package library

import (
	"path"
	"regexp"
	"strings"
)

// sourceMarker is one sign that a file was ripped from a video rather than
// taken from a release: words a video title carries and an album track does
// not (#5410).
//
// Each pattern is used twice, so it is written in the subset that Postgres's
// regex flavour and Go's RE2 read the same way: no \b (Postgres spells word
// boundaries \y), no lookaround, and brackets written as (\(|\[) rather than
// as a bracket expression. The SQL side matches it case-insensitively with ~*,
// the Go side with (?i); [^a-zA-Z] is spelled out so neither has to fold case
// inside a negated class.
type sourceMarker struct {
	label   string
	pattern string
}

// suspectSourceMarkers was calibrated against the operator's library on
// 2026-10-08. Two candidates were left out on purpose:
//   - "live in"/"live at": 229 files, nearly all from real live albums.
//   - a bare "reaction": it caught Beck's "Chain Reaction". The marker below
//     wants the phrases a reaction video actually uses.
var suspectSourceMarkers = []sourceMarker{
	{"music video", `official[^a-zA-Z]*(music[^a-zA-Z]*)?video|music[^a-zA-Z]*video`},
	{"official audio", `official[^a-zA-Z]*audio`},
	{"lyric video", `lyrics?[^a-zA-Z]*video`},
	{"visualiser", `visuali[sz]er`},
	{"reaction", `reaction[^a-zA-Z]*(video|mashup)|reacts?[^a-zA-Z]+to[^a-zA-Z]|first[^a-zA-Z]*time[^a-zA-Z]*(hearing|listening)`},
	{"MV", `(^|[^a-zA-Z])(mv|m/v)([^a-zA-Z]|$)`},
	{"[Audio]", `(\(|\[)audio(\)|\])`},
	{"[HD]", `(\(|\[)(hd|hq|4k)(\)|\])`},
}

// SuspectSourcePattern is every marker as one alternation, for the SQL filter
// behind the admin suspect-sources report.
var SuspectSourcePattern = func() string {
	parts := make([]string, len(suspectSourceMarkers))
	for i, m := range suspectSourceMarkers {
		parts[i] = "(" + m.pattern + ")"
	}
	return strings.Join(parts, "|")
}()

var suspectSourceRegexps = func() []*regexp.Regexp {
	out := make([]*regexp.Regexp, len(suspectSourceMarkers))
	for i, m := range suspectSourceMarkers {
		out[i] = regexp.MustCompile("(?i)" + m.pattern)
	}
	return out
}()

// SourceMarkersFor returns the labels of every marker the file's basename
// carries, in list order. Empty for a file the SQL filter would not return.
func SourceMarkersFor(filePath string) []string {
	base := path.Base(filePath)
	labels := make([]string, 0, 2)
	for i, re := range suspectSourceRegexps {
		if re.MatchString(base) {
			labels = append(labels, suspectSourceMarkers[i].label)
		}
	}
	return labels
}