Remove CowBoxSymStr.

`CowBoxSymStr` is a type that either holds a `SymbolStr` (which is much
the same as a `Symbol`), or an owned string. When computing skeletons,
a `SymbolStr` is stored if the skeleton is the same as the original
string, otherwise an owned string is stored.

So, basically, `CowBoxSymStr` is a type for string interning. But we
already have one of those: `Symbol` itself. This PR removes
`CowBoxSymStr`, using `Symbol` instead. A good thing about this is that
it avoids storing `SymbolStr` values in `skeleton_map`, something that
is discouraged.

The PR also inlines and removes the `calc_skeleton()` function because
that simplifies the code.
This commit is contained in:
Nicholas Nethercote 2020-08-06 12:48:53 +10:00
parent 75b67c2d5e
commit 0a597bd98f

View file

@ -1,7 +1,7 @@
use crate::{EarlyContext, EarlyLintPass, LintContext};
use rustc_ast::ast;
use rustc_data_structures::fx::FxHashMap;
use rustc_span::symbol::SymbolStr;
use rustc_span::symbol::Symbol;
declare_lint! {
pub NON_ASCII_IDENTS,
@ -39,7 +39,6 @@ impl EarlyLintPass for NonAsciiIdents {
use rustc_span::Span;
use std::collections::BTreeMap;
use unicode_security::GeneralSecurityProfile;
use utils::CowBoxSymStr;
let check_non_ascii_idents = cx.builder.lint_level(NON_ASCII_IDENTS).0 != Level::Allow;
let check_uncommon_codepoints =
@ -83,33 +82,34 @@ impl EarlyLintPass for NonAsciiIdents {
}
if has_non_ascii_idents && check_confusable_idents {
let mut skeleton_map: FxHashMap<CowBoxSymStr, (SymbolStr, Span, bool)> =
let mut skeleton_map: FxHashMap<Symbol, (Symbol, Span, bool)> =
FxHashMap::with_capacity_and_hasher(symbols.len(), Default::default());
let mut str_buf = String::new();
for (symbol, &sp) in symbols.iter() {
fn calc_skeleton(symbol_str: &SymbolStr, buffer: &mut String) -> CowBoxSymStr {
use std::mem::replace;
let mut skeleton_buf = String::new();
for (&symbol, &sp) in symbols.iter() {
use unicode_security::confusable_detection::skeleton;
buffer.clear();
buffer.extend(skeleton(symbol_str));
if *symbol_str == *buffer {
CowBoxSymStr::Interned(symbol_str.clone())
} else {
let owned = replace(buffer, String::new());
CowBoxSymStr::Owned(owned.into_boxed_str())
}
}
let symbol_str = symbol.as_str();
let is_ascii = symbol_str.is_ascii();
let skeleton = calc_skeleton(&symbol_str, &mut str_buf);
// Get the skeleton as a `Symbol`.
skeleton_buf.clear();
skeleton_buf.extend(skeleton(&symbol_str));
let skeleton_sym = if *symbol_str == *skeleton_buf {
symbol
} else {
Symbol::intern(&skeleton_buf)
};
skeleton_map
.entry(skeleton)
.and_modify(|(existing_symbolstr, existing_span, existing_is_ascii)| {
.entry(skeleton_sym)
.and_modify(|(existing_symbol, existing_span, existing_is_ascii)| {
if !*existing_is_ascii || !is_ascii {
cx.struct_span_lint(CONFUSABLE_IDENTS, sp, |lint| {
lint.build(&format!(
"identifier pair considered confusable between `{}` and `{}`",
existing_symbolstr, symbol_str
existing_symbol.as_str(),
symbol.as_str()
))
.span_label(
*existing_span,
@ -119,12 +119,12 @@ impl EarlyLintPass for NonAsciiIdents {
});
}
if *existing_is_ascii && !is_ascii {
*existing_symbolstr = symbol_str.clone();
*existing_symbol = symbol;
*existing_span = sp;
*existing_is_ascii = is_ascii;
}
})
.or_insert((symbol_str, sp, is_ascii));
.or_insert((symbol, sp, is_ascii));
}
}
@ -238,41 +238,3 @@ impl EarlyLintPass for NonAsciiIdents {
}
}
}
mod utils {
use rustc_span::symbol::SymbolStr;
use std::hash::{Hash, Hasher};
use std::ops::Deref;
pub(super) enum CowBoxSymStr {
Interned(SymbolStr),
Owned(Box<str>),
}
impl Deref for CowBoxSymStr {
type Target = str;
fn deref(&self) -> &str {
match self {
CowBoxSymStr::Interned(interned) => interned,
CowBoxSymStr::Owned(ref owned) => owned,
}
}
}
impl Hash for CowBoxSymStr {
#[inline]
fn hash<H: Hasher>(&self, state: &mut H) {
Hash::hash(&**self, state)
}
}
impl PartialEq<CowBoxSymStr> for CowBoxSymStr {
#[inline]
fn eq(&self, other: &CowBoxSymStr) -> bool {
PartialEq::eq(&**self, &**other)
}
}
impl Eq for CowBoxSymStr {}
}