feat: 手动上传绕防爬、下载错误诊断与健康检查工具；模块化重构 API 与批量同步
后端：
- 将 handlers.rs (1338行) 拆分为 helpers/papers/notes/sync 四模块
- 将 batch_sync.rs 拆分为 batch/{mod,meta,asset} 三模块
- 新增 POST /api/upload 多部件文件上传接口
- 新增 POST /api/no_resource 标记文献"无全文资源"
- 新增 GET/POST /api/active_bibcode 追踪活跃文献
- StandardPaper 结构体扩展 pdf_error / html_error 错误诊断字段
- download.rs 记录下载失败详情至数据库
- 新增 health_check 二进制工具，支持只读扫描与 --fix 自动修复
- 移除 scratch/ 目录、recovered_handlers.rs 及调试日志
前端：
- 新建 CustomSelect 可复用组件，替换全部原生 select
- LibraryPanel：同步按钮反馈动画、下载失败/无资源状态筛选与计数、
文献类型筛选、状态优先排序、搜索一键清空
- 详情弹窗：错误诊断展示、手动 PDF/HTML 上传区、无资源标记/恢复
- SearchPanel：扩展文献类型徽章、下载失败状态提示
- SyncPanel：同步启动乐观 UI 更新、日志容器内自动滚动
- Tab 状态 localStorage 持久化、弹窗 z-index 修复
This commit is contained in:
@@ -0,0 +1,501 @@
|
||||
// src/bin/health_check.rs
|
||||
use std::fs;
|
||||
use std::path::{Path, PathBuf};
|
||||
use sqlx::{SqlitePool, Row};
|
||||
use astroresearch::Config;
|
||||
use tracing::{error, Level};
|
||||
use tracing_subscriber::FmtSubscriber;
|
||||
|
||||
// 检测防爬、验证码、登录墙特征
|
||||
fn detect_anti_bot(content: &str) -> Option<&'static str> {
|
||||
let lower = content.to_lowercase();
|
||||
let cf_patterns = [
|
||||
("checking your browser", "Cloudflare WAF 浏览器检查"),
|
||||
("please wait while we verify", "Cloudflare WAF 验证"),
|
||||
("cf-browser-verification", "Cloudflare WAF 验证特征"),
|
||||
("cf_chl_opt", "Cloudflare WAF 特征"),
|
||||
("just a moment", "Cloudflare 正在等待提示"),
|
||||
("enable javascript and cookies", "Cloudflare JS 挑战"),
|
||||
("_cf_chl_tk", "Cloudflare Token 特征"),
|
||||
("awswafintegration", "AWS WAF 拦截"),
|
||||
("aws waf", "AWS WAF 拦截"),
|
||||
("captcha", "人机验证码页面"),
|
||||
("recaptcha", "Google reCAPTCHA"),
|
||||
("hcaptcha", "hCaptcha 验证"),
|
||||
("verify you are human", "人机验证提示"),
|
||||
("robot check", "机器人检测"),
|
||||
("login required", "出版商登录墙"),
|
||||
("please log in", "出版商登录墙"),
|
||||
("subscription required", "出版商订阅/付费墙"),
|
||||
("access denied", "拒绝访问/付费墙"),
|
||||
("you do not have access", "无权访问文献"),
|
||||
("purchase this article", "文章付费墙"),
|
||||
("sign in to access", "登录以获取访问权限"),
|
||||
("radware bot manager captcha", "Radware Bot Manager 验证"),
|
||||
("shieldsquare_styles", "ShieldSquare WAF 拦截"),
|
||||
];
|
||||
|
||||
for &(p, desc) in &cf_patterns {
|
||||
if lower.contains(p) {
|
||||
return Some(desc);
|
||||
}
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
// 校验 PDF 完整性与是否为虚假内容
|
||||
fn validate_pdf_content(bytes: &[u8]) -> Result<(), String> {
|
||||
if !bytes.starts_with(b"%PDF") {
|
||||
if bytes.starts_with(b"<!") || bytes.starts_with(b"<html") || bytes.starts_with(b"<HTML") {
|
||||
let scan_len = std::cmp::min(2048, bytes.len());
|
||||
let text = String::from_utf8_lossy(&bytes[..scan_len]);
|
||||
if let Some(desc) = detect_anti_bot(&text) {
|
||||
return Err(format!("虽然文件后缀是 PDF，但实际内容是 HTML（检测到：{}）", desc));
|
||||
}
|
||||
return Err("虽然文件后缀是 PDF，但实际内容是 HTML 网页，可能是重定向或拦截页面".to_string());
|
||||
}
|
||||
return Err("缺少 %PDF 文件头魔数，文件损坏或并非 PDF".to_string());
|
||||
}
|
||||
if bytes.len() < 5000 {
|
||||
return Err(format!("PDF 文件过小（仅 {} 字节），极可能是错误信息页", bytes.len()));
|
||||
}
|
||||
let scan_len = std::cmp::min(1024, bytes.len());
|
||||
let tail = &bytes[bytes.len() - scan_len..];
|
||||
if !tail.windows(5).any(|w| w == b"%%EOF") {
|
||||
return Err("PDF 文件未包含尾部 %%EOF 标记，文件已损坏或不完整".to_string());
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
// 校验 HTML 内容有效性（过滤假网页、存根页、跳转页及摘要页）
|
||||
fn validate_html_content(text: &str) -> Result<(), String> {
|
||||
if let Some(desc) = detect_anti_bot(text) {
|
||||
return Err(format!("检测到安全拦截或登录限制页：{}", desc));
|
||||
}
|
||||
let lower = text.to_lowercase();
|
||||
|
||||
// 1. 检查常见的跳转与错误占位特征
|
||||
if lower.contains("redirecting") || lower.contains("redirect to") || lower.contains("http-equiv=\"refresh\"") || lower.contains("autoredirecttourl") {
|
||||
return Err("检测到 HTML 重定向跳转页面，而非真实文献正文".to_string());
|
||||
}
|
||||
|
||||
if lower.contains("conversion to html had a fatal error") || lower.contains("no content available") || lower.contains("fatal error and exited abruptly") {
|
||||
return Err("检测到 ar5iv 转换失败的占位 HTML 页面".to_string());
|
||||
}
|
||||
|
||||
if lower.contains("see pages 1-last of") {
|
||||
return Err("检测到仅包含 PDF 链接 of 占位 HTML 页面".to_string());
|
||||
}
|
||||
|
||||
// 2. 网页标题精准黑名单校验（防止正文中提及 NSF/VizieR 导致误伤）
|
||||
if let Some(start_pos) = lower.find("<title") {
|
||||
if let Some(tag_end) = lower[start_pos..].find('>') {
|
||||
let title_start = start_pos + tag_end + 1;
|
||||
if let Some(end_pos) = lower[title_start..].find("</title>") {
|
||||
let title = &lower[title_start..title_start + end_pos];
|
||||
if title.contains("nsf award search")
|
||||
|| title.contains("national science foundation")
|
||||
|| title.contains("vizier")
|
||||
|| title.contains("caltechthesis")
|
||||
|| title.contains("caosp abstract")
|
||||
|| title.contains("asp conference series")
|
||||
|| title.contains("aspbooks")
|
||||
{
|
||||
return Err(format!("检测到占位网页标题: \"{}\"，判定为非正本文献", title.trim()));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// 3. 基础字节长度与具体 HTTP 错误特征校验
|
||||
if text.len() < 2000 {
|
||||
let error_patterns = [
|
||||
"404 not found", "403 forbidden", "502 bad gateway",
|
||||
"500 internal server error", "access denied", "site error"
|
||||
];
|
||||
for kw in &error_patterns {
|
||||
if lower.contains(kw) {
|
||||
return Err(format!("HTML 包含错误页面特征（包含: {}）", kw));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// 4. 结构启发式校验：如果是小于 50KB 的 HTML，必须包含基本的章节或参考文献结构，否则判定为摘要/存根占位页
|
||||
if text.len() < 50000 {
|
||||
// 匹配 heading 标签或 Markdown 格式的标题，而不是纯文本中的单词
|
||||
let has_sections = lower.contains("ltx_title_section")
|
||||
|| lower.contains("class=\"section\"")
|
||||
|| lower.contains("## introduction")
|
||||
|| lower.contains("<h2>introduction")
|
||||
|| lower.contains("<h3>introduction")
|
||||
|| lower.contains("class=\"ltx_section\"");
|
||||
let has_bib = lower.contains("ltx_bibliography")
|
||||
|| lower.contains("class=\"references\"")
|
||||
|| lower.contains("<ol class=\"references\"")
|
||||
|| lower.contains("<ul class=\"references\"")
|
||||
|| lower.contains("id=\"bib\"")
|
||||
|| lower.contains("class=\"ltx_bibliography\"");
|
||||
|
||||
if !has_sections && !has_bib {
|
||||
return Err(format!("HTML 长度偏小（{} 字节）且缺少正文章节或参考文献，判定为非正本文献", text.len()));
|
||||
}
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
// 递归扫描目录下的所有物理文件
|
||||
fn scan_directory(dir: &Path, files: &mut Vec<PathBuf>) {
|
||||
if let Ok(entries) = fs::read_dir(dir) {
|
||||
for entry in entries.flatten() {
|
||||
let path = entry.path();
|
||||
if path.is_dir() {
|
||||
scan_directory(&path, files);
|
||||
} else {
|
||||
files.push(path);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::main]
|
||||
async fn main() -> Result<(), Box<dyn std::error::Error>> {
|
||||
// 初始化日志
|
||||
let subscriber = FmtSubscriber::builder()
|
||||
.with_max_level(Level::INFO)
|
||||
.finish();
|
||||
tracing::subscriber::set_global_default(subscriber)?;
|
||||
|
||||
let args: Vec<String> = std::env::args().collect();
|
||||
let fix = args.contains(&"--fix".to_string());
|
||||
|
||||
println!("==================================================");
|
||||
println!(" AstroResearch 馆藏文献健康度检查工具 ");
|
||||
println!("==================================================");
|
||||
if fix {
|
||||
println!("⚠️ 警告：检测到 --fix 参数。程序将自动删除坏文件并将数据库路径重置为 NULL 以便下次重新下载。");
|
||||
} else {
|
||||
println!("ℹ️ 提示：当前处于只读扫描模式。如需自动修复坏文件，请附加 '-- --fix' 参数运行。");
|
||||
}
|
||||
println!("--------------------------------------------------");
|
||||
|
||||
let config = Config::from_env();
|
||||
let library_dir = &config.library_dir;
|
||||
println!("本地文献库目录: {:?}", library_dir);
|
||||
println!("数据库连接串: {}", config.database_url);
|
||||
|
||||
let db_path = config.database_url.replace("sqlite://", "");
|
||||
if !Path::new(&db_path).exists() {
|
||||
error!("找不到 SQLite 数据库文件: {:?}", db_path);
|
||||
return Ok(());
|
||||
}
|
||||
|
||||
let pool = SqlitePool::connect(&config.database_url).await?;
|
||||
println!("成功连接数据库。正在准备进行全面健康检查...");
|
||||
println!("--------------------------------------------------");
|
||||
|
||||
// ─── 阶段 1：磁盘物理文件直接扫描（解决孤儿垃圾文件与坏文件） ───
|
||||
let mut html_files = Vec::new();
|
||||
let mut pdf_files = Vec::new();
|
||||
scan_directory(&library_dir.join("HTML"), &mut html_files);
|
||||
scan_directory(&library_dir.join("PDF"), &mut pdf_files);
|
||||
|
||||
println!("📂 正在扫描物理磁盘文件 (HTML: {} 个, PDF: {} 个)...", html_files.len(), pdf_files.len());
|
||||
|
||||
let mut disk_html_invalid = 0;
|
||||
let mut disk_pdf_invalid = 0;
|
||||
let mut deleted_files = 0;
|
||||
let mut db_updated_count = 0;
|
||||
|
||||
for path in html_files {
|
||||
let rel_path = match path.strip_prefix(library_dir) {
|
||||
Ok(p) => p.to_str().unwrap_or(""),
|
||||
Err(_) => continue,
|
||||
};
|
||||
|
||||
if let Ok(content) = fs::read_to_string(&path) {
|
||||
if let Err(e) = validate_html_content(&content) {
|
||||
disk_html_invalid += 1;
|
||||
println!(" ❌ 发现磁盘上损坏的 HTML 文件: {:?}", rel_path);
|
||||
println!(" 原因: {}", e);
|
||||
|
||||
if fix {
|
||||
let _ = fs::remove_file(&path);
|
||||
deleted_files += 1;
|
||||
println!(" 🧹 [修复] 已物理删除损坏的文件");
|
||||
|
||||
// 检索是否有数据库记录并将其重置
|
||||
let res = sqlx::query("UPDATE papers SET html_path = NULL WHERE html_path = ? OR html_path = ?")
|
||||
.bind(rel_path)
|
||||
.bind(format!("HTML/{}", Path::new(rel_path).file_name().and_then(|f| f.to_str()).unwrap_or("")))
|
||||
.execute(&pool)
|
||||
.await;
|
||||
if let Ok(r) = res {
|
||||
if r.rows_affected() > 0 {
|
||||
db_updated_count += r.rows_affected();
|
||||
println!(" ✅ [修复] 数据库对应状态已重置 (受影响行数: {})", r.rows_affected());
|
||||
}
|
||||
}
|
||||
}
|
||||
println!("--------------------------------------------------");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
for path in pdf_files {
|
||||
let rel_path = match path.strip_prefix(library_dir) {
|
||||
Ok(p) => p.to_str().unwrap_or(""),
|
||||
Err(_) => continue,
|
||||
};
|
||||
|
||||
if let Ok(bytes) = fs::read(&path) {
|
||||
if let Err(e) = validate_pdf_content(&bytes) {
|
||||
disk_pdf_invalid += 1;
|
||||
println!(" ❌ 发现磁盘上损坏的 PDF 文件: {:?}", rel_path);
|
||||
println!(" 原因: {}", e);
|
||||
|
||||
if fix {
|
||||
let _ = fs::remove_file(&path);
|
||||
deleted_files += 1;
|
||||
println!(" 🧹 [修复] 已物理删除损坏的文件");
|
||||
|
||||
let res = sqlx::query("UPDATE papers SET pdf_path = NULL WHERE pdf_path = ? OR pdf_path = ?")
|
||||
.bind(rel_path)
|
||||
.bind(format!("PDF/{}", Path::new(rel_path).file_name().and_then(|f| f.to_str()).unwrap_or("")))
|
||||
.execute(&pool)
|
||||
.await;
|
||||
if let Ok(r) = res {
|
||||
if r.rows_affected() > 0 {
|
||||
db_updated_count += r.rows_affected();
|
||||
println!(" ✅ [修复] 数据库对应状态已重置 (受影响行数: {})", r.rows_affected());
|
||||
}
|
||||
}
|
||||
}
|
||||
println!("--------------------------------------------------");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// ─── 阶段 2：数据库记录校验扫描（检测丢失文件、报错记录与孤立 Markdown） ───
|
||||
println!("🗄️ 正在校验数据库表记录一致性...");
|
||||
let db_rows = sqlx::query(
|
||||
"SELECT bibcode, pdf_path, html_path, title, markdown_path, doctype FROM papers"
|
||||
)
|
||||
.fetch_all(&pool)
|
||||
.await?;
|
||||
|
||||
let mut db_pdf_missing = 0;
|
||||
let mut db_html_missing = 0;
|
||||
let mut db_pdf_err_text = 0;
|
||||
let mut db_html_err_text = 0;
|
||||
let mut db_markdown_missing = 0;
|
||||
let mut db_markdown_orphaned = 0;
|
||||
let mut db_skip_type_cleaned = 0;
|
||||
|
||||
for r in db_rows {
|
||||
let bibcode: String = r.get(0);
|
||||
let pdf_path_opt: Option<String> = r.get(1);
|
||||
let html_path_opt: Option<String> = r.get(2);
|
||||
let title: String = r.get(3);
|
||||
let markdown_path_opt: Option<String> = r.get(4);
|
||||
let doctype_opt: Option<String> = r.get(5);
|
||||
|
||||
let mut need_db_fix = false;
|
||||
let mut pdf_needs_fix = false;
|
||||
let mut html_needs_fix = false;
|
||||
let mut markdown_needs_fix = false;
|
||||
let mut pdf_db_msg = String::new();
|
||||
let mut html_db_msg = String::new();
|
||||
let mut markdown_db_msg = String::new();
|
||||
|
||||
let doctype_str = doctype_opt.unwrap_or_else(|| "article".to_string()).to_lowercase();
|
||||
let is_skip_type = doctype_str == "proposal"
|
||||
|| doctype_str == "abstract"
|
||||
|| doctype_str == "catalog"
|
||||
|| doctype_str == "dataset"
|
||||
|| doctype_str == "software"
|
||||
|| doctype_str == "circular"
|
||||
|| doctype_str == "newsletter"
|
||||
|| doctype_str == "obituary";
|
||||
|
||||
if is_skip_type {
|
||||
let mut has_skip_anomaly = false;
|
||||
if let Some(ref pdf_p) = pdf_path_opt {
|
||||
pdf_db_msg = format!("该文献属于跳过类型 [{}]，但包含下载/报错路径记录: {}", doctype_str, pdf_p);
|
||||
need_db_fix = true;
|
||||
pdf_needs_fix = true;
|
||||
has_skip_anomaly = true;
|
||||
}
|
||||
if let Some(ref html_p) = html_path_opt {
|
||||
html_db_msg = format!("该文献属于跳过类型 [{}]，但包含下载/报错路径记录: {}", doctype_str, html_p);
|
||||
need_db_fix = true;
|
||||
html_needs_fix = true;
|
||||
has_skip_anomaly = true;
|
||||
}
|
||||
if let Some(ref md_p) = markdown_path_opt {
|
||||
markdown_db_msg = format!("该文献属于跳过类型 [{}]，但包含解析路径记录: {}", doctype_str, md_p);
|
||||
need_db_fix = true;
|
||||
markdown_needs_fix = true;
|
||||
has_skip_anomaly = true;
|
||||
}
|
||||
if has_skip_anomaly {
|
||||
db_skip_type_cleaned += 1;
|
||||
}
|
||||
} else {
|
||||
if let Some(ref pdf_p) = pdf_path_opt {
|
||||
if pdf_p.starts_with("error:") {
|
||||
db_pdf_err_text += 1;
|
||||
pdf_db_msg = format!("数据库存储了报错字符串: {}", pdf_p);
|
||||
} else if !library_dir.join(pdf_p).exists() {
|
||||
db_pdf_missing += 1;
|
||||
pdf_db_msg = format!("物理 PDF 文件丢失 (路径: {})", pdf_p);
|
||||
need_db_fix = true;
|
||||
pdf_needs_fix = true;
|
||||
}
|
||||
}
|
||||
|
||||
if let Some(ref html_p) = html_path_opt {
|
||||
if html_p.starts_with("error:") {
|
||||
db_html_err_text += 1;
|
||||
html_db_msg = format!("数据库存储了报错字符串: {}", html_p);
|
||||
} else if !library_dir.join(html_p).exists() {
|
||||
db_html_missing += 1;
|
||||
html_db_msg = format!("物理 HTML 文件丢失 (路径: {})", html_p);
|
||||
need_db_fix = true;
|
||||
html_needs_fix = true;
|
||||
}
|
||||
}
|
||||
|
||||
if let Some(ref md_p) = markdown_path_opt {
|
||||
if !library_dir.join(md_p).exists() {
|
||||
db_markdown_missing += 1;
|
||||
markdown_db_msg = format!("物理 Markdown 文件丢失 (路径: {})", md_p);
|
||||
need_db_fix = true;
|
||||
markdown_needs_fix = true;
|
||||
} else {
|
||||
// 如果 Markdown 物理文件存在，但它既没有有效 PDF 也没有有效 HTML
|
||||
let has_valid_pdf = pdf_path_opt.as_ref()
|
||||
.map(|p| !p.starts_with("error:") && library_dir.join(p).exists())
|
||||
.unwrap_or(false);
|
||||
let has_valid_html = html_path_opt.as_ref()
|
||||
.map(|p| !p.starts_with("error:") && library_dir.join(p).exists())
|
||||
.unwrap_or(false);
|
||||
|
||||
if !has_valid_pdf && !has_valid_html {
|
||||
db_markdown_orphaned += 1;
|
||||
markdown_db_msg = format!("Markdown 存在且完好，但失去有效 PDF/HTML 数据源，判定为孤立的 Markdown (路径: {})", md_p);
|
||||
need_db_fix = true;
|
||||
markdown_needs_fix = true;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if need_db_fix {
|
||||
println!(" ❌ 发现馆藏文献记录损坏/不一致 [{}] 《{}》", bibcode, title);
|
||||
|
||||
if !pdf_db_msg.is_empty() {
|
||||
if pdf_needs_fix {
|
||||
println!(" [异常] PDF 状态: {}", pdf_db_msg);
|
||||
} else {
|
||||
println!(" [日志] PDF 历史下载失败原因: {}", pdf_db_msg.replace("数据库存储了报错字符串: ", ""));
|
||||
}
|
||||
}
|
||||
if !html_db_msg.is_empty() {
|
||||
if html_needs_fix {
|
||||
println!(" [异常] HTML 状态: {}", html_db_msg);
|
||||
} else {
|
||||
println!(" [日志] HTML 历史下载失败原因: {}", html_db_msg.replace("数据库存储了报错字符串: ", ""));
|
||||
}
|
||||
}
|
||||
if !markdown_db_msg.is_empty() {
|
||||
println!(" [异常] Markdown 状态: {}", markdown_db_msg);
|
||||
}
|
||||
|
||||
if fix {
|
||||
let mut sql_parts = Vec::new();
|
||||
if pdf_needs_fix {
|
||||
sql_parts.push("pdf_path = NULL");
|
||||
if let Some(ref pdf_p) = pdf_path_opt {
|
||||
if !pdf_p.starts_with("error:") {
|
||||
let pdf_abs = library_dir.join(pdf_p);
|
||||
if pdf_abs.exists() {
|
||||
let _ = fs::remove_file(&pdf_abs);
|
||||
deleted_files += 1;
|
||||
println!(" 🧹 [修复] 已物理删除跳过类型或丢失的 PDF 文件");
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
if html_needs_fix {
|
||||
sql_parts.push("html_path = NULL");
|
||||
if let Some(ref html_p) = html_path_opt {
|
||||
if !html_p.starts_with("error:") {
|
||||
let html_abs = library_dir.join(html_p);
|
||||
if html_abs.exists() {
|
||||
let _ = fs::remove_file(&html_abs);
|
||||
deleted_files += 1;
|
||||
println!(" 🧹 [修复] 已物理删除跳过类型或丢失的 HTML 文件");
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
if markdown_needs_fix {
|
||||
sql_parts.push("markdown_path = NULL");
|
||||
if let Some(ref md_p) = markdown_path_opt {
|
||||
let md_abs = library_dir.join(md_p);
|
||||
if md_abs.exists() {
|
||||
let _ = fs::remove_file(&md_abs);
|
||||
deleted_files += 1;
|
||||
println!(" 🧹 [修复] 已物理删除孤立或跳过类型的 Markdown 文件");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if !sql_parts.is_empty() {
|
||||
let query_str = format!("UPDATE papers SET {} WHERE bibcode = ?", sql_parts.join(", "));
|
||||
let res = sqlx::query(&query_str)
|
||||
.bind(&bibcode)
|
||||
.execute(&pool)
|
||||
.await;
|
||||
if res.is_ok() {
|
||||
db_updated_count += 1;
|
||||
println!(" ✅ [修复] 数据库损坏字段已成功重置");
|
||||
}
|
||||
}
|
||||
}
|
||||
println!("--------------------------------------------------");
|
||||
}
|
||||
}
|
||||
|
||||
println!("\n==================================================");
|
||||
println!(" 全面健康度检测扫描报告 ");
|
||||
println!("==================================================");
|
||||
println!("磁盘物理损坏统计:");
|
||||
println!(" - 损坏/假 HTML 文件数: {}", disk_html_invalid);
|
||||
println!(" - 损坏/假 PDF 文件数: {}", disk_pdf_invalid);
|
||||
println!("--------------------------------------------------");
|
||||
println!("数据库一致性统计:");
|
||||
println!(" - 数据库记录下载失败数 (error:): PDF: {}, HTML: {}", db_pdf_err_text, db_html_err_text);
|
||||
println!(" - 磁盘文件丢失数 (数据库有记录但文件不存在): PDF: {}, HTML: {}, Markdown: {}", db_pdf_missing, db_html_missing, db_markdown_missing);
|
||||
println!(" - 孤立无源 Markdown 篇数: {}", db_markdown_orphaned);
|
||||
println!(" - 需跳过类型但包含下载记录篇数 (已清理/待清理): {}", db_skip_type_cleaned);
|
||||
println!("--------------------------------------------------");
|
||||
if fix {
|
||||
println!("✨ 修复完成！");
|
||||
println!(" - 共删除磁盘物理损坏/孤立/跳过类型文件: {} 个", deleted_files);
|
||||
println!(" - 共重置修复数据库文献字段: {} 处", db_updated_count);
|
||||
} else {
|
||||
let total_issues = disk_html_invalid + disk_pdf_invalid + db_pdf_missing + db_html_missing + db_markdown_missing + db_markdown_orphaned + db_skip_type_cleaned;
|
||||
if total_issues > 0 {
|
||||
println!("❌ 警告：共检测出 {} 处坏文件、丢失文件或异常数据库记录。", total_issues);
|
||||
println!("👉 您可以附加 '-- --fix' 执行一键全面修复：");
|
||||
println!(" cargo run --bin health_check -- --fix");
|
||||
} else {
|
||||
println!("🎉 恭喜！馆藏物理文件及数据库完全健康，未检测到任何损坏或失效记录！");
|
||||
}
|
||||
}
|
||||
println!("==================================================");
|
||||
|
||||
Ok(())
|
||||
}
|
||||
Reference in New Issue
Block a user