libnovel/backend/internal/storage/import.go

package storage

import (
	"archive/zip"
	"bytes"
	"context"
	"fmt"
	"io"
	"regexp"
	"sort"
	"strconv"
	"strings"

	"github.com/dslipak/pdf"
	"github.com/libnovel/backend/internal/bookstore"
	"github.com/libnovel/backend/internal/domain"
	minio "github.com/minio/minio-go/v7"
	"golang.org/x/net/html"
)

// chapterHeadingRE matches common chapter heading patterns:
//   "Chapter 1", "Chapter 1:", "Chapter 1 -", "CHAPTER ONE", "1.", "Part 1", etc.
var chapterHeadingRE = regexp.MustCompile(
	`(?i)^(?:chapter|ch\.?|part|episode|book)\s+(\d+|[ivxlcdm]+)\b|^\d{1,4}[\.\)]\s+\S`)

type importer struct {
	mc *minioClient
}

// NewBookImporter creates a BookImporter that reads files from MinIO.
func NewBookImporter(s *Store) bookstore.BookImporter {
	return &importer{mc: s.mc}
}

func (i *importer) Import(ctx context.Context, objectKey, fileType string) ([]bookstore.Chapter, error) {
	if fileType != "pdf" && fileType != "epub" {
		return nil, fmt.Errorf("unsupported file type: %s", fileType)
	}

	obj, err := i.mc.client.GetObject(ctx, "imports", objectKey, minio.GetObjectOptions{})
	if err != nil {
		return nil, fmt.Errorf("get object from minio: %w", err)
	}
	defer obj.Close()

	data, err := io.ReadAll(obj)
	if err != nil {
		return nil, fmt.Errorf("read object: %w", err)
	}

	if fileType == "pdf" {
		return parsePDF(data)
	}
	return parseEPUB(data)
}

// AnalyzeFile parses the given PDF or EPUB data and returns the detected
// chapter count and up to 3 preview lines (first non-empty line of each of
// the first 3 chapters). It is used by the analyze-only endpoint so users
// can preview chapter count before committing the import.
func AnalyzeFile(data []byte, fileType string) (chapterCount int, firstLines []string, err error) {
	var chapters []bookstore.Chapter
	switch fileType {
	case "pdf":
		chapters, err = parsePDF(data)
	case "epub":
		chapters, err = parseEPUB(data)
	default:
		return 0, nil, fmt.Errorf("unsupported file type: %s", fileType)
	}
	if err != nil {
		return 0, nil, err
	}
	chapterCount = len(chapters)
	for i, ch := range chapters {
		if i >= 3 {
			break
		}
		line := strings.TrimSpace(ch.Content)
		if nl := strings.Index(line, "\n"); nl > 0 {
			line = line[:nl]
		}
		if len(line) > 120 {
			line = line[:120] + "…"
		}
		firstLines = append(firstLines, line)
	}
	return chapterCount, firstLines, nil
}



func parsePDF(data []byte) ([]bookstore.Chapter, error) {
	r, err := pdf.NewReader(bytes.NewReader(data), int64(len(data)))
	if err != nil {
		return nil, fmt.Errorf("open PDF: %w", err)
	}

	// Extract per-page text so we can detect chapter boundaries.
	numPages := r.NumPage()
	if numPages == 0 {
		return nil, fmt.Errorf("PDF has no pages")
	}

	// Collect full text first with page markers so we can split by chapter.
	var sb strings.Builder
	fonts := make(map[string]*pdf.Font)
	for i := 1; i <= numPages; i++ {
		page := r.Page(i)
		if page.V.IsNull() {
			continue
		}
		text, err := page.GetPlainText(fonts)
		if err != nil {
			continue
		}
		sb.WriteString(text)
		sb.WriteByte('\n')
	}

	return extractChaptersFromText(sb.String()), nil
}

// ── EPUB parsing ──────────────────────────────────────────────────────────────

func parseEPUB(data []byte) ([]bookstore.Chapter, error) {
	zr, err := zip.NewReader(bytes.NewReader(data), int64(len(data)))
	if err != nil {
		return nil, fmt.Errorf("open EPUB zip: %w", err)
	}

	// 1. Read META-INF/container.xml → find rootfile (content.opf path).
	opfPath, err := epubRootfilePath(zr)
	if err != nil {
		return nil, fmt.Errorf("epub container: %w", err)
	}

	// 2. Parse content.opf → spine order of chapter files.
	spineFiles, titleMap, err := epubSpine(zr, opfPath)
	if err != nil {
		return nil, fmt.Errorf("epub spine: %w", err)
	}

	if len(spineFiles) == 0 {
		return nil, fmt.Errorf("EPUB spine is empty")
	}

	// Base directory of the OPF file for resolving relative hrefs.
	opfDir := ""
	if idx := strings.LastIndex(opfPath, "/"); idx >= 0 {
		opfDir = opfPath[:idx+1]
	}

	var chapters []bookstore.Chapter
	for i, href := range spineFiles {
		fullPath := opfDir + href
		content, err := epubFileContent(zr, fullPath)
		if err != nil {
			continue
		}
		text := htmlToText(content)
		if strings.TrimSpace(text) == "" {
			continue
		}
		title := titleMap[href]
		if title == "" {
			title = fmt.Sprintf("Chapter %d", i+1)
		}
		chapters = append(chapters, bookstore.Chapter{
			Number:  i + 1,
			Title:   title,
			Content: text,
		})
	}

	if len(chapters) == 0 {
		return nil, fmt.Errorf("no readable chapters found in EPUB")
	}
	return chapters, nil
}

// epubRootfilePath parses META-INF/container.xml and returns the full-path
// of the OPF package document.
func epubRootfilePath(zr *zip.Reader) (string, error) {
	f := zipFile(zr, "META-INF/container.xml")
	if f == nil {
		return "", fmt.Errorf("META-INF/container.xml not found")
	}
	rc, err := f.Open()
	if err != nil {
		return "", err
	}
	defer rc.Close()

	doc, err := html.Parse(rc)
	if err != nil {
		return "", err
	}

	var path string
	var walk func(*html.Node)
	walk = func(n *html.Node) {
		if n.Type == html.ElementNode && strings.EqualFold(n.Data, "rootfile") {
			for _, a := range n.Attr {
				if strings.EqualFold(a.Key, "full-path") {
					path = a.Val
					return
				}
			}
		}
		for c := n.FirstChild; c != nil; c = c.NextSibling {
			walk(c)
		}
	}
	walk(doc)

	if path == "" {
		return "", fmt.Errorf("rootfile full-path not found in container.xml")
	}
	return path, nil
}

// epubSpine parses the OPF document and returns the spine item hrefs in order,
// plus a map from href → nav title (if available from NCX/NAV).
func epubSpine(zr *zip.Reader, opfPath string) ([]string, map[string]string, error) {
	f := zipFile(zr, opfPath)
	if f == nil {
		return nil, nil, fmt.Errorf("OPF file %q not found in EPUB", opfPath)
	}
	rc, err := f.Open()
	if err != nil {
		return nil, nil, err
	}
	defer rc.Close()

	opfData, err := io.ReadAll(rc)
	if err != nil {
		return nil, nil, err
	}

	// Build id→href map from <manifest>.
	idToHref := make(map[string]string)
	// Also keep a href→navTitle map (populated from NCX later).
	hrefTitle := make(map[string]string)

	// Parse OPF XML with html.Parse (handles malformed XML too).
	doc, _ := html.Parse(bytes.NewReader(opfData))

	var manifestItems []struct{ id, href, mediaType string }
	var spineIdrefs []string
	var ncxID string

	var walk func(*html.Node)
	walk = func(n *html.Node) {
		if n.Type == html.ElementNode {
			tag := strings.ToLower(n.Data)
			switch tag {
			case "item":
				var id, href, mt string
				for _, a := range n.Attr {
					switch strings.ToLower(a.Key) {
					case "id":
						id = a.Val
					case "href":
						href = a.Val
					case "media-type":
						mt = a.Val
					}
				}
				if id != "" && href != "" {
					manifestItems = append(manifestItems, struct{ id, href, mediaType string }{id, href, mt})
					idToHref[id] = href
				}
			case "itemref":
				for _, a := range n.Attr {
					if strings.ToLower(a.Key) == "idref" {
						spineIdrefs = append(spineIdrefs, a.Val)
					}
				}
			case "spine":
				for _, a := range n.Attr {
					if strings.ToLower(a.Key) == "toc" {
						ncxID = a.Val
					}
				}
			}
		}
		for c := n.FirstChild; c != nil; c = c.NextSibling {
			walk(c)
		}
	}
	walk(doc)

	// Build ordered spine href list.
	var spineHrefs []string
	for _, idref := range spineIdrefs {
		if href, ok := idToHref[idref]; ok {
			spineHrefs = append(spineHrefs, href)
		}
	}

	// If no explicit spine, fall back to all XHTML items in manifest order.
	if len(spineHrefs) == 0 {
		sort.Slice(manifestItems, func(i, j int) bool {
			return manifestItems[i].href < manifestItems[j].href
		})
		for _, it := range manifestItems {
			mt := strings.ToLower(it.mediaType)
			if strings.Contains(mt, "html") || strings.HasSuffix(strings.ToLower(it.href), ".html") || strings.HasSuffix(strings.ToLower(it.href), ".xhtml") {
				spineHrefs = append(spineHrefs, it.href)
			}
		}
	}

	// Try to get chapter titles from NCX (toc.ncx).
	opfDir := ""
	if idx := strings.LastIndex(opfPath, "/"); idx >= 0 {
		opfDir = opfPath[:idx+1]
	}
	if ncxHref, ok := idToHref[ncxID]; ok {
		ncxPath := opfDir + ncxHref
		if ncxFile := zipFile(zr, ncxPath); ncxFile != nil {
			if ncxRC, err := ncxFile.Open(); err == nil {
				defer ncxRC.Close()
				parseNCXTitles(ncxRC, hrefTitle)
			}
		}
	}

	return spineHrefs, hrefTitle, nil
}

// parseNCXTitles extracts navPoint label→src mappings from a toc.ncx.
func parseNCXTitles(r io.Reader, out map[string]string) {
	doc, err := html.Parse(r)
	if err != nil {
		return
	}

	// Collect navPoints: each has a <navLabel><text>…</text></navLabel> and
	// a <content src="…"/> child.
	var walk func(*html.Node)
	walk = func(n *html.Node) {
		if n.Type == html.ElementNode && strings.EqualFold(n.Data, "navpoint") {
			var label, src string
			var inner func(*html.Node)
			inner = func(c *html.Node) {
				if c.Type == html.ElementNode {
					if strings.EqualFold(c.Data, "text") && label == "" {
						if c.FirstChild != nil && c.FirstChild.Type == html.TextNode {
							label = strings.TrimSpace(c.FirstChild.Data)
						}
					}
					if strings.EqualFold(c.Data, "content") {
						for _, a := range c.Attr {
							if strings.EqualFold(a.Key, "src") {
								// Strip fragment identifier (#...).
								src = strings.SplitN(a.Val, "#", 2)[0]
							}
						}
					}
				}
				for child := c.FirstChild; child != nil; child = child.NextSibling {
					inner(child)
				}
			}
			inner(n)
			if label != "" && src != "" {
				out[src] = label
			}
		}
		for c := n.FirstChild; c != nil; c = c.NextSibling {
			walk(c)
		}
	}
	walk(doc)
}

// epubFileContent returns the raw bytes of a file inside the EPUB zip.
func epubFileContent(zr *zip.Reader, path string) ([]byte, error) {
	f := zipFile(zr, path)
	if f == nil {
		return nil, fmt.Errorf("file %q not in EPUB", path)
	}
	rc, err := f.Open()
	if err != nil {
		return nil, err
	}
	defer rc.Close()
	return io.ReadAll(rc)
}

// zipFile finds a file by name (case-insensitive) in a zip.Reader.
func zipFile(zr *zip.Reader, name string) *zip.File {
	nameLower := strings.ToLower(name)
	for _, f := range zr.File {
		if strings.ToLower(f.Name) == nameLower {
			return f
		}
	}
	return nil
}

// htmlToText converts HTML/XHTML content to plain text suitable for storage.
func htmlToText(data []byte) string {
	doc, err := html.Parse(bytes.NewReader(data))
	if err != nil {
		return string(data)
	}

	var sb strings.Builder
	var walk func(*html.Node)
	walk = func(n *html.Node) {
		if n.Type == html.TextNode {
			text := strings.TrimSpace(n.Data)
			if text != "" {
				sb.WriteString(text)
				sb.WriteByte(' ')
			}
		}
		if n.Type == html.ElementNode {
			switch strings.ToLower(n.Data) {
			case "p", "div", "br", "h1", "h2", "h3", "h4", "h5", "h6", "li", "tr":
				// Block-level: ensure newline before content.
				if sb.Len() > 0 {
					s := sb.String()
					if s[len(s)-1] != '\n' {
						sb.WriteByte('\n')
					}
				}
			case "script", "style", "head":
				// Skip entirely.
				return
			}
		}
		for c := n.FirstChild; c != nil; c = c.NextSibling {
			walk(c)
		}
		if n.Type == html.ElementNode {
			switch strings.ToLower(n.Data) {
			case "p", "div", "h1", "h2", "h3", "h4", "h5", "h6", "li", "tr":
				sb.WriteByte('\n')
			}
		}
	}
	walk(doc)

	// Collapse multiple blank lines.
	lines := strings.Split(sb.String(), "\n")
	var out []string
	blanks := 0
	for _, l := range lines {
		l = strings.TrimSpace(l)
		if l == "" {
			blanks++
			if blanks <= 1 {
				out = append(out, "")
			}
		} else {
			blanks = 0
			out = append(out, l)
		}
	}
	return strings.TrimSpace(strings.Join(out, "\n"))
}

// ── Chapter segmentation (shared by PDF and plain-text paths) ─────────────────

// extractChaptersFromText splits a block of plain text into chapters by
// detecting heading lines that match chapterHeadingRE.
// Falls back to paragraph-splitting when no headings are found.
func extractChaptersFromText(text string) []bookstore.Chapter {
	lines := strings.Split(text, "\n")

	type segment struct {
		title  string
		number int
		lines  []string
	}

	var segments []segment
	var cur *segment
	chNum := 0

	for _, line := range lines {
		line = strings.TrimSpace(line)
		if chapterHeadingRE.MatchString(line) {
			if cur != nil {
				segments = append(segments, *cur)
			}
			chNum++
			// Try to parse the explicit chapter number from the heading.
			if m := regexp.MustCompile(`\d+`).FindString(line); m != "" {
				if n, err := strconv.Atoi(m); err == nil && n > 0 && n < 100000 {
					chNum = n
				}
			}
			cur = &segment{title: line, number: chNum}
		} else if cur != nil && line != "" {
			cur.lines = append(cur.lines, line)
		}
	}
	if cur != nil {
		segments = append(segments, *cur)
	}

	// Require segments to have meaningful content (>= 100 chars).
	var chapters []bookstore.Chapter
	for _, seg := range segments {
		content := strings.Join(seg.lines, "\n")
		if len(strings.TrimSpace(content)) < 50 {
			continue
		}
		chapters = append(chapters, bookstore.Chapter{
			Number:  seg.number,
			Title:   seg.title,
			Content: content,
		})
	}

	// Fallback: no headings found — split by double newlines (paragraph blocks).
	if len(chapters) == 0 {
		paragraphs := strings.Split(text, "\n\n")
		n := 0
		for _, para := range paragraphs {
			para = strings.TrimSpace(para)
			if len(para) > 100 {
				n++
				chapters = append(chapters, bookstore.Chapter{
					Number:  n,
					Title:   fmt.Sprintf("Chapter %d", n),
					Content: para,
				})
			}
		}
	}

	return chapters
}

// ── Chapter ingestion ─────────────────────────────────────────────────────────

// IngestChapters stores extracted chapters for a book.
// Each chapter is written as a markdown file in the chapters MinIO bucket
// and its index record is upserted in PocketBase via WriteChapter.
func (s *Store) IngestChapters(ctx context.Context, slug string, chapters []bookstore.Chapter) error {
	for _, ch := range chapters {
		var mdContent string
		if ch.Title != "" && ch.Title != fmt.Sprintf("Chapter %d", ch.Number) {
			mdContent = fmt.Sprintf("# %s\n\n%s", ch.Title, ch.Content)
		} else {
			mdContent = fmt.Sprintf("# Chapter %d\n\n%s", ch.Number, ch.Content)
		}
		domainCh := domain.Chapter{
			Ref:  domain.ChapterRef{Number: ch.Number, Title: ch.Title},
			Text: mdContent,
		}
		if err := s.WriteChapter(ctx, slug, domainCh); err != nil {
			return fmt.Errorf("ingest chapter %d: %w", ch.Number, err)
		}
	}
	return nil
}

// GetImportObjectKey returns the MinIO object key for an uploaded import file.
func GetImportObjectKey(filename string) string {
	return fmt.Sprintf("imports/%s", filename)
}