mirror of
https://github.com/carbon-language/carbon-lang.git
synced 2026-09-24 20:50:13 +01:00
Carbon currently requires a comment to be the only non-whitespace on its line. A `//` comment that follows other content on a line, called a _trailing comment_, is a lexer error. This proposal removes that restriction, allowing a comment to follow other content on a line. Everything else about comments is unchanged: a comment still begins with `//`, still requires whitespace after the `//`, and still runs to the end of the line. Carbon continues to provide only line comments; no block or intra-line comments are added. Three observations motivate the change. First, trailing comments are well suited to short _annotations_ attached to a specific entity or value on a line. Second, the lexer design now makes it trivial to lex trailing comments, and in fact requires extra logic and potentially cost to reject them. Third, C++ code routinely uses trailing comments, so allowing them lets Carbon carry the layout of migrated code over directly, rather than reworking each comment to read well in a different structure. Implementation notes (beyond the proposal's design): Keeping trailing comments cheap to lex required a few supporting changes, all of which keep the cost off the lexer's hot path: - The lexer already dispatches `//` to comment lexing wherever it appears, so classifying a comment as trailing is a single O(1) check of whether the `//` is the line's first non-whitespace (`start + indent`). The hot comment path is otherwise unchanged. - That check relies on each line's recorded indentation being its real leading whitespace. Multi-line string literals previously recorded the column where the literal opened for the lines they span; they now record the true (closing-delimiter) indentation instead. - Parser error recovery (`SkipPastLikelyEnd`) had relied on that opening-column indentation to keep tokens following a multi-line string literal attached to the same construct. It now reconstructs that relationship directly by consulting the line on which the literal opened, including when other tokens follow the closing delimiter (such as `''' + "more"`). This is on the cold recovery path. - `CommentData` records the trailing bit in the high bit of its length field, keeping it at 8 bytes. Assisted-by: Claude Code
138 lines
4.0 KiB
C++
138 lines
4.0 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/format/formatter.h"
|
|
|
|
namespace Carbon::Format {
|
|
|
|
auto Formatter::Run() -> bool {
|
|
if (tokens_->has_errors()) {
|
|
// TODO: Error recovery.
|
|
return false;
|
|
}
|
|
|
|
// If there are no tokens or comments, format as empty.
|
|
if (tokens_->size() == 0 && next_comment_ == comments_end_) {
|
|
*out_ << "\n";
|
|
return true;
|
|
}
|
|
|
|
for (auto token : tokens_->tokens()) {
|
|
auto token_kind = tokens_->GetKind(token);
|
|
|
|
// Emit any comments that come before this token in the source. Trailing
|
|
// comments are attached to the still-open current line; full-line comments
|
|
// are emitted on their own line.
|
|
while (next_comment_ != comments_end_ &&
|
|
tokens_->IsAfterComment(token, *next_comment_)) {
|
|
EmitComment();
|
|
}
|
|
|
|
switch (token_kind) {
|
|
case Lex::TokenKind::FileStart:
|
|
break;
|
|
|
|
case Lex::TokenKind::FileEnd:
|
|
RequireEmptyLine();
|
|
break;
|
|
|
|
case Lex::TokenKind::OpenCurlyBrace:
|
|
PrepareForSpacedContent();
|
|
*out_ << "{";
|
|
// Check for `{}`.
|
|
if (NextToken(token) != tokens_->GetMatchedClosingToken(token)) {
|
|
RequireEmptyLine();
|
|
}
|
|
indent_ += 2;
|
|
break;
|
|
|
|
case Lex::TokenKind::CloseCurlyBrace:
|
|
indent_ -= 2;
|
|
PrepareForPackedContent();
|
|
*out_ << "}";
|
|
RequireEmptyLine();
|
|
break;
|
|
|
|
case Lex::TokenKind::Semi:
|
|
PrepareForPackedContent();
|
|
*out_ << ";";
|
|
RequireEmptyLine();
|
|
break;
|
|
|
|
default:
|
|
if (token_kind.IsOneOf(
|
|
{Lex::TokenKind::CloseParen, Lex::TokenKind::Colon,
|
|
Lex::TokenKind::ColonExclaim, Lex::TokenKind::Comma})) {
|
|
PrepareForPackedContent();
|
|
} else {
|
|
PrepareForSpacedContent();
|
|
}
|
|
*out_ << tokens_->GetTokenText(token);
|
|
line_state_ = token_kind.is_opening_symbol()
|
|
? LineState::HasSeparator
|
|
: LineState::NeedsSeparator;
|
|
break;
|
|
}
|
|
}
|
|
|
|
// Materialize any newline deferred by the final line.
|
|
if (line_state_ == LineState::EndOfLine) {
|
|
*out_ << "\n";
|
|
line_state_ = LineState::Empty;
|
|
}
|
|
return true;
|
|
}
|
|
|
|
auto Formatter::EmitComment() -> void {
|
|
auto comment = *next_comment_;
|
|
++next_comment_;
|
|
|
|
if (tokens_->IsTrailingComment(comment) && line_state_ != LineState::Empty) {
|
|
// Keep the trailing comment on the current line, separated by a space. The
|
|
// line still has content because its newline was deferred (`EndOfLine`) or
|
|
// not yet required.
|
|
*out_ << " " << tokens_->GetCommentText(comment);
|
|
} else {
|
|
// A full-line comment (or a trailing comment with nothing left to attach
|
|
// to) is emitted on its own line.
|
|
RequireEmptyLine();
|
|
PrepareForSpacedContent();
|
|
// TODO: We do need to adjust the indent of multi-line comments.
|
|
*out_ << tokens_->GetCommentText(comment);
|
|
}
|
|
// Comment text includes a terminating newline, so just update the state.
|
|
line_state_ = LineState::Empty;
|
|
}
|
|
|
|
auto Formatter::PrepareForPackedContent() -> void {
|
|
// Materialize a deferred newline before starting to fill a fresh line.
|
|
if (line_state_ == LineState::EndOfLine) {
|
|
*out_ << "\n";
|
|
line_state_ = LineState::Empty;
|
|
}
|
|
if (line_state_ == LineState::Empty) {
|
|
out_->indent(indent_);
|
|
line_state_ = LineState::HasSeparator;
|
|
}
|
|
}
|
|
|
|
auto Formatter::RequireEmptyLine() -> void {
|
|
// Defer the newline so a trailing comment can still attach to this line; it
|
|
// is materialized by the next content or at end of file.
|
|
if (line_state_ != LineState::Empty) {
|
|
line_state_ = LineState::EndOfLine;
|
|
}
|
|
}
|
|
|
|
auto Formatter::PrepareForSpacedContent() -> void {
|
|
if (line_state_ == LineState::NeedsSeparator) {
|
|
*out_ << " ";
|
|
line_state_ = LineState::HasSeparator;
|
|
} else {
|
|
PrepareForPackedContent();
|
|
}
|
|
}
|
|
|
|
} // namespace Carbon::Format
|