ReadViewSDK/Sources/RDReaderView/EPUBTextRendering/RDPlainTextBookBuilder.swift

import UIKit

/// 纯文本书籍构建器：将 TXT 文件构建为 RDEPUBTextBook，复用 EPUB 文本渲染和分页管线。
///
/// 本类将纯文本文件（.txt）转换为与 EPUB 相同的分页书籍模型，
/// 使得纯文本阅读器可以复用 EPUBReader 的分页、导航、搜索等全部功能。
///
/// 处理流程：
/// 1. 解码文本文件（UTF-8 → GB18030 → GBK 兼容编码）
/// 2. 按中文章节正则拆分为多个章节
/// 3. 将纯文本包装为 HTML 段落
/// 4. 通过渲染器（DTCoreText）渲染为富文本
/// 5. CoreText 分页 → RDEPUBTextBook
public final class RDPlainTextBookBuilder {
    private let renderer: RDEPUBTextRenderer

    public init(renderer: RDEPUBTextRenderer = RDEPUBDTCoreTextRenderer()) {
        self.renderer = renderer
    }

    /// 从纯文本文件构建分页书籍。
    ///
    /// - Parameters:
    ///   - textFileURL: 纯文本文件的本地 URL
    ///   - pageSize: 页面尺寸
    ///   - style: 渲染样式（字体、行距、颜色）
    /// - Returns: 分页后的书籍模型
    public func build(
        textFileURL: URL,
        pageSize: CGSize,
        style: RDEPUBTextRenderStyle
    ) throws -> RDEPUBTextBook {
        let rawText = rd_decodeTextFile(url: textFileURL)
        let chapterSpecs = splitChapters(from: rawText)

        var chapters: [RDEPUBTextChapter] = []
        var flatPages: [RDEPUBTextPage] = []

        for (index, spec) in chapterSpecs.enumerated() {
            let html = wrapTextAsHTML(spec.content)
            let rendered = try renderer.renderChapter(html: html, baseURL: nil, style: style)

            let content = NSMutableAttributedString(attributedString: rendered.attributedString)
            let layoutFrames = content.length > 0 ? content.rd_paginatedFrames(size: pageSize) : []
            let effectiveFrames = layoutFrames.isEmpty && content.length > 0
                ? [
                    RDEPUBTextLayoutFrame(
                        contentRange: NSRange(location: 0, length: content.length),
                        breakReason: .chapterEnd,
                        blockRange: nil,
                        attachmentRanges: [],
                        attachmentKinds: [],
                        blockKinds: [],
                        semanticHints: [],
                        attachmentPlacements: [],
                        trailingFragmentID: nil,
                        diagnostics: [
                            "page break: chapterEnd",
                            "page range: \(NSStringFromRange(NSRange(location: 0, length: content.length)))"
                        ]
                    )
                ]
                : layoutFrames

            let href = "chapter_\(index).xhtml"
            let chapterAttributedContent = content.copy() as! NSAttributedString
            let pages = effectiveFrames.enumerated().map { localPageIndex, frame in
                let range = frame.contentRange
                return RDEPUBTextPage(
                    absolutePageIndex: flatPages.count + localPageIndex,
                    chapterIndex: index,
                    spineIndex: index,
                    href: href,
                    chapterTitle: spec.title ?? "第 \(index + 1) 章",
                    pageIndexInChapter: localPageIndex,
                    totalPagesInChapter: effectiveFrames.count,
                    chapterContent: chapterAttributedContent,
                    content: content.attributedSubstring(from: range),
                    contentRange: range,
                    pageStartOffset: range.location,
                    pageEndOffset: range.location + max(range.length - 1, 0),
                    metadata: frame.metadata
                )
            }

            chapters.append(
                RDEPUBTextChapter(
                    chapterIndex: index,
                    spineIndex: index,
                    href: href,
                    title: spec.title ?? "第 \(index + 1) 章",
                    attributedContent: chapterAttributedContent,
                    fragmentOffsets: [:],
                    pageBreakReasons: pages.map { $0.metadata.breakReason },
                    pages: pages
                )
            )
            flatPages.append(contentsOf: pages)
        }

        return RDEPUBTextBook(chapters: chapters, pages: flatPages)
    }

    // MARK: - 章节拆分

    /// 章节规格：标题 + 内容
    private struct ChapterSpec {
        let title: String?
        let content: String
    }

    /// 按中文章节正则拆分文本。匹配 "第X章/节/回/卷" 格式，
    /// 无匹配时将整篇文本作为一章处理。
    private func splitChapters(from text: String) -> [ChapterSpec] {
        let pattern = #"^(第[零一二三四五六七八九十百千万\d]+[章节回卷].*)$"#
        guard let regex = try? NSRegularExpression(pattern: pattern, options: [.anchorsMatchLines]) else {
            return [ChapterSpec(title: nil, content: text)]
        }

        let nsText = text as NSString
        let matches = regex.matches(in: text, range: NSRange(location: 0, length: nsText.length))
        guard !matches.isEmpty else {
            return [ChapterSpec(title: nil, content: text)]
        }

        var specs: [ChapterSpec] = []
        for (i, match) in matches.enumerated() {
            let titleRange = match.range(at: 1)
            let title = nsText.substring(with: titleRange).trimmingCharacters(in: .whitespacesAndNewlines)
            let contentStart = titleRange.location + titleRange.length
            let contentEnd = (i + 1 < matches.count) ? matches[i + 1].range.location : nsText.length
            let contentRange = NSRange(location: contentStart, length: contentEnd - contentStart)
            let content = nsText.substring(with: contentRange).trimmingCharacters(in: .whitespacesAndNewlines)
            if !content.isEmpty {
                specs.append(ChapterSpec(title: title, content: content))
            }
        }

        // 拆分结果为空（所有章节内容为空），整体作为一章
        if specs.isEmpty {
            return [ChapterSpec(title: nil, content: text)]
        }
        return specs
    }

    // MARK: - HTML 包装

    /// 将纯文本包装为 HTML 段落：每行一个 `<p>` 标签
    private func wrapTextAsHTML(_ text: String) -> String {
        let paragraphs = text.components(separatedBy: "\n").filter { !$0.isEmpty }
        let body = paragraphs.map { "<p>\($0)</p>" }.joined(separator: "\n")
        return "<html><body>\(body)</body></html>"
    }

    // MARK: - 文本解码

    /// 解码文本文件，按优先级尝试 UTF-8 → GB18030 → GBK 编码
    private func rd_decodeTextFile(url: URL) -> String {
        if let content = try? NSString(contentsOf: url, encoding: String.Encoding.utf8.rawValue) as String {
            return content
        }
        if let content = try? NSString(contentsOf: url, encoding: 0x80000632) as String {
            return content
        }
        if let content = try? NSString(contentsOf: url, encoding: 0x80000631) as String {
            return content
        }
        return ""
    }
}