Golang unicode.IsSymbol函数代码示例

func main() {
	counts := make(map[rune]int)      // counts of Unicode characters
	var utflen [utf8.UTFMax + 1]int   // count of lengths of UTF-8 encodings
	invalid := 0                      // count of invalid UTF-8 characters
	catCounts := make(map[string]int) // counts per Unicode category
	unknown := 0                      // count of characters of unknown category

	in := bufio.NewReader(os.Stdin)
	for {
		r, n, err := in.ReadRune() // returns rune, nbytes, error
		if err == io.EOF {
			break
		}
		if err != nil {
			fmt.Fprintf(os.Stderr, "charcount: %v\n", err)
			os.Exit(1)
		}
		if r == unicode.ReplacementChar && n == 1 {
			invalid++
			continue
		}
		counts[r]++
		utflen[n]++
		switch {
		case unicode.IsLetter(r):
			catCounts["Letter"]++
		case unicode.IsDigit(r):
			catCounts["Digit"]++
		case unicode.IsSymbol(r):
			catCounts["Symbol"]++
		case unicode.IsPunct(r):
			catCounts["Punct"]++
		case unicode.IsSpace(r):
			catCounts["Space"]++
		default:
			unknown++
		}
	}
	fmt.Printf("rune\tcount\n")
	for c, n := range counts {
		fmt.Printf("%q\t%d\n", c, n)
	}
	fmt.Print("\nlen\tcount\n")
	for i, n := range utflen {
		if i > 0 {
			fmt.Printf("%d\t%d\n", i, n)
		}
	}
	if invalid > 0 {
		fmt.Printf("\n%d invalid UTF-8 characters\n", invalid)
	}

	fmt.Print("\ncat\tcount\n")
	for cat, n := range catCounts {
		fmt.Printf("%s\t%d\n", cat, n)
	}
	if unknown > 0 {
		fmt.Printf("\n%d characters of unknown category\n", unknown)
	}
}

// synopsis extracts the first sentence from s. All runs of whitespace are
// replaced by a single space.
func synopsis(s string) string {

	parts := strings.SplitN(s, "\n\n", 2)
	s = parts[0]

	var buf []byte
	const (
		other = iota
		period
		space
	)
	last := space
Loop:
	for i := 0; i < len(s); i++ {
		b := s[i]
		switch b {
		case ' ', '\t', '\r', '\n':
			switch last {
			case period:
				break Loop
			case other:
				buf = append(buf, ' ')
				last = space
			}
		case '.':
			last = period
			buf = append(buf, b)
		default:
			last = other
			buf = append(buf, b)
		}
	}

	// Ensure that synopsis fits an App Engine datastore text property.
	const m = 400
	if len(buf) > m {
		buf = buf[:m]
		if i := bytes.LastIndex(buf, []byte{' '}); i >= 0 {
			buf = buf[:i]
		}
		buf = append(buf, " ..."...)
	}

	s = string(buf)

	r, n := utf8.DecodeRuneInString(s)
	if n < 0 || unicode.IsPunct(r) || unicode.IsSymbol(r) {
		// ignore Markdown headings, editor settings, Go build constraints, and * in poorly formatted block comments.
		s = ""
	} else {
		for _, prefix := range badSynopsisPrefixes {
			if strings.HasPrefix(s, prefix) {
				s = ""
				break
			}
		}
	}

	return s
}

// CharCount scans a *bufio.Reader and returns a map of the counts of its
// Unicode character types.
func CharCount(in *bufio.Reader) map[string]int {
	counts := make(map[string]int) // counts of Unicode character types

	for {
		r, n, err := in.ReadRune() // returns rune, nbytes, error
		if err == io.EOF {
			break
		}
		if err != nil {
			fmt.Fprintf(os.Stderr, "charcount: %v\n", err)
			os.Exit(1)
		}

		switch {
		case r == unicode.ReplacementChar && n == 1:
			counts["invalid"]++
		case unicode.IsControl(r):
			counts["control"]++
		case unicode.IsLetter(r):
			counts["letter"]++
		case unicode.IsMark(r):
			counts["mark"]++
		case unicode.IsNumber(r):
			counts["number"]++
		case unicode.IsPunct(r):
			counts["punct"]++
		case unicode.IsSpace(r):
			counts["space"]++
		case unicode.IsSymbol(r):
			counts["symbol"]++
		}
	}
	return counts
}

func isLetter(ch rune) bool {
	if ch == '(' || ch == ')' || ch == '\'' || ch == '"' {
		return false
	}

	return unicode.IsLetter(ch) || unicode.IsPunct(ch) || unicode.IsSymbol(ch)
}

func TestRune_IsIndependent(t *testing.T) {
	numbers := make([]rune, 0)
	letters := make([]rune, 0)
	marks := make([]rune, 0)
	symbols := make([]rune, 0)
	puncts := make([]rune, 0)
	others := make([]rune, 0)
	for _, r := range unicode.Myanmar.R16 {
		for c := r.Lo; c <= r.Hi; c++ {
			switch mr := rune(c); true {
			case unicode.IsLetter(mr):
				letters = append(letters, mr)
			case unicode.IsNumber(mr):
				numbers = append(numbers, mr)
			case unicode.IsMark(mr):
				marks = append(marks, mr)
			case unicode.IsPunct(mr):
				puncts = append(puncts, mr)
			case unicode.IsSymbol(mr):
				symbols = append(symbols, mr)
			default:
				others = append(others, mr)
			}
		}
	}

	independents := string(letters) + string(numbers) + string(puncts) + " \t\r\n"
	for _, consonant := range independents {
		if ok, _ := Rune(consonant).IsIndependent(); !ok {
			t.Errorf("[%U] expected result is true, but it returns false", consonant)
		}
	}
}

func DeEscapeProse(p md.Prose) md.Prose {
	result := make(md.Prose, 0, len(p))
	var buf []byte
runs:
	for i := 0; i < len(p); i++ {
		if buf == nil {
			buf = p[i].Bytes
		}
		for j := 0; ; {
			k := bytes.IndexByte(buf[j:], '\\')
			if k == -1 {
				result = append(result, md.Run{
					Line:  p[i].Line,
					Bytes: buf,
				})
				buf = nil
				continue runs
			}
			j += k
			r, _ := utf8.DecodeRune(buf[j+1:])
			if unicode.IsPunct(r) || unicode.IsSymbol(r) {
				result = append(result, md.Run{
					Line:  p[i].Line,
					Bytes: buf[:j],
				})
				buf = buf[j+1:]
				i--
				continue runs
			}
			j++
		}
	}
	return result
}

// Stat calculates statistics for all runes read from r.
func (m *Main) Stat(r io.RuneReader) (Stats, error) {
	var stats Stats

	for {
		// Read next character.
		ch, sz, err := r.ReadRune()
		if err == io.EOF {
			break
		} else if err != nil {
			return stats, err
		}

		// Calculate stats.
		stats.TotalN++
		if unicode.IsControl(ch) {
			stats.ControlN++
		}
		if unicode.IsDigit(ch) {
			stats.DigitN++
		}
		if unicode.IsGraphic(ch) {
			stats.GraphicN++
		}
		if unicode.IsLetter(ch) {
			stats.LetterN++
		}
		if unicode.IsLower(ch) {
			stats.LowerN++
		}
		if unicode.IsMark(ch) {
			stats.MarkN++
		}
		if unicode.IsNumber(ch) {
			stats.NumberN++
		}
		if unicode.IsPrint(ch) {
			stats.PrintN++
		}
		if unicode.IsPunct(ch) {
			stats.PunctN++
		}
		if unicode.IsSpace(ch) {
			stats.SpaceN++
		}
		if unicode.IsSymbol(ch) {
			stats.SymbolN++
		}
		if unicode.IsTitle(ch) {
			stats.TitleN++
		}
		if unicode.IsUpper(ch) {
			stats.UpperN++
		}
		if sz > 1 {
			stats.MultiByteN++
		}
	}

	return stats, nil
}

func incrementCount(r rune, counts map[int]int) {
	switch {
	case unicode.IsControl(r):
		counts[isControl]++

	case unicode.IsNumber(r):
		counts[isNumber]++

	case unicode.IsDigit(r):
		counts[isDigit]++

	case unicode.IsLetter(r):
		counts[isLetter]++

	case unicode.IsMark(r):
		counts[isMark]++

	case unicode.IsPunct(r):
		counts[isPunct]++

	case unicode.IsSpace(r):
		counts[isSpace]++

	case unicode.IsSymbol(r):
		counts[isSymbol]++

	case unicode.IsPrint(r):
		counts[isPrint]++

	case unicode.IsGraphic(r):
		counts[isGraphic]++
	}

}

// CharType returns a string representing the unicode type of a rune
func CharType(r rune) string {
	switch {
	case unicode.IsLetter(r):
		return "letter"
	case unicode.IsSpace(r):
		return "space"
	case unicode.IsPunct(r):
		return "punct"
	case unicode.IsNumber(r):
		return "number"
	case unicode.IsSymbol(r):
		return "symbol"
	case unicode.IsMark(r):
		return "mark"
	case unicode.IsDigit(r):
		return "digit"
	case unicode.IsPrint(r):
		return "print"
	case unicode.IsControl(r):
		return "control"
	case unicode.IsGraphic(r):
		return "graphic"
	default:
		return "invalid"
	}
}

/*
 * Password rules:
 * at least 7 letters
 * at least 1 number
 * at least 1 upper case
 * at least 1 special character
 */
func ValidatePassword(value, local string) error {

	fmt.Println("Validate password", value)
	if len(value) < 7 {
		return errors.New(i18n.Translate(local, i18nSec, "text03"))
	}

	var num, lower, upper, spec bool
	for _, r := range value {
		switch {
		case unicode.IsDigit(r):
			num = true
		case unicode.IsUpper(r):
			upper = true
		case unicode.IsLower(r):
			lower = true
		case unicode.IsSymbol(r), unicode.IsPunct(r):
			spec = true
		}
	}
	if num && lower && upper && spec {
		return nil
	}

	return errors.New(i18n.Translate(local, i18nSec, "text03"))
}

func (l *GutsLex) emitIfKeywordMatches() bool {
	l.remember()
	for keyword, typ := range LexKeywords {
		var match bool = true
	next_keyword:
		for _, sc := range keyword {
			c := l.next()
			if c == eof {
				match = false
				break next_keyword
			}
			if sc != c {
				match = false
				break next_keyword
			}
		}
		if match {
			c := l.next()
			if c == '\n' || c == eof || c == ' ' || c == '\t' || unicode.IsSymbol(c) {
				l.backup()
				l.emit(TokenType(typ))
				return true
			}
		}
		l.rollback()
	}
	return false
}

func Sanitize(r rune) rune {
	switch {
	case unicode.IsPunct(r):
		return ' '
	case unicode.IsMark(r):
		return ' '
	case unicode.IsSymbol(r):
		return ' '
	}
	return r
}

func main() {
	counts := make(map[string]int)
	var utflen [utf8.UTFMax + 1]int
	invalid := 0

	in := bufio.NewReader(os.Stdin)
	for {
		r, n, err := in.ReadRune()
		if err == io.EOF {
			break
		}
		if err != nil {
			fmt.Fprintf(os.Stderr, "charcount: %v\n", err)
			os.Exit(1)
		}
		if r == unicode.ReplacementChar && n == 1 {
			invalid++
			continue
		}

		utflen[n]++
		switch {
		case unicode.IsLetter(r):
			counts["Letter"]++
		case unicode.IsMark(r):
			counts["Mark"]++
		case unicode.IsNumber(r):
			counts["Number"]++
		case unicode.IsPunct(r):
			counts["Punct"]++
		case unicode.IsSymbol(r):
			counts["Symbol"]++
		case unicode.IsSpace(r):
			counts["Space"]++
		default:
			counts["Other"]++
		}
	}

	fmt.Printf("rune\tcount\n")
	for c, n := range counts {
		fmt.Printf("%s\t%d\n", c, n)
	}
	fmt.Print("\nlen\tcount\n")
	for i, n := range utflen {
		if i > 0 {
			fmt.Printf("%d\t%d\n", i, n)
		}
	}
	if invalid > 0 {
		fmt.Printf("\n%d invalid UTF-8 characters\n", invalid)
	}
}

func main() {
	in := bufio.NewReader(os.Stdin)
	counts := make(map[string]int)  // counts of Unicode character types
	var utflen [utf8.UTFMax + 1]int // count of lengths of UTF-8 encodings
	invalid := 0                    // count of invalid UTF-8 characters

	for {
		r, n, err := in.ReadRune() // returns rune, nbytes, error
		if err == io.EOF {
			break
		}
		if err != nil {
			fmt.Fprintf(os.Stderr, "charcount: %v\n", err)
			os.Exit(1)
		}
		if r == unicode.ReplacementChar && n == 1 {
			invalid++
			continue
		}

		switch {
		case unicode.IsControl(r):
			counts["control"]++
		case unicode.IsLetter(r):
			counts["letter"]++
		case unicode.IsMark(r):
			counts["mark"]++
		case unicode.IsNumber(r):
			counts["number"]++
		case unicode.IsPunct(r):
			counts["punct"]++
		case unicode.IsSpace(r):
			counts["space"]++
		case unicode.IsSymbol(r):
			counts["symbol"]++
		}
		utflen[n]++
	}
	fmt.Printf("rune\tcount\n")
	for c, n := range counts {
		fmt.Printf("%q\t%d\n", c, n)
	}
	fmt.Print("\nlen\tcount\n")
	for i, n := range utflen {
		if i > 0 {
			fmt.Printf("%d\t%d\n", i, n)
		}
	}
	if invalid > 0 {
		fmt.Printf("\n%d invalid UTF-8 characters\n", invalid)
	}
}

func main() {
	counts := make(map[rune]int) // counts of Unicode characters
	var utflen [utf8.UTFMax]int  // count of lengths of UTF-8 encodings
	invalid := 0                 // count of invalid UTF-8 characters
	cats := make(map[string]int) // counts of Unicode categories

	// In a terminal, use CTRL+Z at line start to signal EOF with ENTER.
	in := bufio.NewReader(os.Stdin)
	for {
		r, n, err := in.ReadRune() // returns rune, nbytes, error
		if err == io.EOF {
			break
		}
		if err != nil {
			fmt.Fprintf(os.Stderr, "charcount: %v\n", err)
			os.Exit(1)
		}
		if r == unicode.ReplacementChar && n == 1 {
			invalid++
			continue
		}
		switch {
		case unicode.IsLetter(r):
			cats["letter"]++
		case unicode.IsDigit(r):
			cats["digit"]++
		case unicode.IsControl(r):
			cats["control"]++
		case unicode.IsMark(r):
			cats["mark"]++
		case unicode.IsPunct(r):
			cats["punct"]++
		case unicode.IsSymbol(r):
			cats["symbol"]++
		}
		counts[r]++
		utflen[n-1]++
	}
	fmt.Printf("rune\tcount\n")
	for c, n := range counts {
		fmt.Printf("%q\t%d\n", c, n)
	}
	fmt.Print("\nlen\tcount\n")
	for i, n := range utflen {
		fmt.Printf("%d\t%d\n", i+1, n)
	}
	fmt.Print("\ncat\tcount\n")
	for s, n := range cats {
		fmt.Printf("%v\t%d\n", s, n)
	}
	fmt.Printf("\n%d invalid UTF-8 characters\n", invalid)
}