html: handle rb and rtc elements
Updates golang/go#23071
Change-Id: Ifef79e077801422eb273af3e5a541c85c63bfce4
Reviewed-on: https://go-review.googlesource.com/107575
Reviewed-by: Nigel Tao <nigeltao@golang.org>
diff --git a/html/parse.go b/html/parse.go
index d9cd147..d23e05e 100644
--- a/html/parse.go
+++ b/html/parse.go
@@ -185,7 +185,7 @@
}
// generateImpliedEndTags pops nodes off the stack of open elements as long as
-// the top node has a tag name of dd, dt, li, optgroup, option, p, rp, or rt.
+// the top node has a tag name of dd, dt, li, optgroup, option, p, rb, rp, rt or rtc.
// If exceptions are specified, nodes with that name will not be popped off.
func (p *parser) generateImpliedEndTags(exceptions ...string) {
var i int
@@ -194,9 +194,7 @@
n := p.oe[i]
if n.Type == ElementNode {
switch n.DataAtom {
- // TODO: add a.Rb and a.Rtc, to match the spec. This needs additions to the
- // atom package. Ditto for generateAllImpliedEndTags.
- case a.Dd, a.Dt, a.Li, a.Optgroup, a.Option, a.P, a.Rp, a.Rt:
+ case a.Dd, a.Dt, a.Li, a.Optgroup, a.Option, a.P, a.Rb, a.Rp, a.Rt, a.Rtc:
for _, except := range exceptions {
if n.Data == except {
break loop
@@ -212,8 +210,8 @@
}
// generateAllImpliedEndTags pops nodes off the stack of open elements as long as
-// the top node has a tag name of caption, colgroup, dd, div, dt, li, optgroup, option, p, rp, rt,
-// span, tbody, td, tfoot, th, thead or tr.
+// the top node has a tag name of caption, colgroup, dd, div, dt, li, optgroup, option, p, rb,
+// rp, rt, rtc, span, tbody, td, tfoot, th, thead or tr.
func (p *parser) generateAllImpliedEndTags() {
var i int
for i = len(p.oe) - 1; i >= 0; i-- {
@@ -221,8 +219,8 @@
if n.Type == ElementNode {
switch n.DataAtom {
// TODO: remove this divergence from the HTML5 spec
- case a.Caption, a.Colgroup, a.Dd, a.Div, a.Dt, a.Li, a.Optgroup, a.Option, a.P, a.Rp, a.Rt,
- a.Span, a.Tbody, a.Td, a.Tfoot, a.Th, a.Thead, a.Tr:
+ case a.Caption, a.Colgroup, a.Dd, a.Div, a.Dt, a.Li, a.Optgroup, a.Option, a.P, a.Rb,
+ a.Rp, a.Rt, a.Rtc, a.Span, a.Tbody, a.Td, a.Tfoot, a.Th, a.Thead, a.Tr:
continue
}
}
@@ -1047,11 +1045,16 @@
}
p.reconstructActiveFormattingElements()
p.addElement()
- case a.Rp, a.Rt:
+ case a.Rb, a.Rtc:
if p.elementInScope(defaultScope, a.Ruby) {
p.generateImpliedEndTags()
}
p.addElement()
+ case a.Rp, a.Rt:
+ if p.elementInScope(defaultScope, a.Ruby) {
+ p.generateImpliedEndTags("rtc")
+ }
+ p.addElement()
case a.Math, a.Svg:
p.reconstructActiveFormattingElements()
if p.tok.DataAtom == a.Math {
@@ -1153,9 +1156,8 @@
return false
} else {
for _, e := range p.oe {
- // TODO(namusyaka): rb and rtc elements should be added after updating atom.
switch e.DataAtom {
- case a.Dd, a.Dt, a.Li, a.Optgroup, a.Option, a.P, a.Rp, a.Rt, a.Tbody, a.Td, a.Tfoot, a.Th,
+ case a.Dd, a.Dt, a.Li, a.Optgroup, a.Option, a.P, a.Rb, a.Rp, a.Rt, a.Rtc, a.Tbody, a.Td, a.Tfoot, a.Th,
a.Thead, a.Tr, a.Body, a.Html:
default:
return true
diff --git a/html/testdata/webkit/ruby.dat b/html/testdata/webkit/ruby.dat
new file mode 100644
index 0000000..1ca8016
--- /dev/null
+++ b/html/testdata/webkit/ruby.dat
@@ -0,0 +1,298 @@
+#data
+<html><ruby>a<rb>b<rb></ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| "a"
+| <rb>
+| "b"
+| <rb>
+
+#data
+<html><ruby>a<rb>b<rt></ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| "a"
+| <rb>
+| "b"
+| <rt>
+
+#data
+<html><ruby>a<rb>b<rtc></ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| "a"
+| <rb>
+| "b"
+| <rtc>
+
+#data
+<html><ruby>a<rb>b<rp></ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| "a"
+| <rb>
+| "b"
+| <rp>
+
+#data
+<html><ruby>a<rb>b<span></ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| "a"
+| <rb>
+| "b"
+| <span>
+
+#data
+<html><ruby>a<rt>b<rb></ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| "a"
+| <rt>
+| "b"
+| <rb>
+
+#data
+<html><ruby>a<rt>b<rt></ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| "a"
+| <rt>
+| "b"
+| <rt>
+
+#data
+<html><ruby>a<rt>b<rtc></ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| "a"
+| <rt>
+| "b"
+| <rtc>
+
+#data
+<html><ruby>a<rt>b<rp></ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| "a"
+| <rt>
+| "b"
+| <rp>
+
+#data
+<html><ruby>a<rt>b<span></ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| "a"
+| <rt>
+| "b"
+| <span>
+
+#data
+<html><ruby>a<rtc>b<rb></ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| "a"
+| <rtc>
+| "b"
+| <rb>
+
+#data
+<html><ruby>a<rtc>b<rt>c<rt>d</ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| "a"
+| <rtc>
+| "b"
+| <rt>
+| "c"
+| <rt>
+| "d"
+
+#data
+<html><ruby>a<rtc>b<rtc></ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| "a"
+| <rtc>
+| "b"
+| <rtc>
+
+#data
+<html><ruby>a<rtc>b<rp></ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| "a"
+| <rtc>
+| "b"
+| <rp>
+
+#data
+<html><ruby>a<rtc>b<span></ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| "a"
+| <rtc>
+| "b"
+| <span>
+
+#data
+<html><ruby>a<rp>b<rb></ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| "a"
+| <rp>
+| "b"
+| <rb>
+
+#data
+<html><ruby>a<rp>b<rt></ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| "a"
+| <rp>
+| "b"
+| <rt>
+
+#data
+<html><ruby>a<rp>b<rtc></ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| "a"
+| <rp>
+| "b"
+| <rtc>
+
+#data
+<html><ruby>a<rp>b<rp></ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| "a"
+| <rp>
+| "b"
+| <rp>
+
+#data
+<html><ruby>a<rp>b<span></ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| "a"
+| <rp>
+| "b"
+| <span>
+
+#data
+<html><ruby><rtc><ruby>a<rb>b<rt></ruby></ruby></html>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+#document
+| <html>
+| <head>
+| <body>
+| <ruby>
+| <rtc>
+| <ruby>
+| "a"
+| <rb>
+| "b"
+| <rt>