Skip to content

Commit 5c47336

Browse files
committed
convert a string to a set of integers...
1 parent 2051c03 commit 5c47336

File tree

2 files changed

+16
-1
lines changed

2 files changed

+16
-1
lines changed

pom.xml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@
77
<modelVersion>4.0.0</modelVersion>
88
<groupId>info.debatty</groupId>
99
<artifactId>java-string-similarity</artifactId>
10-
<version>0.3</version>
10+
<version>0.4</version>
1111
<packaging>jar</packaging>
1212

1313
<name>${project.artifactId}</name>

src/main/java/info/debatty/java/stringsimilarity/KShingling.java

Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,9 @@
22

33
import java.io.Serializable;
44
import java.security.InvalidParameterException;
5+
import java.util.ArrayList;
56
import java.util.HashSet;
7+
import java.util.Set;
68

79
/**
810
* A k-shingling is a set of unique k-grams, used to measure the similarity of
@@ -101,4 +103,17 @@ public boolean[] booleanVectorOf(String s) {
101103
return r;
102104
}
103105

106+
public Set<Integer> integerSetOf(String s) {
107+
Set<Integer> set = new HashSet<Integer>();
108+
int i = 0;
109+
for (String shingle : this) {
110+
if (s.contains(shingle)) {
111+
set.add(i);
112+
}
113+
i++;
114+
}
115+
116+
return set;
117+
}
118+
104119
}

0 commit comments

Comments
 (0)