[ADT][NFC] Early bail out for ComputeEditDistance

[njames93]

Summary

The minimun bound for number of edits is the size difference between the 2 arrays.
If MaxEditDistance is smaller than this, we can bail out early without needing to traverse any of the arrays.

[dblaikie]

Could be unit tested with a counting map functor? Though I'm not sure that's strictly necessary/worthwhile, up to you.

[njames93]

Add tests to verify bailing out.

[dblaikie]

Looks good, thanks!

llvm/unittests/ADT/EditDistanceTest.cpp

36–37

Generally prefer implicit construction over explicit where they're both valid - since implicit is strictly less powerful.

llvm/include/llvm/ADT/edit_distance.h

unsigned ComputeMappedEditDistance(ArrayRef<T> FromArray, ArrayRef<T> ToArray,
   // array, only one row plus one element are used at a time, so this
   // implementation just keeps one vector for the row.  To update one entry,
   // only the entries to the left, top, and top-left are needed.  The left
   // entry is in Row[x-1], the top entry is what's in Row[x] from the last
   // iteration, and the top-left entry is stored in Previous.
   typename ArrayRef<T>::size_type m = FromArray.size();
   typename ArrayRef<T>::size_type n = ToArray.size();
 
+  if (MaxEditDistance) {
+    // If the difference in size between the 2 arrays is larger than the max
+    // distance allowed, we can bail out as we will always need at least
+    // MaxEditDistance insertions or removals.
+    typename ArrayRef<T>::size_type AbsDiff = m > n ? m - n : n - m;
+    if (AbsDiff > MaxEditDistance)
+      return MaxEditDistance + 1;
+  }
+
   const unsigned SmallBufferSize = 64;
   unsigned SmallBuffer[SmallBufferSize];
   std::unique_ptr<unsigned[]> Allocated;
   unsigned *Row = SmallBuffer;
   if (n + 1 > SmallBufferSize) {
     Row = new unsigned[n + 1];
     Allocated.reset(Row);
   }

llvm/unittests/ADT/CMakeLists.txt

add_llvm_unittest(ADTTests
   CoalescingBitVectorTest.cpp
   CombinationGeneratorTest.cpp
   DAGDeltaAlgorithmTest.cpp
   DeltaAlgorithmTest.cpp
   DenseMapTest.cpp
   DenseSetTest.cpp
   DepthFirstIteratorTest.cpp
   DirectedGraphTest.cpp
+  EditDistanceTest.cpp
   EnumeratedArrayTest.cpp
   EquivalenceClassesTest.cpp
   FallibleIteratorTest.cpp
   FloatingPointMode.cpp
   FoldingSet.cpp
   FunctionExtrasTest.cpp
   FunctionRefTest.cpp
   HashingTest.cpp

llvm/unittests/ADT/EditDistanceTest.cpp

+//===- llvm/unittest/Support/EditDistanceTest.cpp - Edit distance tests ---===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/ADT/StringRef.h"
+#include "llvm/ADT/edit_distance.h"
+#include "gtest/gtest.h"
+#include <cstdlib>
+
+using namespace llvm;
+
+namespace {
+
+struct Result {
+  unsigned NumMaps;
+  unsigned EditDist;
+};
+} // namespace
+
+static Result editDistanceAndMaps(StringRef A, StringRef B,
+                                  unsigned MaxEditDistance = 0) {
+  unsigned NumMaps = 0;
+  auto TrackMaps = [&](const char X) {
+    ++NumMaps;
+    return X;
+  };
+  unsigned EditDist = llvm::ComputeMappedEditDistance(
+      makeArrayRef(A.data(), A.size()), makeArrayRef(B.data(), B.size()),
+      TrackMaps, true, MaxEditDistance);
+  return {NumMaps, EditDist};
+}
+
+TEST(EditDistance, VerifyShortCircuit) {
+  StringRef Hello = "Hello";
+  StringRef HelloWorld = "HelloWorld";
+  Result R = editDistanceAndMaps(Hello, HelloWorld, 5);
+  EXPECT_EQ(R.EditDist, 5U);
+  EXPECT_GT(R.NumMaps, 0U);
+
+  R = editDistanceAndMaps(Hello, HelloWorld);
+  EXPECT_EQ(R.EditDist, 5U);
+  EXPECT_GT(R.NumMaps, 0U);
+
+  R = editDistanceAndMaps(Hello, HelloWorld, 4);
+  EXPECT_EQ(R.EditDist, 5U);
+  EXPECT_EQ(R.NumMaps, 0U);
+
+  R = editDistanceAndMaps(HelloWorld, Hello, 4);
+  EXPECT_EQ(R.EditDist, 5U);
+  EXPECT_EQ(R.NumMaps, 0U);
+
+  R = editDistanceAndMaps(Hello, HelloWorld, 1);
+  EXPECT_EQ(R.EditDist, 2U);
+  EXPECT_EQ(R.NumMaps, 0U);
+
+  R = editDistanceAndMaps(HelloWorld, Hello, 1);
+  EXPECT_EQ(R.EditDist, 2U);
+  EXPECT_EQ(R.NumMaps, 0U);
+}