use std::io;
use std::io::{Read, Write};
use super::BinarySerializable;
pub fn serialize_vint_u128(mut val: u128, output: &mut Vec<u8>) {
loop {
let next_byte: u8 = (val % 128u128) as u8;
val /= 128u128;
if val == 0 {
output.push(next_byte | STOP_BIT);
return;
} else {
output.push(next_byte);
}
}
}
#[derive(Clone, Copy, Debug, Eq, PartialEq)]
pub struct VIntU128(pub u128);
impl BinarySerializable for VIntU128 {
fn serialize<W: Write + ?Sized>(&self, writer: &mut W) -> io::Result<()> {
let mut buffer = vec![];
serialize_vint_u128(self.0, &mut buffer);
writer.write_all(&buffer)
}
fn deserialize<R: Read>(reader: &mut R) -> io::Result<Self> {
let mut bytes = reader.bytes();
let mut result = 0u128;
let mut shift = 0u64;
loop {
match bytes.next() {
Some(Ok(b)) => {
result |= u128::from(b % 128u8) << shift;
if b >= STOP_BIT {
return Ok(VIntU128(result));
}
shift += 7;
}
_ => {
return Err(io::Error::new(
io::ErrorKind::InvalidData,
"Reach end of buffer while reading VInt",
));
}
}
}
}
}
#[derive(Clone, Copy, Debug, Eq, PartialEq)]
pub struct VInt(pub u64);
const STOP_BIT: u8 = 128;
#[inline]
pub fn serialize_vint_u32(val: u32, buf: &mut [u8; 8]) -> &[u8] {
const START_2: u64 = 1 << 7;
const START_3: u64 = 1 << 14;
const START_4: u64 = 1 << 21;
const START_5: u64 = 1 << 28;
const MASK_1: u64 = 127;
const MASK_2: u64 = MASK_1 << 7;
const MASK_3: u64 = MASK_2 << 7;
const MASK_4: u64 = MASK_3 << 7;
const MASK_5: u64 = MASK_4 << 7;
let val = u64::from(val);
const STOP_BIT: u64 = 128u64;
let (res, num_bytes) = if val < START_2 {
(val | STOP_BIT, 1)
} else if val < START_3 {
(
(val & MASK_1) | ((val & MASK_2) << 1) | (STOP_BIT << (8)),
2,
)
} else if val < START_4 {
(
(val & MASK_1) | ((val & MASK_2) << 1) | ((val & MASK_3) << 2) | (STOP_BIT << (8 * 2)),
3,
)
} else if val < START_5 {
(
(val & MASK_1)
| ((val & MASK_2) << 1)
| ((val & MASK_3) << 2)
| ((val & MASK_4) << 3)
| (STOP_BIT << (8 * 3)),
4,
)
} else {
(
(val & MASK_1)
| ((val & MASK_2) << 1)
| ((val & MASK_3) << 2)
| ((val & MASK_4) << 3)
| ((val & MASK_5) << 4)
| (STOP_BIT << (8 * 4)),
5,
)
};
*buf = res.to_le_bytes();
&buf[0..num_bytes]
}
fn vint_len(data: &[u8]) -> usize {
for (i, &val) in data.iter().enumerate().take(5) {
if val >= STOP_BIT {
return i + 1;
}
}
panic!("Corrupted data. Invalid VInt 32");
}
pub fn read_u32_vint(data: &mut &[u8]) -> u32 {
let (result, vlen) = read_u32_vint_no_advance(data);
*data = &data[vlen..];
result
}
pub fn read_u32_vint_no_advance(data: &[u8]) -> (u32, usize) {
let vlen = vint_len(data);
let mut result = 0u32;
let mut shift = 0u64;
for &b in &data[..vlen] {
result |= u32::from(b & 127u8) << shift;
shift += 7;
}
(result, vlen)
}
pub fn write_u32_vint<W: io::Write>(val: u32, writer: &mut W) -> io::Result<()> {
let mut buf = [0u8; 8];
let data = serialize_vint_u32(val, &mut buf);
writer.write_all(data)
}
impl VInt {
pub fn val(&self) -> u64 {
self.0
}
pub fn deserialize_u64<R: Read>(reader: &mut R) -> io::Result<u64> {
VInt::deserialize(reader).map(|vint| vint.0)
}
pub fn serialize_into_vec(&self, output: &mut Vec<u8>) {
let mut buffer = [0u8; 10];
let num_bytes = self.serialize_into(&mut buffer);
output.extend(&buffer[0..num_bytes]);
}
pub fn serialize_into(&self, buffer: &mut [u8; 10]) -> usize {
let mut remaining = self.0;
for (i, b) in buffer.iter_mut().enumerate() {
let next_byte: u8 = (remaining % 128u64) as u8;
remaining /= 128u64;
if remaining == 0u64 {
*b = next_byte | STOP_BIT;
return i + 1;
} else {
*b = next_byte;
}
}
unreachable!();
}
}
impl BinarySerializable for VInt {
fn serialize<W: Write + ?Sized>(&self, writer: &mut W) -> io::Result<()> {
let mut buffer = [0u8; 10];
let num_bytes = self.serialize_into(&mut buffer);
writer.write_all(&buffer[0..num_bytes])
}
fn deserialize<R: Read>(reader: &mut R) -> io::Result<Self> {
let mut bytes = reader.bytes();
let mut result = 0u64;
let mut shift = 0u64;
loop {
match bytes.next() {
Some(Ok(b)) => {
result |= u64::from(b % 128u8) << shift;
if b >= STOP_BIT {
return Ok(VInt(result));
}
shift += 7;
}
_ => {
return Err(io::Error::new(
io::ErrorKind::InvalidData,
"Reach end of buffer while reading VInt",
));
}
}
}
}
}
#[cfg(test)]
mod tests {
use super::{serialize_vint_u32, BinarySerializable, VInt};
fn aux_test_vint(val: u64) {
let mut v = [14u8; 10];
let num_bytes = VInt(val).serialize_into(&mut v);
for el in &v[num_bytes..10] {
assert_eq!(el, &14u8);
}
assert!(num_bytes > 0);
if num_bytes < 10 {
assert!(1u64 << (7 * num_bytes) > val);
}
if num_bytes > 1 {
assert!(1u64 << (7 * (num_bytes - 1)) <= val);
}
let serdeser_val = VInt::deserialize(&mut &v[..]).unwrap();
assert_eq!(val, serdeser_val.0);
}
#[test]
fn test_vint() {
aux_test_vint(0);
aux_test_vint(1);
aux_test_vint(5);
aux_test_vint(u64::MAX);
for i in 1..9 {
let power_of_128 = 1u64 << (7 * i);
aux_test_vint(power_of_128 - 1u64);
aux_test_vint(power_of_128);
aux_test_vint(power_of_128 + 1u64);
}
aux_test_vint(10);
}
fn aux_test_serialize_vint_u32(val: u32) {
let mut buffer = [0u8; 10];
let mut buffer2 = [0u8; 8];
let len_vint = VInt(val as u64).serialize_into(&mut buffer);
let res2 = serialize_vint_u32(val, &mut buffer2);
assert_eq!(&buffer[..len_vint], res2, "array wrong for {val}");
}
#[test]
fn test_vint_u32() {
aux_test_serialize_vint_u32(0);
aux_test_serialize_vint_u32(1);
aux_test_serialize_vint_u32(5);
for i in 1..3 {
let power_of_128 = 1u32 << (7 * i);
aux_test_serialize_vint_u32(power_of_128 - 1u32);
aux_test_serialize_vint_u32(power_of_128);
aux_test_serialize_vint_u32(power_of_128 + 1u32);
}
aux_test_serialize_vint_u32(u32::MAX);
}
}