aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJunio C Hamano <gitster@pobox.com>2008-11-27 19:24:47 -0800
committerJunio C Hamano <gitster@pobox.com>2008-11-27 19:24:47 -0800
commitef4daa74af10da41d9af475579a138645ce6d295 (patch)
tree80dea99cbce1bd5edf414ef168702310ab3d5d9c
parentcab7d7d827365959a2713c6d9159f10401acbb51 (diff)
parent850fb6ff81a151887043b7edd10681640b0e91c1 (diff)
downloadgit-ef4daa74af10da41d9af475579a138645ce6d295.tar.gz
git-ef4daa74af10da41d9af475579a138645ce6d295.tar.xz
Merge branch 'st/levenshtein'
* st/levenshtein: Document levenshtein.c Fix deletion of last character in levenshtein distance
-rw-r--r--levenshtein.c39
1 files changed, 38 insertions, 1 deletions
diff --git a/levenshtein.c b/levenshtein.c
index db52f2c20..a32f4cdc4 100644
--- a/levenshtein.c
+++ b/levenshtein.c
@@ -1,6 +1,43 @@
#include "cache.h"
#include "levenshtein.h"
+/*
+ * This function implements the Damerau-Levenshtein algorithm to
+ * calculate a distance between strings.
+ *
+ * Basically, it says how many letters need to be swapped, substituted,
+ * deleted from, or added to string1, at least, to get string2.
+ *
+ * The idea is to build a distance matrix for the substrings of both
+ * strings. To avoid a large space complexity, only the last three rows
+ * are kept in memory (if swaps had the same or higher cost as one deletion
+ * plus one insertion, only two rows would be needed).
+ *
+ * At any stage, "i + 1" denotes the length of the current substring of
+ * string1 that the distance is calculated for.
+ *
+ * row2 holds the current row, row1 the previous row (i.e. for the substring
+ * of string1 of length "i"), and row0 the row before that.
+ *
+ * In other words, at the start of the big loop, row2[j + 1] contains the
+ * Damerau-Levenshtein distance between the substring of string1 of length
+ * "i" and the substring of string2 of length "j + 1".
+ *
+ * All the big loop does is determine the partial minimum-cost paths.
+ *
+ * It does so by calculating the costs of the path ending in characters
+ * i (in string1) and j (in string2), respectively, given that the last
+ * operation is a substition, a swap, a deletion, or an insertion.
+ *
+ * This implementation allows the costs to be weighted:
+ *
+ * - w (as in "sWap")
+ * - s (as in "Substitution")
+ * - a (for insertion, AKA "Add")
+ * - d (as in "Deletion")
+ *
+ * Note that this algorithm calculates a distance _iff_ d == a.
+ */
int levenshtein(const char *string1, const char *string2,
int w, int s, int a, int d)
{
@@ -25,7 +62,7 @@ int levenshtein(const char *string1, const char *string2,
row2[j + 1] > row0[j - 1] + w)
row2[j + 1] = row0[j - 1] + w;
/* deletion */
- if (j + 1 < len2 && row2[j + 1] > row1[j + 1] + d)
+ if (row2[j + 1] > row1[j + 1] + d)
row2[j + 1] = row1[j + 1] + d;
/* insertion */
if (row2[j + 1] > row2[j] + a)