Initial commit: docker compose config

server/rutor/torrsearch/filter.go

@@ -0,0 +1,68 @@
+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", "am", "an", "and", "are", "as", "at", "be",
+		"by", "did", "do", "is", "of", "or", "s", "so", "t",
+		"и", "в", "с", "со", "а", "но", "к", "у",
+		"же", "бы", "по", "от", "о", "из", "ну",
+		"ли", "ни", "нибудь", "уж", "ведь", "ж", "об":
+		return true
+	}
+	return false
+}

server/rutor/torrsearch/index.go

@@ -0,0 +1,77 @@
+package torrsearch
+
+import (
+	"server/rutor/models"
+)
+
+// Index is an inverted Index. It maps tokens to document IDs.
+type Index map[string][]int
+
+var idx Index
+
+func NewIndex(torrs []*models.TorrentDetails) {
+	idx = make(Index)
+	idx.add(torrs)
+}
+
+func Search(text string) []int {
+	return idx.search(text)
+}
+
+func GetIDX() Index {
+	return idx
+}
+
+func (idx Index) add(torrs []*models.TorrentDetails) {
+	for ID, torr := range torrs {
+		for _, token := range analyze(torr.Title) {
+			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
+}