背景

因业务需要使用ZUC算法，GitHub上又没有对ZUC256相对应的Go语言的实现。
吃水不忘挖井人，在这里感谢GmSSL及BouncyCastle两个强大的密码学库！
本ZUC256的编写，参考了这两个库及中科院软件院发布的祖冲之算法白皮书而实现的。
其中IV的长度有歧义，我这里做了兼容并包的处理方式，IV为23位时，使用的是GmSSL的逻辑，IV为25位时，使用的是白皮书中给定的长度逻辑。
代码要用的话，直接拿去用，给我GitHub点个小星星⭐就行，传送门

本代码有且仅遵守MIT协议！！！
本代码有且仅遵守MIT协议！！！
本代码有且仅遵守MIT协议！！！

运行效果

最右边为go的实现，测试与左边两个工具的加密结果做比对！

代码

没有废话，直接干货！

package zuc256import ("fmt"
)/** 本代码有且仅遵守MIT协议！！！*/const AlgorithmName = "ZUC256"
const IVSize = 25
const KeySize = 32var lFSR [16]uint32
var keyStream []uint32
var r1 = uint32(0)
var r2 = uint32(0)var s0 = []byte{0x3e, 0x72, 0x5b, 0x47, 0xca, 0xe0, 0x00, 0x33, 0x04, 0xd1, 0x54, 0x98, 0x09, 0xb9, 0x6d, 0xcb,0x7b, 0x1b, 0xf9, 0x32, 0xaf, 0x9d, 0x6a, 0xa5, 0xb8, 0x2d, 0xfc, 0x1d, 0x08, 0x53, 0x03, 0x90,0x4d, 0x4e, 0x84, 0x99, 0xe4, 0xce, 0xd9, 0x91, 0xdd, 0xb6, 0x85, 0x48, 0x8b, 0x29, 0x6e, 0xac,0xcd, 0xc1, 0xf8, 0x1e, 0x73, 0x43, 0x69, 0xc6, 0xb5, 0xbd, 0xfd, 0x39, 0x63, 0x20, 0xd4, 0x38,0x76, 0x7d, 0xb2, 0xa7, 0xcf, 0xed, 0x57, 0xc5, 0xf3, 0x2c, 0xbb, 0x14, 0x21, 0x06, 0x55, 0x9b,0xe3, 0xef, 0x5e, 0x31, 0x4f, 0x7f, 0x5a, 0xa4, 0x0d, 0x82, 0x51, 0x49, 0x5f, 0xba, 0x58, 0x1c,0x4a, 0x16, 0xd5, 0x17, 0xa8, 0x92, 0x24, 0x1f, 0x8c, 0xff, 0xd8, 0xae, 0x2e, 0x01, 0xd3, 0xad,0x3b, 0x4b, 0xda, 0x46, 0xeb, 0xc9, 0xde, 0x9a, 0x8f, 0x87, 0xd7, 0x3a, 0x80, 0x6f, 0x2f, 0xc8,0xb1, 0xb4, 0x37, 0xf7, 0x0a, 0x22, 0x13, 0x28, 0x7c, 0xcc, 0x3c, 0x89, 0xc7, 0xc3, 0x96, 0x56,0x07, 0xbf, 0x7e, 0xf0, 0x0b, 0x2b, 0x97, 0x52, 0x35, 0x41, 0x79, 0x61, 0xa6, 0x4c, 0x10, 0xfe,0xbc, 0x26, 0x95, 0x88, 0x8a, 0xb0, 0xa3, 0xfb, 0xc0, 0x18, 0x94, 0xf2, 0xe1, 0xe5, 0xe9, 0x5d,0xd0, 0xdc, 0x11, 0x66, 0x64, 0x5c, 0xec, 0x59, 0x42, 0x75, 0x12, 0xf5, 0x74, 0x9c, 0xaa, 0x23,0x0e, 0x86, 0xab, 0xbe, 0x2a, 0x02, 0xe7, 0x67, 0xe6, 0x44, 0xa2, 0x6c, 0xc2, 0x93, 0x9f, 0xf1,0xf6, 0xfa, 0x36, 0xd2, 0x50, 0x68, 0x9e, 0x62, 0x71, 0x15, 0x3d, 0xd6, 0x40, 0xc4, 0xe2, 0x0f,0x8e, 0x83, 0x77, 0x6b, 0x25, 0x05, 0x3f, 0x0c, 0x30, 0xea, 0x70, 0xb7, 0xa1, 0xe8, 0xa9, 0x65,0x8d, 0x27, 0x1a, 0xdb, 0x81, 0xb3, 0xa0, 0xf4, 0x45, 0x7a, 0x19, 0xdf, 0xee, 0x78, 0x34, 0x60,
}var s1 = []byte{0x55, 0xc2, 0x63, 0x71, 0x3b, 0xc8, 0x47, 0x86, 0x9f, 0x3c, 0xda, 0x5b, 0x29, 0xaa, 0xfd, 0x77,0x8c, 0xc5, 0x94, 0x0c, 0xa6, 0x1a, 0x13, 0x00, 0xe3, 0xa8, 0x16, 0x72, 0x40, 0xf9, 0xf8, 0x42,0x44, 0x26, 0x68, 0x96, 0x81, 0xd9, 0x45, 0x3e, 0x10, 0x76, 0xc6, 0xa7, 0x8b, 0x39, 0x43, 0xe1,0x3a, 0xb5, 0x56, 0x2a, 0xc0, 0x6d, 0xb3, 0x05, 0x22, 0x66, 0xbf, 0xdc, 0x0b, 0xfa, 0x62, 0x48,0xdd, 0x20, 0x11, 0x06, 0x36, 0xc9, 0xc1, 0xcf, 0xf6, 0x27, 0x52, 0xbb, 0x69, 0xf5, 0xd4, 0x87,0x7f, 0x84, 0x4c, 0xd2, 0x9c, 0x57, 0xa4, 0xbc, 0x4f, 0x9a, 0xdf, 0xfe, 0xd6, 0x8d, 0x7a, 0xeb,0x2b, 0x53, 0xd8, 0x5c, 0xa1, 0x14, 0x17, 0xfb, 0x23, 0xd5, 0x7d, 0x30, 0x67, 0x73, 0x08, 0x09,0xee, 0xb7, 0x70, 0x3f, 0x61, 0xb2, 0x19, 0x8e, 0x4e, 0xe5, 0x4b, 0x93, 0x8f, 0x5d, 0xdb, 0xa9,0xad, 0xf1, 0xae, 0x2e, 0xcb, 0x0d, 0xfc, 0xf4, 0x2d, 0x46, 0x6e, 0x1d, 0x97, 0xe8, 0xd1, 0xe9,0x4d, 0x37, 0xa5, 0x75, 0x5e, 0x83, 0x9e, 0xab, 0x82, 0x9d, 0xb9, 0x1c, 0xe0, 0xcd, 0x49, 0x89,0x01, 0xb6, 0xbd, 0x58, 0x24, 0xa2, 0x5f, 0x38, 0x78, 0x99, 0x15, 0x90, 0x50, 0xb8, 0x95, 0xe4,0xd0, 0x91, 0xc7, 0xce, 0xed, 0x0f, 0xb4, 0x6f, 0xa0, 0xcc, 0xf0, 0x02, 0x4a, 0x79, 0xc3, 0xde,0xa3, 0xef, 0xea, 0x51, 0xe6, 0x6b, 0x18, 0xec, 0x1b, 0x2c, 0x80, 0xf7, 0x74, 0xe7, 0xff, 0x21,0x5a, 0x6a, 0x54, 0x1e, 0x41, 0x31, 0x92, 0x35, 0xc4, 0x33, 0x07, 0x0a, 0xba, 0x7e, 0x0e, 0x34,0x88, 0xb1, 0x98, 0x7c, 0xf3, 0x3d, 0x60, 0x6c, 0x7b, 0xca, 0xd3, 0x1f, 0x32, 0x65, 0x04, 0x28,0x64, 0xbe, 0x85, 0x9b, 0x2f, 0x59, 0x8a, 0xd7, 0xb0, 0x25, 0xac, 0xaf, 0x12, 0x03, 0xe2, 0xf2,
}var zuc256D = [][]byte{{0x22, 0x2F, 0x24, 0x2A, 0x6D, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x52, 0x10, 0x30},{0x22, 0x2F, 0x25, 0x2A, 0x6D, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x52, 0x10, 0x30},{0x23, 0x2F, 0x24, 0x2A, 0x6D, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x52, 0x10, 0x30},{0x23, 0x2F, 0x25, 0x2A, 0x6D, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x52, 0x10, 0x30},
}func Init(key []byte, iv []byte) {ivLen := len(iv)keyLen := len(key)if ivLen == 0 {fmt.Printf("%s Init requires an IV.\n", AlgorithmName)return}if keyLen == 0 {fmt.Printf("%s Init requires an Key.\n", AlgorithmName)return}if ivLen != 23 && ivLen != 25 {fmt.Printf("%s requires exactly 23 or %d bytes of IV.\n", AlgorithmName, IVSize)return}if keyLen != KeySize {fmt.Printf("%s requires exactly %d bytes of Key.\n", AlgorithmName, KeySize)return}setKey(key, iv, 0)
}func setKey(key []byte, iv []byte, macBits int) {ivLen := len(iv)_r1 := uint32(0)_r2 := uint32(0)x0 := uint32(0)x1 := uint32(0)x2 := uint32(0)w := uint32(0)u := uint32(0)v := uint32(0)var d []byteIV17 := byte(0x00)IV18 := byte(0x00)IV19 := byte(0x00)IV20 := byte(0x00)IV21 := byte(0x00)IV22 := byte(0x00)IV23 := byte(0x00)IV24 := byte(0x00)if ivLen == 23 {IV17 = iv[17] >> 2IV18 = ((iv[17] & 0x3) << 4) | (iv[18] >> 4)IV19 = ((iv[18] & 0xf) << 2) | (iv[19] >> 6)IV20 = iv[19] & 0x3fIV21 = iv[20] >> 2IV22 = ((iv[20] & 0x3) << 4) | (iv[21] >> 4)IV23 = ((iv[21] & 0xf) << 2) | (iv[22] >> 6)IV24 = iv[22] & 0x3f} else {IV17 = iv[17]IV18 = iv[18]IV19 = iv[19]IV20 = iv[20]IV21 = iv[21]IV22 = iv[22]IV23 = iv[23]IV24 = iv[24]}if macBits/32 < 3 {d = zuc256D[macBits/32]} else {d = zuc256D[3]}lFSR[0] = zuc256MakeU31(uint32(key[0]), uint32(d[0]), uint32(key[21]), uint32(key[16]))lFSR[1] = zuc256MakeU31(uint32(key[1]), uint32(d[1]), uint32(key[22]), uint32(key[17]))lFSR[2] = zuc256MakeU31(uint32(key[2]), uint32(d[2]), uint32(key[23]), uint32(key[18]))lFSR[3] = zuc256MakeU31(uint32(key[3]), uint32(d[3]), uint32(key[24]), uint32(key[19]))lFSR[4] = zuc256MakeU31(uint32(key[4]), uint32(d[4]), uint32(key[25]), uint32(key[20]))lFSR[5] = zuc256MakeU31(uint32(iv[0]), uint32(d[5]|IV17), uint32(key[5]), uint32(key[26]))lFSR[6] = zuc256MakeU31(uint32(iv[1]), uint32(d[6]|IV18), uint32(key[6]), uint32(key[27]))lFSR[7] = zuc256MakeU31(uint32(iv[10]), uint32(d[7]|IV19), uint32(key[7]), uint32(iv[2]))lFSR[8] = zuc256MakeU31(uint32(key[8]), uint32(d[8]|IV20), uint32(iv[3]), uint32(iv[11]))lFSR[9] = zuc256MakeU31(uint32(key[9]), uint32(d[9]|IV21), uint32(iv[12]), uint32(iv[4]))lFSR[10] = zuc256MakeU31(uint32(iv[5]), uint32(d[10]|IV22), uint32(key[10]), uint32(key[28]))lFSR[11] = zuc256MakeU31(uint32(key[11]), uint32(d[11]|IV23), uint32(iv[6]), uint32(iv[13]))lFSR[12] = zuc256MakeU31(uint32(key[12]), uint32(d[12]|IV24), uint32(iv[7]), uint32(iv[14]))lFSR[13] = zuc256MakeU31(uint32(key[13]), uint32(d[13]), uint32(iv[15]), uint32(iv[8]))lFSR[14] = zuc256MakeU31(uint32(key[14]), uint32(d[14]|(key[31]>>4)), uint32(iv[16]), uint32(iv[9]))lFSR[15] = zuc256MakeU31(uint32(key[15]), uint32(d[15]|(key[31]&0x0F)), uint32(key[30]), uint32(key[29]))_r1 = 0_r2 = 0for i := 0; i < 32; i++ {bitReconstruction3(lFSR, &x0, &x1, &x2)w = f(&_r1, &_r2, &u, &v, x0, x1, x2)lFSRWithInitialisationMode(&lFSR, &v, w>>1)}bitReconstruction2(lFSR, &x1, &x2)f_(&_r1, &_r2, &u, &v, x1, x2)lFSRWithWorkMode(&lFSR, &v)r1 = _r1r2 = _r2
}func lFSRWithWorkMode(lFSR *[16]uint32, v *uint32) {a := uint64((*lFSR)[0])a += (uint64((*lFSR)[0])) << 8a += (uint64((*lFSR)[4])) << 20a += (uint64((*lFSR)[10])) << 21a += (uint64((*lFSR)[13])) << 17a += (uint64((*lFSR)[15])) << 15a = (a & 0x7fffffff) + (a >> 31)*v = uint32((a & 0x7fffffff) + (a >> 31))for j := 0; j < 15; j++ {(*lFSR)[j] = (*lFSR)[j+1]}(*lFSR)[15] = *v
}func lFSRWithInitialisationMode(lFSR *[16]uint32, v *uint32, u uint32) {*v = (*lFSR)[0]add31(v, rot31((*lFSR)[0], 8))add31(v, rot31((*lFSR)[4], 20))add31(v, rot31((*lFSR)[10], 21))add31(v, rot31((*lFSR)[13], 17))add31(v, rot31((*lFSR)[15], 15))add31(v, u)for j := 0; j < 15; j++ {(*lFSR)[j] = (*lFSR)[j+1]}(*lFSR)[15] = *v
}func DoFinal(input []byte) []byte {length := len(input)var output = make([]byte, length)processBytes(input, 0, length, &output)return output
}func processBytes(input []byte, inOff int, _len int, output *[]byte) {var block = make([]byte, 4)blockLen := len(block)inputLen := len(input)count := inOff + _lengenerateKeyStream(uint32(count))groupCount := count / 4i := 0for ; i < groupCount; i++ {putU32(&block, keyStream[i])memXor(output, i, input, block, blockLen)}if inputLen%4 != 0 {putU32(&block, keyStream[i])memXor(output, i, input, block, inputLen%4)}
}func generateKeyStream(_len uint32) {x0 := uint32(0)x1 := uint32(0)x2 := uint32(0)x3 := uint32(0)u := uint32(0)v := uint32(0)wLen := _len / 4if _len%4 != 0 {wLen++}keyStream = make([]uint32, wLen)for i := 0; i < int(wLen); i++ {bitReconstruction4(lFSR, &x0, &x1, &x2, &x3)keyStream[i] = x3 ^ f(&r1, &r2, &u, &v, x0, x1, x2)lFSRWithWorkMode(&lFSR, &v)}
}func memXor(_out *[]byte, index int, _in []byte, block []byte, _len int) {blockLen := len(block)i := index * blockLenj := 0for i < index*len(block)+_len {(*_out)[i] = _in[i] ^ block[j]i++j++}
}func putU32(block *[]byte, x uint32) {(*block)[0] = byte(x >> 24)(*block)[1] = byte(x >> 16)(*block)[2] = byte(x >> 8)(*block)[3] = byte(x)
}func rot31(a uint32, k int) uint32 {return (((a) << (k)) | ((a) >> (31 - (k)))) & 0x7FFFFFFF
}func add31(a *uint32, b uint32) {*a += b*a = (*a & 0x7fffffff) + (*a >> 31)
}func bitReconstruction2(lFSR [16]uint32, x1 *uint32, x2 *uint32) {*x1 = ((lFSR[11] & 0xFFFF) << 16) | (lFSR[9] >> 15)*x2 = ((lFSR[7] & 0xFFFF) << 16) | (lFSR[5] >> 15)
}func bitReconstruction3(lFSR [16]uint32, x0 *uint32, x1 *uint32, x2 *uint32) {*x0 = ((lFSR[15] & 0x7FFF8000) << 1) | (lFSR[14] & 0xFFFF)bitReconstruction2(lFSR, x1, x2)
}func bitReconstruction4(lFSR [16]uint32, x0 *uint32, x1 *uint32, x2 *uint32, x3 *uint32) {bitReconstruction3(lFSR, x0, x1, x2)*x3 = ((lFSR[2] & 0xFFFF) << 16) | (lFSR[0] >> 15)
}func f_(r1 *uint32, r2 *uint32, u *uint32, v *uint32, x1 uint32, x2 uint32) {W1 := *r1 + x1W2 := *r2 ^ x2*u = l1((W1 << 16) | (W2 >> 16))*v = l2((W2 << 16) | (W1 >> 16))*r1 = makeU32(uint32(s0[(*u)>>24]), uint32(s1[((*u)>>16)&0xFF]), uint32(s0[((*u)>>8)&0xFF]), uint32(s1[(*u)&0xFF]))*r2 = makeU32(uint32(s0[(*v)>>24]), uint32(s1[((*v)>>16)&0xFF]), uint32(s0[((*v)>>8)&0xFF]), uint32(s1[(*v)&0xFF]))
}func makeU32(a uint32, b uint32, c uint32, d uint32) uint32 {return ((a) << 24) | ((b) << 16) | ((c) << 8) | (d)
}func l1(x uint32) uint32 {r := (x) ^ rot32(x, 2) ^ rot32(x, 10) ^ rot32(x, 18) ^ rot32(x, 24)return r
}func l2(x uint32) uint32 {return (x) ^ rot32(x, 8) ^ rot32(x, 14) ^ rot32(x, 22) ^ rot32(x, 30)
}func rot32(a uint32, k int) uint32 {return ((a) << (k)) | ((a) >> (32 - (k)))
}func f(r1 *uint32, r2 *uint32, u *uint32, v *uint32, x0 uint32, x1 uint32, x2 uint32) uint32 {t := (x0 ^ *r1) + *r2f_(r1, r2, u, v, x1, x2)return t
}func zuc256MakeU31(a uint32, b uint32, c uint32, d uint32) uint32 {return (a << 23) | (b << 16) | (c << 8) | d
}