public void Get_Keys() { var simhash = new SimhashLib.Simhash(); var testdata = new Dictionary <long, string>(); testdata.Add(1, "How are you? I Am fine. blar blar blar blar blar Thanks."); var simHashObjs = new Dictionary <long, SimhashResult>(); foreach (var it in testdata) { simHashObjs.Add(it.Key, simhash.ComputeHashByMd5(it.Value)); } var simHashIndex = new SimhashIndex(objs: simHashObjs, k: 10); var listOfKeys = simHashIndex.GetListKeys(simHashObjs[1]); Assert.True(listOfKeys.Count == 11); Assert.Equal("26,0", listOfKeys[0]); Assert.Equal("3,1", listOfKeys[1]); Assert.Equal("7,2", listOfKeys[2]); Assert.Equal("12,3", listOfKeys[3]); Assert.Equal("17,4", listOfKeys[4]); Assert.Equal("0,5", listOfKeys[5]); Assert.Equal("13,6", listOfKeys[6]); Assert.Equal("30,7", listOfKeys[7]); Assert.Equal("1,8", listOfKeys[8]); Assert.Equal("14,9", listOfKeys[9]); Assert.Equal("7496,10", listOfKeys[10]); }
public void test_get_keys() { Dictionary <long, string> testdata = new Dictionary <long, string>(); testdata.Add(1, "How are you? I Am fine. blar blar blar blar blar Thanks."); Dictionary <long, Simhash> simHashObjs = new Dictionary <long, Simhash>(); foreach (var it in testdata) { var simHash = new Simhash(hashingType: Simhash.HashingType.MD5); simHash.GenerateSimhash(it.Value); simHashObjs.Add(it.Key, simHash); } var simHashIndex = new SimhashIndex(objs: simHashObjs, k: 10); var listOfKeys = simHashIndex.get_the_keys(simHashObjs[1]); Assert.IsTrue(listOfKeys.Count == 11); Assert.AreEqual("26,0", listOfKeys[0]); Assert.AreEqual("3,1", listOfKeys[1]); Assert.AreEqual("7,2", listOfKeys[2]); Assert.AreEqual("12,3", listOfKeys[3]); Assert.AreEqual("17,4", listOfKeys[4]); Assert.AreEqual("0,5", listOfKeys[5]); Assert.AreEqual("13,6", listOfKeys[6]); Assert.AreEqual("30,7", listOfKeys[7]); Assert.AreEqual("1,8", listOfKeys[8]); Assert.AreEqual("14,9", listOfKeys[9]); Assert.AreEqual("7496,10", listOfKeys[10]); }
public void test_offset_creation_with_two() { var dict = new Dictionary <long, Simhash>(); var simHashIndex = new SimhashIndex(dict, k: 2); var offsets = simHashIndex.make_offsets(); Assert.AreEqual(0, offsets[0]); Assert.AreEqual(42, offsets[2]); Assert.IsTrue(offsets.Count == 3); }
public void Offset_Creation_With_Two() { var dict = new Dictionary <long, SimhashResult>(); var simHashIndex = new SimhashIndex(dict, k: 2); var offsets = simHashIndex.MakeOffsets(); Assert.Equal(0, offsets[0]); Assert.Equal(42, offsets[2]); Assert.True(offsets.Count == 3); }
public TestSimhashIndexMD5() { var simhash = new SimhashLib.Simhash(); testData.Add(1, "How are you? I Am fine. blar blar blar blar blar Thanks."); testData.Add(2, "How are you i am fine. blar blar blar blar blar than"); testData.Add(3, "This is simhash test."); testData.Add(4, "How are you i am fine. blar blar blar blar blar thank1"); foreach (var it in testData) { objs.Add(it.Key, simhash.ComputeHashByMd5(it.Value)); } index = new SimhashIndex(objs: objs, k: 10); }
public void setUp() { testData.Add(1, "How are you? I Am fine. blar blar blar blar blar Thanks."); testData.Add(2, "How are you i am fine. blar blar blar blar blar than"); testData.Add(3, "This is simhash test."); testData.Add(4, "How are you i am fine. blar blar blar blar blar thank1"); foreach (var it in testData) { var simHash = new Simhash(hashingType: Simhash.HashingType.MD5); simHash.GenerateSimhash(it.Value); objs.Add(it.Key, simHash); } index = new SimhashIndex(objs: objs, k: 10); }