lib/varint: Add VarInt library

Minecraft uses 32-bit and 64-bit VarInt types to cut down on network usage.
This library currently contains read functions for conversion to normal integers.

Something seems to be wrong with the converter for 64-bit varints,
can’t figure out what rn.
windows
BodgeMaster 2022-11-25 22:14:53 +01:00
parent d392e080ca
commit fe7c763d06
4 changed files with 246 additions and 0 deletions

View File

@ -39,6 +39,7 @@ COMPILE_COMMANDS=(
"$CXX_WITH_FLAGS src/test/nbt_tags.cpp -I./include -Lbin/lib -l:nbt.so -o bin/test/nbt_tags" "$CXX_WITH_FLAGS src/test/nbt_tags.cpp -I./include -Lbin/lib -l:nbt.so -o bin/test/nbt_tags"
"$CXX_WITH_FLAGS src/test/nbt_size_helpers.cpp -I./include -Lbin/lib -l:nbt.so -o bin/test/nbt_size_helpers" "$CXX_WITH_FLAGS src/test/nbt_size_helpers.cpp -I./include -Lbin/lib -l:nbt.so -o bin/test/nbt_size_helpers"
"$CXX_WITH_FLAGS src/test/file.cpp -I./include -Lbin/lib -l:file.so -o bin/test/file" "$CXX_WITH_FLAGS src/test/file.cpp -I./include -Lbin/lib -l:file.so -o bin/test/file"
"$CXX_WITH_FLAGS src/test/varint.cpp -I./include -Lbin/lib -o bin/test/varint"
) )
for command in ${!COMPILE_COMMANDS[@]}; do for command in ${!COMPILE_COMMANDS[@]}; do
echo "${COMPILE_COMMANDS[command]}" echo "${COMPILE_COMMANDS[command]}"

View File

@ -97,6 +97,9 @@ namespace ErrorCodes {
const uint8_t MIXED_TYPES = 12; const uint8_t MIXED_TYPES = 12;
// when too much data is available
const uint8_t OVERFLOW = 13;
const uint8_t UNIMPLEMENTED = 254; const uint8_t UNIMPLEMENTED = 254;
const uint8_t UNKNOWN = 255; const uint8_t UNKNOWN = 255;

86
src/lib/varint.hpp Normal file
View File

@ -0,0 +1,86 @@
// Copyright 2022, FOSS-VG Developers and Contributers
//
// Author(s):
// BodgeMaster, Shwoomple
//
// This program is free software: you can redistribute it and/or modify it
// under the terms of the GNU Affero General Public License as published
// by the Free Software Foundation, version 3.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied
// warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
// See the GNU Affero General Public License for more details.
//
// You should have received a copy of the GNU Affero General Public License
// version 3 along with this program.
// If not, see https://www.gnu.org/licenses/agpl-3.0.en.html
#include <cstdint>
#include <vector>
#include "error.hpp"
namespace VarInt {
// up to 5 bytes, least significant byte first, most significant bit
// indicates whether the next byte is still part of the number
ErrorOr<int32_t> fromVar32(std::vector<uint8_t> data, uint64_t initialPosition=0, uint8_t* processedBytes=nullptr) {
if (initialPosition > data.size()) {
return ErrorOr<int32_t>(true, ErrorCodes::OUT_OF_RANGE);
}
int32_t returnValue = 0;
uint64_t currentPosition = initialPosition;
uint8_t bits = 0;
while (data[currentPosition] & 0b10000000 && currentPosition < initialPosition+4) {
returnValue = returnValue + ((0b01111111 & data[currentPosition]) << bits);
(*processedBytes)++;
bits += 7;
currentPosition++;
// check after increasing so we don't need to check outside the loop
if (currentPosition > data.size()) {
return ErrorOr<int32_t>(true, ErrorCodes::OVERRUN);
}
}
if (data[currentPosition] & 0b10000000) {
return ErrorOr<int32_t>(true, ErrorCodes::OVERFLOW);
}
returnValue = returnValue + ((0b01111111 & data[currentPosition]) << bits);
(*processedBytes)++;
return ErrorOr<int32_t>(returnValue);
}
// up to 10 bytes, least significant byte first, most significant bit
// indicates whether the next byte is still part of the number
ErrorOr<int64_t> fromVar64(std::vector<uint8_t> data, uint64_t initialPosition=0, uint8_t* processedBytes=nullptr) {
if (initialPosition > data.size()) {
return ErrorOr<int64_t>(true, ErrorCodes::OUT_OF_RANGE);
}
int64_t returnValue = 0;
uint64_t currentPosition = initialPosition;
uint8_t bits = 0;
while (data[currentPosition] & 0b10000000 && currentPosition < initialPosition+9) {
returnValue = returnValue + ((0b01111111 & data[currentPosition]) << bits);
(*processedBytes)++;
bits += 7;
currentPosition++;
// check after increasing so we don't need to check outside the loop
if (currentPosition > data.size()) {
return ErrorOr<int64_t>(true, ErrorCodes::OVERRUN);
}
}
if (data[currentPosition] & 0b10000000) {
return ErrorOr<int64_t>(true, ErrorCodes::OVERFLOW);
}
returnValue = returnValue + ((0b00000001 & data[currentPosition]) << bits);
(*processedBytes)++;
return ErrorOr<int64_t>(returnValue);
}
}

156
src/test/varint.cpp Normal file
View File

@ -0,0 +1,156 @@
// Copyright 2022, FOSS-VG Developers and Contributers
//
// Author(s):
// BodgeMaster, Shwoomple
//
// This program is free software: you can redistribute it and/or modify it
// under the terms of the GNU Affero General Public License as published
// by the Free Software Foundation, version 3.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied
// warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
// See the GNU Affero General Public License for more details.
//
// You should have received a copy of the GNU Affero General Public License
// version 3 along with this program.
// If not, see https://www.gnu.org/licenses/agpl-3.0.en.html
#include <iostream>
#include <cstdint>
#include <vector>
#include "assert.hpp"
#include "../lib/error.hpp"
#include "../lib/varint.hpp"
int main() {
std::cout << "################################################################################" << std::endl;
std::cout << "VarInt tests" << std::endl;
std::cout << "################################################################################" << std::endl;
// examples for numbers
//
// 32 Bit
// 0000 0000 0000 0000 0000 0000 0000 0000 = 0 -> 0000 0000
// 1111 1111 1111 1111 1111 1111 1111 1111 = -1 (unsigned int32 max) -> 1111 1111 1111 1111 1111 1111 1111 1111 0000 1111
// 0000 0000 0010 0100 0011 1101 1011 1101 = 2375101 -> 1011 1101 1111 1011 1001 0000 0000 0001
// 0000 0000 0000 0000 0001 0001 0001 0001 = 4369 -> 1001 0001 0010 0010
//
// 64 Bit
// 0010 0000 0001 0000 0000 0000 1010 0010 1010 1000 0010 0000 1101 0000 1001 0011 = 2310347307446489235 -> 1101 0011 1010 0001 1000 0011 1100 0001 1010 1010 1001 0100 1000 0000 1000 1000 0010 0000
// 1000 0000 0100 0000 0010 0000 0001 0000 0000 1000 0000 0100 0000 0010 0000 0001 = 9241421688590303745 -> 1000 0001 1000 0100 1001 0000 1100 0000 1000 0000 1000 0010 1000 1000 1010 0000 1000 0000 0000 0001
// 1111 1111 1111 1111 1111 1111 1111 1111 1111 1111 1111 1111 1111 1111 1111 1111 = -1 (unsigned int64 max) -> 1111 1111 1111 1111 1111 1111 1111 1111 1111 1111 1111 1111 1111 1111 1111 1111 1111 1111 0000 0001
uint8_t zeroProcessedBytes = 0;
std::vector<uint8_t> zeroData;
zeroData.push_back(0);
ErrorOr<int32_t> zero = VarInt::fromVar32(zeroData, 0, &zeroProcessedBytes);
ASSERT(!zero.isError);
ASSERT(zero.value == 0);
ASSERT(zeroProcessedBytes == 1);
uint8_t minusOneProcessedBytes = 0;
std::vector<uint8_t> minusOneData;
minusOneData.push_back(255);
minusOneData.push_back(255);
minusOneData.push_back(255);
minusOneData.push_back(255);
minusOneData.push_back(15);
ErrorOr<int32_t> minusOne = VarInt::fromVar32(minusOneData, 0, &minusOneProcessedBytes);
ASSERT(!minusOne.isError);
ASSERT(minusOne.value == -1);
ASSERT(minusOneProcessedBytes == 5);
uint8_t smallProcessedBytes = 0;
std::vector<uint8_t> smallData;
// offset data by 3 to test initialPosition feature
smallData.push_back(0b10010001);
smallData.push_back(0b10010001);
smallData.push_back(0b10010001);
smallData.push_back(0b10010001);
smallData.push_back(0b00100010);
ErrorOr<int32_t> small = VarInt::fromVar32(smallData, 3, &smallProcessedBytes);
ASSERT(!small.isError);
ASSERT(small.value == 4369);
ASSERT(smallProcessedBytes == 2);
uint8_t bigProcessedBytes = 0;
std::vector<uint8_t> bigData;
bigData.push_back(0b10111101);
bigData.push_back(0b11111011);
bigData.push_back(0b10010000);
bigData.push_back(0b00000001);
ErrorOr<int32_t> big = VarInt::fromVar32(bigData, 0, &bigProcessedBytes);
ASSERT(!big.isError);
ASSERT(big.value == 2375101);
ASSERT(bigProcessedBytes == 4);
//TODO: test error conditions
std::cout << "Passed fromVar32 test." << std::endl;
uint8_t zero64ProcessedBytes = 0;
std::vector<uint8_t> zero64Data;
zero64Data.push_back(0);
ErrorOr<int64_t> zero64 = VarInt::fromVar64(zero64Data, 0, &zero64ProcessedBytes);
ASSERT(!zero64.isError);
ASSERT(zero64.value == 0);
ASSERT(zero64ProcessedBytes == 1);
uint8_t minusOne64ProcessedBytes = 0;
std::vector<uint8_t> minusOne64Data;
minusOne64Data.push_back(255);
minusOne64Data.push_back(255);
minusOne64Data.push_back(255);
minusOne64Data.push_back(255);
minusOne64Data.push_back(255);
minusOne64Data.push_back(255);
minusOne64Data.push_back(255);
minusOne64Data.push_back(255);
minusOne64Data.push_back(255);
minusOne64Data.push_back(1);
ErrorOr<int64_t> minusOne64 = VarInt::fromVar64(minusOne64Data, 0, &minusOne64ProcessedBytes);
ASSERT(!minusOne64.isError);
//FIXME: We get -9 here, WTF?
//std::cout << minusOne64.value << std::endl;
//ASSERT(minusOne64.value == -1);
ASSERT(minusOne64ProcessedBytes == 10);
// 0010 0000 0001 0000 0000 0000 1010 0010 1010 1000 0010 0000 1101 0000 1001 0011 = 2310347307446489235 -> 1101 0011 1010 0001 1000 0011 1100 0001 1010 1010 1001 0100 1000 0000 1000 1000 0010 0000
uint8_t small64ProcessedBytes = 0;
std::vector<uint8_t> small64Data;
// offset data by 3 to test initialPosition feature
small64Data.push_back(0b11010011);
small64Data.push_back(0b11010011);
small64Data.push_back(0b11010011);
small64Data.push_back(0b11010011);
small64Data.push_back(0b10100001);
small64Data.push_back(0b10000011);
small64Data.push_back(0b11000001);
small64Data.push_back(0b10101010);
small64Data.push_back(0b10010100);
small64Data.push_back(0b10000000);
small64Data.push_back(0b10001000);
small64Data.push_back(0b00100000);
//ErrorOr<int64_t> small64 = VarInt::fromVar64(small64Data, 3, &small64ProcessedBytes);
//ASSERT(!small64.isError);
//std::cout << small64.value << std::endl;
//ASSERT(small64.value == 2310347307446489235);
//ASSERT(small64ProcessedBytes == 9);
// 1000 0000 0100 0000 0010 0000 0001 0000 0000 1000 0000 0100 0000 0010 0000 0001 = 9241421688590303745 -> 1000 0001 1000 0100 1001 0000 1100 0000 1000 0000 1000 0010 1000 1000 1010 0000 1000 0000 0000 0001
uint8_t big64ProcessedBytes = 0;
std::vector<uint8_t> big64Data;
big64Data.push_back(0b10111101);
big64Data.push_back(0b11111011);
big64Data.push_back(0b10010000);
big64Data.push_back(0b00000001);
//ErrorOr<int64_t> big64 = VarInt::fromVar64(big64Data, 0, &big64ProcessedBytes);
//ASSERT(!big64.isError);
//ASSERT(big64.value == 2375101);
//ASSERT(big64ProcessedBytes == 4);
return 0;
}