Files
carbon-lang/toolchain/parse/tree_node_diagnostic_converter.h
T
Jon Ross-Perkins 8f685b6953 Change how diagnostics are ordered (#4778)
This change deliberately breaks away from the line/column ordering, and
instead focuses on a last byte offset corresponding to the final token
processed as part of producing the message. Where that's equal, this
maintains stable ordering in order to reflect the order that diagnostics
were produced.

The intent of this approach is that lex, parse, and check diagnostics
are interleaved based on where they are produced, but that
subexpressions still have diagnostics emitted prior to containing
expressions. In particular, the prior line/column sort essentially
sorted on the _start_ of where a diagnostic was associated, and this is
closer to sorting based on the _end_. As a consequence, something like
`F(1 2)` will have the error for `1 2` emitted _before_ a diagnostic for
`F(1 2)` not matching parameters, instead of _after_.

In check, we track the last handled node. This provides a
last_byte_offset _separate_ from where a diagnostic is associated. The
intent is that this creates an ordering of diagnostics which may be
associated with earlier code, to cause the diagnostics to be emitted
later. An example consequence of this is the change in ordering of
modifier diagnostics: we are diagnosing those from the same place, but
they have the same last_byte_offset, so we print them out in the order
produced.

I've added similar tracking to parse, but cannot identify any test which
is affected by it (note the separate commit, I thought about this late).
I'm not sure whether we have good out-of-order errors we could produce
for this.

A significant number of tests have reordered diagnostics as a
consequence of this change, so this change does not add further testing.
2025-01-10 18:36:24 +00:00

107 lines
3.7 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
#ifndef CARBON_TOOLCHAIN_PARSE_TREE_NODE_DIAGNOSTIC_CONVERTER_H_
#define CARBON_TOOLCHAIN_PARSE_TREE_NODE_DIAGNOSTIC_CONVERTER_H_
#include <utility>
#include "toolchain/diagnostics/diagnostic_emitter.h"
#include "toolchain/lex/tokenized_buffer.h"
#include "toolchain/parse/tree.h"
#include "toolchain/parse/tree_and_subtrees.h"
namespace Carbon::Parse {
class NodeLoc {
public:
// NOLINTNEXTLINE(google-explicit-constructor)
NodeLoc(NodeId node_id) : NodeLoc(node_id, false) {}
NodeLoc(NodeId node_id, bool token_only)
: node_id_(node_id), token_only_(token_only) {}
// TODO: Have some other way of representing diagnostic that applies to a file
// as a whole.
// NOLINTNEXTLINE(google-explicit-constructor)
NodeLoc(InvalidNodeId node_id) : NodeLoc(node_id, false) {}
auto node_id() const -> NodeId { return node_id_; }
auto token_only() const -> bool { return token_only_; }
private:
NodeId node_id_;
bool token_only_;
};
class NodeLocConverter : public DiagnosticConverter<NodeLoc> {
public:
explicit NodeLocConverter(
const Lex::TokenizedBuffer* tokens, llvm::StringRef filename,
llvm::function_ref<const Parse::TreeAndSubtrees&()> get_tree_and_subtrees)
: token_converter_(tokens),
filename_(filename),
get_tree_and_subtrees_(get_tree_and_subtrees) {}
// Implements `DiagnosticConverter::ConvertLoc`.
auto ConvertLoc(NodeLoc node_loc, ContextFnT context_fn) const
-> ConvertedDiagnosticLoc override {
// Support the invalid token as a way to emit only the filename, when there
// is no line association.
if (!node_loc.node_id().is_valid()) {
return {{.filename = filename_}, -1};
}
const auto& tree = get_tree_and_subtrees_();
if (node_loc.token_only()) {
return token_converter_.ConvertLoc(
tree.tree().node_token(node_loc.node_id()), context_fn);
}
// Construct a location that encompasses all tokens that descend from this
// node (including the root).
Lex::TokenIndex start_token = tree.tree().node_token(node_loc.node_id());
Lex::TokenIndex end_token = start_token;
for (NodeId desc : tree.postorder(node_loc.node_id())) {
Lex::TokenIndex desc_token = tree.tree().node_token(desc);
if (!desc_token.is_valid()) {
continue;
}
if (desc_token < start_token) {
start_token = desc_token;
} else if (desc_token > end_token) {
end_token = desc_token;
}
}
auto start_loc = token_converter_.ConvertLoc(start_token, context_fn);
if (start_token == end_token) {
return start_loc;
}
auto end_loc = token_converter_.ConvertLoc(end_token, context_fn);
start_loc.last_byte_offset = end_loc.last_byte_offset;
// For multiline locations we simply return the rest of the line for now
// since true multiline locations are not yet supported.
if (start_loc.loc.line_number != end_loc.loc.line_number) {
start_loc.loc.length =
start_loc.loc.line.size() - start_loc.loc.column_number + 1;
} else {
if (start_loc.loc.column_number != end_loc.loc.column_number) {
start_loc.loc.length = end_loc.loc.column_number + end_loc.loc.length -
start_loc.loc.column_number;
}
}
return start_loc;
}
private:
Lex::TokenDiagnosticConverter token_converter_;
llvm::StringRef filename_;
// Returns a lazily constructed TreeAndSubtrees.
llvm::function_ref<const Parse::TreeAndSubtrees&()> get_tree_and_subtrees_;
};
} // namespace Carbon::Parse
#endif // CARBON_TOOLCHAIN_PARSE_TREE_NODE_DIAGNOSTIC_CONVERTER_H_