[llvm-commits] [llvm] r92309 - in /llvm/trunk: include/llvm/ADT/StringRef.h lib/Support/StringRef.cpp

[Douglas Gregor]

Author: dgregor
Date: Wed Dec 30 11:23:44 2009
New Revision: 92309

URL: http://llvm.org/viewvc/llvm-project?rev=92309&view=rev
Log:
Implement edit distance for StringRef

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=92309&r1=92308&r2=92309&view=diff

==============================================================================
--- llvm/trunk/include/llvm/ADT/StringRef.h (original)
+++ llvm/trunk/include/llvm/ADT/StringRef.h Wed Dec 30 11:23:44 2009
@@ -133,6 +133,22 @@
     /// compare_lower - Compare two strings, ignoring case.
     int compare_lower(StringRef RHS) const;
 
+    /// \brief Determine the edit distance between this string and another 
+    /// string.
+    ///
+    /// \param Other the string to compare this string against.
+    ///
+    /// \param AllowReplacements whether to allow character
+    /// replacements (change one character into another) as a single
+    /// operation, rather than as two operations (an insertion and a
+    /// removal).
+    ///
+    /// \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);
+
     /// str - Get the contents as an std::string.
     std::string str() const { return std::string(Data, Length); }
 

Modified: llvm/trunk/lib/Support/StringRef.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Support/StringRef.cpp?rev=92309&r1=92308&r2=92309&view=diff

==============================================================================
--- llvm/trunk/lib/Support/StringRef.cpp (original)
+++ llvm/trunk/lib/Support/StringRef.cpp Wed Dec 30 11:23:44 2009
@@ -8,6 +8,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/ADT/StringRef.h"
+#include <vector>
 using namespace llvm;
 
 // MSVC emits references to this into the translation units which reference it.
@@ -35,6 +36,36 @@
   return Length < RHS.Length ? -1 : 1;
 }
 
+/// \brief Compute the edit distance between the two given strings.
+unsigned StringRef::edit_distance(llvm::StringRef Other, 
+                                  bool AllowReplacements) {
+  size_type m = size();
+  size_type n = Other.size();
+
+  std::vector<unsigned> previous(n+1, 0);
+  for (std::vector<unsigned>::size_type i = 0; i <= n; ++i) 
+    previous[i] = i;
+
+  std::vector<unsigned> current(n+1, 0);
+  for (size_type y = 1; y <= m; ++y) {
+    current.assign(n+1, 0);
+    current[0] = y;
+    for (size_type x = 1; x <= n; ++x) {
+      if (AllowReplacements) {
+        current[x] = min(previous[x-1] + ((*this)[y-1] == Other[x-1]? 0u:1u),
+                         min(current[x-1], previous[x])+1);
+      }
+      else {
+        if ((*this)[y-1] == Other[x-1]) current[x] = previous[x-1];
+        else current[x] = min(current[x-1], previous[x]) + 1;
+      }
+    }
+    current.swap(previous);
+  }
+
+  return previous[n];
+}
+
 //===----------------------------------------------------------------------===//
 // String Searching
 //===----------------------------------------------------------------------===//