task 6: produce attributedText in EPUBParser, add attributed string tests

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

VorleserKit/Sources/BookParser/EPUBParser.swift

@@ -2,6 +2,12 @@ import Foundation
 import ZIPFoundation
 import SwiftSoup
 
+#if canImport(UIKit)
+import UIKit
+#elseif canImport(AppKit)
+import AppKit
+#endif
+
 public enum EPUBParserError: Error, CustomStringConvertible {
 	case cannotOpenArchive(URL)
 	case missingContainerXML
@@ -43,6 +49,7 @@ public struct EPUBParser {
 
 			var chapterTitle: String
 			var chapterText: String
+			var formattingRanges: [AttributedStringBuilder.FormattingRange] = []
 			do {
 				let htmlData = try extractData(from: archive, path: fullPath)
 				let html = String(data: htmlData, encoding: .utf8) ?? ""
@@ -50,12 +57,14 @@ public struct EPUBParser {
 				chapterTitle = try doc.select("h1, h2, h3, title").first()?.text() ?? "Chapter \(index + 1)"
 				let body = try doc.body()?.text() ?? ""
 				chapterText = normalizeWhitespace(body)
+				formattingRanges = extractFormattingRanges(from: doc, normalizedText: chapterText)
 			} catch {
 				chapterTitle = "Chapter \(index + 1) (parse error)"
 				chapterText = ""
 			}
 
-			chapters.append(Chapter(index: index, title: chapterTitle, text: chapterText))
+			let attributedText = AttributedStringBuilder.build(text: chapterText, ranges: formattingRanges)
+			chapters.append(Chapter(index: index, title: chapterTitle, text: chapterText, attributedText: attributedText))
 		}
 
 		return Book(
@@ -93,6 +102,32 @@ public struct EPUBParser {
 		return data
 	}
 
+	private static func extractFormattingRanges(from doc: Document, normalizedText: String) -> [AttributedStringBuilder.FormattingRange] {
+		var ranges: [AttributedStringBuilder.FormattingRange] = []
+		guard !normalizedText.isEmpty else { return ranges }
+
+		func findAndAdd(selector: String, style: AttributedStringBuilder.FormattingRange.Style) {
+			guard let elements = try? doc.select(selector) else { return }
+			for element in elements {
+				guard let elementText = try? element.text() else { continue }
+				let normalizedElement = normalizeWhitespace(elementText)
+				guard !normalizedElement.isEmpty else { continue }
+				if let range = normalizedText.range(of: normalizedElement) {
+					let nsRange = NSRange(range, in: normalizedText)
+					ranges.append(AttributedStringBuilder.FormattingRange(range: nsRange, style: style))
+				}
+			}
+		}
+
+		findAndAdd(selector: "b, strong", style: .bold)
+		findAndAdd(selector: "i, em", style: .italic)
+		findAndAdd(selector: "h1", style: .heading(level: 1))
+		findAndAdd(selector: "h2", style: .heading(level: 2))
+		findAndAdd(selector: "h3", style: .heading(level: 3))
+
+		return ranges
+	}
+
 	private static func normalizeWhitespace(_ text: String) -> String {
 		text.components(separatedBy: .whitespacesAndNewlines)
 			.filter { !$0.isEmpty }

VorleserKit/Tests/BookParserTests/EPUBParserTests.swift

@@ -34,4 +34,22 @@ struct EPUBParserTests {
 			#expect(chapter.index == i)
 		}
 	}
+
+	@Test func attributedTextStringMatchesPlainText() throws {
+		let book = try EPUBParser.parse(url: fixtureURL)
+		for chapter in book.chapters {
+			#expect(chapter.attributedText.string == chapter.text,
+				"attributedText.string must be identical to text for chapter '\(chapter.title)'")
+		}
+	}
+
+	@Test func attributedTextHasFontAttributes() throws {
+		let book = try EPUBParser.parse(url: fixtureURL)
+		let chapter = book.chapters[0]
+		var hasFont = false
+		chapter.attributedText.enumerateAttribute(.font, in: NSRange(location: 0, length: chapter.attributedText.length)) { value, _, _ in
+			if value != nil { hasFont = true }
+		}
+		#expect(hasFont, "attributedText should have font attributes")
+	}
 }