html-dom-parser
Version:
HTML to DOM parser.
918 lines (917 loc) • 30.2 kB
JavaScript
const require_decode_data_html = require("../../entities/dist/generated/decode-data-html.js");
const require_decode_data_xml = require("../../entities/dist/generated/decode-data-xml.js");
const require_decode = require("../../entities/dist/decode.js");
//#region node_modules/htmlparser2/dist/Tokenizer.js
var CharCodes;
(function(CharCodes) {
CharCodes[CharCodes["Tab"] = 9] = "Tab";
CharCodes[CharCodes["NewLine"] = 10] = "NewLine";
CharCodes[CharCodes["FormFeed"] = 12] = "FormFeed";
CharCodes[CharCodes["CarriageReturn"] = 13] = "CarriageReturn";
CharCodes[CharCodes["Space"] = 32] = "Space";
CharCodes[CharCodes["ExclamationMark"] = 33] = "ExclamationMark";
CharCodes[CharCodes["Number"] = 35] = "Number";
CharCodes[CharCodes["Amp"] = 38] = "Amp";
CharCodes[CharCodes["SingleQuote"] = 39] = "SingleQuote";
CharCodes[CharCodes["DoubleQuote"] = 34] = "DoubleQuote";
CharCodes[CharCodes["Dash"] = 45] = "Dash";
CharCodes[CharCodes["Slash"] = 47] = "Slash";
CharCodes[CharCodes["Zero"] = 48] = "Zero";
CharCodes[CharCodes["Nine"] = 57] = "Nine";
CharCodes[CharCodes["Semi"] = 59] = "Semi";
CharCodes[CharCodes["Lt"] = 60] = "Lt";
CharCodes[CharCodes["Eq"] = 61] = "Eq";
CharCodes[CharCodes["Gt"] = 62] = "Gt";
CharCodes[CharCodes["Questionmark"] = 63] = "Questionmark";
CharCodes[CharCodes["UpperA"] = 65] = "UpperA";
CharCodes[CharCodes["LowerA"] = 97] = "LowerA";
CharCodes[CharCodes["UpperF"] = 70] = "UpperF";
CharCodes[CharCodes["LowerF"] = 102] = "LowerF";
CharCodes[CharCodes["UpperZ"] = 90] = "UpperZ";
CharCodes[CharCodes["LowerZ"] = 122] = "LowerZ";
CharCodes[CharCodes["LowerX"] = 120] = "LowerX";
CharCodes[CharCodes["OpeningSquareBracket"] = 91] = "OpeningSquareBracket";
})(CharCodes || (CharCodes = {}));
/** All the states the tokenizer can be in. */
var State;
(function(State) {
State[State["Text"] = 1] = "Text";
State[State["BeforeTagName"] = 2] = "BeforeTagName";
State[State["InTagName"] = 3] = "InTagName";
State[State["InSelfClosingTag"] = 4] = "InSelfClosingTag";
State[State["BeforeClosingTagName"] = 5] = "BeforeClosingTagName";
State[State["InClosingTagName"] = 6] = "InClosingTagName";
State[State["AfterClosingTagName"] = 7] = "AfterClosingTagName";
State[State["BeforeAttributeName"] = 8] = "BeforeAttributeName";
State[State["InAttributeName"] = 9] = "InAttributeName";
State[State["AfterAttributeName"] = 10] = "AfterAttributeName";
State[State["BeforeAttributeValue"] = 11] = "BeforeAttributeValue";
State[State["InAttributeValueDq"] = 12] = "InAttributeValueDq";
State[State["InAttributeValueSq"] = 13] = "InAttributeValueSq";
State[State["InAttributeValueNq"] = 14] = "InAttributeValueNq";
State[State["BeforeDeclaration"] = 15] = "BeforeDeclaration";
State[State["InDeclaration"] = 16] = "InDeclaration";
State[State["InProcessingInstruction"] = 17] = "InProcessingInstruction";
State[State["BeforeComment"] = 18] = "BeforeComment";
State[State["CDATASequence"] = 19] = "CDATASequence";
State[State["DeclarationSequence"] = 20] = "DeclarationSequence";
State[State["InSpecialComment"] = 21] = "InSpecialComment";
State[State["InCommentLike"] = 22] = "InCommentLike";
State[State["SpecialStartSequence"] = 23] = "SpecialStartSequence";
State[State["InSpecialTag"] = 24] = "InSpecialTag";
State[State["InPlainText"] = 25] = "InPlainText";
State[State["InEntity"] = 26] = "InEntity";
})(State || (State = {}));
function isWhitespace(c) {
return c === CharCodes.Space || c === CharCodes.NewLine || c === CharCodes.Tab || c === CharCodes.FormFeed || c === CharCodes.CarriageReturn;
}
function isEndOfTagSection(c) {
return c === CharCodes.Slash || c === CharCodes.Gt || isWhitespace(c);
}
function isASCIIAlpha(c) {
return c >= CharCodes.LowerA && c <= CharCodes.LowerZ || c >= CharCodes.UpperA && c <= CharCodes.UpperZ;
}
/**
* Quote style used for parsed attributes.
*/
var QuoteType;
(function(QuoteType) {
QuoteType[QuoteType["NoValue"] = 0] = "NoValue";
QuoteType[QuoteType["Unquoted"] = 1] = "Unquoted";
QuoteType[QuoteType["Single"] = 2] = "Single";
QuoteType[QuoteType["Double"] = 3] = "Double";
})(QuoteType || (QuoteType = {}));
/**
* Sequences used to match longer strings.
*
* We don't have `Script`, `Style`, or `Title` here. Instead, we re-use the *End
* sequences with an increased offset.
*/
const Sequences = {
Empty: /* @__PURE__ */ new Uint8Array(0),
Cdata: new Uint8Array([
67,
68,
65,
84,
65,
91
]),
CdataEnd: new Uint8Array([
93,
93,
62
]),
CommentEnd: new Uint8Array([
45,
45,
33,
62
]),
Doctype: new Uint8Array([
100,
111,
99,
116,
121,
112,
101
]),
IframeEnd: new Uint8Array([
60,
47,
105,
102,
114,
97,
109,
101
]),
NoembedEnd: new Uint8Array([
60,
47,
110,
111,
101,
109,
98,
101,
100
]),
NoframesEnd: new Uint8Array([
60,
47,
110,
111,
102,
114,
97,
109,
101,
115
]),
Plaintext: new Uint8Array([
60,
47,
112,
108,
97,
105,
110,
116,
101,
120,
116
]),
ScriptEnd: new Uint8Array([
60,
47,
115,
99,
114,
105,
112,
116
]),
StyleEnd: new Uint8Array([
60,
47,
115,
116,
121,
108,
101
]),
TitleEnd: new Uint8Array([
60,
47,
116,
105,
116,
108,
101
]),
TextareaEnd: new Uint8Array([
60,
47,
116,
101,
120,
116,
97,
114,
101,
97
]),
XmpEnd: new Uint8Array([
60,
47,
120,
109,
112
])
};
/**
* Maps the first lowercase character of an HTML tag name to the sequence
* used for special-tag detection. All sequences share a common layout
* where index 2 is the first tag-name character, so matching always
* continues from offset 3.
*/
const specialStartSequences = /* @__PURE__ */ new Map([
[Sequences.IframeEnd[2], Sequences.IframeEnd],
[Sequences.NoembedEnd[2], Sequences.NoembedEnd],
[Sequences.Plaintext[2], Sequences.Plaintext],
[Sequences.ScriptEnd[2], Sequences.ScriptEnd],
[Sequences.TitleEnd[2], Sequences.TitleEnd],
[Sequences.XmpEnd[2], Sequences.XmpEnd]
]);
/**
* Tokenizer implementation used by `Parser`.
*/
var Tokenizer = class {
cbs;
/** The current state the tokenizer is in. */
state = State.Text;
/** The read buffer. */
buffer = "";
/** The beginning of the section that is currently being read. */
sectionStart = 0;
/** The index within the buffer that we are currently looking at. */
index = 0;
/** The start of the last entity. */
entityStart = 0;
/** Some behavior, eg. when decoding entities, is done while we are in another state. This keeps track of the other state type. */
baseState = State.Text;
/** For special parsing behavior inside of script and style tags. */
isSpecial = false;
/** Indicates whether the tokenizer has been paused. */
running = true;
/** The offset of the current buffer. */
offset = 0;
xmlMode;
decodeEntities;
recognizeSelfClosing;
entityDecoder;
constructor({ xmlMode = false, decodeEntities = true, recognizeSelfClosing = xmlMode }, cbs) {
this.cbs = cbs;
this.xmlMode = xmlMode;
this.decodeEntities = decodeEntities;
this.recognizeSelfClosing = recognizeSelfClosing;
this.entityDecoder = new require_decode.EntityDecoder(xmlMode ? require_decode_data_xml.xmlDecodeTree : require_decode_data_html.htmlDecodeTree, (cp, consumed) => this.emitCodePoint(cp, consumed));
}
reset() {
this.state = State.Text;
this.buffer = "";
this.sectionStart = 0;
this.index = 0;
this.baseState = State.Text;
this.isSpecial = false;
this.currentSequence = Sequences.Empty;
this.sequenceIndex = 0;
this.running = true;
this.offset = 0;
}
write(chunk) {
this.offset += this.buffer.length;
this.buffer = chunk;
this.parse();
}
end() {
if (this.running) this.finish();
}
pause() {
this.running = false;
}
resume() {
this.running = true;
if (this.index < this.buffer.length + this.offset) this.parse();
}
stateText(c) {
if (c === CharCodes.Lt || !this.decodeEntities && this.fastForwardTo(CharCodes.Lt)) {
if (this.index > this.sectionStart) this.cbs.ontext(this.sectionStart, this.index);
this.state = State.BeforeTagName;
this.sectionStart = this.index;
} else if (this.decodeEntities && c === CharCodes.Amp) this.startEntity();
}
currentSequence = Sequences.Empty;
sequenceIndex = 0;
enterTagBody() {
if (this.currentSequence === Sequences.Plaintext) {
this.currentSequence = Sequences.Empty;
this.state = State.InPlainText;
} else if (this.isSpecial) {
this.state = State.InSpecialTag;
this.sequenceIndex = 0;
} else this.state = State.Text;
}
/**
* Match the opening tag name against an HTML text-only tag sequence.
*
* Some tags share an initial prefix (`script`/`style`, `title`/`textarea`,
* `noembed`/`noframes`), so we may switch to an alternate sequence at the
* first distinguishing byte. On a successful full match we fall back to
* the normal tag-name state; a later `>` will enter raw-text, RCDATA, or
* plaintext mode based on `currentSequence` / `isSpecial`.
* @param c Current character code point.
*/
stateSpecialStartSequence(c) {
const lower = c | 32;
if (this.sequenceIndex < this.currentSequence.length) {
if (lower === this.currentSequence[this.sequenceIndex]) {
this.sequenceIndex++;
return;
}
if (this.sequenceIndex === 3) {
if (this.currentSequence === Sequences.ScriptEnd && lower === Sequences.StyleEnd[3]) {
this.currentSequence = Sequences.StyleEnd;
this.sequenceIndex = 4;
return;
}
if (this.currentSequence === Sequences.TitleEnd && lower === Sequences.TextareaEnd[3]) {
this.currentSequence = Sequences.TextareaEnd;
this.sequenceIndex = 4;
return;
}
} else if (this.sequenceIndex === 4 && this.currentSequence === Sequences.NoembedEnd && lower === Sequences.NoframesEnd[4]) {
this.currentSequence = Sequences.NoframesEnd;
this.sequenceIndex = 5;
return;
}
} else if (isEndOfTagSection(c)) {
this.sequenceIndex = 0;
this.state = State.InTagName;
this.stateInTagName(c);
return;
}
this.isSpecial = false;
this.currentSequence = Sequences.Empty;
this.sequenceIndex = 0;
this.state = State.InTagName;
this.stateInTagName(c);
}
stateCDATASequence(c) {
if (c === Sequences.Cdata[this.sequenceIndex]) {
if (++this.sequenceIndex === Sequences.Cdata.length) {
this.state = State.InCommentLike;
this.currentSequence = Sequences.CdataEnd;
this.sequenceIndex = 0;
this.sectionStart = this.index + 1;
}
} else {
this.sequenceIndex = 0;
if (this.xmlMode) {
this.state = State.InDeclaration;
this.stateInDeclaration(c);
} else {
this.state = State.InSpecialComment;
this.stateInSpecialComment(c);
}
}
}
/**
* When we wait for one specific character, we can speed things up
* by skipping through the buffer until we find it.
* @param c Current character code point.
* @returns Whether the character was found.
*/
fastForwardTo(c) {
while (++this.index < this.buffer.length + this.offset) if (this.buffer.charCodeAt(this.index - this.offset) === c) return true;
this.index = this.buffer.length + this.offset - 1;
return false;
}
/**
* Emit a comment token and return to the text state.
* @param offset Number of characters in the end sequence that have already been matched.
*/
emitComment(offset) {
this.cbs.oncomment(this.sectionStart, this.index, offset);
this.sequenceIndex = 0;
this.sectionStart = this.index + 1;
this.state = State.Text;
}
/**
* Comments and CDATA end with `-->` and `]]>`.
*
* Their common qualities are:
* - Their end sequences have a distinct character they start with.
* - That character is then repeated, so we have to check multiple repeats.
* - All characters but the start character of the sequence can be skipped.
* @param c Current character code point.
*/
stateInCommentLike(c) {
if (!this.xmlMode && this.currentSequence === Sequences.CommentEnd && this.sequenceIndex <= 1 && this.index === this.sectionStart + this.sequenceIndex && c === CharCodes.Gt) this.emitComment(this.sequenceIndex);
else if (this.currentSequence === Sequences.CommentEnd && this.sequenceIndex === 2 && c === CharCodes.Gt) this.emitComment(2);
else if (this.currentSequence === Sequences.CommentEnd && this.sequenceIndex === this.currentSequence.length - 1 && c !== CharCodes.Gt) this.sequenceIndex = Number(c === CharCodes.Dash);
else if (c === this.currentSequence[this.sequenceIndex]) {
if (++this.sequenceIndex === this.currentSequence.length) {
if (this.currentSequence === Sequences.CdataEnd) this.cbs.oncdata(this.sectionStart, this.index, 2);
else this.cbs.oncomment(this.sectionStart, this.index, 3);
this.sequenceIndex = 0;
this.sectionStart = this.index + 1;
this.state = State.Text;
}
} else if (this.sequenceIndex === 0) {
if (this.fastForwardTo(this.currentSequence[0])) this.sequenceIndex = 1;
} else if (c !== this.currentSequence[this.sequenceIndex - 1]) this.sequenceIndex = 0;
}
/**
* 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.
* @param c Current character code point.
*/
isTagStartChar(c) {
return this.xmlMode ? !isEndOfTagSection(c) : isASCIIAlpha(c);
}
/**
* Scan raw-text / RCDATA content for the matching end tag.
*
* For RCDATA tags (`<title>`, `<textarea>`) entities are decoded inline.
* For raw-text tags (`<script>`, `<style>`, etc.) we fast-forward to `<`.
* @param c Current character code point.
*/
stateInSpecialTag(c) {
if (this.sequenceIndex === this.currentSequence.length) {
if (isEndOfTagSection(c)) {
const endOfText = this.index - this.currentSequence.length;
if (this.sectionStart < endOfText) {
const actualIndex = this.index;
this.index = endOfText;
this.cbs.ontext(this.sectionStart, endOfText);
this.index = actualIndex;
}
this.isSpecial = false;
this.sectionStart = endOfText + 2;
this.stateInClosingTagName(c);
return;
}
this.sequenceIndex = 0;
}
if ((c | 32) === this.currentSequence[this.sequenceIndex]) this.sequenceIndex += 1;
else if (this.sequenceIndex === 0) {
if (this.currentSequence === Sequences.TitleEnd || this.currentSequence === Sequences.TextareaEnd) {
if (this.decodeEntities && c === CharCodes.Amp) this.startEntity();
} else if (this.fastForwardTo(CharCodes.Lt)) this.sequenceIndex = 1;
} else this.sequenceIndex = Number(c === CharCodes.Lt);
}
stateBeforeTagName(c) {
if (c === CharCodes.ExclamationMark) {
this.state = State.BeforeDeclaration;
this.sectionStart = this.index + 1;
} else if (c === CharCodes.Questionmark) if (this.xmlMode) {
this.state = State.InProcessingInstruction;
this.sequenceIndex = 0;
this.sectionStart = this.index + 1;
} else {
this.state = State.InSpecialComment;
this.sectionStart = this.index;
}
else if (this.isTagStartChar(c)) {
this.sectionStart = this.index;
const special = this.xmlMode || this.cbs.isInForeignContext?.() ? void 0 : specialStartSequences.get(c | 32);
if (special === void 0) this.state = State.InTagName;
else {
this.isSpecial = true;
this.currentSequence = special;
this.sequenceIndex = 3;
this.state = State.SpecialStartSequence;
}
} else if (c === CharCodes.Slash) this.state = State.BeforeClosingTagName;
else {
this.state = State.Text;
this.stateText(c);
}
}
stateInTagName(c) {
if (isEndOfTagSection(c)) {
this.cbs.onopentagname(this.sectionStart, this.index);
this.sectionStart = -1;
this.state = State.BeforeAttributeName;
this.stateBeforeAttributeName(c);
}
}
stateBeforeClosingTagName(c) {
if (isWhitespace(c)) if (this.xmlMode) {} else {
this.state = State.InSpecialComment;
this.sectionStart = this.index;
}
else if (c === CharCodes.Gt) {
this.state = State.Text;
if (!this.xmlMode) this.sectionStart = this.index + 1;
} else {
this.state = this.isTagStartChar(c) ? State.InClosingTagName : State.InSpecialComment;
this.sectionStart = this.index;
}
}
stateInClosingTagName(c) {
if (isEndOfTagSection(c)) {
this.cbs.onclosetag(this.sectionStart, this.index);
this.sectionStart = -1;
this.state = State.AfterClosingTagName;
this.stateAfterClosingTagName(c);
}
}
stateAfterClosingTagName(c) {
if (c === CharCodes.Gt || this.fastForwardTo(CharCodes.Gt)) {
this.state = State.Text;
this.sectionStart = this.index + 1;
}
}
stateBeforeAttributeName(c) {
if (c === CharCodes.Gt) {
this.cbs.onopentagend(this.index);
this.enterTagBody();
this.sectionStart = this.index + 1;
} else if (c === CharCodes.Slash) this.state = State.InSelfClosingTag;
else if (!isWhitespace(c)) {
this.state = State.InAttributeName;
this.sectionStart = this.index;
}
}
/**
* Handle `/` before `>` in an opening tag.
*
* In HTML mode, text-only tags ignore the self-closing flag and still enter
* their raw-text/RCDATA/plaintext state unless self-closing tags are being
* recognized. In XML mode, or for ordinary tags, the tokenizer returns to
* regular text parsing after emitting the self-closing callback.
* @param c Current character code point.
*/
stateInSelfClosingTag(c) {
if (c === CharCodes.Gt) {
this.cbs.onselfclosingtag(this.index);
this.sectionStart = this.index + 1;
if (!this.recognizeSelfClosing) {
this.enterTagBody();
return;
}
this.state = State.Text;
this.isSpecial = false;
this.currentSequence = Sequences.Empty;
} else if (!isWhitespace(c)) {
this.state = State.BeforeAttributeName;
this.stateBeforeAttributeName(c);
}
}
stateInAttributeName(c) {
if (c === CharCodes.Eq || isEndOfTagSection(c)) {
this.cbs.onattribname(this.sectionStart, this.index);
this.sectionStart = this.index;
this.state = State.AfterAttributeName;
this.stateAfterAttributeName(c);
}
}
stateAfterAttributeName(c) {
if (c === CharCodes.Eq) this.state = State.BeforeAttributeValue;
else if (c === CharCodes.Slash || c === CharCodes.Gt) {
this.cbs.onattribend(QuoteType.NoValue, this.sectionStart);
this.sectionStart = -1;
this.state = State.BeforeAttributeName;
this.stateBeforeAttributeName(c);
} else if (!isWhitespace(c)) {
this.cbs.onattribend(QuoteType.NoValue, this.sectionStart);
this.state = State.InAttributeName;
this.sectionStart = this.index;
}
}
stateBeforeAttributeValue(c) {
if (c === CharCodes.DoubleQuote) {
this.state = State.InAttributeValueDq;
this.sectionStart = this.index + 1;
} else if (c === CharCodes.SingleQuote) {
this.state = State.InAttributeValueSq;
this.sectionStart = this.index + 1;
} else if (!isWhitespace(c)) {
this.sectionStart = this.index;
this.state = State.InAttributeValueNq;
this.stateInAttributeValueNoQuotes(c);
}
}
handleInAttributeValue(c, quote) {
if (c === quote || !this.decodeEntities && this.fastForwardTo(quote)) {
this.cbs.onattribdata(this.sectionStart, this.index);
this.sectionStart = -1;
this.cbs.onattribend(quote === CharCodes.DoubleQuote ? QuoteType.Double : QuoteType.Single, this.index + 1);
this.state = State.BeforeAttributeName;
} else if (this.decodeEntities && c === CharCodes.Amp) this.startEntity();
}
stateInAttributeValueDoubleQuotes(c) {
this.handleInAttributeValue(c, CharCodes.DoubleQuote);
}
stateInAttributeValueSingleQuotes(c) {
this.handleInAttributeValue(c, CharCodes.SingleQuote);
}
stateInAttributeValueNoQuotes(c) {
if (isWhitespace(c) || c === CharCodes.Gt) {
this.cbs.onattribdata(this.sectionStart, this.index);
this.sectionStart = -1;
this.cbs.onattribend(QuoteType.Unquoted, this.index);
this.state = State.BeforeAttributeName;
this.stateBeforeAttributeName(c);
} else if (this.decodeEntities && c === CharCodes.Amp) this.startEntity();
}
/**
* Distinguish between CDATA, declarations, HTML comments, and HTML bogus
* comments after `<!`.
*
* In HTML mode, only real comments and doctypes stay on declaration paths;
* everything else becomes a bogus comment terminated by the next `>`.
* @param c Current character code point.
*/
stateBeforeDeclaration(c) {
if (c === CharCodes.OpeningSquareBracket) {
this.state = State.CDATASequence;
this.sequenceIndex = 0;
} else if (this.xmlMode) this.state = c === CharCodes.Dash ? State.BeforeComment : State.InDeclaration;
else if ((c | 32) === Sequences.Doctype[0]) {
this.state = State.DeclarationSequence;
this.currentSequence = Sequences.Doctype;
this.sequenceIndex = 1;
} else if (c === CharCodes.Gt) {
this.cbs.oncomment(this.sectionStart, this.index, 0);
this.state = State.Text;
this.sectionStart = this.index + 1;
} else if (c === CharCodes.Dash) this.state = State.BeforeComment;
else this.state = State.InSpecialComment;
}
/**
* Continue matching `doctype` after `<!d`.
*
* A full `doctype` match stays on the declaration path; any other name falls
* back to an HTML bogus comment, which matches browser behavior for
* non-doctype `<!...>` constructs.
* @param c Current character code point.
*/
stateDeclarationSequence(c) {
if (this.sequenceIndex === this.currentSequence.length) {
this.state = State.InDeclaration;
this.stateInDeclaration(c);
} else if ((c | 32) === this.currentSequence[this.sequenceIndex]) this.sequenceIndex += 1;
else if (c === CharCodes.Gt) {
this.cbs.oncomment(this.sectionStart, this.index, 0);
this.state = State.Text;
this.sectionStart = this.index + 1;
} else this.state = State.InSpecialComment;
}
stateInDeclaration(c) {
if (c === CharCodes.Gt || this.fastForwardTo(CharCodes.Gt)) {
this.cbs.ondeclaration(this.sectionStart, this.index);
this.state = State.Text;
this.sectionStart = this.index + 1;
}
}
/**
* XML processing instructions (`<?...?>`).
*
* In HTML mode `<?` is routed to `InSpecialComment` instead, so this
* state is only reachable in XML mode.
* @param c Current character code point.
*/
stateInProcessingInstruction(c) {
if (c === CharCodes.Questionmark) this.sequenceIndex = 1;
else if (c === CharCodes.Gt && this.sequenceIndex === 1) {
this.cbs.onprocessinginstruction(this.sectionStart, this.index - 1);
this.sequenceIndex = 0;
this.state = State.Text;
this.sectionStart = this.index + 1;
} else this.sequenceIndex = Number(this.fastForwardTo(CharCodes.Questionmark));
}
stateBeforeComment(c) {
if (c === CharCodes.Dash) {
this.state = State.InCommentLike;
this.currentSequence = Sequences.CommentEnd;
this.sequenceIndex = 0;
this.sectionStart = this.index + 1;
} else if (this.xmlMode) this.state = State.InDeclaration;
else if (c === CharCodes.Gt) {
this.cbs.oncomment(this.sectionStart, this.index, 0);
this.state = State.Text;
this.sectionStart = this.index + 1;
} else this.state = State.InSpecialComment;
}
stateInSpecialComment(c) {
if (c === CharCodes.Gt || this.fastForwardTo(CharCodes.Gt)) {
this.cbs.oncomment(this.sectionStart, this.index, 0);
this.state = State.Text;
this.sectionStart = this.index + 1;
}
}
startEntity() {
this.baseState = this.state;
this.state = State.InEntity;
this.entityStart = this.index;
this.entityDecoder.startEntity(this.xmlMode ? require_decode.DecodingMode.Strict : this.baseState === State.Text || this.baseState === State.InSpecialTag ? require_decode.DecodingMode.Legacy : require_decode.DecodingMode.Attribute);
}
stateInEntity() {
const indexInBuffer = this.index - this.offset;
const length = this.entityDecoder.write(this.buffer, indexInBuffer);
if (length >= 0) {
this.state = this.baseState;
if (length === 0) this.index -= 1;
} else {
if (indexInBuffer < this.buffer.length && this.buffer.charCodeAt(indexInBuffer) === CharCodes.Amp) {
this.state = this.baseState;
this.index -= 1;
return;
}
this.index = this.offset + this.buffer.length - 1;
}
}
/**
* Remove data that has already been consumed from the buffer.
*/
cleanup() {
if (this.running && this.sectionStart !== this.index) {
if (this.state === State.Text || this.state === State.InPlainText || this.state === State.InSpecialTag && this.sequenceIndex === 0) {
this.cbs.ontext(this.sectionStart, this.index);
this.sectionStart = this.index;
} else if (this.state === State.InAttributeValueDq || this.state === State.InAttributeValueSq || this.state === State.InAttributeValueNq) {
this.cbs.onattribdata(this.sectionStart, this.index);
this.sectionStart = this.index;
}
}
}
shouldContinue() {
return this.index < this.buffer.length + this.offset && this.running;
}
/**
* 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.
*/
parse() {
while (this.shouldContinue()) {
const c = this.buffer.charCodeAt(this.index - this.offset);
switch (this.state) {
case State.Text:
this.stateText(c);
break;
case State.InPlainText:
this.index = this.buffer.length + this.offset - 1;
break;
case State.SpecialStartSequence:
this.stateSpecialStartSequence(c);
break;
case State.InSpecialTag:
this.stateInSpecialTag(c);
break;
case State.CDATASequence:
this.stateCDATASequence(c);
break;
case State.DeclarationSequence:
this.stateDeclarationSequence(c);
break;
case State.InAttributeValueDq:
this.stateInAttributeValueDoubleQuotes(c);
break;
case State.InAttributeName:
this.stateInAttributeName(c);
break;
case State.InCommentLike:
this.stateInCommentLike(c);
break;
case State.InSpecialComment:
this.stateInSpecialComment(c);
break;
case State.BeforeAttributeName:
this.stateBeforeAttributeName(c);
break;
case State.InTagName:
this.stateInTagName(c);
break;
case State.InClosingTagName:
this.stateInClosingTagName(c);
break;
case State.BeforeTagName:
this.stateBeforeTagName(c);
break;
case State.AfterAttributeName:
this.stateAfterAttributeName(c);
break;
case State.InAttributeValueSq:
this.stateInAttributeValueSingleQuotes(c);
break;
case State.BeforeAttributeValue:
this.stateBeforeAttributeValue(c);
break;
case State.BeforeClosingTagName:
this.stateBeforeClosingTagName(c);
break;
case State.AfterClosingTagName:
this.stateAfterClosingTagName(c);
break;
case State.InAttributeValueNq:
this.stateInAttributeValueNoQuotes(c);
break;
case State.InSelfClosingTag:
this.stateInSelfClosingTag(c);
break;
case State.InDeclaration:
this.stateInDeclaration(c);
break;
case State.BeforeDeclaration:
this.stateBeforeDeclaration(c);
break;
case State.BeforeComment:
this.stateBeforeComment(c);
break;
case State.InProcessingInstruction:
this.stateInProcessingInstruction(c);
break;
case State.InEntity:
this.stateInEntity();
break;
}
this.index++;
}
this.cleanup();
}
finish() {
if (this.state === State.InEntity) {
this.entityDecoder.end();
this.state = this.baseState;
}
this.handleTrailingData();
this.cbs.onend();
}
handleTrailingCommentLikeData(endIndex) {
if (this.state !== State.InCommentLike) return false;
if (this.currentSequence === Sequences.CdataEnd) if (this.xmlMode) {
if (this.sectionStart < endIndex) this.cbs.oncdata(this.sectionStart, endIndex, 0);
} else {
const cdataStart = this.sectionStart - Sequences.Cdata.length - 1;
this.cbs.oncomment(cdataStart, endIndex, 0);
}
else {
const offset = this.xmlMode ? 0 : Math.min(this.sequenceIndex, Sequences.CommentEnd.length - 1);
this.cbs.oncomment(this.sectionStart, endIndex, offset);
}
return true;
}
handleTrailingMarkupDeclaration(endIndex) {
if (this.xmlMode) switch (this.state) {
case State.InSpecialComment:
case State.BeforeComment:
case State.CDATASequence:
case State.DeclarationSequence:
case State.InDeclaration:
this.cbs.ontext(this.sectionStart, endIndex);
return true;
default: return false;
}
switch (this.state) {
case State.BeforeDeclaration:
case State.InSpecialComment:
case State.BeforeComment:
case State.CDATASequence:
this.cbs.oncomment(this.sectionStart, endIndex, 0);
return true;
case State.DeclarationSequence:
if (this.sequenceIndex !== Sequences.Doctype.length) this.cbs.oncomment(this.sectionStart, endIndex, 0);
return true;
case State.InDeclaration: return true;
default: return false;
}
}
/** Handle any trailing data. */
handleTrailingData() {
const endIndex = this.buffer.length + this.offset;
if (this.handleTrailingCommentLikeData(endIndex) || this.handleTrailingMarkupDeclaration(endIndex)) return;
if (this.sectionStart >= endIndex) return;
switch (this.state) {
case State.InTagName:
case State.BeforeAttributeName:
case State.BeforeAttributeValue:
case State.AfterAttributeName:
case State.InAttributeName:
case State.InAttributeValueSq:
case State.InAttributeValueDq:
case State.InAttributeValueNq:
case State.InClosingTagName: break;
default: this.cbs.ontext(this.sectionStart, endIndex);
}
}
emitCodePoint(cp, consumed) {
if (this.baseState !== State.Text && this.baseState !== State.InSpecialTag) {
if (this.sectionStart < this.entityStart) this.cbs.onattribdata(this.sectionStart, this.entityStart);
this.sectionStart = this.entityStart + consumed;
this.index = this.sectionStart - 1;
this.cbs.onattribentity(cp);
} else {
if (this.sectionStart < this.entityStart) this.cbs.ontext(this.sectionStart, this.entityStart);
this.sectionStart = this.entityStart + consumed;
this.index = this.sectionStart - 1;
this.cbs.ontextentity(cp, this.sectionStart);
}
}
};
//#endregion
Object.defineProperty(exports, "QuoteType", {
enumerable: true,
get: function() {
return QuoteType;
}
});
exports.default = Tokenizer;
//# sourceMappingURL=Tokenizer.js.map