Update tokenizer and parser logic to pass latest test suite

iabudiab · Apr 29, 2021 · 3d9f200 · 3d9f200
1 parent e79f96e
commit 3d9f200
Show file tree

Hide file tree

Showing 3 changed files with 114 additions and 114 deletions.
diff --git a/Sources/HTMLParser.m b/Sources/HTMLParser.m
@@ -1308,7 +1308,7 @@ - (void)processStartTagTokenInBody:(HTMLStartTagToken *)token
 		_framesetOkFlag = NO;
 	} else if ([tagName isEqualToString:@"a"]) {
 		HTMLElement *element = ^ HTMLElement * {
-            for (HTMLElement *element in self->_listOfActiveFormattingElements.reverseObjectEnumerator) {
+			for (HTMLElement *element in self->_listOfActiveFormattingElements.reverseObjectEnumerator) {
 				if ([element isEqual:[HTMLMarker marker]]) return nil;
 				if ([element.tagName isEqualToString:@"a"]) {
 					return element;
@@ -2513,13 +2513,13 @@ - (void)processTokenByApplyingRulesForParsingTokensInForeignContent:(HTMLToken *
 			[characters enumerateSubstringsInRange:NSMakeRange(0, characters.length)
 										   options:NSStringEnumerationByComposedCharacterSequences
 										usingBlock:^(NSString *substring, NSRange substringRange, NSRange enclosingRange, BOOL *stop) {
-											if ([substring isEqualToString:@"\uFFFD"]) {
-												[self emitParseError:@"Unexpected Character (0x0000) in foreign content"];
-											} else if (!substring.htmlkit_isHTMLWhitespaceString) {
-                                                self->_framesetOkFlag = NO;
-											}
-											[self insertCharacters:substring];
-										}];
+				if ([substring isEqualToString:@"\uFFFD"]) {
+					[self emitParseError:@"Unexpected Character (0x0000) in foreign content"];
+				} else if (!substring.htmlkit_isHTMLWhitespaceString) {
+					self->_framesetOkFlag = NO;
+				}
+				[self insertCharacters:substring];
+			}];
 
 			return;
 		}
@@ -2541,23 +2541,19 @@ - (void)processTokenByApplyingRulesForParsingTokensInForeignContent:(HTMLToken *
 				}
 				[self insertForeignElementForToken:token.asTagToken inNamespace:self.adjustedCurrentNode.htmlNamespace];
 				if (token.asTagToken.selfClosing) {
-                    [self->_stackOfOpenElements popCurrentNode];
+					[self->_stackOfOpenElements popCurrentNode];
 				}
 			};
 
 			void (^ matchedCase)(void) = ^ {
 				[self emitParseError:@"Unexpected start tag <%@> in foreign content", token.asTagToken.tagName];
-                if (self->_fragmentParsingAlgorithm) {
-					anythingElse();
-				} else {
-                    [self->_stackOfOpenElements popCurrentNode];
-					while (!IsNodeMathMLTextIntegrationPoint(self.currentNode) &&
-						   !IsNodeHTMLIntegrationPoint(self.currentNode) &&
-						   self.currentNode.htmlNamespace != HTMLNamespaceHTML) {
-                        [self->_stackOfOpenElements popCurrentNode];
-					}
-					[self reprocessToken:token];
+
+				while (!IsNodeMathMLTextIntegrationPoint(self.currentNode) &&
+					   !IsNodeHTMLIntegrationPoint(self.currentNode) &&
+					   self.currentNode.htmlNamespace != HTMLNamespaceHTML) {
+					[self->_stackOfOpenElements popCurrentNode];
 				}
+				[self processToken:token byApplyingRulesForInsertionMode:HTMLInsertionModeInBody];
 			};
 
 			if ([token.asTagToken.tagName isEqualToAny:@"b", @"big", @"blockquote", @"body", @"br",

diff --git a/Sources/HTMLTokenizer.m b/Sources/HTMLTokenizer.m
@@ -2413,6 +2413,7 @@ - (void)HTMLTokenizerStateNamedCharacterReference
 						  usingComparator:^ NSComparisonResult (id obj1, id obj2) { return [obj1 compare:obj2]; }];
 
 		if (searchIndex >= entities.count || ![[entities objectAtIndex:searchIndex] hasPrefix:name]) {
+			[name setString:[name substringToIndex:name.length -1]];
 			break;
 		}
 

diff --git a/Sources/include/HTMLElementAdjustment.h b/Sources/include/HTMLElementAdjustment.h
@@ -29,64 +29,66 @@ NS_INLINE void AdjustSVGAttributes(HTMLTagToken *token)
 		return;
 	}
 
-	NSDictionary *replacements = @{@"attributename": @"attributeName",
-								   @"attributetype": @"attributeType",
-								   @"basefrequency": @"baseFrequency",
-								   @"baseprofile": @"baseProfile",
-								   @"calcmode": @"calcMode",
-								   @"clippathunits": @"clipPathUnits",
-								   @"diffuseconstant": @"diffuseConstant",
-								   @"edgemode": @"edgeMode",
-								   @"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"};
+	NSDictionary *replacements = @{
+		@"attributename": @"attributeName",
+		@"attributetype": @"attributeType",
+		@"basefrequency": @"baseFrequency",
+		@"baseprofile": @"baseProfile",
+		@"calcmode": @"calcMode",
+		@"clippathunits": @"clipPathUnits",
+		@"diffuseconstant": @"diffuseConstant",
+		@"edgemode": @"edgeMode",
+		@"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"
+	};
 
 	HTMLOrderedDictionary *adjusted = [HTMLOrderedDictionary new];
 	for (id key in token.attributes) {
@@ -99,43 +101,44 @@ NS_INLINE void AdjustSVGAttributes(HTMLTagToken *token)
 NS_INLINE void AdjustSVGNameCase(HTMLTagToken *token)
 {
 	NSDictionary *replacements = @{
-								   @"altglyph": @"altGlyph",
-								   @"altglyphdef": @"altGlyphDef",
-								   @"altglyphitem": @"altGlyphItem",
-								   @"animatecolor": @"animateColor",
-								   @"animatemotion": @"animateMotion",
-								   @"animatetransform": @"animateTransform",
-								   @"clippath": @"clipPath",
-								   @"feblend": @"feBlend",
-								   @"fecolormatrix": @"feColorMatrix",
-								   @"fecomponenttransfer": @"feComponentTransfer",
-								   @"fecomposite": @"feComposite",
-								   @"feconvolvematrix": @"feConvolveMatrix",
-								   @"fediffuselighting": @"feDiffuseLighting",
-								   @"fedisplacementmap": @"feDisplacementMap",
-								   @"fedistantlight": @"feDistantLight",
-								   @"fedropshadow": @"feDropShadow",
-								   @"feflood": @"feFlood",
-								   @"fefunca": @"feFuncA",
-								   @"fefuncb": @"feFuncB",
-								   @"fefuncg": @"feFuncG",
-								   @"fefuncr": @"feFuncR",
-								   @"fegaussianblur": @"feGaussianBlur",
-								   @"feimage": @"feImage",
-								   @"femerge": @"feMerge",
-								   @"femergenode": @"feMergeNode",
-								   @"femorphology": @"feMorphology",
-								   @"feoffset": @"feOffset",
-								   @"fepointlight": @"fePointLight",
-								   @"fespecularlighting": @"feSpecularLighting",
-								   @"fespotlight": @"feSpotLight",
-								   @"fetile": @"feTile",
-								   @"feturbulence": @"feTurbulence",
-								   @"foreignobject": @"foreignObject",
-								   @"glyphref": @"glyphRef",
-								   @"lineargradient": @"linearGradient",
-								   @"radialgradient": @"radialGradient",
-								   @"textpath": @"textPath"};
+		@"altglyph": @"altGlyph",
+		@"altglyphdef": @"altGlyphDef",
+		@"altglyphitem": @"altGlyphItem",
+		@"animatecolor": @"animateColor",
+		@"animatemotion": @"animateMotion",
+		@"animatetransform": @"animateTransform",
+		@"clippath": @"clipPath",
+		@"feblend": @"feBlend",
+		@"fecolormatrix": @"feColorMatrix",
+		@"fecomponenttransfer": @"feComponentTransfer",
+		@"fecomposite": @"feComposite",
+		@"feconvolvematrix": @"feConvolveMatrix",
+		@"fediffuselighting": @"feDiffuseLighting",
+		@"fedisplacementmap": @"feDisplacementMap",
+		@"fedistantlight": @"feDistantLight",
+		@"fedropshadow": @"feDropShadow",
+		@"feflood": @"feFlood",
+		@"fefunca": @"feFuncA",
+		@"fefuncb": @"feFuncB",
+		@"fefuncg": @"feFuncG",
+		@"fefuncr": @"feFuncR",
+		@"fegaussianblur": @"feGaussianBlur",
+		@"feimage": @"feImage",
+		@"femerge": @"feMerge",
+		@"femergenode": @"feMergeNode",
+		@"femorphology": @"feMorphology",
+		@"feoffset": @"feOffset",
+		@"fepointlight": @"fePointLight",
+		@"fespecularlighting": @"feSpecularLighting",
+		@"fespotlight": @"feSpotLight",
+		@"fetile": @"feTile",
+		@"feturbulence": @"feTurbulence",
+		@"foreignobject": @"foreignObject",
+		@"glyphref": @"glyphRef",
+		@"lineargradient": @"linearGradient",
+		@"radialgradient": @"radialGradient",
+		@"textpath": @"textPath"
+	};
 
 	NSString *replacement = replacements[token.tagName] ?: token.tagName;
 	token.tagName = replacement;
-Original file line number
+Diff line change
@@ Expand Up / @@ -2413,6 +2413,7 @@ - (void)HTMLTokenizerStateNamedCharacterReference @@
     						  usingComparator:^ NSComparisonResult (id obj1, id obj2) { return [obj1 compare:obj2]; }];
     		if (searchIndex >= entities.count || ![[entities objectAtIndex:searchIndex] hasPrefix:name]) {
+    			[name setString:[name substringToIndex:name.length -1]];
     			break;
     		}
@@ Expand Down @@