Source File
list.go
Belonging Package
golang.org/x/net/publicsuffix
// Copyright 2012 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.
//go:generate go run gen.go
// Package publicsuffix provides a public suffix list based on data from
// https://publicsuffix.org/
//
// A public suffix is one under which Internet users can directly register
// names. It is related to, but different from, a TLD (top level domain).
//
// "com" is a TLD (top level domain). Top level means it has no dots.
//
// "com" is also a public suffix. Amazon and Google have registered different
// siblings under that domain: "amazon.com" and "google.com".
//
// "au" is another TLD, again because it has no dots. But it's not "amazon.au".
// Instead, it's "amazon.com.au".
//
// "com.au" isn't an actual TLD, because it's not at the top level (it has
// dots). But it is an eTLD (effective TLD), because that's the branching point
// for domain name registrars.
//
// Another name for "an eTLD" is "a public suffix". Often, what's more of
// interest is the eTLD+1, or one more label than the public suffix. For
// example, browsers partition read/write access to HTTP cookies according to
// the eTLD+1. Web pages served from "amazon.com.au" can't read cookies from
// "google.com.au", but web pages served from "maps.google.com" can share
// cookies from "www.google.com", so you don't have to sign into Google Maps
// separately from signing into Google Web Search. Note that all four of those
// domains have 3 labels and 2 dots. The first two domains are each an eTLD+1,
// the last two are not (but share the same eTLD+1: "google.com").
//
// All of these domains have the same eTLD+1:
// - "www.books.amazon.co.uk"
// - "books.amazon.co.uk"
// - "amazon.co.uk"
//
// Specifically, the eTLD+1 is "amazon.co.uk", because the eTLD is "co.uk".
//
// There is no closed form algorithm to calculate the eTLD of a domain.
// Instead, the calculation is data driven. This package provides a
// pre-compiled snapshot of Mozilla's PSL (Public Suffix List) data at
// https://publicsuffix.org/
package publicsuffix // import "golang.org/x/net/publicsuffix"
// TODO: specify case sensitivity and leading/trailing dot behavior for
// func PublicSuffix and func EffectiveTLDPlusOne.
import (
)
// List implements the cookiejar.PublicSuffixList interface by calling the
// PublicSuffix function.
var List cookiejar.PublicSuffixList = list{}
type list struct{}
func (list) ( string) string {
, := PublicSuffix()
return
}
func (list) () string {
return version
}
// PublicSuffix returns the public suffix of the domain using a copy of the
// publicsuffix.org database compiled into the library.
//
// icann is whether the public suffix is managed by the Internet Corporation
// for Assigned Names and Numbers. If not, the public suffix is either a
// privately managed domain (and in practice, not a top level domain) or an
// unmanaged top level domain (and not explicitly mentioned in the
// publicsuffix.org list). For example, "foo.org" and "foo.co.uk" are ICANN
// domains, "foo.dyndns.org" and "foo.blogspot.co.uk" are private domains and
// "cromulent" is an unmanaged top level domain.
//
// Use cases for distinguishing ICANN domains like "foo.com" from private
// domains like "foo.appspot.com" can be found at
// https://wiki.mozilla.org/Public_Suffix_List/Use_Cases
func ( string) ( string, bool) {
, := uint32(0), uint32(numTLD)
, , , := , len(), false, false
:
for {
:= strings.LastIndex(, ".")
if {
=
= 1 +
}
if == {
break
}
:= find([1+:], , )
if == notFound {
break
}
:= uint32(nodes.get() >> (nodesBitsTextOffset + nodesBitsTextLength))
= &(1<<nodesBitsICANN-1) != 0
>>= nodesBitsICANN
= children.get( & (1<<nodesBitsChildren - 1))
= & (1<<childrenBitsLo - 1)
>>= childrenBitsLo
= & (1<<childrenBitsHi - 1)
>>= childrenBitsHi
switch & (1<<childrenBitsNodeType - 1) {
case nodeTypeNormal:
= 1 +
case nodeTypeException:
= 1 + len()
break
}
>>= childrenBitsNodeType
= &(1<<childrenBitsWildcard-1) != 0
if ! {
=
}
if == -1 {
break
}
= [:]
}
if == len() {
// If no rules match, the prevailing rule is "*".
return [1+strings.LastIndex(, "."):],
}
return [:],
}
const notFound uint32 = 1<<32 - 1
// find returns the index of the node in the range [lo, hi) whose label equals
// label, or notFound if there is no such node. The range is assumed to be in
// strictly increasing node label order.
func find( string, , uint32) uint32 {
for < {
:= + (-)/2
:= nodeLabel()
if < {
= + 1
} else if == {
return
} else {
=
}
}
return notFound
}
// nodeLabel returns the label for the i'th node.
func nodeLabel( uint32) string {
:= nodes.get()
:= & (1<<nodesBitsTextLength - 1)
>>= nodesBitsTextLength
:= & (1<<nodesBitsTextOffset - 1)
return text[ : +]
}
// EffectiveTLDPlusOne returns the effective top level domain plus one more
// label. For example, the eTLD+1 for "foo.bar.golang.org" is "golang.org".
func ( string) (string, error) {
if strings.HasPrefix(, ".") || strings.HasSuffix(, ".") || strings.Contains(, "..") {
return "", fmt.Errorf("publicsuffix: empty label in domain %q", )
}
, := PublicSuffix()
if len() <= len() {
return "", fmt.Errorf("publicsuffix: cannot derive eTLD+1 for domain %q", )
}
:= len() - len() - 1
if [] != '.' {
return "", fmt.Errorf("publicsuffix: invalid public suffix %q for domain %q", , )
}
return [1+strings.LastIndex([:], "."):], nil
}
type uint32String string
func ( uint32String) ( uint32) uint32 {
:= * 4
return (uint32([])<<24 |
uint32([+1])<<16 |
uint32([+2])<<8 |
uint32([+3]))
}
type uint40String string
func ( uint40String) ( uint32) uint64 {
:= uint64( * (nodesBits / 8))
return uint64([])<<32 |
uint64([+1])<<24 |
uint64([+2])<<16 |
uint64([+3])<<8 |
uint64([+4])
}
The pages are generated with Golds v0.6.7. (GOOS=linux GOARCH=amd64) Golds is a Go 101 project developed by Tapir Liu. PR and bug reports are welcome and can be submitted to the issue list. Please follow @Go100and1 (reachable from the left QR code) to get the latest news of Golds. |