2018-12-17 13:41:24 +00:00
|
|
|
package parse // import "github.com/tdewolff/parse"
|
|
|
|
|
|
|
|
// Copy returns a copy of the given byte slice.
|
|
|
|
func Copy(src []byte) (dst []byte) {
|
|
|
|
dst = make([]byte, len(src))
|
|
|
|
copy(dst, src)
|
|
|
|
return
|
|
|
|
}
|
|
|
|
|
|
|
|
// ToLower converts all characters in the byte slice from A-Z to a-z.
|
|
|
|
func ToLower(src []byte) []byte {
|
|
|
|
for i, c := range src {
|
|
|
|
if c >= 'A' && c <= 'Z' {
|
|
|
|
src[i] = c + ('a' - 'A')
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return src
|
|
|
|
}
|
|
|
|
|
|
|
|
// EqualFold returns true when s matches case-insensitively the targetLower (which must be lowercase).
|
|
|
|
func EqualFold(s, targetLower []byte) bool {
|
|
|
|
if len(s) != len(targetLower) {
|
|
|
|
return false
|
|
|
|
}
|
|
|
|
for i, c := range targetLower {
|
2019-06-09 00:01:48 +00:00
|
|
|
d := s[i]
|
|
|
|
if d != c && (d < 'A' || d > 'Z' || d+('a'-'A') != c) {
|
2018-12-17 13:41:24 +00:00
|
|
|
return false
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return true
|
|
|
|
}
|
|
|
|
|
|
|
|
var whitespaceTable = [256]bool{
|
|
|
|
// ASCII
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, true, true, false, true, true, false, false, // tab, new line, form feed, carriage return
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
|
|
|
|
true, false, false, false, false, false, false, false, // space
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
|
|
|
|
// non-ASCII
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
}
|
|
|
|
|
|
|
|
// IsWhitespace returns true for space, \n, \r, \t, \f.
|
|
|
|
func IsWhitespace(c byte) bool {
|
|
|
|
return whitespaceTable[c]
|
|
|
|
}
|
|
|
|
|
|
|
|
var newlineTable = [256]bool{
|
|
|
|
// ASCII
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, true, false, false, true, false, false, // new line, carriage return
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
|
|
|
|
// non-ASCII
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
false, false, false, false, false, false, false, false,
|
|
|
|
}
|
|
|
|
|
|
|
|
// IsNewline returns true for \n, \r.
|
|
|
|
func IsNewline(c byte) bool {
|
|
|
|
return newlineTable[c]
|
|
|
|
}
|
|
|
|
|
|
|
|
// IsAllWhitespace returns true when the entire byte slice consists of space, \n, \r, \t, \f.
|
|
|
|
func IsAllWhitespace(b []byte) bool {
|
|
|
|
for _, c := range b {
|
|
|
|
if !IsWhitespace(c) {
|
|
|
|
return false
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return true
|
|
|
|
}
|
|
|
|
|
|
|
|
// TrimWhitespace removes any leading and trailing whitespace characters.
|
|
|
|
func TrimWhitespace(b []byte) []byte {
|
|
|
|
n := len(b)
|
|
|
|
start := n
|
|
|
|
for i := 0; i < n; i++ {
|
|
|
|
if !IsWhitespace(b[i]) {
|
|
|
|
start = i
|
|
|
|
break
|
|
|
|
}
|
|
|
|
}
|
|
|
|
end := n
|
|
|
|
for i := n - 1; i >= start; i-- {
|
|
|
|
if !IsWhitespace(b[i]) {
|
|
|
|
end = i + 1
|
|
|
|
break
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return b[start:end]
|
|
|
|
}
|
|
|
|
|
|
|
|
// ReplaceMultipleWhitespace replaces character series of space, \n, \t, \f, \r into a single space or newline (when the serie contained a \n or \r).
|
|
|
|
func ReplaceMultipleWhitespace(b []byte) []byte {
|
|
|
|
j := 0
|
|
|
|
prevWS := false
|
|
|
|
hasNewline := false
|
|
|
|
for i, c := range b {
|
|
|
|
if IsWhitespace(c) {
|
|
|
|
prevWS = true
|
|
|
|
if IsNewline(c) {
|
|
|
|
hasNewline = true
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
if prevWS {
|
|
|
|
prevWS = false
|
|
|
|
if hasNewline {
|
|
|
|
hasNewline = false
|
|
|
|
b[j] = '\n'
|
|
|
|
} else {
|
|
|
|
b[j] = ' '
|
|
|
|
}
|
|
|
|
j++
|
|
|
|
}
|
|
|
|
b[j] = b[i]
|
|
|
|
j++
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if prevWS {
|
|
|
|
if hasNewline {
|
|
|
|
b[j] = '\n'
|
|
|
|
} else {
|
|
|
|
b[j] = ' '
|
|
|
|
}
|
|
|
|
j++
|
|
|
|
}
|
|
|
|
return b[:j]
|
|
|
|
}
|