spray/pkg/utils.go

package pkg

import (
	"encoding/json"
	"github.com/chainreactors/gogo/v2/pkg/fingers"
	"github.com/chainreactors/ipcs"
	"github.com/chainreactors/parsers"
	"github.com/chainreactors/parsers/iutils"
	"github.com/chainreactors/words/mask"
	"math/rand"
	"net/url"
	"os"
	"path"
	"strconv"
	"strings"
	"time"
	"unsafe"
)

var (
	Md5Fingers     map[string]string = make(map[string]string)
	Mmh3Fingers    map[string]string = make(map[string]string)
	Rules          map[string]string = make(map[string]string)
	ActivePath     []string
	Fingers        fingers.Fingers
	ExtractRegexps = map[string][]*parsers.Extractor{}
	Extractors     = make(parsers.Extractors)

	BadExt = []string{".js", ".css", ".scss", ".,", ".jpeg", ".jpg", ".png", ".gif", ".svg", ".vue", ".ts", ".swf", ".pdf", ".mp4", ".zip", ".rar"}
	BadURL = []string{";", "}", "\\n", "webpack://", "{", "www.w3.org", ".src", ".url", ".att", ".href", "location.href", "javascript:", "location:", ".createObject", ":location", ".path"}

	ContentTypeMap = map[string]string{
		"application/javascript":   "js",
		"application/json":         "json",
		"application/xml":          "xml",
		"application/octet-stream": "bin",
		"application/atom+xml":     "atom",
		"application/msword":       "doc",
		"application/pdf":          "pdf",
		"image/gif":                "gif",
		"image/jpeg":               "jpg",
		"image/png":                "png",
		"image/svg+xml":            "svg",
		"text/css":                 "css",
		"text/plain":               "txt",
		"text/html":                "html",
		"audio/mpeg":               "mp3",
		"video/mp4":                "mp4",
		"video/ogg":                "ogg",
		"video/webm":               "webm",
		"video/x-ms-wmv":           "wmv",
		"video/avi":                "avi",
		"image/x-icon":             "ico",
	}
)

func RemoveDuplication(arr []string) []string {
	set := make(map[string]struct{}, len(arr))
	j := 0
	for _, v := range arr {
		_, ok := set[v]
		if ok {
			continue
		}
		set[v] = struct{}{}
		arr[j] = v
		j++
	}

	return arr[:j]
}

// 判断是否存在标准输入数据
func HasStdin() bool {
	stat, err := os.Stdin.Stat()
	if err != nil {
		return false
	}

	isPipedFromChrDev := (stat.Mode() & os.ModeCharDevice) == 0
	isPipedFromFIFO := (stat.Mode() & os.ModeNamedPipe) != 0

	return isPipedFromChrDev || isPipedFromFIFO
}

const letters = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"

var src = rand.NewSource(time.Now().UnixNano())

const (
	// 6 bits to represent a letter index
	letterIdBits = 6
	// All 1-bits as many as letterIdBits
	letterIdMask = 1<<letterIdBits - 1
	letterIdMax  = 63 / letterIdBits
)

func RandPath() string {
	n := 16
	b := make([]byte, n)
	// A rand.Int63() generates 63 random bits, enough for letterIdMax letters!
	for i, cache, remain := n-1, src.Int63(), letterIdMax; i >= 0; {
		if remain == 0 {
			cache, remain = src.Int63(), letterIdMax
		}
		if idx := int(cache & letterIdMask); idx < len(letters) {
			b[i] = letters[idx]
			i--
		}
		cache >>= letterIdBits
		remain--
	}
	return *(*string)(unsafe.Pointer(&b))
}

func RandHost() string {
	n := 8
	b := make([]byte, n)
	// A rand.Int63() generates 63 random bits, enough for letterIdMax letters!
	for i, cache, remain := n-1, src.Int63(), letterIdMax; i >= 1; {
		if remain == 0 {
			cache, remain = src.Int63(), letterIdMax
		}
		if idx := int(cache & letterIdMask); idx < len(letters) {
			b[i] = letters[idx]
			i--
		}
		cache >>= letterIdBits
		remain--
	}

	b[5] = byte(0x2e)
	return *(*string)(unsafe.Pointer(&b))
}

func LoadTemplates() error {
	var err error
	// load fingers
	Fingers, err = fingers.LoadFingers(LoadConfig("http"))
	if err != nil {
		return err
	}

	for _, finger := range Fingers {
		err := finger.Compile(ipcs.ParsePorts)
		if err != nil {
			return err
		}
	}

	for _, f := range Fingers {
		for _, rule := range f.Rules {
			if rule.SendDataStr != "" {
				ActivePath = append(ActivePath, rule.SendDataStr)
			}
			if rule.Favicon != nil {
				for _, mmh3 := range rule.Favicon.Mmh3 {
					Mmh3Fingers[mmh3] = f.Name
				}
				for _, md5 := range rule.Favicon.Md5 {
					Md5Fingers[md5] = f.Name
				}
			}
		}
	}

	// load rule
	var data map[string]interface{}
	err = json.Unmarshal(LoadConfig("rule"), &data)
	if err != nil {
		return err
	}
	for k, v := range data {
		Rules[k] = v.(string)
	}

	// load mask
	var keywords map[string]interface{}
	err = json.Unmarshal(LoadConfig("mask"), &keywords)
	if err != nil {
		return err
	}

	for k, v := range keywords {
		t := make([]string, len(v.([]interface{})))
		for i, vv := range v.([]interface{}) {
			t[i] = iutils.ToString(vv)
		}
		mask.SpecialWords[k] = t
	}

	var extracts []*parsers.Extractor
	err = json.Unmarshal(LoadConfig("extract"), &extracts)
	if err != nil {
		return err
	}

	for _, extract := range extracts {
		extract.Compile()

		ExtractRegexps[extract.Name] = []*parsers.Extractor{extract}
		for _, tag := range extract.Tags {
			if _, ok := ExtractRegexps[tag]; !ok {
				ExtractRegexps[tag] = []*parsers.Extractor{extract}
			} else {
				ExtractRegexps[tag] = append(ExtractRegexps[tag], extract)
			}
		}
	}
	return nil
}

func FingerDetect(content []byte) parsers.Frameworks {
	frames := make(parsers.Frameworks)
	for _, finger := range Fingers {
		// sender置空, 所有的发包交给spray的pool
		frame, _, ok := fingers.FingerMatcher(finger, map[string]interface{}{"content": content}, 0, nil)
		if ok {
			frames[frame.Name] = frame
		}
	}
	return frames
}

func filterJs(u string) bool {
	if commonFilter(u) {
		return true
	}

	return false
}

func filterUrl(u string) bool {
	if commonFilter(u) {
		return true
	}

	parsed, err := url.Parse(u)
	if err != nil {
		return true
	} else {
		ext := path.Ext(parsed.Path)
		for _, e := range BadExt {
			if strings.EqualFold(e, ext) {
				return true
			}
		}
	}
	return false
}

func formatURL(u string) string {
	// 去掉frag与params, 节约url.parse性能, 防止带参数造成意外的影响
	if strings.Contains(u, "2f") || strings.Contains(u, "2F") {
		u = strings.ReplaceAll(u, "\\u002F", "/")
		u = strings.ReplaceAll(u, "\\u002f", "/")
		u = strings.ReplaceAll(u, "%252F", "/")
		u = strings.ReplaceAll(u, "%252f", "/")
		u = strings.ReplaceAll(u, "%2f", "/")
		u = strings.ReplaceAll(u, "%2F", "/")
	}

	u = strings.TrimRight(u, "\\")
	if i := strings.Index(u, "?"); i != -1 {
		return u[:i]
	}
	if i := strings.Index(u, "#"); i != -1 {
		return u[:i]
	}
	return u
}

func commonFilter(u string) bool {
	if strings.HasPrefix(u, "http") && len(u) < 15 {
		return true
	}

	for _, bad := range BadURL {
		if strings.Contains(u, bad) {
			return true
		}
	}
	return false
}

func BakGenerator(domain string) []string {
	var possibilities []string
	for first, _ := range domain {
		for last, _ := range domain[first:] {
			p := domain[first : first+last+1]
			if !iutils.StringsContains(possibilities, p) {
				possibilities = append(possibilities, p)
			}
		}
	}
	return possibilities
}

var MbTable = []uint16{
	0x0000, 0xC0C1, 0xC181, 0x0140, 0xC301, 0x03C0, 0x0280, 0xC241,
	0xC601, 0x06C0, 0x0780, 0xC741, 0x0500, 0xC5C1, 0xC481, 0x0440,
	0xCC01, 0x0CC0, 0x0D80, 0xCD41, 0x0F00, 0xCFC1, 0xCE81, 0x0E40,
	0x0A00, 0xCAC1, 0xCB81, 0x0B40, 0xC901, 0x09C0, 0x0880, 0xC841,
	0xD801, 0x18C0, 0x1980, 0xD941, 0x1B00, 0xDBC1, 0xDA81, 0x1A40,
	0x1E00, 0xDEC1, 0xDF81, 0x1F40, 0xDD01, 0x1DC0, 0x1C80, 0xDC41,
	0x1400, 0xD4C1, 0xD581, 0x1540, 0xD701, 0x17C0, 0x1680, 0xD641,
	0xD201, 0x12C0, 0x1380, 0xD341, 0x1100, 0xD1C1, 0xD081, 0x1040,
	0xF001, 0x30C0, 0x3180, 0xF141, 0x3300, 0xF3C1, 0xF281, 0x3240,
	0x3600, 0xF6C1, 0xF781, 0x3740, 0xF501, 0x35C0, 0x3480, 0xF441,
	0x3C00, 0xFCC1, 0xFD81, 0x3D40, 0xFF01, 0x3FC0, 0x3E80, 0xFE41,
	0xFA01, 0x3AC0, 0x3B80, 0xFB41, 0x3900, 0xF9C1, 0xF881, 0x3840,
	0x2800, 0xE8C1, 0xE981, 0x2940, 0xEB01, 0x2BC0, 0x2A80, 0xEA41,
	0xEE01, 0x2EC0, 0x2F80, 0xEF41, 0x2D00, 0xEDC1, 0xEC81, 0x2C40,
	0xE401, 0x24C0, 0x2580, 0xE541, 0x2700, 0xE7C1, 0xE681, 0x2640,
	0x2200, 0xE2C1, 0xE381, 0x2340, 0xE101, 0x21C0, 0x2080, 0xE041,
	0xA001, 0x60C0, 0x6180, 0xA141, 0x6300, 0xA3C1, 0xA281, 0x6240,
	0x6600, 0xA6C1, 0xA781, 0x6740, 0xA501, 0x65C0, 0x6480, 0xA441,
	0x6C00, 0xACC1, 0xAD81, 0x6D40, 0xAF01, 0x6FC0, 0x6E80, 0xAE41,
	0xAA01, 0x6AC0, 0x6B80, 0xAB41, 0x6900, 0xA9C1, 0xA881, 0x6840,
	0x7800, 0xB8C1, 0xB981, 0x7940, 0xBB01, 0x7BC0, 0x7A80, 0xBA41,
	0xBE01, 0x7EC0, 0x7F80, 0xBF41, 0x7D00, 0xBDC1, 0xBC81, 0x7C40,
	0xB401, 0x74C0, 0x7580, 0xB541, 0x7700, 0xB7C1, 0xB681, 0x7640,
	0x7200, 0xB2C1, 0xB381, 0x7340, 0xB101, 0x71C0, 0x7080, 0xB041,
	0x5000, 0x90C1, 0x9181, 0x5140, 0x9301, 0x53C0, 0x5280, 0x9241,
	0x9601, 0x56C0, 0x5780, 0x9741, 0x5500, 0x95C1, 0x9481, 0x5440,
	0x9C01, 0x5CC0, 0x5D80, 0x9D41, 0x5F00, 0x9FC1, 0x9E81, 0x5E40,
	0x5A00, 0x9AC1, 0x9B81, 0x5B40, 0x9901, 0x59C0, 0x5880, 0x9841,
	0x8801, 0x48C0, 0x4980, 0x8941, 0x4B00, 0x8BC1, 0x8A81, 0x4A40,
	0x4E00, 0x8EC1, 0x8F81, 0x4F40, 0x8D01, 0x4DC0, 0x4C80, 0x8C41,
	0x4400, 0x84C1, 0x8581, 0x4540, 0x8701, 0x47C0, 0x4680, 0x8641,
	0x8201, 0x42C0, 0x4380, 0x8341, 0x4100, 0x81C1, 0x8081, 0x4040}

func CRC16Hash(data []byte) uint16 {
	var crc16 uint16
	crc16 = 0xffff
	for _, v := range data {
		n := uint8(uint16(v) ^ crc16)
		crc16 >>= 8
		crc16 ^= MbTable[n]
	}
	return crc16
}

func UniqueHash(bl *Baseline) uint16 {
	// 由host+状态码+重定向url+content-type+title+length舍去个位与十位组成的hash
	// body length可能会导致一些误报, 目前没有更好的解决办法
	return CRC16Hash([]byte(bl.Host + strconv.Itoa(bl.Status) + bl.RedirectURL + bl.ContentType + bl.Title + strconv.Itoa(bl.BodyLength/100*100)))
}