[llvm-commits] [llvm] r116867 - in /llvm/trunk: include/llvm/ADT/StringRef.h lib/Support/StringRef.cpp

[Douglas Gregor]

Author: dgregor
Date: Tue Oct 19 17:13:48 2010
New Revision: 116867

URL: http://llvm.org/viewvc/llvm-project?rev=116867&view=rev
Log:
Extend StringRef's edit-distance algorithm to permit an upper bound on the allowed edit distance

Modified:
    llvm/trunk/include/llvm/ADT/StringRef.h
    llvm/trunk/lib/Support/StringRef.cpp

Modified: llvm/trunk/include/llvm/ADT/StringRef.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/ADT/StringRef.h?rev=116867&r1=116866&r2=116867&view=diff
==============================================================================
--- llvm/trunk/include/llvm/ADT/StringRef.h (original)
+++ llvm/trunk/include/llvm/ADT/StringRef.h Tue Oct 19 17:13:48 2010
@@ -142,11 +142,16 @@
     /// operation, rather than as two operations (an insertion and a
     /// removal).
     ///
+    /// \param MaxEditDistance If non-zero, the maximum edit distance that
+    /// this routine is allowed to compute. If the edit distance will exceed
+    /// that maximum, returns \c MaxEditDistance+1.
+    ///
     /// \returns the minimum number of character insertions, removals,
     /// or (if \p AllowReplacements is \c true) replacements needed to
     /// transform one of the given strings into the other. If zero,
     /// the strings are identical.
-    unsigned edit_distance(StringRef Other, bool AllowReplacements = true);
+    unsigned edit_distance(StringRef Other, bool AllowReplacements = true,
+                           unsigned MaxEditDistance = 0);
 
     /// str - Get the contents as an std::string.
     std::string str() const {

Modified: llvm/trunk/lib/Support/StringRef.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Support/StringRef.cpp?rev=116867&r1=116866&r2=116867&view=diff
==============================================================================
--- llvm/trunk/lib/Support/StringRef.cpp (original)
+++ llvm/trunk/lib/Support/StringRef.cpp Tue Oct 19 17:13:48 2010
@@ -68,7 +68,8 @@
 
 // Compute the edit distance between the two given strings.
 unsigned StringRef::edit_distance(llvm::StringRef Other, 
-                                  bool AllowReplacements) {
+                                  bool AllowReplacements,
+                                  unsigned MaxEditDistance) {
   // The algorithm implemented below is the "classic"
   // dynamic-programming algorithm for computing the Levenshtein
   // distance, which is described here:
@@ -94,6 +95,8 @@
 
   for (size_type y = 1; y <= m; ++y) {
     current[0] = y;
+    unsigned BestThisRow = current[0];
+    
     for (size_type x = 1; x <= n; ++x) {
       if (AllowReplacements) {
         current[x] = min(previous[x-1] + ((*this)[y-1] == Other[x-1]? 0u:1u),
@@ -103,8 +106,12 @@
         if ((*this)[y-1] == Other[x-1]) current[x] = previous[x-1];
         else current[x] = min(current[x-1], previous[x]) + 1;
       }
+      BestThisRow = min(BestThisRow, current[x]);
     }
     
+    if (MaxEditDistance && BestThisRow > MaxEditDistance)
+      return MaxEditDistance + 1;
+    
     unsigned *tmp = current;
     current = previous;
     previous = tmp;