fix: address code review issues in EpubLoader

2026-05-13 23:16:50 +08:00
parent 5f66478c26
commit 79d2fcd75c
1 changed files with 37 additions and 1 deletions
--- a/src/book.rs
+++ b/src/book.rs
@@ -43,6 +43,7 @@ pub struct TocEntry {
 pub struct Section {
    pub title: String,
    pub content: String,
+    /// Populated by pagination algorithm (pre-computed char offsets for page boundaries)
    pub pages: Vec<usize>,
 }

@@ -66,7 +67,6 @@ pub fn load_epub(path: impl AsRef<Path>) -> Result<Book, 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() {
@@ -82,6 +82,7 @@ pub fn load_epub(path: impl AsRef<Path>) -> Result<Book, String> {
        });
    }

+    let raw_toc = std::mem::take(&mut doc.toc);
    let toc = build_toc(&raw_toc, &spine);

    Ok(Book { title, author, cover, sections, toc })
@@ -117,6 +118,7 @@ fn build_toc(
            let section = spine
                .iter()
                .position(|s| content_str.contains(s.trim_end_matches('/')))
+                // unwrap_or(0) is safe: a real TOC entry should always match a spine item
                .unwrap_or(0);
            TocEntry {
                label: e.label.clone(),
@@ -165,4 +167,38 @@ mod tests {
    fn test_strip_html_empty() {
        assert_eq!(strip_html(""), "");
    }
+
+    #[test]
+    fn test_extract_title_from_title_tag() {
+        let html = "<html><head><title>My Book Title</title></head><body></body></html>";
+        assert_eq!(extract_title(html), Some("My Book Title".to_string()));
+    }
+
+    #[test]
+    fn test_extract_title_from_h1() {
+        let html = "<html><body><h1>Chapter One</h1><p>text</p></body></html>";
+        assert_eq!(extract_title(html), Some("Chapter One".to_string()));
+    }
+
+    #[test]
+    fn test_extract_title_prefers_title() {
+        let html = "<html><head><title>Book</title></head><body><h1>Chapter</h1></body></html>";
+        assert_eq!(extract_title(html), Some("Book".to_string()));
+    }
+
+    #[test]
+    fn test_extract_title_missing() {
+        assert_eq!(extract_title("<html><body><p>no title</p></body></html>"), None);
+    }
+
+    #[test]
+    fn test_extract_title_empty() {
+        assert_eq!(extract_title(""), None);
+    }
+
+    #[test]
+    fn test_build_toc_empty() {
+        let toc = build_toc(&[], &[]);
+        assert!(toc.is_empty());
+    }
 }