summaryrefslogtreecommitdiff
path: root/levenshtein.c
diff options
context:
space:
mode:
authorJohannes Schindelin <Johannes.Schindelin@gmx.de>2008-11-20 14:27:27 +0100
committerJunio C Hamano <gitster@pobox.com>2008-11-23 19:23:34 -0800
commit850fb6ff81a151887043b7edd10681640b0e91c1 (patch)
treeaa18591bf1e3eff73b68030e00422c1a5d6b1bac /levenshtein.c
parent13c6bcd49f8151438aa3302b8764c6f8d42441e2 (diff)
downloadgit-850fb6ff81a151887043b7edd10681640b0e91c1.tar.gz
Document levenshtein.c
Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'levenshtein.c')
-rw-r--r--levenshtein.c37
1 files changed, 37 insertions, 0 deletions
diff --git a/levenshtein.c b/levenshtein.c
index 98fea723d4..a32f4cdc45 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)
{