fix title extraction and epub errors

ebookm-core/src/epub.rs

@@ -3,6 +3,7 @@ use std::fs::File;
 use std::io::Write;
 use std::path::Path;
 
+use chrono::Utc;
 use quick_xml::escape::escape;
 use zip::CompressionMethod;
 use zip::write::{SimpleFileOptions, ZipWriter};
@@ -181,11 +182,16 @@ fn build_ncx(manifest: &crate::manifest::Manifest, built: &[BuiltEntry]) -> Stri
         let section_play_order = play_order;
         play_order += 1;
 
+        let section_target = section_entries[0]
+            .section_anchor
+            .as_ref()
+            .map(|anchor| format!("text/{}.xhtml#{}", section_entries[0].id, anchor))
+            .unwrap_or_else(|| format!("text/{}.xhtml", section_entries[0].id));
         let mut child_points = String::new();
         for entry in &section_entries {
             child_points.push_str(&format!(
                 "<navPoint id=\"nav-{}\" playOrder=\"{}\"><navLabel><text>{}</text></navLabel><content src=\"text/{}.xhtml\"/></navPoint>",
-                escape(&entry.id),
+                escape(&xml_id("nav", &entry.id)),
                 play_order,
                 escape(&entry.chapter.nav_title),
                 escape(&entry.id)
@@ -194,11 +200,11 @@ fn build_ncx(manifest: &crate::manifest::Manifest, built: &[BuiltEntry]) -> Stri
         }
 
         nav_points.push_str(&format!(
-            "<navPoint id=\"section-{}\" playOrder=\"{}\"><navLabel><text>{}</text></navLabel><content src=\"text/{}.xhtml\"/>{}</navPoint>",
-            escape(&section.id),
+            "<navPoint id=\"{}\" playOrder=\"{}\"><navLabel><text>{}</text></navLabel><content src=\"{}\"/>{}</navPoint>",
+            escape(&xml_id("section", &section.id)),
             section_play_order,
             escape(&section.title),
-            escape(&section_entries[0].id),
+            escape(&section_target),
             child_points
         ));
     }
@@ -233,14 +239,17 @@ fn build_opf(
     for entry in built {
         manifest_items.push_str(&format!(
             "<item id=\"{}\" href=\"text/{}.xhtml\" media-type=\"application/xhtml+xml\"/>",
-            escape(&entry.id),
+            escape(&xml_id("entry", &entry.id)),
             escape(&entry.id)
         ));
-        spine_items.push_str(&format!("<itemref idref=\"{}\"/>", escape(&entry.id)));
+        spine_items.push_str(&format!(
+            "<itemref idref=\"{}\"/>",
+            escape(&xml_id("entry", &entry.id))
+        ));
         for asset in &entry.assets {
             manifest_items.push_str(&format!(
                 "<item id=\"{}\" href=\"{}\" media-type=\"{}\"/>",
-                escape(&asset.id),
+                escape(&xml_id("asset", &asset.id)),
                 escape(&asset.href),
                 escape(&asset.media_type)
             ));
@@ -249,8 +258,9 @@ fn build_opf(
 
     if let Some(cover_href) = cover_href {
         manifest_items.push_str(&format!(
-            "<item id=\"cover\" href=\"{}\" media-type=\"image/jpeg\" properties=\"cover-image\"/>",
-            escape(cover_href)
+            "<item id=\"cover\" href=\"{}\" media-type=\"{}\" properties=\"cover-image\"/>",
+            escape(cover_href),
+            escape(&media_type_from_href(cover_href))
         ));
     }
 
@@ -260,6 +270,7 @@ fn build_opf(
         .clone()
         .unwrap_or_else(|| "Unknown".to_string());
     let description = manifest.book.description.clone().unwrap_or_default();
+    let modified = Utc::now().format("%Y-%m-%dT%H:%M:%SZ").to_string();
     format!(
         r#"<?xml version="1.0" encoding="UTF-8"?>
 <package version="3.0" xmlns="http://www.idpf.org/2007/opf" unique-identifier="bookid">
@@ -269,6 +280,7 @@ fn build_opf(
     <dc:creator>{}</dc:creator>
     <dc:language>{}</dc:language>
     <dc:description>{}</dc:description>
+    <meta property="dcterms:modified">{}</meta>
   </metadata>
   <manifest>{}</manifest>
   <spine toc="ncx">{}</spine>
@@ -278,11 +290,42 @@ fn build_opf(
         escape(&author),
         escape(&manifest.book.language),
         escape(&description),
+        escape(&modified),
         manifest_items,
         spine_items
     )
 }
 
+fn xml_id(prefix: &str, value: &str) -> String {
+    let mut id = String::with_capacity(prefix.len() + value.len() + 1);
+    id.push_str(prefix);
+    id.push('-');
+    for ch in value.chars() {
+        if ch.is_ascii_alphanumeric() || matches!(ch, '_' | '-' | '.') {
+            id.push(ch);
+        } else {
+            id.push('-');
+        }
+    }
+    id
+}
+
+fn media_type_from_href(href: &str) -> String {
+    match href.rsplit('.').next().map(|ext| ext.to_ascii_lowercase()) {
+        Some(extension) => match extension.as_str() {
+            "jpg" | "jpeg" => "image/jpeg",
+            "png" => "image/png",
+            "gif" => "image/gif",
+            "svg" => "image/svg+xml",
+            "webp" => "image/webp",
+            "avif" => "image/avif",
+            _ => "application/octet-stream",
+        }
+        .to_string(),
+        None => "application/octet-stream".to_string(),
+    }
+}
+
 const CONTAINER_XML: &str = r#"<?xml version="1.0" encoding="UTF-8"?>
 <container version="1.0" xmlns="urn:oasis:names:tc:opendocument:xmlns:container">
   <rootfiles>