gofront 1.8.0 → 1.9.0

package/stdlib/unicode/unicode.go

@@ -13,6 +13,144 @@ const (
 	Version         = "15.0.0"
 )
 
+// Classes of unicode_is, the host's answer for runes above ASCII.
+const (
+	classLetter = iota
+	classDigit
+	classSpace
+	classUpper
+	classLower
+	classPunct
+	classControl
+	classPrint
+	classGraphic
+)
+
+// hostIs reports whether the host's Unicode tables place r in the class.
+//
+//gofront:intrinsic unicode_is
+func hostIs(r rune, class int) bool
+
+// hostToUpper is the host's upper case mapping of r; a letter whose upper
+// case spans several code points stays as it is.
+//
+//gofront:intrinsic unicode_to_upper
+func hostToUpper(r rune) rune
+
+// hostToLower is the host's lower case mapping of r.
+//
+//gofront:intrinsic unicode_to_lower
+func hostToLower(r rune) rune
+
+func isValid(r rune) bool { return r >= 0 && r <= MaxRune }
+
+// IsLetter reports whether the rune is a letter (category L).
+func IsLetter(r rune) bool {
+	if r < 0x80 {
+		return 'a' <= r && r <= 'z' || 'A' <= r && r <= 'Z'
+	}
+	return isValid(r) && hostIs(r, classLetter)
+}
+
+// IsDigit reports whether the rune is a decimal digit.
+func IsDigit(r rune) bool {
+	if r < 0x80 {
+		return '0' <= r && r <= '9'
+	}
+	return isValid(r) && hostIs(r, classDigit)
+}
+
+// IsSpace reports whether the rune is a space character as defined by
+// Unicode's White Space property.
+func IsSpace(r rune) bool {
+	if r < 0x80 {
+		return r == ' ' || '\t' <= r && r <= '\r'
+	}
+	return isValid(r) && hostIs(r, classSpace)
+}
+
+// IsUpper reports whether the rune is an upper case letter.
+func IsUpper(r rune) bool {
+	if r < 0x80 {
+		return 'A' <= r && r <= 'Z'
+	}
+	return isValid(r) && hostIs(r, classUpper)
+}
+
+// IsLower reports whether the rune is a lower case letter.
+func IsLower(r rune) bool {
+	if r < 0x80 {
+		return 'a' <= r && r <= 'z'
+	}
+	return isValid(r) && hostIs(r, classLower)
+}
+
+// IsPunct reports whether the rune is a Unicode punctuation character
+// (category P).
+func IsPunct(r rune) bool {
+	if r < 0x80 {
+		switch r {
+		case '!', '"', '#', '%', '&', '\'', '(', ')', '*', ',', '-', '.', '/',
+			':', ';', '?', '@', '[', '\\', ']', '_', '{', '}':
+			return true
+		}
+		return false
+	}
+	return isValid(r) && hostIs(r, classPunct)
+}
+
+// IsControl reports whether the rune is a control character.
+func IsControl(r rune) bool {
+	if r < 0x80 {
+		return r >= 0 && r < ' ' || r == 0x7F
+	}
+	return isValid(r) && hostIs(r, classControl)
+}
+
+// IsPrint reports whether the rune is printable.
+func IsPrint(r rune) bool {
+	if r < 0x80 {
+		return ' ' <= r && r <= '~'
+	}
+	return isValid(r) && !IsSpace(r) && hostIs(r, classPrint)
+}
+
+// IsGraphic reports whether the rune is a graphic character.
+func IsGraphic(r rune) bool {
+	if r < 0x80 {
+		return ' ' <= r && r <= '~'
+	}
+	return isValid(r) && hostIs(r, classGraphic)
+}
+
+// ToUpper maps the rune to upper case.
+func ToUpper(r rune) rune {
+	if r < 0x80 {
+		if 'a' <= r && r <= 'z' {
+			return r - ('a' - 'A')
+		}
+		return r
+	}
+	if !isValid(r) {
+		return r
+	}
+	return hostToUpper(r)
+}
+
+// ToLower maps the rune to lower case.
+func ToLower(r rune) rune {
+	if r < 0x80 {
+		if 'A' <= r && r <= 'Z' {
+			return r + ('a' - 'A')
+		}
+		return r
+	}
+	if !isValid(r) {
+		return r
+	}
+	return hostToLower(r)
+}
+
 // ToTitle maps the rune to title case.
 func ToTitle(r rune) rune {
 	if r <= MaxASCII {
@@ -34,7 +172,7 @@ func ToTitle(r rune) rune {
 	if 0x10D0 <= r && r <= 0x10FF {
 		return r
 	}
-	return rune(ToUpper(int(r)))
+	return ToUpper(r)
 }
 
 type foldPair struct {
@@ -105,8 +243,8 @@ func SimpleFold(r rune) rune {
 	if lo < len(caseOrbit) && rune(caseOrbit[lo].From) == r {
 		return rune(caseOrbit[lo].To)
 	}
-	if l := rune(ToLower(int(r))); l != r {
+	if l := ToLower(r); l != r {
 		return l
 	}
-	return rune(ToUpper(int(r)))
+	return ToUpper(r)
 }

package/stdlib/unicode/utf8/utf8.go

@@ -0,0 +1,464 @@
+//go:build gofront
+
+//gofront:target both
+
+// Copyright 2009 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+// Package utf8 implements functions and constants to support text encoded in
+// UTF-8. It includes functions to translate between runes and UTF-8 byte sequences.
+// See https://en.wikipedia.org/wiki/UTF-8
+package utf8
+
+// The conditions RuneError==unicode.ReplacementChar and
+// MaxRune==unicode.MaxRune are verified in the tests.
+// Defining them locally avoids this package depending on package unicode.
+
+// Numbers fundamental to the encoding.
+const (
+	RuneError = '\uFFFD'     // the "error" Rune or "Unicode replacement character"
+	RuneSelf  = 0x80         // characters below RuneSelf are represented as themselves in a single byte.
+	MaxRune   = '\U0010FFFF' // Maximum valid Unicode code point.
+	UTFMax    = 4            // maximum number of bytes of a UTF-8 encoded Unicode character.
+)
+
+// Code points in the surrogate range are not valid for UTF-8.
+const (
+	surrogateMin = 0xD800
+	surrogateMax = 0xDFFF
+)
+
+const (
+	t1 = 0b00000000
+	tx = 0b10000000
+	t2 = 0b11000000
+	t3 = 0b11100000
+	t4 = 0b11110000
+	t5 = 0b11111000
+
+	maskx = 0b00111111
+	mask2 = 0b00011111
+	mask3 = 0b00001111
+	mask4 = 0b00000111
+
+	rune1Max = 1<<7 - 1
+	rune2Max = 1<<11 - 1
+	rune3Max = 1<<16 - 1
+
+	// The default lowest and highest continuation byte.
+	locb = 0b10000000
+	hicb = 0b10111111
+
+	// These names of these constants are chosen to give nice alignment in the
+	// table below. The first nibble is an index into acceptRanges or F for
+	// special one-byte cases. The second nibble is the Rune length or the
+	// Status for the special one-byte case.
+	xx = 0xF1 // invalid: size 1
+	as = 0xF0 // ASCII: size 1
+	s1 = 0x02 // accept 0, size 2
+	s2 = 0x13 // accept 1, size 3
+	s3 = 0x03 // accept 0, size 3
+	s4 = 0x23 // accept 2, size 3
+	s5 = 0x34 // accept 3, size 4
+	s6 = 0x04 // accept 0, size 4
+	s7 = 0x44 // accept 4, size 4
+)
+
+const (
+	runeErrorByte0 = t3 | (RuneError >> 12)
+	runeErrorByte1 = tx | (RuneError>>6)&maskx
+	runeErrorByte2 = tx | RuneError&maskx
+)
+
+// first is information about the first byte in a UTF-8 sequence.
+var first = [256]uint8{
+	//   1   2   3   4   5   6   7   8   9   A   B   C   D   E   F
+	as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, // 0x00-0x0F
+	as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, // 0x10-0x1F
+	as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, // 0x20-0x2F
+	as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, // 0x30-0x3F
+	as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, // 0x40-0x4F
+	as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, // 0x50-0x5F
+	as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, // 0x60-0x6F
+	as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, as, // 0x70-0x7F
+	//   1   2   3   4   5   6   7   8   9   A   B   C   D   E   F
+	xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, // 0x80-0x8F
+	xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, // 0x90-0x9F
+	xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, // 0xA0-0xAF
+	xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, // 0xB0-0xBF
+	xx, xx, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, // 0xC0-0xCF
+	s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, s1, // 0xD0-0xDF
+	s2, s3, s3, s3, s3, s3, s3, s3, s3, s3, s3, s3, s3, s4, s3, s3, // 0xE0-0xEF
+	s5, s6, s6, s6, s7, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, xx, // 0xF0-0xFF
+}
+
+// acceptRange gives the range of valid values for the second byte in a UTF-8
+// sequence.
+type acceptRange struct {
+	lo uint8 // lowest value for second byte.
+	hi uint8 // highest value for second byte.
+}
+
+// acceptRanges has size 16 to avoid bounds checks in the code that uses it.
+var acceptRanges = [16]acceptRange{
+	0: {locb, hicb},
+	1: {0xA0, hicb},
+	2: {locb, 0x9F},
+	3: {0x90, hicb},
+	4: {locb, 0x8F},
+}
+
+// GoFront strings are JavaScript strings, indexed by UTF-16 code unit. The
+// *InString functions therefore decode code points and report widths in
+// code units, so that "s = s[size:]" walks a string as in Go; only for
+// ASCII text do the widths equal Go's byte counts.
+
+func isHigh(c rune) bool { return c >= 0xD800 && c <= 0xDBFF }
+func isLow(c rune) bool  { return c >= 0xDC00 && c <= 0xDFFF }
+
+// FullRune reports whether the bytes in p begin with a full UTF-8 encoding of a rune.
+// An invalid encoding is considered a full Rune since it will convert as a width-1 error rune.
+func FullRune(p []byte) bool {
+	n := len(p)
+	if n == 0 {
+		return false
+	}
+	x := first[p[0]]
+	if n >= int(x&7) {
+		return true // ASCII, invalid or valid.
+	}
+	// Must be short or invalid.
+	accept := acceptRanges[x>>4]
+	if n > 1 && (p[1] < accept.lo || accept.hi < p[1]) {
+		return true
+	} else if n > 2 && (p[2] < locb || hicb < p[2]) {
+		return true
+	}
+	return false
+}
+
+// FullRuneInString is like FullRune but its input is a string.
+func FullRuneInString(s string) bool {
+	return len(s) > 1 || (len(s) == 1 && !isHigh(rune(s[0])))
+}
+
+// DecodeRune unpacks the first UTF-8 encoding in p and returns the rune and
+// its width in bytes. If p is empty it returns ([RuneError], 0). Otherwise, if
+// the encoding is invalid, it returns (RuneError, 1). Both are impossible
+// results for correct, non-empty UTF-8.
+//
+// An encoding is invalid if it is incorrect UTF-8, encodes a rune that is
+// out of range, or is not the shortest possible UTF-8 encoding for the
+// value. No other validation is performed.
+func DecodeRune(p []byte) (r rune, size int) {
+	// Inlineable fast path for ASCII characters; see #48195.
+	// This implementation is weird but effective at rendering the
+	// function inlineable.
+	for _, b := range p {
+		if b < RuneSelf {
+			return rune(b), 1
+		}
+		break
+	}
+	r, size = decodeRuneSlow(p)
+	return
+}
+
+func decodeRuneSlow(p []byte) (r rune, size int) {
+	n := len(p)
+	if n < 1 {
+		return RuneError, 0
+	}
+	p0 := p[0]
+	x := first[p0]
+	if x >= as {
+		// The following code simulates an additional check for x == xx and
+		// handling the ASCII and invalid cases accordingly. This mask-and-or
+		// approach prevents an additional branch.
+		mask := rune(x) << 31 >> 31 // Create 0x0000 or 0xFFFF.
+		return rune(p[0])&^mask | RuneError&mask, 1
+	}
+	sz := int(x & 7)
+	accept := acceptRanges[x>>4]
+	if n < sz {
+		return RuneError, 1
+	}
+	b1 := p[1]
+	if b1 < accept.lo || accept.hi < b1 {
+		return RuneError, 1
+	}
+	if sz <= 2 { // <= instead of == to help the compiler eliminate some bounds checks
+		return rune(p0&mask2)<<6 | rune(b1&maskx), 2
+	}
+	b2 := p[2]
+	if b2 < locb || hicb < b2 {
+		return RuneError, 1
+	}
+	if sz <= 3 {
+		return rune(p0&mask3)<<12 | rune(b1&maskx)<<6 | rune(b2&maskx), 3
+	}
+	b3 := p[3]
+	if b3 < locb || hicb < b3 {
+		return RuneError, 1
+	}
+	return rune(p0&mask4)<<18 | rune(b1&maskx)<<12 | rune(b2&maskx)<<6 | rune(b3&maskx), 4
+}
+
+// DecodeRuneInString is like [DecodeRune] but its input is a string. If s is
+// empty it returns ([RuneError], 0). Otherwise, if the encoding is invalid, it
+// returns (RuneError, 1). Both are impossible results for correct, non-empty
+// UTF-8.
+//
+// An encoding is invalid if it is incorrect UTF-8, encodes a rune that is
+// out of range, or is not the shortest possible UTF-8 encoding for the
+// value. No other validation is performed.
+func DecodeRuneInString(s string) (r rune, size int) {
+	if len(s) == 0 {
+		return RuneError, 0
+	}
+	c := rune(s[0])
+	if isHigh(c) && len(s) > 1 && isLow(rune(s[1])) {
+		return (c-0xD800)<<10 + (rune(s[1]) - 0xDC00) + 0x10000, 2
+	}
+	if isHigh(c) || isLow(c) {
+		return RuneError, 1
+	}
+	return c, 1
+}
+
+// DecodeLastRune unpacks the last UTF-8 encoding in p and returns the rune and
+// its width in bytes. If p is empty it returns ([RuneError], 0). Otherwise, if
+// the encoding is invalid, it returns (RuneError, 1). Both are impossible
+// results for correct, non-empty UTF-8.
+//
+// An encoding is invalid if it is incorrect UTF-8, encodes a rune that is
+// out of range, or is not the shortest possible UTF-8 encoding for the
+// value. No other validation is performed.
+func DecodeLastRune(p []byte) (r rune, size int) {
+	end := len(p)
+	if end == 0 {
+		return RuneError, 0
+	}
+	start := end - 1
+	r = rune(p[start])
+	if r < RuneSelf {
+		return r, 1
+	}
+	// guard against O(n^2) behavior when traversing
+	// backwards through strings with long sequences of
+	// invalid UTF-8.
+	lim := end - UTFMax
+	if lim < 0 {
+		lim = 0
+	}
+	for start--; start >= lim; start-- {
+		if RuneStart(p[start]) {
+			break
+		}
+	}
+	if start < 0 {
+		start = 0
+	}
+	r, size = DecodeRune(p[start:end])
+	if start+size != end {
+		return RuneError, 1
+	}
+	return r, size
+}
+
+// DecodeLastRuneInString is like [DecodeLastRune] but its input is a string. If
+// s is empty it returns ([RuneError], 0). Otherwise, if the encoding is invalid,
+// it returns (RuneError, 1). Both are impossible results for correct,
+// non-empty UTF-8.
+//
+// An encoding is invalid if it is incorrect UTF-8, encodes a rune that is
+// out of range, or is not the shortest possible UTF-8 encoding for the
+// value. No other validation is performed.
+func DecodeLastRuneInString(s string) (r rune, size int) {
+	end := len(s)
+	if end == 0 {
+		return RuneError, 0
+	}
+	c := rune(s[end-1])
+	if isLow(c) && end > 1 && isHigh(rune(s[end-2])) {
+		return (rune(s[end-2])-0xD800)<<10 + (c - 0xDC00) + 0x10000, 2
+	}
+	if isHigh(c) || isLow(c) {
+		return RuneError, 1
+	}
+	return c, 1
+}
+
+// RuneLen returns the number of bytes in the UTF-8 encoding of the rune.
+// It returns -1 if the rune is not a valid value to encode in UTF-8.
+func RuneLen(r rune) int {
+	switch {
+	case r < 0:
+		return -1
+	case r <= rune1Max:
+		return 1
+	case r <= rune2Max:
+		return 2
+	case surrogateMin <= r && r <= surrogateMax:
+		return -1
+	case r <= rune3Max:
+		return 3
+	case r <= MaxRune:
+		return 4
+	}
+	return -1
+}
+
+// EncodeRune writes into p (which must be large enough) the UTF-8 encoding of the rune.
+// If the rune is out of range, it writes the encoding of [RuneError].
+// It returns the number of bytes written.
+func EncodeRune(p []byte, r rune) int {
+	// This function is inlineable for fast handling of ASCII.
+	if uint32(r) <= rune1Max {
+		p[0] = byte(r)
+		return 1
+	}
+	return encodeRuneNonASCII(p, r)
+}
+
+func encodeRuneNonASCII(p []byte, r rune) int {
+	// Negative values are erroneous. Making it unsigned addresses the problem.
+	switch i := uint32(r); {
+	case i <= rune2Max:
+		_ = p[1] // eliminate bounds checks
+		p[0] = t2 | byte(r>>6)
+		p[1] = tx | byte(r)&maskx
+		return 2
+	case i < surrogateMin, surrogateMax < i && i <= rune3Max:
+		_ = p[2] // eliminate bounds checks
+		p[0] = t3 | byte(r>>12)
+		p[1] = tx | byte(r>>6)&maskx
+		p[2] = tx | byte(r)&maskx
+		return 3
+	case i > rune3Max && i <= MaxRune:
+		_ = p[3] // eliminate bounds checks
+		p[0] = t4 | byte(r>>18)
+		p[1] = tx | byte(r>>12)&maskx
+		p[2] = tx | byte(r>>6)&maskx
+		p[3] = tx | byte(r)&maskx
+		return 4
+	default:
+		_ = p[2] // eliminate bounds checks
+		p[0] = runeErrorByte0
+		p[1] = runeErrorByte1
+		p[2] = runeErrorByte2
+		return 3
+	}
+}
+
+// AppendRune appends the UTF-8 encoding of r to the end of p and
+// returns the extended buffer. If the rune is out of range,
+// it appends the encoding of [RuneError].
+func AppendRune(p []byte, r rune) []byte {
+	// This function is inlineable for fast handling of ASCII.
+	if uint32(r) <= rune1Max {
+		return append(p, byte(r))
+	}
+	return appendRuneNonASCII(p, r)
+}
+
+func appendRuneNonASCII(p []byte, r rune) []byte {
+	// Negative values are erroneous. Making it unsigned addresses the problem.
+	switch i := uint32(r); {
+	case i <= rune2Max:
+		return append(p, t2|byte(r>>6), tx|byte(r)&maskx)
+	case i < surrogateMin, surrogateMax < i && i <= rune3Max:
+		return append(p, t3|byte(r>>12), tx|byte(r>>6)&maskx, tx|byte(r)&maskx)
+	case i > rune3Max && i <= MaxRune:
+		return append(p, t4|byte(r>>18), tx|byte(r>>12)&maskx, tx|byte(r>>6)&maskx, tx|byte(r)&maskx)
+	default:
+		return append(p, runeErrorByte0, runeErrorByte1, runeErrorByte2)
+	}
+}
+
+// RuneCount returns the number of runes in p. Erroneous and short
+// encodings are treated as single runes of width 1 byte.
+func RuneCount(p []byte) int {
+	n := 0
+	for i := 0; i < len(p); n++ {
+		if p[i] < RuneSelf {
+			i++
+			continue
+		}
+		_, size := DecodeRune(p[i:])
+		i += size
+	}
+	return n
+}
+
+// RuneCountInString is like [RuneCount] but its input is a string.
+//
+//gofront:native utf8.RuneCountInString
+func RuneCountInString(s string) (n int) {
+	return len([]rune(s))
+}
+
+// RuneStart reports whether the byte could be the first byte of an encoded,
+// possibly invalid rune. Second and subsequent bytes always have the top two
+// bits set to 10.
+func RuneStart(b byte) bool { return b&0xC0 != 0x80 }
+
+// Valid reports whether p consists entirely of valid UTF-8-encoded runes.
+func Valid(p []byte) bool {
+	for len(p) > 0 {
+		p0 := p[0]
+		if p0 < RuneSelf {
+			p = p[1:]
+			continue
+		}
+		x := first[p0]
+		size := int(x & 7)
+		accept := acceptRanges[x>>4]
+		switch size {
+		case 2:
+			if len(p) < 2 || p[1] < accept.lo || accept.hi < p[1] {
+				return false
+			}
+			p = p[2:]
+		case 3:
+			if len(p) < 3 || p[1] < accept.lo || accept.hi < p[1] || p[2] < locb || hicb < p[2] {
+				return false
+			}
+			p = p[3:]
+		case 4:
+			if len(p) < 4 || p[1] < accept.lo || accept.hi < p[1] || p[2] < locb || hicb < p[2] || p[3] < locb || hicb < p[3] {
+				return false
+			}
+			p = p[4:]
+		default:
+			return false // illegal starter byte
+		}
+	}
+	return true
+}
+
+// ValidString reports whether s consists entirely of valid UTF-8-encoded runes.
+func ValidString(s string) bool {
+	for i := 0; i < len(s); i++ {
+		c := rune(s[i])
+		if isHigh(c) && i+1 < len(s) && isLow(rune(s[i+1])) {
+			i++
+		} else if isHigh(c) || isLow(c) {
+			return false
+		}
+	}
+	return true
+}
+
+// ValidRune reports whether r can be legally encoded as UTF-8.
+// Code points that are out of range or a surrogate half are illegal.
+func ValidRune(r rune) bool {
+	switch {
+	case 0 <= r && r < surrogateMin:
+		return true
+	case surrogateMax < r && r <= MaxRune:
+		return true
+	}
+	return false
+}