Summary:
Add fuzzy SymbolIndex, where identifier needn't match exactly.
The purpose for this is global autocomplete in clangd. The query will be a
partial identifier up to the cursor, and the results will be suggestions.
It's in include-fixer because:
- it handles SymbolInfos, actually SymbolIndex is exactly the right interface
- it's a good harness for lit testing the fuzzy YAML index
- (Laziness: we can't unit test clangd until reorganizing with a tool/ dir)
Other questionable choices:
- FuzzySymbolIndex, which just refines the contract of SymbolIndex. This is
an interface to allow extension to large monorepos (*cough*)
- an always-true safety check that Identifier == Name is removed from
SymbolIndexManager, as it's not true for fuzzy matching
- exposing -db=fuzzyYaml from include-fixer is not a very useful feature, and
a non-orthogonal ui (fuzziness vs data source). -db=fixed is similar though.
Reviewers: bkramer
Subscribers: cfe-commits, mgorny
Differential Revision: https://reviews.llvm.org/D30720
llvm-svn: 297630
62 lines
2.0 KiB
C++
62 lines
2.0 KiB
C++
//===-- FuzzySymbolIndexTests.cpp - Fuzzy symbol index unit tests ---------===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "FuzzySymbolIndex.h"
|
|
#include "gmock/gmock.h"
|
|
#include "llvm/Support/Regex.h"
|
|
#include "gtest/gtest.h"
|
|
|
|
using testing::ElementsAre;
|
|
using testing::Not;
|
|
|
|
namespace clang {
|
|
namespace include_fixer {
|
|
namespace {
|
|
|
|
TEST(FuzzySymbolIndexTest, Tokenize) {
|
|
EXPECT_THAT(FuzzySymbolIndex::tokenize("URLHandlerCallback"),
|
|
ElementsAre("url", "handler", "callback"));
|
|
EXPECT_THAT(FuzzySymbolIndex::tokenize("snake_case11"),
|
|
ElementsAre("snake", "case", "11"));
|
|
EXPECT_THAT(FuzzySymbolIndex::tokenize("__$42!!BOB\nbob"),
|
|
ElementsAre("42", "bob", "bob"));
|
|
}
|
|
|
|
MATCHER_P(MatchesSymbol, Identifier, "") {
|
|
llvm::Regex Pattern("^" + arg);
|
|
std::string err;
|
|
if (!Pattern.isValid(err)) {
|
|
*result_listener << "invalid regex: " << err;
|
|
return false;
|
|
}
|
|
auto Tokens = FuzzySymbolIndex::tokenize(Identifier);
|
|
std::string Target = llvm::join(Tokens.begin(), Tokens.end(), " ");
|
|
*result_listener << "matching against '" << Target << "'";
|
|
return llvm::Regex("^" + arg).match(Target);
|
|
}
|
|
|
|
TEST(FuzzySymbolIndexTest, QueryRegexp) {
|
|
auto QueryRegexp = [](const std::string &query) {
|
|
return FuzzySymbolIndex::queryRegexp(FuzzySymbolIndex::tokenize(query));
|
|
};
|
|
EXPECT_THAT(QueryRegexp("uhc"), MatchesSymbol("URLHandlerCallback"));
|
|
EXPECT_THAT(QueryRegexp("urhaca"), MatchesSymbol("URLHandlerCallback"));
|
|
EXPECT_THAT(QueryRegexp("uhcb"), Not(MatchesSymbol("URLHandlerCallback")))
|
|
<< "Non-prefix";
|
|
EXPECT_THAT(QueryRegexp("uc"), Not(MatchesSymbol("URLHandlerCallback")))
|
|
<< "Skip token";
|
|
|
|
EXPECT_THAT(QueryRegexp("uptr"), MatchesSymbol("unique_ptr"));
|
|
EXPECT_THAT(QueryRegexp("UniP"), MatchesSymbol("unique_ptr"));
|
|
}
|
|
|
|
} // namespace
|
|
} // namespace include_fixer
|
|
} // namespace clang
|