zardoz/matrix.go

package main

import (
	"bufio"

	"log"
	"math"
	"os"
	"strings"
	"sync"
)

//ByControlPlane contains all the channels we need.
type ByControlPlane struct {
	BadTokens   chan string
	GoodTokens  chan string
	StatsTokens chan string
}

type bScore struct {
	BadScore  float64
	GoodScore float64
}

type bMap struct {
	bScores map[string]bScore
	busy    sync.Mutex
}

//ControPlane is the variabile
var ControPlane ByControlPlane

//ByClassifier is the structure containing our Pseudo-Bayes classifier.
type ByClassifier struct {
	STATS  sync.Map
	Matrix bMap
}

//AddStats adds the statistics after proper blocking.
func (c *ByClassifier) AddStats(action string) {

	var one int64 = 1

	if v, ok := c.STATS.Load(action); ok {
		c.STATS.Store(action, v.(int64)+1)
	} else {
		c.STATS.Store(action, one)
	}

}

//IsBAD inserts a bad key in the right place.
func (c *ByClassifier) IsBAD(key string) {

	c.Matrix.busy.Lock()
	defer c.Matrix.busy.Unlock()

	var t bScore

	if val, ok := c.Matrix.bScores[key]; ok {
		t.BadScore = val.BadScore + 1
		t.GoodScore = val.GoodScore
	} else {
		t.BadScore = 1
		t.GoodScore = 0
	}

	c.Matrix.bScores[key] = t

}

//IsGOOD inserts the key in the right place.
func (c *ByClassifier) IsGOOD(key string) {

	c.Matrix.busy.Lock()
	defer c.Matrix.busy.Unlock()

	var t bScore

	if val, ok := c.Matrix.bScores[key]; ok {
		t.GoodScore = val.GoodScore + 1
		t.BadScore = val.BadScore
	} else {
		t.BadScore = 0
		t.GoodScore = 1
	}

	c.Matrix.bScores[key] = t

}

//Posterior calculates Shannon based entropy using bad and good as different distributions
func (c *ByClassifier) Posterior(hdr string) map[string]float64 {

	c.Matrix.busy.Lock()
	defer c.Matrix.busy.Unlock()

	tokens := strings.Fields(sanitizeHeaders(hdr))
	lenTokens := float64(len(tokens))

	ff := make(map[string]float64)

	if lenTokens == 0 {
		ff["BAD"] = 0.5
		ff["GOOD"] = 0.5
		return ff
	}

	log.Println("Start classification of: ", tokens)

	var hBadM, hGoodM float64

	for _, tk := range tokens {
		if val, ok := c.Matrix.bScores[tk]; ok {
			if val.BadScore > 0 {
				hBadM += val.BadScore * math.Log2(val.BadScore)
			}
			if val.GoodScore > 0 {
				hGoodM += val.GoodScore * math.Log2(val.GoodScore)
			}
		}
	}

	hBadM = math.Log2(lenTokens) - (hBadM / lenTokens)
	hGoodM = math.Log2(lenTokens) - (hGoodM / lenTokens)

	maxScore := math.Abs(hBadM) + math.Abs(hGoodM)

	if maxScore == 0 {
		maxScore = 1
	}

	ff["BAD"] = math.Abs(hBadM) / maxScore
	ff["GOOD"] = math.Abs(hGoodM) / maxScore

	log.Println("Entropies: ", ff)

	return ff

}

func (c *ByClassifier) enroll() {

	ControPlane.BadTokens = make(chan string, 2048)
	ControPlane.GoodTokens = make(chan string, 2048)
	ControPlane.StatsTokens = make(chan string, 2048)

	c.Matrix.busy.Lock()
	c.Matrix.bScores = make(map[string]bScore)
	c.Matrix.busy.Unlock()

	c.readInitList("blacklist.txt", "BAD")
	c.readInitList("whitelist.txt", "GOOD")

	go c.readBadTokens()
	go c.readGoodTokens()
	go c.readStatsTokens()

	log.Println("Classifier populated...")

}

func (c *ByClassifier) readBadTokens() {

	log.Println("Start reading BAD tokens")

	for token := range ControPlane.BadTokens {
		log.Println("Received BAD Token: ", token)
		c.IsBAD(token)
	}

}

func (c *ByClassifier) readGoodTokens() {

	log.Println("Start reading GOOD tokens")

	for token := range ControPlane.GoodTokens {
		log.Println("Received GOOD Token: ", token)
		c.IsGOOD(token)
	}

}

func (c *ByClassifier) readStatsTokens() {

	log.Println("Start reading STATS tokens")

	for token := range ControPlane.StatsTokens {
		c.AddStats(token)
	}

}

func (c *ByClassifier) readInitList(filePath, class string) {

	inFile, err := os.Open(filePath)
	if err != nil {
		log.Println(err.Error() + `: ` + filePath)
		return
	}
	defer inFile.Close()

	scanner := bufio.NewScanner(inFile)
	for scanner.Scan() {

		if len(scanner.Text()) > 3 {
			switch class {
			case "BAD":
				log.Println("Loading into Blacklist: ", scanner.Text()) // the line
				c.IsBAD(scanner.Text())
			case "GOOD":
				log.Println("Loading into Whitelist: ", scanner.Text()) // the line
				c.IsGOOD(scanner.Text())
			}
		}
	}

}