src/strconv/atoi.go - go.git - Git at Google

 // 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 strconv

 import "errors"

 // lower(c) is a lower-case letter if and only if
 // c is either that lower-case letter or the equivalent upper-case letter.
 // Instead of writing c == 'x' || c == 'X' one can write lower(c) == 'x'.
 // Note that lower of non-letters can produce other non-letters.
 func lower(c byte) byte {
 	return c | ('x' - 'X')
 }

 // ErrRange indicates that a value is out of range for the target type.
 var ErrRange = errors.New("value out of range")

 // ErrSyntax indicates that a value does not have the right syntax for the target type.
 var ErrSyntax = errors.New("invalid syntax")

 // A NumError records a failed conversion.
 type NumError struct {
 	Func string // the failing function (ParseBool, ParseInt, ParseUint, ParseFloat, ParseComplex)
 	Num  string // the input
 	Err  error  // the reason the conversion failed (e.g. ErrRange, ErrSyntax, etc.)
 }

 func (e *NumError) Error() string {
 	return "strconv." + e.Func + ": " + "parsing " + Quote(e.Num) + ": " + e.Err.Error()
 }

 func (e *NumError) Unwrap() error { return e.Err }

 // cloneString returns a string copy of x.
 //
 // All ParseXXX functions allow the input string to escape to the error value.
 // This hurts strconv.ParseXXX(string(b)) calls where b is []byte since
 // the conversion from []byte must allocate a string on the heap.
 // If we assume errors are infrequent, then we can avoid escaping the input
 // back to the output by copying it first. This allows the compiler to call
 // strconv.ParseXXX without a heap allocation for most []byte to string
 // conversions, since it can now prove that the string cannot escape Parse.
 //
 // TODO: Use strings.Clone instead? However, we cannot depend on "strings"
 // since it incurs a transitive dependency on "unicode".
 // Either move strings.Clone to an internal/bytealg or make the
 // "strings" to "unicode" dependency lighter (see https://go.dev/issue/54098).
 func cloneString(x string) string { return string([]byte(x)) }

 func syntaxError(fn, str string) *NumError {
 	return &NumError{fn, cloneString(str), ErrSyntax}
 }

 func rangeError(fn, str string) *NumError {
 	return &NumError{fn, cloneString(str), ErrRange}
 }

 func baseError(fn, str string, base int) *NumError {
 	return &NumError{fn, cloneString(str), errors.New("invalid base " + Itoa(base))}
 }

 func bitSizeError(fn, str string, bitSize int) *NumError {
 	return &NumError{fn, cloneString(str), errors.New("invalid bit size " + Itoa(bitSize))}
 }

 const intSize = 32 << (^uint(0) >> 63)

 // IntSize is the size in bits of an int or uint value.
 const IntSize = intSize

 const maxUint64 = 1<<64 - 1

 // ParseUint is like [ParseInt] but for unsigned numbers.
 //
 // A sign prefix is not permitted.
 func ParseUint(s string, base int, bitSize int) (uint64, error) {
 	const fnParseUint = "ParseUint"

 	if s == "" {
 		return 0, syntaxError(fnParseUint, s)
 	}

 	base0 := base == 0

 	s0 := s
 	switch {
 	case 2 <= base && base <= 36:
 		// valid base; nothing to do

 	case base == 0:
 		// Look for octal, hex prefix.
 		base = 10
 		if s[0] == '0' {
 			switch {
 			case len(s) >= 3 && lower(s[1]) == 'b':
 				base = 2
 				s = s[2:]
 			case len(s) >= 3 && lower(s[1]) == 'o':
 				base = 8
 				s = s[2:]
 			case len(s) >= 3 && lower(s[1]) == 'x':
 				base = 16
 				s = s[2:]
 			default:
 				base = 8
 				s = s[1:]
 			}
 		}

 	default:
 		return 0, baseError(fnParseUint, s0, base)
 	}

 	if bitSize == 0 {
 		bitSize = IntSize
 	} else if bitSize < 0 || bitSize > 64 {
 		return 0, bitSizeError(fnParseUint, s0, bitSize)
 	}

 	// Cutoff is the smallest number such that cutoff*base > maxUint64.
 	// Use compile-time constants for common cases.
 	var cutoff uint64
 	switch base {
 	case 10:
 		cutoff = maxUint64/10 + 1
 	case 16:
 		cutoff = maxUint64/16 + 1
 	default:
 		cutoff = maxUint64/uint64(base) + 1
 	}

 	maxVal := uint64(1)<<uint(bitSize) - 1

 	underscores := false
 	var n uint64
 	for _, c := range []byte(s) {
 		var d byte
 		switch {
 		case c == '_' && base0:
 			underscores = true
 			continue
 		case '0' <= c && c <= '9':
 			d = c - '0'
 		case 'a' <= lower(c) && lower(c) <= 'z':
 			d = lower(c) - 'a' + 10
 		default:
 			return 0, syntaxError(fnParseUint, s0)
 		}

 		if d >= byte(base) {
 			return 0, syntaxError(fnParseUint, s0)
 		}

 		if n >= cutoff {
 			// n*base overflows
 			return maxVal, rangeError(fnParseUint, s0)
 		}
 		n *= uint64(base)

 		n1 := n + uint64(d)
 		if n1 < n || n1 > maxVal {
 			// n+d overflows
 			return maxVal, rangeError(fnParseUint, s0)
 		}
 		n = n1
 	}

 	if underscores && !underscoreOK(s0) {
 		return 0, syntaxError(fnParseUint, s0)
 	}

 	return n, nil
 }

 // ParseInt interprets a string s in the given base (0, 2 to 36) and
 // bit size (0 to 64) and returns the corresponding value i.
 //
 // The string may begin with a leading sign: "+" or "-".
 //
 // If the base argument is 0, the true base is implied by the string's
 // prefix following the sign (if present): 2 for "0b", 8 for "0" or "0o",
 // 16 for "0x", and 10 otherwise. Also, for argument base 0 only,
 // underscore characters are permitted as defined by the Go syntax for
 // [integer literals].
 //
 // The bitSize argument specifies the integer type
 // that the result must fit into. Bit sizes 0, 8, 16, 32, and 64
 // correspond to int, int8, int16, int32, and int64.
 // If bitSize is below 0 or above 64, an error is returned.
 //
 // The errors that ParseInt returns have concrete type [*NumError]
 // and include err.Num = s. If s is empty or contains invalid
 // digits, err.Err = [ErrSyntax] and the returned value is 0;
 // if the value corresponding to s cannot be represented by a
 // signed integer of the given size, err.Err = [ErrRange] and the
 // returned value is the maximum magnitude integer of the
 // appropriate bitSize and sign.
 //
 // [integer literals]: https://go.dev/ref/spec#Integer_literals
 func ParseInt(s string, base int, bitSize int) (i int64, err error) {
 	const fnParseInt = "ParseInt"

 	if s == "" {
 		return 0, syntaxError(fnParseInt, s)
 	}

 	// Pick off leading sign.
 	s0 := s
 	neg := false
 	if s[0] == '+' {
 		s = s[1:]
 	} else if s[0] == '-' {
 		neg = true
 		s = s[1:]
 	}

 	// Convert unsigned and check range.
 	var un uint64
 	un, err = ParseUint(s, base, bitSize)
 	if err != nil && err.(*NumError).Err != ErrRange {
 		err.(*NumError).Func = fnParseInt
 		err.(*NumError).Num = cloneString(s0)
 		return 0, err
 	}

 	if bitSize == 0 {
 		bitSize = IntSize
 	}

 	cutoff := uint64(1 << uint(bitSize-1))
 	if !neg && un >= cutoff {
 		return int64(cutoff - 1), rangeError(fnParseInt, s0)
 	}
 	if neg && un > cutoff {
 		return -int64(cutoff), rangeError(fnParseInt, s0)
 	}
 	n := int64(un)
 	if neg {
 		n = -n
 	}
 	return n, nil
 }

 // Atoi is equivalent to ParseInt(s, 10, 0), converted to type int.
 func Atoi(s string) (int, error) {
 	const fnAtoi = "Atoi"

 	sLen := len(s)
 	if intSize == 32 && (0 < sLen && sLen < 10) ||
 		intSize == 64 && (0 < sLen && sLen < 19) {
 		// Fast path for small integers that fit int type.
 		s0 := s
 		if s[0] == '-' || s[0] == '+' {
 			s = s[1:]
 			if len(s) < 1 {
 				return 0, syntaxError(fnAtoi, s0)
 			}
 		}

 		n := 0
 		for _, ch := range []byte(s) {
 			ch -= '0'
 			if ch > 9 {
 				return 0, syntaxError(fnAtoi, s0)
 			}
 			n = n*10 + int(ch)
 		}
 		if s0[0] == '-' {
 			n = -n
 		}
 		return n, nil
 	}

 	// Slow path for invalid, big, or underscored integers.
 	i64, err := ParseInt(s, 10, 0)
 	if nerr, ok := err.(*NumError); ok {
 		nerr.Func = fnAtoi
 	}
 	return int(i64), err
 }

 // underscoreOK reports whether the underscores in s are allowed.
 // Checking them in this one function lets all the parsers skip over them simply.
 // Underscore must appear only between digits or between a base prefix and a digit.
 func underscoreOK(s string) bool {
 	// saw tracks the last character (class) we saw:
 	// ^ for beginning of number,
 	// 0 for a digit or base prefix,
 	// _ for an underscore,
 	// ! for none of the above.
 	saw := '^'
 	i := 0

 	// Optional sign.
 	if len(s) >= 1 && (s[0] == '-' || s[0] == '+') {
 		s = s[1:]
 	}

 	// Optional base prefix.
 	hex := false
 	if len(s) >= 2 && s[0] == '0' && (lower(s[1]) == 'b' || lower(s[1]) == 'o' || lower(s[1]) == 'x') {
 		i = 2
 		saw = '0' // base prefix counts as a digit for "underscore as digit separator"
 		hex = lower(s[1]) == 'x'
 	}

 	// Number proper.
 	for ; i < len(s); i++ {
 		// Digits are always okay.
 		if '0' <= s[i] && s[i] <= '9' || hex && 'a' <= lower(s[i]) && lower(s[i]) <= 'f' {
 			saw = '0'
 			continue
 		}
 		// Underscore must follow digit.
 		if s[i] == '_' {
 			if saw != '0' {
 				return false
 			}
 			saw = '_'
 			continue
 		}
 		// Underscore must also be followed by digit.
 		if saw == '_' {
 			return false
 		}
 		// Saw non-digit, non-underscore.
 		saw = '!'
 	}
 	return saw != '_'
 }
	// 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 strconv

	import "errors"

	// lower(c) is a lower-case letter if and only if
	// c is either that lower-case letter or the equivalent upper-case letter.
	// Instead of writing c == 'x' \|\| c == 'X' one can write lower(c) == 'x'.
	// Note that lower of non-letters can produce other non-letters.
	func lower(c byte) byte {
	return c \| ('x' - 'X')
	}

	// ErrRange indicates that a value is out of range for the target type.
	var ErrRange = errors.New("value out of range")

	// ErrSyntax indicates that a value does not have the right syntax for the target type.
	var ErrSyntax = errors.New("invalid syntax")

	// A NumError records a failed conversion.
	type NumError struct {
	Func string // the failing function (ParseBool, ParseInt, ParseUint, ParseFloat, ParseComplex)
	Num string // the input
	Err error // the reason the conversion failed (e.g. ErrRange, ErrSyntax, etc.)
	}

	func (e *NumError) Error() string {
	return "strconv." + e.Func + ": " + "parsing " + Quote(e.Num) + ": " + e.Err.Error()
	}

	func (e *NumError) Unwrap() error { return e.Err }

	// cloneString returns a string copy of x.
	//
	// All ParseXXX functions allow the input string to escape to the error value.
	// This hurts strconv.ParseXXX(string(b)) calls where b is []byte since
	// the conversion from []byte must allocate a string on the heap.
	// If we assume errors are infrequent, then we can avoid escaping the input
	// back to the output by copying it first. This allows the compiler to call
	// strconv.ParseXXX without a heap allocation for most []byte to string
	// conversions, since it can now prove that the string cannot escape Parse.
	//
	// TODO: Use strings.Clone instead? However, we cannot depend on "strings"
	// since it incurs a transitive dependency on "unicode".
	// Either move strings.Clone to an internal/bytealg or make the
	// "strings" to "unicode" dependency lighter (see https://go.dev/issue/54098).
	func cloneString(x string) string { return string([]byte(x)) }

	func syntaxError(fn, str string) *NumError {
	return &NumError{fn, cloneString(str), ErrSyntax}
	}

	func rangeError(fn, str string) *NumError {
	return &NumError{fn, cloneString(str), ErrRange}
	}

	func baseError(fn, str string, base int) *NumError {
	return &NumError{fn, cloneString(str), errors.New("invalid base " + Itoa(base))}
	}

	func bitSizeError(fn, str string, bitSize int) *NumError {
	return &NumError{fn, cloneString(str), errors.New("invalid bit size " + Itoa(bitSize))}
	}

	const intSize = 32 << (^uint(0) >> 63)

	// IntSize is the size in bits of an int or uint value.
	const IntSize = intSize

	const maxUint64 = 1<<64 - 1

	// ParseUint is like [ParseInt] but for unsigned numbers.
	//
	// A sign prefix is not permitted.
	func ParseUint(s string, base int, bitSize int) (uint64, error) {
	const fnParseUint = "ParseUint"

	if s == "" {
	return 0, syntaxError(fnParseUint, s)
	}

	base0 := base == 0

	s0 := s
	switch {
	case 2 <= base && base <= 36:
	// valid base; nothing to do

	case base == 0:
	// Look for octal, hex prefix.
	base = 10
	if s[0] == '0' {
	switch {
	case len(s) >= 3 && lower(s[1]) == 'b':
	base = 2
	s = s[2:]
	case len(s) >= 3 && lower(s[1]) == 'o':
	base = 8
	s = s[2:]
	case len(s) >= 3 && lower(s[1]) == 'x':
	base = 16
	s = s[2:]
	default:
	base = 8
	s = s[1:]
	}
	}

	default:
	return 0, baseError(fnParseUint, s0, base)
	}

	if bitSize == 0 {
	bitSize = IntSize
	} else if bitSize < 0 \|\| bitSize > 64 {
	return 0, bitSizeError(fnParseUint, s0, bitSize)
	}

	// Cutoff is the smallest number such that cutoff*base > maxUint64.
	// Use compile-time constants for common cases.
	var cutoff uint64
	switch base {
	case 10:
	cutoff = maxUint64/10 + 1
	case 16:
	cutoff = maxUint64/16 + 1
	default:
	cutoff = maxUint64/uint64(base) + 1
	}

	maxVal := uint64(1)<<uint(bitSize) - 1

	underscores := false
	var n uint64
	for _, c := range []byte(s) {
	var d byte
	switch {
	case c == '_' && base0:
	underscores = true
	continue
	case '0' <= c && c <= '9':
	d = c - '0'
	case 'a' <= lower(c) && lower(c) <= 'z':
	d = lower(c) - 'a' + 10
	default:
	return 0, syntaxError(fnParseUint, s0)
	}

	if d >= byte(base) {
	return 0, syntaxError(fnParseUint, s0)
	}

	if n >= cutoff {
	// n*base overflows
	return maxVal, rangeError(fnParseUint, s0)
	}
	n *= uint64(base)

	n1 := n + uint64(d)
	if n1 < n \|\| n1 > maxVal {
	// n+d overflows
	return maxVal, rangeError(fnParseUint, s0)
	}
	n = n1
	}

	if underscores && !underscoreOK(s0) {
	return 0, syntaxError(fnParseUint, s0)
	}

	return n, nil
	}

	// ParseInt interprets a string s in the given base (0, 2 to 36) and
	// bit size (0 to 64) and returns the corresponding value i.
	//
	// The string may begin with a leading sign: "+" or "-".
	//
	// If the base argument is 0, the true base is implied by the string's
	// prefix following the sign (if present): 2 for "0b", 8 for "0" or "0o",
	// 16 for "0x", and 10 otherwise. Also, for argument base 0 only,
	// underscore characters are permitted as defined by the Go syntax for
	// [integer literals].
	//
	// The bitSize argument specifies the integer type
	// that the result must fit into. Bit sizes 0, 8, 16, 32, and 64
	// correspond to int, int8, int16, int32, and int64.
	// If bitSize is below 0 or above 64, an error is returned.
	//
	// The errors that ParseInt returns have concrete type [*NumError]
	// and include err.Num = s. If s is empty or contains invalid
	// digits, err.Err = [ErrSyntax] and the returned value is 0;
	// if the value corresponding to s cannot be represented by a
	// signed integer of the given size, err.Err = [ErrRange] and the
	// returned value is the maximum magnitude integer of the
	// appropriate bitSize and sign.
	//
	// [integer literals]: https://go.dev/ref/spec#Integer_literals
	func ParseInt(s string, base int, bitSize int) (i int64, err error) {
	const fnParseInt = "ParseInt"

	if s == "" {
	return 0, syntaxError(fnParseInt, s)
	}

	// Pick off leading sign.
	s0 := s
	neg := false
	if s[0] == '+' {
	s = s[1:]
	} else if s[0] == '-' {
	neg = true
	s = s[1:]
	}

	// Convert unsigned and check range.
	var un uint64
	un, err = ParseUint(s, base, bitSize)
	if err != nil && err.(*NumError).Err != ErrRange {
	err.(*NumError).Func = fnParseInt
	err.(*NumError).Num = cloneString(s0)
	return 0, err
	}

	if bitSize == 0 {
	bitSize = IntSize
	}

	cutoff := uint64(1 << uint(bitSize-1))
	if !neg && un >= cutoff {
	return int64(cutoff - 1), rangeError(fnParseInt, s0)
	}
	if neg && un > cutoff {
	return -int64(cutoff), rangeError(fnParseInt, s0)
	}
	n := int64(un)
	if neg {
	n = -n
	}
	return n, nil
	}

	// Atoi is equivalent to ParseInt(s, 10, 0), converted to type int.
	func Atoi(s string) (int, error) {
	const fnAtoi = "Atoi"

	sLen := len(s)
	if intSize == 32 && (0 < sLen && sLen < 10) \|\|
	intSize == 64 && (0 < sLen && sLen < 19) {
	// Fast path for small integers that fit int type.
	s0 := s
	if s[0] == '-' \|\| s[0] == '+' {
	s = s[1:]
	if len(s) < 1 {
	return 0, syntaxError(fnAtoi, s0)
	}
	}

	n := 0
	for _, ch := range []byte(s) {
	ch -= '0'
	if ch > 9 {
	return 0, syntaxError(fnAtoi, s0)
	}
	n = n*10 + int(ch)
	}
	if s0[0] == '-' {
	n = -n
	}
	return n, nil
	}

	// Slow path for invalid, big, or underscored integers.
	i64, err := ParseInt(s, 10, 0)
	if nerr, ok := err.(*NumError); ok {
	nerr.Func = fnAtoi
	}
	return int(i64), err
	}

	// underscoreOK reports whether the underscores in s are allowed.
	// Checking them in this one function lets all the parsers skip over them simply.
	// Underscore must appear only between digits or between a base prefix and a digit.
	func underscoreOK(s string) bool {
	// saw tracks the last character (class) we saw:
	// ^ for beginning of number,
	// 0 for a digit or base prefix,
	// _ for an underscore,
	// ! for none of the above.
	saw := '^'
	i := 0

	// Optional sign.
	if len(s) >= 1 && (s[0] == '-' \|\| s[0] == '+') {
	s = s[1:]
	}

	// Optional base prefix.
	hex := false
	if len(s) >= 2 && s[0] == '0' && (lower(s[1]) == 'b' \|\| lower(s[1]) == 'o' \|\| lower(s[1]) == 'x') {
	i = 2
	saw = '0' // base prefix counts as a digit for "underscore as digit separator"
	hex = lower(s[1]) == 'x'
	}

	// Number proper.
	for ; i < len(s); i++ {
	// Digits are always okay.
	if '0' <= s[i] && s[i] <= '9' \|\| hex && 'a' <= lower(s[i]) && lower(s[i]) <= 'f' {
	saw = '0'
	continue
	}
	// Underscore must follow digit.
	if s[i] == '_' {
	if saw != '0' {
	return false
	}
	saw = '_'
	continue
	}
	// Underscore must also be followed by digit.
	if saw == '_' {
	return false
	}
	// Saw non-digit, non-underscore.
	saw = '!'
	}
	return saw != '_'
	}