test: add extract_epub_chapter_texts + strip_html unit tests (DOC-FULL-024)

- 7 strip_html tests: remove tags, collapse whitespace, nested tags,
  self-closing tags, attributes, empty input, plain text
- 4 extract_epub_chapter_texts tests: chapters with HTML, empty chapter
  filtered, all empty, plain text preserved
- epub_with_chapter_text helper builds EPUB with custom chapter content

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

crates/zx_document_core/src/epub.rs

@@ -655,4 +655,141 @@ mod tests {
         assert_eq!(chapters[1].title, "Chapter 2");
         assert_eq!(chapters[2].title, "Chapter 3");
     }
+
+    // ── strip_html tests ──
+
+    #[test]
+    fn test_strip_html_removes_tags() {
+        assert_eq!(strip_html("<p>Hello World</p>"), "Hello World");
+    }
+
+    #[test]
+    fn test_strip_html_collapses_whitespace() {
+        assert_eq!(strip_html("<p>Hello   World</p>"), "Hello World");
+        assert_eq!(strip_html("<div>\n  Line 1\n  Line 2\n</div>"), "Line 1 Line 2");
+    }
+
+    #[test]
+    fn test_strip_html_handles_nested_tags() {
+        assert_eq!(strip_html("<div><p><b>Bold</b> text</p></div>"), "Bold text");
+    }
+
+    #[test]
+    fn test_strip_html_handles_self_closing_tags() {
+        assert_eq!(strip_html("Text<br/>more<br />text"), "Textmoretext");
+    }
+
+    #[test]
+    fn test_strip_html_handles_attributes() {
+        assert_eq!(strip_html("<p class=\"intro\" id='p1'>Hello</p>"), "Hello");
+    }
+
+    #[test]
+    fn test_strip_html_empty_input() {
+        assert_eq!(strip_html(""), "");
+    }
+
+    #[test]
+    fn test_strip_html_plain_text_unchanged() {
+        assert_eq!(strip_html("Plain text, no HTML tags."), "Plain text, no HTML tags.");
+    }
+
+    // ── extract_epub_chapter_texts tests ──
+
+    fn epub_with_chapter_text(title: &str, chapters: &[(&str, &str)]) -> Vec<u8> {
+        let mut buf = std::io::Cursor::new(Vec::new());
+        {
+            let mut zip = zip::ZipWriter::new(&mut buf);
+            let opts = zip::write::SimpleFileOptions::default()
+                .compression_method(zip::CompressionMethod::Stored);
+
+            zip.start_file("mimetype", opts).unwrap();
+            zip.write_all(b"application/epub+zip").unwrap();
+
+            zip.start_file("META-INF/container.xml", opts).unwrap();
+            zip.write_all(
+                b"<?xml version=\"1.0\"?>\n<container version=\"1.0\" xmlns=\"urn:oasis:names:tc:opendocument:xmlns:container\">\n  <rootfiles>\n    <rootfile full-path=\"OEBPS/content.opf\" media-type=\"application/oebps-package+xml\"/>\n  </rootfiles>\n</container>"
+            ).unwrap();
+
+            let mut opf = format!(
+                "<?xml version=\"1.0\"?>\n<package xmlns=\"http://www.idpf.org/2007/opf\" version=\"2.0\">\n<metadata xmlns:dc=\"http://purl.org/dc/elements/1.1/\">\n  <dc:title>{}</dc:title>\n</metadata>\n<manifest>\n  <item id=\"ncx\" href=\"toc.ncx\" media-type=\"application/x-dtbncx+xml\"/>\n",
+                title
+            );
+            for (i, (href, _)) in chapters.iter().enumerate() {
+                opf.push_str(&format!("  <item id=\"ch{}\" href=\"{}\" media-type=\"application/xhtml+xml\"/>\n", i, href));
+            }
+            opf.push_str("</manifest>\n<spine toc=\"ncx\">\n");
+            for i in 0..chapters.len() {
+                opf.push_str(&format!("  <itemref idref=\"ch{}\"/>\n", i));
+            }
+            opf.push_str("</spine>\n</package>");
+            zip.start_file("OEBPS/content.opf", opts).unwrap();
+            zip.write_all(opf.as_bytes()).unwrap();
+
+            let mut ncx = String::from("<?xml version=\"1.0\"?>\n<ncx xmlns=\"http://www.daisy.org/z3986/2005/ncx/\" version=\"2005-1\">\n<navMap>\n");
+            for (i, (href, _)) in chapters.iter().enumerate() {
+                ncx.push_str(&format!(
+                    "  <navPoint id=\"nav{}\" playOrder=\"{}\">\n    <navLabel><text>Ch {}</text></navLabel>\n    <content src=\"{}\"/>\n  </navPoint>\n",
+                    i, i + 1, i + 1, href
+                ));
+            }
+            ncx.push_str("</navMap>\n</ncx>");
+            zip.start_file("toc.ncx", opts).unwrap();
+            zip.write_all(ncx.as_bytes()).unwrap();
+
+            for (href, content) in chapters {
+                zip.start_file(*href, opts).unwrap();
+                zip.write_all(content.as_bytes()).unwrap();
+            }
+
+            zip.finish().unwrap();
+        }
+        buf.into_inner()
+    }
+
+    #[test]
+    fn test_extract_epub_chapter_texts_with_html() {
+        let data = epub_with_chapter_text("Test", &[
+            ("OEBPS/ch1.xhtml", "<html><body><p>Chapter one content.</p></body></html>"),
+            ("OEBPS/ch2.xhtml", "<html><body><h1>Title</h1><p>Chapter <b>two</b>.</p></body></html>"),
+        ]);
+        let path = write_temp(&data, "chapter_text.epub");
+        let texts = extract_epub_chapter_texts(&path).unwrap();
+        assert_eq!(texts.len(), 2);
+        assert_eq!(texts[0].text, "Chapter one content.");
+        assert_eq!(texts[1].text, "TitleChapter two.");
+    }
+
+    #[test]
+    fn test_extract_epub_chapter_texts_empty_chapter_filtered() {
+        let data = epub_with_chapter_text("Empty", &[
+            ("OEBPS/ch1.xhtml", "<html><body></body></html>"),
+            ("OEBPS/ch2.xhtml", "<html><body><p>Not empty</p></body></html>"),
+        ]);
+        let path = write_temp(&data, "empty_ch.epub");
+        let texts = extract_epub_chapter_texts(&path).unwrap();
+        assert_eq!(texts.len(), 1);
+        assert_eq!(texts[0].text, "Not empty");
+    }
+
+    #[test]
+    fn test_extract_epub_chapter_texts_all_empty() {
+        let data = epub_with_chapter_text("AllEmpty", &[
+            ("OEBPS/ch1.xhtml", "<html/>"),
+        ]);
+        let path = write_temp(&data, "all_empty.epub");
+        let texts = extract_epub_chapter_texts(&path).unwrap();
+        assert!(texts.is_empty());
+    }
+
+    #[test]
+    fn test_extract_epub_chapter_texts_plain_text_preserved() {
+        let data = epub_with_chapter_text("Plain", &[
+            ("OEBPS/ch1.xhtml", "No HTML tags, just plain text."),
+        ]);
+        let path = write_temp(&data, "plain.epub");
+        let texts = extract_epub_chapter_texts(&path).unwrap();
+        assert_eq!(texts.len(), 1);
+        assert_eq!(texts[0].text, "No HTML tags, just plain text.");
+    }
 }