// Tokenize tokenizes the given string with the delimiter
func Tokenize(text util.Chars, delimiter Delimiter) []Token {
if delimiter.str == nil && delimiter.regex == nil {
// AWK-style (\S+\s*)
tokens, prefixLength := awkTokenizer(text)
return withPrefixLengths(tokens, prefixLength)
}
if delimiter.str != nil {
return withPrefixLengths(text.Split(*delimiter.str), 0)
}
// FIXME performance
var tokens []string
if delimiter.regex != nil {
str := text.ToString()
for len(str) > 0 {
loc := delimiter.regex.FindStringIndex(str)
if loc == nil {
loc = []int{0, len(str)}
}
last := util.Max(loc[1], 1)
tokens = append(tokens, str[:last])
str = str[last:]
}
}
asRunes := make([]util.Chars, len(tokens))
for i, token := range tokens {
asRunes[i] = util.RunesToChars([]rune(token))
}
return withPrefixLengths(asRunes, 0)
}
// EqualMatch performs equal-match
func EqualMatch(caseSensitive bool, normalize bool, forward bool, text util.Chars, pattern []rune, withPos bool, slab *util.Slab) (Result, *[]int) {
lenPattern := len(pattern)
if text.Length() != lenPattern {
return Result{-1, -1, 0}, nil
}
match := true
if normalize {
runes := text.ToRunes()
for idx, pchar := range pattern {
char := runes[idx]
if !caseSensitive {
char = unicode.To(unicode.LowerCase, char)
}
if normalizeRune(pchar) != normalizeRune(char) {
match = false
break
}
}
} else {
runesStr := text.ToString()
if !caseSensitive {
runesStr = strings.ToLower(runesStr)
}
match = runesStr == string(pattern)
}
if match {
return Result{0, lenPattern, (scoreMatch+bonusBoundary)*lenPattern +
(bonusFirstCharMultiplier-1)*bonusBoundary}, nil
}
return Result{-1, -1, 0}, nil
}