mirror of
https://github.com/carbon-language/carbon-lang.git
synced 2026-11-14 16:38:29 +00:00
Lexer diagnostics used a single `const char*` as their source location, which only allowed pointing at a single character rather than a run of characters. This limited the underlining of unrecognized tokens, and also made escape sequence diagnostics particularly strange by stopping at whatever point the lexer discovered the error and pointing only at that location. For example: `"\w"` was reported at the `w`, and `"\x"` at the closing `"`. This change tries to always keep the primary location of a diagnostic the point at which typing (inserting or deleting) might fix the error. So for `"\x"`, `\x` is underlined, but the position is at the `"` as that's where you would type a hex code. The lexer's emitter now takes a special lexing source location that represents either a single position _between_ two characters, a single character, or a range of the source buffer. The lexer diagnostics are updated to construct these for the character range as appropriate. Parser diagnostics for a missing token were located at the _next_ token, which is particularly confusing for terminators like missing `;`s. Now they are located at a position after the previous token, with or without a space depending on the token, but typically on the same line. Diagnostics still sort by how far the parser has read. The parser diagnostics for unclosed groups also now attaches a label to the opening token when it is on a separate line. And the diagnostics for mismatched indent in a multi-line string attaches a label to the closing `'''` that establishes that indent. There are likely more location improvements we should do here, but this seemed like a reasonable incremental improvement and is what Claude found when doing an initial audit. One example where I think we should make further improvements is around suggesting raw identifiers when we find an unexpected `Cpp` or `Core` or `base`. We do this consistently now, but raw identifiers should be rare. A TODO is added for these cases. Assisted-by: Claude Code --------- Co-authored-by: Richard Smith <richard@metafoo.co.uk>
134 lines
4.5 KiB
C++
134 lines
4.5 KiB
C++
// Part of the Carbon Language project, under the Apache License v2.0 with LLVM
|
|
// Exceptions. See /LICENSE for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
|
|
#include "toolchain/parse/context.h"
|
|
#include "toolchain/parse/handle.h"
|
|
|
|
namespace Carbon::Parse {
|
|
|
|
auto HandleOnlyParenExpr(Context& context) -> void {
|
|
auto state = context.PopState();
|
|
|
|
// Advance past the open paren.
|
|
auto open_paren = context.ConsumeChecked(Lex::TokenKind::OpenParen);
|
|
context.AddLeafNode(NodeKind::ParenExprStart, open_paren);
|
|
|
|
state.token = open_paren;
|
|
context.PushState(state, StateKind::OnlyParenExprFinish);
|
|
context.PushState(StateKind::Expr);
|
|
}
|
|
|
|
static auto FinishParenExpr(Context& context, const Context::State& state)
|
|
-> void {
|
|
context.AddNode(NodeKind::ParenExpr, context.Consume(), state.has_error);
|
|
}
|
|
|
|
auto HandleOnlyParenExprFinish(Context& context) -> void {
|
|
auto state = context.PopState();
|
|
|
|
if (!context.PositionIs(Lex::TokenKind::CloseParen)) {
|
|
if (!state.has_error) {
|
|
CARBON_DIAGNOSTIC(UnexpectedTokenInCompoundMemberAccess, Error,
|
|
"expected `)`");
|
|
context.emitter().Emit(context.PointAfterPreviousToken(),
|
|
UnexpectedTokenInCompoundMemberAccess);
|
|
state.has_error = true;
|
|
}
|
|
|
|
// Recover from the invalid token.
|
|
context.SkipTo(context.tokens().GetMatchedClosingToken(state.token));
|
|
}
|
|
|
|
FinishParenExpr(context, state);
|
|
}
|
|
|
|
auto HandleParenExpr(Context& context) -> void {
|
|
auto state = context.PopState();
|
|
|
|
// Advance past the open paren. The placeholder will be replaced at the end
|
|
// based on whether we determine this is a tuple or parenthesized expression.
|
|
context.AddLeafNode(NodeKind::Placeholder,
|
|
context.ConsumeChecked(Lex::TokenKind::OpenParen));
|
|
|
|
if (context.PositionIs(Lex::TokenKind::CloseParen)) {
|
|
context.PushState(state, StateKind::TupleLiteralFinish);
|
|
} else {
|
|
context.PushState(state, StateKind::ParenExprFinish);
|
|
context.PushState(StateKind::ExprAfterOpenParenFinish);
|
|
context.PushState(StateKind::Expr);
|
|
}
|
|
}
|
|
|
|
auto HandleExprAfterOpenParenFinish(Context& context) -> void {
|
|
auto state = context.PopState();
|
|
|
|
auto list_token_kind = context.ConsumeListToken(
|
|
NodeKind::TupleLiteralComma, Lex::TokenKind::CloseParen, state.has_error);
|
|
if (list_token_kind == Context::ListTokenKind::Close) {
|
|
return;
|
|
}
|
|
|
|
// We found a comma, so switch parent state to tuple handling.
|
|
auto finish_state = context.PopState();
|
|
CARBON_CHECK(finish_state.kind == StateKind::ParenExprFinish,
|
|
"Unexpected parent state, found: {0}", finish_state.kind);
|
|
context.PushState(finish_state, StateKind::TupleLiteralFinish);
|
|
|
|
// If the comma is not immediately followed by a close paren, push handlers
|
|
// for the next tuple element.
|
|
if (list_token_kind != Context::ListTokenKind::CommaClose) {
|
|
context.PushState(StateKind::TupleLiteralElementFinish);
|
|
context.PushState(StateKind::Expr);
|
|
}
|
|
}
|
|
|
|
auto HandleTupleLiteralElementFinish(Context& context) -> void {
|
|
auto state = context.PopState();
|
|
|
|
if (state.has_error) {
|
|
context.ReturnErrorOnState();
|
|
}
|
|
|
|
if (context.ConsumeListToken(NodeKind::TupleLiteralComma,
|
|
Lex::TokenKind::CloseParen, state.has_error) ==
|
|
Context::ListTokenKind::Comma) {
|
|
context.PushState(StateKind::TupleLiteralElementFinish);
|
|
context.PushState(StateKind::Expr);
|
|
}
|
|
}
|
|
|
|
auto HandleParenExprFinish(Context& context) -> void {
|
|
auto state = context.PopState();
|
|
context.ReplacePlaceholderNode(state.subtree_start, NodeKind::ParenExprStart,
|
|
state.token);
|
|
FinishParenExpr(context, state);
|
|
}
|
|
|
|
auto HandleTupleLiteralFinish(Context& context) -> void {
|
|
auto state = context.PopState();
|
|
|
|
context.ReplacePlaceholderNode(state.subtree_start,
|
|
NodeKind::TupleLiteralStart, state.token);
|
|
context.AddNode(NodeKind::TupleLiteral, context.Consume(), state.has_error);
|
|
}
|
|
|
|
auto HandleCallExpr(Context& context) -> void {
|
|
auto state = context.PopState();
|
|
context.PushState(state, StateKind::CallExprFinish);
|
|
|
|
context.AddNode(NodeKind::CallExprStart, context.Consume(), state.has_error);
|
|
if (!context.PositionIs(Lex::TokenKind::CloseParen)) {
|
|
context.PushState(StateKind::TupleLiteralElementFinish);
|
|
context.PushState(StateKind::Expr);
|
|
}
|
|
}
|
|
|
|
auto HandleCallExprFinish(Context& context) -> void {
|
|
auto state = context.PopState();
|
|
|
|
context.AddNode(NodeKind::CallExpr, context.Consume(), state.has_error);
|
|
}
|
|
|
|
} // namespace Carbon::Parse
|