Implement EpubLoader with load_epub, extract_title, and build_toc functions

src/book.rs

@@ -55,10 +55,88 @@ pub struct Book {
     pub toc: Vec<TocEntry>,
 }
 
+use std::path::Path;
+
+pub fn load_epub(path: impl AsRef<Path>) -> Result<Book, String> {
+    let path = path.as_ref();
+    let mut doc = epub::doc::EpubDoc::new(path)
+        .map_err(|e| format!("无法打开文件: {}", e))?;
+
+    let title = doc.mdata("title").unwrap_or_else(|| "未知标题".to_string());
+    let author = doc.mdata("creator").unwrap_or_else(|| "未知作者".to_string());
+    let cover = doc.get_cover().ok();
+    let spine = doc.spine.clone();
+    let raw_toc = std::mem::take(&mut doc.toc);
+
+    let mut sections = Vec::new();
+    for (i, href) in spine.iter().enumerate() {
+        let raw_html = doc.get_resource_str(href)
+            .map_err(|e| format!("读取章节失败: {}", e))?;
+        let text = strip_html(&raw_html);
+        let title = extract_title(&raw_html)
+            .unwrap_or_else(|| format!("第{}章", i + 1));
+        sections.push(Section {
+            title,
+            content: text,
+            pages: Vec::new(),
+        });
+    }
+
+    let toc = build_toc(&raw_toc, &spine);
+
+    Ok(Book { title, author, cover, sections, toc })
+}
+
+fn extract_title(html: &str) -> Option<String> {
+    if let Some(start) = html.find("<title>") {
+        let rest = &html[start + 7..];
+        if let Some(end) = rest.find("</title>") {
+            return Some(strip_html(&rest[..end]).trim().to_string());
+        }
+    }
+    if let Some(start) = html.find("<h1") {
+        let rest = &html[start..];
+        if let Some(content_start) = rest.find('>') {
+            let inner = &rest[content_start + 1..];
+            if let Some(end) = inner.find("</h1>") {
+                return Some(strip_html(&inner[..end]).trim().to_string());
+            }
+        }
+    }
+    None
+}
+
+fn build_toc(
+    entries: &[epub::doc::NavPoint],
+    spine: &[String],
+) -> Vec<TocEntry> {
+    entries
+        .iter()
+        .map(|e| {
+            let content_str = e.content.to_string_lossy();
+            let section = spine
+                .iter()
+                .position(|s| content_str.contains(s.trim_end_matches('/')))
+                .unwrap_or(0);
+            TocEntry {
+                label: e.label.clone(),
+                section,
+                children: build_toc(&e.children, spine),
+            }
+        })
+        .collect()
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
 
+    #[test]
+    fn test_epub_loader_nonexistent_file() {
+        let result = load_epub("nonexistent.epub");
+        assert!(result.is_err());
+    }
+
     #[test]
     fn test_strip_html_plain_text() {
         assert_eq!(strip_html("Hello World"), "Hello World");