DevFW-CICD/ingress-nginx-helm
6
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Add e2e tests

Browse source
This commit is contained in:
Manuel de Brito Fontes 2017-10-17 19:50:27 -03:00
parent 99a355f25d
commit 601fb7dacf
1163 changed files with 289217 additions and 14195 deletions
Download patch file Download diff file Expand all files Collapse all files

74
vendor/golang.org/x/net/context/ctxhttp/ctxhttp.go generated vendored Normal file
View file

@ -0,0 +1,74 @@
// Copyright 2016 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.
// +build go1.7
// Package ctxhttp provides helper functions for performing context-aware HTTP requests.
package ctxhttp // import "golang.org/x/net/context/ctxhttp"
import (
"io"
"net/http"
"net/url"
"strings"
"golang.org/x/net/context"
)
// Do sends an HTTP request with the provided http.Client and returns
// an HTTP response.
//
// If the client is nil, http.DefaultClient is used.
//
// The provided ctx must be non-nil. If it is canceled or times out,
// ctx.Err() will be returned.
func Do(ctx context.Context, client *http.Client, req *http.Request) (*http.Response, error) {
if client == nil {
client = http.DefaultClient
}
resp, err := client.Do(req.WithContext(ctx))
// If we got an error, and the context has been canceled,
// the context's error is probably more useful.
if err != nil {
select {
case <-ctx.Done():
err = ctx.Err()
default:
}
}
return resp, err
}
// Get issues a GET request via the Do function.
func Get(ctx context.Context, client *http.Client, url string) (*http.Response, error) {
req, err := http.NewRequest("GET", url, nil)
if err != nil {
return nil, err
}
return Do(ctx, client, req)
}
// Head issues a HEAD request via the Do function.
func Head(ctx context.Context, client *http.Client, url string) (*http.Response, error) {
req, err := http.NewRequest("HEAD", url, nil)
if err != nil {
return nil, err
}
return Do(ctx, client, req)
}
// Post issues a POST request via the Do function.
func Post(ctx context.Context, client *http.Client, url string, bodyType string, body io.Reader) (*http.Response, error) {
req, err := http.NewRequest("POST", url, body)
if err != nil {
return nil, err
}
req.Header.Set("Content-Type", bodyType)
return Do(ctx, client, req)
}
// PostForm issues a POST request via the Do function.
func PostForm(ctx context.Context, client *http.Client, url string, data url.Values) (*http.Response, error) {
return Post(ctx, client, url, "application/x-www-form-urlencoded", strings.NewReader(data.Encode()))
}

29
vendor/golang.org/x/net/context/ctxhttp/ctxhttp_17_test.go generated vendored Normal file
View file

@ -0,0 +1,29 @@
// Copyright 2015 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.
// +build !plan9,go1.7
package ctxhttp
import (
"io"
"net/http"
"net/http/httptest"
"testing"
"context"
)
func TestGo17Context(t *testing.T) {
ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
io.WriteString(w, "ok")
}))
defer ts.Close()
ctx := context.Background()
resp, err := Get(ctx, http.DefaultClient, ts.URL)
if resp == nil || err != nil {
t.Fatalf("error received from client: %v %v", err, resp)
}
resp.Body.Close()
}

147
vendor/golang.org/x/net/context/ctxhttp/ctxhttp_pre17.go generated vendored Normal file
View file

@ -0,0 +1,147 @@
// Copyright 2015 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.
// +build !go1.7
package ctxhttp // import "golang.org/x/net/context/ctxhttp"
import (
"io"
"net/http"
"net/url"
"strings"
"golang.org/x/net/context"
)
func nop() {}
var (
testHookContextDoneBeforeHeaders = nop
testHookDoReturned = nop
testHookDidBodyClose = nop
)
// Do sends an HTTP request with the provided http.Client and returns an HTTP response.
// If the client is nil, http.DefaultClient is used.
// If the context is canceled or times out, ctx.Err() will be returned.
func Do(ctx context.Context, client *http.Client, req *http.Request) (*http.Response, error) {
if client == nil {
client = http.DefaultClient
}
// TODO(djd): Respect any existing value of req.Cancel.
cancel := make(chan struct{})
req.Cancel = cancel
type responseAndError struct {
resp *http.Response
err error
}
result := make(chan responseAndError, 1)
// Make local copies of test hooks closed over by goroutines below.
// Prevents data races in tests.
testHookDoReturned := testHookDoReturned
testHookDidBodyClose := testHookDidBodyClose
go func() {
resp, err := client.Do(req)
testHookDoReturned()
result <- responseAndError{resp, err}
}()
var resp *http.Response
select {
case <-ctx.Done():
testHookContextDoneBeforeHeaders()
close(cancel)
// Clean up after the goroutine calling client.Do:
go func() {
if r := <-result; r.resp != nil {
testHookDidBodyClose()
r.resp.Body.Close()
}
}()
return nil, ctx.Err()
case r := <-result:
var err error
resp, err = r.resp, r.err
if err != nil {
return resp, err
}
}
c := make(chan struct{})
go func() {
select {
case <-ctx.Done():
close(cancel)
case <-c:
// The response's Body is closed.
}
}()
resp.Body = &notifyingReader{resp.Body, c}
return resp, nil
}
// Get issues a GET request via the Do function.
func Get(ctx context.Context, client *http.Client, url string) (*http.Response, error) {
req, err := http.NewRequest("GET", url, nil)
if err != nil {
return nil, err
}
return Do(ctx, client, req)
}
// Head issues a HEAD request via the Do function.
func Head(ctx context.Context, client *http.Client, url string) (*http.Response, error) {
req, err := http.NewRequest("HEAD", url, nil)
if err != nil {
return nil, err
}
return Do(ctx, client, req)
}
// Post issues a POST request via the Do function.
func Post(ctx context.Context, client *http.Client, url string, bodyType string, body io.Reader) (*http.Response, error) {
req, err := http.NewRequest("POST", url, body)
if err != nil {
return nil, err
}
req.Header.Set("Content-Type", bodyType)
return Do(ctx, client, req)
}
// PostForm issues a POST request via the Do function.
func PostForm(ctx context.Context, client *http.Client, url string, data url.Values) (*http.Response, error) {
return Post(ctx, client, url, "application/x-www-form-urlencoded", strings.NewReader(data.Encode()))
}
// notifyingReader is an io.ReadCloser that closes the notify channel after
// Close is called or a Read fails on the underlying ReadCloser.
type notifyingReader struct {
io.ReadCloser
notify chan<- struct{}
}
func (r *notifyingReader) Read(p []byte) (int, error) {
n, err := r.ReadCloser.Read(p)
if err != nil && r.notify != nil {
close(r.notify)
r.notify = nil
}
return n, err
}
func (r *notifyingReader) Close() error {
err := r.ReadCloser.Close()
if r.notify != nil {
close(r.notify)
r.notify = nil
}
return err
}

79
vendor/golang.org/x/net/context/ctxhttp/ctxhttp_pre17_test.go generated vendored Normal file
View file

@ -0,0 +1,79 @@
// Copyright 2015 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.
// +build !plan9,!go1.7
package ctxhttp
import (
"net"
"net/http"
"net/http/httptest"
"sync"
"testing"
"time"
"golang.org/x/net/context"
)
// golang.org/issue/14065
func TestClosesResponseBodyOnCancel(t *testing.T) {
defer func() { testHookContextDoneBeforeHeaders = nop }()
defer func() { testHookDoReturned = nop }()
defer func() { testHookDidBodyClose = nop }()
ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {}))
defer ts.Close()
ctx, cancel := context.WithCancel(context.Background())
// closed when Do enters select case <-ctx.Done()
enteredDonePath := make(chan struct{})
testHookContextDoneBeforeHeaders = func() {
close(enteredDonePath)
}
testHookDoReturned = func() {
// We now have the result (the Flush'd headers) at least,
// so we can cancel the request.
cancel()
// But block the client.Do goroutine from sending
// until Do enters into the <-ctx.Done() path, since
// otherwise if both channels are readable, select
// picks a random one.
<-enteredDonePath
}
sawBodyClose := make(chan struct{})
testHookDidBodyClose = func() { close(sawBodyClose) }
tr := &http.Transport{}
defer tr.CloseIdleConnections()
c := &http.Client{Transport: tr}
req, _ := http.NewRequest("GET", ts.URL, nil)
_, doErr := Do(ctx, c, req)
select {
case <-sawBodyClose:
case <-time.After(5 * time.Second):
t.Fatal("timeout waiting for body to close")
}
if doErr != ctx.Err() {
t.Errorf("Do error = %v; want %v", doErr, ctx.Err())
}
}
type noteCloseConn struct {
net.Conn
onceClose sync.Once
closefn func()
}
func (c *noteCloseConn) Close() error {
c.onceClose.Do(c.closefn)
return c.Conn.Close()
}

105
vendor/golang.org/x/net/context/ctxhttp/ctxhttp_test.go generated vendored Normal file
View file

@ -0,0 +1,105 @@
// Copyright 2015 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.
// +build !plan9
package ctxhttp
import (
"io"
"io/ioutil"
"net/http"
"net/http/httptest"
"testing"
"time"
"golang.org/x/net/context"
)
const (
requestDuration = 100 * time.Millisecond
requestBody = "ok"
)
func okHandler(w http.ResponseWriter, r *http.Request) {
time.Sleep(requestDuration)
io.WriteString(w, requestBody)
}
func TestNoTimeout(t *testing.T) {
ts := httptest.NewServer(http.HandlerFunc(okHandler))
defer ts.Close()
ctx := context.Background()
res, err := Get(ctx, nil, ts.URL)
if err != nil {
t.Fatal(err)
}
defer res.Body.Close()
slurp, err := ioutil.ReadAll(res.Body)
if err != nil {
t.Fatal(err)
}
if string(slurp) != requestBody {
t.Errorf("body = %q; want %q", slurp, requestBody)
}
}
func TestCancelBeforeHeaders(t *testing.T) {
ctx, cancel := context.WithCancel(context.Background())
blockServer := make(chan struct{})
ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
cancel()
<-blockServer
io.WriteString(w, requestBody)
}))
defer ts.Close()
defer close(blockServer)
res, err := Get(ctx, nil, ts.URL)
if err == nil {
res.Body.Close()
t.Fatal("Get returned unexpected nil error")
}
if err != context.Canceled {
t.Errorf("err = %v; want %v", err, context.Canceled)
}
}
func TestCancelAfterHangingRequest(t *testing.T) {
ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(http.StatusOK)
w.(http.Flusher).Flush()
<-w.(http.CloseNotifier).CloseNotify()
}))
defer ts.Close()
ctx, cancel := context.WithCancel(context.Background())
resp, err := Get(ctx, nil, ts.URL)
if err != nil {
t.Fatalf("unexpected error in Get: %v", err)
}
// Cancel befer reading the body.
// Reading Request.Body should fail, since the request was
// canceled before anything was written.
cancel()
done := make(chan struct{})
go func() {
b, err := ioutil.ReadAll(resp.Body)
if len(b) != 0 || err == nil {
t.Errorf(`Read got (%q, %v); want ("", error)`, b, err)
}
close(done)
}()
select {
case <-time.After(1 * time.Second):
t.Errorf("Test timed out")
case <-done:
}
}

78
vendor/golang.org/x/net/html/atom/atom.go generated vendored Normal file
View file

@ -0,0 +1,78 @@
// 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.
// Package atom provides integer codes (also known as atoms) for a fixed set of
// frequently occurring HTML strings: tag names and attribute keys such as "p"
// and "id".
//
// Sharing an atom's name between all elements with the same tag can result in
// fewer string allocations when tokenizing and parsing HTML. Integer
// comparisons are also generally faster than string comparisons.
//
// The value of an atom's particular code is not guaranteed to stay the same
// between versions of this package. Neither is any ordering guaranteed:
// whether atom.H1 < atom.H2 may also change. The codes are not guaranteed to
// be dense. The only guarantees are that e.g. looking up "div" will yield
// atom.Div, calling atom.Div.String will return "div", and atom.Div != 0.
package atom // import "golang.org/x/net/html/atom"
// Atom is an integer code for a string. The zero value maps to "".
type Atom uint32
// String returns the atom's name.
func (a Atom) String() string {
start := uint32(a >> 8)
n := uint32(a & 0xff)
if start+n > uint32(len(atomText)) {
return ""
}
return atomText[start : start+n]
}
func (a Atom) string() string {
return atomText[a>>8 : a>>8+a&0xff]
}
// fnv computes the FNV hash with an arbitrary starting value h.
func fnv(h uint32, s []byte) uint32 {
for i := range s {
h ^= uint32(s[i])
h *= 16777619
}
return h
}
func match(s string, t []byte) bool {
for i, c := range t {
if s[i] != c {
return false
}
}
return true
}
// Lookup returns the atom whose name is s. It returns zero if there is no
// such atom. The lookup is case sensitive.
func Lookup(s []byte) Atom {
if len(s) == 0 || len(s) > maxAtomLen {
return 0
}
h := fnv(hash0, s)
if a := table[h&uint32(len(table)-1)]; int(a&0xff) == len(s) && match(a.string(), s) {
return a
}
if a := table[(h>>16)&uint32(len(table)-1)]; int(a&0xff) == len(s) && match(a.string(), s) {
return a
}
return 0
}
// String returns a string whose contents are equal to s. In that sense, it is
// equivalent to string(s) but may be more efficient.
func String(s []byte) string {
if a := Lookup(s); a != 0 {
return a.String()
}
return string(s)
}

109
vendor/golang.org/x/net/html/atom/atom_test.go generated vendored Normal file
View file

@ -0,0 +1,109 @@
// 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.
package atom
import (
"sort"
"testing"
)
func TestKnown(t *testing.T) {
for _, s := range testAtomList {
if atom := Lookup([]byte(s)); atom.String() != s {
t.Errorf("Lookup(%q) = %#x (%q)", s, uint32(atom), atom.String())
}
}
}
func TestHits(t *testing.T) {
for _, a := range table {
if a == 0 {
continue
}
got := Lookup([]byte(a.String()))
if got != a {
t.Errorf("Lookup(%q) = %#x, want %#x", a.String(), uint32(got), uint32(a))
}
}
}
func TestMisses(t *testing.T) {
testCases := []string{
"",
"\x00",
"\xff",
"A",
"DIV",
"Div",
"dIV",
"aa",
"a\x00",
"ab",
"abb",
"abbr0",
"abbr ",
" abbr",
" a",
"acceptcharset",
"acceptCharset",
"accept_charset",
"h0",
"h1h2",
"h7",
"onClick",
"λ",
// The following string has the same hash (0xa1d7fab7) as "onmouseover".
"\x00\x00\x00\x00\x00\x50\x18\xae\x38\xd0\xb7",
}
for _, tc := range testCases {
got := Lookup([]byte(tc))
if got != 0 {
t.Errorf("Lookup(%q): got %d, want 0", tc, got)
}
}
}
func TestForeignObject(t *testing.T) {
const (
afo = Foreignobject
afO = ForeignObject
sfo = "foreignobject"
sfO = "foreignObject"
)
if got := Lookup([]byte(sfo)); got != afo {
t.Errorf("Lookup(%q): got %#v, want %#v", sfo, got, afo)
}
if got := Lookup([]byte(sfO)); got != afO {
t.Errorf("Lookup(%q): got %#v, want %#v", sfO, got, afO)
}
if got := afo.String(); got != sfo {
t.Errorf("Atom(%#v).String(): got %q, want %q", afo, got, sfo)
}
if got := afO.String(); got != sfO {
t.Errorf("Atom(%#v).String(): got %q, want %q", afO, got, sfO)
}
}
func BenchmarkLookup(b *testing.B) {
sortedTable := make([]string, 0, len(table))
for _, a := range table {
if a != 0 {
sortedTable = append(sortedTable, a.String())
}
}
sort.Strings(sortedTable)
x := make([][]byte, 1000)
for i := range x {
x[i] = []byte(sortedTable[i%len(sortedTable)])
}
b.ResetTimer()
for i := 0; i < b.N; i++ {
for _, s := range x {
Lookup(s)
}
}
}

709
vendor/golang.org/x/net/html/atom/gen.go generated vendored Normal file
View file

@ -0,0 +1,709 @@
// 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.
// +build ignore
//go:generate go run gen.go
//go:generate go run gen.go -test
package main
import (
"bytes"
"flag"
"fmt"
"go/format"
"io/ioutil"
"math/rand"
"os"
"sort"
"strings"
)
// identifier converts s to a Go exported identifier.
// It converts "div" to "Div" and "accept-charset" to "AcceptCharset".
func identifier(s string) string {
b := make([]byte, 0, len(s))
cap := true
for _, c := range s {
if c == '-' {
cap = true
continue
}
if cap && 'a' <= c && c <= 'z' {
c -= 'a' - 'A'
}
cap = false
b = append(b, byte(c))
}
return string(b)
}
var test = flag.Bool("test", false, "generate table_test.go")
func genFile(name string, buf *bytes.Buffer) {
b, err := format.Source(buf.Bytes())
if err != nil {
fmt.Fprintln(os.Stderr, err)
os.Exit(1)
}
if err := ioutil.WriteFile(name, b, 0644); err != nil {
fmt.Fprintln(os.Stderr, err)
os.Exit(1)
}
}
func main() {
flag.Parse()
var all []string
all = append(all, elements...)
all = append(all, attributes...)
all = append(all, eventHandlers...)
all = append(all, extra...)
sort.Strings(all)
// uniq - lists have dups
w := 0
for _, s := range all {
if w == 0 || all[w-1] != s {
all[w] = s
w++
}
}
all = all[:w]
if *test {
var buf bytes.Buffer
fmt.Fprintln(&buf, "// Code generated by go generate gen.go; DO NOT EDIT.\n")
fmt.Fprintln(&buf, "//go:generate go run gen.go -test\n")
fmt.Fprintln(&buf, "package atom\n")
fmt.Fprintln(&buf, "var testAtomList = []string{")
for _, s := range all {
fmt.Fprintf(&buf, "\t%q,\n", s)
}
fmt.Fprintln(&buf, "}")
genFile("table_test.go", &buf)
return
}
// Find hash that minimizes table size.
var best *table
for i := 0; i < 1000000; i++ {
if best != nil && 1<<(best.k-1) < len(all) {
break
}
h := rand.Uint32()
for k := uint(0); k <= 16; k++ {
if best != nil && k >= best.k {
break
}
var t table
if t.init(h, k, all) {
best = &t
break
}
}
}
if best == nil {
fmt.Fprintf(os.Stderr, "failed to construct string table\n")
os.Exit(1)
}
// Lay out strings, using overlaps when possible.
layout := append([]string{}, all...)
// Remove strings that are substrings of other strings
for changed := true; changed; {
changed = false
for i, s := range layout {
if s == "" {
continue
}
for j, t := range layout {
if i != j && t != "" && strings.Contains(s, t) {
changed = true
layout[j] = ""
}
}
}
}
// Join strings where one suffix matches another prefix.
for {
// Find best i, j, k such that layout[i][len-k:] == layout[j][:k],
// maximizing overlap length k.
besti := -1
bestj := -1
bestk := 0
for i, s := range layout {
if s == "" {
continue
}
for j, t := range layout {
if i == j {
continue
}
for k := bestk + 1; k <= len(s) && k <= len(t); k++ {
if s[len(s)-k:] == t[:k] {
besti = i
bestj = j
bestk = k
}
}
}
}
if bestk > 0 {
layout[besti] += layout[bestj][bestk:]
layout[bestj] = ""
continue
}
break
}
text := strings.Join(layout, "")
atom := map[string]uint32{}
for _, s := range all {
off := strings.Index(text, s)
if off < 0 {
panic("lost string " + s)
}
atom[s] = uint32(off<<8 | len(s))
}
var buf bytes.Buffer
// Generate the Go code.
fmt.Fprintln(&buf, "// Code generated by go generate gen.go; DO NOT EDIT.\n")
fmt.Fprintln(&buf, "//go:generate go run gen.go\n")
fmt.Fprintln(&buf, "package atom\n\nconst (")
// compute max len
maxLen := 0
for _, s := range all {
if maxLen < len(s) {
maxLen = len(s)
}
fmt.Fprintf(&buf, "\t%s Atom = %#x\n", identifier(s), atom[s])
}
fmt.Fprintln(&buf, ")\n")
fmt.Fprintf(&buf, "const hash0 = %#x\n\n", best.h0)
fmt.Fprintf(&buf, "const maxAtomLen = %d\n\n", maxLen)
fmt.Fprintf(&buf, "var table = [1<<%d]Atom{\n", best.k)
for i, s := range best.tab {
if s == "" {
continue
}
fmt.Fprintf(&buf, "\t%#x: %#x, // %s\n", i, atom[s], s)
}
fmt.Fprintf(&buf, "}\n")
datasize := (1 << best.k) * 4
fmt.Fprintln(&buf, "const atomText =")
textsize := len(text)
for len(text) > 60 {
fmt.Fprintf(&buf, "\t%q +\n", text[:60])
text = text[60:]
}
fmt.Fprintf(&buf, "\t%q\n\n", text)
genFile("table.go", &buf)
fmt.Fprintf(os.Stdout, "%d atoms; %d string bytes + %d tables = %d total data\n", len(all), textsize, datasize, textsize+datasize)
}
type byLen []string
func (x byLen) Less(i, j int) bool { return len(x[i]) > len(x[j]) }
func (x byLen) Swap(i, j int) { x[i], x[j] = x[j], x[i] }
func (x byLen) Len() int { return len(x) }
// fnv computes the FNV hash with an arbitrary starting value h.
func fnv(h uint32, s string) uint32 {
for i := 0; i < len(s); i++ {
h ^= uint32(s[i])
h *= 16777619
}
return h
}
// A table represents an attempt at constructing the lookup table.
// The lookup table uses cuckoo hashing, meaning that each string
// can be found in one of two positions.
type table struct {
h0 uint32
k uint
mask uint32
tab []string
}
// hash returns the two hashes for s.
func (t *table) hash(s string) (h1, h2 uint32) {
h := fnv(t.h0, s)
h1 = h & t.mask
h2 = (h >> 16) & t.mask
return
}
// init initializes the table with the given parameters.
// h0 is the initial hash value,
// k is the number of bits of hash value to use, and
// x is the list of strings to store in the table.
// init returns false if the table cannot be constructed.
func (t *table) init(h0 uint32, k uint, x []string) bool {
t.h0 = h0
t.k = k
t.tab = make([]string, 1<<k)
t.mask = 1<<k - 1
for _, s := range x {
if !t.insert(s) {
return false
}
}
return true
}
// insert inserts s in the table.
func (t *table) insert(s string) bool {
h1, h2 := t.hash(s)
if t.tab[h1] == "" {
t.tab[h1] = s
return true
}
if t.tab[h2] == "" {
t.tab[h2] = s
return true
}
if t.push(h1, 0) {
t.tab[h1] = s
return true
}
if t.push(h2, 0) {
t.tab[h2] = s
return true
}
return false
}
// push attempts to push aside the entry in slot i.
func (t *table) push(i uint32, depth int) bool {
if depth > len(t.tab) {
return false
}
s := t.tab[i]
h1, h2 := t.hash(s)
j := h1 + h2 - i
if t.tab[j] != "" && !t.push(j, depth+1) {
return false
}
t.tab[j] = s
return true
}
// The lists of element names and attribute keys were taken from
// https://html.spec.whatwg.org/multipage/indices.html#index
// as of the "HTML Living Standard - Last Updated 18 September 2017" version.
// "command", "keygen" and "menuitem" have been removed from the spec,
// but are kept here for backwards compatibility.
var elements = []string{
"a",
"abbr",
"address",
"area",
"article",
"aside",
"audio",
"b",
"base",
"bdi",
"bdo",
"blockquote",
"body",
"br",
"button",
"canvas",
"caption",
"cite",
"code",
"col",
"colgroup",
"command",
"data",
"datalist",
"dd",
"del",
"details",
"dfn",
"dialog",
"div",
"dl",
"dt",
"em",
"embed",
"fieldset",
"figcaption",
"figure",
"footer",
"form",
"h1",
"h2",
"h3",
"h4",
"h5",
"h6",
"head",
"header",
"hgroup",
"hr",
"html",
"i",
"iframe",
"img",
"input",
"ins",
"kbd",
"keygen",
"label",
"legend",
"li",
"link",
"main",
"map",
"mark",
"menu",
"menuitem",
"meta",
"meter",
"nav",
"noscript",
"object",
"ol",
"optgroup",
"option",
"output",
"p",
"param",
"picture",
"pre",
"progress",
"q",
"rp",
"rt",
"ruby",
"s",
"samp",
"script",
"section",
"select",
"slot",
"small",
"source",
"span",
"strong",
"style",
"sub",
"summary",
"sup",
"table",
"tbody",
"td",
"template",
"textarea",
"tfoot",
"th",
"thead",
"time",
"title",
"tr",
"track",
"u",
"ul",
"var",
"video",
"wbr",
}
// https://html.spec.whatwg.org/multipage/indices.html#attributes-3
//
// "challenge", "command", "contextmenu", "dropzone", "icon", "keytype", "mediagroup",
// "radiogroup", "spellcheck", "scoped", "seamless", "sortable" and "sorted" have been removed from the spec,
// but are kept here for backwards compatibility.
var attributes = []string{
"abbr",
"accept",
"accept-charset",
"accesskey",
"action",
"allowfullscreen",
"allowpaymentrequest",
"allowusermedia",
"alt",
"as",
"async",
"autocomplete",
"autofocus",
"autoplay",
"challenge",
"charset",
"checked",
"cite",
"class",
"color",
"cols",
"colspan",
"command",
"content",
"contenteditable",
"contextmenu",
"controls",
"coords",
"crossorigin",
"data",
"datetime",
"default",
"defer",
"dir",
"dirname",
"disabled",
"download",
"draggable",
"dropzone",
"enctype",
"for",
"form",
"formaction",
"formenctype",
"formmethod",
"formnovalidate",
"formtarget",
"headers",
"height",
"hidden",
"high",
"href",
"hreflang",
"http-equiv",
"icon",
"id",
"inputmode",
"integrity",
"is",
"ismap",
"itemid",
"itemprop",
"itemref",
"itemscope",
"itemtype",
"keytype",
"kind",
"label",
"lang",
"list",
"loop",
"low",
"manifest",
"max",
"maxlength",
"media",
"mediagroup",
"method",
"min",
"minlength",
"multiple",
"muted",
"name",
"nomodule",
"nonce",
"novalidate",
"open",
"optimum",
"pattern",
"ping",
"placeholder",
"playsinline",
"poster",
"preload",
"radiogroup",
"readonly",
"referrerpolicy",
"rel",
"required",
"reversed",
"rows",
"rowspan",
"sandbox",
"spellcheck",
"scope",
"scoped",
"seamless",
"selected",
"shape",
"size",
"sizes",
"sortable",
"sorted",
"slot",
"span",
"spellcheck",
"src",
"srcdoc",
"srclang",
"srcset",
"start",
"step",
"style",
"tabindex",
"target",
"title",
"translate",
"type",
"typemustmatch",
"updateviacache",
"usemap",
"value",
"width",
"workertype",
"wrap",
}
// "onautocomplete", "onautocompleteerror", "onmousewheel",
// "onshow" and "onsort" have been removed from the spec,
// but are kept here for backwards compatibility.
var eventHandlers = []string{
"onabort",
"onautocomplete",
"onautocompleteerror",
"onauxclick",
"onafterprint",
"onbeforeprint",
"onbeforeunload",
"onblur",
"oncancel",
"oncanplay",
"oncanplaythrough",
"onchange",
"onclick",
"onclose",
"oncontextmenu",
"oncopy",
"oncuechange",
"oncut",
"ondblclick",
"ondrag",
"ondragend",
"ondragenter",
"ondragexit",
"ondragleave",
"ondragover",
"ondragstart",
"ondrop",
"ondurationchange",
"onemptied",
"onended",
"onerror",
"onfocus",
"onhashchange",
"oninput",
"oninvalid",
"onkeydown",
"onkeypress",
"onkeyup",
"onlanguagechange",
"onload",
"onloadeddata",
"onloadedmetadata",
"onloadend",
"onloadstart",
"onmessage",
"onmessageerror",
"onmousedown",
"onmouseenter",
"onmouseleave",
"onmousemove",
"onmouseout",
"onmouseover",
"onmouseup",
"onmousewheel",
"onwheel",
"onoffline",
"ononline",
"onpagehide",
"onpageshow",
"onpaste",
"onpause",
"onplay",
"onplaying",
"onpopstate",
"onprogress",
"onratechange",
"onreset",
"onresize",
"onrejectionhandled",
"onscroll",
"onsecuritypolicyviolation",
"onseeked",
"onseeking",
"onselect",
"onshow",
"onsort",
"onstalled",
"onstorage",
"onsubmit",
"onsuspend",
"ontimeupdate",
"ontoggle",
"onunhandledrejection",
"onunload",
"onvolumechange",
"onwaiting",
}
// extra are ad-hoc values not covered by any of the lists above.
var extra = []string{
"align",
"annotation",
"annotation-xml",
"applet",
"basefont",
"bgsound",
"big",
"blink",
"center",
"color",
"desc",
"face",
"font",
"foreignObject", // HTML is case-insensitive, but SVG-embedded-in-HTML is case-sensitive.
"foreignobject",
"frame",
"frameset",
"image",
"isindex",
"listing",
"malignmark",
"marquee",
"math",
"mglyph",
"mi",
"mn",
"mo",
"ms",
"mtext",
"nobr",
"noembed",
"noframes",
"plaintext",
"prompt",
"public",
"spacer",
"strike",
"svg",
"system",
"tt",
"xmp",
}

777
vendor/golang.org/x/net/html/atom/table.go generated vendored Normal file
View file

@ -0,0 +1,777 @@
// Code generated by go generate gen.go; DO NOT EDIT.
//go:generate go run gen.go
package atom
const (
A Atom = 0x1
Abbr Atom = 0x4
Accept Atom = 0x1a06
AcceptCharset Atom = 0x1a0e
Accesskey Atom = 0x2c09
Action Atom = 0x25a06
Address Atom = 0x6ed07
Align Atom = 0x6d405
Allowfullscreen Atom = 0x1f00f
Allowpaymentrequest Atom = 0x6913
Allowusermedia Atom = 0x850e
Alt Atom = 0xb003
Annotation Atom = 0x1b90a
AnnotationXml Atom = 0x1b90e
Applet Atom = 0x30106
Area Atom = 0x34a04
Article Atom = 0x3f007
As Atom = 0xb902
Aside Atom = 0xc105
Async Atom = 0xb905
Audio Atom = 0xcf05
Autocomplete Atom = 0x2600c
Autofocus Atom = 0xeb09
Autoplay Atom = 0x10608
B Atom = 0x101
Base Atom = 0x11504
Basefont Atom = 0x11508
Bdi Atom = 0x16103
Bdo Atom = 0x13403
Bgsound Atom = 0x14707
Big Atom = 0x15903
Blink Atom = 0x15c05
Blockquote Atom = 0x1680a
Body Atom = 0x2804
Br Atom = 0x202
Button Atom = 0x17206
Canvas Atom = 0xbd06
Caption Atom = 0x21907
Center Atom = 0x20806
Challenge Atom = 0x28309
Charset Atom = 0x2107
Checked Atom = 0x46d07
Cite Atom = 0x55804
Class Atom = 0x5b905
Code Atom = 0x19004
Col Atom = 0x19703
Colgroup Atom = 0x19708
Color Atom = 0x1af05
Cols Atom = 0x1b404
Colspan Atom = 0x1b407
Command Atom = 0x1c707
Content Atom = 0x57f07
Contenteditable Atom = 0x57f0f
Contextmenu Atom = 0x3740b
Controls Atom = 0x1ce08
Coords Atom = 0x1da06
Crossorigin Atom = 0x1e30b
Data Atom = 0x49904
Datalist Atom = 0x49908
Datetime Atom = 0x2a008
Dd Atom = 0x2bf02
Default Atom = 0xc407
Defer Atom = 0x19205
Del Atom = 0x44603
Desc Atom = 0x55504
Details Atom = 0x4607
Dfn Atom = 0x5f03
Dialog Atom = 0x16206
Dir Atom = 0xa303
Dirname Atom = 0xa307
Disabled Atom = 0x14d08
Div Atom = 0x15403
Dl Atom = 0x5e202
Download Atom = 0x45708
Draggable Atom = 0x18309
Dropzone Atom = 0x3f908
Dt Atom = 0x64702
Em Atom = 0x4202
Embed Atom = 0x4205
Enctype Atom = 0x27507
Face Atom = 0x20604
Fieldset Atom = 0x20e08
Figcaption Atom = 0x2160a
Figure Atom = 0x23006
Font Atom = 0x11904
Footer Atom = 0xb306
For Atom = 0x23c03
ForeignObject Atom = 0x23c0d
Foreignobject Atom = 0x2490d
Form Atom = 0x25604
Formaction Atom = 0x2560a
Formenctype Atom = 0x2710b
Formmethod Atom = 0x28c0a
Formnovalidate Atom = 0x2960e
Formtarget Atom = 0x2a80a
Frame Atom = 0x5705
Frameset Atom = 0x5708
H1 Atom = 0x14502
H2 Atom = 0x2c602
H3 Atom = 0x2f502
H4 Atom = 0x33902
H5 Atom = 0x34302
H6 Atom = 0x64902
Head Atom = 0x32504
Header Atom = 0x32506
Headers Atom = 0x32507
Height Atom = 0x12c06
Hgroup Atom = 0x2b206
Hidden Atom = 0x2bd06
High Atom = 0x2c304
Hr Atom = 0x14002
Href Atom = 0x2c804
Hreflang Atom = 0x2c808
Html Atom = 0x13004
HttpEquiv Atom = 0x2d00a
I Atom = 0x601
Icon Atom = 0x57e04
Id Atom = 0xc302
Iframe Atom = 0x2e406
Image Atom = 0x2ea05
Img Atom = 0x2ef03
Input Atom = 0x43f05
Inputmode Atom = 0x43f09
Ins Atom = 0x1ec03
Integrity Atom = 0x22709
Is Atom = 0x14e02
Isindex Atom = 0x2f707
Ismap Atom = 0x2fe05
Itemid Atom = 0x37f06
Itemprop Atom = 0x55908
Itemref Atom = 0x3c107
Itemscope Atom = 0x66d09
Itemtype Atom = 0x30708
Kbd Atom = 0x16003
Keygen Atom = 0x3206
Keytype Atom = 0x7e07
Kind Atom = 0x18004
Label Atom = 0xda05
Lang Atom = 0x2cc04
Legend Atom = 0x18a06
Li Atom = 0x11102
Link Atom = 0x15d04
List Atom = 0x49d04
Listing Atom = 0x49d07
Loop Atom = 0xde04
Low Atom = 0x6b03
Main Atom = 0x1004
Malignmark Atom = 0x6d30a
Manifest Atom = 0x30f08
Map Atom = 0x30003
Mark Atom = 0x6d904
Marquee Atom = 0x31b07
Math Atom = 0x32204
Max Atom = 0x33103
Maxlength Atom = 0x33109
Media Atom = 0x8e05
Mediagroup Atom = 0x8e0a
Menu Atom = 0x37b04
Menuitem Atom = 0x37b08
Meta Atom = 0x4ac04
Meter Atom = 0xa805
Method Atom = 0x29006
Mglyph Atom = 0x2f006
Mi Atom = 0x33b02
Min Atom = 0x33b03
Minlength Atom = 0x33b09
Mn Atom = 0x29902
Mo Atom = 0x6302
Ms Atom = 0x67002
Mtext Atom = 0x34505
Multiple Atom = 0x35308
Muted Atom = 0x35b05
Name Atom = 0xa604
Nav Atom = 0x1303
Nobr Atom = 0x3704
Noembed Atom = 0x4007
Noframes Atom = 0x5508
Nomodule Atom = 0x6108
Nonce Atom = 0x56205
Noscript Atom = 0x1fe08
Novalidate Atom = 0x29a0a
Object Atom = 0x25006
Ol Atom = 0x10102
Onabort Atom = 0x17607
Onafterprint Atom = 0x21e0c
Onautocomplete Atom = 0x25e0e
Onautocompleteerror Atom = 0x25e13
Onauxclick Atom = 0x61b0a
Onbeforeprint Atom = 0x69a0d
Onbeforeunload Atom = 0x6e10e
Onblur Atom = 0x5c206
Oncancel Atom = 0xd308
Oncanplay Atom = 0x13609
Oncanplaythrough Atom = 0x13610
Onchange Atom = 0x40f08
Onclick Atom = 0x2dd07
Onclose Atom = 0x36007
Oncontextmenu Atom = 0x3720d
Oncopy Atom = 0x38506
Oncuechange Atom = 0x38b0b
Oncut Atom = 0x39605
Ondblclick Atom = 0x39b0a
Ondrag Atom = 0x3a506
Ondragend Atom = 0x3a509
Ondragenter Atom = 0x3ae0b
Ondragexit Atom = 0x3b90a
Ondragleave Atom = 0x3d30b
Ondragover Atom = 0x3de0a
Ondragstart Atom = 0x3e80b
Ondrop Atom = 0x3f706
Ondurationchange Atom = 0x40710
Onemptied Atom = 0x3fe09
Onended Atom = 0x41707
Onerror Atom = 0x41e07
Onfocus Atom = 0x42507
Onhashchange Atom = 0x4310c
Oninput Atom = 0x43d07
Oninvalid Atom = 0x44909
Onkeydown Atom = 0x45209
Onkeypress Atom = 0x45f0a
Onkeyup Atom = 0x47407
Onlanguagechange Atom = 0x48110
Onload Atom = 0x49106
Onloadeddata Atom = 0x4910c
Onloadedmetadata Atom = 0x4a410
Onloadend Atom = 0x4ba09
Onloadstart Atom = 0x4c30b
Onmessage Atom = 0x4ce09
Onmessageerror Atom = 0x4ce0e
Onmousedown Atom = 0x4dc0b
Onmouseenter Atom = 0x4e70c
Onmouseleave Atom = 0x4f30c
Onmousemove Atom = 0x4ff0b
Onmouseout Atom = 0x50a0a
Onmouseover Atom = 0x5170b
Onmouseup Atom = 0x52209
Onmousewheel Atom = 0x5300c
Onoffline Atom = 0x53c09
Ononline Atom = 0x54508
Onpagehide Atom = 0x54d0a
Onpageshow Atom = 0x5670a
Onpaste Atom = 0x57307
Onpause Atom = 0x58e07
Onplay Atom = 0x59806
Onplaying Atom = 0x59809
Onpopstate Atom = 0x5a10a
Onprogress Atom = 0x5ab0a
Onratechange Atom = 0x5c80c
Onrejectionhandled Atom = 0x5d412
Onreset Atom = 0x5e607
Onresize Atom = 0x5ed08
Onscroll Atom = 0x5fc08
Onsecuritypolicyviolation Atom = 0x60419
Onseeked Atom = 0x62508
Onseeking Atom = 0x62d09
Onselect Atom = 0x63608
Onshow Atom = 0x64006
Onsort Atom = 0x64b06
Onstalled Atom = 0x65509
Onstorage Atom = 0x65e09
Onsubmit Atom = 0x66708
Onsuspend Atom = 0x67709
Ontimeupdate Atom = 0x11a0c
Ontoggle Atom = 0x68008
Onunhandledrejection Atom = 0x68814
Onunload Atom = 0x6a708
Onvolumechange Atom = 0x6af0e
Onwaiting Atom = 0x6bd09
Onwheel Atom = 0x6c607
Open Atom = 0x55f04
Optgroup Atom = 0xe008
Optimum Atom = 0x6cd07
Option Atom = 0x6dd06
Output Atom = 0x51106
P Atom = 0xc01
Param Atom = 0xc05
Pattern Atom = 0x4f07
Picture Atom = 0x9707
Ping Atom = 0xe704
Placeholder Atom = 0xfb0b
Plaintext Atom = 0x19e09
Playsinline Atom = 0x10a0b
Poster Atom = 0x2b706
Pre Atom = 0x46403
Preload Atom = 0x47a07
Progress Atom = 0x5ad08
Prompt Atom = 0x52a06
Public Atom = 0x57a06
Q Atom = 0x7701
Radiogroup Atom = 0x30a
Readonly Atom = 0x34b08
Referrerpolicy Atom = 0x3c50e
Rel Atom = 0x47b03
Required Atom = 0x23408
Reversed Atom = 0x9c08
Rows Atom = 0x3a04
Rowspan Atom = 0x3a07
Rp Atom = 0x22402
Rt Atom = 0x17b02
Ruby Atom = 0xac04
S Atom = 0x2501
Samp Atom = 0x4c04
Sandbox Atom = 0xf307
Scope Atom = 0x67105
Scoped Atom = 0x67106
Script Atom = 0x20006
Seamless Atom = 0x36508
Section Atom = 0x5bd07
Select Atom = 0x63806
Selected Atom = 0x63808
Shape Atom = 0x1d505
Size Atom = 0x5f104
Sizes Atom = 0x5f105
Slot Atom = 0x1df04
Small Atom = 0x1ee05
Sortable Atom = 0x64d08
Sorted Atom = 0x32b06
Source Atom = 0x36c06
Spacer Atom = 0x42b06
Span Atom = 0x3d04
Spellcheck Atom = 0x4680a
Src Atom = 0x5b403
Srcdoc Atom = 0x5b406
Srclang Atom = 0x5f507
Srcset Atom = 0x6f306
Start Atom = 0x3ee05
Step Atom = 0x57704
Strike Atom = 0x7a06
Strong Atom = 0x31506
Style Atom = 0x6f905
Sub Atom = 0x66903
Summary Atom = 0x6fe07
Sup Atom = 0x70503
Svg Atom = 0x70803
System Atom = 0x70b06
Tabindex Atom = 0x4b208
Table Atom = 0x58905
Target Atom = 0x2ac06
Tbody Atom = 0x2705
Td Atom = 0x5e02
Template Atom = 0x70e08
Textarea Atom = 0x34608
Tfoot Atom = 0xb205
Th Atom = 0x13f02
Thead Atom = 0x32405
Time Atom = 0x11c04
Title Atom = 0xca05
Tr Atom = 0x7402
Track Atom = 0x17c05
Translate Atom = 0x1a609
Tt Atom = 0x5102
Type Atom = 0x8104
Typemustmatch Atom = 0x2780d
U Atom = 0xb01
Ul Atom = 0x6602
Updateviacache Atom = 0x1200e
Usemap Atom = 0x59206
Value Atom = 0x1505
Var Atom = 0x15603
Video Atom = 0x2d905
Wbr Atom = 0x57003
Width Atom = 0x64505
Workertype Atom = 0x7160a
Wrap Atom = 0x72004
Xmp Atom = 0xf903
)
const hash0 = 0x81cdf10e
const maxAtomLen = 25
var table = [1 << 9]Atom{
0x1: 0x8e0a, // mediagroup
0x2: 0x2cc04, // lang
0x4: 0x2c09, // accesskey
0x5: 0x5708, // frameset
0x7: 0x63608, // onselect
0x8: 0x70b06, // system
0xa: 0x64505, // width
0xc: 0x2710b, // formenctype
0xd: 0x10102, // ol
0xe: 0x38b0b, // oncuechange
0x10: 0x13403, // bdo
0x11: 0xcf05, // audio
0x12: 0x18309, // draggable
0x14: 0x2d905, // video
0x15: 0x29902, // mn
0x16: 0x37b04, // menu
0x17: 0x2b706, // poster
0x19: 0xb306, // footer
0x1a: 0x29006, // method
0x1b: 0x2a008, // datetime
0x1c: 0x17607, // onabort
0x1d: 0x1200e, // updateviacache
0x1e: 0xb905, // async
0x1f: 0x49106, // onload
0x21: 0xd308, // oncancel
0x22: 0x62508, // onseeked
0x23: 0x2ea05, // image
0x24: 0x5d412, // onrejectionhandled
0x26: 0x15d04, // link
0x27: 0x51106, // output
0x28: 0x32504, // head
0x29: 0x4f30c, // onmouseleave
0x2a: 0x57307, // onpaste
0x2b: 0x59809, // onplaying
0x2c: 0x1b407, // colspan
0x2f: 0x1af05, // color
0x30: 0x5f104, // size
0x31: 0x2d00a, // http-equiv
0x33: 0x601, // i
0x34: 0x54d0a, // onpagehide
0x35: 0x68814, // onunhandledrejection
0x37: 0x41e07, // onerror
0x3a: 0x11508, // basefont
0x3f: 0x1303, // nav
0x40: 0x18004, // kind
0x41: 0x34b08, // readonly
0x42: 0x2f006, // mglyph
0x44: 0x11102, // li
0x46: 0x2bd06, // hidden
0x47: 0x70803, // svg
0x48: 0x57704, // step
0x49: 0x22709, // integrity
0x4a: 0x57a06, // public
0x4c: 0x19703, // col
0x4d: 0x1680a, // blockquote
0x4e: 0x34302, // h5
0x50: 0x5ad08, // progress
0x51: 0x5f105, // sizes
0x52: 0x33902, // h4
0x56: 0x32405, // thead
0x57: 0x7e07, // keytype
0x58: 0x5ab0a, // onprogress
0x59: 0x43f09, // inputmode
0x5a: 0x3a509, // ondragend
0x5d: 0x39605, // oncut
0x5e: 0x42b06, // spacer
0x5f: 0x19708, // colgroup
0x62: 0x14e02, // is
0x65: 0xb902, // as
0x66: 0x53c09, // onoffline
0x67: 0x32b06, // sorted
0x69: 0x48110, // onlanguagechange
0x6c: 0x4310c, // onhashchange
0x6d: 0xa604, // name
0x6e: 0xb205, // tfoot
0x6f: 0x55504, // desc
0x70: 0x33103, // max
0x72: 0x1da06, // coords
0x73: 0x2f502, // h3
0x74: 0x6e10e, // onbeforeunload
0x75: 0x3a04, // rows
0x76: 0x63806, // select
0x77: 0xa805, // meter
0x78: 0x37f06, // itemid
0x79: 0x5300c, // onmousewheel
0x7a: 0x5b406, // srcdoc
0x7d: 0x17c05, // track
0x7f: 0x30708, // itemtype
0x82: 0x6302, // mo
0x83: 0x40f08, // onchange
0x84: 0x32507, // headers
0x85: 0x5c80c, // onratechange
0x86: 0x60419, // onsecuritypolicyviolation
0x88: 0x49908, // datalist
0x89: 0x4dc0b, // onmousedown
0x8a: 0x1df04, // slot
0x8b: 0x4a410, // onloadedmetadata
0x8c: 0x1a06, // accept
0x8d: 0x25006, // object
0x91: 0x6af0e, // onvolumechange
0x92: 0x2107, // charset
0x93: 0x25e13, // onautocompleteerror
0x94: 0x6913, // allowpaymentrequest
0x95: 0x2804, // body
0x96: 0xc407, // default
0x97: 0x63808, // selected
0x98: 0x20604, // face
0x99: 0x1d505, // shape
0x9b: 0x68008, // ontoggle
0x9e: 0x64702, // dt
0x9f: 0x6d904, // mark
0xa1: 0xb01, // u
0xa4: 0x6a708, // onunload
0xa5: 0xde04, // loop
0xa6: 0x14d08, // disabled
0xaa: 0x41707, // onended
0xab: 0x6d30a, // malignmark
0xad: 0x67709, // onsuspend
0xae: 0x34505, // mtext
0xaf: 0x64b06, // onsort
0xb0: 0x55908, // itemprop
0xb3: 0x66d09, // itemscope
0xb4: 0x15c05, // blink
0xb6: 0x3a506, // ondrag
0xb7: 0x6602, // ul
0xb8: 0x25604, // form
0xb9: 0xf307, // sandbox
0xba: 0x5705, // frame
0xbb: 0x1505, // value
0xbc: 0x65e09, // onstorage
0xc0: 0x17b02, // rt
0xc2: 0x202, // br
0xc3: 0x20e08, // fieldset
0xc4: 0x2780d, // typemustmatch
0xc5: 0x6108, // nomodule
0xc6: 0x4007, // noembed
0xc7: 0x69a0d, // onbeforeprint
0xc8: 0x17206, // button
0xc9: 0x2dd07, // onclick
0xca: 0x6fe07, // summary
0xcd: 0xac04, // ruby
0xce: 0x5b905, // class
0xcf: 0x3e80b, // ondragstart
0xd0: 0x21907, // caption
0xd4: 0x850e, // allowusermedia
0xd5: 0x4c30b, // onloadstart
0xd9: 0x15403, // div
0xda: 0x49d04, // list
0xdb: 0x32204, // math
0xdc: 0x43f05, // input
0xdf: 0x3de0a, // ondragover
0xe0: 0x2c602, // h2
0xe2: 0x19e09, // plaintext
0xe4: 0x4e70c, // onmouseenter
0xe7: 0x46d07, // checked
0xe8: 0x46403, // pre
0xea: 0x35308, // multiple
0xeb: 0x16103, // bdi
0xec: 0x33109, // maxlength
0xed: 0x7701, // q
0xee: 0x61b0a, // onauxclick
0xf0: 0x57003, // wbr
0xf2: 0x11504, // base
0xf3: 0x6dd06, // option
0xf5: 0x40710, // ondurationchange
0xf7: 0x5508, // noframes
0xf9: 0x3f908, // dropzone
0xfb: 0x67105, // scope
0xfc: 0x9c08, // reversed
0xfd: 0x3ae0b, // ondragenter
0xfe: 0x3ee05, // start
0xff: 0xf903, // xmp
0x100: 0x5f507, // srclang
0x101: 0x2ef03, // img
0x104: 0x101, // b
0x105: 0x23c03, // for
0x106: 0xc105, // aside
0x107: 0x43d07, // oninput
0x108: 0x34a04, // area
0x109: 0x28c0a, // formmethod
0x10a: 0x72004, // wrap
0x10c: 0x22402, // rp
0x10d: 0x45f0a, // onkeypress
0x10e: 0x5102, // tt
0x110: 0x33b02, // mi
0x111: 0x35b05, // muted
0x112: 0xb003, // alt
0x113: 0x19004, // code
0x114: 0x4202, // em
0x115: 0x3b90a, // ondragexit
0x117: 0x3d04, // span
0x119: 0x30f08, // manifest
0x11a: 0x37b08, // menuitem
0x11b: 0x57f07, // content
0x11d: 0x6bd09, // onwaiting
0x11f: 0x4ba09, // onloadend
0x121: 0x3720d, // oncontextmenu
0x123: 0x5c206, // onblur
0x124: 0x3f007, // article
0x125: 0xa303, // dir
0x126: 0xe704, // ping
0x127: 0x23408, // required
0x128: 0x44909, // oninvalid
0x129: 0x6d405, // align
0x12b: 0x57e04, // icon
0x12c: 0x64902, // h6
0x12d: 0x1b404, // cols
0x12e: 0x2160a, // figcaption
0x12f: 0x45209, // onkeydown
0x130: 0x66708, // onsubmit
0x131: 0x13609, // oncanplay
0x132: 0x70503, // sup
0x133: 0xc01, // p
0x135: 0x3fe09, // onemptied
0x136: 0x38506, // oncopy
0x137: 0x55804, // cite
0x138: 0x39b0a, // ondblclick
0x13a: 0x4ff0b, // onmousemove
0x13c: 0x66903, // sub
0x13d: 0x47b03, // rel
0x13e: 0xe008, // optgroup
0x142: 0x3a07, // rowspan
0x143: 0x36c06, // source
0x144: 0x1fe08, // noscript
0x145: 0x55f04, // open
0x146: 0x1ec03, // ins
0x147: 0x23c0d, // foreignObject
0x148: 0x5a10a, // onpopstate
0x14a: 0x27507, // enctype
0x14b: 0x25e0e, // onautocomplete
0x14c: 0x34608, // textarea
0x14e: 0x2600c, // autocomplete
0x14f: 0x14002, // hr
0x150: 0x1ce08, // controls
0x151: 0xc302, // id
0x153: 0x21e0c, // onafterprint
0x155: 0x2490d, // foreignobject
0x156: 0x31b07, // marquee
0x157: 0x58e07, // onpause
0x158: 0x5e202, // dl
0x159: 0x12c06, // height
0x15a: 0x33b03, // min
0x15b: 0xa307, // dirname
0x15c: 0x1a609, // translate
0x15d: 0x13004, // html
0x15e: 0x33b09, // minlength
0x15f: 0x47a07, // preload
0x160: 0x70e08, // template
0x161: 0x3d30b, // ondragleave
0x164: 0x5b403, // src
0x165: 0x31506, // strong
0x167: 0x4c04, // samp
0x168: 0x6ed07, // address
0x169: 0x54508, // ononline
0x16b: 0xfb0b, // placeholder
0x16c: 0x2ac06, // target
0x16d: 0x1ee05, // small
0x16e: 0x6c607, // onwheel
0x16f: 0x1b90a, // annotation
0x170: 0x4680a, // spellcheck
0x171: 0x4607, // details
0x172: 0xbd06, // canvas
0x173: 0xeb09, // autofocus
0x174: 0xc05, // param
0x176: 0x45708, // download
0x177: 0x44603, // del
0x178: 0x36007, // onclose
0x179: 0x16003, // kbd
0x17a: 0x30106, // applet
0x17b: 0x2c804, // href
0x17c: 0x5ed08, // onresize
0x17e: 0x4910c, // onloadeddata
0x180: 0x7402, // tr
0x181: 0x2a80a, // formtarget
0x182: 0xca05, // title
0x183: 0x6f905, // style
0x184: 0x7a06, // strike
0x185: 0x59206, // usemap
0x186: 0x2e406, // iframe
0x187: 0x1004, // main
0x189: 0x9707, // picture
0x18c: 0x2fe05, // ismap
0x18e: 0x49904, // data
0x18f: 0xda05, // label
0x191: 0x3c50e, // referrerpolicy
0x192: 0x13f02, // th
0x194: 0x52a06, // prompt
0x195: 0x5bd07, // section
0x197: 0x6cd07, // optimum
0x198: 0x2c304, // high
0x199: 0x14502, // h1
0x19a: 0x65509, // onstalled
0x19b: 0x15603, // var
0x19c: 0x11c04, // time
0x19e: 0x67002, // ms
0x19f: 0x32506, // header
0x1a0: 0x4ce09, // onmessage
0x1a1: 0x56205, // nonce
0x1a2: 0x2560a, // formaction
0x1a3: 0x20806, // center
0x1a4: 0x3704, // nobr
0x1a5: 0x58905, // table
0x1a6: 0x49d07, // listing
0x1a7: 0x18a06, // legend
0x1a9: 0x28309, // challenge
0x1aa: 0x23006, // figure
0x1ab: 0x8e05, // media
0x1ae: 0x8104, // type
0x1af: 0x11904, // font
0x1b0: 0x4ce0e, // onmessageerror
0x1b1: 0x36508, // seamless
0x1b2: 0x5f03, // dfn
0x1b3: 0x19205, // defer
0x1b4: 0x6b03, // low
0x1b5: 0x62d09, // onseeking
0x1b6: 0x5170b, // onmouseover
0x1b7: 0x29a0a, // novalidate
0x1b8: 0x7160a, // workertype
0x1ba: 0x3c107, // itemref
0x1bd: 0x1, // a
0x1be: 0x30003, // map
0x1bf: 0x11a0c, // ontimeupdate
0x1c0: 0x14707, // bgsound
0x1c1: 0x3206, // keygen
0x1c2: 0x2705, // tbody
0x1c5: 0x64006, // onshow
0x1c7: 0x2501, // s
0x1c8: 0x4f07, // pattern
0x1cc: 0x13610, // oncanplaythrough
0x1ce: 0x2bf02, // dd
0x1cf: 0x6f306, // srcset
0x1d0: 0x15903, // big
0x1d2: 0x64d08, // sortable
0x1d3: 0x47407, // onkeyup
0x1d5: 0x59806, // onplay
0x1d7: 0x4ac04, // meta
0x1d8: 0x3f706, // ondrop
0x1da: 0x5fc08, // onscroll
0x1db: 0x1e30b, // crossorigin
0x1dc: 0x5670a, // onpageshow
0x1dd: 0x4, // abbr
0x1de: 0x5e02, // td
0x1df: 0x57f0f, // contenteditable
0x1e0: 0x25a06, // action
0x1e1: 0x10a0b, // playsinline
0x1e2: 0x42507, // onfocus
0x1e3: 0x2c808, // hreflang
0x1e5: 0x50a0a, // onmouseout
0x1e6: 0x5e607, // onreset
0x1e7: 0x10608, // autoplay
0x1ea: 0x67106, // scoped
0x1ec: 0x30a, // radiogroup
0x1ee: 0x3740b, // contextmenu
0x1ef: 0x52209, // onmouseup
0x1f1: 0x2b206, // hgroup
0x1f2: 0x1f00f, // allowfullscreen
0x1f3: 0x4b208, // tabindex
0x1f6: 0x2f707, // isindex
0x1f7: 0x1a0e, // accept-charset
0x1f8: 0x2960e, // formnovalidate
0x1fb: 0x1b90e, // annotation-xml
0x1fc: 0x4205, // embed
0x1fd: 0x20006, // script
0x1fe: 0x16206, // dialog
0x1ff: 0x1c707, // command
}
const atomText = "abbradiogrouparamainavalueaccept-charsetbodyaccesskeygenobro" +
"wspanoembedetailsampatternoframesetdfnomoduleallowpaymentreq" +
"uestrikeytypeallowusermediagroupictureversedirnameterubyaltf" +
"ooterasyncanvasidefaultitleaudioncancelabelooptgroupingautof" +
"ocusandboxmplaceholderautoplaysinlinebasefontimeupdateviacac" +
"heightmlbdoncanplaythrough1bgsoundisabledivarbigblinkbdialog" +
"blockquotebuttonabortrackindraggablegendcodefercolgrouplaint" +
"extranslatecolorcolspannotation-xmlcommandcontrolshapecoords" +
"lotcrossoriginsmallowfullscreenoscriptfacenterfieldsetfigcap" +
"tionafterprintegrityfigurequiredforeignObjectforeignobjectfo" +
"rmactionautocompleteerrorformenctypemustmatchallengeformmeth" +
"odformnovalidatetimeformtargethgrouposterhiddenhigh2hreflang" +
"http-equivideonclickiframeimageimglyph3isindexismappletitemt" +
"ypemanifestrongmarqueematheadersortedmaxlength4minlength5mte" +
"xtareadonlymultiplemutedoncloseamlessourceoncontextmenuitemi" +
"doncopyoncuechangeoncutondblclickondragendondragenterondrage" +
"xitemreferrerpolicyondragleaveondragoverondragstarticleondro" +
"pzonemptiedondurationchangeonendedonerroronfocuspaceronhashc" +
"hangeoninputmodeloninvalidonkeydownloadonkeypresspellchecked" +
"onkeyupreloadonlanguagechangeonloadeddatalistingonloadedmeta" +
"databindexonloadendonloadstartonmessageerroronmousedownonmou" +
"seenteronmouseleaveonmousemoveonmouseoutputonmouseoveronmous" +
"eupromptonmousewheelonofflineononlineonpagehidescitempropeno" +
"nceonpageshowbronpastepublicontenteditableonpausemaponplayin" +
"gonpopstateonprogressrcdoclassectionbluronratechangeonreject" +
"ionhandledonresetonresizesrclangonscrollonsecuritypolicyviol" +
"ationauxclickonseekedonseekingonselectedonshowidth6onsortabl" +
"eonstalledonstorageonsubmitemscopedonsuspendontoggleonunhand" +
"ledrejectionbeforeprintonunloadonvolumechangeonwaitingonwhee" +
"loptimumalignmarkoptionbeforeunloaddressrcsetstylesummarysup" +
"svgsystemplateworkertypewrap"

373
vendor/golang.org/x/net/html/atom/table_test.go generated vendored Normal file
View file

@ -0,0 +1,373 @@
// Code generated by go generate gen.go; DO NOT EDIT.
//go:generate go run gen.go -test
package atom
var testAtomList = []string{
"a",
"abbr",
"accept",
"accept-charset",
"accesskey",
"action",
"address",
"align",
"allowfullscreen",
"allowpaymentrequest",
"allowusermedia",
"alt",
"annotation",
"annotation-xml",
"applet",
"area",
"article",
"as",
"aside",
"async",
"audio",
"autocomplete",
"autofocus",
"autoplay",
"b",
"base",
"basefont",
"bdi",
"bdo",
"bgsound",
"big",
"blink",
"blockquote",
"body",
"br",
"button",
"canvas",
"caption",
"center",
"challenge",
"charset",
"checked",
"cite",
"class",
"code",
"col",
"colgroup",
"color",
"cols",
"colspan",
"command",
"content",
"contenteditable",
"contextmenu",
"controls",
"coords",
"crossorigin",
"data",
"datalist",
"datetime",
"dd",
"default",
"defer",
"del",
"desc",
"details",
"dfn",
"dialog",
"dir",
"dirname",
"disabled",
"div",
"dl",
"download",
"draggable",
"dropzone",
"dt",
"em",
"embed",
"enctype",
"face",
"fieldset",
"figcaption",
"figure",
"font",
"footer",
"for",
"foreignObject",
"foreignobject",
"form",
"formaction",
"formenctype",
"formmethod",
"formnovalidate",
"formtarget",
"frame",
"frameset",
"h1",
"h2",
"h3",
"h4",
"h5",
"h6",
"head",
"header",
"headers",
"height",
"hgroup",
"hidden",
"high",
"hr",
"href",
"hreflang",
"html",
"http-equiv",
"i",
"icon",
"id",
"iframe",
"image",
"img",
"input",
"inputmode",
"ins",
"integrity",
"is",
"isindex",
"ismap",
"itemid",
"itemprop",
"itemref",
"itemscope",
"itemtype",
"kbd",
"keygen",
"keytype",
"kind",
"label",
"lang",
"legend",
"li",
"link",
"list",
"listing",
"loop",
"low",
"main",
"malignmark",
"manifest",
"map",
"mark",
"marquee",
"math",
"max",
"maxlength",
"media",
"mediagroup",
"menu",
"menuitem",
"meta",
"meter",
"method",
"mglyph",
"mi",
"min",
"minlength",
"mn",
"mo",
"ms",
"mtext",
"multiple",
"muted",
"name",
"nav",
"nobr",
"noembed",
"noframes",
"nomodule",
"nonce",
"noscript",
"novalidate",
"object",
"ol",
"onabort",
"onafterprint",
"onautocomplete",
"onautocompleteerror",
"onauxclick",
"onbeforeprint",
"onbeforeunload",
"onblur",
"oncancel",
"oncanplay",
"oncanplaythrough",
"onchange",
"onclick",
"onclose",
"oncontextmenu",
"oncopy",
"oncuechange",
"oncut",
"ondblclick",
"ondrag",
"ondragend",
"ondragenter",
"ondragexit",
"ondragleave",
"ondragover",
"ondragstart",
"ondrop",
"ondurationchange",
"onemptied",
"onended",
"onerror",
"onfocus",
"onhashchange",
"oninput",
"oninvalid",
"onkeydown",
"onkeypress",
"onkeyup",
"onlanguagechange",
"onload",
"onloadeddata",
"onloadedmetadata",
"onloadend",
"onloadstart",
"onmessage",
"onmessageerror",
"onmousedown",
"onmouseenter",
"onmouseleave",
"onmousemove",
"onmouseout",
"onmouseover",
"onmouseup",
"onmousewheel",
"onoffline",
"ononline",
"onpagehide",
"onpageshow",
"onpaste",
"onpause",
"onplay",
"onplaying",
"onpopstate",
"onprogress",
"onratechange",
"onrejectionhandled",
"onreset",
"onresize",
"onscroll",
"onsecuritypolicyviolation",
"onseeked",
"onseeking",
"onselect",
"onshow",
"onsort",
"onstalled",
"onstorage",
"onsubmit",
"onsuspend",
"ontimeupdate",
"ontoggle",
"onunhandledrejection",
"onunload",
"onvolumechange",
"onwaiting",
"onwheel",
"open",
"optgroup",
"optimum",
"option",
"output",
"p",
"param",
"pattern",
"picture",
"ping",
"placeholder",
"plaintext",
"playsinline",
"poster",
"pre",
"preload",
"progress",
"prompt",
"public",
"q",
"radiogroup",
"readonly",
"referrerpolicy",
"rel",
"required",
"reversed",
"rows",
"rowspan",
"rp",
"rt",
"ruby",
"s",
"samp",
"sandbox",
"scope",
"scoped",
"script",
"seamless",
"section",
"select",
"selected",
"shape",
"size",
"sizes",
"slot",
"small",
"sortable",
"sorted",
"source",
"spacer",
"span",
"spellcheck",
"src",
"srcdoc",
"srclang",
"srcset",
"start",
"step",
"strike",
"strong",
"style",
"sub",
"summary",
"sup",
"svg",
"system",
"tabindex",
"table",
"target",
"tbody",
"td",
"template",
"textarea",
"tfoot",
"th",
"thead",
"time",
"title",
"tr",
"track",
"translate",
"tt",
"type",
"typemustmatch",
"u",
"ul",
"updateviacache",
"usemap",
"value",
"var",
"video",
"wbr",
"width",
"workertype",
"wrap",
"xmp",
}

257
vendor/golang.org/x/net/html/charset/charset.go generated vendored Normal file
View file

@ -0,0 +1,257 @@
// Copyright 2013 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 charset provides common text encodings for HTML documents.
//
// The mapping from encoding labels to encodings is defined at
// https://encoding.spec.whatwg.org/.
package charset // import "golang.org/x/net/html/charset"
import (
"bytes"
"fmt"
"io"
"mime"
"strings"
"unicode/utf8"
"golang.org/x/net/html"
"golang.org/x/text/encoding"
"golang.org/x/text/encoding/charmap"
"golang.org/x/text/encoding/htmlindex"
"golang.org/x/text/transform"
)
// Lookup returns the encoding with the specified label, and its canonical
// name. It returns nil and the empty string if label is not one of the
// standard encodings for HTML. Matching is case-insensitive and ignores
// leading and trailing whitespace. Encoders will use HTML escape sequences for
// runes that are not supported by the character set.
func Lookup(label string) (e encoding.Encoding, name string) {
e, err := htmlindex.Get(label)
if err != nil {
return nil, ""
}
name, _ = htmlindex.Name(e)
return &htmlEncoding{e}, name
}
type htmlEncoding struct{ encoding.Encoding }
func (h *htmlEncoding) NewEncoder() *encoding.Encoder {
// HTML requires a non-terminating legacy encoder. We use HTML escapes to
// substitute unsupported code points.
return encoding.HTMLEscapeUnsupported(h.Encoding.NewEncoder())
}
// DetermineEncoding determines the encoding of an HTML document by examining
// up to the first 1024 bytes of content and the declared Content-Type.
//
// See http://www.whatwg.org/specs/web-apps/current-work/multipage/parsing.html#determining-the-character-encoding
func DetermineEncoding(content []byte, contentType string) (e encoding.Encoding, name string, certain bool) {
if len(content) > 1024 {
content = content[:1024]
}
for _, b := range boms {
if bytes.HasPrefix(content, b.bom) {
e, name = Lookup(b.enc)
return e, name, true
}
}
if _, params, err := mime.ParseMediaType(contentType); err == nil {
if cs, ok := params["charset"]; ok {
if e, name = Lookup(cs); e != nil {
return e, name, true
}
}
}
if len(content) > 0 {
e, name = prescan(content)
if e != nil {
return e, name, false
}
}
// Try to detect UTF-8.
// First eliminate any partial rune at the end.
for i := len(content) - 1; i >= 0 && i > len(content)-4; i-- {
b := content[i]
if b < 0x80 {
break
}
if utf8.RuneStart(b) {
content = content[:i]
break
}
}
hasHighBit := false
for _, c := range content {
if c >= 0x80 {
hasHighBit = true
break
}
}
if hasHighBit && utf8.Valid(content) {
return encoding.Nop, "utf-8", false
}
// TODO: change default depending on user's locale?
return charmap.Windows1252, "windows-1252", false
}
// NewReader returns an io.Reader that converts the content of r to UTF-8.
// It calls DetermineEncoding to find out what r's encoding is.
func NewReader(r io.Reader, contentType string) (io.Reader, error) {
preview := make([]byte, 1024)
n, err := io.ReadFull(r, preview)
switch {
case err == io.ErrUnexpectedEOF:
preview = preview[:n]
r = bytes.NewReader(preview)
case err != nil:
return nil, err
default:
r = io.MultiReader(bytes.NewReader(preview), r)
}
if e, _, _ := DetermineEncoding(preview, contentType); e != encoding.Nop {
r = transform.NewReader(r, e.NewDecoder())
}
return r, nil
}
// NewReaderLabel returns a reader that converts from the specified charset to
// UTF-8. It uses Lookup to find the encoding that corresponds to label, and
// returns an error if Lookup returns nil. It is suitable for use as
// encoding/xml.Decoder's CharsetReader function.
func NewReaderLabel(label string, input io.Reader) (io.Reader, error) {
e, _ := Lookup(label)
if e == nil {
return nil, fmt.Errorf("unsupported charset: %q", label)
}
return transform.NewReader(input, e.NewDecoder()), nil
}
func prescan(content []byte) (e encoding.Encoding, name string) {
z := html.NewTokenizer(bytes.NewReader(content))
for {
switch z.Next() {
case html.ErrorToken:
return nil, ""
case html.StartTagToken, html.SelfClosingTagToken:
tagName, hasAttr := z.TagName()
if !bytes.Equal(tagName, []byte("meta")) {
continue
}
attrList := make(map[string]bool)
gotPragma := false
const (
dontKnow = iota
doNeedPragma
doNotNeedPragma
)
needPragma := dontKnow
name = ""
e = nil
for hasAttr {
var key, val []byte
key, val, hasAttr = z.TagAttr()
ks := string(key)
if attrList[ks] {
continue
}
attrList[ks] = true
for i, c := range val {
if 'A' <= c && c <= 'Z' {
val[i] = c + 0x20
}
}
switch ks {
case "http-equiv":
if bytes.Equal(val, []byte("content-type")) {
gotPragma = true
}
case "content":
if e == nil {
name = fromMetaElement(string(val))
if name != "" {
e, name = Lookup(name)
if e != nil {
needPragma = doNeedPragma
}
}
}
case "charset":
e, name = Lookup(string(val))
needPragma = doNotNeedPragma
}
}
if needPragma == dontKnow || needPragma == doNeedPragma && !gotPragma {
continue
}
if strings.HasPrefix(name, "utf-16") {
name = "utf-8"
e = encoding.Nop
}
if e != nil {
return e, name
}
}
}
}
func fromMetaElement(s string) string {
for s != "" {
csLoc := strings.Index(s, "charset")
if csLoc == -1 {
return ""
}
s = s[csLoc+len("charset"):]
s = strings.TrimLeft(s, " \t\n\f\r")
if !strings.HasPrefix(s, "=") {
continue
}
s = s[1:]
s = strings.TrimLeft(s, " \t\n\f\r")
if s == "" {
return ""
}
if q := s[0]; q == '"' || q == '\'' {
s = s[1:]
closeQuote := strings.IndexRune(s, rune(q))
if closeQuote == -1 {
return ""
}
return s[:closeQuote]
}
end := strings.IndexAny(s, "; \t\n\f\r")
if end == -1 {
end = len(s)
}
return s[:end]
}
return ""
}
var boms = []struct {
bom []byte
enc string
}{
{[]byte{0xfe, 0xff}, "utf-16be"},
{[]byte{0xff, 0xfe}, "utf-16le"},
{[]byte{0xef, 0xbb, 0xbf}, "utf-8"},
}

237
vendor/golang.org/x/net/html/charset/charset_test.go generated vendored Normal file
View file

@ -0,0 +1,237 @@
// Copyright 2013 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 charset
import (
"bytes"
"encoding/xml"
"io/ioutil"
"runtime"
"strings"
"testing"
"golang.org/x/text/transform"
)
func transformString(t transform.Transformer, s string) (string, error) {
r := transform.NewReader(strings.NewReader(s), t)
b, err := ioutil.ReadAll(r)
return string(b), err
}
type testCase struct {
utf8, other, otherEncoding string
}
// testCases for encoding and decoding.
var testCases = []testCase{
{"Résumé", "Résumé", "utf8"},
{"Résumé", "R\xe9sum\xe9", "latin1"},
{"これは漢字です。", "S0\x8c0o0\"oW[g0Y0\x020", "UTF-16LE"},
{"これは漢字です。", "0S0\x8c0oo\"[W0g0Y0\x02", "UTF-16BE"},
{"Hello, world", "Hello, world", "ASCII"},
{"Gdańsk", "Gda\xf1sk", "ISO-8859-2"},
{"Ââ Čč Đđ Ŋŋ Õõ Šš Žž Åå Ää", "\xc2\xe2 \xc8\xe8 \xa9\xb9 \xaf\xbf \xd5\xf5 \xaa\xba \xac\xbc \xc5\xe5 \xc4\xe4", "ISO-8859-10"},
{"สำหรับ", "\xca\xd3\xcb\xc3\u047a", "ISO-8859-11"},
{"latviešu", "latvie\xf0u", "ISO-8859-13"},
{"Seònaid", "Se\xf2naid", "ISO-8859-14"},
{"€1 is cheap", "\xa41 is cheap", "ISO-8859-15"},
{"românește", "rom\xe2ne\xbate", "ISO-8859-16"},
{"nutraĵo", "nutra\xbco", "ISO-8859-3"},
{"Kalâdlit", "Kal\xe2dlit", "ISO-8859-4"},
{"русский", "\xe0\xe3\xe1\xe1\xda\xd8\xd9", "ISO-8859-5"},
{"ελληνικά", "\xe5\xeb\xeb\xe7\xed\xe9\xea\xdc", "ISO-8859-7"},
{"Kağan", "Ka\xf0an", "ISO-8859-9"},
{"Résumé", "R\x8esum\x8e", "macintosh"},
{"Gdańsk", "Gda\xf1sk", "windows-1250"},
{"русский", "\xf0\xf3\xf1\xf1\xea\xe8\xe9", "windows-1251"},
{"Résumé", "R\xe9sum\xe9", "windows-1252"},
{"ελληνικά", "\xe5\xeb\xeb\xe7\xed\xe9\xea\xdc", "windows-1253"},
{"Kağan", "Ka\xf0an", "windows-1254"},
{"עִבְרִית", "\xf2\xc4\xe1\xc0\xf8\xc4\xe9\xfa", "windows-1255"},
{"العربية", "\xc7\xe1\xda\xd1\xc8\xed\xc9", "windows-1256"},
{"latviešu", "latvie\xf0u", "windows-1257"},
{"Việt", "Vi\xea\xf2t", "windows-1258"},
{"สำหรับ", "\xca\xd3\xcb\xc3\u047a", "windows-874"},
{"русский", "\xd2\xd5\xd3\xd3\xcb\xc9\xca", "KOI8-R"},
{"українська", "\xd5\xcb\xd2\xc1\xa7\xce\xd3\xd8\xcb\xc1", "KOI8-U"},
{"Hello 常用國字標準字體表", "Hello \xb1`\xa5\u03b0\xea\xa6r\xbc\u0437\u01e6r\xc5\xe9\xaa\xed", "big5"},
{"Hello 常用國字標準字體表", "Hello \xb3\xa3\xd3\xc3\x87\xf8\xd7\xd6\x98\xcb\x9c\xca\xd7\xd6\xf3\x77\xb1\xed", "gbk"},
{"Hello 常用國字標準字體表", "Hello \xb3\xa3\xd3\xc3\x87\xf8\xd7\xd6\x98\xcb\x9c\xca\xd7\xd6\xf3\x77\xb1\xed", "gb18030"},
{"עִבְרִית", "\x81\x30\xfb\x30\x81\x30\xf6\x34\x81\x30\xf9\x33\x81\x30\xf6\x30\x81\x30\xfb\x36\x81\x30\xf6\x34\x81\x30\xfa\x31\x81\x30\xfb\x38", "gb18030"},
{"㧯", "\x82\x31\x89\x38", "gb18030"},
{"これは漢字です。", "\x82\xb1\x82\xea\x82\xcd\x8a\xbf\x8e\x9a\x82\xc5\x82\xb7\x81B", "SJIS"},
{"Hello, 世界!", "Hello, \x90\xa2\x8aE!", "SJIS"},
{"ｲｳｴｵｶ", "\xb2\xb3\xb4\xb5\xb6", "SJIS"},
{"これは漢字です。", "\xa4\xb3\xa4\xec\xa4\u03f4\xc1\xbb\xfa\xa4\u01e4\xb9\xa1\xa3", "EUC-JP"},
{"Hello, 世界!", "Hello, \x1b$B@$3&\x1b(B!", "ISO-2022-JP"},
{"다음과 같은 조건을 따라야 합니다: 저작자표시", "\xb4\xd9\xc0\xbd\xb0\xfa \xb0\xb0\xc0\xba \xc1\xb6\xb0\xc7\xc0\xbb \xb5\xfb\xb6\xf3\xbe\xdf \xc7մϴ\xd9: \xc0\xfa\xc0\xdb\xc0\xdaǥ\xbd\xc3", "EUC-KR"},
}
func TestDecode(t *testing.T) {
testCases := append(testCases, []testCase{
// Replace multi-byte maximum subpart of ill-formed subsequence with
// single replacement character (WhatWG requirement).
{"Rés\ufffdumé", "Rés\xe1\x80umé", "utf8"},
}...)
for _, tc := range testCases {
e, _ := Lookup(tc.otherEncoding)
if e == nil {
t.Errorf("%s: not found", tc.otherEncoding)
continue
}
s, err := transformString(e.NewDecoder(), tc.other)
if err != nil {
t.Errorf("%s: decode %q: %v", tc.otherEncoding, tc.other, err)
continue
}
if s != tc.utf8 {
t.Errorf("%s: got %q, want %q", tc.otherEncoding, s, tc.utf8)
}
}
}
func TestEncode(t *testing.T) {
testCases := append(testCases, []testCase{
// Use Go-style replacement.
{"Rés\xe1\x80umé", "Rés\ufffd\ufffdumé", "utf8"},
// U+0144 LATIN SMALL LETTER N WITH ACUTE not supported by encoding.
{"Gdańsk", "Gda&#324;sk", "ISO-8859-11"},
{"\ufffd", "&#65533;", "ISO-8859-11"},
{"a\xe1\x80b", "a&#65533;&#65533;b", "ISO-8859-11"},
}...)
for _, tc := range testCases {
e, _ := Lookup(tc.otherEncoding)
if e == nil {
t.Errorf("%s: not found", tc.otherEncoding)
continue
}
s, err := transformString(e.NewEncoder(), tc.utf8)
if err != nil {
t.Errorf("%s: encode %q: %s", tc.otherEncoding, tc.utf8, err)
continue
}
if s != tc.other {
t.Errorf("%s: got %q, want %q", tc.otherEncoding, s, tc.other)
}
}
}
var sniffTestCases = []struct {
filename, declared, want string
}{
{"HTTP-charset.html", "text/html; charset=iso-8859-15", "iso-8859-15"},
{"UTF-16LE-BOM.html", "", "utf-16le"},
{"UTF-16BE-BOM.html", "", "utf-16be"},
{"meta-content-attribute.html", "text/html", "iso-8859-15"},
{"meta-charset-attribute.html", "text/html", "iso-8859-15"},
{"No-encoding-declaration.html", "text/html", "utf-8"},
{"HTTP-vs-UTF-8-BOM.html", "text/html; charset=iso-8859-15", "utf-8"},
{"HTTP-vs-meta-content.html", "text/html; charset=iso-8859-15", "iso-8859-15"},
{"HTTP-vs-meta-charset.html", "text/html; charset=iso-8859-15", "iso-8859-15"},
{"UTF-8-BOM-vs-meta-content.html", "text/html", "utf-8"},
{"UTF-8-BOM-vs-meta-charset.html", "text/html", "utf-8"},
}
func TestSniff(t *testing.T) {
switch runtime.GOOS {
case "nacl": // platforms that don't permit direct file system access
t.Skipf("not supported on %q", runtime.GOOS)
}
for _, tc := range sniffTestCases {
content, err := ioutil.ReadFile("testdata/" + tc.filename)
if err != nil {
t.Errorf("%s: error reading file: %v", tc.filename, err)
continue
}
_, name, _ := DetermineEncoding(content, tc.declared)
if name != tc.want {
t.Errorf("%s: got %q, want %q", tc.filename, name, tc.want)
continue
}
}
}
func TestReader(t *testing.T) {
switch runtime.GOOS {
case "nacl": // platforms that don't permit direct file system access
t.Skipf("not supported on %q", runtime.GOOS)
}
for _, tc := range sniffTestCases {
content, err := ioutil.ReadFile("testdata/" + tc.filename)
if err != nil {
t.Errorf("%s: error reading file: %v", tc.filename, err)
continue
}
r, err := NewReader(bytes.NewReader(content), tc.declared)
if err != nil {
t.Errorf("%s: error creating reader: %v", tc.filename, err)
continue
}
got, err := ioutil.ReadAll(r)
if err != nil {
t.Errorf("%s: error reading from charset.NewReader: %v", tc.filename, err)
continue
}
e, _ := Lookup(tc.want)
want, err := ioutil.ReadAll(transform.NewReader(bytes.NewReader(content), e.NewDecoder()))
if err != nil {
t.Errorf("%s: error decoding with hard-coded charset name: %v", tc.filename, err)
continue
}
if !bytes.Equal(got, want) {
t.Errorf("%s: got %q, want %q", tc.filename, got, want)
continue
}
}
}
var metaTestCases = []struct {
meta, want string
}{
{"", ""},
{"text/html", ""},
{"text/html; charset utf-8", ""},
{"text/html; charset=latin-2", "latin-2"},
{"text/html; charset; charset = utf-8", "utf-8"},
{`charset="big5"`, "big5"},
{"charset='shift_jis'", "shift_jis"},
}
func TestFromMeta(t *testing.T) {
for _, tc := range metaTestCases {
got := fromMetaElement(tc.meta)
if got != tc.want {
t.Errorf("%q: got %q, want %q", tc.meta, got, tc.want)
}
}
}
func TestXML(t *testing.T) {
const s = "<?xml version=\"1.0\" encoding=\"windows-1252\"?><a><Word>r\xe9sum\xe9</Word></a>"
d := xml.NewDecoder(strings.NewReader(s))
d.CharsetReader = NewReaderLabel
var a struct {
Word string
}
err := d.Decode(&a)
if err != nil {
t.Fatalf("Decode: %v", err)
}
want := "résumé"
if a.Word != want {
t.Errorf("got %q, want %q", a.Word, want)
}
}

104
vendor/golang.org/x/net/html/const.go generated vendored Normal file
View file

@ -0,0 +1,104 @@
// Copyright 2011 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 html
// Section 12.2.3.2 of the HTML5 specification says "The following elements
// have varying levels of special parsing rules".
// https://html.spec.whatwg.org/multipage/syntax.html#the-stack-of-open-elements
var isSpecialElementMap = map[string]bool{
"address": true,
"applet": true,
"area": true,
"article": true,
"aside": true,
"base": true,
"basefont": true,
"bgsound": true,
"blockquote": true,
"body": true,
"br": true,
"button": true,
"caption": true,
"center": true,
"col": true,
"colgroup": true,
"dd": true,
"details": true,
"dir": true,
"div": true,
"dl": true,
"dt": true,
"embed": true,
"fieldset": true,
"figcaption": true,
"figure": true,
"footer": true,
"form": true,
"frame": true,
"frameset": true,
"h1": true,
"h2": true,
"h3": true,
"h4": true,
"h5": true,
"h6": true,
"head": true,
"header": true,
"hgroup": true,
"hr": true,
"html": true,
"iframe": true,
"img": true,
"input": true,
"isindex": true, // The 'isindex' element has been removed, but keep it for backwards compatibility.
"keygen": true,
"li": true,
"link": true,
"listing": true,
"main": true,
"marquee": true,
"menu": true,
"meta": true,
"nav": true,
"noembed": true,
"noframes": true,
"noscript": true,
"object": true,
"ol": true,
"p": true,
"param": true,
"plaintext": true,
"pre": true,
"script": true,
"section": true,
"select": true,
"source": true,
"style": true,
"summary": true,
"table": true,
"tbody": true,
"td": true,
"template": true,
"textarea": true,
"tfoot": true,
"th": true,
"thead": true,
"title": true,
"tr": true,
"track": true,
"ul": true,
"wbr": true,
"xmp": true,
}
func isSpecialElement(element *Node) bool {
switch element.Namespace {
case "", "html":
return isSpecialElementMap[element.Data]
case "svg":
return element.Data == "foreignObject"
}
return false
}

106
vendor/golang.org/x/net/html/doc.go generated vendored Normal file
View file

@ -0,0 +1,106 @@
// Copyright 2010 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 html implements an HTML5-compliant tokenizer and parser.
Tokenization is done by creating a Tokenizer for an io.Reader r. It is the
caller's responsibility to ensure that r provides UTF-8 encoded HTML.
z := html.NewTokenizer(r)
Given a Tokenizer z, the HTML is tokenized by repeatedly calling z.Next(),
which parses the next token and returns its type, or an error:
for {
tt := z.Next()
if tt == html.ErrorToken {
// ...
return ...
}
// Process the current token.
}
There are two APIs for retrieving the current token. The high-level API is to
call Token; the low-level API is to call Text or TagName / TagAttr. Both APIs
allow optionally calling Raw after Next but before Token, Text, TagName, or
TagAttr. In EBNF notation, the valid call sequence per token is:
Next {Raw} [ Token | Text | TagName {TagAttr} ]
Token returns an independent data structure that completely describes a token.
Entities (such as "&lt;") are unescaped, tag names and attribute keys are
lower-cased, and attributes are collected into a []Attribute. For example:
for {
if z.Next() == html.ErrorToken {
// Returning io.EOF indicates success.
return z.Err()
}
emitToken(z.Token())
}
The low-level API performs fewer allocations and copies, but the contents of
the []byte values returned by Text, TagName and TagAttr may change on the next
call to Next. For example, to extract an HTML page's anchor text:
depth := 0
for {
tt := z.Next()
switch tt {
case ErrorToken:
return z.Err()
case TextToken:
if depth > 0 {
// emitBytes should copy the []byte it receives,
// if it doesn't process it immediately.
emitBytes(z.Text())
}
case StartTagToken, EndTagToken:
tn, _ := z.TagName()
if len(tn) == 1 && tn[0] == 'a' {
if tt == StartTagToken {
depth++
} else {
depth--
}
}
}
}
Parsing is done by calling Parse with an io.Reader, which returns the root of
the parse tree (the document element) as a *Node. It is the caller's
responsibility to ensure that the Reader provides UTF-8 encoded HTML. For
example, to process each anchor node in depth-first order:
doc, err := html.Parse(r)
if err != nil {
// ...
}
var f func(*html.Node)
f = func(n *html.Node) {
if n.Type == html.ElementNode && n.Data == "a" {
// Do something with n...
}
for c := n.FirstChild; c != nil; c = c.NextSibling {
f(c)
}
}
f(doc)
The relevant specifications include:
https://html.spec.whatwg.org/multipage/syntax.html and
https://html.spec.whatwg.org/multipage/syntax.html#tokenization
*/
package html // import "golang.org/x/net/html"
// The tokenization algorithm implemented by this package is not a line-by-line
// transliteration of the relatively verbose state-machine in the WHATWG
// specification. A more direct approach is used instead, where the program
// counter implies the state, such as whether it is tokenizing a tag or a text
// node. Specification compliance is verified by checking expected and actual
// outputs over a test suite rather than aiming for algorithmic fidelity.
// TODO(nigeltao): Does a DOM API belong in this package or a separate one?
// TODO(nigeltao): How does parsing interact with a JavaScript engine?

156
vendor/golang.org/x/net/html/doctype.go generated vendored Normal file
View file

@ -0,0 +1,156 @@
// Copyright 2011 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 html
import (
"strings"
)
// parseDoctype parses the data from a DoctypeToken into a name,
// public identifier, and system identifier. It returns a Node whose Type
// is DoctypeNode, whose Data is the name, and which has attributes
// named "system" and "public" for the two identifiers if they were present.
// quirks is whether the document should be parsed in "quirks mode".
func parseDoctype(s string) (n *Node, quirks bool) {
n = &Node{Type: DoctypeNode}
// Find the name.
space := strings.IndexAny(s, whitespace)
if space == -1 {
space = len(s)
}
n.Data = s[:space]
// The comparison to "html" is case-sensitive.
if n.Data != "html" {
quirks = true
}
n.Data = strings.ToLower(n.Data)
s = strings.TrimLeft(s[space:], whitespace)
if len(s) < 6 {
// It can't start with "PUBLIC" or "SYSTEM".
// Ignore the rest of the string.
return n, quirks || s != ""
}
key := strings.ToLower(s[:6])
s = s[6:]
for key == "public" || key == "system" {
s = strings.TrimLeft(s, whitespace)
if s == "" {
break
}
quote := s[0]
if quote != '"' && quote != '\'' {
break
}
s = s[1:]
q := strings.IndexRune(s, rune(quote))
var id string
if q == -1 {
id = s
s = ""
} else {
id = s[:q]
s = s[q+1:]
}
n.Attr = append(n.Attr, Attribute{Key: key, Val: id})
if key == "public" {
key = "system"
} else {
key = ""
}
}
if key != "" || s != "" {
quirks = true
} else if len(n.Attr) > 0 {
if n.Attr[0].Key == "public" {
public := strings.ToLower(n.Attr[0].Val)
switch public {
case "-//w3o//dtd w3 html strict 3.0//en//", "-/w3d/dtd html 4.0 transitional/en", "html":
quirks = true
default:
for _, q := range quirkyIDs {
if strings.HasPrefix(public, q) {
quirks = true
break
}
}
}
// The following two public IDs only cause quirks mode if there is no system ID.
if len(n.Attr) == 1 && (strings.HasPrefix(public, "-//w3c//dtd html 4.01 frameset//") ||
strings.HasPrefix(public, "-//w3c//dtd html 4.01 transitional//")) {
quirks = true
}
}
if lastAttr := n.Attr[len(n.Attr)-1]; lastAttr.Key == "system" &&
strings.ToLower(lastAttr.Val) == "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd" {
quirks = true
}
}
return n, quirks
}
// quirkyIDs is a list of public doctype identifiers that cause a document
// to be interpreted in quirks mode. The identifiers should be in lower case.
var quirkyIDs = []string{
"+//silmaril//dtd html pro v0r11 19970101//",
"-//advasoft ltd//dtd html 3.0 aswedit + extensions//",
"-//as//dtd html 3.0 aswedit + extensions//",
"-//ietf//dtd html 2.0 level 1//",
"-//ietf//dtd html 2.0 level 2//",
"-//ietf//dtd html 2.0 strict level 1//",
"-//ietf//dtd html 2.0 strict level 2//",
"-//ietf//dtd html 2.0 strict//",
"-//ietf//dtd html 2.0//",
"-//ietf//dtd html 2.1e//",
"-//ietf//dtd html 3.0//",
"-//ietf//dtd html 3.2 final//",
"-//ietf//dtd html 3.2//",
"-//ietf//dtd html 3//",
"-//ietf//dtd html level 0//",
"-//ietf//dtd html level 1//",
"-//ietf//dtd html level 2//",
"-//ietf//dtd html level 3//",
"-//ietf//dtd html strict level 0//",
"-//ietf//dtd html strict level 1//",
"-//ietf//dtd html strict level 2//",
"-//ietf//dtd html strict level 3//",
"-//ietf//dtd html strict//",
"-//ietf//dtd html//",
"-//metrius//dtd metrius presentational//",
"-//microsoft//dtd internet explorer 2.0 html strict//",
"-//microsoft//dtd internet explorer 2.0 html//",
"-//microsoft//dtd internet explorer 2.0 tables//",
"-//microsoft//dtd internet explorer 3.0 html strict//",
"-//microsoft//dtd internet explorer 3.0 html//",
"-//microsoft//dtd internet explorer 3.0 tables//",
"-//netscape comm. corp.//dtd html//",
"-//netscape comm. corp.//dtd strict html//",
"-//o'reilly and associates//dtd html 2.0//",
"-//o'reilly and associates//dtd html extended 1.0//",
"-//o'reilly and associates//dtd html extended relaxed 1.0//",
"-//softquad software//dtd hotmetal pro 6.0::19990601::extensions to html 4.0//",
"-//softquad//dtd hotmetal pro 4.0::19971010::extensions to html 4.0//",
"-//spyglass//dtd html 2.0 extended//",
"-//sq//dtd html 2.0 hotmetal + extensions//",
"-//sun microsystems corp.//dtd hotjava html//",
"-//sun microsystems corp.//dtd hotjava strict html//",
"-//w3c//dtd html 3 1995-03-24//",
"-//w3c//dtd html 3.2 draft//",
"-//w3c//dtd html 3.2 final//",
"-//w3c//dtd html 3.2//",
"-//w3c//dtd html 3.2s draft//",
"-//w3c//dtd html 4.0 frameset//",
"-//w3c//dtd html 4.0 transitional//",
"-//w3c//dtd html experimental 19960712//",
"-//w3c//dtd html experimental 970421//",
"-//w3c//dtd w3 html//",
"-//w3o//dtd w3 html 3.0//",
"-//webtechs//dtd mozilla html 2.0//",
"-//webtechs//dtd mozilla html//",
}

2253
vendor/golang.org/x/net/html/entity.go generated vendored Normal file
View file

File diff suppressed because it is too large Load diff

29
vendor/golang.org/x/net/html/entity_test.go generated vendored Normal file
View file

@ -0,0 +1,29 @@
// Copyright 2010 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 html
import (
"testing"
"unicode/utf8"
)
func TestEntityLength(t *testing.T) {
// We verify that the length of UTF-8 encoding of each value is <= 1 + len(key).
// The +1 comes from the leading "&". This property implies that the length of
// unescaped text is <= the length of escaped text.
for k, v := range entity {
if 1+len(k) < utf8.RuneLen(v) {
t.Error("escaped entity &" + k + " is shorter than its UTF-8 encoding " + string(v))
}
if len(k) > longestEntityWithoutSemicolon && k[len(k)-1] != ';' {
t.Errorf("entity name %s is %d characters, but longestEntityWithoutSemicolon=%d", k, len(k), longestEntityWithoutSemicolon)
}
}
for k, v := range entity2 {
if 1+len(k) < utf8.RuneLen(v[0])+utf8.RuneLen(v[1]) {
t.Error("escaped entity &" + k + " is shorter than its UTF-8 encoding " + string(v[0]) + string(v[1]))
}
}
}

258
vendor/golang.org/x/net/html/escape.go generated vendored Normal file
View file

@ -0,0 +1,258 @@
// Copyright 2010 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 html
import (
"bytes"
"strings"
"unicode/utf8"
)
// These replacements permit compatibility with old numeric entities that
// assumed Windows-1252 encoding.
// https://html.spec.whatwg.org/multipage/syntax.html#consume-a-character-reference
var replacementTable = [...]rune{
'\u20AC', // First entry is what 0x80 should be replaced with.
'\u0081',
'\u201A',
'\u0192',
'\u201E',
'\u2026',
'\u2020',
'\u2021',
'\u02C6',
'\u2030',
'\u0160',
'\u2039',
'\u0152',
'\u008D',
'\u017D',
'\u008F',
'\u0090',
'\u2018',
'\u2019',
'\u201C',
'\u201D',
'\u2022',
'\u2013',
'\u2014',
'\u02DC',
'\u2122',
'\u0161',
'\u203A',
'\u0153',
'\u009D',
'\u017E',
'\u0178', // Last entry is 0x9F.
// 0x00->'\uFFFD' is handled programmatically.
// 0x0D->'\u000D' is a no-op.
}
// unescapeEntity reads an entity like "&lt;" from b[src:] and writes the
// corresponding "<" to b[dst:], returning the incremented dst and src cursors.
// Precondition: b[src] == '&' && dst <= src.
// attribute should be true if parsing an attribute value.
func unescapeEntity(b []byte, dst, src int, attribute bool) (dst1, src1 int) {
// https://html.spec.whatwg.org/multipage/syntax.html#consume-a-character-reference
// i starts at 1 because we already know that s[0] == '&'.
i, s := 1, b[src:]
if len(s) <= 1 {
b[dst] = b[src]
return dst + 1, src + 1
}
if s[i] == '#' {
if len(s) <= 3 { // We need to have at least "&#.".
b[dst] = b[src]
return dst + 1, src + 1
}
i++
c := s[i]
hex := false
if c == 'x' || c == 'X' {
hex = true
i++
}
x := '\x00'
for i < len(s) {
c = s[i]
i++
if hex {
if '0' <= c && c <= '9' {
x = 16*x + rune(c) - '0'
continue
} else if 'a' <= c && c <= 'f' {
x = 16*x + rune(c) - 'a' + 10
continue
} else if 'A' <= c && c <= 'F' {
x = 16*x + rune(c) - 'A' + 10
continue
}
} else if '0' <= c && c <= '9' {
x = 10*x + rune(c) - '0'
continue
}
if c != ';' {
i--
}
break
}
if i <= 3 { // No characters matched.
b[dst] = b[src]
return dst + 1, src + 1
}
if 0x80 <= x && x <= 0x9F {
// Replace characters from Windows-1252 with UTF-8 equivalents.
x = replacementTable[x-0x80]
} else if x == 0 || (0xD800 <= x && x <= 0xDFFF) || x > 0x10FFFF {
// Replace invalid characters with the replacement character.
x = '\uFFFD'
}
return dst + utf8.EncodeRune(b[dst:], x), src + i
}
// Consume the maximum number of characters possible, with the
// consumed characters matching one of the named references.
for i < len(s) {
c := s[i]
i++
// Lower-cased characters are more common in entities, so we check for them first.
if 'a' <= c && c <= 'z' || 'A' <= c && c <= 'Z' || '0' <= c && c <= '9' {
continue
}
if c != ';' {
i--
}
break
}
entityName := string(s[1:i])
if entityName == "" {
// No-op.
} else if attribute && entityName[len(entityName)-1] != ';' && len(s) > i && s[i] == '=' {
// No-op.
} else if x := entity[entityName]; x != 0 {
return dst + utf8.EncodeRune(b[dst:], x), src + i
} else if x := entity2[entityName]; x[0] != 0 {
dst1 := dst + utf8.EncodeRune(b[dst:], x[0])
return dst1 + utf8.EncodeRune(b[dst1:], x[1]), src + i
} else if !attribute {
maxLen := len(entityName) - 1
if maxLen > longestEntityWithoutSemicolon {
maxLen = longestEntityWithoutSemicolon
}
for j := maxLen; j > 1; j-- {
if x := entity[entityName[:j]]; x != 0 {
return dst + utf8.EncodeRune(b[dst:], x), src + j + 1
}
}
}
dst1, src1 = dst+i, src+i
copy(b[dst:dst1], b[src:src1])
return dst1, src1
}
// unescape unescapes b's entities in-place, so that "a&lt;b" becomes "a<b".
// attribute should be true if parsing an attribute value.
func unescape(b []byte, attribute bool) []byte {
for i, c := range b {
if c == '&' {
dst, src := unescapeEntity(b, i, i, attribute)
for src < len(b) {
c := b[src]
if c == '&' {
dst, src = unescapeEntity(b, dst, src, attribute)
} else {
b[dst] = c
dst, src = dst+1, src+1
}
}
return b[0:dst]
}
}
return b
}
// lower lower-cases the A-Z bytes in b in-place, so that "aBc" becomes "abc".
func lower(b []byte) []byte {
for i, c := range b {
if 'A' <= c && c <= 'Z' {
b[i] = c + 'a' - 'A'
}
}
return b
}
const escapedChars = "&'<>\"\r"
func escape(w writer, s string) error {
i := strings.IndexAny(s, escapedChars)
for i != -1 {
if _, err := w.WriteString(s[:i]); err != nil {
return err
}
var esc string
switch s[i] {
case '&':
esc = "&amp;"
case '\'':
// "&#39;" is shorter than "&apos;" and apos was not in HTML until HTML5.
esc = "&#39;"
case '<':
esc = "&lt;"
case '>':
esc = "&gt;"
case '"':
// "&#34;" is shorter than "&quot;".
esc = "&#34;"
case '\r':
esc = "&#13;"
default:
panic("unrecognized escape character")
}
s = s[i+1:]
if _, err := w.WriteString(esc); err != nil {
return err
}
i = strings.IndexAny(s, escapedChars)
}
_, err := w.WriteString(s)
return err
}
// EscapeString escapes special characters like "<" to become "&lt;". It
// escapes only five such characters: <, >, &, ' and ".
// UnescapeString(EscapeString(s)) == s always holds, but the converse isn't
// always true.
func EscapeString(s string) string {
if strings.IndexAny(s, escapedChars) == -1 {
return s
}
var buf bytes.Buffer
escape(&buf, s)
return buf.String()
}
// UnescapeString unescapes entities like "&lt;" to become "<". It unescapes a
// larger range of entities than EscapeString escapes. For example, "&aacute;"
// unescapes to "á", as does "&#225;" and "&xE1;".
// UnescapeString(EscapeString(s)) == s always holds, but the converse isn't
// always true.
func UnescapeString(s string) string {
for _, c := range s {
if c == '&' {
return string(unescape([]byte(s), false))
}
}
return s
}

97
vendor/golang.org/x/net/html/escape_test.go generated vendored Normal file
View file

@ -0,0 +1,97 @@
// Copyright 2013 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 html
import "testing"
type unescapeTest struct {
// A short description of the test case.
desc string
// The HTML text.
html string
// The unescaped text.
unescaped string
}
var unescapeTests = []unescapeTest{
// Handle no entities.
{
"copy",
"A\ttext\nstring",
"A\ttext\nstring",
},
// Handle simple named entities.
{
"simple",
"&amp; &gt; &lt;",
"& > <",
},
// Handle hitting the end of the string.
{
"stringEnd",
"&amp &amp",
"& &",
},
// Handle entities with two codepoints.
{
"multiCodepoint",
"text &gesl; blah",
"text \u22db\ufe00 blah",
},
// Handle decimal numeric entities.
{
"decimalEntity",
"Delta = &#916; ",
"Delta = Δ ",
},
// Handle hexadecimal numeric entities.
{
"hexadecimalEntity",
"Lambda = &#x3bb; = &#X3Bb ",
"Lambda = λ = λ ",
},
// Handle numeric early termination.
{
"numericEnds",
"&# &#x &#128;43 &copy = &#169f = &#xa9",
"&# &#x €43 © = ©f = ©",
},
// Handle numeric ISO-8859-1 entity replacements.
{
"numericReplacements",
"Footnote&#x87;",
"Footnote‡",
},
}
func TestUnescape(t *testing.T) {
for _, tt := range unescapeTests {
unescaped := UnescapeString(tt.html)
if unescaped != tt.unescaped {
t.Errorf("TestUnescape %s: want %q, got %q", tt.desc, tt.unescaped, unescaped)
}
}
}
func TestUnescapeEscape(t *testing.T) {
ss := []string{
``,
`abc def`,
`a & b`,
`a&amp;b`,
`a &amp b`,
`&quot;`,
`"`,
`"<&>"`,
`&quot;&lt;&amp;&gt;&quot;`,
`3&5==1 && 0<1, "0&lt;1", a+acute=&aacute;`,
`The special characters are: <, >, &, ' and "`,
}
for _, s := range ss {
if got := UnescapeString(EscapeString(s)); got != s {
t.Errorf("got %q want %q", got, s)
}
}
}

40
vendor/golang.org/x/net/html/example_test.go generated vendored Normal file
View file

@ -0,0 +1,40 @@
// 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.
// This example demonstrates parsing HTML data and walking the resulting tree.
package html_test
import (
"fmt"
"log"
"strings"
"golang.org/x/net/html"
)
func ExampleParse() {
s := `<p>Links:</p><ul><li><a href="foo">Foo</a><li><a href="/bar/baz">BarBaz</a></ul>`
doc, err := html.Parse(strings.NewReader(s))
if err != nil {
log.Fatal(err)
}
var f func(*html.Node)
f = func(n *html.Node) {
if n.Type == html.ElementNode && n.Data == "a" {
for _, a := range n.Attr {
if a.Key == "href" {
fmt.Println(a.Val)
break
}
}
}
for c := n.FirstChild; c != nil; c = c.NextSibling {
f(c)
}
}
f(doc)
// Output:
// foo
// /bar/baz
}

226
vendor/golang.org/x/net/html/foreign.go generated vendored Normal file
View file

@ -0,0 +1,226 @@
// Copyright 2011 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 html
import (
"strings"
)
func adjustAttributeNames(aa []Attribute, nameMap map[string]string) {
for i := range aa {
if newName, ok := nameMap[aa[i].Key]; ok {
aa[i].Key = newName
}
}
}
func adjustForeignAttributes(aa []Attribute) {
for i, a := range aa {
if a.Key == "" || a.Key[0] != 'x' {
continue
}
switch a.Key {
case "xlink:actuate", "xlink:arcrole", "xlink:href", "xlink:role", "xlink:show",
"xlink:title", "xlink:type", "xml:base", "xml:lang", "xml:space", "xmlns:xlink":
j := strings.Index(a.Key, ":")
aa[i].Namespace = a.Key[:j]
aa[i].Key = a.Key[j+1:]
}
}
}
func htmlIntegrationPoint(n *Node) bool {
if n.Type != ElementNode {
return false
}
switch n.Namespace {
case "math":
if n.Data == "annotation-xml" {
for _, a := range n.Attr {
if a.Key == "encoding" {
val := strings.ToLower(a.Val)
if val == "text/html" || val == "application/xhtml+xml" {
return true
}
}
}
}
case "svg":
switch n.Data {
case "desc", "foreignObject", "title":
return true
}
}
return false
}
func mathMLTextIntegrationPoint(n *Node) bool {
if n.Namespace != "math" {
return false
}
switch n.Data {
case "mi", "mo", "mn", "ms", "mtext":
return true
}
return false
}
// Section 12.2.5.5.
var breakout = map[string]bool{
"b": true,
"big": true,
"blockquote": true,
"body": true,
"br": true,
"center": true,
"code": true,
"dd": true,
"div": true,
"dl": true,
"dt": true,
"em": true,
"embed": true,
"h1": true,
"h2": true,
"h3": true,
"h4": true,
"h5": true,
"h6": true,
"head": true,
"hr": true,
"i": true,
"img": true,
"li": true,
"listing": true,
"menu": true,
"meta": true,
"nobr": true,
"ol": true,
"p": true,
"pre": true,
"ruby": true,
"s": true,
"small": true,
"span": true,
"strong": true,
"strike": true,
"sub": true,
"sup": true,
"table": true,
"tt": true,
"u": true,
"ul": true,
"var": true,
}
// Section 12.2.5.5.
var svgTagNameAdjustments = map[string]string{
"altglyph": "altGlyph",
"altglyphdef": "altGlyphDef",
"altglyphitem": "altGlyphItem",
"animatecolor": "animateColor",
"animatemotion": "animateMotion",
"animatetransform": "animateTransform",
"clippath": "clipPath",
"feblend": "feBlend",
"fecolormatrix": "feColorMatrix",
"fecomponenttransfer": "feComponentTransfer",
"fecomposite": "feComposite",
"feconvolvematrix": "feConvolveMatrix",
"fediffuselighting": "feDiffuseLighting",
"fedisplacementmap": "feDisplacementMap",
"fedistantlight": "feDistantLight",
"feflood": "feFlood",
"fefunca": "feFuncA",
"fefuncb": "feFuncB",
"fefuncg": "feFuncG",
"fefuncr": "feFuncR",
"fegaussianblur": "feGaussianBlur",
"feimage": "feImage",
"femerge": "feMerge",
"femergenode": "feMergeNode",
"femorphology": "feMorphology",
"feoffset": "feOffset",
"fepointlight": "fePointLight",
"fespecularlighting": "feSpecularLighting",
"fespotlight": "feSpotLight",
"fetile": "feTile",
"feturbulence": "feTurbulence",
"foreignobject": "foreignObject",
"glyphref": "glyphRef",
"lineargradient": "linearGradient",
"radialgradient": "radialGradient",
"textpath": "textPath",
}
// Section 12.2.5.1
var mathMLAttributeAdjustments = map[string]string{
"definitionurl": "definitionURL",
}
var svgAttributeAdjustments = map[string]string{
"attributename": "attributeName",
"attributetype": "attributeType",
"basefrequency": "baseFrequency",
"baseprofile": "baseProfile",
"calcmode": "calcMode",
"clippathunits": "clipPathUnits",
"contentscripttype": "contentScriptType",
"contentstyletype": "contentStyleType",
"diffuseconstant": "diffuseConstant",
"edgemode": "edgeMode",
"externalresourcesrequired": "externalResourcesRequired",
"filterres": "filterRes",
"filterunits": "filterUnits",
"glyphref": "glyphRef",
"gradienttransform": "gradientTransform",
"gradientunits": "gradientUnits",
"kernelmatrix": "kernelMatrix",
"kernelunitlength": "kernelUnitLength",
"keypoints": "keyPoints",
"keysplines": "keySplines",
"keytimes": "keyTimes",
"lengthadjust": "lengthAdjust",
"limitingconeangle": "limitingConeAngle",
"markerheight": "markerHeight",
"markerunits": "markerUnits",
"markerwidth": "markerWidth",
"maskcontentunits": "maskContentUnits",
"maskunits": "maskUnits",
"numoctaves": "numOctaves",
"pathlength": "pathLength",
"patterncontentunits": "patternContentUnits",
"patterntransform": "patternTransform",
"patternunits": "patternUnits",
"pointsatx": "pointsAtX",
"pointsaty": "pointsAtY",
"pointsatz": "pointsAtZ",
"preservealpha": "preserveAlpha",
"preserveaspectratio": "preserveAspectRatio",
"primitiveunits": "primitiveUnits",
"refx": "refX",
"refy": "refY",
"repeatcount": "repeatCount",
"repeatdur": "repeatDur",
"requiredextensions": "requiredExtensions",
"requiredfeatures": "requiredFeatures",
"specularconstant": "specularConstant",
"specularexponent": "specularExponent",
"spreadmethod": "spreadMethod",
"startoffset": "startOffset",
"stddeviation": "stdDeviation",
"stitchtiles": "stitchTiles",
"surfacescale": "surfaceScale",
"systemlanguage": "systemLanguage",
"tablevalues": "tableValues",
"targetx": "targetX",
"targety": "targetY",
"textlength": "textLength",
"viewbox": "viewBox",
"viewtarget": "viewTarget",
"xchannelselector": "xChannelSelector",
"ychannelselector": "yChannelSelector",
"zoomandpan": "zoomAndPan",
}

193
vendor/golang.org/x/net/html/node.go generated vendored Normal file
View file

@ -0,0 +1,193 @@
// Copyright 2011 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 html
import (
"golang.org/x/net/html/atom"
)
// A NodeType is the type of a Node.
type NodeType uint32
const (
ErrorNode NodeType = iota
TextNode
DocumentNode
ElementNode
CommentNode
DoctypeNode
scopeMarkerNode
)
// Section 12.2.3.3 says "scope markers are inserted when entering applet
// elements, buttons, object elements, marquees, table cells, and table
// captions, and are used to prevent formatting from 'leaking'".
var scopeMarker = Node{Type: scopeMarkerNode}
// A Node consists of a NodeType and some Data (tag name for element nodes,
// content for text) and are part of a tree of Nodes. Element nodes may also
// have a Namespace and contain a slice of Attributes. Data is unescaped, so
// that it looks like "a<b" rather than "a&lt;b". For element nodes, DataAtom
// is the atom for Data, or zero if Data is not a known tag name.
//
// An empty Namespace implies a "http://www.w3.org/1999/xhtml" namespace.
// Similarly, "math" is short for "http://www.w3.org/1998/Math/MathML", and
// "svg" is short for "http://www.w3.org/2000/svg".
type Node struct {
Parent, FirstChild, LastChild, PrevSibling, NextSibling *Node
Type NodeType
DataAtom atom.Atom
Data string
Namespace string
Attr []Attribute
}
// InsertBefore inserts newChild as a child of n, immediately before oldChild
// in the sequence of n's children. oldChild may be nil, in which case newChild
// is appended to the end of n's children.
//
// It will panic if newChild already has a parent or siblings.
func (n *Node) InsertBefore(newChild, oldChild *Node) {
if newChild.Parent != nil || newChild.PrevSibling != nil || newChild.NextSibling != nil {
panic("html: InsertBefore called for an attached child Node")
}
var prev, next *Node
if oldChild != nil {
prev, next = oldChild.PrevSibling, oldChild
} else {
prev = n.LastChild
}
if prev != nil {
prev.NextSibling = newChild
} else {
n.FirstChild = newChild
}
if next != nil {
next.PrevSibling = newChild
} else {
n.LastChild = newChild
}
newChild.Parent = n
newChild.PrevSibling = prev
newChild.NextSibling = next
}
// AppendChild adds a node c as a child of n.
//
// It will panic if c already has a parent or siblings.
func (n *Node) AppendChild(c *Node) {
if c.Parent != nil || c.PrevSibling != nil || c.NextSibling != nil {
panic("html: AppendChild called for an attached child Node")
}
last := n.LastChild
if last != nil {
last.NextSibling = c
} else {
n.FirstChild = c
}
n.LastChild = c
c.Parent = n
c.PrevSibling = last
}
// RemoveChild removes a node c that is a child of n. Afterwards, c will have
// no parent and no siblings.
//
// It will panic if c's parent is not n.
func (n *Node) RemoveChild(c *Node) {
if c.Parent != n {
panic("html: RemoveChild called for a non-child Node")
}
if n.FirstChild == c {
n.FirstChild = c.NextSibling
}
if c.NextSibling != nil {
c.NextSibling.PrevSibling = c.PrevSibling
}
if n.LastChild == c {
n.LastChild = c.PrevSibling
}
if c.PrevSibling != nil {
c.PrevSibling.NextSibling = c.NextSibling
}
c.Parent = nil
c.PrevSibling = nil
c.NextSibling = nil
}
// reparentChildren reparents all of src's child nodes to dst.
func reparentChildren(dst, src *Node) {
for {
child := src.FirstChild
if child == nil {
break
}
src.RemoveChild(child)
dst.AppendChild(child)
}
}
// clone returns a new node with the same type, data and attributes.
// The clone has no parent, no siblings and no children.
func (n *Node) clone() *Node {
m := &Node{
Type: n.Type,
DataAtom: n.DataAtom,
Data: n.Data,
Attr: make([]Attribute, len(n.Attr)),
}
copy(m.Attr, n.Attr)
return m
}
// nodeStack is a stack of nodes.
type nodeStack []*Node
// pop pops the stack. It will panic if s is empty.
func (s *nodeStack) pop() *Node {
i := len(*s)
n := (*s)[i-1]
*s = (*s)[:i-1]
return n
}
// top returns the most recently pushed node, or nil if s is empty.
func (s *nodeStack) top() *Node {
if i := len(*s); i > 0 {
return (*s)[i-1]
}
return nil
}
// index returns the index of the top-most occurrence of n in the stack, or -1
// if n is not present.
func (s *nodeStack) index(n *Node) int {
for i := len(*s) - 1; i >= 0; i-- {
if (*s)[i] == n {
return i
}
}
return -1
}
// insert inserts a node at the given index.
func (s *nodeStack) insert(i int, n *Node) {
(*s) = append(*s, nil)
copy((*s)[i+1:], (*s)[i:])
(*s)[i] = n
}
// remove removes a node from the stack. It is a no-op if n is not present.
func (s *nodeStack) remove(n *Node) {
i := s.index(n)
if i == -1 {
return
}
copy((*s)[i:], (*s)[i+1:])
j := len(*s) - 1
(*s)[j] = nil
*s = (*s)[:j]
}

146
vendor/golang.org/x/net/html/node_test.go generated vendored Normal file
View file

@ -0,0 +1,146 @@
// Copyright 2010 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 html
import (
"fmt"
)
// checkTreeConsistency checks that a node and its descendants are all
// consistent in their parent/child/sibling relationships.
func checkTreeConsistency(n *Node) error {
return checkTreeConsistency1(n, 0)
}
func checkTreeConsistency1(n *Node, depth int) error {
if depth == 1e4 {
return fmt.Errorf("html: tree looks like it contains a cycle")
}
if err := checkNodeConsistency(n); err != nil {
return err
}
for c := n.FirstChild; c != nil; c = c.NextSibling {
if err := checkTreeConsistency1(c, depth+1); err != nil {
return err
}
}
return nil
}
// checkNodeConsistency checks that a node's parent/child/sibling relationships
// are consistent.
func checkNodeConsistency(n *Node) error {
if n == nil {
return nil
}
nParent := 0
for p := n.Parent; p != nil; p = p.Parent {
nParent++
if nParent == 1e4 {
return fmt.Errorf("html: parent list looks like an infinite loop")
}
}
nForward := 0
for c := n.FirstChild; c != nil; c = c.NextSibling {
nForward++
if nForward == 1e6 {
return fmt.Errorf("html: forward list of children looks like an infinite loop")
}
if c.Parent != n {
return fmt.Errorf("html: inconsistent child/parent relationship")
}
}
nBackward := 0
for c := n.LastChild; c != nil; c = c.PrevSibling {
nBackward++
if nBackward == 1e6 {
return fmt.Errorf("html: backward list of children looks like an infinite loop")
}
if c.Parent != n {
return fmt.Errorf("html: inconsistent child/parent relationship")
}
}
if n.Parent != nil {
if n.Parent == n {
return fmt.Errorf("html: inconsistent parent relationship")
}
if n.Parent == n.FirstChild {
return fmt.Errorf("html: inconsistent parent/first relationship")
}
if n.Parent == n.LastChild {
return fmt.Errorf("html: inconsistent parent/last relationship")
}
if n.Parent == n.PrevSibling {
return fmt.Errorf("html: inconsistent parent/prev relationship")
}
if n.Parent == n.NextSibling {
return fmt.Errorf("html: inconsistent parent/next relationship")
}
parentHasNAsAChild := false
for c := n.Parent.FirstChild; c != nil; c = c.NextSibling {
if c == n {
parentHasNAsAChild = true
break
}
}
if !parentHasNAsAChild {
return fmt.Errorf("html: inconsistent parent/child relationship")
}
}
if n.PrevSibling != nil && n.PrevSibling.NextSibling != n {
return fmt.Errorf("html: inconsistent prev/next relationship")
}
if n.NextSibling != nil && n.NextSibling.PrevSibling != n {
return fmt.Errorf("html: inconsistent next/prev relationship")
}
if (n.FirstChild == nil) != (n.LastChild == nil) {
return fmt.Errorf("html: inconsistent first/last relationship")
}
if n.FirstChild != nil && n.FirstChild == n.LastChild {
// We have a sole child.
if n.FirstChild.PrevSibling != nil || n.FirstChild.NextSibling != nil {
return fmt.Errorf("html: inconsistent sole child's sibling relationship")
}
}
seen := map[*Node]bool{}
var last *Node
for c := n.FirstChild; c != nil; c = c.NextSibling {
if seen[c] {
return fmt.Errorf("html: inconsistent repeated child")
}
seen[c] = true
last = c
}
if last != n.LastChild {
return fmt.Errorf("html: inconsistent last relationship")
}
var first *Node
for c := n.LastChild; c != nil; c = c.PrevSibling {
if !seen[c] {
return fmt.Errorf("html: inconsistent missing child")
}
delete(seen, c)
first = c
}
if first != n.FirstChild {
return fmt.Errorf("html: inconsistent first relationship")
}
if len(seen) != 0 {
return fmt.Errorf("html: inconsistent forwards/backwards child list")
}
return nil
}

2094
vendor/golang.org/x/net/html/parse.go generated vendored Normal file
View file

File diff suppressed because it is too large Load diff

388
vendor/golang.org/x/net/html/parse_test.go generated vendored Normal file
View file

@ -0,0 +1,388 @@
// Copyright 2010 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 html
import (
"bufio"
"bytes"
"errors"
"fmt"
"io"
"io/ioutil"
"os"
"path/filepath"
"runtime"
"sort"
"strings"
"testing"
"golang.org/x/net/html/atom"
)
// readParseTest reads a single test case from r.
func readParseTest(r *bufio.Reader) (text, want, context string, err error) {
line, err := r.ReadSlice('\n')
if err != nil {
return "", "", "", err
}
var b []byte
// Read the HTML.
if string(line) != "#data\n" {
return "", "", "", fmt.Errorf(`got %q want "#data\n"`, line)
}
for {
line, err = r.ReadSlice('\n')
if err != nil {
return "", "", "", err
}
if line[0] == '#' {
break
}
b = append(b, line...)
}
text = strings.TrimSuffix(string(b), "\n")
b = b[:0]
// Skip the error list.
if string(line) != "#errors\n" {
return "", "", "", fmt.Errorf(`got %q want "#errors\n"`, line)
}
for {
line, err = r.ReadSlice('\n')
if err != nil {
return "", "", "", err
}
if line[0] == '#' {
break
}
}
if string(line) == "#document-fragment\n" {
line, err = r.ReadSlice('\n')
if err != nil {
return "", "", "", err
}
context = strings.TrimSpace(string(line))
line, err = r.ReadSlice('\n')
if err != nil {
return "", "", "", err
}
}
// Read the dump of what the parse tree should be.
if string(line) != "#document\n" {
return "", "", "", fmt.Errorf(`got %q want "#document\n"`, line)
}
inQuote := false
for {
line, err = r.ReadSlice('\n')
if err != nil && err != io.EOF {
return "", "", "", err
}
trimmed := bytes.Trim(line, "| \n")
if len(trimmed) > 0 {
if line[0] == '|' && trimmed[0] == '"' {
inQuote = true
}
if trimmed[len(trimmed)-1] == '"' && !(line[0] == '|' && len(trimmed) == 1) {
inQuote = false
}
}
if len(line) == 0 || len(line) == 1 && line[0] == '\n' && !inQuote {
break
}
b = append(b, line...)
}
return text, string(b), context, nil
}
func dumpIndent(w io.Writer, level int) {
io.WriteString(w, "| ")
for i := 0; i < level; i++ {
io.WriteString(w, " ")
}
}
type sortedAttributes []Attribute
func (a sortedAttributes) Len() int {
return len(a)
}
func (a sortedAttributes) Less(i, j int) bool {
if a[i].Namespace != a[j].Namespace {
return a[i].Namespace < a[j].Namespace
}
return a[i].Key < a[j].Key
}
func (a sortedAttributes) Swap(i, j int) {
a[i], a[j] = a[j], a[i]
}
func dumpLevel(w io.Writer, n *Node, level int) error {
dumpIndent(w, level)
switch n.Type {
case ErrorNode:
return errors.New("unexpected ErrorNode")
case DocumentNode:
return errors.New("unexpected DocumentNode")
case ElementNode:
if n.Namespace != "" {
fmt.Fprintf(w, "<%s %s>", n.Namespace, n.Data)
} else {
fmt.Fprintf(w, "<%s>", n.Data)
}
attr := sortedAttributes(n.Attr)
sort.Sort(attr)
for _, a := range attr {
io.WriteString(w, "\n")
dumpIndent(w, level+1)
if a.Namespace != "" {
fmt.Fprintf(w, `%s %s="%s"`, a.Namespace, a.Key, a.Val)
} else {
fmt.Fprintf(w, `%s="%s"`, a.Key, a.Val)
}
}
case TextNode:
fmt.Fprintf(w, `"%s"`, n.Data)
case CommentNode:
fmt.Fprintf(w, "<!-- %s -->", n.Data)
case DoctypeNode:
fmt.Fprintf(w, "<!DOCTYPE %s", n.Data)
if n.Attr != nil {
var p, s string
for _, a := range n.Attr {
switch a.Key {
case "public":
p = a.Val
case "system":
s = a.Val
}
}
if p != "" || s != "" {
fmt.Fprintf(w, ` "%s"`, p)
fmt.Fprintf(w, ` "%s"`, s)
}
}
io.WriteString(w, ">")
case scopeMarkerNode:
return errors.New("unexpected scopeMarkerNode")
default:
return errors.New("unknown node type")
}
io.WriteString(w, "\n")
for c := n.FirstChild; c != nil; c = c.NextSibling {
if err := dumpLevel(w, c, level+1); err != nil {
return err
}
}
return nil
}
func dump(n *Node) (string, error) {
if n == nil || n.FirstChild == nil {
return "", nil
}
var b bytes.Buffer
for c := n.FirstChild; c != nil; c = c.NextSibling {
if err := dumpLevel(&b, c, 0); err != nil {
return "", err
}
}
return b.String(), nil
}
const testDataDir = "testdata/webkit/"
func TestParser(t *testing.T) {
testFiles, err := filepath.Glob(testDataDir + "*.dat")
if err != nil {
t.Fatal(err)
}
for _, tf := range testFiles {
f, err := os.Open(tf)
if err != nil {
t.Fatal(err)
}
defer f.Close()
r := bufio.NewReader(f)
for i := 0; ; i++ {
text, want, context, err := readParseTest(r)
if err == io.EOF {
break
}
if err != nil {
t.Fatal(err)
}
err = testParseCase(text, want, context)
if err != nil {
t.Errorf("%s test #%d %q, %s", tf, i, text, err)
}
}
}
}
// testParseCase tests one test case from the test files. If the test does not
// pass, it returns an error that explains the failure.
// text is the HTML to be parsed, want is a dump of the correct parse tree,
// and context is the name of the context node, if any.
func testParseCase(text, want, context string) (err error) {
defer func() {
if x := recover(); x != nil {
switch e := x.(type) {
case error:
err = e
default:
err = fmt.Errorf("%v", e)
}
}
}()
var doc *Node
if context == "" {
doc, err = Parse(strings.NewReader(text))
if err != nil {
return err
}
} else {
contextNode := &Node{
Type: ElementNode,
DataAtom: atom.Lookup([]byte(context)),
Data: context,
}
nodes, err := ParseFragment(strings.NewReader(text), contextNode)
if err != nil {
return err
}
doc = &Node{
Type: DocumentNode,
}
for _, n := range nodes {
doc.AppendChild(n)
}
}
if err := checkTreeConsistency(doc); err != nil {
return err
}
got, err := dump(doc)
if err != nil {
return err
}
// Compare the parsed tree to the #document section.
if got != want {
return fmt.Errorf("got vs want:\n----\n%s----\n%s----", got, want)
}
if renderTestBlacklist[text] || context != "" {
return nil
}
// Check that rendering and re-parsing results in an identical tree.
pr, pw := io.Pipe()
go func() {
pw.CloseWithError(Render(pw, doc))
}()
doc1, err := Parse(pr)
if err != nil {
return err
}
got1, err := dump(doc1)
if err != nil {
return err
}
if got != got1 {
return fmt.Errorf("got vs got1:\n----\n%s----\n%s----", got, got1)
}
return nil
}
// Some test input result in parse trees are not 'well-formed' despite
// following the HTML5 recovery algorithms. Rendering and re-parsing such a
// tree will not result in an exact clone of that tree. We blacklist such
// inputs from the render test.
var renderTestBlacklist = map[string]bool{
// The second <a> will be reparented to the first <table>'s parent. This
// results in an <a> whose parent is an <a>, which is not 'well-formed'.
`<a><table><td><a><table></table><a></tr><a></table><b>X</b>C<a>Y`: true,
// The same thing with a <p>:
`<p><table></p>`: true,
// More cases of <a> being reparented:
`<a href="blah">aba<table><a href="foo">br<tr><td></td></tr>x</table>aoe`: true,
`<a><table><a></table><p><a><div><a>`: true,
`<a><table><td><a><table></table><a></tr><a></table><a>`: true,
// A similar reparenting situation involving <nobr>:
`<!DOCTYPE html><body><b><nobr>1<table><nobr></b><i><nobr>2<nobr></i>3`: true,
// A <plaintext> element is reparented, putting it before a table.
// A <plaintext> element can't have anything after it in HTML.
`<table><plaintext><td>`: true,
`<!doctype html><table><plaintext></plaintext>`: true,
`<!doctype html><table><tbody><plaintext></plaintext>`: true,
`<!doctype html><table><tbody><tr><plaintext></plaintext>`: true,
// A form inside a table inside a form doesn't work either.
`<!doctype html><form><table></form><form></table></form>`: true,
// A script that ends at EOF may escape its own closing tag when rendered.
`<!doctype html><script><!--<script `: true,
`<!doctype html><script><!--<script <`: true,
`<!doctype html><script><!--<script <a`: true,
`<!doctype html><script><!--<script </`: true,
`<!doctype html><script><!--<script </s`: true,
`<!doctype html><script><!--<script </script`: true,
`<!doctype html><script><!--<script </scripta`: true,
`<!doctype html><script><!--<script -`: true,
`<!doctype html><script><!--<script -a`: true,
`<!doctype html><script><!--<script -<`: true,
`<!doctype html><script><!--<script --`: true,
`<!doctype html><script><!--<script --a`: true,
`<!doctype html><script><!--<script --<`: true,
`<script><!--<script `: true,
`<script><!--<script <a`: true,
`<script><!--<script </script`: true,
`<script><!--<script </scripta`: true,
`<script><!--<script -`: true,
`<script><!--<script -a`: true,
`<script><!--<script --`: true,
`<script><!--<script --a`: true,
`<script><!--<script <`: true,
`<script><!--<script </`: true,
`<script><!--<script </s`: true,
// Reconstructing the active formatting elements results in a <plaintext>
// element that contains an <a> element.
`<!doctype html><p><a><plaintext>b`: true,
}
func TestNodeConsistency(t *testing.T) {
// inconsistentNode is a Node whose DataAtom and Data do not agree.
inconsistentNode := &Node{
Type: ElementNode,
DataAtom: atom.Frameset,
Data: "table",
}
_, err := ParseFragment(strings.NewReader("<p>hello</p>"), inconsistentNode)
if err == nil {
t.Errorf("got nil error, want non-nil")
}
}
func BenchmarkParser(b *testing.B) {
buf, err := ioutil.ReadFile("testdata/go1.html")
if err != nil {
b.Fatalf("could not read testdata/go1.html: %v", err)
}
b.SetBytes(int64(len(buf)))
runtime.GC()
b.ReportAllocs()
b.ResetTimer()
for i := 0; i < b.N; i++ {
Parse(bytes.NewBuffer(buf))
}
}

271
vendor/golang.org/x/net/html/render.go generated vendored Normal file
View file

@ -0,0 +1,271 @@
// Copyright 2011 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 html
import (
"bufio"
"errors"
"fmt"
"io"
"strings"
)
type writer interface {
io.Writer
io.ByteWriter
WriteString(string) (int, error)
}
// Render renders the parse tree n to the given writer.
//
// Rendering is done on a 'best effort' basis: calling Parse on the output of
// Render will always result in something similar to the original tree, but it
// is not necessarily an exact clone unless the original tree was 'well-formed'.
// 'Well-formed' is not easily specified; the HTML5 specification is
// complicated.
//
// Calling Parse on arbitrary input typically results in a 'well-formed' parse
// tree. However, it is possible for Parse to yield a 'badly-formed' parse tree.
// For example, in a 'well-formed' parse tree, no <a> element is a child of
// another <a> element: parsing "<a><a>" results in two sibling elements.
// Similarly, in a 'well-formed' parse tree, no <a> element is a child of a
// <table> element: parsing "<p><table><a>" results in a <p> with two sibling
// children; the <a> is reparented to the <table>'s parent. However, calling
// Parse on "<a><table><a>" does not return an error, but the result has an <a>
// element with an <a> child, and is therefore not 'well-formed'.
//
// Programmatically constructed trees are typically also 'well-formed', but it
// is possible to construct a tree that looks innocuous but, when rendered and
// re-parsed, results in a different tree. A simple example is that a solitary
// text node would become a tree containing <html>, <head> and <body> elements.
// Another example is that the programmatic equivalent of "a<head>b</head>c"
// becomes "<html><head><head/><body>abc</body></html>".
func Render(w io.Writer, n *Node) error {
if x, ok := w.(writer); ok {
return render(x, n)
}
buf := bufio.NewWriter(w)
if err := render(buf, n); err != nil {
return err
}
return buf.Flush()
}
// plaintextAbort is returned from render1 when a <plaintext> element
// has been rendered. No more end tags should be rendered after that.
var plaintextAbort = errors.New("html: internal error (plaintext abort)")
func render(w writer, n *Node) error {
err := render1(w, n)
if err == plaintextAbort {
err = nil
}
return err
}
func render1(w writer, n *Node) error {
// Render non-element nodes; these are the easy cases.
switch n.Type {
case ErrorNode:
return errors.New("html: cannot render an ErrorNode node")
case TextNode:
return escape(w, n.Data)
case DocumentNode:
for c := n.FirstChild; c != nil; c = c.NextSibling {
if err := render1(w, c); err != nil {
return err
}
}
return nil
case ElementNode:
// No-op.
case CommentNode:
if _, err := w.WriteString("<!--"); err != nil {
return err
}
if _, err := w.WriteString(n.Data); err != nil {
return err
}
if _, err := w.WriteString("-->"); err != nil {
return err
}
return nil
case DoctypeNode:
if _, err := w.WriteString("<!DOCTYPE "); err != nil {
return err
}
if _, err := w.WriteString(n.Data); err != nil {
return err
}
if n.Attr != nil {
var p, s string
for _, a := range n.Attr {
switch a.Key {
case "public":
p = a.Val
case "system":
s = a.Val
}
}
if p != "" {
if _, err := w.WriteString(" PUBLIC "); err != nil {
return err
}
if err := writeQuoted(w, p); err != nil {
return err
}
if s != "" {
if err := w.WriteByte(' '); err != nil {
return err
}
if err := writeQuoted(w, s); err != nil {
return err
}
}
} else if s != "" {
if _, err := w.WriteString(" SYSTEM "); err != nil {
return err
}
if err := writeQuoted(w, s); err != nil {
return err
}
}
}
return w.WriteByte('>')
default:
return errors.New("html: unknown node type")
}
// Render the <xxx> opening tag.
if err := w.WriteByte('<'); err != nil {
return err
}
if _, err := w.WriteString(n.Data); err != nil {
return err
}
for _, a := range n.Attr {
if err := w.WriteByte(' '); err != nil {
return err
}
if a.Namespace != "" {
if _, err := w.WriteString(a.Namespace); err != nil {
return err
}
if err := w.WriteByte(':'); err != nil {
return err
}
}
if _, err := w.WriteString(a.Key); err != nil {
return err
}
if _, err := w.WriteString(`="`); err != nil {
return err
}
if err := escape(w, a.Val); err != nil {
return err
}
if err := w.WriteByte('"'); err != nil {
return err
}
}
if voidElements[n.Data] {
if n.FirstChild != nil {
return fmt.Errorf("html: void element <%s> has child nodes", n.Data)
}
_, err := w.WriteString("/>")
return err
}
if err := w.WriteByte('>'); err != nil {
return err
}
// Add initial newline where there is danger of a newline beging ignored.
if c := n.FirstChild; c != nil && c.Type == TextNode && strings.HasPrefix(c.Data, "\n") {
switch n.Data {
case "pre", "listing", "textarea":
if err := w.WriteByte('\n'); err != nil {
return err
}
}
}
// Render any child nodes.
switch n.Data {
case "iframe", "noembed", "noframes", "noscript", "plaintext", "script", "style", "xmp":
for c := n.FirstChild; c != nil; c = c.NextSibling {
if c.Type == TextNode {
if _, err := w.WriteString(c.Data); err != nil {
return err
}
} else {
if err := render1(w, c); err != nil {
return err
}
}
}
if n.Data == "plaintext" {
// Don't render anything else. <plaintext> must be the
// last element in the file, with no closing tag.
return plaintextAbort
}
default:
for c := n.FirstChild; c != nil; c = c.NextSibling {
if err := render1(w, c); err != nil {
return err
}
}
}
// Render the </xxx> closing tag.
if _, err := w.WriteString("</"); err != nil {
return err
}
if _, err := w.WriteString(n.Data); err != nil {
return err
}
return w.WriteByte('>')
}
// writeQuoted writes s to w surrounded by quotes. Normally it will use double
// quotes, but if s contains a double quote, it will use single quotes.
// It is used for writing the identifiers in a doctype declaration.
// In valid HTML, they can't contain both types of quotes.
func writeQuoted(w writer, s string) error {
var q byte = '"'
if strings.Contains(s, `"`) {
q = '\''
}
if err := w.WriteByte(q); err != nil {
return err
}
if _, err := w.WriteString(s); err != nil {
return err
}
if err := w.WriteByte(q); err != nil {
return err
}
return nil
}
// Section 12.1.2, "Elements", gives this list of void elements. Void elements
// are those that can't have any contents.
var voidElements = map[string]bool{
"area": true,
"base": true,
"br": true,
"col": true,
"command": true,
"embed": true,
"hr": true,
"img": true,
"input": true,
"keygen": true,
"link": true,
"meta": true,
"param": true,
"source": true,
"track": true,
"wbr": true,
}

156
vendor/golang.org/x/net/html/render_test.go generated vendored Normal file
View file

@ -0,0 +1,156 @@
// Copyright 2010 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 html
import (
"bytes"
"testing"
)
func TestRenderer(t *testing.T) {
nodes := [...]*Node{
0: {
Type: ElementNode,
Data: "html",
},
1: {
Type: ElementNode,
Data: "head",
},
2: {
Type: ElementNode,
Data: "body",
},
3: {
Type: TextNode,
Data: "0<1",
},
4: {
Type: ElementNode,
Data: "p",
Attr: []Attribute{
{
Key: "id",
Val: "A",
},
{
Key: "foo",
Val: `abc"def`,
},
},
},
5: {
Type: TextNode,
Data: "2",
},
6: {
Type: ElementNode,
Data: "b",
Attr: []Attribute{
{
Key: "empty",
Val: "",
},
},
},
7: {
Type: TextNode,
Data: "3",
},
8: {
Type: ElementNode,
Data: "i",
Attr: []Attribute{
{
Key: "backslash",
Val: `\`,
},
},
},
9: {
Type: TextNode,
Data: "&4",
},
10: {
Type: TextNode,
Data: "5",
},
11: {
Type: ElementNode,
Data: "blockquote",
},
12: {
Type: ElementNode,
Data: "br",
},
13: {
Type: TextNode,
Data: "6",
},
}
// Build a tree out of those nodes, based on a textual representation.
// Only the ".\t"s are significant. The trailing HTML-like text is
// just commentary. The "0:" prefixes are for easy cross-reference with
// the nodes array.
treeAsText := [...]string{
0: `<html>`,
1: `. <head>`,
2: `. <body>`,
3: `. . "0&lt;1"`,
4: `. . <p id="A" foo="abc&#34;def">`,
5: `. . . "2"`,
6: `. . . <b empty="">`,
7: `. . . . "3"`,
8: `. . . <i backslash="\">`,
9: `. . . . "&amp;4"`,
10: `. . "5"`,
11: `. . <blockquote>`,
12: `. . <br>`,
13: `. . "6"`,
}
if len(nodes) != len(treeAsText) {
t.Fatal("len(nodes) != len(treeAsText)")
}
var stack [8]*Node
for i, line := range treeAsText {
level := 0
for line[0] == '.' {
// Strip a leading ".\t".
line = line[2:]
level++
}
n := nodes[i]
if level == 0 {
if stack[0] != nil {
t.Fatal("multiple root nodes")
}
stack[0] = n
} else {
stack[level-1].AppendChild(n)
stack[level] = n
for i := level + 1; i < len(stack); i++ {
stack[i] = nil
}
}
// At each stage of tree construction, we check all nodes for consistency.
for j, m := range nodes {
if err := checkNodeConsistency(m); err != nil {
t.Fatalf("i=%d, j=%d: %v", i, j, err)
}
}
}
want := `<html><head></head><body>0&lt;1<p id="A" foo="abc&#34;def">` +
`2<b empty="">3</b><i backslash="\">&amp;4</i></p>` +
`5<blockquote></blockquote><br/>6</body></html>`
b := new(bytes.Buffer)
if err := Render(b, nodes[0]); err != nil {
t.Fatal(err)
}
if got := b.String(); got != want {
t.Errorf("got vs want:\n%s\n%s\n", got, want)
}
}

1219
vendor/golang.org/x/net/html/token.go generated vendored Normal file
View file

File diff suppressed because it is too large Load diff

748
vendor/golang.org/x/net/html/token_test.go generated vendored Normal file
View file

@ -0,0 +1,748 @@
// Copyright 2010 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 html
import (
"bytes"
"io"
"io/ioutil"
"reflect"
"runtime"
"strings"
"testing"
)
type tokenTest struct {
// A short description of the test case.
desc string
// The HTML to parse.
html string
// The string representations of the expected tokens, joined by '$'.
golden string
}
var tokenTests = []tokenTest{
{
"empty",
"",
"",
},
// A single text node. The tokenizer should not break text nodes on whitespace,
// nor should it normalize whitespace within a text node.
{
"text",
"foo bar",
"foo bar",
},
// An entity.
{
"entity",
"one &lt; two",
"one &lt; two",
},
// A start, self-closing and end tag. The tokenizer does not care if the start
// and end tokens don't match; that is the job of the parser.
{
"tags",
"<a>b<c/>d</e>",
"<a>$b$<c/>$d$</e>",
},
// Angle brackets that aren't a tag.
{
"not a tag #0",
"<",
"&lt;",
},
{
"not a tag #1",
"</",
"&lt;/",
},
{
"not a tag #2",
"</>",
"<!---->",
},
{
"not a tag #3",
"a</>b",
"a$<!---->$b",
},
{
"not a tag #4",
"</ >",
"<!-- -->",
},
{
"not a tag #5",
"</.",
"<!--.-->",
},
{
"not a tag #6",
"</.>",
"<!--.-->",
},
{
"not a tag #7",
"a < b",
"a &lt; b",
},
{
"not a tag #8",
"<.>",
"&lt;.&gt;",
},
{
"not a tag #9",
"a<<<b>>>c",
"a&lt;&lt;$<b>$&gt;&gt;c",
},
{
"not a tag #10",
"if x<0 and y < 0 then x*y>0",
"if x&lt;0 and y &lt; 0 then x*y&gt;0",
},
{
"not a tag #11",
"<<p>",
"&lt;$<p>",
},
// EOF in a tag name.
{
"tag name eof #0",
"<a",
"",
},
{
"tag name eof #1",
"<a ",
"",
},
{
"tag name eof #2",
"a<b",
"a",
},
{
"tag name eof #3",
"<a><b",
"<a>",
},
{
"tag name eof #4",
`<a x`,
``,
},
// Some malformed tags that are missing a '>'.
{
"malformed tag #0",
`<p</p>`,
`<p< p="">`,
},
{
"malformed tag #1",
`<p </p>`,
`<p <="" p="">`,
},
{
"malformed tag #2",
`<p id`,
``,
},
{
"malformed tag #3",
`<p id=`,
``,
},
{
"malformed tag #4",
`<p id=>`,
`<p id="">`,
},
{
"malformed tag #5",
`<p id=0`,
``,
},
{
"malformed tag #6",
`<p id=0</p>`,
`<p id="0&lt;/p">`,
},
{
"malformed tag #7",
`<p id="0</p>`,
``,
},
{
"malformed tag #8",
`<p id="0"</p>`,
`<p id="0" <="" p="">`,
},
{
"malformed tag #9",
`<p></p id`,
`<p>`,
},
// Raw text and RCDATA.
{
"basic raw text",
"<script><a></b></script>",
"<script>$&lt;a&gt;&lt;/b&gt;$</script>",
},
{
"unfinished script end tag",
"<SCRIPT>a</SCR",
"<script>$a&lt;/SCR",
},
{
"broken script end tag",
"<SCRIPT>a</SCR ipt>",
"<script>$a&lt;/SCR ipt&gt;",
},
{
"EOF in script end tag",
"<SCRIPT>a</SCRipt",
"<script>$a&lt;/SCRipt",
},
{
"scriptx end tag",
"<SCRIPT>a</SCRiptx",
"<script>$a&lt;/SCRiptx",
},
{
"' ' completes script end tag",
"<SCRIPT>a</SCRipt ",
"<script>$a",
},
{
"'>' completes script end tag",
"<SCRIPT>a</SCRipt>",
"<script>$a$</script>",
},
{
"self-closing script end tag",
"<SCRIPT>a</SCRipt/>",
"<script>$a$</script>",
},
{
"nested script tag",
"<SCRIPT>a</SCRipt<script>",
"<script>$a&lt;/SCRipt&lt;script&gt;",
},
{
"script end tag after unfinished",
"<SCRIPT>a</SCRipt</script>",
"<script>$a&lt;/SCRipt$</script>",
},
{
"script/style mismatched tags",
"<script>a</style>",
"<script>$a&lt;/style&gt;",
},
{
"style element with entity",
"<style>&apos;",
"<style>$&amp;apos;",
},
{
"textarea with tag",
"<textarea><div></textarea>",
"<textarea>$&lt;div&gt;$</textarea>",
},
{
"title with tag and entity",
"<title><b>K&amp;R C</b></title>",
"<title>$&lt;b&gt;K&amp;R C&lt;/b&gt;$</title>",
},
// DOCTYPE tests.
{
"Proper DOCTYPE",
"<!DOCTYPE html>",
"<!DOCTYPE html>",
},
{
"DOCTYPE with no space",
"<!doctypehtml>",
"<!DOCTYPE html>",
},
{
"DOCTYPE with two spaces",
"<!doctype html>",
"<!DOCTYPE html>",
},
{
"looks like DOCTYPE but isn't",
"<!DOCUMENT html>",
"<!--DOCUMENT html-->",
},
{
"DOCTYPE at EOF",
"<!DOCtype",
"<!DOCTYPE >",
},
// XML processing instructions.
{
"XML processing instruction",
"<?xml?>",
"<!--?xml?-->",
},
// Comments.
{
"comment0",
"abc<b><!-- skipme --></b>def",
"abc$<b>$<!-- skipme -->$</b>$def",
},
{
"comment1",
"a<!-->z",
"a$<!---->$z",
},
{
"comment2",
"a<!--->z",
"a$<!---->$z",
},
{
"comment3",
"a<!--x>-->z",
"a$<!--x>-->$z",
},
{
"comment4",
"a<!--x->-->z",
"a$<!--x->-->$z",
},
{
"comment5",
"a<!>z",
"a$<!---->$z",
},
{
"comment6",
"a<!->z",
"a$<!----->$z",
},
{
"comment7",
"a<!---<>z",
"a$<!---<>z-->",
},
{
"comment8",
"a<!--z",
"a$<!--z-->",
},
{
"comment9",
"a<!--z-",
"a$<!--z-->",
},
{
"comment10",
"a<!--z--",
"a$<!--z-->",
},
{
"comment11",
"a<!--z---",
"a$<!--z--->",
},
{
"comment12",
"a<!--z----",
"a$<!--z---->",
},
{
"comment13",
"a<!--x--!>z",
"a$<!--x-->$z",
},
// An attribute with a backslash.
{
"backslash",
`<p id="a\"b">`,
`<p id="a\" b"="">`,
},
// Entities, tag name and attribute key lower-casing, and whitespace
// normalization within a tag.
{
"tricky",
"<p \t\n iD=\"a&quot;B\" foo=\"bar\"><EM>te&lt;&amp;;xt</em></p>",
`<p id="a&#34;B" foo="bar">$<em>$te&lt;&amp;;xt$</em>$</p>`,
},
// A nonexistent entity. Tokenizing and converting back to a string should
// escape the "&" to become "&amp;".
{
"noSuchEntity",
`<a b="c&noSuchEntity;d">&lt;&alsoDoesntExist;&`,
`<a b="c&amp;noSuchEntity;d">$&lt;&amp;alsoDoesntExist;&amp;`,
},
{
"entity without semicolon",
`&notit;&notin;<a b="q=z&amp=5&notice=hello&not;=world">`,
`¬it;∉$<a b="q=z&amp;amp=5&amp;notice=hello¬=world">`,
},
{
"entity with digits",
"&frac12;",
"½",
},
// Attribute tests:
// http://dev.w3.org/html5/pf-summary/Overview.html#attributes
{
"Empty attribute",
`<input disabled FOO>`,
`<input disabled="" foo="">`,
},
{
"Empty attribute, whitespace",
`<input disabled FOO >`,
`<input disabled="" foo="">`,
},
{
"Unquoted attribute value",
`<input value=yes FOO=BAR>`,
`<input value="yes" foo="BAR">`,
},
{
"Unquoted attribute value, spaces",
`<input value = yes FOO = BAR>`,
`<input value="yes" foo="BAR">`,
},
{
"Unquoted attribute value, trailing space",
`<input value=yes FOO=BAR >`,
`<input value="yes" foo="BAR">`,
},
{
"Single-quoted attribute value",
`<input value='yes' FOO='BAR'>`,
`<input value="yes" foo="BAR">`,
},
{
"Single-quoted attribute value, trailing space",
`<input value='yes' FOO='BAR' >`,
`<input value="yes" foo="BAR">`,
},
{
"Double-quoted attribute value",
`<input value="I'm an attribute" FOO="BAR">`,
`<input value="I&#39;m an attribute" foo="BAR">`,
},
{
"Attribute name characters",
`<meta http-equiv="content-type">`,
`<meta http-equiv="content-type">`,
},
{
"Mixed attributes",
`a<P V="0 1" w='2' X=3 y>z`,
`a$<p v="0 1" w="2" x="3" y="">$z`,
},
{
"Attributes with a solitary single quote",
`<p id=can't><p id=won't>`,
`<p id="can&#39;t">$<p id="won&#39;t">`,
},
}
func TestTokenizer(t *testing.T) {
loop:
for _, tt := range tokenTests {
z := NewTokenizer(strings.NewReader(tt.html))
if tt.golden != "" {
for i, s := range strings.Split(tt.golden, "$") {
if z.Next() == ErrorToken {
t.Errorf("%s token %d: want %q got error %v", tt.desc, i, s, z.Err())
continue loop
}
actual := z.Token().String()
if s != actual {
t.Errorf("%s token %d: want %q got %q", tt.desc, i, s, actual)
continue loop
}
}
}
z.Next()
if z.Err() != io.EOF {
t.Errorf("%s: want EOF got %q", tt.desc, z.Err())
}
}
}
func TestMaxBuffer(t *testing.T) {
// Exceeding the maximum buffer size generates ErrBufferExceeded.
z := NewTokenizer(strings.NewReader("<" + strings.Repeat("t", 10)))
z.SetMaxBuf(5)
tt := z.Next()
if got, want := tt, ErrorToken; got != want {
t.Fatalf("token type: got: %v want: %v", got, want)
}
if got, want := z.Err(), ErrBufferExceeded; got != want {
t.Errorf("error type: got: %v want: %v", got, want)
}
if got, want := string(z.Raw()), "<tttt"; got != want {
t.Fatalf("buffered before overflow: got: %q want: %q", got, want)
}
}
func TestMaxBufferReconstruction(t *testing.T) {
// Exceeding the maximum buffer size at any point while tokenizing permits
// reconstructing the original input.
tests:
for _, test := range tokenTests {
for maxBuf := 1; ; maxBuf++ {
r := strings.NewReader(test.html)
z := NewTokenizer(r)
z.SetMaxBuf(maxBuf)
var tokenized bytes.Buffer
for {
tt := z.Next()
tokenized.Write(z.Raw())
if tt == ErrorToken {
if err := z.Err(); err != io.EOF && err != ErrBufferExceeded {
t.Errorf("%s: unexpected error: %v", test.desc, err)
}
break
}
}
// Anything tokenized along with untokenized input or data left in the reader.
assembled, err := ioutil.ReadAll(io.MultiReader(&tokenized, bytes.NewReader(z.Buffered()), r))
if err != nil {
t.Errorf("%s: ReadAll: %v", test.desc, err)
continue tests
}
if got, want := string(assembled), test.html; got != want {
t.Errorf("%s: reassembled html:\n got: %q\nwant: %q", test.desc, got, want)
continue tests
}
// EOF indicates that we completed tokenization and hence found the max
// maxBuf that generates ErrBufferExceeded, so continue to the next test.
if z.Err() == io.EOF {
break
}
} // buffer sizes
} // tests
}
func TestPassthrough(t *testing.T) {
// Accumulating the raw output for each parse event should reconstruct the
// original input.
for _, test := range tokenTests {
z := NewTokenizer(strings.NewReader(test.html))
var parsed bytes.Buffer
for {
tt := z.Next()
parsed.Write(z.Raw())
if tt == ErrorToken {
break
}
}
if got, want := parsed.String(), test.html; got != want {
t.Errorf("%s: parsed output:\n got: %q\nwant: %q", test.desc, got, want)
}
}
}
func TestBufAPI(t *testing.T) {
s := "0<a>1</a>2<b>3<a>4<a>5</a>6</b>7</a>8<a/>9"
z := NewTokenizer(bytes.NewBufferString(s))
var result bytes.Buffer
depth := 0
loop:
for {
tt := z.Next()
switch tt {
case ErrorToken:
if z.Err() != io.EOF {
t.Error(z.Err())
}
break loop
case TextToken:
if depth > 0 {
result.Write(z.Text())
}
case StartTagToken, EndTagToken:
tn, _ := z.TagName()
if len(tn) == 1 && tn[0] == 'a' {
if tt == StartTagToken {
depth++
} else {
depth--
}
}
}
}
u := "14567"
v := string(result.Bytes())
if u != v {
t.Errorf("TestBufAPI: want %q got %q", u, v)
}
}
func TestConvertNewlines(t *testing.T) {
testCases := map[string]string{
"Mac\rDOS\r\nUnix\n": "Mac\nDOS\nUnix\n",
"Unix\nMac\rDOS\r\n": "Unix\nMac\nDOS\n",
"DOS\r\nDOS\r\nDOS\r\n": "DOS\nDOS\nDOS\n",
"": "",
"\n": "\n",
"\n\r": "\n\n",
"\r": "\n",
"\r\n": "\n",
"\r\n\n": "\n\n",
"\r\n\r": "\n\n",
"\r\n\r\n": "\n\n",
"\r\r": "\n\n",
"\r\r\n": "\n\n",
"\r\r\n\n": "\n\n\n",
"\r\r\r\n": "\n\n\n",
"\r \n": "\n \n",
"xyz": "xyz",
}
for in, want := range testCases {
if got := string(convertNewlines([]byte(in))); got != want {
t.Errorf("input %q: got %q, want %q", in, got, want)
}
}
}
func TestReaderEdgeCases(t *testing.T) {
const s = "<p>An io.Reader can return (0, nil) or (n, io.EOF).</p>"
testCases := []io.Reader{
&zeroOneByteReader{s: s},
&eofStringsReader{s: s},
&stuckReader{},
}
for i, tc := range testCases {
got := []TokenType{}
z := NewTokenizer(tc)
for {
tt := z.Next()
if tt == ErrorToken {
break
}
got = append(got, tt)
}
if err := z.Err(); err != nil && err != io.EOF {
if err != io.ErrNoProgress {
t.Errorf("i=%d: %v", i, err)
}
continue
}
want := []TokenType{
StartTagToken,
TextToken,
EndTagToken,
}
if !reflect.DeepEqual(got, want) {
t.Errorf("i=%d: got %v, want %v", i, got, want)
continue
}
}
}
// zeroOneByteReader is like a strings.Reader that alternates between
// returning 0 bytes and 1 byte at a time.
type zeroOneByteReader struct {
s string
n int
}
func (r *zeroOneByteReader) Read(p []byte) (int, error) {
if len(p) == 0 {
return 0, nil
}
if len(r.s) == 0 {
return 0, io.EOF
}
r.n++
if r.n%2 != 0 {
return 0, nil
}
p[0], r.s = r.s[0], r.s[1:]
return 1, nil
}
// eofStringsReader is like a strings.Reader but can return an (n, err) where
// n > 0 && err != nil.
type eofStringsReader struct {
s string
}
func (r *eofStringsReader) Read(p []byte) (int, error) {
n := copy(p, r.s)
r.s = r.s[n:]
if r.s != "" {
return n, nil
}
return n, io.EOF
}
// stuckReader is an io.Reader that always returns no data and no error.
type stuckReader struct{}
func (*stuckReader) Read(p []byte) (int, error) {
return 0, nil
}
const (
rawLevel = iota
lowLevel
highLevel
)
func benchmarkTokenizer(b *testing.B, level int) {
buf, err := ioutil.ReadFile("testdata/go1.html")
if err != nil {
b.Fatalf("could not read testdata/go1.html: %v", err)
}
b.SetBytes(int64(len(buf)))
runtime.GC()
b.ReportAllocs()
b.ResetTimer()
for i := 0; i < b.N; i++ {
z := NewTokenizer(bytes.NewBuffer(buf))
for {
tt := z.Next()
if tt == ErrorToken {
if err := z.Err(); err != nil && err != io.EOF {
b.Fatalf("tokenizer error: %v", err)
}
break
}
switch level {
case rawLevel:
// Calling z.Raw just returns the raw bytes of the token. It does
// not unescape &lt; to <, or lower-case tag names and attribute keys.
z.Raw()
case lowLevel:
// Caling z.Text, z.TagName and z.TagAttr returns []byte values
// whose contents may change on the next call to z.Next.
switch tt {
case TextToken, CommentToken, DoctypeToken:
z.Text()
case StartTagToken, SelfClosingTagToken:
_, more := z.TagName()
for more {
_, _, more = z.TagAttr()
}
case EndTagToken:
z.TagName()
}
case highLevel:
// Calling z.Token converts []byte values to strings whose validity
// extend beyond the next call to z.Next.
z.Token()
}
}
}
}
func BenchmarkRawLevelTokenizer(b *testing.B) { benchmarkTokenizer(b, rawLevel) }
func BenchmarkLowLevelTokenizer(b *testing.B) { benchmarkTokenizer(b, lowLevel) }
func BenchmarkHighLevelTokenizer(b *testing.B) { benchmarkTokenizer(b, highLevel) }

42
vendor/golang.org/x/net/http2/server.go generated vendored
View file

@ -853,8 +853,13 @@ func (sc *serverConn) serve() {
}
}
if sc.inGoAway && sc.curOpenStreams() == 0 && !sc.needToSendGoAway && !sc.writingFrame {
return
// Start the shutdown timer after sending a GOAWAY. When sending GOAWAY
// with no error code (graceful shutdown), don't start the timer until
// all open streams have been completed.
sentGoAway := sc.inGoAway && !sc.needToSendGoAway && !sc.writingFrame
gracefulShutdownComplete := sc.goAwayCode == ErrCodeNo && sc.curOpenStreams() == 0
if sentGoAway && sc.shutdownTimer == nil && (sc.goAwayCode != ErrCodeNo || gracefulShutdownComplete) {
sc.shutDownIn(goAwayTimeout)
}
}
}
@ -1218,30 +1223,31 @@ func (sc *serverConn) startGracefulShutdown() {
sc.shutdownOnce.Do(func() { sc.sendServeMsg(gracefulShutdownMsg) })
}
// After sending GOAWAY, the connection will close after goAwayTimeout.
// If we close the connection immediately after sending GOAWAY, there may
// be unsent data in our kernel receive buffer, which will cause the kernel
// to send a TCP RST on close() instead of a FIN. This RST will abort the
// connection immediately, whether or not the client had received the GOAWAY.
//
// Ideally we should delay for at least 1 RTT + epsilon so the client has
// a chance to read the GOAWAY and stop sending messages. Measuring RTT
// is hard, so we approximate with 1 second. See golang.org/issue/18701.
//
// This is a var so it can be shorter in tests, where all requests uses the
// loopback interface making the expected RTT very small.
//
// TODO: configurable?
var goAwayTimeout = 1 * time.Second
func (sc *serverConn) startGracefulShutdownInternal() {
sc.goAwayIn(ErrCodeNo, 0)
sc.goAway(ErrCodeNo)
}
func (sc *serverConn) goAway(code ErrCode) {
sc.serveG.check()
var forceCloseIn time.Duration
if code != ErrCodeNo {
forceCloseIn = 250 * time.Millisecond
} else {
// TODO: configurable
forceCloseIn = 1 * time.Second
}
sc.goAwayIn(code, forceCloseIn)
}
func (sc *serverConn) goAwayIn(code ErrCode, forceCloseIn time.Duration) {
sc.serveG.check()
if sc.inGoAway {
return
}
if forceCloseIn != 0 {
sc.shutDownIn(forceCloseIn)
}
sc.inGoAway = true
sc.needToSendGoAway = true
sc.goAwayCode = code

1
vendor/golang.org/x/net/http2/server_test.go generated vendored
View file

@ -68,6 +68,7 @@ type serverTester struct {
func init() {
testHookOnPanicMu = new(sync.Mutex)
goAwayTimeout = 25 * time.Millisecond
}
func resetHooks() {

12
vendor/golang.org/x/net/http2/transport.go generated vendored
View file

@ -1536,7 +1536,17 @@ func (rl *clientConnReadLoop) run() error {
func (rl *clientConnReadLoop) processHeaders(f *MetaHeadersFrame) error {
cc := rl.cc
cs := cc.streamByID(f.StreamID, f.StreamEnded())
if f.StreamEnded() {
// Issue 20521: If the stream has ended, streamByID() causes
// clientStream.done to be closed, which causes the request's bodyWriter
// to be closed with an errStreamClosed, which may be received by
// clientConn.RoundTrip before the result of processing these headers.
// Deferring stream closure allows the header processing to occur first.
// clientConn.RoundTrip may still receive the bodyWriter error first, but
// the fix for issue 16102 prioritises any response.
defer cc.streamByID(f.StreamID, true)
}
cs := cc.streamByID(f.StreamID, false)
if cs == nil {
// We'd get here if we canceled a request while the
// server had its response still in flight. So if this

28
vendor/golang.org/x/net/http2/transport_test.go generated vendored
View file

@ -3678,6 +3678,34 @@ func benchSimpleRoundTrip(b *testing.B, nHeaders int) {
}
}
type infiniteReader struct{}
func (r infiniteReader) Read(b []byte) (int, error) {
return len(b), nil
}
// Issue 20521: it is not an error to receive a response and end stream
// from the server without the body being consumed.
func TestTransportResponseAndResetWithoutConsumingBodyRace(t *testing.T) {
st := newServerTester(t, func(w http.ResponseWriter, r *http.Request) {
w.WriteHeader(http.StatusOK)
}, optOnlyServer)
defer st.Close()
tr := &Transport{TLSClientConfig: tlsConfigInsecure}
defer tr.CloseIdleConnections()
// The request body needs to be big enough to trigger flow control.
req, _ := http.NewRequest("PUT", st.ts.URL, infiniteReader{})
res, err := tr.RoundTrip(req)
if err != nil {
t.Fatal(err)
}
if res.StatusCode != http.StatusOK {
t.Fatalf("Response code = %v; want %v", res.StatusCode, http.StatusOK)
}
}
func BenchmarkClientRequestHeaders(b *testing.B) {
b.Run(" 0 Headers", func(b *testing.B) { benchSimpleRoundTrip(b, 0) })
b.Run(" 10 Headers", func(b *testing.B) { benchSimpleRoundTrip(b, 10) })

7
vendor/golang.org/x/net/http2/write.go generated vendored
View file

@ -10,7 +10,6 @@ import (
"log"
"net/http"
"net/url"
"time"
"golang.org/x/net/http2/hpack"
"golang.org/x/net/lex/httplex"
@ -90,11 +89,7 @@ type writeGoAway struct {
func (p *writeGoAway) writeFrame(ctx writeContext) error {
err := ctx.Framer().WriteGoAway(p.maxStreamID, p.code, nil)
if p.code != 0 {
ctx.Flush() // ignore error: we're hanging up on them anyway
time.Sleep(50 * time.Millisecond)
ctx.CloseConn()
}
ctx.Flush() // ignore error: we're hanging up on them anyway
return err
}

713
vendor/golang.org/x/net/publicsuffix/gen.go generated vendored Normal file
View file

@ -0,0 +1,713 @@
// 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.
// +build ignore
package main
// This program generates table.go and table_test.go based on the authoritative
// public suffix list at https://publicsuffix.org/list/effective_tld_names.dat
//
// The version is derived from
// https://api.github.com/repos/publicsuffix/list/commits?path=public_suffix_list.dat
// and a human-readable form is at
// https://github.com/publicsuffix/list/commits/master/public_suffix_list.dat
//
// To fetch a particular git revision, such as 5c70ccd250, pass
// -url "https://raw.githubusercontent.com/publicsuffix/list/5c70ccd250/public_suffix_list.dat"
// and -version "an explicit version string".
import (
"bufio"
"bytes"
"flag"
"fmt"
"go/format"
"io"
"io/ioutil"
"net/http"
"os"
"regexp"
"sort"
"strings"
"golang.org/x/net/idna"
)
const (
// These sum of these four values must be no greater than 32.
nodesBitsChildren = 10
nodesBitsICANN = 1
nodesBitsTextOffset = 15
nodesBitsTextLength = 6
// These sum of these four values must be no greater than 32.
childrenBitsWildcard = 1
childrenBitsNodeType = 2
childrenBitsHi = 14
childrenBitsLo = 14
)
var (
maxChildren int
maxTextOffset int
maxTextLength int
maxHi uint32
maxLo uint32
)
func max(a, b int) int {
if a < b {
return b
}
return a
}
func u32max(a, b uint32) uint32 {
if a < b {
return b
}
return a
}
const (
nodeTypeNormal = 0
nodeTypeException = 1
nodeTypeParentOnly = 2
numNodeType = 3
)
func nodeTypeStr(n int) string {
switch n {
case nodeTypeNormal:
return "+"
case nodeTypeException:
return "!"
case nodeTypeParentOnly:
return "o"
}
panic("unreachable")
}
const (
defaultURL = "https://publicsuffix.org/list/effective_tld_names.dat"
gitCommitURL = "https://api.github.com/repos/publicsuffix/list/commits?path=public_suffix_list.dat"
)
var (
labelEncoding = map[string]uint32{}
labelsList = []string{}
labelsMap = map[string]bool{}
rules = []string{}
// validSuffixRE is used to check that the entries in the public suffix
// list are in canonical form (after Punycode encoding). Specifically,
// capital letters are not allowed.
validSuffixRE = regexp.MustCompile(`^[a-z0-9_\!\*\-\.]+$`)
shaRE = regexp.MustCompile(`"sha":"([^"]+)"`)
dateRE = regexp.MustCompile(`"committer":{[^{]+"date":"([^"]+)"`)
comments = flag.Bool("comments", false, "generate table.go comments, for debugging")
subset = flag.Bool("subset", false, "generate only a subset of the full table, for debugging")
url = flag.String("url", defaultURL, "URL of the publicsuffix.org list. If empty, stdin is read instead")
v = flag.Bool("v", false, "verbose output (to stderr)")
version = flag.String("version", "", "the effective_tld_names.dat version")
)
func main() {
if err := main1(); err != nil {
fmt.Fprintln(os.Stderr, err)
os.Exit(1)
}
}
func main1() error {
flag.Parse()
if nodesBitsTextLength+nodesBitsTextOffset+nodesBitsICANN+nodesBitsChildren > 32 {
return fmt.Errorf("not enough bits to encode the nodes table")
}
if childrenBitsLo+childrenBitsHi+childrenBitsNodeType+childrenBitsWildcard > 32 {
return fmt.Errorf("not enough bits to encode the children table")
}
if *version == "" {
if *url != defaultURL {
return fmt.Errorf("-version was not specified, and the -url is not the default one")
}
sha, date, err := gitCommit()
if err != nil {
return err
}
*version = fmt.Sprintf("publicsuffix.org's public_suffix_list.dat, git revision %s (%s)", sha, date)
}
var r io.Reader = os.Stdin
if *url != "" {
res, err := http.Get(*url)
if err != nil {
return err
}
if res.StatusCode != http.StatusOK {
return fmt.Errorf("bad GET status for %s: %d", *url, res.Status)
}
r = res.Body
defer res.Body.Close()
}
var root node
icann := false
br := bufio.NewReader(r)
for {
s, err := br.ReadString('\n')
if err != nil {
if err == io.EOF {
break
}
return err
}
s = strings.TrimSpace(s)
if strings.Contains(s, "BEGIN ICANN DOMAINS") {
icann = true
continue
}
if strings.Contains(s, "END ICANN DOMAINS") {
icann = false
continue
}
if s == "" || strings.HasPrefix(s, "//") {
continue
}
s, err = idna.ToASCII(s)
if err != nil {
return err
}
if !validSuffixRE.MatchString(s) {
return fmt.Errorf("bad publicsuffix.org list data: %q", s)
}
if *subset {
switch {
case s == "ac.jp" || strings.HasSuffix(s, ".ac.jp"):
case s == "ak.us" || strings.HasSuffix(s, ".ak.us"):
case s == "ao" || strings.HasSuffix(s, ".ao"):
case s == "ar" || strings.HasSuffix(s, ".ar"):
case s == "arpa" || strings.HasSuffix(s, ".arpa"):
case s == "cy" || strings.HasSuffix(s, ".cy"):
case s == "dyndns.org" || strings.HasSuffix(s, ".dyndns.org"):
case s == "jp":
case s == "kobe.jp" || strings.HasSuffix(s, ".kobe.jp"):
case s == "kyoto.jp" || strings.HasSuffix(s, ".kyoto.jp"):
case s == "om" || strings.HasSuffix(s, ".om"):
case s == "uk" || strings.HasSuffix(s, ".uk"):
case s == "uk.com" || strings.HasSuffix(s, ".uk.com"):
case s == "tw" || strings.HasSuffix(s, ".tw"):
case s == "zw" || strings.HasSuffix(s, ".zw"):
case s == "xn--p1ai" || strings.HasSuffix(s, ".xn--p1ai"):
// xn--p1ai is Russian-Cyrillic "рф".
default:
continue
}
}
rules = append(rules, s)
nt, wildcard := nodeTypeNormal, false
switch {
case strings.HasPrefix(s, "*."):
s, nt = s[2:], nodeTypeParentOnly
wildcard = true
case strings.HasPrefix(s, "!"):
s, nt = s[1:], nodeTypeException
}
labels := strings.Split(s, ".")
for n, i := &root, len(labels)-1; i >= 0; i-- {
label := labels[i]
n = n.child(label)
if i == 0 {
if nt != nodeTypeParentOnly && n.nodeType == nodeTypeParentOnly {
n.nodeType = nt
}
n.icann = n.icann && icann
n.wildcard = n.wildcard || wildcard
}
labelsMap[label] = true
}
}
labelsList = make([]string, 0, len(labelsMap))
for label := range labelsMap {
labelsList = append(labelsList, label)
}
sort.Strings(labelsList)
if err := generate(printReal, &root, "table.go"); err != nil {
return err
}
if err := generate(printTest, &root, "table_test.go"); err != nil {
return err
}
return nil
}
func generate(p func(io.Writer, *node) error, root *node, filename string) error {
buf := new(bytes.Buffer)
if err := p(buf, root); err != nil {
return err
}
b, err := format.Source(buf.Bytes())
if err != nil {
return err
}
return ioutil.WriteFile(filename, b, 0644)
}
func gitCommit() (sha, date string, retErr error) {
res, err := http.Get(gitCommitURL)
if err != nil {
return "", "", err
}
if res.StatusCode != http.StatusOK {
return "", "", fmt.Errorf("bad GET status for %s: %d", gitCommitURL, res.Status)
}
defer res.Body.Close()
b, err := ioutil.ReadAll(res.Body)
if err != nil {
return "", "", err
}
if m := shaRE.FindSubmatch(b); m != nil {
sha = string(m[1])
}
if m := dateRE.FindSubmatch(b); m != nil {
date = string(m[1])
}
if sha == "" || date == "" {
retErr = fmt.Errorf("could not find commit SHA and date in %s", gitCommitURL)
}
return sha, date, retErr
}
func printTest(w io.Writer, n *node) error {
fmt.Fprintf(w, "// generated by go run gen.go; DO NOT EDIT\n\n")
fmt.Fprintf(w, "package publicsuffix\n\nvar rules = [...]string{\n")
for _, rule := range rules {
fmt.Fprintf(w, "%q,\n", rule)
}
fmt.Fprintf(w, "}\n\nvar nodeLabels = [...]string{\n")
if err := n.walk(w, printNodeLabel); err != nil {
return err
}
fmt.Fprintf(w, "}\n")
return nil
}
func printReal(w io.Writer, n *node) error {
const header = `// generated by go run gen.go; DO NOT EDIT
package publicsuffix
const version = %q
const (
nodesBitsChildren = %d
nodesBitsICANN = %d
nodesBitsTextOffset = %d
nodesBitsTextLength = %d
childrenBitsWildcard = %d
childrenBitsNodeType = %d
childrenBitsHi = %d
childrenBitsLo = %d
)
const (
nodeTypeNormal = %d
nodeTypeException = %d
nodeTypeParentOnly = %d
)
// numTLD is the number of top level domains.
const numTLD = %d
`
fmt.Fprintf(w, header, *version,
nodesBitsChildren, nodesBitsICANN, nodesBitsTextOffset, nodesBitsTextLength,
childrenBitsWildcard, childrenBitsNodeType, childrenBitsHi, childrenBitsLo,
nodeTypeNormal, nodeTypeException, nodeTypeParentOnly, len(n.children))
text := combineText(labelsList)
if text == "" {
return fmt.Errorf("internal error: makeText returned no text")
}
for _, label := range labelsList {
offset, length := strings.Index(text, label), len(label)
if offset < 0 {
return fmt.Errorf("internal error: could not find %q in text %q", label, text)
}
maxTextOffset, maxTextLength = max(maxTextOffset, offset), max(maxTextLength, length)
if offset >= 1<<nodesBitsTextOffset {
return fmt.Errorf("text offset %d is too large, or nodeBitsTextOffset is too small", offset)
}
if length >= 1<<nodesBitsTextLength {
return fmt.Errorf("text length %d is too large, or nodeBitsTextLength is too small", length)
}
labelEncoding[label] = uint32(offset)<<nodesBitsTextLength | uint32(length)
}
fmt.Fprintf(w, "// Text is the combined text of all labels.\nconst text = ")
for len(text) > 0 {
n, plus := len(text), ""
if n > 64 {
n, plus = 64, " +"
}
fmt.Fprintf(w, "%q%s\n", text[:n], plus)
text = text[n:]
}
if err := n.walk(w, assignIndexes); err != nil {
return err
}
fmt.Fprintf(w, `
// nodes is the list of nodes. Each node is represented as a uint32, which
// encodes the node's children, wildcard bit and node type (as an index into
// the children array), ICANN bit and text.
//
// If the table was generated with the -comments flag, there is a //-comment
// after each node's data. In it is the nodes-array indexes of the children,
// formatted as (n0x1234-n0x1256), with * denoting the wildcard bit. The
// nodeType is printed as + for normal, ! for exception, and o for parent-only
// nodes that have children but don't match a domain label in their own right.
// An I denotes an ICANN domain.
//
// The layout within the uint32, from MSB to LSB, is:
// [%2d bits] unused
// [%2d bits] children index
// [%2d bits] ICANN bit
// [%2d bits] text index
// [%2d bits] text length
var nodes = [...]uint32{
`,
32-nodesBitsChildren-nodesBitsICANN-nodesBitsTextOffset-nodesBitsTextLength,
nodesBitsChildren, nodesBitsICANN, nodesBitsTextOffset, nodesBitsTextLength)
if err := n.walk(w, printNode); err != nil {
return err
}
fmt.Fprintf(w, `}
// children is the list of nodes' children, the parent's wildcard bit and the
// parent's node type. If a node has no children then their children index
// will be in the range [0, 6), depending on the wildcard bit and node type.
//
// The layout within the uint32, from MSB to LSB, is:
// [%2d bits] unused
// [%2d bits] wildcard bit
// [%2d bits] node type
// [%2d bits] high nodes index (exclusive) of children
// [%2d bits] low nodes index (inclusive) of children
var children=[...]uint32{
`,
32-childrenBitsWildcard-childrenBitsNodeType-childrenBitsHi-childrenBitsLo,
childrenBitsWildcard, childrenBitsNodeType, childrenBitsHi, childrenBitsLo)
for i, c := range childrenEncoding {
s := "---------------"
lo := c & (1<<childrenBitsLo - 1)
hi := (c >> childrenBitsLo) & (1<<childrenBitsHi - 1)
if lo != hi {
s = fmt.Sprintf("n0x%04x-n0x%04x", lo, hi)
}
nodeType := int(c>>(childrenBitsLo+childrenBitsHi)) & (1<<childrenBitsNodeType - 1)
wildcard := c>>(childrenBitsLo+childrenBitsHi+childrenBitsNodeType) != 0
if *comments {
fmt.Fprintf(w, "0x%08x, // c0x%04x (%s)%s %s\n",
c, i, s, wildcardStr(wildcard), nodeTypeStr(nodeType))
} else {
fmt.Fprintf(w, "0x%x,\n", c)
}
}
fmt.Fprintf(w, "}\n\n")
fmt.Fprintf(w, "// max children %d (capacity %d)\n", maxChildren, 1<<nodesBitsChildren-1)
fmt.Fprintf(w, "// max text offset %d (capacity %d)\n", maxTextOffset, 1<<nodesBitsTextOffset-1)
fmt.Fprintf(w, "// max text length %d (capacity %d)\n", maxTextLength, 1<<nodesBitsTextLength-1)
fmt.Fprintf(w, "// max hi %d (capacity %d)\n", maxHi, 1<<childrenBitsHi-1)
fmt.Fprintf(w, "// max lo %d (capacity %d)\n", maxLo, 1<<childrenBitsLo-1)
return nil
}
type node struct {
label string
nodeType int
icann bool
wildcard bool
// nodesIndex and childrenIndex are the index of this node in the nodes
// and the index of its children offset/length in the children arrays.
nodesIndex, childrenIndex int
// firstChild is the index of this node's first child, or zero if this
// node has no children.
firstChild int
// children are the node's children, in strictly increasing node label order.
children []*node
}
func (n *node) walk(w io.Writer, f func(w1 io.Writer, n1 *node) error) error {
if err := f(w, n); err != nil {
return err
}
for _, c := range n.children {
if err := c.walk(w, f); err != nil {
return err
}
}
return nil
}
// child returns the child of n with the given label. The child is created if
// it did not exist beforehand.
func (n *node) child(label string) *node {
for _, c := range n.children {
if c.label == label {
return c
}
}
c := &node{
label: label,
nodeType: nodeTypeParentOnly,
icann: true,
}
n.children = append(n.children, c)
sort.Sort(byLabel(n.children))
return c
}
type byLabel []*node
func (b byLabel) Len() int { return len(b) }
func (b byLabel) Swap(i, j int) { b[i], b[j] = b[j], b[i] }
func (b byLabel) Less(i, j int) bool { return b[i].label < b[j].label }
var nextNodesIndex int
// childrenEncoding are the encoded entries in the generated children array.
// All these pre-defined entries have no children.
var childrenEncoding = []uint32{
0 << (childrenBitsLo + childrenBitsHi), // Without wildcard bit, nodeTypeNormal.
1 << (childrenBitsLo + childrenBitsHi), // Without wildcard bit, nodeTypeException.
2 << (childrenBitsLo + childrenBitsHi), // Without wildcard bit, nodeTypeParentOnly.
4 << (childrenBitsLo + childrenBitsHi), // With wildcard bit, nodeTypeNormal.
5 << (childrenBitsLo + childrenBitsHi), // With wildcard bit, nodeTypeException.
6 << (childrenBitsLo + childrenBitsHi), // With wildcard bit, nodeTypeParentOnly.
}
var firstCallToAssignIndexes = true
func assignIndexes(w io.Writer, n *node) error {
if len(n.children) != 0 {
// Assign nodesIndex.
n.firstChild = nextNodesIndex
for _, c := range n.children {
c.nodesIndex = nextNodesIndex
nextNodesIndex++
}
// The root node's children is implicit.
if firstCallToAssignIndexes {
firstCallToAssignIndexes = false
return nil
}
// Assign childrenIndex.
maxChildren = max(maxChildren, len(childrenEncoding))
if len(childrenEncoding) >= 1<<nodesBitsChildren {
return fmt.Errorf("children table size %d is too large, or nodeBitsChildren is too small", len(childrenEncoding))
}
n.childrenIndex = len(childrenEncoding)
lo := uint32(n.firstChild)
hi := lo + uint32(len(n.children))
maxLo, maxHi = u32max(maxLo, lo), u32max(maxHi, hi)
if lo >= 1<<childrenBitsLo {
return fmt.Errorf("children lo %d is too large, or childrenBitsLo is too small", lo)
}
if hi >= 1<<childrenBitsHi {
return fmt.Errorf("children hi %d is too large, or childrenBitsHi is too small", hi)
}
enc := hi<<childrenBitsLo | lo
enc |= uint32(n.nodeType) << (childrenBitsLo + childrenBitsHi)
if n.wildcard {
enc |= 1 << (childrenBitsLo + childrenBitsHi + childrenBitsNodeType)
}
childrenEncoding = append(childrenEncoding, enc)
} else {
n.childrenIndex = n.nodeType
if n.wildcard {
n.childrenIndex += numNodeType
}
}
return nil
}
func printNode(w io.Writer, n *node) error {
for _, c := range n.children {
s := "---------------"
if len(c.children) != 0 {
s = fmt.Sprintf("n0x%04x-n0x%04x", c.firstChild, c.firstChild+len(c.children))
}
encoding := labelEncoding[c.label]
if c.icann {
encoding |= 1 << (nodesBitsTextLength + nodesBitsTextOffset)
}
encoding |= uint32(c.childrenIndex) << (nodesBitsTextLength + nodesBitsTextOffset + nodesBitsICANN)
if *comments {
fmt.Fprintf(w, "0x%08x, // n0x%04x c0x%04x (%s)%s %s %s %s\n",
encoding, c.nodesIndex, c.childrenIndex, s, wildcardStr(c.wildcard),
nodeTypeStr(c.nodeType), icannStr(c.icann), c.label,
)
} else {
fmt.Fprintf(w, "0x%x,\n", encoding)
}
}
return nil
}
func printNodeLabel(w io.Writer, n *node) error {
for _, c := range n.children {
fmt.Fprintf(w, "%q,\n", c.label)
}
return nil
}
func icannStr(icann bool) string {
if icann {
return "I"
}
return " "
}
func wildcardStr(wildcard bool) string {
if wildcard {
return "*"
}
return " "
}
// combineText combines all the strings in labelsList to form one giant string.
// Overlapping strings will be merged: "arpa" and "parliament" could yield
// "arparliament".
func combineText(labelsList []string) string {
beforeLength := 0
for _, s := range labelsList {
beforeLength += len(s)
}
text := crush(removeSubstrings(labelsList))
if *v {
fmt.Fprintf(os.Stderr, "crushed %d bytes to become %d bytes\n", beforeLength, len(text))
}
return text
}
type byLength []string
func (s byLength) Len() int { return len(s) }
func (s byLength) Swap(i, j int) { s[i], s[j] = s[j], s[i] }
func (s byLength) Less(i, j int) bool { return len(s[i]) < len(s[j]) }
// removeSubstrings returns a copy of its input with any strings removed
// that are substrings of other provided strings.
func removeSubstrings(input []string) []string {
// Make a copy of input.
ss := append(make([]string, 0, len(input)), input...)
sort.Sort(byLength(ss))
for i, shortString := range ss {
// For each string, only consider strings higher than it in sort order, i.e.
// of equal length or greater.
for _, longString := range ss[i+1:] {
if strings.Contains(longString, shortString) {
ss[i] = ""
break
}
}
}
// Remove the empty strings.
sort.Strings(ss)
for len(ss) > 0 && ss[0] == "" {
ss = ss[1:]
}
return ss
}
// crush combines a list of strings, taking advantage of overlaps. It returns a
// single string that contains each input string as a substring.
func crush(ss []string) string {
maxLabelLen := 0
for _, s := range ss {
if maxLabelLen < len(s) {
maxLabelLen = len(s)
}
}
for prefixLen := maxLabelLen; prefixLen > 0; prefixLen-- {
prefixes := makePrefixMap(ss, prefixLen)
for i, s := range ss {
if len(s) <= prefixLen {
continue
}
mergeLabel(ss, i, prefixLen, prefixes)
}
}
return strings.Join(ss, "")
}
// mergeLabel merges the label at ss[i] with the first available matching label
// in prefixMap, where the last "prefixLen" characters in ss[i] match the first
// "prefixLen" characters in the matching label.
// It will merge ss[i] repeatedly until no more matches are available.
// All matching labels merged into ss[i] are replaced by "".
func mergeLabel(ss []string, i, prefixLen int, prefixes prefixMap) {
s := ss[i]
suffix := s[len(s)-prefixLen:]
for _, j := range prefixes[suffix] {
// Empty strings mean "already used." Also avoid merging with self.
if ss[j] == "" || i == j {
continue
}
if *v {
fmt.Fprintf(os.Stderr, "%d-length overlap at (%4d,%4d): %q and %q share %q\n",
prefixLen, i, j, ss[i], ss[j], suffix)
}
ss[i] += ss[j][prefixLen:]
ss[j] = ""
// ss[i] has a new suffix, so merge again if possible.
// Note: we only have to merge again at the same prefix length. Shorter
// prefix lengths will be handled in the next iteration of crush's for loop.
// Can there be matches for longer prefix lengths, introduced by the merge?
// I believe that any such matches would by necessity have been eliminated
// during substring removal or merged at a higher prefix length. For
// instance, in crush("abc", "cde", "bcdef"), combining "abc" and "cde"
// would yield "abcde", which could be merged with "bcdef." However, in
// practice "cde" would already have been elimintated by removeSubstrings.
mergeLabel(ss, i, prefixLen, prefixes)
return
}
}
// prefixMap maps from a prefix to a list of strings containing that prefix. The
// list of strings is represented as indexes into a slice of strings stored
// elsewhere.
type prefixMap map[string][]int
// makePrefixMap constructs a prefixMap from a slice of strings.
func makePrefixMap(ss []string, prefixLen int) prefixMap {
prefixes := make(prefixMap)
for i, s := range ss {
// We use < rather than <= because if a label matches on a prefix equal to
// its full length, that's actually a substring match handled by
// removeSubstrings.
if prefixLen < len(s) {
prefix := s[:prefixLen]
prefixes[prefix] = append(prefixes[prefix], i)
}
}
return prefixes
}

135
vendor/golang.org/x/net/publicsuffix/list.go generated vendored Normal file
View file

@ -0,0 +1,135 @@
// 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
// http://publicsuffix.org/. A public suffix is one under which Internet users
// can directly register names.
package publicsuffix // import "golang.org/x/net/publicsuffix"
// TODO: specify case sensitivity and leading/trailing dot behavior for
// func PublicSuffix and func EffectiveTLDPlusOne.
import (
"fmt"
"net/http/cookiejar"
"strings"
)
// List implements the cookiejar.PublicSuffixList interface by calling the
// PublicSuffix function.
var List cookiejar.PublicSuffixList = list{}
type list struct{}
func (list) PublicSuffix(domain string) string {
ps, _ := PublicSuffix(domain)
return ps
}
func (list) String() 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 privately
// managed. For example, foo.org and foo.co.uk are ICANN domains,
// foo.dyndns.org and foo.blogspot.co.uk are private domains.
//
// 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 PublicSuffix(domain string) (publicSuffix string, icann bool) {
lo, hi := uint32(0), uint32(numTLD)
s, suffix, wildcard := domain, len(domain), false
loop:
for {
dot := strings.LastIndex(s, ".")
if wildcard {
suffix = 1 + dot
}
if lo == hi {
break
}
f := find(s[1+dot:], lo, hi)
if f == notFound {
break
}
u := nodes[f] >> (nodesBitsTextOffset + nodesBitsTextLength)
icann = u&(1<<nodesBitsICANN-1) != 0
u >>= nodesBitsICANN
u = children[u&(1<<nodesBitsChildren-1)]
lo = u & (1<<childrenBitsLo - 1)
u >>= childrenBitsLo
hi = u & (1<<childrenBitsHi - 1)
u >>= childrenBitsHi
switch u & (1<<childrenBitsNodeType - 1) {
case nodeTypeNormal:
suffix = 1 + dot
case nodeTypeException:
suffix = 1 + len(s)
break loop
}
u >>= childrenBitsNodeType
wildcard = u&(1<<childrenBitsWildcard-1) != 0
if dot == -1 {
break
}
s = s[:dot]
}
if suffix == len(domain) {
// If no rules match, the prevailing rule is "*".
return domain[1+strings.LastIndex(domain, "."):], icann
}
return domain[suffix:], icann
}
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(label string, lo, hi uint32) uint32 {
for lo < hi {
mid := lo + (hi-lo)/2
s := nodeLabel(mid)
if s < label {
lo = mid + 1
} else if s == label {
return mid
} else {
hi = mid
}
}
return notFound
}
// nodeLabel returns the label for the i'th node.
func nodeLabel(i uint32) string {
x := nodes[i]
length := x & (1<<nodesBitsTextLength - 1)
x >>= nodesBitsTextLength
offset := x & (1<<nodesBitsTextOffset - 1)
return text[offset : offset+length]
}
// 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 EffectiveTLDPlusOne(domain string) (string, error) {
suffix, _ := PublicSuffix(domain)
if len(domain) <= len(suffix) {
return "", fmt.Errorf("publicsuffix: cannot derive eTLD+1 for domain %q", domain)
}
i := len(domain) - len(suffix) - 1
if domain[i] != '.' {
return "", fmt.Errorf("publicsuffix: invalid public suffix %q for domain %q", suffix, domain)
}
return domain[1+strings.LastIndex(domain[:i], "."):], nil
}

416
vendor/golang.org/x/net/publicsuffix/list_test.go generated vendored Normal file
View file

@ -0,0 +1,416 @@
// 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.
package publicsuffix
import (
"sort"
"strings"
"testing"
)
func TestNodeLabel(t *testing.T) {
for i, want := range nodeLabels {
got := nodeLabel(uint32(i))
if got != want {
t.Errorf("%d: got %q, want %q", i, got, want)
}
}
}
func TestFind(t *testing.T) {
testCases := []string{
"",
"a",
"a0",
"aaaa",
"ao",
"ap",
"ar",
"aro",
"arp",
"arpa",
"arpaa",
"arpb",
"az",
"b",
"b0",
"ba",
"z",
"zu",
"zv",
"zw",
"zx",
"zy",
"zz",
"zzzz",
}
for _, tc := range testCases {
got := find(tc, 0, numTLD)
want := notFound
for i := uint32(0); i < numTLD; i++ {
if tc == nodeLabel(i) {
want = i
break
}
}
if got != want {
t.Errorf("%q: got %d, want %d", tc, got, want)
}
}
}
func TestICANN(t *testing.T) {
testCases := map[string]bool{
"foo.org": true,
"foo.co.uk": true,
"foo.dyndns.org": false,
"foo.go.dyndns.org": false,
"foo.blogspot.co.uk": false,
"foo.intranet": false,
}
for domain, want := range testCases {
_, got := PublicSuffix(domain)
if got != want {
t.Errorf("%q: got %v, want %v", domain, got, want)
}
}
}
var publicSuffixTestCases = []struct {
domain, want string
}{
// Empty string.
{"", ""},
// The .ao rules are:
// ao
// ed.ao
// gv.ao
// og.ao
// co.ao
// pb.ao
// it.ao
{"ao", "ao"},
{"www.ao", "ao"},
{"pb.ao", "pb.ao"},
{"www.pb.ao", "pb.ao"},
{"www.xxx.yyy.zzz.pb.ao", "pb.ao"},
// The .ar rules are:
// ar
// com.ar
// edu.ar
// gob.ar
// gov.ar
// int.ar
// mil.ar
// net.ar
// org.ar
// tur.ar
// blogspot.com.ar
{"ar", "ar"},
{"www.ar", "ar"},
{"nic.ar", "ar"},
{"www.nic.ar", "ar"},
{"com.ar", "com.ar"},
{"www.com.ar", "com.ar"},
{"blogspot.com.ar", "blogspot.com.ar"},
{"www.blogspot.com.ar", "blogspot.com.ar"},
{"www.xxx.yyy.zzz.blogspot.com.ar", "blogspot.com.ar"},
{"logspot.com.ar", "com.ar"},
{"zlogspot.com.ar", "com.ar"},
{"zblogspot.com.ar", "com.ar"},
// The .arpa rules are:
// arpa
// e164.arpa
// in-addr.arpa
// ip6.arpa
// iris.arpa
// uri.arpa
// urn.arpa
{"arpa", "arpa"},
{"www.arpa", "arpa"},
{"urn.arpa", "urn.arpa"},
{"www.urn.arpa", "urn.arpa"},
{"www.xxx.yyy.zzz.urn.arpa", "urn.arpa"},
// The relevant {kobe,kyoto}.jp rules are:
// jp
// *.kobe.jp
// !city.kobe.jp
// kyoto.jp
// ide.kyoto.jp
{"jp", "jp"},
{"kobe.jp", "jp"},
{"c.kobe.jp", "c.kobe.jp"},
{"b.c.kobe.jp", "c.kobe.jp"},
{"a.b.c.kobe.jp", "c.kobe.jp"},
{"city.kobe.jp", "kobe.jp"},
{"www.city.kobe.jp", "kobe.jp"},
{"kyoto.jp", "kyoto.jp"},
{"test.kyoto.jp", "kyoto.jp"},
{"ide.kyoto.jp", "ide.kyoto.jp"},
{"b.ide.kyoto.jp", "ide.kyoto.jp"},
{"a.b.ide.kyoto.jp", "ide.kyoto.jp"},
// The .tw rules are:
// tw
// edu.tw
// gov.tw
// mil.tw
// com.tw
// net.tw
// org.tw
// idv.tw
// game.tw
// ebiz.tw
// club.tw
// 網路.tw (xn--zf0ao64a.tw)
// 組織.tw (xn--uc0atv.tw)
// 商業.tw (xn--czrw28b.tw)
// blogspot.tw
{"tw", "tw"},
{"aaa.tw", "tw"},
{"www.aaa.tw", "tw"},
{"xn--czrw28b.aaa.tw", "tw"},
{"edu.tw", "edu.tw"},
{"www.edu.tw", "edu.tw"},
{"xn--czrw28b.edu.tw", "edu.tw"},
{"xn--czrw28b.tw", "xn--czrw28b.tw"},
{"www.xn--czrw28b.tw", "xn--czrw28b.tw"},
{"xn--uc0atv.xn--czrw28b.tw", "xn--czrw28b.tw"},
{"xn--kpry57d.tw", "tw"},
// The .uk rules are:
// uk
// ac.uk
// co.uk
// gov.uk
// ltd.uk
// me.uk
// net.uk
// nhs.uk
// org.uk
// plc.uk
// police.uk
// *.sch.uk
// blogspot.co.uk
{"uk", "uk"},
{"aaa.uk", "uk"},
{"www.aaa.uk", "uk"},
{"mod.uk", "uk"},
{"www.mod.uk", "uk"},
{"sch.uk", "uk"},
{"mod.sch.uk", "mod.sch.uk"},
{"www.sch.uk", "www.sch.uk"},
{"blogspot.co.uk", "blogspot.co.uk"},
{"blogspot.nic.uk", "uk"},
{"blogspot.sch.uk", "blogspot.sch.uk"},
// The .рф rules are
// рф (xn--p1ai)
{"xn--p1ai", "xn--p1ai"},
{"aaa.xn--p1ai", "xn--p1ai"},
{"www.xxx.yyy.xn--p1ai", "xn--p1ai"},
// The .bd rules are:
// *.bd
{"bd", "bd"},
{"www.bd", "www.bd"},
{"zzz.bd", "zzz.bd"},
{"www.zzz.bd", "zzz.bd"},
{"www.xxx.yyy.zzz.bd", "zzz.bd"},
// There are no .nosuchtld rules.
{"nosuchtld", "nosuchtld"},
{"foo.nosuchtld", "nosuchtld"},
{"bar.foo.nosuchtld", "nosuchtld"},
}
func BenchmarkPublicSuffix(b *testing.B) {
for i := 0; i < b.N; i++ {
for _, tc := range publicSuffixTestCases {
List.PublicSuffix(tc.domain)
}
}
}
func TestPublicSuffix(t *testing.T) {
for _, tc := range publicSuffixTestCases {
got := List.PublicSuffix(tc.domain)
if got != tc.want {
t.Errorf("%q: got %q, want %q", tc.domain, got, tc.want)
}
}
}
func TestSlowPublicSuffix(t *testing.T) {
for _, tc := range publicSuffixTestCases {
got := slowPublicSuffix(tc.domain)
if got != tc.want {
t.Errorf("%q: got %q, want %q", tc.domain, got, tc.want)
}
}
}
// slowPublicSuffix implements the canonical (but O(number of rules)) public
// suffix algorithm described at http://publicsuffix.org/list/.
//
// 1. Match domain against all rules and take note of the matching ones.
// 2. If no rules match, the prevailing rule is "*".
// 3. If more than one rule matches, the prevailing rule is the one which is an exception rule.
// 4. If there is no matching exception rule, the prevailing rule is the one with the most labels.
// 5. If the prevailing rule is a exception rule, modify it by removing the leftmost label.
// 6. The public suffix is the set of labels from the domain which directly match the labels of the prevailing rule (joined by dots).
// 7. The registered or registrable domain is the public suffix plus one additional label.
//
// This function returns the public suffix, not the registrable domain, and so
// it stops after step 6.
func slowPublicSuffix(domain string) string {
match := func(rulePart, domainPart string) bool {
switch rulePart[0] {
case '*':
return true
case '!':
return rulePart[1:] == domainPart
}
return rulePart == domainPart
}
domainParts := strings.Split(domain, ".")
var matchingRules [][]string
loop:
for _, rule := range rules {
ruleParts := strings.Split(rule, ".")
if len(domainParts) < len(ruleParts) {
continue
}
for i := range ruleParts {
rulePart := ruleParts[len(ruleParts)-1-i]
domainPart := domainParts[len(domainParts)-1-i]
if !match(rulePart, domainPart) {
continue loop
}
}
matchingRules = append(matchingRules, ruleParts)
}
if len(matchingRules) == 0 {
matchingRules = append(matchingRules, []string{"*"})
} else {
sort.Sort(byPriority(matchingRules))
}
prevailing := matchingRules[0]
if prevailing[0][0] == '!' {
prevailing = prevailing[1:]
}
if prevailing[0][0] == '*' {
replaced := domainParts[len(domainParts)-len(prevailing)]
prevailing = append([]string{replaced}, prevailing[1:]...)
}
return strings.Join(prevailing, ".")
}
type byPriority [][]string
func (b byPriority) Len() int { return len(b) }
func (b byPriority) Swap(i, j int) { b[i], b[j] = b[j], b[i] }
func (b byPriority) Less(i, j int) bool {
if b[i][0][0] == '!' {
return true
}
if b[j][0][0] == '!' {
return false
}
return len(b[i]) > len(b[j])
}
// eTLDPlusOneTestCases come from
// https://github.com/publicsuffix/list/blob/master/tests/test_psl.txt
var eTLDPlusOneTestCases = []struct {
domain, want string
}{
// Empty input.
{"", ""},
// Unlisted TLD.
{"example", ""},
{"example.example", "example.example"},
{"b.example.example", "example.example"},
{"a.b.example.example", "example.example"},
// TLD with only 1 rule.
{"biz", ""},
{"domain.biz", "domain.biz"},
{"b.domain.biz", "domain.biz"},
{"a.b.domain.biz", "domain.biz"},
// TLD with some 2-level rules.
{"com", ""},
{"example.com", "example.com"},
{"b.example.com", "example.com"},
{"a.b.example.com", "example.com"},
{"uk.com", ""},
{"example.uk.com", "example.uk.com"},
{"b.example.uk.com", "example.uk.com"},
{"a.b.example.uk.com", "example.uk.com"},
{"test.ac", "test.ac"},
// TLD with only 1 (wildcard) rule.
{"mm", ""},
{"c.mm", ""},
{"b.c.mm", "b.c.mm"},
{"a.b.c.mm", "b.c.mm"},
// More complex TLD.
{"jp", ""},
{"test.jp", "test.jp"},
{"www.test.jp", "test.jp"},
{"ac.jp", ""},
{"test.ac.jp", "test.ac.jp"},
{"www.test.ac.jp", "test.ac.jp"},
{"kyoto.jp", ""},
{"test.kyoto.jp", "test.kyoto.jp"},
{"ide.kyoto.jp", ""},
{"b.ide.kyoto.jp", "b.ide.kyoto.jp"},
{"a.b.ide.kyoto.jp", "b.ide.kyoto.jp"},
{"c.kobe.jp", ""},
{"b.c.kobe.jp", "b.c.kobe.jp"},
{"a.b.c.kobe.jp", "b.c.kobe.jp"},
{"city.kobe.jp", "city.kobe.jp"},
{"www.city.kobe.jp", "city.kobe.jp"},
// TLD with a wildcard rule and exceptions.
{"ck", ""},
{"test.ck", ""},
{"b.test.ck", "b.test.ck"},
{"a.b.test.ck", "b.test.ck"},
{"www.ck", "www.ck"},
{"www.www.ck", "www.ck"},
// US K12.
{"us", ""},
{"test.us", "test.us"},
{"www.test.us", "test.us"},
{"ak.us", ""},
{"test.ak.us", "test.ak.us"},
{"www.test.ak.us", "test.ak.us"},
{"k12.ak.us", ""},
{"test.k12.ak.us", "test.k12.ak.us"},
{"www.test.k12.ak.us", "test.k12.ak.us"},
// Punycoded IDN labels
{"xn--85x722f.com.cn", "xn--85x722f.com.cn"},
{"xn--85x722f.xn--55qx5d.cn", "xn--85x722f.xn--55qx5d.cn"},
{"www.xn--85x722f.xn--55qx5d.cn", "xn--85x722f.xn--55qx5d.cn"},
{"shishi.xn--55qx5d.cn", "shishi.xn--55qx5d.cn"},
{"xn--55qx5d.cn", ""},
{"xn--85x722f.xn--fiqs8s", "xn--85x722f.xn--fiqs8s"},
{"www.xn--85x722f.xn--fiqs8s", "xn--85x722f.xn--fiqs8s"},
{"shishi.xn--fiqs8s", "shishi.xn--fiqs8s"},
{"xn--fiqs8s", ""},
}
func TestEffectiveTLDPlusOne(t *testing.T) {
for _, tc := range eTLDPlusOneTestCases {
got, _ := EffectiveTLDPlusOne(tc.domain)
if got != tc.want {
t.Errorf("%q: got %q, want %q", tc.domain, got, tc.want)
}
}
}

9419
vendor/golang.org/x/net/publicsuffix/table.go generated vendored Normal file
View file

File diff suppressed because it is too large Load diff

16756
vendor/golang.org/x/net/publicsuffix/table_test.go generated vendored Normal file
View file

File diff suppressed because it is too large Load diff