AstroResearch/src/services/batch/asset/helpers.rs

// src/services/batch/asset/helpers.rs
//
// 批量处理各步骤的独立函数，从 process_single_bibcode 提取，
// 降低单文件行数并提高可测试性。

use std::sync::atomic::{AtomicI32, Ordering};
use std::sync::Arc;

use sqlx::SqlitePool;
use tokio::sync::Mutex;

use crate::services::download::Downloader;
use crate::Config;

use super::{AssetBatchStatus, BatchAction};

/// 执行单篇文献的下载步骤。
///
/// 若成功下载 PDF 或 HTML 任一格式，更新 `pdf_path` / `html_path` 并写回数据库。
/// 返回 true 表示下载成功（至少一个文件），false 表示全部失败。
#[allow(clippy::too_many_arguments)]
pub(super) async fn run_download_step(
    bibcode: &str,
    action: BatchAction,
    db: &SqlitePool,
    config: &Config,
    downloader: &Arc<Downloader>,
    status: &Arc<Mutex<AssetBatchStatus>>,
    dl_count: &AtomicI32,
    dl_failed_count: &AtomicI32,
    arxiv_id: &str,
    doi: &str,
    pdf_path: &mut Option<String>,
    html_path: &mut Option<String>,
) -> bool {
    // 仅当 action 包含下载时执行
    if action != BatchAction::Download && action != BatchAction::All {
        return true; // 无需下载，视为"成功"
    }

    let is_pdf_exist = pdf_path
        .as_ref()
        .map(|p| config.library_dir.join(p).exists())
        .unwrap_or(false);
    let is_html_exist = html_path
        .as_ref()
        .map(|p| config.library_dir.join(p).exists())
        .unwrap_or(false);

    if is_pdf_exist || is_html_exist {
        {
            let mut s = status.lock().await;
            s.add_log(format!(
                "文献 {} 本地已存在 PDF 或 HTML，跳过下载。",
                bibcode
            ));
        }
        let _c = dl_count.fetch_add(1, Ordering::SeqCst) + 1;
        {
            let mut s = status.lock().await;
            s.downloaded = _c;
        }
        return true;
    }

    // 需要执行下载
    {
        let mut s = status.lock().await;
        s.add_log(format!("文献 {} 本地无 PDF/HTML，开始下载...", bibcode));
    }

    let (pdf_res, html_res) = if !arxiv_id.is_empty() {
        let res = downloader
            .download_arxiv_direct(arxiv_id, &config.library_dir)
            .await;
        if res.0.is_ok() || res.1.is_ok() {
            res
        } else {
            {
                let mut s = status.lock().await;
                s.add_log(format!(
                    "文献 {} arXiv 通道下载失败，回退尝试 ADS/出版商下载...",
                    bibcode
                ));
            }
            let doi_opt = if !doi.is_empty() { Some(doi) } else { None };
            downloader
                .download_paper(bibcode, doi_opt, &config.library_dir)
                .await
        }
    } else {
        let doi_opt = if !doi.is_empty() { Some(doi) } else { None };
        downloader
            .download_paper(bibcode, doi_opt, &config.library_dir)
            .await
    };

    if pdf_res.is_ok() || html_res.is_ok() {
        let pdf_rel = match pdf_res {
            Ok(p) => Some(
                p.strip_prefix(&config.library_dir)
                    .unwrap_or(&p)
                    .to_string_lossy()
                    .to_string(),
            ),
            Err(_) => None,
        };
        let html_rel = match html_res {
            Ok(p) => Some(
                p.strip_prefix(&config.library_dir)
                    .unwrap_or(&p)
                    .to_string_lossy()
                    .to_string(),
            ),
            Err(_) => None,
        };

        *pdf_path = pdf_rel.clone();
        *html_path = html_rel.clone();

        let _ = sqlx::query("UPDATE papers SET pdf_path = ?, html_path = ? WHERE bibcode = ?")
            .bind(pdf_rel)
            .bind(html_rel)
            .bind(bibcode)
            .execute(db)
            .await;

        let _c = dl_count.fetch_add(1, Ordering::SeqCst) + 1;
        {
            let mut s = status.lock().await;
            s.downloaded = _c;
            s.add_log(format!("文献 {} 下载成功！", bibcode));
        }
        true
    } else {
        let _f = dl_failed_count.fetch_add(1, Ordering::SeqCst) + 1;
        let mut s = status.lock().await;
        s.download_failed = _f;

        let pdf_err = match pdf_res {
            Err(e) => format!("error: {}", e),
            _ => "error: 未知错误".to_string(),
        };
        let html_err = match html_res {
            Err(e) => format!("error: {}", e),
            _ => "error: 未知错误".to_string(),
        };

        s.add_log(format!(
            "文献 {} 下载失败。PDF: {}, HTML: {}",
            bibcode, pdf_err, html_err
        ));

        let _ = sqlx::query("UPDATE papers SET pdf_path = ?, html_path = ? WHERE bibcode = ?")
            .bind(&pdf_err)
            .bind(&html_err)
            .bind(bibcode)
            .execute(db)
            .await;

        false
    }
}

/// 生成文献的源链接 URL（优先 ADS 标准 bibcode，其次 arXiv）。
pub(super) fn build_source_url(bibcode: &str, arxiv_id: &str) -> String {
    if bibcode.len() == 19 {
        format!("https://ui.adsabs.harvard.edu/abs/{}/abstract", bibcode)
    } else if !arxiv_id.is_empty() {
        format!(
            "https://ui.adsabs.harvard.edu/abs/arXiv:{}/abstract",
            arxiv_id
        )
    } else {
        format!("https://ui.adsabs.harvard.edu/abs/{}/abstract", bibcode)
    }
}

/// 为已解析的 Markdown 内容构建 YAML frontmatter 头部。
pub(super) async fn build_markdown_with_frontmatter(
    db: &SqlitePool,
    bibcode: &str,
    md_body: &str,
    source_url: &str,
) -> Option<String> {
    use sqlx::Row;

    let row =
        sqlx::query("SELECT title, authors, pub, year, keywords FROM papers WHERE bibcode = ?")
            .bind(bibcode)
            .fetch_optional(db)
            .await
            .ok()??;

    let title: String = row.get(0);
    let authors_json: String = row.get(1);
    let pub_journal: String = row.get(2);
    let year: String = row.get(3);
    let keywords_json: String = row.get(4);

    let authors: Vec<String> = serde_json::from_str(&authors_json).unwrap_or_default();
    let keywords: Vec<String> = serde_json::from_str(&keywords_json).unwrap_or_default();

    let front_matter = format!(
        "---\ntitle: {}\nauthor: [{}]\npublisher: {}\nsource: \"{}\"\ndate: \"{}\"\ntags: \"{}\"\n---\n\n",
        serde_json::to_string(&title).unwrap_or_else(|_| format!("\"{}\"", title)),
        authors
            .iter()
            .map(|a| format!("\"{}\"", a))
            .collect::<Vec<_>>()
            .join(", "),
        serde_json::to_string(&pub_journal)
            .unwrap_or_else(|_| format!("\"{}\"", pub_journal)),
        source_url,
        year,
        keywords.join(",")
    );

    Some(format!("{}{}", front_matter, md_body))
}

/// 将 Markdown 内容写入 library_dir 并更新数据库 markdown_path。
pub(super) fn write_markdown_and_update_db(
    config: &Config,
    bibcode: &str,
    content: &str,
) -> Option<String> {
    let md_filename = format!("{}.md", bibcode);
    let md_dest = config.library_dir.join("Markdown").join(&md_filename);
    if let Some(parent) = md_dest.parent() {
        let _ = std::fs::create_dir_all(parent);
    }
    if std::fs::write(&md_dest, content).is_ok() {
        Some(format!("Markdown/{}", md_filename))
    } else {
        None
    }
}