1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278
/*!
This module provides several integer oriented traits for converting between
both fixed size integers and integers whose size varies based on the target
(like `usize`).
The main design principle for this module is to centralize all uses of `as`.
The thinking here is that `as` makes it very easy to perform accidental lossy
conversions, and if we centralize all its uses here under more descriptive
higher level operations, its use and correctness becomes easier to audit.
This was copied mostly wholesale from `regex-automata`.
NOTE: for simplicity, we don't take target pointer width into account here for
`usize` conversions. Since we currently only panic in debug mode, skipping the
check when it can be proven it isn't needed at compile time doesn't really
matter. Now, if we wind up wanting to do as many checks as possible in release
mode, then we would want to skip those when we know the conversions are always
non-lossy.
*/
// We define a little more than what we need, but I'd rather just have
// everything via a consistent and uniform API then have holes.
#![allow(dead_code)]
pub(crate) trait U8 {
fn as_usize(self) -> usize;
}
impl U8 for u8 {
fn as_usize(self) -> usize {
usize::from(self)
}
}
pub(crate) trait U16 {
fn as_usize(self) -> usize;
fn low_u8(self) -> u8;
fn high_u8(self) -> u8;
}
impl U16 for u16 {
fn as_usize(self) -> usize {
usize::from(self)
}
fn low_u8(self) -> u8 {
self as u8
}
fn high_u8(self) -> u8 {
(self >> 8) as u8
}
}
pub(crate) trait U32 {
fn as_usize(self) -> usize;
fn low_u8(self) -> u8;
fn low_u16(self) -> u16;
fn high_u16(self) -> u16;
}
impl U32 for u32 {
#[inline]
fn as_usize(self) -> usize {
#[cfg(debug_assertions)]
{
usize::try_from(self).expect("u32 overflowed usize")
}
#[cfg(not(debug_assertions))]
{
self as usize
}
}
fn low_u8(self) -> u8 {
self as u8
}
fn low_u16(self) -> u16 {
self as u16
}
fn high_u16(self) -> u16 {
(self >> 16) as u16
}
}
pub(crate) trait U64 {
fn as_usize(self) -> usize;
fn low_u8(self) -> u8;
fn low_u16(self) -> u16;
fn low_u32(self) -> u32;
fn high_u32(self) -> u32;
}
impl U64 for u64 {
fn as_usize(self) -> usize {
#[cfg(debug_assertions)]
{
usize::try_from(self).expect("u64 overflowed usize")
}
#[cfg(not(debug_assertions))]
{
self as usize
}
}
fn low_u8(self) -> u8 {
self as u8
}
fn low_u16(self) -> u16 {
self as u16
}
fn low_u32(self) -> u32 {
self as u32
}
fn high_u32(self) -> u32 {
(self >> 32) as u32
}
}
pub(crate) trait I8 {
fn as_usize(self) -> usize;
fn to_bits(self) -> u8;
fn from_bits(n: u8) -> i8;
}
impl I8 for i8 {
fn as_usize(self) -> usize {
#[cfg(debug_assertions)]
{
usize::try_from(self).expect("i8 overflowed usize")
}
#[cfg(not(debug_assertions))]
{
self as usize
}
}
fn to_bits(self) -> u8 {
self as u8
}
fn from_bits(n: u8) -> i8 {
n as i8
}
}
pub(crate) trait I32 {
fn as_usize(self) -> usize;
fn to_bits(self) -> u32;
fn from_bits(n: u32) -> i32;
}
impl I32 for i32 {
fn as_usize(self) -> usize {
#[cfg(debug_assertions)]
{
usize::try_from(self).expect("i32 overflowed usize")
}
#[cfg(not(debug_assertions))]
{
self as usize
}
}
fn to_bits(self) -> u32 {
self as u32
}
fn from_bits(n: u32) -> i32 {
n as i32
}
}
pub(crate) trait I64 {
fn as_usize(self) -> usize;
fn to_bits(self) -> u64;
fn from_bits(n: u64) -> i64;
}
impl I64 for i64 {
fn as_usize(self) -> usize {
#[cfg(debug_assertions)]
{
usize::try_from(self).expect("i64 overflowed usize")
}
#[cfg(not(debug_assertions))]
{
self as usize
}
}
fn to_bits(self) -> u64 {
self as u64
}
fn from_bits(n: u64) -> i64 {
n as i64
}
}
pub(crate) trait Usize {
fn as_u8(self) -> u8;
fn as_u16(self) -> u16;
fn as_u32(self) -> u32;
fn as_u64(self) -> u64;
}
impl Usize for usize {
fn as_u8(self) -> u8 {
#[cfg(debug_assertions)]
{
u8::try_from(self).expect("usize overflowed u8")
}
#[cfg(not(debug_assertions))]
{
self as u8
}
}
fn as_u16(self) -> u16 {
#[cfg(debug_assertions)]
{
u16::try_from(self).expect("usize overflowed u16")
}
#[cfg(not(debug_assertions))]
{
self as u16
}
}
fn as_u32(self) -> u32 {
#[cfg(debug_assertions)]
{
u32::try_from(self).expect("usize overflowed u32")
}
#[cfg(not(debug_assertions))]
{
self as u32
}
}
fn as_u64(self) -> u64 {
#[cfg(debug_assertions)]
{
u64::try_from(self).expect("usize overflowed u64")
}
#[cfg(not(debug_assertions))]
{
self as u64
}
}
}
// Pointers aren't integers, but we convert pointers to integers to perform
// offset arithmetic in some places. (And no, we don't convert the integers
// back to pointers.) So add 'as_usize' conversions here too for completeness.
//
// These 'as' casts are actually okay because they're always non-lossy. But the
// idea here is to just try and remove as much 'as' as possible, particularly
// in this crate where we are being really paranoid about offsets and making
// sure we don't panic on inputs that might be untrusted. This way, the 'as'
// casts become easier to audit if they're all in one place, even when some of
// them are actually okay 100% of the time.
pub(crate) trait Pointer {
fn as_usize(self) -> usize;
}
impl<T> Pointer for *const T {
fn as_usize(self) -> usize {
self as usize
}
}