🐛 fix(text_coordinates): convert LSP UTF-16 positions

This commit is contained in:
csh
2026-07-12 12:15:46 +08:00
parent 16986281a7
commit 61d16d0147
5 changed files with 205 additions and 42 deletions
@@ -28,6 +28,7 @@ set(SOURCES
interpreter_test.cppm
provider_misc_test.cppm
provider_surface_test.cppm
text_coordinates_test.cppm
../../src/tree-sitter/parser.c
../../src/tree-sitter/scanner.c)
@@ -56,6 +57,7 @@ target_sources(
${CMAKE_CURRENT_SOURCE_DIR}/interpreter_test.cppm
${CMAKE_CURRENT_SOURCE_DIR}/provider_misc_test.cppm
${CMAKE_CURRENT_SOURCE_DIR}/provider_surface_test.cppm
${CMAKE_CURRENT_SOURCE_DIR}/text_coordinates_test.cppm
../../src/bridge/glaze.cppm
../../src/bridge/spdlog.cppm
../../src/bridge/taskflow.cppm
@@ -12,6 +12,7 @@ import lsp.test.provider.json_flow;
import lsp.test.provider.json_provider_coverage;
import lsp.test.provider.misc;
import lsp.test.provider.surface;
import lsp.test.provider.text_coordinates;
import lsp.test.provider.fixtures;
export int Run(int argc, char** argv)
@@ -59,6 +60,8 @@ export int Run(int argc, char** argv)
lsp::test::provider::ProviderMiscTests::Register(runner);
std::cout << " - Provider surface tests" << std::endl;
lsp::test::provider::ProviderSurfaceTests::Register(runner);
std::cout << " - Text coordinate tests" << std::endl;
lsp::test::provider::TextCoordinatesTests::Register(runner);
runner.runAllTests();
return runner.getFailedCount();
@@ -0,0 +1,96 @@
module;
export module lsp.test.provider.text_coordinates;
import std;
import lsp.protocol;
import lsp.test.framework;
import lsp.utils.text_coordinates;
export namespace lsp::test::provider
{
class TextCoordinatesTests
{
public:
static void Register(TestRunner& runner);
private:
static TestResult TestAsciiAndBmpPositions();
static TestResult TestSupplementaryPlanePositions();
static TestResult TestMultilineAndClampedPositions();
static TestResult TestMalformedUtf8IsBounded();
static TestResult TestCalculateEndPointUsesByteColumns();
};
}
namespace lsp::test::provider
{
namespace
{
void ExpectPosition(const utils::text_coordinates::BytePosition& actual,
protocol::uinteger offset,
std::uint32_t row,
std::uint32_t column)
{
assertEqual(offset, actual.offset, "byte offset should match");
assertEqual(row, actual.point.row, "Tree-sitter row should match");
assertEqual(column, actual.point.column, "Tree-sitter byte column should match");
}
}
void TextCoordinatesTests::Register(TestRunner& runner)
{
runner.addTest("text coordinates convert ASCII and BMP positions", TestAsciiAndBmpPositions);
runner.addTest("text coordinates convert supplementary-plane positions", TestSupplementaryPlanePositions);
runner.addTest("text coordinates clamp multiline positions", TestMultilineAndClampedPositions);
runner.addTest("text coordinates bound malformed UTF-8", TestMalformedUtf8IsBounded);
runner.addTest("text coordinates calculate byte end points", TestCalculateEndPointUsesByteColumns);
}
TestResult TextCoordinatesTests::TestAsciiAndBmpPositions()
{
const protocol::string content = "A中Z";
ExpectPosition(utils::text_coordinates::ToBytePosition({ 0, 0 }, content), 0U, 0U, 0U);
ExpectPosition(utils::text_coordinates::ToBytePosition({ 0, 1 }, content), 1U, 0U, 1U);
ExpectPosition(utils::text_coordinates::ToBytePosition({ 0, 2 }, content), 4U, 0U, 4U);
assertEqual(4U, utils::text_coordinates::ToOffset({ 0, 2 }, content), "ToOffset should use the paired conversion");
return { "", true, "ok" };
}
TestResult TextCoordinatesTests::TestSupplementaryPlanePositions()
{
const protocol::string content = "A😀Z";
ExpectPosition(utils::text_coordinates::ToBytePosition({ 0, 1 }, content), 1U, 0U, 1U);
ExpectPosition(utils::text_coordinates::ToBytePosition({ 0, 2 }, content), 1U, 0U, 1U);
ExpectPosition(utils::text_coordinates::ToBytePosition({ 0, 3 }, content), 5U, 0U, 5U);
ExpectPosition(utils::text_coordinates::ToBytePosition({ 0, 4 }, content), 6U, 0U, 6U);
return { "", true, "ok" };
}
TestResult TextCoordinatesTests::TestMultilineAndClampedPositions()
{
const protocol::string content = "中x\n😀y";
ExpectPosition(utils::text_coordinates::ToBytePosition({ 1, 0 }, content), 5U, 1U, 0U);
ExpectPosition(utils::text_coordinates::ToBytePosition({ 1, 2 }, content), 9U, 1U, 4U);
ExpectPosition(utils::text_coordinates::ToBytePosition({ 1, 100 }, content), 10U, 1U, 5U);
ExpectPosition(utils::text_coordinates::ToBytePosition({ 9, 0 }, content), 10U, 1U, 5U);
return { "", true, "ok" };
}
TestResult TextCoordinatesTests::TestMalformedUtf8IsBounded()
{
const protocol::string content{ 'A', static_cast<char>(0xF0), static_cast<char>(0x9F), 'Z' };
ExpectPosition(utils::text_coordinates::ToBytePosition({ 0, 2 }, content), 2U, 0U, 2U);
ExpectPosition(utils::text_coordinates::ToBytePosition({ 0, 100 }, content), 4U, 0U, 4U);
return { "", true, "ok" };
}
TestResult TextCoordinatesTests::TestCalculateEndPointUsesByteColumns()
{
const auto end = utils::text_coordinates::CalculateEndPoint("中\n😀x", { 2U, 3U });
assertEqual(3U, end.row, "newline should advance the Tree-sitter row");
assertEqual(5U, end.column, "multibyte text should advance the byte column");
return { "", true, "ok" };
}
}