diff options
Diffstat (limited to 'libgo/go/strings/strings.go')
| -rw-r--r-- | libgo/go/strings/strings.go | 147 |
1 files changed, 113 insertions, 34 deletions
diff --git a/libgo/go/strings/strings.go b/libgo/go/strings/strings.go index a98f5d8..7337481 100644 --- a/libgo/go/strings/strings.go +++ b/libgo/go/strings/strings.go @@ -341,38 +341,38 @@ func Fields(s string) []string { wasSpace = isSpace } - if setBits < utf8.RuneSelf { // ASCII fast path - a := make([]string, n) - na := 0 - fieldStart := 0 - i := 0 - // Skip spaces in the front of the input. - for i < len(s) && asciiSpace[s[i]] != 0 { + if setBits >= utf8.RuneSelf { + // Some runes in the input string are not ASCII. + return FieldsFunc(s, unicode.IsSpace) + } + // ASCII fast path + a := make([]string, n) + na := 0 + fieldStart := 0 + i := 0 + // Skip spaces in the front of the input. + for i < len(s) && asciiSpace[s[i]] != 0 { + i++ + } + fieldStart = i + for i < len(s) { + if asciiSpace[s[i]] == 0 { i++ + continue } - fieldStart = i - for i < len(s) { - if asciiSpace[s[i]] == 0 { - i++ - continue - } - a[na] = s[fieldStart:i] - na++ + a[na] = s[fieldStart:i] + na++ + i++ + // Skip spaces in between fields. + for i < len(s) && asciiSpace[s[i]] != 0 { i++ - // Skip spaces in between fields. - for i < len(s) && asciiSpace[s[i]] != 0 { - i++ - } - fieldStart = i } - if fieldStart < len(s) { // Last field might end at EOF. - a[na] = s[fieldStart:] - } - return a + fieldStart = i } - - // Some runes in the input string are not ASCII. - return FieldsFunc(s, unicode.IsSpace) + if fieldStart < len(s) { // Last field might end at EOF. + a[na] = s[fieldStart:] + } + return a } // FieldsFunc splits the string s at each run of Unicode code points c satisfying f(c) @@ -550,7 +550,7 @@ func Repeat(s string, count int) string { return b.String() } -// ToUpper returns a copy of the string s with all Unicode letters mapped to their upper case. +// ToUpper returns s with all Unicode letters mapped to their upper case. func ToUpper(s string) string { isASCII, hasLower := true, false for i := 0; i < len(s); i++ { @@ -559,7 +559,7 @@ func ToUpper(s string) string { isASCII = false break } - hasLower = hasLower || (c >= 'a' && c <= 'z') + hasLower = hasLower || ('a' <= c && c <= 'z') } if isASCII { // optimize for ASCII-only strings. @@ -570,7 +570,7 @@ func ToUpper(s string) string { b.Grow(len(s)) for i := 0; i < len(s); i++ { c := s[i] - if c >= 'a' && c <= 'z' { + if 'a' <= c && c <= 'z' { c -= 'a' - 'A' } b.WriteByte(c) @@ -580,7 +580,7 @@ func ToUpper(s string) string { return Map(unicode.ToUpper, s) } -// ToLower returns a copy of the string s with all Unicode letters mapped to their lower case. +// ToLower returns s with all Unicode letters mapped to their lower case. func ToLower(s string) string { isASCII, hasUpper := true, false for i := 0; i < len(s); i++ { @@ -589,7 +589,7 @@ func ToLower(s string) string { isASCII = false break } - hasUpper = hasUpper || (c >= 'A' && c <= 'Z') + hasUpper = hasUpper || ('A' <= c && c <= 'Z') } if isASCII { // optimize for ASCII-only strings. @@ -600,7 +600,7 @@ func ToLower(s string) string { b.Grow(len(s)) for i := 0; i < len(s); i++ { c := s[i] - if c >= 'A' && c <= 'Z' { + if 'A' <= c && c <= 'Z' { c += 'a' - 'A' } b.WriteByte(c) @@ -631,6 +631,56 @@ func ToTitleSpecial(c unicode.SpecialCase, s string) string { return Map(c.ToTitle, s) } +// ToValidUTF8 returns a copy of the string s with each run of invalid UTF-8 byte sequences +// replaced by the replacement string, which may be empty. +func ToValidUTF8(s, replacement string) string { + var b Builder + + for i, c := range s { + if c != utf8.RuneError { + continue + } + + _, wid := utf8.DecodeRuneInString(s[i:]) + if wid == 1 { + b.Grow(len(s) + len(replacement)) + b.WriteString(s[:i]) + s = s[i:] + break + } + } + + // Fast path for unchanged input + if b.Cap() == 0 { // didn't call b.Grow above + return s + } + + invalid := false // previous byte was from an invalid UTF-8 sequence + for i := 0; i < len(s); { + c := s[i] + if c < utf8.RuneSelf { + i++ + invalid = false + b.WriteByte(c) + continue + } + _, wid := utf8.DecodeRuneInString(s[i:]) + if wid == 1 { + i++ + if !invalid { + invalid = true + b.WriteString(replacement) + } + continue + } + invalid = false + b.WriteString(s[i : i+wid]) + i += wid + } + + return b.String() +} + // isSeparator reports whether the rune could mark a word boundary. // TODO: update when package unicode captures more of the properties. func isSeparator(r rune) bool { @@ -818,7 +868,36 @@ func TrimRight(s string, cutset string) string { // TrimSpace returns a slice of the string s, with all leading // and trailing white space removed, as defined by Unicode. func TrimSpace(s string) string { - return TrimFunc(s, unicode.IsSpace) + // Fast path for ASCII: look for the first ASCII non-space byte + start := 0 + for ; start < len(s); start++ { + c := s[start] + if c >= utf8.RuneSelf { + // If we run into a non-ASCII byte, fall back to the + // slower unicode-aware method on the remaining bytes + return TrimFunc(s[start:], unicode.IsSpace) + } + if asciiSpace[c] == 0 { + break + } + } + + // Now look for the first ASCII non-space byte from the end + stop := len(s) + for ; stop > start; stop-- { + c := s[stop-1] + if c >= utf8.RuneSelf { + return TrimFunc(s[start:stop], unicode.IsSpace) + } + if asciiSpace[c] == 0 { + break + } + } + + // At this point s[start:stop] starts and ends with an ASCII + // non-space bytes, so we're done. Non-ASCII cases have already + // been handled above. + return s[start:stop] } // TrimPrefix returns s without the provided leading prefix string. |