github.com/cockroachdb/cockroachdb-parser@v0.23.3-0.20240213214944-911057d40c9a/pkg/util/ipaddr/ip.go

// Copyright 2021 The Cockroach Authors.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.

// 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.

// See the go license at https://golang.org/LICENSE.

// IP address manipulations
//
// IPv4 addresses are 4 bytes; IPv6 addresses are 16 bytes.
// An IPv4 address can be converted to an IPv6 address by
// adding a canonical prefix (10 zeros, 2 0xFFs).
// This library accepts either size of byte slice but always
// returns 16-byte addresses.

// This code was copied out of Go 1.16 as Go 1.17 removed the ability to
// parse leading 0s in IP addresses. We copy the Go 1.16 to keep the ParseIP
// function's capability to parse leading 0s and hence be compatible with
// Postgres.
// Example: '10.1.1.017' should be parsed as '10.1.1.17'.

package ipaddr

// An IP is a single IP address, a slice of bytes.
// Functions in this package accept either 4-byte (IPv4)
// or 16-byte (IPv6) slices as input.
//
// Note that in this documentation, referring to an
// IP address as an IPv4 address or an IPv6 address
// is a semantic property of the address, not just the
// length of the byte slice: a 16-byte slice can still
// be an IPv4 address.
type IP []byte

// IP address lengths (bytes).
const (
	IPv4len = 4
	IPv6len = 16
)

// ParseIP parses s as an IP address, returning the result.
// The string s can be in IPv4 dotted decimal ("192.0.2.1"), IPv6
// ("2001:db8::68"), or IPv4-mapped IPv6 ("::ffff:192.0.2.1") form.
// If s is not a valid textual representation of an IP address,
// ParseIP returns nil.
func ParseIP(s string) IP {
	for i := 0; i < len(s); i++ {
		switch s[i] {
		case '.':
			return parseIPv4(s)
		case ':':
			return parseIPv6(s)
		}
	}
	return nil
}

func parseIPv4(s string) IP {
	var p [IPv4len]byte
	for i := 0; i < IPv4len; i++ {
		if len(s) == 0 {
			// Missing octets.
			return nil
		}
		if i > 0 {
			if s[0] != '.' {
				return nil
			}
			s = s[1:]
		}
		n, c, ok := dtoi(s)
		if !ok || n > 0xFF {
			return nil
		}
		s = s[c:]
		p[i] = byte(n)
	}
	if len(s) != 0 {
		return nil
	}
	return makeIPv4(p[0], p[1], p[2], p[3])
}

var v4InV6Prefix = []byte{0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0xff, 0xff}

// makeIPv4 returns the IP address (in 16-byte form) of the
// IPv4 address a.b.c.d.
func makeIPv4(a, b, c, d byte) IP {
	p := make(IP, IPv6len)
	copy(p, v4InV6Prefix)
	p[12] = a
	p[13] = b
	p[14] = c
	p[15] = d
	return p
}

// parseIPv6 parses s as a literal IPv6 address described in RFC 4291
// and RFC 5952.
func parseIPv6(s string) (ip IP) {
	ip = make(IP, IPv6len)
	ellipsis := -1 // position of ellipsis in ip

	// Might have leading ellipsis
	if len(s) >= 2 && s[0] == ':' && s[1] == ':' {
		ellipsis = 0
		s = s[2:]
		// Might be only ellipsis
		if len(s) == 0 {
			return ip
		}
	}

	// Loop, parsing hex numbers followed by colon.
	i := 0
	for i < IPv6len {
		// Hex number.
		n, c, ok := xtoi(s)
		if !ok || n > 0xFFFF {
			return nil
		}

		// If followed by dot, might be in trailing IPv4.
		if c < len(s) && s[c] == '.' {
			if ellipsis < 0 && i != IPv6len-IPv4len {
				// Not the right place.
				return nil
			}
			if i+IPv4len > IPv6len {
				// Not enough room.
				return nil
			}
			ip4 := parseIPv4(s)
			if ip4 == nil {
				return nil
			}
			ip[i] = ip4[12]
			ip[i+1] = ip4[13]
			ip[i+2] = ip4[14]
			ip[i+3] = ip4[15]
			s = ""
			i += IPv4len
			break
		}

		// Save this 16-bit chunk.
		ip[i] = byte(n >> 8)
		ip[i+1] = byte(n)
		i += 2

		// Stop at end of string.
		s = s[c:]
		if len(s) == 0 {
			break
		}

		// Otherwise must be followed by colon and more.
		if s[0] != ':' || len(s) == 1 {
			return nil
		}
		s = s[1:]

		// Look for ellipsis.
		if s[0] == ':' {
			if ellipsis >= 0 { // already have one
				return nil
			}
			ellipsis = i
			s = s[1:]
			if len(s) == 0 { // can be at end
				break
			}
		}
	}

	// Must have used entire string.
	if len(s) != 0 {
		return nil
	}

	// If didn't parse enough, expand ellipsis.
	if i < IPv6len {
		if ellipsis < 0 {
			return nil
		}
		n := IPv6len - i
		for j := i - 1; j >= ellipsis; j-- {
			ip[j+n] = ip[j]
		}
		for j := ellipsis + n - 1; j >= ellipsis; j-- {
			ip[j] = 0
		}
	} else if ellipsis >= 0 {
		// Ellipsis must represent at least one 0 group.
		return nil
	}
	return ip
}

// Bigger than we need, not too big to worry about overflow
const big = 0xFFFFFF

// Decimal to integer.
// Returns number, characters consumed, success.
func dtoi(s string) (n int, i int, ok bool) {
	n = 0
	for i = 0; i < len(s) && '0' <= s[i] && s[i] <= '9'; i++ {
		n = n*10 + int(s[i]-'0')
		if n >= big {
			return big, i, false
		}
	}
	if i == 0 {
		return 0, 0, false
	}
	return n, i, true
}

// Hexadecimal to integer.
// Returns number, characters consumed, success.
func xtoi(s string) (n int, i int, ok bool) {
	n = 0
	for i = 0; i < len(s); i++ {
		if '0' <= s[i] && s[i] <= '9' {
			n *= 16
			n += int(s[i] - '0')
		} else if 'a' <= s[i] && s[i] <= 'f' {
			n *= 16
			n += int(s[i]-'a') + 10
		} else if 'A' <= s[i] && s[i] <= 'F' {
			n *= 16
			n += int(s[i]-'A') + 10
		} else {
			break
		}
		if n >= big {
			return 0, i, false
		}
	}
	if i == 0 {
		return 0, i, false
	}
	return n, i, true
}