示例#1
0
func extractACMeta(r io.Reader) []acMeta {
	var meta []acMeta

	z := html.NewTokenizer(r)

	for {
		switch z.Next() {
		case html.ErrorToken:
			return meta

		case html.StartTagToken, html.SelfClosingTagToken:
			tok := z.Token()
			if tok.DataAtom == atom.Meta {
				meta = appendMeta(meta, tok.Attr)
			}
		}
	}
}
示例#2
0
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
			}
		}
	}
}