之前google开发了一个库,strip,后来不知为何(也许是嫌太重)丢到一边,下方是原库代码,将之复制到src/strip/strip.go里就可以跑起来。
// 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 strip
import (
"bytes"
"encoding/json"
"fmt"
"html"
"io"
"io/ioutil"
"path/filepath"
"reflect"
"strings"
"sync"
"text/template"
"text/template/parse"
"unicode"
"unicode/utf8"
)
// htmlNospaceEscaper escapes for inclusion in unquoted attribute values.
func htmlNospaceEscaper(args ...interface{}) string {
s, t := stringify(args...)
if t == contentTypeHTML {
return htmlReplacer(StripTags(s), htmlNospaceNormReplacementTable, false)
}
return htmlReplacer(s, htmlNospaceReplacementTable, false)
}
// attrEscaper escapes for inclusion in quoted attribute values.
func attrEscaper(args ...interface{}) string {
s, t := stringify(args...)
if t == contentTypeHTML {
return htmlReplacer(StripTags(s), htmlNormReplacementTable, true)
}
return htmlReplacer(s, htmlReplacementTable, true)
}
// rcdataEscaper escapes for inclusion in an RCDATA element body.
func rcdataEscaper(args ...interface{}) string {
s, t := stringify(args...)
if t == contentTypeHTML {
return htmlReplacer(s, htmlNormReplacementTable, true)
}
return htmlReplacer(s, htmlReplacementTable, true)
}
// htmlEscaper escapes for inclusion in HTML text.
func htmlEscaper(args ...interface{}) string {
s, t := stringify(args...)
if t == contentTypeHTML {
return s
}
return htmlReplacer(s, htmlReplacementTable, true)
}
// htmlReplacementTable contains the runes that need to be escaped
// inside a quoted attribute value or in a text node.
var htmlReplacementTable = []string{
// http://www.w3.org/TR/html5/syntax.html#attribute-value-(unquoted)-state
// U+0000 NULL Parse error. Append a U+FFFD REPLACEMENT
// CHARACTER character to the current attribute's value.
// "
// and similarly
// http://www.w3.org/TR/html5/syntax.html#before-attribute-value-state
0: "\uFFFD",
'"': """,
'&': "&",
'\'': "'",
'+': "+",
'<': "<",
'>': ">",
}
// htmlNormReplacementTable is like htmlReplacementTable but without '&' to
// avoid over-encoding existing entities.
var htmlNormReplacementTable = []string{
0: "\uFFFD",
'"': """,
'\'': "'",
'+': "+",
'<': "<",
'>': ">",
}
// htmlNospaceReplacementTable contains the runes that need to be escaped
// inside an unquoted attribute value.
// The set of runes escaped is the union of the HTML specials and
// those determined by running the JS below in browsers:
// <div id=d></div>
// <script>(function () {
// var a = [], d = document.getElementById("d"), i, c, s;
// for (i = 0; i < 0x10000; ++i) {
// c = String.fromCharCode(i);
// d.innerHTML = "<span title=" + c + "lt" + c + "></span>"
// s = d.getElementsByTagName("SPAN")[0];
// if (!s || s.title !== c + "lt" + c) { a.push(i.toString(16)); }
// }
// document.write(a.join(", "));
// })()</script>
var htmlNospaceReplacementTable = []string{
0: "�",
'\t': "	",
'\n': " ",
'\v': "",
'\f': "",
'\r': " ",
' ': " ",
'"': """,
'&': "&",
'\'': "'",
'+': "+",
'<': "<",
'=': "=",
'>': ">",
// A parse error in the attribute value (unquoted) and
// before attribute value states.
// Treated as a quoting character by IE.
'`': "`",
}
// htmlNospaceNormReplacementTable is like htmlNospaceReplacementTable but
// without '&' to avoid over-encoding existing entities.
var htmlNospaceNormReplacementTable = []string{
0: "�",
'\t': "	",
'\n': " ",
'\v': "",
'\f': "",
'\r': " ",
' ': " ",
'"': """,
'\'': "'",
'+': "+",
'<': "<",
'=': "=",
'>': ">",
// A parse error in the attribute value (unquoted) and
// before attribute value states.
// Treated as a quoting character by IE.
'`': "`",
}
// htmlReplacer returns s with runes replaced according to replacementTable
// and when badRunes is true, certain bad runes are allowed through unescaped.
func htmlReplacer(s string, replacementTable []string, badRunes bool) string {
written, b := 0, new(bytes.Buffer)
for i, r := range s {
if int(r) < len(replacementTable) {
if repl := replacementTable[r]; len(repl) != 0 {
b.WriteString(s[written:i])
b.WriteString(repl)
// Valid as long as replacementTable doesn't
// include anything above 0x7f.
written = i + utf8.RuneLen(r)
}
} else if badRunes {
// No-op.
// IE does not allow these ranges in unquoted attrs.
} else if 0xfdd0 <= r && r <= 0xfdef || 0xfff0 <= r && r <= 0xffff {
fmt.Fprintf(b, "%s&#x%x;", s[written:i], r)
written = i + utf8.RuneLen(r)
}
}
if written == 0 {
return s
}
b.WriteString(s[written:])
return b.String()
}
// stripTags takes a snippet of HTML and returns only the text content.
// For example, `<b>¡Hi!</b> <script>...</script>` -> `¡Hi! `.
func StripTags(html string) string {
var b bytes.Buffer
s, c, i, allText := []byte(html), context{}, 0, true
// Using the transition funcs helps us avoid mangling
// `<div title="1>2">` or `I <3 Ponies!`.
for i != len(s) {
if c.delim == delimNone {
st := c.state
// Use RCDATA instead of parsing into JS or CSS styles.
if c.element != elementNone && !isInTag(st) {
st = stateRCDATA
}
d, nread := transitionFunc[st](c, s[i:])
i1 := i + nread
if c.state == stateText || c.state == stateRCDATA {
// Emit text up to the start of the tag or comment.
j := i1
if d.state != c.state {
for j1 := j - 1; j1 >= i; j1-- {
if s[j1] == '<' {
j = j1
break
}
}
}
b.Write(s[i:j])
} else {
allText = false
}
c, i = d, i1
continue
}
i1 := i + bytes.IndexAny(s[i:], delimEnds[c.delim])
if i1 < i {
break
}
if c.delim != delimSpaceOrTagEnd {
// Consume any quote.
i1++
}
c, i = context{state: stateTag, element: c.element}, i1
}
if allText {
return html
} else if c.state == stateText || c.state == stateRCDATA {
b.Write(s[i:])
}
return b.String()
}
// htmlNameFilter accepts valid parts of an HTML attribute or tag name or
// a known-safe HTML attribute.
func htmlNameFilter(args ...interface{}) string {
s, t := stringify(args...)
if t == contentTypeHTMLAttr {
return s
}
if len(s) == 0 {
// Avoid violation of structure preservation.
// <input checked {{.K}}={{.V}}>.
// Without this, if .K is empty then .V is the value of
// checked, but otherwise .V is the value of the attribute
// named .K.
return filterFailsafe
}
s = strings.ToLower(s)
if t := attrType(s); t != contentTypePlain {
// TODO: Split attr and element name part filters so we can whitelist
// attributes.
return filterFailsafe
}
for _, r := range s {
switch {
case '0' <= r && r <= '9':
case 'a' <= r && r <= 'z':
default:
return filterFailsafe
}
}
return s
}
// commentEscaper returns the empty string regardless of input.
// Comment content does not correspond to any parsed structure or
// human-readable content, so the simplest and most secure policy is to drop
// content interpolated into comments.
// This approach is equally valid whether or not static comment content is
// removed from the template.
func commentEscaper(args ...interface{}) string {
return ""
}
// 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.
// context describes the state an HTML parser must be in when it reaches the
// portion of HTML produced by evaluating a particular template node.
//
// The zero value of type context is the start context for a template that
// produces an HTML fragment as defined at
// http://www.w3.org/TR/html5/syntax.html#the-end
// where the context element is null.
type context struct {
state state
delim delim
urlPart urlPart
jsCtx jsCtx
attr attr
element element
err *Error
}
func (c context) String() string {
return fmt.Sprintf("{%v %v %v %v %v %v %v}", c.state, c.delim, c.urlPart, c.jsCtx, c.attr, c.element, c.err)
}
// eq reports whether two contexts are equal.
func (c context) eq(d context) bool {
return c.state == d.state &&
c.delim == d.delim &&
c.urlPart == d.urlPart &&
c.jsCtx == d.jsCtx &&
c.attr == d.attr &&
c.element == d.element &&
c.err == d.err
}
// mangle produces an identifier that includes a suffix that distinguishes it
// from template names mangled with different contexts.
func (c context) mangle(templateName string) string {
// The mangled name for the default context is the input templateName.
if c.state == stateText {
return templateName
}
s := templateName + "$htmltemplate_" + c.state.String()
if c.delim != 0 {
s += "_" + c.delim.String()
}
if c.urlPart != 0 {
s += "_" + c.urlPart.String()
}
if c.jsCtx != 0 {
s += "_" + c.jsCtx.String()
}
if c.attr != 0 {
s += "_" + c.attr.String()
}
if c.element != 0 {
s += "_" + c.element.String()
}
return s
}
// state describes a high-level HTML parser state.
//
// It bounds the top of the element stack, and by extension the HTML insertion
// mode, but also contains state that does not correspond to anything in the
// HTML5 parsing algorithm because a single token production in the HTML
// grammar may contain embedded actions in a template. For instance, the quoted
// HTML attribute produced by
// <div title="Hello {{.World}}">
// is a single token in HTML's grammar but in a template spans several nodes.
type state uint8
const (
// stateText is parsed character data. An HTML parser is in
// this state when its parse position is outside an HTML tag,
// directive, comment, and special element body.
stateText state = iota
// stateTag occurs before an HTML attribute or the end of a tag.
stateTag
// stateAttrName occurs inside an attribute name.
// It occurs between the ^'s in ` ^name^ = value`.
stateAttrName
// stateAfterName occurs after an attr name has ended but before any
// equals sign. It occurs between the ^'s in ` name^ ^= value`.
stateAfterName
// stateBeforeValue occurs after the equals sign but before the value.
// It occurs between the ^'s in ` name =^ ^value`.
stateBeforeValue
// stateHTMLCmt occurs inside an <!-- HTML comment -->.
stateHTMLCmt
// stateRCDATA occurs inside an RCDATA element (<textarea> or <title>)
// as described at http://www.w3.org/TR/html5/syntax.html#elements-0
stateRCDATA
// stateAttr occurs inside an HTML attribute whose content is text.
stateAttr
// stateURL occurs inside an HTML attribute whose content is a URL.
stateURL
// stateJS occurs inside an event handler or script element.
stateJS
// stateJSDqStr occurs inside a JavaScript double quoted string.
stateJSDqStr
// stateJSSqStr occurs inside a JavaScript single quoted string.
stateJSSqStr
// stateJSRegexp occurs inside a JavaScript regexp literal.
stateJSRegexp
// stateJSBlockCmt occurs inside a JavaScript /* block comment */.
stateJSBlockCmt
// stateJSLineCmt occurs inside a JavaScript // line comment.
stateJSLineCmt
// stateCSS occurs inside a <style> element or style attribute.
stateCSS
// stateCSSDqStr occurs inside a CSS double quoted string.
stateCSSDqStr
// stateCSSSqStr occurs inside a CSS single quoted string.
stateCSSSqStr
// stateCSSDqURL occurs inside a CSS double quoted url("...").
stateCSSDqURL
// stateCSSSqURL occurs inside a CSS single quoted url('...').
stateCSSSqURL
// stateCSSURL occurs inside a CSS unquoted url(...).
stateCSSURL
// stateCSSBlockCmt occurs inside a CSS /* block comment */.
stateCSSBlockCmt
// stateCSSLineCmt occurs inside a CSS // line comment.
stateCSSLineCmt
// stateError is an infectious error state outside any valid
// HTML/CSS/JS construct.
stateError
)
var stateNames = [...]string{
stateText: "stateText",
stateTag: "stateTag",
stateAttrName: "stateAttrName",
stateAfterName: "stateAfterName",
stateBeforeValue: "stateBeforeValue",
stateHTMLCmt: "stateHTMLCmt",
stateRCDATA: "stateRCDATA",
stateAttr: "stateAttr",
stateURL: "stateURL",
stateJS: "stateJS",
stateJSDqStr: "stateJSDqStr",
stateJSSqStr: "stateJSSqStr",
stateJSRegexp: "stateJSRegexp",
stateJSBlockCmt: "stateJSBlockCmt",
stateJSLineCmt: "stateJSLineCmt",
stateCSS: "stateCSS",
stateCSSDqStr: "stateCSSDqStr",
stateCSSSqStr: "stateCSSSqStr",
stateCSSDqURL: "stateCSSDqURL",
stateCSSSqURL: "stateCSSSqURL",
stateCSSURL: "stateCSSURL",
stateCSSBlockCmt: "stateCSSBlockCmt",
stateCSSLineCmt: "stateCSSLineCmt",
stateError: "stateError",
}
func (s state) String() string {
if int(s) < len(stateNames) {
return stateNames[s]
}
return fmt.Sprintf("illegal state %d", int(s))
}
// isComment is true for any state that contains content meant for template
// authors & maintainers, not for end-users or machines.
func isComment(s state) bool {
switch s {
case stateHTMLCmt, stateJSBlockCmt, stateJSLineCmt, stateCSSBlockCmt, stateCSSLineCmt:
return true
}
return false
}
// isInTag return whether s occurs solely inside an HTML tag.
func isInTag(s state) bool {
switch s {
case stateTag, stateAttrName, stateAfterName, stateBeforeValue, stateAttr:
return true
}
return false
}
// delim is the delimiter that will end the current HTML attribute.
type delim uint8
const (
// delimNone occurs outside any attribute.
delimNone delim = iota
// delimDoubleQuote occurs when a double quote (") closes the attribute.
delimDoubleQuote
// delimSingleQuote occurs when a single quote (') closes the attribute.
delimSingleQuote
// delimSpaceOrTagEnd occurs when a space or right angle bracket (>)
// closes the attribute.
delimSpaceOrTagEnd
)
var delimNames = [...]string{
delimNone: "delimNone",
delimDoubleQuote: "delimDoubleQuote",
delimSingleQuote: "delimSingleQuote",
delimSpaceOrTagEnd: "delimSpaceOrTagEnd",
}
func (d delim) String() string {
if int(d) < len(delimNames) {
return delimNames[d]
}
return fmt.Sprintf("illegal delim %d", int(d))
}
// urlPart identifies a part in an RFC 3986 hierarchical URL to allow different
// encoding strategies.
type urlPart uint8
const (
// urlPartNone occurs when not in a URL, or possibly at the start:
// ^ in "^http://auth/path?k=v#frag".
urlPartNone urlPart = iota
// urlPartPreQuery occurs in the scheme, authority, or path; between the
// ^s in "h^ttp://auth/path^?k=v#frag".
urlPartPreQuery
// urlPartQueryOrFrag occurs in the query portion between the ^s in
// "http://auth/path?^k=v#frag^".
urlPartQueryOrFrag
// urlPartUnknown occurs due to joining of contexts both before and
// after the query separator.
urlPartUnknown
)
var urlPartNames = [...]string{
urlPartNone: "urlPartNone",
urlPartPreQuery: "urlPartPreQuery",
urlPartQueryOrFrag: "urlPartQueryOrFrag",
urlPartUnknown: "urlPartUnknown",
}
func (u urlPart) String() string {
if int(u) < len(urlPartNames) {
return urlPartNames[u]
}
return fmt.Sprintf("illegal urlPart %d", int(u))
}
// jsCtx determines whether a '/' starts a regular expression literal or a
// division operator.
type jsCtx uint8
const (
// jsCtxRegexp occurs where a '/' would start a regexp literal.
jsCtxRegexp jsCtx = iota
// jsCtxDivOp occurs where a '/' would start a division operator.
jsCtxDivOp
// jsCtxUnknown occurs where a '/' is ambiguous due to context joining.
jsCtxUnknown
)
func (c jsCtx) String() string {
switch c {
case jsCtxRegexp:
return "jsCtxRegexp"
case jsCtxDivOp:
return "jsCtxDivOp"
case jsCtxUnknown:
return "jsCtxUnknown"
}
return fmt.Sprintf("illegal jsCtx %d", int(c))
}
// element identifies the HTML element when inside a start tag or special body.
// Certain HTML element (for example <script> and <style>) have bodies that are
// treated differently from stateText so the element type is necessary to
// transition into the correct context at the end of a tag and to identify the
// end delimiter for the body.
type element uint8
const (
// elementNone occurs outside a special tag or special element body.
elementNone element = iota
// elementScript corresponds to the raw text <script> element.
elementScript
// elementStyle corresponds to the raw text <style> element.
elementStyle
// elementTextarea corresponds to the RCDATA <textarea> 
