mangaBookmark/backend/internal/latest/sites.go

package latest

import (
	"encoding/json"
	"html"
	"log"
	"net/url"
	"regexp"
	"strconv"
	"strings"
)

// latestChapter is the newest chapter a series page advertises.
type latestChapter struct {
	Num   float64
	Label string
}

// asuraSlugRe pulls the series slug out of a stored series_url.
// Shape verified live 2026-07-26: https://asurascans.com/comics/<slug>, where
// the slug carries a trailing build-hash suffix (e.g. "-f886a8af") that
// rotates on every site redeploy — callers must strip it (asuraBuildHash)
// before using the slug to scope anything.
var asuraSlugRe = regexp.MustCompile(`/comics/([^/?#]+)`)

// asuraBuildHash matches the trailing "-xxxxxxxx" site-wide build ID Asura
// appends to every series slug. It rotates on each site redeploy, so it is
// never part of a stable series_id. Must stay in sync with stripBuildHash in
// userscript/manga-bookmark.user.js.
var asuraBuildHash = regexp.MustCompile(`-[0-9a-f]{8}$`)

// demonicChapterRe matches the pre-redirect anchors demonic series pages link
// through. Both the raw "&" and the HTML-escaped "&amp;" forms occur.
var demonicChapterRe = regexp.MustCompile(`chaptered\.php\?manga=\d+&(?:amp;)?chapter=([0-9.]+)`)

// comixSlugRe pulls the "<id>-<slug>" segment out of a stored series_url.
// Only the id prefix is stable; the slug tail follows the title.
var comixSlugRe = regexp.MustCompile(`/title/([^/?#]+)`)

func comixSeriesID(seriesURL string) (string, bool) {
	m := comixSlugRe.FindStringSubmatch(seriesURL)
	if m == nil {
		return "", false
	}
	id := m[1]
	if i := strings.Index(id, "-"); i != -1 {
		id = id[:i]
	}
	return id, true
}

// kaganeChapterRe matches the chapter numbers in a kagane API response. This
// branch is fed by the browser fetcher, so the body is JSON rather than HTML —
// there are no anchors to scan.
var kaganeChapterRe = regexp.MustCompile(`"chapter_no":"([0-9.]+)"`)

// novelfullSlugRe pulls the series slug out of a stored series_url. novelfull
// series pages are "/<slug>.html"; their chapter anchors are
// "/<slug>/chapter-<n>[-<title-slug>].html". Verified live 2026-08-05.
var novelfullSlugRe = regexp.MustCompile(`^/([^/?#]+)\.html$`)

// lnwChapterRe matches any chapter-shaped address on lightnovelworld. Unlike
// asura, novelfull and comix — which scope to their stored series slug so a
// foreign chapter link cannot contribute — this Site's chapter addresses carry
// the Chapter Slug, which is not the Series identity: one Series may publish
// under several Chapter Slugs (measured 2026-08-11: a sampled novel serves
// 1-99 under one slug and 100-423 under another), so no stored-slug pattern can
// cover a Series' whole list. An unscoped match is safe because
// latestChapterFrom truncates the body at the comment thread before scanning
// (lnwCommentMarker); without that, a visitor's comment could set the Latest
// Chapter on the shared Series row.
var lnwChapterRe = regexp.MustCompile(`lightnovelworld\.net/[a-z0-9-]+-chapter-([0-9.]+)/`)

// lnwCommentMarker is the boundary of lightnovelworld's server-rendered
// wpdiscuz comment thread. It occurs exactly once per page and follows every
// chapter anchor (measured 2026-08-11,
// docs/research/lightnovelworld-chapter-vs-series-slug.md §6), so cutting the
// body at its first occurrence keeps the whole chapter list while excluding a
// region any visitor can write to. Absent means the page shape changed: the
// body is skipped, never scanned whole.
const lnwCommentMarker = "wpd-threads"

// latestChapterFrom returns the highest chapter number body advertises for this
// series. ok is false when the body yields nothing usable — an unknown site, an
// empty body, a Cloudflare challenge page, and a site redesign all land here,
// and the caller treats all four identically.
//
// Ported from the userscript's latestChapterFromAnchors (asura L123-133,
// demonic L183-193), including its reason for taking a maximum rather than a
// first or last: neither site lists chapters in a dependable order.
//
// The userscript's asura rule additionally requires the anchor text to match
// /Chapter\s+[\d.]+/i. That check exists only to skip the "First Chapter"
// shortcut, which points at chapter/1 and therefore can never win a maximum, so
// it is redundant here. For asura, scoping the pattern to this series' own slug
// replaces it with a stronger guarantee: a chapter link belonging to some other
// series cannot contribute even if the page starts carrying them. demonic has no
// such guarantee — demonicChapterRe matches any chaptered.php?manga=<id> anchor
// with no per-series scoping, because the stored series_id for demonic is a
// slug, not the numeric id the URL carries, so it cannot easily be scoped.
// lightnovelworld is unscoped and body-truncated instead — see lnwChapterRe.
func latestChapterFrom(site, seriesURL, body string) (latestChapter, bool) {
	var re *regexp.Regexp
	switch site {
	case "asura":
		m := asuraSlugRe.FindStringSubmatch(seriesURL)
		if m == nil {
			return latestChapter{}, false
		}
		// Stored URLs predating a redeploy may carry a stale build hash;
		// chapter hrefs in the fetched body carry the current one. Strip to
		// the stable ID and make the hash optional in the pattern, so scoping
		// survives rotations.
		slug := asuraBuildHash.ReplaceAllString(m[1], "")
		// Compiled per call rather than cached: this runs once per fetch, which
		// is at most a few times a minute, and the slug varies per series.
		re = regexp.MustCompile(`/comics/` + regexp.QuoteMeta(slug) + `(?:-[0-9a-f]{8})?/chapter/([0-9.]+)`)
	case "demonic":
		re = demonicChapterRe
	case "comix":
		id, ok := comixSeriesID(seriesURL)
		if !ok {
			return latestChapter{}, false
		}
		// comix ships an SPA: the served HTML carries a JSON state blob instead
		// of chapter anchors, and latestChapterUrl is the only place the newest
		// chapter appears. Scoping to this series' id prefix keeps a
		// "recommended" strip's entries from winning the maximum.
		re = regexp.MustCompile(`"latestChapterUrl":"/title/` + regexp.QuoteMeta(id) + `-[^"]*-chapter-([0-9.]+)"`)
	case "kagane":
		re = kaganeChapterRe
	case "novelfull":
		u, err := url.Parse(seriesURL)
		if err != nil {
			return latestChapter{}, false
		}
		m := novelfullSlugRe.FindStringSubmatch(u.Path)
		if m == nil {
			return latestChapter{}, false
		}
		// Scoped to this series' slug for the same reason asura is: page 1
		// carries a "latest chapters" widget and a "you may also like" strip,
		// and neither may contribute to the maximum.
		re = regexp.MustCompile(`/` + regexp.QuoteMeta(m[1]) + `/chapter-([0-9.]+)`)
	case "lightnovelworld":
		// The comment thread below the chapter list is the one region of the
		// page any visitor can write to, so the scan never reads past it (see
		// lnwChapterRe). A body without the marker is skipped, never scanned
		// whole — a redesign must degrade into staleness, not into a wrong
		// shared value; the logged body length tells a markup change from a
		// body the size cap cut short.
		i := strings.Index(body, lnwCommentMarker)
		if i < 0 {
			log.Printf("latest poll %q: no %s marker in %d bytes", seriesURL, lnwCommentMarker, len(body))
			return latestChapter{}, false
		}
		body = body[:i]
		re = lnwChapterRe
	default:
		return latestChapter{}, false
	}

	var best latestChapter
	found := false
	for _, m := range re.FindAllStringSubmatch(body, -1) {
		// [0-9.]+ can swallow a trailing separator, e.g. "chapter/12." in a
		// sentence; ParseFloat would reject the whole match.
		raw := strings.Trim(m[1], ".")
		num, err := strconv.ParseFloat(raw, 64)
		if err != nil {
			continue
		}
		if !found || num > best.Num {
			best = latestChapter{Num: num, Label: "Chapter " + raw}
			found = true
		}
	}
	return best, found
}

var metaTagRe = regexp.MustCompile(`(?is)<meta\b[^>]*>`)
var doubleQuotedMetaAttrRe = regexp.MustCompile(`(?is)([a-z][a-z0-9:_-]*)\s*=\s*"([^"]*)"`)
var singleQuotedMetaAttrRe = regexp.MustCompile(`(?is)([a-z][a-z0-9:_-]*)\s*=\s*'([^']*)'`)

// comix's server-rendered page embeds query data in this JSON script; parsing
// the target detail entry avoids matching posters from recommended results.
var comixInitialDataRe = regexp.MustCompile(`(?is)<script\b[^>]*\bid\s*=\s*["']initial-data["'][^>]*>(.*?)</script>`)

// kaganeImageURLRe matches the canonical compressed image route kagane's API
// publishes — the only cover URL form the extractor emits and the browser
// fetcher accepts. The URL is matched in full (scheme, host, id shape) rather
// than trusted: the value a fetcher is pointed at may have been client-
// supplied, and a headless browser is a strong SSRF primitive.
var kaganeImageURLRe = regexp.MustCompile(`^https://kagane\.to/api/v2/image/([0-9a-f-]{36})/compressed$`)

// browserOnlyCoverURL reports whether the browser sidecar is the only fetcher
// for cover bytes at imageURL. kagane's image route answers a plain fetch with
// a challenge and `cross-origin-resource-policy: same-origin`, so a TLS fetch
// would only ever retrieve a challenge page and must not be attempted
// (ADR-0007). This is the byte-fetch router's per-Site knowledge; it lives in
// the extraction module, which owns kagane's URL shapes.
func browserOnlyCoverURL(imageURL string) bool {
	return kaganeImageURLRe.MatchString(imageURL)
}

// kagane's browser-fetched series response publishes cover image IDs under
// series_covers. The API's canonical compressed image route is the only URL
// form accepted by the store and browser fetcher; no rendition is guessed.
func kaganeCoverURL(body string) string {
	var response struct {
		SeriesCovers []struct {
			ImageID string `json:"image_id"`
		} `json:"series_covers"`
	}
	if err := json.Unmarshal([]byte(body), &response); err != nil {
		return ""
	}
	for _, cover := range response.SeriesCovers {
		// Validate the assembled URL against the same regex the browser
		// fetcher enforces, so the extractor can never emit an address the
		// fetch would refuse.
		imageURL := "https://kagane.to/api/v2/image/" + cover.ImageID + "/compressed"
		if kaganeImageURLRe.MatchString(imageURL) {
			return imageURL
		}
	}
	return ""
}

func comixCoverURL(seriesURL, body string) string {
	id, ok := comixSeriesID(seriesURL)
	if !ok {
		return ""
	}
	data := comixInitialDataRe.FindStringSubmatch(body)
	if data == nil {
		return ""
	}
	var state struct {
		Queries map[string]json.RawMessage `json:"queries"`
	}
	if err := json.Unmarshal([]byte(data[1]), &state); err != nil {
		return ""
	}
	raw := state.Queries[`["manga","detail","`+id+`"]`]
	if len(raw) == 0 {
		return ""
	}
	var detail struct {
		Poster struct {
			Medium string `json:"medium"`
		} `json:"poster"`
	}
	if err := json.Unmarshal(raw, &detail); err != nil {
		return ""
	}
	return publishedCoverURL(detail.Poster.Medium)
}

// coverFrom reports false for unknown sites, challenge bodies, and pages with
// no usable cover. Metadata extraction keeps scanning after an empty match so
// a later published cover is not hidden by an empty tag.
func coverFrom(site, seriesURL, body string) (string, bool) {
	var cover string
	switch site {
	case "asura", "demonic", "lightnovelworld":
		cover = metaContent(body, "property", "og:image")
	case "novelfull":
		cover = metaContent(body, "name", "image")
	case "comix":
		cover = comixCoverURL(seriesURL, body)
	case "kagane":
		cover = kaganeCoverURL(body)
	}
	return cover, cover != ""
}

func metaContent(body, attrName, attrValue string) string {
	for _, tag := range metaTagRe.FindAllString(body, -1) {
		attrs := make(map[string]string)
		for _, m := range doubleQuotedMetaAttrRe.FindAllStringSubmatch(tag, -1) {
			attrs[strings.ToLower(m[1])] = m[2]
		}
		for _, m := range singleQuotedMetaAttrRe.FindAllStringSubmatch(tag, -1) {
			attrs[strings.ToLower(m[1])] = m[2]
		}
		if strings.EqualFold(attrs[strings.ToLower(attrName)], attrValue) {
			if cover := publishedCoverURL(attrs["content"]); cover != "" {
				return cover
			}
		}
	}
	return ""
}

func publishedCoverURL(value string) string {
	value = strings.TrimSpace(html.UnescapeString(value))
	return strings.ReplaceAll(value, " ", "%20")
}