in libgo/go/encoding/xml/xml.go [552:852]
func (d *Decoder) rawToken() (Token, error) {
if d.t != nil {
return d.t.Token()
}
if d.err != nil {
return nil, d.err
}
if d.needClose {
// The last element we read was self-closing and
// we returned just the StartElement half.
// Return the EndElement half now.
d.needClose = false
return EndElement{d.toClose}, nil
}
b, ok := d.getc()
if !ok {
return nil, d.err
}
if b != '<' {
// Text section.
d.ungetc(b)
data := d.text(-1, false)
if data == nil {
return nil, d.err
}
return CharData(data), nil
}
if b, ok = d.mustgetc(); !ok {
return nil, d.err
}
switch b {
case '/':
// </: End element
var name Name
if name, ok = d.nsname(); !ok {
if d.err == nil {
d.err = d.syntaxError("expected element name after </")
}
return nil, d.err
}
d.space()
if b, ok = d.mustgetc(); !ok {
return nil, d.err
}
if b != '>' {
d.err = d.syntaxError("invalid characters between </" + name.Local + " and >")
return nil, d.err
}
return EndElement{name}, nil
case '?':
// <?: Processing instruction.
var target string
if target, ok = d.name(); !ok {
if d.err == nil {
d.err = d.syntaxError("expected target name after <?")
}
return nil, d.err
}
d.space()
d.buf.Reset()
var b0 byte
for {
if b, ok = d.mustgetc(); !ok {
return nil, d.err
}
d.buf.WriteByte(b)
if b0 == '?' && b == '>' {
break
}
b0 = b
}
data := d.buf.Bytes()
data = data[0 : len(data)-2] // chop ?>
if target == "xml" {
content := string(data)
ver := procInst("version", content)
if ver != "" && ver != "1.0" {
d.err = fmt.Errorf("xml: unsupported version %q; only version 1.0 is supported", ver)
return nil, d.err
}
enc := procInst("encoding", content)
if enc != "" && enc != "utf-8" && enc != "UTF-8" && !strings.EqualFold(enc, "utf-8") {
if d.CharsetReader == nil {
d.err = fmt.Errorf("xml: encoding %q declared but Decoder.CharsetReader is nil", enc)
return nil, d.err
}
newr, err := d.CharsetReader(enc, d.r.(io.Reader))
if err != nil {
d.err = fmt.Errorf("xml: opening charset %q: %v", enc, err)
return nil, d.err
}
if newr == nil {
panic("CharsetReader returned a nil Reader for charset " + enc)
}
d.switchToReader(newr)
}
}
return ProcInst{target, data}, nil
case '!':
// <!: Maybe comment, maybe CDATA.
if b, ok = d.mustgetc(); !ok {
return nil, d.err
}
switch b {
case '-': // <!-
// Probably <!-- for a comment.
if b, ok = d.mustgetc(); !ok {
return nil, d.err
}
if b != '-' {
d.err = d.syntaxError("invalid sequence <!- not part of <!--")
return nil, d.err
}
// Look for terminator.
d.buf.Reset()
var b0, b1 byte
for {
if b, ok = d.mustgetc(); !ok {
return nil, d.err
}
d.buf.WriteByte(b)
if b0 == '-' && b1 == '-' {
if b != '>' {
d.err = d.syntaxError(
`invalid sequence "--" not allowed in comments`)
return nil, d.err
}
break
}
b0, b1 = b1, b
}
data := d.buf.Bytes()
data = data[0 : len(data)-3] // chop -->
return Comment(data), nil
case '[': // <![
// Probably <![CDATA[.
for i := 0; i < 6; i++ {
if b, ok = d.mustgetc(); !ok {
return nil, d.err
}
if b != "CDATA["[i] {
d.err = d.syntaxError("invalid <![ sequence")
return nil, d.err
}
}
// Have <![CDATA[. Read text until ]]>.
data := d.text(-1, true)
if data == nil {
return nil, d.err
}
return CharData(data), nil
}
// Probably a directive: <!DOCTYPE ...>, <!ENTITY ...>, etc.
// We don't care, but accumulate for caller. Quoted angle
// brackets do not count for nesting.
d.buf.Reset()
d.buf.WriteByte(b)
inquote := uint8(0)
depth := 0
for {
if b, ok = d.mustgetc(); !ok {
return nil, d.err
}
if inquote == 0 && b == '>' && depth == 0 {
break
}
HandleB:
d.buf.WriteByte(b)
switch {
case b == inquote:
inquote = 0
case inquote != 0:
// in quotes, no special action
case b == '\'' || b == '"':
inquote = b
case b == '>' && inquote == 0:
depth--
case b == '<' && inquote == 0:
// Look for <!-- to begin comment.
s := "!--"
for i := 0; i < len(s); i++ {
if b, ok = d.mustgetc(); !ok {
return nil, d.err
}
if b != s[i] {
for j := 0; j < i; j++ {
d.buf.WriteByte(s[j])
}
depth++
goto HandleB
}
}
// Remove < that was written above.
d.buf.Truncate(d.buf.Len() - 1)
// Look for terminator.
var b0, b1 byte
for {
if b, ok = d.mustgetc(); !ok {
return nil, d.err
}
if b0 == '-' && b1 == '-' && b == '>' {
break
}
b0, b1 = b1, b
}
// Replace the comment with a space in the returned Directive
// body, so that markup parts that were separated by the comment
// (like a "<" and a "!") don't get joined when re-encoding the
// Directive, taking new semantic meaning.
d.buf.WriteByte(' ')
}
}
return Directive(d.buf.Bytes()), nil
}
// Must be an open element like <a href="foo">
d.ungetc(b)
var (
name Name
empty bool
attr []Attr
)
if name, ok = d.nsname(); !ok {
if d.err == nil {
d.err = d.syntaxError("expected element name after <")
}
return nil, d.err
}
attr = []Attr{}
for {
d.space()
if b, ok = d.mustgetc(); !ok {
return nil, d.err
}
if b == '/' {
empty = true
if b, ok = d.mustgetc(); !ok {
return nil, d.err
}
if b != '>' {
d.err = d.syntaxError("expected /> in element")
return nil, d.err
}
break
}
if b == '>' {
break
}
d.ungetc(b)
a := Attr{}
if a.Name, ok = d.nsname(); !ok {
if d.err == nil {
d.err = d.syntaxError("expected attribute name in element")
}
return nil, d.err
}
d.space()
if b, ok = d.mustgetc(); !ok {
return nil, d.err
}
if b != '=' {
if d.Strict {
d.err = d.syntaxError("attribute name without = in element")
return nil, d.err
}
d.ungetc(b)
a.Value = a.Name.Local
} else {
d.space()
data := d.attrval()
if data == nil {
return nil, d.err
}
a.Value = string(data)
}
attr = append(attr, a)
}
if empty {
d.needClose = true
d.toClose = name
}
return StartElement{name, attr}, nil
}