Enhance the function to find an ideal VM OS image

go.mod

@@ -3,7 +3,7 @@ module github.com/cloud-barista/cm-beetle
 go 1.21.6
 
 require (
-	github.com/cloud-barista/cb-store v0.8.0
+	github.com/cloud-barista/cb-store v0.8.2
 	github.com/cloud-barista/cb-tumblebug v0.8.12
 	github.com/cloud-barista/cm-honeybee/agent v0.0.0-20240530070023-ee1c0a77fbf7
 	github.com/docker/docker v26.1.3+incompatible
@@ -26,7 +26,7 @@ require (
 require (
 	github.com/KyleBanks/depth v1.2.1 // indirect
 	github.com/bwmarrin/snowflake v0.3.0 // indirect
-	github.com/cloud-barista/cb-log v0.8.0 // indirect
+	github.com/cloud-barista/cb-log v0.8.2 // indirect
 	github.com/coreos/go-semver v0.3.1 // indirect
 	github.com/coreos/go-systemd/v22 v22.5.0 // indirect
 	github.com/docker/go-connections v0.5.0 // indirect

go.sum

@@ -16,8 +16,12 @@ github.com/chzyer/readline v1.5.0/go.mod h1:x22KAscuvRqlLoK9CsoYsmxoXZMMFVyOl86c
 github.com/chzyer/test v0.0.0-20210722231415-061457976a23/go.mod h1:Q3SI9o4m/ZMnBNeIyt5eFwwo7qiLfzFZmjNmxjkiQlU=
 github.com/cloud-barista/cb-log v0.8.0 h1:ArWCs1EgpoD3ZnBgcC4cAw5ufI/JHmFKfJswlv4whgk=
 github.com/cloud-barista/cb-log v0.8.0/go.mod h1:nGgfTFMPwl1MpCO3FBjexUkNdOYA0BNJoyM9Pd0lMms=
+github.com/cloud-barista/cb-log v0.8.2 h1:hPCbLj6TW6m9UWlq002sDuGgxKFVp68w4V3k493+MxY=
+github.com/cloud-barista/cb-log v0.8.2/go.mod h1:nGgfTFMPwl1MpCO3FBjexUkNdOYA0BNJoyM9Pd0lMms=
 github.com/cloud-barista/cb-store v0.8.0 h1:0K47YEf+K3wx18D+m0XirlDbdTz229XxsTXw6WACjRA=
 github.com/cloud-barista/cb-store v0.8.0/go.mod h1:6NuA5TdeVRExd59ULXv6LEhm4EE0ODn9L820g4VqApo=
+github.com/cloud-barista/cb-store v0.8.2 h1:7excW7SX0Xw9Xxo0xO4HkndjOYonh4z6mFzNqYN3XH4=
+github.com/cloud-barista/cb-store v0.8.2/go.mod h1:GBTRuOApzMWSENFSgIPtrbWUKSwP30bn90gWE0ENUD8=
 github.com/cloud-barista/cb-tumblebug v0.8.12 h1:uc5aOI9q5XhMq7GQ9s7WyWyLoxtklcqib/gdDaSgumw=
 github.com/cloud-barista/cb-tumblebug v0.8.12/go.mod h1:yOwgw7jXqMdSSgC2g0TvgCG1WyXNw6Q7J6JGfbsqEOw=
 github.com/cloud-barista/cm-honeybee/agent v0.0.0-20240530070023-ee1c0a77fbf7 h1:4r7YI8FlWfk2H/H+fICupvzEjCP+4cCkqG5CMzvhDdo=

pkg/core/recommendation/recommendation.go

@@ -3,7 +3,6 @@ package recommendation
 import (
 	"encoding/json"
 	"fmt"
-	"os"
 	"regexp"
 	"strings"
 
@@ -14,14 +13,15 @@ import (
 	"github.com/cloud-barista/cm-beetle/pkg/core/common"
 	"github.com/go-resty/resty/v2"
 	"github.com/rs/zerolog/log"
+	"github.com/spf13/viper"
 )
 
 func Recommend(srcInfra []infra.Infra) (cloudmodel.InfraMigrationReq, error) {
 
 	// Initialize resty client with basic auth
 	client := resty.New()
-	apiUser := os.Getenv("API_USERNAME")
-	apiPass := os.Getenv("API_PASSWORD")
+	apiUser := viper.GetString("api.username")
+	apiPass := viper.GetString("api.password")
 	client.SetBasicAuth(apiUser, apiPass)
 
 	// set endpoint
@@ -260,7 +260,7 @@ func Recommend(srcInfra []infra.Infra) (cloudmodel.InfraMigrationReq, error) {
 		log.Debug().Msg("keywords for the VM OS image recommendation: " + keywords)
 
 		// Select VM OS image via LevenshteinDistance-based text similarity
-		delimiters1 := []string{" ", "-", "_", ",", "(", ")", "[", "]"}
+		delimiters1 := []string{" ", "-", "_", ",", "(", ")", "[", "]", "/"}
 		delimiters2 := delimiters1
 		vmOsImageId := FindBestVmOsImage(keywords, delimiters1, resMcisDynamicCheck.ReqCheck[0].Image, delimiters2)
 
@@ -301,7 +301,7 @@ func FindBestVmOsImage(keywords string, kwDelimiters []string, vmImages []mcir.T
 	var highestScore float64
 
 	for _, image := range vmImages {
-		score := calculateSimilarity(keywords, kwDelimiters, image.CspImageName, imgDelimiters)
+		score := CalculateSimilarity(keywords, kwDelimiters, image.CspImageName, imgDelimiters)
 		if score > highestScore {
 			highestScore = score
 			bestVmOsImageID = image.Id
@@ -314,27 +314,37 @@ func FindBestVmOsImage(keywords string, kwDelimiters []string, vmImages []mcir.T
 	return bestVmOsImageID
 }
 
-// calculateSimilarity calculates the similarity between two texts based on word similarities
-func calculateSimilarity(text1 string, delimiters1 []string, text2 string, delimiters2 []string) float64 {
+// CalculateSimilarity calculates the similarity between two texts based on word similarities
+func CalculateSimilarity(text1 string, delimiters1 []string, text2 string, delimiters2 []string) float64 {
+
 	words1 := splitToArray(text1, delimiters1)
 	words2 := splitToArray(text2, delimiters2)
 
+	log.Trace().Msgf("From text 1: %s", text1)
+	log.Trace().Msgf("To word array 1: %v", words1)
+	log.Trace().Msgf("From text 2: %s", text2)
+	log.Trace().Msgf("To word array 2: %v", words2)
+
 	// Calculate the similarity between two texts based on word similarities
 	totalSimilarity := 0.0
 	for _, word1 := range words1 {
 		bestMatch := 0.0
+		bestMatchWord := ""
 		for _, word2 := range words2 {
-			similarity := wordSimilarity(word1, word2)
+			// similarity := CalculateSimilarityByLevenshteinDistance(word1, word2)
+			similarity := CalculateSimilarityBySequenceMatcher(word1, word2)
 			if similarity > bestMatch {
 				bestMatch = similarity
-			}
+				bestMatchWord = word2
 
-			totalSimilarity += activateByReLU(bestMatch, 0.3)
+			}
 		}
+		log.Trace().Msgf("Best match for '%s': '%s' (similarity: %.2f)", word1, bestMatchWord, bestMatch)
+		totalSimilarity += activateByReLU(bestMatch, 0.5)
 	}
 
 	// Normalize by the number of words
-	return totalSimilarity / float64(len(words1))
+	return totalSimilarity // / float64(len(words1))
 }
 
 func splitToArray(text string, delimiters []string) []string {
@@ -348,24 +358,41 @@ func splitToArray(text string, delimiters []string) []string {
 	text = strings.ToLower(text)
 
 	// Create a regular expression pattern for the delimiters
-	pattern := strings.Join(delimiters, "|")
+	escapedDelimiters := make([]string, len(delimiters))
+	for i, d := range delimiters {
+		escapedDelimiters[i] = regexp.QuoteMeta(d)
+	}
+	pattern := strings.Join(escapedDelimiters, "|")
 	re := regexp.MustCompile(pattern)
 
 	// Split text by the delimiters
 	arr := re.Split(text, -1)
 
-	return arr
+	// Remove empty strings resulting from the split
+	result := []string{}
+	for _, str := range arr {
+		if str != "" {
+			result = append(result, str)
+		}
+	}
+
+	return result
 }
 
-// wordSimilarity calculates the similarity between two words based on Levenshtein distance
-func wordSimilarity(word1, word2 string) float64 {
+// CalculateSimilarityByLevenshteinDistance calculates the similarity between two words based on Levenshtein distance
+func CalculateSimilarityByLevenshteinDistance(word1, word2 string) float64 {
 	maxLen := float64(max(len(word1), len(word2)))
 	if maxLen == 0 {
 		return 1.0
 	}
 	return 1.0 - float64(LevenshteinDistance(word1, word2))/maxLen
 }
 
+// CalculateSimilarityBySequenceMatcher calculates the similarity between two words based on Levenshtein distance
+func CalculateSimilarityBySequenceMatcher(word1, word2 string) float64 {
+	return SequenceMatcher(word1, word2)
+}
+
 // activateByReLU applies a ReLU function that activates if the similarity is greater than a threshold
 func activateByReLU(similarity, threshold float64) float64 {
 	if similarity > threshold {
@@ -421,6 +448,37 @@ func min(a, b int) int {
 	return b
 }
 
+// longestCommonSubstring finds the longest common substring between two strings.
+func longestCommonSubstring(s1, s2 string) string {
+	l1, l2 := len(s1), len(s2)
+	matrix := make([][]int, l1+1)
+	for i := range matrix {
+		matrix[i] = make([]int, l2+1)
+	}
+
+	longest := 0
+	endIndex := l1
+	for i := 1; i <= l1; i++ {
+		for j := 1; j <= l2; j++ {
+			if s1[i-1] == s2[j-1] {
+				matrix[i][j] = matrix[i-1][j-1] + 1
+				if matrix[i][j] > longest {
+					longest = matrix[i][j]
+					endIndex = i
+				}
+			}
+		}
+	}
+
+	return s1[endIndex-longest : endIndex]
+}
+
+// SequenceMatcher calculates the similarity ratio between two strings.
+func SequenceMatcher(text1, text2 string) float64 {
+	lcs := longestCommonSubstring(text1, text2)
+	return 2.0 * float64(len(lcs)) / float64(len(text1)+len(text2))
+}
+
 // // JaccardSimilarity calculates the Jaccard similarity between two strings
 // func JaccardSimilarity(text1, delimiter1, text2, delimiter2 string) float64 {
 

pkg/example/levenshtein-distance/main.go

@@ -0,0 +1,48 @@
+package main
+
+import (
+	"fmt"
+
+	"github.com/cloud-barista/cm-beetle/pkg/core/recommendation"
+)
+
+func main() {
+
+	compareWordSet := []struct {
+		str1 string
+		str2 string
+	}{
+		{"22.04", "22.04.1"},
+		{"22.04", "20.04"},
+		{"20.04", "18.04"},
+		{"x86_64", "amd64"},
+		{"hvm-ssd", "ssd"},
+		{"hvm-ssd", "hdd"},
+	}
+
+	for _, set := range compareWordSet {
+		fmt.Printf("Comparing '%s' with '%s':\n", set.str1, set.str2)
+		fmt.Printf(" - LevenshteinDistance, Similarity ratio: %.2f\n", recommendation.CalculateSimilarityByLevenshteinDistance(set.str1, set.str2))
+		fmt.Printf(" - SequenceMatcher, Similarity ratio: %.2f\n", recommendation.CalculateSimilarityBySequenceMatcher(set.str1, set.str2))
+		fmt.Println("--------------------------------------------------------")
+	}
+
+	keywords := "Ubuntu 22.04.4 LTS (Jammy Jellyfish) x86_64 SSD"
+	vmImages := []string{
+		"ubuntu/images/hvm-ssd/ubuntu-jammy-22.04-amd64-server-20220609",
+		"ubuntu/images/hvm-ssd/ubuntu-bionic-18.04-amd64-server-20191002",
+	}
+
+	// Select VM OS image via LevenshteinDistance-based text similarity
+	delimiters1 := []string{" ", "-", "_", ",", "(", ")", "[", "]", "/"}
+	delimiters2 := delimiters1
+
+	for _, image := range vmImages {
+		fmt.Printf("Comparing keywords with VM Image:\n")
+		fmt.Printf("Keywords: '%s'\n", keywords)
+		fmt.Printf("VM Image: '%s'\n", image)
+		score := recommendation.CalculateSimilarity(keywords, delimiters1, image, delimiters2)
+		fmt.Printf(" - Similarity Score: %.2f\n", score)
+		fmt.Println("--------------------------------------------------------")
+	}
+}