#5960 Add utility for computing "edit distance" between two strings.

This commit is contained in:
Kristian Bendiksen 2020-05-24 11:36:28 +02:00 committed by Magne Sjaastad
parent 30ee125749
commit 8a0f911856
3 changed files with 68 additions and 0 deletions

View File

@ -142,3 +142,51 @@ size_t RiaStdStringTools::findCharMatchCount( const std::string& s, char c )
}
return count;
}
//--------------------------------------------------------------------------------------------------
/// Function to find Levenshtein Distance between two strings (x and y).
/// Adapted from pseudocode from wikipedia: https://en.wikipedia.org/wiki/Levenshtein_distance
/// Implementation is the Wagner-Fischer variant: https://en.wikipedia.org/wiki/Wagner-Fischer_algorithm
///
/// Return value is higher when strings are more "different", and zero when strings are equal.
//--------------------------------------------------------------------------------------------------
int RiaStdStringTools::computeEditDistance( const std::string& x, const std::string& y )
{
// for all i and j, T[i,j] will hold the Levenshtein distance between
// the first i characters of x and the first j characters of y
int m = x.length();
int n = y.length();
std::vector<std::vector<int>> T( m + 1, std::vector<int>( n + 1, 0 ) );
// source prefixes can be transformed into empty string by
// dropping all characters
for ( int i = 1; i <= m; i++ )
T[i][0] = i;
// target prefixes can be reached from empty source prefix
// by inserting every character
for ( int j = 1; j <= n; j++ )
T[0][j] = j;
// fill the lookup table in bottom-up manner
for ( int i = 1; i <= m; i++ )
{
for ( int j = 1; j <= n; j++ )
{
int substitutionCost;
if ( x[i - 1] == y[j - 1] )
substitutionCost = 0;
else
substitutionCost = 1;
int deletion = T[i - 1][j] + 1;
int insertion = T[i][j - 1] + 1;
int replacement = T[i - 1][j - 1] + substitutionCost;
T[i][j] = std::min( std::min( deletion, insertion ), replacement );
}
}
// The distance between the two full strings as the last value computed.
return T[m][n];
}

View File

@ -43,6 +43,8 @@ public:
static std::vector<std::string> splitStringBySpace( const std::string& s );
static int computeEditDistance( const std::string& x, const std::string& y);
private:
template <class Container>
static void splitByDelimiter( const std::string& str, Container& cont, char delimiter = ' ' );

View File

@ -23,3 +23,21 @@ TEST( RiaStdStringToolsTest, ParseNumbers )
EXPECT_TRUE( RiaStdStringTools::isNumber( text, decimalPoint ) );
}
}
//--------------------------------------------------------------------------------------------------
///
//--------------------------------------------------------------------------------------------------
TEST( RiaStdStringToolsTest, EditDistance )
{
// Equal string needs zero edits
EXPECT_EQ( 0, RiaStdStringTools::computeEditDistance( "same", "same" ) );
// Empty strings are also zero edits
EXPECT_EQ( 0, RiaStdStringTools::computeEditDistance( "", "" ) );
// Examples from wikipedia
EXPECT_EQ( 3, RiaStdStringTools::computeEditDistance( "kitten", "sitting" ) );
EXPECT_EQ( 3, RiaStdStringTools::computeEditDistance( "sitting", "kitten" ) );
EXPECT_EQ( 3, RiaStdStringTools::computeEditDistance( "Saturday", "Sunday" ) );
EXPECT_EQ( 3, RiaStdStringTools::computeEditDistance( "Sunday", "Saturday" ) );
}