Tokenizer
class Tokenizer { }
constructor(options: {
xmlMode?: boolean;
decodeEntities?: boolean;
} | null, cbs: Callbacks);private baseState;
private buffer;
private bufferOffset;
private readonly cbs;
private cleanup;
private readonly decodeEntities;
private decodeNumericEntity;
private emitPartial;
private emitToken;
private ended;
private finish;
private getSection;
private handleInAttributeValue;
private handleTrailingData;
private isTagStartChar;
private parse;
private parseFixedEntity;
private parseLegacyEntity;
private running;
private special;
private stateAfterAttributeName;
private stateAfterCdata1;
private stateAfterCdata2;
private stateAfterClosingTagName;
private stateAfterComment1;
private stateAfterComment2;
private stateAfterSpecialLast;
private stateBeforeAttributeName;
private stateBeforeAttributeValue;
private stateBeforeCdata6;
private stateBeforeClosingTagName;
private stateBeforeComment;
private stateBeforeDeclaration;
private stateBeforeSpecialLast;
private stateBeforeSpecialS;
private stateBeforeSpecialSEnd;
private stateBeforeTagName;
private stateInAttributeName;
private stateInAttributeValueDoubleQuotes;
private stateInAttributeValueNoQuotes;
private stateInAttributeValueSingleQuotes;
private stateInCdata;
private stateInClosingTagName;
private stateInComment;
private stateInDeclaration;
private stateInHexEntity;
private stateInNamedEntity;
private stateInNumericEntity;
private stateInProcessingInstruction;
private stateInSelfClosingTag;
private stateInSpecialComment;
private stateInTagName;
private stateText;
private readonly xmlMode;
_index: number;
_state: State;
sectionStart: number;
end(chunk?: string): void;
getAbsoluteIndex(): number;
pause(): void;
reset(): void;
resume(): void;
write(chunk: string): void;
§Constructors
§Properties
§
baseState
[src]Some behavior, eg. when decoding entities, is done while we are in another state. This keeps track of the other state type.
§
bufferOffset
[src]Data that has already been processed will be removed from the buffer occasionally.
_bufferOffset keeps track of how many characters have been removed, to make sure position information is accurate.
§
isTagStartChar
[src]HTML only allows ASCII alpha characters (a-z and A-Z) at the beginning of a tag name.
XML allows a lot more characters here (@see https://www.w3.org/TR/REC-xml/#NT-NameStartChar). We allow anything that wouldn't end the tag.
§
parse
[src]Iterates through the buffer, calling the function corresponding to the current state.
States that are more likely to be hit are higher up, as a performance improvement.