This commit is contained in:
jdl
2024-11-11 06:36:55 +01:00
parent d0587cc585
commit c5419d662e
102 changed files with 4181 additions and 0 deletions

30
tagengine/ngram.go Normal file
View File

@@ -0,0 +1,30 @@
package tagengine
import "unicode"
func ngramLength(s string) int {
N := len(s)
i := 0
count := 0
for {
// Eat spaces.
for i < N && unicode.IsSpace(rune(s[i])) {
i++
}
// Done?
if i == N {
break
}
// Non-space!
count++
// Eat non-spaces.
for i < N && !unicode.IsSpace(rune(s[i])) {
i++
}
}
return count
}