fix title extraction and epub errors

ageofpeace/ageofpeace.yaml

@@ -2,7 +2,7 @@ book:
   title: "Age of Peace"
   author: "John Gu"
   language: "en"
-  identifier: "urn:uuid:ageofpeace:johngu"
+  identifier: "urn:book:ageofpeace:johngu"
   description: "Age of Peace: a novel"
 
 output:
@@ -36,7 +36,9 @@ sections:
       - "biridana"
   - id: "part-3"
     title: "Nameless Country"
-    entries: []
+    entries:
+      - "in_the_east"
+      - "finale"
       
 
 entries:
@@ -79,7 +81,7 @@ entries:
   finale:
     source:
       kind: "substack"
-      url: "https://ageofpeace.substack.com/p/finale"
+      url: "https://ageofpeace.substack.com/p/age-of-peace"
     toc:
       title: "Finale"
     processing:

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>",
+            "<navPoint id=\"{}\" playOrder=\"{}\"><navLabel><text>{}</text></navLabel><content src=\"{}\"/>{}</navPoint>",
-            escape(&section.id),
+            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\"/>",
+            "<item id=\"cover\" href=\"{}\" media-type=\"{}\" properties=\"cover-image\"/>",
-            escape(cover_href)
+            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>

ebookm-core/src/extract.rs

@@ -26,25 +26,7 @@ pub struct InspectResult {
 pub fn extract_article(loaded: &LoadedSource) -> Result<ExtractedArticle> {
     let document = Html::parse_document(&loaded.html);
     let json_ld = extract_primary_json_ld(&document);
-    let title = select_content(
+    let title = extract_title(&document, &json_ld).ok_or_else(|| EbookmError::Extraction {
-        &document,
-        &[
-            r#"meta[property="og:title"]"#,
-            r#"article .post-title"#,
-            ".post-title",
-            "h1",
-            "title",
-        ],
-        "content",
-    )
-    .or_else(|| {
-        select_text(
-            &document,
-            &[r#"article .post-title"#, ".post-title", "h1", "title"],
-        )
-    })
-    .or_else(|| json_ld_string(&json_ld, "headline"))
-    .ok_or_else(|| EbookmError::Extraction {
         input: origin_label(&loaded.origin),
     })?;
 
@@ -131,6 +113,20 @@ fn select_content(document: &Html, selectors: &[&str], attr: &str) -> Option<Str
     })
 }
 
+fn extract_title(document: &Html, json_ld: &Option<Value>) -> Option<String> {
+    select_text(
+        document,
+        &[
+            "h1.post-title",
+            ".post-title",
+            r#"article .post-title"#,
+            "title",
+            "h1",
+        ],
+    )
+    .or_else(|| json_ld_string(json_ld, "headline"))
+}
+
 fn select_text(document: &Html, selectors: &[&str]) -> Option<String> {
     selectors.iter().find_map(|selector| {
         let selector = Selector::parse(selector).ok()?;
@@ -205,7 +201,11 @@ fn json_ld_string(json_ld: &Option<Value>, key: &str) -> Option<String> {
 
 fn json_ld_author(json_ld: &Option<Value>) -> Option<String> {
     let author = json_ld.as_ref()?.get("author")?;
-    if let Some(author_name) = author.get(0).and_then(|entry| entry.get("name")).and_then(Value::as_str) {
+    if let Some(author_name) = author
+        .get(0)
+        .and_then(|entry| entry.get("name"))
+        .and_then(Value::as_str)
+    {
         return Some(author_name.to_string());
     }
     if let Some(author_name) = author.get("name").and_then(Value::as_str) {
@@ -255,7 +255,7 @@ mod tests {
         };
 
         let extracted = extract_article(&loaded).expect("extract article");
-        assert_eq!(extracted.title, "A Contested Island");
+        assert_eq!(extracted.title, "Chapter 1: A Contested Island");
         assert_eq!(extracted.author.as_deref(), Some("John Gu"));
         assert_eq!(
             extracted.published,

ebookm-core/src/normalize.rs

@@ -3,6 +3,7 @@ use std::path::Path;
 
 use kuchiki::traits::*;
 use regex::Regex;
+use reqwest::header::CONTENT_TYPE;
 use sha1::{Digest, Sha1};
 use url::Url;
 
@@ -159,12 +160,18 @@ fn fetch_local_asset(base_path: &Path, src: &str) -> Result<Asset> {
 }
 
 fn fetch_remote_asset(url: &Url) -> Result<Asset> {
-    let bytes = reqwest::blocking::get(url.clone())
+    let response = reqwest::blocking::get(url.clone())
         .and_then(|response| response.error_for_status())
         .map_err(|source| EbookmError::Request {
             url: url.to_string(),
             source,
-        })?
+        })?;
+    let content_type = response
+        .headers()
+        .get(CONTENT_TYPE)
+        .and_then(|value| value.to_str().ok())
+        .map(|value| value.to_string());
+    let bytes = response
         .bytes()
         .map_err(|source| EbookmError::Request {
             url: url.to_string(),
@@ -172,7 +179,7 @@ fn fetch_remote_asset(url: &Url) -> Result<Asset> {
         })?
         .to_vec();
 
-    let extension = infer_extension_from_str(url.path());
+    let extension = infer_extension_from_response(url.path(), content_type.as_deref(), &bytes);
     let media_type = infer_media_type(&extension);
     let digest = Sha1::digest(url.as_str().as_bytes());
     let id = format!("{:x}", digest);
@@ -189,7 +196,8 @@ fn build_asset_from_path(path: &Path) -> Result<Asset> {
         path: path.display().to_string(),
         source,
     })?;
-    let extension = infer_extension_from_path(path);
+    let path_extension = infer_extension_from_path(path);
+    let extension = infer_extension_from_bytes(Some(path_extension.as_str()), &bytes);
     let media_type = infer_media_type(&extension);
     let digest = Sha1::digest(path.display().to_string().as_bytes());
     let id = format!("{:x}", digest);
@@ -292,8 +300,8 @@ fn infer_extension_from_path(path: &Path) -> String {
     path.extension()
         .and_then(|value| value.to_str())
         .filter(|value| !value.is_empty())
-        .unwrap_or("bin")
+        .map(|value| value.to_ascii_lowercase())
-        .to_string()
+        .unwrap_or_else(|| "bin".to_string())
 }
 
 fn infer_extension_from_str(path: &str) -> String {
@@ -301,8 +309,59 @@ fn infer_extension_from_str(path: &str) -> String {
         .extension()
         .and_then(|value| value.to_str())
         .filter(|value| !value.is_empty())
-        .unwrap_or("bin")
+        .map(|value| value.to_ascii_lowercase())
-        .to_string()
+        .unwrap_or_else(|| "bin".to_string())
+}
+
+fn infer_extension_from_response(path: &str, content_type: Option<&str>, bytes: &[u8]) -> String {
+    let path_extension = infer_extension_from_str(path);
+    if let Some(extension) = extension_from_content_type(content_type) {
+        return extension;
+    }
+    infer_extension_from_bytes(Some(path_extension.as_str()), bytes)
+}
+
+fn infer_extension_from_bytes(path_extension: Option<&str>, bytes: &[u8]) -> String {
+    if let Some(extension) = sniff_image_extension(bytes) {
+        return extension.to_string();
+    }
+    path_extension.unwrap_or("bin").to_string()
+}
+
+fn extension_from_content_type(content_type: Option<&str>) -> Option<String> {
+    let normalized = content_type?.split(';').next()?.trim().to_ascii_lowercase();
+    let extension = match normalized.as_str() {
+        "image/jpeg" => "jpeg",
+        "image/png" => "png",
+        "image/gif" => "gif",
+        "image/svg+xml" => "svg",
+        "image/webp" => "webp",
+        "image/avif" => "avif",
+        _ => return None,
+    };
+    Some(extension.to_string())
+}
+
+fn sniff_image_extension(bytes: &[u8]) -> Option<&'static str> {
+    if bytes.len() >= 3 && bytes.starts_with(&[0xff, 0xd8, 0xff]) {
+        return Some("jpeg");
+    }
+    if bytes.len() >= 8 && bytes.starts_with(&[0x89, b'P', b'N', b'G', 0x0d, 0x0a, 0x1a, 0x0a]) {
+        return Some("png");
+    }
+    if bytes.len() >= 6 && (bytes.starts_with(b"GIF87a") || bytes.starts_with(b"GIF89a")) {
+        return Some("gif");
+    }
+    if bytes.len() >= 12 && bytes.starts_with(b"RIFF") && &bytes[8..12] == b"WEBP" {
+        return Some("webp");
+    }
+    if bytes.len() >= 12
+        && &bytes[4..8] == b"ftyp"
+        && bytes.windows(4).any(|window| window == b"avif")
+    {
+        return Some("avif");
+    }
+    None
 }
 
 fn infer_media_type(extension: &str) -> String {
@@ -312,6 +371,7 @@ fn infer_media_type(extension: &str) -> String {
         "gif" => "image/gif",
         "svg" => "image/svg+xml",
         "webp" => "image/webp",
+        "avif" => "image/avif",
         _ => "application/octet-stream",
     }
     .to_string()
@@ -329,9 +389,12 @@ fn to_xhtml_fragment(html: &str) -> String {
 
 #[cfg(test)]
 mod tests {
-    use super::to_xhtml_fragment;
+    use super::{
-    use quick_xml::events::Event;
+        extension_from_content_type, infer_extension_from_bytes, infer_extension_from_response,
+        to_xhtml_fragment,
+    };
     use quick_xml::Reader;
+    use quick_xml::events::Event;
 
     #[test]
     fn converts_void_html_tags_to_xhtml_self_closing_tags() {
@@ -354,4 +417,36 @@ mod tests {
             }
         }
     }
+
+    #[test]
+    fn prefers_actual_jpeg_bytes_over_png_path() {
+        let jpeg_bytes = [0xff, 0xd8, 0xff, 0xdb];
+        assert_eq!(
+            infer_extension_from_response("image.png", None, &jpeg_bytes),
+            "jpeg"
+        );
+    }
+
+    #[test]
+    fn prefers_content_type_for_remote_assets() {
+        let png_bytes = [0x89, b'P', b'N', b'G', 0x0d, 0x0a, 0x1a, 0x0a];
+        assert_eq!(
+            infer_extension_from_response(
+                "image.jpeg",
+                Some("image/png; charset=binary"),
+                &png_bytes
+            ),
+            "png"
+        );
+        assert_eq!(
+            extension_from_content_type(Some("image/avif")),
+            Some("avif".to_string())
+        );
+    }
+
+    #[test]
+    fn preserves_path_extension_when_bytes_are_unknown() {
+        let bytes = b"not an image";
+        assert_eq!(infer_extension_from_bytes(Some("jpg"), bytes), "jpg");
+    }
 }

ebookm-core/src/pipeline.rs

@@ -28,6 +28,7 @@ struct ChapterHeaderOptions {
 pub struct BuiltEntry {
     pub id: String,
     pub hidden_from_toc: bool,
+    pub section_anchor: Option<String>,
     pub chapter: BuiltChapter,
     pub assets: Vec<Asset>,
 }
@@ -186,10 +187,23 @@ pub fn build_epub(manifest: &Manifest, manifest_path: &Path) -> Result<()> {
                 &metadata,
             )?;
 
+            let section_anchor = section
+                .entries
+                .first()
+                .filter(|first_entry_id| *first_entry_id == entry_id)
+                .map(|_| format!("section-{}", section.id));
+
             built_entries.push(BuiltEntry {
                 id: entry_id.clone(),
                 hidden_from_toc: entry.toc.hidden,
-                chapter: build_chapter(entry_id, entry, &manifest.defaults, &normalized),
+                section_anchor: section_anchor.clone(),
+                chapter: build_chapter(
+                    entry_id,
+                    entry,
+                    &manifest.defaults,
+                    &normalized,
+                    section_anchor.as_deref(),
+                ),
                 assets: normalized.assets,
             });
         }
@@ -215,6 +229,7 @@ fn build_chapter(
     entry: &crate::manifest::EntryDefinition,
     defaults: &crate::manifest::DefaultsConfig,
     doc: &NormalizedDocument,
+    section_anchor: Option<&str>,
 ) -> BuiltChapter {
     let nav_title = entry.toc.title.clone().unwrap_or_else(|| doc.title.clone());
     let header = resolve_header_options(entry, defaults);
@@ -243,6 +258,10 @@ fn build_chapter(
         format!(r#"<div class="chapter-meta">{}</div>"#, meta_lines.join(""))
     };
 
+    let section_anchor_markup = section_anchor
+        .map(|anchor| format!(r#"<div id="{}"></div>"#, escape_html(anchor)))
+        .unwrap_or_default();
+
     let xhtml = format!(
         r#"<?xml version="1.0" encoding="UTF-8"?>
 <html xmlns="http://www.w3.org/1999/xhtml">
@@ -251,6 +270,7 @@ fn build_chapter(
     <link rel="stylesheet" type="text/css" href="../styles/book.css"/>
   </head>
   <body id="{}">
+    {}
     <h1>{}</h1>
     {}
     {}
@@ -258,6 +278,7 @@ fn build_chapter(
 </html>"#,
         escape_html(&doc.title),
         escape_html(entry_id),
+        section_anchor_markup,
         escape_html(&doc.title),
         meta_block,
         doc.body_xhtml
@@ -425,8 +446,10 @@ link_rules:
         assert!(!chapter_contents.contains("urn:uuid:test-book"));
         assert!(chapter_contents.contains("../assets/"));
         drop(chapter);
-        assert!(archive
+        assert!(
-            .file_names()
+            archive
-            .any(|name| name.starts_with("OEBPS/assets/") && name.ends_with(".jpg")));
+                .file_names()
+                .any(|name| name.starts_with("OEBPS/assets/") && name.ends_with(".jpg"))
+        );
     }
 }