exp/html: make inBodyIM match spec

This CL corrects the remaining differences that I could find between the
implementation of inBodyIM and the spec:

Handle <rp> and <rt>.

Adjust SVG and MathML attributes.

Reconstruct active formatting elements in the "any other start tag" case.

Pass 7 additional tests.

R=nigeltao
CC=golang-dev
https://golang.org/cl/6101055

src/pkg/exp/html/foreign.go

@@ -8,6 +8,14 @@ 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' {
@@ -129,4 +137,72 @@ var svgTagNameAdjustments = map[string]string{
 	"textpath":            "textPath",
 }
 
-// TODO: add look-up tables for MathML and SVG attribute adjustments.
+// 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",
+}

src/pkg/exp/html/parse.go

@@ -813,18 +813,6 @@ func inBodyIM(p *parser) bool {
 			p.oe.pop()
 			p.acknowledgeSelfClosingTag()
 			p.framesetOK = false
-		case "select":
-			p.reconstructActiveFormattingElements()
-			p.addElement(p.tok.Data, p.tok.Attr)
-			p.framesetOK = false
-			p.im = inSelectIM
-			return true
-		case "optgroup", "option":
-			if p.top().Data == "option" {
-				p.oe.pop()
-			}
-			p.reconstructActiveFormattingElements()
-			p.addElement(p.tok.Data, p.tok.Attr)
 		case "image":
 			p.tok.Data = "img"
 			return false
@@ -887,12 +875,29 @@ func inBodyIM(p *parser) bool {
 			p.addElement(p.tok.Data, p.tok.Attr)
 			p.setOriginalIM()
 			p.im = textIM
+		case "select":
+			p.reconstructActiveFormattingElements()
+			p.addElement(p.tok.Data, p.tok.Attr)
+			p.framesetOK = false
+			p.im = inSelectIM
+			return true
+		case "optgroup", "option":
+			if p.top().Data == "option" {
+				p.oe.pop()
+			}
+			p.reconstructActiveFormattingElements()
+			p.addElement(p.tok.Data, p.tok.Attr)
+		case "rp", "rt":
+			if p.elementInScope(defaultScope, "ruby") {
+				p.generateImpliedEndTags()
+			}
+			p.addElement(p.tok.Data, p.tok.Attr)
 		case "math", "svg":
 			p.reconstructActiveFormattingElements()
 			if p.tok.Data == "math" {
-				// TODO: adjust MathML attributes.
+				adjustAttributeNames(p.tok.Attr, mathMLAttributeAdjustments)
 			} else {
-				// TODO: adjust SVG attributes.
+				adjustAttributeNames(p.tok.Attr, svgAttributeAdjustments)
 			}
 			adjustForeignAttributes(p.tok.Attr)
 			p.addElement(p.tok.Data, p.tok.Attr)
@@ -901,7 +906,7 @@ func inBodyIM(p *parser) bool {
 		case "caption", "col", "colgroup", "frame", "head", "tbody", "td", "tfoot", "th", "thead", "tr":
 			// Ignore the token.
 		default:
-			// TODO.
+			p.reconstructActiveFormattingElements()
 			p.addElement(p.tok.Data, p.tok.Attr)
 		}
 	case EndTagToken:
@@ -1785,14 +1790,14 @@ func parseForeignContent(p *parser) bool {
 		}
 		switch p.top().Namespace {
 		case "math":
-			// TODO: adjust MathML attributes.
+			adjustAttributeNames(p.tok.Attr, mathMLAttributeAdjustments)
 		case "svg":
 			// Adjust SVG tag names. The tokenizer lower-cases tag names, but
 			// SVG wants e.g. "foreignObject" with a capital second "O".
 			if x := svgTagNameAdjustments[p.tok.Data]; x != "" {
 				p.tok.Data = x
 			}
-			// TODO: adjust SVG attributes.
+			adjustAttributeNames(p.tok.Attr, svgAttributeAdjustments)
 		default:
 			panic("html: bad parser state: unexpected namespace")
 		}

src/pkg/exp/html/testlogs/tests11.dat.log

@@ -1,6 +1,6 @@
-FAIL "<!DOCTYPE html><body><svg attributeName='' attributeType='' baseFrequency='' baseProfile='' calcMode='' clipPathUnits='' contentScriptType='' contentStyleType='' diffuseConstant='' edgeMode='' externalResourcesRequired='' filterRes='' filterUnits='' glyphRef='' gradientTransform='' gradientUnits='' kernelMatrix='' kernelUnitLength='' keyPoints='' keySplines='' keyTimes='' lengthAdjust='' limitingConeAngle='' markerHeight='' markerUnits='' markerWidth='' maskContentUnits='' maskUnits='' numOctaves='' pathLength='' patternContentUnits='' patternTransform='' patternUnits='' pointsAtX='' pointsAtY='' pointsAtZ='' preserveAlpha='' preserveAspectRatio='' primitiveUnits='' refX='' refY='' repeatCount='' repeatDur='' requiredExtensions='' requiredFeatures='' specularConstant='' specularExponent='' spreadMethod='' startOffset='' stdDeviation='' stitchTiles='' surfaceScale='' systemLanguage='' tableValues='' targetX='' targetY='' textLength='' viewBox='' viewTarget='' xChannelSelector='' yChannelSelector='' zoomAndPan=''></svg>"
+PASS "<!DOCTYPE html><body><svg attributeName='' attributeType='' baseFrequency='' baseProfile='' calcMode='' clipPathUnits='' contentScriptType='' contentStyleType='' diffuseConstant='' edgeMode='' externalResourcesRequired='' filterRes='' filterUnits='' glyphRef='' gradientTransform='' gradientUnits='' kernelMatrix='' kernelUnitLength='' keyPoints='' keySplines='' keyTimes='' lengthAdjust='' limitingConeAngle='' markerHeight='' markerUnits='' markerWidth='' maskContentUnits='' maskUnits='' numOctaves='' pathLength='' patternContentUnits='' patternTransform='' patternUnits='' pointsAtX='' pointsAtY='' pointsAtZ='' preserveAlpha='' preserveAspectRatio='' primitiveUnits='' refX='' refY='' repeatCount='' repeatDur='' requiredExtensions='' requiredFeatures='' specularConstant='' specularExponent='' spreadMethod='' startOffset='' stdDeviation='' stitchTiles='' surfaceScale='' systemLanguage='' tableValues='' targetX='' targetY='' textLength='' viewBox='' viewTarget='' xChannelSelector='' yChannelSelector='' zoomAndPan=''></svg>"
-FAIL "<!DOCTYPE html><BODY><SVG ATTRIBUTENAME='' ATTRIBUTETYPE='' BASEFREQUENCY='' BASEPROFILE='' CALCMODE='' CLIPPATHUNITS='' CONTENTSCRIPTTYPE='' CONTENTSTYLETYPE='' DIFFUSECONSTANT='' EDGEMODE='' EXTERNALRESOURCESREQUIRED='' FILTERRES='' FILTERUNITS='' GLYPHREF='' GRADIENTTRANSFORM='' GRADIENTUNITS='' KERNELMATRIX='' KERNELUNITLENGTH='' KEYPOINTS='' KEYSPLINES='' KEYTIMES='' LENGTHADJUST='' LIMITINGCONEANGLE='' MARKERHEIGHT='' MARKERUNITS='' MARKERWIDTH='' MASKCONTENTUNITS='' MASKUNITS='' NUMOCTAVES='' PATHLENGTH='' PATTERNCONTENTUNITS='' PATTERNTRANSFORM='' PATTERNUNITS='' POINTSATX='' POINTSATY='' POINTSATZ='' PRESERVEALPHA='' PRESERVEASPECTRATIO='' PRIMITIVEUNITS='' REFX='' REFY='' REPEATCOUNT='' REPEATDUR='' REQUIREDEXTENSIONS='' REQUIREDFEATURES='' SPECULARCONSTANT='' SPECULAREXPONENT='' SPREADMETHOD='' STARTOFFSET='' STDDEVIATION='' STITCHTILES='' SURFACESCALE='' SYSTEMLANGUAGE='' TABLEVALUES='' TARGETX='' TARGETY='' TEXTLENGTH='' VIEWBOX='' VIEWTARGET='' XCHANNELSELECTOR='' YCHANNELSELECTOR='' ZOOMANDPAN=''></SVG>"
+PASS "<!DOCTYPE html><BODY><SVG ATTRIBUTENAME='' ATTRIBUTETYPE='' BASEFREQUENCY='' BASEPROFILE='' CALCMODE='' CLIPPATHUNITS='' CONTENTSCRIPTTYPE='' CONTENTSTYLETYPE='' DIFFUSECONSTANT='' EDGEMODE='' EXTERNALRESOURCESREQUIRED='' FILTERRES='' FILTERUNITS='' GLYPHREF='' GRADIENTTRANSFORM='' GRADIENTUNITS='' KERNELMATRIX='' KERNELUNITLENGTH='' KEYPOINTS='' KEYSPLINES='' KEYTIMES='' LENGTHADJUST='' LIMITINGCONEANGLE='' MARKERHEIGHT='' MARKERUNITS='' MARKERWIDTH='' MASKCONTENTUNITS='' MASKUNITS='' NUMOCTAVES='' PATHLENGTH='' PATTERNCONTENTUNITS='' PATTERNTRANSFORM='' PATTERNUNITS='' POINTSATX='' POINTSATY='' POINTSATZ='' PRESERVEALPHA='' PRESERVEASPECTRATIO='' PRIMITIVEUNITS='' REFX='' REFY='' REPEATCOUNT='' REPEATDUR='' REQUIREDEXTENSIONS='' REQUIREDFEATURES='' SPECULARCONSTANT='' SPECULAREXPONENT='' SPREADMETHOD='' STARTOFFSET='' STDDEVIATION='' STITCHTILES='' SURFACESCALE='' SYSTEMLANGUAGE='' TABLEVALUES='' TARGETX='' TARGETY='' TEXTLENGTH='' VIEWBOX='' VIEWTARGET='' XCHANNELSELECTOR='' YCHANNELSELECTOR='' ZOOMANDPAN=''></SVG>"
-FAIL "<!DOCTYPE html><body><svg attributename='' attributetype='' basefrequency='' baseprofile='' calcmode='' clippathunits='' contentscripttype='' contentstyletype='' diffuseconstant='' edgemode='' externalresourcesrequired='' filterres='' filterunits='' glyphref='' gradienttransform='' gradientunits='' kernelmatrix='' kernelunitlength='' keypoints='' keysplines='' keytimes='' lengthadjust='' limitingconeangle='' markerheight='' markerunits='' markerwidth='' maskcontentunits='' maskunits='' numoctaves='' pathlength='' patterncontentunits='' patterntransform='' patternunits='' pointsatx='' pointsaty='' pointsatz='' preservealpha='' preserveaspectratio='' primitiveunits='' refx='' refy='' repeatcount='' repeatdur='' requiredextensions='' requiredfeatures='' specularconstant='' specularexponent='' spreadmethod='' startoffset='' stddeviation='' stitchtiles='' surfacescale='' systemlanguage='' tablevalues='' targetx='' targety='' textlength='' viewbox='' viewtarget='' xchannelselector='' ychannelselector='' zoomandpan=''></svg>"
+PASS "<!DOCTYPE html><body><svg attributename='' attributetype='' basefrequency='' baseprofile='' calcmode='' clippathunits='' contentscripttype='' contentstyletype='' diffuseconstant='' edgemode='' externalresourcesrequired='' filterres='' filterunits='' glyphref='' gradienttransform='' gradientunits='' kernelmatrix='' kernelunitlength='' keypoints='' keysplines='' keytimes='' lengthadjust='' limitingconeangle='' markerheight='' markerunits='' markerwidth='' maskcontentunits='' maskunits='' numoctaves='' pathlength='' patterncontentunits='' patterntransform='' patternunits='' pointsatx='' pointsaty='' pointsatz='' preservealpha='' preserveaspectratio='' primitiveunits='' refx='' refy='' repeatcount='' repeatdur='' requiredextensions='' requiredfeatures='' specularconstant='' specularexponent='' spreadmethod='' startoffset='' stddeviation='' stitchtiles='' surfacescale='' systemlanguage='' tablevalues='' targetx='' targety='' textlength='' viewbox='' viewtarget='' xchannelselector='' ychannelselector='' zoomandpan=''></svg>"
 PASS "<!DOCTYPE html><body><math attributeName='' attributeType='' baseFrequency='' baseProfile='' calcMode='' clipPathUnits='' contentScriptType='' contentStyleType='' diffuseConstant='' edgeMode='' externalResourcesRequired='' filterRes='' filterUnits='' glyphRef='' gradientTransform='' gradientUnits='' kernelMatrix='' kernelUnitLength='' keyPoints='' keySplines='' keyTimes='' lengthAdjust='' limitingConeAngle='' markerHeight='' markerUnits='' markerWidth='' maskContentUnits='' maskUnits='' numOctaves='' pathLength='' patternContentUnits='' patternTransform='' patternUnits='' pointsAtX='' pointsAtY='' pointsAtZ='' preserveAlpha='' preserveAspectRatio='' primitiveUnits='' refX='' refY='' repeatCount='' repeatDur='' requiredExtensions='' requiredFeatures='' specularConstant='' specularExponent='' spreadMethod='' startOffset='' stdDeviation='' stitchTiles='' surfaceScale='' systemLanguage='' tableValues='' targetX='' targetY='' textLength='' viewBox='' viewTarget='' xChannelSelector='' yChannelSelector='' zoomAndPan=''></math>"
 PASS "<!DOCTYPE html><body><svg><altGlyph /><altGlyphDef /><altGlyphItem /><animateColor /><animateMotion /><animateTransform /><clipPath /><feBlend /><feColorMatrix /><feComponentTransfer /><feComposite /><feConvolveMatrix /><feDiffuseLighting /><feDisplacementMap /><feDistantLight /><feFlood /><feFuncA /><feFuncB /><feFuncG /><feFuncR /><feGaussianBlur /><feImage /><feMerge /><feMergeNode /><feMorphology /><feOffset /><fePointLight /><feSpecularLighting /><feSpotLight /><feTile /><feTurbulence /><foreignObject /><glyphRef /><linearGradient /><radialGradient /><textPath /></svg>"
 PASS "<!DOCTYPE html><body><svg><altglyph /><altglyphdef /><altglyphitem /><animatecolor /><animatemotion /><animatetransform /><clippath /><feblend /><fecolormatrix /><fecomponenttransfer /><fecomposite /><feconvolvematrix /><fediffuselighting /><fedisplacementmap /><fedistantlight /><feflood /><fefunca /><fefuncb /><fefuncg /><fefuncr /><fegaussianblur /><feimage /><femerge /><femergenode /><femorphology /><feoffset /><fepointlight /><fespecularlighting /><fespotlight /><fetile /><feturbulence /><foreignobject /><glyphref /><lineargradient /><radialgradient /><textpath /></svg>"

src/pkg/exp/html/testlogs/tests16.dat.log

@@ -185,5 +185,5 @@ PASS "<iframe>...<!--X->...<!--/X->...</iframe>"
 PASS "<xmp><!--<xmp></xmp>--></xmp>"
 PASS "<noembed><!--<noembed></noembed>--></noembed>"
 FAIL "<!doctype html><table>"
-FAIL "<!doctype html><table><td><span><font></span><span>"
+PASS "<!doctype html><table><td><span><font></span><span>"
 FAIL "<!doctype html><form><table></form><form></table></form>"

src/pkg/exp/html/testlogs/tests19.dat.log

@@ -1,4 +1,4 @@
-FAIL "<!doctype html><math><mn DefinitionUrl=\"foo\">"
+PASS "<!doctype html><math><mn DefinitionUrl=\"foo\">"
 PASS "<!doctype html><html></p><!--foo-->"
 PASS "<!doctype html><head></head></p><!--foo-->"
 PASS "<!doctype html><body><p><pre>"
@@ -10,10 +10,10 @@ PASS "<!doctype html><isindex action=\"POST\">"
 PASS "<!doctype html><isindex prompt=\"this is isindex\">"
 PASS "<!doctype html><isindex type=\"hidden\">"
 PASS "<!doctype html><isindex name=\"foo\">"
-FAIL "<!doctype html><ruby><p><rp>"
+PASS "<!doctype html><ruby><p><rp>"
 FAIL "<!doctype html><ruby><div><span><rp>"
 FAIL "<!doctype html><ruby><div><p><rp>"
-FAIL "<!doctype html><ruby><p><rt>"
+PASS "<!doctype html><ruby><p><rt>"
 FAIL "<!doctype html><ruby><div><span><rt>"
 FAIL "<!doctype html><ruby><div><p><rt>"
 PASS "<!doctype html><math/><foo>"