Add tests for pkg/str methods

server/pkg/str/levenshtein_test.go

@@ -37,3 +37,32 @@ func TestLevenshteinDistance(t *testing.T) {
 		})
 	}
 }
+
+// goos: darwin
+// goarch: arm64
+// pkg: github.com/cortezaproject/corteza/server/pkg/str
+// BenchmarkLeven_100_100-12                  39949             25767 ns/op           93184 B/op        102 allocs/op
+// BenchmarkLeven_1000_1000-12                  390           3081967 ns/op         8298552 B/op       1011 allocs/op
+// BenchmarkLeven_10000_10000-12                  4         299103531 ns/op        829957216 B/op     10131 allocs/op
+// PASS
+
+func benchmarkLeven(b *testing.B, w1l, w2l int) {
+	w1 := randStringRunes(w1l)
+	w2 := randStringRunes(w2l)
+
+	for i := 0; i < b.N; i++ {
+		ToLevenshteinDistance(w1, w2)
+	}
+}
+
+func BenchmarkLeven_100_100(b *testing.B) {
+	benchmarkLeven(b, 100, 100)
+}
+
+func BenchmarkLeven_1000_1000(b *testing.B) {
+	benchmarkLeven(b, 1000, 1000)
+}
+
+func BenchmarkLeven_10000_10000(b *testing.B) {
+	benchmarkLeven(b, 10000, 10000)
+}

server/pkg/str/main_test.go

@@ -0,0 +1,13 @@
+package str
+
+import "math/rand"
+
+var letterRunes = []rune("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890?*_Ž!$%&'()=?*")
+
+func randStringRunes(n int) string {
+	b := make([]rune, n)
+	for i := range b {
+		b[i] = letterRunes[rand.Intn(len(letterRunes))]
+	}
+	return string(b)
+}

server/pkg/str/soundex.go

@@ -7,21 +7,21 @@ import (
 // ToSoundex takes a word and returns the soundex code for it.
 // https://en.wikipedia.org/wiki/Soundex
 //
-// 1. Retain the first letter of the name and drop all other occurrences of a, e, i, o, u, y, h, w.
-// 2. Replace consonants with digits as follows (after the first letter):
-//		b, f, p, v → 1
-//		c, g, j, k, q, s, x, z → 2
-//		d, t → 3
-//		l → 4
-//		m, n → 5
-//		r → 6
-// 3. If two or more letters with the same number are adjacent in the original name (before step 1),
-//		only retain the first letter; also two letters with the same number separated
-//		by 'h' or 'w' are coded as a single number, whereas such letters separated by a vowel are coded twice.
-//		This rule also applies to the first letter.
-// 4. Iterate the previous step until you have one letter and three numbers.
-//		If you have too few letters in your word that you can't assign three numbers, append with zeros
-//		until there are three numbers. If you have more than 3 letters, just retain the first 3 numbers.
+//  1. Retain the first letter of the name and drop all other occurrences of a, e, i, o, u, y, h, w.
+//  2. Replace consonants with digits as follows (after the first letter):
+//     b, f, p, v → 1
+//     c, g, j, k, q, s, x, z → 2
+//     d, t → 3
+//     l → 4
+//     m, n → 5
+//     r → 6
+//  3. If two or more letters with the same number are adjacent in the original name (before step 1),
+//     only retain the first letter; also two letters with the same number separated
+//     by 'h' or 'w' are coded as a single number, whereas such letters separated by a vowel are coded twice.
+//     This rule also applies to the first letter.
+//  4. Iterate the previous step until you have one letter and three numbers.
+//     If you have too few letters in your word that you can't assign three numbers, append with zeros
+//     until there are three numbers. If you have more than 3 letters, just retain the first 3 numbers.
 func ToSoundex(s string) string {
 	var (
 		// soundex code

server/pkg/str/soundex_test.go

@@ -62,3 +62,34 @@ func Test_soundex(t *testing.T) {
 		})
 	}
 }
+
+// goos: darwin
+// goarch: arm64
+// pkg: github.com/cortezaproject/corteza/server/pkg/str
+// BenchmarkSoundex_100_100-12               475930              2835 ns/op            3568 B/op         80 allocs/op
+// BenchmarkSoundex_1000_1000-12              30688             37494 ns/op          225458 B/op        657 allocs/op
+// BenchmarkSoundex_10000_10000-12              568           2023842 ns/op        25114459 B/op       6892 allocs/op
+// BenchmarkSoundex_100000_100000-12              7         160967804 ns/op        2544780057 B/op    69015 allocs/op
+func benchmarkSoundex(b *testing.B, w1l int) {
+	w1 := randStringRunes(w1l)
+
+	for i := 0; i < b.N; i++ {
+		ToSoundex(w1)
+	}
+}
+
+func BenchmarkSoundex_100_100(b *testing.B) {
+	benchmarkSoundex(b, 100)
+}
+
+func BenchmarkSoundex_1000_1000(b *testing.B) {
+	benchmarkSoundex(b, 1000)
+}
+
+func BenchmarkSoundex_10000_10000(b *testing.B) {
+	benchmarkSoundex(b, 10000)
+}
+
+func BenchmarkSoundex_100000_100000(b *testing.B) {
+	benchmarkSoundex(b, 100000)
+}