AstroResearch/recovered_handlers.rs

// src/handlers.rs
use axum::{
    extract::{Query, State},
    http::StatusCode,
    Json,
};
use serde::{Deserialize, Serialize};
use std::sync::Arc;
use std::fs;
use tracing::{info, warn, error};
use sqlx::{SqlitePool, Row};

use crate::config::Config;
use crate::translation::Dictionary;
use crate::qiniu::QiniuClient;
use crate::ads::{AdsClient, AdsPaperDoc};
use crate::arxiv::{ArxivClient, ArxivPaper};
use crate::download::Downloader;

// 全局共享的 Axum 应用上下文状态
pub struct AppState {
    pub config: Config,
    pub db: SqlitePool,
    pub dict: Dictionary,
    pub qiniu: QiniuClient,
    pub ads: AdsClient,
    pub arxiv: ArxivClient,
    pub downloader: Downloader,
    pub harvest_status: Arc<tokio::sync::Mutex<crate::harvester::HarvestStatus>>,
    pub process_status: Arc<tokio::sync::Mutex<crate::processor::ProcessStatus>>,
}

// 检索请求参数
#[derive(Debug, Deserialize)]
pub struct SearchParams {
    pub q: String,
    pub source: Option<String>, // "all" | "ads" | "arxiv"
    pub rows: Option<i32>,
    pub start: Option<i32>,      // 分页起始偏移量
    pub sort: Option<String>,    // 排序字段，例如 "date_desc", "citations_desc", "relevance"
}

// 统一标准化的文献格式，用于向前端传输
#[derive(Debug, Serialize, Deserialize, Clone)]
pub struct StandardPaper {
    pub bibcode: String,
    pub title: String,
    pub authors: Vec<String>,






























































































































































































































































































































































































































































































































































































































































































































    let doi = doc.doi.as_ref()
        .and_then(|v: &Vec<String>| v.first())
        .cloned()
        .unwrap_or_default();
    
    let mut arxiv_id = String::new();
    if let Some(identifiers) = &doc.identifier {
        for id in identifiers {
            if id.starts_with("arXiv:") {
                arxiv_id = id.replace("arXiv:", "").trim().to_string();
                break;
            }
        }
    }
    if arxiv_id.is_empty() {
        if doc.bibcode.starts_with("arXiv") {
            arxiv_id = doc.bibcode.replace("arXiv", "").trim().to_string();
        }
    }

    StandardPaper {
        bibcode: doc.bibcode.clone(),
        title,
        authors,
        year: doc.year.clone().unwrap_or_default(),
        pub_journal: doc.pub_journal.clone().unwrap_or_default(),
        keywords,
        abstract_text: doc.abstract_text.clone().unwrap_or_default(),
        doi,
        arxiv_id,
        citation_count: doc.citation_count.unwrap_or(0),
        reference_count: doc.reference_count.unwrap_or(0),
        is_downloaded: false,
        has_markdown: false,
        has_translation: false,
    }
}

pub(crate) fn convert_arxiv_to_standard(doc: &ArxivPaper) -> StandardPaper {
    StandardPaper {
        bibcode: doc.id.clone(),
        title: doc.title.clone(),
        authors: doc.authors.clone(),
        year: doc.year.clone(),
        pub_journal: "arXiv Preprint".to_string(),
        keywords: Vec::new(),
        abstract_text: doc.abstract_text.clone(),
        doi: doc.doi.clone().unwrap_or_default(),
        arxiv_id: doc.id.clone(),
        citation_count: 0,
        reference_count: 0,
        is_downloaded: false,
        has_markdown: false,
        has_translation: false,
    }
}

pub(crate) async fn save_paper_to_db(db: &SqlitePool, p: &StandardPaper) -> anyhow::Result<()> {
    let authors_json = serde_json::to_string(&p.authors)?;
    let keywords_json = serde_json::to_string(&p.keywords)?;

    // 1. 如果存在 arxiv_id，检查是否有已存在的相同 arxiv_id 记录以防 duplicate
    if !p.arxiv_id.is_empty() {
        let existing_opt: Option<(String, Option<String>, Option<String>, Option<String>, Option<String>)> = sqlx::query_as(
            "SELECT bibcode, pdf_path, html_path, markdown_path, translation_path FROM papers WHERE arxiv_id = ?"
        )
        .bind(&p.arxiv_id)
        .fetch_optional(db)
        .await?;

        if let Some((existing_bibcode, _pdf, _html, _md, _tr)) = existing_opt {
            if existing_bibcode != p.bibcode {
                // 发现不同 bibcode 标识的同一篇文献记录，需要进行合并合并
                // 如果已存在的记录使用的是临时 arXiv ID 作为 bibcode，且新记录使用的是正式 ADS bibcode，我们升级 bibcode 主键
                let is_existing_temp = existing_bibcode == p.arxiv_id;
                let is_new_formal = p.bibcode != p.arxiv_id;

                if is_existing_temp && is_new_formal {
                    info!("发现相同 arXiv ID 的











































































































































































































































































































































































































            .await?;

        // 运行迁移
        sqlx::migrate!("./migrations")
            .run(&pool)
            .await?;

        let paper = StandardPaper {
            bibcode: "2026A&A...123..456X".to_string(),
            title: "A Test Title".to_string(),
            authors: vec!["Author A".to_string()],
            year: "2026".to_string(),
            pub_journal: "Astronomy & Astrophysics".to_string(),
            keywords: vec!["Keyword 1".to_string()],
            abstract_text: "This is abstract".to_string(),
            doi: "10.1000/test.doi".to_string(),
            arxiv_id: "".to_string(),
            citation_count: 5,
            reference_count: 10,
            is_downloaded: false,
            has_markdown: false,
            has_translation: false,
        };

        // 保存
        save_paper_to_db(&pool, &paper).await?;

        // 读取
        let retrieved = get_paper_from_db(&pool, std::path::Path::new(""), "2026A&A...123..456X").await?;
        assert_eq!(retrieved.title, paper.title);
        assert_eq!(retrieved.authors, paper.authors);
        assert_eq!(retrieved.keywords, paper.keywords);

        // 检查路径状态（初始为 None）
        let paths = check_paper_paths_in_db(&pool, std::path::Path::new(""), "2026A&A...123..456X").await?;
        assert!(paths.is_some());
        let (pdf, html, md, tr) = paths.unwrap();
        assert!(pdf.is_none());
        assert!(html.is_none());
        assert!(md.is_none());
        assert!(tr.is_none());

        Ok(())
    }
}