Пример #1
1
// Is the item exported from the package?
func (n *Named) Exported() bool {
	if n.Imported() {
		return false
	}
	r, _ := utf8.DecodeRuneInString(n.Name)
	return unicode.IsUpper(r)
}
Пример #2
0
// Trim returns a slice of the string s, with all leading and trailing white space
// removed, as defined by Unicode.
func TrimSpace(s string) string {
	start, end := 0, len(s)
	for start < end {
		wid := 1
		rune := int(s[start])
		if rune >= utf8.RuneSelf {
			rune, wid = utf8.DecodeRuneInString(s[start:end])
		}
		if !unicode.IsSpace(rune) {
			break
		}
		start += wid
	}
	for start < end {
		wid := 1
		rune := int(s[end-1])
		if rune >= utf8.RuneSelf {
			// Back up carefully looking for beginning of rune. Mustn't pass start.
			for wid = 2; start <= end-wid && !utf8.RuneStart(s[end-wid]); wid++ {
			}
			if start > end-wid { // invalid UTF-8 sequence; stop processing
				return s[start:end]
			}
			rune, wid = utf8.DecodeRuneInString(s[end-wid : end])
		}
		if !unicode.IsSpace(rune) {
			break
		}
		end -= wid
	}
	return s[start:end]
}
Пример #3
0
// EqualFold reports whether s and t, interpreted as UTF-8 strings,
// are equal under Unicode case-folding.
func EqualFold(s, t string) bool {
	for s != "" && t != "" {
		// Extract first rune from each string.
		var sr, tr rune
		if s[0] < utf8.RuneSelf {
			sr, s = rune(s[0]), s[1:]
		} else {
			r, size := utf8.DecodeRuneInString(s)
			sr, s = r, s[size:]
		}
		if t[0] < utf8.RuneSelf {
			tr, t = rune(t[0]), t[1:]
		} else {
			r, size := utf8.DecodeRuneInString(t)
			tr, t = r, t[size:]
		}

		// If they match, keep going; if not, return false.

		// Easy case.
		if tr == sr {
			continue
		}

		// Make sr < tr to simplify what follows.
		if tr < sr {
			tr, sr = sr, tr
		}
		// Fast check for ASCII.
		if tr < utf8.RuneSelf && 'A' <= sr && sr <= 'Z' {
			// ASCII, and sr is upper case.  tr must be lower case.
			if tr == sr+'a'-'A' {
				continue
			}
			return false
		}

		// General case.  SimpleFold(x) returns the next equivalent rune > x
		// or wraps around to smaller values.
		r := unicode.SimpleFold(sr)
		for r != sr && r < tr {
			r = unicode.SimpleFold(r)
		}
		if r == tr {
			continue
		}
		return false
	}

	// One string is empty.  Are both?
	return s == t
}
Пример #4
0
// Peek at the next focus rune in SafeReader.
func (r *SafeReader) peek() int {
	if r.pos < len(r.str) {
		rune, _ := utf8.DecodeRuneInString(r.str[r.pos:])
		return rune
	}
	return -1
}
Пример #5
0
// insertString inserts the given rune in the buffer ordered by CCC.
// It returns true if the buffer was large enough to hold the decomposed rune.
func (rb *reorderBuffer) insertString(src string, info runeInfo) bool {
	if info.size == 3 && isHangulString(src) {
		rune, _ := utf8.DecodeRuneInString(src)
		return rb.decomposeHangul(uint32(rune))
	}
	if info.flags.hasDecomposition() {
		dcomp := rb.f.decomposeString(src)
		for i := 0; i < len(dcomp); {
			info = rb.f.info(dcomp[i:])
			pos := rb.nbyte
			if !rb.insertOrdered(info) {
				return false
			}
			end := i + int(info.size)
			copy(rb.byte[pos:], dcomp[i:end])
			i = end
		}
	} else {
		copy(rb.byte[rb.nbyte:], src[:info.size])
		if !rb.insertOrdered(info) {
			return false
		}
	}
	return true
}
Пример #6
0
func compile(expr string, mode syntax.Flags, longest bool) (*Regexp, error) {
	re, err := syntax.Parse(expr, mode)
	if err != nil {
		return nil, err
	}
	maxCap := re.MaxCap()
	re = re.Simplify()
	prog, err := syntax.Compile(re)
	if err != nil {
		return nil, err
	}
	regexp := &Regexp{
		expr:      expr,
		prog:      prog,
		numSubexp: maxCap,
		cond:      prog.StartCond(),
		longest:   longest,
	}
	regexp.prefix, regexp.prefixComplete = prog.Prefix()
	if regexp.prefix != "" {
		// TODO(rsc): Remove this allocation by adding
		// IndexString to package bytes.
		regexp.prefixBytes = []byte(regexp.prefix)
		regexp.prefixRune, _ = utf8.DecodeRuneInString(regexp.prefix)
	}
	return regexp, nil
}
Пример #7
0
// matchChunk checks whether chunk matches the beginning of s.
// If so, it returns the remainder of s (after the match).
// Chunk is all single-character operators: literals, char classes, and ?.
func matchChunk(chunk, s string) (rest string, ok bool, err os.Error) {
	for len(chunk) > 0 {
		if len(s) == 0 {
			return
		}
		switch chunk[0] {
		case '?':
			_, n := utf8.DecodeRuneInString(s)
			s = s[n:]
			chunk = chunk[1:]

		case '\\':
			chunk = chunk[1:]
			if len(chunk) == 0 {
				err = ErrBadPattern
				return
			}
			fallthrough

		default:
			if chunk[0] != s[0] {
				return
			}
			s = s[1:]
			chunk = chunk[1:]
		}
	}
	return s, true, nil
}
Пример #8
0
func (e *encodeState) string(s string) {
	e.WriteByte('"')
	start := 0
	for i := 0; i < len(s); {
		if b := s[i]; b < utf8.RuneSelf {
			if 0x20 <= b && b != '\\' && b != '"' {
				i++
				continue
			}
			if start < i {
				e.WriteString(s[start:i])
			}
			if b == '\\' || b == '"' {
				e.WriteByte('\\')
				e.WriteByte(b)
			} else {
				e.WriteString(`\u00`)
				e.WriteByte(hex[b>>4])
				e.WriteByte(hex[b&0xF])
			}
			i++
			start = i
			continue
		}
		c, size := utf8.DecodeRuneInString(s[i:])
		if c == utf8.RuneError && size == 1 {
			e.error(&InvalidUTF8Error{s})
		}
		i += size
	}
	if start < len(s) {
		e.WriteString(s[start:])
	}
	e.WriteByte('"')
}
Пример #9
0
// Converts a single Go utf-token to it's an Html entity.
//   ex: "♣" -> "&#9827;"
func UTF8ToHtml(token string) string {
	rune, size := utf8.DecodeRuneInString(token)
	if size == 0 {
		return ""
	}
	return fmt.Sprintf("&#%d;", rune)
}
Пример #10
0
func (s inputString) hangul(p int) uint32 {
	if !isHangulString(string(s[p:])) {
		return 0
	}
	rune, _ := utf8.DecodeRuneInString(string(s[p:]))
	return uint32(rune)
}
Пример #11
0
func nextRune(s string) (c rune, t string, err error) {
	c, size := utf8.DecodeRuneInString(s)
	if c == utf8.RuneError && size == 1 {
		return 0, "", &Error{Code: ErrInvalidUTF8, Expr: s}
	}
	return c, s[size:], nil
}
Пример #12
0
// Replace returns a copy of the string s with the first n
// non-overlapping instances of old replaced by new.
// If n < 0, there is no limit on the number of replacements.
func Replace(s, old, new string, n int) string {
	if old == new || n == 0 {
		return s // avoid allocation
	}

	// Compute number of replacements.
	if m := Count(s, old); m == 0 {
		return s // avoid allocation
	} else if n < 0 || m < n {
		n = m
	}

	// Apply replacements to buffer.
	t := make([]byte, len(s)+n*(len(new)-len(old)))
	w := 0
	start := 0
	for i := 0; i < n; i++ {
		j := start
		if len(old) == 0 {
			if i > 0 {
				_, wid := utf8.DecodeRuneInString(s[start:])
				j += wid
			}
		} else {
			j += Index(s[start:], old)
		}
		w += copy(t[w:], s[start:j])
		w += copy(t[w:], new)
		start = j + len(old)
	}
	w += copy(t[w:], s[start:])
	return string(t[0:w])
}
Пример #13
0
// fieldNeedsQuotes returns true if our field must be enclosed in quotes.
// Empty fields, files with a Comma, fields with a quote or newline, and
// fields which start with a space must be enclosed in quotes.
func (w *Writer) fieldNeedsQuotes(field string) bool {
	if len(field) == 0 || strings.IndexRune(field, w.Comma) >= 0 || strings.IndexAny(field, "\"\r\n") >= 0 {
		return true
	}

	r1, _ := utf8.DecodeRuneInString(field)
	return unicode.IsSpace(r1)
}
Пример #14
0
func (s State) Next() (rune int, state State, ok bool) {
	if len(s.text) > 0 {
		rune, size := utf8.DecodeRuneInString(s.text)
		return rune, State{s.text[size:], s.increment(rune, size)}, true
	}

	return 0, s, false
}
func equal(m string, s1, s2 string, t *testing.T) bool {
	if s1 == s2 {
		return true
	}
	e1 := Split(s1, "", -1)
	e2 := Split(s2, "", -1)
	for i, c1 := range e1 {
		if i > len(e2) {
			break
		}
		r1, _ := utf8.DecodeRuneInString(c1)
		r2, _ := utf8.DecodeRuneInString(e2[i])
		if r1 != r2 {
			t.Errorf("%s diff at %d: U+%04X U+%04X", m, i, r1, r2)
		}
	}
	return false
}
Пример #16
0
func (v *verifier) verifyChar(x *Token) int {
	s := x.String
	if utf8.RuneCountInString(s) != 1 {
		v.error(x.Pos(), "single char expected, found "+s)
		return 0
	}
	ch, _ := utf8.DecodeRuneInString(s)
	return ch
}
Пример #17
0
func (l *lexer) next() (rune int) {
	if l.pos >= len(l.input) {
		l.width = 0
		return eof
	}
	rune, l.width = utf8.DecodeRuneInString(l.input[l.pos:])
	l.pos += l.width
	return rune
}
Пример #18
0
func quoteWith(s string, quote byte) string {
	var buf bytes.Buffer
	buf.WriteByte(quote)
	for ; len(s) > 0; s = s[1:] {
		switch c := s[0]; {
		case c == quote:
			buf.WriteByte('\\')
			buf.WriteByte(quote)
		case c == '\\':
			buf.WriteString(`\\`)
		case ' ' <= c && c <= '~':
			buf.WriteString(string(c))
		case c == '\a':
			buf.WriteString(`\a`)
		case c == '\b':
			buf.WriteString(`\b`)
		case c == '\f':
			buf.WriteString(`\f`)
		case c == '\n':
			buf.WriteString(`\n`)
		case c == '\r':
			buf.WriteString(`\r`)
		case c == '\t':
			buf.WriteString(`\t`)
		case c == '\v':
			buf.WriteString(`\v`)

		case c >= utf8.RuneSelf && utf8.FullRuneInString(s):
			r, size := utf8.DecodeRuneInString(s)
			if r == utf8.RuneError && size == 1 {
				goto EscX
			}
			s = s[size-1:] // next iteration will slice off 1 more
			if r < 0x10000 {
				buf.WriteString(`\u`)
				for j := uint(0); j < 4; j++ {
					buf.WriteByte(lowerhex[(r>>(12-4*j))&0xF])
				}
			} else {
				buf.WriteString(`\U`)
				for j := uint(0); j < 8; j++ {
					buf.WriteByte(lowerhex[(r>>(28-4*j))&0xF])
				}
			}

		default:
		EscX:
			buf.WriteString(`\x`)
			buf.WriteByte(lowerhex[c>>4])
			buf.WriteByte(lowerhex[c&0xF])
		}
	}
	buf.WriteByte(quote)
	return buf.String()

}
Пример #19
0
// Unquote interprets s as a single-quoted, double-quoted,
// or backquoted Go string literal, returning the string value
// that s quotes.  (If s is single-quoted, it would be a Go
// character literal; Unquote returns the corresponding
// one-character string.)
func Unquote(s string) (t string, err os.Error) {
	n := len(s)
	if n < 2 {
		return "", os.EINVAL
	}
	quote := s[0]
	if quote != s[n-1] {
		return "", os.EINVAL
	}
	s = s[1 : n-1]

	if quote == '`' {
		if strings.Contains(s, "`") {
			return "", os.EINVAL
		}
		return s, nil
	}
	if quote != '"' && quote != '\'' {
		return "", os.EINVAL
	}
	if strings.Index(s, "\n") >= 0 {
		return "", os.EINVAL
	}

	// Is it trivial?  Avoid allocation.
	if strings.Index(s, `\`) < 0 && strings.IndexRune(s, int(quote)) < 0 {
		switch quote {
		case '"':
			return s, nil
		case '\'':
			r, size := utf8.DecodeRuneInString(s)
			if size == len(s) && (r != utf8.RuneError || size != 1) {
				return s, nil
			}
		}
	}

	var buf bytes.Buffer
	for len(s) > 0 {
		c, multibyte, ss, err := UnquoteChar(s, quote)
		if err != nil {
			return "", err
		}
		s = ss
		if c < utf8.RuneSelf || !multibyte {
			buf.WriteByte(byte(c))
		} else {
			buf.WriteString(string(c))
		}
		if quote == '\'' && len(s) != 0 {
			// single-quoted must be single character
			return "", os.EINVAL
		}
	}
	return buf.String(), nil
}
Пример #20
0
func checkUTF8(s string) error {
	for s != "" {
		rune, size := utf8.DecodeRuneInString(s)
		if rune == utf8.RuneError && size == 1 {
			return &Error{Code: ErrInvalidUTF8, Expr: s}
		}
		s = s[size:]
	}
	return nil
}
Пример #21
0
// TrimRightFunc returns a slice of the string s with all trailing
// Unicode code points c satisfying f(c) removed.
func TrimRightFunc(s string, f func(rune) bool) string {
	i := lastIndexFunc(s, f, false)
	if i >= 0 && s[i] >= utf8.RuneSelf {
		_, wid := utf8.DecodeRuneInString(s[i:])
		i += wid
	} else {
		i++
	}
	return s[0:i]
}
Пример #22
0
func (i *inputString) context(pos int) syntax.EmptyOp {
	r1, r2 := endOfText, endOfText
	if pos > 0 && pos <= len(i.str) {
		r1, _ = utf8.DecodeLastRuneInString(i.str[:pos])
	}
	if pos < len(i.str) {
		r2, _ = utf8.DecodeRuneInString(i.str[pos:])
	}
	return syntax.EmptyOpContext(r1, r2)
}
Пример #23
0
func (i *inputString) step(pos int) (rune, int) {
	if pos < len(i.str) {
		c := i.str[pos]
		if c < utf8.RuneSelf {
			return rune(c), 1
		}
		return utf8.DecodeRuneInString(i.str[pos:])
	}
	return endOfText, 0
}
Пример #24
0
func (p *parser) nextc() int {
	if p.pos >= len(p.re.expr) {
		p.ch = endOfFile
	} else {
		c, w := utf8.DecodeRuneInString(p.re.expr[p.pos:])
		p.ch = c
		p.pos += w
	}
	return p.ch
}
Пример #25
0
func TestIndexRune(t *testing.T) {
	for _, tt := range indexRuneTests {
		a := []byte(tt.a)
		r, _ := utf8.DecodeRuneInString(tt.b)
		pos := IndexRune(a, r)
		if pos != tt.i {
			t.Errorf(`IndexRune(%q, '%c') = %v`, tt.a, r, pos)
		}
	}
}
Пример #26
0
// isTest tells whether name looks like a test (or benchmark, according to prefix).
// It is a Test (say) if there is a character after Test that is not a lower-case letter.
// We don't want TesticularCancer.
func isTest(name, prefix string) bool {
	if !strings.HasPrefix(name, prefix) {
		return false
	}
	if len(name) == len(prefix) { // "Test" is ok
		return true
	}
	rune, _ := utf8.DecodeRuneInString(name[len(prefix):])
	return !unicode.IsLower(rune)
}
Пример #27
0
func main() {
	maths, err := io.ReadFile("math.peg")
	if err != nil {
		log.Exit("Error: ", err)
	}

	fmt.Println(maths)
	rune, size := utf8.DecodeRuneInString(string(maths))
	fmt.Println(rune, size)
	return
}
Пример #28
0
func main() {
	var chars [6]int
	chars[0] = 'a'
	chars[1] = 'b'
	chars[2] = 'c'
	chars[3] = '\u65e5'
	chars[4] = '\u672c'
	chars[5] = '\u8a9e'
	s := ""
	for i := 0; i < 6; i++ {
		s += string(chars[i])
	}
	var l = len(s)
	for w, i, j := 0, 0, 0; i < l; i += w {
		var r int
		r, w = utf8.DecodeRuneInString(s[i:len(s)])
		if w == 0 {
			panic("zero width in string")
		}
		if r != chars[j] {
			panic("wrong value from string")
		}
		j++
	}
	// encoded as bytes:  'a' 'b' 'c' e6 97 a5 e6 9c ac e8 aa 9e
	const L = 12
	if L != l {
		panic("wrong length constructing array")
	}
	a := make([]byte, L)
	a[0] = 'a'
	a[1] = 'b'
	a[2] = 'c'
	a[3] = 0xe6
	a[4] = 0x97
	a[5] = 0xa5
	a[6] = 0xe6
	a[7] = 0x9c
	a[8] = 0xac
	a[9] = 0xe8
	a[10] = 0xaa
	a[11] = 0x9e
	for w, i, j := 0, 0, 0; i < L; i += w {
		var r int
		r, w = utf8.DecodeRune(a[i:L])
		if w == 0 {
			panic("zero width in bytes")
		}
		if r != chars[j] {
			panic("wrong value from bytes")
		}
		j++
	}
}
Пример #29
0
func getrune() (result int) {
	var n int
	if linep >= len(line) {
		return 0
	}
	result, n = utf8.DecodeRuneInString(line[linep:len(line)])
	linep += n
	if result == '\n' {
		result = 0
	}
	return
}
Пример #30
0
// advance determines whether the next characters in the input match
// those of the format.  It returns the number of bytes (sic) consumed
// in the format. Newlines included, all runs of space characters in
// either input or format behave as a single space. This routine also
// handles the %% case.  If the return value is zero, either format
// starts with a % (with no following %) or the input is empty.
// If it is negative, the input did not match the string.
func (s *ss) advance(format string) (i int) {
	for i < len(format) {
		fmtc, w := utf8.DecodeRuneInString(format[i:])
		if fmtc == '%' {
			// %% acts like a real percent
			nextc, _ := utf8.DecodeRuneInString(format[i+w:]) // will not match % if string is empty
			if nextc != '%' {
				return
			}
			i += w // skip the first %
		}
		sawSpace := false
		for unicode.IsSpace(fmtc) && i < len(format) {
			sawSpace = true
			i += w
			fmtc, w = utf8.DecodeRuneInString(format[i:])
		}
		if sawSpace {
			// There was space in the format, so there should be space (EOF)
			// in the input.
			inputc := s.getRune()
			if inputc == eof {
				return
			}
			if !unicode.IsSpace(inputc) {
				// Space in format but not in input: error
				s.errorString("expected space in input to match format")
			}
			s.skipSpace(true)
			continue
		}
		inputc := s.mustReadRune()
		if fmtc != inputc {
			s.UnreadRune()
			return -1
		}
		i += w
	}
	return
}