mirror of
https://github.com/rust-lang/rust.git
synced 2024-10-30 14:01:51 +00:00
Improve invalid UTF-8 lint by finding the expression initializer
This commit is contained in:
parent
6192690b92
commit
f156d3bc57
@ -1,6 +1,6 @@
|
||||
use std::str::Utf8Error;
|
||||
|
||||
use rustc_ast::{BorrowKind, LitKind};
|
||||
use rustc_ast::LitKind;
|
||||
use rustc_hir::{Expr, ExprKind};
|
||||
use rustc_span::source_map::Spanned;
|
||||
use rustc_span::sym;
|
||||
@ -11,7 +11,7 @@ use crate::{LateContext, LateLintPass, LintContext};
|
||||
declare_lint! {
|
||||
/// The `invalid_from_utf8_unchecked` lint checks for calls to
|
||||
/// `std::str::from_utf8_unchecked` and `std::str::from_utf8_unchecked_mut`
|
||||
/// with an invalid UTF-8 literal.
|
||||
/// with a known invalid UTF-8 value.
|
||||
///
|
||||
/// ### Example
|
||||
///
|
||||
@ -36,7 +36,7 @@ declare_lint! {
|
||||
declare_lint! {
|
||||
/// The `invalid_from_utf8` lint checks for calls to
|
||||
/// `std::str::from_utf8` and `std::str::from_utf8_mut`
|
||||
/// with an invalid UTF-8 literal.
|
||||
/// with a known invalid UTF-8 value.
|
||||
///
|
||||
/// ### Example
|
||||
///
|
||||
@ -67,8 +67,7 @@ impl<'tcx> LateLintPass<'tcx> for InvalidFromUtf8 {
|
||||
&& [sym::str_from_utf8, sym::str_from_utf8_mut,
|
||||
sym::str_from_utf8_unchecked, sym::str_from_utf8_unchecked_mut].contains(&diag_item)
|
||||
{
|
||||
let lint = |utf8_error: Utf8Error| {
|
||||
let label = arg.span;
|
||||
let lint = |label, utf8_error: Utf8Error| {
|
||||
let method = diag_item.as_str().strip_prefix("str_").unwrap();
|
||||
let method = format!("std::str::{method}");
|
||||
let valid_up_to = utf8_error.valid_up_to();
|
||||
@ -78,22 +77,26 @@ impl<'tcx> LateLintPass<'tcx> for InvalidFromUtf8 {
|
||||
if is_unchecked_variant { INVALID_FROM_UTF8_UNCHECKED } else { INVALID_FROM_UTF8 },
|
||||
expr.span,
|
||||
if is_unchecked_variant {
|
||||
InvalidFromUtf8Diag::Unchecked { method, valid_up_to, label }
|
||||
InvalidFromUtf8Diag::Unchecked { method, valid_up_to, label }
|
||||
} else {
|
||||
InvalidFromUtf8Diag::Checked { method, valid_up_to, label }
|
||||
InvalidFromUtf8Diag::Checked { method, valid_up_to, label }
|
||||
}
|
||||
)
|
||||
};
|
||||
|
||||
match &arg.kind {
|
||||
let mut init = cx.expr_or_init(arg);
|
||||
while let ExprKind::AddrOf(.., inner) = init.kind {
|
||||
init = cx.expr_or_init(inner);
|
||||
}
|
||||
match init.kind {
|
||||
ExprKind::Lit(Spanned { node: lit, .. }) => {
|
||||
if let LitKind::ByteStr(bytes, _) = &lit
|
||||
&& let Err(utf8_error) = std::str::from_utf8(bytes)
|
||||
{
|
||||
lint(utf8_error);
|
||||
lint(init.span, utf8_error);
|
||||
}
|
||||
},
|
||||
ExprKind::AddrOf(BorrowKind::Ref, _, Expr { kind: ExprKind::Array(args), .. }) => {
|
||||
ExprKind::Array(args) => {
|
||||
let elements = args.iter().map(|e|{
|
||||
match &e.kind {
|
||||
ExprKind::Lit(Spanned { node: lit, .. }) => match lit {
|
||||
@ -108,7 +111,7 @@ impl<'tcx> LateLintPass<'tcx> for InvalidFromUtf8 {
|
||||
if let Some(elements) = elements
|
||||
&& let Err(utf8_error) = std::str::from_utf8(&elements)
|
||||
{
|
||||
lint(utf8_error);
|
||||
lint(init.span, utf8_error);
|
||||
}
|
||||
}
|
||||
_ => {}
|
||||
|
@ -1,6 +1,8 @@
|
||||
// check-pass
|
||||
|
||||
#![feature(inline_const)]
|
||||
#![feature(concat_bytes)]
|
||||
|
||||
#![warn(invalid_from_utf8_unchecked)]
|
||||
#![warn(invalid_from_utf8)]
|
||||
|
||||
@ -90,4 +92,29 @@ pub fn from_utf8() {
|
||||
}
|
||||
}
|
||||
|
||||
pub fn from_utf8_with_indirections() {
|
||||
let mut a = [99, 108, 130, 105, 112, 112, 121];
|
||||
std::str::from_utf8_mut(&mut a);
|
||||
//~^ WARN calls to `std::str::from_utf8_mut`
|
||||
let mut b = &mut a;
|
||||
let mut c = b;
|
||||
std::str::from_utf8_mut(c);
|
||||
//~^ WARN calls to `std::str::from_utf8_mut`
|
||||
let mut c = &[99, 108, 130, 105, 112, 112, 121];
|
||||
std::str::from_utf8(c);
|
||||
//~^ WARN calls to `std::str::from_utf8`
|
||||
const INVALID_1: [u8; 7] = [99, 108, 130, 105, 112, 112, 121];
|
||||
std::str::from_utf8(&INVALID_1);
|
||||
//~^ WARN calls to `std::str::from_utf8`
|
||||
static INVALID_2: [u8; 7] = [99, 108, 130, 105, 112, 112, 121];
|
||||
std::str::from_utf8(&INVALID_2);
|
||||
//~^ WARN calls to `std::str::from_utf8`
|
||||
const INVALID_3: &'static [u8; 7] = &[99, 108, 130, 105, 112, 112, 121];
|
||||
std::str::from_utf8(INVALID_3);
|
||||
//~^ WARN calls to `std::str::from_utf8`
|
||||
const INVALID_4: &'static [u8; 7] = { &[99, 108, 130, 105, 112, 112, 121] };
|
||||
std::str::from_utf8(INVALID_4);
|
||||
//~^ WARN calls to `std::str::from_utf8`
|
||||
}
|
||||
|
||||
fn main() {}
|
||||
|
@ -1,51 +1,51 @@
|
||||
warning: calls to `std::str::from_utf8_unchecked_mut` with a invalid literal are undefined behavior
|
||||
--> $DIR/invalid_from_utf8.rs:19:9
|
||||
--> $DIR/invalid_from_utf8.rs:21:9
|
||||
|
|
||||
LL | std::str::from_utf8_unchecked_mut(&mut [99, 108, 130, 105, 112, 112, 121]);
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^---------------------------------------^
|
||||
| |
|
||||
| the literal was valid UTF-8 up to the 2 bytes
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^----------------------------------^
|
||||
| |
|
||||
| the literal was valid UTF-8 up to the 2 bytes
|
||||
|
|
||||
note: the lint level is defined here
|
||||
--> $DIR/invalid_from_utf8.rs:4:9
|
||||
--> $DIR/invalid_from_utf8.rs:6:9
|
||||
|
|
||||
LL | #![warn(invalid_from_utf8_unchecked)]
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
|
||||
warning: calls to `std::str::from_utf8_unchecked_mut` with a invalid literal are undefined behavior
|
||||
--> $DIR/invalid_from_utf8.rs:21:9
|
||||
--> $DIR/invalid_from_utf8.rs:23:9
|
||||
|
|
||||
LL | std::str::from_utf8_unchecked_mut(&mut [b'c', b'l', b'\x82', b'i', b'p', b'p', b'y']);
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^--------------------------------------------------^
|
||||
| |
|
||||
| the literal was valid UTF-8 up to the 2 bytes
|
||||
|
||||
warning: calls to `std::str::from_utf8_unchecked` with a invalid literal are undefined behavior
|
||||
--> $DIR/invalid_from_utf8.rs:39:9
|
||||
|
|
||||
LL | std::str::from_utf8_unchecked(&[99, 108, 130, 105, 112, 112, 121]);
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^-----------------------------------^
|
||||
| |
|
||||
| the literal was valid UTF-8 up to the 2 bytes
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^---------------------------------------------^
|
||||
| |
|
||||
| the literal was valid UTF-8 up to the 2 bytes
|
||||
|
||||
warning: calls to `std::str::from_utf8_unchecked` with a invalid literal are undefined behavior
|
||||
--> $DIR/invalid_from_utf8.rs:41:9
|
||||
|
|
||||
LL | std::str::from_utf8_unchecked(&[b'c', b'l', b'\x82', b'i', b'p', b'p', b'y']);
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^----------------------------------------------^
|
||||
| |
|
||||
| the literal was valid UTF-8 up to the 2 bytes
|
||||
LL | std::str::from_utf8_unchecked(&[99, 108, 130, 105, 112, 112, 121]);
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^----------------------------------^
|
||||
| |
|
||||
| the literal was valid UTF-8 up to the 2 bytes
|
||||
|
||||
warning: calls to `std::str::from_utf8_unchecked` with a invalid literal are undefined behavior
|
||||
--> $DIR/invalid_from_utf8.rs:43:9
|
||||
|
|
||||
LL | std::str::from_utf8_unchecked(&[b'c', b'l', b'\x82', b'i', b'p', b'p', b'y']);
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^---------------------------------------------^
|
||||
| |
|
||||
| the literal was valid UTF-8 up to the 2 bytes
|
||||
|
||||
warning: calls to `std::str::from_utf8_unchecked` with a invalid literal are undefined behavior
|
||||
--> $DIR/invalid_from_utf8.rs:45:9
|
||||
|
|
||||
LL | std::str::from_utf8_unchecked(b"cl\x82ippy");
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^-------------^
|
||||
| |
|
||||
| the literal was valid UTF-8 up to the 2 bytes
|
||||
|
||||
warning: calls to `std::str::from_utf8_unchecked` with a invalid literal are undefined behavior
|
||||
--> $DIR/invalid_from_utf8.rs:45:9
|
||||
--> $DIR/invalid_from_utf8.rs:47:9
|
||||
|
|
||||
LL | std::str::from_utf8_unchecked(concat_bytes!(b"cl", b"\x82ippy"));
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^---------------------------------^
|
||||
@ -53,58 +53,115 @@ LL | std::str::from_utf8_unchecked(concat_bytes!(b"cl", b"\x82ippy"));
|
||||
| the literal was valid UTF-8 up to the 2 bytes
|
||||
|
||||
warning: calls to `std::str::from_utf8_mut` with a invalid literal always return an error
|
||||
--> $DIR/invalid_from_utf8.rs:62:9
|
||||
--> $DIR/invalid_from_utf8.rs:64:9
|
||||
|
|
||||
LL | std::str::from_utf8_mut(&mut [99, 108, 130, 105, 112, 112, 121]);
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^---------------------------------------^
|
||||
| |
|
||||
| the literal was valid UTF-8 up to the 2 bytes
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^----------------------------------^
|
||||
| |
|
||||
| the literal was valid UTF-8 up to the 2 bytes
|
||||
|
|
||||
note: the lint level is defined here
|
||||
--> $DIR/invalid_from_utf8.rs:5:9
|
||||
--> $DIR/invalid_from_utf8.rs:7:9
|
||||
|
|
||||
LL | #![warn(invalid_from_utf8)]
|
||||
| ^^^^^^^^^^^^^^^^^
|
||||
|
||||
warning: calls to `std::str::from_utf8_mut` with a invalid literal always return an error
|
||||
--> $DIR/invalid_from_utf8.rs:64:9
|
||||
--> $DIR/invalid_from_utf8.rs:66:9
|
||||
|
|
||||
LL | std::str::from_utf8_mut(&mut [b'c', b'l', b'\x82', b'i', b'p', b'p', b'y']);
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^--------------------------------------------------^
|
||||
| |
|
||||
| the literal was valid UTF-8 up to the 2 bytes
|
||||
|
||||
warning: calls to `std::str::from_utf8` with a invalid literal always return an error
|
||||
--> $DIR/invalid_from_utf8.rs:82:9
|
||||
|
|
||||
LL | std::str::from_utf8(&[99, 108, 130, 105, 112, 112, 121]);
|
||||
| ^^^^^^^^^^^^^^^^^^^^-----------------------------------^
|
||||
| |
|
||||
| the literal was valid UTF-8 up to the 2 bytes
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^---------------------------------------------^
|
||||
| |
|
||||
| the literal was valid UTF-8 up to the 2 bytes
|
||||
|
||||
warning: calls to `std::str::from_utf8` with a invalid literal always return an error
|
||||
--> $DIR/invalid_from_utf8.rs:84:9
|
||||
|
|
||||
LL | std::str::from_utf8(&[b'c', b'l', b'\x82', b'i', b'p', b'p', b'y']);
|
||||
| ^^^^^^^^^^^^^^^^^^^^----------------------------------------------^
|
||||
| |
|
||||
| the literal was valid UTF-8 up to the 2 bytes
|
||||
LL | std::str::from_utf8(&[99, 108, 130, 105, 112, 112, 121]);
|
||||
| ^^^^^^^^^^^^^^^^^^^^^----------------------------------^
|
||||
| |
|
||||
| the literal was valid UTF-8 up to the 2 bytes
|
||||
|
||||
warning: calls to `std::str::from_utf8` with a invalid literal always return an error
|
||||
--> $DIR/invalid_from_utf8.rs:86:9
|
||||
|
|
||||
LL | std::str::from_utf8(&[b'c', b'l', b'\x82', b'i', b'p', b'p', b'y']);
|
||||
| ^^^^^^^^^^^^^^^^^^^^^---------------------------------------------^
|
||||
| |
|
||||
| the literal was valid UTF-8 up to the 2 bytes
|
||||
|
||||
warning: calls to `std::str::from_utf8` with a invalid literal always return an error
|
||||
--> $DIR/invalid_from_utf8.rs:88:9
|
||||
|
|
||||
LL | std::str::from_utf8(b"cl\x82ippy");
|
||||
| ^^^^^^^^^^^^^^^^^^^^-------------^
|
||||
| |
|
||||
| the literal was valid UTF-8 up to the 2 bytes
|
||||
|
||||
warning: calls to `std::str::from_utf8` with a invalid literal always return an error
|
||||
--> $DIR/invalid_from_utf8.rs:88:9
|
||||
--> $DIR/invalid_from_utf8.rs:90:9
|
||||
|
|
||||
LL | std::str::from_utf8(concat_bytes!(b"cl", b"\x82ippy"));
|
||||
| ^^^^^^^^^^^^^^^^^^^^---------------------------------^
|
||||
| |
|
||||
| the literal was valid UTF-8 up to the 2 bytes
|
||||
|
||||
warning: 12 warnings emitted
|
||||
warning: calls to `std::str::from_utf8_mut` with a invalid literal always return an error
|
||||
--> $DIR/invalid_from_utf8.rs:97:5
|
||||
|
|
||||
LL | let mut a = [99, 108, 130, 105, 112, 112, 121];
|
||||
| ---------------------------------- the literal was valid UTF-8 up to the 2 bytes
|
||||
LL | std::str::from_utf8_mut(&mut a);
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
|
||||
warning: calls to `std::str::from_utf8_mut` with a invalid literal always return an error
|
||||
--> $DIR/invalid_from_utf8.rs:101:5
|
||||
|
|
||||
LL | let mut a = [99, 108, 130, 105, 112, 112, 121];
|
||||
| ---------------------------------- the literal was valid UTF-8 up to the 2 bytes
|
||||
...
|
||||
LL | std::str::from_utf8_mut(c);
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
|
||||
warning: calls to `std::str::from_utf8` with a invalid literal always return an error
|
||||
--> $DIR/invalid_from_utf8.rs:104:5
|
||||
|
|
||||
LL | let mut c = &[99, 108, 130, 105, 112, 112, 121];
|
||||
| ---------------------------------- the literal was valid UTF-8 up to the 2 bytes
|
||||
LL | std::str::from_utf8(c);
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^
|
||||
|
||||
warning: calls to `std::str::from_utf8` with a invalid literal always return an error
|
||||
--> $DIR/invalid_from_utf8.rs:107:5
|
||||
|
|
||||
LL | const INVALID_1: [u8; 7] = [99, 108, 130, 105, 112, 112, 121];
|
||||
| ---------------------------------- the literal was valid UTF-8 up to the 2 bytes
|
||||
LL | std::str::from_utf8(&INVALID_1);
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
|
||||
warning: calls to `std::str::from_utf8` with a invalid literal always return an error
|
||||
--> $DIR/invalid_from_utf8.rs:110:5
|
||||
|
|
||||
LL | static INVALID_2: [u8; 7] = [99, 108, 130, 105, 112, 112, 121];
|
||||
| ---------------------------------- the literal was valid UTF-8 up to the 2 bytes
|
||||
LL | std::str::from_utf8(&INVALID_2);
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
|
||||
warning: calls to `std::str::from_utf8` with a invalid literal always return an error
|
||||
--> $DIR/invalid_from_utf8.rs:113:5
|
||||
|
|
||||
LL | const INVALID_3: &'static [u8; 7] = &[99, 108, 130, 105, 112, 112, 121];
|
||||
| ---------------------------------- the literal was valid UTF-8 up to the 2 bytes
|
||||
LL | std::str::from_utf8(INVALID_3);
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
|
||||
warning: calls to `std::str::from_utf8` with a invalid literal always return an error
|
||||
--> $DIR/invalid_from_utf8.rs:116:5
|
||||
|
|
||||
LL | const INVALID_4: &'static [u8; 7] = { &[99, 108, 130, 105, 112, 112, 121] };
|
||||
| ---------------------------------- the literal was valid UTF-8 up to the 2 bytes
|
||||
LL | std::str::from_utf8(INVALID_4);
|
||||
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
|
||||
warning: 19 warnings emitted
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user