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

llvm-svn: 288553

1 files changed, 22 insertions, 2 deletions

diff --git a/llvm/unittests/Support/TrigramIndexTest.cpp b/llvm/unittests/Support/TrigramIndexTest.cpp
index 9f61e7ee4a9..fb0ad1749bb 100644
--- a/llvm/unittests/Support/TrigramIndexTest.cpp
+++ b/llvm/unittests/Support/TrigramIndexTest.cpp
@@ -94,9 +94,29 @@ TEST_F(TrigramIndexTest, TooComplicatedRegex2) {
   EXPECT_TRUE(TI->isDefeated());
 }
 
-TEST_F(TrigramIndexTest, SpecialSymbol) {
+TEST_F(TrigramIndexTest, EscapedSymbols) {
   std::unique_ptr<TrigramIndex> TI =
-      makeTrigramIndex({"*c\\+\\+*"});
+      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());
 }