llvm/unittests/Support/TrigramIndexTest.cpp
Ivan Krasin 8460d68f0a Support escaping in TrigramIndex.
Summary:
This is a follow up to r288303, where I have introduced TrigramIndex
to speed up SpecialCaseList for the cases when all rules are
simple wildcards, like *hello*wor.d*.

Here, I add support for escaping, so that it's possible to
specify rules like *c\+\+abi*.

Reviewers: pcc

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D27318

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@288553 91177308-0d34-0410-b5e6-96231b3b80d8
2016-12-02 23:30:16 +00:00

133 lines
3.9 KiB
C++

//===- TrigramIndexTest.cpp - Unit tests for TrigramIndex -----------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#include "llvm/ADT/STLExtras.h"
#include "llvm/Support/TrigramIndex.h"
#include "gtest/gtest.h"
#include <string>
#include <vector>
using namespace llvm;
namespace {
class TrigramIndexTest : public ::testing::Test {
protected:
std::unique_ptr<TrigramIndex> makeTrigramIndex(
std::vector<std::string> Rules) {
std::unique_ptr<TrigramIndex> TI =
make_unique<TrigramIndex>();
for (auto &Rule : Rules)
TI->insert(Rule);
return TI;
}
};
TEST_F(TrigramIndexTest, Empty) {
std::unique_ptr<TrigramIndex> TI =
makeTrigramIndex({});
EXPECT_FALSE(TI->isDefeated());
EXPECT_TRUE(TI->isDefinitelyOut("foo"));
}
TEST_F(TrigramIndexTest, Basic) {
std::unique_ptr<TrigramIndex> TI =
makeTrigramIndex({"*hello*", "*wor.d*"});
EXPECT_FALSE(TI->isDefeated());
EXPECT_TRUE(TI->isDefinitelyOut("foo"));
}
TEST_F(TrigramIndexTest, NoTrigramsInRules) {
std::unique_ptr<TrigramIndex> TI =
makeTrigramIndex({"b.r", "za*az"});
EXPECT_TRUE(TI->isDefeated());
EXPECT_FALSE(TI->isDefinitelyOut("foo"));
EXPECT_FALSE(TI->isDefinitelyOut("bar"));
EXPECT_FALSE(TI->isDefinitelyOut("zakaz"));
}
TEST_F(TrigramIndexTest, NoTrigramsInARule) {
std::unique_ptr<TrigramIndex> TI =
makeTrigramIndex({"*hello*", "*wo.ld*"});
EXPECT_TRUE(TI->isDefeated());
EXPECT_FALSE(TI->isDefinitelyOut("foo"));
}
TEST_F(TrigramIndexTest, RepetitiveRule) {
std::unique_ptr<TrigramIndex> TI =
makeTrigramIndex({"*bar*bar*bar*bar*bar", "bar*bar"});
EXPECT_FALSE(TI->isDefeated());
EXPECT_TRUE(TI->isDefinitelyOut("foo"));
EXPECT_TRUE(TI->isDefinitelyOut("bar"));
EXPECT_FALSE(TI->isDefinitelyOut("barbara"));
EXPECT_FALSE(TI->isDefinitelyOut("bar+bar"));
}
TEST_F(TrigramIndexTest, PopularTrigram) {
std::unique_ptr<TrigramIndex> TI =
makeTrigramIndex({"*aaa*", "*aaaa*", "*aaaaa*", "*aaaaa*", "*aaaaaa*"});
EXPECT_TRUE(TI->isDefeated());
}
TEST_F(TrigramIndexTest, PopularTrigram2) {
std::unique_ptr<TrigramIndex> TI =
makeTrigramIndex({"class1.h", "class2.h", "class3.h", "class4.h", "class.h"});
EXPECT_TRUE(TI->isDefeated());
}
TEST_F(TrigramIndexTest, TooComplicatedRegex) {
std::unique_ptr<TrigramIndex> TI =
makeTrigramIndex({"[0-9]+"});
EXPECT_TRUE(TI->isDefeated());
}
TEST_F(TrigramIndexTest, TooComplicatedRegex2) {
std::unique_ptr<TrigramIndex> TI =
makeTrigramIndex({"foo|bar"});
EXPECT_TRUE(TI->isDefeated());
}
TEST_F(TrigramIndexTest, EscapedSymbols) {
std::unique_ptr<TrigramIndex> TI =
makeTrigramIndex({"*c\\+\\+*", "*hello\\\\world*", "a\\tb", "a\\0b"});
EXPECT_FALSE(TI->isDefeated());
EXPECT_FALSE(TI->isDefinitelyOut("c++"));
EXPECT_TRUE(TI->isDefinitelyOut("c\\+\\+"));
EXPECT_FALSE(TI->isDefinitelyOut("hello\\world"));
EXPECT_TRUE(TI->isDefinitelyOut("hello\\\\world"));
EXPECT_FALSE(TI->isDefinitelyOut("atb"));
EXPECT_TRUE(TI->isDefinitelyOut("a\\tb"));
EXPECT_TRUE(TI->isDefinitelyOut("a\tb"));
EXPECT_FALSE(TI->isDefinitelyOut("a0b"));
}
TEST_F(TrigramIndexTest, Backreference1) {
std::unique_ptr<TrigramIndex> TI =
makeTrigramIndex({"*foo\\1*"});
EXPECT_TRUE(TI->isDefeated());
}
TEST_F(TrigramIndexTest, Backreference2) {
std::unique_ptr<TrigramIndex> TI =
makeTrigramIndex({"*foo\\2*"});
EXPECT_TRUE(TI->isDefeated());
}
TEST_F(TrigramIndexTest, Sequence) {
std::unique_ptr<TrigramIndex> TI =
makeTrigramIndex({"class1.h", "class2.h", "class3.h", "class4.h"});
EXPECT_FALSE(TI->isDefeated());
EXPECT_FALSE(TI->isDefinitelyOut("class1"));
EXPECT_TRUE(TI->isDefinitelyOut("class.h"));
EXPECT_TRUE(TI->isDefinitelyOut("class"));
}
} // namespace