add rutor api

server/rutor/models/torrentDetails.go

@@ -0,0 +1,76 @@
+package models
+
+import (
+	"strings"
+	"time"
+)
+
+const (
+	CatMovie         = "Movie"
+	CatSeries        = "Series"
+	CatDocMovie      = "DocMovie"
+	CatDocSeries     = "DocSeries"
+	CatCartoonMovie  = "CartoonMovie"
+	CatCartoonSeries = "CartoonSeries"
+	CatTVShow        = "TVShow"
+	CatAnime         = "Anime"
+
+	Q_LOWER           = 0
+	Q_WEBDL_720       = 100
+	Q_BDRIP_720       = 101
+	Q_BDRIP_HEVC_720  = 102
+	Q_WEBDL_1080      = 200
+	Q_BDRIP_1080      = 201
+	Q_BDRIP_HEVC_1080 = 202
+	Q_BDREMUX_1080    = 203
+	Q_WEBDL_SDR_2160  = 300
+	Q_WEBDL_HDR_2160  = 301
+	Q_WEBDL_DV_2160   = 302
+	Q_BDRIP_SDR_2160  = 303
+	Q_BDRIP_HDR_2160  = 304
+	Q_BDRIP_DV_2160   = 305
+	Q_UHD_BDREMUX_SDR = 306
+	Q_UHD_BDREMUX_HDR = 307
+	Q_UHD_BDREMUX_DV  = 308
+
+	Q_UNKNOWN = 0
+	Q_A       = 1   // Авторский, по типу Гоблина или старых переводчиков
+	Q_L1      = 100 // Любительский одноголосый закадровый
+	Q_L2      = 101 // Любительский двухголосый закадровый
+	Q_L       = 102 // Любительский 3-5 человек закадровый
+	Q_LS      = 103 // Любительский студия
+	Q_P1      = 200 // Професиональный одноголосый закадровый
+	Q_P2      = 201 // Профессиональный двухголосый закадровый
+	Q_P       = 202 // Профессиональный 3-5 человек закадровый
+	Q_PS      = 203 // Профессиональный студия
+	Q_D       = 300 // Официальное профессиональное многоголосое озвучивание
+	Q_LICENSE = 301 // Лицензия
+)
+
+type TorrentDetails struct {
+	Title        string
+	Name         string
+	Names        []string
+	Categories   string
+	Size         string
+	CreateDate   time.Time
+	Tracker      string
+	Link         string
+	Year         int
+	Peer         int
+	Seed         int
+	Magnet       string
+	Hash         string
+	IMDBID       string
+	VideoQuality int
+	AudioQuality int
+}
+
+type TorrentFile struct {
+	Name string
+	Size int64
+}
+
+func (d TorrentDetails) GetNames() string {
+	return strings.Join(d.Names, " ")
+}

server/rutor/rutor.go

@@ -0,0 +1,128 @@
+package rutor
+
+import (
+	"bytes"
+	"compress/flate"
+	"encoding/json"
+	"github.com/agnivade/levenshtein"
+	"io"
+	"net/http"
+	"os"
+	"path/filepath"
+	"server/log"
+	"server/rutor/models"
+	"server/rutor/torrsearch"
+	"server/rutor/utils"
+	"server/settings"
+	"sort"
+	"strconv"
+	"strings"
+	"time"
+)
+
+var (
+	torrs  []*models.TorrentDetails
+	isStop bool
+)
+
+func Start() {
+	go func() {
+		if settings.BTsets.EnableRutorSearch {
+			updateDB()
+			isStop = false
+			for !isStop {
+				for i := 0; i < 3*60*60; i++ {
+					time.Sleep(time.Second)
+					if isStop {
+						return
+					}
+				}
+				updateDB()
+			}
+		}
+	}()
+}
+
+func Stop() {
+	isStop = true
+	time.Sleep(time.Millisecond * 1500)
+}
+
+// https://github.com/yourok-0001/releases/raw/master/torr/rutor.ls
+func updateDB() {
+	log.TLogln("Update rutor db")
+	filename := filepath.Join(settings.Path, "rutor.tmp")
+	out, err := os.Create(filename)
+	if err != nil {
+		log.TLogln("Error create file rutor.tmp:", err)
+		return
+	}
+	defer out.Close()
+	resp, err := http.Get("https://github.com/yourok-0001/releases/raw/master/torr/rutor.ls")
+	if err != nil {
+		log.TLogln("Error connect to rutor db:", err)
+		return
+	}
+	defer resp.Body.Close()
+	_, err = io.Copy(out, resp.Body)
+	if err != nil {
+		log.TLogln("Error download rutor db:", err)
+		return
+	}
+
+	err = os.Remove(filepath.Join(settings.Path, "rutor.ls"))
+	if err != nil && !os.IsNotExist(err) {
+		log.TLogln("Error remove old rutor db:", err)
+		return
+	}
+	err = os.Rename(filename, filepath.Join(settings.Path, "rutor.ls"))
+	if err != nil {
+		log.TLogln("Error rename rutor db:", err)
+		return
+	}
+	loadDB()
+}
+
+func loadDB() {
+	log.TLogln("Load rutor db")
+	buf, err := os.ReadFile("rutor.ls")
+	if err == nil {
+		r := flate.NewReader(bytes.NewReader(buf))
+		buf, err = io.ReadAll(r)
+		r.Close()
+		if err == nil {
+			var ftors []*models.TorrentDetails
+			err = json.Unmarshal(buf, &ftors)
+			if err == nil {
+				torrs = ftors
+				log.TLogln("Index rutor db")
+				torrsearch.NewIndex(torrs)
+			}
+		}
+	}
+}
+
+func Search(query string) []*models.TorrentDetails {
+	matchedIDs := torrsearch.Search(query)
+	if len(matchedIDs) == 0 {
+		return nil
+	}
+	var list []*models.TorrentDetails
+	for _, id := range matchedIDs {
+		list = append(list, torrs[id])
+	}
+
+	hash := utils.ClearStr(query)
+
+	sort.Slice(list, func(i, j int) bool {
+		lhash := utils.ClearStr(strings.ToLower(list[i].Name+list[i].GetNames())) + strconv.Itoa(list[i].Year)
+		lev1 := levenshtein.ComputeDistance(hash, lhash)
+		lhash = utils.ClearStr(strings.ToLower(list[j].Name+list[j].GetNames())) + strconv.Itoa(list[j].Year)
+		lev2 := levenshtein.ComputeDistance(hash, lhash)
+		if lev1 == lev2 {
+			return list[j].CreateDate.Before(list[i].CreateDate)
+		}
+		return lev1 < lev2
+	})
+	return list
+}

server/rutor/torrsearch/filter.go

@@ -0,0 +1,99 @@
+package torrsearch
+
+import (
+	"strings"
+
+	snowballeng "github.com/kljensen/snowball/english"
+	snowballru "github.com/kljensen/snowball/russian"
+)
+
+// lowercaseFilter returns a slice of tokens normalized to lower case.
+func lowercaseFilter(tokens []string) []string {
+	r := make([]string, len(tokens))
+	for i, token := range tokens {
+		r[i] = replaceChars(strings.ToLower(token))
+	}
+	return r
+}
+
+// stopwordFilter returns a slice of tokens with stop words removed.
+func stopwordFilter(tokens []string) []string {
+	r := make([]string, 0, len(tokens))
+	for _, token := range tokens {
+		if !isStopWord(token) {
+			r = append(r, token)
+		}
+	}
+	return r
+}
+
+// stemmerFilter returns a slice of stemmed tokens.
+func stemmerFilter(tokens []string) []string {
+	r := make([]string, len(tokens))
+	for i, token := range tokens {
+		worden := snowballeng.Stem(token, false)
+		wordru := snowballru.Stem(token, false)
+		if wordru == "" || worden == "" {
+			continue
+		}
+		if wordru != token {
+			r[i] = wordru
+		} else {
+			r[i] = worden
+		}
+	}
+	return r
+}
+
+func replaceChars(word string) string {
+	out := []rune(word)
+	for i, r := range out {
+		if r == 'ё' {
+			out[i] = 'е'
+		}
+	}
+	return string(out)
+}
+
+func isStopWord(word string) bool {
+	switch word {
+	case "a", "about", "above", "after", "again", "against", "all", "am", "an",
+		"and", "any", "are", "as", "at", "be", "because", "been", "before",
+		"being", "below", "between", "both", "but", "by", "can", "did", "do",
+		"does", "doing", "don", "down", "during", "each", "few", "for", "from",
+		"further", "had", "has", "have", "having", "he", "her", "here", "hers",
+		"herself", "him", "himself", "his", "how", "i", "if", "in", "into", "is",
+		"it", "its", "itself", "just", "me", "more", "most", "my", "myself",
+		"no", "nor", "not", "now", "of", "off", "on", "once", "only", "or",
+		"other", "our", "ours", "ourselves", "out", "over", "own", "s", "same",
+		"she", "should", "so", "some", "such", "t", "than", "that", "the", "their",
+		"theirs", "them", "themselves", "then", "there", "these", "they",
+		"this", "those", "through", "to", "too", "under", "until", "up",
+		"very", "was", "we", "were", "what", "when", "where", "which", "while",
+		"who", "whom", "why", "will", "with", "you", "your", "yours", "yourself",
+		"yourselves", "и", "в", "во", "не", "что", "он", "на", "я", "с",
+		"со", "как", "а", "то", "все", "она", "так", "его",
+		"но", "да", "ты", "к", "у", "же", "вы", "за", "бы",
+		"по", "только", "ее", "мне", "было", "вот", "от",
+		"меня", "еще", "нет", "о", "из", "ему", "теперь",
+		"когда", "даже", "ну", "вдруг", "ли", "если", "уже",
+		"или", "ни", "быть", "был", "него", "до", "вас",
+		"нибудь", "опять", "уж", "вам", "ведь", "там", "потом",
+		"себя", "ничего", "ей", "может", "они", "тут", "где",
+		"есть", "надо", "ней", "для", "мы", "тебя", "их",
+		"чем", "была", "сам", "чтоб", "без", "будто", "чего",
+		"раз", "тоже", "себе", "под", "будет", "ж", "тогда",
+		"кто", "этот", "того", "потому", "этого", "какой",
+		"совсем", "ним", "здесь", "этом", "один", "почти",
+		"мой", "тем", "чтобы", "нее", "сейчас", "были", "куда",
+		"зачем", "всех", "никогда", "можно", "при", "наконец",
+		"два", "об", "другой", "хоть", "после", "над", "больше",
+		"тот", "через", "эти", "нас", "про", "всего", "них",
+		"какая", "много", "разве", "три", "эту", "моя",
+		"впрочем", "хорошо", "свою", "этой", "перед", "иногда",
+		"лучше", "чуть", "том", "нельзя", "такой", "им", "более",
+		"всегда", "конечно", "всю", "между":
+		return true
+	}
+	return false
+}

server/rutor/torrsearch/index.go

@@ -0,0 +1,76 @@
+package torrsearch
+
+import (
+	"log"
+	"server/rutor/models"
+	"strconv"
+)
+
+// Index is an inverted Index. It maps tokens to document IDs.
+type Index map[string][]int
+
+var idx Index
+
+func NewIndex(torrs []*models.TorrentDetails) {
+	log.Println("Index torrs")
+	idx = make(Index)
+	idx.add(torrs)
+}
+
+func Search(text string) []int {
+	return idx.search(text)
+}
+
+func (idx Index) add(torrs []*models.TorrentDetails) {
+	for ID, torr := range torrs {
+		for _, token := range analyze(torr.Name + " " + torr.GetNames() + " " + strconv.Itoa(torr.Year)) {
+			ids := idx[token]
+			if ids != nil && ids[len(ids)-1] == ID {
+				// Don't add same ID twice.
+				continue
+			}
+			idx[token] = append(ids, ID)
+		}
+	}
+}
+
+// intersection returns the set intersection between a and b.
+// a and b have to be sorted in ascending order and contain no duplicates.
+func intersection(a []int, b []int) []int {
+	maxLen := len(a)
+	if len(b) > maxLen {
+		maxLen = len(b)
+	}
+	r := make([]int, 0, maxLen)
+	var i, j int
+	for i < len(a) && j < len(b) {
+		if a[i] < b[j] {
+			i++
+		} else if a[i] > b[j] {
+			j++
+		} else {
+			r = append(r, a[i])
+			i++
+			j++
+		}
+	}
+	return r
+}
+
+// Search queries the Index for the given text.
+func (idx Index) search(text string) []int {
+	var r []int
+	for _, token := range analyze(text) {
+		if ids, ok := idx[token]; ok {
+			if r == nil {
+				r = ids
+			} else {
+				r = intersection(r, ids)
+			}
+		} else {
+			// Token doesn't exist.
+			return nil
+		}
+	}
+	return r
+}

server/rutor/torrsearch/tokenizer.go

@@ -0,0 +1,23 @@
+package torrsearch
+
+import (
+	"strings"
+	"unicode"
+)
+
+// tokenize returns a slice of tokens for the given text.
+func tokenize(text string) []string {
+	return strings.FieldsFunc(text, func(r rune) bool {
+		// Split on any character that is not a letter or a number.
+		return !unicode.IsLetter(r) && !unicode.IsNumber(r)
+	})
+}
+
+// analyze analyzes the text and returns a slice of tokens.
+func analyze(text string) []string {
+	tokens := tokenize(text)
+	tokens = lowercaseFilter(tokens)
+	tokens = stopwordFilter(tokens)
+	tokens = stemmerFilter(tokens)
+	return tokens
+}

server/rutor/utils/utils.go

@@ -0,0 +1,14 @@
+package utils
+
+import "strings"
+
+func ClearStr(str string) string {
+	ret := ""
+	str = strings.ToLower(str)
+	for _, r := range str {
+		if (r >= '0' && r <= '9') || (r >= 'a' && r <= 'z') || (r >= 'а' && r <= 'я') || r == 'ё' {
+			ret = ret + string(r)
+		}
+	}
+	return ret
+}

server/web/api/rutor.go

@@ -0,0 +1,12 @@
+package api
+
+import (
+	"github.com/gin-gonic/gin"
+	"server/rutor"
+)
+
+func rutorSearch(c *gin.Context) {
+	query := c.Query("query")
+	list := rutor.Search(query)
+	c.JSON(200, list)
+}