存后写入取餐记录", 735, 770, ), SourceSlice( "zhctproject/store/application/api/service/Consume.php", "队列订单保存后写入取餐记录", 1070, 1120, ), SourceSlice( "zhctproject/store/application/cron/command/MealOrderPickupComplete.php", "过期取餐记录自动完结", ), SourceSlice( "zhctproject/ai_api/app/api/controller/MealCheckout.php", "下单页取餐方式解析、取餐柜列表查询和取餐柜合法性校验", 180, 310, ), SourceSlice( "zhctproject/ai_api/app/api/controller/MealCheckout.php", "按档口规则生成取餐柜选项、取餐方式校验、取餐柜设备列表过滤", 450, 690, ), SourceSlice( "zhctproject/ai_api/app/api/service/meal/Checkout.php", "订单初始化、取餐柜字段写入、取餐柜表单校验和取餐柜设备核验", ), SourceSlice( "zhctproject/ai_api/app/api/service/meal/Order.php", "用户订单列表详情中的取餐状态、柜门状态和取餐号展示", ), SourceSlice( "zhctproject/ai_api/app/api/service/meal/DirectPay.php", "直接支付订单生成与取餐号记录写入", ), SourceSlice( "zhctproject/ai_api/app/api/listener/meal/PaySuccess.php", "支付成功后取餐记录补建、Redis 异常处理", ), SourceSlice( "zhctproject/ai_api/app/common/enum/order/LockerStatus.php", "取餐柜状态枚举", ), SourceSlice( "zhctproject/ai_api/app/common/enum/order/TakeMethod.php", "取餐方式枚举", ), SourceSlice( "zhctproject/store/application/common/enum/EquipmentType.php", "设备类型中的取餐柜设备标识", 1, 105, ), ] EXCLUDED_HINTS = [ "passport/Login.php", "controller/Login.php", "logic/Login.php", "route.php", "config.php", "helper", "vendor", "node_modules", "tools", "tests", "权限", "登录", ] def strip_php_comments(source: str) -> str: result: list[str] = [] i = 0 n = len(source) state = "normal" while i < n: ch = source[i] nxt = source[i + 1] if i + 1 < n else "" if state == "normal": if ch == "/" and nxt == "/": i += 2 while i < n and source[i] not in "\r\n": i += 1 continue if ch == "#": i += 1 while i < n and source[i] not in "\r\n": i += 1 continue if ch == "/" and nxt == "*": i += 2 while i < n - 1 and not (source[i] == "*" and source[i + 1] == "/"): if source[i] in "\r\n": result.append(source[i]) i += 1 i += 2 continue if ch == "'": state = "single" result.append(ch) i += 1 continue if ch == '"': state = "double" result.append(ch) i += 1 continue result.append(ch) i += 1 continue if state == "single": result.append(ch) if ch == "\\" and i + 1 < n: result.append(source[i + 1]) i += 2 continue if ch == "'": state = "normal" i += 1 continue if state == "double": result.append(ch) if ch == "\\" and i + 1 < n: result.append(source[i + 1]) i += 2 continue if ch == '"': state = "normal" i += 1 continue return "".join(result) def read_slice(item: SourceSlice) -> list[str]: full_path = ROOT / item.path lines = full_path.read_text(encoding="utf-8", errors="ignore").splitlines() start = item.start or 1 end = item.end or len(lines) selected = "\n".join(lines[start - 1 : end]) stripped = strip_php_comments(selected) return [line.rstrip() for line in stripped.splitlines() if line.strip()] def normalize_lines(raw_lines: list[str]) -> list[str]: cleaned: list[str] = [] for line in raw_lines: line = line.replace("\t", " ").rstrip() if not line.strip(): continue cleaned.append(line) return cleaned def collect_source() -> tuple[list[str], list[dict[str, object]]]: source_lines: list[str] = [] manifest: list[dict[str, object]] = [] for item in SOURCES: before = len(source_lines) lines = normalize_lines(read_slice(item)) source_lines.extend(lines) manifest.append( { "path": str((ROOT / item.path).resolve()), "range": [item.start or 1, item.end or "EOF"], "reason": item.reason, "clean_lines": len(lines), "selected_output_lines": [before + 1, len(source_lines)], } ) if len(source_lines) < TOTAL_LINES: raise RuntimeError(f"selected source has only {len(source_lines)} clean lines, need {TOTAL_LINES}") return source_lines[:TOTAL_LINES], manifest def set_run_font(run) -> None: run.font.name = "Courier New" run.font.size = Pt(7.5) run._element.rPr.rFonts.set(qn("w:ascii"), "Courier New") run._element.rPr.rFonts.set(qn("w:hAnsi"), "Courier New") run._element.rPr.rFonts.set(qn("w:eastAsia"), "SimSun") def build_docx(lines: list[str]) -> None: document = Document() section = document.sections[0] section.start_type = WD_SECTION_START.NEW_PAGE section.page_width = Cm(21) section.page_height = Cm(29.7) section.top_margin = Cm(1.2) section.bottom_margin = Cm(1.2) section.left_margin = Cm(1.0) section.right_margin = Cm(1.0) section.header_distance = Cm(0.4) section.footer_distance = Cm(0.4) styles = document.styles normal = styles["Normal"] normal.font.name = "Courier New" normal.font.size = Pt(7.5) normal._element.rPr.rFonts.set(qn("w:eastAsia"), "SimSun") for page_index in range(PAGE_COUNT): start = page_index * LINES_PER_PAGE end = start + LINES_PER_PAGE page_lines = lines[start:end] paragraph = document.add_paragraph() if page_index > 0: paragraph.paragraph_format.page_break_before = True paragraph.paragraph_format.space_before = Pt(0) paragraph.paragraph_format.space_after = Pt(0) paragraph.paragraph_format.line_spacing_rule = WD_LINE_SPACING.EXACTLY paragraph.paragraph_format.line_spacing = Pt(11) run = paragraph.add_run("\n".join(page_lines)) set_run_font(run) document.save(DOCX_PATH) def write_manifest(lines: list[str], manifest: list[dict[str, object]]) -> None: payload = { "project": "取餐柜系统", "generated_at": "2026-05-20", "workspace": str(ROOT), "output_docx": str(DOCX_PATH), "clean_text": str(CLEAN_TEXT_PATH), "pages": PAGE_COUNT, "lines_per_page": LINES_PER_PAGE, "total_clean_lines": len(lines), "source_selection": manifest, "excluded_scope": EXCLUDED_HINTS, } MANIFEST_PATH.write_text(json.dumps(payload, ensure_ascii=False, indent=2), encoding="utf-8") def has_comment_marker(line: str) -> bool: stripped = line.strip() if stripped.startswith("//") or stripped.startswith("#") or stripped.startswith("*"): return True if "/*" in stripped or "*/" in stripped: return True if re.search(r"(^|[^:])//", stripped): return True return False def write_check(lines: list[str]) -> None: blank_count = sum(1 for line in lines if not line.strip()) comment_marker_count = sum(1 for line in lines if has_comment_marker(line)) paths = [str((ROOT / item.path).resolve()) for item in SOURCES] content = [ "# 取餐柜系统软著源码材料提交前自查", "", f"- 本地工作目录：{WORK_DIR}", f"- Word 材料：{DOCX_PATH}", f"- 清洗后源码文本：{CLEAN_TEXT_PATH}", f"- 选码清单：{MANIFEST_PATH}", f"- 页数目标：{PAGE_COUNT} 页", f"- 每页源码行数：{LINES_PER_PAGE} 行", f"- 清洗后入册源码行数：{len(lines)} 行", f"- 空行检查：{blank_count} 行", f"- 注释标记检查：{comment_marker_count} 行", "- 核心覆盖：取餐流程、取餐柜选择、订单核验、柜端存取回调、柜格编号、设备类型、取餐号生成、状态展示、异常兜底。", "- 已避开：登录、权限、通用工具、框架配置、路由、测试、vendor、node_modules、工具脚本。", "", "## 本地相关项目路径", "", ] content.extend(f"- {path}" for path in paths) content.append("") content.append("## 自查结论") content.append("") if blank_count == 0 and comment_marker_count == 0 and len(lines) == TOTAL_LINES: content.append("- 通过：源码已去空行、去注释，并按 30 页模板生成。") else: content.append("- 需复查：清洗结果存在异常，请查看上方统计。") CHECK_PATH.write_text("\n".join(content) + "\n", encoding="utf-8") def main() -> None: WORK_DIR.mkdir(parents=True, exist_ok=True) lines, manifest = collect_source() CLEAN_TEXT_PATH.write_text("\n".join(lines) + "\n", encoding="utf-8") build_docx(lines) write_manifest(lines, manifest) write_check(lines) print(json.dumps({ "docx": str(DOCX_PATH), "clean_text": str(CLEAN_TEXT_PATH), "manifest": str(MANIFEST_PATH), "check": str(CHECK_PATH), "pages": PAGE_COUNT, "lines": len(lines), }, ensure_ascii=False, indent=2)) if __name__ == "__main__": main()