feat(ui): finalize E-TIB modernization with footer redesign, video optimization, and TS fixes

Former-commit-id: 67ac02c8404cc66893fdf97308574701cca6000c
This commit is contained in:
2026-05-07 10:43:20 +02:00
parent f2fdea96ec
commit 5439df72ea
3712 changed files with 932332 additions and 1867 deletions
@@ -0,0 +1 @@
../../domelementtype@2.3.0/node_modules/domelementtype
+1
View File
@@ -0,0 +1 @@
../../domhandler@5.0.3/node_modules/domhandler
+1
View File
@@ -0,0 +1 @@
../../domutils@3.2.2/node_modules/domutils
+1
View File
@@ -0,0 +1 @@
../../entities@4.5.0/node_modules/entities
@@ -0,0 +1,518 @@
"use strict";
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
if (k2 === undefined) k2 = k;
var desc = Object.getOwnPropertyDescriptor(m, k);
if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
desc = { enumerable: true, get: function() { return m[k]; } };
}
Object.defineProperty(o, k2, desc);
}) : (function(o, m, k, k2) {
if (k2 === undefined) k2 = k;
o[k2] = m[k];
}));
var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
Object.defineProperty(o, "default", { enumerable: true, value: v });
}) : function(o, v) {
o["default"] = v;
});
var __importStar = (this && this.__importStar) || function (mod) {
if (mod && mod.__esModule) return mod;
var result = {};
if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
__setModuleDefault(result, mod);
return result;
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.Parser = void 0;
var Tokenizer_js_1 = __importStar(require("./Tokenizer.js"));
var decode_js_1 = require("entities/lib/decode.js");
var formTags = new Set([
"input",
"option",
"optgroup",
"select",
"button",
"datalist",
"textarea",
]);
var pTag = new Set(["p"]);
var tableSectionTags = new Set(["thead", "tbody"]);
var ddtTags = new Set(["dd", "dt"]);
var rtpTags = new Set(["rt", "rp"]);
var openImpliesClose = new Map([
["tr", new Set(["tr", "th", "td"])],
["th", new Set(["th"])],
["td", new Set(["thead", "th", "td"])],
["body", new Set(["head", "link", "script"])],
["li", new Set(["li"])],
["p", pTag],
["h1", pTag],
["h2", pTag],
["h3", pTag],
["h4", pTag],
["h5", pTag],
["h6", pTag],
["select", formTags],
["input", formTags],
["output", formTags],
["button", formTags],
["datalist", formTags],
["textarea", formTags],
["option", new Set(["option"])],
["optgroup", new Set(["optgroup", "option"])],
["dd", ddtTags],
["dt", ddtTags],
["address", pTag],
["article", pTag],
["aside", pTag],
["blockquote", pTag],
["details", pTag],
["div", pTag],
["dl", pTag],
["fieldset", pTag],
["figcaption", pTag],
["figure", pTag],
["footer", pTag],
["form", pTag],
["header", pTag],
["hr", pTag],
["main", pTag],
["nav", pTag],
["ol", pTag],
["pre", pTag],
["section", pTag],
["table", pTag],
["ul", pTag],
["rt", rtpTags],
["rp", rtpTags],
["tbody", tableSectionTags],
["tfoot", tableSectionTags],
]);
var voidElements = new Set([
"area",
"base",
"basefont",
"br",
"col",
"command",
"embed",
"frame",
"hr",
"img",
"input",
"isindex",
"keygen",
"link",
"meta",
"param",
"source",
"track",
"wbr",
]);
var foreignContextElements = new Set(["math", "svg"]);
var htmlIntegrationElements = new Set([
"mi",
"mo",
"mn",
"ms",
"mtext",
"annotation-xml",
"foreignobject",
"desc",
"title",
]);
var reNameEnd = /\s|\//;
var Parser = /** @class */ (function () {
function Parser(cbs, options) {
if (options === void 0) { options = {}; }
var _a, _b, _c, _d, _e;
this.options = options;
/** The start index of the last event. */
this.startIndex = 0;
/** The end index of the last event. */
this.endIndex = 0;
/**
* Store the start index of the current open tag,
* so we can update the start index for attributes.
*/
this.openTagStart = 0;
this.tagname = "";
this.attribname = "";
this.attribvalue = "";
this.attribs = null;
this.stack = [];
this.foreignContext = [];
this.buffers = [];
this.bufferOffset = 0;
/** The index of the last written buffer. Used when resuming after a `pause()`. */
this.writeIndex = 0;
/** Indicates whether the parser has finished running / `.end` has been called. */
this.ended = false;
this.cbs = cbs !== null && cbs !== void 0 ? cbs : {};
this.lowerCaseTagNames = (_a = options.lowerCaseTags) !== null && _a !== void 0 ? _a : !options.xmlMode;
this.lowerCaseAttributeNames =
(_b = options.lowerCaseAttributeNames) !== null && _b !== void 0 ? _b : !options.xmlMode;
this.tokenizer = new ((_c = options.Tokenizer) !== null && _c !== void 0 ? _c : Tokenizer_js_1.default)(this.options, this);
(_e = (_d = this.cbs).onparserinit) === null || _e === void 0 ? void 0 : _e.call(_d, this);
}
// Tokenizer event handlers
/** @internal */
Parser.prototype.ontext = function (start, endIndex) {
var _a, _b;
var data = this.getSlice(start, endIndex);
this.endIndex = endIndex - 1;
(_b = (_a = this.cbs).ontext) === null || _b === void 0 ? void 0 : _b.call(_a, data);
this.startIndex = endIndex;
};
/** @internal */
Parser.prototype.ontextentity = function (cp) {
var _a, _b;
/*
* Entities can be emitted on the character, or directly after.
* We use the section start here to get accurate indices.
*/
var index = this.tokenizer.getSectionStart();
this.endIndex = index - 1;
(_b = (_a = this.cbs).ontext) === null || _b === void 0 ? void 0 : _b.call(_a, (0, decode_js_1.fromCodePoint)(cp));
this.startIndex = index;
};
Parser.prototype.isVoidElement = function (name) {
return !this.options.xmlMode && voidElements.has(name);
};
/** @internal */
Parser.prototype.onopentagname = function (start, endIndex) {
this.endIndex = endIndex;
var name = this.getSlice(start, endIndex);
if (this.lowerCaseTagNames) {
name = name.toLowerCase();
}
this.emitOpenTag(name);
};
Parser.prototype.emitOpenTag = function (name) {
var _a, _b, _c, _d;
this.openTagStart = this.startIndex;
this.tagname = name;
var impliesClose = !this.options.xmlMode && openImpliesClose.get(name);
if (impliesClose) {
while (this.stack.length > 0 &&
impliesClose.has(this.stack[this.stack.length - 1])) {
var element = this.stack.pop();
(_b = (_a = this.cbs).onclosetag) === null || _b === void 0 ? void 0 : _b.call(_a, element, true);
}
}
if (!this.isVoidElement(name)) {
this.stack.push(name);
if (foreignContextElements.has(name)) {
this.foreignContext.push(true);
}
else if (htmlIntegrationElements.has(name)) {
this.foreignContext.push(false);
}
}
(_d = (_c = this.cbs).onopentagname) === null || _d === void 0 ? void 0 : _d.call(_c, name);
if (this.cbs.onopentag)
this.attribs = {};
};
Parser.prototype.endOpenTag = function (isImplied) {
var _a, _b;
this.startIndex = this.openTagStart;
if (this.attribs) {
(_b = (_a = this.cbs).onopentag) === null || _b === void 0 ? void 0 : _b.call(_a, this.tagname, this.attribs, isImplied);
this.attribs = null;
}
if (this.cbs.onclosetag && this.isVoidElement(this.tagname)) {
this.cbs.onclosetag(this.tagname, true);
}
this.tagname = "";
};
/** @internal */
Parser.prototype.onopentagend = function (endIndex) {
this.endIndex = endIndex;
this.endOpenTag(false);
// Set `startIndex` for next node
this.startIndex = endIndex + 1;
};
/** @internal */
Parser.prototype.onclosetag = function (start, endIndex) {
var _a, _b, _c, _d, _e, _f;
this.endIndex = endIndex;
var name = this.getSlice(start, endIndex);
if (this.lowerCaseTagNames) {
name = name.toLowerCase();
}
if (foreignContextElements.has(name) ||
htmlIntegrationElements.has(name)) {
this.foreignContext.pop();
}
if (!this.isVoidElement(name)) {
var pos = this.stack.lastIndexOf(name);
if (pos !== -1) {
if (this.cbs.onclosetag) {
var count = this.stack.length - pos;
while (count--) {
// We know the stack has sufficient elements.
this.cbs.onclosetag(this.stack.pop(), count !== 0);
}
}
else
this.stack.length = pos;
}
else if (!this.options.xmlMode && name === "p") {
// Implicit open before close
this.emitOpenTag("p");
this.closeCurrentTag(true);
}
}
else if (!this.options.xmlMode && name === "br") {
// We can't use `emitOpenTag` for implicit open, as `br` would be implicitly closed.
(_b = (_a = this.cbs).onopentagname) === null || _b === void 0 ? void 0 : _b.call(_a, "br");
(_d = (_c = this.cbs).onopentag) === null || _d === void 0 ? void 0 : _d.call(_c, "br", {}, true);
(_f = (_e = this.cbs).onclosetag) === null || _f === void 0 ? void 0 : _f.call(_e, "br", false);
}
// Set `startIndex` for next node
this.startIndex = endIndex + 1;
};
/** @internal */
Parser.prototype.onselfclosingtag = function (endIndex) {
this.endIndex = endIndex;
if (this.options.xmlMode ||
this.options.recognizeSelfClosing ||
this.foreignContext[this.foreignContext.length - 1]) {
this.closeCurrentTag(false);
// Set `startIndex` for next node
this.startIndex = endIndex + 1;
}
else {
// Ignore the fact that the tag is self-closing.
this.onopentagend(endIndex);
}
};
Parser.prototype.closeCurrentTag = function (isOpenImplied) {
var _a, _b;
var name = this.tagname;
this.endOpenTag(isOpenImplied);
// Self-closing tags will be on the top of the stack
if (this.stack[this.stack.length - 1] === name) {
// If the opening tag isn't implied, the closing tag has to be implied.
(_b = (_a = this.cbs).onclosetag) === null || _b === void 0 ? void 0 : _b.call(_a, name, !isOpenImplied);
this.stack.pop();
}
};
/** @internal */
Parser.prototype.onattribname = function (start, endIndex) {
this.startIndex = start;
var name = this.getSlice(start, endIndex);
this.attribname = this.lowerCaseAttributeNames
? name.toLowerCase()
: name;
};
/** @internal */
Parser.prototype.onattribdata = function (start, endIndex) {
this.attribvalue += this.getSlice(start, endIndex);
};
/** @internal */
Parser.prototype.onattribentity = function (cp) {
this.attribvalue += (0, decode_js_1.fromCodePoint)(cp);
};
/** @internal */
Parser.prototype.onattribend = function (quote, endIndex) {
var _a, _b;
this.endIndex = endIndex;
(_b = (_a = this.cbs).onattribute) === null || _b === void 0 ? void 0 : _b.call(_a, this.attribname, this.attribvalue, quote === Tokenizer_js_1.QuoteType.Double
? '"'
: quote === Tokenizer_js_1.QuoteType.Single
? "'"
: quote === Tokenizer_js_1.QuoteType.NoValue
? undefined
: null);
if (this.attribs &&
!Object.prototype.hasOwnProperty.call(this.attribs, this.attribname)) {
this.attribs[this.attribname] = this.attribvalue;
}
this.attribvalue = "";
};
Parser.prototype.getInstructionName = function (value) {
var index = value.search(reNameEnd);
var name = index < 0 ? value : value.substr(0, index);
if (this.lowerCaseTagNames) {
name = name.toLowerCase();
}
return name;
};
/** @internal */
Parser.prototype.ondeclaration = function (start, endIndex) {
this.endIndex = endIndex;
var value = this.getSlice(start, endIndex);
if (this.cbs.onprocessinginstruction) {
var name = this.getInstructionName(value);
this.cbs.onprocessinginstruction("!".concat(name), "!".concat(value));
}
// Set `startIndex` for next node
this.startIndex = endIndex + 1;
};
/** @internal */
Parser.prototype.onprocessinginstruction = function (start, endIndex) {
this.endIndex = endIndex;
var value = this.getSlice(start, endIndex);
if (this.cbs.onprocessinginstruction) {
var name = this.getInstructionName(value);
this.cbs.onprocessinginstruction("?".concat(name), "?".concat(value));
}
// Set `startIndex` for next node
this.startIndex = endIndex + 1;
};
/** @internal */
Parser.prototype.oncomment = function (start, endIndex, offset) {
var _a, _b, _c, _d;
this.endIndex = endIndex;
(_b = (_a = this.cbs).oncomment) === null || _b === void 0 ? void 0 : _b.call(_a, this.getSlice(start, endIndex - offset));
(_d = (_c = this.cbs).oncommentend) === null || _d === void 0 ? void 0 : _d.call(_c);
// Set `startIndex` for next node
this.startIndex = endIndex + 1;
};
/** @internal */
Parser.prototype.oncdata = function (start, endIndex, offset) {
var _a, _b, _c, _d, _e, _f, _g, _h, _j, _k;
this.endIndex = endIndex;
var value = this.getSlice(start, endIndex - offset);
if (this.options.xmlMode || this.options.recognizeCDATA) {
(_b = (_a = this.cbs).oncdatastart) === null || _b === void 0 ? void 0 : _b.call(_a);
(_d = (_c = this.cbs).ontext) === null || _d === void 0 ? void 0 : _d.call(_c, value);
(_f = (_e = this.cbs).oncdataend) === null || _f === void 0 ? void 0 : _f.call(_e);
}
else {
(_h = (_g = this.cbs).oncomment) === null || _h === void 0 ? void 0 : _h.call(_g, "[CDATA[".concat(value, "]]"));
(_k = (_j = this.cbs).oncommentend) === null || _k === void 0 ? void 0 : _k.call(_j);
}
// Set `startIndex` for next node
this.startIndex = endIndex + 1;
};
/** @internal */
Parser.prototype.onend = function () {
var _a, _b;
if (this.cbs.onclosetag) {
// Set the end index for all remaining tags
this.endIndex = this.startIndex;
for (var index = this.stack.length; index > 0; this.cbs.onclosetag(this.stack[--index], true))
;
}
(_b = (_a = this.cbs).onend) === null || _b === void 0 ? void 0 : _b.call(_a);
};
/**
* Resets the parser to a blank state, ready to parse a new HTML document
*/
Parser.prototype.reset = function () {
var _a, _b, _c, _d;
(_b = (_a = this.cbs).onreset) === null || _b === void 0 ? void 0 : _b.call(_a);
this.tokenizer.reset();
this.tagname = "";
this.attribname = "";
this.attribs = null;
this.stack.length = 0;
this.startIndex = 0;
this.endIndex = 0;
(_d = (_c = this.cbs).onparserinit) === null || _d === void 0 ? void 0 : _d.call(_c, this);
this.buffers.length = 0;
this.bufferOffset = 0;
this.writeIndex = 0;
this.ended = false;
};
/**
* Resets the parser, then parses a complete document and
* pushes it to the handler.
*
* @param data Document to parse.
*/
Parser.prototype.parseComplete = function (data) {
this.reset();
this.end(data);
};
Parser.prototype.getSlice = function (start, end) {
while (start - this.bufferOffset >= this.buffers[0].length) {
this.shiftBuffer();
}
var slice = this.buffers[0].slice(start - this.bufferOffset, end - this.bufferOffset);
while (end - this.bufferOffset > this.buffers[0].length) {
this.shiftBuffer();
slice += this.buffers[0].slice(0, end - this.bufferOffset);
}
return slice;
};
Parser.prototype.shiftBuffer = function () {
this.bufferOffset += this.buffers[0].length;
this.writeIndex--;
this.buffers.shift();
};
/**
* Parses a chunk of data and calls the corresponding callbacks.
*
* @param chunk Chunk to parse.
*/
Parser.prototype.write = function (chunk) {
var _a, _b;
if (this.ended) {
(_b = (_a = this.cbs).onerror) === null || _b === void 0 ? void 0 : _b.call(_a, new Error(".write() after done!"));
return;
}
this.buffers.push(chunk);
if (this.tokenizer.running) {
this.tokenizer.write(chunk);
this.writeIndex++;
}
};
/**
* Parses the end of the buffer and clears the stack, calls onend.
*
* @param chunk Optional final chunk to parse.
*/
Parser.prototype.end = function (chunk) {
var _a, _b;
if (this.ended) {
(_b = (_a = this.cbs).onerror) === null || _b === void 0 ? void 0 : _b.call(_a, new Error(".end() after done!"));
return;
}
if (chunk)
this.write(chunk);
this.ended = true;
this.tokenizer.end();
};
/**
* Pauses parsing. The parser won't emit events until `resume` is called.
*/
Parser.prototype.pause = function () {
this.tokenizer.pause();
};
/**
* Resumes parsing after `pause` was called.
*/
Parser.prototype.resume = function () {
this.tokenizer.resume();
while (this.tokenizer.running &&
this.writeIndex < this.buffers.length) {
this.tokenizer.write(this.buffers[this.writeIndex++]);
}
if (this.ended)
this.tokenizer.end();
};
/**
* Alias of `write`, for backwards compatibility.
*
* @param chunk Chunk to parse.
* @deprecated
*/
Parser.prototype.parseChunk = function (chunk) {
this.write(chunk);
};
/**
* Alias of `end`, for backwards compatibility.
*
* @param chunk Optional final chunk to parse.
* @deprecated
*/
Parser.prototype.done = function (chunk) {
this.end(chunk);
};
return Parser;
}());
exports.Parser = Parser;
//# sourceMappingURL=Parser.js.map
@@ -0,0 +1,938 @@
"use strict";
Object.defineProperty(exports, "__esModule", { value: true });
exports.QuoteType = void 0;
var decode_js_1 = require("entities/lib/decode.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";
// Attributes
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";
// Declarations
State[State["BeforeDeclaration"] = 15] = "BeforeDeclaration";
State[State["InDeclaration"] = 16] = "InDeclaration";
// Processing instructions
State[State["InProcessingInstruction"] = 17] = "InProcessingInstruction";
// Comments & CDATA
State[State["BeforeComment"] = 18] = "BeforeComment";
State[State["CDATASequence"] = 19] = "CDATASequence";
State[State["InSpecialComment"] = 20] = "InSpecialComment";
State[State["InCommentLike"] = 21] = "InCommentLike";
// Special tags
State[State["BeforeSpecialS"] = 22] = "BeforeSpecialS";
State[State["SpecialStartSequence"] = 23] = "SpecialStartSequence";
State[State["InSpecialTag"] = 24] = "InSpecialTag";
State[State["BeforeEntity"] = 25] = "BeforeEntity";
State[State["BeforeNumericEntity"] = 26] = "BeforeNumericEntity";
State[State["InNamedEntity"] = 27] = "InNamedEntity";
State[State["InNumericEntity"] = 28] = "InNumericEntity";
State[State["InHexEntity"] = 29] = "InHexEntity";
})(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 isNumber(c) {
return c >= CharCodes.Zero && c <= CharCodes.Nine;
}
function isASCIIAlpha(c) {
return ((c >= CharCodes.LowerA && c <= CharCodes.LowerZ) ||
(c >= CharCodes.UpperA && c <= CharCodes.UpperZ));
}
function isHexDigit(c) {
return ((c >= CharCodes.UpperA && c <= CharCodes.UpperF) ||
(c >= CharCodes.LowerA && c <= CharCodes.LowerF));
}
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 = exports.QuoteType || (exports.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.
*/
var Sequences = {
Cdata: new Uint8Array([0x43, 0x44, 0x41, 0x54, 0x41, 0x5b]),
CdataEnd: new Uint8Array([0x5d, 0x5d, 0x3e]),
CommentEnd: new Uint8Array([0x2d, 0x2d, 0x3e]),
ScriptEnd: new Uint8Array([0x3c, 0x2f, 0x73, 0x63, 0x72, 0x69, 0x70, 0x74]),
StyleEnd: new Uint8Array([0x3c, 0x2f, 0x73, 0x74, 0x79, 0x6c, 0x65]),
TitleEnd: new Uint8Array([0x3c, 0x2f, 0x74, 0x69, 0x74, 0x6c, 0x65]), // `</title`
};
var Tokenizer = /** @class */ (function () {
function Tokenizer(_a, cbs) {
var _b = _a.xmlMode, xmlMode = _b === void 0 ? false : _b, _c = _a.decodeEntities, decodeEntities = _c === void 0 ? true : _c;
this.cbs = cbs;
/** The current state the tokenizer is in. */
this.state = State.Text;
/** The read buffer. */
this.buffer = "";
/** The beginning of the section that is currently being read. */
this.sectionStart = 0;
/** The index within the buffer that we are currently looking at. */
this.index = 0;
/** Some behavior, eg. when decoding entities, is done while we are in another state. This keeps track of the other state type. */
this.baseState = State.Text;
/** For special parsing behavior inside of script and style tags. */
this.isSpecial = false;
/** Indicates whether the tokenizer has been paused. */
this.running = true;
/** The offset of the current buffer. */
this.offset = 0;
this.currentSequence = undefined;
this.sequenceIndex = 0;
this.trieIndex = 0;
this.trieCurrent = 0;
/** For named entities, the index of the value. For numeric entities, the code point. */
this.entityResult = 0;
this.entityExcess = 0;
this.xmlMode = xmlMode;
this.decodeEntities = decodeEntities;
this.entityTrie = xmlMode ? decode_js_1.xmlDecodeTree : decode_js_1.htmlDecodeTree;
}
Tokenizer.prototype.reset = function () {
this.state = State.Text;
this.buffer = "";
this.sectionStart = 0;
this.index = 0;
this.baseState = State.Text;
this.currentSequence = undefined;
this.running = true;
this.offset = 0;
};
Tokenizer.prototype.write = function (chunk) {
this.offset += this.buffer.length;
this.buffer = chunk;
this.parse();
};
Tokenizer.prototype.end = function () {
if (this.running)
this.finish();
};
Tokenizer.prototype.pause = function () {
this.running = false;
};
Tokenizer.prototype.resume = function () {
this.running = true;
if (this.index < this.buffer.length + this.offset) {
this.parse();
}
};
/**
* The current index within all of the written data.
*/
Tokenizer.prototype.getIndex = function () {
return this.index;
};
/**
* The start of the current section.
*/
Tokenizer.prototype.getSectionStart = function () {
return this.sectionStart;
};
Tokenizer.prototype.stateText = function (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.state = State.BeforeEntity;
}
};
Tokenizer.prototype.stateSpecialStartSequence = function (c) {
var isEnd = this.sequenceIndex === this.currentSequence.length;
var isMatch = isEnd
? // If we are at the end of the sequence, make sure the tag name has ended
isEndOfTagSection(c)
: // Otherwise, do a case-insensitive comparison
(c | 0x20) === this.currentSequence[this.sequenceIndex];
if (!isMatch) {
this.isSpecial = false;
}
else if (!isEnd) {
this.sequenceIndex++;
return;
}
this.sequenceIndex = 0;
this.state = State.InTagName;
this.stateInTagName(c);
};
/** Look for an end tag. For <title> tags, also decode entities. */
Tokenizer.prototype.stateInSpecialTag = function (c) {
if (this.sequenceIndex === this.currentSequence.length) {
if (c === CharCodes.Gt || isWhitespace(c)) {
var endOfText = this.index - this.currentSequence.length;
if (this.sectionStart < endOfText) {
// Spoof the index so that reported locations match up.
var actualIndex = this.index;
this.index = endOfText;
this.cbs.ontext(this.sectionStart, endOfText);
this.index = actualIndex;
}
this.isSpecial = false;
this.sectionStart = endOfText + 2; // Skip over the `</`
this.stateInClosingTagName(c);
return; // We are done; skip the rest of the function.
}
this.sequenceIndex = 0;
}
if ((c | 0x20) === this.currentSequence[this.sequenceIndex]) {
this.sequenceIndex += 1;
}
else if (this.sequenceIndex === 0) {
if (this.currentSequence === Sequences.TitleEnd) {
// We have to parse entities in <title> tags.
if (this.decodeEntities && c === CharCodes.Amp) {
this.state = State.BeforeEntity;
}
}
else if (this.fastForwardTo(CharCodes.Lt)) {
// Outside of <title> tags, we can fast-forward.
this.sequenceIndex = 1;
}
}
else {
// If we see a `<`, set the sequence index to 1; useful for eg. `<</script>`.
this.sequenceIndex = Number(c === CharCodes.Lt);
}
};
Tokenizer.prototype.stateCDATASequence = function (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;
this.state = State.InDeclaration;
this.stateInDeclaration(c); // Reconsume the character
}
};
/**
* When we wait for one specific character, we can speed things up
* by skipping through the buffer until we find it.
*
* @returns Whether the character was found.
*/
Tokenizer.prototype.fastForwardTo = function (c) {
while (++this.index < this.buffer.length + this.offset) {
if (this.buffer.charCodeAt(this.index - this.offset) === c) {
return true;
}
}
/*
* We increment the index at the end of the `parse` loop,
* so set it to `buffer.length - 1` here.
*
* TODO: Refactor `parse` to increment index before calling states.
*/
this.index = this.buffer.length + this.offset - 1;
return false;
};
/**
* 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.
*/
Tokenizer.prototype.stateInCommentLike = function (c) {
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, 2);
}
this.sequenceIndex = 0;
this.sectionStart = this.index + 1;
this.state = State.Text;
}
}
else if (this.sequenceIndex === 0) {
// Fast-forward to the first character of the sequence
if (this.fastForwardTo(this.currentSequence[0])) {
this.sequenceIndex = 1;
}
}
else if (c !== this.currentSequence[this.sequenceIndex - 1]) {
// Allow long sequences, eg. --->, ]]]>
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.
*/
Tokenizer.prototype.isTagStartChar = function (c) {
return this.xmlMode ? !isEndOfTagSection(c) : isASCIIAlpha(c);
};
Tokenizer.prototype.startSpecial = function (sequence, offset) {
this.isSpecial = true;
this.currentSequence = sequence;
this.sequenceIndex = offset;
this.state = State.SpecialStartSequence;
};
Tokenizer.prototype.stateBeforeTagName = function (c) {
if (c === CharCodes.ExclamationMark) {
this.state = State.BeforeDeclaration;
this.sectionStart = this.index + 1;
}
else if (c === CharCodes.Questionmark) {
this.state = State.InProcessingInstruction;
this.sectionStart = this.index + 1;
}
else if (this.isTagStartChar(c)) {
var lower = c | 0x20;
this.sectionStart = this.index;
if (!this.xmlMode && lower === Sequences.TitleEnd[2]) {
this.startSpecial(Sequences.TitleEnd, 3);
}
else {
this.state =
!this.xmlMode && lower === Sequences.ScriptEnd[2]
? State.BeforeSpecialS
: State.InTagName;
}
}
else if (c === CharCodes.Slash) {
this.state = State.BeforeClosingTagName;
}
else {
this.state = State.Text;
this.stateText(c);
}
};
Tokenizer.prototype.stateInTagName = function (c) {
if (isEndOfTagSection(c)) {
this.cbs.onopentagname(this.sectionStart, this.index);
this.sectionStart = -1;
this.state = State.BeforeAttributeName;
this.stateBeforeAttributeName(c);
}
};
Tokenizer.prototype.stateBeforeClosingTagName = function (c) {
if (isWhitespace(c)) {
// Ignore
}
else if (c === CharCodes.Gt) {
this.state = State.Text;
}
else {
this.state = this.isTagStartChar(c)
? State.InClosingTagName
: State.InSpecialComment;
this.sectionStart = this.index;
}
};
Tokenizer.prototype.stateInClosingTagName = function (c) {
if (c === CharCodes.Gt || isWhitespace(c)) {
this.cbs.onclosetag(this.sectionStart, this.index);
this.sectionStart = -1;
this.state = State.AfterClosingTagName;
this.stateAfterClosingTagName(c);
}
};
Tokenizer.prototype.stateAfterClosingTagName = function (c) {
// Skip everything until ">"
if (c === CharCodes.Gt || this.fastForwardTo(CharCodes.Gt)) {
this.state = State.Text;
this.baseState = State.Text;
this.sectionStart = this.index + 1;
}
};
Tokenizer.prototype.stateBeforeAttributeName = function (c) {
if (c === CharCodes.Gt) {
this.cbs.onopentagend(this.index);
if (this.isSpecial) {
this.state = State.InSpecialTag;
this.sequenceIndex = 0;
}
else {
this.state = State.Text;
}
this.baseState = this.state;
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;
}
};
Tokenizer.prototype.stateInSelfClosingTag = function (c) {
if (c === CharCodes.Gt) {
this.cbs.onselfclosingtag(this.index);
this.state = State.Text;
this.baseState = State.Text;
this.sectionStart = this.index + 1;
this.isSpecial = false; // Reset special state, in case of self-closing special tags
}
else if (!isWhitespace(c)) {
this.state = State.BeforeAttributeName;
this.stateBeforeAttributeName(c);
}
};
Tokenizer.prototype.stateInAttributeName = function (c) {
if (c === CharCodes.Eq || isEndOfTagSection(c)) {
this.cbs.onattribname(this.sectionStart, this.index);
this.sectionStart = -1;
this.state = State.AfterAttributeName;
this.stateAfterAttributeName(c);
}
};
Tokenizer.prototype.stateAfterAttributeName = function (c) {
if (c === CharCodes.Eq) {
this.state = State.BeforeAttributeValue;
}
else if (c === CharCodes.Slash || c === CharCodes.Gt) {
this.cbs.onattribend(QuoteType.NoValue, this.index);
this.state = State.BeforeAttributeName;
this.stateBeforeAttributeName(c);
}
else if (!isWhitespace(c)) {
this.cbs.onattribend(QuoteType.NoValue, this.index);
this.state = State.InAttributeName;
this.sectionStart = this.index;
}
};
Tokenizer.prototype.stateBeforeAttributeValue = function (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); // Reconsume token
}
};
Tokenizer.prototype.handleInAttributeValue = function (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);
this.state = State.BeforeAttributeName;
}
else if (this.decodeEntities && c === CharCodes.Amp) {
this.baseState = this.state;
this.state = State.BeforeEntity;
}
};
Tokenizer.prototype.stateInAttributeValueDoubleQuotes = function (c) {
this.handleInAttributeValue(c, CharCodes.DoubleQuote);
};
Tokenizer.prototype.stateInAttributeValueSingleQuotes = function (c) {
this.handleInAttributeValue(c, CharCodes.SingleQuote);
};
Tokenizer.prototype.stateInAttributeValueNoQuotes = function (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.baseState = this.state;
this.state = State.BeforeEntity;
}
};
Tokenizer.prototype.stateBeforeDeclaration = function (c) {
if (c === CharCodes.OpeningSquareBracket) {
this.state = State.CDATASequence;
this.sequenceIndex = 0;
}
else {
this.state =
c === CharCodes.Dash
? State.BeforeComment
: State.InDeclaration;
}
};
Tokenizer.prototype.stateInDeclaration = function (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;
}
};
Tokenizer.prototype.stateInProcessingInstruction = function (c) {
if (c === CharCodes.Gt || this.fastForwardTo(CharCodes.Gt)) {
this.cbs.onprocessinginstruction(this.sectionStart, this.index);
this.state = State.Text;
this.sectionStart = this.index + 1;
}
};
Tokenizer.prototype.stateBeforeComment = function (c) {
if (c === CharCodes.Dash) {
this.state = State.InCommentLike;
this.currentSequence = Sequences.CommentEnd;
// Allow short comments (eg. <!-->)
this.sequenceIndex = 2;
this.sectionStart = this.index + 1;
}
else {
this.state = State.InDeclaration;
}
};
Tokenizer.prototype.stateInSpecialComment = function (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;
}
};
Tokenizer.prototype.stateBeforeSpecialS = function (c) {
var lower = c | 0x20;
if (lower === Sequences.ScriptEnd[3]) {
this.startSpecial(Sequences.ScriptEnd, 4);
}
else if (lower === Sequences.StyleEnd[3]) {
this.startSpecial(Sequences.StyleEnd, 4);
}
else {
this.state = State.InTagName;
this.stateInTagName(c); // Consume the token again
}
};
Tokenizer.prototype.stateBeforeEntity = function (c) {
// Start excess with 1 to include the '&'
this.entityExcess = 1;
this.entityResult = 0;
if (c === CharCodes.Number) {
this.state = State.BeforeNumericEntity;
}
else if (c === CharCodes.Amp) {
// We have two `&` characters in a row. Stay in the current state.
}
else {
this.trieIndex = 0;
this.trieCurrent = this.entityTrie[0];
this.state = State.InNamedEntity;
this.stateInNamedEntity(c);
}
};
Tokenizer.prototype.stateInNamedEntity = function (c) {
this.entityExcess += 1;
this.trieIndex = (0, decode_js_1.determineBranch)(this.entityTrie, this.trieCurrent, this.trieIndex + 1, c);
if (this.trieIndex < 0) {
this.emitNamedEntity();
this.index--;
return;
}
this.trieCurrent = this.entityTrie[this.trieIndex];
var masked = this.trieCurrent & decode_js_1.BinTrieFlags.VALUE_LENGTH;
// If the branch is a value, store it and continue
if (masked) {
// The mask is the number of bytes of the value, including the current byte.
var valueLength = (masked >> 14) - 1;
// If we have a legacy entity while parsing strictly, just skip the number of bytes
if (!this.allowLegacyEntity() && c !== CharCodes.Semi) {
this.trieIndex += valueLength;
}
else {
// Add 1 as we have already incremented the excess
var entityStart = this.index - this.entityExcess + 1;
if (entityStart > this.sectionStart) {
this.emitPartial(this.sectionStart, entityStart);
}
// If this is a surrogate pair, consume the next two bytes
this.entityResult = this.trieIndex;
this.trieIndex += valueLength;
this.entityExcess = 0;
this.sectionStart = this.index + 1;
if (valueLength === 0) {
this.emitNamedEntity();
}
}
}
};
Tokenizer.prototype.emitNamedEntity = function () {
this.state = this.baseState;
if (this.entityResult === 0) {
return;
}
var valueLength = (this.entityTrie[this.entityResult] & decode_js_1.BinTrieFlags.VALUE_LENGTH) >>
14;
switch (valueLength) {
case 1: {
this.emitCodePoint(this.entityTrie[this.entityResult] &
~decode_js_1.BinTrieFlags.VALUE_LENGTH);
break;
}
case 2: {
this.emitCodePoint(this.entityTrie[this.entityResult + 1]);
break;
}
case 3: {
this.emitCodePoint(this.entityTrie[this.entityResult + 1]);
this.emitCodePoint(this.entityTrie[this.entityResult + 2]);
}
}
};
Tokenizer.prototype.stateBeforeNumericEntity = function (c) {
if ((c | 0x20) === CharCodes.LowerX) {
this.entityExcess++;
this.state = State.InHexEntity;
}
else {
this.state = State.InNumericEntity;
this.stateInNumericEntity(c);
}
};
Tokenizer.prototype.emitNumericEntity = function (strict) {
var entityStart = this.index - this.entityExcess - 1;
var numberStart = entityStart + 2 + Number(this.state === State.InHexEntity);
if (numberStart !== this.index) {
// Emit leading data if any
if (entityStart > this.sectionStart) {
this.emitPartial(this.sectionStart, entityStart);
}
this.sectionStart = this.index + Number(strict);
this.emitCodePoint((0, decode_js_1.replaceCodePoint)(this.entityResult));
}
this.state = this.baseState;
};
Tokenizer.prototype.stateInNumericEntity = function (c) {
if (c === CharCodes.Semi) {
this.emitNumericEntity(true);
}
else if (isNumber(c)) {
this.entityResult = this.entityResult * 10 + (c - CharCodes.Zero);
this.entityExcess++;
}
else {
if (this.allowLegacyEntity()) {
this.emitNumericEntity(false);
}
else {
this.state = this.baseState;
}
this.index--;
}
};
Tokenizer.prototype.stateInHexEntity = function (c) {
if (c === CharCodes.Semi) {
this.emitNumericEntity(true);
}
else if (isNumber(c)) {
this.entityResult = this.entityResult * 16 + (c - CharCodes.Zero);
this.entityExcess++;
}
else if (isHexDigit(c)) {
this.entityResult =
this.entityResult * 16 + ((c | 0x20) - CharCodes.LowerA + 10);
this.entityExcess++;
}
else {
if (this.allowLegacyEntity()) {
this.emitNumericEntity(false);
}
else {
this.state = this.baseState;
}
this.index--;
}
};
Tokenizer.prototype.allowLegacyEntity = function () {
return (!this.xmlMode &&
(this.baseState === State.Text ||
this.baseState === State.InSpecialTag));
};
/**
* Remove data that has already been consumed from the buffer.
*/
Tokenizer.prototype.cleanup = function () {
// If we are inside of text or attributes, emit what we already have.
if (this.running && this.sectionStart !== this.index) {
if (this.state === State.Text ||
(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;
}
}
};
Tokenizer.prototype.shouldContinue = function () {
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.
*/
Tokenizer.prototype.parse = function () {
while (this.shouldContinue()) {
var c = this.buffer.charCodeAt(this.index - this.offset);
switch (this.state) {
case State.Text: {
this.stateText(c);
break;
}
case State.SpecialStartSequence: {
this.stateSpecialStartSequence(c);
break;
}
case State.InSpecialTag: {
this.stateInSpecialTag(c);
break;
}
case State.CDATASequence: {
this.stateCDATASequence(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.BeforeSpecialS: {
this.stateBeforeSpecialS(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.InNamedEntity: {
this.stateInNamedEntity(c);
break;
}
case State.BeforeEntity: {
this.stateBeforeEntity(c);
break;
}
case State.InHexEntity: {
this.stateInHexEntity(c);
break;
}
case State.InNumericEntity: {
this.stateInNumericEntity(c);
break;
}
default: {
// `this._state === State.BeforeNumericEntity`
this.stateBeforeNumericEntity(c);
}
}
this.index++;
}
this.cleanup();
};
Tokenizer.prototype.finish = function () {
if (this.state === State.InNamedEntity) {
this.emitNamedEntity();
}
// If there is remaining data, emit it in a reasonable way
if (this.sectionStart < this.index) {
this.handleTrailingData();
}
this.cbs.onend();
};
/** Handle any trailing data. */
Tokenizer.prototype.handleTrailingData = function () {
var endIndex = this.buffer.length + this.offset;
if (this.state === State.InCommentLike) {
if (this.currentSequence === Sequences.CdataEnd) {
this.cbs.oncdata(this.sectionStart, endIndex, 0);
}
else {
this.cbs.oncomment(this.sectionStart, endIndex, 0);
}
}
else if (this.state === State.InNumericEntity &&
this.allowLegacyEntity()) {
this.emitNumericEntity(false);
// All trailing data will have been consumed
}
else if (this.state === State.InHexEntity &&
this.allowLegacyEntity()) {
this.emitNumericEntity(false);
// All trailing data will have been consumed
}
else if (this.state === State.InTagName ||
this.state === State.BeforeAttributeName ||
this.state === State.BeforeAttributeValue ||
this.state === State.AfterAttributeName ||
this.state === State.InAttributeName ||
this.state === State.InAttributeValueSq ||
this.state === State.InAttributeValueDq ||
this.state === State.InAttributeValueNq ||
this.state === State.InClosingTagName) {
/*
* If we are currently in an opening or closing tag, us not calling the
* respective callback signals that the tag should be ignored.
*/
}
else {
this.cbs.ontext(this.sectionStart, endIndex);
}
};
Tokenizer.prototype.emitPartial = function (start, endIndex) {
if (this.baseState !== State.Text &&
this.baseState !== State.InSpecialTag) {
this.cbs.onattribdata(start, endIndex);
}
else {
this.cbs.ontext(start, endIndex);
}
};
Tokenizer.prototype.emitCodePoint = function (cp) {
if (this.baseState !== State.Text &&
this.baseState !== State.InSpecialTag) {
this.cbs.onattribentity(cp);
}
else {
this.cbs.ontextentity(cp);
}
};
return Tokenizer;
}());
exports.default = Tokenizer;
//# sourceMappingURL=Tokenizer.js.map
@@ -0,0 +1,100 @@
"use strict";
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
if (k2 === undefined) k2 = k;
var desc = Object.getOwnPropertyDescriptor(m, k);
if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
desc = { enumerable: true, get: function() { return m[k]; } };
}
Object.defineProperty(o, k2, desc);
}) : (function(o, m, k, k2) {
if (k2 === undefined) k2 = k;
o[k2] = m[k];
}));
var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
Object.defineProperty(o, "default", { enumerable: true, value: v });
}) : function(o, v) {
o["default"] = v;
});
var __importStar = (this && this.__importStar) || function (mod) {
if (mod && mod.__esModule) return mod;
var result = {};
if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
__setModuleDefault(result, mod);
return result;
};
var __importDefault = (this && this.__importDefault) || function (mod) {
return (mod && mod.__esModule) ? mod : { "default": mod };
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.DomUtils = exports.parseFeed = exports.getFeed = exports.ElementType = exports.Tokenizer = exports.createDomStream = exports.parseDOM = exports.parseDocument = exports.DefaultHandler = exports.DomHandler = exports.Parser = void 0;
var Parser_js_1 = require("./Parser.js");
var Parser_js_2 = require("./Parser.js");
Object.defineProperty(exports, "Parser", { enumerable: true, get: function () { return Parser_js_2.Parser; } });
var domhandler_1 = require("domhandler");
var domhandler_2 = require("domhandler");
Object.defineProperty(exports, "DomHandler", { enumerable: true, get: function () { return domhandler_2.DomHandler; } });
// Old name for DomHandler
Object.defineProperty(exports, "DefaultHandler", { enumerable: true, get: function () { return domhandler_2.DomHandler; } });
// Helper methods
/**
* Parses the data, returns the resulting document.
*
* @param data The data that should be parsed.
* @param options Optional options for the parser and DOM builder.
*/
function parseDocument(data, options) {
var handler = new domhandler_1.DomHandler(undefined, options);
new Parser_js_1.Parser(handler, options).end(data);
return handler.root;
}
exports.parseDocument = parseDocument;
/**
* Parses data, returns an array of the root nodes.
*
* Note that the root nodes still have a `Document` node as their parent.
* Use `parseDocument` to get the `Document` node instead.
*
* @param data The data that should be parsed.
* @param options Optional options for the parser and DOM builder.
* @deprecated Use `parseDocument` instead.
*/
function parseDOM(data, options) {
return parseDocument(data, options).children;
}
exports.parseDOM = parseDOM;
/**
* Creates a parser instance, with an attached DOM handler.
*
* @param callback A callback that will be called once parsing has been completed.
* @param options Optional options for the parser and DOM builder.
* @param elementCallback An optional callback that will be called every time a tag has been completed inside of the DOM.
*/
function createDomStream(callback, options, elementCallback) {
var handler = new domhandler_1.DomHandler(callback, options, elementCallback);
return new Parser_js_1.Parser(handler, options);
}
exports.createDomStream = createDomStream;
var Tokenizer_js_1 = require("./Tokenizer.js");
Object.defineProperty(exports, "Tokenizer", { enumerable: true, get: function () { return __importDefault(Tokenizer_js_1).default; } });
/*
* All of the following exports exist for backwards-compatibility.
* They should probably be removed eventually.
*/
exports.ElementType = __importStar(require("domelementtype"));
var domutils_1 = require("domutils");
var domutils_2 = require("domutils");
Object.defineProperty(exports, "getFeed", { enumerable: true, get: function () { return domutils_2.getFeed; } });
var parseFeedDefaultOptions = { xmlMode: true };
/**
* Parse a feed.
*
* @param feed The feed that should be parsed, as a string.
* @param options Optionally, options for parsing. When using this, you should set `xmlMode` to `true`.
*/
function parseFeed(feed, options) {
if (options === void 0) { options = parseFeedDefaultOptions; }
return (0, domutils_1.getFeed)(parseDOM(feed, options));
}
exports.parseFeed = parseFeed;
exports.DomUtils = __importStar(require("domutils"));
//# sourceMappingURL=index.js.map
@@ -0,0 +1,97 @@
{
"name": "htmlparser2",
"description": "Fast & forgiving HTML/XML parser",
"version": "8.0.2",
"author": "Felix Boehm <me@feedic.com>",
"funding": [
"https://github.com/fb55/htmlparser2?sponsor=1",
{
"type": "github",
"url": "https://github.com/sponsors/fb55"
}
],
"license": "MIT",
"sideEffects": false,
"keywords": [
"html",
"parser",
"streams",
"xml",
"dom",
"rss",
"feed",
"atom"
],
"repository": {
"type": "git",
"url": "git://github.com/fb55/htmlparser2.git"
},
"directories": {
"lib": "lib/"
},
"main": "lib/index.js",
"types": "lib/index.d.ts",
"module": "lib/esm/index.js",
"exports": {
".": {
"require": "./lib/index.js",
"import": "./lib/esm/index.js"
},
"./lib/WritableStream": {
"require": "./lib/WritableStream.js",
"import": "./lib/esm/WritableStream.js"
}
},
"files": [
"lib/**/*"
],
"scripts": {
"test": "npm run test:jest && npm run lint",
"test:jest": "jest",
"lint": "npm run lint:es && npm run lint:prettier",
"lint:es": "eslint src",
"lint:prettier": "npm run format:prettier:raw -- --check",
"format": "npm run format:es && npm run format:prettier",
"format:es": "npm run lint:es -- --fix",
"format:prettier": "npm run format:prettier:raw -- --write",
"format:prettier:raw": "prettier '**/*.{ts,md,json,yml}'",
"build": "npm run build:cjs && npm run build:esm",
"build:cjs": "tsc --sourceRoot https://raw.githubusercontent.com/fb55/htmlparser2/$(git rev-parse HEAD)/src/",
"build:esm": "npm run build:cjs -- --module esnext --target es2019 --outDir lib/esm && echo '{\"type\":\"module\"}' > lib/esm/package.json",
"prepare": "npm run build"
},
"dependencies": {
"domelementtype": "^2.3.0",
"domhandler": "^5.0.3",
"domutils": "^3.0.1",
"entities": "^4.4.0"
},
"devDependencies": {
"@types/jest": "^29.5.0",
"@types/node": "^18.15.5",
"@typescript-eslint/eslint-plugin": "^5.56.0",
"@typescript-eslint/parser": "^5.56.0",
"eslint": "^8.36.0",
"eslint-config-prettier": "^8.8.0",
"eslint-plugin-n": "^15.6.1",
"eslint-plugin-unicorn": "^46.0.0",
"jest": "^29.5.0",
"prettier": "^2.8.6",
"ts-jest": "^29.0.5",
"typescript": "^4.9.5"
},
"jest": {
"preset": "ts-jest",
"testEnvironment": "node",
"coverageProvider": "v8",
"moduleNameMapper": {
"^(.*)\\.js$": [
"$1",
"$1.js"
]
}
},
"prettier": {
"tabWidth": 4
}
}